diff options
Diffstat (limited to 'tools')
200 files changed, 8531 insertions, 1556 deletions
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 2769360f195c..03cd7c19a683 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -131,8 +131,9 @@ struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 67c21f9bdbad..820e5751ada7 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -164,8 +164,9 @@ struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; @@ -323,6 +324,8 @@ struct kvm_vcpu_events { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_PVTIME_CTRL 2 +#define KVM_ARM_VCPU_PVTIME_IPA 0 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_VCPU2_SHIFT 28 diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index b0f72dea8b11..264e266a85bf 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char { /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ +#define KVM_DEV_XICS_GRP_CTRL 2 +#define KVM_DEV_XICS_NR_SERVERS 1 /* Layout of 64-bit source attribute values */ #define KVM_XICS_DESTINATION_SHIFT 0 @@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char { #define KVM_DEV_XIVE_GRP_CTRL 1 #define KVM_DEV_XIVE_RESET 1 #define KVM_DEV_XIVE_EQ_SYNC 2 +#define KVM_DEV_XIVE_NR_SERVERS 3 #define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG 3 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_EQ_CONFIG 4 /* 64-bit EQ identifier */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 0652d3eed9bd..e9b62498fe75 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -292,6 +292,7 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ #define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ #define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ @@ -399,5 +400,7 @@ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 20ce682a2540..084e98da04a7 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -93,6 +93,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -103,6 +115,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 @@ -393,6 +409,8 @@ #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 +#define MSR_AMD_PPIN_CTL 0xc00102f0 +#define MSR_AMD_PPIN 0xc00102f1 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_BU_CFG2 0xc001102a diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 92748660ba51..df767afc690f 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -28,8 +28,8 @@ * Output: * rax original destination */ -ENTRY(__memcpy) -ENTRY(memcpy) +SYM_FUNC_START_ALIAS(__memcpy) +SYM_FUNC_START_LOCAL(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -41,8 +41,8 @@ ENTRY(memcpy) movl %edx, %ecx rep movsb ret -ENDPROC(memcpy) -ENDPROC(__memcpy) +SYM_FUNC_END(memcpy) +SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(memcpy) EXPORT_SYMBOL(__memcpy) @@ -50,14 +50,14 @@ EXPORT_SYMBOL(__memcpy) * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. */ -ENTRY(memcpy_erms) +SYM_FUNC_START(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret -ENDPROC(memcpy_erms) +SYM_FUNC_END(memcpy_erms) -ENTRY(memcpy_orig) +SYM_FUNC_START(memcpy_orig) movq %rdi, %rax cmpq $0x20, %rdx @@ -182,7 +182,7 @@ ENTRY(memcpy_orig) .Lend: retq -ENDPROC(memcpy_orig) +SYM_FUNC_END(memcpy_orig) #ifndef CONFIG_UML @@ -193,7 +193,7 @@ MCSAFE_TEST_CTL * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(__memcpy_mcsafe) +SYM_FUNC_START(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe) xorl %eax, %eax .L_done: ret -ENDPROC(__memcpy_mcsafe) +SYM_FUNC_END(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index f8f3dc0a6690..fd5d25a474b7 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,8 +18,8 @@ * * rax original destination */ -ENTRY(memset) -ENTRY(__memset) +SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended * to use it when possible. If not available, use fast string instructions. @@ -42,8 +42,8 @@ ENTRY(__memset) rep stosb movq %r9,%rax ret -ENDPROC(memset) -ENDPROC(__memset) +SYM_FUNC_END(__memset) +SYM_FUNC_END_ALIAS(memset) /* * ISO C memset - set a memory block to a byte value. This function uses @@ -56,16 +56,16 @@ ENDPROC(__memset) * * rax original destination */ -ENTRY(memset_erms) +SYM_FUNC_START(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx rep stosb movq %r9,%rax ret -ENDPROC(memset_erms) +SYM_FUNC_END(memset_erms) -ENTRY(memset_orig) +SYM_FUNC_START(memset_orig) movq %rdi,%r10 /* expand byte value */ @@ -136,4 +136,4 @@ ENTRY(memset_orig) subq %r8,%rdx jmp .Lafter_bad_alignment .Lfinal: -ENDPROC(memset_orig) +SYM_FUNC_END(memset_orig) diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index 0a0e9112f284..8908c58bd6cd 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -695,16 +695,28 @@ AVXcode: 2 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) -# Skip 0x50-0x57 +50: vpdpbusd Vx,Hx,Wx (66),(ev) +51: vpdpbusds Vx,Hx,Wx (66),(ev) +52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) +53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) +54: vpopcntb/w Vx,Wx (66),(ev) +55: vpopcntd/q Vx,Wx (66),(ev) 58: vpbroadcastd Vx,Wx (66),(v) 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-0x63 +# Skip 0x5c-0x61 +62: vpexpandb/w Vx,Wx (66),(ev) +63: vpcompressb/w Wx,Vx (66),(ev) 64: vpblendmd/q Vx,Hx,Wx (66),(ev) 65: vblendmps/d Vx,Hx,Wx (66),(ev) 66: vpblendmb/w Vx,Hx,Wx (66),(ev) -# Skip 0x67-0x74 +68: vp2intersectd/q Kx,Hx,Wx (F2),(ev) +# Skip 0x69-0x6f +70: vpshldvw Vx,Hx,Wx (66),(ev) +71: vpshldvd/q Vx,Hx,Wx (66),(ev) +72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev) +73: vpshrdvd/q Vx,Hx,Wx (66),(ev) 75: vpermi2b/w Vx,Hx,Wx (66),(ev) 76: vpermi2d/q Vx,Hx,Wx (66),(ev) 77: vpermi2ps/d Vx,Hx,Wx (66),(ev) @@ -727,6 +739,7 @@ AVXcode: 2 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) 8d: vpermb/w Vx,Hx,Wx (66),(ev) 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) +8f: vpshufbitqmb Kx,Hx,Wx (66),(ev) # 0x0f 0x38 0x90-0xbf (FMA) 90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) 91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) @@ -738,8 +751,8 @@ AVXcode: 2 97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v) 98: vfmadd132ps/d Vx,Hx,Wx (66),(v) 99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1) -9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) -9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) +9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) | v4fmaddps Vdqq,Hdqq,Wdq (F2),(ev) +9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) | v4fmaddss Vdq,Hdq,Wdq (F2),(ev) 9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v) 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) @@ -752,8 +765,8 @@ a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1) -aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) -ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) +aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) | v4fnmaddps Vdqq,Hdqq,Wdq (F2),(ev) +ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) | v4fnmaddss Vdq,Hdq,Wdq (F2),(ev) ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) @@ -780,11 +793,12 @@ ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) +cf: vgf2p8mulb Vx,Wx (66) db: VAESIMC Vdq,Wdq (66),(v1) -dc: VAESENC Vdq,Hdq,Wdq (66),(v1) -dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) -de: VAESDEC Vdq,Hdq,Wdq (66),(v1) -df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1) +dc: vaesenc Vx,Hx,Wx (66) +dd: vaesenclast Vx,Hx,Wx (66) +de: vaesdec Vx,Hx,Wx (66) +df: vaesdeclast Vx,Hx,Wx (66) f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2) f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2) f2: ANDN Gy,By,Ey (v) @@ -848,7 +862,7 @@ AVXcode: 3 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) 42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) 43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) -44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) +44: vpclmulqdq Vx,Hx,Wx,Ib (66) 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) 4a: vblendvps Vx,Hx,Wx,Lx (66),(v) 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) @@ -865,7 +879,13 @@ AVXcode: 3 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) 66: vfpclassps/d Vk,Wx,Ib (66),(ev) 67: vfpclassss/d Vk,Wx,Ib (66),(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) 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) EndTable diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 4535c863d2cd..2ce9c5ba1934 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -493,7 +493,7 @@ static int do_dump(int argc, char **argv) info = &info_linear->info; if (mode == DUMP_JITED) { - if (info->jited_prog_len == 0) { + if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); goto err_free; } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 494d7ae3614d..5b91ee65a080 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -174,7 +174,7 @@ static const char *print_call(void *private_data, struct kernel_sym *sym; if (insn->src_reg == BPF_PSEUDO_CALL && - (__u32) insn->imm < dd->nr_jited_ksyms) + (__u32) insn->imm < dd->nr_jited_ksyms && dd->jited_ksyms) address = dd->jited_ksyms[insn->imm]; sym = kernel_syms_search(dd, address); diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 8a19753cc26a..574c2e0b9d20 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -96,7 +96,8 @@ FEATURE_TESTS_EXTRA := \ cxx \ llvm \ llvm-version \ - clang + clang \ + libbpf FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC) diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 8499385365c0..f30a89046aa3 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -53,6 +53,7 @@ FILES= \ test-zlib.bin \ test-lzma.bin \ test-bpf.bin \ + test-libbpf.bin \ test-get_cpuid.bin \ test-sdt.bin \ test-cxx.bin \ @@ -270,6 +271,9 @@ $(OUTPUT)test-get_cpuid.bin: $(OUTPUT)test-bpf.bin: $(BUILD) +$(OUTPUT)test-libbpf.bin: + $(BUILD) -lbpf + $(OUTPUT)test-sdt.bin: $(BUILD) diff --git a/tools/build/feature/test-libbpf.c b/tools/build/feature/test-libbpf.c new file mode 100644 index 000000000000..a508756cf4cc --- /dev/null +++ b/tools/build/feature/test-libbpf.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bpf/libbpf.h> + +int main(void) +{ + return bpf_object__open("test") ? 0 : -1; +} diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 8a5b2f8f8eb9..868bf7996c0f 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -778,11 +778,12 @@ struct drm_syncobj_array { __u32 pad; }; +#define DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED (1 << 0) /* last available point on timeline syncobj */ struct drm_syncobj_timeline_array { __u64 handles; __u64 points; __u32 count_handles; - __u32 pad; + __u32 flags; }; diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 469dc512cca3..5400d7e057f1 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -611,6 +611,13 @@ typedef struct drm_i915_irq_wait { * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT. */ #define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53 + +/* + * Revision of the i915-perf uAPI. The value returned helps determine what + * i915-perf features are available. See drm_i915_perf_property_id. + */ +#define I915_PARAM_PERF_REVISION 54 + /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1565,6 +1572,21 @@ struct drm_i915_gem_context_param { * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) */ #define I915_CONTEXT_PARAM_ENGINES 0xa + +/* + * I915_CONTEXT_PARAM_PERSISTENCE: + * + * Allow the context and active rendering to survive the process until + * completion. Persistence allows fire-and-forget clients to queue up a + * bunch of work, hand the output over to a display server and then quit. + * If the context is marked as not persistent, upon closing (either via + * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure + * or process termination), the context and any outstanding requests will be + * cancelled (and exported fences for cancelled requests marked as -EIO). + * + * By default, new contexts allow persistence. + */ +#define I915_CONTEXT_PARAM_PERSISTENCE 0xb /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -1844,23 +1866,31 @@ enum drm_i915_perf_property_id { * Open the stream for a specific context handle (as used with * execbuffer2). A stream opened for a specific context this way * won't typically require root privileges. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_CTX_HANDLE = 1, /** * A value of 1 requests the inclusion of raw OA unit reports as * part of stream samples. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_SAMPLE_OA, /** * The value specifies which set of OA unit metrics should be * be configured, defining the contents of any OA unit reports. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_METRICS_SET, /** * The value specifies the size and layout of OA unit reports. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_FORMAT, @@ -1870,9 +1900,22 @@ enum drm_i915_perf_property_id { * from this exponent as follows: * * 80ns * 2^(period_exponent + 1) + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_EXPONENT, + /** + * Specifying this property is only valid when specify a context to + * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property + * will hold preemption of the particular context we want to gather + * performance data about. The execbuf2 submissions must include a + * drm_i915_gem_execbuffer_ext_perf parameter for this to apply. + * + * This property is available in perf revision 3. + */ + DRM_I915_PERF_PROP_HOLD_PREEMPTION, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; @@ -1901,6 +1944,8 @@ struct drm_i915_perf_open_param { * to close and re-open a stream with the same configuration. * * It's undefined whether any pending data for the stream will be lost. + * + * This ioctl is available in perf revision 1. */ #define I915_PERF_IOCTL_ENABLE _IO('i', 0x0) @@ -1908,10 +1953,25 @@ struct drm_i915_perf_open_param { * Disable data capture for a stream. * * It is an error to try and read a stream that is disabled. + * + * This ioctl is available in perf revision 1. */ #define I915_PERF_IOCTL_DISABLE _IO('i', 0x1) /** + * Change metrics_set captured by a stream. + * + * If the stream is bound to a specific context, the configuration change + * will performed inline with that context such that it takes effect before + * the next execbuf submission. + * + * Returns the previously bound metrics set id, or a negative error code. + * + * This ioctl is available in perf revision 2. + */ +#define I915_PERF_IOCTL_CONFIG _IO('i', 0x2) + +/** * Common to all i915 perf records */ struct drm_i915_perf_record_header { @@ -1984,6 +2044,7 @@ struct drm_i915_query_item { __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 #define DRM_I915_QUERY_ENGINE_INFO 2 +#define DRM_I915_QUERY_PERF_CONFIG 3 /* Must be kept compact -- no holes and well documented */ /* @@ -1995,9 +2056,18 @@ struct drm_i915_query_item { __s32 length; /* - * Unused for now. Must be cleared to zero. + * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. + * + * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the + * following : + * - DRM_I915_QUERY_PERF_CONFIG_LIST + * - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID + * - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID */ __u32 flags; +#define DRM_I915_QUERY_PERF_CONFIG_LIST 1 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID 3 /* * Data will be written at the location pointed by data_ptr when the @@ -2033,8 +2103,10 @@ struct drm_i915_query { * (data[X / 8] >> (X % 8)) & 1 * * - the subslice mask for each slice with one bit per subslice telling - * whether a subslice is available. The availability of subslice Y in slice - * X can be queried with the following formula : + * whether a subslice is available. Gen12 has dual-subslices, which are + * similar to two gen11 subslices. For gen12, this array represents dual- + * subslices. The availability of subslice Y in slice X can be queried + * with the following formula : * * (data[subslice_offset + * X * subslice_stride + @@ -2123,6 +2195,56 @@ struct drm_i915_query_engine_info { struct drm_i915_engine_info engines[]; }; +/* + * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG. + */ +struct drm_i915_query_perf_config { + union { + /* + * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets + * this fields to the number of configurations available. + */ + __u64 n_configs; + + /* + * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, + * i915 will use the value in this field as configuration + * identifier to decide what data to write into config_ptr. + */ + __u64 config; + + /* + * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, + * i915 will use the value in this field as configuration + * identifier to decide what data to write into config_ptr. + * + * String formatted like "%08x-%04x-%04x-%04x-%012x" + */ + char uuid[36]; + }; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /* + * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will + * write an array of __u64 of configuration identifiers. + * + * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will + * write a struct drm_i915_perf_oa_config. If the following fields of + * drm_i915_perf_oa_config are set not set to 0, i915 will write into + * the associated pointers the values of submitted when the + * configuration was created : + * + * - n_mux_regs + * - n_boolean_regs + * - n_flex_regs + */ + __u8 data[]; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 39ccfe9311c3..1beb174ad950 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -17,7 +17,8 @@ #define FSCRYPT_POLICY_FLAGS_PAD_32 0x03 #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 -#define FSCRYPT_POLICY_FLAGS_VALID 0x07 +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 +#define FSCRYPT_POLICY_FLAGS_VALID 0x0F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 52641d8ca9e8..f0a16b4adbbd 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -235,6 +235,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_S390_STSI 25 #define KVM_EXIT_IOAPIC_EOI 26 #define KVM_EXIT_HYPERV 27 +#define KVM_EXIT_ARM_NISV 28 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -394,6 +395,11 @@ struct kvm_run { } eoi; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; + /* KVM_EXIT_ARM_NISV */ + struct { + __u64 esr_iss; + __u64 fault_ipa; + } arm_nisv; /* Fix the size of the union. */ char padding[256]; }; @@ -1000,6 +1006,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PMU_EVENT_FILTER 173 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174 #define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175 +#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176 +#define KVM_CAP_ARM_NISV_TO_USER 177 +#define KVM_CAP_ARM_INJECT_EXT_DABT 178 #ifdef KVM_CAP_IRQ_ROUTING @@ -1227,6 +1236,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_XIVE, #define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE + KVM_DEV_TYPE_ARM_PV_TIME, +#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_MAX, }; @@ -1337,6 +1348,7 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) /* Available with KVM_CAP_PMU_EVENT_FILTER */ #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) +#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 99335e1f4a27..4a0217832464 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -33,27 +33,48 @@ #define CLONE_NEWNET 0x40000000 /* New network namespace */ #define CLONE_IO 0x80000000 /* Clone io context */ +/* Flags for the clone3() syscall. */ +#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ + #ifndef __ASSEMBLY__ /** * struct clone_args - arguments for the clone3 syscall - * @flags: Flags for the new process as listed above. - * All flags are valid except for CSIGNAL and - * CLONE_DETACHED. - * @pidfd: If CLONE_PIDFD is set, a pidfd will be - * returned in this argument. - * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the - * child process will be returned in the child's - * memory. - * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of - * the child process will be returned in the - * parent's memory. - * @exit_signal: The exit_signal the parent process will be - * sent when the child exits. - * @stack: Specify the location of the stack for the - * child process. - * @stack_size: The size of the stack for the child process. - * @tls: If CLONE_SETTLS is set, the tls descriptor - * is set to tls. + * @flags: Flags for the new process as listed above. + * All flags are valid except for CSIGNAL and + * CLONE_DETACHED. + * @pidfd: If CLONE_PIDFD is set, a pidfd will be + * returned in this argument. + * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the + * child process will be returned in the child's + * memory. + * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of + * the child process will be returned in the + * parent's memory. + * @exit_signal: The exit_signal the parent process will be + * sent when the child exits. + * @stack: Specify the location of the stack for the + * child process. + * Note, @stack is expected to point to the + * lowest address. The stack direction will be + * determined by the kernel and set up + * appropriately based on @stack_size. + * @stack_size: The size of the stack for the child process. + * @tls: If CLONE_SETTLS is set, the tls descriptor + * is set to tls. + * @set_tid: Pointer to an array of type *pid_t. The size + * of the array is defined using @set_tid_size. + * This array is used to select PIDs/TIDs for + * newly created processes. The first element in + * this defines the PID in the most nested PID + * namespace. Each additional element in the array + * defines the PID in the parent PID namespace of + * the original PID namespace. If the array has + * less entries than the number of currently + * nested PID namespaces only the PIDs in the + * corresponding namespaces are set. + * @set_tid_size: This defines the size of the array referenced + * in @set_tid. This cannot be larger than the + * kernel's limit of nested PID namespaces. * * The structure is versioned by size and thus extensible. * New struct members must go at the end of the struct and @@ -68,10 +89,13 @@ struct clone_args { __aligned_u64 stack; __aligned_u64 stack_size; __aligned_u64 tls; + __aligned_u64 set_tid; + __aligned_u64 set_tid_size; }; #endif #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ +#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ /* * Scheduling policies diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 7b35e98d3c58..ad80a5c885d5 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -167,8 +167,8 @@ struct statx { #define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */ #define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ - #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 35bf013e368c..e97c2ebcf447 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,7 +1,6 @@ libbpf_version.h libbpf.pc FEATURE-DUMP.libbpf -test_libbpf libbpf.so.* TAGS tags diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 99425d0be6ff..97830e46d1a0 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -138,6 +138,7 @@ STATIC_OBJDIR := $(OUTPUT)staticobjs/ BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o VERSION_SCRIPT := libbpf.map +BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) @@ -147,19 +148,19 @@ TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) -CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) $(OUTPUT)test_libbpf +CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) all: fixdep $(Q)$(MAKE) all_cmd all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h +$(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -177,12 +178,12 @@ $(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force elfdep bpfdep bpf_helper_defs.h +$(BPF_IN_STATIC): force elfdep bpfdep $(BPF_HELPER_DEFS) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) -bpf_helper_defs.h: $(srctree)/include/uapi/linux/bpf.h +$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \ - --file $(srctree)/include/uapi/linux/bpf.h > bpf_helper_defs.h + --file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS) $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) @@ -196,9 +197,6 @@ $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(OUTPUT)libbpf.a: $(BPF_IN_STATIC) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ -$(OUTPUT)test_libbpf: test_libbpf.c $(OUTPUT)libbpf.a - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(INCLUDES) $^ -lelf -o $@ - $(OUTPUT)libbpf.pc: $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ -e "s|@LIBDIR@|$(libdir_SQ)|" \ @@ -214,9 +212,9 @@ check_abi: $(OUTPUT)libbpf.so "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \ "Please make sure all LIBBPF_API symbols are" \ "versioned in $(VERSION_SCRIPT)." >&2; \ - readelf -s --wide $(OUTPUT)libbpf-in.o | \ + readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ @@ -246,7 +244,7 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) -install_headers: bpf_helper_defs.h +install_headers: $(BPF_HELPER_DEFS) $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ @@ -254,7 +252,7 @@ install_headers: bpf_helper_defs.h $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ - $(call do_install,bpf_helper_defs.h,$(prefix)/include/bpf,644); \ + $(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \ $(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644); @@ -274,7 +272,7 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ - *.pc LIBBPF-CFLAGS bpf_helper_defs.h \ + *.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index b20f82e58989..3f09772192f1 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -171,10 +171,8 @@ struct bpf_program { RELO_DATA, } type; int insn_idx; - union { - int map_idx; - int text_off; - }; + int map_idx; + int sym_off; } *reloc_desc; int nr_reloc; int log_level; @@ -1819,12 +1817,12 @@ static int bpf_program__record_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } if (sym->st_value % 8) { - pr_warn("bad call relo offset: %lu\n", sym->st_value); + pr_warn("bad call relo offset: %llu\n", (__u64)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_CALL; reloc_desc->insn_idx = insn_idx; - reloc_desc->text_off = sym->st_value / 8; + reloc_desc->sym_off = sym->st_value; obj->has_pseudo_calls = true; return 0; } @@ -1868,6 +1866,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog, reloc_desc->type = RELO_LD64; reloc_desc->insn_idx = insn_idx; reloc_desc->map_idx = map_idx; + reloc_desc->sym_off = 0; /* sym->st_value determines map_idx */ return 0; } @@ -1899,6 +1898,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog, reloc_desc->type = RELO_DATA; reloc_desc->insn_idx = insn_idx; reloc_desc->map_idx = map_idx; + reloc_desc->sym_off = sym->st_value; return 0; } @@ -3563,8 +3563,8 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, return -LIBBPF_ERRNO__RELOC; if (prog->idx == obj->efile.text_shndx) { - pr_warn("relo in .text insn %d into off %d\n", - relo->insn_idx, relo->text_off); + pr_warn("relo in .text insn %d into off %d (insn #%d)\n", + relo->insn_idx, relo->sym_off, relo->sym_off / 8); return -LIBBPF_ERRNO__RELOC; } @@ -3599,7 +3599,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, prog->section_name); } insn = &prog->insns[relo->insn_idx]; - insn->imm += relo->text_off + prog->main_prog_cnt - relo->insn_idx; + insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx; return 0; } @@ -3622,31 +3622,26 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; for (i = 0; i < prog->nr_reloc; i++) { - if (prog->reloc_desc[i].type == RELO_LD64 || - prog->reloc_desc[i].type == RELO_DATA) { - bool relo_data = prog->reloc_desc[i].type == RELO_DATA; - struct bpf_insn *insns = prog->insns; - int insn_idx, map_idx; + struct reloc_desc *relo = &prog->reloc_desc[i]; - insn_idx = prog->reloc_desc[i].insn_idx; - map_idx = prog->reloc_desc[i].map_idx; + if (relo->type == RELO_LD64 || relo->type == RELO_DATA) { + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; - if (insn_idx + 1 >= (int)prog->insns_cnt) { + if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { pr_warn("relocation out of range: '%s'\n", prog->section_name); return -LIBBPF_ERRNO__RELOC; } - if (!relo_data) { - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + if (relo->type != RELO_DATA) { + insn[0].src_reg = BPF_PSEUDO_MAP_FD; } else { - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE; - insns[insn_idx + 1].imm = insns[insn_idx].imm; + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[1].imm = insn[0].imm + relo->sym_off; } - insns[insn_idx].imm = obj->maps[map_idx].fd; - } else if (prog->reloc_desc[i].type == RELO_CALL) { - err = bpf_program__reloc_text(prog, obj, - &prog->reloc_desc[i]); + insn[0].imm = obj->maps[relo->map_idx].fd; + } else if (relo->type == RELO_CALL) { + err = bpf_program__reloc_text(prog, obj, relo); if (err) return err; } diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index cbb429f55062..c874c017c636 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -39,11 +39,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) - libdir_relative = lib64 + libdir_relative_temp = lib64 else - libdir_relative = lib + libdir_relative_temp = lib endif +libdir_relative ?= $(libdir_relative_temp) prefix ?= /usr/local libdir = $(prefix)/$(libdir_relative) man_dir = $(prefix)/share/man @@ -97,6 +98,7 @@ EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION) LIB_TARGET = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION) LIB_INSTALL = libtraceevent.a libtraceevent.so* +LIB_INSTALL := $(addprefix $(OUTPUT),$(LIB_INSTALL)) INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES) @@ -207,10 +209,11 @@ define do_install $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' endef -PKG_CONFIG_FILE = libtraceevent.pc +PKG_CONFIG_SOURCE_FILE = libtraceevent.pc +PKG_CONFIG_FILE := $(addprefix $(OUTPUT),$(PKG_CONFIG_SOURCE_FILE)) define do_install_pkgconfig_file if [ -n "${pkgconfig_dir}" ]; then \ - cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; \ + cp -f ${PKG_CONFIG_SOURCE_FILE}.template ${PKG_CONFIG_FILE}; \ sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \ diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile index f440989fa55e..349bb81482ab 100644 --- a/tools/lib/traceevent/plugins/Makefile +++ b/tools/lib/traceevent/plugins/Makefile @@ -32,11 +32,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) - libdir_relative = lib64 + libdir_relative_tmp = lib64 else - libdir_relative = lib + libdir_relative_tmp = lib endif +libdir_relative ?= $(libdir_relative_tmp) prefix ?