diff options
Diffstat (limited to 'tools')
252 files changed, 12581 insertions, 1782 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index b3edde68bc3e..490d489d0ee8 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2 + /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) @@ -362,6 +367,7 @@ struct kvm_arm_copy_mte_tags { #define KVM_ARM_VCPU_PMU_V3_IRQ 0 #define KVM_ARM_VCPU_PMU_V3_INIT 1 #define KVM_ARM_VCPU_PMU_V3_FILTER 2 +#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3 #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 18de5f76f198..65d147974f8d 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ /* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ @@ -299,7 +299,9 @@ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ #define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index dc632b41f135..65c0d9ce1e29 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -124,7 +124,7 @@ struct insn { #define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ #define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ /* VEX bit fields */ -#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ +#define X86_EVEX_M(vex) ((vex) & 0x07) /* EVEX Byte1 */ #define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ #define X86_VEX2_M 1 /* VEX2.M always 1 */ #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 3faf0f97edb1..a4a39c3e0f19 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -476,6 +476,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 59cf2343f3d9..d0d7b9bc6cad 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -27,8 +27,7 @@ * Output: * rax original destination */ -SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_WEAK(memcpy) +SYM_FUNC_START(__memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -40,11 +39,12 @@ SYM_FUNC_START_WEAK(memcpy) movl %edx, %ecx rep movsb RET -SYM_FUNC_END(memcpy) -SYM_FUNC_END_ALIAS(__memcpy) -EXPORT_SYMBOL(memcpy) +SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) +SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy) +EXPORT_SYMBOL(memcpy) + /* * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index d624f2bc42f1..fc9ffd3ff3b2 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -17,7 +17,6 @@ * * rax original destination */ -SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended @@ -42,10 +41,11 @@ SYM_FUNC_START(__memset) movq %r9,%rax RET SYM_FUNC_END(__memset) -SYM_FUNC_END_ALIAS(memset) -EXPORT_SYMBOL(memset) EXPORT_SYMBOL(__memset) +SYM_FUNC_ALIAS_WEAK(memset, __memset) +EXPORT_SYMBOL(memset) + /* * ISO C memset - set a memory block to a byte value. This function uses * enhanced rep stosb to override the fast string function. diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index ec31f5b60323..d12d1358f96d 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -690,7 +690,10 @@ AVXcode: 2 45: vpsrlvd/q Vx,Hx,Wx (66),(v) 46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) 47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x4b +# Skip 0x48 +49: TILERELEASE (v1),(000),(11B) | LDTILECFG Mtc (v1)(000) | STTILECFG Mtc (66),(v1),(000) | TILEZERO Vt (F2),(v1),(11B) +# Skip 0x4a +4b: TILELOADD Vt,Wsm (F2),(v1) | TILELOADDT1 Vt,Wsm (66),(v1) | TILESTORED Wsm,Vt (F3),(v) 4c: vrcp14ps/d Vpd,Wpd (66),(ev) 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) @@ -705,7 +708,10 @@ AVXcode: 2 59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) 5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) 5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) -# Skip 0x5c-0x61 +5c: TDPBF16PS Vt,Wt,Ht (F3),(v1) +# Skip 0x5d +5e: TDPBSSD Vt,Wt,Ht (F2),(v1) | TDPBSUD Vt,Wt,Ht (F3),(v1) | TDPBUSD Vt,Wt,Ht (66),(v1) | TDPBUUD Vt,Wt,Ht (v1) +# Skip 0x5f-0x61 62: vpexpandb/w Vx,Wx (66),(ev) 63: vpcompressb/w Wx,Vx (66),(ev) 64: vpblendmd/q Vx,Hx,Wx (66),(ev) @@ -822,9 +828,9 @@ AVXcode: 3 05: vpermilpd Vx,Wx,Ib (66),(v) 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) 07: -08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) +08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) | vrndscaleph Vx,Wx,Ib (evo) 09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) -0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) +0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) | vrndscalesh Vx,Hx,Wx,Ib (evo) 0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) 0c: vblendps Vx,Hx,Wx,Ib (66) 0d: vblendpd Vx,Hx,Wx,Ib (66) @@ -846,8 +852,8 @@ AVXcode: 3 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) 23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) 25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) -26: vgetmantps/d Vx,Wx,Ib (66),(ev) -27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) +26: vgetmantps/d Vx,Wx,Ib (66),(ev) | vgetmantph Vx,Wx,Ib (ev) +27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) | vgetmantsh Vx,Hx,Wx,Ib (ev) 30: kshiftrb/w Vk,Uk,Ib (66),(v) 31: kshiftrd/q Vk,Uk,Ib (66),(v) 32: kshiftlb/w Vk,Uk,Ib (66),(v) @@ -871,23 +877,102 @@ AVXcode: 3 51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) 54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) 55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) -56: vreduceps/d Vx,Wx,Ib (66),(ev) -57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) +56: vreduceps/d Vx,Wx,Ib (66),(ev) | vreduceph Vx,Wx,Ib (ev) +57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) | vreducesh Vx,Hx,Wx,Ib (ev) 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) -66: vfpclassps/d Vk,Wx,Ib (66),(ev) -67: vfpclassss/d Vk,Wx,Ib (66),(ev) +66: vfpclassps/d Vk,Wx,Ib (66),(ev) | vfpclassph Vx,Wx,Ib (ev) +67: vfpclassss/d Vk,Wx,Ib (66),(ev) | vfpclasssh Vx,Wx,Ib (ev) 70: vpshldw Vx,Hx,Wx,Ib (66),(ev) 71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev) 72: vpshrdw Vx,Hx,Wx,Ib (66),(ev) 73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev) +c2: vcmpph Vx,Hx,Wx,Ib (ev) | vcmpsh Vx,Hx,Wx,Ib (F3),(ev) cc: sha1rnds4 Vdq,Wdq,Ib ce: vgf2p8affineqb Vx,Wx,Ib (66) cf: vgf2p8affineinvqb Vx,Wx,Ib (66) df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) -f0: RORX Gy,Ey,Ib (F2),(v) +f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B) +EndTable + +Table: EVEX map 5 +Referrer: +AVXcode: 5 +10: vmovsh Vx,Hx,Wx (F3),(ev) | vmovsh Vx,Wx (F3),(ev) +11: vmovsh Wx,Hx,Vx (F3),(ev) | vmovsh Wx,Vx (F3),(ev) +1d: vcvtps2phx Vx,Wx (66),(ev) | vcvtss2sh Vx,Hx,Wx (ev) +2a: vcvtsi2sh Vx,Hx,Wx (F3),(ev) +2c: vcvttsh2si Vx,Wx (F3),(ev) +2d: vcvtsh2si Vx,Wx (F3),(ev) +2e: vucomish Vx,Wx (ev) +2f: vcomish Vx,Wx (ev) +51: vsqrtph Vx,Wx (ev) | vsqrtsh Vx,Hx,Wx (F3),(ev) +58: vaddph Vx,Hx,Wx (ev) | vaddsh Vx,Hx,Wx (F3),(ev) +59: vmulph Vx,Hx,Wx (ev) | vmulsh Vx,Hx,Wx (F3),(ev) +5a: vcvtpd2ph Vx,Wx (66),(ev) | vcvtph2pd Vx,Wx (ev) | vcvtsd2sh Vx,Hx,Wx (F2),(ev) | vcvtsh2sd Vx,Hx,Wx (F3),(ev) +5b: vcvtdq2ph Vx,Wx (ev) | vcvtph2dq Vx,Wx (66),(ev) | vcvtqq2ph Vx,Wx (ev) | vcvttph2dq Vx,Wx (F3),(ev) +5c: vsubph Vx,Hx,Wx (ev) | vsubsh Vx,Hx,Wx (F3),(ev) +5d: vminph Vx,Hx,Wx (ev) | vminsh Vx,Hx,Wx (F3),(ev) +5e: vdivph Vx,Hx,Wx (ev) | vdivsh Vx,Hx,Wx (F3),(ev) +5f: vmaxph Vx,Hx,Wx (ev) | vmaxsh Vx,Hx,Wx (F3),(ev) +6e: vmovw Vx,Wx (66),(ev) +78: vcvttph2udq Vx,Wx (ev) | vcvttph2uqq Vx,Wx (66),(ev) | vcvttsh2usi Vx,Wx (F3),(ev) +79: vcvtph2udq Vx,Wx (ev) | vcvtph2uqq Vx,Wx (66),(ev) | vcvtsh2usi Vx,Wx (F3),(ev) +7a: vcvttph2qq Vx,Wx (66),(ev) | vcvtudq2ph Vx,Wx (F2),(ev) | vcvtuqq2ph Vx,Wx (F2),(ev) +7b: vcvtph2qq Vx,Wx (66),(ev) | vcvtusi2sh Vx,Hx,Wx (F3),(ev) +7c: vcvttph2uw Vx,Wx (ev) | vcvttph2w Vx,Wx (66),(ev) +7d: vcvtph2uw Vx,Wx (ev) | vcvtph2w Vx,Wx (66),(ev) | vcvtuw2ph Vx,Wx (F2),(ev) | vcvtw2ph Vx,Wx (F3),(ev) +7e: vmovw Wx,Vx (66),(ev) +EndTable + +Table: EVEX map 6 +Referrer: +AVXcode: 6 +13: vcvtph2psx Vx,Wx (66),(ev) | vcvtsh2ss Vx,Hx,Wx (ev) +2c: vscalefph Vx,Hx,Wx (66),(ev) +2d: vscalefsh Vx,Hx,Wx (66),(ev) +42: vgetexpph Vx,Wx (66),(ev) +43: vgetexpsh Vx,Hx,Wx (66),(ev) +4c: vrcpph Vx,Wx (66),(ev) +4d: vrcpsh Vx,Hx,Wx (66),(ev) +4e: vrsqrtph Vx,Wx (66),(ev) +4f: vrsqrtsh Vx,Hx,Wx (66),(ev) +56: vfcmaddcph Vx,Hx,Wx (F2),(ev) | vfmaddcph Vx,Hx,Wx (F3),(ev) +57: vfcmaddcsh Vx,Hx,Wx (F2),(ev) | vfmaddcsh Vx,Hx,Wx (F3),(ev) +96: vfmaddsub132ph Vx,Hx,Wx (66),(ev) +97: vfmsubadd132ph Vx,Hx,Wx (66),(ev) +98: vfmadd132ph Vx,Hx,Wx (66),(ev) +99: vfmadd132sh Vx,Hx,Wx (66),(ev) +9a: vfmsub132ph Vx,Hx,Wx (66),(ev) +9b: vfmsub132sh Vx,Hx,Wx (66),(ev) +9c: vfnmadd132ph Vx,Hx,Wx (66),(ev) +9d: vfnmadd132sh Vx,Hx,Wx (66),(ev) +9e: vfnmsub132ph Vx,Hx,Wx (66),(ev) +9f: vfnmsub132sh Vx,Hx,Wx (66),(ev) +a6: vfmaddsub213ph Vx,Hx,Wx (66),(ev) +a7: vfmsubadd213ph Vx,Hx,Wx (66),(ev) +a8: vfmadd213ph Vx,Hx,Wx (66),(ev) +a9: vfmadd213sh Vx,Hx,Wx (66),(ev) +aa: vfmsub213ph Vx,Hx,Wx (66),(ev) +ab: vfmsub213sh Vx,Hx,Wx (66),(ev) +ac: vfnmadd213ph Vx,Hx,Wx (66),(ev) +ad: vfnmadd213sh Vx,Hx,Wx (66),(ev) +ae: vfnmsub213ph Vx,Hx,Wx (66),(ev) +af: vfnmsub213sh Vx,Hx,Wx (66),(ev) +b6: vfmaddsub231ph Vx,Hx,Wx (66),(ev) +b7: vfmsubadd231ph Vx,Hx,Wx (66),(ev) +b8: vfmadd231ph Vx,Hx,Wx (66),(ev) +b9: vfmadd231sh Vx,Hx,Wx (66),(ev) +ba: vfmsub231ph Vx,Hx,Wx (66),(ev) +bb: vfmsub231sh Vx,Hx,Wx (66),(ev) +bc: vfnmadd231ph Vx,Hx,Wx (66),(ev) +bd: vfnmadd231sh Vx,Hx,Wx (66),(ev) +be: vfnmsub231ph Vx,Hx,Wx (66),(ev) +bf: vfnmsub231sh Vx,Hx,Wx (66),(ev) +d6: vfcmulcph Vx,Hx,Wx (F2),(ev) | vfmulcph Vx,Hx,Wx (F3),(ev) +d7: vfcmulcsh Vx,Hx,Wx (F2),(ev) | vfmulcsh Vx,Hx,Wx (F3),(ev) EndTable GrpTable: Grp1 @@ -970,7 +1055,7 @@ GrpTable: Grp7 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv -5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B) +5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B) | CLUI (F3),(110),(11B) | SERIALIZE (000),(11B) | STUI (F3),(111),(11B) | TESTUI (F3)(101)(11B) | UIRET (F3),(100),(11B) | XRESLDTRK (F2),(000),(11B) | XSUSLDTRK (F2),(001),(11B) 6: LMSW Ew 7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) EndTable @@ -987,7 +1072,7 @@ GrpTable: Grp9 3: xrstors 4: xsavec 5: xsaves -6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) +6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) | SENDUIPI Gq (F3) 7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B) EndTable diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 9ddeca947635..320a88ac28c9 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -9,7 +9,11 @@ ifeq ($(V),1) msg = else Q = @ - msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + ifeq ($(silent),1) + msg = + else + msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + endif MAKEFLAGS=--no-print-directory endif diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py index 1600b17dbb8a..1d3a90d93fe2 100644 --- a/tools/cgroup/memcg_slabinfo.py +++ b/tools/cgroup/memcg_slabinfo.py @@ -11,7 +11,7 @@ from drgn.helpers.linux import list_for_each_entry, list_empty from drgn.helpers.linux import for_each_page from drgn.helpers.linux.cpumask import for_each_online_cpu from drgn.helpers.linux.percpu import per_cpu_ptr -from drgn import container_of, FaultError, Object +from drgn import container_of, FaultError, Object, cast DESC = """ @@ -69,15 +69,15 @@ def oo_objects(s): def count_partial(n, fn): - nr_pages = 0 - for page in list_for_each_entry('struct page', n.partial.address_of_(), - 'lru'): - nr_pages += fn(page) - return nr_pages + nr_objs = 0 + for slab in list_for_each_entry('struct slab', n.partial.address_of_(), + 'slab_list'): + nr_objs += fn(slab) + return nr_objs -def count_free(page): - return page.objects - page.inuse +def count_free(slab): + return slab.objects - slab.inuse def slub_get_slabinfo(s, cfg): @@ -145,14 +145,14 @@ def detect_kernel_config(): return cfg -def for_each_slab_page(prog): +def for_each_slab(prog): PGSlab = 1 << prog.constant('PG_slab') PGHead = 1 << prog.constant('PG_head') for page in for_each_page(prog): try: if page.flags.value_() & PGSlab: - yield page + yield cast('struct slab *', page) except FaultError: pass @@ -190,13 +190,13 @@ def main(): 'list'): obj_cgroups.add(ptr.value_()) - # look over all slab pages, belonging to non-root memcgs - # and look for objects belonging to the given memory cgroup - for page in for_each_slab_page(prog): - objcg_vec_raw = page.memcg_data.value_() + # look over all slab folios and look for objects belonging + # to the given memory cgroup + for slab in for_each_slab(prog): + objcg_vec_raw = slab.memcg_data.value_() if objcg_vec_raw == 0: continue - cache = page.slab_cache + cache = slab.slab_cache if not cache: continue addr = cache.value_() diff --git a/tools/include/asm/barrier.h b/tools/include/asm/barrier.h index dc696c151e1c..8d378c57cb01 100644 --- a/tools/include/asm/barrier.h +++ b/tools/include/asm/barrier.h @@ -24,8 +24,6 @@ #include "../../arch/ia64/include/asm/barrier.h" #elif defined(__xtensa__) #include "../../arch/xtensa/include/asm/barrier.h" -#elif defined(__nds32__) -#include "../../arch/nds32/include/asm/barrier.h" #else #include <asm-generic/barrier.h> #endif diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b46bcdb0cab1..bbc6b7c2dc1b 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1134,6 +1134,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 #define KVM_CAP_SYS_ATTRIBUTES 209 +#define KVM_CAP_PPC_AIL_MODE_3 210 +#define KVM_CAP_S390_MEM_OP_EXTENSION 211 +#define KVM_CAP_PMU_CAPABILITY 212 #ifdef KVM_CAP_IRQ_ROUTING @@ -1624,9 +1627,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -/* Available with KVM_CAP_XSAVE2 */ -#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) - struct kvm_s390_pv_sec_parm { __u64 origin; __u64 length; @@ -1973,6 +1973,8 @@ struct kvm_dirty_gfn { #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) +#define KVM_PMU_CAP_DISABLE (1 << 0) + /** * struct kvm_stats_header - Header of per vm/vcpu binary statistics data. * @flags: Some extra information for header, always 0 for now. @@ -2048,4 +2050,7 @@ struct kvm_stats_desc { #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) +/* Available with KVM_CAP_XSAVE2 */ +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) + #endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h deleted file mode 100644 index 45fcbf99d72e..000000000000 --- a/tools/include/uapi/linux/lirc.h +++ /dev/null @@ -1,229 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * lirc.h - linux infrared remote control header file - * last modified 2010/07/13 by Jarod Wilson - */ - -#ifndef _LINUX_LIRC_H -#define _LINUX_LIRC_H - -#include <linux/types.h> -#include <linux/ioctl.h> - -#define PULSE_BIT 0x01000000 -#define PULSE_MASK 0x00FFFFFF - -#define LIRC_MODE2_SPACE 0x00000000 -#define LIRC_MODE2_PULSE 0x01000000 -#define LIRC_MODE2_FREQUENCY 0x02000000 -#define LIRC_MODE2_TIMEOUT 0x03000000 - -#define LIRC_VALUE_MASK 0x00FFFFFF -#define LIRC_MODE2_MASK 0xFF000000 - -#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE) -#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE) -#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY) -#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT) - -#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK) -#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK) - -#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE) -#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE) -#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY) -#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT) - -/* used heavily by lirc userspace */ -#define lirc_t int - -/*** lirc compatible hardware features ***/ - -#define LIRC_MODE2SEND(x) (x) -#define LIRC_SEND2MODE(x) (x) -#define LIRC_MODE2REC(x) ((x) << 16) -#define LIRC_REC2MODE(x) ((x) >> 16) - -#define LIRC_MODE_RAW 0x00000001 -#define LIRC_MODE_PULSE 0x00000002 -#define LIRC_MODE_MODE2 0x00000004 -#define LIRC_MODE_SCANCODE 0x00000008 -#define LIRC_MODE_LIRCCODE 0x00000010 - - -#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW) -#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE) -#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2) -#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE) - -#define LIRC_CAN_SEND_MASK 0x0000003f - -#define LIRC_CAN_SET_SEND_CARRIER 0x00000100 -#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200 -#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400 - -#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW) -#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE) -#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2) -#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE) -#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE) - -#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK) - -#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16) -#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16) - -#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000 -#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000 -#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000 -#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000 -#define LIRC_CAN_SET_REC_FILTER 0x08000000 - -#define LIRC_CAN_MEASURE_CARRIER 0x02000000 -#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000 - -#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) -#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) - -#define LIRC_CAN_NOTIFY_DECODE 0x01000000 - -/*** IOCTL commands for lirc driver ***/ - -#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) - -#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32) -#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32) -#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32) - -#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32) -#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32) - -/* code length in bits, currently only for LIRC_MODE_LIRCCODE */ -#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32) - -#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32) -#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32) -/* Note: these can reset the according pulse_width */ -#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32) -#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32) -#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32) -#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32) - -/* - * when a timeout != 0 is set the driver will send a - * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is - * never sent, timeout is disabled by default - */ -#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32) - -/* 1 enables, 0 disables timeout reports in MODE2 */ -#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32) - -/* - * if enabled from the next key press on the driver will send - * LIRC_MODE2_FREQUENCY packets - */ -#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32) - -/* - * to set a range use LIRC_SET_REC_CARRIER_RANGE with the - * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound - */ -#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32) - -#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32) - -/* - * Return the recording timeout, which is either set by - * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols. - */ -#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32) - -/* - * struct lirc_scancode - decoded scancode with protocol for use with - * LIRC_MODE_SCANCODE - * - * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR - * was decoded. - * @flags: should be 0 for transmit. When receiving scancodes, - * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set - * depending on the protocol - * @rc_proto: see enum rc_proto - * @keycode: the translated keycode. Set to 0 for transmit. - * @scancode: the scancode received or to be sent - */ -struct lirc_scancode { - __u64 timestamp; - __u16 flags; - __u16 rc_proto; - __u32 keycode; - __u64 scancode; -}; - -/* Set if the toggle bit of rc-5 or rc-6 is enabled */ -#define LIRC_SCANCODE_FLAG_TOGGLE 1 -/* Set if this is a nec or sanyo repeat */ -#define LIRC_SCANCODE_FLAG_REPEAT 2 - -/** - * enum rc_proto - the Remote Controller protocol - * - * @RC_PROTO_UNKNOWN: Protocol not known - * @RC_PROTO_OTHER: Protocol known but proprietary - * @RC_PROTO_RC5: Philips RC5 protocol - * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol - * @RC_PROTO_RC5_SZ: StreamZap variant of RC5 - * @RC_PROTO_JVC: JVC protocol - * @RC_PROTO_SONY12: Sony 12 bit protocol - * @RC_PROTO_SONY15: Sony 15 bit protocol - * @RC_PROTO_SONY20: Sony 20 bit protocol - * @RC_PROTO_NEC: NEC protocol - * @RC_PROTO_NECX: Extended NEC protocol - * @RC_PROTO_NEC32: NEC 32 bit protocol - * @RC_PROTO_SANYO: Sanyo protocol - * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard - * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse - * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol - * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol - * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol - * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol - * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol - * @RC_PROTO_SHARP: Sharp protocol - * @RC_PROTO_XMP: XMP protocol - * @RC_PROTO_CEC: CEC protocol - * @RC_PROTO_IMON: iMon Pad protocol - * @RC_PROTO_RCMM12: RC-MM protocol 12 bits - * @RC_PROTO_RCMM24: RC-MM protocol 24 bits - * @RC_PROTO_RCMM32: RC-MM protocol 32 bits - */ -enum rc_proto { - RC_PROTO_UNKNOWN = 0, - RC_PROTO_OTHER = 1, - RC_PROTO_RC5 = 2, - RC_PROTO_RC5X_20 = 3, - RC_PROTO_RC5_SZ = 4, - RC_PROTO_JVC = 5, - RC_PROTO_SONY12 = 6, - RC_PROTO_SONY15 = 7, - RC_PROTO_SONY20 = 8, - RC_PROTO_NEC = 9, - RC_PROTO_NECX = 10, - RC_PROTO_NEC32 = 11, - RC_PROTO_SANYO = 12, - RC_PROTO_MCIR2_KBD = 13, - RC_PROTO_MCIR2_MSE = 14, - RC_PROTO_RC6_0 = 15, - RC_PROTO_RC6_6A_20 = 16, - RC_PROTO_RC6_6A_24 = 17, - RC_PROTO_RC6_6A_32 = 18, - RC_PROTO_RC6_MCE = 19, - RC_PROTO_SHARP = 20, - RC_PROTO_XMP = 21, - RC_PROTO_CEC = 22, - RC_PROTO_IMON = 23, - RC_PROTO_RCMM12 = 24, - RC_PROTO_RCMM24 = 25, - RC_PROTO_RCMM32 = 26, -}; - -#endif diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 4cd39aaccbe7..d37629dbad72 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -251,6 +251,8 @@ enum { PERF_BR_SYSRET = 8, /* syscall return */ PERF_BR_COND_CALL = 9, /* conditional function call */ PERF_BR_COND_RET = 10, /* conditional function return */ + PERF_BR_ERET = 11, /* exception return */ + PERF_BR_IRQ = 12, /* irq */ PERF_BR_MAX, }; @@ -465,6 +467,8 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via * siginfo_t::si_perf_data, e.g. to permit user to identify the event. + * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be + * truncated accordingly on 32 bit architectures. */ __u64 sig_data; }; @@ -1332,9 +1336,9 @@ union perf_mem_data_src { /* hop level */ #define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ -#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ -#define PERF_MEM_HOPS_3 0x04 /* remote board */ +#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ +#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ +#define PERF_MEM_HOPS_3 0x04 /* remote board */ /* 5-7 available */ #define PERF_MEM_HOPS_SHIFT 43 diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index bb73e9a0b24f..e998764f0262 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -272,4 +272,7 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 5fbb79e30819..2d3e5df39a59 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -56,8 +56,10 @@ * * ****************************************************************************/ +#define AES_IEC958_STATUS_SIZE 24 + struct snd_aes_iec958 { - unsigned char status[24]; /* AES/IEC958 channel status bits */ + unsigned char status[AES_IEC958_STATUS_SIZE]; /* AES/IEC958 channel status bits */ unsigned char subcode[147]; /* AES/IEC958 subcode bits */ unsigned char pad; /* nothing */ unsigned char dig_subframe[4]; /* AES/IEC958 subframe bits */ @@ -202,6 +204,11 @@ typedef int __bitwise snd_pcm_format_t; #define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */ +/* + * For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the + * available bit count in most significant bit. It's for the case of so-called 'left-justified' or + * `right-padding` sample which has less width than 32 bit. + */ #define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10) #define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11) #define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12) @@ -300,7 +307,7 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME 0x04000000 /* report estimated link audio time */ #define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000 /* report synchronized audio/system time */ #define SNDRV_PCM_INFO_EXPLICIT_SYNC 0x10000000 /* needs explicit sync of pointers and data */ - +#define SNDRV_PCM_INFO_NO_REWINDS 0x20000000 /* hardware can only support monotonic changes of appl_ptr */ #define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */ #define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 581f9ffb4237..1973a18c096b 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -3,11 +3,7 @@ #define __LIBPERF_INTERNAL_CPUMAP_H #include <linux/refcount.h> - -/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ -struct perf_cpu { - int cpu; -}; +#include <perf/cpumap.h> /** * A sized, reference counted, sorted array of integers representing CPU diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 15b8faafd615..4a2edbdb5e2b 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -7,6 +7,11 @@ #include <stdio.h> #include <stdbool.h> +/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ +struct perf_cpu { + int cpu; +}; + LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 75ee385fb078..e7758707cadd 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -240,7 +240,7 @@ struct id_index_entry { struct perf_record_id_index { struct perf_event_header header; __u64 nr; - struct id_index_entry entries[0]; + struct id_index_entry entries[]; }; struct perf_record_auxtrace_info { diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map index 93696affda2e..6fa0d651576b 100644 --- a/tools/lib/perf/libperf.map +++ b/tools/lib/perf/libperf.map @@ -2,6 +2,7 @@ LIBPERF_0.0.1 { global: libperf_init; perf_cpu_map__dummy_new; + perf_cpu_map__default_new; perf_cpu_map__get; perf_cpu_map__put; perf_cpu_map__new; diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c index f7ee07cb5818..0d1634cedf44 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -13,6 +13,7 @@ #include <internal/lib.h> #include <linux/kernel.h> #include <linux/math64.h> +#include <linux/stringify.h> #include "internal.h" void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, @@ -294,6 +295,103 @@ static u64 read_timestamp(void) return low | ((u64)high) << 32; } +#elif defined(__aarch64__) +#define read_sysreg(r) ({ \ + u64 __val; \ + asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ + __val; \ +}) + +static u64 read_pmccntr(void) +{ + return read_sysreg(pmccntr_el0); +} + +#define PMEVCNTR_READ(idx) \ + static u64 read_pmevcntr_##idx(void) { \ + return read_sysreg(pmevcntr##idx##_el0); \ + } + +PMEVCNTR_READ(0); +PMEVCNTR_READ(1); +PMEVCNTR_READ(2); +PMEVCNTR_READ(3); +PMEVCNTR_READ(4); +PMEVCNTR_READ(5); +PMEVCNTR_READ(6); +PMEVCNTR_READ(7); +PMEVCNTR_READ(8); +PMEVCNTR_READ(9); +PMEVCNTR_READ(10); +PMEVCNTR_READ(11); +PMEVCNTR_READ(12); +PMEVCNTR_READ(13); +PMEVCNTR_READ(14); +PMEVCNTR_READ(15); +PMEVCNTR_READ(16); +PMEVCNTR_READ(17); +PMEVCNTR_READ(18); +PMEVCNTR_READ(19); +PMEVCNTR_READ(20); +PMEVCNTR_READ(21); +PMEVCNTR_READ(22); +PMEVCNTR_READ(23); +PMEVCNTR_READ(24); +PMEVCNTR_READ(25); +PMEVCNTR_READ(26); +PMEVCNTR_READ(27); +PMEVCNTR_READ(28); +PMEVCNTR_READ(29); +PMEVCNTR_READ(30); + +/* + * Read a value direct from PMEVCNTR<idx> + */ +static u64 read_perf_counter(unsigned int counter) +{ + static u64 (* const read_f[])(void) = { + read_pmevcntr_0, + read_pmevcntr_1, + read_pmevcntr_2, + read_pmevcntr_3, + read_pmevcntr_4, + read_pmevcntr_5, + read_pmevcntr_6, + read_pmevcntr_7, + read_pmevcntr_8, + read_pmevcntr_9, + read_pmevcntr_10, + read_pmevcntr_11, + read_pmevcntr_13, + read_pmevcntr_12, + read_pmevcntr_14, + read_pmevcntr_15, + read_pmevcntr_16, + read_pmevcntr_17, + read_pmevcntr_18, + read_pmevcntr_19, + read_pmevcntr_20, + read_pmevcntr_21, + read_pmevcntr_22, + read_pmevcntr_23, + read_pmevcntr_24, + read_pmevcntr_25, + read_pmevcntr_26, + read_pmevcntr_27, + read_pmevcntr_28, + read_pmevcntr_29, + read_pmevcntr_30, + read_pmccntr + }; + + if (counter < ARRAY_SIZE(read_f)) + return (read_f[counter])(); + + return 0; +} + +static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); } + #else static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; } static u64 read_timestamp(void) { return 0; } diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c index d39378eaf897..87b0510a556f 100644 --- a/tools/lib/perf/tests/test-cpumap.c +++ b/tools/lib/perf/tests/test-cpumap.c @@ -14,6 +14,8 @@ static int libperf_print(enum libperf_print_level level, int test_cpumap(int argc, char **argv) { struct perf_cpu_map *cpus; + struct perf_cpu cpu; + int idx; __T_START; @@ -27,6 +29,15 @@ int test_cpumap(int argc, char **argv) perf_cpu_map__put(cpus); perf_cpu_map__put(cpus); + cpus = perf_cpu_map__default_new(); + if (!cpus) + return -1; + + perf_cpu_map__for_each_cpu(cpu, idx, cpus) + __T("wrong cpu number", cpu.cpu != -1); + + perf_cpu_map__put(cpus); + __T_END; return tests_failed == 0 ? 0 : -1; } diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index b3479dfa9a1c..fa854c83b7e7 100644 --- a/tools/lib/perf/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE // needed for sched.h to get sched_[gs]etaffinity and CPU_(ZERO,SET) +#include <inttypes.h> #include <sched.h> #include <stdio.h> #include <stdarg.h> @@ -526,12 +527,12 @@ static int test_stat_multiplexing(void) min = counts[0].val; for (i = 0; i < EVENT_NUM; i++) { - __T_VERBOSE("Event %2d -- Raw count = %lu, run = %lu, enable = %lu\n", + __T_VERBOSE("Event %2d -- Raw count = %" PRIu64 ", run = %" PRIu64 ", enable = %" PRIu64 "\n", i, counts[i].val, counts[i].run, counts[i].ena); perf_counts_values__scale(&counts[i], true, &scaled); if (scaled == 1) { - __T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n", + __T_VERBOSE("\t Scaled count = %" PRIu64 " (%.2lf%%, %" PRIu64 "/%" PRIu64 ")\n", counts[i].val, (double)counts[i].run / (double)counts[i].ena * 100.0, counts[i].run, counts[i].ena); diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 33ae9334861a..89be89afb24d 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -130,6 +130,9 @@ static int test_stat_user_read(int event) struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = event, +#ifdef __aarch64__ + .config1 = 0x2, /* Request user access */ +#endif }; int err, i; @@ -150,7 +153,7 @@ static int test_stat_user_read(int event) pc = perf_evsel__mmap_base(evsel, 0, 0); __T("failed to get mmapped address", pc); -#if defined(__i386__) || defined(__x86_64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) __T("userspace counter access not supported", pc->cap_user_rdpmc); __T("userspace counter access not enabled", pc->index); __T("userspace counter width not set", pc->pmc_width >= 32); diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h index 794a375dad36..b2aec04fce8f 100644 --- a/tools/lib/subcmd/subcmd-util.h +++ b/tools/lib/subcmd/subcmd-util.h @@ -50,15 +50,8 @@ static NORETURN inline void die(const char *err, ...) static inline void *xrealloc(void *ptr, size_t size) { void *ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) { - ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) - die("Out of memory, realloc failed"); - } + if (!ret) + die("Out of memory, realloc failed"); return ret; } diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index 394ee57d58f2..ee819a402b69 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -485,6 +485,57 @@ have R ->po X. It wouldn't make sense for a computation to depend somehow on a value that doesn't get loaded from shared memory until later in the code! +Here's a trick question: When is a dependency not a dependency? Answer: +When it is purely syntactic rather than semantic. We say a dependency +between two accesses is purely syntactic if the second access doesn't +actually depend on the result of the first. Here is a trivial example: + + r1 = READ_ONCE(x); + WRITE_ONCE(y, r1 * 0); + +There appears to be a data dependency from the load of x to the store +of y, since the value to be stored is computed from the value that was +loaded. But in fact, the value stored does not really depend on +anything since it will always be 0. Thus the data dependency is only +syntactic (it appears to exist in the code) but not semantic (the +second access will always be the same, regardless of the value of the +first access). Given code like this, a compiler could simply discard +the value returned by the load from x, which would certainly destroy +any dependency. (The compiler is not permitted to eliminate entirely +the load generated for a READ_ONCE() -- that's one of the nice +properties of READ_ONCE() -- but it is allowed to ignore the load's +value.) + +It's natural to object that no one in their right mind would write +code like the above. However, macro expansions can easily give rise +to this sort of thing, in ways that often are not apparent to the +programmer. + +Another mechanism that can lead to purely syntactic dependencies is +related to the notion of "undefined behavior". Certain program +behaviors are called "undefined" in the C language specification, +which means that when they occur there are no guarantees at all about +the outcome. Consider the following example: + + int a[1]; + int i; + + r1 = READ_ONCE(i); + r2 = READ_ONCE(a[r1]); + +Access beyond the end or before the beginning of an array is one kind +of undefined behavior. Therefore the compiler doesn't have to worry +about what will happen if r1 is nonzero, and it can assume that r1 +will always be zero regardless of the value actually loaded from i. +(If the assumption turns out to be wrong the resulting behavior will +be undefined anyway, so the compiler doesn't care!) Thus the value +from the load can be discarded, breaking the address dependency. + +The LKMM is unaware that purely syntactic dependencies are different +from semantic dependencies and therefore mistakenly predicts that the +accesses in the two examples above will be ordered. This is another +example of how the compiler can undermine the memory model. Be warned. + THE READS-FROM RELATION: rf, rfi, and rfe ----------------------------------------- diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index c10ef78df050..479e769ca324 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -112,7 +112,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec const struct elf *elf = file->elf; struct insn insn; int x86_64, ret; - unsigned char op1, op2, + unsigned char op1, op2, op3, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0, rex_x = 0, modrm = 0, modrm_mod = 0, modrm_rm = 0, modrm_reg = 0, sib = 0, /* sib_scale = 0, */ sib_index = 0, sib_base = 0; @@ -139,6 +139,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec op1 = insn.opcode.bytes[0]; op2 = insn.opcode.bytes[1]; + op3 = insn.opcode.bytes[2]; if (insn.rex_prefix.nbytes) { rex = insn.rex_prefix.bytes[0]; @@ -491,6 +492,14 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec /* nopl/nopw */ *type = INSN_NOP; + } else if (op2 == 0x38 && op3 == 0xf8) { + if (insn.prefixes.nbytes == 1 && + insn.prefixes.bytes[0] == 0xf2) { + /* ENQCMD cannot be used in the kernel. */ + WARN("ENQCMD instruction at %s:%lx", sec->name, + offset); + } + } else if (op2 == 0xa0 || op2 == 0xa8) { /* push fs/gs */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c2d2ab9a2861..7c33ec67c4a9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2854,7 +2854,7 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { - static char pvname[16]; + static char pvname[19]; struct reloc *rel; int idx; diff --git a/tools/perf/arch/nds32/Build b/tools/perf/arch/nds32/Build deleted file mode 100644 index e4e5f33c84d8..000000000000 --- a/tools/perf/arch/nds32/Build +++ /dev/null @@ -1 +0,0 @@ -perf-y += util/ diff --git a/tools/perf/arch/nds32/util/Build b/tools/perf/arch/nds32/util/Build deleted file mode 100644 index d0bc205fe49a..000000000000 --- a/tools/perf/arch/nds32/util/Build +++ /dev/null @@ -1 +0,0 @@ -perf-y += header.o diff --git a/tools/perf/arch/nds32/util/header.c b/tools/perf/arch/nds32/util/header.c deleted file mode 100644 index ef9dbdbe7968..000000000000 --- a/tools/perf/arch/nds32/util/header.c +++ /dev/null @@ -1,29 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2005-2017 Andes Technology Corporation - -#include <stdio.h> -#include <stdlib.h> -#include <api/fs/fs.h> -#include "header.h" - -#define STR_LEN 1024 - -char *get_cpuid_str(struct perf_pmu *pmu) -{ - /* In nds32, we only have one cpu */ - char *buf = NULL; - struct cpu_map *cpus; - const char *sysfs = sysfs__mountpoint(); - - if (!sysfs || !pmu || !pmu->cpus) - return NULL; - - buf = malloc(STR_LEN); - if (!buf) - return NULL; - - cpus = cpu_map__get(pmu->cpus); - sprintf(buf, "0x%x", cpus->nr - 1); - cpu_map__put(cpus); - return buf; -} diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index 9708ae892061..ba429cadb18f 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -2197,6 +2197,924 @@ "3e f2 ff 25 78 56 34 12 \tnotrack bnd jmp *0x12345678",}, {{0x3e, 0xf2, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "jmp", "indirect", "3e f2 ff a4 c8 78 56 34 12 \tnotrack bnd jmp *0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 58 cb \tvaddph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 58 cb \tvaddph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 58 cb \tvaddph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 58 cb \tvaddsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 58 8c c8 78 56 34 12 \tvaddsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6c 48 c2 eb 12 \tvcmple_oqph %zmm3,%zmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 48 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%zmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 c2 eb 12 \tvcmple_oqph %xmm3,%xmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%xmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6c 28 c2 eb 12 \tvcmple_oqph %ymm3,%ymm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 28 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%ymm2,%k5",}, +{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6e 08 c2 eb 12 \tvcmple_oqsh %xmm3,%xmm2,%k5",}, +{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6e 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqsh 0x12345678(%eax,%ecx,8),%xmm2,%k5",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 2f ca \tvcomish %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 2f 8c c8 78 56 34 12 \tvcomish 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 5b ca \tvcvtdq2ph %zmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 5b 8c c8 78 56 34 12 \tvcvtdq2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 5b ca \tvcvtdq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 5b ca \tvcvtdq2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0xfd, 0x48, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 fd 48 5a ca \tvcvtpd2ph %zmm2,%xmm1",}, +{{0x62, 0xf5, 0xfd, 0x08, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 fd 08 5a ca \tvcvtpd2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0xfd, 0x28, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 fd 28 5a ca \tvcvtpd2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 5b ca \tvcvtph2dq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 5b ca \tvcvtph2dq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 5b ca \tvcvtph2dq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 5a ca \tvcvtph2pd %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 5a ca \tvcvtph2pd %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 5a ca \tvcvtph2pd %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "", +"62 f2 7d 48 13 ca \tvcvtph2ps %ymm2,%zmm1",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 13 ca \tvcvtph2psx %ymm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 13 ca \tvcvtph2psx %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 13 ca \tvcvtph2psx %xmm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7b ca \tvcvtph2qq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7b ca \tvcvtph2qq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7b ca \tvcvtph2qq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 79 ca \tvcvtph2udq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 79 ca \tvcvtph2udq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 79 ca \tvcvtph2udq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 79 ca \tvcvtph2uqq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 79 ca \tvcvtph2uqq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 79 ca \tvcvtph2uqq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 7d ca \tvcvtph2uw %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 7d ca \tvcvtph2uw %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 7d ca \tvcvtph2uw %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7d ca \tvcvtph2w %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7d ca \tvcvtph2w %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7d ca \tvcvtph2w %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7d 48 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%zmm1,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0xd1, 0x12, }, 7, 0, "", "", +"62 f3 7d 48 1d d1 12 \tvcvtps2ph $0x12,%zmm2,%ymm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 7d 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm1,0x12345678(%eax,%ecx,8)",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 79 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm1,0x12345678(%eax,%ecx,8)",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 7d 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm2,0x12345678(%eax,%ecx,8)",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 79 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm2,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 1d ca \tvcvtps2phx %zmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 1d 8c c8 78 56 34 12 \tvcvtps2phx 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x1d, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 1d ca \tvcvtps2phx %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x1d, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 1d ca \tvcvtps2phx %ymm2,%xmm1",}, +{{0x62, 0xf5, 0xfc, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 fc 48 5b ca \tvcvtqq2ph %zmm2,%xmm1",}, +{{0x62, 0xf5, 0xfc, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 fc 08 5b ca \tvcvtqq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0xfc, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 fc 28 5b ca \tvcvtqq2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0xef, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 ef 08 5a 8c c8 78 56 34 12 \tvcvtsd2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5a 8c c8 78 56 34 12 \tvcvtsh2sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x2d, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 2d 84 c8 78 56 34 12 \tvcvtsh2si 0x12345678(%eax,%ecx,8),%eax",}, +{{0x62, 0xf6, 0x6c, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6c 08 13 8c c8 78 56 34 12 \tvcvtsh2ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0xc1, }, 6, 0, "", "", +"62 f5 7e 08 79 c1 \tvcvtsh2usi %xmm1,%eax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%eax,%ecx,8),%eax",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0xc8, }, 6, 0, "", "", +"62 f5 6e 08 2a c8 \tvcvtsi2sh %eax,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 1d cb \tvcvtss2sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 1d 8c c8 78 56 34 12 \tvcvtss2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7e 48 5b ca \tvcvttph2dq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 48 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7e 08 5b ca \tvcvttph2dq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7e 28 5b ca \tvcvttph2dq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 28 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7a ca \tvcvttph2qq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7a ca \tvcvttph2qq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7a ca \tvcvttph2qq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 78 ca \tvcvttph2udq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 78 ca \tvcvttph2udq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 78 ca \tvcvttph2udq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 78 ca \tvcvttph2uqq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 78 ca \tvcvttph2uqq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 78 ca \tvcvttph2uqq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 7c ca \tvcvttph2uw %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 7c ca \tvcvttph2uw %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 7c ca \tvcvttph2uw %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7c ca \tvcvttph2w %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7c ca \tvcvttph2w %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7c ca \tvcvttph2w %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0xc1, }, 6, 0, "", "", +"62 f5 7e 08 2c c1 \tvcvttsh2si %xmm1,%eax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%eax,%ecx,8),%eax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0xc1, }, 6, 0, "", "", +"62 f5 7e 08 78 c1 \tvcvttsh2usi %xmm1,%eax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%eax,%ecx,8),%eax",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7f 48 7a ca \tvcvtudq2ph %zmm2,%ymm1",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 48 7a 8c c8 78 56 34 12 \tvcvtudq2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7f, 0x08, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7f 08 7a ca \tvcvtudq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x28, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7f 28 7a ca \tvcvtudq2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0xff, 0x48, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 ff 48 7a ca \tvcvtuqq2ph %zmm2,%xmm1",}, +{{0x62, 0xf5, 0xff, 0x08, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 ff 08 7a ca \tvcvtuqq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0xff, 0x28, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 ff 28 7a ca \tvcvtuqq2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0xc8, }, 6, 0, "", "", +"62 f5 6e 08 7b c8 \tvcvtusi2sh %eax,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7f 48 7d ca \tvcvtuw2ph %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 48 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7f 08 7d ca \tvcvtuw2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 08 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7f 28 7d ca \tvcvtuw2ph %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 28 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7e 48 7d ca \tvcvtw2ph %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 48 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7e 08 7d ca \tvcvtw2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7e 28 7d ca \tvcvtw2ph %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 28 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5e cb \tvdivph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5e cb \tvdivph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5e cb \tvdivph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5e cb \tvdivsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5e 8c c8 78 56 34 12 \tvdivsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6f 48 56 cb \tvfcmaddcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 48 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 56 cb \tvfcmaddcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6f 28 56 cb \tvfcmaddcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 28 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 57 cb \tvfcmaddcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 57 8c c8 78 56 34 12 \tvfcmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6f 48 d6 cb \tvfcmulcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 48 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 d6 cb \tvfcmulcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6f 28 d6 cb \tvfcmulcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 28 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 d7 cb \tvfcmulcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 d7 8c c8 78 56 34 12 \tvfcmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 98 cb \tvfmadd132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 98 cb \tvfmadd132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 98 cb \tvfmadd132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 99 cb \tvfmadd132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 99 8c c8 78 56 34 12 \tvfmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 a8 cb \tvfmadd213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a8 cb \tvfmadd213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 a8 cb \tvfmadd213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a9 cb \tvfmadd213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a9 8c c8 78 56 34 12 \tvfmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 b8 cb \tvfmadd231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b8 cb \tvfmadd231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 b8 cb \tvfmadd231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b9 cb \tvfmadd231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b9 8c c8 78 56 34 12 \tvfmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6e 48 56 cb \tvfmaddcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 48 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 56 cb \tvfmaddcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6e 28 56 cb \tvfmaddcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 28 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 57 cb \tvfmaddcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 57 8c c8 78 56 34 12 \tvfmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 96 cb \tvfmaddsub132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 96 cb \tvfmaddsub132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 96 cb \tvfmaddsub132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 a6 cb \tvfmaddsub213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a6 cb \tvfmaddsub213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 a6 cb \tvfmaddsub213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 b6 cb \tvfmaddsub231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b6 cb \tvfmaddsub231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 b6 cb \tvfmaddsub231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 9a cb \tvfmsub132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9a cb \tvfmsub132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 9a cb \tvfmsub132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9b cb \tvfmsub132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9b 8c c8 78 56 34 12 \tvfmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 aa cb \tvfmsub213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 aa cb \tvfmsub213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 aa cb \tvfmsub213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ab cb \tvfmsub213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ab 8c c8 78 56 34 12 \tvfmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 ba cb \tvfmsub231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ba cb \tvfmsub231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 ba cb \tvfmsub231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bb cb \tvfmsub231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bb 8c c8 78 56 34 12 \tvfmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 97 cb \tvfmsubadd132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 97 cb \tvfmsubadd132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 97 cb \tvfmsubadd132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 a7 cb \tvfmsubadd213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a7 cb \tvfmsubadd213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 a7 cb \tvfmsubadd213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 b7 cb \tvfmsubadd231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b7 cb \tvfmsubadd231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 b7 cb \tvfmsubadd231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6e 48 d6 cb \tvfmulcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 48 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 d6 cb \tvfmulcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6e 28 d6 cb \tvfmulcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 28 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 d7 cb \tvfmulcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 d7 8c c8 78 56 34 12 \tvfmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 9c cb \tvfnmadd132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9c cb \tvfnmadd132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 9c cb \tvfnmadd132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9d cb \tvfnmadd132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9d 8c c8 78 56 34 12 \tvfnmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 ac cb \tvfnmadd213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ac cb \tvfnmadd213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 ac cb \tvfnmadd213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ad cb \tvfnmadd213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ad 8c c8 78 56 34 12 \tvfnmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 bc cb \tvfnmadd231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bc cb \tvfnmadd231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 bc cb \tvfnmadd231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bd cb \tvfnmadd231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bd 8c c8 78 56 34 12 \tvfnmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 9e cb \tvfnmsub132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9e cb \tvfnmsub132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 9e cb \tvfnmsub132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9f cb \tvfnmsub132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9f 8c c8 78 56 34 12 \tvfnmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 ae cb \tvfnmsub213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ae cb \tvfnmsub213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 ae cb \tvfnmsub213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 af cb \tvfnmsub213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 af 8c c8 78 56 34 12 \tvfnmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 be cb \tvfnmsub231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 be cb \tvfnmsub231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 be cb \tvfnmsub231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bf cb \tvfnmsub231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bf 8c c8 78 56 34 12 \tvfnmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x66, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 66 e9 12 \tvfpclassph $0x12,%zmm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x66, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 66 e9 12 \tvfpclassph $0x12,%xmm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x66, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 66 e9 12 \tvfpclassph $0x12,%ymm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 67 e9 12 \tvfpclasssh $0x12,%xmm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 67 ac c8 78 56 34 12 12 \tvfpclasssh $0x12,0x12345678(%eax,%ecx,8),%k5",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 42 ca \tvgetexpph %zmm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 42 ca \tvgetexpph %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 42 ca \tvgetexpph %ymm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 43 cb \tvgetexpsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 43 8c c8 78 56 34 12 \tvgetexpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 26 ca 12 \tvgetmantph $0x12,%zmm2,%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 48 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 26 ca 12 \tvgetmantph $0x12,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 26 ca 12 \tvgetmantph $0x12,%ymm2,%ymm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 28 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0xcb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 27 cb 12 \tvgetmantsh $0x12,%xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 27 8c c8 78 56 34 12 12 \tvgetmantsh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5f cb \tvmaxph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5f cb \tvmaxph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5f cb \tvmaxph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5f cb \tvmaxsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5f 8c c8 78 56 34 12 \tvmaxsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5d cb \tvminph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5d cb \tvminph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5d cb \tvminph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5d cb \tvminsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5d 8c c8 78 56 34 12 \tvminsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x11, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 11 8c c8 78 56 34 12 \tvmovsh %xmm1,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x10, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 10 8c c8 78 56 34 12 \tvmovsh 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x10, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 10 cb \tvmovsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0xc8, }, 6, 0, "", "", +"62 f5 7d 08 7e c8 \tvmovw %xmm1,%eax",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7e 8c c8 78 56 34 12 \tvmovw %xmm1,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0xc8, }, 6, 0, "", "", +"62 f5 7d 08 6e c8 \tvmovw %eax,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 6e 8c c8 78 56 34 12 \tvmovw 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 59 cb \tvmulph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 59 cb \tvmulph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 59 cb \tvmulph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 59 cb \tvmulsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 59 8c c8 78 56 34 12 \tvmulsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 4c ca \tvrcpph %zmm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 4c ca \tvrcpph %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 4c ca \tvrcpph %ymm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 4d cb \tvrcpsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 4d 8c c8 78 56 34 12 \tvrcpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 56 ca 12 \tvreduceph $0x12,%zmm2,%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 48 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 56 ca 12 \tvreduceph $0x12,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 56 ca 12 \tvreduceph $0x12,%ymm2,%ymm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 28 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0xcb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 57 cb 12 \tvreducesh $0x12,%xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 57 8c c8 78 56 34 12 12 \tvreducesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 08 ca 12 \tvrndscaleph $0x12,%zmm2,%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 48 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 08 ca 12 \tvrndscaleph $0x12,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 08 ca 12 \tvrndscaleph $0x12,%ymm2,%ymm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 28 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0xcb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 0a cb 12 \tvrndscalesh $0x12,%xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 0a 8c c8 78 56 34 12 12 \tvrndscalesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 4e ca \tvrsqrtph %zmm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 4e ca \tvrsqrtph %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 4e ca \tvrsqrtph %ymm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 4f cb \tvrsqrtsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 4f 8c c8 78 56 34 12 \tvrsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 2c cb \tvscalefph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 2c cb \tvscalefph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 2c cb \tvscalefph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 2d cb \tvscalefsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 2d 8c c8 78 56 34 12 \tvscalefsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 51 ca \tvsqrtph %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 51 ca \tvsqrtph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 51 ca \tvsqrtph %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 51 cb \tvsqrtsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 51 8c c8 78 56 34 12 \tvsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5c cb \tvsubph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5c cb \tvsubph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5c cb \tvsubph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5c cb \tvsubsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5c 8c c8 78 56 34 12 \tvsubsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 2e ca \tvucomish %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 2e 8c c8 78 56 34 12 \tvucomish 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0xf3, 0x0f, 0x3a, 0xf0, 0xc0, 0x00, }, 6, 0, "", "", +"f3 0f 3a f0 c0 00 \threset $0x0",}, +{{0x0f, 0x01, 0xe8, }, 3, 0, "", "", +"0f 01 e8 \tserialize ",}, +{{0xf2, 0x0f, 0x01, 0xe9, }, 4, 0, "", "", +"f2 0f 01 e9 \txresldtrk ",}, +{{0xf2, 0x0f, 0x01, 0xe8, }, 4, 0, "", "", +"f2 0f 01 e8 \txsusldtrk ",}, {{0x0f, 0x01, 0xcf, }, 3, 0, "", "", "0f 01 cf \tencls ",}, {{0x0f, 0x01, 0xd7, }, 3, 0, "", "", diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index 5da17d41d302..3a47e98fec33 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -2459,6 +2459,1432 @@ "3e f2 ff a4 c8 78 56 34 12 \tnotrack bnd jmpq *0x12345678(%rax,%rcx,8)",}, {{0x3e, 0xf2, 0x41, 0xff, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "jmp", "indirect", "3e f2 41 ff a4 c8 78 56 34 12 \tnotrack bnd jmpq *0x12345678(%r8,%rcx,8)",}, +{{0xc4, 0xe2, 0x78, 0x49, 0x04, 0xc8, }, 6, 0, "", "", +"c4 e2 78 49 04 c8 \tldtilecfg (%rax,%rcx,8)",}, +{{0xc4, 0xc2, 0x78, 0x49, 0x04, 0xc8, }, 6, 0, "", "", +"c4 c2 78 49 04 c8 \tldtilecfg (%r8,%rcx,8)",}, +{{0xc4, 0xe2, 0x79, 0x49, 0x04, 0xc8, }, 6, 0, "", "", +"c4 e2 79 49 04 c8 \tsttilecfg (%rax,%rcx,8)",}, +{{0xc4, 0xc2, 0x79, 0x49, 0x04, 0xc8, }, 6, 0, "", "", +"c4 c2 79 49 04 c8 \tsttilecfg (%r8,%rcx,8)",}, +{{0xc4, 0xe2, 0x7a, 0x5c, 0xd1, }, 5, 0, "", "", +"c4 e2 7a 5c d1 \ttdpbf16ps %tmm0,%tmm1,%tmm2",}, +{{0xc4, 0xe2, 0x7b, 0x5e, 0xd1, }, 5, 0, "", "", +"c4 e2 7b 5e d1 \ttdpbssd %tmm0,%tmm1,%tmm2",}, +{{0xc4, 0xe2, 0x7a, 0x5e, 0xd1, }, 5, 0, "", "", +"c4 e2 7a 5e d1 \ttdpbsud %tmm0,%tmm1,%tmm2",}, +{{0xc4, 0xe2, 0x79, 0x5e, 0xd1, }, 5, 0, "", "", +"c4 e2 79 5e d1 \ttdpbusd %tmm0,%tmm1,%tmm2",}, +{{0xc4, 0xe2, 0x78, 0x5e, 0xd1, }, 5, 0, "", "", +"c4 e2 78 5e d1 \ttdpbuud %tmm0,%tmm1,%tmm2",}, +{{0xc4, 0xe2, 0x7b, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "", +"c4 e2 7b 4b 0c c8 \ttileloadd (%rax,%rcx,8),%tmm1",}, +{{0xc4, 0xc2, 0x7b, 0x4b, 0x14, 0xc8, }, 6, 0, "", "", +"c4 c2 7b 4b 14 c8 \ttileloadd (%r8,%rcx,8),%tmm2",}, +{{0xc4, 0xe2, 0x79, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "", +"c4 e2 79 4b 0c c8 \ttileloaddt1 (%rax,%rcx,8),%tmm1",}, +{{0xc4, 0xc2, 0x79, 0x4b, 0x14, 0xc8, }, 6, 0, "", "", +"c4 c2 79 4b 14 c8 \ttileloaddt1 (%r8,%rcx,8),%tmm2",}, +{{0xc4, 0xe2, 0x78, 0x49, 0xc0, }, 5, 0, "", "", +"c4 e2 78 49 c0 \ttilerelease ",}, +{{0xc4, 0xe2, 0x7a, 0x4b, 0x0c, 0xc8, }, 6, 0, "", "", +"c4 e2 7a 4b 0c c8 \ttilestored %tmm1,(%rax,%rcx,8)",}, +{{0xc4, 0xc2, 0x7a, 0x4b, 0x14, 0xc8, }, 6, 0, "", "", +"c4 c2 7a 4b 14 c8 \ttilestored %tmm2,(%r8,%rcx,8)",}, +{{0xc4, 0xe2, 0x7b, 0x49, 0xc0, }, 5, 0, "", "", +"c4 e2 7b 49 c0 \ttilezero %tmm0",}, +{{0xc4, 0xe2, 0x7b, 0x49, 0xf8, }, 5, 0, "", "", +"c4 e2 7b 49 f8 \ttilezero %tmm7",}, +{{0xf3, 0x0f, 0x01, 0xee, }, 4, 0, "", "", +"f3 0f 01 ee \tclui ",}, +{{0xf3, 0x0f, 0xc7, 0xf0, }, 4, 0, "", "", +"f3 0f c7 f0 \tsenduipi %rax",}, +{{0xf3, 0x41, 0x0f, 0xc7, 0xf0, }, 5, 0, "", "", +"f3 41 0f c7 f0 \tsenduipi %r8",}, +{{0xf3, 0x0f, 0x01, 0xef, }, 4, 0, "", "", +"f3 0f 01 ef \tstui ",}, +{{0xf3, 0x0f, 0x01, 0xed, }, 4, 0, "", "", +"f3 0f 01 ed \ttestui ",}, +{{0xf3, 0x0f, 0x01, 0xec, }, 4, 0, "", "", +"f3 0f 01 ec \tuiret ",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 58 cb \tvaddph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 48 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 58 cb \tvaddph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 08 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 58 cb \tvaddph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 28 58 8c c8 78 56 34 12 \tvaddph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 58 cb \tvaddsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 58 8c c8 78 56 34 12 \tvaddsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x58, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 58 8c c8 78 56 34 12 \tvaddsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6c 48 c2 eb 12 \tvcmple_oqph %zmm3,%zmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 48 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%rax,%rcx,8),%zmm2,%k5",}, +{{0x67, 0x62, 0xf3, 0x6c, 0x48, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 6c 48 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%zmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 c2 eb 12 \tvcmple_oqph %xmm3,%xmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%rax,%rcx,8),%xmm2,%k5",}, +{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 6c 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%xmm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6c 28 c2 eb 12 \tvcmple_oqph %ymm3,%ymm2,%k5",}, +{{0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 28 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%rax,%rcx,8),%ymm2,%k5",}, +{{0x67, 0x62, 0xf3, 0x6c, 0x28, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 6c 28 c2 ac c8 78 56 34 12 12 \tvcmple_oqph 0x12345678(%eax,%ecx,8),%ymm2,%k5",}, +{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xeb, 0x12, }, 7, 0, "", "", +"62 f3 6e 08 c2 eb 12 \tvcmple_oqsh %xmm3,%xmm2,%k5",}, +{{0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6e 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqsh 0x12345678(%rax,%rcx,8),%xmm2,%k5",}, +{{0x67, 0x62, 0xf3, 0x6e, 0x08, 0xc2, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 6e 08 c2 ac c8 78 56 34 12 12 \tvcmple_oqsh 0x12345678(%eax,%ecx,8),%xmm2,%k5",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 2f ca \tvcomish %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 2f 8c c8 78 56 34 12 \tvcomish 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x2f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 2f 8c c8 78 56 34 12 \tvcomish 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 5b ca \tvcvtdq2ph %zmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 5b 8c c8 78 56 34 12 \tvcvtdq2ph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 48 5b 8c c8 78 56 34 12 \tvcvtdq2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 5b ca \tvcvtdq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 5b ca \tvcvtdq2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0xfd, 0x48, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 fd 48 5a ca \tvcvtpd2ph %zmm2,%xmm1",}, +{{0x62, 0xf5, 0xfd, 0x08, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 fd 08 5a ca \tvcvtpd2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0xfd, 0x28, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 fd 28 5a ca \tvcvtpd2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 5b ca \tvcvtph2dq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 5b ca \tvcvtph2dq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 5b ca \tvcvtph2dq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 28 5b 8c c8 78 56 34 12 \tvcvtph2dq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 5a ca \tvcvtph2pd %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 48 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 5a ca \tvcvtph2pd %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 5a ca \tvcvtph2pd %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 28 5a 8c c8 78 56 34 12 \tvcvtph2pd 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "", +"62 f2 7d 48 13 ca \tvcvtph2ps %ymm2,%zmm1",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 79 13 ca \tvcvtph2ps %xmm2,%xmm1",}, +{{0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0xc4, 0xe2, 0x79, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 79 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xca, }, 5, 0, "", "", +"c4 e2 7d 13 ca \tvcvtph2ps %xmm2,%ymm1",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0xc4, 0xe2, 0x7d, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 7d 13 8c c8 78 56 34 12 \tvcvtph2ps 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 13 ca \tvcvtph2psx %ymm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 48 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 13 ca \tvcvtph2psx %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 08 