= /usr/local libdir = $(prefix)/$(libdir_relative) diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c index cb1e51fcc84e..32b7c6f9043d 100644 --- a/tools/pci/pcitest.c +++ b/tools/pci/pcitest.c @@ -129,6 +129,7 @@ static int run_test(struct pci_test *test) } fflush(stdout); + close(fd); return (ret < 0) ? ret : 1 - ret; /* return 0 if test succeeded */ } diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt index 6a5bb2b17039..cf95baef7b61 100644 --- a/tools/perf/Documentation/perf-kvm.txt +++ b/tools/perf/Documentation/perf-kvm.txt @@ -68,10 +68,11 @@ OPTIONS ------- -i:: --input=<path>:: - Input file name. + Input file name, for the 'report', 'diff' and 'buildid-list' subcommands. -o:: --output=<path>:: - Output file name. + Output file name, for the 'record' subcommand. Doesn't work with 'report', + just redirect the output to a file when using 'report'. --host:: Collect host side performance profile. --guest:: diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 70f1ff4e2eb4..4934edb5adfd 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -19,3 +19,4 @@ tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c tools/lib/zalloc.c +scripts/bpf_helpers_doc.py diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 1783427da9b0..c90f4146e5a2 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -483,6 +483,16 @@ ifndef NO_LIBELF ifeq ($(feature-bpf), 1) CFLAGS += -DHAVE_LIBBPF_SUPPORT $(call detected,CONFIG_LIBBPF) + + # detecting libbpf without LIBBPF_DYNAMIC, so make VF=1 shows libbpf detection status + $(call feature_check,libbpf) + ifdef LIBBPF_DYNAMIC + ifeq ($(feature-libbpf), 1) + EXTLIBS += -lbpf + else + dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); + endif + endif endif ifndef NO_DWARF diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1cd294468a1f..eae5d5e95952 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -116,6 +116,8 @@ include ../scripts/utilities.mak # # Define TCMALLOC to enable tcmalloc heap profiling. # +# Define LIBBPF_DYNAMIC to enable libbpf dynamic linking. +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -360,7 +362,9 @@ export PERL_PATH PERFLIBS = $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD) $(LIBPERF) ifndef NO_LIBBPF - PERFLIBS += $(LIBBPF) + ifndef LIBBPF_DYNAMIC + PERFLIBS += $(LIBBPF) + endif endif # We choose to avoid "if .. else if .. else .. endif endif" diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c index 2c35e532bc9a..ccfa87055c4a 100644 --- a/tools/perf/arch/arm/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -3,7 +3,7 @@ #include "perf_regs.h" #include "thread.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "event.h" #include "debug.h" #include "tests/tests.h" @@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_ARM_SP]; - map = map_groups__find(thread->mg, (u64)sp); + map = maps__find(thread->maps, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S index 6e2495cc4517..4284307d7822 100644 --- a/tools/perf/arch/arm/tests/regs_load.S +++ b/tools/perf/arch/arm/tests/regs_load.S @@ -37,7 +37,7 @@ .text .type perf_regs_load,%function -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) str r0, [r0, #R0] str r1, [r0, #R1] str r2, [r0, #R2] @@ -56,4 +56,4 @@ ENTRY(perf_regs_load) str lr, [r0, #PC] // store pc as lr in order to skip the call // to this function mov pc, lr -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c index a6a407fa1b8b..46147a483049 100644 --- a/tools/perf/arch/arm64/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c @@ -3,7 +3,7 @@ #include "perf_regs.h" #include "thread.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "event.h" #include "debug.h" #include "tests/tests.h" @@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_ARM64_SP]; - map = map_groups__find(thread->mg, (u64)sp); + map = maps__find(thread->maps, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S index 07042511dca9..d49de40b6818 100644 --- a/tools/perf/arch/arm64/tests/regs_load.S +++ b/tools/perf/arch/arm64/tests/regs_load.S @@ -7,7 +7,7 @@ #define LDR_REG(r) ldr x##r, [x0, 8 * r] #define SP (8 * 31) #define PC (8 * 32) -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) STR_REG(0) STR_REG(1) STR_REG(2) @@ -44,4 +44,4 @@ ENTRY(perf_regs_load) str x30, [x0, #PC] LDR_REG(1) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c index 5c178e4a1995..8efd9ed9e9db 100644 --- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c +++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c @@ -3,7 +3,7 @@ #include "perf_regs.h" #include "thread.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "event.h" #include "debug.h" #include "tests/tests.h" @@ -27,7 +27,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_POWERPC_R1]; - map = map_groups__find(thread->mg, (u64)sp); + map = maps__find(thread->maps, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index 2a6662e42f89..0e136630659e 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -38,7 +38,7 @@ static int s390_call__parse(struct arch *arch, struct ins_operands *ops, return -1; target.addr = map__objdump_2mem(map, ops->target.addr); - if (map_groups__find_ams(ms->mg, &target) == 0 && + if (maps__find_ams(ms->maps, &target) == 0 && map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 6ad0a1cedb13..ef43be9b6ec2 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -3,7 +3,7 @@ #include "perf_regs.h" #include "thread.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "event.h" #include "debug.h" #include "tests/tests.h" @@ -27,7 +27,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_X86_SP]; - map = map_groups__find(thread->mg, (u64)sp); + map = maps__find(thread->maps, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(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 58f8f2a095c4..e6461abc9e7b 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -667,6 +667,86 @@ "62 f2 55 0f 4f f4 \tvrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}",}, {{0x62, 0xf2, 0xd5, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "", "62 f2 d5 0f 4f f4 \tvrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 50 d9 \tvpdpbusd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 50 d9 \tvpdpbusd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 50 d9 \tvpdpbusd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 50 9c c8 78 56 34 12 \tvpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 51 d9 \tvpdpbusds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 51 d9 \tvpdpbusds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 51 d9 \tvpdpbusds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 51 9c c8 78 56 34 12 \tvpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 08 52 d9 \tvdpbf16ps %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6e, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 28 52 d9 \tvdpbf16ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 48 52 d9 \tvdpbf16ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6e 48 52 9c c8 78 56 34 12 \tvdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 52 d9 \tvpdpwssd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 52 d9 \tvpdpwssd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 52 d9 \tvpdpwssd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 52 9c c8 78 56 34 12 \tvpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 52 20 \tvp4dpwssd (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 52 a4 c8 78 56 34 12 \tvp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 53 d9 \tvpdpwssds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 53 d9 \tvpdpwssds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 53 d9 \tvpdpwssds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 53 9c c8 78 56 34 12 \tvpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 53 20 \tvp4dpwssds (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 53 a4 c8 78 56 34 12 \tvp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 54 d1 \tvpopcntb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 54 d1 \tvpopcntb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 54 d1 \tvpopcntb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 54 94 c8 78 56 34 12 \tvpopcntb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 54 d1 \tvpopcntw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 54 d1 \tvpopcntw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 54 d1 \tvpopcntw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 54 94 c8 78 56 34 12 \tvpopcntw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 55 d1 \tvpopcntd %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 55 d1 \tvpopcntd %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 55 d1 \tvpopcntd %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 55 94 c8 78 56 34 12 \tvpopcntd 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 55 d1 \tvpopcntq %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 55 d1 \tvpopcntq %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 55 d1 \tvpopcntq %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 55 94 c8 78 56 34 12 \tvpopcntq 0x12345678(%eax,%ecx,8),%zmm2",}, {{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "", "c4 e2 79 59 f4 \tvpbroadcastq %xmm4,%xmm6",}, {{0x62, 0xf2, 0x7d, 0x48, 0x59, 0xf7, }, 6, 0, "", "", @@ -681,6 +761,38 @@ "62 f2 7d 48 5b 31 \tvbroadcasti32x8 (%ecx),%zmm6",}, {{0x62, 0xf2, 0xfd, 0x48, 0x5b, 0x31, }, 6, 0, "", "", "62 f2 fd 48 5b 31 \tvbroadcasti64x4 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 62 d1 \tvpexpandb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 62 d1 \tvpexpandb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 62 d1 \tvpexpandb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 62 94 c8 78 56 34 12 \tvpexpandb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 62 d1 \tvpexpandw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 62 d1 \tvpexpandw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 62 d1 \tvpexpandw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 62 94 c8 78 56 34 12 \tvpexpandw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 08 63 ca \tvpcompressb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 28 63 ca \tvpcompressb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 48 63 ca \tvpcompressb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 63 94 c8 78 56 34 12 \tvpcompressb %zmm2,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 08 63 ca \tvpcompressw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 28 63 ca \tvpcompressw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 48 63 ca \tvpcompressw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 63 94 c8 78 56 34 12 \tvpcompressw %zmm2,0x12345678(%eax,%ecx,8)",}, {{0x62, 0xf2, 0x55, 0x48, 0x64, 0xf4, }, 6, 0, "", "", "62 f2 55 48 64 f4 \tvpblendmd %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x64, 0xf4, }, 6, 0, "", "", @@ -693,6 +805,86 @@ "62 f2 55 48 66 f4 \tvpblendmb %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x66, 0xf4, }, 6, 0, "", "", "62 f2 d5 48 66 f4 \tvpblendmw %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 68 d9 \tvp2intersectd %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 68 d9 \tvp2intersectd %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 68 d9 \tvp2intersectd %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 68 9c c8 78 56 34 12 \tvp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 08 68 d9 \tvp2intersectq %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 28 68 d9 \tvp2intersectq %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 48 68 d9 \tvp2intersectq %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ef 48 68 9c c8 78 56 34 12 \tvp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 70 d9 \tvpshldvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 70 d9 \tvpshldvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 70 d9 \tvpshldvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 70 9c c8 78 56 34 12 \tvpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 71 d9 \tvpshldvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 71 d9 \tvpshldvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 71 d9 \tvpshldvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 71 9c c8 78 56 34 12 \tvpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 71 d9 \tvpshldvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 71 d9 \tvpshldvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 71 d9 \tvpshldvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 71 9c c8 78 56 34 12 \tvpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 72 d9 \tvcvtne2ps2bf16 %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 72 d9 \tvcvtne2ps2bf16 %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 72 d9 \tvcvtne2ps2bf16 %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 72 9c c8 78 56 34 12 \tvcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7e, 0x08, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 08 72 d1 \tvcvtneps2bf16 %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x28, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 28 72 d1 \tvcvtneps2bf16 %ymm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 48 72 d1 \tvcvtneps2bf16 %zmm1,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7e 48 72 94 c8 78 56 34 12 \tvcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2",}, +{{0x62, 0xf2, 0xed, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 72 d9 \tvpshrdvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 72 d9 \tvpshrdvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 72 d9 \tvpshrdvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 72 9c c8 78 56 34 12 \tvpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 73 d9 \tvpshrdvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 73 d9 \tvpshrdvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 73 d9 \tvpshrdvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 73 9c c8 78 56 34 12 \tvpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 73 d9 \tvpshrdvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 73 d9 \tvpshrdvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 73 d9 \tvpshrdvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 73 9c c8 78 56 34 12 \tvpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0xf2, 0x55, 0x48, 0x75, 0xf4, }, 6, 0, "", "", "62 f2 55 48 75 f4 \tvpermi2b %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x75, 0xf4, }, 6, 0, "", "", @@ -745,6 +937,14 @@ "62 f2 55 48 8d f4 \tvpermb %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x8d, 0xf4, }, 6, 0, "", "", "62 f2 d5 48 8d f4 \tvpermw %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 8f d9 \tvpshufbitqmb %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 8f d9 \tvpshufbitqmb %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 8f d9 \tvpshufbitqmb %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 8f 9c c8 78 56 34 12 \tvpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, {{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", "c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",}, {{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "", @@ -761,6 +961,38 @@ "62 f2 7d 49 91 b4 fd 7b 00 00 00 \tvpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}",}, {{0x62, 0xf2, 0xfd, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 f2 fd 49 91 b4 fd 7b 00 00 00 \tvpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",}, +{{0xc4, 0xe2, 0x69, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9a d9 \tvfmsub132ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 6d 9a d9 \tvfmsub132ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 9a d9 \tvfmsub132ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 9a 9c c8 78 56 34 12 \tvfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9a d9 \tvfmsub132pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 ed 9a d9 \tvfmsub132pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 9a d9 \tvfmsub132pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 9a 9c c8 78 56 34 12 \tvfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 9a 20 \tv4fmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 9a a4 c8 78 56 34 12 \tv4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9b d9 \tvfmsub132ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 9b 9c c8 78 56 34 12 \tvfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9b d9 \tvfmsub132sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 9b 9c c8 78 56 34 12 \tvfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 9b 20 \tv4fmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 9b a4 c8 78 56 34 12 \tv4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0xf2, 0x7d, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 f2 7d 49 a0 b4 fd 7b 00 00 00 \tvpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",}, {{0x62, 0xf2, 0xfd, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", @@ -777,6 +1009,38 @@ "62 f2 7d 49 a3 b4 fd 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}",}, {{0x62, 0xf2, 0xfd, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 f2 fd 49 a3 b4 fd 7b 00 00 00 \tvscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",}, +{{0xc4, 0xe2, 0x69, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 69 aa d9 \tvfmsub213ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 6d aa d9 \tvfmsub213ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 aa d9 \tvfmsub213ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 aa 9c c8 78 56 34 12 \tvfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 aa d9 \tvfmsub213pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 ed aa d9 \tvfmsub213pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 aa d9 \tvfmsub213pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 aa 9c c8 78 56 34 12 \tvfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 aa 20 \tv4fnmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 aa a4 c8 78 56 34 12 \tv4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 69 ab d9 \tvfmsub213ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 ab 9c c8 78 56 34 12 \tvfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 ab d9 \tvfmsub213sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 ab 9c c8 78 56 34 12 \tvfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 ab 20 \tv4fnmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 ab a4 c8 78 56 34 12 \tv4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0xf2, 0xd5, 0x48, 0xb4, 0xf4, }, 6, 0, "", "", "62 f2 d5 48 b4 f4 \tvpmadd52luq %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0xb5, 0xf4, }, 6, 0, "", "", @@ -805,6 +1069,50 @@ "62 f2 4d 0f cd fd \tvrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}",}, {{0x62, 0xf2, 0xcd, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "", "62 f2 cd 0f cd fd \tvrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}",}, +{{0x66, 0x0f, 0x38, 0xcf, 0xd9, }, 5, 0, "", "", +"66 0f 38 cf d9 \tgf2p8mulb %xmm1,%xmm3",}, +{{0x66, 0x0f, 0x38, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"66 0f 38 cf 9c c8 78 56 34 12 \tgf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 cf d9 \tvgf2p8mulb %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d cf d9 \tvgf2p8mulb %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 cf d9 \tvgf2p8mulb %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 cf 9c c8 78 56 34 12 \tvgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dc d9 \tvaesenc %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dc d9 \tvaesenc %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dc d9 \tvaesenc %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dc 9c c8 78 56 34 12 \tvaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dd d9 \tvaesenclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dd d9 \tvaesenclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dd d9 \tvaesenclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dd 9c c8 78 56 34 12 \tvaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 69 de d9 \tvaesdec %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 6d de d9 \tvaesdec %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 de d9 \tvaesdec %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 de 9c c8 78 56 34 12 \tvaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 df d9 \tvaesdeclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d df d9 \tvaesdeclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 df d9 \tvaesdeclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 df 9c c8 78 56 34 12 \tvaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0xf3, 0x4d, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "", "62 f3 4d 48 03 fd 12 \tvalignd $0x12,%zmm5,%zmm6,%zmm7",}, {{0x62, 0xf3, 0xcd, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "", @@ -905,6 +1213,12 @@ "62 f3 4d 48 43 fd 12 \tvshufi32x4 $0x12,%zmm5,%zmm6,%zmm7",}, {{0x62, 0xf3, 0xcd, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "", "62 f3 cd 48 43 fd 12 \tvshufi64x2 $0x12,%zmm5,%zmm6,%zmm7",}, +{{0xc4, 0xe3, 0x69, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 69 44 d9 12 \tvpclmulqdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0x6d, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 6d 44 d9 12 \tvpclmulqdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x44, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 44 d9 12 \tvpclmulqdq $0x12,%zmm1,%zmm2,%zmm3",}, {{0x62, 0xf3, 0x4d, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "", "62 f3 4d 48 50 fd 12 \tvrangeps $0x12,%zmm5,%zmm6,%zmm7",}, {{0x62, 0xf3, 0xcd, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "", @@ -937,6 +1251,58 @@ "62 f3 7d 08 67 ef 12 \tvfpclassss $0x12,%xmm7,%k5",}, {{0x62, 0xf3, 0xfd, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "", "62 f3 fd 08 67 ef 12 \tvfpclasssd $0x12,%xmm7,%k5",}, +{{0x62, 0xf3, 0xed, 0x08, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 70 d9 12 \tvpshldw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 70 d9 12 \tvpshldw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 70 d9 12 \tvpshldw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 71 d9 12 \tvpshldd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 71 d9 12 \tvpshldd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 71 d9 12 \tvpshldd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0xed, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 71 d9 12 \tvpshldq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 71 d9 12 \tvpshldq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 71 d9 12 \tvpshldq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0xed, 0x08, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 72 d9 12 \tvpshrdw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 72 d9 12 \tvpshrdw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 72 d9 12 \tvpshrdw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 73 d9 12 \tvpshrdd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 73 d9 12 \tvpshrdd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 73 d9 12 \tvpshrdd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0xed, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 73 d9 12 \tvpshrdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 73 d9 12 \tvpshrdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 73 d9 12 \tvpshrdq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x66, 0x0f, 0x3a, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a ce d9 12 \tgf2p8affineqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 ce d9 12 \tvgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed ce d9 12 \tvgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xce, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 ce d9 12 \tvgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x66, 0x0f, 0x3a, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a cf d9 12 \tgf2p8affineinvqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 cf d9 12 \tvgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed cf d9 12 \tvgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xcf, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 cf d9 12 \tvgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3",}, {{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "", "62 f1 4d 48 72 c5 12 \tvprord $0x12,%zmm5,%zmm6",}, {{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xc5, 0x12, }, 7, 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 656f8aed31de..567ecccfad7c 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -587,6 +587,112 @@ "62 02 35 07 4f d0 \tvrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}",}, {{0x62, 0x02, 0xb5, 0x07, 0x4f, 0xd0, }, 6, 0, "", "", "62 02 b5 07 4f d0 \tvrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 50 d9 \tvpdpbusd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 50 d9 \tvpdpbusd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 50 d9 \tvpdpbusd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 50 9c c8 78 56 34 12 \tvpdpbusd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x50, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 50 9c c8 78 56 34 12 \tvpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 51 d9 \tvpdpbusds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 51 d9 \tvpdpbusds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 51 d9 \tvpdpbusds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 51 9c c8 78 56 34 12 \tvpdpbusds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x51, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 51 9c c8 78 56 34 12 \tvpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 08 52 d9 \tvdpbf16ps %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6e, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 28 52 d9 \tvdpbf16ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 48 52 d9 \tvdpbf16ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6e 48 52 9c c8 78 56 34 12 \tvdpbf16ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6e, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6e 48 52 9c c8 78 56 34 12 \tvdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 52 d9 \tvpdpwssd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 52 d9 \tvpdpwssd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 52 d9 \tvpdpwssd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 52 9c c8 78 56 34 12 \tvpdpwssd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 52 9c c8 78 56 34 12 \tvpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 52 20 \tvp4dpwssd (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x52, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 52 20 \tvp4dpwssd (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 52 a4 c8 78 56 34 12 \tvp4dpwssd 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x52, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 52 a4 c8 78 56 34 12 \tvp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 53 d9 \tvpdpwssds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 53 d9 \tvpdpwssds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 53 d9 \tvpdpwssds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 53 9c c8 78 56 34 12 \tvpdpwssds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x53, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 53 9c c8 78 56 34 12 \tvpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 53 20 \tvp4dpwssds (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x53, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 53 20 \tvp4dpwssds (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 53 a4 c8 78 56 34 12 \tvp4dpwssds 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x53, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 53 a4 c8 78 56 34 12 \tvp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 54 d1 \tvpopcntb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 54 d1 \tvpopcntb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 54 d1 \tvpopcntb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 54 94 c8 78 56 34 12 \tvpopcntb 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 54 94 c8 78 56 34 12 \tvpopcntb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 54 d1 \tvpopcntw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 54 d1 \tvpopcntw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 54 d1 \tvpopcntw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 54 94 c8 78 56 34 12 \tvpopcntw 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 54 94 c8 78 56 34 12 \tvpopcntw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 55 d1 \tvpopcntd %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 55 d1 \tvpopcntd %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 55 d1 \tvpopcntd %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 55 94 c8 78 56 34 12 \tvpopcntd 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 55 94 c8 78 56 34 12 \tvpopcntd 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 55 d1 \tvpopcntq %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 55 d1 \tvpopcntq %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 55 d1 \tvpopcntq %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 55 94 c8 78 56 34 12 \tvpopcntq 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 55 94 c8 78 56 34 12 \tvpopcntq 0x12345678(%eax,%ecx,8),%zmm2",}, {{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "", "c4 e2 79 59 f4 \tvpbroadcastq %xmm4,%xmm6",}, {{0x62, 0x02, 0x7d, 0x48, 0x59, 0xd3, }, 6, 0, "", "", @@ -601,6 +707,46 @@ "62 62 7d 48 5b 21 \tvbroadcasti32x8 (%rcx),%zmm28",}, {{0x62, 0x62, 0xfd, 0x48, 0x5b, 0x11, }, 6, 0, "", "", "62 62 fd 48 5b 11 \tvbroadcasti64x4 (%rcx),%zmm26",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 62 d1 \tvpexpandb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 62 d1 \tvpexpandb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 62 d1 \tvpexpandb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 62 94 c8 78 56 34 12 \tvpexpandb 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 62 94 c8 78 56 34 12 \tvpexpandb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 62 d1 \tvpexpandw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 62 d1 \tvpexpandw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 62 d1 \tvpexpandw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 62 94 c8 78 56 34 12 \tvpexpandw 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 62 94 c8 78 56 34 12 \tvpexpandw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 08 63 ca \tvpcompressb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 28 63 ca \tvpcompressb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 48 63 ca \tvpcompressb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 63 94 c8 78 56 34 12 \tvpcompressb %zmm2,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 63 94 c8 78 56 34 12 \tvpcompressb %zmm2,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 08 63 ca \tvpcompressw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 28 63 ca \tvpcompressw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 48 63 ca \tvpcompressw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 63 94 c8 78 56 34 12 \tvpcompressw %zmm2,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 63 94 c8 78 56 34 12 \tvpcompressw %zmm2,0x12345678(%eax,%ecx,8)",}, {{0x62, 0x02, 0x25, 0x40, 0x64, 0xe2, }, 6, 0, "", "", "62 02 25 40 64 e2 \tvpblendmd %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0x64, 0xe2, }, 6, 0, "", "", @@ -613,6 +759,106 @@ "62 02 25 40 66 e2 \tvpblendmb %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0x66, 0xe2, }, 6, 0, "", "", "62 02 a5 40 66 e2 \tvpblendmw %zmm26,%zmm27,%zmm28",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 68 d9 \tvp2intersectd %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 68 d9 \tvp2intersectd %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 68 d9 \tvp2intersectd %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 68 9c c8 78 56 34 12 \tvp2intersectd 0x12345678(%rax,%rcx,8),%zmm2,%k3",}, +{{0x67, 0x62, 0xf2, 0x6f, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6f 48 68 9c c8 78 56 34 12 \tvp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 08 68 d9 \tvp2intersectq %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 28 68 d9 \tvp2intersectq %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 48 68 d9 \tvp2intersectq %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ef 48 68 9c c8 78 56 34 12 \tvp2intersectq 0x12345678(%rax,%rcx,8),%zmm2,%k3",}, +{{0x67, 0x62, 0xf2, 0xef, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ef 48 68 9c c8 78 56 34 12 \tvp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 70 d9 \tvpshldvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 70 d9 \tvpshldvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 70 d9 \tvpshldvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 70 9c c8 78 56 34 12 \tvpshldvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x70, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 70 9c c8 78 56 34 12 \tvpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 71 d9 \tvpshldvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 71 d9 \tvpshldvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 71 d9 \tvpshldvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 71 9c c8 78 56 34 12 \tvpshldvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 71 9c c8 78 56 34 12 \tvpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 71 d9 \tvpshldvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 71 d9 \tvpshldvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 71 d9 \tvpshldvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 71 9c c8 78 56 34 12 \tvpshldvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 71 9c c8 78 56 34 12 \tvpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 72 d9 \tvcvtne2ps2bf16 %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 72 d9 \tvcvtne2ps2bf16 %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 72 d9 \tvcvtne2ps2bf16 %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 72 9c c8 78 56 34 12 \tvcvtne2ps2bf16 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6f, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6f 48 72 9c c8 78 56 34 12 \tvcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7e, 0x08, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 08 72 d1 \tvcvtneps2bf16 %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x28, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 28 72 d1 \tvcvtneps2bf16 %ymm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 48 72 d1 \tvcvtneps2bf16 %zmm1,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7e 48 72 94 c8 78 56 34 12 \tvcvtneps2bf16 0x12345678(%rax,%rcx,8),%ymm2",}, +{{0x67, 0x62, 0xf2, 0x7e, 0x48, 0x72, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7e 48 72 94 c8 78 56 34 12 \tvcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2",}, +{{0x62, 0xf2, 0xed, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 72 d9 \tvpshrdvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 72 d9 \tvpshrdvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 72 d9 \tvpshrdvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 72 9c c8 78 56 34 12 \tvpshrdvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 72 9c c8 78 56 34 12 \tvpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 73 d9 \tvpshrdvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 73 d9 \tvpshrdvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 73 d9 \tvpshrdvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 73 9c c8 78 56 34 12 \tvpshrdvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 73 9c c8 78 56 34 12 \tvpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 73 d9 \tvpshrdvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 73 d9 \tvpshrdvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 73 d9 \tvpshrdvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 73 9c c8 78 56 34 12 \tvpshrdvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 73 9c c8 78 56 34 12 \tvpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0x02, 0x35, 0x40, 0x75, 0xd0, }, 6, 0, "", "", "62 02 35 40 75 d0 \tvpermi2b %zmm24,%zmm25,%zmm26",}, {{0x62, 0x02, 0xa5, 0x40, 0x75, 0xe2, }, 6, 0, "", "", @@ -667,6 +913,16 @@ "62 02 25 40 8d e2 \tvpermb %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0x8d, 0xe2, }, 6, 0, "", "", "62 02 a5 40 8d e2 \tvpermw %zmm26,%zmm27,%zmm28",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 8f d9 \tvpshufbitqmb %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 8f d9 \tvpshufbitqmb %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 8f d9 \tvpshufbitqmb %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 8f 9c c8 78 56 34 12 \tvpshufbitqmb 0x12345678(%rax,%rcx,8),%zmm2,%k3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x8f, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 8f 9c c8 78 56 34 12 \tvpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, {{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", "c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",}, {{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "", @@ -683,6 +939,54 @@ "62 22 7d 41 91 94 dd 7b 00 00 00 \tvpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}",}, {{0x62, 0x22, 0xfd, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 22 fd 41 91 94 dd 7b 00 00 00 \tvpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",}, +{{0xc4, 0xe2, 0x69, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9a d9 \tvfmsub132ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 6d 9a d9 \tvfmsub132ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 9a d9 \tvfmsub132ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 9a 9c c8 78 56 34 12 \tvfmsub132ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 9a 9c c8 78 56 34 12 \tvfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9a d9 \tvfmsub132pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 ed 9a d9 \tvfmsub132pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 9a d9 \tvfmsub132pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 9a 9c c8 78 56 34 12 \tvfmsub132pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 9a 9c c8 78 56 34 12 \tvfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 9a 20 \tv4fmaddps (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x9a, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 9a 20 \tv4fmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 9a a4 c8 78 56 34 12 \tv4fmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x9a, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 9a a4 c8 78 56 34 12 \tv4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9b d9 \tvfmsub132ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 9b 9c c8 78 56 34 12 \tvfmsub132ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0x69, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 69 9b 9c c8 78 56 34 12 \tvfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9b d9 \tvfmsub132sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 9b 9c c8 78 56 34 12 \tvfmsub132sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0xe9, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 e9 9b 9c c8 78 56 34 12 \tvfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 9b 20 \tv4fmaddss (%rax),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0x9b, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 08 9b 20 \tv4fmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 9b a4 c8 78 56 34 12 \tv4fmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0x9b, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 08 9b a4 c8 78 56 34 12 \tv4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0x22, 0x7d, 0x41, 0xa0, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 22 7d 41 a0 a4 ed 7b 00 00 00 \tvpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",}, {{0x62, 0x22, 0xfd, 0x41, 0xa0, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", @@ -699,6 +1003,54 @@ "62 b2 7d 41 a3 b4 ed 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}",}, {{0x62, 0x22, 0xfd, 0x41, 0xa3, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 22 fd 41 a3 a4 ed 7b 00 00 00 \tvscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",}, +{{0xc4, 0xe2, 0x69, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 69 aa d9 \tvfmsub213ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 6d aa d9 \tvfmsub213ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 aa d9 \tvfmsub213ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 aa 9c c8 78 56 34 12 \tvfmsub213ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 aa 9c c8 78 56 34 12 \tvfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 aa d9 \tvfmsub213pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 ed aa d9 \tvfmsub213pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 aa d9 \tvfmsub213pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 aa 9c c8 78 56 34 12 \tvfmsub213pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 aa 9c c8 78 56 34 12 \tvfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 aa 20 \tv4fnmaddps (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0xaa, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 aa 20 \tv4fnmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 aa a4 c8 78 56 34 12 \tv4fnmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0xaa, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 aa a4 c8 78 56 34 12 \tv4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 69 ab d9 \tvfmsub213ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 ab 9c c8 78 56 34 12 \tvfmsub213ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0x69, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 69 ab 9c c8 78 56 34 12 \tvfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 ab d9 \tvfmsub213sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 ab 9c c8 78 56 34 12 \tvfmsub213sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0xe9, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 e9 ab 9c c8 78 56 34 12 \tvfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 ab 20 \tv4fnmaddss (%rax),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0xab, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 08 ab 20 \tv4fnmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 ab a4 c8 78 56 34 12 \tv4fnmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0xab, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 08 ab a4 c8 78 56 34 12 \tv4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0x02, 0xa5, 0x40, 0xb4, 0xe2, }, 6, 0, "", "", "62 02 a5 40 b4 e2 \tvpmadd52luq %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0xb5, 0xe2, }, 6, 0, "", "", @@ -727,6 +1079,62 @@ "62 02 15 07 cd f4 \tvrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}",}, {{0x62, 0x02, 0xad, 0x07, 0xcd, 0xd9, }, 6, 0, "", "", "62 02 ad 07 cd d9 \tvrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}",}, +{{0x66, 0x0f, 0x38, 0xcf, 0xd9, }, 5, 0, "", "", +"66 0f 38 cf d9 \tgf2p8mulb %xmm1,%xmm3",}, +{{0x66, 0x0f, 0x38, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"66 0f 38 cf 9c c8 78 56 34 12 \tgf2p8mulb 0x12345678(%rax,%rcx,8),%xmm3",}, +{{0x67, 0x66, 0x0f, 0x38, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 66 0f 38 cf 9c c8 78 56 34 12 \tgf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 cf d9 \tvgf2p8mulb %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d cf d9 \tvgf2p8mulb %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 cf d9 \tvgf2p8mulb %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 cf 9c c8 78 56 34 12 \tvgf2p8mulb 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 cf 9c c8 78 56 34 12 \tvgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dc d9 \tvaesenc %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dc d9 \tvaesenc %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dc d9 \tvaesenc %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dc 9c c8 78 56 34 12 \tvaesenc 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xdc, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 dc 9c c8 78 56 34 12 \tvaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dd d9 \tvaesenclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dd d9 \tvaesenclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dd d9 \tvaesenclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dd 9c c8 78 56 34 12 \tvaesenclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xdd, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 dd 9c c8 78 56 34 12 \tvaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 69 de d9 \tvaesdec %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 6d de d9 \tvaesdec %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 de d9 \tvaesdec %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 de 9c c8 78 56 34 12 \tvaesdec 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xde, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 de 9c c8 78 56 34 12 \tvaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 df d9 \tvaesdeclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d df d9 \tvaesdeclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 df d9 \tvaesdeclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 df 9c c8 78 56 34 12 \tvaesdeclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xdf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 df 9c c8 78 56 34 12 \tvaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0x03, 0x15, 0x40, 0x03, 0xf4, 0x12, }, 7, 0, "", "", "62 03 15 40 03 f4 12 \tvalignd $0x12,%zmm28,%zmm29,%zmm30",}, {{0x62, 0x03, 0xad, 0x40, 0x03, 0xd9, 0x12, }, 7, 0, "", "", @@ -827,6 +1235,14 @@ "62 03 2d 40 43 d9 12 \tvshufi32x4 $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x03, 0x95, 0x40, 0x43, 0xf4, 0x12, }, 7, 0, "", "", "62 03 95 40 43 f4 12 \tvshufi64x2 $0x12,%zmm28,%zmm29,%zmm30",}, +{{0xc4, 0xe3, 0x69, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 69 44 d9 12 \tvpclmulqdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0x6d, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 6d 44 d9 12 \tvpclmulqdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x44, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 44 d9 12 \tvpclmulqdq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0x2d, 0x40, 0x44, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 44 d9 12 \tvpclmulqdq $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x03, 0x2d, 0x40, 0x50, 0xd9, 0x12, }, 7, 0, "", "", "62 03 2d 40 50 d9 12 \tvrangeps $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x03, 0x95, 0x40, 0x50, 0xf4, 0x12, }, 7, 0, "", "", @@ -859,6 +1275,74 @@ "62 93 7d 08 67 eb 12 \tvfpclassss $0x12,%xmm27,%k5",}, {{0x62, 0x93, 0xfd, 0x08, 0x67, 0xee, 0x12, }, 7, 0, "", "", "62 93 fd 08 67 ee 12 \tvfpclasssd $0x12,%xmm30,%k5",}, +{{0x62, 0xf3, 0xed, 0x08, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 70 d9 12 \tvpshldw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 70 d9 12 \tvpshldw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 70 d9 12 \tvpshldw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 70 d9 12 \tvpshldw $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 71 d9 12 \tvpshldd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 71 d9 12 \tvpshldd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 71 d9 12 \tvpshldd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0x2d, 0x40, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 71 d9 12 \tvpshldd $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0xed, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 71 d9 12 \tvpshldq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 71 d9 12 \tvpshldq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 71 d9 12 \tvpshldq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 71 d9 12 \tvpshldq $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0xed, 0x08, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 72 d9 12 \tvpshrdw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 72 d9 12 \tvpshrdw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 72 d9 12 \tvpshrdw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 72 d9 12 \tvpshrdw $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 73 d9 12 \tvpshrdd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 73 d9 12 \tvpshrdd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 73 d9 12 \tvpshrdd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0x2d, 0x40, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 73 d9 12 \tvpshrdd $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0xed, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 73 d9 12 \tvpshrdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 73 d9 12 \tvpshrdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 73 d9 12 \tvpshrdq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 73 d9 12 \tvpshrdq $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x66, 0x0f, 0x3a, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a ce d9 12 \tgf2p8affineqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 ce d9 12 \tvgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed ce d9 12 \tvgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xce, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 ce d9 12 \tvgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0xce, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 ce d9 12 \tvgf2p8affineqb $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x66, 0x0f, 0x3a, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a cf d9 12 \tgf2p8affineinvqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 cf d9 12 \tvgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed cf d9 12 \tvgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xcf, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 cf d9 12 \tvgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0xcf, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 cf d9 12 \tvgf2p8affineinvqb $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x91, 0x2d, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "", "62 91 2d 40 72 c1 12 \tvprord $0x12,%zmm25,%zmm26",}, {{0x62, 0x91, 0xad, 0x40, 0x72, 0xc1, 0x12, }, 7, 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 dd85a3afd9ce..ddbf07c50bb8 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -510,6 +510,82 @@ int main(void) asm volatile("vrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}"); asm volatile("vrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}"); + /* AVX-512: Op code 0f 38 50 */ + + asm volatile("vpdpbusd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 51 */ + + asm volatile("vpdpbusds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 52 */ + + asm volatile("vdpbf16ps %xmm1, %xmm2, %xmm3"); + asm volatile("vdpbf16ps %ymm1, %ymm2, %ymm3"); + asm volatile("vdpbf16ps %zmm1, %zmm2, %zmm3"); + asm volatile("vdpbf16ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpdpwssd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssd (%rax), %zmm0, %zmm4"); + asm volatile("vp4dpwssd (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssd 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("vp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 53 */ + + asm volatile("vpdpwssds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssds (%rax), %zmm0, %zmm4"); + asm volatile("vp4dpwssds (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssds 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("vp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 54 */ + + asm volatile("vpopcntb %xmm1, %xmm2"); + asm volatile("vpopcntb %ymm1, %ymm2"); + asm volatile("vpopcntb %zmm1, %zmm2"); + asm volatile("vpopcntb 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntw %xmm1, %xmm2"); + asm volatile("vpopcntw %ymm1, %ymm2"); + asm volatile("vpopcntw %zmm1, %zmm2"); + asm volatile("vpopcntw 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 55 */ + + asm volatile("vpopcntd %xmm1, %xmm2"); + asm volatile("vpopcntd %ymm1, %ymm2"); + asm volatile("vpopcntd %zmm1, %zmm2"); + asm volatile("vpopcntd 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntd 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntq %xmm1, %xmm2"); + asm volatile("vpopcntq %ymm1, %ymm2"); + asm volatile("vpopcntq %zmm1, %zmm2"); + asm volatile("vpopcntq 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntq 0x12345678(%eax,%ecx,8),%zmm2"); + /* AVX-512: Op code 0f 38 59 */ asm volatile("vpbroadcastq %xmm4,%xmm6"); @@ -526,6 +602,34 @@ int main(void) asm volatile("vbroadcasti32x8 (%rcx),%zmm28"); asm volatile("vbroadcasti64x4 (%rcx),%zmm26"); + /* AVX-512: Op code 0f 38 62 */ + + asm volatile("vpexpandb %xmm1, %xmm2"); + asm volatile("vpexpandb %ymm1, %ymm2"); + asm volatile("vpexpandb %zmm1, %zmm2"); + asm volatile("vpexpandb 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpexpandb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpexpandw %xmm1, %xmm2"); + asm volatile("vpexpandw %ymm1, %ymm2"); + asm volatile("vpexpandw %zmm1, %zmm2"); + asm volatile("vpexpandw 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpexpandw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 63 */ + + asm volatile("vpcompressb %xmm1, %xmm2"); + asm volatile("vpcompressb %ymm1, %ymm2"); + asm volatile("vpcompressb %zmm1, %zmm2"); + asm volatile("vpcompressb %zmm2,0x12345678(%rax,%rcx,8)"); + asm volatile("vpcompressb %zmm2,0x12345678(%eax,%ecx,8)"); + + asm volatile("vpcompressw %xmm1, %xmm2"); + asm volatile("vpcompressw %ymm1, %ymm2"); + asm volatile("vpcompressw %zmm1, %zmm2"); + asm volatile("vpcompressw %zmm2,0x12345678(%rax,%rcx,8)"); + asm volatile("vpcompressw %zmm2,0x12345678(%eax,%ecx,8)"); + /* AVX-512: Op code 0f 38 64 */ asm volatile("vpblendmd %zmm26,%zmm27,%zmm28"); @@ -541,6 +645,76 @@ int main(void) asm volatile("vpblendmb %zmm26,%zmm27,%zmm28"); asm volatile("vpblendmw %zmm26,%zmm27,%zmm28"); + /* AVX-512: Op code 0f 38 68 */ + + asm volatile("vp2intersectd %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectd %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectd %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectd 0x12345678(%rax,%rcx,8),%zmm2,%k3"); + asm volatile("vp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + asm volatile("vp2intersectq %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectq %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectq %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectq 0x12345678(%rax,%rcx,8),%zmm2,%k3"); + asm volatile("vp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + /* AVX-512: Op code 0f 38 70 */ + + asm volatile("vpshldvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 71 */ + + asm volatile("vpshldvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshldvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 72 */ + + asm volatile("vcvtne2ps2bf16 %xmm1, %xmm2, %xmm3"); + asm volatile("vcvtne2ps2bf16 %ymm1, %ymm2, %ymm3"); + asm volatile("vcvtne2ps2bf16 %zmm1, %zmm2, %zmm3"); + asm volatile("vcvtne2ps2bf16 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vcvtneps2bf16 %xmm1, %xmm2"); + asm volatile("vcvtneps2bf16 %ymm1, %xmm2"); + asm volatile("vcvtneps2bf16 %zmm1, %ymm2"); + asm volatile("vcvtneps2bf16 0x12345678(%rax,%rcx,8),%ymm2"); + asm volatile("vcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2"); + + asm volatile("vpshrdvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 73 */ + + asm volatile("vpshrdvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshrdvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 38 75 */ asm volatile("vpermi2b %zmm24,%zmm25,%zmm26"); @@ -613,6 +787,14 @@ int main(void) asm volatile("vpermb %zmm26,%zmm27,%zmm28"); asm volatile("vpermw %zmm26,%zmm27,%zmm28"); + /* AVX-512: Op code 0f 38 8f */ + + asm volatile("vpshufbitqmb %xmm1, %xmm2, %k3"); + asm volatile("vpshufbitqmb %ymm1, %ymm2, %k3"); + asm volatile("vpshufbitqmb %zmm1, %zmm2, %k3"); + asm volatile("vpshufbitqmb 0x12345678(%rax,%rcx,8),%zmm2,%k3"); + asm volatile("vpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + /* AVX-512: Op code 0f 38 90 */ asm volatile("vpgatherdd %xmm2,0x02(%rbp,%xmm7,2),%xmm1"); @@ -627,6 +809,40 @@ int main(void) asm volatile("vpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}"); asm volatile("vpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}"); + /* AVX-512: Op code 0f 38 9a */ + + asm volatile("vfmsub132ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub132pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fmaddps (%rax), %zmm0, %zmm4"); + asm volatile("v4fmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("v4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 9b */ + + asm volatile("vfmsub132ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub132sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fmaddss (%rax), %xmm0, %xmm4"); + asm volatile("v4fmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4"); + asm volatile("v4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 a0 */ asm volatile("vpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}"); @@ -647,6 +863,40 @@ int main(void) asm volatile("vscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}"); asm volatile("vscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}"); + /* AVX-512: Op code 0f 38 aa */ + + asm volatile("vfmsub213ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub213pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fnmaddps (%rax), %zmm0, %zmm4"); + asm volatile("v4fnmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fnmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("v4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 ab */ + + asm volatile("vfmsub213ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub213sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fnmaddss (%rax), %xmm0, %xmm4"); + asm volatile("v4fnmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fnmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4"); + asm volatile("v4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 b4 */ asm volatile("vpmadd52luq %zmm26,%zmm27,%zmm28"); @@ -685,6 +935,50 @@ int main(void) asm volatile("vrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}"); asm volatile("vrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}"); + /* AVX-512: Op code 0f 38 cf */ + + asm volatile("gf2p8mulb %xmm1, %xmm3"); + asm volatile("gf2p8mulb 0x12345678(%rax,%rcx,8),%xmm3"); + asm volatile("gf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3"); + + asm volatile("vgf2p8mulb %xmm1, %xmm2, %xmm3"); + asm volatile("vgf2p8mulb %ymm1, %ymm2, %ymm3"); + asm volatile("vgf2p8mulb %zmm1, %zmm2, %zmm3"); + asm volatile("vgf2p8mulb 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dc */ + + asm volatile("vaesenc %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenc %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenc %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenc 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dd */ + + asm volatile("vaesenclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 de */ + + asm volatile("vaesdec %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdec %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdec %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdec 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 df */ + + asm volatile("vaesdeclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdeclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdeclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdeclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 3a 03 */ asm volatile("valignd $0x12,%zmm28,%zmm29,%zmm30"); @@ -804,6 +1098,13 @@ int main(void) asm volatile("vshufi32x4 $0x12,%zmm25,%zmm26,%zmm27"); asm volatile("vshufi64x2 $0x12,%zmm28,%zmm29,%zmm30"); + /* AVX-512: Op code 0f 3a 44 */ + + asm volatile("vpclmulqdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpclmulqdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpclmulqdq $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpclmulqdq $0x12,%zmm25,%zmm26,%zmm27"); + /* AVX-512: Op code 0f 3a 50 */ asm volatile("vrangeps $0x12,%zmm25,%zmm26,%zmm27"); @@ -844,6 +1145,62 @@ int main(void) asm volatile("vfpclassss $0x12,%xmm27,%k5"); asm volatile("vfpclasssd $0x12,%xmm30,%k5"); + /* AVX-512: Op code 0f 3a 70 */ + + asm volatile("vpshldw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldw $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshldw $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 71 */ + + asm volatile("vpshldd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldd $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshldd $0x12,%zmm25,%zmm26,%zmm27"); + + asm volatile("vpshldq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldq $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshldq $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 72 */ + + asm volatile("vpshrdw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdw $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshrdw $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 73 */ + + asm volatile("vpshrdd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdd $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshrdd $0x12,%zmm25,%zmm26,%zmm27"); + + asm volatile("vpshrdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdq $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshrdq $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a ce */ + + asm volatile("gf2p8affineqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vgf2p8affineqb $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a cf */ + + asm volatile("gf2p8affineinvqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vgf2p8affineinvqb $0x12,%zmm25,%zmm26,%zmm27"); + /* AVX-512: Op code 0f 72 (Grp13) */ asm volatile("vprord $0x12,%zmm25,%zmm26"); @@ -1946,6 +2303,69 @@ int main(void) asm volatile("vrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}"); asm volatile("vrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}"); + /* AVX-512: Op code 0f 38 50 */ + + asm volatile("vpdpbusd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 51 */ + + asm volatile("vpdpbusds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 52 */ + + asm volatile("vdpbf16ps %xmm1, %xmm2, %xmm3"); + asm volatile("vdpbf16ps %ymm1, %ymm2, %ymm3"); + asm volatile("vdpbf16ps %zmm1, %zmm2, %zmm3"); + asm volatile("vdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpdpwssd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssd (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 53 */ + + asm volatile("vpdpwssds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssds (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 54 */ + + asm volatile("vpopcntb %xmm1, %xmm2"); + asm volatile("vpopcntb %ymm1, %ymm2"); + asm volatile("vpopcntb %zmm1, %zmm2"); + asm volatile("vpopcntb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntw %xmm1, %xmm2"); + asm volatile("vpopcntw %ymm1, %ymm2"); + asm volatile("vpopcntw %zmm1, %zmm2"); + asm volatile("vpopcntw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 55 */ + + asm volatile("vpopcntd %xmm1, %xmm2"); + asm volatile("vpopcntd %ymm1, %ymm2"); + asm volatile("vpopcntd %zmm1, %zmm2"); + asm volatile("vpopcntd 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntq %xmm1, %xmm2"); + asm volatile("vpopcntq %ymm1, %ymm2"); + asm volatile("vpopcntq %zmm1, %zmm2"); + asm