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 13 ca \tvcvtph2psx %xmm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 28 13 8c c8 78 56 34 12 \tvcvtph2psx 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7b ca \tvcvtph2qq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7b ca \tvcvtph2qq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7b ca \tvcvtph2qq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 28 7b 8c c8 78 56 34 12 \tvcvtph2qq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 79 ca \tvcvtph2udq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 48 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 79 ca \tvcvtph2udq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 79 ca \tvcvtph2udq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 28 79 8c c8 78 56 34 12 \tvcvtph2udq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 79 ca \tvcvtph2uqq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 79 ca \tvcvtph2uqq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 79 ca \tvcvtph2uqq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x79, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 28 79 8c c8 78 56 34 12 \tvcvtph2uqq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 7d ca \tvcvtph2uw %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 48 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 7d ca \tvcvtph2uw %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 7d ca \tvcvtph2uw %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 28 7d 8c c8 78 56 34 12 \tvcvtph2uw 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7d ca \tvcvtph2w %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7d ca \tvcvtph2w %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7d ca \tvcvtph2w %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 28 7d 8c c8 78 56 34 12 \tvcvtph2w 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7d 48 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%zmm1,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0x62, 0xf3, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7d 48 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%zmm1,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x1d, 0xd1, 0x12, }, 7, 0, "", "", +"62 f3 7d 48 1d d1 12 \tvcvtps2ph $0x12,%zmm2,%ymm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 7d 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm1,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0xc4, 0xe3, 0x7d, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"67 c4 e3 7d 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm1,0x12345678(%eax,%ecx,8)",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 79 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm1,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0xc4, 0xe3, 0x79, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"67 c4 e3 79 1d 8c c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm1,0x12345678(%eax,%ecx,8)",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 7d 1d d1 12 \tvcvtps2ph $0x12,%ymm2,%xmm1",}, +{{0xc4, 0xe3, 0x7d, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 7d 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm2,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0xc4, 0xe3, 0x7d, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"67 c4 e3 7d 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%ymm2,0x12345678(%eax,%ecx,8)",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0xd1, 0x12, }, 6, 0, "", "", +"c4 e3 79 1d d1 12 \tvcvtps2ph $0x12,%xmm2,%xmm1",}, +{{0xc4, 0xe3, 0x79, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 11, 0, "", "", +"c4 e3 79 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm2,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0xc4, 0xe3, 0x79, 0x1d, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"67 c4 e3 79 1d 94 c8 78 56 34 12 12 \tvcvtps2ph $0x12,%xmm2,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 1d ca \tvcvtps2phx %zmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 1d 8c c8 78 56 34 12 \tvcvtps2phx 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 1d 8c c8 78 56 34 12 \tvcvtps2phx 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x1d, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 1d ca \tvcvtps2phx %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x1d, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 1d ca \tvcvtps2phx %ymm2,%xmm1",}, +{{0x62, 0xf5, 0xfc, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 fc 48 5b ca \tvcvtqq2ph %zmm2,%xmm1",}, +{{0x62, 0xf5, 0xfc, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 fc 08 5b ca \tvcvtqq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0xfc, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 fc 28 5b ca \tvcvtqq2ph %ymm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0xef, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 ef 08 5a 8c c8 78 56 34 12 \tvcvtsd2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 5a 8c c8 78 56 34 12 \tvcvtsh2sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x2d, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 2d 84 c8 78 56 34 12 \tvcvtsh2si 0x12345678(%eax,%ecx,8),%eax",}, +{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x2d, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 fe 08 2d 84 c8 78 56 34 12 \tvcvtsh2si 0x12345678(%eax,%ecx,8),%rax",}, +{{0x67, 0x62, 0xf6, 0x6c, 0x08, 0x13, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6c 08 13 8c c8 78 56 34 12 \tvcvtsh2ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0xc1, }, 6, 0, "", "", +"62 f5 7e 08 79 c1 \tvcvtsh2usi %xmm1,%eax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%rax,%rcx,8),%eax",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%eax,%ecx,8),%eax",}, +{{0x62, 0xf5, 0xfe, 0x08, 0x79, 0xc1, }, 6, 0, "", "", +"62 f5 fe 08 79 c1 \tvcvtsh2usi %xmm1,%rax",}, +{{0x62, 0xf5, 0xfe, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 fe 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%rax,%rcx,8),%rax",}, +{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x79, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 fe 08 79 84 c8 78 56 34 12 \tvcvtsh2usi 0x12345678(%eax,%ecx,8),%rax",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0xc8, }, 6, 0, "", "", +"62 f5 6e 08 2a c8 \tvcvtsi2sh %eax,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0xee, 0x08, 0x2a, 0xc8, }, 6, 0, "", "", +"62 f5 ee 08 2a c8 \tvcvtsi2sh %rax,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x2a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 2a 8c c8 78 56 34 12 \tvcvtsi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 1d cb \tvcvtss2sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 1d 8c c8 78 56 34 12 \tvcvtss2sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x1d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 08 1d 8c c8 78 56 34 12 \tvcvtss2sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7e 48 5b ca \tvcvttph2dq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 48 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x48, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 48 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7e 08 5b ca \tvcvttph2dq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0xca, }, 6, 0, "", "", +"62 f5 7e 28 5b ca \tvcvttph2dq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 28 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x28, 0x5b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 28 5b 8c c8 78 56 34 12 \tvcvttph2dq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7a ca \tvcvttph2qq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7a ca \tvcvttph2qq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7a ca \tvcvttph2qq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 28 7a 8c c8 78 56 34 12 \tvcvttph2qq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 78 ca \tvcvttph2udq %ymm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 48 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 78 ca \tvcvttph2udq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 78 ca \tvcvttph2udq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 28 78 8c c8 78 56 34 12 \tvcvttph2udq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 78 ca \tvcvttph2uqq %xmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 78 ca \tvcvttph2uqq %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 78 ca \tvcvttph2uqq %xmm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x78, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 28 78 8c c8 78 56 34 12 \tvcvttph2uqq 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 7c ca \tvcvttph2uw %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 48 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 7c ca \tvcvttph2uw %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 7c ca \tvcvttph2uw %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 28 7c 8c c8 78 56 34 12 \tvcvttph2uw 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7d 48 7c ca \tvcvttph2w %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 48 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x48, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 48 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7d 08 7c ca \tvcvttph2w %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0xca, }, 6, 0, "", "", +"62 f5 7d 28 7c ca \tvcvttph2w %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7d, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 28 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x28, 0x7c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 28 7c 8c c8 78 56 34 12 \tvcvttph2w 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0xc1, }, 6, 0, "", "", +"62 f5 7e 08 2c c1 \tvcvttsh2si %xmm1,%eax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%rax,%rcx,8),%eax",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%eax,%ecx,8),%eax",}, +{{0x62, 0xf5, 0xfe, 0x08, 0x2c, 0xc1, }, 6, 0, "", "", +"62 f5 fe 08 2c c1 \tvcvttsh2si %xmm1,%rax",}, +{{0x62, 0xf5, 0xfe, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 fe 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%rax,%rcx,8),%rax",}, +{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x2c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 fe 08 2c 84 c8 78 56 34 12 \tvcvttsh2si 0x12345678(%eax,%ecx,8),%rax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0xc1, }, 6, 0, "", "", +"62 f5 7e 08 78 c1 \tvcvttsh2usi %xmm1,%eax",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%rax,%rcx,8),%eax",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%eax,%ecx,8),%eax",}, +{{0x62, 0xf5, 0xfe, 0x08, 0x78, 0xc1, }, 6, 0, "", "", +"62 f5 fe 08 78 c1 \tvcvttsh2usi %xmm1,%rax",}, +{{0x62, 0xf5, 0xfe, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 fe 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%rax,%rcx,8),%rax",}, +{{0x67, 0x62, 0xf5, 0xfe, 0x08, 0x78, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 fe 08 78 84 c8 78 56 34 12 \tvcvttsh2usi 0x12345678(%eax,%ecx,8),%rax",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7f 48 7a ca \tvcvtudq2ph %zmm2,%ymm1",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 48 7a 8c c8 78 56 34 12 \tvcvtudq2ph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7f, 0x48, 0x7a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7f 48 7a 8c c8 78 56 34 12 \tvcvtudq2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7f, 0x08, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7f 08 7a ca \tvcvtudq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x28, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 7f 28 7a ca \tvcvtudq2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0xff, 0x48, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 ff 48 7a ca \tvcvtuqq2ph %zmm2,%xmm1",}, +{{0x62, 0xf5, 0xff, 0x08, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 ff 08 7a ca \tvcvtuqq2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0xff, 0x28, 0x7a, 0xca, }, 6, 0, "", "", +"62 f5 ff 28 7a ca \tvcvtuqq2ph %ymm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0xc8, }, 6, 0, "", "", +"62 f5 6e 08 7b c8 \tvcvtusi2sh %eax,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0xee, 0x08, 0x7b, 0xc8, }, 6, 0, "", "", +"62 f5 ee 08 7b c8 \tvcvtusi2sh %rax,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x7b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 7b 8c c8 78 56 34 12 \tvcvtusi2shl 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7f 48 7d ca \tvcvtuw2ph %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7f, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 48 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7f, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7f 48 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7f 08 7d ca \tvcvtuw2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 08 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7f, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7f 08 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7f 28 7d ca \tvcvtuw2ph %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7f, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7f 28 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7f, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7f 28 7d 8c c8 78 56 34 12 \tvcvtuw2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7e 48 7d ca \tvcvtw2ph %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 48 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x48, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 48 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7e 08 7d ca \tvcvtw2ph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0xca, }, 6, 0, "", "", +"62 f5 7e 28 7d ca \tvcvtw2ph %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7e, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 28 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x28, 0x7d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 28 7d 8c c8 78 56 34 12 \tvcvtw2ph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5e cb \tvdivph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 48 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5e cb \tvdivph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 08 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5e cb \tvdivph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 28 5e 8c c8 78 56 34 12 \tvdivph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5e cb \tvdivsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5e 8c c8 78 56 34 12 \tvdivsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 5e 8c c8 78 56 34 12 \tvdivsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6f 48 56 cb \tvfcmaddcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 48 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 48 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 56 cb \tvfcmaddcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 08 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6f 28 56 cb \tvfcmaddcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 28 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 28 56 8c c8 78 56 34 12 \tvfcmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 57 cb \tvfcmaddcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 57 8c c8 78 56 34 12 \tvfcmaddcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 08 57 8c c8 78 56 34 12 \tvfcmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6f 48 d6 cb \tvfcmulcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 48 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 48 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 d6 cb \tvfcmulcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 08 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6f 28 d6 cb \tvfcmulcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 28 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 28 d6 8c c8 78 56 34 12 \tvfcmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0xcb, }, 6, 0, "", "", +"62 f6 6f 08 d7 cb \tvfcmulcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6f, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6f 08 d7 8c c8 78 56 34 12 \tvfcmulcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6f, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6f 08 d7 8c c8 78 56 34 12 \tvfcmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 98 cb \tvfmadd132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 98 cb \tvfmadd132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 98 cb \tvfmadd132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x98, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 98 8c c8 78 56 34 12 \tvfmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 99 cb \tvfmadd132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x99, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 99 8c c8 78 56 34 12 \tvfmadd132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x99, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 99 8c c8 78 56 34 12 \tvfmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 a8 cb \tvfmadd213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a8 cb \tvfmadd213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 a8 cb \tvfmadd213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xa8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 a8 8c c8 78 56 34 12 \tvfmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a9 cb \tvfmadd213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a9 8c c8 78 56 34 12 \tvfmadd213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 a9 8c c8 78 56 34 12 \tvfmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 b8 cb \tvfmadd231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b8 cb \tvfmadd231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 b8 cb \tvfmadd231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xb8, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 b8 8c c8 78 56 34 12 \tvfmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b9 cb \tvfmadd231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b9 8c c8 78 56 34 12 \tvfmadd231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb9, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 b9 8c c8 78 56 34 12 \tvfmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6e 48 56 cb \tvfmaddcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 48 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 48 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 56 cb \tvfmaddcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 08 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0xcb, }, 6, 0, "", "", +"62 f6 6e 28 56 cb \tvfmaddcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 28 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 28 56 8c c8 78 56 34 12 \tvfmaddcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 57 cb \tvfmaddcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 57 8c c8 78 56 34 12 \tvfmaddcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 08 57 8c c8 78 56 34 12 \tvfmaddcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 96 cb \tvfmaddsub132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 96 cb \tvfmaddsub132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 96 cb \tvfmaddsub132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x96, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 96 8c c8 78 56 34 12 \tvfmaddsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 a6 cb \tvfmaddsub213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a6 cb \tvfmaddsub213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 a6 cb \tvfmaddsub213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xa6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 a6 8c c8 78 56 34 12 \tvfmaddsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 b6 cb \tvfmaddsub231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b6 cb \tvfmaddsub231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 b6 cb \tvfmaddsub231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xb6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 b6 8c c8 78 56 34 12 \tvfmaddsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 9a cb \tvfmsub132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9a cb \tvfmsub132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 9a cb \tvfmsub132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x9a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 9a 8c c8 78 56 34 12 \tvfmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9b cb \tvfmsub132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9b 8c c8 78 56 34 12 \tvfmsub132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9b, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 9b 8c c8 78 56 34 12 \tvfmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 aa cb \tvfmsub213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 aa cb \tvfmsub213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 aa cb \tvfmsub213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xaa, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 aa 8c c8 78 56 34 12 \tvfmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ab cb \tvfmsub213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xab, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ab 8c c8 78 56 34 12 \tvfmsub213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xab, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 ab 8c c8 78 56 34 12 \tvfmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 ba cb \tvfmsub231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ba cb \tvfmsub231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 ba cb \tvfmsub231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xba, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 ba 8c c8 78 56 34 12 \tvfmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bb cb \tvfmsub231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bb 8c c8 78 56 34 12 \tvfmsub231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 bb 8c c8 78 56 34 12 \tvfmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 97 cb \tvfmsubadd132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 97 cb \tvfmsubadd132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 97 cb \tvfmsubadd132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x97, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 97 8c c8 78 56 34 12 \tvfmsubadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 a7 cb \tvfmsubadd213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 a7 cb \tvfmsubadd213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 a7 cb \tvfmsubadd213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xa7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 a7 8c c8 78 56 34 12 \tvfmsubadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 b7 cb \tvfmsubadd231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 b7 cb \tvfmsubadd231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 b7 cb \tvfmsubadd231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xb7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 b7 8c c8 78 56 34 12 \tvfmsubadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6e 48 d6 cb \tvfmulcph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 48 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x48, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 48 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 d6 cb \tvfmulcph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 08 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0xcb, }, 6, 0, "", "", +"62 f6 6e 28 d6 cb \tvfmulcph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 28 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x28, 0xd6, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 28 d6 8c c8 78 56 34 12 \tvfmulcph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0xcb, }, 6, 0, "", "", +"62 f6 6e 08 d7 cb \tvfmulcsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6e, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6e 08 d7 8c c8 78 56 34 12 \tvfmulcsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6e, 0x08, 0xd7, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6e 08 d7 8c c8 78 56 34 12 \tvfmulcsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 9c cb \tvfnmadd132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9c cb \tvfnmadd132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 9c cb \tvfnmadd132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x9c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 9c 8c c8 78 56 34 12 \tvfnmadd132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9d cb \tvfnmadd132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9d 8c c8 78 56 34 12 \tvfnmadd132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 9d 8c c8 78 56 34 12 \tvfnmadd132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 ac cb \tvfnmadd213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ac cb \tvfnmadd213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 ac cb \tvfnmadd213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xac, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 ac 8c c8 78 56 34 12 \tvfnmadd213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ad cb \tvfnmadd213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xad, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ad 8c c8 78 56 34 12 \tvfnmadd213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xad, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 ad 8c c8 78 56 34 12 \tvfnmadd213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 bc cb \tvfnmadd231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bc cb \tvfnmadd231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 bc cb \tvfnmadd231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xbc, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 bc 8c c8 78 56 34 12 \tvfnmadd231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bd cb \tvfnmadd231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbd, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bd 8c c8 78 56 34 12 \tvfnmadd231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbd, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 bd 8c c8 78 56 34 12 \tvfnmadd231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 9e cb \tvfnmsub132ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9e cb \tvfnmsub132ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 9e cb \tvfnmsub132ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x9e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 9e 8c c8 78 56 34 12 \tvfnmsub132ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 9f cb \tvfnmsub132sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x9f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 9f 8c c8 78 56 34 12 \tvfnmsub132sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x9f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 9f 8c c8 78 56 34 12 \tvfnmsub132sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 ae cb \tvfnmsub213ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 ae cb \tvfnmsub213ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 ae cb \tvfnmsub213ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xae, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 ae 8c c8 78 56 34 12 \tvfnmsub213ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 af cb \tvfnmsub213sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xaf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 af 8c c8 78 56 34 12 \tvfnmsub213sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xaf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 af 8c c8 78 56 34 12 \tvfnmsub213sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 be cb \tvfnmsub231ph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 be cb \tvfnmsub231ph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 be cb \tvfnmsub231ph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0xbe, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 be 8c c8 78 56 34 12 \tvfnmsub231ph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 bf cb \tvfnmsub231sh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0xbf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 bf 8c c8 78 56 34 12 \tvfnmsub231sh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0xbf, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 bf 8c c8 78 56 34 12 \tvfnmsub231sh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x66, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 66 e9 12 \tvfpclassph $0x12,%zmm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x66, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 66 e9 12 \tvfpclassph $0x12,%xmm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x66, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 66 e9 12 \tvfpclassph $0x12,%ymm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xe9, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 67 e9 12 \tvfpclasssh $0x12,%xmm1,%k5",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x67, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 67 ac c8 78 56 34 12 12 \tvfpclasssh $0x12,0x12345678(%rax,%rcx,8),%k5",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x67, 0xac, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 08 67 ac c8 78 56 34 12 12 \tvfpclasssh $0x12,0x12345678(%eax,%ecx,8),%k5",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 42 ca \tvgetexpph %zmm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 48 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 42 ca \tvgetexpph %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 08 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 42 ca \tvgetexpph %ymm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x42, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 28 42 8c c8 78 56 34 12 \tvgetexpph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 43 cb \tvgetexpsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x43, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 43 8c c8 78 56 34 12 \tvgetexpsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x43, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 43 8c c8 78 56 34 12 \tvgetexpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 26 ca 12 \tvgetmantph $0x12,%zmm2,%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 48 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x48, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 48 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 26 ca 12 \tvgetmantph $0x12,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 08 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 26 ca 12 \tvgetmantph $0x12,%ymm2,%ymm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 28 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x28, 0x26, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 28 26 8c c8 78 56 34 12 12 \tvgetmantph $0x12,0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0xcb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 27 cb 12 \tvgetmantsh $0x12,%xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x27, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 27 8c c8 78 56 34 12 12 \tvgetmantsh $0x12,0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0x27, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 6c 08 27 8c c8 78 56 34 12 12 \tvgetmantsh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5f cb \tvmaxph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 48 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5f cb \tvmaxph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 08 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5f cb \tvmaxph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 28 5f 8c c8 78 56 34 12 \tvmaxph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5f cb \tvmaxsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5f 8c c8 78 56 34 12 \tvmaxsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 5f 8c c8 78 56 34 12 \tvmaxsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5d cb \tvminph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 48 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5d cb \tvminph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 08 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5d cb \tvminph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 28 5d 8c c8 78 56 34 12 \tvminph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5d cb \tvminsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5d 8c c8 78 56 34 12 \tvminsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 5d 8c c8 78 56 34 12 \tvminsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x11, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 11 8c c8 78 56 34 12 \tvmovsh %xmm1,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x11, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 11 8c c8 78 56 34 12 \tvmovsh %xmm1,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf5, 0x7e, 0x08, 0x10, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7e 08 10 8c c8 78 56 34 12 \tvmovsh 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7e, 0x08, 0x10, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7e 08 10 8c c8 78 56 34 12 \tvmovsh 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x10, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 10 cb \tvmovsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0xc8, }, 6, 0, "", "", +"62 f5 7d 08 7e c8 \tvmovw %xmm1,%eax",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x7e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 7e 8c c8 78 56 34 12 \tvmovw %xmm1,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x7e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 7e 8c c8 78 56 34 12 \tvmovw %xmm1,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0xc8, }, 6, 0, "", "", +"62 f5 7d 08 6e c8 \tvmovw %eax,%xmm1",}, +{{0x62, 0xf5, 0x7d, 0x08, 0x6e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7d 08 6e 8c c8 78 56 34 12 \tvmovw 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7d, 0x08, 0x6e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7d 08 6e 8c c8 78 56 34 12 \tvmovw 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 59 cb \tvmulph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 48 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 59 cb \tvmulph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 08 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 59 cb \tvmulph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 28 59 8c c8 78 56 34 12 \tvmulph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 59 cb \tvmulsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 59 8c c8 78 56 34 12 \tvmulsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x59, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 59 8c c8 78 56 34 12 \tvmulsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 4c ca \tvrcpph %zmm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 48 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 4c ca \tvrcpph %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 08 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 4c ca \tvrcpph %ymm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x4c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 28 4c 8c c8 78 56 34 12 \tvrcpph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 4d cb \tvrcpsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 4d 8c c8 78 56 34 12 \tvrcpsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x4d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 4d 8c c8 78 56 34 12 \tvrcpsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 56 ca 12 \tvreduceph $0x12,%zmm2,%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 48 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x48, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 48 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 56 ca 12 \tvreduceph $0x12,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 08 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 56 ca 12 \tvreduceph $0x12,%ymm2,%ymm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 28 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x28, 0x56, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 28 56 8c c8 78 56 34 12 12 \tvreduceph $0x12,0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0xcb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 57 cb 12 \tvreducesh $0x12,%xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 57 8c c8 78 56 34 12 12 \tvreducesh $0x12,0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0x57, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 6c 08 57 8c c8 78 56 34 12 12 \tvreducesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 48 08 ca 12 \tvrndscaleph $0x12,%zmm2,%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x48, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 48 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x48, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 48 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 08 08 ca 12 \tvrndscaleph $0x12,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x08, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 08 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x08, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 08 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0xca, 0x12, }, 7, 0, "", "", +"62 f3 7c 28 08 ca 12 \tvrndscaleph $0x12,%ymm2,%ymm1",}, +{{0x62, 0xf3, 0x7c, 0x28, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 7c 28 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf3, 0x7c, 0x28, 0x08, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 7c 28 08 8c c8 78 56 34 12 12 \tvrndscaleph $0x12,0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0xcb, 0x12, }, 7, 0, "", "", +"62 f3 6c 08 0a cb 12 \tvrndscalesh $0x12,%xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf3, 0x6c, 0x08, 0x0a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 12, 0, "", "", +"62 f3 6c 08 0a 8c c8 78 56 34 12 12 \tvrndscalesh $0x12,0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf3, 0x6c, 0x08, 0x0a, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x12, }, 13, 0, "", "", +"67 62 f3 6c 08 0a 8c c8 78 56 34 12 12 \tvrndscalesh $0x12,0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0xca, }, 6, 0, "", "", +"62 f6 7d 48 4e ca \tvrsqrtph %zmm2,%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x48, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 48 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x48, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 48 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0xca, }, 6, 0, "", "", +"62 f6 7d 08 4e ca \tvrsqrtph %xmm2,%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x08, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 08 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x08, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 08 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0xca, }, 6, 0, "", "", +"62 f6 7d 28 4e ca \tvrsqrtph %ymm2,%ymm1",}, +{{0x62, 0xf6, 0x7d, 0x28, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 7d 28 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf6, 0x7d, 0x28, 0x4e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 7d 28 4e 8c c8 78 56 34 12 \tvrsqrtph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 4f cb \tvrsqrtsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x4f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 4f 8c c8 78 56 34 12 \tvrsqrtsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x4f, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 4f 8c c8 78 56 34 12 \tvrsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 48 2c cb \tvscalefph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x48, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 48 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x48, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 48 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 2c cb \tvscalefph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0xcb, }, 6, 0, "", "", +"62 f6 6d 28 2c cb \tvscalefph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x28, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 28 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x28, 0x2c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 28 2c 8c c8 78 56 34 12 \tvscalefph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0xcb, }, 6, 0, "", "", +"62 f6 6d 08 2d cb \tvscalefsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf6, 0x6d, 0x08, 0x2d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f6 6d 08 2d 8c c8 78 56 34 12 \tvscalefsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf6, 0x6d, 0x08, 0x2d, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f6 6d 08 2d 8c c8 78 56 34 12 \tvscalefsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0xca, }, 6, 0, "", "", +"62 f5 7c 48 51 ca \tvsqrtph %zmm2,%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x48, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 48 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%rax,%rcx,8),%zmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x48, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 48 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%zmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 51 ca \tvsqrtph %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0xca, }, 6, 0, "", "", +"62 f5 7c 28 51 ca \tvsqrtph %ymm2,%ymm1",}, +{{0x62, 0xf5, 0x7c, 0x28, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 28 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%rax,%rcx,8),%ymm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x28, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 28 51 8c c8 78 56 34 12 \tvsqrtph 0x12345678(%eax,%ecx,8),%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 51 cb \tvsqrtsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 51 8c c8 78 56 34 12 \tvsqrtsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x51, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 51 8c c8 78 56 34 12 \tvsqrtsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6c 48 5c cb \tvsubph %zmm3,%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x48, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 48 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%rax,%rcx,8),%zmm2,%zmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x48, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 48 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%zmm2,%zmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6c 08 5c cb \tvsubph %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 08 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 08 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6c 28 5c cb \tvsubph %ymm3,%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6c, 0x28, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6c 28 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%rax,%rcx,8),%ymm2,%ymm1",}, +{{0x67, 0x62, 0xf5, 0x6c, 0x28, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6c 28 5c 8c c8 78 56 34 12 \tvsubph 0x12345678(%eax,%ecx,8),%ymm2,%ymm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0xcb, }, 6, 0, "", "", +"62 f5 6e 08 5c cb \tvsubsh %xmm3,%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x6e, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 6e 08 5c 8c c8 78 56 34 12 \tvsubsh 0x12345678(%rax,%rcx,8),%xmm2,%xmm1",}, +{{0x67, 0x62, 0xf5, 0x6e, 0x08, 0x5c, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 6e 08 5c 8c c8 78 56 34 12 \tvsubsh 0x12345678(%eax,%ecx,8),%xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0xca, }, 6, 0, "", "", +"62 f5 7c 08 2e ca \tvucomish %xmm2,%xmm1",}, +{{0x62, 0xf5, 0x7c, 0x08, 0x2e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f5 7c 08 2e 8c c8 78 56 34 12 \tvucomish 0x12345678(%rax,%rcx,8),%xmm1",}, +{{0x67, 0x62, 0xf5, 0x7c, 0x08, 0x2e, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f5 7c 08 2e 8c c8 78 56 34 12 \tvucomish 0x12345678(%eax,%ecx,8),%xmm1",}, +{{0xf3, 0x0f, 0x3a, 0xf0, 0xc0, 0x00, }, 6, 0, "", "", +"f3 0f 3a f0 c0 00 \threset $0x0",}, +{{0x0f, 0x01, 0xe8, }, 3, 0, "", "", +"0f 01 e8 \tserialize ",}, +{{0xf2, 0x0f, 0x01, 0xe9, }, 4, 0, "", "", +"f2 0f 01 e9 \txresldtrk ",}, +{{0xf2, 0x0f, 0x01, 0xe8, }, 4, 0, "", "", +"f2 0f 01 e8 \txsusldtrk ",}, {{0x0f, 0x01, 0xcf, }, 3, 0, "", "", "0f 01 cf \tencls ",}, {{0x0f, 0x01, 0xd7, }, 3, 0, "", "", diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index c3808e94c46e..a391464c8dee 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -1910,6 +1910,724 @@ int main(void) asm volatile("notrack bnd jmpq *0x12345678(%rax,%rcx,8)"); /* Expecting: jmp indirect 0 */ asm volatile("notrack bnd jmpq *0x12345678(%r8,%rcx,8)"); /* Expecting: jmp indirect 0 */ + /* AMX */ + + asm volatile("ldtilecfg (%rax,%rcx,8)"); + asm volatile("ldtilecfg (%r8,%rcx,8)"); + asm volatile("sttilecfg (%rax,%rcx,8)"); + asm volatile("sttilecfg (%r8,%rcx,8)"); + asm volatile("tdpbf16ps %tmm0, %tmm1, %tmm2"); + asm volatile("tdpbssd %tmm0, %tmm1, %tmm2"); + asm volatile("tdpbsud %tmm0, %tmm1, %tmm2"); + asm volatile("tdpbusd %tmm0, %tmm1, %tmm2"); + asm volatile("tdpbuud %tmm0, %tmm1, %tmm2"); + asm volatile("tileloadd (%rax,%rcx,8), %tmm1"); + asm volatile("tileloadd (%r8,%rcx,8), %tmm2"); + asm volatile("tileloaddt1 (%rax,%rcx,8), %tmm1"); + asm volatile("tileloaddt1 (%r8,%rcx,8), %tmm2"); + asm volatile("tilerelease"); + asm volatile("tilestored %tmm1, (%rax,%rcx,8)"); + asm volatile("tilestored %tmm2, (%r8,%rcx,8)"); + asm volatile("tilezero %tmm0"); + asm volatile("tilezero %tmm7"); + + /* User Interrupt */ + + asm volatile("clui"); + asm volatile("senduipi %rax"); + asm volatile("senduipi %r8"); + asm volatile("stui"); + asm volatile("testui"); + asm volatile("uiret"); + + /* AVX512-FP16 */ + + asm volatile("vaddph %zmm3, %zmm2, %zmm1"); + asm volatile("vaddph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vaddph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vaddph %xmm3, %xmm2, %xmm1"); + asm volatile("vaddph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vaddph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vaddph %ymm3, %ymm2, %ymm1"); + asm volatile("vaddph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vaddph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vaddsh %xmm3, %xmm2, %xmm1"); + asm volatile("vaddsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vaddsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcmpph $0x12, %zmm3, %zmm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%rax,%rcx,8), %zmm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %zmm2, %k5"); + asm volatile("vcmpph $0x12, %xmm3, %xmm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5"); + asm volatile("vcmpph $0x12, %ymm3, %ymm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%rax,%rcx,8), %ymm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %ymm2, %k5"); + asm volatile("vcmpsh $0x12, %xmm3, %xmm2, %k5"); + asm volatile("vcmpsh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %k5"); + asm volatile("vcmpsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5"); + asm volatile("vcomish %xmm2, %xmm1"); + asm volatile("vcomish 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcomish 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtdq2ph %zmm2, %ymm1"); + asm volatile("vcvtdq2ph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtdq2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtdq2ph %xmm2, %xmm1"); + asm volatile("vcvtdq2ph %ymm2, %xmm1"); + asm volatile("vcvtpd2ph %zmm2, %xmm1"); + asm volatile("vcvtpd2ph %xmm2, %xmm1"); + asm volatile("vcvtpd2ph %ymm2, %xmm1"); + asm volatile("vcvtph2dq %ymm2, %zmm1"); + asm volatile("vcvtph2dq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2dq %xmm2, %xmm1"); + asm volatile("vcvtph2dq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2dq %xmm2, %ymm1"); + asm volatile("vcvtph2dq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2pd %xmm2, %zmm1"); + asm volatile("vcvtph2pd 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2pd %xmm2, %xmm1"); + asm volatile("vcvtph2pd 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2pd %xmm2, %ymm1"); + asm volatile("vcvtph2pd 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2ps %ymm2, %zmm1"); + asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2ps %xmm2, %xmm1"); + asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2ps %xmm2, %ymm1"); + asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2ps %xmm2, %xmm1"); + asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2ps %xmm2, %ymm1"); + asm volatile("vcvtph2ps 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2psx %ymm2, %zmm1"); + asm volatile("vcvtph2psx 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2psx %xmm2, %xmm1"); + asm volatile("vcvtph2psx 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2psx %xmm2, %ymm1"); + asm volatile("vcvtph2psx 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2qq %xmm2, %zmm1"); + asm volatile("vcvtph2qq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2qq %xmm2, %xmm1"); + asm volatile("vcvtph2qq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2qq %xmm2, %ymm1"); + asm volatile("vcvtph2qq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2udq %ymm2, %zmm1"); + asm volatile("vcvtph2udq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2udq %xmm2, %xmm1"); + asm volatile("vcvtph2udq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2udq %xmm2, %ymm1"); + asm volatile("vcvtph2udq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2uqq %xmm2, %zmm1"); + asm volatile("vcvtph2uqq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2uqq %xmm2, %xmm1"); + asm volatile("vcvtph2uqq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2uqq %xmm2, %ymm1"); + asm volatile("vcvtph2uqq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2uw %zmm2, %zmm1"); + asm volatile("vcvtph2uw 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2uw %xmm2, %xmm1"); + asm volatile("vcvtph2uw 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2uw %ymm2, %ymm1"); + asm volatile("vcvtph2uw 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2w %zmm2, %zmm1"); + asm volatile("vcvtph2w 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2w %xmm2, %xmm1"); + asm volatile("vcvtph2w 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2w %ymm2, %ymm1"); + asm volatile("vcvtph2w 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtps2ph $0x12, %zmm1, 0x12345678(%rax,%rcx,8)"); + asm volatile("vcvtps2ph $0x12, %zmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %zmm2, %ymm1"); + asm volatile("vcvtps2ph $0x12, %ymm1, 0x12345678(%rax,%rcx,8)"); + asm volatile("vcvtps2ph $0x12, %ymm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm1, 0x12345678(%rax,%rcx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %ymm2, 0x12345678(%rax,%rcx,8)"); + asm volatile("vcvtps2ph $0x12, %ymm2, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %xmm2, 0x12345678(%rax,%rcx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm2, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2phx %zmm2, %ymm1"); + asm volatile("vcvtps2phx 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtps2phx 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtps2phx %xmm2, %xmm1"); + asm volatile("vcvtps2phx %ymm2, %xmm1"); + asm volatile("vcvtqq2ph %zmm2, %xmm1"); + asm volatile("vcvtqq2ph %xmm2, %xmm1"); + asm volatile("vcvtqq2ph %ymm2, %xmm1"); + asm volatile("vcvtsd2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsh2sd 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsh2si 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvtsh2si 0x12345678(%eax,%ecx,8), %rax"); + asm volatile("vcvtsh2ss 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsh2usi %xmm1, %eax"); + asm volatile("vcvtsh2usi 0x12345678(%rax,%rcx,8), %eax"); + asm volatile("vcvtsh2usi 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvtsh2usi %xmm1, %rax"); + asm volatile("vcvtsh2usi 0x12345678(%rax,%rcx,8), %rax"); + asm volatile("vcvtsh2usi 0x12345678(%eax,%ecx,8), %rax"); + asm volatile("vcvtsi2sh %eax, %xmm2, %xmm1"); + asm volatile("vcvtsi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsi2sh %rax, %xmm2, %xmm1"); + asm volatile("vcvtsi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtss2sh %xmm3, %xmm2, %xmm1"); + asm volatile("vcvtss2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vcvtss2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvttph2dq %ymm2, %zmm1"); + asm volatile("vcvttph2dq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2dq %xmm2, %xmm1"); + asm volatile("vcvttph2dq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2dq %xmm2, %ymm1"); + asm volatile("vcvttph2dq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2qq %xmm2, %zmm1"); + asm volatile("vcvttph2qq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2qq %xmm2, %xmm1"); + asm volatile("vcvttph2qq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2qq %xmm2, %ymm1"); + asm volatile("vcvttph2qq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2udq %ymm2, %zmm1"); + asm volatile("vcvttph2udq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2udq %xmm2, %xmm1"); + asm volatile("vcvttph2udq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2udq %xmm2, %ymm1"); + asm volatile("vcvttph2udq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2uqq %xmm2, %zmm1"); + asm volatile("vcvttph2uqq 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2uqq %xmm2, %xmm1"); + asm volatile("vcvttph2uqq 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2uqq %xmm2, %ymm1"); + asm volatile("vcvttph2uqq 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2uw %zmm2, %zmm1"); + asm volatile("vcvttph2uw 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2uw %xmm2, %xmm1"); + asm volatile("vcvttph2uw 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2uw %ymm2, %ymm1"); + asm volatile("vcvttph2uw 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2w %zmm2, %zmm1"); + asm volatile("vcvttph2w 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2w %xmm2, %xmm1"); + asm volatile("vcvttph2w 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2w %ymm2, %ymm1"); + asm volatile("vcvttph2w 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttsh2si %xmm1, %eax"); + asm volatile("vcvttsh2si 0x12345678(%rax,%rcx,8), %eax"); + asm volatile("vcvttsh2si 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvttsh2si %xmm1, %rax"); + asm volatile("vcvttsh2si 0x12345678(%rax,%rcx,8), %rax"); + asm volatile("vcvttsh2si 0x12345678(%eax,%ecx,8), %rax"); + asm volatile("vcvttsh2usi %xmm1, %eax"); + asm volatile("vcvttsh2usi 0x12345678(%rax,%rcx,8), %eax"); + asm volatile("vcvttsh2usi 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvttsh2usi %xmm1, %rax"); + asm volatile("vcvttsh2usi 0x12345678(%rax,%rcx,8), %rax"); + asm volatile("vcvttsh2usi 0x12345678(%eax,%ecx,8), %rax"); + asm volatile("vcvtudq2ph %zmm2, %ymm1"); + asm volatile("vcvtudq2ph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtudq2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtudq2ph %xmm2, %xmm1"); + asm volatile("vcvtudq2ph %ymm2, %xmm1"); + asm volatile("vcvtuqq2ph %zmm2, %xmm1"); + asm volatile("vcvtuqq2ph %xmm2, %xmm1"); + asm volatile("vcvtuqq2ph %ymm2, %xmm1"); + asm volatile("vcvtusi2sh %eax, %xmm2, %xmm1"); + asm volatile("vcvtusi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtusi2sh %rax, %xmm2, %xmm1"); + asm volatile("vcvtusi2sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtuw2ph %zmm2, %zmm1"); + asm volatile("vcvtuw2ph 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtuw2ph %xmm2, %xmm1"); + asm volatile("vcvtuw2ph 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtuw2ph %ymm2, %ymm1"); + asm volatile("vcvtuw2ph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtw2ph %zmm2, %zmm1"); + asm volatile("vcvtw2ph 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtw2ph %xmm2, %xmm1"); + asm volatile("vcvtw2ph 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtw2ph %ymm2, %ymm1"); + asm volatile("vcvtw2ph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vdivph %zmm3, %zmm2, %zmm1"); + asm volatile("vdivph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vdivph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vdivph %xmm3, %xmm2, %xmm1"); + asm volatile("vdivph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vdivph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vdivph %ymm3, %ymm2, %ymm1"); + asm volatile("vdivph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vdivph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vdivsh %xmm3, %xmm2, %xmm1"); + asm volatile("vdivsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vdivsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmaddcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfcmaddcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfcmaddcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmaddcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmaddcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfcmaddcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfcmaddcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmaddcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfcmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmulcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfcmulcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfcmulcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmulcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmulcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfcmulcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfcmulcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmulcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfcmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmadd132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmadd132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmadd132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmadd132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmadd213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmadd213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmadd213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmadd213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmadd231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmadd231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmadd231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmadd231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmaddcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddsub132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddsub132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddsub132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmaddsub213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddsub213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddsub213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddsub213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmaddsub231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddsub231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddsub231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddsub231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsub132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsub132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsub132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsub213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsub213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsub213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsub231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsub231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsub231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsubadd132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsubadd132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsubadd132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsubadd213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsubadd213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsubadd213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsubadd213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsubadd231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsubadd231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsubadd231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsubadd231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmulcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmulcph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmulcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmulcph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmulcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmulcph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmulcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmulcsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmadd132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmadd132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmadd213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmadd213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmadd231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmadd231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmsub132ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub132ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmsub132ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub132sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmsub213ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub213ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmsub213ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub213sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmsub231ph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub231ph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmsub231ph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub231sh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfpclassph $0x12, %zmm1, %k5"); + asm volatile("vfpclassph $0x12, %xmm1, %k5"); + asm volatile("vfpclassph $0x12, %ymm1, %k5"); + asm volatile("vfpclasssh $0x12, %xmm1, %k5"); + asm volatile("vfpclasssh $0x12, 0x12345678(%rax,%rcx,8), %k5"); + asm volatile("vfpclasssh $0x12, 0x12345678(%eax,%ecx,8), %k5"); + asm volatile("vgetexpph %zmm2, %zmm1"); + asm volatile("vgetexpph 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vgetexpph %xmm2, %xmm1"); + asm volatile("vgetexpph 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vgetexpph %ymm2, %ymm1"); + asm volatile("vgetexpph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vgetexpsh %xmm3, %xmm2, %xmm1"); + asm volatile("vgetexpsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vgetexpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vgetmantph $0x12, %zmm2, %zmm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vgetmantph $0x12, %xmm2, %xmm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vgetmantph $0x12, %ymm2, %ymm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vgetmantsh $0x12, %xmm3, %xmm2, %xmm1"); + asm volatile("vgetmantsh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vgetmantsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmaxph %zmm3, %zmm2, %zmm1"); + asm volatile("vmaxph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vmaxph %xmm3, %xmm2, %xmm1"); + asm volatile("vmaxph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmaxph %ymm3, %ymm2, %ymm1"); + asm volatile("vmaxph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vmaxsh %xmm3, %xmm2, %xmm1"); + asm volatile("vmaxsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vmaxsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vminph %zmm3, %zmm2, %zmm1"); + asm volatile("vminph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vminph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vminph %xmm3, %xmm2, %xmm1"); + asm volatile("vminph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vminph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vminph %ymm3, %ymm2, %ymm1"); + asm volatile("vminph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vminph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vminsh %xmm3, %xmm2, %xmm1"); + asm volatile("vminsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vminsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmovsh %xmm1, 0x12345678(%rax,%rcx,8)"); + asm volatile("vmovsh %xmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vmovsh 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vmovsh 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vmovsh %xmm3, %xmm2, %xmm1"); + asm volatile("vmovw %xmm1, %eax"); + asm volatile("vmovw %xmm1, 0x12345678(%rax,%rcx,8)"); + asm volatile("vmovw %xmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vmovw %eax, %xmm1"); + asm volatile("vmovw 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vmovw 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vmulph %zmm3, %zmm2, %zmm1"); + asm volatile("vmulph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vmulph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vmulph %xmm3, %xmm2, %xmm1"); + asm volatile("vmulph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vmulph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmulph %ymm3, %ymm2, %ymm1"); + asm volatile("vmulph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vmulph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vmulsh %xmm3, %xmm2, %xmm1"); + asm volatile("vmulsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vmulsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vrcpph %zmm2, %zmm1"); + asm volatile("vrcpph 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vrcpph %xmm2, %xmm1"); + asm volatile("vrcpph 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vrcpph %ymm2, %ymm1"); + asm volatile("vrcpph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vrcpsh %xmm3, %xmm2, %xmm1"); + asm volatile("vrcpsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vrcpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vreduceph $0x12, %zmm2, %zmm1"); + asm volatile("vreduceph $0x12, 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vreduceph $0x12, %xmm2, %xmm1"); + asm volatile("vreduceph $0x12, 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vreduceph $0x12, %ymm2, %ymm1"); + asm volatile("vreduceph $0x12, 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vreducesh $0x12, %xmm3, %xmm2, %xmm1"); + asm volatile("vreducesh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vreducesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vrndscaleph $0x12, %zmm2, %zmm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vrndscaleph $0x12, %xmm2, %xmm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vrndscaleph $0x12, %ymm2, %ymm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vrndscalesh $0x12, %xmm3, %xmm2, %xmm1"); + asm volatile("vrndscalesh $0x12, 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vrndscalesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vrsqrtph %zmm2, %zmm1"); + asm volatile("vrsqrtph 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vrsqrtph %xmm2, %xmm1"); + asm volatile("vrsqrtph 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vrsqrtph %ymm2, %ymm1"); + asm volatile("vrsqrtph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vrsqrtsh %xmm3, %xmm2, %xmm1"); + asm volatile("vrsqrtsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vrsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vscalefph %zmm3, %zmm2, %zmm1"); + asm volatile("vscalefph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vscalefph %xmm3, %xmm2, %xmm1"); + asm volatile("vscalefph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vscalefph %ymm3, %ymm2, %ymm1"); + asm volatile("vscalefph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vscalefsh %xmm3, %xmm2, %xmm1"); + asm volatile("vscalefsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vscalefsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vsqrtph %zmm2, %zmm1"); + asm volatile("vsqrtph 0x12345678(%rax,%rcx,8), %zmm1"); + asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vsqrtph %xmm2, %xmm1"); + asm volatile("vsqrtph 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vsqrtph %ymm2, %ymm1"); + asm volatile("vsqrtph 0x12345678(%rax,%rcx,8), %ymm1"); + asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vsqrtsh %xmm3, %xmm2, %xmm1"); + asm volatile("vsqrtsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vsubph %zmm3, %zmm2, %zmm1"); + asm volatile("vsubph 0x12345678(%rax,%rcx,8), %zmm2, %zmm1"); + asm volatile("vsubph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vsubph %xmm3, %xmm2, %xmm1"); + asm volatile("vsubph 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vsubph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vsubph %ymm3, %ymm2, %ymm1"); + asm volatile("vsubph 0x12345678(%rax,%rcx,8), %ymm2, %ymm1"); + asm volatile("vsubph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vsubsh %xmm3, %xmm2, %xmm1"); + asm volatile("vsubsh 0x12345678(%rax,%rcx,8), %xmm2, %xmm1"); + asm volatile("vsubsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vucomish %xmm2, %xmm1"); + asm volatile("vucomish 0x12345678(%rax,%rcx,8), %xmm1"); + asm volatile("vucomish 0x12345678(%eax,%ecx,8), %xmm1"); + #else /* #ifdef __x86_64__ */ /* bound r32, mem (same op code as EVEX prefix) */ @@ -3670,8 +4388,479 @@ int main(void) asm volatile("notrack bnd jmp *(0x12345678)"); /* Expecting: jmp indirect 0 */ asm volatile("notrack bnd jmp *0x12345678(%eax,%ecx,8)"); /* Expecting: jmp indirect 0 */ + /* AVX512-FP16 */ + + asm volatile("vaddph %zmm3, %zmm2, %zmm1"); + asm volatile("vaddph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vaddph %xmm3, %xmm2, %xmm1"); + asm volatile("vaddph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vaddph %ymm3, %ymm2, %ymm1"); + asm volatile("vaddph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vaddsh %xmm3, %xmm2, %xmm1"); + asm volatile("vaddsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcmpph $0x12, %zmm3, %zmm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %zmm2, %k5"); + asm volatile("vcmpph $0x12, %xmm3, %xmm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5"); + asm volatile("vcmpph $0x12, %ymm3, %ymm2, %k5"); + asm volatile("vcmpph $0x12, 0x12345678(%eax,%ecx,8), %ymm2, %k5"); + asm volatile("vcmpsh $0x12, %xmm3, %xmm2, %k5"); + asm volatile("vcmpsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %k5"); + asm volatile("vcomish %xmm2, %xmm1"); + asm volatile("vcomish 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtdq2ph %zmm2, %ymm1"); + asm volatile("vcvtdq2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtdq2ph %xmm2, %xmm1"); + asm volatile("vcvtdq2ph %ymm2, %xmm1"); + asm volatile("vcvtpd2ph %zmm2, %xmm1"); + asm volatile("vcvtpd2ph %xmm2, %xmm1"); + asm volatile("vcvtpd2ph %ymm2, %xmm1"); + asm volatile("vcvtph2dq %ymm2, %zmm1"); + asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2dq %xmm2, %xmm1"); + asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2dq %xmm2, %ymm1"); + asm volatile("vcvtph2dq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2pd %xmm2, %zmm1"); + asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2pd %xmm2, %xmm1"); + asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2pd %xmm2, %ymm1"); + asm volatile("vcvtph2pd 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2ps %ymm2, %zmm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2ps %xmm2, %xmm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2ps %xmm2, %ymm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2ps %xmm2, %xmm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2ps %xmm2, %ymm1"); + asm volatile("vcvtph2ps 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2psx %ymm2, %zmm1"); + asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2psx %xmm2, %xmm1"); + asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2psx %xmm2, %ymm1"); + asm volatile("vcvtph2psx 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2qq %xmm2, %zmm1"); + asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2qq %xmm2, %xmm1"); + asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2qq %xmm2, %ymm1"); + asm volatile("vcvtph2qq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2udq %ymm2, %zmm1"); + asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2udq %xmm2, %xmm1"); + asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2udq %xmm2, %ymm1"); + asm volatile("vcvtph2udq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2uqq %xmm2, %zmm1"); + asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2uqq %xmm2, %xmm1"); + asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2uqq %xmm2, %ymm1"); + asm volatile("vcvtph2uqq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2uw %zmm2, %zmm1"); + asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2uw %xmm2, %xmm1"); + asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2uw %ymm2, %ymm1"); + asm volatile("vcvtph2uw 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtph2w %zmm2, %zmm1"); + asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtph2w %xmm2, %xmm1"); + asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtph2w %ymm2, %ymm1"); + asm volatile("vcvtph2w 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtps2ph $0x12, %zmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %zmm2, %ymm1"); + asm volatile("vcvtps2ph $0x12, %ymm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %ymm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %ymm2, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2ph $0x12, %xmm2, %xmm1"); + asm volatile("vcvtps2ph $0x12, %xmm2, 0x12345678(%eax,%ecx,8)"); + asm volatile("vcvtps2phx %zmm2, %ymm1"); + asm volatile("vcvtps2phx 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtps2phx %xmm2, %xmm1"); + asm volatile("vcvtps2phx %ymm2, %xmm1"); + asm volatile("vcvtqq2ph %zmm2, %xmm1"); + asm volatile("vcvtqq2ph %xmm2, %xmm1"); + asm volatile("vcvtqq2ph %ymm2, %xmm1"); + asm volatile("vcvtsd2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsh2sd 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsh2si 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvtsh2ss 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsh2usi %xmm1, %eax"); + asm volatile("vcvtsh2usi 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvtsi2sh %eax, %xmm2, %xmm1"); + asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtsi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtss2sh %xmm3, %xmm2, %xmm1"); + asm volatile("vcvtss2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvttph2dq %ymm2, %zmm1"); + asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2dq %xmm2, %xmm1"); + asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2dq %xmm2, %ymm1"); + asm volatile("vcvttph2dq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2qq %xmm2, %zmm1"); + asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2qq %xmm2, %xmm1"); + asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2qq %xmm2, %ymm1"); + asm volatile("vcvttph2qq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2udq %ymm2, %zmm1"); + asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2udq %xmm2, %xmm1"); + asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2udq %xmm2, %ymm1"); + asm volatile("vcvttph2udq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2uqq %xmm2, %zmm1"); + asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2uqq %xmm2, %xmm1"); + asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2uqq %xmm2, %ymm1"); + asm volatile("vcvttph2uqq 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2uw %zmm2, %zmm1"); + asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2uw %xmm2, %xmm1"); + asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2uw %ymm2, %ymm1"); + asm volatile("vcvttph2uw 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttph2w %zmm2, %zmm1"); + asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvttph2w %xmm2, %xmm1"); + asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvttph2w %ymm2, %ymm1"); + asm volatile("vcvttph2w 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvttsh2si %xmm1, %eax"); + asm volatile("vcvttsh2si 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvttsh2usi %xmm1, %eax"); + asm volatile("vcvttsh2usi 0x12345678(%eax,%ecx,8), %eax"); + asm volatile("vcvtudq2ph %zmm2, %ymm1"); + asm volatile("vcvtudq2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtudq2ph %xmm2, %xmm1"); + asm volatile("vcvtudq2ph %ymm2, %xmm1"); + asm volatile("vcvtuqq2ph %zmm2, %xmm1"); + asm volatile("vcvtuqq2ph %xmm2, %xmm1"); + asm volatile("vcvtuqq2ph %ymm2, %xmm1"); + asm volatile("vcvtusi2sh %eax, %xmm2, %xmm1"); + asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtusi2sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vcvtuw2ph %zmm2, %zmm1"); + asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtuw2ph %xmm2, %xmm1"); + asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtuw2ph %ymm2, %ymm1"); + asm volatile("vcvtuw2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vcvtw2ph %zmm2, %zmm1"); + asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vcvtw2ph %xmm2, %xmm1"); + asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vcvtw2ph %ymm2, %ymm1"); + asm volatile("vcvtw2ph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vdivph %zmm3, %zmm2, %zmm1"); + asm volatile("vdivph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vdivph %xmm3, %xmm2, %xmm1"); + asm volatile("vdivph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vdivph %ymm3, %ymm2, %ymm1"); + asm volatile("vdivph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vdivsh %xmm3, %xmm2, %xmm1"); + asm volatile("vdivsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmaddcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfcmaddcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmaddcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfcmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfcmaddcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmulcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfcmulcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfcmulcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfcmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfcmulcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfcmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmadd132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmadd132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmadd213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmadd213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmadd231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmadd231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmadd231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmaddcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmaddsub213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmaddsub231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmaddsub231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmaddsub231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmaddsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsub132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsub213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsub231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsub231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsub231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsubadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsubadd213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsubadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmsubadd231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmsubadd231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmsubadd231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmsubadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmulcph %zmm3, %zmm2, %zmm1"); + asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfmulcph %xmm3, %xmm2, %xmm1"); + asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfmulcph %ymm3, %ymm2, %ymm1"); + asm volatile("vfmulcph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfmulcsh %xmm3, %xmm2, %xmm1"); + asm volatile("vfmulcsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmadd132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmadd213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmadd231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmadd231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmadd231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmadd231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmadd231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub132ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub132ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub132ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmsub132ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub132sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub132sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub213ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub213ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub213ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmsub213ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub213sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub213sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub231ph %zmm3, %zmm2, %zmm1"); + asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vfnmsub231ph %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfnmsub231ph %ymm3, %ymm2, %ymm1"); + asm volatile("vfnmsub231ph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vfnmsub231sh %xmm3, %xmm2, %xmm1"); + asm volatile("vfnmsub231sh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vfpclassph $0x12, %zmm1, %k5"); + asm volatile("vfpclassph $0x12, %xmm1, %k5"); + asm volatile("vfpclassph $0x12, %ymm1, %k5"); + asm volatile("vfpclasssh $0x12, %xmm1, %k5"); + asm volatile("vfpclasssh $0x12, 0x12345678(%eax,%ecx,8), %k5"); + asm volatile("vgetexpph %zmm2, %zmm1"); + asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vgetexpph %xmm2, %xmm1"); + asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vgetexpph %ymm2, %ymm1"); + asm volatile("vgetexpph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vgetexpsh %xmm3, %xmm2, %xmm1"); + asm volatile("vgetexpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vgetmantph $0x12, %zmm2, %zmm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vgetmantph $0x12, %xmm2, %xmm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vgetmantph $0x12, %ymm2, %ymm1"); + asm volatile("vgetmantph $0x12, 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vgetmantsh $0x12, %xmm3, %xmm2, %xmm1"); + asm volatile("vgetmantsh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmaxph %zmm3, %zmm2, %zmm1"); + asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vmaxph %xmm3, %xmm2, %xmm1"); + asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmaxph %ymm3, %ymm2, %ymm1"); + asm volatile("vmaxph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vmaxsh %xmm3, %xmm2, %xmm1"); + asm volatile("vmaxsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vminph %zmm3, %zmm2, %zmm1"); + asm volatile("vminph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vminph %xmm3, %xmm2, %xmm1"); + asm volatile("vminph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vminph %ymm3, %ymm2, %ymm1"); + asm volatile("vminph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vminsh %xmm3, %xmm2, %xmm1"); + asm volatile("vminsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmovsh %xmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vmovsh 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vmovsh %xmm3, %xmm2, %xmm1"); + asm volatile("vmovw %xmm1, %eax"); + asm volatile("vmovw %xmm1, 0x12345678(%eax,%ecx,8)"); + asm volatile("vmovw %eax, %xmm1"); + asm volatile("vmovw 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vmulph %zmm3, %zmm2, %zmm1"); + asm volatile("vmulph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vmulph %xmm3, %xmm2, %xmm1"); + asm volatile("vmulph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vmulph %ymm3, %ymm2, %ymm1"); + asm volatile("vmulph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vmulsh %xmm3, %xmm2, %xmm1"); + asm volatile("vmulsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vrcpph %zmm2, %zmm1"); + asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vrcpph %xmm2, %xmm1"); + asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vrcpph %ymm2, %ymm1"); + asm volatile("vrcpph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vrcpsh %xmm3, %xmm2, %xmm1"); + asm volatile("vrcpsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vreduceph $0x12, %zmm2, %zmm1"); + asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vreduceph $0x12, %xmm2, %xmm1"); + asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vreduceph $0x12, %ymm2, %ymm1"); + asm volatile("vreduceph $0x12, 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vreducesh $0x12, %xmm3, %xmm2, %xmm1"); + asm volatile("vreducesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vrndscaleph $0x12, %zmm2, %zmm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vrndscaleph $0x12, %xmm2, %xmm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vrndscaleph $0x12, %ymm2, %ymm1"); + asm volatile("vrndscaleph $0x12, 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vrndscalesh $0x12, %xmm3, %xmm2, %xmm1"); + asm volatile("vrndscalesh $0x12, 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vrsqrtph %zmm2, %zmm1"); + asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vrsqrtph %xmm2, %xmm1"); + asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vrsqrtph %ymm2, %ymm1"); + asm volatile("vrsqrtph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vrsqrtsh %xmm3, %xmm2, %xmm1"); + asm volatile("vrsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vscalefph %zmm3, %zmm2, %zmm1"); + asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vscalefph %xmm3, %xmm2, %xmm1"); + asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vscalefph %ymm3, %ymm2, %ymm1"); + asm volatile("vscalefph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vscalefsh %xmm3, %xmm2, %xmm1"); + asm volatile("vscalefsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vsqrtph %zmm2, %zmm1"); + asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %zmm1"); + asm volatile("vsqrtph %xmm2, %xmm1"); + asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %xmm1"); + asm volatile("vsqrtph %ymm2, %ymm1"); + asm volatile("vsqrtph 0x12345678(%eax,%ecx,8), %ymm1"); + asm volatile("vsqrtsh %xmm3, %xmm2, %xmm1"); + asm volatile("vsqrtsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vsubph %zmm3, %zmm2, %zmm1"); + asm volatile("vsubph 0x12345678(%eax,%ecx,8), %zmm2, %zmm1"); + asm volatile("vsubph %xmm3, %xmm2, %xmm1"); + asm volatile("vsubph 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vsubph %ymm3, %ymm2, %ymm1"); + asm volatile("vsubph 0x12345678(%eax,%ecx,8), %ymm2, %ymm1"); + asm volatile("vsubsh %xmm3, %xmm2, %xmm1"); + asm volatile("vsubsh 0x12345678(%eax,%ecx,8), %xmm2, %xmm1"); + asm volatile("vucomish %xmm2, %xmm1"); + asm volatile("vucomish 0x12345678(%eax,%ecx,8), %xmm1"); + #endif /* #ifndef __x86_64__ */ + /* Prediction history reset */ + + asm volatile("hreset $0"); + + /* Serialize instruction execution */ + + asm volatile("serialize"); + + /* TSX suspend load address tracking */ + + asm volatile("xresldtrk"); + asm volatile("xsusldtrk"); + /* SGX */ asm volatile("encls"); diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index f924246eff78..8d9b55959256 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -29,7 +29,7 @@ struct evsel *arch_evlist__leader(struct list_head *list) __evlist__for_each_entry(list, evsel) { if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && - evsel->name && strstr(evsel->name, "slots")) + evsel->name && strcasestr(evsel->name, "slots")) return evsel; } return first; diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 740ae764537e..134612bde0cb 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -106,7 +106,7 @@ static void nest_epollfd(void) printinfo("Nesting level(s): %d\n", nested); epollfdp = calloc(nested, sizeof(int)); - if (!epollfd) + if (!epollfdp) err(EXIT_FAILURE, "calloc"); for (i = 0; i < nested; i++) { diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index dec24dc0e767..a8785dec5ca6 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1115,6 +1115,7 @@ enum perf_ftrace_subcommand { int cmd_ftrace(int argc, const char **argv) { int ret; + int (*cmd_func)(struct perf_ftrace *) = NULL; struct perf_ftrace ftrace = { .tracer = DEFAULT_TRACER, .target = { .uid = UINT_MAX, }, @@ -1221,6 +1222,28 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_filters; } + switch (subcmd) { + case PERF_FTRACE_TRACE: + if (!argc && target__none(&ftrace.target)) + ftrace.target.system_wide = true; + cmd_func = __cmd_ftrace; + break; + case PERF_FTRACE_LATENCY: + if (list_empty(&ftrace.filters)) { + pr_err("Should provide a function to measure\n"); + parse_options_usage(ftrace_usage, options, "T", 1); + ret = -EINVAL; + goto out_delete_filters; + } + cmd_func = __cmd_latency; + break; + case PERF_FTRACE_NONE: + default: + pr_err("Invalid subcommand\n"); + ret = -EINVAL; + goto out_delete_filters; + } + ret = target__validate(&ftrace.target); if (ret) { char errbuf[512]; @@ -1248,27 +1271,7 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_evlist; } - switch (subcmd) { - case PERF_FTRACE_TRACE: - if (!argc && target__none(&ftrace.target)) - ftrace.target.system_wide = true; - ret = __cmd_ftrace(&ftrace); - break; - case PERF_FTRACE_LATENCY: - if (list_empty(&ftrace.filters)) { - pr_err("Should provide a function to measure\n"); - parse_options_usage(ftrace_usage, options, "T", 1); - ret = -EINVAL; - goto out_delete_evlist; - } - ret = __cmd_latency(&ftrace); - break; - case PERF_FTRACE_NONE: - default: - pr_err("Invalid subcommand\n"); - ret = -EINVAL; - break; - } + ret = cmd_func(&ftrace); out_delete_evlist: evlist__delete(ftrace.evlist); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index abae8184e171..fa478ddcd18a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -463,7 +463,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__do_check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT, allow_user_set)) return -EINVAL; if (PRINT_FIELD(SYM) && diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 32844d8a0ea5..52b137a184a6 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1536,13 +1536,20 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) return fprintf(fp, " ? "); } +static pid_t workload_pid = -1; static bool done = false; static bool interrupted = false; -static void sig_handler(int sig) +static void sighandler_interrupt(int sig __maybe_unused) { - done = true; - interrupted = sig == SIGINT; + done = interrupted = true; +} + +static void sighandler_chld(int sig __maybe_unused, siginfo_t *info, + void *context __maybe_unused) +{ + if (info->si_pid == workload_pid) + done = true; } static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp) @@ -3938,7 +3945,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) bool draining = false; trace->live = true; - signal(SIGCHLD, sig_handler); if (!trace->raw_augmented_syscalls) { if (trace->trace_syscalls && trace__add_syscall_newtp(trace)) @@ -4018,6 +4024,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) fprintf(trace->output, "Couldn't run the workload!\n"); goto out_delete_evlist; } + workload_pid = evlist->workload.pid; } err = evlist__open(evlist); @@ -4887,10 +4894,16 @@ int cmd_trace(int argc, const char **argv) const char * const trace_subcommands[] = { "record", NULL }; int err = -1; char bf[BUFSIZ]; + struct sigaction sigchld_act; signal(SIGSEGV, sighandler_dump_stack); signal(SIGFPE, sighandler_dump_stack); - signal(SIGINT, sig_handler); + signal(SIGINT, sighandler_interrupt); + + memset(&sigchld_act, 0, sizeof(sigchld_act)); + sigchld_act.sa_flags = SA_SIGINFO; + sigchld_act.sa_sigaction = sighandler_chld; + sigaction(SIGCHLD, &sigchld_act, NULL); trace.evlist = evlist__new(); trace.sctbl = syscalltbl__new(); diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index a36f49fb4dbe..1116fc6bf2ac 100644 --- a/tools/perf/tests/attr/README +++ b/tools/perf/tests/attr/README @@ -45,8 +45,10 @@ Following tests are defined (with perf commands): perf record -d kill (test-record-data) perf record -F 100 kill (test-record-freq) perf record -g kill (test-record-graph-default) + perf record -g kill (test-record-graph-default-aarch64) perf record --call-graph dwarf kill (test-record-graph-dwarf) perf record --call-graph fp kill (test-record-graph-fp) + perf record --call-graph fp kill (test-record-graph-fp-aarch64) perf record --group -e cycles,instructions kill (test-record-group) perf record -e '{cycles,instructions}' kill (test-record-group1) perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2) diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default index 5d8234d50845..f0a18b4ea4f5 100644 --- a/tools/perf/tests/attr/test-record-graph-default +++ b/tools/perf/tests/attr/test-record-graph-default @@ -2,6 +2,8 @@ command = record args = --no-bpf-event -g kill >/dev/null 2>&1 ret = 1 +# arm64 enables registers in the default mode (fp) +arch = !aarch64 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-graph-default-aarch64 b/tools/perf/tests/attr/test-record-graph-default-aarch64 new file mode 100644 index 000000000000..e98d62efb6f7 --- /dev/null +++ b/tools/perf/tests/attr/test-record-graph-default-aarch64 @@ -0,0 +1,9 @@ +[config] +command = record +args = --no-bpf-event -g kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event:base-record] +sample_type=4391 +sample_regs_user=1073741824 diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp index 5630521c0b0f..a6e60e839205 100644 --- a/tools/perf/tests/attr/test-record-graph-fp +++ b/tools/perf/tests/attr/test-record-graph-fp @@ -2,6 +2,8 @@ command = record args = --no-bpf-event --call-graph fp kill >/dev/null 2>&1 ret = 1 +# arm64 enables registers in fp mode +arch = !aarch64 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-graph-fp-aarch64 b/tools/perf/tests/attr/test-record-graph-fp-aarch64 new file mode 100644 index 000000000000..cbeea9971285 --- /dev/null +++ b/tools/perf/tests/attr/test-record-graph-fp-aarch64 @@ -0,0 +1,9 @@ +[config] +command = record +args = --no-bpf-event --call-graph fp kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event:base-record] +sample_type=4391 +sample_regs_user=1073741824 diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c index 1f147fe6595f..e32ece90e164 100644 --- a/tools/perf/tests/sigtrap.c +++ b/tools/perf/tests/sigtrap.c @@ -22,19 +22,6 @@ #include "tests.h" #include "../perf-sys.h" -/* - * PowerPC and S390 do not support creation of instruction breakpoints using the - * perf_event interface. - * - * Just disable the test for these architectures until these issues are - * resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) -#define BP_ACCOUNT_IS_SUPPORTED 0 -#else -#define BP_ACCOUNT_IS_SUPPORTED 1 -#endif - #define NUM_THREADS 5 static struct { @@ -135,7 +122,7 @@ static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __m char sbuf[STRERR_BUFSIZE]; int i, fd, ret = TEST_FAIL; - if (!BP_ACCOUNT_IS_SUPPORTED) { + if (!BP_SIGNAL_IS_SUPPORTED) { pr_debug("Test not supported on this architecture"); return TEST_SKIP; } diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh index 3109d7b05e11..3d278785fe57 100755 --- a/tools/perf/trace/beauty/prctl_option.sh +++ b/tools/perf/trace/beauty/prctl_option.sh @@ -4,7 +4,7 @@ [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *prctl_options[] = {\n" -regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*' +regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$' egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \ sed -r "s/$regex/\2 \1/g" | \ sort -n | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 01900689dc00..8190a124b99d 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2036,6 +2036,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) memset(&objdump_process, 0, sizeof(objdump_process)); objdump_process.argv = objdump_argv; objdump_process.out = -1; + objdump_process.err = -1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 7ecfaac7536a..16ec605a9fe4 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1220,9 +1220,10 @@ bpf__obj_config_map(struct bpf_object *obj, pr_debug("ERROR: Invalid map config option '%s'\n", map_opt); err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT; out: - free(map_name); if (!err) *key_scan_pos += strlen(map_opt); + + free(map_name); return err; } diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 631e34a0b66f..ac60c08e8e2a 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -266,7 +266,7 @@ static int bperf_cgrp__read(struct evsel *evsel) idx = evsel->core.idx; err = bpf_map_lookup_elem(reading_map_fd, &idx, values); if (err) { - pr_err("bpf map lookup falied: idx=%u, event=%s, cgrp=%s\n", + pr_err("bpf map lookup failed: idx=%u, event=%s, cgrp=%s\n", idx, evsel__name(evsel), evsel->cgrp->name); goto out; } diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c index 2285b1eb3128..a9a909db8cc7 100644 --- a/tools/perf/util/branch.c +++ b/tools/perf/util/branch.c @@ -49,7 +49,9 @@ const char *branch_type_name(int type) "SYSCALL", "SYSRET", "COND_CALL", - "COND_RET" + "COND_RET", + "ERET", + "IRQ" }; if (type >= 0 && type < PERF_BR_MAX) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 4f672f7d008c..8b95fb3c4d7b 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -50,8 +50,6 @@ struct cs_etm_auxtrace { u8 timeless_decoding; u8 snapshot_mode; u8 data_queued; - u8 sample_branches; - u8 sample_instructions; int num_cpu; u64 latest_kernel_timestamp; @@ -410,8 +408,8 @@ static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm, { struct cs_etm_packet *tmp; - if (etm->sample_branches || etm->synth_opts.last_branch || - etm->sample_instructions) { + if (etm->synth_opts.branches || etm->synth_opts.last_branch || + etm->synth_opts.instructions) { /* * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. @@ -1365,7 +1363,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, err = cs_etm__synth_event(session, &attr, id); if (err) return err; - etm->sample_branches = true; etm->branches_sample_type = attr.sample_type; etm->branches_id = id; id += 1; @@ -1389,7 +1386,6 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, err = cs_etm__synth_event(session, &attr, id); if (err) return err; - etm->sample_instructions = true; etm->instructions_sample_type = attr.sample_type; etm->instructions_id = id; id += 1; @@ -1420,7 +1416,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, tidq->prev_packet->last_instr_taken_branch) cs_etm__update_last_branch_rb(etmq, tidq); - if (etm->sample_instructions && + if (etm->synth_opts.instructions && tidq->period_instructions >= etm->instructions_sample_period) { /* * Emit instruction sample periodically @@ -1503,7 +1499,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, } } - if (etm->sample_branches) { + if (etm->synth_opts.branches) { bool generate_sample = false; /* Generate sample for tracing on packet */ @@ -1557,6 +1553,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, goto swap_packet; if (etmq->etm->synth_opts.last_branch && + etmq->etm->synth_opts.instructions && tidq->prev_packet->sample_type == CS_ETM_RANGE) { u64 addr; @@ -1582,7 +1579,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, } - if (etm->sample_branches && + if (etm->synth_opts.branches && tidq->prev_packet->sample_type == CS_ETM_RANGE) { err = cs_etm__synth_branch_sample(etmq, tidq); if (err) @@ -1614,6 +1611,7 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq, * the trace. */ if (etmq->etm->synth_opts.last_branch && + etmq->etm->synth_opts.instructions && tidq->prev_packet->sample_type == CS_ETM_RANGE) { u64 addr; diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index f5d260b1df4d..15a4547d608e 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -44,10 +44,6 @@ int perf_data__create_dir(struct perf_data *data, int nr) if (!files) return -ENOMEM; - data->dir.version = PERF_DIR_VERSION; - data->dir.files = files; - data->dir.nr = nr; - for (i = 0; i < nr; i++) { struct perf_data_file *file = &files[i]; @@ -62,6 +58,9 @@ int perf_data__create_dir(struct perf_data *data, int nr) file->fd = ret; } + data->dir.version = PERF_DIR_VERSION; + data->dir.files = files; + data->dir.nr = nr; return 0; out_err: diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c index 7f234215147d..57f02beef023 100644 --- a/tools/perf/util/evlist-hybrid.c +++ b/tools/perf/util/evlist-hybrid.c @@ -154,8 +154,8 @@ int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list) perf_cpu_map__put(matched_cpus); perf_cpu_map__put(unmatched_cpus); } - - ret = (unmatched_count == events_nr) ? -1 : 0; + if (events_nr) + ret = (unmatched_count == events_nr) ? -1 : 0; out: perf_cpu_map__put(cpus); return ret; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index eaad04e1672a..41a66a48cbdf 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -346,7 +346,7 @@ struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affin { struct evlist_cpu_iterator itr = { .container = evlist, - .evsel = evlist__first(evlist), + .evsel = NULL, .cpu_map_idx = 0, .evlist_cpu_map_idx = 0, .evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus), @@ -354,16 +354,22 @@ struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affin .affinity = affinity, }; - if (itr.affinity) { - itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0); - affinity__set(itr.affinity, itr.cpu.cpu); - itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu); - /* - * If this CPU isn't in the evsel's cpu map then advance through - * the list. - */ - if (itr.cpu_map_idx == -1) - evlist_cpu_iterator__next(&itr); + if (evlist__empty(evlist)) { + /* Ensure the empty list doesn't iterate. */ + itr.evlist_cpu_map_idx = itr.evlist_cpu_map_nr; + } else { + itr.evsel = evlist__first(evlist); + if (itr.affinity) { + itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0); + affinity__set(itr.affinity, itr.cpu.cpu); + itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu); + /* + * If this CPU isn't in the evsel's cpu map then advance + * through the list. + */ + if (itr.cpu_map_idx == -1) + evlist_cpu_iterator__next(&itr); + } } return itr; } diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index 5acf053fca7d..aa0c5179836d 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -50,41 +50,32 @@ #ifndef SYM_END #define SYM_END(name, sym_type) \ .type name sym_type ASM_NL \ + .set .L__sym_size_##name, .-name ASM_NL \ .size name, .-name #endif -/* - * SYM_FUNC_START_ALIAS -- use where there are two global names for one - * function - */ -#ifndef SYM_FUNC_START_ALIAS -#define SYM_FUNC_START_ALIAS(name) \ - SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +/* SYM_ALIAS -- use only if you have to */ +#ifndef SYM_ALIAS +#define SYM_ALIAS(alias, name, sym_type, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL \ + .type alias sym_type ASM_NL \ + .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ + .size alias, .L__sym_size_##alias #endif /* SYM_FUNC_START -- use for global functions */ #ifndef SYM_FUNC_START -/* - * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two - * later. - */ #define SYM_FUNC_START(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #endif /* SYM_FUNC_START_LOCAL -- use for local functions */ #ifndef SYM_FUNC_START_LOCAL -/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) #endif -/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */ -#ifndef SYM_FUNC_END_ALIAS -#define SYM_FUNC_END_ALIAS(name) \ - SYM_END(name, SYM_T_FUNC) -#endif - /* SYM_FUNC_START_WEAK -- use for weak functions */ #ifndef SYM_FUNC_START_WEAK #define SYM_FUNC_START_WEAK(name) \ @@ -96,9 +87,32 @@ * SYM_FUNC_START_WEAK, ... */ #ifndef SYM_FUNC_END -/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_END(name) \ SYM_END(name, SYM_T_FUNC) #endif +/* + * SYM_FUNC_ALIAS -- define a global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS +#define SYM_FUNC_ALIAS(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) +#endif + +/* + * SYM_FUNC_ALIAS_LOCAL -- define a local alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_LOCAL +#define SYM_FUNC_ALIAS_LOCAL(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) +#endif + +/* + * SYM_FUNC_ALIAS_WEAK -- define a weak global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_WEAK +#define SYM_FUNC_ALIAS_WEAK(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) +#endif + #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index f70ba56912d4..394550003693 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2073,6 +2073,7 @@ static void ip__resolve_ams(struct thread *thread, ams->addr = ip; ams->al_addr = al.addr; + ams->al_level = al.level; ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; @@ -2092,6 +2093,7 @@ static void ip__resolve_data(struct thread *thread, ams->addr = addr; ams->al_addr = al.addr; + ams->al_level = al.level; ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 7d22ade082c8..e08817b0c30f 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -18,6 +18,7 @@ struct addr_map_symbol { struct map_symbol ms; u64 addr; u64 al_addr; + char al_level; u64 phys_addr; u64 data_page_size; }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9739b05b999e..24997925ae00 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1648,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, { struct parse_events_term *term; struct list_head *list = NULL; + struct list_head *orig_head = NULL; struct perf_pmu *pmu = NULL; int ok = 0; char *config; @@ -1674,7 +1675,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } list_add_tail(&term->list, head); - /* Add it for all PMUs that support the alias */ list = malloc(sizeof(struct list_head)); if (!list) @@ -1687,13 +1687,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { + parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, - pmu->name, head, + pmu->name, orig_head, true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; } + parse_events_terms__delete(orig_head); } } } @@ -2193,7 +2195,7 @@ int perf_pmu__test_parse_init(void) for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) { tmp->type = symbols[i].type; tmp->symbol = strdup(symbols[i].symbol); - if (!list->symbol) + if (!tmp->symbol) goto err_free; } diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 47b7531f51da..98af3fa4ea35 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -52,7 +52,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value) bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), - bit_name(HW_INDEX), + bit_name(TYPE_SAVE), bit_name(HW_INDEX), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 2c0d30f08e78..498b05708db5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1503,11 +1503,12 @@ static int machines__deliver_event(struct machines *machines, ++evlist->stats.nr_unknown_id; return 0; } - dump_sample(evsel, event, sample, perf_env__arch(machine->env)); if (machine == NULL) { ++evlist->stats.nr_unprocessable_samples; + dump_sample(evsel, event, sample, perf_env__arch(NULL)); return 0; } + dump_sample(evsel, event, sample, perf_env__arch(machine->env)); return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index cfba8c337783..2da081ef532b 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -915,7 +915,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, struct addr_map_symbol *from = &he->branch_info->from; return _hist_entry__sym_snprintf(&from->ms, from->al_addr, - he->level, bf, size, width); + from->al_level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -928,7 +928,7 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, struct addr_map_symbol *to = &he->branch_info->to; return _hist_entry__sym_snprintf(&to->ms, to->al_addr, - he->level, bf, size, width); + to->al_level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 5db83e51ceef..9cbe351b141f 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -585,15 +585,16 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c alias = list_prepare_entry(counter, &(evlist->core.entries), core.node); list_for_each_entry_continue (alias, &evlist->core.entries, core.node) { - if (strcmp(evsel__name(alias), evsel__name(counter)) || - alias->scale != counter->scale || - alias->cgrp != counter->cgrp || - strcmp(alias->unit, counter->unit) || - evsel__is_clock(alias) != evsel__is_clock(counter) || - !strcmp(alias->pmu_name, counter->pmu_name)) - break; - alias->merged_stat = true; - cb(config, alias, data, false); + /* Merge events with the same name, etc. but on different PMUs. */ + if (!strcmp(evsel__name(alias), evsel__name(counter)) && + alias->scale == counter->scale && + alias->cgrp == counter->cgrp && + !strcmp(alias->unit, counter->unit) && + evsel__is_clock(alias) == evsel__is_clock(counter) && + strcmp(alias->pmu_name, counter->pmu_name)) { + alias->merged_stat = true; + cb(config, alias, data, false); + } } } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index b2ed3140a1fa..dfde9eada224 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -231,7 +231,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols) prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start && prev->end != curr->start) + if (prev->end == prev->start || prev->end != curr->start) arch__symbols__fixup_end(prev, curr); } diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 70f095624a0b..b654de0841f8 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1784,6 +1784,25 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too perf_event__handler_t process, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize) { + /* + * When perf runs in non-root PID namespace, and the namespace's proc FS + * is not mounted, nsinfo__is_in_root_namespace() returns false. + * In this case, the proc FS is coming for the parent namespace, thus + * perf tool will wrongly gather process info from its parent PID + * namespace. + * + * To avoid the confusion that the perf tool runs in a child PID + * namespace but it synthesizes thread info from its parent PID + * namespace, returns failure with warning. + */ + if (!nsinfo__is_in_root_namespace()) { + pr_err("Perf runs in non-root PID namespace but it tries to "); + pr_err("gather process info from its parent PID namespace.\n"); + pr_err("Please mount the proc file system properly, e.g. "); + pr_err("add the option '--mount-proc' for unshare command.\n"); + return -EPERM; + } + if (target__has_task(target)) return perf_event__synthesize_thread_map(tool, threads, process, machine, needs_mmap, data_mmap); diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 3b1594447f29..e9b6de314654 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -143,9 +143,9 @@ UTIL_HEADERS = utils/helpers/helpers.h utils/idle_monitor/cpupower-monitor.h \ utils/helpers/bitmask.h \ utils/idle_monitor/idle_monitors.h utils/idle_monitor/idle_monitors.def -LIB_HEADERS = lib/cpufreq.h lib/cpupower.h lib/cpuidle.h -LIB_SRC = lib/cpufreq.c lib/cpupower.c lib/cpuidle.c -LIB_OBJS = lib/cpufreq.o lib/cpupower.o lib/cpuidle.o +LIB_HEADERS = lib/cpufreq.h lib/cpupower.h lib/cpuidle.h lib/acpi_cppc.h +LIB_SRC = lib/cpufreq.c lib/cpupower.c lib/cpuidle.c lib/acpi_cppc.c +LIB_OBJS = lib/cpufreq.o lib/cpupower.o lib/cpuidle.o lib/acpi_cppc.o LIB_OBJS := $(addprefix $(OUTPUT),$(LIB_OBJS)) override CFLAGS += -pipe diff --git a/tools/power/cpupower/ToDo b/tools/power/cpupower/TODO index b196a139a3e4..b196a139a3e4 100644 --- a/tools/power/cpupower/ToDo +++ b/tools/power/cpupower/TODO diff --git a/tools/power/cpupower/lib/acpi_cppc.c b/tools/power/cpupower/lib/acpi_cppc.c new file mode 100644 index 000000000000..c401ac331e9f --- /dev/null +++ b/tools/power/cpupower/lib/acpi_cppc.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> + +#include "cpupower_intern.h" +#include "acpi_cppc.h" + +/* ACPI CPPC sysfs access ***********************************************/ + +static int acpi_cppc_read_file(unsigned int cpu, const char *fname, + char *buf, size_t buflen) +{ + char path[SYSFS_PATH_MAX]; + + snprintf(path, sizeof(path), PATH_TO_CPU "cpu%u/acpi_cppc/%s", + cpu, fname); + return cpupower_read_sysfs(path, buf, buflen); +} + +static const char * const acpi_cppc_value_files[] = { + [HIGHEST_PERF] = "highest_perf", + [LOWEST_PERF] = "lowest_perf", + [NOMINAL_PERF] = "nominal_perf", + [LOWEST_NONLINEAR_PERF] = "lowest_nonlinear_perf", + [LOWEST_FREQ] = "lowest_freq", + [NOMINAL_FREQ] = "nominal_freq", + [REFERENCE_PERF] = "reference_perf", + [WRAPAROUND_TIME] = "wraparound_time" +}; + +unsigned long acpi_cppc_get_data(unsigned int cpu, enum acpi_cppc_value which) +{ + unsigned long long value; + unsigned int len; + char linebuf[MAX_LINE_LEN]; + char *endp; + + if (which >= MAX_CPPC_VALUE_FILES) + return 0; + + len = acpi_cppc_read_file(cpu, acpi_cppc_value_files[which], + linebuf, sizeof(linebuf)); + if (len == 0) + return 0; + + value = strtoull(linebuf, &endp, 0); + + if (endp == linebuf || errno == ERANGE) + return 0; + + return value; +} diff --git a/tools/power/cpupower/lib/acpi_cppc.h b/tools/power/cpupower/lib/acpi_cppc.h new file mode 100644 index 000000000000..85ca83080316 --- /dev/null +++ b/tools/power/cpupower/lib/acpi_cppc.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ACPI_CPPC_H__ +#define __ACPI_CPPC_H__ + +enum acpi_cppc_value { + HIGHEST_PERF, + LOWEST_PERF, + NOMINAL_PERF, + LOWEST_NONLINEAR_PERF, + LOWEST_FREQ, + NOMINAL_FREQ, + REFERENCE_PERF, + WRAPAROUND_TIME, + MAX_CPPC_VALUE_FILES +}; + +unsigned long acpi_cppc_get_data(unsigned int cpu, + enum acpi_cppc_value which); + +#endif /* _ACPI_CPPC_H */ diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index c3b56db8b921..1516d23c17c9 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -83,20 +83,21 @@ static const char *cpufreq_value_files[MAX_CPUFREQ_VALUE_READ_FILES] = { [STATS_NUM_TRANSITIONS] = "stats/total_trans" }; - -static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, - enum cpufreq_value which) +unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu, + const char **table, + unsigned int index, + unsigned int size) { unsigned long value; unsigned int len; char linebuf[MAX_LINE_LEN]; char *endp; - if (which >= MAX_CPUFREQ_VALUE_READ_FILES) + if (!table || index >= size || !table[index]) return 0; - len = sysfs_cpufreq_read_file(cpu, cpufreq_value_files[which], - linebuf, sizeof(linebuf)); + len = sysfs_cpufreq_read_file(cpu, table[index], linebuf, + sizeof(linebuf)); if (len == 0) return 0; @@ -109,6 +110,14 @@ static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, return value; } +static unsigned long sysfs_cpufreq_get_one_value(unsigned int cpu, + enum cpufreq_value which) +{ + return cpufreq_get_sysfs_value_from_table(cpu, cpufreq_value_files, + which, + MAX_CPUFREQ_VALUE_READ_FILES); +} + /* read access to files which contain one string */ enum cpufreq_string { @@ -124,7 +133,7 @@ static const char *cpufreq_string_files[MAX_CPUFREQ_STRING_FILES] = { static char *sysfs_cpufreq_get_one_string(unsigned int cpu, - enum cpufreq_string which) + enum cpufreq_string which) { char linebuf[MAX_LINE_LEN]; char *result; diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h index 95f4fd9e2656..2f3c84035806 100644 --- a/tools/power/cpupower/lib/cpufreq.h +++ b/tools/power/cpupower/lib/cpufreq.h @@ -203,6 +203,18 @@ int cpufreq_modify_policy_governor(unsigned int cpu, char *governor); int cpufreq_set_frequency(unsigned int cpu, unsigned long target_frequency); +/* + * get the sysfs value from specific table + * + * Read the value with the sysfs file name from specific table. Does + * only work if the cpufreq driver has the specific sysfs interfaces. + */ + +unsigned long cpufreq_get_sysfs_value_from_table(unsigned int cpu, + const char **table, + unsigned int index, + unsigned int size); + #ifdef __cplusplus } #endif diff --git a/tools/power/cpupower/man/cpupower-frequency-info.1 b/tools/power/cpupower/man/cpupower-frequency-info.1 index 6aa8d239dff9..dd545b499480 100644 --- a/tools/power/cpupower/man/cpupower-frequency-info.1 +++ b/tools/power/cpupower/man/cpupower-frequency-info.1 @@ -53,6 +53,9 @@ human\-readable output for the \-f, \-w, \-s and \-y parameters. \fB\-n\fR \fB\-\-no-rounding\fR Output frequencies and latencies without rounding off values. .TP +\fB\-c\fR \fB\-\-perf\fR +Get performances and frequencies capabilities of CPPC, by reading it from hardware (only available on the hardware with CPPC). +.TP .SH "REMARKS" .LP By default only values of core zero are displayed. How to display settings of diff --git a/tools/power/cpupower/man/cpupower-idle-set.1 b/tools/power/cpupower/man/cpupower-idle-set.1 index 21916cff7516..8cef3c71e19e 100644 --- a/tools/power/cpupower/man/cpupower-idle-set.1 +++ b/tools/power/cpupower/man/cpupower-idle-set.1 @@ -4,7 +4,7 @@ cpupower\-idle\-set \- Utility to set cpu idle state specific kernel options .SH "SYNTAX" .LP -cpupower [ \-c cpulist ] idle\-info [\fIoptions\fP] +cpupower [ \-c cpulist ] idle\-set [\fIoptions\fP] .SH "DESCRIPTION" .LP The cpupower idle\-set subcommand allows to set cpu idle, also called cpu diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index f9895e31ff5a..0646f615fe2d 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -84,43 +84,6 @@ static void proc_cpufreq_output(void) } static int no_rounding; -static void print_speed(unsigned long speed) -{ - unsigned long tmp; - - if (no_rounding) { - if (speed > 1000000) - printf("%u.%06u GHz", ((unsigned int) speed/1000000), - ((unsigned int) speed%1000000)); - else if (speed > 1000) - printf("%u.%03u MHz", ((unsigned int) speed/1000), - (unsigned int) (speed%1000)); - else - printf("%lu kHz", speed); - } else { - if (speed > 1000000) { - tmp = speed%10000; - if (tmp >= 5000) - speed += 10000; - printf("%u.%02u GHz", ((unsigned int) speed/1000000), - ((unsigned int) (speed%1000000)/10000)); - } else if (speed > 100000) { - tmp = speed%1000; - if (tmp >= 500) - speed += 1000; - printf("%u MHz", ((unsigned int) speed/1000)); - } else if (speed > 1000) { - tmp = speed%100; - if (tmp >= 50) - speed += 100; - printf("%u.%01u MHz", ((unsigned int) speed/1000), - ((unsigned int) (speed%1000)/100)); - } - } - - return; -} - static void print_duration(unsigned long duration) { unsigned long tmp; @@ -183,9 +146,12 @@ static int get_boost_mode_x86(unsigned int cpu) printf(_(" Supported: %s\n"), support ? _("yes") : _("no")); printf(_(" Active: %s\n"), active ? _("yes") : _("no")); - if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD && - cpupower_cpu_info.family >= 0x10) || - cpupower_cpu_info.vendor == X86_VENDOR_HYGON) { + if (cpupower_cpu_info.vendor == X86_VENDOR_AMD && + cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) { + return 0; + } else if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD && + cpupower_cpu_info.family >= 0x10) || + cpupower_cpu_info.vendor == X86_VENDOR_HYGON) { ret = decode_pstates(cpu, b_states, pstates, &pstate_no); if (ret) return ret; @@ -254,11 +220,11 @@ static int get_boost_mode(unsigned int cpu) if (freqs) { printf(_(" boost frequency steps: ")); while (freqs->next) { - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf(", "); freqs = freqs->next; } - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf("\n"); cpufreq_put_available_frequencies(freqs); } @@ -277,7 +243,7 @@ static int get_freq_kernel(unsigned int cpu, unsigned int human) return -EINVAL; } if (human) { - print_speed(freq); + print_speed(freq, no_rounding); } else printf("%lu", freq); printf(_(" (asserted by call to kernel)\n")); @@ -296,7 +262,7 @@ static int get_freq_hardware(unsigned int cpu, unsigned int human) return -EINVAL; } if (human) { - print_speed(freq); + print_speed(freq, no_rounding); } else printf("%lu", freq); printf(_(" (asserted by call to hardware)\n")); @@ -316,9 +282,9 @@ static int get_hardware_limits(unsigned int cpu, unsigned int human) if (human) { printf(_(" hardware limits: ")); - print_speed(min); + print_speed(min, no_rounding); printf(" - "); - print_speed(max); + print_speed(max, no_rounding); printf("\n"); } else { printf("%lu %lu\n", min, max); @@ -350,9 +316,9 @@ static int get_policy(unsigned int cpu) return -EINVAL; } printf(_(" current policy: frequency should be within ")); - print_speed(policy->min); + print_speed(policy->min, no_rounding); printf(_(" and ")); - print_speed(policy->max); + print_speed(policy->max, no_rounding); printf(".\n "); printf(_("The governor \"%s\" may decide which speed to use\n" @@ -436,7 +402,7 @@ static int get_freq_stats(unsigned int cpu, unsigned int human) struct cpufreq_stats *stats = cpufreq_get_stats(cpu, &total_time); while (stats) { if (human) { - print_speed(stats->frequency); + print_speed(stats->frequency, no_rounding); printf(":%.2f%%", (100.0 * stats->time_in_state) / total_time); } else @@ -472,6 +438,17 @@ static int get_latency(unsigned int cpu, unsigned int human) return 0; } +/* --performance / -c */ + +static int get_perf_cap(unsigned int cpu) +{ + if (cpupower_cpu_info.vendor == X86_VENDOR_AMD && + cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) + amd_pstate_show_perf_and_freq(cpu, no_rounding); + + return 0; +} + static void debug_output_one(unsigned int cpu) { struct cpufreq_available_frequencies *freqs; @@ -486,11 +463,11 @@ static void debug_output_one(unsigned int cpu) if (freqs) { printf(_(" available frequency steps: ")); while (freqs->next) { - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf(", "); freqs = freqs->next; } - print_speed(freqs->frequency); + print_speed(freqs->frequency, no_rounding); printf("\n"); cpufreq_put_available_frequencies(freqs); } @@ -500,6 +477,7 @@ static void debug_output_one(unsigned int cpu) if (get_freq_hardware(cpu, 1) < 0) get_freq_kernel(cpu, 1); get_boost_mode(cpu); + get_perf_cap(cpu); } static struct option info_opts[] = { @@ -518,6 +496,7 @@ static struct option info_opts[] = { {"proc", no_argument, NULL, 'o'}, {"human", no_argument, NULL, 'm'}, {"no-rounding", no_argument, NULL, 'n'}, + {"performance", no_argument, NULL, 'c'}, { }, }; @@ -531,7 +510,7 @@ int cmd_freq_info(int argc, char **argv) int output_param = 0; do { - ret = getopt_long(argc, argv, "oefwldpgrasmybn", info_opts, + ret = getopt_long(argc, argv, "oefwldpgrasmybnc", info_opts, NULL); switch (ret) { case '?': @@ -554,6 +533,7 @@ int cmd_freq_info(int argc, char **argv) case 'e': case 's': case 'y': + case 'c': if (output_param) { output_param = -1; cont = 0; @@ -660,6 +640,9 @@ int cmd_freq_info(int argc, char **argv) case 'y': ret = get_latency(cpu, human); break; + case 'c': + ret = get_perf_cap(cpu); + break; } if (ret) return ret; diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c index 97f2c857048e..c519cc89c97f 100644 --- a/tools/power/cpupower/utils/helpers/amd.c +++ b/tools/power/cpupower/utils/helpers/amd.c @@ -8,7 +8,10 @@ #include <pci/pci.h> #include "helpers/helpers.h" +#include "cpufreq.h" +#include "acpi_cppc.h" +/* ACPI P-States Helper Functions for AMD Processors ***************/ #define MSR_AMD_PSTATE_STATUS 0xc0010063 #define MSR_AMD_PSTATE 0xc0010064 #define MSR_AMD_PSTATE_LIMIT 0xc0010061 @@ -146,4 +149,78 @@ int amd_pci_get_num_boost_states(int *active, int *states) pci_cleanup(pci_acc); return 0; } + +/* ACPI P-States Helper Functions for AMD Processors ***************/ + +/* AMD P-State Helper Functions ************************************/ +enum amd_pstate_value { + AMD_PSTATE_HIGHEST_PERF, + AMD_PSTATE_MAX_FREQ, + AMD_PSTATE_LOWEST_NONLINEAR_FREQ, + MAX_AMD_PSTATE_VALUE_READ_FILES, +}; + +static const char *amd_pstate_value_files[MAX_AMD_PSTATE_VALUE_READ_FILES] = { + [AMD_PSTATE_HIGHEST_PERF] = "amd_pstate_highest_perf", + [AMD_PSTATE_MAX_FREQ] = "amd_pstate_max_freq", + [AMD_PSTATE_LOWEST_NONLINEAR_FREQ] = "amd_pstate_lowest_nonlinear_freq", +}; + +static unsigned long amd_pstate_get_data(unsigned int cpu, + enum amd_pstate_value value) +{ + return cpufreq_get_sysfs_value_from_table(cpu, + amd_pstate_value_files, + value, + MAX_AMD_PSTATE_VALUE_READ_FILES); +} + +void amd_pstate_boost_init(unsigned int cpu, int *support, int *active) +{ + unsigned long highest_perf, nominal_perf, cpuinfo_min, + cpuinfo_max, amd_pstate_max; + + highest_perf = amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF); + nominal_perf = acpi_cppc_get_data(cpu, NOMINAL_PERF); + + *support = highest_perf > nominal_perf ? 1 : 0; + if (!(*support)) + return; + + cpufreq_get_hardware_limits(cpu, &cpuinfo_min, &cpuinfo_max); + amd_pstate_max = amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ); + + *active = cpuinfo_max == amd_pstate_max ? 1 : 0; +} + +void amd_pstate_show_perf_and_freq(unsigned int cpu, int no_rounding) +{ + printf(_(" AMD PSTATE Highest Performance: %lu. Maximum Frequency: "), + amd_pstate_get_data(cpu, AMD_PSTATE_HIGHEST_PERF)); + /* + * If boost isn't active, the cpuinfo_max doesn't indicate real max + * frequency. So we read it back from amd-pstate sysfs entry. + */ + print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_MAX_FREQ), no_rounding); + printf(".\n"); + + printf(_(" AMD PSTATE Nominal Performance: %lu. Nominal Frequency: "), + acpi_cppc_get_data(cpu, NOMINAL_PERF)); + print_speed(acpi_cppc_get_data(cpu, NOMINAL_FREQ) * 1000, + no_rounding); + printf(".\n"); + + printf(_(" AMD PSTATE Lowest Non-linear Performance: %lu. Lowest Non-linear Frequency: "), + acpi_cppc_get_data(cpu, LOWEST_NONLINEAR_PERF)); + print_speed(amd_pstate_get_data(cpu, AMD_PSTATE_LOWEST_NONLINEAR_FREQ), + no_rounding); + printf(".\n"); + + printf(_(" AMD PSTATE Lowest Performance: %lu. Lowest Frequency: "), + acpi_cppc_get_data(cpu, LOWEST_PERF)); + print_speed(acpi_cppc_get_data(cpu, LOWEST_FREQ) * 1000, no_rounding); + printf(".\n"); +} + +/* AMD P-State Helper Functions ************************************/ #endif /* defined(__i386__) || defined(__x86_64__) */ diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 72eb43593180..eae91f11d187 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -149,6 +149,19 @@ out: if (ext_cpuid_level >= 0x80000008 && cpuid_ebx(0x80000008) & (1 << 4)) cpu_info->caps |= CPUPOWER_CAP_AMD_RDPRU; + + if (cpupower_amd_pstate_enabled()) { + cpu_info->caps |= CPUPOWER_CAP_AMD_PSTATE; + + /* + * If AMD P-State is enabled, the firmware will treat + * AMD P-State function as high priority. + */ + cpu_info->caps &= ~CPUPOWER_CAP_AMD_CPB; + cpu_info->caps &= ~CPUPOWER_CAP_AMD_CPB_MSR; + cpu_info->caps &= ~CPUPOWER_CAP_AMD_HW_PSTATE; + cpu_info->caps &= ~CPUPOWER_CAP_AMD_PSTATEDEF; + } } if (cpu_info->vendor == X86_VENDOR_INTEL) { diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 33ffacee7fcb..96e4bede078b 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -11,6 +11,7 @@ #include <libintl.h> #include <locale.h> +#include <stdbool.h> #include "helpers/bitmask.h" #include <cpupower.h> @@ -73,6 +74,7 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL, #define CPUPOWER_CAP_AMD_HW_PSTATE 0x00000100 #define CPUPOWER_CAP_AMD_PSTATEDEF 0x00000200 #define CPUPOWER_CAP_AMD_CPB_MSR 0x00000400 +#define CPUPOWER_CAP_AMD_PSTATE 0x00000800 #define CPUPOWER_AMD_CPBDIS 0x02000000 @@ -135,6 +137,16 @@ extern int decode_pstates(unsigned int cpu, int boost_states, extern int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, int * states); + +/* AMD P-State stuff **************************/ +bool cpupower_amd_pstate_enabled(void); +void amd_pstate_boost_init(unsigned int cpu, + int *support, int *active); +void amd_pstate_show_perf_and_freq(unsigned int cpu, + int no_rounding); + +/* AMD P-State stuff **************************/ + /* * CPUID functions returning a single datum */ @@ -167,6 +179,15 @@ static inline int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, int * states) { return -1; } +static inline bool cpupower_amd_pstate_enabled(void) +{ return false; } +static inline void amd_pstate_boost_init(unsigned int cpu, int *support, + int *active) +{} +static inline void amd_pstate_show_perf_and_freq(unsigned int cpu, + int no_rounding) +{} + /* cpuid and cpuinfo helpers **************************/ static inline unsigned int cpuid_eax(unsigned int op) { return 0; }; @@ -184,5 +205,6 @@ extern struct bitmask *offline_cpus; void get_cpustate(void); void print_online_cpus(void); void print_offline_cpus(void); +void print_speed(unsigned long speed, int no_rounding); #endif /* __CPUPOWERUTILS_HELPERS__ */ diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index fc6e34511721..9547b29254a7 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -3,9 +3,11 @@ #include <stdio.h> #include <errno.h> #include <stdlib.h> +#include <string.h> #include "helpers/helpers.h" #include "helpers/sysfs.h" +#include "cpufreq.h" #if defined(__i386__) || defined(__x86_64__) @@ -39,6 +41,8 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, if (ret) return ret; } + } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) { + amd_pstate_boost_init(cpu, support, active); } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) *support = *active = 1; return 0; @@ -83,6 +87,22 @@ int cpupower_intel_set_perf_bias(unsigned int cpu, unsigned int val) return 0; } +bool cpupower_amd_pstate_enabled(void) +{ + char *driver = cpufreq_get_driver(0); + bool ret = false; + + if (!driver) + return ret; + + if (!strcmp(driver, "amd-pstate")) + ret = true; + + cpufreq_put_driver(driver); + + return ret; +} + #endif /* #if defined(__i386__) || defined(__x86_64__) */ /* get_cpustate @@ -144,3 +164,43 @@ void print_offline_cpus(void) printf(_("cpupower set operation was not performed on them\n")); } } + +/* + * print_speed + * + * Print the exact CPU frequency with appropriate unit + */ +void print_speed(unsigned long speed, int no_rounding) +{ + unsigned long tmp; + + if (no_rounding) { + if (speed > 1000000) + printf("%u.%06u GHz", ((unsigned int)speed / 1000000), + ((unsigned int)speed % 1000000)); + else if (speed > 1000) + printf("%u.%03u MHz", ((unsigned int)speed / 1000), + (unsigned int)(speed % 1000)); + else + printf("%lu kHz", speed); + } else { + if (speed > 1000000) { + tmp = speed % 10000; + if (tmp >= 5000) + speed += 10000; + printf("%u.%02u GHz", ((unsigned int)speed / 1000000), + ((unsigned int)(speed % 1000000) / 10000)); + } else if (speed > 100000) { + tmp = speed % 1000; + if (tmp >= 500) + speed += 1000; + printf("%u MHz", ((unsigned int)speed / 1000)); + } else if (speed > 1000) { + tmp = speed % 100; + if (tmp >= 50) + speed += 100; + printf("%u.%01u MHz", ((unsigned int)speed / 1000), + ((unsigned int)(speed % 1000) / 100)); + } + } +} diff --git a/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py b/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py new file mode 100755 index 000000000000..2dea4032ac56 --- /dev/null +++ b/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py @@ -0,0 +1,354 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-only +# -*- coding: utf-8 -*- +# +""" This utility can be used to debug and tune the performance of the +AMD P-State driver. It imports intel_pstate_tracer to analyze AMD P-State +trace event. + +Prerequisites: + Python version 2.7.x or higher + gnuplot 5.0 or higher + gnuplot-py 1.8 or higher + (Most of the distributions have these required packages. They may be called + gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... ) + + Kernel config for Linux trace is enabled + + see print_help(): for Usage and Output details + +""" +from __future__ import print_function +from datetime import datetime +import subprocess +import os +import time +import re +import signal +import sys +import getopt +import Gnuplot +from numpy import * +from decimal import * +sys.path.append('../intel_pstate_tracer') +#import intel_pstate_tracer +import intel_pstate_tracer as ipt + +__license__ = "GPL version 2" + +MAX_CPUS = 256 +# Define the csv file columns +C_COMM = 15 +C_ELAPSED = 14 +C_SAMPLE = 13 +C_DURATION = 12 +C_LOAD = 11 +C_TSC = 10 +C_APERF = 9 +C_MPERF = 8 +C_FREQ = 7 +C_MAX_PERF = 6 +C_DES_PERF = 5 +C_MIN_PERF = 4 +C_USEC = 3 +C_SEC = 2 +C_CPU = 1 + +global sample_num, last_sec_cpu, last_usec_cpu, start_time, test_name, trace_file + +getcontext().prec = 11 + +sample_num =0 +last_sec_cpu = [0] * MAX_CPUS +last_usec_cpu = [0] * MAX_CPUS + +def plot_per_cpu_freq(cpu_index): + """ Plot per cpu frequency """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_frequency.png" % cpu_index + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:7]') + g_plot('set ytics 0, 1') + g_plot('set ylabel "CPU Frequency (GHz)"') + g_plot('set title "{} : frequency : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now())) + g_plot('set ylabel "CPU frequency"') + g_plot('set key off') + ipt.set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_FREQ)) + +def plot_per_cpu_des_perf(cpu_index): + """ Plot per cpu desired perf """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_des_perf.png" % cpu_index + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:255]') + g_plot('set ylabel "des perf"') + g_plot('set title "{} : cpu des perf : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now())) + g_plot('set key off') + ipt.set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_DES_PERF)) + +def plot_per_cpu_load(cpu_index): + """ Plot per cpu load """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_load.png" % cpu_index + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:100]') + g_plot('set ytics 0, 10') + g_plot('set ylabel "CPU load (percent)"') + g_plot('set title "{} : cpu load : CPU {:0>3} : {:%F %H:%M}"'.format(test_name, cpu_index, datetime.now())) + g_plot('set key off') + ipt.set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_LOAD)) + +def plot_all_cpu_frequency(): + """ Plot all cpu frequencies """ + + output_png = 'all_cpu_frequencies.png' + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set ylabel "CPU Frequency (GHz)"') + g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(test_name, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_all_cpu_des_perf(): + """ Plot all cpu desired perf """ + + output_png = 'all_cpu_des_perf.png' + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set ylabel "des perf"') + g_plot('set title "{} : cpu des perf : {:%F %H:%M}"'.format(test_name, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 255 ps 1 title i".format(C_ELAPSED, C_DES_PERF) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_all_cpu_load(): + """ Plot all cpu load """ + + output_png = 'all_cpu_load.png' + g_plot = ipt.common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + g_plot('set yrange [0:100]') + g_plot('set ylabel "CPU load (percent)"') + g_plot('set title "{} : cpu load : {:%F %H:%M}"'.format(test_name, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 255 ps 1 title i".format(C_ELAPSED, C_LOAD) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def store_csv(cpu_int, time_pre_dec, time_post_dec, min_perf, des_perf, max_perf, freq_ghz, mperf, aperf, tsc, common_comm, load, duration_ms, sample_num, elapsed_time, cpu_mask): + """ Store master csv file information """ + + global graph_data_present + + if cpu_mask[cpu_int] == 0: + return + + try: + f_handle = open('cpu.csv', 'a') + string_buffer = "CPU_%03u, %05u, %06u, %u, %u, %u, %.4f, %u, %u, %u, %.2f, %.3f, %u, %.3f, %s\n" % (cpu_int, int(time_pre_dec), int(time_post_dec), int(min_perf), int(des_perf), int(max_perf), freq_ghz, int(mperf), int(aperf), int(tsc), load, duration_ms, sample_num, elapsed_time, common_comm) + f_handle.write(string_buffer) + f_handle.close() + except: + print('IO error cpu.csv') + return + + graph_data_present = True; + + +def cleanup_data_files(): + """ clean up existing data files """ + + if os.path.exists('cpu.csv'): + os.remove('cpu.csv') + f_handle = open('cpu.csv', 'a') + f_handle.write('common_cpu, common_secs, common_usecs, min_perf, des_perf, max_perf, freq, mperf, aperf, tsc, load, duration_ms, sample_num, elapsed_time, common_comm') + f_handle.write('\n') + f_handle.close() + +def read_trace_data(file_name, cpu_mask): + """ Read and parse trace data """ + + global current_max_cpu + global sample_num, last_sec_cpu, last_usec_cpu, start_time + + try: + data = open(file_name, 'r').read() + except: + print('Error opening ', file_name) + sys.exit(2) + + for line in data.splitlines(): + search_obj = \ + re.search(r'(^(.*?)\[)((\d+)[^\]])(.*?)(\d+)([.])(\d+)(.*?amd_min_perf=)(\d+)(.*?amd_des_perf=)(\d+)(.*?amd_max_perf=)(\d+)(.*?freq=)(\d+)(.*?mperf=)(\d+)(.*?aperf=)(\d+)(.*?tsc=)(\d+)' + , line) + + if search_obj: + cpu = search_obj.group(3) + cpu_int = int(cpu) + cpu = str(cpu_int) + + time_pre_dec = search_obj.group(6) + time_post_dec = search_obj.group(8) + min_perf = search_obj.group(10) + des_perf = search_obj.group(12) + max_perf = search_obj.group(14) + freq = search_obj.group(16) + mperf = search_obj.group(18) + aperf = search_obj.group(20) + tsc = search_obj.group(22) + + common_comm = search_obj.group(2).replace(' ', '') + + if sample_num == 0 : + start_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) + sample_num += 1 + + if last_sec_cpu[cpu_int] == 0 : + last_sec_cpu[cpu_int] = time_pre_dec + last_usec_cpu[cpu_int] = time_post_dec + else : + duration_us = (int(time_pre_dec) - int(last_sec_cpu[cpu_int])) * 1000000 + (int(time_post_dec) - int(last_usec_cpu[cpu_int])) + duration_ms = Decimal(duration_us) / Decimal(1000) + last_sec_cpu[cpu_int] = time_pre_dec + last_usec_cpu[cpu_int] = time_post_dec + elapsed_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) - start_time + load = Decimal(int(mperf)*100)/ Decimal(tsc) + freq_ghz = Decimal(freq)/Decimal(1000000) + store_csv(cpu_int, time_pre_dec, time_post_dec, min_perf, des_perf, max_perf, freq_ghz, mperf, aperf, tsc, common_comm, load, duration_ms, sample_num, elapsed_time, cpu_mask) + + if cpu_int > current_max_cpu: + current_max_cpu = cpu_int +# Now separate the main overall csv file into per CPU csv files. + ipt.split_csv(current_max_cpu, cpu_mask) + + +def signal_handler(signal, frame): + print(' SIGINT: Forcing cleanup before exit.') + if interval: + ipt.disable_trace(trace_file) + ipt.clear_trace_file() + ipt.free_trace_buffer() + sys.exit(0) + +trace_file = "/sys/kernel/debug/tracing/events/amd_cpu/enable" +signal.signal(signal.SIGINT, signal_handler) + +interval = "" +file_name = "" +cpu_list = "" +test_name = "" +memory = "10240" +graph_data_present = False; + +valid1 = False +valid2 = False + +cpu_mask = zeros((MAX_CPUS,), dtype=int) + + +try: + opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="]) +except getopt.GetoptError: + ipt.print_help('amd_pstate') + sys.exit(2) +for opt, arg in opts: + if opt == '-h': + print() + sys.exit() + elif opt in ("-t", "--trace_file"): + valid1 = True + location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) + file_name = os.path.join(location, arg) + elif opt in ("-i", "--interval"): + valid1 = True + interval = arg + elif opt in ("-c", "--cpu"): + cpu_list = arg + elif opt in ("-n", "--name"): + valid2 = True + test_name = arg + elif opt in ("-m", "--memory"): + memory = arg + +if not (valid1 and valid2): + ipt.print_help('amd_pstate') + sys.exit() + +if cpu_list: + for p in re.split("[,]", cpu_list): + if int(p) < MAX_CPUS : + cpu_mask[int(p)] = 1 +else: + for i in range (0, MAX_CPUS): + cpu_mask[i] = 1 + +if not os.path.exists('results'): + os.mkdir('results') + ipt.fix_ownership('results') + +os.chdir('results') +if os.path.exists(test_name): + print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') + sys.exit() +os.mkdir(test_name) +ipt.fix_ownership(test_name) +os.chdir(test_name) + +cur_version = sys.version_info +print('python version (should be >= 2.7):') +print(cur_version) + +cleanup_data_files() + +if interval: + file_name = "/sys/kernel/debug/tracing/trace" + ipt.clear_trace_file() + ipt.set_trace_buffer_size(memory) + ipt.enable_trace(trace_file) + time.sleep(int(interval)) + ipt.disable_trace(trace_file) + +current_max_cpu = 0 + +read_trace_data(file_name, cpu_mask) + +if interval: + ipt.clear_trace_file() + ipt.free_trace_buffer() + +if graph_data_present == False: + print('No valid data to plot') + sys.exit(2) + +for cpu_no in range(0, current_max_cpu + 1): + plot_per_cpu_freq(cpu_no) + plot_per_cpu_des_perf(cpu_no) + plot_per_cpu_load(cpu_no) + +plot_all_cpu_des_perf() +plot_all_cpu_frequency() +plot_all_cpu_load() + +for root, dirs, files in os.walk('.'): + for f in files: + ipt.fix_ownership(f) + +os.chdir('../../') diff --git a/tools/power/x86/intel-speed-select/Build b/tools/power/x86/intel-speed-select/Build index b61456d75190..81e36bd578b1 100644 --- a/tools/power/x86/intel-speed-select/Build +++ b/tools/power/x86/intel-speed-select/Build @@ -1 +1 @@ -intel-speed-select-y += isst-config.o isst-core.o isst-display.o +intel-speed-select-y += isst-config.o isst-core.o isst-display.o isst-daemon.o hfi-events.o diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile index 12c6939dca2a..d2fba1297d96 100644 --- a/tools/power/x86/intel-speed-select/Makefile +++ b/tools/power/x86/intel-speed-select/Makefile @@ -13,8 +13,8 @@ endif # Do not use make's built-in rules # (this improves performance and avoids hard-to-debug behaviour); MAKEFLAGS += -r - -override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include +override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include -I/usr/include/libnl3 +override LDFLAGS += -lnl-genl-3 -lnl-3 ALL_TARGETS := intel-speed-select ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) @@ -31,7 +31,11 @@ $(OUTPUT)include/linux/isst_if.h: ../../../../include/uapi/linux/isst_if.h mkdir -p $(OUTPUT)include/linux 2>&1 || true ln -sf $(CURDIR)/../../../../include/uapi/linux/isst_if.h $@ -prepare: $(OUTPUT)include/linux/isst_if.h +$(OUTPUT)include/linux/thermal.h: ../../../../include/uapi/linux/thermal.h + mkdir -p $(OUTPUT)include/linux 2>&1 || true + ln -sf $(CURDIR)/../../../../include/uapi/linux/thermal.h $@ + +prepare: $(OUTPUT)include/linux/isst_if.h $(OUTPUT)include/linux/thermal.h ISST_IN := $(OUTPUT)intel-speed-select-in.o diff --git a/tools/power/x86/intel-speed-select/hfi-events.c b/tools/power/x86/intel-speed-select/hfi-events.c new file mode 100644 index 000000000000..e85676711372 --- /dev/null +++ b/tools/power/x86/intel-speed-select/hfi-events.