volatile("vpopcntq 0x12345678(%eax,%ecx,8),%zmm2"); + /* AVX-512: Op code 0f 38 59 */ asm volatile("vpbroadcastq %xmm4,%xmm6"); @@ -1962,6 +2382,30 @@ int main(void) asm volatile("vbroadcasti32x8 (%ecx),%zmm6"); asm volatile("vbroadcasti64x4 (%ecx),%zmm6"); + /* AVX-512: Op code 0f 38 62 */ + + asm volatile("vpexpandb %xmm1, %xmm2"); + asm volatile("vpexpandb %ymm1, %ymm2"); + asm volatile("vpexpandb %zmm1, %zmm2"); + asm volatile("vpexpandb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpexpandw %xmm1, %xmm2"); + asm volatile("vpexpandw %ymm1, %ymm2"); + asm volatile("vpexpandw %zmm1, %zmm2"); + asm volatile("vpexpandw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 63 */ + + asm volatile("vpcompressb %xmm1, %xmm2"); + asm volatile("vpcompressb %ymm1, %ymm2"); + asm volatile("vpcompressb %zmm1, %zmm2"); + asm volatile("vpcompressb %zmm2,0x12345678(%eax,%ecx,8)"); + + asm volatile("vpcompressw %xmm1, %xmm2"); + asm volatile("vpcompressw %ymm1, %ymm2"); + asm volatile("vpcompressw %zmm1, %zmm2"); + asm volatile("vpcompressw %zmm2,0x12345678(%eax,%ecx,8)"); + /* AVX-512: Op code 0f 38 64 */ asm volatile("vpblendmd %zmm4,%zmm5,%zmm6"); @@ -1977,6 +2421,66 @@ int main(void) asm volatile("vpblendmb %zmm4,%zmm5,%zmm6"); asm volatile("vpblendmw %zmm4,%zmm5,%zmm6"); + /* AVX-512: Op code 0f 38 68 */ + + asm volatile("vp2intersectd %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectd %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectd %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + asm volatile("vp2intersectq %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectq %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectq %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + /* AVX-512: Op code 0f 38 70 */ + + asm volatile("vpshldvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 71 */ + + asm volatile("vpshldvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshldvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 72 */ + + asm volatile("vcvtne2ps2bf16 %xmm1, %xmm2, %xmm3"); + asm volatile("vcvtne2ps2bf16 %ymm1, %ymm2, %ymm3"); + asm volatile("vcvtne2ps2bf16 %zmm1, %zmm2, %zmm3"); + asm volatile("vcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vcvtneps2bf16 %xmm1, %xmm2"); + asm volatile("vcvtneps2bf16 %ymm1, %xmm2"); + asm volatile("vcvtneps2bf16 %zmm1, %ymm2"); + asm volatile("vcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2"); + + asm volatile("vpshrdvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 73 */ + + asm volatile("vpshrdvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshrdvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 38 75 */ asm volatile("vpermi2b %zmm4,%zmm5,%zmm6"); @@ -2048,6 +2552,13 @@ int main(void) asm volatile("vpermb %zmm4,%zmm5,%zmm6"); asm volatile("vpermw %zmm4,%zmm5,%zmm6"); + /* AVX-512: Op code 0f 38 8f */ + + asm volatile("vpshufbitqmb %xmm1, %xmm2, %k3"); + asm volatile("vpshufbitqmb %ymm1, %ymm2, %k3"); + asm volatile("vpshufbitqmb %zmm1, %zmm2, %k3"); + asm volatile("vpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + /* AVX-512: Op code 0f 38 90 */ asm volatile("vpgatherdd %xmm2,0x02(%ebp,%xmm7,2),%xmm1"); @@ -2062,6 +2573,32 @@ int main(void) asm volatile("vpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}"); asm volatile("vpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}"); + /* AVX-512: Op code 0f 38 9a */ + + asm volatile("vfmsub132ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub132pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 9b */ + + asm volatile("vfmsub132ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub132sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 a0 */ asm volatile("vpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}"); @@ -2082,6 +2619,32 @@ int main(void) asm volatile("vscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}"); asm volatile("vscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}"); + /* AVX-512: Op code 0f 38 aa */ + + asm volatile("vfmsub213ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub213pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fnmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 ab */ + + asm volatile("vfmsub213ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub213sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fnmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 b4 */ asm volatile("vpmadd52luq %zmm4,%zmm5,%zmm6"); @@ -2120,6 +2683,44 @@ int main(void) asm volatile("vrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}"); asm volatile("vrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}"); + /* AVX-512: Op code 0f 38 cf */ + + asm volatile("gf2p8mulb %xmm1, %xmm3"); + asm volatile("gf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3"); + + asm volatile("vgf2p8mulb %xmm1, %xmm2, %xmm3"); + asm volatile("vgf2p8mulb %ymm1, %ymm2, %ymm3"); + asm volatile("vgf2p8mulb %zmm1, %zmm2, %zmm3"); + asm volatile("vgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dc */ + + asm volatile("vaesenc %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenc %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenc %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dd */ + + asm volatile("vaesenclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 de */ + + asm volatile("vaesdec %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdec %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdec %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 df */ + + asm volatile("vaesdeclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdeclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdeclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 3a 03 */ asm volatile("valignd $0x12,%zmm5,%zmm6,%zmm7"); @@ -2239,6 +2840,12 @@ int main(void) asm volatile("vshufi32x4 $0x12,%zmm5,%zmm6,%zmm7"); asm volatile("vshufi64x2 $0x12,%zmm5,%zmm6,%zmm7"); + /* AVX-512: Op code 0f 3a 44 */ + + asm volatile("vpclmulqdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpclmulqdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpclmulqdq $0x12,%zmm1,%zmm2,%zmm3"); + /* AVX-512: Op code 0f 3a 50 */ asm volatile("vrangeps $0x12,%zmm5,%zmm6,%zmm7"); @@ -2279,6 +2886,54 @@ int main(void) asm volatile("vfpclassss $0x12,%xmm7,%k5"); asm volatile("vfpclasssd $0x12,%xmm7,%k5"); + /* AVX-512: Op code 0f 3a 70 */ + + asm volatile("vpshldw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldw $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a 71 */ + + asm volatile("vpshldd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldd $0x12,%zmm1,%zmm2,%zmm3"); + + asm volatile("vpshldq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldq $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a 72 */ + + asm volatile("vpshrdw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdw $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a 73 */ + + asm volatile("vpshrdd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdd $0x12,%zmm1,%zmm2,%zmm3"); + + asm volatile("vpshrdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdq $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a ce */ + + asm volatile("gf2p8affineqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a cf */ + + asm volatile("gf2p8affineinvqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3"); + /* AVX-512: Op code 0f 72 (Grp13) */ asm volatile("vprord $0x12,%zmm5,%zmm6"); diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S index bbe5a0d16e51..80f14f52e3f6 100644 --- a/tools/perf/arch/x86/tests/regs_load.S +++ b/tools/perf/arch/x86/tests/regs_load.S @@ -28,7 +28,7 @@ .text #ifdef HAVE_ARCH_X86_64_SUPPORT -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) movq %rax, AX(%rdi) movq %rbx, BX(%rdi) movq %rcx, CX(%rdi) @@ -60,9 +60,9 @@ ENTRY(perf_regs_load) movq %r14, R14(%rdi) movq %r15, R15(%rdi) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) #else -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) push %edi movl 8(%esp), %edi movl %eax, AX(%edi) @@ -88,7 +88,7 @@ ENTRY(perf_regs_load) movl $0, FS(%edi) movl $0, GS(%edi) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) #endif /* diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index d1044df7c0d7..ac45015cc6ba 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -18,8 +18,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, { int rc = 0; struct map *pos; - struct map_groups *kmaps = &machine->kmaps; - struct maps *maps = &kmaps->maps; + struct maps *kmaps = &machine->kmaps; union perf_event *event = zalloc(sizeof(event->mmap) + machine->id_hdr_size); @@ -29,7 +28,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, return -1; } - maps__for_each_entry(maps, pos) { + maps__for_each_entry(kmaps, pos) { struct kmap *kmap; size_t size; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 376dbf10ad64..f8b6ae557d8b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -547,8 +547,8 @@ static int64_t block_cycles_diff_cmp(struct hist_entry *left, if (!pairs_left && !pairs_right) return 0; - l = labs(left->diff.cycles); - r = labs(right->diff.cycles); + l = llabs(left->diff.cycles); + r = llabs(right->diff.cycles); return r - l; } @@ -646,7 +646,7 @@ static void compute_cycles_diff(struct hist_entry *he, if (i >= he->block_info->num || i >= NUM_SPARKS) break; - val = labs(pair->block_info->cycles_spark[i] - + val = llabs(pair->block_info->cycles_spark[i] - he->block_info->cycles_spark[i]); update_spark_value(pair->diff.svals, NUM_SPARKS, diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 9664a72a089d..7e124a7b8bfd 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -403,17 +403,6 @@ static int perf_event__repipe_tracing_data(struct perf_session *session, return err; } -static int perf_event__repipe_id_index(struct perf_session *session, - union perf_event *event) -{ - int err; - - perf_event__repipe_synth(session->tool, event); - err = perf_event__process_id_index(session, event); - - return err; -} - static int dso__read_build_id(struct dso *dso) { if (dso->has_build_id) @@ -651,7 +640,7 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.comm = perf_event__repipe_comm; inject->tool.namespaces = perf_event__repipe_namespaces; inject->tool.exit = perf_event__repipe_exit; - inject->tool.id_index = perf_event__repipe_id_index; + inject->tool.id_index = perf_event__process_id_index; inject->tool.auxtrace_info = perf_event__process_auxtrace_info; inject->tool.auxtrace = perf_event__process_auxtrace; inject->tool.aux = perf_event__drop_aux; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index b5063d3b6fd0..fb19ef63cc35 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -832,7 +832,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && pos->leader != pos && pos->weak_group) { - pos = perf_evlist__reset_weak_group(evlist, pos); + pos = perf_evlist__reset_weak_group(evlist, pos, true); goto try_again; } rc = -errno; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ab0f6e516b03..387311c67264 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -388,6 +388,14 @@ static int report__setup_sample_type(struct report *rep) } } + if (sort__mode == SORT_MODE__MEMORY) { + if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) { + ui__error("Selected --mem-mode but no mem data. " + "Did you call perf record without -d?\n"); + return -1; + } + } + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { if ((sample_type & PERF_SAMPLE_REGS_USER) && (sample_type & PERF_SAMPLE_STACK_USER)) { @@ -780,11 +788,6 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) return printed; } -static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp) -{ - return maps__fprintf_task(&mg->maps, indent, fp); -} - static void task__print_level(struct task *task, FILE *fp, int level) { struct thread *thread = task->thread; @@ -795,7 +798,7 @@ static void task__print_level(struct task *task, FILE *fp, int level) fprintf(fp, "%s\n", thread__comm_str(thread)); - map_groups__fprintf_task(thread->mg, comm_indent, fp); + maps__fprintf_task(thread->maps, comm_indent, fp); if (!list_empty(&task->children)) { list_for_each_entry(child, &task->children, list) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index f86c5cce5b2c..e2406b291c1c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -448,7 +448,7 @@ static int perf_evsel__check_attr(struct evsel *evsel, "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - if (PRINT_FIELD(BRSTACKINSN) && + if (PRINT_FIELD(BRSTACKINSN) && !allow_user_set && !(perf_evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) { pr_err("Display of branch stack assembler requested, but non all-branch filter set\n" @@ -932,6 +932,48 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return len; } +static int map__fprintf_srccode(struct map *map, u64 addr, FILE *fp, struct srccode_state *state) +{ + char *srcfile; + int ret = 0; + unsigned line; + int len; + char *srccode; + + if (!map || !map->dso) + return 0; + srcfile = get_srcline_split(map->dso, + map__rip_2objdump(map, addr), + &line); + if (!srcfile) + return 0; + + /* Avoid redundant printing */ + if (state && + state->srcfile && + !strcmp(state->srcfile, srcfile) && + state->line == line) { + free(srcfile); + return 0; + } + + srccode = find_sourceline(srcfile, line, &len); + if (!srccode) + goto out_free_line; + + ret = fprintf(fp, "|%-8d %.*s", line, len, srccode); + + if (state) { + state->srcfile = srcfile; + state->line = line; + } + return ret; + +out_free_line: + free(srcfile); + return ret; +} + static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr) { struct addr_location al; @@ -1084,7 +1126,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, insn++; } } - if (off != (unsigned)len) + if (off != end - start) printed += fprintf(fp, "\tmismatch of LBR data and executable\n"); } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0a15253b438c..a098c2ebf4ea 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -65,6 +65,7 @@ #include "util/target.h" #include "util/time-utils.h" #include "util/top.h" +#include "util/affinity.h" #include "asm/bug.h" #include <linux/time64.h> @@ -265,15 +266,10 @@ static int read_single_counter(struct evsel *counter, int cpu, * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter(struct evsel *counter, struct timespec *rs) +static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) { int nthreads = perf_thread_map__nr(evsel_list->core.threads); - int ncpus, cpu, thread; - - if (target__has_cpu(&target) && !target__has_per_thread(&target)) - ncpus = perf_evsel__nr_cpus(counter); - else - ncpus = 1; + int thread; if (!counter->supported) return -ENOENT; @@ -282,40 +278,38 @@ static int read_counter(struct evsel *counter, struct timespec *rs) nthreads = 1; for (thread = 0; thread < nthreads; thread++) { - for (cpu = 0; cpu < ncpus; cpu++) { - struct perf_counts_values *count; - - count = perf_counts(counter->counts, cpu, thread); - - /* - * The leader's group read loads data into its group members - * (via perf_evsel__read_counter) and sets threir count->loaded. - */ - if (!perf_counts__is_loaded(counter->counts, cpu, thread) && - read_single_counter(counter, cpu, thread, rs)) { - counter->counts->scaled = -1; - perf_counts(counter->counts, cpu, thread)->ena = 0; - perf_counts(counter->counts, cpu, thread)->run = 0; - return -1; - } + struct perf_counts_values *count; - perf_counts__set_loaded(counter->counts, cpu, thread, false); + count = perf_counts(counter->counts, cpu, thread); - if (STAT_RECORD) { - if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { - pr_err("failed to write stat event\n"); - return -1; - } - } + /* + * The leader's group read loads data into its group members + * (via perf_evsel__read_counter()) and sets their count->loaded. + */ + if (!perf_counts__is_loaded(counter->counts, cpu, thread) && + read_single_counter(counter, cpu, thread, rs)) { + counter->counts->scaled = -1; + perf_counts(counter->counts, cpu, thread)->ena = 0; + perf_counts(counter->counts, cpu, thread)->run = 0; + return -1; + } + + perf_counts__set_loaded(counter->counts, cpu, thread, false); - if (verbose > 1) { - fprintf(stat_config.output, - "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", - perf_evsel__name(counter), - cpu, - count->val, count->ena, count->run); + if (STAT_RECORD) { + if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { + pr_err("failed to write stat event\n"); + return -1; } } + + if (verbose > 1) { + fprintf(stat_config.output, + "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", + perf_evsel__name(counter), + cpu, + count->val, count->ena, count->run); + } } return 0; @@ -324,15 +318,37 @@ static int read_counter(struct evsel *counter, struct timespec *rs) static void read_counters(struct timespec *rs) { struct evsel *counter; - int ret; + struct affinity affinity; + int i, ncpus, cpu; + + if (affinity__setup(&affinity) < 0) + return; + + ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus); + if (!target__has_cpu(&target) || target__has_per_thread(&target)) + ncpus = 1; + evlist__for_each_cpu(evsel_list, i, cpu) { + if (i >= ncpus) + break; + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evsel_list, counter) { + if (evsel__cpu_iter_skip(counter, cpu)) + continue; + if (!counter->err) { + counter->err = read_counter_cpu(counter, rs, + counter->cpu_iter - 1); + } + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evsel_list, counter) { - ret = read_counter(counter, rs); - if (ret) + if (counter->err) pr_debug("failed to read counter %s\n", counter->name); - - if (ret == 0 && perf_stat_process_counter(&stat_config, counter)) + if (counter->err == 0 && perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); + counter->err = 0; } } @@ -420,6 +436,62 @@ static bool is_target_alive(struct target *_target, return false; } +enum counter_recovery { + COUNTER_SKIP, + COUNTER_RETRY, + COUNTER_FATAL, +}; + +static enum counter_recovery stat_handle_error(struct evsel *counter) +{ + char msg[BUFSIZ]; + /* + * PPC returns ENXIO for HW counters until 2.6.37 + * (behavior changed with commit b0a873e). + */ + if (errno == EINVAL || errno == ENOSYS || + errno == ENOENT || errno == EOPNOTSUPP || + errno == ENXIO) { + if (verbose > 0) + ui__warning("%s event is not supported by the kernel.\n", + perf_evsel__name(counter)); + counter->supported = false; + /* + * errored is a sticky flag that means one of the counter's + * cpu event had a problem and needs to be reexamined. + */ + counter->errored = true; + + if ((counter->leader != counter) || + !(counter->leader->core.nr_members > 1)) + return COUNTER_SKIP; + } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { + if (verbose > 0) + ui__warning("%s\n", msg); + return COUNTER_RETRY; + } else if (target__has_per_thread(&target) && + evsel_list->core.threads && + evsel_list->core.threads->err_thread != -1) { + /* + * For global --per-thread case, skip current + * error thread. + */ + if (!thread_map__remove(evsel_list->core.threads, + evsel_list->core.threads->err_thread)) { + evsel_list->core.threads->err_thread = -1; + return COUNTER_RETRY; + } + } + + perf_evsel__open_strerror(counter, &target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); + + if (child_pid != -1) + kill(child_pid, SIGTERM); + return COUNTER_FATAL; +} + static int __run_perf_stat(int argc, const char **argv, int run_idx) { int interval = stat_config.interval; @@ -433,6 +505,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) int status = 0; const bool forks = (argc > 0); bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false; + struct affinity affinity; + int i, cpu; + bool second_pass = false; if (interval) { ts.tv_sec = interval / USEC_PER_MSEC; @@ -457,61 +532,104 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (group) perf_evlist__set_leader(evsel_list); - evlist__for_each_entry(evsel_list, counter) { + if (affinity__setup(&affinity) < 0) + return -1; + + evlist__for_each_cpu (evsel_list, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evsel_list, counter) { + if (evsel__cpu_iter_skip(counter, cpu)) + continue; + if (counter->reset_group || counter->errored) + continue; try_again: - if (create_perf_stat_counter(counter, &stat_config, &target) < 0) { - - /* Weak group failed. Reset the group. */ - if ((errno == EINVAL || errno == EBADF) && - counter->leader != counter && - counter->weak_group) { - counter = perf_evlist__reset_weak_group(evsel_list, counter); - goto try_again; - } + if (create_perf_stat_counter(counter, &stat_config, &target, + counter->cpu_iter - 1) < 0) { - /* - * PPC returns ENXIO for HW counters until 2.6.37 - * (behavior changed with commit b0a873e). - */ - if (errno == EINVAL || errno == ENOSYS || - errno == ENOENT || errno == EOPNOTSUPP || - errno == ENXIO) { - if (verbose > 0) - ui__warning("%s event is not supported by the kernel.\n", - perf_evsel__name(counter)); - counter->supported = false; - - if ((counter->leader != counter) || - !(counter->leader->core.nr_members > 1)) - continue; - } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { - if (verbose > 0) - ui__warning("%s\n", msg); - goto try_again; - } else if (target__has_per_thread(&target) && - evsel_list->core.threads && - evsel_list->core.threads->err_thread != -1) { /* - * For global --per-thread case, skip current - * error thread. + * Weak group failed. We cannot just undo this here + * because earlier CPUs might be in group mode, and the kernel + * doesn't support mixing group and non group reads. Defer + * it to later. + * Don't close here because we're in the wrong affinity. */ - if (!thread_map__remove(evsel_list->core.threads, - evsel_list->core.threads->err_thread)) { - evsel_list->core.threads->err_thread = -1; + if ((errno == EINVAL || errno == EBADF) && + counter->leader != counter && + counter->weak_group) { + perf_evlist__reset_weak_group(evsel_list, counter, false); + assert(counter->reset_group); + second_pass = true; + continue; + } + + switch (stat_handle_error(counter)) { + case COUNTER_FATAL: + return -1; + case COUNTER_RETRY: goto try_again; + case COUNTER_SKIP: + continue; + default: + break; } + } + counter->supported = true; + } + } - perf_evsel__open_strerror(counter, &target, - errno, msg, sizeof(msg)); - ui__error("%s\n", msg); + if (second_pass) { + /* + * Now redo all the weak group after closing them, + * and also close errored counters. + */ - if (child_pid != -1) - kill(child_pid, SIGTERM); + evlist__for_each_cpu(evsel_list, i, cpu) { + affinity__set(&affinity, cpu); + /* First close errored or weak retry */ + evlist__for_each_entry(evsel_list, counter) { + if (!counter->reset_group && !counter->errored) + continue; + if (evsel__cpu_iter_skip_no_inc(counter, cpu)) + continue; + perf_evsel__close_cpu(&counter->core, counter->cpu_iter); + } + /* Now reopen weak */ + evlist__for_each_entry(evsel_list, counter) { + if (!counter->reset_group && !counter->errored) + continue; + if (evsel__cpu_iter_skip(counter, cpu)) + continue; + if (!counter->reset_group) + continue; +try_again_reset: + pr_debug2("reopening weak %s\n", perf_evsel__name(counter)); + if (create_perf_stat_counter(counter, &stat_config, &target, + counter->cpu_iter - 1) < 0) { + + switch (stat_handle_error(counter)) { + case COUNTER_FATAL: + return -1; + case COUNTER_RETRY: + goto try_again_reset; + case COUNTER_SKIP: + continue; + default: + break; + } + } + counter->supported = true; + } + } + } + affinity__cleanup(&affinity); - return -1; + evlist__for_each_entry(evsel_list, counter) { + if (!counter->supported) { + perf_evsel__free_fd(&counter->core); + continue; } - counter->supported = true; l = strlen(counter->unit); if (l > stat_config.unit_width) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index dc80044bc46f..795e353de095 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1568,9 +1568,13 @@ int cmd_top(int argc, const char **argv) */ status = perf_env__read_cpuid(&perf_env); if (status) { - pr_err("Couldn't read the cpuid for this machine: %s\n", - str_error_r(errno, errbuf, sizeof(errbuf))); - goto out_delete_evlist; + /* + * Some arches do not provide a get_cpuid(), so just use pr_debug, otherwise + * warn the user explicitely. + */ + eprintf(status == ENOSYS ? 1 : 0, verbose, + "Couldn't read the cpuid for this machine: %s\n", + str_error_r(errno, errbuf, sizeof(errbuf))); } top.evlist->env = &perf_env; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index a1dc16724352..68039a96c1dc 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -110,8 +110,8 @@ for i in $FILES; do done # diff with extra ignore lines -check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' -check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' +check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"' +check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' check include/linux/ctype.h '-I "isdigit("' diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c index 2ca1fafa620d..f93f4e703e4c 100644 --- a/tools/perf/lib/cpumap.c +++ b/tools/perf/lib/cpumap.c @@ -68,14 +68,28 @@ static struct perf_cpu_map *cpu_map__default_new(void) return cpus; } +static int cmp_int(const void *a, const void *b) +{ + return *(const int *)a - *(const int*)b; +} + static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) { size_t payload_size = nr_cpus * sizeof(int); struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); + int i, j; if (cpus != NULL) { - cpus->nr = nr_cpus; memcpy(cpus->map, tmp_cpus, payload_size); + qsort(cpus->map, nr_cpus, sizeof(int), cmp_int); + /* Remove dups */ + j = 0; + for (i = 0; i < nr_cpus; i++) { + if (i == 0 || cpus->map[i] != cpus->map[i - 1]) + cpus->map[j++] = cpus->map[i]; + } + cpus->nr = j; + assert(j <= nr_cpus); refcount_set(&cpus->refcnt, 1); } @@ -272,3 +286,60 @@ int perf_cpu_map__max(struct perf_cpu_map *map) return max; } + +/* + * Merge two cpumaps + * + * orig either gets freed and replaced with a new map, or reused + * with no reference count change (similar to "realloc") + * other has its reference count increased. + */ + +struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other) +{ + int *tmp_cpus; + int tmp_len; + int i, j, k; + struct perf_cpu_map *merged; + + if (!orig && !other) + return NULL; + if (!orig) { + perf_cpu_map__get(other); + return other; + } + if (!other) + return orig; + if (orig->nr == other->nr && + !memcmp(orig->map, other->map, orig->nr * sizeof(int))) + return orig; + + tmp_len = orig->nr + other->nr; + tmp_cpus = malloc(tmp_len * sizeof(int)); + if (!tmp_cpus) + return NULL; + + /* Standard merge algorithm from wikipedia */ + i = j = k = 0; + while (i < orig->nr && j < other->nr) { + if (orig->map[i] <= other->map[j]) { + if (orig->map[i] == other->map[j]) + j++; + tmp_cpus[k++] = orig->map[i++]; + } else + tmp_cpus[k++] = other->map[j++]; + } + + while (i < orig->nr) + tmp_cpus[k++] = orig->map[i++]; + + while (j < other->nr) + tmp_cpus[k++] = other->map[j++]; + assert(k <= tmp_len); + + merged = cpu_map__trim_new(k, tmp_cpus); + free(tmp_cpus); + perf_cpu_map__put(orig); + return merged; +} diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c index 205ddbb80bc1..ae9e65aa2491 100644 --- a/tools/perf/lib/evlist.c +++ b/tools/perf/lib/evlist.c @@ -54,6 +54,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, perf_thread_map__put(evsel->threads); evsel->threads = perf_thread_map__get(evlist->threads); + evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus); } static void perf_evlist__propagate_maps(struct perf_evlist *evlist) diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c index 5a89857b0381..4dc06289f4c7 100644 --- a/tools/perf/lib/evsel.c +++ b/tools/perf/lib/evsel.c @@ -114,16 +114,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, return err; } +static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) +{ + int thread; + + for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { + if (FD(evsel, cpu, thread) >= 0) + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } +} + void perf_evsel__close_fd(struct perf_evsel *evsel) { - int cpu, thread; + int cpu; for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) - for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - if (FD(evsel, cpu, thread) >= 0) - close(FD(evsel, cpu, thread)); - FD(evsel, cpu, thread) = -1; - } + perf_evsel__close_fd_cpu(evsel, cpu); } void perf_evsel__free_fd(struct perf_evsel *evsel) @@ -141,6 +148,14 @@ void perf_evsel__close(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); } +void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd_cpu(evsel, cpu); +} + int perf_evsel__read_size(struct perf_evsel *evsel) { u64 read_format = evsel->attr.read_format; @@ -183,38 +198,61 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, } static int perf_evsel__run_ioctl(struct perf_evsel *evsel, - int ioc, void *arg) + int ioc, void *arg, + int cpu) { - int cpu, thread; + int thread; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { - for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread), - err = ioctl(fd, ioc, arg); + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { + int fd = FD(evsel, cpu, thread), + err = ioctl(fd, ioc, arg); - if (err) - return err; - } + if (err) + return err; } return 0; } +int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu); +} + int perf_evsel__enable(struct perf_evsel *evsel) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0); + int i; + int err = 0; + + for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, i); + return err; +} + +int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu); } int perf_evsel__disable(struct perf_evsel *evsel) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0); + int i; + int err = 0; + + for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, i); + return err; } int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) { - return perf_evsel__run_ioctl(evsel, + int err = 0, i; + + for (i = 0; i < evsel->cpus->nr && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_SET_FILTER, - (void *)filter); + (void *)filter, i); + return err; } struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h index a2fbccf1922f..74dc8c3f0b66 100644 --- a/tools/perf/lib/include/internal/evlist.h +++ b/tools/perf/lib/include/internal/evlist.h @@ -18,6 +18,7 @@ struct perf_evlist { int nr_entries; bool has_user_cpus; struct perf_cpu_map *cpus; + struct perf_cpu_map *all_cpus; struct perf_thread_map *threads; int nr_mmaps; size_t mmap_len; diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h index ac9aa497f84a..6a17ad730cbc 100644 --- a/tools/perf/lib/include/perf/cpumap.h +++ b/tools/perf/lib/include/perf/cpumap.h @@ -12,6 +12,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file); LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other); LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h index 557f5815a9c9..c82ec39a4ad0 100644 --- a/tools/perf/lib/include/perf/evsel.h +++ b/tools/perf/lib/include/perf/evsel.h @@ -26,10 +26,13 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel); +LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 436ce33f1182..5da8296b667e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -32,7 +32,7 @@ "EventCode": "132", "EventName": "DTLB1_GPAGE_WRITES", "BriefDescription": "DTLB1 Two-Gigabyte Page Writes", - "PublicDescription": "Counter:132 Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index 68618152ea2c..89e070727e1b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -4,7 +4,7 @@ "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", - "PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index bc7151d639d7..45a34ce4fe89 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -297,7 +297,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index 49c5f123d811..961fe4395758 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -115,7 +115,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 113d19e92678..746734ce09be 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -297,7 +297,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 2ba32af9bc36..f94653229dd4 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -315,7 +315,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index c80f16fde6d0..5402cd3120f9 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -267,7 +267,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index e501729c3dd1..832f3cb40b34 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -267,7 +267,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index e2446966b651..d69b2a8fc0bc 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -285,7 +285,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 9294769dec64..5f465fd81315 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -285,7 +285,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index 603ff9c2e9a1..3e909b306003 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -171,7 +171,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index c6b485b3a2cb..50c053235752 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -171,7 +171,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 0ca539bb60f6..e7feb60f9fa9 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -303,7 +303,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 047d7e11aa6f..21d7a0c2c2e8 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -315,7 +315,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index e72accefd669..1692529639b0 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -27,7 +27,7 @@ perf-y += wp.o perf-y += task-exit.o perf-y += sw-clock.o perf-y += mmap-thread-lookup.o -perf-y += thread-mg-share.o +perf-y += thread-maps-share.o perf-y += switch-tracking.o perf-y += keep-tracking.o perf-y += code-reading.o @@ -52,8 +52,9 @@ perf-y += perf-hooks.o perf-y += clang.o perf-y += unit_number__scnprintf.o perf-y += mem2node.o -perf-y += map_groups.o +perf-y += maps.o perf-y += time-utils-test.o +perf-y += genelf.