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select -- Read HFI events for OOB + * Copyright (c) 2022 Intel Corporation. + */ + +/* + * This file incorporates work covered by the following copyright and + * permission notice: + + * WPA Supplicant - driver interaction with Linux nl80211/cfg80211 + * Copyright (c) 2003-2008, Jouni Malinen <j@w1.fi> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Alternatively, this software may be distributed under the terms of + * BSD license. + * + * Requires + * libnl-genl-3-dev + * + * For Fedora/CenOS + * dnf install libnl3-devel + * For Ubuntu + * apt install libnl-3-dev libnl-genl-3-dev + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdarg.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/file.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <errno.h> +#include <getopt.h> +#include <signal.h> +#include <netlink/genl/genl.h> +#include <netlink/genl/family.h> +#include <netlink/genl/ctrl.h> + +#include <linux/thermal.h> +#include "isst.h" + +struct hfi_event_data { + struct nl_sock *nl_handle; + struct nl_cb *nl_cb; +}; + +struct hfi_event_data drv; + +static int ack_handler(struct nl_msg *msg, void *arg) +{ + int *err = arg; + *err = 0; + return NL_STOP; +} + +static int finish_handler(struct nl_msg *msg, void *arg) +{ + int *ret = arg; + *ret = 0; + return NL_SKIP; +} + +static int error_handler(struct sockaddr_nl *nla, struct nlmsgerr *err, + void *arg) +{ + int *ret = arg; + *ret = err->error; + return NL_SKIP; +} + +static int seq_check_handler(struct nl_msg *msg, void *arg) +{ + return NL_OK; +} + +static int send_and_recv_msgs(struct hfi_event_data *drv, + struct nl_msg *msg, + int (*valid_handler)(struct nl_msg *, void *), + void *valid_data) +{ + struct nl_cb *cb; + int err = -ENOMEM; + + cb = nl_cb_clone(drv->nl_cb); + if (!cb) + goto out; + + err = nl_send_auto_complete(drv->nl_handle, msg); + if (err < 0) + goto out; + + err = 1; + + nl_cb_err(cb, NL_CB_CUSTOM, error_handler, &err); + nl_cb_set(cb, NL_CB_FINISH, NL_CB_CUSTOM, finish_handler, &err); + nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, ack_handler, &err); + + if (valid_handler) + nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, + valid_handler, valid_data); + + while (err > 0) + nl_recvmsgs(drv->nl_handle, cb); + out: + nl_cb_put(cb); + nlmsg_free(msg); + return err; +} + +struct family_data { + const char *group; + int id; +}; + +static int family_handler(struct nl_msg *msg, void *arg) +{ + struct family_data *res = arg; + struct nlattr *tb[CTRL_ATTR_MAX + 1]; + struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg)); + struct nlattr *mcgrp; + int i; + + nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0), + genlmsg_attrlen(gnlh, 0), NULL); + if (!tb[CTRL_ATTR_MCAST_GROUPS]) + return NL_SKIP; + + nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], i) { + struct nlattr *tb2[CTRL_ATTR_MCAST_GRP_MAX + 1]; + nla_parse(tb2, CTRL_ATTR_MCAST_GRP_MAX, nla_data(mcgrp), + nla_len(mcgrp), NULL); + if (!tb2[CTRL_ATTR_MCAST_GRP_NAME] || + !tb2[CTRL_ATTR_MCAST_GRP_ID] || + strncmp(nla_data(tb2[CTRL_ATTR_MCAST_GRP_NAME]), + res->group, + nla_len(tb2[CTRL_ATTR_MCAST_GRP_NAME])) != 0) + continue; + res->id = nla_get_u32(tb2[CTRL_ATTR_MCAST_GRP_ID]); + break; + }; + + return 0; +} + +static int nl_get_multicast_id(struct hfi_event_data *drv, + const char *family, const char *group) +{ + struct nl_msg *msg; + int ret = -1; + struct family_data res = { group, -ENOENT }; + + msg = nlmsg_alloc(); + if (!msg) + return -ENOMEM; + genlmsg_put(msg, 0, 0, genl_ctrl_resolve(drv->nl_handle, "nlctrl"), + 0, 0, CTRL_CMD_GETFAMILY, 0); + NLA_PUT_STRING(msg, CTRL_ATTR_FAMILY_NAME, family); + + ret = send_and_recv_msgs(drv, msg, family_handler, &res); + msg = NULL; + if (ret == 0) + ret = res.id; + +nla_put_failure: + nlmsg_free(msg); + return ret; +} + +struct perf_cap { + int cpu; + int perf; + int eff; +}; + +static void process_hfi_event(struct perf_cap *perf_cap) +{ + process_level_change(perf_cap->cpu); +} + +static int handle_event(struct nl_msg *n, void *arg) +{ + struct nlmsghdr *nlh = nlmsg_hdr(n); + struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); + struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; + int ret; + struct perf_cap perf_cap; + + ret = genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); + + debug_printf("Received event %d parse_rer:%d\n", genlhdr->cmd, ret); + if (genlhdr->cmd == THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE) { + struct nlattr *cap; + int j, index = 0; + + debug_printf("THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE\n"); + nla_for_each_nested(cap, attrs[THERMAL_GENL_ATTR_CPU_CAPABILITY], j) { + switch (index) { + case 0: + perf_cap.cpu = nla_get_u32(cap); + break; + case 1: + perf_cap.perf = nla_get_u32(cap); + break; + case 2: + perf_cap.eff = nla_get_u32(cap); + break; + default: + break; + } + ++index; + if (index == 3) { + index = 0; + process_hfi_event(&perf_cap); + } + } + } + + return 0; +} + +static int _hfi_exit; + +static int check_hf_suport(void) +{ + unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0; + + __cpuid(6, eax, ebx, ecx, edx); + if (eax & BIT(19)) + return 1; + + return 0; +} + +int hfi_main(void) +{ + struct nl_sock *sock; + struct nl_cb *cb; + int err = 0; + int mcast_id; + int no_block = 0; + + if (!check_hf_suport()) { + fprintf(stderr, "CPU Doesn't support HFI\n"); + return -1; + } + + sock = nl_socket_alloc(); + if (!sock) { + fprintf(stderr, "nl_socket_alloc failed\n"); + return -1; + } + + if (genl_connect(sock)) { + fprintf(stderr, "genl_connect(sk_event) failed\n"); + goto free_sock; + } + + drv.nl_handle = sock; + drv.nl_cb = cb = nl_cb_alloc(NL_CB_DEFAULT); + if (drv.nl_cb == NULL) { + printf("Failed to allocate netlink callbacks"); + goto free_sock; + } + + mcast_id = nl_get_multicast_id(&drv, THERMAL_GENL_FAMILY_NAME, + THERMAL_GENL_EVENT_GROUP_NAME); + if (mcast_id < 0) { + fprintf(stderr, "nl_get_multicast_id failed\n"); + goto free_sock; + } + + if (nl_socket_add_membership(sock, mcast_id)) { + fprintf(stderr, "nl_socket_add_membership failed"); + goto free_sock; + } + + nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, seq_check_handler, 0); + nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, handle_event, NULL); + + if (no_block) + nl_socket_set_nonblocking(sock); + + debug_printf("hfi is initialized\n"); + + while (!_hfi_exit && !err) { + err = nl_recvmsgs(sock, cb); + debug_printf("nl_recv_message err:%d\n", err); + } + + return 0; + + /* Netlink library doesn't have calls to dealloc cb or disconnect */ +free_sock: + nl_socket_free(sock); + + return -1; +} + +void hfi_exit(void) +{ + _hfi_exit = 1; +} diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index efe72fa48224..060390e88e37 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -15,7 +15,8 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.11"; +static const char *version_str = "v1.12"; + static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -368,7 +369,7 @@ int get_topo_max_cpus(void) return topo_max_cpus; } -static void set_cpu_online_offline(int cpu, int state) +void set_cpu_online_offline(int cpu, int state) { char buffer[128]; int fd, ret; @@ -409,12 +410,10 @@ static void force_all_cpus_online(void) unlink("/var/run/isst_cpu_topology.dat"); } -#define MAX_PACKAGE_COUNT 8 -#define MAX_DIE_PER_PACKAGE 2 -static void for_each_online_package_in_set(void (*callback)(int, void *, void *, - void *, void *), - void *arg1, void *arg2, void *arg3, - void *arg4) +void for_each_online_package_in_set(void (*callback)(int, void *, void *, + void *, void *), + void *arg1, void *arg2, void *arg3, + void *arg4) { int max_packages[MAX_PACKAGE_COUNT * MAX_PACKAGE_COUNT]; int pkg_index = 0, i; @@ -2803,7 +2802,9 @@ static void usage(void) printf("\t[-p|--pause] : Delay between two mail box commands in milliseconds\n"); printf("\t[-r|--retry] : Retry count for mail box commands on failure, default 3\n"); printf("\t[-v|--version] : Print version\n"); - + printf("\t[-b|--oob : Start a daemon to process HFI events for perf profile change from Out of Band agent.\n"); + printf("\t[-n|--no-daemon : Don't run as daemon. By default --oob will turn on daemon mode\n"); + printf("\t[-w|--delay : Delay for reading config level state change in OOB poll mode.\n"); printf("\nResult format\n"); printf("\tResult display uses a common format for each command:\n"); printf("\tResults are formatted in text/JSON with\n"); @@ -2837,6 +2838,9 @@ static void cmdline(int argc, char **argv) int opt, force_cpus_online = 0; int option_index = 0; int ret; + int oob_mode = 0; + int poll_interval = -1; + int no_daemon = 0; static struct option long_options[] = { { "all-cpus-online", no_argument, 0, 'a' }, @@ -2849,6 +2853,9 @@ static void cmdline(int argc, char **argv) { "out", required_argument, 0, 'o' }, { "retry", required_argument, 0, 'r' }, { "version", no_argument, 0, 'v' }, + { "oob", no_argument, 0, 'b' }, + { "no-daemon", no_argument, 0, 'n' }, + { "poll-interval", required_argument, 0, 'w' }, { 0, 0, 0, 0 } }; @@ -2875,7 +2882,7 @@ static void cmdline(int argc, char **argv) } progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+c:df:hio:va", long_options, + while ((opt = getopt_long_only(argc, argv, "+c:df:hio:vabw:n", long_options, &option_index)) != -1) { switch (opt) { case 'a': @@ -2920,12 +2927,26 @@ static void cmdline(int argc, char **argv) case 'v': print_version(); break; + case 'b': + oob_mode = 1; + break; + case 'n': + no_daemon = 1; + break; + case 'w': + ret = strtol(optarg, &ptr, 10); + if (!ret) { + fprintf(stderr, "Invalid poll interval count\n"); + exit(0); + } + poll_interval = ret; + break; default: usage(); } } - if (optind > (argc - 2)) { + if (optind > (argc - 2) && !oob_mode) { usage(); exit(0); } @@ -2936,6 +2957,17 @@ static void cmdline(int argc, char **argv) set_cpu_present_cpu_mask(); set_cpu_target_cpu_mask(); + if (oob_mode) { + create_cpu_map(); + if (debug_flag) + fprintf(stderr, "OOB mode is enabled in debug mode\n"); + + ret = isst_daemon(debug_flag, poll_interval, no_daemon); + if (ret) + fprintf(stderr, "OOB mode enable failed\n"); + goto out; + } + if (!is_clx_n_platform()) { ret = isst_fill_platform_info(); if (ret) diff --git a/tools/power/x86/intel-speed-select/isst-daemon.c b/tools/power/x86/intel-speed-select/isst-daemon.c new file mode 100644 index 000000000000..dd372924bc82 --- /dev/null +++ b/tools/power/x86/intel-speed-select/isst-daemon.c @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select -- Allow speed select to daemonize + * Copyright (c) 2022 Intel Corporation. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdarg.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/file.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <errno.h> +#include <getopt.h> +#include <signal.h> +#include <time.h> + +#include "isst.h" + +static int per_package_levels_info[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE]; +static time_t per_package_levels_tm[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE]; + +static void init_levels(void) +{ + int i, j; + + for (i = 0; i < MAX_PACKAGE_COUNT; ++i) + for (j = 0; j < MAX_DIE_PER_PACKAGE; ++j) + per_package_levels_info[i][j] = -1; +} + +void process_level_change(int cpu) +{ + struct isst_pkg_ctdp_level_info ctdp_level; + int pkg_id = get_physical_package_id(cpu); + int die_id = get_physical_die_id(cpu); + struct isst_pkg_ctdp pkg_dev; + time_t tm; + int ret; + + if (pkg_id >= MAX_PACKAGE_COUNT || die_id > MAX_DIE_PER_PACKAGE) { + debug_printf("Invalid package/die info for cpu:%d\n", cpu); + return; + } + + tm = time(NULL); + if (tm - per_package_levels_tm[pkg_id][die_id] < 2 ) + return; + + per_package_levels_tm[pkg_id][die_id] = tm; + + ret = isst_get_ctdp_levels(cpu, &pkg_dev); + if (ret) { + debug_printf("Can't get tdp levels for cpu:%d\n", cpu); + return; + } + + debug_printf("Get Config level %d pkg:%d die:%d current_level:%d \n", cpu, + pkg_id, die_id, pkg_dev.current_level); + + if (pkg_dev.locked) { + debug_printf("config TDP s locked \n"); + return; + } + + if (per_package_levels_info[pkg_id][die_id] == pkg_dev.current_level) + return; + + debug_printf("**Config level change for cpu:%d pkg:%d die:%d from %d to %d\n", + cpu, pkg_id, die_id, per_package_levels_info[pkg_id][die_id], + pkg_dev.current_level); + + per_package_levels_info[pkg_id][die_id] = pkg_dev.current_level; + + ctdp_level.core_cpumask_size = + alloc_cpu_set(&ctdp_level.core_cpumask); + ret = isst_get_coremask_info(cpu, pkg_dev.current_level, &ctdp_level); + if (ret) { + free_cpu_set(ctdp_level.core_cpumask); + debug_printf("Can't get core_mask:%d\n", cpu); + return; + } + + if (ctdp_level.cpu_count) { + int i, max_cpus = get_topo_max_cpus(); + for (i = 0; i < max_cpus; ++i) { + if (pkg_id != get_physical_package_id(i) || die_id != get_physical_die_id(i)) + continue; + if (CPU_ISSET_S(i, ctdp_level.core_cpumask_size, ctdp_level.core_cpumask)) { + fprintf(stderr, "online cpu %d\n", i); + set_cpu_online_offline(i, 1); + } else { + fprintf(stderr, "offline cpu %d\n", i); + set_cpu_online_offline(i, 0); + } + } + } + + free_cpu_set(ctdp_level.core_cpumask); +} + +static void _poll_for_config_change(int cpu, void *arg1, void *arg2, + void *arg3, void *arg4) +{ + process_level_change(cpu); +} + +static void poll_for_config_change(void) +{ + for_each_online_package_in_set(_poll_for_config_change, NULL, NULL, + NULL, NULL); +} + +static int done = 0; +static int pid_file_handle; + +static void signal_handler(int sig) +{ + switch (sig) { + case SIGINT: + case SIGTERM: + done = 1; + hfi_exit(); + exit(0); + break; + default: + break; + } +} + +static void daemonize(char *rundir, char *pidfile) +{ + int pid, sid, i; + char str[10]; + struct sigaction sig_actions; + sigset_t sig_set; + int ret; + + if (getppid() == 1) + return; + + sigemptyset(&sig_set); + sigaddset(&sig_set, SIGCHLD); + sigaddset(&sig_set, SIGTSTP); + sigaddset(&sig_set, SIGTTOU); + sigaddset(&sig_set, SIGTTIN); + sigprocmask(SIG_BLOCK, &sig_set, NULL); + + sig_actions.sa_handler = signal_handler; + sigemptyset(&sig_actions.sa_mask); + sig_actions.sa_flags = 0; + + sigaction(SIGHUP, &sig_actions, NULL); + sigaction(SIGTERM, &sig_actions, NULL); + sigaction(SIGINT, &sig_actions, NULL); + + pid = fork(); + if (pid < 0) { + /* Could not fork */ + exit(EXIT_FAILURE); + } + if (pid > 0) + exit(EXIT_SUCCESS); + + umask(027); + + sid = setsid(); + if (sid < 0) + exit(EXIT_FAILURE); + + /* close all descriptors */ + for (i = getdtablesize(); i >= 0; --i) + close(i); + + i = open("/dev/null", O_RDWR); + ret = dup(i); + if (ret == -1) + exit(EXIT_FAILURE); + + ret = dup(i); + if (ret == -1) + exit(EXIT_FAILURE); + + ret = chdir(rundir); + if (ret == -1) + exit(EXIT_FAILURE); + + pid_file_handle = open(pidfile, O_RDWR | O_CREAT, 0600); + if (pid_file_handle == -1) { + /* Couldn't open lock file */ + exit(1); + } + /* Try to lock file */ +#ifdef LOCKF_SUPPORT + if (lockf(pid_file_handle, F_TLOCK, 0) == -1) { +#else + if (flock(pid_file_handle, LOCK_EX|LOCK_NB) < 0) { +#endif + /* Couldn't get lock on lock file */ + fprintf(stderr, "Couldn't get lock file %d\n", getpid()); + exit(1); + } + snprintf(str, sizeof(str), "%d\n", getpid()); + ret = write(pid_file_handle, str, strlen(str)); + if (ret == -1) + exit(EXIT_FAILURE); + + close(i); +} + +int isst_daemon(int debug_mode, int poll_interval, int no_daemon) +{ + int ret; + + if (!no_daemon && poll_interval < 0 && !debug_mode) { + fprintf(stderr, "OOB mode is enabled and will run as daemon\n"); + daemonize((char *) "/tmp/", + (char *)"/tmp/hfi-events.pid"); + } else { + signal(SIGINT, signal_handler); + } + + init_levels(); + + if (poll_interval < 0) { + ret = hfi_main(); + if (ret) { + fprintf(stderr, "HFI initialization failed\n"); + } + fprintf(stderr, "Must specify poll-interval\n"); + return ret; + } + + debug_printf("Starting loop\n"); + while (!done) { + sleep(poll_interval); + poll_for_config_change(); + } + + return 0; +} diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h index 1aa15d5ea57c..0796d8c6a882 100644 --- a/tools/power/x86/intel-speed-select/isst.h +++ b/tools/power/x86/intel-speed-select/isst.h @@ -76,6 +76,9 @@ #define DISP_FREQ_MULTIPLIER 100 +#define MAX_PACKAGE_COUNT 8 +#define MAX_DIE_PER_PACKAGE 2 + struct isst_clos_config { int pkg_id; int die_id; @@ -260,4 +263,14 @@ extern int is_skx_based_platform(void); extern int is_spr_platform(void); extern int is_icx_platform(void); extern void isst_trl_display_information(int cpu, FILE *outf, unsigned long long trl); + +extern void set_cpu_online_offline(int cpu, int state); +extern void for_each_online_package_in_set(void (*callback)(int, void *, void *, + void *, void *), + void *arg1, void *arg2, void *arg3, + void *arg4); +extern int isst_daemon(int debug_mode, int poll_interval, int no_daemon); +extern void process_level_change(int cpu); +extern int hfi_main(void); +extern void hfi_exit(void); #endif diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py index e15e20696d17..b46e9eb8f5aa 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -63,7 +63,7 @@ C_USEC = 3 C_SEC = 2 C_CPU = 1 -global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname +global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname, trace_file # 11 digits covers uptime to 115 days getcontext().prec = 11 @@ -72,17 +72,17 @@ sample_num =0 last_sec_cpu = [0] * MAX_CPUS last_usec_cpu = [0] * MAX_CPUS -def print_help(): - print('intel_pstate_tracer.py:') +def print_help(driver_name): + print('%s_tracer.py:'%driver_name) print(' Usage:') print(' If the trace file is available, then to simply parse and plot, use (sudo not required):') - print(' ./intel_pstate_tracer.py [-c cpus] -t <trace_file> -n <test_name>') + print(' ./%s_tracer.py [-c cpus] -t <trace_file> -n <test_name>'%driver_name) print(' Or') - print(' ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>') + print(' ./%s_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>'%driver_name) print(' To generate trace file, parse and plot, use (sudo required):') - print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>') + print(' sudo ./%s_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>'%driver_name) print(' Or') - print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>') + print(' sudo ./%s_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>'%driver_name) print(' Optional argument:') print(' cpus: comma separated list of CPUs') print(' kbytes: Kilo bytes of memory per CPU to allocate to the trace buffer. Default: 10240') @@ -323,7 +323,7 @@ def set_4_plot_linestyles(g_plot): g_plot('set style line 3 linetype 1 linecolor rgb "purple" pointtype -1') g_plot('set style line 4 linetype 1 linecolor rgb "blue" pointtype -1') -def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz): +def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz, cpu_mask): """ Store master csv file information """ global graph_data_present @@ -342,11 +342,9 @@ def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _t graph_data_present = True; -def split_csv(): +def split_csv(current_max_cpu, cpu_mask): """ seperate the all csv file into per CPU csv files. """ - global current_max_cpu - if os.path.exists('cpu.csv'): for index in range(0, current_max_cpu + 1): if cpu_mask[int(index)] != 0: @@ -381,27 +379,25 @@ def clear_trace_file(): print('IO error clearing trace file ') sys.exit(2) -def enable_trace(): +def enable_trace(trace_file): """ Enable trace """ try: - open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable' - , 'w').write("1") + open(trace_file,'w').write("1") except: print('IO error enabling trace ') sys.exit(2) -def disable_trace(): +def disable_trace(trace_file): """ Disable trace """ try: - open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable' - , 'w').write("0") + open(trace_file, 'w').write("0") except: print('IO error disabling trace ') sys.exit(2) -def set_trace_buffer_size(): +def set_trace_buffer_size(memory): """ Set trace buffer size """ try: @@ -421,7 +417,7 @@ def free_trace_buffer(): print('IO error freeing trace buffer ') sys.exit(2) -def read_trace_data(filename): +def read_trace_data(filename, cpu_mask): """ Read and parse trace data """ global current_max_cpu @@ -481,135 +477,137 @@ def read_trace_data(filename): tsc_ghz = Decimal(0) if duration_ms != Decimal(0) : tsc_ghz = Decimal(tsc)/duration_ms/Decimal(1000000) - store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz) + store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz, cpu_mask) if cpu_int > current_max_cpu: current_max_cpu = cpu_int # End of for each trace line loop # Now seperate the main overall csv file into per CPU csv files. - split_csv() + split_csv(current_max_cpu, cpu_mask) def signal_handler(signal, frame): print(' SIGINT: Forcing cleanup before exit.') if interval: - disable_trace() + disable_trace(trace_file) clear_trace_file() # Free the memory free_trace_buffer() sys.exit(0) -signal.signal(signal.SIGINT, signal_handler) +if __name__ == "__main__": + trace_file = "/sys/kernel/debug/tracing/events/power/pstate_sample/enable" + signal.signal(signal.SIGINT, signal_handler) -interval = "" -filename = "" -cpu_list = "" -testname = "" -memory = "10240" -graph_data_present = False; + interval = "" + filename = "" + cpu_list = "" + testname = "" + memory = "10240" + graph_data_present = False; -valid1 = False -valid2 = False + valid1 = False + valid2 = False -cpu_mask = zeros((MAX_CPUS,), dtype=int) + cpu_mask = zeros((MAX_CPUS,), dtype=int) -try: - opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="]) -except getopt.GetoptError: - print_help() - sys.exit(2) -for opt, arg in opts: - if opt == '-h': - print() + try: + opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="]) + except getopt.GetoptError: + print_help('intel_pstate') + sys.exit(2) + for opt, arg in opts: + if opt == '-h': + print_help('intel_pstate') + sys.exit() + elif opt in ("-t", "--trace_file"): + valid1 = True + location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) + filename = os.path.join(location, arg) + elif opt in ("-i", "--interval"): + valid1 = True + interval = arg + elif opt in ("-c", "--cpu"): + cpu_list = arg + elif opt in ("-n", "--name"): + valid2 = True + testname = arg + elif opt in ("-m", "--memory"): + memory = arg + + if not (valid1 and valid2): + print_help('intel_pstate') sys.exit() - elif opt in ("-t", "--trace_file"): - valid1 = True - location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) - filename = os.path.join(location, arg) - elif opt in ("-i", "--interval"): - valid1 = True - interval = arg - elif opt in ("-c", "--cpu"): - cpu_list = arg - elif opt in ("-n", "--name"): - valid2 = True - testname = arg - elif opt in ("-m", "--memory"): - memory = arg - -if not (valid1 and valid2): - print_help() - sys.exit() - -if cpu_list: - for p in re.split("[,]", cpu_list): - if int(p) < MAX_CPUS : - cpu_mask[int(p)] = 1 -else: - for i in range (0, MAX_CPUS): - cpu_mask[i] = 1 - -if not os.path.exists('results'): - os.mkdir('results') + + if cpu_list: + for p in re.split("[,]", cpu_list): + if int(p) < MAX_CPUS : + cpu_mask[int(p)] = 1 + else: + for i in range (0, MAX_CPUS): + cpu_mask[i] = 1 + + if not os.path.exists('results'): + os.mkdir('results') + # The regular user needs to own the directory, not root. + fix_ownership('results') + + os.chdir('results') + if os.path.exists(testname): + print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') + sys.exit() + os.mkdir(testname) # The regular user needs to own the directory, not root. - fix_ownership('results') - -os.chdir('results') -if os.path.exists(testname): - print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') - sys.exit() -os.mkdir(testname) -# The regular user needs to own the directory, not root. -fix_ownership(testname) -os.chdir(testname) - -# Temporary (or perhaps not) -cur_version = sys.version_info -print('python version (should be >= 2.7):') -print(cur_version) - -# Left as "cleanup" for potential future re-run ability. -cleanup_data_files() - -if interval: - filename = "/sys/kernel/debug/tracing/trace" - clear_trace_file() - set_trace_buffer_size() - enable_trace() - print('Sleeping for ', interval, 'seconds') - time.sleep(int(interval)) - disable_trace() - -current_max_cpu = 0 - -read_trace_data(filename) - -if interval: - clear_trace_file() - # Free the memory - free_trace_buffer() - -if graph_data_present == False: - print('No valid data to plot') - sys.exit(2) - -for cpu_no in range(0, current_max_cpu + 1): - plot_perf_busy_with_sample(cpu_no) - plot_perf_busy(cpu_no) - plot_durations(cpu_no) - plot_loads(cpu_no) - -plot_pstate_cpu_with_sample() -plot_pstate_cpu() -plot_load_cpu() -plot_frequency_cpu() -plot_duration_cpu() -plot_scaled_cpu() -plot_boost_cpu() -plot_ghz_cpu() - -# It is preferrable, but not necessary, that the regular user owns the files, not root. -for root, dirs, files in os.walk('.'): - for f in files: - fix_ownership(f) - -os.chdir('../../') + fix_ownership(testname) + os.chdir(testname) + + # Temporary (or perhaps not) + cur_version = sys.version_info + print('python version (should be >= 2.7):') + print(cur_version) + + # Left as "cleanup" for potential future re-run ability. + cleanup_data_files() + + if interval: + filename = "/sys/kernel/debug/tracing/trace" + clear_trace_file() + set_trace_buffer_size(memory) + enable_trace(trace_file) + print('Sleeping for ', interval, 'seconds') + time.sleep(int(interval)) + disable_trace(trace_file) + + current_max_cpu = 0 + + read_trace_data(filename, cpu_mask) + + if interval: + clear_trace_file() + # Free the memory + free_trace_buffer() + + if graph_data_present == False: + print('No valid data to plot') + sys.exit(2) + + for cpu_no in range(0, current_max_cpu + 1): + plot_perf_busy_with_sample(cpu_no) + plot_perf_busy(cpu_no) + plot_durations(cpu_no) + plot_loads(cpu_no) + + plot_pstate_cpu_with_sample() + plot_pstate_cpu() + plot_load_cpu() + plot_frequency_cpu() + plot_duration_cpu() + plot_scaled_cpu() + plot_boost_cpu() + plot_ghz_cpu() + + # It is preferrable, but not necessary, that the regular user owns the files, not root. + for root, dirs, files in os.walk('.'): + for f in files: + fix_ownership(f) + + os.chdir('../../') diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 47d3ba895d6d..bc5ae0872fed 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2323,7 +2323,7 @@ int skx_pkg_cstate_limits[16] = }; int icx_pkg_cstate_limits[16] = - { PCL__0, PCL__2, PCL__6, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, + { PCL__0, PCL__2, PCL__6, PCL__6, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV }; diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index b0be5f40a3f1..79d102304470 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -90,7 +90,7 @@ EXTRA_WARNINGS += -Wstrict-aliasing=3 else ifneq ($(CROSS_COMPILE),) CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) -GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc)) +GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null)) ifneq ($(GCC_TOOLCHAIN_DIR),) CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot) diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 7a706f96f68d..9274c6355809 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -17,7 +17,7 @@ assert sys.version_info >= (3, 7), "Python version is too old" from dataclasses import dataclass from enum import Enum, auto -from typing import Any, Iterable, Sequence, List, Optional +from typing import Iterable, List, Optional, Sequence, Tuple import kunit_json import kunit_kernel @@ -32,7 +32,6 @@ class KunitStatus(Enum): @dataclass class KunitResult: status: KunitStatus - result: Any elapsed_time: float @dataclass @@ -82,10 +81,8 @@ def config_tests(linux: kunit_kernel.LinuxSourceTree, config_end = time.time() if not success: return KunitResult(KunitStatus.CONFIG_FAILURE, - 'could not configure kernel', config_end - config_start) return KunitResult(KunitStatus.SUCCESS, - 'configured kernel successfully', config_end - config_start) def build_tests(linux: kunit_kernel.LinuxSourceTree, @@ -100,14 +97,11 @@ def build_tests(linux: kunit_kernel.LinuxSourceTree, build_end = time.time() if not success: return KunitResult(KunitStatus.BUILD_FAILURE, - 'could not build kernel', build_end - build_start) if not success: return KunitResult(KunitStatus.BUILD_FAILURE, - 'could not build kernel', build_end - build_start) return KunitResult(KunitStatus.SUCCESS, - 'built kernel successfully', build_end - build_start) def config_and_build_tests(linux: kunit_kernel.LinuxSourceTree, @@ -173,14 +167,14 @@ def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) - filter_glob=filter_glob, build_dir=request.build_dir) - result = parse_tests(request, run_result) + _, test_result = parse_tests(request, run_result) # run_kernel() doesn't block on the kernel exiting. # That only happens after we get the last line of output from `run_result`. # So exec_time here actually contains parsing + execution time, which is fine. test_end = time.time() exec_time += test_end - test_start - test_counts.add_subtest_counts(result.result.counts) + test_counts.add_subtest_counts(test_result.counts) if len(filter_globs) == 1 and test_counts.crashed > 0: bd = request.build_dir @@ -189,7 +183,7 @@ def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) - bd, bd, kunit_kernel.get_outfile_path(bd), bd, sys.argv[0])) kunit_status = _map_to_overall_status(test_counts.get_status()) - return KunitResult(status=kunit_status, result=result, elapsed_time=exec_time) + return KunitResult(status=kunit_status, elapsed_time=exec_time) def _map_to_overall_status(test_status: kunit_parser.TestStatus) -> KunitStatus: if test_status in (kunit_parser.TestStatus.SUCCESS, kunit_parser.TestStatus.SKIPPED): @@ -197,7 +191,7 @@ def _map_to_overall_status(test_status: kunit_parser.TestStatus) -> KunitStatus: else: return KunitStatus.TEST_FAILURE -def parse_tests(request: KunitParseRequest, input_data: Iterable[str]) -> KunitResult: +def parse_tests(request: KunitParseRequest, input_data: Iterable[str]) -> Tuple[KunitResult, kunit_parser.Test]: parse_start = time.time() test_result = kunit_parser.Test() @@ -231,11 +225,9 @@ def parse_tests(request: KunitParseRequest, input_data: Iterable[str]) -> KunitR print(json_obj) if test_result.status != kunit_parser.TestStatus.SUCCESS: - return KunitResult(KunitStatus.TEST_FAILURE, test_result, - parse_end - parse_start) + return KunitResult(KunitStatus.TEST_FAILURE, parse_end - parse_start), test_result - return KunitResult(KunitStatus.SUCCESS, test_result, - parse_end - parse_start) + return KunitResult(KunitStatus.SUCCESS, parse_end - parse_start), test_result def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: @@ -513,7 +505,7 @@ def main(argv, linux=None): request = KunitParseRequest(raw_output=cli_args.raw_output, build_dir='', json=cli_args.json) - result = parse_tests(request, kunit_output) + result, _ = parse_tests(request, kunit_output) if result.status != KunitStatus.SUCCESS: sys.exit(1) else: diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 44bbe54f25f1..3c4196cef3ed 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,6 +6,7 @@ # Author: Felix Guo <felixguoxiuping@gmail.com> # Author: Brendan Higgins <brendanhiggins@google.com> +import importlib.abc import importlib.util import logging import subprocess diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py index 4f32133ed77c..13d854afca9d 100755 --- a/tools/testing/kunit/run_checks.py +++ b/tools/testing/kunit/run_checks.py @@ -61,7 +61,7 @@ def main(argv: Sequence[str]) -> None: elif isinstance(ex, subprocess.CalledProcessError): print(f'{name}: FAILED') else: - print('{name}: unexpected exception: {ex}') + print(f'{name}: unexpected exception: {ex}') continue output = ex.output diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore index 055a5019b13c..cb24124ac5b9 100644 --- a/tools/testing/selftests/.gitignore +++ b/tools/testing/selftests/.gitignore @@ -3,6 +3,7 @@ gpiogpio-event-mon gpiogpio-hammer gpioinclude/ gpiolsgpio +kselftest_install/ tpm2/SpaceTest.log # Python bytecode and cache diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index d08fe4cfe811..2319ec87f53d 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -114,23 +114,35 @@ ifdef building_out_of_srctree override LDFLAGS = endif -ifneq ($(O),) - BUILD := $(O)/kselftest +top_srcdir ?= ../../.. + +ifeq ("$(origin O)", "command line") + KBUILD_OUTPUT := $(O) +endif + +ifneq ($(KBUILD_OUTPUT),) + # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot + # expand a shell special character '~'. We use a somewhat tedious way here. + abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) + $(if $(abs_objtree),, \ + $(error failed to create output directory "$(KBUILD_OUTPUT)")) + # $(realpath ...) resolves symlinks + abs_objtree := $(realpath $(abs_objtree)) + BUILD := $(abs_objtree)/kselftest + KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include else - ifneq ($(KBUILD_OUTPUT),) - BUILD := $(KBUILD_OUTPUT)/kselftest - else - BUILD := $(shell pwd) - DEFAULT_INSTALL_HDR_PATH := 1 - endif + BUILD := $(CURDIR) + abs_srctree := $(shell cd $(top_srcdir) && pwd) + KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include + DEFAULT_INSTALL_HDR_PATH := 1 endif # Prepare for headers install -top_srcdir ?= ../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) export KSFT_KHDR_INSTALL_DONE := 1 export BUILD +export KHDR_INCLUDES # set default goal to all, so make without a target runs all, even when # all isn't the first target in the file. @@ -155,7 +167,7 @@ khdr: ifeq (1,$(DEFAULT_INSTALL_HDR_PATH)) $(MAKE) --no-builtin-rules ARCH=$(ARCH) -C $(top_srcdir) headers_install else - $(MAKE) --no-builtin-rules INSTALL_HDR_PATH=$$BUILD/usr \ + $(MAKE) --no-builtin-rules INSTALL_HDR_PATH=$(abs_objtree)/usr \ ARCH=$(ARCH) -C $(top_srcdir) headers_install endif @@ -165,6 +177,7 @@ all: khdr BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \ + O=$(abs_objtree) \ $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; @@ -172,7 +185,8 @@ all: khdr run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests \ + O=$(abs_objtree); \ done; hotplug: @@ -223,6 +237,7 @@ ifdef INSTALL_PATH for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \ + O=$(abs_objtree) \ $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index 17f158d7a767..eb2213540fe3 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -3,7 +3,7 @@ // kselftest for the ALSA mixer API // // Original author: Mark Brown <broonie@kernel.org> -// Copyright (c) 2021 Arm Limited +// Copyright (c) 2021-2 Arm Limited // This test will iterate over all cards detected in the system, exercising // every mixer control it can find. This may conflict with other system @@ -13,6 +13,7 @@ #include <stdio.h> #include <stdlib.h> #include <stdbool.h> +#include <limits.h> #include <string.h> #include <getopt.h> #include <stdarg.h> @@ -26,11 +27,12 @@ #include "../kselftest.h" -#define TESTS_PER_CONTROL 3 +#define TESTS_PER_CONTROL 6 struct card_data { snd_ctl_t *handle; int card; + struct pollfd pollfd; int num_ctls; snd_ctl_elem_list_t *ctls; struct card_data *next; @@ -42,6 +44,8 @@ struct ctl_data { snd_ctl_elem_info_t *info; snd_ctl_elem_value_t *def_val; int elem; + int event_missing; + int event_spurious; struct card_data *card; struct ctl_data *next; }; @@ -67,7 +71,8 @@ struct ctl_data *ctl_list = NULL; #endif #ifndef LIB_HAS_LOAD_STRING -int snd_config_load_string(snd_config_t **config, const char *s, size_t size) +static int snd_config_load_string(snd_config_t **config, const char *s, + size_t size) { snd_input_t *input; snd_config_t *dst; @@ -95,7 +100,7 @@ int snd_config_load_string(snd_config_t **config, const char *s, size_t size) } #endif -void find_controls(void) +static void find_controls(void) { char name[32]; int card, ctl, err; @@ -148,6 +153,7 @@ void find_controls(void) if (!ctl_data) ksft_exit_fail_msg("Out of memory\n"); + memset(ctl_data, 0, sizeof(*ctl_data)); ctl_data->card = card_data; ctl_data->elem = ctl; ctl_data->name = snd_ctl_elem_list_get_name(card_data->ctls, @@ -183,6 +189,26 @@ void find_controls(void) ctl_list = ctl_data; } + /* Set up for events */ + err = snd_ctl_subscribe_events(card_data->handle, true); + if (err < 0) { + ksft_exit_fail_msg("snd_ctl_subscribe_events() failed for card %d: %d\n", + card, err); + } + + err = snd_ctl_poll_descriptors_count(card_data->handle); + if (err != 1) { + ksft_exit_fail_msg("Unexpected descriptor count %d for card %d\n", + err, card); + } + + err = snd_ctl_poll_descriptors(card_data->handle, + &card_data->pollfd, 1); + if (err != 1) { + ksft_exit_fail_msg("snd_ctl_poll_descriptors() failed for %d\n", + card, err); + } + next_card: if (snd_card_next(&card) < 0) { ksft_print_msg("snd_card_next"); @@ -193,8 +219,82 @@ void find_controls(void) snd_config_delete(config); } -bool ctl_value_index_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val, - int index) +/* + * Block for up to timeout ms for an event, returns a negative value + * on error, 0 for no event and 1 for an event. + */ +static int wait_for_event(struct ctl_data *ctl, int timeout) +{ + unsigned short revents; + snd_ctl_event_t *event; + int count, err; + unsigned int mask = 0; + unsigned int ev_id; + + snd_ctl_event_alloca(&event); + + do { + err = poll(&(ctl->card->pollfd), 1, timeout); + if (err < 0) { + ksft_print_msg("poll() failed for %s: %s (%d)\n", + ctl->name, strerror(errno), errno); + return -1; + } + /* Timeout */ + if (err == 0) + return 0; + + err = snd_ctl_poll_descriptors_revents(ctl->card->handle, + &(ctl->card->pollfd), + 1, &revents); + if (err < 0) { + ksft_print_msg("snd_ctl_poll_descriptors_revents() failed for %s: %d\n", + ctl->name, err); + return err; + } + if (revents & POLLERR) { + ksft_print_msg("snd_ctl_poll_descriptors_revents() reported POLLERR for %s\n", + ctl->name); + return -1; + } + /* No read events */ + if (!(revents & POLLIN)) { + ksft_print_msg("No POLLIN\n"); + continue; + } + + err = snd_ctl_read(ctl->card->handle, event); + if (err < 0) { + ksft_print_msg("snd_ctl_read() failed for %s: %d\n", + ctl->name, err); + return err; + } + + if (snd_ctl_event_get_type(event) != SND_CTL_EVENT_ELEM) + continue; + + /* The ID returned from the event is 1 less than numid */ + mask = snd_ctl_event_elem_get_mask(event); + ev_id = snd_ctl_event_elem_get_numid(event); + if (ev_id != snd_ctl_elem_info_get_numid(ctl->info)) { + ksft_print_msg("Event for unexpected ctl %s\n", + snd_ctl_event_elem_get_name(event)); + continue; + } + + if ((mask & SND_CTL_EVENT_MASK_REMOVE) == SND_CTL_EVENT_MASK_REMOVE) { + ksft_print_msg("Removal event for %s\n", + ctl->name); + return -1; + } + } while ((mask & SND_CTL_EVENT_MASK_VALUE) != SND_CTL_EVENT_MASK_VALUE); + + return 1; +} + +static bool ctl_value_index_valid(struct ctl_data *ctl, + snd_ctl_elem_value_t *val, + int index) { long int_val; long long int64_val; @@ -305,7 +405,7 @@ bool ctl_value_index_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val, * Check that the provided value meets the constraints for the * provided control. */ -bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val) +static bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val) { int i; bool valid = true; @@ -321,7 +421,7 @@ bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val) * Check that we can read the default value and it is valid. Write * tests use the read value to restore the default. */ -void test_ctl_get_value(struct ctl_data *ctl) +static void test_ctl_get_value(struct ctl_data *ctl) { int err; @@ -356,9 +456,9 @@ out: ctl->card->card, ctl->elem); } -bool show_mismatch(struct ctl_data *ctl, int index, - snd_ctl_elem_value_t *read_val, - snd_ctl_elem_value_t *expected_val) +static bool show_mismatch(struct ctl_data *ctl, int index, + snd_ctl_elem_value_t *read_val, + snd_ctl_elem_value_t *expected_val) { long long expected_int, read_int; @@ -421,13 +521,14 @@ bool show_mismatch(struct ctl_data *ctl, int index, * the write to fail, for verifying that invalid writes don't corrupt * anything. */ -int write_and_verify(struct ctl_data *ctl, - snd_ctl_elem_value_t *write_val, - snd_ctl_elem_value_t *expected_val) +static int write_and_verify(struct ctl_data *ctl, + snd_ctl_elem_value_t *write_val, + snd_ctl_elem_value_t *expected_val) { int err, i; bool error_expected, mismatch_shown; - snd_ctl_elem_value_t *read_val, *w_val; + snd_ctl_elem_value_t *initial_val, *read_val, *w_val; + snd_ctl_elem_value_alloca(&initial_val); snd_ctl_elem_value_alloca(&read_val); snd_ctl_elem_value_alloca(&w_val); @@ -445,6 +546,18 @@ int write_and_verify(struct ctl_data *ctl, snd_ctl_elem_value_copy(expected_val, write_val); } + /* Store the value before we write */ + if (snd_ctl_elem_info_is_readable(ctl->info)) { + snd_ctl_elem_value_set_id(initial_val, ctl->id); + + err = snd_ctl_elem_read(ctl->card->handle, initial_val); + if (err < 0) { + ksft_print_msg("snd_ctl_elem_read() failed: %s\n", + snd_strerror(err)); + return err; + } + } + /* * Do the write, if we have an expected value ignore the error * and carry on to validate the expected value. @@ -470,6 +583,30 @@ int write_and_verify(struct ctl_data *ctl, } /* + * Check for an event if the value changed, or confirm that + * there was none if it didn't. We rely on the kernel + * generating the notification before it returns from the + * write, this is currently true, should that ever change this + * will most likely break and need updating. + */ + if (!snd_ctl_elem_info_is_volatile(ctl->info)) { + err = wait_for_event(ctl, 0); + if (snd_ctl_elem_value_compare(initial_val, read_val)) { + if (err < 1) { + ksft_print_msg("No event generated for %s\n", + ctl->name); + ctl->event_missing++; + } + } else { + if (err != 0) { + ksft_print_msg("Spurious event generated for %s\n", + ctl->name); + ctl->event_spurious++; + } + } + } + + /* * Use the libray to compare values, if there's a mismatch * carry on and try to provide a more useful diagnostic than * just "mismatch". @@ -493,7 +630,7 @@ int write_and_verify(struct ctl_data *ctl, * Make sure we can write the default value back to the control, this * should validate that at least some write works. */ -void test_ctl_write_default(struct ctl_data *ctl) +static void test_ctl_write_default(struct ctl_data *ctl) { int err; @@ -526,7 +663,7 @@ void test_ctl_write_default(struct ctl_data *ctl) ctl->card->card, ctl->elem); } -bool test_ctl_write_valid_boolean(struct ctl_data *ctl) +static bool test_ctl_write_valid_boolean(struct ctl_data *ctl) { int err, i, j; bool fail = false; @@ -547,7 +684,7 @@ bool test_ctl_write_valid_boolean(struct ctl_data *ctl) return !fail; } -bool test_ctl_write_valid_integer(struct ctl_data *ctl) +static bool test_ctl_write_valid_integer(struct ctl_data *ctl) { int err; int i; @@ -577,7 +714,7 @@ bool test_ctl_write_valid_integer(struct ctl_data *ctl) return !fail; } -bool test_ctl_write_valid_integer64(struct ctl_data *ctl) +static bool test_ctl_write_valid_integer64(struct ctl_data *ctl) { int err, i; long long j, step; @@ -605,7 +742,7 @@ bool test_ctl_write_valid_integer64(struct ctl_data *ctl) return !fail; } -bool test_ctl_write_valid_enumerated(struct ctl_data *ctl) +static bool test_ctl_write_valid_enumerated(struct ctl_data *ctl) { int err, i, j; bool fail = false; @@ -626,7 +763,7 @@ bool test_ctl_write_valid_enumerated(struct ctl_data *ctl) return !fail; } -void test_ctl_write_valid(struct ctl_data *ctl) +static void test_ctl_write_valid(struct ctl_data *ctl) { bool pass; int err; @@ -679,6 +816,236 @@ void test_ctl_write_valid(struct ctl_data *ctl) ctl->card->card, ctl->elem); } +static bool test_ctl_write_invalid_value(struct ctl_data *ctl, + snd_ctl_elem_value_t *val) +{ + int err; + long val_read; + + /* Ideally this will fail... */ + err = snd_ctl_elem_write(ctl->card->handle, val); + if (err < 0) + return false; + + /* ...but some devices will clamp to an in range value */ + err = snd_ctl_elem_read(ctl->card->handle, val); + if (err < 0) { + ksft_print_msg("%s failed to read: %s\n", + ctl->name, snd_strerror(err)); + return true; + } + + return !ctl_value_valid(ctl, val); +} + +static bool test_ctl_write_invalid_boolean(struct ctl_data *ctl) +{ + int err, i; + long val_read; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_boolean(val, i, 2); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + + return !fail; +} + +static bool test_ctl_write_invalid_integer(struct ctl_data *ctl) +{ + int i; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + if (snd_ctl_elem_info_get_min(ctl->info) != LONG_MIN) { + /* Just under range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, + snd_ctl_elem_info_get_min(ctl->info) - 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Minimum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, LONG_MIN); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + + if (snd_ctl_elem_info_get_max(ctl->info) != LONG_MAX) { + /* Just over range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, + snd_ctl_elem_info_get_max(ctl->info) + 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Maximum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, LONG_MAX); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + } + + return !fail; +} + +static bool test_ctl_write_invalid_integer64(struct ctl_data *ctl) +{ + int i; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + if (snd_ctl_elem_info_get_min64(ctl->info) != LLONG_MIN) { + /* Just under range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, + snd_ctl_elem_info_get_min64(ctl->info) - 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Minimum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, LLONG_MIN); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + + if (snd_ctl_elem_info_get_max64(ctl->info) != LLONG_MAX) { + /* Just over range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, + snd_ctl_elem_info_get_max64(ctl->info) + 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Maximum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, LLONG_MAX); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + } + + return !fail; +} + +static bool test_ctl_write_invalid_enumerated(struct ctl_data *ctl) +{ + int err, i; + unsigned int val_read; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + snd_ctl_elem_value_set_id(val, ctl->id); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + /* One beyond maximum */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_enumerated(val, i, + snd_ctl_elem_info_get_items(ctl->info)); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Maximum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_enumerated(val, i, UINT_MAX); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + } + + return !fail; +} + + +static void test_ctl_write_invalid(struct ctl_data *ctl) +{ + bool pass; + int err; + + /* If the control is turned off let's be polite */ + if (snd_ctl_elem_info_is_inactive(ctl->info)) { + ksft_print_msg("%s is inactive\n", ctl->name); + ksft_test_result_skip("write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + if (!snd_ctl_elem_info_is_writable(ctl->info)) { + ksft_print_msg("%s is not writeable\n", ctl->name); + ksft_test_result_skip("write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + switch (snd_ctl_elem_info_get_type(ctl->info)) { + case SND_CTL_ELEM_TYPE_BOOLEAN: + pass = test_ctl_write_invalid_boolean(ctl); + break; + + case SND_CTL_ELEM_TYPE_INTEGER: + pass = test_ctl_write_invalid_integer(ctl); + break; + + case SND_CTL_ELEM_TYPE_INTEGER64: + pass = test_ctl_write_invalid_integer64(ctl); + break; + + case SND_CTL_ELEM_TYPE_ENUMERATED: + pass = test_ctl_write_invalid_enumerated(ctl); + break; + + default: + /* No tests for this yet */ + ksft_test_result_skip("write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + /* Restore the default value to minimise disruption */ + err = write_and_verify(ctl, ctl->def_val, NULL); + if (err < 0) + pass = false; + + ksft_test_result(pass, "write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); +} + +static void test_ctl_event_missing(struct ctl_data *ctl) +{ + ksft_test_result(!ctl->event_missing, "event_missing.%d.%d\n", + ctl->card->card, ctl->elem); +} + +static void test_ctl_event_spurious(struct ctl_data *ctl) +{ + ksft_test_result(!ctl->event_spurious, "event_spurious.%d.%d\n", + ctl->card->card, ctl->elem); +} + int main(void) { struct ctl_data *ctl; @@ -697,6 +1064,9 @@ int main(void) test_ctl_get_value(ctl); test_ctl_write_default(ctl); test_ctl_write_valid(ctl); + test_ctl_write_invalid(ctl); + test_ctl_event_missing(ctl); + test_ctl_event_spurious(ctl); } ksft_exit_pass(); diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c index d8eeeafb50dc..1e13b7523918 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi.c +++ b/tools/testing/selftests/arm64/abi/syscall-abi.c @@ -18,7 +18,6 @@ #include "../../kselftest.h" -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) #define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1) extern void do_syscall(int sve_vl); diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index a3c1e67441f9..4c418b2021e0 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -21,8 +21,6 @@ #include "../../kselftest.h" -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) - /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ #ifndef NT_ARM_SVE #define NT_ARM_SVE 0x405 @@ -489,6 +487,8 @@ static int do_parent(pid_t child) unsigned int vq, vl; bool vl_supported; + ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); + /* Attach to the child */ while (1) { int sig; diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c index a876db1f096a..325bca0de0f6 100644 --- a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c +++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c @@ -19,17 +19,6 @@ #include "kselftest.h" #include "mte_common_util.h" -#define PR_SET_TAGGED_ADDR_CTRL 55 -#define PR_GET_TAGGED_ADDR_CTRL 56 -# define PR_TAGGED_ADDR_ENABLE (1UL << 0) -# define PR_MTE_TCF_SHIFT 1 -# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TAG_SHIFT 3 -# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) - #include "mte_def.h" #define NUM_ITERATIONS 1024 diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c index 1de7a0abd0ae..f4ae5f87a3b7 100644 --- a/tools/testing/selftests/arm64/mte/check_user_mem.c +++ b/tools/testing/selftests/arm64/mte/check_user_mem.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE +#include <assert.h> #include <errno.h> #include <fcntl.h> #include <signal.h> @@ -11,6 +12,7 @@ #include <string.h> #include <ucontext.h> #include <unistd.h> +#include <sys/uio.h> #include <sys/mman.h> #include "kselftest.h" @@ -19,14 +21,28 @@ static size_t page_sz; -static int check_usermem_access_fault(int mem_type, int mode, int mapping) +#define TEST_NAME_MAX 100 + +enum test_type { + READ_TEST, + WRITE_TEST, + READV_TEST, + WRITEV_TEST, + LAST_TEST, +}; + +static int check_usermem_access_fault(int mem_type, int mode, int mapping, + int tag_offset, int tag_len, + enum test_type test_type) { int fd, i, err; char val = 'A'; - size_t len, read_len; + ssize_t len, syscall_len; void *ptr, *ptr_next; + int fileoff, ptroff, size; + int sizes[] = {1, 2, 3, 8, 16, 32, 4096, page_sz}; - err = KSFT_FAIL; + err = KSFT_PASS; len = 2 * page_sz; mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); fd = create_temp_file(); @@ -43,9 +59,9 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping) } mte_initialize_current_context(mode, (uintptr_t)ptr, len); /* Copy from file into buffer with valid tag */ - read_len = read(fd, ptr, len); + syscall_len = read(fd, ptr, len); mte_wait_after_trig(); - if (cur_mte_cxt.fault_valid || read_len < len) + if (cur_mte_cxt.fault_valid || syscall_len < len) goto usermem_acc_err; /* Verify same pattern is read */ for (i = 0; i < len; i++) @@ -54,36 +70,136 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping) if (i < len) goto usermem_acc_err; - /* Tag the next half of memory with different value */ - ptr_next = (void *)((unsigned long)ptr + page_sz); + if (!tag_len) + tag_len = len - tag_offset; + /* Tag a part of memory with different value */ + ptr_next = (void *)((unsigned long)ptr + tag_offset); ptr_next = mte_insert_new_tag(ptr_next); - mte_set_tag_address_range(ptr_next, page_sz); + mte_set_tag_address_range(ptr_next, tag_len); - lseek(fd, 0, 0); - /* Copy from file into buffer with invalid tag */ - read_len = read(fd, ptr, len); - mte_wait_after_trig(); - /* - * Accessing user memory in kernel with invalid tag should fail in sync - * mode without fault but may not fail in async mode as per the - * implemented MTE userspace support in Arm64 kernel. - */ - if (mode == MTE_SYNC_ERR && - !cur_mte_cxt.fault_valid && read_len < len) { - err = KSFT_PASS; - } else if (mode == MTE_ASYNC_ERR && - !cur_mte_cxt.fault_valid && read_len == len) { - err = KSFT_PASS; + for (fileoff = 0; fileoff < 16; fileoff++) { + for (ptroff = 0; ptroff < 16; ptroff++) { + for (i = 0; i < ARRAY_SIZE(sizes); i++) { + size = sizes[i]; + lseek(fd, 0, 0); + + /* perform file operation on buffer with invalid tag */ + switch (test_type) { + case READ_TEST: + syscall_len = read(fd, ptr + ptroff, size); + break; + case WRITE_TEST: + syscall_len = write(fd, ptr + ptroff, size); + break; + case READV_TEST: { + struct iovec iov[1]; + iov[0].iov_base = ptr + ptroff; + iov[0].iov_len = size; + syscall_len = readv(fd, iov, 1); + break; + } + case WRITEV_TEST: { + struct iovec iov[1]; + iov[0].iov_base = ptr + ptroff; + iov[0].iov_len = size; + syscall_len = writev(fd, iov, 1); + break; + } + case LAST_TEST: + goto usermem_acc_err; + } + + mte_wait_after_trig(); + /* + * Accessing user memory in kernel with invalid tag should fail in sync + * mode without fault but may not fail in async mode as per the + * implemented MTE userspace support in Arm64 kernel. + */ + if (cur_mte_cxt.fault_valid) { + goto usermem_acc_err; + } + if (mode == MTE_SYNC_ERR && syscall_len < len) { + /* test passed */ + } else if (mode == MTE_ASYNC_ERR && syscall_len == size) { + /* test passed */ + } else { + goto usermem_acc_err; + } + } + } } + + goto exit; + usermem_acc_err: + err = KSFT_FAIL; +exit: mte_free_memory((void *)ptr, len, mem_type, true); close(fd); return err; } +void format_test_name(char* name, int name_len, int type, int sync, int map, int len, int offset) { + const char* test_type; + const char* mte_type; + const char* map_type; + + switch (type) { + case READ_TEST: + test_type = "read"; + break; + case WRITE_TEST: + test_type = "write"; + break; + case READV_TEST: + test_type = "readv"; + break; + case WRITEV_TEST: + test_type = "writev"; + break; + default: + assert(0); + break; + } + + switch (sync) { + case MTE_SYNC_ERR: + mte_type = "MTE_SYNC_ERR"; + break; + case MTE_ASYNC_ERR: + mte_type = "MTE_ASYNC_ERR"; + break; + default: + assert(0); + break; + } + + switch (map) { + case MAP_SHARED: + map_type = "MAP_SHARED"; + break; + case MAP_PRIVATE: + map_type = "MAP_PRIVATE"; + break; + default: + assert(0); + break; + } + + snprintf(name, name_len, + "test type: %s, %s, %s, tag len: %d, tag offset: %d\n", + test_type, mte_type, map_type, len, offset); +} + int main(int argc, char *argv[]) { int err; + int t, s, m, l, o; + int mte_sync[] = {MTE_SYNC_ERR, MTE_ASYNC_ERR}; + int maps[] = {MAP_SHARED, MAP_PRIVATE}; + int tag_lens[] = {0, MT_GRANULE_SIZE}; + int tag_offsets[] = {page_sz, MT_GRANULE_SIZE}; + char test_name[TEST_NAME_MAX]; page_sz = getpagesize(); if (!page_sz) { @@ -98,17 +214,28 @@ int main(int argc, char *argv[]) mte_register_signal(SIGSEGV, mte_default_handler); /* Set test plan */ - ksft_set_plan(4); + ksft_set_plan(64); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE), - "Check memory access from kernel in sync mode, private mapping and mmap memory\n"); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED), - "Check memory access from kernel in sync mode, shared mapping and mmap memory\n"); - - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE), - "Check memory access from kernel in async mode, private mapping and mmap memory\n"); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED), - "Check memory access from kernel in async mode, shared mapping and mmap memory\n"); + for (t = 0; t < LAST_TEST; t++) { + for (s = 0; s < ARRAY_SIZE(mte_sync); s++) { + for (m = 0; m < ARRAY_SIZE(maps); m++) { + for (l = 0; l < ARRAY_SIZE(tag_lens); l++) { + for (o = 0; o < ARRAY_SIZE(tag_offsets); o++) { + int sync = mte_sync[s]; + int map = maps[m]; + int offset = tag_offsets[o]; + int tag_len = tag_lens[l]; + int res = check_usermem_access_fault(USE_MMAP, sync, + map, offset, + tag_len, t); + format_test_name(test_name, TEST_NAME_MAX, + t, sync, map, tag_len, offset); + evaluate_test(res, test_name); + } + } + } + } + } mte_restore_setup(); ksft_print_cnts(); diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index ebe8694dbef0..f909b70d9e98 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -53,6 +53,7 @@ struct tdescr { char *name; char *descr; unsigned long feats_required; + unsigned long feats_incompatible; /* bitmask of effectively supported feats: populated at run-time */ unsigned long feats_supported; bool initialized; diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 2f8c23af3b5e..5743897984b0 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -36,6 +36,8 @@ static inline char *feats_to_string(unsigned long feats) { size_t flen = MAX_FEATS_SZ - 1; + feats_string[0] = '\0'; + for (int i = 0; i < FMAX_END; i++) { if (feats & (1UL << i)) { size_t tlen = strlen(feats_names[i]); @@ -256,7 +258,7 @@ int test_init(struct tdescr *td) td->minsigstksz = MINSIGSTKSZ; fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz); - if (td->feats_required) { + if (td->feats_required || td->feats_incompatible) { td->feats_supported = 0; /* * Checking for CPU required features using both the @@ -267,15 +269,29 @@ int test_init(struct tdescr *td) if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; if (feats_ok(td)) { - fprintf(stderr, - "Required Features: [%s] supported\n", - feats_to_string(td->feats_required & - td->feats_supported)); + if (td->feats_required & td->feats_supported) + fprintf(stderr, + "Required Features: [%s] supported\n", + feats_to_string(td->feats_required & + td->feats_supported)); + if (!(td->feats_incompatible & td->feats_supported)) + fprintf(stderr, + "Incompatible Features: [%s] absent\n", + feats_to_string(td->feats_incompatible)); } else { - fprintf(stderr, - "Required Features: [%s] NOT supported\n", - feats_to_string(td->feats_required & - ~td->feats_supported)); + if ((td->feats_required & td->feats_supported) != + td->feats_supported) + fprintf(stderr, + "Required Features: [%s] NOT supported\n", + feats_to_string(td->feats_required & + ~td->feats_supported)); + if (td->feats_incompatible & td->feats_supported) + fprintf(stderr, + "Incompatible Features: [%s] supported\n", + feats_to_string(td->feats_incompatible & + ~td->feats_supported)); + + td->result = KSFT_SKIP; return 0; } diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h index 6772b5c8d274..f3aa99ba67bb 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.h +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h @@ -18,6 +18,8 @@ void test_result(struct tdescr *td); static inline bool feats_ok(struct tdescr *td) { + if (td->feats_incompatible & td->feats_supported) + return false; return (td->feats_required & td->feats_supported) == td->feats_required; } diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c new file mode 100644 index 000000000000..f74b82305da8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "timer_crash.skel.h" + +enum { + MODE_ARRAY, + MODE_HASH, +}; + +static void test_timer_crash_mode(int mode) +{ + struct timer_crash *skel; + + skel = timer_crash__open_and_load(); + if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load")) + return; + skel->bss->pid = getpid(); + skel->bss->crash_map = mode; + if (!ASSERT_OK(timer_crash__attach(skel), "timer_crash__attach")) + goto end; + usleep(1); +end: + timer_crash__destroy(skel); +} + +void test_timer_crash(void) +{ + if (test__start_subtest("array")) + test_timer_crash_mode(MODE_ARRAY); + if (test__start_subtest("hash")) + test_timer_crash_mode(MODE_HASH); +} diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 2966564b8497..6c85b00f27b2 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -235,7 +235,7 @@ SEC("sk_msg1") int bpf_prog4(struct sk_msg_md *msg) { int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; - int *start, *end, *start_push, *end_push, *start_pop, *pop; + int *start, *end, *start_push, *end_push, *start_pop, *pop, err = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); if (bytes) @@ -249,8 +249,11 @@ int bpf_prog4(struct sk_msg_md *msg) bpf_msg_pull_data(msg, *start, *end, 0); start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); if (start_pop && pop) @@ -263,6 +266,7 @@ int bpf_prog6(struct sk_msg_md *msg) { int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0; int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f; + int err = 0; __u64 flags = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); @@ -279,8 +283,11 @@ int bpf_prog6(struct sk_msg_md *msg) start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); @@ -338,7 +345,7 @@ SEC("sk_msg5") int bpf_prog10(struct sk_msg_md *msg) { int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop; - int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; + int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, err = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); if (bytes) @@ -352,8 +359,11 @@ int bpf_prog10(struct sk_msg_md *msg) bpf_msg_pull_data(msg, *start, *end, 0); start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_PASS; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); if (start_pop && pop) diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c new file mode 100644 index 000000000000..f8f7944e70da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_crash.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct map_elem { + struct bpf_timer timer; + struct bpf_spin_lock lock; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} amap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} hmap SEC(".maps"); + +int pid = 0; +int crash_map = 0; /* 0 for amap, 1 for hmap */ + +SEC("fentry/do_nanosleep") +int sys_enter(void *ctx) +{ + struct map_elem *e, value = {}; + void *map = crash_map ? (void *)&hmap : (void *)&amap; + + if (bpf_get_current_task_btf()->tgid != pid) + return 0; + + *(void **)&value = (void *)0xdeadcaf3; + + bpf_map_update_elem(map, &(int){0}, &value, 0); + /* For array map, doing bpf_map_update_elem will do a + * check_and_free_timer_in_array, which will trigger the crash if timer + * pointer was overwritten, for hmap we need to use bpf_timer_cancel. + */ + if (crash_map == 1) { + e = bpf_map_lookup_elem(map, &(int){0}); + if (!e) + return 0; + bpf_timer_cancel(&e->timer); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c index ebf68dce5504..2893e9f2f1e0 100644 --- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -28,7 +28,6 @@ // 5. We can read keycode from same /dev/lirc device #include <linux/bpf.h> -#include <linux/lirc.h> #include <linux/input.h> #include <errno.h> #include <stdio.h> diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 0cf7e90c0052..dbaa7aabbb4a 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -583,7 +583,7 @@ int clone_into_cgroup_run_wait(const char *cgroup) return 0; } -int cg_prepare_for_wait(const char *cgroup) +static int __prepare_for_wait(const char *cgroup, const char *filename) { int fd, ret = -1; @@ -591,8 +591,7 @@ int cg_prepare_for_wait(const char *cgroup) if (fd == -1) return fd; - ret = inotify_add_watch(fd, cg_control(cgroup, "cgroup.events"), - IN_MODIFY); + ret = inotify_add_watch(fd, cg_control(cgroup, filename), IN_MODIFY); if (ret == -1) { close(fd); fd = -1; @@ -601,6 +600,16 @@ int cg_prepare_for_wait(const char *cgroup) return fd; } +int cg_prepare_for_wait(const char *cgroup) +{ + return __prepare_for_wait(cgroup, "cgroup.events"); +} + +int memcg_prepare_for_wait(const char *cgroup) +{ + return __prepare_for_wait(cgroup, "memory.events"); +} + int cg_wait_for(int fd) { int ret = -1; diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 4f66d10626d2..628738532ac9 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -55,4 +55,5 @@ extern int clone_reap(pid_t pid, int options); extern int clone_into_cgroup_run_wait(const char *cgroup); extern int dirfd_open_opath(const char *dir); extern int cg_prepare_for_wait(const char *cgroup); +extern int memcg_prepare_for_wait(const char *cgroup); extern int cg_wait_for(int fd); diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index c19a97dd02d4..36ccf2322e21 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -16,6 +16,7 @@ #include <netinet/in.h> #include <netdb.h> #include <errno.h> +#include <sys/mman.h> #include "../kselftest.h" #include "cgroup_util.h" @@ -628,6 +629,82 @@ cleanup: return ret; } +static int alloc_anon_mlock(const char *cgroup, void *arg) +{ + size_t size = (size_t)arg; + void *buf; + + buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, + 0, 0); + if (buf == MAP_FAILED) + return -1; + + mlock(buf, size); + munmap(buf, size); + return 0; +} + +/* + * This test checks that memory.high is able to throttle big single shot + * allocation i.e. large allocation within one kernel entry. + */ +static int test_memcg_high_sync(const char *root) +{ + int ret = KSFT_FAIL, pid, fd = -1; + char *memcg; + long pre_high, pre_max; + long post_high, post_max; + + memcg = cg_name(root, "memcg_test"); + if (!memcg) + goto cleanup; + + if (cg_create(memcg)) + goto cleanup; + + pre_high = cg_read_key_long(memcg, "memory.events", "high "); + pre_max = cg_read_key_long(memcg, "memory.events", "max "); + if (pre_high < 0 || pre_max < 0) + goto cleanup; + + if (cg_write(memcg, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(memcg, "memory.high", "30M")) + goto cleanup; + + if (cg_write(memcg, "memory.max", "140M")) + goto cleanup; + + fd = memcg_prepare_for_wait(memcg); + if (fd < 0) + goto cleanup; + + pid = cg_run_nowait(memcg, alloc_anon_mlock, (void *)MB(200)); + if (pid < 0) + goto cleanup; + + cg_wait_for(fd); + + post_high = cg_read_key_long(memcg, "memory.events", "high "); + post_max = cg_read_key_long(memcg, "memory.events", "max "); + if (post_high < 0 || post_max < 0) + goto cleanup; + + if (pre_high == post_high || pre_max != post_max) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (fd >= 0) + close(fd); + cg_destroy(memcg); + free(memcg); + + return ret; +} + /* * This test checks that memory.max limits the amount of * memory which can be consumed by either anonymous memory @@ -1180,6 +1257,7 @@ struct memcg_test { T(test_memcg_min), T(test_memcg_low), T(test_memcg_high), + T(test_memcg_high_sync), T(test_memcg_max), T(test_memcg_oom_events), T(test_memcg_swap_max), diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 076cf4325f78..cd4582129c7d 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -126,8 +126,6 @@ static void test_clone3(uint64_t flags, size_t size, int expected, int main(int argc, char *argv[]) { - pid_t pid; - uid_t uid = getuid(); ksft_print_header(); diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh index 31f8c9a76c5f..60ce18ed0666 100755 --- a/tools/testing/selftests/cpufreq/main.sh +++ b/tools/testing/selftests/cpufreq/main.sh @@ -194,5 +194,5 @@ prerequisite # Run requested functions clear_dumps $OUTFILE -do_test >> $OUTFILE.txt +do_test | tee -a $OUTFILE.txt dmesg_dumps $OUTFILE diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 937d36ae9a69..0470c5f3e690 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -6,5 +6,6 @@ TEST_GEN_FILES += huge_count_read_write TEST_FILES = _chk_dependency.sh _debugfs_common.sh TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh +TEST_PROGS += sysfs.sh include ../lib.mk diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh new file mode 100644 index 000000000000..2e3ae77cb6db --- /dev/null +++ b/tools/testing/selftests/damon/sysfs.sh @@ -0,0 +1,306 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest frmework requirement - SKIP code is 4. +ksft_skip=4 + +ensure_write_succ() +{ + file=$1 + content=$2 + reason=$3 + + if ! echo "$content" > "$file" + then + echo "writing $content to $file failed" + echo "expected success because $reason" + exit 1 + fi +} + +ensure_write_fail() +{ + file=$1 + content=$2 + reason=$3 + + if echo "$content" > "$file" + then + echo "writing $content to $file succeed ($fail_reason)" + echo "expected failure because $reason" + exit 1 + fi +} + +ensure_dir() +{ + dir=$1 + to_ensure=$2 + if [ "$to_ensure" = "exist" ] && [ ! -d "$dir" ] + then + echo "$dir dir is expected but not found" + exit 1 + elif [ "$to_ensure" = "not_exist" ] && [ -d "$dir" ] + then + echo "$dir dir is not expected but found" + exit 1 + fi +} + +ensure_file() +{ + file=$1 + to_ensure=$2 + permission=$3 + if [ "$to_ensure" = "exist" ] + then + if [ ! -f "$file" ] + then + echo "$file is expected but not found" + exit 1 + fi + perm=$(stat -c "%a" "$file") + if [ ! "$perm" = "$permission" ] + then + echo "$file permission: expected $permission but $perm" + exit 1 + fi + elif [ "$to_ensure" = "not_exist" ] && [ -f "$dir" ] + then + echo "$file is not expected but found" + exit 1 + fi +} + +test_range() +{ + range_dir=$1 + ensure_dir "$range_dir" "exist" + ensure_file "$range_dir/min" "exist" 600 + ensure_file "$range_dir/max" "exist" 600 +} + +test_stats() +{ + stats_dir=$1 + ensure_dir "$stats_dir" "exist" + for f in nr_tried sz_tried nr_applied sz_applied qt_exceeds + do + ensure_file "$stats_dir/$f" "exist" "400" + done +} + +test_watermarks() +{ + watermarks_dir=$1 + ensure_dir "$watermarks_dir" "exist" + ensure_file "$watermarks_dir/metric" "exist" "600" + ensure_file "$watermarks_dir/interval_us" "exist" "600" + ensure_file "$watermarks_dir/high" "exist" "600" + ensure_file "$watermarks_dir/mid" "exist" "600" + ensure_file "$watermarks_dir/low" "exist" "600" +} + +test_weights() +{ + weights_dir=$1 + ensure_dir "$weights_dir" "exist" + ensure_file "$weights_dir/sz_permil" "exist" "600" + ensure_file "$weights_dir/nr_accesses_permil" "exist" "600" + ensure_file "$weights_dir/age_permil" "exist" "600" +} + +test_quotas() +{ + quotas_dir=$1 + ensure_dir "$quotas_dir" "exist" + ensure_file "$quotas_dir/ms" "exist" 600 + ensure_file "$quotas_dir/bytes" "exist" 600 + ensure_file "$quotas_dir/reset_interval_ms" "exist" 600 + test_weights "$quotas_dir/weights" +} + +test_access_pattern() +{ + access_pattern_dir=$1 + ensure_dir "$access_pattern_dir" "exist" + test_range "$access_pattern_dir/age" + test_range "$access_pattern_dir/nr_accesses" + test_range "$access_pattern_dir/sz" +} + +test_scheme() +{ + scheme_dir=$1 + ensure_dir "$scheme_dir" "exist" + ensure_file "$scheme_dir/action" "exist" "600" + test_access_pattern "$scheme_dir/access_pattern" + test_quotas "$scheme_dir/quotas" + test_watermarks "$scheme_dir/watermarks" + test_stats "$scheme_dir/stats" +} + +test_schemes() +{ + schemes_dir=$1 + ensure_dir "$schemes_dir" "exist" + ensure_file "$schemes_dir/nr_schemes" "exist" 600 + + ensure_write_succ "$schemes_dir/nr_schemes" "1" "valid input" + test_scheme "$schemes_dir/0" + + ensure_write_succ "$schemes_dir/nr_schemes" "2" "valid input" + test_scheme "$schemes_dir/0" + test_scheme "$schemes_dir/1" + + ensure_write_succ "$schemes_dir/nr_schemes" "0" "valid input" + ensure_dir "$schemes_dir/0" "not_exist" + ensure_dir "$schemes_dir/1" "not_exist" +} + +test_region() +{ + region_dir=$1 + ensure_dir "$region_dir" "exist" + ensure_file "$region_dir/start" "exist" 600 + ensure_file "$region_dir/end" "exist" 600 +} + +test_regions() +{ + regions_dir=$1 + ensure_dir "$regions_dir" "exist" + ensure_file "$regions_dir/nr_regions" "exist" 600 + + ensure_write_succ "$regions_dir/nr_regions" "1" "valid input" + test_region "$regions_dir/0" + + ensure_write_succ "$regions_dir/nr_regions" "2" "valid input" + test_region "$regions_dir/0" + test_region "$regions_dir/1" + + ensure_write_succ "$regions_dir/nr_regions" "0" "valid input" + ensure_dir "$regions_dir/0" "not_exist" + ensure_dir "$regions_dir/1" "not_exist" +} + +test_target() +{ + target_dir=$1 + ensure_dir "$target_dir" "exist" + ensure_file "$target_dir/pid_target" "exist" "600" + test_regions "$target_dir/regions" +} + +test_targets() +{ + targets_dir=$1 + ensure_dir "$targets_dir" "exist" + ensure_file "$targets_dir/nr_targets" "exist" 600 + + ensure_write_succ "$targets_dir/nr_targets" "1" "valid input" + test_target "$targets_dir/0" + + ensure_write_succ "$targets_dir/nr_targets" "2" "valid input" + test_target "$targets_dir/0" + test_target "$targets_dir/1" + + ensure_write_succ "$targets_dir/nr_targets" "0" "valid input" + ensure_dir "$targets_dir/0" "not_exist" + ensure_dir "$targets_dir/1" "not_exist" +} + +test_intervals() +{ + intervals_dir=$1 + ensure_dir "$intervals_dir" "exist" + ensure_file "$intervals_dir/aggr_us" "exist" "600" + ensure_file "$intervals_dir/sample_us" "exist" "600" + ensure_file "$intervals_dir/update_us" "exist" "600" +} + +test_monitoring_attrs() +{ + monitoring_attrs_dir=$1 + ensure_dir "$monitoring_attrs_dir" "exist" + test_intervals "$monitoring_attrs_dir/intervals" + test_range "$monitoring_attrs_dir/nr_regions" +} + +test_context() +{ + context_dir=$1 + ensure_dir "$context_dir" "exist" + ensure_file "$context_dir/operations" "exist" 600 + test_monitoring_attrs "$context_dir/monitoring_attrs" + test_targets "$context_dir/targets" + test_schemes "$context_dir/schemes" +} + +test_contexts() +{ + contexts_dir=$1 + ensure_dir "$contexts_dir" "exist" + ensure_file "$contexts_dir/nr_contexts" "exist" 600 + + ensure_write_succ "$contexts_dir/nr_contexts" "1" "valid input" + test_context "$contexts_dir/0" + + ensure_write_fail "$contexts_dir/nr_contexts" "2" "only 0/1 are supported" + test_context "$contexts_dir/0" + + ensure_write_succ "$contexts_dir/nr_contexts" "0" "valid input" + ensure_dir "$contexts_dir/0" "not_exist" +} + +test_kdamond() +{ + kdamond_dir=$1 + ensure_dir "$kdamond_dir" "exist" + ensure_file "$kdamond_dir/state" "exist" "600" + ensure_file "$kdamond_dir/pid" "exist" 400 + test_contexts "$kdamond_dir/contexts" +} + +test_kdamonds() +{ + kdamonds_dir=$1 + ensure_dir "$kdamonds_dir" "exist" + + ensure_file "$kdamonds_dir/nr_kdamonds" "exist" "600" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "1" "valid input" + test_kdamond "$kdamonds_dir/0" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "2" "valid input" + test_kdamond "$kdamonds_dir/0" + test_kdamond "$kdamonds_dir/1" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "0" "valid input" + ensure_dir "$kdamonds_dir/0" "not_exist" + ensure_dir "$kdamonds_dir/1" "not_exist" +} + +test_damon_sysfs() +{ + damon_sysfs=$1 + if [ ! -d "$damon_sysfs" ] + then + echo "$damon_sysfs not found" + exit $ksft_skip + fi + + test_kdamonds "$damon_sysfs/kdamonds" +} + +check_dependencies() +{ + if [ $EUID -ne 0 ] + then + echo "Run as root" + exit $ksft_skip + fi +} + +check_dependencies +test_damon_sysfs "/sys/kernel/mm/damon/admin" diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index bcb110e830ce..dea33dc93790 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -50,8 +50,8 @@ for current_test in ${TESTS:-$ALL_TESTS}; do else log_test "'$current_test' [$profile] overflow $target" fi + RET_FIN=$(( RET_FIN || RET )) done - RET_FIN=$(( RET_FIN || RET )) done done current_test="" diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh index 3e3e06ea5703..86e787895f78 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh @@ -60,7 +60,8 @@ __tc_police_test() tc_police_rules_create $count $should_fail - offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l) + offload_count=$(tc -j filter show dev $swp1 ingress | + jq "[.[] | select(.options.in_hw == true)] | length") ((offload_count == count)) check_err_fail $should_fail $? "tc police offload count" } diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore index 9e2f00343f15..90c238ba6a4b 100644 --- a/tools/testing/selftests/exec/.gitignore +++ b/tools/testing/selftests/exec/.gitignore @@ -7,6 +7,8 @@ execveat.moved execveat.path.ephemeral execveat.ephemeral execveat.denatured +non-regular +null-argv /load_address_* /recursion-depth xxxxxxxx* diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index dd61118df66e..a0b8688b0836 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -3,13 +3,14 @@ CFLAGS = -Wall CFLAGS += -Wno-nonnull CFLAGS += -D_GNU_SOURCE -TEST_PROGS := binfmt_script non-regular -TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 -TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe +TEST_PROGS := binfmt_script.py +TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 non-regular +TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile TEST_GEN_PROGS += recursion-depth +TEST_GEN_PROGS += null-argv EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* \ $(OUTPUT)/S_I*.test diff --git a/tools/testing/selftests/exec/binfmt_script b/tools/testing/selftests/exec/binfmt_script.py index 05f94a741c7a..05f94a741c7a 100755 --- a/tools/testing/selftests/exec/binfmt_script +++ b/tools/testing/selftests/exec/binfmt_script.py diff --git a/tools/testing/selftests/exec/null-argv.c b/tools/testing/selftests/exec/null-argv.c new file mode 100644 index 000000000000..c19726e710d1 --- /dev/null +++ b/tools/testing/selftests/exec/null-argv.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Test that empty argvs are swapped out for a single empty string. */ +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "../kselftest.h" + +#define FORK(exec) \ +do { \ + pid = fork(); \ + if (pid == 0) { \ + /* Child */ \ + exec; /* Some kind of exec */ \ + perror("# " #exec); \ + return 1; \ + } \ + check_result(pid, #exec); \ +} while (0) + +void check_result(pid_t pid, const char *msg) +{ + int wstatus; + + if (pid == (pid_t)-1) { + perror("# fork"); + ksft_test_result_fail("fork failed: %s\n", msg); + return; + } + if (waitpid(pid, &wstatus, 0) < 0) { + perror("# waitpid"); + ksft_test_result_fail("waitpid failed: %s\n", msg); + return; + } + if (!WIFEXITED(wstatus)) { + ksft_test_result_fail("child did not exit: %s\n", msg); + return; + } + if (WEXITSTATUS(wstatus) != 0) { + ksft_test_result_fail("non-zero exit: %s\n", msg); + return; + } + ksft_test_result_pass("%s\n", msg); +} + +int main(int argc, char *argv[], char *envp[]) +{ + pid_t pid; + static char * const args[] = { NULL }; + static char * const str[] = { "", NULL }; + + /* argc counting checks */ + if (argc < 1) { + fprintf(stderr, "# FAIL: saw argc == 0 (old kernel?)\n"); + return 1; + } + if (argc != 1) { + fprintf(stderr, "# FAIL: unknown argc (%d)\n", argc); + return 1; + } + if (argv[0][0] == '\0') { + /* Good, we found a NULL terminated string at argv[0]! */ + return 0; + } + + /* Test runner. */ + ksft_print_header(); + ksft_set_plan(5); + + FORK(execve(argv[0], str, NULL)); + FORK(execve(argv[0], NULL, NULL)); + FORK(execve(argv[0], NULL, envp)); + FORK(execve(argv[0], args, NULL)); + FORK(execve(argv[0], args, envp)); + + ksft_exit(ksft_cnt.ksft_pass == ksft_plan); +} diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc index e96e279e0533..25432b8cd5bd 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -19,7 +19,7 @@ fail() { # mesg FILTER=set_ftrace_filter FUNC1="schedule" -FUNC2="do_softirq" +FUNC2="scheduler_tick" ALL_FUNCS="#### all functions enabled ####" diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 12631f0076a1..11e157d7533b 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -11,7 +11,7 @@ all: @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ if [ -e $$DIR/$(TEST_PROGS) ]; then \ rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \ fi \ @@ -32,6 +32,6 @@ override define CLEAN @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ done endef diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 5cc38de9d8ea..b8152c573e8a 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -INCLUDES := -I../include -I../../ -I../../../../../usr/include/ \ - -I$(KBUILD_OUTPUT)/kselftest/usr/include -CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) +INCLUDES := -I../include -I../../ -I../../../../../usr/include/ +CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) $(KHDR_INCLUDES) LDLIBS := -lpthread -lrt HEADERS := \ @@ -24,6 +23,7 @@ TEST_PROGS := run.sh top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 +DEFAULT_INSTALL_HDR_PATH := 1 include ../../lib.mk $(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index 06256c96df12..f4a15cbdd5ea 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -29,6 +29,16 @@ #define SYSFS_PATH_MAX 256 #define DNAME_PATH_MAX 256 +/* + * Support ancient lirc.h which does not have these values. Can be removed + * once RHEL 8 is no longer a relevant testing platform. + */ +#if RC_PROTO_MAX < 26 +#define RC_PROTO_RCMM12 24 +#define RC_PROTO_RCMM24 25 +#define RC_PROTO_RCMM32 26 +#endif + static const struct { enum rc_proto proto; const char *name; diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index a9ba782d8ca0..294619ade49f 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -18,6 +18,8 @@ if [ -z "$BASE_DIR" ]; then exit 1 fi +TR_CMD=$(command -v tr) + # If Perl is unavailable, we must fall back to line-at-a-time prefixing # with sed instead of unbuffered output. tap_prefix() @@ -49,6 +51,31 @@ run_one() # Reset any "settings"-file variables. export kselftest_timeout="$kselftest_default_timeout" + + # Safe default if tr not available + kselftest_cmd_args_ref="KSELFTEST_ARGS" + + # Optional arguments for this command, possibly defined as an + # environment variable built using the test executable in all + # uppercase and sanitized substituting non acceptable shell + # variable name characters with "_" as in: + # + # KSELFTEST_<UPPERCASE_SANITIZED_TESTNAME>_ARGS="<options>" + # + # e.g. + # + # rtctest --> KSELFTEST_RTCTEST_ARGS="/dev/rtc1" + # + # cpu-on-off-test.sh --> KSELFTEST_CPU_ON_OFF_TEST_SH_ARGS="-a -p 10" + # + if [ -n "$TR_CMD" ]; then + BASENAME_SANITIZED=$(echo "$BASENAME_TEST" | \ + $TR_CMD -d "[:blank:][:cntrl:]" | \ + $TR_CMD -c "[:alnum:]_" "_" | \ + $TR_CMD [:lower:] [:upper:]) + kselftest_cmd_args_ref="KSELFTEST_${BASENAME_SANITIZED}_ARGS" + fi + # Load per-test-directory kselftest "settings" file. settings="$BASE_DIR/$DIR/settings" if [ -r "$settings" ] ; then @@ -69,7 +96,8 @@ run_one() echo "# Warning: file $TEST is missing!" echo "not ok $test_num $TEST_HDR_MSG" else - cmd="./$BASENAME_TEST" + eval kselftest_cmd_args="\$${kselftest_cmd_args_ref:-}" + cmd="./$BASENAME_TEST $kselftest_cmd_args" if [ ! -x "$TEST" ]; then echo "# Warning: file $TEST is not executable" diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 471eaa7b3a3f..11779405dc80 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -877,7 +877,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) } t->timed_out = true; - kill(t->pid, SIGKILL); + // signal process group + kill(-(t->pid), SIGKILL); } void __wait_for_test(struct __test_metadata *t) @@ -987,6 +988,7 @@ void __run_test(struct __fixture_metadata *f, ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { + setpgrp(); t->fn(t, variant); if (t->skip) _exit(255); diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index dce7de7755e6..d1e8f5237469 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -8,6 +8,7 @@ /s390x/memop /s390x/resets /s390x/sync_regs_test +/s390x/tprot /x86_64/amx_test /x86_64/cpuid_test /x86_64/cr4_cpuid_sync_test @@ -20,6 +21,7 @@ /x86_64/hyperv_clock /x86_64/hyperv_cpuid /x86_64/hyperv_features +/x86_64/hyperv_svm_test /x86_64/mmio_warning_test /x86_64/mmu_role_test /x86_64/platform_info_test @@ -45,6 +47,7 @@ /x86_64/vmx_tsc_adjust_test /x86_64/vmx_nested_tsc_scaling_test /x86_64/xapic_ipi_test +/x86_64/xapic_state_test /x86_64/xen_shinfo_test /x86_64/xen_vmcall_test /x86_64/xss_msr_test @@ -56,6 +59,7 @@ /hardware_disable_test /kvm_create_max_vcpus /kvm_page_table_test +/max_guest_memory_test /memslot_modification_stress_test /memslot_perf_test /rseq_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0e4926bc9a58..21c2dbd21a81 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -51,6 +51,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test @@ -76,13 +77,13 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test +TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test @@ -92,6 +93,7 @@ TEST_GEN_PROGS_x86_64 += dirty_log_perf_test TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test +TEST_GEN_PROGS_x86_64 += max_guest_memory_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test TEST_GEN_PROGS_x86_64 += memslot_perf_test TEST_GEN_PROGS_x86_64 += rseq_test @@ -121,6 +123,7 @@ TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test TEST_GEN_PROGS_s390x = s390x/memop TEST_GEN_PROGS_s390x += s390x/resets TEST_GEN_PROGS_s390x += s390x/sync_regs_test +TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus @@ -150,7 +153,7 @@ endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS) + -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 9ad38bd360a4..b08d30bf71c5 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -366,6 +366,7 @@ static struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; + int ret; int nr_vcpus = test_args.nr_vcpus; vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); @@ -382,7 +383,11 @@ static struct kvm_vm *test_vm_create(void) ucall_init(vm, NULL); test_init_timer_irq(vm); - vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); + ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); + if (ret < 0) { + print_skip("Failed to create vgic-v3"); + exit(KSFT_SKIP); + } /* Make all the test's cmdline args visible to the guest */ sync_global_to_guest(vm, test_args); diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c index ea189d83abf7..63b2178210c4 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c @@ -23,7 +23,7 @@ #define SPSR_D (1 << 9) #define SPSR_SS (1 << 21) -extern unsigned char sw_bp, hw_bp, bp_svc, bp_brk, hw_wp, ss_start; +extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start; static volatile uint64_t sw_bp_addr, hw_bp_addr; static volatile uint64_t wp_addr, wp_data_addr; static volatile uint64_t svc_addr; @@ -47,6 +47,14 @@ static void reset_debug_state(void) isb(); } +static void enable_os_lock(void) +{ + write_sysreg(1, oslar_el1); + isb(); + + GUEST_ASSERT(read_sysreg(oslsr_el1) & 2); +} + static void install_wp(uint64_t addr) { uint32_t wcr; @@ -99,6 +107,7 @@ static void guest_code(void) GUEST_SYNC(0); /* Software-breakpoint */ + reset_debug_state(); asm volatile("sw_bp: brk #0"); GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp)); @@ -152,6 +161,51 @@ static void guest_code(void) GUEST_ASSERT_EQ(ss_addr[1], PC(ss_start) + 4); GUEST_ASSERT_EQ(ss_addr[2], PC(ss_start) + 8); + GUEST_SYNC(6); + + /* OS Lock does not block software-breakpoint */ + reset_debug_state(); + enable_os_lock(); + sw_bp_addr = 0; + asm volatile("sw_bp2: brk #0"); + GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp2)); + + GUEST_SYNC(7); + + /* OS Lock blocking hardware-breakpoint */ + reset_debug_state(); + enable_os_lock(); + install_hw_bp(PC(hw_bp2)); + hw_bp_addr = 0; + asm volatile("hw_bp2: nop"); + GUEST_ASSERT_EQ(hw_bp_addr, 0); + + GUEST_SYNC(8); + + /* OS Lock blocking watchpoint */ + reset_debug_state(); + enable_os_lock(); + write_data = '\0'; + wp_data_addr = 0; + install_wp(PC(write_data)); + write_data = 'x'; + GUEST_ASSERT_EQ(write_data, 'x'); + GUEST_ASSERT_EQ(wp_data_addr, 0); + + GUEST_SYNC(9); + + /* OS Lock blocking single-step */ + reset_debug_state(); + enable_os_lock(); + ss_addr[0] = 0; + install_ss(); + ss_idx = 0; + asm volatile("mrs x0, esr_el1\n\t" + "add x0, x0, #1\n\t" + "msr daifset, #8\n\t" + : : : "x0"); + GUEST_ASSERT_EQ(ss_addr[0], 0); + GUEST_DONE(); } @@ -223,7 +277,7 @@ int main(int argc, char *argv[]) vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT, ESR_EC_SVC64, guest_svc_handler); - for (stage = 0; stage < 7; stage++) { + for (stage = 0; stage < 11; stage++) { vcpu_run(vm, VCPU_ID); switch (get_ucall(vm, VCPU_ID, &uc)) { diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index f769fc6cd927..f12147c43464 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -760,6 +760,7 @@ static __u64 base_regs[] = { ARM64_SYS_REG(2, 0, 0, 15, 5), ARM64_SYS_REG(2, 0, 0, 15, 6), ARM64_SYS_REG(2, 0, 0, 15, 7), + ARM64_SYS_REG(2, 0, 1, 1, 4), /* OSLSR_EL1 */ ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */ ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */ ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */ diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index e6c7d7f8fbd1..554ca649d470 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -306,7 +306,8 @@ static void guest_restore_active(struct test_args *args, uint32_t prio, intid, ap1r; int i; - /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs + /* + * Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs * in descending order, so intid+1 can preempt intid. */ for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) { @@ -315,7 +316,8 @@ static void guest_restore_active(struct test_args *args, gic_set_priority(intid, prio); } - /* In a real migration, KVM would restore all GIC state before running + /* + * In a real migration, KVM would restore all GIC state before running * guest code. */ for (i = 0; i < num; i++) { @@ -472,10 +474,10 @@ static void test_restore_active(struct test_args *args, struct kvm_inject_desc * guest_restore_active(args, MIN_SPI, 4, f->cmd); } -static void guest_code(struct test_args args) +static void guest_code(struct test_args *args) { - uint32_t i, nr_irqs = args.nr_irqs; - bool level_sensitive = args.level_sensitive; + uint32_t i, nr_irqs = args->nr_irqs; + bool level_sensitive = args->level_sensitive; struct kvm_inject_desc *f, *inject_fns; gic_init(GIC_V3, 1, dist, redist); @@ -484,11 +486,11 @@ static void guest_code(struct test_args args) gic_irq_enable(i); for (i = MIN_SPI; i < nr_irqs; i++) - gic_irq_set_config(i, !args.level_sensitive); + gic_irq_set_config(i, !level_sensitive); - gic_set_eoi_split(args.eoi_split); + gic_set_eoi_split(args->eoi_split); - reset_priorities(&args); + reset_priorities(args); gic_set_priority_mask(CPU_PRIO_MASK); inject_fns = level_sensitive ? inject_level_fns @@ -497,17 +499,18 @@ static void guest_code(struct test_args args) local_irq_enable(); /* Start the tests. */ - for_each_supported_inject_fn(&args, inject_fns, f) { - test_injection(&args, f); - test_preemption(&args, f); - test_injection_failure(&args, f); + for_each_supported_inject_fn(args, inject_fns, f) { + test_injection(args, f); + test_preemption(args, f); + test_injection_failure(args, f); } - /* Restore the active state of IRQs. This would happen when live + /* + * Restore the active state of IRQs. This would happen when live * migrating IRQs in the middle of being handled. */ - for_each_supported_activate_fn(&args, set_active_fns, f) - test_restore_active(&args, f); + for_each_supported_activate_fn(args, set_active_fns, f) + test_restore_active(args, f); GUEST_DONE(); } @@ -573,8 +576,8 @@ static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm, kvm_gsi_routing_write(vm, routing); } else { ret = _kvm_gsi_routing_write(vm, routing); - /* The kernel only checks for KVM_IRQCHIP_NUM_PINS. */ - if (intid >= KVM_IRQCHIP_NUM_PINS) + /* The kernel only checks e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS */ + if (((uint64_t)intid + num - 1 - MIN_SPI) >= KVM_IRQCHIP_NUM_PINS) TEST_ASSERT(ret != 0 && errno == EINVAL, "Bad intid %u did not cause KVM_SET_GSI_ROUTING " "error: rc: %i errno: %i", intid, ret, errno); @@ -739,6 +742,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) int gic_fd; struct kvm_vm *vm; struct kvm_inject_args inject_args; + vm_vaddr_t args_gva; struct test_args args = { .nr_irqs = nr_irqs, @@ -757,10 +761,16 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) vcpu_init_descriptor_tables(vm, VCPU_ID); /* Setup the guest args page (so it gets the args). */ - vcpu_args_set(vm, 0, 1, args); + args_gva = vm_vaddr_alloc_page(vm); + memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args)); + vcpu_args_set(vm, 0, 1, args_gva); gic_fd = vgic_v3_setup(vm, 1, nr_irqs, GICD_BASE_GPA, GICR_BASE_GPA); + if (gic_fd < 0) { + print_skip("Failed to create vgic-v3, skipping"); + exit(KSFT_SKIP); + } vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handlers[args.eoi_split][args.level_sensitive]); @@ -837,7 +847,8 @@ int main(int argc, char **argv) } } - /* If the user just specified nr_irqs and/or gic_version, then run all + /* + * If the user just specified nr_irqs and/or gic_version, then run all * combinations. */ if (default_args) { diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 1954b964d1cf..c9d9e513ca04 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -18,6 +18,12 @@ #include "test_util.h" #include "perf_test_util.h" #include "guest_modes.h" +#ifdef __aarch64__ +#include "aarch64/vgic.h" + +#define GICD_BASE_GPA 0x8000000ULL +#define GICR_BASE_GPA 0x80A0000ULL +#endif /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ #define TEST_HOST_LOOP_N 2UL @@ -200,6 +206,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, &cap); } +#ifdef __aarch64__ + vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); +#endif + /* Start the iterations */ iteration = 0; host_quit = false; @@ -298,12 +308,18 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-i iterations] [-p offset] " + printf("usage: %s [-h] [-i iterations] [-p offset] [-g]" "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]" "[-x memslots]\n", name); puts(""); printf(" -i: specify iteration counts (default: %"PRIu64")\n", TEST_HOST_LOOP_N); + printf(" -g: Do not enable KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2. This\n" + " makes KVM_GET_DIRTY_LOG clear the dirty log (i.e.\n" + " KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is not enabled)\n" + " and writes will be tracked as soon as dirty logging is\n" + " enabled on the memslot (i.e. KVM_DIRTY_LOG_INITIALLY_SET\n" + " is not enabled).\n"); printf(" -p: specify guest physical test memory offset\n" " Warning: a low offset can conflict with the loaded test code.\n"); guest_modes_help(); @@ -343,8 +359,11 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:os:x:")) != -1) { + while ((opt = getopt(argc, argv, "ghi:p:m:b:f:v:os:x:")) != -1) { switch (opt) { + case 'g': + dirty_log_manual_caps = 0; + break; case 'i': p.iterations = atoi(optarg); break; diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 4ed6aa049a91..92cef0ffb19e 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -123,6 +123,7 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, size_t len); void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); +int kvm_memfd_alloc(size_t size, bool hugepages); void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); @@ -147,6 +148,10 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, void vm_create_irqchip(struct kvm_vm *vm); +void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); +int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); void vm_userspace_mem_region_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, uint64_t guest_paddr, uint32_t slot, uint64_t npages, @@ -336,6 +341,9 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]); +/* Create a default VM without any vcpus. */ +struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages); + /* * Adds a vCPU with reasonable defaults (e.g. a stack) * diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h index e0e96a5f608c..255c9b990f4c 100644 --- a/tools/testing/selftests/kvm/include/s390x/processor.h +++ b/tools/testing/selftests/kvm/include/s390x/processor.h @@ -5,6 +5,8 @@ #ifndef SELFTEST_KVM_PROCESSOR_H #define SELFTEST_KVM_PROCESSOR_H +#include <linux/compiler.h> + /* Bits in the region/segment table entry */ #define REGION_ENTRY_ORIGIN ~0xfffUL /* region/segment table origin */ #define REGION_ENTRY_PROTECT 0x200 /* region protection bit */ @@ -19,4 +21,10 @@ #define PAGE_PROTECT 0x200 /* HW read-only bit */ #define PAGE_NOEXEC 0x100 /* HW no-execute bit */ +/* Is there a portable way to do this? */ +static inline void cpu_relax(void) +{ + barrier(); +} + #endif diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h index 0be4757f1f20..ac88557dcc9a 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -33,6 +33,7 @@ #define APIC_SPIV 0xF0 #define APIC_SPIV_FOCUS_DISABLED (1 << 9) #define APIC_SPIV_APIC_ENABLED (1 << 8) +#define APIC_IRR 0x200 #define APIC_ICR 0x300 #define APIC_DEST_SELF 0x40000 #define APIC_DEST_ALLINC 0x80000 diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h index c9af97abd622..cc5d14a45702 100644 --- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h @@ -213,6 +213,25 @@ struct hv_enlightened_vmcs { u64 padding64_6[7]; }; +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP BIT(1) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2 BIT(2) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1 BIT(3) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC BIT(4) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT BIT(5) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY BIT(6) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN BIT(7) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR BIT(8) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT BIT(9) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC BIT(10) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1 BIT(11) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2 BIT(12) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER BIT(13) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1 BIT(14) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF + #define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 #define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 @@ -648,381 +667,507 @@ static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value) switch (encoding) { case GUEST_RIP: current_evmcs->guest_rip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case GUEST_RSP: current_evmcs->guest_rsp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC; break; case GUEST_RFLAGS: current_evmcs->guest_rflags = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC; break; case HOST_IA32_PAT: current_evmcs->host_ia32_pat = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_IA32_EFER: current_evmcs->host_ia32_efer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CR0: current_evmcs->host_cr0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CR3: current_evmcs->host_cr3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CR4: current_evmcs->host_cr4 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_IA32_SYSENTER_ESP: current_evmcs->host_ia32_sysenter_esp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_IA32_SYSENTER_EIP: current_evmcs->host_ia32_sysenter_eip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_RIP: current_evmcs->host_rip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case IO_BITMAP_A: current_evmcs->io_bitmap_a = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP; break; case IO_BITMAP_B: current_evmcs->io_bitmap_b = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP; break; case MSR_BITMAP: current_evmcs->msr_bitmap = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; break; case GUEST_ES_BASE: current_evmcs->guest_es_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_BASE: current_evmcs->guest_cs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_BASE: current_evmcs->guest_ss_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_BASE: current_evmcs->guest_ds_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_BASE: current_evmcs->guest_fs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_BASE: current_evmcs->guest_gs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_BASE: current_evmcs->guest_ldtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_BASE: current_evmcs->guest_tr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GDTR_BASE: current_evmcs->guest_gdtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_IDTR_BASE: current_evmcs->guest_idtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case TSC_OFFSET: current_evmcs->tsc_offset = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; break; case VIRTUAL_APIC_PAGE_ADDR: current_evmcs->virtual_apic_page_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; break; case VMCS_LINK_POINTER: current_evmcs->vmcs_link_pointer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_IA32_DEBUGCTL: current_evmcs->guest_ia32_debugctl = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_IA32_PAT: current_evmcs->guest_ia32_pat = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_IA32_EFER: current_evmcs->guest_ia32_efer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR0: current_evmcs->guest_pdptr0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR1: current_evmcs->guest_pdptr1 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR2: current_evmcs->guest_pdptr2 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR3: current_evmcs->guest_pdptr3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PENDING_DBG_EXCEPTIONS: current_evmcs->guest_pending_dbg_exceptions = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_SYSENTER_ESP: current_evmcs->guest_sysenter_esp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_SYSENTER_EIP: current_evmcs->guest_sysenter_eip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case CR0_GUEST_HOST_MASK: current_evmcs->cr0_guest_host_mask = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case CR4_GUEST_HOST_MASK: current_evmcs->cr4_guest_host_mask = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case CR0_READ_SHADOW: current_evmcs->cr0_read_shadow = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case CR4_READ_SHADOW: current_evmcs->cr4_read_shadow = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_CR0: current_evmcs->guest_cr0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_CR3: current_evmcs->guest_cr3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_CR4: current_evmcs->guest_cr4 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_DR7: current_evmcs->guest_dr7 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case HOST_FS_BASE: current_evmcs->host_fs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_GS_BASE: current_evmcs->host_gs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_TR_BASE: current_evmcs->host_tr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_GDTR_BASE: current_evmcs->host_gdtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_IDTR_BASE: current_evmcs->host_idtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_RSP: current_evmcs->host_rsp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case EPT_POINTER: current_evmcs->ept_pointer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT; break; case GUEST_BNDCFGS: current_evmcs->guest_bndcfgs = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case XSS_EXIT_BITMAP: current_evmcs->xss_exit_bitmap = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; break; case GUEST_PHYSICAL_ADDRESS: current_evmcs->guest_physical_address = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case EXIT_QUALIFICATION: current_evmcs->exit_qualification = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case GUEST_LINEAR_ADDRESS: current_evmcs->guest_linear_address = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_MSR_STORE_ADDR: current_evmcs->vm_exit_msr_store_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_EXIT_MSR_LOAD_ADDR: current_evmcs->vm_exit_msr_load_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_ENTRY_MSR_LOAD_ADDR: current_evmcs->vm_entry_msr_load_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE0: current_evmcs->cr3_target_value0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE1: current_evmcs->cr3_target_value1 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE2: current_evmcs->cr3_target_value2 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE3: current_evmcs->cr3_target_value3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case TPR_THRESHOLD: current_evmcs->tpr_threshold = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case GUEST_INTERRUPTIBILITY_INFO: current_evmcs->guest_interruptibility_info = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC; break; case CPU_BASED_VM_EXEC_CONTROL: current_evmcs->cpu_based_vm_exec_control = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC; break; case EXCEPTION_BITMAP: current_evmcs->exception_bitmap = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN; break; case VM_ENTRY_CONTROLS: current_evmcs->vm_entry_controls = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY; break; case VM_ENTRY_INTR_INFO_FIELD: current_evmcs->vm_entry_intr_info_field = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT; break; case VM_ENTRY_EXCEPTION_ERROR_CODE: current_evmcs->vm_entry_exception_error_code = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT; break; case VM_ENTRY_INSTRUCTION_LEN: current_evmcs->vm_entry_instruction_len = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT; break; case HOST_IA32_SYSENTER_CS: current_evmcs->host_ia32_sysenter_cs = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case PIN_BASED_VM_EXEC_CONTROL: current_evmcs->pin_based_vm_exec_control = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1; break; case VM_EXIT_CONTROLS: current_evmcs->vm_exit_controls = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1; break; case SECONDARY_VM_EXEC_CONTROL: current_evmcs->secondary_vm_exec_control = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1; break; case GUEST_ES_LIMIT: current_evmcs->guest_es_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_LIMIT: current_evmcs->guest_cs_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_LIMIT: current_evmcs->guest_ss_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_LIMIT: current_evmcs->guest_ds_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_LIMIT: current_evmcs->guest_fs_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_LIMIT: current_evmcs->guest_gs_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_LIMIT: current_evmcs->guest_ldtr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_LIMIT: current_evmcs->guest_tr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GDTR_LIMIT: current_evmcs->guest_gdtr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_IDTR_LIMIT: current_evmcs->guest_idtr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_ES_AR_BYTES: current_evmcs->guest_es_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_AR_BYTES: current_evmcs->guest_cs_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_AR_BYTES: current_evmcs->guest_ss_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_AR_BYTES: current_evmcs->guest_ds_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_AR_BYTES: current_evmcs->guest_fs_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_AR_BYTES: current_evmcs->guest_gs_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_AR_BYTES: current_evmcs->guest_ldtr_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_AR_BYTES: current_evmcs->guest_tr_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_ACTIVITY_STATE: current_evmcs->guest_activity_state = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_SYSENTER_CS: current_evmcs->guest_sysenter_cs = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case VM_INSTRUCTION_ERROR: current_evmcs->vm_instruction_error = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_REASON: current_evmcs->vm_exit_reason = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_INTR_INFO: current_evmcs->vm_exit_intr_info = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_INTR_ERROR_CODE: current_evmcs->vm_exit_intr_error_code = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case IDT_VECTORING_INFO_FIELD: current_evmcs->idt_vectoring_info_field = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case IDT_VECTORING_ERROR_CODE: current_evmcs->idt_vectoring_error_code = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_INSTRUCTION_LEN: current_evmcs->vm_exit_instruction_len = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VMX_INSTRUCTION_INFO: current_evmcs->vmx_instruction_info = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case PAGE_FAULT_ERROR_CODE_MASK: current_evmcs->page_fault_error_code_mask = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case PAGE_FAULT_ERROR_CODE_MATCH: current_evmcs->page_fault_error_code_match = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_COUNT: current_evmcs->cr3_target_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_EXIT_MSR_STORE_COUNT: current_evmcs->vm_exit_msr_store_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_EXIT_MSR_LOAD_COUNT: current_evmcs->vm_exit_msr_load_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_ENTRY_MSR_LOAD_COUNT: current_evmcs->vm_entry_msr_load_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case HOST_ES_SELECTOR: current_evmcs->host_es_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CS_SELECTOR: current_evmcs->host_cs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_SS_SELECTOR: current_evmcs->host_ss_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_DS_SELECTOR: current_evmcs->host_ds_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_FS_SELECTOR: current_evmcs->host_fs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_GS_SELECTOR: current_evmcs->host_gs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_TR_SELECTOR: current_evmcs->host_tr_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case GUEST_ES_SELECTOR: current_evmcs->guest_es_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_SELECTOR: current_evmcs->guest_cs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_SELECTOR: current_evmcs->guest_ss_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_SELECTOR: current_evmcs->guest_ds_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_SELECTOR: current_evmcs->guest_fs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_SELECTOR: current_evmcs->guest_gs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_SELECTOR: current_evmcs->guest_ldtr_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_SELECTOR: current_evmcs->guest_tr_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case VIRTUAL_PROCESSOR_ID: current_evmcs->virtual_processor_id = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT; break; default: return 1; } @@ -1070,7 +1215,10 @@ static inline int evmcs_vmresume(void) { int ret; - current_evmcs->hv_clean_fields = 0; + /* HOST_RIP */ + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; + /* HOST_RSP */ + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; __asm__ __volatile__("push %%rbp;" "push %%rcx;" diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 8a470da7b71a..37db341d4cc5 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -363,6 +363,11 @@ static inline unsigned long get_xmm(int n) return 0; } +static inline void cpu_relax(void) +{ + asm volatile("rep; nop" ::: "memory"); +} + bool is_intel_cpu(void); bool is_amd_cpu(void); diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h index f4ea2355dbc2..2225e5077350 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm.h @@ -99,7 +99,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u8 reserved_6[8]; /* Offset 0xe8 */ u64 avic_logical_id; /* Offset 0xf0 */ u64 avic_physical_id; /* Offset 0xf8 */ - u8 reserved_7[768]; + u8 reserved_7[8]; + u64 vmsa_pa; /* Used for an SEV-ES guest */ + u8 reserved_8[720]; + /* + * Offset 0x3e0, 32 bytes reserved + * for use by hypervisor/software. + */ + u8 reserved_sw[32]; }; diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h index 587fbe408b99..a25aabd8f5e7 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -16,6 +16,7 @@ #define CPUID_SVM_BIT 2 #define CPUID_SVM BIT_ULL(CPUID_SVM_BIT) +#define SVM_EXIT_MSR 0x07c #define SVM_EXIT_VMMCALL 0x081 struct svm_test_data { @@ -28,6 +29,11 @@ struct svm_test_data { struct vmcb_save_area *save_area; /* gva */ void *save_area_hva; uint64_t save_area_gpa; + + /* MSR-Bitmap */ + void *msr; /* gva */ + void *msr_hva; + uint64_t msr_gpa; }; struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c index 00f613c0583c..263bf3ed8fd5 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c +++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c @@ -19,7 +19,7 @@ struct gicv3_data { unsigned int nr_spis; }; -#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K) +#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K) #define DIST_BIT (1U << 31) enum gicv3_intid_range { @@ -105,7 +105,8 @@ static void gicv3_set_eoi_split(bool split) { uint32_t val; - /* All other fields are read-only, so no need to read CTLR first. In + /* + * All other fields are read-only, so no need to read CTLR first. In * fact, the kernel does the same. */ val = split ? (1U << 1) : 0; @@ -159,9 +160,10 @@ static void gicv3_access_reg(uint32_t intid, uint64_t offset, uint32_t cpu_or_dist; GUEST_ASSERT(bits_per_field <= reg_bits); - GUEST_ASSERT(*val < (1U << bits_per_field)); - /* Some registers like IROUTER are 64 bit long. Those are currently not - * supported by readl nor writel, so just asserting here until then. + GUEST_ASSERT(!write || *val < (1U << bits_per_field)); + /* + * This function does not support 64 bit accesses. Just asserting here + * until we implement readq/writeq. */ GUEST_ASSERT(reg_bits == 32); diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c index b3a0fca0d780..5d45046c1b80 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c @@ -52,7 +52,9 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, nr_vcpus, nr_vcpus_created); /* Distributor setup */ - gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, + false, &gic_fd) != 0) + return -1; kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, 0, &nr_irqs, true); @@ -138,9 +140,6 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid, uint64_t val; bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid); - /* Check that the addr part of the attr is within 32 bits. */ - assert(attr <= KVM_DEV_ARM_VGIC_OFFSET_MASK); - uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS : KVM_DEV_ARM_VGIC_GRP_DIST_REGS; @@ -150,7 +149,11 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid, attr += SZ_64K; } - /* All calls will succeed, even with invalid intid's, as long as the + /* Check that the addr part of the attr is within 32 bits. */ + assert((attr & ~KVM_DEV_ARM_VGIC_OFFSET_MASK) == 0); + + /* + * All calls will succeed, even with invalid intid's, as long as the * addr part of the attr is within 32 bits (checked above). An invalid * intid will just make the read/writes point to above the intended * register space (i.e., ICPENDR after ISPENDR). diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index d8cf851ab119..1665a220abcb 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -362,6 +362,20 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } +struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages) +{ + struct kvm_vm *vm; + + vm = vm_create(mode, pages, O_RDWR); + + kvm_vm_elf_load(vm, program_invocation_name); + +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + return vm; +} + /* * VM Create with customized parameters * @@ -412,13 +426,8 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); pages = vm_adjust_num_guest_pages(mode, pages); - vm = vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name); - -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif + vm = vm_create_without_vcpus(mode, pages); for (i = 0; i < nr_vcpus; ++i) { uint32_t vcpuid = vcpuids ? vcpuids[i] : i; @@ -709,6 +718,27 @@ void kvm_vm_free(struct kvm_vm *vmp) free(vmp); } +int kvm_memfd_alloc(size_t size, bool hugepages) +{ + int memfd_flags = MFD_CLOEXEC; + int fd, r; + + if (hugepages) + memfd_flags |= MFD_HUGETLB; + + fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(fd != -1, "memfd_create() failed, errno: %i (%s)", + errno, strerror(errno)); + + r = ftruncate(fd, size); + TEST_ASSERT(!r, "ftruncate() failed, errno: %i (%s)", errno, strerror(errno)); + + r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size); + TEST_ASSERT(!r, "fallocate() failed, errno: %i (%s)", errno, strerror(errno)); + + return fd; +} + /* * Memory Compare, host virtual to guest virtual * @@ -830,6 +860,30 @@ static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, rb_insert_color(®ion->hva_node, hva_tree); } + +int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva) +{ + struct kvm_userspace_memory_region region = { + .slot = slot, + .flags = flags, + .guest_phys_addr = gpa, + .memory_size = size, + .userspace_addr = (uintptr_t)hva, + }; + + return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion); +} + +void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva) +{ + int ret = __vm_set_user_memory_region(vm, slot, flags, gpa, size, hva); + + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed, errno = %d (%s)", + errno, strerror(errno)); +} + /* * VM Userspace Memory Region Add * @@ -937,24 +991,9 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region->mmap_size += alignment; region->fd = -1; - if (backing_src_is_shared(src_type)) { - int memfd_flags = MFD_CLOEXEC; - - if (src_type == VM_MEM_SRC_SHARED_HUGETLB) - memfd_flags |= MFD_HUGETLB; - - region->fd = memfd_create("kvm_selftest", memfd_flags); - TEST_ASSERT(region->fd != -1, - "memfd_create failed, errno: %i", errno); - - ret = ftruncate(region->fd, region->mmap_size); - TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); - - ret = fallocate(region->fd, - FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - region->mmap_size); - TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); - } + if (backing_src_is_shared(src_type)) + region->fd = kvm_memfd_alloc(region->mmap_size, + src_type == VM_MEM_SRC_SHARED_HUGETLB); region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 0ebc03ce079c..736ee4a23df6 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -43,6 +43,11 @@ vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva) svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area); svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area); + svm->msr = (void *)vm_vaddr_alloc_page(vm); + svm->msr_hva = addr_gva2hva(vm, (uintptr_t)svm->msr); + svm->msr_gpa = addr_gva2gpa(vm, (uintptr_t)svm->msr); + memset(svm->msr_hva, 0, getpagesize()); + *p_svm_gva = svm_gva; return svm; } @@ -106,6 +111,7 @@ void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_r save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR); ctrl->intercept = (1ULL << INTERCEPT_VMRUN) | (1ULL << INTERCEPT_VMMCALL); + ctrl->msrpm_base_pa = svm->msr_gpa; vmcb->save.rip = (u64)guest_rip; vmcb->save.rsp = (u64)guest_rsp; diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c new file mode 100644 index 000000000000..3875c4b23a04 --- /dev/null +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <pthread.h> +#include <semaphore.h> +#include <sys/types.h> +#include <signal.h> +#include <errno.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/atomic.h> + +#include "kvm_util.h" +#include "test_util.h" +#include "guest_modes.h" +#include "processor.h" + +static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) +{ + uint64_t gpa; + + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + *((volatile uint64_t *)gpa) = gpa; + + GUEST_DONE(); +} + +struct vcpu_info { + struct kvm_vm *vm; + uint32_t id; + uint64_t start_gpa; + uint64_t end_gpa; +}; + +static int nr_vcpus; +static atomic_t rendezvous; + +static void rendezvous_with_boss(void) +{ + int orig = atomic_read(&rendezvous); + + if (orig > 0) { + atomic_dec_and_test(&rendezvous); + while (atomic_read(&rendezvous) > 0) + cpu_relax(); + } else { + atomic_inc(&rendezvous); + while (atomic_read(&rendezvous) < 0) + cpu_relax(); + } +} + +static void run_vcpu(struct kvm_vm *vm, uint32_t vcpu_id) +{ + vcpu_run(vm, vcpu_id); + ASSERT_EQ(get_ucall(vm, vcpu_id, NULL), UCALL_DONE); +} + +static void *vcpu_worker(void *data) +{ + struct vcpu_info *vcpu = data; + struct kvm_vm *vm = vcpu->vm; + struct kvm_sregs sregs; + struct kvm_regs regs; + + vcpu_args_set(vm, vcpu->id, 3, vcpu->start_gpa, vcpu->end_gpa, + vm_get_page_size(vm)); + + /* Snapshot regs before the first run. */ + vcpu_regs_get(vm, vcpu->id, ®s); + rendezvous_with_boss(); + + run_vcpu(vm, vcpu->id); + rendezvous_with_boss(); + vcpu_regs_set(vm, vcpu->id, ®s); + vcpu_sregs_get(vm, vcpu->id, &sregs); +#ifdef __x86_64__ + /* Toggle CR0.WP to trigger a MMU context reset. */ + sregs.cr0 ^= X86_CR0_WP; +#endif + vcpu_sregs_set(vm, vcpu->id, &sregs); + rendezvous_with_boss(); + + run_vcpu(vm, vcpu->id); + rendezvous_with_boss(); + + return NULL; +} + +static pthread_t *spawn_workers(struct kvm_vm *vm, uint64_t start_gpa, + uint64_t end_gpa) +{ + struct vcpu_info *info; + uint64_t gpa, nr_bytes; + pthread_t *threads; + int i; + + threads = malloc(nr_vcpus * sizeof(*threads)); + TEST_ASSERT(threads, "Failed to allocate vCPU threads"); + + info = malloc(nr_vcpus * sizeof(*info)); + TEST_ASSERT(info, "Failed to allocate vCPU gpa ranges"); + + nr_bytes = ((end_gpa - start_gpa) / nr_vcpus) & + ~((uint64_t)vm_get_page_size(vm) - 1); + TEST_ASSERT(nr_bytes, "C'mon, no way you have %d CPUs", nr_vcpus); + + for (i = 0, gpa = start_gpa; i < nr_vcpus; i++, gpa += nr_bytes) { + info[i].vm = vm; + info[i].id = i; + info[i].start_gpa = gpa; + info[i].end_gpa = gpa + nr_bytes; + pthread_create(&threads[i], NULL, vcpu_worker, &info[i]); + } + return threads; +} + +static void rendezvous_with_vcpus(struct timespec *time, const char *name) +{ + int i, rendezvoused; + + pr_info("Waiting for vCPUs to finish %s...\n", name); + + rendezvoused = atomic_read(&rendezvous); + for (i = 0; abs(rendezvoused) != 1; i++) { + usleep(100); + if (!(i & 0x3f)) + pr_info("\r%d vCPUs haven't rendezvoused...", + abs(rendezvoused) - 1); + rendezvoused = atomic_read(&rendezvous); + } + + clock_gettime(CLOCK_MONOTONIC, time); + + /* Release the vCPUs after getting the time of the previous action. */ + pr_info("\rAll vCPUs finished %s, releasing...\n", name); + if (rendezvoused > 0) + atomic_set(&rendezvous, -nr_vcpus - 1); + else + atomic_set(&rendezvous, nr_vcpus + 1); +} + +static void calc_default_nr_vcpus(void) +{ + cpu_set_t possible_mask; + int r; + + r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask); + TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", + errno, strerror(errno)); + + nr_vcpus = CPU_COUNT(&possible_mask) * 3/4; + TEST_ASSERT(nr_vcpus > 0, "Uh, no CPUs?"); +} + +int main(int argc, char *argv[]) +{ + /* + * Skip the first 4gb and slot0. slot0 maps <1gb and is used to back + * the guest's code, stack, and page tables. Because selftests creates + * an IRQCHIP, a.k.a. a local APIC, KVM creates an internal memslot + * just below the 4gb boundary. This test could create memory at + * 1gb-3gb,but it's simpler to skip straight to 4gb. + */ + const uint64_t size_1gb = (1 << 30); + const uint64_t start_gpa = (4ull * size_1gb); + const int first_slot = 1; + + struct timespec time_start, time_run1, time_reset, time_run2; + uint64_t max_gpa, gpa, slot_size, max_mem, i; + int max_slots, slot, opt, fd; + bool hugepages = false; + pthread_t *threads; + struct kvm_vm *vm; + void *mem; + + /* + * Default to 2gb so that maxing out systems with MAXPHADDR=46, which + * are quite common for x86, requires changing only max_mem (KVM allows + * 32k memslots, 32k * 2gb == ~64tb of guest memory). + */ + slot_size = 2 * size_1gb; + + max_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); + TEST_ASSERT(max_slots > first_slot, "KVM is broken"); + + /* All KVM MMUs should be able to survive a 128gb guest. */ + max_mem = 128 * size_1gb; + + calc_default_nr_vcpus(); + + while ((opt = getopt(argc, argv, "c:h:m:s:H")) != -1) { + switch (opt) { + case 'c': + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0, "number of vcpus must be >0"); + break; + case 'm': + max_mem = atoi(optarg) * size_1gb; + TEST_ASSERT(max_mem > 0, "memory size must be >0"); + break; + case 's': + slot_size = atoi(optarg) * size_1gb; + TEST_ASSERT(slot_size > 0, "slot size must be >0"); + break; + case 'H': + hugepages = true; + break; + case 'h': + default: + printf("usage: %s [-c nr_vcpus] [-m max_mem_in_gb] [-s slot_size_in_gb] [-H]\n", argv[0]); + exit(1); + } + } + + vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); + + max_gpa = vm_get_max_gfn(vm) << vm_get_page_shift(vm); + TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb "); + + fd = kvm_memfd_alloc(slot_size, hugepages); + mem = mmap(NULL, slot_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() failed"); + + TEST_ASSERT(!madvise(mem, slot_size, MADV_NOHUGEPAGE), "madvise() failed"); + + /* Pre-fault the memory to avoid taking mmap_sem on guest page faults. */ + for (i = 0; i < slot_size; i += vm_get_page_size(vm)) + ((uint8_t *)mem)[i] = 0xaa; + + gpa = 0; + for (slot = first_slot; slot < max_slots; slot++) { + gpa = start_gpa + ((slot - first_slot) * slot_size); + if (gpa + slot_size > max_gpa) + break; + + if ((gpa - start_gpa) >= max_mem) + break; + + vm_set_user_memory_region(vm, slot, 0, gpa, slot_size, mem); + +#ifdef __x86_64__ + /* Identity map memory in the guest using 1gb pages. */ + for (i = 0; i < slot_size; i += size_1gb) + __virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G); +#else + for (i = 0; i < slot_size; i += vm_get_page_size(vm)) + virt_pg_map(vm, gpa + i, gpa + i); +#endif + } + + atomic_set(&rendezvous, nr_vcpus + 1); + threads = spawn_workers(vm, start_gpa, gpa); + + pr_info("Running with %lugb of guest memory and %u vCPUs\n", + (gpa - start_gpa) / size_1gb, nr_vcpus); + + rendezvous_with_vcpus(&time_start, "spawning"); + rendezvous_with_vcpus(&time_run1, "run 1"); + rendezvous_with_vcpus(&time_reset, "reset"); + rendezvous_with_vcpus(&time_run2, "run 2"); + + time_run2 = timespec_sub(time_run2, time_reset); + time_reset = timespec_sub(time_reset, time_run1); + time_run1 = timespec_sub(time_run1, time_start); + + pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 = %ld.%.9lds\n", + time_run1.tv_sec, time_run1.tv_nsec, + time_reset.tv_sec, time_reset.tv_nsec, + time_run2.tv_sec, time_run2.tv_nsec); + + /* + * Delete even numbered slots (arbitrary) and unmap the first half of + * the backing (also arbitrary) to verify KVM correctly drops all + * references to the removed regions. + */ + for (slot = (slot - 1) & ~1ull; slot >= first_slot; slot -= 2) + vm_set_user_memory_region(vm, slot, 0, 0, 0, NULL); + + munmap(mem, slot_size / 2); + + /* Sanity check that the vCPUs actually ran. */ + for (i = 0; i < nr_vcpus; i++) + pthread_join(threads[i], NULL); + + /* + * Deliberately exit without deleting the remaining memslots or closing + * kvm_fd to test cleanup via mmu_notifier.release. + */ +} diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 9f49ead380ab..b04c2c1b3c30 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -13,154 +13,668 @@ #include "test_util.h" #include "kvm_util.h" +enum mop_target { + LOGICAL, + SIDA, + ABSOLUTE, + INVALID, +}; + +enum mop_access_mode { + READ, + WRITE, +}; + +struct mop_desc { + uintptr_t gaddr; + uintptr_t gaddr_v; + uint64_t set_flags; + unsigned int f_check : 1; + unsigned int f_inject : 1; + unsigned int f_key : 1; + unsigned int _gaddr_v : 1; + unsigned int _set_flags : 1; + unsigned int _sida_offset : 1; + unsigned int _ar : 1; + uint32_t size; + enum mop_target target; + enum mop_access_mode mode; + void *buf; + uint32_t sida_offset; + uint8_t ar; + uint8_t key; +}; + +static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc desc) +{ + struct kvm_s390_mem_op ksmo = { + .gaddr = (uintptr_t)desc.gaddr, + .size = desc.size, + .buf = ((uintptr_t)desc.buf), + .reserved = "ignored_ignored_ignored_ignored" + }; + + switch (desc.target) { + case LOGICAL: + if (desc.mode == READ) + ksmo.op = KVM_S390_MEMOP_LOGICAL_READ; + if (desc.mode == WRITE) + ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; + break; + case SIDA: + if (desc.mode == READ) + ksmo.op = KVM_S390_MEMOP_SIDA_READ; + if (desc.mode == WRITE) + ksmo.op = KVM_S390_MEMOP_SIDA_WRITE; + break; + case ABSOLUTE: + if (desc.mode == READ) + ksmo.op = KVM_S390_MEMOP_ABSOLUTE_READ; + if (desc.mode == WRITE) + ksmo.op = KVM_S390_MEMOP_ABSOLUTE_WRITE; + break; + case INVALID: + ksmo.op = -1; + } + if (desc.f_check) + ksmo.flags |= KVM_S390_MEMOP_F_CHECK_ONLY; + if (desc.f_inject) + ksmo.flags |= KVM_S390_MEMOP_F_INJECT_EXCEPTION; + if (desc._set_flags) + ksmo.flags = desc.set_flags; + if (desc.f_key) { + ksmo.