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 8b286e9b7549..5f05db75cdd8 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -166,8 +166,8 @@ static struct test generic_tests[] = { .func = test__mmap_thread_lookup, }, { - .desc = "Share thread mg", - .func = test__thread_mg_share, + .desc = "Share thread maps", + .func = test__thread_maps_share, }, { .desc = "Sort output of hist entries", @@ -260,6 +260,11 @@ static struct test generic_tests[] = { .func = test__cpu_map_print, }, { + .desc = "Merge cpu map", + .func = test__cpu_map_merge, + }, + + { .desc = "Probe SDT events", .func = test__sdt_event, }, @@ -297,8 +302,12 @@ static struct test generic_tests[] = { .func = test__time_utils, }, { - .desc = "map_groups__merge_in", - .func = test__map_groups__merge_in, + .desc = "Test jit_write_elf", + .func = test__jit_write_elf, + }, + { + .desc = "maps__merge_in", + .func = test__maps__merge_in, }, { .func = NULL, diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 1f017e1b2a55..6fe221d31f07 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -276,7 +276,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, len = al.map->end - addr; /* Read the object code using perf */ - ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine, + ret_len = dso__data_read_offset(al.map->dso, thread->maps->machine, al.addr, buf1, len); if (ret_len != len) { pr_debug("dso__data_read_offset failed\n"); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 8a0d236202b0..4ac56741ac5f 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -120,3 +120,19 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40")); return 0; } + +int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused) +{ + struct perf_cpu_map *a = perf_cpu_map__new("4,2,1"); + struct perf_cpu_map *b = perf_cpu_map__new("4,5,7"); + struct perf_cpu_map *c = perf_cpu_map__merge(a, b); + char buf[100]; + + TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5); + cpu_map__snprint(c, buf, sizeof(buf)); + TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7")); + perf_cpu_map__put(a); + perf_cpu_map__put(b); + perf_cpu_map__put(c); + return 0; +} diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 1ee8704e2284..1e8a9f5c356d 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -125,7 +125,7 @@ static int attach__cpu_disabled(struct evlist *evlist) evsel->core.attr.disabled = 1; - err = perf_evsel__open_per_cpu(evsel, cpus); + err = perf_evsel__open_per_cpu(evsel, cpus, -1); if (err) { if (err == -EACCES) return TEST_SKIP; @@ -152,7 +152,7 @@ static int attach__cpu_enabled(struct evlist *evlist) return -1; } - err = perf_evsel__open_per_cpu(evsel, cpus); + err = perf_evsel__open_per_cpu(evsel, cpus, -1); if (err == -EACCES) return TEST_SKIP; diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c new file mode 100644 index 000000000000..f797f9823e89 --- /dev/null +++ b/tools/perf/tests/genelf.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <limits.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <linux/compiler.h> + +#include "debug.h" +#include "tests.h" + +#ifdef HAVE_JITDUMP +#include <libelf.h> +#include "../util/genelf.h" +#endif + +#define TEMPL "/tmp/perf-test-XXXXXX" + +int test__jit_write_elf(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ +#ifdef HAVE_JITDUMP + static unsigned char x86_code[] = { + 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */ + 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */ + 0xCD, 0x80 /* int $0x80 */ + }; + char path[PATH_MAX]; + int fd, ret; + + strcpy(path, TEMPL); + + fd = mkstemp(path); + if (fd < 0) { + perror("mkstemp failed"); + return TEST_FAIL; + } + + pr_info("Writing jit code to: %s\n", path); + + ret = jit_write_elf(fd, 0, "main", x86_code, sizeof(x86_code), + NULL, 0, NULL, 0, 0); + close(fd); + + unlink(path); + + return ret ? TEST_FAIL : 0; +#else + return TEST_SKIP; +#endif +} diff --git a/tools/perf/tests/map_groups.c b/tools/perf/tests/maps.c index 6b9f1cdcbe5b..edcbc70ff9d6 100644 --- a/tools/perf/tests/map_groups.c +++ b/tools/perf/tests/maps.c @@ -3,7 +3,7 @@ #include <linux/kernel.h> #include "tests.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "dso.h" #include "debug.h" @@ -13,12 +13,12 @@ struct map_def { u64 end; }; -static int check_maps(struct map_def *merged, unsigned int size, struct map_groups *mg) +static int check_maps(struct map_def *merged, unsigned int size, struct maps *maps) { struct map *map; unsigned int i = 0; - map_groups__for_each_entry(mg, map) { + maps__for_each_entry(maps, map) { if (i > 0) TEST_ASSERT_VAL("less maps expected", (map && i < size) || (!map && i == size)); @@ -33,9 +33,9 @@ static int check_maps(struct map_def *merged, unsigned int size, struct map_grou return TEST_OK; } -int test__map_groups__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused) +int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused) { - struct map_groups mg; + struct maps maps; unsigned int i; struct map_def bpf_progs[] = { { "bpf_prog_1", 200, 300 }, @@ -64,7 +64,7 @@ int test__map_groups__merge_in(struct test *t __maybe_unused, int subtest __mayb struct map *map_kcore1, *map_kcore2, *map_kcore3; int ret; - map_groups__init(&mg, NULL); + maps__init(&maps, NULL); for (i = 0; i < ARRAY_SIZE(bpf_progs); i++) { struct map *map; @@ -74,7 +74,7 @@ int test__map_groups__merge_in(struct test *t __maybe_unused, int subtest __mayb map->start = bpf_progs[i].start; map->end = bpf_progs[i].end; - map_groups__insert(&mg, map); + maps__insert(&maps, map); map__put(map); } @@ -99,22 +99,22 @@ int test__map_groups__merge_in(struct test *t __maybe_unused, int subtest __mayb map_kcore3->start = 880; map_kcore3->end = 1100; - ret = map_groups__merge_in(&mg, map_kcore1); + ret = maps__merge_in(&maps, map_kcore1); TEST_ASSERT_VAL("failed to merge map", !ret); - ret = check_maps(merged12, ARRAY_SIZE(merged12), &mg); + ret = check_maps(merged12, ARRAY_SIZE(merged12), &maps); TEST_ASSERT_VAL("merge check failed", !ret); - ret = map_groups__merge_in(&mg, map_kcore2); + ret = maps__merge_in(&maps, map_kcore2); TEST_ASSERT_VAL("failed to merge map", !ret); - ret = check_maps(merged12, ARRAY_SIZE(merged12), &mg); + ret = check_maps(merged12, ARRAY_SIZE(merged12), &maps); TEST_ASSERT_VAL("merge check failed", !ret); - ret = map_groups__merge_in(&mg, map_kcore3); + ret = maps__merge_in(&maps, map_kcore3); TEST_ASSERT_VAL("failed to merge map", !ret); - ret = check_maps(merged3, ARRAY_SIZE(merged3), &mg); + ret = check_maps(merged3, ARRAY_SIZE(merged3), &maps); TEST_ASSERT_VAL("merge check failed", !ret); return TEST_OK; } diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 9837b6e93023..9a160fef47c9 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -73,7 +73,7 @@ int test__dwarf_unwind(struct test *test, int subtest); int test__expr(struct test *test, int subtest); int test__hists_filter(struct test *test, int subtest); int test__mmap_thread_lookup(struct test *test, int subtest); -int test__thread_mg_share(struct test *test, int subtest); +int test__thread_maps_share(struct test *test, int subtest); int test__hists_output(struct test *test, int subtest); int test__hists_cumulate(struct test *test, int subtest); int test__switch_tracking(struct test *test, int subtest); @@ -98,6 +98,7 @@ int test__event_update(struct test *test, int subtest); int test__event_times(struct test *test, int subtest); int test__backward_ring_buffer(struct test *test, int subtest); int test__cpu_map_print(struct test *test, int subtest); +int test__cpu_map_merge(struct test *test, int subtest); int test__sdt_event(struct test *test, int subtest); int test__is_printable_array(struct test *test, int subtest); int test__bitmap_print(struct test *test, int subtest); @@ -107,8 +108,9 @@ const char *test__clang_subtest_get_desc(int subtest); int test__clang_subtest_get_nr(void); int test__unit_number__scnprint(struct test *test, int subtest); int test__mem2node(struct test *t, int subtest); -int test__map_groups__merge_in(struct test *t, int subtest); +int test__maps__merge_in(struct test *t, int subtest); int test__time_utils(struct test *t, int subtest); +int test__jit_write_elf(struct test *test, int subtest); bool test__bp_signal_is_supported(void); bool test__bp_account_is_supported(void); diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-maps-share.c index cbac71716dec..9371484973f2 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -4,7 +4,7 @@ #include "thread.h" #include "debug.h" -int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__thread_maps_share(struct test *test __maybe_unused, int subtest __maybe_unused) { struct machines machines; struct machine *machine; @@ -12,16 +12,16 @@ int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_ /* thread group */ struct thread *leader; struct thread *t1, *t2, *t3; - struct map_groups *mg; + struct maps *maps; /* other process */ struct thread *other, *other_leader; - struct map_groups *other_mg; + struct maps *other_maps; /* * This test create 2 processes abstractions (struct thread) * with several threads and checks they properly share and - * maintain map groups info (struct map_groups). + * maintain maps info (struct maps). * * thread group (pid: 0, tids: 0, 1, 2, 3) * other group (pid: 4, tids: 4, 5) @@ -42,17 +42,17 @@ int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_ TEST_ASSERT_VAL("failed to create threads", leader && t1 && t2 && t3 && other); - mg = leader->mg; - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 4); + maps = leader->maps; + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 4); - /* test the map groups pointer is shared */ - TEST_ASSERT_VAL("map groups don't match", mg == t1->mg); - TEST_ASSERT_VAL("map groups don't match", mg == t2->mg); - TEST_ASSERT_VAL("map groups don't match", mg == t3->mg); + /* test the maps pointer is shared */ + TEST_ASSERT_VAL("maps don't match", maps == t1->maps); + TEST_ASSERT_VAL("maps don't match", maps == t2->maps); + TEST_ASSERT_VAL("maps don't match", maps == t3->maps); /* * Verify the other leader was created by previous call. - * It should have shared map groups with no change in + * It should have shared maps with no change in * refcnt. */ other_leader = machine__find_thread(machine, 4, 4); @@ -70,26 +70,26 @@ int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_ machine__remove_thread(machine, other); machine__remove_thread(machine, other_leader); - other_mg = other->mg; - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 2); + other_maps = other->maps; + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_maps->refcnt), 2); - TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg); + TEST_ASSERT_VAL("maps don't match", other_maps == other_leader->maps); /* release thread group */ thread__put(leader); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 3); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 3); thread__put(t1); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 2); thread__put(t2); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 1); thread__put(t3); /* release other group */ thread__put(other_leader); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_maps->refcnt), 1); thread__put(other); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index ff649078da9a..193b7c91b4e2 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -190,10 +190,9 @@ next_pair: * so use the short name, less descriptive but the same ("[kernel]" in * both cases. */ - pair = map_groups__find_by_name(&kallsyms.kmaps, - (map->dso->kernel ? - map->dso->short_name : - map->dso->name)); + pair = maps__find_by_name(&kallsyms.kmaps, (map->dso->kernel ? + map->dso->short_name : + map->dso->name)); if (pair) { pair->priv = 1; } else { @@ -213,7 +212,7 @@ next_pair: mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start); mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end); - pair = map_groups__find(&kallsyms.kmaps, mem_start); + pair = maps__find(&kallsyms.kmaps, mem_start); if (pair == NULL || pair->priv) continue; diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c index 1a8d3be2030e..062ca849c8fd 100644 --- a/tools/perf/trace/beauty/clone.c +++ b/tools/perf/trace/beauty/clone.c @@ -45,6 +45,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size, P_FLAG(NEWPID); P_FLAG(NEWNET); P_FLAG(IO); + P_FLAG(CLEAR_SIGHAND); #undef P_FLAG if (flags) diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 992705c78bd0..badbddbb30f8 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -430,7 +430,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, return true; } - target_ms.mg = ms->mg; + target_ms.maps = ms->maps; target_ms.map = ms->map; target_ms.sym = dl->ops.target.sym; pthread_mutex_unlock(¬es->lock); diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 132056c7d5b7..2ab2af4d4849 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -8,7 +8,7 @@ #include "../../util/event.h" #include "../../util/hist.h" #include "../../util/map.h" -#include "../../util/map_groups.h" +#include "../../util/maps.h" #include "../../util/symbol.h" #include "../../util/sort.h" #include "../../util/evsel.h" @@ -885,7 +885,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, } if (h->ms.map == NULL && verbose > 1) { - map_groups__fprintf(h->thread->mg, fp); + maps__fprintf(h->thread->maps, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index b8e05a147b2b..07da6c790b63 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -49,6 +49,7 @@ perf-y += header.o perf-y += callchain.o perf-y += values.o perf-y += debug.o +perf-y += fncache.o perf-y += machine.o perf-y += map.o perf-y += pstack.o @@ -76,6 +77,7 @@ perf-y += sort.o perf-y += hist.o perf-y += util.o perf-y += cpumap.o +perf-y += affinity.o perf-y += cputopo.o perf-y += cgroup.o perf-y += target.o diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c new file mode 100644 index 000000000000..a5e31f826828 --- /dev/null +++ b/tools/perf/util/affinity.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Manage affinity to optimize IPIs inside the kernel perf API. */ +#define _GNU_SOURCE 1 +#include <sched.h> +#include <stdlib.h> +#include <linux/bitmap.h> +#include <linux/zalloc.h> +#include "perf.h" +#include "cpumap.h" +#include "affinity.h" + +static int get_cpu_set_size(void) +{ + int sz = cpu__max_cpu() + 8 - 1; + /* + * sched_getaffinity doesn't like masks smaller than the kernel. + * Hopefully that's big enough. + */ + if (sz < 4096) + sz = 4096; + return sz / 8; +} + +int affinity__setup(struct affinity *a) +{ + int cpu_set_size = get_cpu_set_size(); + + a->orig_cpus = bitmap_alloc(cpu_set_size * 8); + if (!a->orig_cpus) + return -1; + sched_getaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus); + a->sched_cpus = bitmap_alloc(cpu_set_size * 8); + if (!a->sched_cpus) { + zfree(&a->orig_cpus); + return -1; + } + bitmap_zero((unsigned long *)a->sched_cpus, cpu_set_size); + a->changed = false; + return 0; +} + +/* + * perf_event_open does an IPI internally to the target CPU. + * It is more efficient to change perf's affinity to the target + * CPU and then set up all events on that CPU, so we amortize + * CPU communication. + */ +void affinity__set(struct affinity *a, int cpu) +{ + int cpu_set_size = get_cpu_set_size(); + + if (cpu == -1) + return; + a->changed = true; + set_bit(cpu, a->sched_cpus); + /* + * We ignore errors because affinity is just an optimization. + * This could happen for example with isolated CPUs or cpusets. + * In this case the IPIs inside the kernel's perf API still work. + */ + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->sched_cpus); + clear_bit(cpu, a->sched_cpus); +} + +void affinity__cleanup(struct affinity *a) +{ + int cpu_set_size = get_cpu_set_size(); + + if (a->changed) + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus); + zfree(&a->sched_cpus); + zfree(&a->orig_cpus); +} diff --git a/tools/perf/util/affinity.h b/tools/perf/util/affinity.h new file mode 100644 index 000000000000..0ad6a18ef20c --- /dev/null +++ b/tools/perf/util/affinity.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef PERF_AFFINITY_H +#define PERF_AFFINITY_H 1 + +#include <stdbool.h> + +struct affinity { + unsigned long *orig_cpus; + unsigned long *sched_cpus; + bool changed; +}; + +void affinity__cleanup(struct affinity *a); +void affinity__set(struct affinity *a, int cpu); +int affinity__setup(struct affinity *a); + +#endif // PERF_AFFINITY_H diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 5ea9a4534848..f5e77ed237e8 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -23,7 +23,7 @@ #include "dso.h" #include "env.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "symbol.h" #include "srcline.h" #include "units.h" @@ -271,7 +271,7 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s find_target: target.addr = map__objdump_2mem(map, ops->target.addr); - if (map_groups__find_ams(ms->mg, &target) == 0 && + if (maps__find_ams(ms->maps, &target) == 0 && map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; @@ -391,7 +391,7 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * Actual navigation will come next, with further understanding of how * the symbol searching and disassembly should be done. */ - if (map_groups__find_ams(ms->mg, &target) == 0 && + if (maps__find_ams(ms->maps, &target) == 0 && map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; @@ -1545,7 +1545,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, .ms = { .map = map, }, }; - if (!map_groups__find_ams(args->ms.mg, &target) && + if (!maps__find_ams(args->ms.maps, &target) && target.ms.sym->start == target.al_addr) dl->ops.target.sym = target.ms.sym; } diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index f7ed5d122e22..a3207d900339 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -52,9 +52,7 @@ static int machine__process_bpf_event_load(struct machine *machine, for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) { u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms); u64 addr = addrs[i]; - struct map *map; - - map = map_groups__find(&machine->kmaps, addr); + struct map *map = maps__find(&machine->kmaps, addr); if (map) { map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 5cefce33b66b..818aa4efd386 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1106,7 +1106,7 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { - al->mg = node->ms.mg; + al->maps = node->ms.maps; al->map = node->ms.map; al->sym = node->ms.sym; al->srcline = node->srcline; @@ -1119,8 +1119,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * goto out; } - if (al->mg == &al->mg->machine->kmaps) { - if (machine__is_host(al->mg->machine)) { + if (al->maps == &al->maps->machine->kmaps) { + if (machine__is_host(al->maps->machine)) { al->cpumode = PERF_RECORD_MISC_KERNEL; al->level = 'k'; } else { @@ -1128,7 +1128,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * al->level = 'g'; } } else { - if (machine__is_host(al->mg->machine)) { + if (machine__is_host(al->maps->machine)) { al->cpumode = PERF_RECORD_MISC_USER; al->level = '.'; } else if (perf_guest) { diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 57943f3685f8..3a442f021468 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -63,4 +63,5 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index f5f855fff412..5471045ebf5c 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2569,7 +2569,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread; - if (thread__init_map_groups(etm->unknown_thread, etm->machine)) { + if (thread__init_maps(etm->unknown_thread, etm->machine)) { err = -ENOMEM; goto err_delete_thread; } diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index d029faf9fc9f..db7447154622 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -181,7 +181,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, if (al->map) { struct dso *dso = al->map->dso; - err = db_export__dso(dbe, dso, al->mg->machine); + err = db_export__dso(dbe, dso, al->maps->machine); if (err) return err; *dso_db_id = dso->db_id; @@ -251,7 +251,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, */ al.sym = node->ms.sym; al.map = node->ms.map; - al.mg = thread->mg; + al.maps = thread->maps; al.addr = node->ip; if (al.map && !al.sym) @@ -360,13 +360,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, if (err) return err; - err = db_export__machine(dbe, al->mg->machine); + err = db_export__machine(dbe, al->maps->machine); if (err) return err; - main_thread = thread__main_thread(al->mg->machine, thread); + main_thread = thread__main_thread(al->maps->machine, thread); - err = db_export__threads(dbe, thread, main_thread, al->mg->machine, &comm); + err = db_export__threads(dbe, thread, main_thread, al->maps->machine, &comm); if (err) goto out_put; @@ -380,7 +380,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, goto out_put; if (dbe->cpr) { - struct call_path *cp = call_path_from_sample(dbe, al->mg->machine, + struct call_path *cp = call_path_from_sample(dbe, al->maps->machine, thread, sample, evsel); if (cp) { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 0141b26bae47..c5447ff516a2 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -457,11 +457,11 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { - struct map_groups *mg = thread->mg; - struct machine *machine = mg->machine; + struct maps *maps = thread->maps; + struct machine *machine = maps->machine; bool load_map = false; - al->mg = mg; + al->maps = maps; al->thread = thread; al->addr = addr; al->cpumode = cpumode; @@ -474,13 +474,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - al->mg = mg = &machine->kmaps; + al->maps = maps = &machine->kmaps; load_map = true; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; - al->mg = mg = &machine->kmaps; + al->maps = maps = &machine->kmaps; load_map = true; } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) { al->level = 'u'; @@ -500,7 +500,7 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return NULL; } - al->map = map_groups__find(mg, al->addr); + al->map = maps__find(maps, al->addr); if (al->map != NULL) { /* * Kernel maps might be changed when loading symbols so loading @@ -523,7 +523,7 @@ struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { struct map *map = thread__find_map(thread, cpumode, addr, al); - struct machine *machine = thread->mg->machine; + struct machine *machine = thread->maps->machine; u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr); if (map || addr_cpumode == cpumode) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index fdce590d2278..1548237b6558 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -18,6 +18,7 @@ #include "debug.h" #include "units.h" #include <internal/lib.h> // page_size +#include "affinity.h" #include "../perf.h" #include "asm/bug.h" #include "bpf-event.h" @@ -342,14 +343,63 @@ static int perf_evlist__nr_threads(struct evlist *evlist, return perf_thread_map__nr(evlist->core.threads); } +void evlist__cpu_iter_start(struct evlist *evlist) +{ + struct evsel *pos; + + /* + * Reset the per evsel cpu_iter. This is needed because + * each evsel's cpumap may have a different index space, + * and some operations need the index to modify + * the FD xyarray (e.g. open, close) + */ + evlist__for_each_entry(evlist, pos) + pos->cpu_iter = 0; +} + +bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu) +{ + if (ev->cpu_iter >= ev->core.cpus->nr) + return true; + if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu) + return true; + return false; +} + +bool evsel__cpu_iter_skip(struct evsel *ev, int cpu) +{ + if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) { + ev->cpu_iter++; + return false; + } + return true; +} + void evlist__disable(struct evlist *evlist) { struct evsel *pos; + struct affinity affinity; + int cpu, i; + + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evlist, pos) { + if (evsel__cpu_iter_skip(pos, cpu)) + continue; + if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__disable_cpu(pos, pos->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { - if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd) + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - evsel__disable(pos); + pos->disabled = true; } evlist->enabled = false; @@ -358,11 +408,28 @@ void evlist__disable(struct evlist *evlist) void evlist__enable(struct evlist *evlist) { struct evsel *pos; + struct affinity affinity; + int cpu, i; + + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evlist, pos) { + if (evsel__cpu_iter_skip(pos, cpu)) + continue; + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__enable_cpu(pos, pos->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - evsel__enable(pos); + pos->disabled = false; } evlist->enabled = true; @@ -1137,9 +1204,35 @@ void perf_evlist__set_selected(struct evlist *evlist, void evlist__close(struct evlist *evlist) { struct evsel *evsel; + struct affinity affinity; + int cpu, i; - evlist__for_each_entry_reverse(evlist, evsel) - evsel__close(evsel); + /* + * With perf record core.cpus is usually NULL. + * Use the old method to handle this for now. + */ + if (!evlist->core.cpus) { + evlist__for_each_entry_reverse(evlist, evsel) + evsel__close(evsel); + return; + } + + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry_reverse(evlist, evsel) { + if (evsel__cpu_iter_skip(evsel, cpu)) + continue; + perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); + evlist__for_each_entry_reverse(evlist, evsel) { + perf_evsel__free_fd(&evsel->core); + perf_evsel__free_id(&evsel->core); + } } static int perf_evlist__create_syswide_maps(struct evlist *evlist) @@ -1577,7 +1670,8 @@ void perf_evlist__force_leader(struct evlist *evlist) } struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, - struct evsel *evsel) + struct evsel *evsel, + bool close) { struct evsel *c2, *leader; bool is_open = true; @@ -1594,10 +1688,15 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, if (c2 == evsel) is_open = false; if (c2->leader == leader) { - if (is_open) + if (is_open && close) perf_evsel__close(&c2->core); c2->leader = c2; c2->core.nr_members = 0; + /* + * Set this for all former members of the group + * to indicate they get reopened. + */ + c2->reset_group = true; } } return leader; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 3655b9ebb147..f5bd5c386df1 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -334,9 +334,17 @@ void perf_evlist__to_front(struct evlist *evlist, #define evlist__for_each_entry_safe(evlist, tmp, evsel) \ __evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel) +#define evlist__for_each_cpu(evlist, index, cpu) \ + evlist__cpu_iter_start(evlist); \ + perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) + void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); +void evlist__cpu_iter_start(struct evlist *evlist); +bool evsel__cpu_iter_skip(struct evsel *ev, int cpu); +bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu); + struct evsel * perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str); @@ -348,5 +356,6 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist); void perf_evlist__force_leader(struct evlist *evlist); struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, - struct evsel *evsel); + struct evsel *evsel, + bool close); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f4dea055b080..a69e64236120 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1223,16 +1223,27 @@ int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter) return perf_evsel__append_filter(evsel, "%s,%s", filter); } +/* Caller has to clear disabled after going through all CPUs. */ +int evsel__enable_cpu(struct evsel *evsel, int cpu) +{ + return perf_evsel__enable_cpu(&evsel->core, cpu); +} + int evsel__enable(struct evsel *evsel) { int err = perf_evsel__enable(&evsel->core); if (!err) evsel->disabled = false; - return err; } +/* Caller has to set disabled after going through all CPUs. */ +int evsel__disable_cpu(struct evsel *evsel, int cpu) +{ + return perf_evsel__disable_cpu(&evsel->core, cpu); +} + int evsel__disable(struct evsel *evsel) { int err = perf_evsel__disable(&evsel->core); @@ -1587,8 +1598,9 @@ static int perf_event_open(struct evsel *evsel, return fd; } -int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, - struct perf_thread_map *threads) +static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads, + int start_cpu, int end_cpu) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; @@ -1665,7 +1677,7 @@ retry_sample_id: display_attr(&evsel->core.attr); - for (cpu = 0; cpu < cpus->nr; cpu++) { + for (cpu = start_cpu; cpu < end_cpu; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; @@ -1843,6 +1855,12 @@ out_close: return err; } +int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1); +} + void evsel__close(struct evsel *evsel) { perf_evsel__close(&evsel->core); @@ -1850,9 +1868,14 @@ void evsel__close(struct evsel *evsel) } int perf_evsel__open_per_cpu(struct evsel *evsel, - struct perf_cpu_map *cpus) + struct perf_cpu_map *cpus, + int cpu) { - return evsel__open(evsel, cpus, NULL); + if (cpu == -1) + return evsel__open_cpu(evsel, cpus, NULL, 0, + cpus ? cpus->nr : 1); + + return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1); } int perf_evsel__open_per_thread(struct evsel *evsel, diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index ddc5ee6f6592..dc14f4a823cd 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -86,6 +86,7 @@ struct evsel { struct list_head config_terms; struct bpf_object *bpf_obj; int bpf_fd; + int err; bool auto_merge_stats; bool merged_stat; const char * metric_expr; @@ -94,7 +95,10 @@ struct evsel { struct evsel *metric_leader; bool collect_stat; bool weak_group; + bool reset_group; + bool errored; bool percore; + int cpu_iter; const char *pmu_name; struct { perf_evsel__sb_cb_t *cb; @@ -218,11 +222,14 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter); int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter); int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter); +int evsel__enable_cpu(struct evsel *evsel, int cpu); int evsel__enable(struct evsel *evsel); int evsel__disable(struct evsel *evsel); +int evsel__disable_cpu(struct evsel *evsel, int cpu); int perf_evsel__open_per_cpu(struct evsel *evsel, - struct perf_cpu_map *cpus); + struct perf_cpu_map *cpus, + int cpu); int perf_evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads); int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, diff --git a/tools/perf/util/fncache.c b/tools/perf/util/fncache.c new file mode 100644 index 000000000000..6225cbc52310 --- /dev/null +++ b/tools/perf/util/fncache.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Manage a cache of file names' existence */ +#include <stdlib.h> +#include <unistd.h> +#include <string.h> +#include <linux/list.h> +#include "fncache.h" + +struct fncache { + struct hlist_node nd; + bool res; + char name[]; +}; + +#define FNHSIZE 61 + +static struct hlist_head fncache_hash[FNHSIZE]; + +unsigned shash(const unsigned char *s) +{ + unsigned h = 0; + while (*s) + h = 65599 * h + *s++; + return h ^ (h >> 16); +} + +static bool lookup_fncache(const char *name, bool *res) +{ + int h = shash((const unsigned char *)name) % FNHSIZE; + struct fncache *n; + + hlist_for_each_entry(n, &fncache_hash[h], nd) { + if (!strcmp(n->name, name)) { + *res = n->res; + return true; + } + } + return false; +} + +static void update_fncache(const char *name, bool res) +{ + struct fncache *n = malloc(sizeof(struct fncache) + strlen(name) + 1); + int h = shash((const unsigned char *)name) % FNHSIZE; + + if (!n) + return; + strcpy(n->name, name); + n->res = res; + hlist_add_head(&n->nd, &fncache_hash[h]); +} + +/* No LRU, only use when bounded in some other way. */ +bool file_available(const char *name) +{ + bool res; + + if (lookup_fncache(name, &res)) + return res; + res = access(name, R_OK) == 0; + update_fncache(name, res); + return res; +} diff --git a/tools/perf/util/fncache.h b/tools/perf/util/fncache.h new file mode 100644 index 000000000000..fe020beaefb1 --- /dev/null +++ b/tools/perf/util/fncache.h @@ -0,0 +1,7 @@ +#ifndef _FCACHE_H +#define _FCACHE_H 1 + +unsigned shash(const unsigned char *s); +bool file_available(const char *name); + +#endif diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index f9f18b8b1df9..aed49806a09b 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -8,15 +8,12 @@ */ #include <sys/types.h> -#include <stdio.h> -#include <getopt.h> #include <stddef.h> #include <libelf.h> #include <string.h> #include <stdlib.h> #include <unistd.h> #include <inttypes.h> -#include <limits.h> #include <fcntl.h> #include <err.h> #ifdef HAVE_DWARF_SUPPORT @@ -31,8 +28,6 @@ #define NT_GNU_BUILD_ID 3 #endif -#define JVMTI - #define BUILD_ID_URANDOM /* different uuid for each run */ #ifdef HAVE_LIBCRYPTO @@ -511,44 +506,3 @@ error: return retval; } - -#ifndef JVMTI - -static unsigned char x86_code[] = { - 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */ - 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */ - 0xCD, 0x80 /* int $0x80 */ -}; - -static struct options options; - -int main(int argc, char **argv) -{ - int c, fd, ret; - - while ((c = getopt(argc, argv, "o:h")) != -1) { - switch (c) { - case 'o': - options.output = optarg; - break; - case 'h': - printf("Usage: genelf -o output_file [-h]\n"); - return 0; - default: - errx(1, "unknown option"); - } - } - - fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666); - if (fd == -1) - err(1, "cannot create file %s", options.output); - - ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code)); - close(fd); - - if (ret != 0) - unlink(options.output); - - return ret; -} -#endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index becc2d109423..93ad27830e2b 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -850,7 +850,7 @@ int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) */ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) { - return -1; + return ENOSYS; /* Not implemented */ } static int write_cpuid(struct feat_fd *ff, @@ -1089,21 +1089,18 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); } -static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) +#define MAX_CACHE_LVL 4 + +static int build_caches(struct cpu_cache_level caches[], u32 *cntp) { u32 i, cnt = 0; - long ncpus; u32 nr, cpu; u16 level; - ncpus = sysconf(_SC_NPROCESSORS_CONF); - if (ncpus < 0) - return -1; - - nr = (u32)(ncpus & UINT_MAX); + nr = cpu__max_cpu(); for (cpu = 0; cpu < nr; cpu++) { - for (level = 0; level < 10; level++) { + for (level = 0; level < MAX_CACHE_LVL; level++) { struct cpu_cache_level c; int err; @@ -1123,18 +1120,12 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) caches[cnt++] = c; else cpu_cache_level__free(&c); - - if (WARN_ONCE(cnt == size, "way too many cpu caches..")) - goto out; } } - out: *cntp = cnt; return 0; } -#define MAX_CACHE_LVL 4 - static int write_cache(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { @@ -1143,7 +1134,7 @@ static int write_cache(struct feat_fd *ff, u32 cnt = 0, i, version = 1; int ret; - ret = build_caches(caches, max_caches, &cnt); + ret = build_caches(caches, &cnt); if (ret) goto out; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0a8d72ae93ca..ca5a8f4d007e 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -692,7 +692,7 @@ __hists__add_entry(struct hists *hists, .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, }, .ms = { - .mg = al->mg, + .maps = al->maps, .map = al->map, .sym = al->sym, }, @@ -760,7 +760,7 @@ struct hist_entry *hists__add_entry_block(struct hists *hists, .block_info = block_info, .hists = hists, .ms = { - .mg = al->mg, + .maps = al->maps, .map = al->map, .sym = al->sym, }, @@ -895,7 +895,7 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) if (iter->curr >= iter->total) return 0; - al->mg = bi[i].to.ms.mg; + al->maps = bi[i].to.ms.maps; al->map = bi[i].to.ms.map; al->sym = bi[i].to.ms.sym; al->addr = bi[i].to.addr; @@ -1072,7 +1072,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .comm = thread__comm(al->thread), .ip = al->addr, .ms = { - .mg = al->mg, + .maps = al->maps, .map = al->map, .sym = al->sym, }, diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index f01d48a8d707..b8a5159361b4 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -5,10 +5,93 @@ /* linkage.h ... for including arch/x86/lib/memcpy_64.S */ -#define ENTRY(name) \ - .globl name; \ +/* Some toolchains use other characters (e.g. '`') to mark new line in macro */ +#ifndef ASM_NL +#define ASM_NL ; +#endif + +#ifndef __ALIGN +#define __ALIGN .align 4,0x90 +#define __ALIGN_STR ".align 4,0x90" +#endif + +/* SYM_T_FUNC -- type used by assembler to mark functions */ +#ifndef SYM_T_FUNC +#define SYM_T_FUNC STT_FUNC +#endif + +/* SYM_A_* -- align the symbol? */ +#define SYM_A_ALIGN ALIGN + +/* SYM_L_* -- linkage of symbols */ +#define SYM_L_GLOBAL(name) .globl name +#define SYM_L_LOCAL(name) /* nothing */ + +#define ALIGN __ALIGN + +/* === generic annotations === */ + +/* SYM_ENTRY -- use only if you have to for non-paired symbols */ +#ifndef SYM_ENTRY +#define SYM_ENTRY(name, linkage, align...) \ + linkage(name) ASM_NL \ + align ASM_NL \ name: +#endif + +/* SYM_START -- use only if you have to */ +#ifndef SYM_START +#define SYM_START(name, linkage, align...) \ + SYM_ENTRY(name, linkage, align) +#endif + +/* SYM_END -- use only if you have to */ +#ifndef SYM_END +#define SYM_END(name, sym_type) \ + .type name sym_type 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) +#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 -#define ENDPROC(name) +/* + * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, + * 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 #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 409afc611be9..33cf8928cf05 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3296,7 +3296,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, err = thread__set_comm(pt->unknown_thread, "unknown", 0); if (err) goto err_delete_thread; - if (thread__init_map_groups(pt->unknown_thread, pt->machine)) { + if (thread__init_maps(pt->unknown_thread, pt->machine)) { err = -ENOMEM; goto err_delete_thread; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index e2a312c649f0..c8c5410315e8 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -86,7 +86,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) int err = -ENOMEM; memset(machine, 0, sizeof(*machine)); - map_groups__init(&machine->kmaps, machine); + maps__init(&machine->kmaps, machine); RB_CLEAR_NODE(&machine->rb_node); dsos__init(&machine->dsos); @@ -217,7 +217,7 @@ void machine__exit(struct machine *machine) return; machine__destroy_kernel_maps(machine); - map_groups__exit(&machine->kmaps); + maps__exit(&machine->kmaps); dsos__exit(&machine->dsos); machine__exit_vdso(machine); zfree(&machine->root_dir); @@ -412,28 +412,28 @@ static void machine__update_thread_pid(struct machine *machine, if (!leader) goto out_err; - if (!leader->mg) - leader->mg = map_groups__new(machine); + if (!leader->maps) + leader->maps = maps__new(machine); - if (!leader->mg) + if (!leader->maps) goto out_err; - if (th->mg == leader->mg) + if (th->maps == leader->maps) return; - if (th->mg) { + if (th->maps) { /* * Maps are created from MMAP events which provide the pid and * tid. Consequently there never should be any maps on a thread * with an unknown pid. Just print an error if there are. */ - if (!map_groups__empty(th->mg)) + if (!maps__empty(th->maps)) pr_err("Discarding thread maps for %d:%d\n", th->pid_, th->tid); - map_groups__put(th->mg); + maps__put(th->maps); } - th->mg = map_groups__get(leader->mg); + th->maps = maps__get(leader->maps); out_put: thread__put(leader); return; @@ -536,14 +536,13 @@ static struct thread *____machine__findnew_thread(struct machine *machine, rb_insert_color_cached(&th->rb_node, &threads->entries, leftmost); /* - * We have to initialize map_groups separately - * after rb tree is updated. + * We have to initialize maps separately after rb tree is updated. * * The reason is that we call machine__findnew_thread - * within thread__init_map_groups to find the thread + * within thread__init_maps to find the thread * leader and that would screwed the rb tree. */ - if (thread__init_map_groups(th, machine)) { + if (thread__init_maps(th, machine)) { rb_erase_cached(&th->rb_node, &threads->entries); RB_CLEAR_NODE(&th->rb_node); thread__put(th); @@ -724,9 +723,8 @@ static int machine__process_ksymbol_register(struct machine *machine, struct perf_sample *sample __maybe_unused) { struct symbol *sym; - struct map *map; + struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr); - map = map_groups__find(&machine->kmaps, event->ksymbol.addr); if (!map) { map = dso__new_map(event->ksymbol.name); if (!map) @@ -734,7 +732,7 @@ static int machine__process_ksymbol_register(struct machine *machine, map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); } sym = symbol__new(map->map_ip(map, map->start), @@ -752,9 +750,9 @@ static int machine__process_ksymbol_unregister(struct machine *machine, { struct map *map; - map = map_groups__find(&machine->kmaps, event->ksymbol.addr); + map = maps__find(&machine->kmaps, event->ksymbol.addr); if (map) - map_groups__remove(&machine->kmaps, map); + maps__remove(&machine->kmaps, map); return 0; } @@ -790,9 +788,9 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start if (map == NULL) goto out; - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); - /* Put the map here because map_groups__insert alread got it */ + /* Put the map here because maps__insert alread got it */ map__put(map); out: /* put the dso here, corresponding to machine__findnew_module_dso */ @@ -977,7 +975,7 @@ int machine__create_extra_kernel_map(struct machine *machine, kmap->kmaps = &machine->kmaps; strlcpy(kmap->name, xm->name, KMAP_NAME_LEN); - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n", kmap->name, map->start, map->end); @@ -1022,8 +1020,7 @@ static u64 find_entry_trampoline(struct dso *dso) int machine__map_x86_64_entry_trampolines(struct machine *machine, struct dso *kernel) { - struct map_groups *kmaps = &machine->kmaps; - struct maps *maps = &kmaps->maps; + struct maps *kmaps = &machine->kmaps; int nr_cpus_avail, cpu; bool found = false; struct map *map; @@ -1033,14 +1030,14 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine, * In the vmlinux case, pgoff is a virtual address which must now be * mapped to a vmlinux offset. */ - maps__for_each_entry(maps, map) { + maps__for_each_entry(kmaps, map) { struct kmap *kmap = __map__kmap(map); struct map *dest_map; if (!kmap || !is_entry_trampoline(kmap->name)) continue; - dest_map = map_groups__find(kmaps, map->pgoff); + dest_map = maps__find(kmaps, map->pgoff); if (dest_map != map) map->pgoff = dest_map->map_ip(dest_map, map->pgoff); found = true; @@ -1102,7 +1099,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) return -1; kmap->kmaps = &machine->kmaps; - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); return 0; } @@ -1116,7 +1113,7 @@ void machine__destroy_kernel_maps(struct machine *machine) return; kmap = map__kmap(map); - map_groups__remove(&machine->kmaps, map); + maps__remove(&machine->kmaps, map); if (kmap && kmap->ref_reloc_sym) { zfree((char **)&kmap->ref_reloc_sym->name); zfree(&kmap->ref_reloc_sym); @@ -1211,7 +1208,7 @@ int machine__load_kallsyms(struct machine *machine, const char *filename) * kernel, with modules between them, fixup the end of all * sections. */ - map_groups__fixup_end(&machine->kmaps); + maps__fixup_end(&machine->kmaps); } return ret; @@ -1262,11 +1259,10 @@ static bool is_kmod_dso(struct dso *dso) dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; } -static int map_groups__set_module_path(struct map_groups *mg, const char *path, - struct kmod_path *m) +static int maps__set_module_path(struct maps *maps, const char *path, struct kmod_path *m) { char *long_name; - struct map *map = map_groups__find_by_name(mg, m->name); + struct map *map = maps__find_by_name(maps, m->name); if (map == NULL) return 0; @@ -1290,8 +1286,7 @@ static int map_groups__set_module_path(struct map_groups *mg, const char *path, return 0; } -static int map_groups__set_modules_path_dir(struct map_groups *mg, - const char *dir_name, int depth) +static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, int depth) { struct dirent *dent; DIR *dir = opendir(dir_name); @@ -1323,8 +1318,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, continue; } - ret = map_groups__set_modules_path_dir(mg, path, - depth + 1); + ret = maps__set_modules_path_dir(maps, path, depth + 1); if (ret < 0) goto out; } else { @@ -1335,7 +1329,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, goto out; if (m.kmod) - ret = map_groups__set_module_path(mg, path, &m); + ret = maps__set_module_path(maps, path, &m); zfree(&m.name); @@ -1362,7 +1356,7 @@ static int machine__set_modules_path(struct machine *machine) machine->root_dir, version); free(version); - return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); + return maps__set_modules_path_dir(&machine->kmaps, modules_path, 0); } int __weak arch__fix_module_text_start(u64 *start __maybe_unused, u64 *size __maybe_unused, @@ -1435,11 +1429,11 @@ static void machine__update_kernel_mmap(struct machine *machine, struct map *map = machine__kernel_map(machine); map__get(map); - map_groups__remove(&machine->kmaps, map); + maps__remove(&machine->kmaps, map); machine__set_kernel_mmap(machine, start, end); - map_groups__insert(&machine->kmaps, map); + maps__insert(&machine->kmaps, map); map__put(map); } @@ -1940,7 +1934,7 @@ static void ip__resolve_ams(struct thread *thread, ams->addr = ip; ams->al_addr = al.addr; - ams->ms.mg = al.mg; + ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = 0; @@ -1958,7 +1952,7 @@ static void ip__resolve_data(struct thread *thread, ams->addr = addr; ams->al_addr = al.addr; - ams->ms.mg = al.mg; + ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = phys_addr; @@ -2075,7 +2069,7 @@ static int add_callchain_ip(struct thread *thread, iter_cycles = iter->cycles; } - ms.mg = al.mg; + ms.maps = al.maps; ms.map = al.map; ms.sym = al.sym; srcline = callchain_srcline(&ms, al.addr); @@ -2452,6 +2446,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms list_for_each_entry(ilist, &inline_node->val, list) { struct map_symbol ilist_ms = { + .maps = ms->maps, .map = map, .sym = ilist->symbol, }; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 499be204830d..be0a930eca89 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -4,7 +4,7 @@ #include <sys/types.h> #include <linux/rbtree.h> -#include "map_groups.h" +#include "maps.h" #include "dsos.h" #include "rwsem.h" @@ -51,7 +51,7 @@ struct machine { struct vdso_info *vdso_info; struct perf_env *env; struct dsos dsos; - struct map_groups kmaps; + struct maps kmaps; struct map *vmlinux_map; u64 kernel_start; pid_t *current_tid; @@ -83,7 +83,7 @@ struct map *machine__kernel_map(struct machine *machine) static inline struct maps *machine__kernel_maps(struct machine *machine) { - return &machine->kmaps.maps; + return &machine->kmaps; } int machine__get_kernel_start(struct machine *machine); @@ -212,7 +212,7 @@ static inline struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr, struct map **mapp) { - return map_groups__find_symbol(&machine->kmaps, addr, mapp); + return maps__find_symbol(&machine->kmaps, addr, mapp); } static inline @@ -220,7 +220,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, const char *name, struct map **mapp) { - return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp); + return maps__find_symbol_by_name(&machine->kmaps, name, mapp); } int arch__fix_module_text_start(u64 *start, u64 *size, const char *name); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 744bfbaf35cf..fdd5bddb3075 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -433,51 +433,6 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, return ret; } -int map__fprintf_srccode(struct map *map, u64 addr, - FILE *fp, - struct srccode_state *state) -{ - char *srcfile; - int ret = 0; - unsigned line; - int len; - char *srccode; - - if (!map || !map->dso) - return 0; - srcfile = get_srcline_split(map->dso, - map__rip_2objdump(map, addr), - &line); - if (!srcfile) - return 0; - - /* Avoid redundant printing */ - if (state && - state->srcfile && - !strcmp(state->srcfile, srcfile) && - state->line == line) { - free(srcfile); - return 0; - } - - srccode = find_sourceline(srcfile, line, &len); - if (!srccode) - goto out_free_line; - - ret = fprintf(fp, "|%-8d %.*s", line, len, srccode); - - if (state) { - state->srcfile = srcfile; - state->line = line; - } - return ret; - -out_free_line: - free(srcfile); - return ret; -} - - void srccode_state_free(struct srccode_state *state) { zfree(&state->srcfile); @@ -557,73 +512,71 @@ u64 map__objdump_2mem(struct map *map, u64 ip) return ip + map->reloc; } -static void maps__init(struct maps *maps) +void maps__init(struct maps *maps, struct machine *machine) { maps->entries = RB_ROOT; init_rwsem(&maps->lock); + maps->machine = machine; + maps->last_search_by_name = NULL; + maps->nr_maps = 0; + maps->maps_by_name = NULL; + refcount_set(&maps->refcnt, 1); } -void map_groups__init(struct map_groups *mg, struct machine *machine) -{ - maps__init(&mg->maps); - mg->machine = machine; - mg->last_search_by_name = NULL; - mg->nr_maps = 0; - mg->maps_by_name = NULL; - refcount_set(&mg->refcnt, 1); -} - -static void __map_groups__free_maps_by_name(struct map_groups *mg) +static void __maps__free_maps_by_name(struct maps *maps) { /* * Free everything to try to do it from the rbtree in the next search */ - zfree(&mg->maps_by_name); - mg->nr_maps_allocated = 0; + zfree(&maps->maps_by_name); + maps->nr_maps_allocated = 0; } -void map_groups__insert(struct map_groups *mg, struct map *map) +void maps__insert(struct maps *maps, struct map *map) { - struct maps *maps = &mg->maps; - down_write(&maps->lock); __maps__insert(maps, map); - ++mg->nr_maps; + ++maps->nr_maps; /* * If we already performed some search by name, then we need to add the just * inserted map and resort. */ - if (mg->maps_by_name) { - if (mg->nr_maps > mg->nr_maps_allocated) { - int nr_allocate = mg->nr_maps * 2; - struct map **maps_by_name = realloc(mg->maps_by_name, nr_allocate * sizeof(map)); + if (maps->maps_by_name) { + if (maps->nr_maps > maps->nr_maps_allocated) { + int nr_allocate = maps->nr_maps * 2; + struct map **maps_by_name = realloc(maps->maps_by_name, nr_allocate * sizeof(map)); if (maps_by_name == NULL) { - __map_groups__free_maps_by_name(mg); + __maps__free_maps_by_name(maps); return; } - mg->maps_by_name = maps_by_name; - mg->nr_maps_allocated = nr_allocate; + maps->maps_by_name = maps_by_name; + maps->nr_maps_allocated = nr_allocate; } - mg->maps_by_name[mg->nr_maps - 1] = map; - __map_groups__sort_by_name(mg); + maps->maps_by_name[maps->nr_maps - 1] = map; + __maps__sort_by_name(maps); } up_write(&maps->lock); } -void map_groups__remove(struct map_groups *mg, struct map *map) +static void __maps__remove(struct maps *maps, struct map *map) +{ + rb_erase_init(&map->rb_node, &maps->entries); + map__put(map); +} + +void maps__remove(struct maps *maps, struct map *map) { - struct maps *maps = &mg->maps; down_write(&maps->lock); - if (mg->last_search_by_name == map) - mg->last_search_by_name = NULL; + if (maps->last_search_by_name == map) + maps->last_search_by_name = NULL; __maps__remove(maps, map); - --mg->nr_maps; - if (mg->maps_by_name) - __map_groups__free_maps_by_name(mg); + --maps->nr_maps; + if (maps->maps_by_name) + __maps__free_maps_by_name(maps); up_write(&maps->lock); } @@ -637,50 +590,44 @@ static void __maps__purge(struct maps *maps) } } -static void maps__exit(struct maps *maps) +void maps__exit(struct maps *maps) { down_write(&maps->lock); __maps__purge(maps); up_write(&maps->lock); } -void map_groups__exit(struct map_groups *mg) -{ - maps__exit(&mg->maps); -} - -bool map_groups__empty(struct map_groups *mg) +bool maps__empty(struct maps *maps) { - return !maps__first(&mg->maps); + return !maps__first(maps); } -struct map_groups *map_groups__new(struct machine *machine) +struct maps *maps__new(struct machine *machine) { - struct map_groups *mg = zalloc(sizeof(*mg)); + struct maps *maps = zalloc(sizeof(*maps)); - if (mg != NULL) - map_groups__init(mg, machine); + if (maps != NULL) + maps__init(maps, machine); - return mg; + return maps; } -void map_groups__delete(struct map_groups *mg) +void maps__delete(struct maps *maps) { - map_groups__exit(mg); - unwind__finish_access(mg); - free(mg); + maps__exit(maps); + unwind__finish_access(maps); + free(maps); } -void map_groups__put(struct map_groups *mg) +void maps__put(struct maps *maps) { - if (mg && refcount_dec_and_test(&mg->refcnt)) - map_groups__delete(mg); + if (maps && refcount_dec_and_test(&maps->refcnt)) + maps__delete(maps); } -struct symbol *map_groups__find_symbol(struct map_groups *mg, - u64 addr, struct map **mapp) +struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) { - struct map *map = map_groups__find(mg, addr); + struct map *map = maps__find(maps, addr); /* Ensure map is loaded before using map->map_ip */ if (map != NULL && map__load(map) >= 0) { @@ -699,8 +646,7 @@ static bool map__contains_symbol(struct map *map, struct symbol *sym) return ip >= map->start && ip < map->end; } -struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, - struct map **mapp) +struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { struct symbol *sym; struct map *pos; @@ -727,19 +673,12 @@ out: return sym; } -struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, - const char *name, - struct map **mapp) -{ - return maps__find_symbol_by_name(&mg->maps, name, mapp); -} - -int map_groups__find_ams(struct map_groups *mg, struct addr_map_symbol *ams) +int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) { if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) { - if (mg == NULL) + if (maps == NULL) return -1; - ams->ms.map = map_groups__find(mg, ams->addr); + ams->ms.map = maps__find(maps, ams->addr); if (ams->ms.map == NULL) return -1; } @@ -750,7 +689,7 @@ int map_groups__find_ams(struct map_groups *mg, struct addr_map_symbol *ams) return ams->ms.sym ? 0 : -1; } -static size_t maps__fprintf(struct maps *maps, FILE *fp) +size_t maps__fprintf(struct maps *maps, FILE *fp) { size_t printed = 0; struct map *pos; @@ -771,19 +710,8 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) return printed; } -size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) -{ - return maps__fprintf(&mg->maps, fp); -} - -static void __map_groups__insert(struct map_groups *mg, struct map *map) -{ - __maps__insert(&mg->maps, map); -} - -int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp) +int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) { - struct maps *maps = &mg->maps; struct rb_root *root; struct rb_node *next, *first; int err = 0; @@ -848,7 +776,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE } before->end = map->start; - __map_groups__insert(mg, before); + __maps__insert(maps, before); if (verbose >= 2 && !use_browser) map__fprintf(before, fp); map__put(before); @@ -865,7 +793,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE after->start = map->end; after->pgoff += map->end - pos->start; assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end)); - __map_groups__insert(mg, after); + __maps__insert(maps, after); if (verbose >= 2 && !use_browser) map__fprintf(after, fp); map__put(after); @@ -886,31 +814,30 @@ out: /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct thread *thread, struct map_groups *parent) +int maps__clone(struct thread *thread, struct maps *parent) { - struct map_groups *mg = thread->mg; + struct maps *maps = thread->maps; int err = -ENOMEM; struct map *map; - struct maps *maps = &parent->maps; - down_read(&maps->lock); + down_read(&parent->lock); - maps__for_each_entry(maps, map) { + maps__for_each_entry(parent, map) { struct map *new = map__clone(map); if (new == NULL) goto out_unlock; - err = unwind__prepare_access(mg, new, NULL); + err = unwind__prepare_access(maps, new, NULL); if (err) goto out_unlock; - map_groups__insert(mg, new); + maps__insert(maps, new); map__put(new); } err = 0; out_unlock: - up_read(&maps->lock); + up_read(&parent->lock); return err; } @@ -935,26 +862,6 @@ static void __maps__insert(struct maps *maps, struct map *map) map__get(map); } -void maps__insert(struct maps *maps, struct map *map) -{ - down_write(&maps->lock); - __maps__insert(maps, map); - up_write(&maps->lock); -} - -void __maps__remove(struct maps *maps, struct map *map) -{ - rb_erase_init(&map->rb_node, &maps->entries); - map__put(map); -} - -void maps__remove(struct maps *maps, struct map *map) -{ - down_write(&maps->lock); - __maps__remove(maps, map); - up_write(&maps->lock); -} - struct map *maps__find(struct maps *maps, u64 ip) { struct rb_node *p; @@ -1018,7 +925,7 @@ struct kmap *map__kmap(struct map *map) return kmap; } -struct map_groups *map__kmaps(struct map *map) +struct maps *map__kmaps(struct map *map) { struct kmap *kmap = map__kmap(map); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 5e8899883231..067036e8970c 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -12,11 +12,8 @@ #include <linux/types.h> struct dso; -struct ip_callchain; -struct ref_reloc_sym; -struct map_groups; +struct maps; struct machine; -struct evsel; struct map { union { @@ -45,7 +42,7 @@ struct kmap; struct kmap *__map__kmap(struct map *map); struct kmap *map__kmap(struct map *map); -struct map_groups *map__kmaps(struct map *map); +struct maps *map__kmaps(struct map *map); static inline u64 map__map_ip(struct map *map, u64 ip) { @@ -138,19 +135,12 @@ char *map__srcline(struct map *map, u64 addr, struct symbol *sym); int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp); -struct srccode_state; - -int map__fprintf_srccode(struct map *map, u64 addr, - FILE *fp, struct srccode_state *state); - int map__load(struct map *map); struct symbol *map__find_symbol(struct map *map, u64 addr); struct symbol *map__find_symbol_by_name(struct map *map, const char *name); void map__fixup_start(struct map *map); void map__fixup_end(struct map *map); -void map__reloc_vmlinux(struct map *map); - int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr); diff --git a/tools/perf/util/map_groups.h b/tools/perf/util/map_groups.h deleted file mode 100644 index 63ed211fe241..000000000000 --- a/tools/perf/util/map_groups.h +++ /dev/null @@ -1,106 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERF_MAP_GROUPS_H -#define __PERF_MAP_GROUPS_H - -#include <linux/refcount.h> -#include <linux/rbtree.h> -#include <stdio.h> -#include <stdbool.h> -#include <linux/types.h> -#include "rwsem.h" - -struct ref_reloc_sym; -struct machine; -struct map; -struct thread; - -struct maps { - struct rb_root entries; - struct rw_semaphore lock; -}; - -void maps__insert(struct maps *maps, struct map *map); -void maps__remove(struct maps *maps, struct map *map); -void __maps__remove(struct maps *maps, struct map *map); -struct map *maps__find(struct maps *maps, u64 addr); -struct map *maps__first(struct maps *maps); -struct map *map__next(struct map *map); - -#define maps__for_each_entry(maps, map) \ - for (map = maps__first(maps); map; map = map__next(map)) - -#define maps__for_each_entry_safe(maps, map, next) \ - for (map = maps__first(maps), next = map__next(map); map; map = next, next = map__next(map)) - -struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp); - -struct map_groups { - struct maps maps; - struct machine *machine; - struct map *last_search_by_name; - struct map **maps_by_name; - refcount_t refcnt; - unsigned int nr_maps; - unsigned int nr_maps_allocated; -#ifdef HAVE_LIBUNWIND_SUPPORT - void *addr_space; - struct unwind_libunwind_ops *unwind_libunwind_ops; -#endif -}; - -#define KMAP_NAME_LEN 256 - -struct kmap { - struct ref_reloc_sym *ref_reloc_sym; - struct map_groups *kmaps; - char name[KMAP_NAME_LEN]; -}; - -struct map_groups *map_groups__new(struct machine *machine); -void map_groups__delete(struct map_groups *mg); -bool map_groups__empty(struct map_groups *mg); - -static inline struct map_groups *map_groups__get(struct map_groups *mg) -{ - if (mg) - refcount_inc(&mg->refcnt); - return mg; -} - -void map_groups__put(struct map_groups *mg); -void map_groups__init(struct map_groups *mg, struct machine *machine); -void map_groups__exit(struct map_groups *mg); -int map_groups__clone(struct thread *thread, struct map_groups *parent); -size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); - -void map_groups__insert(struct map_groups *mg, struct map *map); - -void map_groups__remove(struct map_groups *mg, struct map *map); - -static inline struct map *map_groups__find(struct map_groups *mg, u64 addr) -{ - return maps__find(&mg->maps, addr); -} - -#define map_groups__for_each_entry(mg, map) \ - for (map = maps__first(&mg->maps); map; map = map__next(map)) - -#define map_groups__for_each_entry_safe(mg, map, next) \ - for (map = maps__first(&mg->maps), next = map__next(map); map; map = next, next = map__next(map)) - -struct symbol *map_groups__find_symbol(struct map_groups *mg, u64 addr, struct map **mapp); -struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, const char *name, struct map **mapp); - -struct addr_map_symbol; - -int map_groups__find_ams(struct map_groups *mg, struct addr_map_symbol *ams); - -int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp); - -struct map *map_groups__find_by_name(struct map_groups *mg, const char *name); - -int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map); - -void __map_groups__sort_by_name(struct map_groups *mg); - -#endif // __PERF_MAP_GROUPS_H diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 2964d971aeab..5b8ca93798e9 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -4,12 +4,12 @@ #include <linux/types.h> -struct map_groups; +struct maps; struct map; struct symbol; struct map_symbol { - struct map_groups *mg; + struct maps *maps; struct map *map; struct symbol *sym; }; diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h new file mode 100644 index 000000000000..3dd000ddf925 --- /dev/null +++ b/tools/perf/util/maps.