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION; + ksmo.key = desc.key; + } + if (desc._ar) + ksmo.ar = desc.ar; + else + ksmo.ar = 0; + if (desc._sida_offset) + ksmo.sida_offset = desc.sida_offset; + + return ksmo; +} + +/* vcpu dummy id signifying that vm instead of vcpu ioctl is to occur */ +const uint32_t VM_VCPU_ID = (uint32_t)-1; + +struct test_vcpu { + struct kvm_vm *vm; + uint32_t id; +}; + +#define PRINT_MEMOP false +static void print_memop(uint32_t vcpu_id, const struct kvm_s390_mem_op *ksmo) +{ + if (!PRINT_MEMOP) + return; + + if (vcpu_id == VM_VCPU_ID) + printf("vm memop("); + else + printf("vcpu memop("); + switch (ksmo->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + printf("LOGICAL, READ, "); + break; + case KVM_S390_MEMOP_LOGICAL_WRITE: + printf("LOGICAL, WRITE, "); + break; + case KVM_S390_MEMOP_SIDA_READ: + printf("SIDA, READ, "); + break; + case KVM_S390_MEMOP_SIDA_WRITE: + printf("SIDA, WRITE, "); + break; + case KVM_S390_MEMOP_ABSOLUTE_READ: + printf("ABSOLUTE, READ, "); + break; + case KVM_S390_MEMOP_ABSOLUTE_WRITE: + printf("ABSOLUTE, WRITE, "); + break; + } + printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u", + ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key); + if (ksmo->flags & KVM_S390_MEMOP_F_CHECK_ONLY) + printf(", CHECK_ONLY"); + if (ksmo->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) + printf(", INJECT_EXCEPTION"); + if (ksmo->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) + printf(", SKEY_PROTECTION"); + puts(")"); +} + +static void memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) +{ + if (vcpu.id == VM_VCPU_ID) + vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo); + else + vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo); +} + +static int err_memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) +{ + if (vcpu.id == VM_VCPU_ID) + return _vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo); + else + return _vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo); +} + +#define MEMOP(err, vcpu_p, mop_target_p, access_mode_p, buf_p, size_p, ...) \ +({ \ + struct test_vcpu __vcpu = (vcpu_p); \ + struct mop_desc __desc = { \ + .target = (mop_target_p), \ + .mode = (access_mode_p), \ + .buf = (buf_p), \ + .size = (size_p), \ + __VA_ARGS__ \ + }; \ + struct kvm_s390_mem_op __ksmo; \ + \ + if (__desc._gaddr_v) { \ + if (__desc.target == ABSOLUTE) \ + __desc.gaddr = addr_gva2gpa(__vcpu.vm, __desc.gaddr_v); \ + else \ + __desc.gaddr = __desc.gaddr_v; \ + } \ + __ksmo = ksmo_from_desc(__desc); \ + print_memop(__vcpu.id, &__ksmo); \ + err##memop_ioctl(__vcpu, &__ksmo); \ +}) + +#define MOP(...) MEMOP(, __VA_ARGS__) +#define ERR_MOP(...) MEMOP(err_, __VA_ARGS__) + +#define GADDR(a) .gaddr = ((uintptr_t)a) +#define GADDR_V(v) ._gaddr_v = 1, .gaddr_v = ((uintptr_t)v) +#define CHECK_ONLY .f_check = 1 +#define SET_FLAGS(f) ._set_flags = 1, .set_flags = (f) +#define SIDA_OFFSET(o) ._sida_offset = 1, .sida_offset = (o) +#define AR(a) ._ar = 1, .ar = (a) +#define KEY(a) .f_key = 1, .key = (a) + +#define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) + #define VCPU_ID 1 +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1ULL << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) +#define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) static uint8_t mem1[65536]; static uint8_t mem2[65536]; -static void guest_code(void) +struct test_default { + struct kvm_vm *kvm_vm; + struct test_vcpu vm; + struct test_vcpu vcpu; + struct kvm_run *run; + int size; +}; + +static struct test_default test_default_init(void *guest_code) +{ + struct test_default t; + + t.size = min((size_t)kvm_check_cap(KVM_CAP_S390_MEM_OP), sizeof(mem1)); + t.kvm_vm = vm_create_default(VCPU_ID, 0, guest_code); + t.vm = (struct test_vcpu) { t.kvm_vm, VM_VCPU_ID }; + t.vcpu = (struct test_vcpu) { t.kvm_vm, VCPU_ID }; + t.run = vcpu_state(t.kvm_vm, VCPU_ID); + return t; +} + +enum stage { + /* Synced state set by host, e.g. DAT */ + STAGE_INITED, + /* Guest did nothing */ + STAGE_IDLED, + /* Guest set storage keys (specifics up to test case) */ + STAGE_SKEYS_SET, + /* Guest copied memory (locations up to test case) */ + STAGE_COPIED, +}; + +#define HOST_SYNC(vcpu_p, stage) \ +({ \ + struct test_vcpu __vcpu = (vcpu_p); \ + struct ucall uc; \ + int __stage = (stage); \ + \ + vcpu_run(__vcpu.vm, __vcpu.id); \ + get_ucall(__vcpu.vm, __vcpu.id, &uc); \ + ASSERT_EQ(uc.cmd, UCALL_SYNC); \ + ASSERT_EQ(uc.args[1], __stage); \ +}) \ + +static void prepare_mem12(void) { int i; + for (i = 0; i < sizeof(mem1); i++) + mem1[i] = rand(); + memset(mem2, 0xaa, sizeof(mem2)); +} + +#define ASSERT_MEM_EQ(p1, p2, size) \ + TEST_ASSERT(!memcmp(p1, p2, size), "Memory contents do not match!") + +#define DEFAULT_WRITE_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ +({ \ + struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ + enum mop_target __target = (mop_target_p); \ + uint32_t __size = (size); \ + \ + prepare_mem12(); \ + CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ + GADDR_V(mem1), ##__VA_ARGS__); \ + HOST_SYNC(__copy_cpu, STAGE_COPIED); \ + CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, \ + GADDR_V(mem2), ##__VA_ARGS__); \ + ASSERT_MEM_EQ(mem1, mem2, __size); \ +}) + +#define DEFAULT_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ +({ \ + struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ + enum mop_target __target = (mop_target_p); \ + uint32_t __size = (size); \ + \ + prepare_mem12(); \ + CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ + GADDR_V(mem1)); \ + HOST_SYNC(__copy_cpu, STAGE_COPIED); \ + CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, ##__VA_ARGS__);\ + ASSERT_MEM_EQ(mem1, mem2, __size); \ +}) + +static void guest_copy(void) +{ + GUEST_SYNC(STAGE_INITED); + memcpy(&mem2, &mem1, sizeof(mem2)); + GUEST_SYNC(STAGE_COPIED); +} + +static void test_copy(void) +{ + struct test_default t = test_default_init(guest_copy); + + HOST_SYNC(t.vcpu, STAGE_INITED); + + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size); + + kvm_vm_free(t.kvm_vm); +} + +static void set_storage_key_range(void *addr, size_t len, uint8_t key) +{ + uintptr_t _addr, abs, i; + int not_mapped = 0; + + _addr = (uintptr_t)addr; + for (i = _addr & PAGE_MASK; i < _addr + len; i += PAGE_SIZE) { + abs = i; + asm volatile ( + "lra %[abs], 0(0,%[abs])\n" + " jz 0f\n" + " llill %[not_mapped],1\n" + " j 1f\n" + "0: sske %[key], %[abs]\n" + "1:" + : [abs] "+&a" (abs), [not_mapped] "+r" (not_mapped) + : [key] "r" (key) + : "cc" + ); + GUEST_ASSERT_EQ(not_mapped, 0); + } +} + +static void guest_copy_key(void) +{ + set_storage_key_range(mem1, sizeof(mem1), 0x90); + set_storage_key_range(mem2, sizeof(mem2), 0x90); + GUEST_SYNC(STAGE_SKEYS_SET); + for (;;) { - for (i = 0; i < sizeof(mem2); i++) - mem2[i] = mem1[i]; - GUEST_SYNC(0); + memcpy(&mem2, &mem1, sizeof(mem2)); + GUEST_SYNC(STAGE_COPIED); } } -int main(int argc, char *argv[]) +static void test_copy_key(void) { - struct kvm_vm *vm; - struct kvm_run *run; - struct kvm_s390_mem_op ksmo; - int rv, i, maxsize; + struct test_default t = test_default_init(guest_copy_key); - setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); - maxsize = kvm_check_cap(KVM_CAP_S390_MEM_OP); - if (!maxsize) { - print_skip("CAP_S390_MEM_OP not supported"); - exit(KSFT_SKIP); + /* vm, no key */ + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size); + + /* vm/vcpu, machting key or key 0 */ + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(9)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(9)); + /* + * There used to be different code paths for key handling depending on + * if the region crossed a page boundary. + * There currently are not, but the more tests the merrier. + */ + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(9)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(9)); + + /* vm/vcpu, mismatching keys on read, but no fetch protection */ + DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(2)); + DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem1), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void guest_copy_key_fetch_prot(void) +{ + /* + * For some reason combining the first sync with override enablement + * results in an exception when calling HOST_SYNC. + */ + GUEST_SYNC(STAGE_INITED); + /* Storage protection override applies to both store and fetch. */ + set_storage_key_range(mem1, sizeof(mem1), 0x98); + set_storage_key_range(mem2, sizeof(mem2), 0x98); + GUEST_SYNC(STAGE_SKEYS_SET); + + for (;;) { + memcpy(&mem2, &mem1, sizeof(mem2)); + GUEST_SYNC(STAGE_COPIED); } - if (maxsize > sizeof(mem1)) - maxsize = sizeof(mem1); +} - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); +static void test_copy_key_storage_prot_override(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); - for (i = 0; i < sizeof(mem1); i++) - mem1[i] = i * i + i; - - /* Set the first array */ - ksmo.gaddr = addr_gva2gpa(vm, (uintptr_t)mem1); - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); - - /* Let the guest code copy the first array to the second */ - vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, - "Unexpected exit reason: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); - memset(mem2, 0xaa, sizeof(mem2)); + /* vcpu, mismatching keys, storage protection override in effect */ + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void test_copy_key_fetch_prot(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); - /* Get the second array */ - ksmo.gaddr = (uintptr_t)mem2; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_READ; - ksmo.buf = (uintptr_t)mem2; - ksmo.ar = 0; - vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); - - TEST_ASSERT(!memcmp(mem1, mem2, maxsize), - "Memory contents do not match!"); - - /* Check error conditions - first bad size: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = -1; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vm/vcpu, matching key, fetch protection in effect */ + DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(9)); + DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem2), KEY(9)); + + kvm_vm_free(t.kvm_vm); +} + +#define ERR_PROT_MOP(...) \ +({ \ + int rv; \ + \ + rv = ERR_MOP(__VA_ARGS__); \ + TEST_ASSERT(rv == 4, "Should result in protection exception"); \ +}) + +static void test_errors_key(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); + + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vm/vcpu, mismatching keys, fetch protection in effect */ + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_key_storage_prot_override(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); + + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vm, mismatching keys, storage protection override not applicable to vm */ + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +const uint64_t last_page_addr = -PAGE_SIZE; + +static void guest_copy_key_fetch_prot_override(void) +{ + int i; + char *page_0 = 0; + + GUEST_SYNC(STAGE_INITED); + set_storage_key_range(0, PAGE_SIZE, 0x18); + set_storage_key_range((void *)last_page_addr, PAGE_SIZE, 0x0); + asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0), [key] "r"(0x18) : "cc"); + GUEST_SYNC(STAGE_SKEYS_SET); + + for (;;) { + for (i = 0; i < PAGE_SIZE; i++) + page_0[i] = mem1[i]; + GUEST_SYNC(STAGE_COPIED); + } +} + +static void test_copy_key_fetch_prot_override(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); + vm_vaddr_t guest_0_page, guest_last_page; + + guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + if (guest_0_page != 0 || guest_last_page != last_page_addr) { + print_skip("did not allocate guest pages at required positions"); + goto out; + } + + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vcpu, mismatching keys on fetch, fetch protection override applies */ + prepare_mem12(); + MOP(t.vcpu, LOGICAL, WRITE, mem1, PAGE_SIZE, GADDR_V(mem1)); + HOST_SYNC(t.vcpu, STAGE_COPIED); + CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2)); + ASSERT_MEM_EQ(mem1, mem2, 2048); + + /* + * vcpu, mismatching keys on fetch, fetch protection override applies, + * wraparound + */ + prepare_mem12(); + MOP(t.vcpu, LOGICAL, WRITE, mem1, 2 * PAGE_SIZE, GADDR_V(guest_last_page)); + HOST_SYNC(t.vcpu, STAGE_COPIED); + CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048, + GADDR_V(guest_last_page), KEY(2)); + ASSERT_MEM_EQ(mem1, mem2, 2048); + +out: + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_key_fetch_prot_override_not_enabled(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); + vm_vaddr_t guest_0_page, guest_last_page; + + guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + if (guest_0_page != 0 || guest_last_page != last_page_addr) { + print_skip("did not allocate guest pages at required positions"); + goto out; + } + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vcpu, mismatching keys on fetch, fetch protection override not enabled */ + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(0), KEY(2)); + +out: + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_key_fetch_prot_override_enabled(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); + vm_vaddr_t guest_0_page, guest_last_page; + + guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + if (guest_0_page != 0 || guest_last_page != last_page_addr) { + print_skip("did not allocate guest pages at required positions"); + goto out; + } + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* + * vcpu, mismatching keys on fetch, + * fetch protection override does not apply because memory range acceeded + */ + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048 + 1, GADDR_V(0), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048 + 1, + GADDR_V(guest_last_page), KEY(2)); + /* vm, fetch protected override does not apply */ + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR(0), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2)); + +out: + kvm_vm_free(t.kvm_vm); +} + +static void guest_idle(void) +{ + GUEST_SYNC(STAGE_INITED); /* for consistency's sake */ + for (;;) + GUEST_SYNC(STAGE_IDLED); +} + +static void _test_errors_common(struct test_vcpu vcpu, enum mop_target target, int size) +{ + int rv; + + /* Bad size: */ + rv = ERR_MOP(vcpu, target, WRITE, mem1, -1, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && errno == E2BIG, "ioctl allows insane sizes"); /* Zero size: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = 0; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, mem1, 0, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && (errno == EINVAL || errno == ENOMEM), "ioctl allows 0 as size"); /* Bad flags: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = -1; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), SET_FLAGS(-1)); TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows all flags"); - /* Bad operation: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = -1; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); - TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations"); - /* Bad guest address: */ - ksmo.gaddr = ~0xfffUL; - ksmo.flags = KVM_S390_MEMOP_F_CHECK_ONLY; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY); TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory access"); /* Bad host address: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = 0; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, 0, size, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && errno == EFAULT, "ioctl does not report bad host memory address"); + /* Bad key: */ + rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), KEY(17)); + TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows invalid key"); +} + +static void test_errors(void) +{ + struct test_default t = test_default_init(guest_idle); + int rv; + + HOST_SYNC(t.vcpu, STAGE_INITED); + + _test_errors_common(t.vcpu, LOGICAL, t.size); + _test_errors_common(t.vm, ABSOLUTE, t.size); + + /* Bad operation: */ + rv = ERR_MOP(t.vcpu, INVALID, WRITE, mem1, t.size, GADDR_V(mem1)); + TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations"); + /* virtual addresses are not translated when passing INVALID */ + rv = ERR_MOP(t.vm, INVALID, WRITE, mem1, PAGE_SIZE, GADDR(0)); + TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations"); + /* Bad access register: */ - run->psw_mask &= ~(3UL << (63 - 17)); - run->psw_mask |= 1UL << (63 - 17); /* Enable AR mode */ - vcpu_run(vm, VCPU_ID); /* To sync new state to SIE block */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 17; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + t.run->psw_mask &= ~(3UL << (63 - 17)); + t.run->psw_mask |= 1UL << (63 - 17); /* Enable AR mode */ + HOST_SYNC(t.vcpu, STAGE_IDLED); /* To sync new state to SIE block */ + rv = ERR_MOP(t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), AR(17)); TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows ARs > 15"); - run->psw_mask &= ~(3UL << (63 - 17)); /* Disable AR mode */ - vcpu_run(vm, VCPU_ID); /* Run to sync new state */ + t.run->psw_mask &= ~(3UL << (63 - 17)); /* Disable AR mode */ + HOST_SYNC(t.vcpu, STAGE_IDLED); /* Run to sync new state */ + + /* Check that the SIDA calls are rejected for non-protected guests */ + rv = ERR_MOP(t.vcpu, SIDA, READ, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl does not reject SIDA_READ in non-protected mode"); + rv = ERR_MOP(t.vcpu, SIDA, WRITE, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl does not reject SIDA_WRITE in non-protected mode"); + + kvm_vm_free(t.kvm_vm); +} - kvm_vm_free(vm); +int main(int argc, char *argv[]) +{ + int memop_cap, extension_cap; + + setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ + + memop_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP); + extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); + if (!memop_cap) { + print_skip("CAP_S390_MEM_OP not supported"); + exit(KSFT_SKIP); + } + + test_copy(); + if (extension_cap > 0) { + test_copy_key(); + test_copy_key_storage_prot_override(); + test_copy_key_fetch_prot(); + test_copy_key_fetch_prot_override(); + test_errors_key(); + test_errors_key_storage_prot_override(); + test_errors_key_fetch_prot_override_not_enabled(); + test_errors_key_fetch_prot_override_enabled(); + } else { + print_skip("storage key memop extension not supported"); + } + test_errors(); return 0; } diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c new file mode 100644 index 000000000000..c097b9db495e --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test TEST PROTECTION emulation. + * + * Copyright IBM Corp. 2021 + */ + +#include <sys/mman.h> +#include "test_util.h" +#include "kvm_util.h" + +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1 << PAGE_SHIFT) +#define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) +#define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) + +#define VCPU_ID 1 + +static __aligned(PAGE_SIZE) uint8_t pages[2][PAGE_SIZE]; +static uint8_t *const page_store_prot = pages[0]; +static uint8_t *const page_fetch_prot = pages[1]; + +/* Nonzero return value indicates that address not mapped */ +static int set_storage_key(void *addr, uint8_t key) +{ + int not_mapped = 0; + + asm volatile ( + "lra %[addr], 0(0,%[addr])\n" + " jz 0f\n" + " llill %[not_mapped],1\n" + " j 1f\n" + "0: sske %[key], %[addr]\n" + "1:" + : [addr] "+&a" (addr), [not_mapped] "+r" (not_mapped) + : [key] "r" (key) + : "cc" + ); + return -not_mapped; +} + +enum permission { + READ_WRITE = 0, + READ = 1, + RW_PROTECTED = 2, + TRANSL_UNAVAIL = 3, +}; + +static enum permission test_protection(void *addr, uint8_t key) +{ + uint64_t mask; + + asm volatile ( + "tprot %[addr], 0(%[key])\n" + " ipm %[mask]\n" + : [mask] "=r" (mask) + : [addr] "Q" (*(char *)addr), + [key] "a" (key) + : "cc" + ); + + return (enum permission)(mask >> 28); +} + +enum stage { + STAGE_END, + STAGE_INIT_SIMPLE, + TEST_SIMPLE, + STAGE_INIT_FETCH_PROT_OVERRIDE, + TEST_FETCH_PROT_OVERRIDE, + TEST_STORAGE_PROT_OVERRIDE, +}; + +struct test { + enum stage stage; + void *addr; + uint8_t key; + enum permission expected; +} tests[] = { + /* + * We perform each test in the array by executing TEST PROTECTION on + * the specified addr with the specified key and checking if the returned + * permissions match the expected value. + * Both guest and host cooperate to set up the required test conditions. + * A central condition is that the page targeted by addr has to be DAT + * protected in the host mappings, in order for KVM to emulate the + * TEST PROTECTION instruction. + * Since the page tables are shared, the host uses mprotect to achieve + * this. + * + * Test resulting in RW_PROTECTED/TRANSL_UNAVAIL will be interpreted + * by SIE, not KVM, but there is no harm in testing them also. + * See Enhanced Suppression-on-Protection Facilities in the + * Interpretive-Execution Mode + */ + /* + * guest: set storage key of page_store_prot to 1 + * storage key of page_fetch_prot to 9 and enable + * protection for it + * STAGE_INIT_SIMPLE + * host: write protect both via mprotect + */ + /* access key 0 matches any storage key -> RW */ + { TEST_SIMPLE, page_store_prot, 0x00, READ_WRITE }, + /* access key matches storage key -> RW */ + { TEST_SIMPLE, page_store_prot, 0x10, READ_WRITE }, + /* mismatched keys, but no fetch protection -> RO */ + { TEST_SIMPLE, page_store_prot, 0x20, READ }, + /* access key 0 matches any storage key -> RW */ + { TEST_SIMPLE, page_fetch_prot, 0x00, READ_WRITE }, + /* access key matches storage key -> RW */ + { TEST_SIMPLE, page_fetch_prot, 0x90, READ_WRITE }, + /* mismatched keys, fetch protection -> inaccessible */ + { TEST_SIMPLE, page_fetch_prot, 0x10, RW_PROTECTED }, + /* page 0 not mapped yet -> translation not available */ + { TEST_SIMPLE, (void *)0x00, 0x10, TRANSL_UNAVAIL }, + /* + * host: try to map page 0 + * guest: set storage key of page 0 to 9 and enable fetch protection + * STAGE_INIT_FETCH_PROT_OVERRIDE + * host: write protect page 0 + * enable fetch protection override + */ + /* mismatched keys, fetch protection, but override applies -> RO */ + { TEST_FETCH_PROT_OVERRIDE, (void *)0x00, 0x10, READ }, + /* mismatched keys, fetch protection, override applies to 0-2048 only -> inaccessible */ + { TEST_FETCH_PROT_OVERRIDE, (void *)2049, 0x10, RW_PROTECTED }, + /* + * host: enable storage protection override + */ + /* mismatched keys, but override applies (storage key 9) -> RW */ + { TEST_STORAGE_PROT_OVERRIDE, page_fetch_prot, 0x10, READ_WRITE }, + /* mismatched keys, no fetch protection, override doesn't apply -> RO */ + { TEST_STORAGE_PROT_OVERRIDE, page_store_prot, 0x20, READ }, + /* mismatched keys, but override applies (storage key 9) -> RW */ + { TEST_STORAGE_PROT_OVERRIDE, (void *)2049, 0x10, READ_WRITE }, + /* end marker */ + { STAGE_END, 0, 0, 0 }, +}; + +static enum stage perform_next_stage(int *i, bool mapped_0) +{ + enum stage stage = tests[*i].stage; + enum permission result; + bool skip; + + for (; tests[*i].stage == stage; (*i)++) { + /* + * Some fetch protection override tests require that page 0 + * be mapped, however, when the hosts tries to map that page via + * vm_vaddr_alloc, it may happen that some other page gets mapped + * instead. + * In order to skip these tests we detect this inside the guest + */ + skip = tests[*i].addr < (void *)4096 && + tests[*i].expected != TRANSL_UNAVAIL && + !mapped_0; + if (!skip) { + result = test_protection(tests[*i].addr, tests[*i].key); + GUEST_ASSERT_2(result == tests[*i].expected, *i, result); + } + } + return stage; +} + +static void guest_code(void) +{ + bool mapped_0; + int i = 0; + + GUEST_ASSERT_EQ(set_storage_key(page_store_prot, 0x10), 0); + GUEST_ASSERT_EQ(set_storage_key(page_fetch_prot, 0x98), 0); + GUEST_SYNC(STAGE_INIT_SIMPLE); + GUEST_SYNC(perform_next_stage(&i, false)); + + /* Fetch-protection override */ + mapped_0 = !set_storage_key((void *)0, 0x98); + GUEST_SYNC(STAGE_INIT_FETCH_PROT_OVERRIDE); + GUEST_SYNC(perform_next_stage(&i, mapped_0)); + + /* Storage-protection override */ + GUEST_SYNC(perform_next_stage(&i, mapped_0)); +} + +#define HOST_SYNC(vmp, stage) \ +({ \ + struct kvm_vm *__vm = (vmp); \ + struct ucall uc; \ + int __stage = (stage); \ + \ + vcpu_run(__vm, VCPU_ID); \ + get_ucall(__vm, VCPU_ID, &uc); \ + if (uc.cmd == UCALL_ABORT) { \ + TEST_FAIL("line %lu: %s, hints: %lu, %lu", uc.args[1], \ + (const char *)uc.args[0], uc.args[2], uc.args[3]); \ + } \ + ASSERT_EQ(uc.cmd, UCALL_SYNC); \ + ASSERT_EQ(uc.args[1], __stage); \ +}) + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_run *run; + vm_vaddr_t guest_0_page; + + vm = vm_create_default(VCPU_ID, 0, guest_code); + run = vcpu_state(vm, VCPU_ID); + + HOST_SYNC(vm, STAGE_INIT_SIMPLE); + mprotect(addr_gva2hva(vm, (vm_vaddr_t)pages), PAGE_SIZE * 2, PROT_READ); + HOST_SYNC(vm, TEST_SIMPLE); + + guest_0_page = vm_vaddr_alloc(vm, PAGE_SIZE, 0); + if (guest_0_page != 0) + print_skip("Did not allocate page at 0 for fetch protection override tests"); + HOST_SYNC(vm, STAGE_INIT_FETCH_PROT_OVERRIDE); + if (guest_0_page == 0) + mprotect(addr_gva2hva(vm, (vm_vaddr_t)0), PAGE_SIZE, PROT_READ); + run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; + run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(vm, TEST_FETCH_PROT_OVERRIDE); + + run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE; + run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(vm, TEST_STORAGE_PROT_OVERRIDE); +} diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 72a1c9b4882c..73bc297dabe6 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -329,22 +329,6 @@ static void test_zero_memory_regions(void) } #endif /* __x86_64__ */ -static int test_memory_region_add(struct kvm_vm *vm, void *mem, uint32_t slot, - uint32_t size, uint64_t guest_addr) -{ - struct kvm_userspace_memory_region region; - int ret; - - region.slot = slot; - region.flags = 0; - region.guest_phys_addr = guest_addr; - region.memory_size = size; - region.userspace_addr = (uintptr_t) mem; - ret = ioctl(vm_get_fd(vm), KVM_SET_USER_MEMORY_REGION, ®ion); - - return ret; -} - /* * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any * tentative to add further slots should fail. @@ -382,23 +366,20 @@ static void test_add_max_memory_regions(void) TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host"); mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1)); - for (slot = 0; slot < max_mem_slots; slot++) { - ret = test_memory_region_add(vm, mem_aligned + - ((uint64_t)slot * MEM_REGION_SIZE), - slot, MEM_REGION_SIZE, - (uint64_t)slot * MEM_REGION_SIZE); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" - " rc: %i errno: %i slot: %i\n", - ret, errno, slot); - } + for (slot = 0; slot < max_mem_slots; slot++) + vm_set_user_memory_region(vm, slot, 0, + ((uint64_t)slot * MEM_REGION_SIZE), + MEM_REGION_SIZE, + mem_aligned + (uint64_t)slot * MEM_REGION_SIZE); /* Check it cannot be added memory slots beyond the limit */ mem_extra = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); TEST_ASSERT(mem_extra != MAP_FAILED, "Failed to mmap() host"); - ret = test_memory_region_add(vm, mem_extra, max_mem_slots, MEM_REGION_SIZE, - (uint64_t)max_mem_slots * MEM_REGION_SIZE); + ret = __vm_set_user_memory_region(vm, max_mem_slots, 0, + (uint64_t)max_mem_slots * MEM_REGION_SIZE, + MEM_REGION_SIZE, mem_extra); TEST_ASSERT(ret == -1 && errno == EINVAL, "Adding one more memory slot should fail with EINVAL"); diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 4c7841dfd481..d12e043aa2ee 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -10,6 +10,7 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> +#include <linux/bitmap.h> #include "test_util.h" @@ -32,6 +33,22 @@ static void guest_nmi_handler(struct ex_regs *regs) { } +/* Exits to L1 destroy GRPs! */ +static inline void rdmsr_fs_base(void) +{ + __asm__ __volatile__ ("mov $0xc0000100, %%rcx; rdmsr" : : : + "rax", "rbx", "rcx", "rdx", + "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", + "r13", "r14", "r15"); +} +static inline void rdmsr_gs_base(void) +{ + __asm__ __volatile__ ("mov $0xc0000101, %%rcx; rdmsr" : : : + "rax", "rbx", "rcx", "rdx", + "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", + "r13", "r14", "r15"); +} + void l2_guest_code(void) { GUEST_SYNC(7); @@ -41,6 +58,15 @@ void l2_guest_code(void) /* Forced exit to L1 upon restore */ GUEST_SYNC(9); + vmcall(); + + /* MSR-Bitmap tests */ + rdmsr_fs_base(); /* intercepted */ + rdmsr_fs_base(); /* intercepted */ + rdmsr_gs_base(); /* not intercepted */ + vmcall(); + rdmsr_gs_base(); /* intercepted */ + /* Done, exit to L1 and never come back. */ vmcall(); } @@ -76,8 +102,9 @@ void guest_code(struct vmx_pages *vmx_pages) current_evmcs->revision_id = EVMCS_VERSION; GUEST_SYNC(6); - current_evmcs->pin_based_vm_exec_control |= - PIN_BASED_NMI_EXITING; + vmwrite(PIN_BASED_VM_EXEC_CONTROL, vmreadz(PIN_BASED_VM_EXEC_CONTROL) | + PIN_BASED_NMI_EXITING); + GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); @@ -91,6 +118,39 @@ void guest_code(struct vmx_pages *vmx_pages) GUEST_SYNC(10); GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + current_evmcs->guest_rip += 3; /* vmcall */ + + /* Intercept RDMSR 0xc0000100 */ + vmwrite(CPU_BASED_VM_EXEC_CONTROL, vmreadz(CPU_BASED_VM_EXEC_CONTROL) | + CPU_BASED_USE_MSR_BITMAPS); + set_bit(MSR_FS_BASE & 0x1fff, vmx_pages->msr + 0x400); + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + /* Enable enlightened MSR bitmap */ + current_evmcs->hv_enlightenments_control.msr_bitmap = 1; + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + /* Intercept RDMSR 0xc0000101 without telling KVM about it */ + set_bit(MSR_GS_BASE & 0x1fff, vmx_pages->msr + 0x400); + /* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */ + current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + GUEST_ASSERT(!vmresume()); + /* Make sure we don't see EXIT_REASON_MSR_READ here so eMSR bitmap works */ + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + current_evmcs->guest_rip += 3; /* vmcall */ + + /* Now tell KVM we've changed MSR-Bitmap */ + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); GUEST_SYNC(11); /* Try enlightened vmptrld with an incorrect GPA */ diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 7e2d2d17d2ed..8c245ab2d98a 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -49,16 +49,13 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, bool evmcs_expected) { int i; - int nent = 9; + int nent_expected = 10; u32 test_val; - if (evmcs_expected) - nent += 1; /* 0x4000000A */ - - TEST_ASSERT(hv_cpuid_entries->nent == nent, + TEST_ASSERT(hv_cpuid_entries->nent == nent_expected, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" - " with evmcs=%d (returned %d)", - nent, evmcs_expected, hv_cpuid_entries->nent); + " (returned %d)", + nent_expected, hv_cpuid_entries->nent); for (i = 0; i < hv_cpuid_entries->nent; i++) { struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; @@ -68,9 +65,6 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, "function %x is our of supported range", entry->function); - TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A), - "0x4000000A leaf should not be reported"); - TEST_ASSERT(entry->index == 0, ".index field should be zero"); @@ -97,8 +91,20 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); break; - } + case 0x4000000A: + TEST_ASSERT(entry->eax & (1UL << 19), + "Enlightened MSR-Bitmap should always be supported" + " 0x40000000.EAX: %x", entry->eax); + if (evmcs_expected) + TEST_ASSERT((entry->eax & 0xffff) == 0x101, + "Supported Enlightened VMCS version range is supposed to be 1:1" + " 0x40000000.EAX: %x", entry->eax); + + break; + default: + break; + } /* * If needed for debug: * fprintf(stdout, @@ -107,7 +113,6 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, * entry->edx); */ } - } void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c new file mode 100644 index 000000000000..21f5ca9197da --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM_GET/SET_* tests + * + * Copyright (C) 2022, Red Hat, Inc. + * + * Tests for Hyper-V extensions to SVM. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <linux/bitmap.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "hyperv.h" + +#define VCPU_ID 1 +#define L2_GUEST_STACK_SIZE 256 + +struct hv_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB + */ +#define VMCB_HV_NESTED_ENLIGHTENMENTS (1U << 31) + +static inline void vmmcall(void) +{ + __asm__ __volatile__("vmmcall"); +} + +void l2_guest_code(void) +{ + GUEST_SYNC(3); + /* Exit to L1 */ + vmmcall(); + + /* MSR-Bitmap tests */ + rdmsr(MSR_FS_BASE); /* intercepted */ + rdmsr(MSR_FS_BASE); /* intercepted */ + rdmsr(MSR_GS_BASE); /* not intercepted */ + vmmcall(); + rdmsr(MSR_GS_BASE); /* intercepted */ + + GUEST_SYNC(5); + + /* Done, exit to L1 and never come back. */ + vmmcall(); +} + +static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + GUEST_SYNC(1); + + wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48); + + GUEST_ASSERT(svm->vmcb_gpa); + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(2); + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_SYNC(4); + vmcb->save.rip += 3; + + /* Intercept RDMSR 0xc0000100 */ + vmcb->control.intercept |= 1ULL << INTERCEPT_MSR_PROT; + set_bit(2 * (MSR_FS_BASE & 0x1fff), svm->msr + 0x800); + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + /* Enable enlightened MSR bitmap */ + hve->hv_enlightenments_control.msr_bitmap = 1; + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + /* Intercept RDMSR 0xc0000101 without telling KVM about it */ + set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800); + /* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */ + vmcb->control.clean |= VMCB_HV_NESTED_ENLIGHTENMENTS; + run_guest(vmcb, svm->vmcb_gpa); + /* Make sure we don't see SVM_EXIT_MSR here so eMSR bitmap works */ + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + vmcb->save.rip += 3; /* vmcall */ + + /* Now tell KVM we've changed MSR-Bitmap */ + vmcb->control.clean &= ~VMCB_HV_NESTED_ENLIGHTENMENTS; + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_SYNC(6); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t nested_gva = 0; + + struct kvm_vm *vm; + struct kvm_run *run; + struct ucall uc; + int stage; + + if (!nested_svm_supported()) { + print_skip("Nested SVM not supported"); + exit(KSFT_SKIP); + } + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + vcpu_set_hv_cpuid(vm, VCPU_ID); + run = vcpu_state(vm, VCPU_ID); + vcpu_alloc_svm(vm, &nested_gva); + vcpu_args_set(vm, VCPU_ID, 1, nested_gva); + + for (stage = 1;; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + /* UCALL_SYNC is handled here. */ + TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", + stage, (ulong)uc.args[1]); + + } + +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index c715adcbd487..0d06ffa95d9d 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -326,6 +326,37 @@ static void test_not_member_allow_list(struct kvm_vm *vm) } /* + * Verify that setting KVM_PMU_CAP_DISABLE prevents the use of the PMU. + * + * Note that KVM_CAP_PMU_CAPABILITY must be invoked prior to creating VCPUs. + */ +static void test_pmu_config_disable(void (*guest_code)(void)) +{ + int r; + struct kvm_vm *vm; + struct kvm_enable_cap cap = { 0 }; + + r = kvm_check_cap(KVM_CAP_PMU_CAPABILITY); + if (!(r & KVM_PMU_CAP_DISABLE)) + return; + + vm = vm_create_without_vcpus(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES); + + cap.cap = KVM_CAP_PMU_CAPABILITY; + cap.args[0] = KVM_PMU_CAP_DISABLE; + TEST_ASSERT(!vm_enable_cap(vm, &cap), "Failed to set KVM_PMU_CAP_DISABLE."); + + vm_vcpu_add_default(vm, VCPU_ID, guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + TEST_ASSERT(!sanity_check_pmu(vm), + "Guest should not be able to use disabled PMU."); + + kvm_vm_free(vm); +} + +/* * Check for a non-zero PMU version, at least one general-purpose * counter per logical processor, an EBX bit vector of length greater * than 5, and EBX[5] clear. @@ -430,5 +461,7 @@ int main(int argc, char *argv[]) kvm_vm_free(vm); + test_pmu_config_disable(guest_code); + return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c index 80056bbbb003..d1dc1acf997c 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -21,6 +21,8 @@ #define NR_LOCK_TESTING_THREADS 3 #define NR_LOCK_TESTING_ITERATIONS 10000 +bool have_sev_es; + static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error) { struct kvm_sev_cmd cmd = { @@ -172,10 +174,18 @@ static void test_sev_migrate_parameters(void) *sev_es_vm_no_vmsa; int ret; - sev_vm = sev_vm_create(/* es= */ false); - sev_es_vm = sev_vm_create(/* es= */ true); vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); vm_no_sev = aux_vm_create(true); + ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Migrations require SEV enabled. ret %d, errno: %d\n", ret, + errno); + + if (!have_sev_es) + goto out; + + sev_vm = sev_vm_create(/* es= */ false); + sev_es_vm = sev_vm_create(/* es= */ true); sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); vm_vcpu_add(sev_es_vm_no_vmsa, 1); @@ -204,14 +214,10 @@ static void test_sev_migrate_parameters(void) "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); - TEST_ASSERT(ret == -1 && errno == EINVAL, - "Migrations require SEV enabled. ret %d, errno: %d\n", ret, - errno); - kvm_vm_free(sev_vm); kvm_vm_free(sev_es_vm); kvm_vm_free(sev_es_vm_no_vmsa); +out: kvm_vm_free(vm_no_vcpu); kvm_vm_free(vm_no_sev); } @@ -300,7 +306,6 @@ static void test_sev_mirror_parameters(void) int ret; sev_vm = sev_vm_create(/* es= */ false); - sev_es_vm = sev_vm_create(/* es= */ true); vm_with_vcpu = aux_vm_create(true); vm_no_vcpu = aux_vm_create(false); @@ -310,6 +315,21 @@ static void test_sev_mirror_parameters(void) "Should not be able copy context to self. ret: %d, errno: %d\n", ret, errno); + ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, + errno); + + ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", + ret, errno); + + if (!have_sev_es) + goto out; + + sev_es_vm = sev_vm_create(/* es= */ true); ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd); TEST_ASSERT( ret == -1 && errno == EINVAL, @@ -322,63 +342,97 @@ static void test_sev_mirror_parameters(void) "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); - TEST_ASSERT(ret == -1 && errno == EINVAL, - "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, - errno); - - ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); - TEST_ASSERT( - ret == -1 && errno == EINVAL, - "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", - ret, errno); + kvm_vm_free(sev_es_vm); +out: kvm_vm_free(sev_vm); - kvm_vm_free(sev_es_vm); kvm_vm_free(vm_with_vcpu); kvm_vm_free(vm_no_vcpu); } static void test_sev_move_copy(void) { - struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm; - int ret; + struct kvm_vm *dst_vm, *dst2_vm, *dst3_vm, *sev_vm, *mirror_vm, + *dst_mirror_vm, *dst2_mirror_vm, *dst3_mirror_vm; sev_vm = sev_vm_create(/* es= */ false); dst_vm = aux_vm_create(true); + dst2_vm = aux_vm_create(true); + dst3_vm = aux_vm_create(true); mirror_vm = aux_vm_create(false); dst_mirror_vm = aux_vm_create(false); + dst2_mirror_vm = aux_vm_create(false); + dst3_mirror_vm = aux_vm_create(false); sev_mirror_create(mirror_vm->fd, sev_vm->fd); - ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); - TEST_ASSERT(ret == -1 && errno == EBUSY, - "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, - errno); - /* The mirror itself can be migrated. */ sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); - ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); - TEST_ASSERT(ret == -1 && errno == EBUSY, - "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, - errno); + sev_migrate_from(dst_vm->fd, sev_vm->fd); + + sev_migrate_from(dst2_vm->fd, dst_vm->fd); + sev_migrate_from(dst2_mirror_vm->fd, dst_mirror_vm->fd); + + sev_migrate_from(dst3_mirror_vm->fd, dst2_mirror_vm->fd); + sev_migrate_from(dst3_vm->fd, dst2_vm->fd); + + kvm_vm_free(dst_vm); + kvm_vm_free(sev_vm); + kvm_vm_free(dst2_vm); + kvm_vm_free(dst3_vm); + kvm_vm_free(mirror_vm); + kvm_vm_free(dst_mirror_vm); + kvm_vm_free(dst2_mirror_vm); + kvm_vm_free(dst3_mirror_vm); /* - * mirror_vm is not a mirror anymore, dst_mirror_vm is. Thus, - * the owner can be copied as soon as dst_mirror_vm is gone. + * Run similar test be destroy mirrors before mirrored VMs to ensure + * destruction is done safely. */ - kvm_vm_free(dst_mirror_vm); + sev_vm = sev_vm_create(/* es= */ false); + dst_vm = aux_vm_create(true); + mirror_vm = aux_vm_create(false); + dst_mirror_vm = aux_vm_create(false); + + sev_mirror_create(mirror_vm->fd, sev_vm->fd); + + sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); sev_migrate_from(dst_vm->fd, sev_vm->fd); kvm_vm_free(mirror_vm); + kvm_vm_free(dst_mirror_vm); kvm_vm_free(dst_vm); kvm_vm_free(sev_vm); } +#define X86_FEATURE_SEV (1 << 1) +#define X86_FEATURE_SEV_ES (1 << 3) + int main(int argc, char *argv[]) { + struct kvm_cpuid_entry2 *cpuid; + + if (!kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM) && + !kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { + print_skip("Capabilities not available"); + exit(KSFT_SKIP); + } + + cpuid = kvm_get_supported_cpuid_entry(0x80000000); + if (cpuid->eax < 0x8000001f) { + print_skip("AMD memory encryption not available"); + exit(KSFT_SKIP); + } + cpuid = kvm_get_supported_cpuid_entry(0x8000001f); + if (!(cpuid->eax & X86_FEATURE_SEV)) { + print_skip("AMD SEV not available"); + exit(KSFT_SKIP); + } + have_sev_es = !!(cpuid->eax & X86_FEATURE_SEV_ES); + if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { test_sev_migrate_from(/* es= */ false); - test_sev_migrate_from(/* es= */ true); + if (have_sev_es) + test_sev_migrate_from(/* es= */ true); test_sev_migrate_locking(); test_sev_migrate_parameters(); if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) @@ -386,7 +440,8 @@ int main(int argc, char *argv[]) } if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { test_sev_mirror(/* es= */ false); - test_sev_mirror(/* es= */ true); + if (have_sev_es) + test_sev_mirror(/* es= */ true); test_sev_mirror_parameters(); } return 0; diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c new file mode 100644 index 000000000000..0792334ba243 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "apic.h" +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +struct kvm_vcpu { + uint32_t id; + bool is_x2apic; +}; + +static void xapic_guest_code(void) +{ + asm volatile("cli"); + + xapic_enable(); + + while (1) { + uint64_t val = (u64)xapic_read_reg(APIC_IRR) | + (u64)xapic_read_reg(APIC_IRR + 0x10) << 32; + + xapic_write_reg(APIC_ICR2, val >> 32); + xapic_write_reg(APIC_ICR, val); + GUEST_SYNC(val); + } +} + +static void x2apic_guest_code(void) +{ + asm volatile("cli"); + + x2apic_enable(); + + do { + uint64_t val = x2apic_read_reg(APIC_IRR) | + x2apic_read_reg(APIC_IRR + 0x10) << 32; + + x2apic_write_reg(APIC_ICR, val); + GUEST_SYNC(val); + } while (1); +} + +static void ____test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val) +{ + struct kvm_lapic_state xapic; + struct ucall uc; + uint64_t icr; + + /* + * Tell the guest what ICR value to write. Use the IRR to pass info, + * all bits are valid and should not be modified by KVM (ignoring the + * fact that vectors 0-15 are technically illegal). + */ + vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic); + *((u32 *)&xapic.regs[APIC_IRR]) = val; + *((u32 *)&xapic.regs[APIC_IRR + 0x10]) = val >> 32; + vcpu_ioctl(vm, vcpu->id, KVM_SET_LAPIC, &xapic); + + vcpu_run(vm, vcpu->id); + ASSERT_EQ(get_ucall(vm, vcpu->id, &uc), UCALL_SYNC); + ASSERT_EQ(uc.args[1], val); + + vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic); + icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | + (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; + if (!vcpu->is_x2apic) + val &= (-1u | (0xffull << (32 + 24))); + ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); +} + +static void __test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val) +{ + ____test_icr(vm, vcpu, val | APIC_ICR_BUSY); + ____test_icr(vm, vcpu, val & ~(u64)APIC_ICR_BUSY); +} + +static void test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +{ + uint64_t icr, i, j; + + icr = APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_FIXED; + for (i = 0; i <= 0xff; i++) + __test_icr(vm, vcpu, icr | i); + + icr = APIC_INT_ASSERT | APIC_DM_FIXED; + for (i = 0; i <= 0xff; i++) + __test_icr(vm, vcpu, icr | i); + + /* + * Send all flavors of IPIs to non-existent vCPUs. TODO: use number of + * vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff. + */ + icr = APIC_INT_ASSERT | 0xff; + for (i = vcpu->id + 1; i < 0xff; i++) { + for (j = 0; j < 8; j++) + __test_icr(vm, vcpu, i << (32 + 24) | APIC_INT_ASSERT | (j << 8)); + } + + /* And again with a shorthand destination for all types of IPIs. */ + icr = APIC_DEST_ALLBUT | APIC_INT_ASSERT; + for (i = 0; i < 8; i++) + __test_icr(vm, vcpu, icr | (i << 8)); + + /* And a few garbage value, just make sure it's an IRQ (blocked). */ + __test_icr(vm, vcpu, 0xa5a5a5a5a5a5a5a5 & ~APIC_DM_FIXED_MASK); + __test_icr(vm, vcpu, 0x5a5a5a5a5a5a5a5a & ~APIC_DM_FIXED_MASK); + __test_icr(vm, vcpu, -1ull & ~APIC_DM_FIXED_MASK); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu vcpu = { + .id = 0, + .is_x2apic = true, + }; + struct kvm_cpuid2 *cpuid; + struct kvm_vm *vm; + int i; + + vm = vm_create_default(vcpu.id, 0, x2apic_guest_code); + test_icr(vm, &vcpu); + kvm_vm_free(vm); + + /* + * Use a second VM for the xAPIC test so that x2APIC can be hidden from + * the guest in order to test AVIC. KVM disallows changing CPUID after + * KVM_RUN and AVIC is disabled if _any_ vCPU is allowed to use x2APIC. + */ + vm = vm_create_default(vcpu.id, 0, xapic_guest_code); + vcpu.is_x2apic = false; + + cpuid = vcpu_get_cpuid(vm, vcpu.id); + for (i = 0; i < cpuid->nent; i++) { + if (cpuid->entries[i].function == 1) + break; + } + cpuid->entries[i].ecx &= ~BIT(21); + vcpu_set_cpuid(vm, vcpu.id, cpuid); + + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + test_icr(vm, &vcpu); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index a99596ca9882..0b0049e133bb 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wall -O2 +CFLAGS += -Wall -O2 $(KHDR_INCLUDES) src_test := $(wildcard *_test.c) diff --git a/tools/testing/selftests/lkdtm/config b/tools/testing/selftests/lkdtm/config index a26a3fa9e925..46f39ee76208 100644 --- a/tools/testing/selftests/lkdtm/config +++ b/tools/testing/selftests/lkdtm/config @@ -3,9 +3,9 @@ CONFIG_DEBUG_LIST=y CONFIG_SLAB_FREELIST_HARDENED=y CONFIG_FORTIFY_SOURCE=y CONFIG_HARDENED_USERCOPY=y -# CONFIG_HARDENED_USERCOPY_FALLBACK is not set CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT=y CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y +CONFIG_UBSAN=y CONFIG_UBSAN_BOUNDS=y CONFIG_UBSAN_TRAP=y CONFIG_STACKPROTECTOR_STRONG=y diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 192a2899bae8..94df2692e6e4 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -455,6 +455,7 @@ static void mfd_fail_write(int fd) printf("mmap()+mprotect() didn't fail as expected\n"); abort(); } + munmap(p, mfd_def_size); } /* verify PUNCH_HOLE fails */ diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index e54106643337..4c88238fc8f0 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -207,15 +207,21 @@ TEST(check_file_mmap) errno = 0; fd = open(".", O_TMPFILE | O_RDWR, 0600); - ASSERT_NE(-1, fd) { - TH_LOG("Can't create temporary file: %s", - strerror(errno)); + if (fd < 0) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Can't create temporary file: %s", + strerror(errno)); + } + SKIP(goto out_free, "O_TMPFILE not supported by filesystem."); } errno = 0; retval = fallocate(fd, 0, 0, FILE_SIZE); - ASSERT_EQ(0, retval) { - TH_LOG("Error allocating space for the temporary file: %s", - strerror(errno)); + if (retval) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Error allocating space for the temporary file: %s", + strerror(errno)); + } + SKIP(goto out_close, "fallocate not supported by filesystem."); } /* @@ -271,7 +277,9 @@ TEST(check_file_mmap) } munmap(addr, FILE_SIZE); +out_close: close(fd); +out_free: free(vec); } diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index f31205f04ee0..8c5fea68ae67 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1236,7 +1236,7 @@ static int get_userns_fd(unsigned long nsid, unsigned long hostid, unsigned long } /** - * Validate that an attached mount in our mount namespace can be idmapped. + * Validate that an attached mount in our mount namespace cannot be idmapped. * (The kernel enforces that the mount's mount namespace and the caller's mount * namespace match.) */ @@ -1259,7 +1259,7 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace) attr.userns_fd = get_userns_fd(0, 10000, 10000); ASSERT_GE(attr.userns_fd, 0); - ASSERT_EQ(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 9897fa9ab953..0b1488616c55 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -2,7 +2,7 @@ # Makefile for net selftests CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -CFLAGS += -I../../../../usr/include/ +CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 0356c4501c99..f905d5358e68 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -3,7 +3,7 @@ top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 2674ba20d524..ff821025d309 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -71,6 +71,36 @@ chk_msk_remote_key_nr() __chk_nr "grep -c remote_key" $* } +# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp | \ + awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +wait_connected() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break + sleep 0.1 + done +} trap cleanup EXIT ip netns add $ns @@ -81,15 +111,15 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10000 -l -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10000 chk_msk_nr 0 "no msk on netns creation" echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10000 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" @@ -101,13 +131,13 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10001 echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10001 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" flush_pids @@ -119,7 +149,7 @@ for I in `seq 1 $NR_CLIENTS`; do ./mptcp_connect -p $((I+10001)) -l -w 10 \ -t ${timeout_poll} 0.0.0.0 >/dev/null & done -sleep 0.1 +wait_local_port_listen $ns $((NR_CLIENTS + 10001)) for I in `seq 1 $NR_CLIENTS`; do echo "b" | \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index cb5809b89081..f0f4ab96b8f3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -763,8 +763,8 @@ run_tests_disconnect() run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin" # restore previous status - cout=$old_cout - cout_disconnect="$cout".disconnect + sin=$old_sin + sin_disconnect="$cout".disconnect cin=$old_cin cin_disconnect="$cin".disconnect connect_per_transfer=1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index b8bdbec0cf69..0c8a2a20b96c 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -660,6 +660,7 @@ chk_join_nr() local ack_nr=$4 local count local dump_stats + local with_cookie printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` @@ -673,12 +674,20 @@ chk_join_nr() fi echo -n " - synack" + with_cookie=`ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies` count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'` [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then - echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" - ret=1 - dump_stats=1 + # simult connections exceeding the limit with cookie enabled could go up to + # synack validation as the conn limit can be enforced reliably only after + # the subflow creation + if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then + echo -n "[ ok ]" + else + echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" + ret=1 + dump_stats=1 + fi else echo -n "[ ok ]" fi @@ -752,11 +761,17 @@ chk_add_nr() local mis_ack_nr=${8:-0} local count local dump_stats + local timeout + + timeout=`ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout` printf "%-39s %s" " " "add" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'` + count=`ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}'` [ -z "$count" ] && count=0 - if [ "$count" != "$add_nr" ]; then + + # if the test configured a short timeout tolerate greater then expected + # add addrs options, due to retransmissions + if [ "$count" != "$add_nr" ] && [ "$timeout" -gt 1 -o "$count" -lt "$add_nr" ]; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" ret=1 dump_stats=1 @@ -961,7 +976,7 @@ wait_for_tw() local ns=$1 while [ $time -lt $timeout_ms ]; do - local cnt=$(ip netns exec $ns ss -t state time-wait |wc -l) + local cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -1158,7 +1173,11 @@ signal_address_tests() ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal - run_tests $ns1 $ns2 10.0.1.1 + + # the peer could possibly miss some addr notification, allow retransmission + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr "signal addresses race test" 3 3 3 # the server will not signal the address terminating # the MPC subflow diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 543ad7513a8e..694732e4b344 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -374,6 +374,16 @@ run_cmd() { return $rc } +run_cmd_bg() { + cmd="$*" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: %s &\n" "${cmd}" + fi + + $cmd 2>&1 & +} + # Find the auto-generated name for this namespace nsname() { eval echo \$NS_$1 @@ -670,10 +680,10 @@ setup_nettest_xfrm() { [ ${1} -eq 6 ] && proto="-6" || proto="" port=${2} - run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + run_cmd_bg "${ns_a}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5 nettest_pids="${nettest_pids} $!" - run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + run_cmd_bg "${ns_b}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5 nettest_pids="${nettest_pids} $!" } @@ -865,7 +875,6 @@ setup_ovs_bridge() { setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip - cleanup for arg do eval setup_${arg} || { echo " ${arg} not supported"; return 1; } done @@ -876,7 +885,7 @@ trace() { for arg do [ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue - ${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null & + ${ns_cmd} tcpdump --immediate-mode -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null & tcpdump_pids="${tcpdump_pids} $!" ns_cmd= done @@ -1836,6 +1845,10 @@ run_test() { unset IFS + # Since cleanup() relies on variables modified by this subshell, it + # has to run in this context. + trap cleanup EXIT + if [ "$VERBOSE" = "1" ]; then printf "\n##########################################################################\n\n" fi diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore index 8448f74adfec..4cb887b57413 100644 --- a/tools/testing/selftests/netfilter/.gitignore +++ b/tools/testing/selftests/netfilter/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only nf-queue +connect_close diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index ffca314897c4..600e3a19d5e2 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -6,9 +6,10 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ - conntrack_vrf.sh + conntrack_vrf.sh nft_synproxy.sh +CFLAGS += $(shell pkg-config --cflags libmnl 2>/dev/null || echo "-I/usr/include/libmnl") LDLIBS = -lmnl -TEST_GEN_FILES = nf-queue +TEST_GEN_FILES = nf-queue connect_close include ../lib.mk diff --git a/tools/testing/selftests/netfilter/connect_close.c b/tools/testing/selftests/netfilter/connect_close.c new file mode 100644 index 000000000000..1c3b0add54c4 --- /dev/null +++ b/tools/testing/selftests/netfilter/connect_close.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <signal.h> + +#include <arpa/inet.h> +#include <sys/socket.h> + +#define PORT 12345 +#define RUNTIME 10 + +static struct { + unsigned int timeout; + unsigned int port; +} opts = { + .timeout = RUNTIME, + .port = PORT, +}; + +static void handler(int sig) +{ + _exit(sig == SIGALRM ? 0 : 1); +} + +static void set_timeout(void) +{ + struct sigaction action = { + .sa_handler = handler, + }; + + sigaction(SIGALRM, &action, NULL); + + alarm(opts.timeout); +} + +static void do_connect(const struct sockaddr_in *dst) +{ + int s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + + if (s >= 0) + fcntl(s, F_SETFL, O_NONBLOCK); + + connect(s, (struct sockaddr *)dst, sizeof(*dst)); + close(s); +} + +static void do_accept(const struct sockaddr_in *src) +{ + int c, one = 1, s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + + if (s < 0) + return; + + setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)); + setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + + bind(s, (struct sockaddr *)src, sizeof(*src)); + + listen(s, 16); + + c = accept(s, NULL, NULL); + if (c >= 0) + close(c); + + close(s); +} + +static int accept_loop(void) +{ + struct sockaddr_in src = { + .sin_family = AF_INET, + .sin_port = htons(opts.port), + }; + + inet_pton(AF_INET, "127.0.0.1", &src.sin_addr); + + set_timeout(); + + for (;;) + do_accept(&src); + + return 1; +} + +static int connect_loop(void) +{ + struct sockaddr_in dst = { + .sin_family = AF_INET, + .sin_port = htons(opts.port), + }; + + inet_pton(AF_INET, "127.0.0.1", &dst.sin_addr); + + set_timeout(); + + for (;;) + do_connect(&dst); + + return 1; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "t:p:")) != -1) { + switch (c) { + case 't': + opts.timeout = atoi(optarg); + break; + case 'p': + opts.port = atoi(optarg); + break; + } + } +} + +int main(int argc, char *argv[]) +{ + pid_t p; + + parse_opts(argc, argv); + + p = fork(); + if (p < 0) + return 111; + + if (p > 0) + return accept_loop(); + + return connect_loop(); +} diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index ed61f6cab60f..b35010cc7f6a 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below -BUGS="flush_remove_add" +BUGS="flush_remove_add reload" # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" @@ -354,6 +354,23 @@ TYPE_flush_remove_add=" display Add two elements, flush, re-add " +TYPE_reload=" +display net,mac with reload +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 1 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() { nft flush ruleset } +# - add ranged element, check that packets match it +# - reload the set, check packets still match +test_bug_reload() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + rstart=${start} + + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + # check kernel does allocate pcpu sctrach map + # for reload with no elemet add/delete + ( echo flush set inet filter test ; + nft list set inet filter test ) | nft -f - + + start=${rstart} + range_size=1 + + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush ruleset +} + test_reported_issues() { eval test_bug_"${subtest}" } @@ -1531,4 +1601,4 @@ for name in ${TESTS}; do done done -[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} +[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} || exit 0 diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh index 6caf6ac8c285..695a1958723f 100755 --- a/tools/testing/selftests/netfilter/nft_fib.sh +++ b/tools/testing/selftests/netfilter/nft_fib.sh @@ -174,6 +174,7 @@ test_ping() { ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null +ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null sleep 3 diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 349a319a9e51..eb8543b9a5c4 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -880,9 +880,8 @@ EOF return $ksft_skip fi - # test default behaviour. Packet from ns1 to ns0 is not redirected - # due to automatic port translation. - test_port_shadow "default" "ROUTER" + # test default behaviour. Packet from ns1 to ns0 is redirected to ns2. + test_port_shadow "default" "CLIENT" # test packet filter based mitigation: prevent forwarding of # packets claiming to come from the service port. @@ -899,6 +898,144 @@ EOF ip netns exec "$ns0" nft delete table $family nat } +test_stateless_nat_ip() +{ + local lret=0 + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules" + return 1 + fi + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table ip stateless { + map xlate_in { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2, + } + } + map xlate_out { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99 + } + } + + chain prerouting { + type filter hook prerouting priority -400; policy accept; + ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in + ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add ip statless rules" + return $ksft_skip + fi + + reset_counters + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules" + lret=1 + fi + + # ns1 should have seen packets from .2.2, due to stateless rewrite. + expect="packets 1 bytes 84" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 1" + lret=1 + fi + + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3" + lret=1 + fi + + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4" + lret=1 + fi + done + + reset_counters + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run stateless nat frag test without socat tool" + if [ $lret -eq 0 ]; then + return $ksft_skip + fi + + ip netns exec "$ns0" nft delete table ip stateless + return $lret + fi + + local tmpfile=$(mktemp) + dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null + + local outfile=$(mktemp) + ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null & + sc_r=$! + + sleep 1 + # re-do with large ping -> ip fragmentation + ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null + if [ $? -ne 0 ] ; then + echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2 + lret=1 + fi + + wait + + cmp "$tmpfile" "$outfile" + if [ $? -ne 0 ]; then + ls -l "$tmpfile" "$outfile" + echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2 + lret=1 + fi + + rm -f "$tmpfile" "$outfile" + + # ns1 should have seen packets from 2.2, due to stateless rewrite. + expect="packets 3 bytes 4164" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 5" + lret=1 + fi + + ip netns exec "$ns0" nft delete table ip stateless + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete table ip stateless" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP statless for $ns2" + + return $lret +} + # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF @@ -965,6 +1102,19 @@ table inet filter { EOF done +# special case for stateless nat check, counter needs to +# be done before (input) ip defragmentation +ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF +table inet filter { + counter ns0insl {} + + chain pre { + type filter hook prerouting priority -400; policy accept; + ip saddr 10.0.2.2 counter name "ns0insl" + } +} +EOF + sleep 3 # test basic connectivity for i in 1 2; do @@ -1019,6 +1169,7 @@ $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet test_port_shadowing +test_stateless_nat_ip if [ $ret -ne 0 ];then echo -n "FAIL: " diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 7d27f1f3bc01..e12729753351 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -113,6 +113,7 @@ table inet $name { chain output { type filter hook output priority $prio; policy accept; tcp dport 12345 queue num 3 + tcp sport 23456 queue num 3 jump nfq } chain post { @@ -296,6 +297,23 @@ test_tcp_localhost() wait 2>/dev/null } +test_tcp_localhost_connectclose() +{ + tmpfile=$(mktemp) || exit 1 + + ip netns exec ${nsrouter} ./connect_close -p 23456 -t $timeout & + + ip netns exec ${nsrouter} ./nf-queue -q 3 -t $timeout & + local nfqpid=$! + + sleep 1 + rm -f "$tmpfile" + + wait $rpid + [ $? -eq 0 ] && echo "PASS: tcp via loopback with connect/close" + wait 2>/dev/null +} + test_tcp_localhost_requeue() { ip netns exec ${nsrouter} nft -f /dev/stdin <<EOF @@ -424,6 +442,7 @@ test_queue 20 test_tcp_forward test_tcp_localhost +test_tcp_localhost_connectclose test_tcp_localhost_requeue test_icmp_vrf diff --git a/tools/testing/selftests/netfilter/nft_synproxy.sh b/tools/testing/selftests/netfilter/nft_synproxy.sh new file mode 100755 index 000000000000..b62933b680d6 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_synproxy.sh @@ -0,0 +1,117 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +rnd=$(mktemp -u XXXXXXXX) +nsr="nsr-$rnd" # synproxy machine +ns1="ns1-$rnd" # iperf client +ns2="ns2-$rnd" # iperf server + +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} + +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "iperf3 --version" "run test without iperf3" +checktool "ip netns add $nsr" "create net namespace" + +modprobe -q nf_conntrack + +ip netns add $ns1 +ip netns add $ns2 + +cleanup() { + ip netns pids $ns1 | xargs kill 2>/dev/null + ip netns pids $ns2 | xargs kill 2>/dev/null + ip netns del $ns1 + ip netns del $ns2 + + ip netns del $nsr +} + +trap cleanup EXIT + +ip link add veth0 netns $nsr type veth peer name eth0 netns $ns1 +ip link add veth1 netns $nsr type veth peer name eth0 netns $ns2 + +for dev in lo veth0 veth1; do +ip -net $nsr link set $dev up +done + +ip -net $nsr addr add 10.0.1.1/24 dev veth0 +ip -net $nsr addr add 10.0.2.1/24 dev veth1 + +ip netns exec $nsr sysctl -q net.ipv4.conf.veth0.forwarding=1 +ip netns exec $nsr sysctl -q net.ipv4.conf.veth1.forwarding=1 +ip netns exec $nsr sysctl -q net.netfilter.nf_conntrack_tcp_loose=0 + +for n in $ns1 $ns2; do + ip -net $n link set lo up + ip -net $n link set eth0 up +done +ip -net $ns1 addr add 10.0.1.99/24 dev eth0 +ip -net $ns2 addr add 10.0.2.99/24 dev eth0 +ip -net $ns1 route add default via 10.0.1.1 +ip -net $ns2 route add default via 10.0.2.1 + +# test basic connectivity +if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then + echo "ERROR: $ns1 cannot reach $ns2" 1>&2 + exit 1 +fi + +if ! ip netns exec $ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then + echo "ERROR: $ns2 cannot reach $ns1" 1>&2 + exit 1 +fi + +ip netns exec $ns2 iperf3 -s > /dev/null 2>&1 & +# ip netns exec $nsr tcpdump -vvv -n -i veth1 tcp | head -n 10 & + +sleep 1 + +ip netns exec $nsr nft -f - <<EOF +table inet filter { + chain prerouting { + type filter hook prerouting priority -300; policy accept; + meta iif veth0 tcp flags syn counter notrack + } + + chain forward { + type filter hook forward priority 0; policy accept; + + ct state new,established counter accept + + meta iif veth0 meta l4proto tcp ct state untracked,invalid synproxy mss 1460 sack-perm timestamp + + ct state invalid counter drop + + # make ns2 unreachable w.o. tcp synproxy + tcp flags syn counter drop + } +} +EOF +if [ $? -ne 0 ]; then + echo "SKIP: Cannot add nft synproxy" + exit $ksft_skip +fi + +ip netns exec $ns1 timeout 5 iperf3 -c 10.0.2.99 -n $((1 * 1024 * 1024)) > /dev/null + +if [ $? -ne 0 ]; then + echo "FAIL: iperf3 returned an error" 1>&2 + ret=$? + ip netns exec $nsr nft list ruleset +else + echo "PASS: synproxy connection successful" +fi + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh index 04633119b29a..5a8db0b48928 100755 --- a/tools/testing/selftests/netfilter/nft_zones_many.sh +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -9,7 +9,7 @@ ns="ns-$sfx" # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -zones=20000 +zones=2000 have_ct_tool=0 ret=0 @@ -75,10 +75,10 @@ EOF while [ $i -lt $max_zones ]; do local start=$(date +%s%3N) - i=$((i + 10000)) + i=$((i + 1000)) j=$((j + 1)) # nft rule in output places each packet in a different zone. - dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 + dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 if [ $? -ne 0 ] ;then ret=1 break @@ -86,7 +86,7 @@ EOF stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)" done if [ $have_ct_tool -eq 1 ]; then @@ -128,11 +128,11 @@ test_conntrack_tool() { break fi - if [ $((i%10000)) -eq 0 ];then + if [ $((i%1000)) -eq 0 ];then stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total)" + echo "PASS: added 1000 entries in $duration ms (now $i total)" start=$stop fi done diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 4b93b1417b86..843ba56d8e49 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test include ../lib.mk -$(TEST_GEN_PROGS): helpers.c +$(TEST_GEN_PROGS): helpers.c helpers.h diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h index a6ea27344db2..7056340b9339 100644 --- a/tools/testing/selftests/openat2/helpers.h +++ b/tools/testing/selftests/openat2/helpers.h @@ -9,6 +9,7 @@ #define _GNU_SOURCE #include <stdint.h> +#include <stdbool.h> #include <errno.h> #include <linux/types.h> #include "../kselftest.h" @@ -62,11 +63,12 @@ bool needs_openat2(const struct open_how *how); (similar to chroot(2)). */ #endif /* RESOLVE_IN_ROOT */ -#define E_func(func, ...) \ - do { \ - if (func(__VA_ARGS__) < 0) \ - ksft_exit_fail_msg("%s:%d %s failed\n", \ - __FILE__, __LINE__, #func);\ +#define E_func(func, ...) \ + do { \ + errno = 0; \ + if (func(__VA_ARGS__) < 0) \ + ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \ + __FILE__, __LINE__, #func, errno); \ } while (0) #define E_asprintf(...) E_func(asprintf, __VA_ARGS__) diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c index 1bddbe934204..7fb902099de4 100644 --- a/tools/testing/selftests/openat2/openat2_test.c +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -259,6 +259,16 @@ void test_openat2_flags(void) unlink(path); fd = sys_openat2(AT_FDCWD, path, &test->how); + if (fd < 0 && fd == -EOPNOTSUPP) { + /* + * Skip the testcase if it failed because not supported + * by FS. (e.g. a valid O_TMPFILE combination on NFS) + */ + ksft_test_result_skip("openat2 with %s fails with %d (%s)\n", + test->name, fd, strerror(-fd)); + goto next; + } + if (test->err >= 0) failed = (fd < 0); else @@ -303,7 +313,7 @@ skip: else resultfn("openat2 with %s fails with %d (%s)\n", test->name, test->err, strerror(-test->err)); - +next: free(fdpath); fflush(stdout); } diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c index 8e83cf91513a..6d849dc2bee0 100644 --- a/tools/testing/selftests/perf_events/sigtrap_threads.c +++ b/tools/testing/selftests/perf_events/sigtrap_threads.c @@ -44,9 +44,10 @@ static struct { } ctx; /* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */ -#define TEST_SIG_DATA(addr) (~(unsigned long)(addr)) +#define TEST_SIG_DATA(addr, id) (~(unsigned long)(addr) + id) -static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) +static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr, + unsigned long id) { struct perf_event_attr attr = { .type = PERF_TYPE_BREAKPOINT, @@ -60,7 +61,7 @@ static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) .inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */ .remove_on_exec = 1, /* Required by sigtrap. */ .sigtrap = 1, /* Request synchronous SIGTRAP on event. */ - .sig_data = TEST_SIG_DATA(addr), + .sig_data = TEST_SIG_DATA(addr, id), }; return attr; } @@ -110,7 +111,7 @@ FIXTURE(sigtrap_threads) FIXTURE_SETUP(sigtrap_threads) { - struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on); + struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on, 0); struct sigaction action = {}; int i; @@ -165,7 +166,7 @@ TEST_F(sigtrap_threads, enable_event) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -175,7 +176,7 @@ TEST_F(sigtrap_threads, enable_event) /* Test that modification propagates to all inherited events. */ TEST_F(sigtrap_threads, modify_and_enable_event) { - struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on); + struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on, 42); EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr), 0); run_test_threads(_metadata, self); @@ -184,7 +185,7 @@ TEST_F(sigtrap_threads, modify_and_enable_event) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 42)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -204,7 +205,7 @@ TEST_F(sigtrap_threads, signal_stress) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0)); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 01f8d3c0cf2c..6922d6417e1c 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -68,7 +68,7 @@ #define PIDFD_SKIP 3 #define PIDFD_XFAIL 4 -int wait_for_pid(pid_t pid) +static inline int wait_for_pid(pid_t pid) { int status, ret; @@ -78,13 +78,20 @@ again: if (errno == EINTR) goto again; + ksft_print_msg("waitpid returned -1, errno=%d\n", errno); return -1; } - if (!WIFEXITED(status)) + if (!WIFEXITED(status)) { + ksft_print_msg( + "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n", + WIFSIGNALED(status), WTERMSIG(status)); return -1; + } - return WEXITSTATUS(status); + ret = WEXITSTATUS(status); + ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); + return ret; } static inline int sys_pidfd_open(pid_t pid, unsigned int flags) diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index 22558524f71c..3fd8e903118f 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -12,6 +12,7 @@ #include <string.h> #include <syscall.h> #include <sys/wait.h> +#include <sys/mman.h> #include "pidfd.h" #include "../kselftest.h" @@ -80,7 +81,10 @@ static inline int error_check(struct error *err, const char *test_name) return err->code; } +#define CHILD_STACK_SIZE 8192 + struct child { + char *stack; pid_t pid; int fd; }; @@ -89,17 +93,22 @@ static struct child clone_newns(int (*fn)(void *), void *args, struct error *err) { static int flags = CLONE_PIDFD | CLONE_NEWPID | CLONE_NEWNS | SIGCHLD; - size_t stack_size = 1024; - char *stack[1024] = { 0 }; struct child ret; if (!(flags & CLONE_NEWUSER) && geteuid() != 0) flags |= CLONE_NEWUSER; + ret.stack = mmap(NULL, CHILD_STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (ret.stack == MAP_FAILED) { + error_set(err, -1, "mmap of stack failed (errno %d)", errno); + return ret; + } + #ifdef __ia64__ - ret.pid = __clone2(fn, stack, stack_size, flags, args, &ret.fd); + ret.pid = __clone2(fn, ret.stack, CHILD_STACK_SIZE, flags, args, &ret.fd); #else - ret.pid = clone(fn, stack + stack_size, flags, args, &ret.fd); + ret.pid = clone(fn, ret.stack + CHILD_STACK_SIZE, flags, args, &ret.fd); #endif if (ret.pid < 0) { @@ -129,6 +138,11 @@ static inline int child_join(struct child *child, struct error *err) else if (r > 0) error_set(err, r, "child %d reported: %d", child->pid, r); + if (munmap(child->stack, CHILD_STACK_SIZE)) { + error_set(err, -1, "munmap of child stack failed (errno %d)", errno); + r = -1; + } + return r; } diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 529eb700ac26..9a2d64901d59 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -441,7 +441,6 @@ static void test_pidfd_poll_exec(int use_waitpid) { int pid, pidfd = 0; int status, ret; - pthread_t t1; time_t prog_start = time(NULL); const char *test_name = "pidfd_poll check for premature notification on child thread exec"; @@ -500,13 +499,14 @@ static int child_poll_leader_exit_test(void *args) */ *child_exit_secs = time(NULL); syscall(SYS_exit, 0); + /* Never reached, but appeases compiler thinking we should return. */ + exit(0); } static void test_pidfd_poll_leader_exit(int use_waitpid) { int pid, pidfd = 0; - int status, ret; - time_t prog_start = time(NULL); + int status, ret = 0; const char *test_name = "pidfd_poll check for premature notification on non-empty" "group leader exit"; diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index be2943f072f6..17999e082aa7 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -39,7 +39,7 @@ static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, TEST(wait_simple) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), @@ -47,7 +47,6 @@ TEST(wait_simple) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, @@ -88,7 +87,7 @@ TEST(wait_simple) TEST(wait_states) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh index e6a132df6172..69f8a5958cef 100755 --- a/tools/testing/selftests/rcutorture/bin/console-badness.sh +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -10,7 +10,7 @@ # # Authors: Paul E. McKenney <paulmck@kernel.org> -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +egrep 'Badness|WARNING:|Warn|BUG|===========|BUG: KCSAN:|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | grep -v 'ODEBUG: ' | grep -v 'This means that this is a DEBUG kernel and it is' | grep -v 'Warning: unable to open an initial console' | diff --git a/tools/testing/selftests/rcutorture/bin/kvm-again.sh b/tools/testing/selftests/rcutorture/bin/kvm-again.sh index 5a0023d183da..0941f1ddab65 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-again.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-again.sh @@ -47,8 +47,8 @@ else exit 1 fi -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh dryrun= diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh index 370406bbfeed..f17000a2ccf1 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh @@ -49,8 +49,8 @@ fi mkdir $resdir/$ds echo Results directory: $resdir/$ds -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh echo Using all `identify_qemu_vcpus` CPUs. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh index e4a00779b8c6..ee886b40a5d2 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh @@ -22,8 +22,8 @@ T=${TMPDIR-/tmp}/kvm-end-run-stats.sh.$$ trap 'rm -rf $T' 0 mkdir $T -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh default_starttime="`get_starttime`" starttime="${2-default_starttime}" diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh index 2e9e9e2eedb6..5f682fc892dd 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh @@ -30,10 +30,16 @@ editor=${EDITOR-vi} files= for i in ${rundir}/*/Make.out do + scenariodir="`dirname $i`" + scenariobasedir="`echo ${scenariodir} | sed -e 's/\.[0-9]*$//'`" if egrep -q "error:|warning:|^ld: .*undefined reference to" < $i then egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags files="$files $i.diags $i" + elif ! test -f ${scenariobasedir}/vmlinux + then + echo No ${scenariobasedir}/vmlinux file > $i.diags + files="$files $i.diags $i" fi done if test -n "$files" diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 1c4c2c727dad..43e1387234d1 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -25,7 +25,7 @@ stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null | tail -1 | sed -e 's/^\[[ 0-9.]