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_MAPS_H +#define __PERF_MAPS_H + +#include <linux/refcount.h> +#include <linux/rbtree.h> +#include <stdio.h> +#include <stdbool.h> +#include <linux/types.h> +#include "rwsem.h" + +struct ref_reloc_sym; +struct machine; +struct map; +struct maps; +struct thread; + +struct map *maps__find(struct maps *maps, u64 addr); +struct map *maps__first(struct maps *maps); +struct map *map__next(struct map *map); + +#define maps__for_each_entry(maps, map) \ + for (map = maps__first(maps); map; map = map__next(map)) + +#define maps__for_each_entry_safe(maps, map, next) \ + for (map = maps__first(maps), next = map__next(map); map; map = next, next = map__next(map)) + +struct maps { + struct rb_root entries; + struct rw_semaphore lock; + struct machine *machine; + struct map *last_search_by_name; + struct map **maps_by_name; + refcount_t refcnt; + unsigned int nr_maps; + unsigned int nr_maps_allocated; +#ifdef HAVE_LIBUNWIND_SUPPORT + void *addr_space; + struct unwind_libunwind_ops *unwind_libunwind_ops; +#endif +}; + +#define KMAP_NAME_LEN 256 + +struct kmap { + struct ref_reloc_sym *ref_reloc_sym; + struct maps *kmaps; + char name[KMAP_NAME_LEN]; +}; + +struct maps *maps__new(struct machine *machine); +void maps__delete(struct maps *maps); +bool maps__empty(struct maps *maps); + +static inline struct maps *maps__get(struct maps *maps) +{ + if (maps) + refcount_inc(&maps->refcnt); + return maps; +} + +void maps__put(struct maps *maps); +void maps__init(struct maps *maps, struct machine *machine); +void maps__exit(struct maps *maps); +int maps__clone(struct thread *thread, struct maps *parent); +size_t maps__fprintf(struct maps *maps, FILE *fp); + +void maps__insert(struct maps *maps, struct map *map); + +void maps__remove(struct maps *maps, struct map *map); + +struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp); +struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp); + +struct addr_map_symbol; + +int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams); + +int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp); + +struct map *maps__find_by_name(struct maps *maps, const char *name); + +int maps__merge_in(struct maps *kmaps, struct map *new_map); + +void __maps__sort_by_name(struct maps *maps); + +#endif // __PERF_MAPS_H diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 6a4d350d5cdb..02aee946b6c1 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -103,8 +103,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, if (!strcmp(ev->name, ids[i])) { if (!metric_events[i]) metric_events[i] = ev; + i++; + if (i == idnum) + break; } else { - if (++i == idnum) { + if (i + 1 == idnum) { /* Discard the whole match and start again */ i = 0; memset(metric_events, 0, @@ -124,7 +127,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, } } - if (i != idnum - 1) { + if (i != idnum) { /* Not whole match */ return NULL; } diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index e014c2c038f4..a45499126184 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -41,7 +41,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); static inline const char *perf_reg_name(int id __maybe_unused) { - return NULL; + return "unknown"; } static inline int perf_reg_value(u64 *valp __maybe_unused, diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index e8d348988026..8b99fd312aae 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -24,6 +24,7 @@ #include "pmu-events/pmu-events.h" #include "string2.h" #include "strbuf.h" +#include "fncache.h" struct perf_pmu_format { char *name; @@ -82,7 +83,6 @@ int perf_pmu__format_parse(char *dir, struct list_head *head) */ static int pmu_format(const char *name, struct list_head *format) { - struct stat st; char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -92,8 +92,8 @@ static int pmu_format(const char *name, struct list_head *format) snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name); - if (stat(path, &st) < 0) - return 0; /* no error if format does not exist */ + if (!file_available(path)) + return 0; if (perf_pmu__format_parse(path, format)) return -1; @@ -475,7 +475,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) */ static int pmu_aliases(const char *name, struct list_head *head) { - struct stat st; char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -485,8 +484,8 @@ static int pmu_aliases(const char *name, struct list_head *head) snprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events", sysfs, name); - if (stat(path, &st) < 0) - return 0; /* no error if 'events' does not exist */ + if (!file_available(path)) + return 0; if (pmu_aliases_parse(path, head)) return -1; @@ -525,7 +524,6 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, */ static int pmu_type(const char *name, __u32 *type) { - struct stat st; char path[PATH_MAX]; FILE *file; int ret = 0; @@ -537,7 +535,7 @@ static int pmu_type(const char *name, __u32 *type) snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name); - if (stat(path, &st) < 0) + if (access(path, R_OK) < 0) return -1; file = fopen(path, "r"); @@ -628,14 +626,11 @@ static struct perf_cpu_map *pmu_cpumask(const char *name) static bool pmu_is_uncore(const char *name) { char path[PATH_MAX]; - struct perf_cpu_map *cpus; - const char *sysfs = sysfs__mountpoint(); + const char *sysfs; + sysfs = sysfs__mountpoint(); snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); - cpus = __pmu_cpumask(path); - perf_cpu_map__put(cpus); - - return !!cpus; + return file_available(path); } /* @@ -645,7 +640,6 @@ static bool pmu_is_uncore(const char *name) */ static int is_arm_pmu_core(const char *name) { - struct stat st; char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -655,10 +649,7 @@ static int is_arm_pmu_core(const char *name) /* Look for cpu sysfs (specific to arm) */ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus", sysfs, name); - if (stat(path, &st) == 0) - return 1; - - return 0; + return file_available(path); } static char *perf_pmu__getcpuid(struct perf_pmu *pmu) @@ -1544,7 +1535,6 @@ bool pmu_have_event(const char *pname, const char *name) static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) { - struct stat st; char path[PATH_MAX]; const char *sysfs; @@ -1554,10 +1544,8 @@ static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name); - - if (stat(path, &st) < 0) + if (!file_available(path)) return NULL; - return fopen(path, "r"); } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 52b2d165453a..eea132f512b0 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -28,7 +28,7 @@ #include "dso.h" #include "color.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "symbol.h" #include <api/fs/fs.h> #include "trace-event.h" /* For __maybe_unused */ @@ -321,7 +321,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) char module_name[128]; snprintf(module_name, sizeof(module_name), "[%s]", module); - map = map_groups__find_by_name(&host_machine->kmaps, module_name); + map = maps__find_by_name(&host_machine->kmaps, module_name); if (map) { dso = map->dso; goto found; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 9af183860fbd..e7279ea6043a 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -33,3 +33,4 @@ util/trace-event.c util/string.c util/symbol_fprintf.c util/units.c +util/affinity.c diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 9581a904af29..80ca5d0ab7fe 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1127,7 +1127,7 @@ static void python_export_sample_table(struct db_export *dbe, tuple_set_u64(t, 0, es->db_id); tuple_set_u64(t, 1, es->evsel->db_id); - tuple_set_u64(t, 2, es->al->mg->machine->db_id); + tuple_set_u64(t, 2, es->al->maps->machine->db_id); tuple_set_u64(t, 3, es->al->thread->db_id); tuple_set_u64(t, 4, es->comm_db_id); tuple_set_u64(t, 5, es->dso_db_id); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 345b5ccc90f6..9fcba2872130 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2681,12 +2681,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok))) - pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); + ui__error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else - pr_err("Invalid --sort key: `%s'", tok); + ui__error("Invalid --sort key: `%s'", tok); break; } else if (ret == -ESRCH) { - pr_err("Unknown --sort key: `%s'", tok); + ui__error("Unknown --sort key: `%s'", tok); break; } } @@ -2743,7 +2743,7 @@ static int setup_sort_order(struct evlist *evlist) return 0; if (sort_order[1] == '\0') { - pr_err("Invalid --sort key: `+'"); + ui__error("Invalid --sort key: `+'"); return -EINVAL; } @@ -2959,6 +2959,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sort__mode != SORT_MODE__MEMORY) + return -EINVAL; + return __sort_dimension__add_output(list, sd); } @@ -2968,6 +2971,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sort__mode != SORT_MODE__BRANCH) + return -EINVAL; + return __sort_dimension__add_output(list, sd); } @@ -3034,7 +3040,7 @@ static int __setup_output_field(void) strp++; if (!strlen(strp)) { - pr_err("Invalid --fields key: `+'"); + ui__error("Invalid --fields key: `+'"); goto out; } diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c index d84ed8b6caaa..c29edaaca863 100644 --- a/tools/perf/util/srccode.c +++ b/tools/perf/util/srccode.c @@ -16,6 +16,7 @@ #include "srccode.h" #include "debug.h" #include <internal/lib.h> // page_size +#include "fncache.h" #define MAXSRCCACHE (32*1024*1024) #define MAXSRCFILES 64 @@ -36,14 +37,6 @@ static LIST_HEAD(srcfile_list); static long map_total_sz; static int num_srcfiles; -static unsigned shash(unsigned char *s) -{ - unsigned h = 0; - while (*s) - h = 65599 * h + *s++; - return h ^ (h >> 16); -} - static int countlines(char *map, int maplen) { int numl; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 332cb730785b..5f26137b8d60 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -464,7 +464,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, - struct target *target) + struct target *target, + int cpu) { struct perf_event_attr *attr = &evsel->core.attr; struct evsel *leader = evsel->leader; @@ -518,7 +519,7 @@ int create_perf_stat_counter(struct evsel *evsel, } if (target__has_cpu(target) && !target__has_per_thread(target)) - return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel)); + return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu); return perf_evsel__open_per_thread(evsel, evsel->core.threads); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index bfa9aaf36ce6..fb990efa54a8 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -214,7 +214,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, - struct target *target); + struct target *target, + int cpu); void perf_evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 16776d5fbaea..6658fbf196e6 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -9,7 +9,7 @@ #include "dso.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "symbol.h" #include "symsrc.h" #include "demangle-java.h" @@ -844,7 +844,7 @@ void __weak arch__sym_update(struct symbol *s __maybe_unused, static int dso__process_kernel_symbol(struct dso *dso, struct map *map, GElf_Sym *sym, GElf_Shdr *shdr, - struct map_groups *kmaps, struct kmap *kmap, + struct maps *kmaps, struct kmap *kmap, struct dso **curr_dsop, struct map **curr_mapp, const char *section_name, bool adjust_kernel_syms, bool kmodule, bool *remap_kernel) @@ -876,8 +876,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, /* Ensure maps are correctly ordered */ if (kmaps) { map__get(map); - map_groups__remove(kmaps, map); - map_groups__insert(kmaps, map); + maps__remove(kmaps, map); + maps__insert(kmaps, map); map__put(map); } } @@ -902,7 +902,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name); - curr_map = map_groups__find_by_name(kmaps, dso_name); + curr_map = maps__find_by_name(kmaps, dso_name); if (curr_map == NULL) { u64 start = sym->st_value; @@ -928,7 +928,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; } curr_dso->symtab_type = dso->symtab_type; - map_groups__insert(kmaps, curr_map); + maps__insert(kmaps, curr_map); /* * Add it before we drop the referece to curr_map, i.e. while * we still are sure to have a reference to this DSO via @@ -950,7 +950,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; - struct map_groups *kmaps = kmap ? map__kmaps(map) : NULL; + struct maps *kmaps = kmap ? map__kmaps(map) : NULL; struct map *curr_map = map; struct dso *curr_dso = dso; Elf_Data *symstrs, *secstrs; @@ -1162,7 +1162,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, * We need to fixup this here too because we create new * maps here, for things like vsyscall sections. */ - map_groups__fixup_end(kmaps); + maps__fixup_end(kmaps); } } err = nr; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index db9667aacb88..3b379b1296f1 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -239,9 +239,8 @@ void symbols__fixup_end(struct rb_root_cached *symbols) curr->end = roundup(curr->start, 4096) + 4096; } -void map_groups__fixup_end(struct map_groups *mg) +void maps__fixup_end(struct maps *maps) { - struct maps *maps = &mg->maps; struct map *prev = NULL, *curr; down_write(&maps->lock); @@ -698,7 +697,7 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename) return kallsyms__parse(filename, dso, map__process_kallsym_symbol); } -static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct dso *dso) +static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso) { struct map *curr_map; struct symbol *pos; @@ -724,7 +723,7 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct if (module) *module = '\0'; - curr_map = map_groups__find(kmaps, pos->start); + curr_map = maps__find(kmaps, pos->start); if (!curr_map) { symbol__delete(pos); @@ -751,8 +750,8 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct * kernel range is broken in several maps, named [kernel].N, as we don't have * the original ELF section names vmlinux have. */ -static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, u64 delta, - struct map *initial_map) +static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, + struct map *initial_map) { struct machine *machine; struct map *curr_map = initial_map; @@ -797,7 +796,7 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, dso__set_loaded(curr_map->dso); } - curr_map = map_groups__find_by_name(kmaps, module); + curr_map = maps__find_by_name(kmaps, module); if (curr_map == NULL) { pr_debug("%s/proc/{kallsyms,modules} " "inconsistency while looking " @@ -864,7 +863,7 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, } curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; - map_groups__insert(kmaps, curr_map); + maps__insert(kmaps, curr_map); ++kernel_range; } else if (delta) { /* Kernel was relocated at boot time */ @@ -1049,8 +1048,7 @@ out_delete_from: return ret; } -static int do_validate_kcore_modules(const char *filename, - struct map_groups *kmaps) +static int do_validate_kcore_modules(const char *filename, struct maps *kmaps) { struct rb_root modules = RB_ROOT; struct map *old_map; @@ -1060,7 +1058,7 @@ static int do_validate_kcore_modules(const char *filename, if (err) return err; - map_groups__for_each_entry(kmaps, old_map) { + maps__for_each_entry(kmaps, old_map) { struct module_info *mi; if (!__map__is_kmodule(old_map)) { @@ -1107,7 +1105,7 @@ static bool filename_from_kallsyms_filename(char *filename, static int validate_kcore_modules(const char *kallsyms_filename, struct map *map) { - struct map_groups *kmaps = map__kmaps(map); + struct maps *kmaps = map__kmaps(map); char modules_filename[PATH_MAX]; if (!kmaps) @@ -1167,15 +1165,15 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) } /* - * Merges map into map_groups by splitting the new map - * within the existing map regions. + * Merges map into maps by splitting the new map within the existing map + * regions. */ -int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map) +int maps__merge_in(struct maps *kmaps, struct map *new_map) { struct map *old_map; LIST_HEAD(merged); - map_groups__for_each_entry(kmaps, old_map) { + maps__for_each_entry(kmaps, old_map) { /* no overload with this one */ if (new_map->end < old_map->start || new_map->start >= old_map->end) @@ -1232,12 +1230,12 @@ int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map) while (!list_empty(&merged)) { old_map = list_entry(merged.next, struct map, node); list_del_init(&old_map->node); - map_groups__insert(kmaps, old_map); + maps__insert(kmaps, old_map); map__put(old_map); } if (new_map) { - map_groups__insert(kmaps, new_map); + maps__insert(kmaps, new_map); map__put(new_map); } return 0; @@ -1246,7 +1244,7 @@ int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map) static int dso__load_kcore(struct dso *dso, struct map *map, const char *kallsyms_filename) { - struct map_groups *kmaps = map__kmaps(map); + struct maps *kmaps = map__kmaps(map); struct kcore_mapfn_data md; struct map *old_map, *new_map, *replacement_map = NULL, *next; struct machine *machine; @@ -1295,14 +1293,14 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Remove old maps */ - map_groups__for_each_entry_safe(kmaps, old_map, next) { + maps__for_each_entry_safe(kmaps, old_map, next) { /* * We need to preserve eBPF maps even if they are * covered by kcore, because we need to access * eBPF dso for source data. */ if (old_map != map && !__map__is_bpf_prog(old_map)) - map_groups__remove(kmaps, old_map); + maps__remove(kmaps, old_map); } machine->trampolines_mapped = false; @@ -1331,8 +1329,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map, map->unmap_ip = new_map->unmap_ip; /* Ensure maps are correctly ordered */ map__get(map); - map_groups__remove(kmaps, map); - map_groups__insert(kmaps, map); + maps__remove(kmaps, map); + maps__insert(kmaps, map); map__put(map); map__put(new_map); } else { @@ -1341,7 +1339,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, * and ensure that current maps (eBPF) * stay intact. */ - if (map_groups__merge_in(kmaps, new_map)) + if (maps__merge_in(kmaps, new_map)) goto out_err; } } @@ -1433,9 +1431,9 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; if (!no_kcore && !dso__load_kcore(dso, map, filename)) - return map_groups__split_kallsyms_for_kcore(kmap->kmaps, dso); + return maps__split_kallsyms_for_kcore(kmap->kmaps, dso); else - return map_groups__split_kallsyms(kmap->kmaps, dso, delta, map); + return maps__split_kallsyms(kmap->kmaps, dso, delta, map); } int dso__load_kallsyms(struct dso *dso, const char *filename, @@ -1772,68 +1770,67 @@ static int map__strcmp_name(const void *name, const void *b) return strcmp(name, map->dso->short_name); } -void __map_groups__sort_by_name(struct map_groups *mg) +void __maps__sort_by_name(struct maps *maps) { - qsort(mg->maps_by_name, mg->nr_maps, sizeof(struct map *), map__strcmp); + qsort(maps->maps_by_name, maps->nr_maps, sizeof(struct map *), map__strcmp); } -static int map__groups__sort_by_name_from_rbtree(struct map_groups *mg) +static int map__groups__sort_by_name_from_rbtree(struct maps *maps) { struct map *map; - struct map **maps_by_name = realloc(mg->maps_by_name, mg->nr_maps * sizeof(map)); + struct map **maps_by_name = realloc(maps->maps_by_name, maps->nr_maps * sizeof(map)); int i = 0; if (maps_by_name == NULL) return -1; - mg->maps_by_name = maps_by_name; - mg->nr_maps_allocated = mg->nr_maps; + maps->maps_by_name = maps_by_name; + maps->nr_maps_allocated = maps->nr_maps; - maps__for_each_entry(&mg->maps, map) + maps__for_each_entry(maps, map) maps_by_name[i++] = map; - __map_groups__sort_by_name(mg); + __maps__sort_by_name(maps); return 0; } -static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) +static struct map *__maps__find_by_name(struct maps *maps, const char *name) { struct map **mapp; - if (mg->maps_by_name == NULL && - map__groups__sort_by_name_from_rbtree(mg)) + if (maps->maps_by_name == NULL && + map__groups__sort_by_name_from_rbtree(maps)) return NULL; - mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); + mapp = bsearch(name, maps->maps_by_name, maps->nr_maps, sizeof(*mapp), map__strcmp_name); if (mapp) return *mapp; return NULL; } -struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) +struct map *maps__find_by_name(struct maps *maps, const char *name) { - struct maps *maps = &mg->maps; struct map *map; down_read(&maps->lock); - if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { - map = mg->last_search_by_name; + if (maps->last_search_by_name && strcmp(maps->last_search_by_name->dso->short_name, name) == 0) { + map = maps->last_search_by_name; goto out_unlock; } /* - * If we have mg->maps_by_name, then the name isn't in the rbtree, - * as mg->maps_by_name mirrors the rbtree when lookups by name are + * If we have maps->maps_by_name, then the name isn't in the rbtree, + * as maps->maps_by_name mirrors the rbtree when lookups by name are * made. */ - map = __map_groups__find_by_name(mg, name); - if (map || mg->maps_by_name != NULL) + map = __maps__find_by_name(maps, name); + if (map || maps->maps_by_name != NULL) goto out_unlock; /* Fallback to traversing the rbtree... */ maps__for_each_entry(maps, map) if (strcmp(map->dso->short_name, name) == 0) { - mg->last_search_by_name = map; + maps->last_search_by_name = map; goto out_unlock; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 0b718cc9fb28..93fc43db1be3 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -21,7 +21,7 @@ struct dso; struct map; -struct map_groups; +struct maps; struct option; /* @@ -108,7 +108,7 @@ struct ref_reloc_sym { struct addr_location { struct thread *thread; - struct map_groups *mg; + struct maps *maps; struct map *map; struct symbol *sym; const char *srcline; @@ -186,7 +186,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); void symbols__fixup_end(struct rb_root_cached *symbols); -void map_groups__fixup_end(struct map_groups *mg); +void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 48c3f8b9c852..c423298fe62d 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -493,7 +493,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, /* * send mmap only for thread group leader - * see thread__init_map_groups + * see thread__init_maps() */ if (pid == tgid && perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index cd8a948d03ec..0885967d5bc3 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -134,8 +134,8 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread, if (err) return err; - if (thread->mg && thread->mg->machine) { - struct machine *machine = thread->mg->machine; + if (thread->maps && thread->maps->machine) { + struct machine *machine = thread->maps->machine; const char *arch = perf_env__arch(machine->env); ts->kernel_start = machine__kernel_start(machine); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0a277a920970..28b719388028 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -19,21 +19,21 @@ #include <api/fs/fs.h> -int thread__init_map_groups(struct thread *thread, struct machine *machine) +int thread__init_maps(struct thread *thread, struct machine *machine) { pid_t pid = thread->pid_; if (pid == thread->tid || pid == -1) { - thread->mg = map_groups__new(machine); + thread->maps = maps__new(machine); } else { struct thread *leader = __machine__findnew_thread(machine, pid, pid); if (leader) { - thread->mg = map_groups__get(leader->mg); + thread->maps = maps__get(leader->maps); thread__put(leader); } } - return thread->mg ? 0 : -1; + return thread->maps ? 0 : -1; } struct thread *thread__new(pid_t pid, pid_t tid) @@ -86,9 +86,9 @@ void thread__delete(struct thread *thread) thread_stack__free(thread); - if (thread->mg) { - map_groups__put(thread->mg); - thread->mg = NULL; + if (thread->maps) { + maps__put(thread->maps); + thread->maps = NULL; } down_write(&thread->namespaces_lock); list_for_each_entry_safe(namespaces, tmp_namespaces, @@ -251,7 +251,7 @@ static int ____thread__set_comm(struct thread *thread, const char *str, list_add(&new->list, &thread->comm_list); if (exec) - unwind__flush_access(thread->mg); + unwind__flush_access(thread->maps); } thread->comm_set = true; @@ -324,19 +324,19 @@ int thread__comm_len(struct thread *thread) size_t thread__fprintf(struct thread *thread, FILE *fp) { return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + - map_groups__fprintf(thread->mg, fp); + maps__fprintf(thread->maps, fp); } int thread__insert_map(struct thread *thread, struct map *map) { int ret; - ret = unwind__prepare_access(thread->mg, map, NULL); + ret = unwind__prepare_access(thread->maps, map, NULL); if (ret) return ret; - map_groups__fixup_overlappings(thread->mg, map, stderr); - map_groups__insert(thread->mg, map); + maps__fixup_overlappings(thread->maps, map, stderr); + maps__insert(thread->maps, map); return 0; } @@ -345,13 +345,13 @@ static int __thread__prepare_access(struct thread *thread) { bool initialized = false; int err = 0; - struct maps *maps = &thread->mg->maps; + struct maps *maps = thread->maps; struct map *map; down_read(&maps->lock); maps__for_each_entry(maps, map) { - err = unwind__prepare_access(thread->mg, map, &initialized); + err = unwind__prepare_access(thread->maps, map, &initialized); if (err || initialized) break; } @@ -371,21 +371,19 @@ static int thread__prepare_access(struct thread *thread) return err; } -static int thread__clone_map_groups(struct thread *thread, - struct thread *parent, - bool do_maps_clone) +static int thread__clone_maps(struct thread *thread, struct thread *parent, bool do_maps_clone) { /* This is new thread, we share map groups for process. */ if (thread->pid_ == parent->pid_) return thread__prepare_access(thread); - if (thread->mg == parent->mg) { + if (thread->maps == parent->maps) { pr_debug("broken map groups on thread %d/%d parent %d/%d\n", thread->pid_, thread->tid, parent->pid_, parent->tid); return 0; } /* But this one is new process, copy maps. */ - return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0; + return do_maps_clone ? maps__clone(thread, parent->maps) : 0; } int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone) @@ -401,7 +399,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bo } thread->ppid = parent->tid; - return thread__clone_map_groups(thread, parent, do_maps_clone); + return thread__clone_maps(thread, parent, do_maps_clone); } void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 51bdb9a7af7f..20b96b5d1f15 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -25,7 +25,7 @@ struct thread { struct rb_node rb_node; struct list_head node; }; - struct map_groups *mg; + struct maps *maps; pid_t pid_; /* Not all tools update this */ pid_t tid; pid_t ppid; @@ -53,7 +53,7 @@ struct namespaces; struct comm; struct thread *thread__new(pid_t pid, pid_t tid); -int thread__init_map_groups(struct thread *thread, struct machine *machine); +int thread__init_maps(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); struct thread *thread__get(struct thread *thread); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index d2a8df01c4a7..7a3dbc259cec 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -81,7 +81,7 @@ static int entry(u64 ip, struct unwind_info *ui) return -1; e->ip = ip; - e->ms.mg = al.mg; + e->ms.maps = al.maps; e->ms.map = al.map; e->ms.sym = al.sym; @@ -200,7 +200,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct unwind_info *ui, ui_buf = { .sample = data, .thread = thread, - .machine = thread->mg->machine, + .machine = thread->maps->machine, .cb = cb, .arg = arg, .max_stack = max_stack, diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6d53347d6744..b4649f5a0c2f 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -578,7 +578,7 @@ static int entry(u64 ip, struct thread *thread, e.ms.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); e.ip = ip; e.ms.map = al.map; - e.ms.mg = al.mg; + e.ms.maps = al.maps; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", @@ -616,26 +616,26 @@ static unw_accessors_t accessors = { .get_proc_name = get_proc_name, }; -static int _unwind__prepare_access(struct map_groups *mg) +static int _unwind__prepare_access(struct maps *maps) { - mg->addr_space = unw_create_addr_space(&accessors, 0); - if (!mg->addr_space) { + maps->addr_space = unw_create_addr_space(&accessors, 0); + if (!maps->addr_space) { pr_err("unwind: Can't create unwind address space.