*] //' | awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' | tr -d '\012\015'`" -fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }'`" +fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }' | tr -d '\015'`" if test -z "$ngps" then echo "$configfile ------- " $stopstate diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh index e09b1bc78708..8c4c1e4792d0 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh @@ -19,8 +19,8 @@ then exit 1 fi -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh starttime="`get_starttime`" @@ -108,8 +108,8 @@ else cat $T/kvm-again.sh.out | tee -a "$oldrun/remote-log" exit 2 fi - cp -a "$rundir" "$KVM/res/" - oldrun="$KVM/res/$ds" + cp -a "$rundir" "$RCUTORTURE/res/" + oldrun="$RCUTORTURE/res/$ds" fi echo | tee -a "$oldrun/remote-log" echo " ----" kvm-again.sh output: "(`date`)" | tee -a "$oldrun/remote-log" @@ -155,18 +155,23 @@ do echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log" cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" ret=$? - if test "$ret" -ne 0 - then - echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. | tee -a "$oldrun/remote-log" + tries=0 + while test "$ret" -ne 0 + do + echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. $tries prior retries. | tee -a "$oldrun/remote-log" sleep 60 cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" ret=$? if test "$ret" -ne 0 then - echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log" - exit 10 + if test "$tries" > 5 + then + echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log" + exit 10 + fi fi - fi + tries=$((tries+1)) + done done # Function to check for presence of a file on the specified system. diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 6de0c183db5b..55b2c1533282 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -25,15 +25,15 @@ LANG=en_US.UTF-8; export LANG dur=$((30*60)) dryrun="" -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" TORTURE_DEFCONFIG=defconfig TORTURE_BOOT_IMAGE="" TORTURE_BUILDONLY= -TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD +TORTURE_INITRD="$RCUTORTURE/initrd"; export TORTURE_INITRD TORTURE_KCONFIG_ARG="" TORTURE_KCONFIG_GDB_ARG="" TORTURE_BOOT_GDB_ARG="" @@ -262,7 +262,7 @@ else exit 1 fi -CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG +CONFIGFRAG=${RCUTORTURE}/configs/${TORTURE_SUITE}; export CONFIGFRAG defaultconfigs="`tr '\012' ' ' < $CONFIGFRAG/CFLIST`" if test -z "$configs" @@ -272,7 +272,7 @@ fi if test -z "$resdir" then - resdir=$KVM/res + resdir=$RCUTORTURE/res fi # Create a file of test-name/#cpus pairs, sorted by decreasing #cpus. @@ -280,7 +280,7 @@ configs_derep= for CF in $configs do case $CF in - [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**) + [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**|[0-9][0-9][0-9][0-9]\**) config_reps=`echo $CF | sed -e 's/\*.*$//'` CF1=`echo $CF | sed -e 's/^[^*]*\*//'` ;; @@ -386,7 +386,7 @@ END { # Generate a script to execute the tests in appropriate batches. cat << ___EOF___ > $T/script CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG -KVM="$KVM"; export KVM +RCUTORTURE="$RCUTORTURE"; export RCUTORTURE PATH="$PATH"; export PATH TORTURE_ALLOTED_CPUS="$TORTURE_ALLOTED_CPUS"; export TORTURE_ALLOTED_CPUS TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE @@ -569,7 +569,7 @@ ___EOF___ awk < $T/cfgcpu.pack \ -v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \ -v CONFIGDIR="$CONFIGFRAG/" \ - -v KVM="$KVM" \ + -v RCUTORTURE="$RCUTORTURE" \ -v ncpus=$cpus \ -v jitter="$jitter" \ -v rd=$resdir/$ds/ \ diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 9f624bd53c27..822eb037a057 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -138,6 +138,16 @@ then then summary="$summary Bugs: $n_bugs" fi + n_kcsan=`egrep -c 'BUG: KCSAN: ' $file` + if test "$n_kcsan" -ne 0 + then + if test "$n_bugs" = "$n_kcsan" + then + summary="$summary (all bugs kcsan)" + else + summary="$summary KCSAN: $n_kcsan" + fi + fi n_calltrace=`grep -c 'Call Trace:' $file` if test "$n_calltrace" -ne 0 then diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index eae88aacca2a..bfe09e2829c8 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -13,8 +13,8 @@ scriptname=$0 args="$*" -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" @@ -37,7 +37,7 @@ configs_scftorture= kcsan_kmake_args= # Default compression, duration, and apportionment. -compress_kasan_vmlinux="`identify_qemu_vcpus`" +compress_concurrency="`identify_qemu_vcpus`" duration_base=10 duration_rcutorture_frac=7 duration_locktorture_frac=1 @@ -67,12 +67,12 @@ function doyesno () { usage () { echo "Usage: $scriptname optional arguments:" - echo " --compress-kasan-vmlinux concurrency" + echo " --compress-concurrency concurrency" echo " --configs-rcutorture \"config-file list w/ repeat factor (3*TINY01)\"" echo " --configs-locktorture \"config-file list w/ repeat factor (10*LOCK01)\"" echo " --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\"" - echo " --doall" - echo " --doallmodconfig / --do-no-allmodconfig" + echo " --do-all" + echo " --do-allmodconfig / --do-no-allmodconfig" echo " --do-clocksourcewd / --do-no-clocksourcewd" echo " --do-kasan / --do-no-kasan" echo " --do-kcsan / --do-no-kcsan" @@ -91,9 +91,9 @@ usage () { while test $# -gt 0 do case "$1" in - --compress-kasan-vmlinux) - checkarg --compress-kasan-vmlinux "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error' - compress_kasan_vmlinux=$2 + --compress-concurrency) + checkarg --compress-concurrency "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error' + compress_concurrency=$2 shift ;; --config-rcutorture|--configs-rcutorture) @@ -414,8 +414,14 @@ nfailures=0 echo FAILURES: | tee -a $T/log if test -s "$T/failures" then - cat "$T/failures" | tee -a $T/log + awk < "$T/failures" -v sq="'" '{ print "echo " sq $0 sq; print "sed -e " sq "1,/^ --- .* Test summary:$/d" sq " " $2 "/log | grep Summary: | sed -e " sq "s/^[^S]*/ /" sq; }' | sh | tee -a $T/log | tee "$T/failuresum" nfailures="`wc -l "$T/failures" | awk '{ print $1 }'`" + grep "^ Summary: " "$T/failuresum" | + grep -v '^ Summary: Bugs: [0-9]* (all bugs kcsan)$' > "$T/nonkcsan" + if test -s "$T/nonkcsan" + then + nonkcsanbug="yes" + fi ret=2 fi if test "$do_kcsan" = "yes" @@ -424,12 +430,16 @@ then fi echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log echo Summary: Successes: $nsuccesses Failures: $nfailures. | tee -a $T/log +if test -z "$nonkcsanbug" && test -s "$T/failuresum" +then + echo " All bugs were KCSAN failures." +fi tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`" -if test -n "$tdir" && test $compress_kasan_vmlinux -gt 0 +if test -n "$tdir" && test $compress_concurrency -gt 0 then # KASAN vmlinux files can approach 1GB in size, so compress them. - echo Looking for KASAN files to compress: `date` > "$tdir/log-xz" 2>&1 - find "$tdir" -type d -name '*-kasan' -print > $T/xz-todo + echo Looking for K[AC]SAN files to compress: `date` > "$tdir/log-xz" 2>&1 + find "$tdir" -type d -name '*-k[ac]san' -print > $T/xz-todo ncompresses=0 batchno=1 if test -s $T/xz-todo @@ -447,7 +457,7 @@ then do xz "$j" >> "$tdir/log-xz" 2>&1 & ncompresses=$((ncompresses+1)) - if test $ncompresses -ge $compress_kasan_vmlinux + if test $ncompresses -ge $compress_concurrency then echo Waiting for batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log wait diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 index 3ca112444ce7..7093422050f6 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 @@ -1,5 +1,5 @@ CONFIG_SMP=y -CONFIG_NR_CPUS=4 +CONFIG_NR_CPUS=3 CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot index 238bfe3bd0cc..ce0694fd9b92 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot @@ -1 +1,2 @@ rcutorture.torture_type=srcu +rcutorture.fwd_progress=3 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot index ce48c7b82673..2db39f298d18 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot @@ -1,2 +1,4 @@ rcutorture.torture_type=srcud rcupdate.rcu_self_test=1 +rcutorture.fwd_progress=3 +srcutree.big_cpu_lim=5 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 index 34c8ff5a12f2..e4d74e5fc1d0 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 @@ -1,5 +1,5 @@ CONFIG_SMP=y -CONFIG_NR_CPUS=4 +CONFIG_NR_CPUS=5 CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 2af9d39a9716..215e1067f037 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -6,7 +6,7 @@ endif CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) -LDLIBS += -lpthread +LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but # still track changes to header files and depend on shared object. diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c index b953a52ff706..517756afc2a4 100644 --- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -167,7 +167,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, for (;;) { struct percpu_list_node *head; intptr_t *targetptr, expectnot, *load; - off_t offset; + long offset; int ret, cpu; cpu = rseq_cpu_start(); diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h new file mode 100644 index 000000000000..876eb6a7f75b --- /dev/null +++ b/tools/testing/selftests/rseq/compiler.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq/compiler.h + * + * Work-around asm goto compiler bugs. + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef RSEQ_COMPILER_H +#define RSEQ_COMPILER_H + +/* + * gcc prior to 4.8.2 miscompiles asm goto. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * gcc prior to 8.1.0 miscompiles asm goto at O1. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908 + * + * clang prior to version 13.0.1 miscompiles asm goto at O2. + * https://github.com/llvm/llvm-project/issues/52735 + * + * Work around these issues by adding a volatile inline asm with + * memory clobber in the fallthrough after the asm goto and at each + * label target. Emit this for all compilers in case other similar + * issues are found in the future. + */ +#define rseq_after_asm_goto() asm volatile ("" : : : "memory") + +#endif /* RSEQ_COMPILER_H_ */ diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 699ad5f93c34..da23c22d5882 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -161,7 +161,7 @@ unsigned int yield_mod_cnt, nr_abort; " cbnz " INJECT_ASM_REG ", 222b\n" \ "333:\n" -#elif __PPC__ +#elif defined(__PPC__) #define RSEQ_INJECT_INPUT \ , [loop_cnt_1]"m"(loop_cnt[1]) \ @@ -368,9 +368,7 @@ void *test_percpu_spinlock_thread(void *arg) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { - int cpu = rseq_cpu_start(); - - cpu = rseq_this_cpu_lock(&data->lock); + int cpu = rseq_this_cpu_lock(&data->lock); data->c[cpu].count++; rseq_percpu_unlock(&data->lock, cpu); #ifndef BENCHMARK @@ -551,7 +549,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, for (;;) { struct percpu_list_node *head; intptr_t *targetptr, expectnot, *load; - off_t offset; + long offset; int ret; cpu = rseq_cpu_start(); diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h new file mode 100644 index 000000000000..a8c44d9af71f --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-abi.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _RSEQ_ABI_H +#define _RSEQ_ABI_H + +/* + * rseq-abi.h + * + * Restartable sequences system call API + * + * Copyright (c) 2015-2022 Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#include <linux/types.h> +#include <asm/byteorder.h> + +enum rseq_abi_cpu_id_state { + RSEQ_ABI_CPU_ID_UNINITIALIZED = -1, + RSEQ_ABI_CPU_ID_REGISTRATION_FAILED = -2, +}; + +enum rseq_abi_flags { + RSEQ_ABI_FLAG_UNREGISTER = (1 << 0), +}; + +enum rseq_abi_cs_flags_bit { + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0, + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1, + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2, +}; + +enum rseq_abi_cs_flags { + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT), + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT), + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT), +}; + +/* + * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always + * contained within a single cache-line. It is usually declared as + * link-time constant data. + */ +struct rseq_abi_cs { + /* Version of this structure. */ + __u32 version; + /* enum rseq_abi_cs_flags */ + __u32 flags; + __u64 start_ip; + /* Offset from start_ip. */ + __u64 post_commit_offset; + __u64 abort_ip; +} __attribute__((aligned(4 * sizeof(__u64)))); + +/* + * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always + * contained within a single cache-line. + * + * A single struct rseq_abi per thread is allowed. + */ +struct rseq_abi { + /* + * Restartable sequences cpu_id_start field. Updated by the + * kernel. Read by user-space with single-copy atomicity + * semantics. This field should only be read by the thread which + * registered this data structure. Aligned on 32-bit. Always + * contains a value in the range of possible CPUs, although the + * value may not be the actual current CPU (e.g. if rseq is not + * initialized). This CPU number value should always be compared + * against the value of the cpu_id field before performing a rseq + * commit or returning a value read from a data structure indexed + * using the cpu_id_start value. + */ + __u32 cpu_id_start; + /* + * Restartable sequences cpu_id field. Updated by the kernel. + * Read by user-space with single-copy atomicity semantics. This + * field should only be read by the thread which registered this + * data structure. Aligned on 32-bit. Values + * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED + * have a special semantic: the former means "rseq uninitialized", + * and latter means "rseq initialization failed". This value is + * meant to be read within rseq critical sections and compared + * with the cpu_id_start value previously read, before performing + * the commit instruction, or read and compared with the + * cpu_id_start value before returning a value loaded from a data + * structure indexed using the cpu_id_start value. + */ + __u32 cpu_id; + /* + * Restartable sequences rseq_cs field. + * + * Contains NULL when no critical section is active for the current + * thread, or holds a pointer to the currently active struct rseq_cs. + * + * Updated by user-space, which sets the address of the currently + * active rseq_cs at the beginning of assembly instruction sequence + * block, and set to NULL by the kernel when it restarts an assembly + * instruction sequence block, as well as when the kernel detects that + * it is preempting or delivering a signal outside of the range + * targeted by the rseq_cs. Also needs to be set to NULL by user-space + * before reclaiming memory that contains the targeted struct rseq_cs. + * + * Read and set by the kernel. Set by user-space with single-copy + * atomicity semantics. This field should only be updated by the + * thread which registered this data structure. Aligned on 64-bit. + */ + union { + __u64 ptr64; + + /* + * The "arch" field provides architecture accessor for + * the ptr field based on architecture pointer size and + * endianness. + */ + struct { +#ifdef __LP64__ + __u64 ptr; +#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN) + __u32 padding; /* Initialized to zero. */ + __u32 ptr; +#else + __u32 ptr; + __u32 padding; /* Initialized to zero. */ +#endif + } arch; + } rseq_cs; + + /* + * Restartable sequences flags field. + * + * This field should only be updated by the thread which + * registered this data structure. Read by the kernel. + * Mainly used for single-stepping through rseq critical sections + * with debuggers. + * + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT + * Inhibit instruction sequence block restart on preemption + * for this thread. + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL + * Inhibit instruction sequence block restart on signal + * delivery for this thread. + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE + * Inhibit instruction sequence block restart on migration for + * this thread. + */ + __u32 flags; +} __attribute__((aligned(4 * sizeof(__u64)))); + +#endif /* _RSEQ_ABI_H */ diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h index 5943c816c07c..893a11eca9d5 100644 --- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -147,14 +147,11 @@ do { \ teardown \ "b %l[" __rseq_str(cmpfail_label) "]\n\t" -#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") - static inline __attribute__((always_inline)) int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -185,8 +182,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -198,30 +195,31 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -255,8 +253,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -270,19 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -292,7 +292,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ #ifdef RSEQ_COMPARE_TWICE @@ -316,8 +315,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -328,14 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -347,7 +347,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -381,8 +380,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -398,19 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -422,7 +423,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -474,19 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -498,7 +500,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -537,8 +538,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -554,21 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -582,7 +586,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -657,8 +660,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -678,21 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -706,7 +709,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -782,8 +784,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -803,21 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h index 200dae9e4208..cbe190a4d005 100644 --- a/tools/testing/selftests/rseq/rseq-arm64.h +++ b/tools/testing/selftests/rseq/rseq-arm64.h @@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -242,24 +242,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -287,8 +291,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expectnot] "r" (expectnot), [load] "Qo" (*load), @@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -337,8 +346,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [count] "r" (count) RSEQ_INJECT_INPUT @@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -388,8 +400,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -447,8 +463,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -508,8 +528,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expect] "r" (expect), [v2] "Qo" (*v2), @@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -569,8 +594,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -629,8 +658,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h new file mode 100644 index 000000000000..38c584661571 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-generic-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_GENERIC_THREAD_POINTER +#define _RSEQ_GENERIC_THREAD_POINTER + +#ifdef __cplusplus +extern "C" { +#endif + +/* Use gcc builtin thread pointer. */ +static inline void *rseq_thread_pointer(void) +{ + return __builtin_thread_pointer(); +} + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h index e989e7c14b09..878739fae2fd 100644 --- a/tools/testing/selftests/rseq/rseq-mips.h +++ b/tools/testing/selftests/rseq/rseq-mips.h @@ -154,14 +154,11 @@ do { \ teardown \ "b %l[" __rseq_str(cmpfail_label) "]\n\t" -#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") - static inline __attribute__((always_inline)) int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -190,8 +187,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -203,14 +200,11 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -222,11 +216,10 @@ error2: static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -258,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -273,14 +266,11 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -295,7 +285,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ #ifdef RSEQ_COMPARE_TWICE @@ -319,8 +308,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -331,10 +320,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE @@ -350,7 +337,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -382,8 +368,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -399,14 +385,11 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -423,7 +406,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -456,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -473,14 +455,11 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -497,7 +476,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -532,8 +510,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -549,14 +527,11 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -577,7 +552,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -649,8 +623,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -670,21 +644,16 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("expected value comparison failed"); #endif } @@ -698,7 +667,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -771,8 +739,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -792,21 +760,16 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h new file mode 100644 index 000000000000..263eee84fb76 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-ppc-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_PPC_THREAD_POINTER +#define _RSEQ_PPC_THREAD_POINTER + +#ifdef __cplusplus +extern "C" { +#endif + +static inline void *rseq_thread_pointer(void) +{ +#ifdef __powerpc64__ + register void *__result asm ("r13"); +#else + register void *__result asm ("r2"); +#endif + asm ("" : "=r" (__result)); + return __result; +} + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h index 76be90196fe4..bab8e0b9fb11 100644 --- a/tools/testing/selftests/rseq/rseq-ppc.h +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -47,10 +47,13 @@ do { \ #ifdef __PPC64__ -#define STORE_WORD "std " -#define LOAD_WORD "ld " -#define LOADX_WORD "ldx " -#define CMP_WORD "cmpd " +#define RSEQ_STORE_LONG(arg) "std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "ldx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpd " +#define RSEQ_CMP_LONG_INT "cmpdi " #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -89,10 +92,13 @@ do { \ #else /* #ifdef __PPC64__ */ -#define STORE_WORD "stw " -#define LOAD_WORD "lwz " -#define LOADX_WORD "lwzx " -#define CMP_WORD "cmpw " +#define RSEQ_STORE_LONG(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) RSEQ_STORE_LONG(arg) /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) RSEQ_LOAD_LONG(arg) /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "lwzx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpw " +#define RSEQ_CMP_LONG_INT "cmpwi " #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -125,7 +131,7 @@ do { \ RSEQ_INJECT_ASM(1) \ "lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t" \ "addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \ - "stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ + RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ __rseq_str(label) ":\n\t" #endif /* #ifdef __PPC64__ */ @@ -136,7 +142,7 @@ do { \ #define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ RSEQ_INJECT_ASM(2) \ - "lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ + RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ "cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t" @@ -153,25 +159,25 @@ do { \ * RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7) */ #define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t" #define RSEQ_ASM_OP_CMPNE(var, expectnot, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ "beq- cr7, " __rseq_str(label) "\n\t" #define RSEQ_ASM_OP_STORE(value, var) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" /* Load @var to r17 */ #define RSEQ_ASM_OP_R_LOAD(var) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" /* Store r17 to @var */ #define RSEQ_ASM_OP_R_STORE(var) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" /* Add @count to r17 */ #define RSEQ_ASM_OP_R_ADD(count) \ @@ -179,11 +185,11 @@ do { \ /* Load (r17 + voffp) to r17 */ #define RSEQ_ASM_OP_R_LOADX(voffp) \ - LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" + RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" /* TODO: implement a faster memcpy. */ #define RSEQ_ASM_OP_R_MEMCPY() \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "beq 333f\n\t" \ "addi %%r20, %%r20, -1\n\t" \ "addi %%r21, %%r21, -1\n\t" \ @@ -191,16 +197,16 @@ do { \ "lbzu %%r18, 1(%%r20)\n\t" \ "stbu %%r18, 1(%%r21)\n\t" \ "addi %%r19, %%r19, -1\n\t" \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "bne 222b\n\t" \ "333:\n\t" \ #define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t" #define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t" static inline __attribute__((always_inline)) @@ -235,8 +241,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -248,23 +254,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -301,8 +312,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -316,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -359,8 +375,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -372,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -419,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -436,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -489,8 +513,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -506,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -560,8 +589,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -577,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -635,8 +670,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -653,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -711,8 +751,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -729,23 +769,23 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } -#undef STORE_WORD -#undef LOAD_WORD -#undef LOADX_WORD -#undef CMP_WORD - #endif /* !RSEQ_SKIP_FASTPATH */ diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h index 8ef94ad1cbb4..4e6dc5f0cb42 100644 --- a/tools/testing/selftests/rseq/rseq-s390.h +++ b/tools/testing/selftests/rseq/rseq-s390.h @@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -198,7 +203,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -233,8 +238,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -288,8 +298,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -347,8 +360,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -426,8 +444,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -534,8 +558,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h index 72750b5905a9..7b53dac1fcdd 100644 --- a/tools/testing/selftests/rseq/rseq-skip.h +++ b/tools/testing/selftests/rseq/rseq-skip.h @@ -13,7 +13,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { return -1; } diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h new file mode 100644 index 000000000000..977c25d758b2 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_THREAD_POINTER +#define _RSEQ_THREAD_POINTER + +#if defined(__x86_64__) || defined(__i386__) +#include "rseq-x86-thread-pointer.h" +#elif defined(__PPC__) +#include "rseq-ppc-thread-pointer.h" +#else +#include "rseq-generic-thread-pointer.h" +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h new file mode 100644 index 000000000000..d3133587d996 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-x86-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_X86_THREAD_POINTER +#define _RSEQ_X86_THREAD_POINTER + +#include <features.h> + +#ifdef __cplusplus +extern "C" { +#endif + +#if __GNUC_PREREQ (11, 1) +static inline void *rseq_thread_pointer(void) +{ + return __builtin_thread_pointer(); +} +#else +static inline void *rseq_thread_pointer(void) +{ + void *__result; + +# ifdef __x86_64__ + __asm__ ("mov %%fs:0, %0" : "=r" (__result)); +# else + __asm__ ("mov %%gs:0, %0" : "=r" (__result)); +# endif + return __result; +} +#endif /* !GCC 11 */ + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h index 640411518e46..bd01dc41ca13 100644 --- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -28,6 +28,8 @@ #ifdef __x86_64__ +#define RSEQ_ASM_TP_SEGMENT %%fs + #define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc") #define rseq_smp_rmb() rseq_barrier() @@ -123,14 +125,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -141,7 +143,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -152,16 +154,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -172,7 +179,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -184,15 +191,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movq %[v], %%rbx\n\t" "cmpq %%rbx, %[expectnot]\n\t" "je %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movq %[v], %%rbx\n\t" "cmpq %%rbx, %[expectnot]\n\t" "je %l[error2]\n\t" @@ -207,7 +214,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -220,16 +227,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -245,11 +257,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* final store */ "addq %[count], %[v]\n\t" @@ -258,7 +270,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [count] "er" (count) @@ -269,12 +281,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -286,7 +301,7 @@ error1: * *pval += inc; */ static inline __attribute__((always_inline)) -int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) +int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu) { RSEQ_INJECT_C(9) @@ -296,11 +311,11 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* get p+v */ "movq %[ptr], %%rbx\n\t" @@ -314,7 +329,7 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [ptr] "m" (*ptr), [off] "er" (off), @@ -351,14 +366,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -372,7 +387,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -387,16 +402,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -426,8 +446,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" @@ -436,7 +456,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(5) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" "cmpq %[v2], %[expect2]\n\t" @@ -449,7 +469,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -464,18 +484,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -500,14 +526,14 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "movq %[dst], %[rseq_scratch1]\n\t" "movq %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "cmpq %[v], %[expect]\n\t" "jnz 7f\n\t" #endif @@ -555,7 +581,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -574,16 +600,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -600,7 +631,9 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, #endif /* !RSEQ_SKIP_FASTPATH */ -#elif __i386__ +#elif defined(__i386__) + +#define RSEQ_ASM_TP_SEGMENT %%gs #define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc") @@ -701,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -719,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -730,16 +763,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -750,7 +788,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -762,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[error2]\n\t" @@ -785,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -798,16 +836,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -823,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* final store */ "addl %[count], %[v]\n\t" @@ -836,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [count] "ir" (count) @@ -847,12 +890,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -872,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -894,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "m" (newv2), @@ -909,16 +955,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -938,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[error2]\n\t" @@ -962,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -977,16 +1028,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif @@ -1008,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" @@ -1018,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(5) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" "cmpl %[expect2], %[v2]\n\t" @@ -1032,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -1047,18 +1103,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -1084,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1142,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1161,16 +1223,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -1196,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1255,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1274,16 +1341,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index fb440dfca158..986b9458efb2 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -26,130 +26,124 @@ #include <assert.h> #include <signal.h> #include <limits.h> +#include <dlfcn.h> +#include <stddef.h> #include "../kselftest.h" #include "rseq.h" -__thread volatile struct rseq __rseq_abi = { - .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, -}; - -/* - * Shared with other libraries. This library may take rseq ownership if it is - * still 0 when executing the library constructor. Set to 1 by library - * constructor when handling rseq. Set to 0 in destructor if handling rseq. - */ -int __rseq_handled; - -/* Whether this library have ownership of rseq registration. */ -static int rseq_ownership; +static const ptrdiff_t *libc_rseq_offset_p; +static const unsigned int *libc_rseq_size_p; +static const unsigned int *libc_rseq_flags_p; -static __thread volatile uint32_t __rseq_refcount; +/* Offset from the thread pointer to the rseq area. */ +ptrdiff_t rseq_offset; -static void signal_off_save(sigset_t *oldset) -{ - sigset_t set; - int ret; +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +unsigned int rseq_size = -1U; - sigfillset(&set); - ret = pthread_sigmask(SIG_BLOCK, &set, oldset); - if (ret) - abort(); -} +/* Flags used during rseq registration. */ +unsigned int rseq_flags; -static void signal_restore(sigset_t oldset) -{ - int ret; +static int rseq_ownership; - ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL); - if (ret) - abort(); -} +static +__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = { + .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, +}; -static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len, +static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len, int flags, uint32_t sig) { return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig); } -int rseq_register_current_thread(void) +int rseq_available(void) { - int rc, ret = 0; - sigset_t oldset; + int rc; - if (!rseq_ownership) + rc = sys_rseq(NULL, 0, 0, 0); + if (rc != -1) + abort(); + switch (errno) { + case ENOSYS: return 0; - signal_off_save(&oldset); - if (__rseq_refcount == UINT_MAX) { - ret = -1; - goto end; - } - if (__rseq_refcount++) - goto end; - rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG); - if (!rc) { - assert(rseq_current_cpu_raw() >= 0); - goto end; + case EINVAL: + return 1; + default: + abort(); } - if (errno != EBUSY) - __rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED; - ret = -1; - __rseq_refcount--; -end: - signal_restore(oldset); - return ret; } -int rseq_unregister_current_thread(void) +int rseq_register_current_thread(void) { - int rc, ret = 0; - sigset_t oldset; + int rc; - if (!rseq_ownership) + if (!rseq_ownership) { + /* Treat libc's ownership as a successful registration. */ return 0; - signal_off_save(&oldset); - if (!__rseq_refcount) { - ret = -1; - goto end; } - if (--__rseq_refcount) - goto end; - rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), - RSEQ_FLAG_UNREGISTER, RSEQ_SIG); - if (!rc) - goto end; - __rseq_refcount = 1; - ret = -1; -end: - signal_restore(oldset); - return ret; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG); + if (rc) + return -1; + assert(rseq_current_cpu_raw() >= 0); + return 0; } -int32_t rseq_fallback_current_cpu(void) +int rseq_unregister_current_thread(void) { - int32_t cpu; + int rc; - cpu = sched_getcpu(); - if (cpu < 0) { - perror("sched_getcpu()"); - abort(); + if (!rseq_ownership) { + /* Treat libc's ownership as a successful unregistration. */ + return 0; } - return cpu; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + if (rc) + return -1; + return 0; } -void __attribute__((constructor)) rseq_init(void) +static __attribute__((constructor)) +void rseq_init(void) { - /* Check whether rseq is handled by another library. */ - if (__rseq_handled) + libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); + libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); + libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) { + /* rseq registration owned by glibc */ + rseq_offset = *libc_rseq_offset_p; + rseq_size = *libc_rseq_size_p; + rseq_flags = *libc_rseq_flags_p; + return; + } + if (!rseq_available()) return; - __rseq_handled = 1; rseq_ownership = 1; + rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + rseq_size = sizeof(struct rseq_abi); + rseq_flags = 0; } -void __attribute__((destructor)) rseq_fini(void) +static __attribute__((destructor)) +void rseq_exit(void) { if (!rseq_ownership) return; - __rseq_handled = 0; + rseq_offset = 0; + rseq_size = -1U; rseq_ownership = 0; } + +int32_t rseq_fallback_current_cpu(void) +{ + int32_t cpu; + + cpu = sched_getcpu(); + if (cpu < 0) { + perror("sched_getcpu()"); + abort(); + } + return cpu; +} diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 3f63eb362b92..9d850b290c2e 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -16,7 +16,9 @@ #include <errno.h> #include <stdio.h> #include <stdlib.h> -#include <linux/rseq.h> +#include <stddef.h> +#include "rseq-abi.h" +#include "compiler.h" /* * Empty code injection macros, override when testing. @@ -43,8 +45,20 @@ #define RSEQ_INJECT_FAILED #endif -extern __thread volatile struct rseq __rseq_abi; -extern int __rseq_handled; +#include "rseq-thread-pointer.h" + +/* Offset from the thread pointer to the rseq area. */ +extern ptrdiff_t rseq_offset; +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +extern unsigned int rseq_size; +/* Flags used during rseq registration. */ +extern unsigned int rseq_flags; + +static inline struct rseq_abi *rseq_get_abi(void) +{ + return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset); +} #define rseq_likely(x) __builtin_expect(!!(x), 1) #define rseq_unlikely(x) __builtin_expect(!!(x), 0) @@ -108,7 +122,7 @@ int32_t rseq_fallback_current_cpu(void); */ static inline int32_t rseq_current_cpu_raw(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id); } /* @@ -124,7 +138,7 @@ static inline int32_t rseq_current_cpu_raw(void) */ static inline uint32_t rseq_cpu_start(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start); } static inline uint32_t rseq_current_cpu(void) @@ -139,11 +153,7 @@ static inline uint32_t rseq_current_cpu(void) static inline void rseq_clear_rseq_cs(void) { -#ifdef __LP64__ - __rseq_abi.rseq_cs.ptr = 0; -#else - __rseq_abi.rseq_cs.ptr.ptr32 = 0; -#endif + RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0); } /* diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index 66af608fb4c6..2b9d929a24ed 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -20,6 +20,8 @@ #define NUM_UIE 3 #define ALARM_DELTA 3 +#define READ_LOOP_DURATION_SEC 30 +#define READ_LOOP_SLEEP_MS 11 static char *rtc_file = "/dev/rtc0"; @@ -49,6 +51,70 @@ TEST_F(rtc, date_read) { rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); } +static time_t rtc_time_to_timestamp(struct rtc_time *rtc_time) +{ + struct tm tm_time = { + .tm_sec = rtc_time->tm_sec, + .tm_min = rtc_time->tm_min, + .tm_hour = rtc_time->tm_hour, + .tm_mday = rtc_time->tm_mday, + .tm_mon = rtc_time->tm_mon, + .tm_year = rtc_time->tm_year, + }; + + return mktime(&tm_time); +} + +static void nanosleep_with_retries(long ns) +{ + struct timespec req = { + .tv_sec = 0, + .tv_nsec = ns, + }; + struct timespec rem; + + while (nanosleep(&req, &rem) != 0) { + req.tv_sec = rem.tv_sec; + req.tv_nsec = rem.tv_nsec; + } +} + +TEST_F_TIMEOUT(rtc, date_read_loop, READ_LOOP_DURATION_SEC + 2) { + int rc; + long iter_count = 0; + struct rtc_time rtc_tm; + time_t start_rtc_read, prev_rtc_read; + + TH_LOG("Continuously reading RTC time for %ds (with %dms breaks after every read).", + READ_LOOP_DURATION_SEC, READ_LOOP_SLEEP_MS); + + rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm); + ASSERT_NE(-1, rc); + start_rtc_read = rtc_time_to_timestamp(&rtc_tm); + prev_rtc_read = start_rtc_read; + + do { + time_t rtc_read; + + rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm); + ASSERT_NE(-1, rc); + + rtc_read = rtc_time_to_timestamp(&rtc_tm); + /* Time should not go backwards */ + ASSERT_LE(prev_rtc_read, rtc_read); + /* Time should not increase more then 1s at a time */ + ASSERT_GE(prev_rtc_read + 1, rtc_read); + + /* Sleep 11ms to avoid killing / overheating the RTC */ + nanosleep_with_retries(READ_LOOP_SLEEP_MS * 1000000); + + prev_rtc_read = rtc_read; + iter_count++; + } while (prev_rtc_read <= start_rtc_read + READ_LOOP_DURATION_SEC); + + TH_LOG("Performed %ld RTC time reads.", iter_count); +} + TEST_F_TIMEOUT(rtc, uie_read, NUM_UIE + 2) { int i, rc, irq = 0; unsigned long data; diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings index ba4d85f74cd6..0c1a2075d5f3 100644 --- a/tools/testing/selftests/rtc/settings +++ b/tools/testing/selftests/rtc/settings @@ -1 +1 @@ -timeout=90 +timeout=210 diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile index 0ebfe8b0e147..585f7a0c10cb 100644 --- a/tools/testing/selftests/seccomp/Makefile +++ b/tools/testing/selftests/seccomp/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wl,-no-as-needed -Wall +CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/ LDFLAGS += -lpthread TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 2956584e1e37..75af864e07b6 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -4,7 +4,7 @@ include ../lib.mk .PHONY: all clean -CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh $(CC) \ +CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh "$(CC)" \ ../x86/trivial_64bit_program.c) ifndef OBJCOPY diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c index 9d4322c946e2..006b464c8fc9 100644 --- a/tools/testing/selftests/sgx/load.c +++ b/tools/testing/selftests/sgx/load.c @@ -21,7 +21,7 @@ void encl_delete(struct encl *encl) { - struct encl_segment *heap_seg = &encl->segment_tbl[encl->nr_segments - 1]; + struct encl_segment *heap_seg; if (encl->encl_base) munmap((void *)encl->encl_base, encl->encl_size); @@ -32,10 +32,11 @@ void encl_delete(struct encl *encl) if (encl->fd) close(encl->fd); - munmap(heap_seg->src, heap_seg->size); - - if (encl->segment_tbl) + if (encl->segment_tbl) { + heap_seg = &encl->segment_tbl[encl->nr_segments - 1]; + munmap(heap_seg->src, heap_seg->size); free(encl->segment_tbl); + } memset(encl, 0, sizeof(*encl)); } diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index 370c4995f7c4..dd74fa42302e 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -146,7 +146,8 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl, if (!encl_load("test_encl.elf", encl, heap_size)) { encl_delete(encl); - TH_LOG("Failed to load the test enclave.\n"); + TH_LOG("Failed to load the test enclave."); + return false; } if (!encl_measure(encl)) @@ -185,8 +186,6 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl, return true; err: - encl_delete(encl); - for (i = 0; i < encl->nr_segments; i++) { seg = &encl->segment_tbl[i]; @@ -205,7 +204,9 @@ err: fclose(maps_file); } - TH_LOG("Failed to initialize the test enclave.\n"); + TH_LOG("Failed to initialize the test enclave."); + + encl_delete(encl); return false; } diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index f34486cd7342..057a4f49c79d 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -56,6 +56,7 @@ TSS2_RESMGR_TPM_RC_LAYER = (11 << TSS2_RC_LAYER_SHIFT) TPM2_CAP_HANDLES = 0x00000001 TPM2_CAP_COMMANDS = 0x00000002 +TPM2_CAP_PCRS = 0x00000005 TPM2_CAP_TPM_PROPERTIES = 0x00000006 TPM2_PT_FIXED = 0x100 @@ -712,3 +713,33 @@ class Client: pt += 1 return handles + + def get_cap_pcrs(self): + pcr_banks = {} + + fmt = '>HII III' + + cmd = struct.pack(fmt, + TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + TPM2_CC_GET_CAPABILITY, + TPM2_CAP_PCRS, 0, 1) + rsp = self.send_cmd(cmd)[10:] + _, _, cnt = struct.unpack('>BII', rsp[:9]) + rsp = rsp[9:] + + # items are TPMS_PCR_SELECTION's + for i in range(0, cnt): + hash, sizeOfSelect = struct.unpack('>HB', rsp[:3]) + rsp = rsp[3:] + + pcrSelect = 0 + if sizeOfSelect > 0: + pcrSelect, = struct.unpack('%ds' % sizeOfSelect, + rsp[:sizeOfSelect]) + rsp = rsp[sizeOfSelect:] + pcrSelect = int.from_bytes(pcrSelect, byteorder='big') + + pcr_banks[hash] = pcrSelect + + return pcr_banks diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index 9d764306887b..ffe98b5c8d22 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -27,7 +27,17 @@ class SmokeTest(unittest.TestCase): result = self.client.unseal(self.root_key, blob, auth, None) self.assertEqual(data, result) + def determine_bank_alg(self, mask): + pcr_banks = self.client.get_cap_pcrs() + for bank_alg, pcrSelection in pcr_banks.items(): + if pcrSelection & mask == mask: + return bank_alg + return None + def test_seal_with_policy(self): + bank_alg = self.determine_bank_alg(1 << 16) + self.assertIsNotNone(bank_alg) + handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) data = ('X' * 64).encode() @@ -35,7 +45,7 @@ class SmokeTest(unittest.TestCase): pcrs = [16] try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) policy_dig = self.client.get_policy_digest(handle) @@ -47,7 +57,7 @@ class SmokeTest(unittest.TestCase): handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) @@ -72,6 +82,9 @@ class SmokeTest(unittest.TestCase): self.assertEqual(rc, tpm2.TPM2_RC_AUTH_FAIL) def test_unseal_with_wrong_policy(self): + bank_alg = self.determine_bank_alg(1 << 16 | 1 << 1) + self.assertIsNotNone(bank_alg) + handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) data = ('X' * 64).encode() @@ -79,7 +92,7 @@ class SmokeTest(unittest.TestCase): pcrs = [16] try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) policy_dig = self.client.get_policy_digest(handle) @@ -91,13 +104,13 @@ class SmokeTest(unittest.TestCase): # Extend first a PCR that is not part of the policy and try to unseal. # This should succeed. - ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1) - self.client.extend_pcr(1, ('X' * ds).encode()) + ds = tpm2.get_digest_size(bank_alg) + self.client.extend_pcr(1, ('X' * ds).encode(), bank_alg=bank_alg) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) @@ -109,14 +122,14 @@ class SmokeTest(unittest.TestCase): # Then, extend a PCR that is part of the policy and try to unseal. # This should fail. - self.client.extend_pcr(16, ('X' * ds).encode()) + self.client.extend_pcr(16, ('X' * ds).encode(), bank_alg=bank_alg) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) rc = 0 try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) @@ -302,3 +315,19 @@ class AsyncTest(unittest.TestCase): log.debug("Calling get_cap in a NON_BLOCKING mode") async_client.get_cap(tpm2.TPM2_CAP_HANDLES, tpm2.HR_LOADED_SESSION) async_client.close() + + def test_flush_invalid_context(self): + log = logging.getLogger(__name__) + log.debug(sys._getframe().f_code.co_name) + + async_client = tpm2.Client(tpm2.Client.FLAG_SPACE | tpm2.Client.FLAG_NONBLOCK) + log.debug("Calling flush_context passing in an invalid handle ") + handle = 0x80123456 + rc = 0 + try: + async_client.flush_context(handle) + except OSError as e: + rc = e.errno + + self.assertEqual(rc, 22) + async_client.close() diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile new file mode 100644 index 000000000000..c765d8635d9a --- /dev/null +++ b/tools/testing/selftests/user_events/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include +LDLIBS += -lrt -lpthread -lm + +TEST_GEN_PROGS = ftrace_test dyn_test perf_test + +TEST_FILES := settings + +include ../lib.mk diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c new file mode 100644 index 000000000000..d6265d14cd51 --- /dev/null +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events Dyn Events Test Program + * + * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com> + */ + +#include <errno.h> +#include <linux/user_events.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +const char *dyn_file = "/sys/kernel/debug/tracing/dynamic_events"; +const char *clear = "!u:__test_event"; + +static int Append(const char *value) +{ + int fd = open(dyn_file, O_RDWR | O_APPEND); + int ret = write(fd, value, strlen(value)); + + close(fd); + return ret; +} + +#define CLEAR() \ +do { \ + int ret = Append(clear); \ + if (ret == -1) \ + ASSERT_EQ(ENOENT, errno); \ +} while (0) + +#define TEST_PARSE(x) \ +do { \ + ASSERT_NE(-1, Append(x)); \ + CLEAR(); \ +} while (0) + +#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x)) + +FIXTURE(user) { +}; + +FIXTURE_SETUP(user) { + CLEAR(); +} + +FIXTURE_TEARDOWN(user) { + CLEAR(); +} + +TEST_F(user, basic_types) { + /* All should work */ + TEST_PARSE("u:__test_event u64 a"); + TEST_PARSE("u:__test_event u32 a"); + TEST_PARSE("u:__test_event u16 a"); + TEST_PARSE("u:__test_event u8 a"); + TEST_PARSE("u:__test_event char a"); + TEST_PARSE("u:__test_event unsigned char a"); + TEST_PARSE("u:__test_event int a"); + TEST_PARSE("u:__test_event unsigned int a"); + TEST_PARSE("u:__test_event short a"); + TEST_PARSE("u:__test_event unsigned short a"); + TEST_PARSE("u:__test_event char[20] a"); + TEST_PARSE("u:__test_event unsigned char[20] a"); + TEST_PARSE("u:__test_event char[0x14] a"); + TEST_PARSE("u:__test_event unsigned char[0x14] a"); + /* Bad size format should fail */ + TEST_NPARSE("u:__test_event char[aa] a"); + /* Large size should fail */ + TEST_NPARSE("u:__test_event char[9999] a"); + /* Long size string should fail */ + TEST_NPARSE("u:__test_event char[0x0000000000001] a"); +} + +TEST_F(user, loc_types) { + /* All should work */ + TEST_PARSE("u:__test_event __data_loc char[] a"); + TEST_PARSE("u:__test_event __data_loc unsigned char[] a"); + TEST_PARSE("u:__test_event __rel_loc char[] a"); + TEST_PARSE("u:__test_event __rel_loc unsigned char[] a"); +} + +TEST_F(user, size_types) { + /* Should work */ + TEST_PARSE("u:__test_event struct custom a 20"); + /* Size not specified on struct should fail */ + TEST_NPARSE("u:__test_event struct custom a"); + /* Size specified on non-struct should fail */ + TEST_NPARSE("u:__test_event char a 20"); +} + +TEST_F(user, flags) { + /* Should work */ + TEST_PARSE("u:__test_event:BPF_ITER u32 a"); + /* Forward compat */ + TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a"); +} + +TEST_F(user, matching) { + /* Register */ + ASSERT_NE(-1, Append("u:__test_event struct custom a 20")); + /* Should not match */ + TEST_NPARSE("!u:__test_event struct custom b"); + /* Should match */ + TEST_PARSE("!u:__test_event struct custom a"); + /* Multi field reg */ + ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); + /* Non matching cases */ + TEST_NPARSE("!u:__test_event u32 a"); + TEST_NPARSE("!u:__test_event u32 b"); + TEST_NPARSE("!u:__test_event u32 a; u32 "); + TEST_NPARSE("!u:__test_event u32 a; u32 a"); + /* Matching case */ + TEST_PARSE("!u:__test_event u32 a; u32 b"); + /* Register */ + ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); + /* Ensure trailing semi-colon case */ + TEST_PARSE("!u:__test_event u32 a; u32 b;"); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c new file mode 100644 index 000000000000..a80fb5ef61d5 --- /dev/null +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events FTrace Test Program + * + * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com> + */ + +#include <errno.h> +#include <linux/user_events.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; +const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; +const char *enable_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/enable"; +const char *trace_file = "/sys/kernel/debug/tracing/trace"; +const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; + +static int trace_bytes(void) +{ + int fd = open(trace_file, O_RDONLY); + char buf[256]; + int bytes = 0, got; + + if (fd == -1) + return -1; + + while (true) { + got = read(fd, buf, sizeof(buf)); + + if (got == -1) + return -1; + + if (got == 0) + break; + + bytes += got; + } + + close(fd); + + return bytes; +} + +static int skip_until_empty_line(FILE *fp) +{ + int c, last = 0; + + while (true) { + c = getc(fp); + + if (c == EOF) + break; + + if (last == '\n' && c == '\n') + return 0; + + last = c; + } + + return -1; +} + +static int get_print_fmt(char *buffer, int len) +{ + FILE *fp = fopen(fmt_file, "r"); + char *newline; + + if (!fp) + return -1; + + /* Read until empty line (Skip Common) */ + if (skip_until_empty_line(fp) < 0) + goto err; + + /* Read until empty line (Skip Properties) */ + if (skip_until_empty_line(fp) < 0) + goto err; + + /* Read in print_fmt: */ + if (fgets(buffer, len, fp) == NULL) + goto err; + + newline = strchr(buffer, '\n'); + + if (newline) + *newline = '\0'; + + fclose(fp); + + return 0; +err: + fclose(fp); + + return -1; +} + +static int clear(void) +{ + int fd = open(data_file, O_RDWR); + + if (fd == -1) + return -1; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) + if (errno != ENOENT) + return -1; + + close(fd); + + return 0; +} + +static int check_print_fmt(const char *event, const char *expected) +{ + struct user_reg reg = {0}; + char print_fmt[256]; + int ret; + int fd; + + /* Ensure cleared */ + ret = clear(); + + if (ret != 0) + return ret; + + fd = open(data_file, O_RDWR); + + if (fd == -1) + return fd; + + reg.size = sizeof(reg); + reg.name_args = (__u64)event; + + /* Register should work */ + ret = ioctl(fd, DIAG_IOCSREG, ®); + + close(fd); + + if (ret != 0) + return ret; + + /* Ensure correct print_fmt */ + ret = get_print_fmt(print_fmt, sizeof(print_fmt)); + + if (ret != 0) + return ret; + + return strcmp(print_fmt, expected); +} + +FIXTURE(user) { + int status_fd; + int data_fd; + int enable_fd; +}; + +FIXTURE_SETUP(user) { + self->status_fd = open(status_file, O_RDONLY); + ASSERT_NE(-1, self->status_fd); + + self->data_fd = open(data_file, O_RDWR); + ASSERT_NE(-1, self->data_fd); + + self->enable_fd = -1; +} + +FIXTURE_TEARDOWN(user) { + close(self->status_fd); + close(self->data_fd); + + if (self->enable_fd != -1) { + write(self->enable_fd, "0", sizeof("0")); + close(self->enable_fd); + } + + ASSERT_EQ(0, clear()); +} + +TEST_F(user, register_events) { + struct user_reg reg = {0}; + int page_size = sysconf(_SC_PAGESIZE); + char *status_page; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + + status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, + self->status_fd, 0); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Multiple registers should result in same index */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Ensure disabled */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, self->enable_fd); + ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) + + /* MMAP should work and be zero'd */ + ASSERT_NE(MAP_FAILED, status_page); + ASSERT_NE(NULL, status_page); + ASSERT_EQ(0, status_page[reg.status_index]); + + /* Enable event and ensure bits updated in status */ + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + ASSERT_EQ(EVENT_STATUS_FTRACE, status_page[reg.status_index]); + + /* Disable event and ensure bits updated in status */ + ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) + ASSERT_EQ(0, status_page[reg.status_index]); + + /* File still open should return -EBUSY for delete */ + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + ASSERT_EQ(EBUSY, errno); + + /* Delete should work only after close */ + close(self->data_fd); + self->data_fd = open(data_file, O_RDWR); + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + + /* Unmap should work */ + ASSERT_EQ(0, munmap(status_page, page_size)); +} + +TEST_F(user, write_events) { + struct user_reg reg = {0}; + struct iovec io[3]; + __u32 field1, field2; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + + field1 = 1; + field2 = 2; + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + io[1].iov_base = &field1; + io[1].iov_len = sizeof(field1); + io[2].iov_base = &field2; + io[2].iov_len = sizeof(field2); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Write should fail on invalid slot with ENOENT */ + io[0].iov_base = &field2; + io[0].iov_len = sizeof(field2); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(ENOENT, errno); + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Write should make it out to ftrace buffers */ + before = trace_bytes(); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + after = trace_bytes(); + ASSERT_GT(after, before); +} + +TEST_F(user, write_fault) { + struct user_reg reg = {0}; + struct iovec io[2]; + int l = sizeof(__u64); + void *anon; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u64 anon"; + + anon = mmap(NULL, l, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, anon); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + io[1].iov_base = anon; + io[1].iov_len = l; + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Write should work normally */ + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); + + /* Faulted data should zero fill and work */ + ASSERT_EQ(0, madvise(anon, l, MADV_DONTNEED)); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); + ASSERT_EQ(0, munmap(anon, l)); +} + +TEST_F(user, write_validator) { + struct user_reg reg = {0}; + struct iovec io[3]; + int loc, bytes; + char data[8]; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event __rel_loc char[] data"; + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + io[1].iov_base = &loc; + io[1].iov_len = sizeof(loc); + io[2].iov_base = data; + bytes = snprintf(data, sizeof(data), "Test") + 1; + io[2].iov_len = bytes; + + /* Undersized write should fail */ + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 1)); + ASSERT_EQ(EINVAL, errno); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Full in-bounds write should work */ + before = trace_bytes(); + loc = DYN_LOC(0, bytes); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + after = trace_bytes(); + ASSERT_GT(after, before); + + /* Out of bounds write should fault (offset way out) */ + loc = DYN_LOC(1024, bytes); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Out of bounds write should fault (offset 1 byte out) */ + loc = DYN_LOC(1, bytes); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Out of bounds write should fault (size way out) */ + loc = DYN_LOC(0, bytes + 1024); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Out of bounds write should fault (size 1 byte out) */ + loc = DYN_LOC(0, bytes + 1); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Non-Null should fault */ + memset(data, 'A', sizeof(data)); + loc = DYN_LOC(0, bytes); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); +} + +TEST_F(user, print_fmt) { + int ret; + + ret = check_print_fmt("__test_event __rel_loc char[] data", + "print fmt: \"data=%s\", __get_rel_str(data)"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event __data_loc char[] data", + "print fmt: \"data=%s\", __get_str(data)"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s64 data", + "print fmt: \"data=%lld\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u64 data", + "print fmt: \"data=%llu\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s32 data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u32 data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event int data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event unsigned int data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s16 data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u16 data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event short data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event unsigned short data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s8 data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u8 data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event char data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event unsigned char data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event char[4] data", + "print fmt: \"data=%s\", REC->data"); + ASSERT_EQ(0, ret); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c new file mode 100644 index 000000000000..26851d51d6bb --- /dev/null +++ b/tools/testing/selftests/user_events/perf_test.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events Perf Events Test Program + * + * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com> + */ + +#include <errno.h> +#include <linux/user_events.h> +#include <linux/perf_event.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <unistd.h> +#include <asm/unistd.h> + +#include "../kselftest_harness.h" + +const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; +const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; +const char *id_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/id"; +const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; + +struct event { + __u32 index; + __u32 field1; + __u32 field2; +}; + +static long perf_event_open(struct perf_event_attr *pe, pid_t pid, + int cpu, int group_fd, unsigned long flags) +{ + return syscall(__NR_perf_event_open, pe, pid, cpu, group_fd, flags); +} + +static int get_id(void) +{ + FILE *fp = fopen(id_file, "r"); + int ret, id = 0; + + if (!fp) + return -1; + + ret = fscanf(fp, "%d", &id); + fclose(fp); + + if (ret != 1) + return -1; + + return id; +} + +static int get_offset(void) +{ + FILE *fp = fopen(fmt_file, "r"); + int ret, c, last = 0, offset = 0; + + if (!fp) + return -1; + + /* Read until empty line */ + while (true) { + c = getc(fp); + + if (c == EOF) + break; + + if (last == '\n' && c == '\n') + break; + + last = c; + } + + ret = fscanf(fp, "\tfield:u32 field1;\toffset:%d;", &offset); + fclose(fp); + + if (ret != 1) + return -1; + + return offset; +} + +FIXTURE(user) { + int status_fd; + int data_fd; +}; + +FIXTURE_SETUP(user) { + self->status_fd = open(status_file, O_RDONLY); + ASSERT_NE(-1, self->status_fd); + + self->data_fd = open(data_file, O_RDWR); + ASSERT_NE(-1, self->data_fd); +} + +FIXTURE_TEARDOWN(user) { + close(self->status_fd); + close(self->data_fd); +} + +TEST_F(user, perf_write) { + struct perf_event_attr pe = {0}; + struct user_reg reg = {0}; + int page_size = sysconf(_SC_PAGESIZE); + char *status_page; + struct event event; + struct perf_event_mmap_page *perf_page; + int id, fd, offset; + __u32 *val; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + + status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, + self->status_fd, 0); + ASSERT_NE(MAP_FAILED, status_page); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + ASSERT_EQ(0, status_page[reg.status_index]); + + /* Id should be there */ + id = get_id(); + ASSERT_NE(-1, id); + offset = get_offset(); + ASSERT_NE(-1, offset); + + pe.type = PERF_TYPE_TRACEPOINT; + pe.size = sizeof(pe); + pe.config = id; + pe.sample_type = PERF_SAMPLE_RAW; + pe.sample_period = 1; + pe.wakeup_events = 1; + + /* Tracepoint attach should work */ + fd = perf_event_open(&pe, 0, -1, -1, 0); + ASSERT_NE(-1, fd); + + perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0); + ASSERT_NE(MAP_FAILED, perf_page); + + /* Status should be updated */ + ASSERT_EQ(EVENT_STATUS_PERF, status_page[reg.status_index]); + + event.index = reg.write_index; + event.field1 = 0xc001; + event.field2 = 0xc01a; + + /* Ensure write shows up at correct offset */ + ASSERT_NE(-1, write(self->data_fd, &event, sizeof(event))); + val = (void *)(((char *)perf_page) + perf_page->data_offset); + ASSERT_EQ(PERF_RECORD_SAMPLE, *val); + /* Skip over header and size, move to offset */ + val += 3; + val = (void *)((char *)val) + offset; + /* Ensure correct */ + ASSERT_EQ(event.field1, *val++); + ASSERT_EQ(event.field2, *val++); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/user_events/settings b/tools/testing/selftests/user_events/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/user_events/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h index 6188b16827d1..cdfed403ba13 100644 --- a/tools/testing/selftests/vDSO/vdso_config.h +++ b/tools/testing/selftests/vDSO/vdso_config.h @@ -53,10 +53,6 @@ #if __riscv_xlen == 32 #define VDSO_32BIT 1 #endif -#else /* nds32 */ -#define VDSO_VERSION 4 -#define VDSO_NAMES 1 -#define VDSO_32BIT 1 #endif static const char *versions[6] = { diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c index 3d603f1394af..883ca85424bc 100644 --- a/tools/testing/selftests/vDSO/vdso_test_abi.c +++ b/tools/testing/selftests/vDSO/vdso_test_abi.c @@ -33,110 +33,114 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts); typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts); typedef time_t (*vdso_time_t)(time_t *t); -static int vdso_test_gettimeofday(void) +#define VDSO_TEST_PASS_MSG() "\n%s(): PASS\n", __func__ +#define VDSO_TEST_FAIL_MSG(x) "\n%s(): %s FAIL\n", __func__, x +#define VDSO_TEST_SKIP_MSG(x) "\n%s(): SKIP: Could not find %s\n", __func__, x + +static void vdso_test_gettimeofday(void) { /* Find gettimeofday. */ vdso_gettimeofday_t vdso_gettimeofday = (vdso_gettimeofday_t)vdso_sym(version, name[0]); if (!vdso_gettimeofday) { - printf("Could not find %s\n", name[0]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0])); + return; } struct timeval tv; long ret = vdso_gettimeofday(&tv, 0); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[0]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0])); } - - return KSFT_PASS; } -static int vdso_test_clock_gettime(clockid_t clk_id) +static void vdso_test_clock_gettime(clockid_t clk_id) { /* Find clock_gettime. */ vdso_clock_gettime_t vdso_clock_gettime = (vdso_clock_gettime_t)vdso_sym(version, name[1]); if (!vdso_clock_gettime) { - printf("Could not find %s\n", name[1]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1])); + return; } struct timespec ts; long ret = vdso_clock_gettime(clk_id, &ts); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[1]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1])); } - - return KSFT_PASS; } -static int vdso_test_time(void) +static void vdso_test_time(void) { /* Find time. */ vdso_time_t vdso_time = (vdso_time_t)vdso_sym(version, name[2]); if (!vdso_time) { - printf("Could not find %s\n", name[2]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2])); + return; } long ret = vdso_time(NULL); if (ret > 0) { - printf("The time in hours since January 1, 1970 is %lld\n", + ksft_print_msg("The time in hours since January 1, 1970 is %lld\n", (long long)(ret / 3600)); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[2]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2])); } - - return KSFT_PASS; } -static int vdso_test_clock_getres(clockid_t clk_id) +static void vdso_test_clock_getres(clockid_t clk_id) { + int clock_getres_fail = 0; + /* Find clock_getres. */ vdso_clock_getres_t vdso_clock_getres = (vdso_clock_getres_t)vdso_sym(version, name[3]); if (!vdso_clock_getres) { - printf("Could not find %s\n", name[3]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3])); + return; } struct timespec ts, sys_ts; long ret = vdso_clock_getres(clk_id, &ts); if (ret == 0) { - printf("The resolution is %lld %lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The vdso resolution is %lld %lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); } else { - printf("%s failed\n", name[3]); - return KSFT_FAIL; + clock_getres_fail++; } ret = syscall(SYS_clock_getres, clk_id, &sys_ts); - if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) { - printf("%s failed\n", name[3]); - return KSFT_FAIL; - } + ksft_print_msg("The syscall resolution is %lld %lld\n", + (long long)sys_ts.tv_sec, (long long)sys_ts.tv_nsec); - return KSFT_PASS; + if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) + clock_getres_fail++; + + if (clock_getres_fail > 0) { + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3])); + } else { + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); + } } const char *vdso_clock_name[12] = { @@ -158,36 +162,23 @@ const char *vdso_clock_name[12] = { * This function calls vdso_test_clock_gettime and vdso_test_clock_getres * with different values for clock_id. */ -static inline int vdso_test_clock(clockid_t clock_id) +static inline void vdso_test_clock(clockid_t clock_id) { - int ret0, ret1; - - ret0 = vdso_test_clock_gettime(clock_id); - /* A skipped test is considered passed */ - if (ret0 == KSFT_SKIP) - ret0 = KSFT_PASS; - - ret1 = vdso_test_clock_getres(clock_id); - /* A skipped test is considered passed */ - if (ret1 == KSFT_SKIP) - ret1 = KSFT_PASS; + ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]); - ret0 += ret1; + vdso_test_clock_gettime(clock_id); - printf("clock_id: %s", vdso_clock_name[clock_id]); - - if (ret0 > 0) - printf(" [FAIL]\n"); - else - printf(" [PASS]\n"); - - return ret0; + vdso_test_clock_getres(clock_id); } +#define VDSO_TEST_PLAN 16 + int main(int argc, char **argv) { unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); - int ret; + + ksft_print_header(); + ksft_set_plan(VDSO_TEST_PLAN); if (!sysinfo_ehdr) { printf("AT_SYSINFO_EHDR is not present!\n"); @@ -201,44 +192,42 @@ int main(int argc, char **argv) vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); - ret = vdso_test_gettimeofday(); + vdso_test_gettimeofday(); #if _POSIX_TIMERS > 0 #ifdef CLOCK_REALTIME - ret += vdso_test_clock(CLOCK_REALTIME); + vdso_test_clock(CLOCK_REALTIME); #endif #ifdef CLOCK_BOOTTIME - ret += vdso_test_clock(CLOCK_BOOTTIME); + vdso_test_clock(CLOCK_BOOTTIME); #endif #ifdef CLOCK_TAI - ret += vdso_test_clock(CLOCK_TAI); + vdso_test_clock(CLOCK_TAI); #endif #ifdef CLOCK_REALTIME_COARSE - ret += vdso_test_clock(CLOCK_REALTIME_COARSE); + vdso_test_clock(CLOCK_REALTIME_COARSE); #endif #ifdef CLOCK_MONOTONIC - ret += vdso_test_clock(CLOCK_MONOTONIC); + vdso_test_clock(CLOCK_MONOTONIC); #endif #ifdef CLOCK_MONOTONIC_RAW - ret += vdso_test_clock(CLOCK_MONOTONIC_RAW); + vdso_test_clock(CLOCK_MONOTONIC_RAW); #endif #ifdef CLOCK_MONOTONIC_COARSE - ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE); + vdso_test_clock(CLOCK_MONOTONIC_COARSE); #endif #endif - ret += vdso_test_time(); - - if (ret > 0) - return KSFT_FAIL; + vdso_test_time(); - return KSFT_PASS; + ksft_print_cnts(); + return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL; } diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 2e7e86e85282..3b5faec3c04f 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -2,6 +2,7 @@ hugepage-mmap hugepage-mremap hugepage-shm +hugepage-vmemmap khugepaged map_hugetlb map_populate diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 1607322a112c..fbf390b51c2f 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for vm selftests +LOCAL_HDRS += $(selfdir)/vm/local_config.h $(top_srcdir)/mm/gup_test.h + include local_config.mk uname_M := $(shell uname -m 2>/dev/null || echo not) @@ -23,7 +25,7 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) +CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_FILES = compaction_test TEST_GEN_FILES += gup_test @@ -31,6 +33,7 @@ TEST_GEN_FILES += hmm-tests TEST_GEN_FILES += hugepage-mmap TEST_GEN_FILES += hugepage-mremap TEST_GEN_FILES += hugepage-shm +TEST_GEN_FILES += hugepage-vmemmap TEST_GEN_FILES += khugepaged TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace @@ -49,9 +52,9 @@ TEST_GEN_FILES += split_huge_page_test TEST_GEN_FILES += ksm_tests ifeq ($(MACHINE),x86_64) -CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) -CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c) -CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie) +CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) +CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) TARGETS := protection_keys BINARIES_32 := $(TARGETS:%=%_32) @@ -140,10 +143,6 @@ endif $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap -$(OUTPUT)/gup_test: ../../../../mm/gup_test.h - -$(OUTPUT)/hmm-tests: local_config.h - # HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. $(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS) diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 2a7c33631a29..1d689084a54b 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -3,9 +3,10 @@ * hugepage-mremap: * * Example of remapping huge page memory in a user application using the - * mremap system call. Code assumes a hugetlbfs filesystem is mounted - * at './huge'. The amount of memory used by this test is decided by a command - * line argument in MBs. If missing, the default amount is 10MB. + * mremap system call. The path to a file in a hugetlbfs filesystem must + * be passed as the last argument to this test. The amount of memory used + * by this test in MBs can optionally be passed as an argument. If no memory + * amount is passed, the default amount is 10MB. * * To make sure the test triggers pmd sharing and goes through the 'unshare' * path in the mremap code use 1GB (1024) or more. @@ -25,7 +26,6 @@ #define DEFAULT_LENGTH_MB 10UL #define MB_TO_BYTES(x) (x * 1024 * 1024) -#define FILE_NAME "huge/hugepagefile" #define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC) #define FLAGS (MAP_SHARED | MAP_ANONYMOUS) @@ -107,17 +107,26 @@ static void register_region_with_uffd(char *addr, size_t len) int main(int argc, char *argv[]) { + size_t length; + + if (argc != 2 && argc != 3) { + printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]); + exit(1); + } + /* Read memory length as the first arg if valid, otherwise fallback to - * the default length. Any additional args are ignored. + * the default length. */ - size_t length = argc > 1 ? (size_t)atoi(argv[1]) : 0UL; + if (argc == 3) + length = argc > 2 ? (size_t)atoi(argv[1]) : 0UL; length = length > 0 ? length : DEFAULT_LENGTH_MB; length = MB_TO_BYTES(length); int ret = 0; - int fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755); + /* last arg is the hugetlb file name */ + int fd = open(argv[argc-1], O_CREAT | O_RDWR, 0755); if (fd < 0) { perror("Open failed"); @@ -169,5 +178,8 @@ int main(int argc, char *argv[]) munmap(addr, length); + close(fd); + unlink(argv[argc-1]); + return ret; } diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/vm/hugepage-vmemmap.c new file mode 100644 index 000000000000..557bdbd4f87e --- /dev/null +++ b/tools/testing/selftests/vm/hugepage-vmemmap.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test case of using hugepage memory in a user application using the + * mmap system call with MAP_HUGETLB flag. Before running this program + * make sure the administrator has allocated enough default sized huge + * pages to cover the 2 MB allocation. + */ +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/mman.h> +#include <fcntl.h> + +#define MAP_LENGTH (2UL * 1024 * 1024) + +#ifndef MAP_HUGETLB +#define MAP_HUGETLB 0x40000 /* arch specific */ +#endif + +#define PAGE_SIZE 4096 + +#define PAGE_COMPOUND_HEAD (1UL << 15) +#define PAGE_COMPOUND_TAIL (1UL << 16) +#define PAGE_HUGE (1UL << 17) + +#define HEAD_PAGE_FLAGS (PAGE_COMPOUND_HEAD | PAGE_HUGE) +#define TAIL_PAGE_FLAGS (PAGE_COMPOUND_TAIL | PAGE_HUGE) + +#define PM_PFRAME_BITS 55 +#define PM_PFRAME_MASK ~((1UL << PM_PFRAME_BITS) - 1) + +/* + * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages. + * That means the addresses starting with 0x800000... will need to be + * specified. Specifying a fixed address is not required on ppc64, i386 + * or x86_64. + */ +#ifdef __ia64__ +#define MAP_ADDR (void *)(0x8000000000000000UL) +#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED) +#else +#define MAP_ADDR NULL +#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB) +#endif + +static void write_bytes(char *addr, size_t length) +{ + unsigned long i; + + for (i = 0; i < length; i++) + *(addr + i) = (char)i; +} + +static unsigned long virt_to_pfn(void *addr) +{ + int fd; + unsigned long pagemap; + + fd = open("/proc/self/pagemap", O_RDONLY); + if (fd < 0) + return -1UL; + + lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET); + read(fd, &pagemap, sizeof(pagemap)); + close(fd); + + return pagemap & ~PM_PFRAME_MASK; +} + +static int check_page_flags(unsigned long pfn) +{ + int fd, i; + unsigned long pageflags; + + fd = open("/proc/kpageflags", O_RDONLY); + if (fd < 0) + return -1; + + lseek(fd, pfn * sizeof(pageflags), SEEK_SET); + + read(fd, &pageflags, sizeof(pageflags)); + if ((pageflags & HEAD_PAGE_FLAGS) != HEAD_PAGE_FLAGS) { + close(fd); + printf("Head page flags (%lx) is invalid\n", pageflags); + return -1; + } + + /* + * pages other than the first page must be tail and shouldn't be head; + * this also verifies kernel has correctly set the fake page_head to tail + * while hugetlb_free_vmemmap is enabled. + */ + for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) { + read(fd, &pageflags, sizeof(pageflags)); + if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS || + (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) { + close(fd); + printf("Tail page flags (%lx) is invalid\n", pageflags); + return -1; + } + } + + close(fd); + + return 0; +} + +int main(int argc, char **argv) +{ + void *addr; + unsigned long pfn; + + addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* Trigger allocation of HugeTLB page. */ + write_bytes(addr, MAP_LENGTH); + + pfn = virt_to_pfn(addr); + if (pfn == -1UL) { + munmap(addr, MAP_LENGTH); + perror("virt_to_pfn"); + exit(1); + } + + printf("Returned address is %p whose pfn is %lx\n", addr, pfn); + + if (check_page_flags(pfn) < 0) { + munmap(addr, MAP_LENGTH); + perror("check_page_flags"); + exit(1); + } + + /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ + if (munmap(addr, MAP_LENGTH)) { + perror("munmap"); + exit(1); + } + + return 0; +} diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c index d91bde511268..eed44322d1a6 100644 --- a/tools/testing/selftests/vm/map_fixed_noreplace.c +++ b/tools/testing/selftests/vm/map_fixed_noreplace.c @@ -17,9 +17,6 @@ #define MAP_FIXED_NOREPLACE 0x100000 #endif -#define BASE_ADDRESS (256ul * 1024 * 1024) - - static void dump_maps(void) { char cmd[32]; @@ -28,18 +25,46 @@ static void dump_maps(void) system(cmd); } +static unsigned long find_base_addr(unsigned long size) +{ + void *addr; + unsigned long flags; + + flags = MAP_PRIVATE | MAP_ANONYMOUS; + addr = mmap(NULL, size, PROT_NONE, flags, -1, 0); + if (addr == MAP_FAILED) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + + if (munmap(addr, size) != 0) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + return (unsigned long)addr; +} + int main(void) { + unsigned long base_addr; unsigned long flags, addr, size, page_size; char *p; page_size = sysconf(_SC_PAGE_SIZE); + //let's find a base addr that is free before we start the tests + size = 5 * page_size; + base_addr = find_base_addr(size); + if (!base_addr) { + printf("Error: couldn't map the space we need for the test\n"); + return 1; + } + flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE; // Check we can map all the areas we need below errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); @@ -60,7 +85,7 @@ int main(void) printf("unmap() successful\n"); errno = 0; - addr = BASE_ADDRESS + page_size; + addr = base_addr + page_size; size = 3 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -80,7 +105,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -101,7 +126,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS + (2 * page_size); + addr = base_addr + (2 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -121,7 +146,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (3 * page_size); + addr = base_addr + (3 * page_size); size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -141,7 +166,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -161,7 +186,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -181,7 +206,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (4 * page_size); + addr = base_addr + (4 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -192,7 +217,7 @@ int main(void) return 1; } - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; if (munmap((void *)addr, size) != 0) { dump_maps(); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 75d401741394..e10d50e0b8e8 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -111,7 +111,19 @@ fi echo "-----------------------" echo "running hugepage-mremap" echo "-----------------------" -./hugepage-mremap 256 +./hugepage-mremap $mnt/huge_mremap +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi +rm -f $mnt/huge_mremap + +echo "------------------------" +echo "running hugepage-vmemmap" +echo "------------------------" +./hugepage-vmemmap if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c index 5e4c036f6ad3..a03cb3fce1f6 100644 --- a/tools/testing/selftests/vm/transhuge-stress.c +++ b/tools/testing/selftests/vm/transhuge-stress.c @@ -26,15 +26,17 @@ #define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) int pagemap_fd; +int backing_fd = -1; +int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; +#define PROT_RW (PROT_READ | PROT_WRITE) int64_t allocate_transhuge(void *ptr) { uint64_t ent[2]; /* drop pmd */ - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_ANONYMOUS | - MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + if (mmap(ptr, HPAGE_SIZE, PROT_RW, MAP_FIXED | mmap_flags, + backing_fd, 0) != ptr) errx(2, "mmap transhuge"); if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) @@ -60,6 +62,8 @@ int main(int argc, char **argv) size_t ram, len; void *ptr, *p; struct timespec a, b; + int i = 0; + char *name = NULL; double s; uint8_t *map; size_t map_len; @@ -69,13 +73,23 @@ int main(int argc, char **argv) ram = SIZE_MAX / 4; else ram *= sysconf(_SC_PAGESIZE); + len = ram; + + while (++i < argc) { + if (!strcmp(argv[i], "-h")) + errx(1, "usage: %s [size in MiB]", argv[0]); + else if (!strcmp(argv[i], "-f")) + name = argv[++i]; + else + len = atoll(argv[i]) << 20; + } - if (argc == 1) - len = ram; - else if (!strcmp(argv[1], "-h")) - errx(1, "usage: %s [size in MiB]", argv[0]); - else - len = atoll(argv[1]) << 20; + if (name) { + backing_fd = open(name, O_RDWR); + if (backing_fd == -1) + errx(2, "open %s", name); + mmap_flags = MAP_SHARED; + } warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, @@ -86,8 +100,7 @@ int main(int argc, char **argv) err(2, "open pagemap"); len -= len % HPAGE_SIZE; - ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0); if (ptr == MAP_FAILED) err(2, "initial mmap"); ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index d3fd24f9fae8..39403b8931de 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -46,6 +46,7 @@ #include <signal.h> #include <poll.h> #include <string.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/syscall.h> #include <sys/ioctl.h> @@ -119,6 +120,9 @@ struct uffd_stats { ~(unsigned long)(sizeof(unsigned long long) \ - 1))) +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + const char *examples = "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" "./userfaultfd anon 100 99999\n\n" @@ -539,7 +543,7 @@ static void continue_range(int ufd, __u64 start, __u64 len) static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; - unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */ + unsigned long page_nr; unsigned long long count; if (!(bounces & BOUNCE_RANDOM)) { @@ -1417,6 +1421,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) static int userfaultfd_stress(void) { void *area; + char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; @@ -1527,9 +1532,13 @@ static int userfaultfd_stress(void) count_verify[nr], nr); /* prepare next bounce */ - swap(area_src, area_dst); + tmp_area = area_src; + area_src = area_dst; + area_dst = tmp_area; - swap(area_src_alias, area_dst_alias); + tmp_area = area_src_alias; + area_src_alias = area_dst_alias; + area_dst_alias = tmp_area; uffd_stats_report(uffd_stats, nr_cpus); } diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 8a1f62ab3c8e..53df7d3893d3 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -6,9 +6,9 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean UNAME_M := $(shell uname -m) -CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) -CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) -CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) +CAN_BUILD_I386 := $(shell ./check_cc.sh "$(CC)" trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./check_cc.sh "$(CC)" trivial_64bit_program.c) +CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh "$(CC)" trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ diff --git a/tools/testing/selftests/x86/check_cc.sh b/tools/testing/selftests/x86/check_cc.sh index 3e2089c8cf54..8c669c0d662e 100755 --- a/tools/testing/selftests/x86/check_cc.sh +++ b/tools/testing/selftests/x86/check_cc.sh @@ -7,7 +7,7 @@ CC="$1" TESTPROG="$2" shift 2 -if "$CC" -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then +if [ -n "$CC" ] && $CC -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then echo 1 else echo 0 diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh index 232e958ec454..b0b91d9b0dc2 100755 --- a/tools/testing/selftests/zram/zram.sh +++ b/tools/testing/selftests/zram/zram.sh @@ -2,9 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 TCID="zram.sh" -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - . ./zram_lib.sh run_zram () { @@ -18,14 +15,4 @@ echo "" check_prereqs -# check zram module exists -MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko -if [ -f $MODULE_PATH ]; then - run_zram -elif [ -b /dev/zram0 ]; then - run_zram -else - echo "$TCID : No zram.ko module or /dev/zram0 device file not found" - echo "$TCID : CONFIG_ZRAM is not set" - exit $ksft_skip -fi +run_zram diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh index 114863d9fb87..8f4affe34f3e 100755 --- a/tools/testing/selftests/zram/zram01.sh +++ b/tools/testing/selftests/zram/zram01.sh @@ -33,9 +33,7 @@ zram_algs="lzo" zram_fill_fs() { - local mem_free0=$(free -m | awk 'NR==2 {print $4}') - - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "fill zram$i..." local b=0 while [ true ]; do @@ -45,29 +43,17 @@ zram_fill_fs() b=$(($b + 1)) done echo "zram$i can be filled with '$b' KB" - done - local mem_free1=$(free -m | awk 'NR==2 {print $4}') - local used_mem=$(($mem_free0 - $mem_free1)) + local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"` + local v=$((100 * 1024 * $b / $mem_used_total)) + if [ "$v" -lt 100 ]; then + echo "FAIL compression ratio: 0.$v:1" + ERR_CODE=-1 + return + fi - local total_size=0 - for sm in $zram_sizes; do - local s=$(echo $sm | sed 's/M//') - total_size=$(($total_size + $s)) + echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" done - - echo "zram used ${used_mem}M, zram disk sizes ${total_size}M" - - local v=$((100 * $total_size / $used_mem)) - - if [ "$v" -lt 100 ]; then - echo "FAIL compression ratio: 0.$v:1" - ERR_CODE=-1 - zram_cleanup - return - fi - - echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" } check_prereqs @@ -81,7 +67,6 @@ zram_mount zram_fill_fs zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh index e83b404807c0..2418b0c4ed13 100755 --- a/tools/testing/selftests/zram/zram02.sh +++ b/tools/testing/selftests/zram/zram02.sh @@ -36,7 +36,6 @@ zram_set_memlimit zram_makeswap zram_swapoff zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index 6f872f266fd1..21ec1966de76 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -5,12 +5,17 @@ # Author: Alexey Kodanev <alexey.kodanev@oracle.com> # Modified: Naresh Kamboju <naresh.kamboju@linaro.org> -MODULE=0 dev_makeswap=-1 dev_mounted=-1 - +dev_start=0 +dev_end=-1 +module_load=-1 +sys_control=-1 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +kernel_version=`uname -r | cut -d'.' -f1,2` +kernel_major=${kernel_version%.*} +kernel_minor=${kernel_version#*.} trap INT @@ -25,68 +30,104 @@ check_prereqs() fi } +kernel_gte() +{ + major=${1%.*} + minor=${1#*.} + + if [ $kernel_major -gt $major ]; then + return 0 + elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then + return 0 + fi + + return 1 +} + zram_cleanup() { echo "zram cleanup" local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_makeswap); do swapoff /dev/zram$i done - for i in $(seq 0 $dev_mounted); do + for i in $(seq $dev_start $dev_mounted); do umount /dev/zram$i done - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo 1 > /sys/block/zram${i}/reset rm -rf zram$i done -} + if [ $sys_control -eq 1 ]; then + for i in $(seq $dev_start $dev_end); do + echo $i > /sys/class/zram-control/hot_remove + done + fi -zram_unload() -{ - if [ $MODULE -ne 0 ] ; then - echo "zram rmmod zram" + if [ $module_load -eq 1 ]; then rmmod zram > /dev/null 2>&1 fi } zram_load() { - # check zram module exists - MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko - if [ -f $MODULE_PATH ]; then - MODULE=1 - echo "create '$dev_num' zram device(s)" - modprobe zram num_devices=$dev_num - if [ $? -ne 0 ]; then - echo "failed to insert zram module" - exit 1 - fi - - dev_num_created=$(ls /dev/zram* | wc -w) + echo "create '$dev_num' zram device(s)" + + # zram module loaded, new kernel + if [ -d "/sys/class/zram-control" ]; then + echo "zram modules already loaded, kernel supports" \ + "zram-control interface" + dev_start=$(ls /dev/zram* | wc -w) + dev_end=$(($dev_start + $dev_num - 1)) + sys_control=1 + + for i in $(seq $dev_start $dev_end); do + cat /sys/class/zram-control/hot_add > /dev/null + done + + echo "all zram devices (/dev/zram$dev_start~$dev_end" \ + "successfully created" + return 0 + fi - if [ "$dev_num_created" -ne "$dev_num" ]; then - echo "unexpected num of devices: $dev_num_created" - ERR_CODE=-1 + # detect old kernel or built-in + modprobe zram num_devices=$dev_num + if [ ! -d "/sys/class/zram-control" ]; then + if grep -q '^zram' /proc/modules; then + rmmod zram > /dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "zram module is being used on old kernel" \ + "without zram-control interface" + exit $ksft_skip + fi else - echo "zram load module successful" + echo "test needs CONFIG_ZRAM=m on old kernel without" \ + "zram-control interface" + exit $ksft_skip fi - elif [ -b /dev/zram0 ]; then - echo "/dev/zram0 device file found: OK" - else - echo "ERROR: No zram.ko module or no /dev/zram0 device found" - echo "$TCID : CONFIG_ZRAM is not set" - exit 1 + modprobe zram num_devices=$dev_num fi + + module_load=1 + dev_end=$(($dev_num - 1)) + echo "all zram devices (/dev/zram0~$dev_end) successfully created" } zram_max_streams() { echo "set max_comp_streams to zram device(s)" - local i=0 + kernel_gte 4.7 + if [ $? -eq 0 ]; then + echo "The device attribute max_comp_streams was"\ + "deprecated in 4.7" + return 0 + fi + + local i=$dev_start for max_s in $zram_max_streams; do local sys_path="/sys/block/zram${i}/max_comp_streams" echo $max_s > $sys_path || \ @@ -98,7 +139,7 @@ zram_max_streams() echo "FAIL can't set max_streams '$max_s', get $max_stream" i=$(($i + 1)) - echo "$sys_path = '$max_streams' ($i/$dev_num)" + echo "$sys_path = '$max_streams'" done echo "zram max streams: OK" @@ -108,15 +149,16 @@ zram_compress_alg() { echo "test that we can set compression algorithm" - local algs=$(cat /sys/block/zram0/comp_algorithm) + local i=$dev_start + local algs=$(cat /sys/block/zram${i}/comp_algorithm) echo "supported algs: $algs" - local i=0 + for alg in $zram_algs; do local sys_path="/sys/block/zram${i}/comp_algorithm" echo "$alg" > $sys_path || \ echo "FAIL can't set '$alg' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$alg' ($i/$dev_num)" + echo "$sys_path = '$alg'" done echo "zram set compression algorithm: OK" @@ -125,14 +167,14 @@ zram_compress_alg() zram_set_disksizes() { echo "set disk size to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_sizes; do local sys_path="/sys/block/zram${i}/disksize" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set disksizes: OK" @@ -142,14 +184,14 @@ zram_set_memlimit() { echo "set memory limit to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_mem_limits; do local sys_path="/sys/block/zram${i}/mem_limit" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set memory limit: OK" @@ -158,8 +200,8 @@ zram_set_memlimit() zram_makeswap() { echo "make swap with zram device(s)" - local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + local i=$dev_start + for i in $(seq $dev_start $dev_end); do mkswap /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -182,7 +224,7 @@ zram_makeswap() zram_swapoff() { local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_end); do swapoff /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -196,7 +238,7 @@ zram_swapoff() zram_makefs() { - local i=0 + local i=$dev_start for fs in $zram_filesystems; do # if requested fs not supported default it to ext2 which mkfs.$fs > /dev/null 2>&1 || fs=ext2 @@ -215,7 +257,7 @@ zram_makefs() zram_mount() { local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "mount /dev/zram$i" mkdir zram$i mount /dev/zram$i zram$i > /dev/null || \ diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 7c39728d08de..5a1eda617992 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -1,5 +1,6 @@ NAME := rtla -VERSION := 0.5 +# Follow the kernel version +VERSION := $(shell cat VERSION 2> /dev/null || make -sC ../../.. kernelversion) # From libtracefs: # Makefiles suck: This macro sets a default value of $(2) for the @@ -85,6 +86,7 @@ clean: doc_clean tarball: clean rm -rf $(NAME)-$(VERSION) && mkdir $(NAME)-$(VERSION) + echo $(VERSION) > $(NAME)-$(VERSION)/VERSION cp -r $(DIRS) $(FILES) $(NAME)-$(VERSION) mkdir $(NAME)-$(VERSION)/Documentation/ cp -rp $(SRCTREE)/../../../Documentation/tools/rtla/* $(NAME)-$(VERSION)/Documentation/ diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c index 7b73d1eccd0e..b8ec6c15bccb 100644 --- a/tools/tracing/rtla/src/osnoise.c +++ b/tools/tracing/rtla/src/osnoise.c @@ -656,6 +656,85 @@ void osnoise_put_print_stack(struct osnoise_context *context) } /* + * osnoise_get_tracing_thresh - read and save the original "tracing_thresh" + */ +static long long +osnoise_get_tracing_thresh(struct osnoise_context *context) +{ + long long tracing_thresh; + + if (context->tracing_thresh != OSNOISE_OPTION_INIT_VAL) + return context->tracing_thresh; + + if (context->orig_tracing_thresh != OSNOISE_OPTION_INIT_VAL) + return context->orig_tracing_thresh; + + tracing_thresh = osnoise_read_ll_config("tracing_thresh"); + if (tracing_thresh < 0) + goto out_err; + + context->orig_tracing_thresh = tracing_thresh; + return tracing_thresh; + +out_err: + return OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_set_tracing_thresh - set "tracing_thresh" + */ +int osnoise_set_tracing_thresh(struct osnoise_context *context, long long tracing_thresh) +{ + long long curr_tracing_thresh = osnoise_get_tracing_thresh(context); + int retval; + + if (curr_tracing_thresh == OSNOISE_OPTION_INIT_VAL) + return -1; + + retval = osnoise_write_ll_config("tracing_thresh", tracing_thresh); + if (retval < 0) + return -1; + + context->tracing_thresh = tracing_thresh; + + return 0; +} + +/* + * osnoise_restore_tracing_thresh - restore the original "tracing_thresh" + */ +void osnoise_restore_tracing_thresh(struct osnoise_context *context) +{ + int retval; + + if (context->orig_tracing_thresh == OSNOISE_OPTION_INIT_VAL) + return; + + if (context->orig_tracing_thresh == context->tracing_thresh) + goto out_done; + + retval = osnoise_write_ll_config("tracing_thresh", context->orig_tracing_thresh); + if (retval < 0) + err_msg("Could not restore original tracing_thresh\n"); + +out_done: + context->tracing_thresh = OSNOISE_OPTION_INIT_VAL; +} + +/* + * osnoise_put_tracing_thresh - restore original values and cleanup data + */ +void osnoise_put_tracing_thresh(struct osnoise_context *context) +{ + osnoise_restore_tracing_thresh(context); + + if (context->orig_tracing_thresh == OSNOISE_OPTION_INIT_VAL) + return; + + context->orig_tracing_thresh = OSNOISE_OPTION_INIT_VAL; +} + +/* * enable_osnoise - enable osnoise tracer in the trace_instance */ int enable_osnoise(struct trace_instance *trace) @@ -716,6 +795,9 @@ struct osnoise_context *osnoise_context_alloc(void) context->orig_print_stack = OSNOISE_OPTION_INIT_VAL; context->print_stack = OSNOISE_OPTION_INIT_VAL; + context->orig_tracing_thresh = OSNOISE_OPTION_INIT_VAL; + context->tracing_thresh = OSNOISE_OPTION_INIT_VAL; + osnoise_get_context(context); return context; @@ -741,6 +823,7 @@ void osnoise_put_context(struct osnoise_context *context) osnoise_put_stop_total_us(context); osnoise_put_timerlat_period_us(context); osnoise_put_print_stack(context); + osnoise_put_tracing_thresh(context); free(context); } @@ -750,6 +833,9 @@ void osnoise_put_context(struct osnoise_context *context) */ void osnoise_destroy_tool(struct osnoise_tool *top) { + if (!top) + return; + trace_instance_destroy(&top->trace); if (top->context) @@ -807,7 +893,7 @@ struct osnoise_tool *osnoise_init_trace_tool(char *tracer) retval = enable_tracer_by_name(trace->trace.inst, tracer); if (retval) { - err_msg("Could not enable osnoiser tracer for tracing\n"); + err_msg("Could not enable %s tracer for tracing\n", tracer); goto out_err; } diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h index 9e4b2e2a4559..04a4384cc544 100644 --- a/tools/tracing/rtla/src/osnoise.h +++ b/tools/tracing/rtla/src/osnoise.h @@ -23,6 +23,10 @@ struct osnoise_context { long long orig_timerlat_period_us; long long timerlat_period_us; + /* 0 as init value */ + long long orig_tracing_thresh; + long long tracing_thresh; + /* -1 as init value because 0 is disabled */ long long orig_stop_us; long long stop_us; @@ -67,6 +71,10 @@ int osnoise_set_timerlat_period_us(struct osnoise_context *context, long long timerlat_period_us); void osnoise_restore_timerlat_period_us(struct osnoise_context *context); +int osnoise_set_tracing_thresh(struct osnoise_context *context, + long long tracing_thresh); +void osnoise_restore_tracing_thresh(struct osnoise_context *context); + void osnoise_restore_print_stack(struct osnoise_context *context); int osnoise_set_print_stack(struct osnoise_context *context, long long print_stack); diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 180fcbe423cd..b4380d45cacd 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -21,6 +21,7 @@ struct osnoise_hist_params { char *trace_output; unsigned long long runtime; unsigned long long period; + long long threshold; long long stop_us; long long stop_total_us; int sleep_time; @@ -28,6 +29,7 @@ struct osnoise_hist_params { int set_sched; int output_divisor; struct sched_attr sched_param; + struct trace_events *events; char no_header; char no_summary; @@ -425,21 +427,27 @@ static void osnoise_hist_usage(char *usage) static const char * const msg[] = { "", - " usage: rtla osnoise hist [-h] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\", - " [-c cpu-list] [-P priority] [-b N] [-e N] [--no-header] [--no-summary] \\", - " [--no-index] [--with-zeros]", + " usage: rtla osnoise hist [-h] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\", + " [-T us] [-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] \\", + " [-c cpu-list] [-P priority] [-b N] [-E N] [--no-header] [--no-summary] [--no-index] \\", + " [--with-zeros]", "", " -h/--help: print this menu", + " -a/--auto: set automatic trace mode, stopping the session if argument in us sample is hit", " -p/--period us: osnoise period in us", " -r/--runtime us: osnoise runtime in us", " -s/--stop us: stop trace if a single sample is higher than the argument in us", " -S/--stop-total us: stop trace if the total sample is higher than the argument in us", + " -T/--threshold us: the minimum delta to be considered a noise", " -c/--cpus cpu-list: list of cpus to run osnoise threads", " -d/--duration time[s|m|h|d]: duration of the session", " -D/--debug: print debug info", " -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]", + " -e/--event <sys:event>: enable the <sys:event> in the trace instance, multiple -e are allowed", + " --filter <filter>: enable a trace event filter to the previous -e event", + " --trigger <trigger>: enable a trace event trigger to the previous -e event", " -b/--bucket-size N: set the histogram bucket size (default 1)", - " -e/--entries N: set the number of entries of the histogram (default 256)", + " -E/--entries N: set the number of entries of the histogram (default 256)", " --no-header: do not print header", " --no-summary: do not print summary", " --no-index: do not print index", @@ -471,6 +479,7 @@ static struct osnoise_hist_params *osnoise_hist_parse_args(int argc, char *argv[]) { struct osnoise_hist_params *params; + struct trace_events *tevent; int retval; int c; @@ -485,8 +494,9 @@ static struct osnoise_hist_params while (1) { static struct option long_options[] = { + {"auto", required_argument, 0, 'a'}, {"bucket-size", required_argument, 0, 'b'}, - {"entries", required_argument, 0, 'e'}, + {"entries", required_argument, 0, 'E'}, {"cpus", required_argument, 0, 'c'}, {"debug", no_argument, 0, 'D'}, {"duration", required_argument, 0, 'd'}, @@ -497,17 +507,21 @@ static struct osnoise_hist_params {"stop", required_argument, 0, 's'}, {"stop-total", required_argument, 0, 'S'}, {"trace", optional_argument, 0, 't'}, + {"event", required_argument, 0, 'e'}, + {"threshold", required_argument, 0, 'T'}, {"no-header", no_argument, 0, '0'}, {"no-summary", no_argument, 0, '1'}, {"no-index", no_argument, 0, '2'}, {"with-zeros", no_argument, 0, '3'}, + {"trigger", required_argument, 0, '4'}, + {"filter", required_argument, 0, '5'}, {0, 0, 0, 0} }; /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "c:b:d:e:Dhp:P:r:s:S:t::0123", + c = getopt_long(argc, argv, "a:c:b:d:e:E:Dhp:P:r:s:S:t::T:01234:5:", long_options, &option_index); /* detect the end of the options. */ @@ -515,6 +529,17 @@ static struct osnoise_hist_params break; switch (c) { + case 'a': + /* set sample stop to auto_thresh */ + params->stop_us = get_llong_from_str(optarg); + + /* set sample threshold to 1 */ + params->threshold = 1; + + /* set trace */ + params->trace_output = "osnoise_trace.txt"; + + break; case 'b': params->bucket_size = get_llong_from_str(optarg); if ((params->bucket_size == 0) || (params->bucket_size >= 1000000)) @@ -535,6 +560,18 @@ static struct osnoise_hist_params osnoise_hist_usage("Invalid -D duration\n"); break; case 'e': + tevent = trace_event_alloc(optarg); + if (!tevent) { + err_msg("Error alloc trace event"); + exit(EXIT_FAILURE); + } + + if (params->events) + tevent->next = params->events; + + params->events = tevent; + break; + case 'E': params->entries = get_llong_from_str(optarg); if ((params->entries < 10) || (params->entries > 9999999)) osnoise_hist_usage("Entries must be > 10 and < 9999999\n"); @@ -565,6 +602,9 @@ static struct osnoise_hist_params case 'S': params->stop_total_us = get_llong_from_str(optarg); break; + case 'T': + params->threshold = get_llong_from_str(optarg); + break; case 't': if (optarg) /* skip = */ @@ -584,6 +624,28 @@ static struct osnoise_hist_params case '3': /* with zeros */ params->with_zeros = 1; break; + case '4': /* trigger */ + if (params->events) { + retval = trace_event_add_trigger(params->events, optarg); + if (retval) { + err_msg("Error adding trigger %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + osnoise_hist_usage("--trigger requires a previous -e\n"); + } + break; + case '5': /* filter */ + if (params->events) { + retval = trace_event_add_filter(params->events, optarg); + if (retval) { + err_msg("Error adding filter %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + osnoise_hist_usage("--filter requires a previous -e\n"); + } + break; default: osnoise_hist_usage("Invalid option"); } @@ -645,6 +707,14 @@ osnoise_hist_apply_config(struct osnoise_tool *tool, struct osnoise_hist_params } } + if (params->threshold) { + retval = osnoise_set_tracing_thresh(tool->context, params->threshold); + if (retval) { + err_msg("Failed to set tracing_thresh\n"); + goto out_err; + } + } + return 0; out_err: @@ -701,9 +771,9 @@ osnoise_hist_set_signals(struct osnoise_hist_params *params) int osnoise_hist_main(int argc, char *argv[]) { struct osnoise_hist_params *params; + struct osnoise_tool *record = NULL; + struct osnoise_tool *tool = NULL; struct trace_instance *trace; - struct osnoise_tool *record; - struct osnoise_tool *tool; int return_value = 1; int retval; @@ -751,6 +821,13 @@ int osnoise_hist_main(int argc, char *argv[]) err_msg("Failed to enable the trace instance\n"); goto out_hist; } + + if (params->events) { + retval = trace_events_enable(&record->trace, params->events); + if (retval) + goto out_hist; + } + trace_instance_start(&record->trace); } @@ -771,9 +848,9 @@ int osnoise_hist_main(int argc, char *argv[]) goto out_hist; } - if (!tracefs_trace_is_on(trace->inst)) + if (trace_is_off(&tool->trace, &record->trace)) break; - }; + } osnoise_read_trace_hist(tool); @@ -781,8 +858,8 @@ int osnoise_hist_main(int argc, char *argv[]) return_value = 0; - if (!tracefs_trace_is_on(trace->inst)) { - printf("rtla timelat hit stop tracing\n"); + if (trace_is_off(&tool->trace, &record->trace)) { + printf("rtla osnoise hit stop tracing\n"); if (params->trace_output) { printf(" Saving trace to %s\n", params->trace_output); save_trace_to_file(record->trace.inst, params->trace_output); @@ -790,11 +867,12 @@ int osnoise_hist_main(int argc, char *argv[]) } out_hist: + trace_events_destroy(&record->trace, params->events); + params->events = NULL; osnoise_free_histogram(tool->data); out_destroy: + osnoise_destroy_tool(record); osnoise_destroy_tool(tool); - if (params->trace_output) - osnoise_destroy_tool(record); free(params); out_exit: exit(return_value); diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 332b2ac205fc..72c2fd6ce005 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -23,6 +23,7 @@ struct osnoise_top_params { char *trace_output; unsigned long long runtime; unsigned long long period; + long long threshold; long long stop_us; long long stop_total_us; int sleep_time; @@ -30,6 +31,7 @@ struct osnoise_top_params { int quiet; int set_sched; struct sched_attr sched_param; + struct trace_events *events; }; struct osnoise_top_cpu { @@ -244,18 +246,24 @@ void osnoise_top_usage(char *usage) int i; static const char * const msg[] = { - " usage: rtla osnoise [top] [-h] [-q] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\", + " usage: rtla osnoise [top] [-h] [-q] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\", + " [-T us] [-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] \\", " [-c cpu-list] [-P priority]", "", " -h/--help: print this menu", + " -a/--auto: set automatic trace mode, stopping the session if argument in us sample is hit", " -p/--period us: osnoise period in us", " -r/--runtime us: osnoise runtime in us", " -s/--stop us: stop trace if a single sample is higher than the argument in us", " -S/--stop-total us: stop trace if the total sample is higher than the argument in us", + " -T/--threshold us: the minimum delta to be considered a noise", " -c/--cpus cpu-list: list of cpus to run osnoise threads", " -d/--duration time[s|m|h|d]: duration of the session", " -D/--debug: print debug info", " -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]", + " -e/--event <sys:event>: enable the <sys:event> in the trace instance, multiple -e are allowed", + " --filter <filter>: enable a trace event filter to the previous -e event", + " --trigger <trigger>: enable a trace event trigger to the previous -e event", " -q/--quiet print only a summary at the end", " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters", " o:prio - use SCHED_OTHER with prio", @@ -283,6 +291,7 @@ void osnoise_top_usage(char *usage) struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) { struct osnoise_top_params *params; + struct trace_events *tevent; int retval; int c; @@ -292,9 +301,11 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) while (1) { static struct option long_options[] = { + {"auto", required_argument, 0, 'a'}, {"cpus", required_argument, 0, 'c'}, {"debug", no_argument, 0, 'D'}, {"duration", required_argument, 0, 'd'}, + {"event", required_argument, 0, 'e'}, {"help", no_argument, 0, 'h'}, {"period", required_argument, 0, 'p'}, {"priority", required_argument, 0, 'P'}, @@ -302,14 +313,17 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) {"runtime", required_argument, 0, 'r'}, {"stop", required_argument, 0, 's'}, {"stop-total", required_argument, 0, 'S'}, + {"threshold", required_argument, 0, 'T'}, {"trace", optional_argument, 0, 't'}, + {"trigger", required_argument, 0, '0'}, + {"filter", required_argument, 0, '1'}, {0, 0, 0, 0} }; /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "c:d:Dhp:P:qr:s:S:t::", + c = getopt_long(argc, argv, "a:c:d:De:hp:P:qr:s:S:t::T:0:1:", long_options, &option_index); /* Detect the end of the options. */ @@ -317,6 +331,17 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) break; switch (c) { + case 'a': + /* set sample stop to auto_thresh */ + params->stop_us = get_llong_from_str(optarg); + + /* set sample threshold to 1 */ + params->threshold = 1; + + /* set trace */ + params->trace_output = "osnoise_trace.txt"; + + break; case 'c': retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); if (retval) @@ -331,6 +356,18 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) if (!params->duration) osnoise_top_usage("Invalid -D duration\n"); break; + case 'e': + tevent = trace_event_alloc(optarg); + if (!tevent) { + err_msg("Error alloc trace event"); + exit(EXIT_FAILURE); + } + + if (params->events) + tevent->next = params->events; + params->events = tevent; + + break; case 'h': case '?': osnoise_top_usage(NULL); @@ -367,6 +404,31 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) else params->trace_output = "osnoise_trace.txt"; break; + case 'T': + params->threshold = get_llong_from_str(optarg); + break; + case '0': /* trigger */ + if (params->events) { + retval = trace_event_add_trigger(params->events, optarg); + if (retval) { + err_msg("Error adding trigger %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + osnoise_top_usage("--trigger requires a previous -e\n"); + } + break; + case '1': /* filter */ + if (params->events) { + retval = trace_event_add_filter(params->events, optarg); + if (retval) { + err_msg("Error adding filter %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + osnoise_top_usage("--filter requires a previous -e\n"); + } + break; default: osnoise_top_usage("Invalid option"); } @@ -425,6 +487,14 @@ osnoise_top_apply_config(struct osnoise_tool *tool, struct osnoise_top_params *p } } + if (params->threshold) { + retval = osnoise_set_tracing_thresh(tool->context, params->threshold); + if (retval) { + err_msg("Failed to set tracing_thresh\n"); + goto out_err; + } + } + return 0; out_err: @@ -483,9 +553,9 @@ static void osnoise_top_set_signals(struct osnoise_top_params *params) int osnoise_top_main(int argc, char **argv) { struct osnoise_top_params *params; + struct osnoise_tool *record = NULL; + struct osnoise_tool *tool = NULL; struct trace_instance *trace; - struct osnoise_tool *record; - struct osnoise_tool *tool; int return_value = 1; int retval; @@ -529,13 +599,20 @@ int osnoise_top_main(int argc, char **argv) err_msg("Failed to enable the trace instance\n"); goto out_top; } + + if (params->events) { + retval = trace_events_enable(&record->trace, params->events); + if (retval) + goto out_top; + } + trace_instance_start(&record->trace); } tool->start_time = time(NULL); osnoise_top_set_signals(params); - do { + while (!stop_tracing) { sleep(params->sleep_time); retval = tracefs_iterate_raw_events(trace->tep, @@ -552,16 +629,16 @@ int osnoise_top_main(int argc, char **argv) if (!params->quiet) osnoise_print_stats(params, tool); - if (!tracefs_trace_is_on(trace->inst)) + if (trace_is_off(&tool->trace, &record->trace)) break; - } while (!stop_tracing); + } osnoise_print_stats(params, tool); return_value = 0; - if (!tracefs_trace_is_on(trace->inst)) { + if (trace_is_off(&tool->trace, &record->trace)) { printf("osnoise hit stop tracing\n"); if (params->trace_output) { printf(" Saving trace to %s\n", params->trace_output); @@ -570,10 +647,12 @@ int osnoise_top_main(int argc, char **argv) } out_top: + trace_events_destroy(&record->trace, params->events); + params->events = NULL; osnoise_free_top(tool->data); + osnoise_destroy_tool(record); osnoise_destroy_tool(tool); - if (params->trace_output) - osnoise_destroy_tool(record); + free(params); out_exit: exit(return_value); } diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 235f9620ef3d..dc908126c610 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -28,7 +28,9 @@ struct timerlat_hist_params { int output_divisor; int duration; int set_sched; + int dma_latency; struct sched_attr sched_param; + struct trace_events *events; char no_irq; char no_thread; @@ -428,11 +430,13 @@ static void timerlat_hist_usage(char *usage) char *msg[] = { "", - " usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\", - " [-c cpu-list] [-P priority] [-e N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\", - " [--no-index] [--with-zeros]", + " usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-a us] [-p us] [-i us] [-T us] [-s us] \\", + " [-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] [-c cpu-list] \\", + " [-P priority] [-E N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\", + " [--no-index] [--with-zeros] [--dma-latency us]", "", " -h/--help: print this menu", + " -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit", " -p/--period us: timerlat period in us", " -i/--irq us: stop trace if the irq latency is higher than the argument in us", " -T/--thread us: stop trace if the thread latency is higher than the argument in us", @@ -440,16 +444,20 @@ static void timerlat_hist_usage(char *usage) " -c/--cpus cpus: run the tracer only on the given cpus", " -d/--duration time[m|h|d]: duration of the session in seconds", " -D/--debug: print debug info", - " -T/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]", + " -t/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]", + " -e/--event <sys:event>: enable the <sys:event> in the trace instance, multiple -e are allowed", + " --filter <filter>: enable a trace event filter to the previous -e event", + " --trigger <trigger>: enable a trace event trigger to the previous -e event", " -n/--nano: display data in nanoseconds", " -b/--bucket-size N: set the histogram bucket size (default 1)", - " -e/--entries N: set the number of entries of the histogram (default 256)", + " -E/--entries N: set the number of entries of the histogram (default 256)", " --no-irq: ignore IRQ latencies", " --no-thread: ignore thread latencies", " --no-header: do not print header", " --no-summary: do not print summary", " --no-index: do not print index", " --with-zeros: print zero only entries", + " --dma-latency us: set /dev/cpu_dma_latency latency <us> to reduce exit from idle latency", " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters", " o:prio - use SCHED_OTHER with prio", " r:prio - use SCHED_RR with prio", @@ -477,6 +485,8 @@ static struct timerlat_hist_params *timerlat_hist_parse_args(int argc, char *argv[]) { struct timerlat_hist_params *params; + struct trace_events *tevent; + int auto_thresh; int retval; int c; @@ -484,6 +494,9 @@ static struct timerlat_hist_params if (!params) exit(1); + /* disabled by default */ + params->dma_latency = -1; + /* display data in microseconds */ params->output_divisor = 1000; params->bucket_size = 1; @@ -491,10 +504,11 @@ static struct timerlat_hist_params while (1) { static struct option long_options[] = { + {"auto", required_argument, 0, 'a'}, {"cpus", required_argument, 0, 'c'}, {"bucket-size", required_argument, 0, 'b'}, {"debug", no_argument, 0, 'D'}, - {"entries", required_argument, 0, 'e'}, + {"entries", required_argument, 0, 'E'}, {"duration", required_argument, 0, 'd'}, {"help", no_argument, 0, 'h'}, {"irq", required_argument, 0, 'i'}, @@ -504,19 +518,23 @@ static struct timerlat_hist_params {"stack", required_argument, 0, 's'}, {"thread", required_argument, 0, 'T'}, {"trace", optional_argument, 0, 't'}, + {"event", required_argument, 0, 'e'}, {"no-irq", no_argument, 0, '0'}, {"no-thread", no_argument, 0, '1'}, {"no-header", no_argument, 0, '2'}, {"no-summary", no_argument, 0, '3'}, {"no-index", no_argument, 0, '4'}, {"with-zeros", no_argument, 0, '5'}, + {"trigger", required_argument, 0, '6'}, + {"filter", required_argument, 0, '7'}, + {"dma-latency", required_argument, 0, '8'}, {0, 0, 0, 0} }; /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "c:b:d:e:Dhi:np:P:s:t::T:012345", + c = getopt_long(argc, argv, "a:c:b:d:e:E:Dhi:np:P:s:t::T:0123456:7:8:", long_options, &option_index); /* detect the end of the options. */ @@ -524,6 +542,19 @@ static struct timerlat_hist_params break; switch (c) { + case 'a': + auto_thresh = get_llong_from_str(optarg); + + /* set thread stop to auto_thresh */ + params->stop_total_us = auto_thresh; + + /* get stack trace */ + params->print_stack = auto_thresh; + + /* set trace */ + params->trace_output = "timerlat_trace.txt"; + + break; case 'c': retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); if (retval) @@ -544,6 +575,18 @@ static struct timerlat_hist_params timerlat_hist_usage("Invalid -D duration\n"); break; case 'e': + tevent = trace_event_alloc(optarg); + if (!tevent) { + err_msg("Error alloc trace event"); + exit(EXIT_FAILURE); + } + + if (params->events) + tevent->next = params->events; + + params->events = tevent; + break; + case 'E': params->entries = get_llong_from_str(optarg); if ((params->entries < 10) || (params->entries > 9999999)) timerlat_hist_usage("Entries must be > 10 and < 9999999\n"); @@ -600,6 +643,35 @@ static struct timerlat_hist_params case '5': /* with zeros */ params->with_zeros = 1; break; + case '6': /* trigger */ + if (params->events) { + retval = trace_event_add_trigger(params->events, optarg); + if (retval) { + err_msg("Error adding trigger %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + timerlat_hist_usage("--trigger requires a previous -e\n"); + } + break; + case '7': /* filter */ + if (params->events) { + retval = trace_event_add_filter(params->events, optarg); + if (retval) { + err_msg("Error adding filter %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + timerlat_hist_usage("--filter requires a previous -e\n"); + } + break; + case '8': + params->dma_latency = get_llong_from_str(optarg); + if (params->dma_latency < 0 || params->dma_latency > 10000) { + err_msg("--dma-latency needs to be >= 0 and < 10000"); + exit(EXIT_FAILURE); + } + break; default: timerlat_hist_usage("Invalid option"); } @@ -729,9 +801,10 @@ timerlat_hist_set_signals(struct timerlat_hist_params *params) int timerlat_hist_main(int argc, char *argv[]) { struct timerlat_hist_params *params; + struct osnoise_tool *record = NULL; + struct osnoise_tool *tool = NULL; struct trace_instance *trace; - struct osnoise_tool *record; - struct osnoise_tool *tool; + int dma_latency_fd = -1; int return_value = 1; int retval; @@ -767,6 +840,14 @@ int timerlat_hist_main(int argc, char *argv[]) } } + if (params->dma_latency >= 0) { + dma_latency_fd = set_cpu_dma_latency(params->dma_latency); + if (dma_latency_fd < 0) { + err_msg("Could not set /dev/cpu_dma_latency.\n"); + goto out_hist; + } + } + trace_instance_start(trace); if (params->trace_output) { @@ -775,6 +856,13 @@ int timerlat_hist_main(int argc, char *argv[]) err_msg("Failed to enable the trace instance\n"); goto out_hist; } + + if (params->events) { + retval = trace_events_enable(&record->trace, params->events); + if (retval) + goto out_hist; + } + trace_instance_start(&record->trace); } @@ -795,15 +883,15 @@ int timerlat_hist_main(int argc, char *argv[]) goto out_hist; } - if (!tracefs_trace_is_on(trace->inst)) + if (trace_is_off(&tool->trace, &record->trace)) break; - }; + } timerlat_print_stats(params, tool); return_value = 0; - if (!tracefs_trace_is_on(trace->inst)) { + if (trace_is_off(&tool->trace, &record->trace)) { printf("rtla timelat hit stop tracing\n"); if (params->trace_output) { printf(" Saving trace to %s\n", params->trace_output); @@ -812,10 +900,13 @@ int timerlat_hist_main(int argc, char *argv[]) } out_hist: + if (dma_latency_fd >= 0) + close(dma_latency_fd); + trace_events_destroy(&record->trace, params->events); + params->events = NULL; timerlat_free_histogram(tool->data); + osnoise_destroy_tool(record); osnoise_destroy_tool(tool); - if (params->trace_output) - osnoise_destroy_tool(record); free(params); out_exit: exit(return_value); diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 1ebd5291539c..1f754c3df53f 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -29,7 +29,9 @@ struct timerlat_top_params { int duration; int quiet; int set_sched; + int dma_latency; struct sched_attr sched_param; + struct trace_events *events; }; struct timerlat_top_cpu { @@ -266,10 +268,12 @@ static void timerlat_top_usage(char *usage) static const char *const msg[] = { "", - " usage: rtla timerlat [top] [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\", - " [-c cpu-list] [-P priority]", + " usage: rtla timerlat [top] [-h] [-q] [-a us] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] \\", + " [[-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] [-c cpu-list] \\", + " [-P priority] [--dma-latency us]", "", " -h/--help: print this menu", + " -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit", " -p/--period us: timerlat period in us", " -i/--irq us: stop trace if the irq latency is higher than the argument in us", " -T/--thread us: stop trace if the thread latency is higher than the argument in us", @@ -278,8 +282,12 @@ static void timerlat_top_usage(char *usage) " -d/--duration time[m|h|d]: duration of the session in seconds", " -D/--debug: print debug info", " -t/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]", + " -e/--event <sys:event>: enable the <sys:event> in the trace instance, multiple -e are allowed", + " --filter <command>: enable a trace event filter to the previous -e event", + " --trigger <command>: enable a trace event trigger to the previous -e event", " -n/--nano: display data in nanoseconds", " -q/--quiet print only a summary at the end", + " --dma-latency us: set /dev/cpu_dma_latency latency <us> to reduce exit from idle latency", " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters", " o:prio - use SCHED_OTHER with prio", " r:prio - use SCHED_RR with prio", @@ -307,6 +315,8 @@ static struct timerlat_top_params *timerlat_top_parse_args(int argc, char **argv) { struct timerlat_top_params *params; + struct trace_events *tevent; + long long auto_thresh; int retval; int c; @@ -314,14 +324,19 @@ static struct timerlat_top_params if (!params) exit(1); + /* disabled by default */ + params->dma_latency = -1; + /* display data in microseconds */ params->output_divisor = 1000; while (1) { static struct option long_options[] = { + {"auto", required_argument, 0, 'a'}, {"cpus", required_argument, 0, 'c'}, {"debug", no_argument, 0, 'D'}, {"duration", required_argument, 0, 'd'}, + {"event", required_argument, 0, 'e'}, {"help", no_argument, 0, 'h'}, {"irq", required_argument, 0, 'i'}, {"nano", no_argument, 0, 'n'}, @@ -331,13 +346,16 @@ static struct timerlat_top_params {"stack", required_argument, 0, 's'}, {"thread", required_argument, 0, 'T'}, {"trace", optional_argument, 0, 't'}, + {"trigger", required_argument, 0, '0'}, + {"filter", required_argument, 0, '1'}, + {"dma-latency", required_argument, 0, '2'}, {0, 0, 0, 0} }; /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "c:d:Dhi:np:P:qs:t::T:", + c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:", long_options, &option_index); /* detect the end of the options. */ @@ -345,6 +363,19 @@ static struct timerlat_top_params break; switch (c) { + case 'a': + auto_thresh = get_llong_from_str(optarg); + + /* set thread stop to auto_thresh */ + params->stop_total_us = auto_thresh; + + /* get stack trace */ + params->print_stack = auto_thresh; + + /* set trace */ + params->trace_output = "timerlat_trace.txt"; + + break; case 'c': retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); if (retval) @@ -359,6 +390,17 @@ static struct timerlat_top_params if (!params->duration) timerlat_top_usage("Invalid -D duration\n"); break; + case 'e': + tevent = trace_event_alloc(optarg); + if (!tevent) { + err_msg("Error alloc trace event"); + exit(EXIT_FAILURE); + } + + if (params->events) + tevent->next = params->events; + params->events = tevent; + break; case 'h': case '?': timerlat_top_usage(NULL); @@ -396,6 +438,35 @@ static struct timerlat_top_params else params->trace_output = "timerlat_trace.txt"; break; + case '0': /* trigger */ + if (params->events) { + retval = trace_event_add_trigger(params->events, optarg); + if (retval) { + err_msg("Error adding trigger %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + timerlat_top_usage("--trigger requires a previous -e\n"); + } + break; + case '1': /* filter */ + if (params->events) { + retval = trace_event_add_filter(params->events, optarg); + if (retval) { + err_msg("Error adding filter %s\n", optarg); + exit(EXIT_FAILURE); + } + } else { + timerlat_top_usage("--filter requires a previous -e\n"); + } + break; + case '2': /* dma-latency */ + params->dma_latency = get_llong_from_str(optarg); + if (params->dma_latency < 0 || params->dma_latency > 10000) { + err_msg("--dma-latency needs to be >= 0 and < 10000"); + exit(EXIT_FAILURE); + } + break; default: timerlat_top_usage("Invalid option"); } @@ -521,9 +592,10 @@ timerlat_top_set_signals(struct timerlat_top_params *params) int timerlat_top_main(int argc, char *argv[]) { struct timerlat_top_params *params; + struct osnoise_tool *record = NULL; + struct osnoise_tool *top = NULL; struct trace_instance *trace; - struct osnoise_tool *record; - struct osnoise_tool *top; + int dma_latency_fd = -1; int return_value = 1; int retval; @@ -559,6 +631,14 @@ int timerlat_top_main(int argc, char *argv[]) } } + if (params->dma_latency >= 0) { + dma_latency_fd = set_cpu_dma_latency(params->dma_latency); + if (dma_latency_fd < 0) { + err_msg("Could not set /dev/cpu_dma_latency.\n"); + goto out_top; + } + } + trace_instance_start(trace); if (params->trace_output) { @@ -567,6 +647,13 @@ int timerlat_top_main(int argc, char *argv[]) err_msg("Failed to enable the trace instance\n"); goto out_top; } + + if (params->events) { + retval = trace_events_enable(&record->trace, params->events); + if (retval) + goto out_top; + } + trace_instance_start(&record->trace); } @@ -590,16 +677,16 @@ int timerlat_top_main(int argc, char *argv[]) if (!params->quiet) timerlat_print_stats(params, top); - if (!tracefs_trace_is_on(trace->inst)) + if (trace_is_off(&top->trace, &record->trace)) break; - }; + } timerlat_print_stats(params, top); return_value = 0; - if (!tracefs_trace_is_on(trace->inst)) { + if (trace_is_off(&top->trace, &record->trace)) { printf("rtla timelat hit stop tracing\n"); if (params->trace_output) { printf(" Saving trace to %s\n", params->trace_output); @@ -608,10 +695,13 @@ int timerlat_top_main(int argc, char *argv[]) } out_top: + if (dma_latency_fd >= 0) + close(dma_latency_fd); + trace_events_destroy(&record->trace, params->events); + params->events = NULL; timerlat_free_top(top->data); + osnoise_destroy_tool(record); osnoise_destroy_tool(top); - if (params->trace_output) - osnoise_destroy_tool(record); free(params); out_exit: exit(return_value); diff --git a/tools/tracing/rtla/src/trace.c b/tools/tracing/rtla/src/trace.c index 107a0c6387f7..5784c9f9e570 100644 --- a/tools/tracing/rtla/src/trace.c +++ b/tools/tracing/rtla/src/trace.c @@ -20,14 +20,14 @@ int enable_tracer_by_name(struct tracefs_instance *inst, const char *tracer_name tracer = TRACEFS_TRACER_CUSTOM; - debug_msg("enabling %s tracer\n", tracer_name); + debug_msg("Enabling %s tracer\n", tracer_name); retval = tracefs_tracer_set(inst, tracer, tracer_name); if (retval < 0) { if (errno == ENODEV) - err_msg("tracer %s not found!\n", tracer_name); + err_msg("Tracer %s not found!\n", tracer_name); - err_msg("failed to enable the tracer %s\n", tracer_name); + err_msg("Failed to enable the %s tracer\n", tracer_name); return -1; } @@ -44,7 +44,7 @@ void disable_tracer(struct tracefs_instance *inst) retval = tracefs_tracer_set(inst, t); if (retval < 0) - err_msg("oops, error disabling tracer\n"); + err_msg("Oops, error disabling tracer\n"); } /* @@ -190,3 +190,348 @@ int trace_instance_start(struct trace_instance *trace) { return tracefs_trace_on(trace->inst); } + +/* + * trace_events_free - free a list of trace events + */ +static void trace_events_free(struct trace_events *events) +{ + struct trace_events *tevent = events; + struct trace_events *free_event; + + while (tevent) { + free_event = tevent; + + tevent = tevent->next; + + if (free_event->filter) + free(free_event->filter); + if (free_event->trigger) + free(free_event->trigger); + free(free_event->system); + free(free_event); + } +} + +/* + * trace_event_alloc - alloc and parse a single trace event + */ +struct trace_events *trace_event_alloc(const char *event_string) +{ + struct trace_events *tevent; + + tevent = calloc(1, sizeof(*tevent)); + if (!tevent) + return NULL; + + tevent->system = strdup(event_string); + if (!tevent->system) { + free(tevent); + return NULL; + } + + tevent->event = strstr(tevent->system, ":"); + if (tevent->event) { + *tevent->event = '\0'; + tevent->event = &tevent->event[1]; + } + + return tevent; +} + +/* + * trace_event_add_filter - record an event filter + */ +int trace_event_add_filter(struct trace_events *event, char *filter) +{ + if (event->filter) + free(event->filter); + + event->filter = strdup(filter); + if (!event->filter) + return 1; + + return 0; +} + +/* + * trace_event_add_trigger - record an event trigger action + */ +int trace_event_add_trigger(struct trace_events *event, char *trigger) +{ + if (event->trigger) + free(event->trigger); + + event->trigger = strdup(trigger); + if (!event->trigger) + return 1; + + return 0; +} + +/* + * trace_event_disable_filter - disable an event filter + */ +static void trace_event_disable_filter(struct trace_instance *instance, + struct trace_events *tevent) +{ + char filter[1024]; + int retval; + + if (!tevent->filter) + return; + + if (!tevent->filter_enabled) + return; + + debug_msg("Disabling %s:%s filter %s\n", tevent->system, + tevent->event ? : "*", tevent->filter); + + snprintf(filter, 1024, "!%s\n", tevent->filter); + + retval = tracefs_event_file_write(instance->inst, tevent->system, + tevent->event, "filter", filter); + if (retval < 0) + err_msg("Error disabling %s:%s filter %s\n", tevent->system, + tevent->event ? : "*", tevent->filter); +} + +/* + * trace_event_save_hist - save the content of an event hist + * + * If the trigger is a hist: one, save the content of the hist file. + */ +static void trace_event_save_hist(struct trace_instance *instance, + struct trace_events *tevent) +{ + int retval, index, out_fd; + mode_t mode = 0644; + char path[1024]; + char *hist; + + if (!tevent) + return; + + /* trigger enables hist */ + if (!tevent->trigger) + return; + + /* is this a hist: trigger? */ + retval = strncmp(tevent->trigger, "hist:", strlen("hist:")); + if (retval) + return; + + snprintf(path, 1024, "%s_%s_hist.txt", tevent->system, tevent->event); + + printf(" Saving event %s:%s hist to %s\n", tevent->system, tevent->event, path); + + out_fd = creat(path, mode); + if (out_fd < 0) { + err_msg(" Failed to create %s output file\n", path); + return; + } + + hist = tracefs_event_file_read(instance->inst, tevent->system, tevent->event, "hist", 0); + if (!hist) { + err_msg(" Failed to read %s:%s hist file\n", tevent->system, tevent->event); + goto out_close; + } + + index = 0; + do { + index += write(out_fd, &hist[index], strlen(hist) - index); + } while (index < strlen(hist)); + + free(hist); +out_close: + close(out_fd); +} + +/* + * trace_event_disable_trigger - disable an event trigger + */ +static void trace_event_disable_trigger(struct trace_instance *instance, + struct trace_events *tevent) +{ + char trigger[1024]; + int retval; + + if (!tevent->trigger) + return; + + if (!tevent->trigger_enabled) + return; + + debug_msg("Disabling %s:%s trigger %s\n", tevent->system, + tevent->event ? : "*", tevent->trigger); + + trace_event_save_hist(instance, tevent); + + snprintf(trigger, 1024, "!%s\n", tevent->trigger); + + retval = tracefs_event_file_write(instance->inst, tevent->system, + tevent->event, "trigger", trigger); + if (retval < 0) + err_msg("Error disabling %s:%s trigger %s\n", tevent->system, + tevent->event ? : "*", tevent->trigger); +} + +/* + * trace_events_disable - disable all trace events + */ +void trace_events_disable(struct trace_instance *instance, + struct trace_events *events) +{ + struct trace_events *tevent = events; + + if (!events) + return; + + while (tevent) { + debug_msg("Disabling event %s:%s\n", tevent->system, tevent->event ? : "*"); + if (tevent->enabled) { + trace_event_disable_filter(instance, tevent); + trace_event_disable_trigger(instance, tevent); + tracefs_event_disable(instance->inst, tevent->system, tevent->event); + } + + tevent->enabled = 0; + tevent = tevent->next; + } +} + +/* + * trace_event_enable_filter - enable an event filter associated with an event + */ +static int trace_event_enable_filter(struct trace_instance *instance, + struct trace_events *tevent) +{ + char filter[1024]; + int retval; + + if (!tevent->filter) + return 0; + + if (!tevent->event) { + err_msg("Filter %s applies only for single events, not for all %s:* events\n", + tevent->filter, tevent->system); + return 1; + } + + snprintf(filter, 1024, "%s\n", tevent->filter); + + debug_msg("Enabling %s:%s filter %s\n", tevent->system, + tevent->event ? : "*", tevent->filter); + + retval = tracefs_event_file_write(instance->inst, tevent->system, + tevent->event, "filter", filter); + if (retval < 0) { + err_msg("Error enabling %s:%s filter %s\n", tevent->system, + tevent->event ? : "*", tevent->filter); + return 1; + } + + tevent->filter_enabled = 1; + return 0; +} + +/* + * trace_event_enable_trigger - enable an event trigger associated with an event + */ +static int trace_event_enable_trigger(struct trace_instance *instance, + struct trace_events *tevent) +{ + char trigger[1024]; + int retval; + + if (!tevent->trigger) + return 0; + + if (!tevent->event) { + err_msg("Trigger %s applies only for single events, not for all %s:* events\n", + tevent->trigger, tevent->system); + return 1; + } + + snprintf(trigger, 1024, "%s\n", tevent->trigger); + + debug_msg("Enabling %s:%s trigger %s\n", tevent->system, + tevent->event ? : "*", tevent->trigger); + + retval = tracefs_event_file_write(instance->inst, tevent->system, + tevent->event, "trigger", trigger); + if (retval < 0) { + err_msg("Error enabling %s:%s trigger %s\n", tevent->system, + tevent->event ? : "*", tevent->trigger); + return 1; + } + + tevent->trigger_enabled = 1; + + return 0; +} + +/* + * trace_events_enable - enable all events + */ +int trace_events_enable(struct trace_instance *instance, + struct trace_events *events) +{ + struct trace_events *tevent = events; + int retval; + + while (tevent) { + debug_msg("Enabling event %s:%s\n", tevent->system, tevent->event ? : "*"); + retval = tracefs_event_enable(instance->inst, tevent->system, tevent->event); + if (retval < 0) { + err_msg("Error enabling event %s:%s\n", tevent->system, + tevent->event ? : "*"); + return 1; + } + + retval = trace_event_enable_filter(instance, tevent); + if (retval) + return 1; + + retval = trace_event_enable_trigger(instance, tevent); + if (retval) + return 1; + + tevent->enabled = 1; + tevent = tevent->next; + } + + return 0; +} + +/* + * trace_events_destroy - disable and free all trace events + */ +void trace_events_destroy(struct trace_instance *instance, + struct trace_events *events) +{ + if (!events) + return; + + trace_events_disable(instance, events); + trace_events_free(events); +} + +int trace_is_off(struct trace_instance *tool, struct trace_instance *trace) +{ + /* + * The tool instance is always present, it is the one used to collect + * data. + */ + if (!tracefs_trace_is_on(tool->inst)) + return 1; + + /* + * The trace instance is only enabled when -t is set. IOW, when the system + * is tracing. + */ + if (trace && !tracefs_trace_is_on(trace->inst)) + return 1; + + return 0; +} diff --git a/tools/tracing/rtla/src/trace.h b/tools/tracing/rtla/src/trace.h index 0ea1df0ad9a7..2e9a89a25615 100644 --- a/tools/tracing/rtla/src/trace.h +++ b/tools/tracing/rtla/src/trace.h @@ -2,6 +2,17 @@ #include <tracefs.h> #include <stddef.h> +struct trace_events { + struct trace_events *next; + char *system; + char *event; + char *filter; + char *trigger; + char enabled; + char filter_enabled; + char trigger_enabled; +}; + struct trace_instance { struct tracefs_instance *inst; struct tep_handle *tep; @@ -25,3 +36,15 @@ void destroy_instance(struct tracefs_instance *inst); int save_trace_to_file(struct tracefs_instance *inst, const char *filename); int collect_registered_events(struct tep_event *tep, struct tep_record *record, int cpu, void *context); + +struct trace_events *trace_event_alloc(const char *event_string); +void trace_events_disable(struct trace_instance *instance, + struct trace_events *events); +void trace_events_destroy(struct trace_instance *instance, + struct trace_events *events); +int trace_events_enable(struct trace_instance *instance, + struct trace_events *events); + +int trace_event_add_filter(struct trace_events *event, char *filter); +int trace_event_add_trigger(struct trace_events *event, char *trigger); +int trace_is_off(struct trace_instance *tool, struct trace_instance *trace); diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index 1c9f0eea6166..da2b590edaed 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -10,6 +10,7 @@ #include <unistd.h> #include <ctype.h> #include <errno.h> +#include <fcntl.h> #include <sched.h> #include <stdio.h> @@ -77,11 +78,11 @@ void get_duration(time_t start_time, char *output, int output_size) time_t duration; duration = difftime(now, start_time); - tm_info = localtime(&duration); + tm_info = gmtime(&duration); snprintf(output, output_size, "%3d %02d:%02d:%02d", tm_info->tm_yday, - tm_info->tm_hour - 1, + tm_info->tm_hour, tm_info->tm_min, tm_info->tm_sec); } @@ -431,3 +432,35 @@ int parse_prio(char *arg, struct sched_attr *sched_param) } return 0; } + +/* + * set_cpu_dma_latency - set the /dev/cpu_dma_latecy + * + * This is used to reduce the exit from idle latency. The value + * will be reset once the file descriptor of /dev/cpu_dma_latecy + * is closed. + * + * Return: the /dev/cpu_dma_latecy file descriptor + */ +int set_cpu_dma_latency(int32_t latency) +{ + int retval; + int fd; + + fd = open("/dev/cpu_dma_latency", O_RDWR); + if (fd < 0) { + err_msg("Error opening /dev/cpu_dma_latency\n"); + return -1; + } + + retval = write(fd, &latency, 4); + if (retval < 1) { + err_msg("Error setting /dev/cpu_dma_latency\n"); + close(fd); + return -1; + } + + debug_msg("Set /dev/cpu_dma_latency to %d\n", latency); + + return fd; +} diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index 9aa962319ca2..fa08e374870a 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -54,3 +54,4 @@ struct sched_attr { int parse_prio(char *arg, struct sched_attr *sched_param); int set_comm_sched_attr(const char *comm, struct sched_attr *attr); +int set_cpu_dma_latency(int32_t latency); diff --git a/tools/virtio/linux/mm_types.h b/tools/virtio/linux/mm_types.h new file mode 100644 index 000000000000..356ba4d496f6 --- /dev/null +++ b/tools/virtio/linux/mm_types.h @@ -0,0 +1,3 @@ +struct folio { + struct page page; +}; diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index cb3f29c09aff..23f142af544a 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -130,6 +130,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features) memset(dev, 0, sizeof *dev); dev->vdev.features = features; INIT_LIST_HEAD(&dev->vdev.vqs); + spin_lock_init(&dev->vdev.vqs_list_lock); dev->buf_size = 1024; dev->buf = malloc(dev->buf_size); assert(dev->buf); |