\n"); return -ENOMEM; } - unw_set_caching_policy(mg->addr_space, UNW_CACHE_GLOBAL); + unw_set_caching_policy(maps->addr_space, UNW_CACHE_GLOBAL); return 0; } -static void _unwind__flush_access(struct map_groups *mg) +static void _unwind__flush_access(struct maps *maps) { - unw_flush_cache(mg->addr_space, 0, 0); + unw_flush_cache(maps->addr_space, 0, 0); } -static void _unwind__finish_access(struct map_groups *mg) +static void _unwind__finish_access(struct maps *maps) { - unw_destroy_addr_space(mg->addr_space); + unw_destroy_addr_space(maps->addr_space); } static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, @@ -660,7 +660,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, */ if (max_stack - 1 > 0) { WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); - addr_space = ui->thread->mg->addr_space; + addr_space = ui->thread->maps->addr_space; if (addr_space == NULL) return -1; @@ -709,7 +709,7 @@ static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct unwind_info ui = { .sample = data, .thread = thread, - .machine = thread->mg->machine, + .machine = thread->maps->machine, }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index a24fb57c9b2c..e89a5479b361 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -12,14 +12,12 @@ struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops; -static void unwind__register_ops(struct map_groups *mg, - struct unwind_libunwind_ops *ops) +static void unwind__register_ops(struct maps *maps, struct unwind_libunwind_ops *ops) { - mg->unwind_libunwind_ops = ops; + maps->unwind_libunwind_ops = ops; } -int unwind__prepare_access(struct map_groups *mg, struct map *map, - bool *initialized) +int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized) { const char *arch; enum dso_type dso_type; @@ -29,7 +27,7 @@ int unwind__prepare_access(struct map_groups *mg, struct map *map, if (!dwarf_callchain_users) return 0; - if (mg->addr_space) { + if (maps->addr_space) { pr_debug("unwind: thread map already set, dso=%s\n", map->dso->name); if (initialized) @@ -38,14 +36,14 @@ int unwind__prepare_access(struct map_groups *mg, struct map *map, } /* env->arch is NULL for live-mode (i.e. perf top) */ - if (!mg->machine->env || !mg->machine->env->arch) + if (!maps->machine->env || !maps->machine->env->arch) goto out_register; - dso_type = dso__type(map->dso, mg->machine); + dso_type = dso__type(map->dso, maps->machine); if (dso_type == DSO__TYPE_UNKNOWN) return 0; - arch = perf_env__arch(mg->machine->env); + arch = perf_env__arch(maps->machine->env); if (!strcmp(arch, "x86")) { if (dso_type != DSO__TYPE_64BIT) @@ -60,31 +58,31 @@ int unwind__prepare_access(struct map_groups *mg, struct map *map, return 0; } out_register: - unwind__register_ops(mg, ops); + unwind__register_ops(maps, ops); - err = mg->unwind_libunwind_ops->prepare_access(mg); + err = maps->unwind_libunwind_ops->prepare_access(maps); if (initialized) *initialized = err ? false : true; return err; } -void unwind__flush_access(struct map_groups *mg) +void unwind__flush_access(struct maps *maps) { - if (mg->unwind_libunwind_ops) - mg->unwind_libunwind_ops->flush_access(mg); + if (maps->unwind_libunwind_ops) + maps->unwind_libunwind_ops->flush_access(maps); } -void unwind__finish_access(struct map_groups *mg) +void unwind__finish_access(struct maps *maps) { - if (mg->unwind_libunwind_ops) - mg->unwind_libunwind_ops->finish_access(mg); + if (maps->unwind_libunwind_ops) + maps->unwind_libunwind_ops->finish_access(maps); } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack) { - if (thread->mg->unwind_libunwind_ops) - return thread->mg->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + if (thread->maps->unwind_libunwind_ops) + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 50337c966979..ab8ad469c8de 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -6,7 +6,7 @@ #include <linux/types.h> #include "util/map_symbol.h" -struct map_groups; +struct maps; struct perf_sample; struct thread; @@ -18,9 +18,9 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); struct unwind_libunwind_ops { - int (*prepare_access)(struct map_groups *mg); - void (*flush_access)(struct map_groups *mg); - void (*finish_access)(struct map_groups *mg); + int (*prepare_access)(struct maps *maps); + void (*flush_access)(struct maps *maps); + void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack); @@ -45,20 +45,19 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, #endif int LIBUNWIND__ARCH_REG_ID(int regnum); -int unwind__prepare_access(struct map_groups *mg, struct map *map, - bool *initialized); -void unwind__flush_access(struct map_groups *mg); -void unwind__finish_access(struct map_groups *mg); +int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized); +void unwind__flush_access(struct maps *maps); +void unwind__finish_access(struct maps *maps); #else -static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused, +static inline int unwind__prepare_access(struct maps *maps __maybe_unused, struct map *map __maybe_unused, bool *initialized __maybe_unused) { return 0; } -static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {} -static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {} +static inline void unwind__flush_access(struct maps *maps __maybe_unused) {} +static inline void unwind__finish_access(struct maps *maps __maybe_unused) {} #endif #else static inline int @@ -71,14 +70,14 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, return 0; } -static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused, +static inline int unwind__prepare_access(struct maps *maps __maybe_unused, struct map *map __maybe_unused, bool *initialized __maybe_unused) { return 0; } -static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {} -static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {} +static inline void unwind__flush_access(struct maps *maps __maybe_unused) {} +static inline void unwind__finish_access(struct maps *maps __maybe_unused) {} #endif /* HAVE_DWARF_UNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 6e00793c10ee..3cc91ad048ea 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -144,7 +144,7 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, enum dso_type dso_type = DSO__TYPE_UNKNOWN; struct map *map; - map_groups__for_each_entry(thread->mg, map) { + maps__for_each_entry(thread->maps, map) { struct dso *dso = map->dso; if (!dso || dso->long_name[0] != '/') continue; diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 2a9890c8395a..944183f9ed5a 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -11,10 +11,11 @@ struct process_cmd_struct { char *feature; char *command; - void (*process_fn)(void); + void (*process_fn)(int arg); + int arg; }; -static const char *version_str = "v1.0"; +static const char *version_str = "v1.1"; static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -22,6 +23,7 @@ static int debug_flag; static FILE *outf; static int cpu_model; +static int cpu_stepping; #define MAX_CPUS_IN_ONE_REQ 64 static short max_target_cpus; @@ -39,6 +41,7 @@ static unsigned long long fact_trl; static int out_format_json; static int cmd_help; static int force_online_offline; +static int auto_mode; /* clos related */ static int current_clos = -1; @@ -70,7 +73,16 @@ void debug_printf(const char *format, ...) va_end(args); } -static void update_cpu_model(void) + +int is_clx_n_platform(void) +{ + if (cpu_model == 0x55) + if (cpu_stepping == 0x6 || cpu_stepping == 0x7) + return 1; + return 0; +} + +static int update_cpu_model(void) { unsigned int ebx, ecx, edx; unsigned int fms, family; @@ -80,6 +92,33 @@ static void update_cpu_model(void) cpu_model = (fms >> 4) & 0xf; if (family == 6 || family == 0xf) cpu_model += ((fms >> 16) & 0xf) << 4; + + cpu_stepping = fms & 0xf; + /* only three CascadeLake-N models are supported */ + if (is_clx_n_platform()) { + FILE *fp; + size_t n = 0; + char *line = NULL; + int ret = 1; + + fp = fopen("/proc/cpuinfo", "r"); + if (!fp) + err(-1, "cannot open /proc/cpuinfo\n"); + + while (getline(&line, &n, fp) > 0) { + if (strstr(line, "model name")) { + if (strstr(line, "6252N") || + strstr(line, "6230N") || + strstr(line, "5218N")) + ret = 0; + break; + } + } + free(line); + fclose(fp); + return ret; + } + return 0; } /* Open a file, and exit on failure */ @@ -161,6 +200,11 @@ int get_physical_die_id(int cpu) return ret; } +int get_cpufreq_base_freq(int cpu) +{ + return parse_int_file(0, "/sys/devices/system/cpu/cpu%d/cpufreq/base_frequency", cpu); +} + int get_topo_max_cpus(void) { return topo_max_cpus; @@ -169,7 +213,7 @@ int get_topo_max_cpus(void) static void set_cpu_online_offline(int cpu, int state) { char buffer[128]; - int fd; + int fd, ret; snprintf(buffer, sizeof(buffer), "/sys/devices/system/cpu/cpu%d/online", cpu); @@ -179,9 +223,12 @@ static void set_cpu_online_offline(int cpu, int state) err(-1, "%s open failed", buffer); if (state) - write(fd, "1\n", 2); + ret = write(fd, "1\n", 2); else - write(fd, "0\n", 2); + ret = write(fd, "0\n", 2); + + if (ret == -1) + perror("Online/Offline: Operation failed\n"); close(fd); } @@ -291,6 +338,7 @@ void free_cpu_set(cpu_set_t *cpu_set) } static int cpu_cnt[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE]; +static long long core_mask[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE]; static void set_cpu_present_cpu_mask(void) { size_t size; @@ -315,13 +363,33 @@ static void set_cpu_present_cpu_mask(void) pkg_id = get_physical_package_id(i); if (pkg_id < MAX_PACKAGE_COUNT && - die_id < MAX_DIE_PER_PACKAGE) + die_id < MAX_DIE_PER_PACKAGE) { + int core_id = get_physical_core_id(i); + cpu_cnt[pkg_id][die_id]++; + core_mask[pkg_id][die_id] |= (1ULL << core_id); + } } closedir(dir); } } +int get_core_count(int pkg_id, int die_id) +{ + int cnt = 0; + + if (pkg_id < MAX_PACKAGE_COUNT && die_id < MAX_DIE_PER_PACKAGE) { + int i; + + for (i = 0; i < sizeof(long long) * 8; ++i) { + if (core_mask[pkg_id][die_id] & (1ULL << i)) + cnt++; + } + } + + return cnt; +} + int get_cpu_count(int pkg_id, int die_id) { if (pkg_id < MAX_PACKAGE_COUNT && die_id < MAX_DIE_PER_PACKAGE) @@ -532,12 +600,6 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, if (!ret && !write) *resp = value; break; - case CLOS_PM_QOS_CONFIG: - ret = isst_send_mmio_command(cpu, PM_QOS_CONFIG_OFFSET, - write, &value); - if (!ret && !write) - *resp = value; - break; case CLOS_STATUS: break; default: @@ -562,6 +624,7 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, fprintf(outf, "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x\n", cpu, command, sub_command, parameter, req_data); + return -1; } else { *resp = mbox_cmds.mbox_cmd[0].resp_data; debug_printf( @@ -678,7 +741,7 @@ static void exec_on_get_ctdp_cpu(int cpu, void *arg1, void *arg2, void *arg3, } #define _get_tdp_level(desc, suffix, object, help) \ - static void get_tdp_##object(void) \ + static void get_tdp_##object(int arg) \ { \ struct isst_pkg_ctdp ctdp; \ \ @@ -708,6 +771,152 @@ _get_tdp_level("get-config-current_level", levels, current_level, "Current TDP Level"); _get_tdp_level("get-lock-status", levels, locked, "TDP lock status"); +struct isst_pkg_ctdp clx_n_pkg_dev; + +static int clx_n_get_base_ratio(void) +{ + FILE *fp; + char *begin, *end, *line = NULL; + char number[5]; + float value = 0; + size_t n = 0; + + fp = fopen("/proc/cpuinfo", "r"); + if (!fp) + err(-1, "cannot open /proc/cpuinfo\n"); + + while (getline(&line, &n, fp) > 0) { + if (strstr(line, "model name")) { + /* this is true for CascadeLake-N */ + begin = strstr(line, "@ ") + 2; + end = strstr(line, "GHz"); + strncpy(number, begin, end - begin); + value = atof(number) * 10; + break; + } + } + free(line); + fclose(fp); + + return (int)(value); +} + +static int clx_n_config(int cpu) +{ + int i, ret, pkg_id, die_id; + unsigned long cpu_bf; + struct isst_pkg_ctdp_level_info *ctdp_level; + struct isst_pbf_info *pbf_info; + + ctdp_level = &clx_n_pkg_dev.ctdp_level[0]; + pbf_info = &ctdp_level->pbf_info; + ctdp_level->core_cpumask_size = + alloc_cpu_set(&ctdp_level->core_cpumask); + + /* find the frequency base ratio */ + ctdp_level->tdp_ratio = clx_n_get_base_ratio(); + if (ctdp_level->tdp_ratio == 0) { + debug_printf("CLX: cn base ratio is zero\n"); + ret = -1; + goto error_ret; + } + + /* find the high and low priority frequencies */ + pbf_info->p1_high = 0; + pbf_info->p1_low = ~0; + + pkg_id = get_physical_package_id(cpu); + die_id = get_physical_die_id(cpu); + + for (i = 0; i < topo_max_cpus; i++) { + if (!CPU_ISSET_S(i, present_cpumask_size, present_cpumask)) + continue; + + if (pkg_id != get_physical_package_id(i) || + die_id != get_physical_die_id(i)) + continue; + + CPU_SET_S(i, ctdp_level->core_cpumask_size, + ctdp_level->core_cpumask); + + cpu_bf = parse_int_file(1, + "/sys/devices/system/cpu/cpu%d/cpufreq/base_frequency", + i); + if (cpu_bf > pbf_info->p1_high) + pbf_info->p1_high = cpu_bf; + if (cpu_bf < pbf_info->p1_low) + pbf_info->p1_low = cpu_bf; + } + + if (pbf_info->p1_high == ~0UL) { + debug_printf("CLX: maximum base frequency not set\n"); + ret = -1; + goto error_ret; + } + + if (pbf_info->p1_low == 0) { + debug_printf("CLX: minimum base frequency not set\n"); + ret = -1; + goto error_ret; + } + + /* convert frequencies back to ratios */ + pbf_info->p1_high = pbf_info->p1_high / 100000; + pbf_info->p1_low = pbf_info->p1_low / 100000; + + /* create high priority cpu mask */ + pbf_info->core_cpumask_size = alloc_cpu_set(&pbf_info->core_cpumask); + for (i = 0; i < topo_max_cpus; i++) { + if (!CPU_ISSET_S(i, present_cpumask_size, present_cpumask)) + continue; + + if (pkg_id != get_physical_package_id(i) || + die_id != get_physical_die_id(i)) + continue; + + cpu_bf = parse_int_file(1, + "/sys/devices/system/cpu/cpu%d/cpufreq/base_frequency", + i); + cpu_bf = cpu_bf / 100000; + if (cpu_bf == pbf_info->p1_high) + CPU_SET_S(i, pbf_info->core_cpumask_size, + pbf_info->core_cpumask); + } + + /* extra ctdp & pbf struct parameters */ + ctdp_level->processed = 1; + ctdp_level->pbf_support = 1; /* PBF is always supported and enabled */ + ctdp_level->pbf_enabled = 1; + ctdp_level->fact_support = 0; /* FACT is never supported */ + ctdp_level->fact_enabled = 0; + + return 0; + +error_ret: + free_cpu_set(ctdp_level->core_cpumask); + return ret; +} + +static void dump_clx_n_config_for_cpu(int cpu, void *arg1, void *arg2, + void *arg3, void *arg4) +{ + int ret; + + ret = clx_n_config(cpu); + if (ret) { + perror("isst_get_process_ctdp"); + } else { + struct isst_pkg_ctdp_level_info *ctdp_level; + struct isst_pbf_info *pbf_info; + + ctdp_level = &clx_n_pkg_dev.ctdp_level[0]; + pbf_info = &ctdp_level->pbf_info; + isst_ctdp_display_information(cpu, outf, tdp_level, &clx_n_pkg_dev); + free_cpu_set(ctdp_level->core_cpumask); + free_cpu_set(pbf_info->core_cpumask); + } +} + static void dump_isst_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, void *arg4) { @@ -724,8 +933,10 @@ static void dump_isst_config_for_cpu(int cpu, void *arg1, void *arg2, } } -static void dump_isst_config(void) +static void dump_isst_config(int arg) { + void *fn; + if (cmd_help) { fprintf(stderr, "Print Intel(R) Speed Select Technology Performance profile configuration\n"); @@ -737,14 +948,17 @@ static void dump_isst_config(void) exit(0); } + if (!is_clx_n_platform()) + fn = dump_isst_config_for_cpu; + else + fn = dump_clx_n_config_for_cpu; + isst_ctdp_display_information_start(outf); if (max_target_cpus) - for_each_online_target_cpu_in_set(dump_isst_config_for_cpu, - NULL, NULL, NULL, NULL); + for_each_online_target_cpu_in_set(fn, NULL, NULL, NULL, NULL); else - for_each_online_package_in_set(dump_isst_config_for_cpu, NULL, - NULL, NULL, NULL); + for_each_online_package_in_set(fn, NULL, NULL, NULL, NULL); isst_ctdp_display_information_end(outf); } @@ -787,7 +1001,7 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, } } -static void set_tdp_level(void) +static void set_tdp_level(int arg) { if (cmd_help) { fprintf(stderr, "Set Config TDP level\n"); @@ -812,6 +1026,26 @@ static void set_tdp_level(void) isst_ctdp_display_information_end(outf); } +static void clx_n_dump_pbf_config_for_cpu(int cpu, void *arg1, void *arg2, + void *arg3, void *arg4) +{ + int ret; + + ret = clx_n_config(cpu); + if (ret) { + perror("isst_get_process_ctdp"); + } else { + struct isst_pkg_ctdp_level_info *ctdp_level; + struct isst_pbf_info *pbf_info; + + ctdp_level = &clx_n_pkg_dev.ctdp_level[0]; + pbf_info = &ctdp_level->pbf_info; + isst_pbf_display_information(cpu, outf, tdp_level, pbf_info); + free_cpu_set(ctdp_level->core_cpumask); + free_cpu_set(pbf_info->core_cpumask); + } +} + static void dump_pbf_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, void *arg4) { @@ -827,8 +1061,10 @@ static void dump_pbf_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, } } -static void dump_pbf_config(void) +static void dump_pbf_config(int arg) { + void *fn; + if (cmd_help) { fprintf(stderr, "Print Intel(R) Speed Select Technology base frequency configuration for a TDP level\n"); @@ -842,72 +1078,372 @@ static void dump_pbf_config(void) exit(1); } + if (!is_clx_n_platform()) + fn = dump_pbf_config_for_cpu; + else + fn = clx_n_dump_pbf_config_for_cpu; + isst_ctdp_display_information_start(outf); + if (max_target_cpus) - for_each_online_target_cpu_in_set(dump_pbf_config_for_cpu, NULL, - NULL, NULL, NULL); + for_each_online_target_cpu_in_set(fn, NULL, NULL, NULL, NULL); else - for_each_online_package_in_set(dump_pbf_config_for_cpu, NULL, - NULL, NULL, NULL); + for_each_online_package_in_set(fn, NULL, NULL, NULL, NULL); + isst_ctdp_display_information_end(outf); } -static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, - void *arg4) +static int set_clos_param(int cpu, int clos, int epp, int wt, int min, int max) { + struct isst_clos_config clos_config; int ret; - int status = *(int *)arg4; - ret = isst_set_pbf_fact_status(cpu, 1, status); + ret = isst_pm_get_clos(cpu, clos, &clos_config); if (ret) { - perror("isst_set_pbf"); - } else { - if (status) - isst_display_result(cpu, outf, "base-freq", "enable", - ret); + perror("isst_pm_get_clos"); + return ret; + } + clos_config.clos_min = min; + clos_config.clos_max = max; + clos_config.epp = epp; + clos_config.clos_prop_prio = wt; + ret = isst_set_clos(cpu, clos, &clos_config); + if (ret) { + perror("isst_pm_set_clos"); + return ret; + } + + return 0; +} + +static int set_cpufreq_scaling_min_max(int cpu, int max, int freq) +{ + char buffer[128], freq_str[16]; + int fd, ret, len; + + if (max) + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_max_freq", cpu); + else + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_min_freq", cpu); + + fd = open(buffer, O_WRONLY); + if (fd < 0) + return fd; + + snprintf(freq_str, sizeof(freq_str), "%d", freq); + len = strlen(freq_str); + ret = write(fd, freq_str, len); + if (ret == -1) { + close(fd); + return ret; + } + close(fd); + + return 0; +} + +static int set_clx_pbf_cpufreq_scaling_min_max(int cpu) +{ + struct isst_pkg_ctdp_level_info *ctdp_level; + struct isst_pbf_info *pbf_info; + int i, pkg_id, die_id, freq, freq_high, freq_low; + int ret; + + ret = clx_n_config(cpu); + if (ret) { + perror("set_clx_pbf_cpufreq_scaling_min_max"); + return ret; + } + + ctdp_level = &clx_n_pkg_dev.ctdp_level[0]; + pbf_info = &ctdp_level->pbf_info; + freq_high = pbf_info->p1_high * 100000; + freq_low = pbf_info->p1_low * 100000; + + pkg_id = get_physical_package_id(cpu); + die_id = get_physical_die_id(cpu); + for (i = 0; i < get_topo_max_cpus(); ++i) { + if (pkg_id != get_physical_package_id(i) || + die_id != get_physical_die_id(i)) + continue; + + if (CPU_ISSET_S(i, pbf_info->core_cpumask_size, + pbf_info->core_cpumask)) + freq = freq_high; else - isst_display_result(cpu, outf, "base-freq", "disable", - ret); + freq = freq_low; + + set_cpufreq_scaling_min_max(i, 1, freq); + set_cpufreq_scaling_min_max(i, 0, freq); } + + return 0; } -static void set_pbf_enable(void) +static int set_cpufreq_scaling_min_max_from_cpuinfo(int cpu, int cpuinfo_max, int scaling_max) { - int status = 1; + char buffer[128], min_freq[16]; + int fd, ret, len; - if (cmd_help) { - fprintf(stderr, - "Enable Intel Speed Select Technology base frequency feature [No command arguments are required]\n"); - exit(0); + if (!CPU_ISSET_S(cpu, present_cpumask_size, present_cpumask)) + return -1; + + if (cpuinfo_max) + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d/cpufreq/cpuinfo_max_freq", cpu); + else + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d/cpufreq/cpuinfo_min_freq", cpu); + + fd = open(buffer, O_RDONLY); + if (fd < 0) + return fd; + + len = read(fd, min_freq, sizeof(min_freq)); + close(fd); + + if (len < 0) + return len; + + if (scaling_max) + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_max_freq", cpu); + else + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_min_freq", cpu); + + fd = open(buffer, O_WRONLY); + if (fd < 0) + return fd; + + len = strlen(min_freq); + ret = write(fd, min_freq, len); + if (ret == -1) { + close(fd); + return ret; } + close(fd); - isst_ctdp_display_information_start(outf); - if (max_target_cpus) - for_each_online_target_cpu_in_set(set_pbf_for_cpu, NULL, NULL, - NULL, &status); + return 0; +} + +static void set_scaling_min_to_cpuinfo_max(int cpu) +{ + int i, pkg_id, die_id; + + pkg_id = get_physical_package_id(cpu); + die_id = get_physical_die_id(cpu); + for (i = 0; i < get_topo_max_cpus(); ++i) { + if (pkg_id != get_physical_package_id(i) || + die_id != get_physical_die_id(i)) + continue; + + set_cpufreq_scaling_min_max_from_cpuinfo(i, 1, 0); + } +} + +static void set_scaling_min_to_cpuinfo_min(int cpu) +{ + int i, pkg_id, die_id; + + pkg_id = get_physical_package_id(cpu); + die_id = get_physical_die_id(cpu); + for (i = 0; i < get_topo_max_cpus(); ++i) { + if (pkg_id != get_physical_package_id(i) || + die_id != get_physical_die_id(i)) + continue; + + set_cpufreq_scaling_min_max_from_cpuinfo(i, 0, 0); + } +} + +static void set_scaling_max_to_cpuinfo_max(int cpu) +{ + int i, pkg_id, die_id; + + pkg_id = get_physical_package_id(cpu); + die_id = get_physical_die_id(cpu); + for (i = 0; i < get_topo_max_cpus(); ++i) { + if (pkg_id != get_physical_package_id(i) || + die_id != get_physical_die_id(i)) + continue; + + set_cpufreq_scaling_min_max_from_cpuinfo(i, 1, 1); + } +} + +static int set_core_priority_and_min(int cpu, int mask_size, + cpu_set_t *cpu_mask, int min_high, + int min_low) +{ + int pkg_id, die_id, ret, i; + + if (!CPU_COUNT_S(mask_size, cpu_mask)) + return -1; + + ret = set_clos_param(cpu, 0, 0, 0, min_high, 0xff); + if (ret) + return ret; + + ret = set_clos_param(cpu, 1, 15, 15, min_low, 0xff); + if (ret) + return ret; + + ret = set_clos_param(cpu, 2, 15, 15, min_low, 0xff); + if (ret) + return ret; + + ret = set_clos_param(cpu, 3, 15, 15, min_low, 0xff); + if (ret) + return ret; + + pkg_id = get_physical_package_id(cpu); + die_id = get_physical_die_id(cpu); + for (i = 0; i < get_topo_max_cpus(); ++i) { + int clos; + + if (pkg_id != get_physical_package_id(i) || + die_id != get_physical_die_id(i)) + continue; + + if (CPU_ISSET_S(i, mask_size, cpu_mask)) + clos = 0; + else + clos = 3; + + debug_printf("Associate cpu: %d clos: %d\n", i, clos); + ret = isst_clos_associate(i, clos); + if (ret) { + perror("isst_clos_associate"); + return ret; + } + } + + return 0; +} + +static int set_pbf_core_power(int cpu) +{ + struct isst_pbf_info pbf_info; + struct isst_pkg_ctdp pkg_dev; + int ret; + + ret = isst_get_ctdp_levels(cpu, &pkg_dev); + if (ret) { + perror("isst_get_ctdp_levels"); + return ret; + } + debug_printf("Current_level: %d\n", pkg_dev.current_level); + + ret = isst_get_pbf_info(cpu, pkg_dev.current_level, &pbf_info); + if (ret) { + perror("isst_get_pbf_info"); + return ret; + } + debug_printf("p1_high: %d p1_low: %d\n", pbf_info.p1_high, + pbf_info.p1_low); + + ret = set_core_priority_and_min(cpu, pbf_info.core_cpumask_size, + pbf_info.core_cpumask, + pbf_info.p1_high, pbf_info.p1_low); + if (ret) { + perror("set_core_priority_and_min"); + return ret; + } + + ret = isst_pm_qos_config(cpu, 1, 1); + if (ret) { + perror("isst_pm_qos_config"); + return ret; + } + + return 0; +} + +static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int ret; + int status = *(int *)arg4; + + if (is_clx_n_platform()) { + if (status) { + ret = 0; + if (auto_mode) + set_clx_pbf_cpufreq_scaling_min_max(cpu); + + } else { + ret = -1; + if (auto_mode) { + set_scaling_max_to_cpuinfo_max(cpu); + set_scaling_min_to_cpuinfo_min(cpu); + } + } + goto disp_result; + } + + if (auto_mode) { + if (status) { + ret = set_pbf_core_power(cpu); + if (ret) + goto disp_result; + } else { + isst_pm_qos_config(cpu, 0, 0); + } + } + + ret = isst_set_pbf_fact_status(cpu, 1, status); + if (ret) { + perror("isst_set_pbf"); + if (auto_mode) + isst_pm_qos_config(cpu, 0, 0); + } else { + if (auto_mode) { + if (status) + set_scaling_min_to_cpuinfo_max(cpu); + else + set_scaling_min_to_cpuinfo_min(cpu); + } + } + +disp_result: + if (status) + isst_display_result(cpu, outf, "base-freq", "enable", + ret); else - for_each_online_package_in_set(set_pbf_for_cpu, NULL, NULL, - NULL, &status); - isst_ctdp_display_information_end(outf); + isst_display_result(cpu, outf, "base-freq", "disable", + ret); } -static void set_pbf_disable(void) +static void set_pbf_enable(int arg) { - int status = 0; + int enable = arg; if (cmd_help) { - fprintf(stderr, - "Disable Intel Speed Select Technology base frequency feature [No command arguments are required]\n"); + if (enable) { + fprintf(stderr, + "Enable Intel Speed Select Technology base frequency feature\n"); + fprintf(stderr, + "\tOptional Arguments: -a|--auto : Use priority of cores to set core-power associations\n"); + } else { + + fprintf(stderr, + "Disable Intel Speed Select Technology base frequency feature\n"); + fprintf(stderr, + "\tOptional Arguments: -a|--auto : Also disable core-power associations\n"); + } exit(0); } isst_ctdp_display_information_start(outf); if (max_target_cpus) for_each_online_target_cpu_in_set(set_pbf_for_cpu, NULL, NULL, - NULL, &status); + NULL, &enable); else for_each_online_package_in_set(set_pbf_for_cpu, NULL, NULL, - NULL, &status); + NULL, &enable); isst_ctdp_display_information_end(outf); } @@ -925,7 +1461,7 @@ static void dump_fact_config_for_cpu(int cpu, void *arg1, void *arg2, fact_avx, &fact_info); } -static void dump_fact_config(void) +static void dump_fact_config(int arg) { if (cmd_help) { fprintf(stderr, @@ -960,73 +1496,156 @@ static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, int ret; int status = *(int *)arg4; + if (auto_mode) { + if (status) { + ret = isst_pm_qos_config(cpu, 1, 1); + if (ret) + goto disp_results; + } else { + isst_pm_qos_config(cpu, 0, 0); + } + } + ret = isst_set_pbf_fact_status(cpu, 0, status); - if (ret) + if (ret) { perror("isst_set_fact"); - else { - if (status) { - struct isst_pkg_ctdp pkg_dev; + if (auto_mode) + isst_pm_qos_config(cpu, 0, 0); - ret = isst_get_ctdp_levels(cpu, &pkg_dev); - if (ret) { - isst_display_result(cpu, outf, "turbo-freq", - "enable", ret); - return; - } + goto disp_results; + } + + /* Set TRL */ + if (status) { + struct isst_pkg_ctdp pkg_dev; + + ret = isst_get_ctdp_levels(cpu, &pkg_dev); + if (!ret) ret = isst_set_trl(cpu, fact_trl); - isst_display_result(cpu, outf, "turbo-freq", "enable", - ret); - } else { - /* Since we modified TRL during Fact enable, restore it */ - isst_set_trl_from_current_tdp(cpu, fact_trl); - isst_display_result(cpu, outf, "turbo-freq", "disable", - ret); - } + if (ret && auto_mode) + isst_pm_qos_config(cpu, 0, 0); + } + +disp_results: + if (status) { + isst_display_result(cpu, outf, "turbo-freq", "enable", ret); + } else { + /* Since we modified TRL during Fact enable, restore it */ + isst_set_trl_from_current_tdp(cpu, fact_trl); + isst_display_result(cpu, outf, "turbo-freq", "disable", ret); } } -static void set_fact_enable(void) +static void set_fact_enable(int arg) { - int status = 1; + int i, ret, enable = arg; if (cmd_help) { - fprintf(stderr, - "Enable Intel Speed Select Technology Turbo frequency feature\n"); - fprintf(stderr, - "Optional: -t|--trl : Specify turbo ratio limit\n"); + if (enable) { + fprintf(stderr, + "Enable Intel Speed Select Technology Turbo frequency feature\n"); + fprintf(stderr, + "Optional: -t|--trl : Specify turbo ratio limit\n"); + fprintf(stderr, + "\tOptional Arguments: -a|--auto : Designate specified target CPUs with"); + fprintf(stderr, + "-C|--cpu option as as high priority using core-power feature\n"); + } else { + fprintf(stderr, + "Disable Intel Speed Select Technology turbo frequency feature\n"); + fprintf(stderr, + "Optional: -t|--trl : Specify turbo ratio limit\n"); + fprintf(stderr, + "\tOptional Arguments: -a|--auto : Also disable core-power associations\n"); + } exit(0); } isst_ctdp_display_information_start(outf); if (max_target_cpus) for_each_online_target_cpu_in_set(set_fact_for_cpu, NULL, NULL, - NULL, &status); + NULL, &enable); else for_each_online_package_in_set(set_fact_for_cpu, NULL, NULL, - NULL, &status); + NULL, &enable); isst_ctdp_display_information_end(outf); -} -static void set_fact_disable(void) -{ - int status = 0; + if (enable && auto_mode) { + /* + * When we adjust CLOS param, we have to set for siblings also. + * So for the each user specified CPU, also add the sibling + * in the present_cpu_mask. + */ + for (i = 0; i < get_topo_max_cpus(); ++i) { + char buffer[128], sibling_list[128], *cpu_str; + int fd, len; - if (cmd_help) { - fprintf(stderr, - "Disable Intel Speed Select Technology turbo frequency feature\n"); - fprintf(stderr, - "Optional: -t|--trl : Specify turbo ratio limit\n"); - exit(0); + if (!CPU_ISSET_S(i, target_cpumask_size, target_cpumask)) + continue; + + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", i); + + fd = open(buffer, O_RDONLY); + if (fd < 0) + continue; + + len = read(fd, sibling_list, sizeof(sibling_list)); + close(fd); + + if (len < 0) + continue; + + cpu_str = strtok(sibling_list, ","); + while (cpu_str != NULL) { + int cpu; + + sscanf(cpu_str, "%d", &cpu); + CPU_SET_S(cpu, target_cpumask_size, target_cpumask); + cpu_str = strtok(NULL, ","); + } + } + + for (i = 0; i < get_topo_max_cpus(); ++i) { + int clos; + + if (!CPU_ISSET_S(i, present_cpumask_size, present_cpumask)) + continue; + + ret = set_clos_param(i, 0, 0, 0, 0, 0xff); + if (ret) + goto error_disp; + + ret = set_clos_param(i, 1, 15, 15, 0, 0xff); + if (ret) + goto error_disp; + + ret = set_clos_param(i, 2, 15, 15, 0, 0xff); + if (ret) + goto error_disp; + + ret = set_clos_param(i, 3, 15, 15, 0, 0xff); + if (ret) + goto error_disp; + + if (CPU_ISSET_S(i, target_cpumask_size, target_cpumask)) + clos = 0; + else + clos = 3; + + debug_printf("Associate cpu: %d clos: %d\n", i, clos); + ret = isst_clos_associate(i, clos); + if (ret) + goto error_disp; + } + isst_display_result(i, outf, "turbo-freq --auto", "enable", 0); } - isst_ctdp_display_information_start(outf); - if (max_target_cpus) - for_each_online_target_cpu_in_set(set_fact_for_cpu, NULL, NULL, - NULL, &status); - else - for_each_online_package_in_set(set_fact_for_cpu, NULL, NULL, - NULL, &status); - isst_ctdp_display_information_end(outf); + return; + +error_disp: + isst_display_result(i, outf, "turbo-freq --auto", "enable", ret); + } static void enable_clos_qos_config(int cpu, void *arg1, void *arg2, void *arg3, @@ -1036,31 +1655,36 @@ static void enable_clos_qos_config(int cpu, void *arg1, void *arg2, void *arg3, int status = *(int *)arg4; ret = isst_pm_qos_config(cpu, status, clos_priority_type); - if (ret) { + if (ret) perror("isst_pm_qos_config"); - } else { - if (status) - isst_display_result(cpu, outf, "core-power", "enable", - ret); - else - isst_display_result(cpu, outf, "core-power", "disable", - ret); - } + + if (status) + isst_display_result(cpu, outf, "core-power", "enable", + ret); + else + isst_display_result(cpu, outf, "core-power", "disable", + ret); } -static void set_clos_enable(void) +static void set_clos_enable(int arg) { - int status = 1; + int enable = arg; if (cmd_help) { - fprintf(stderr, "Enable core-power for a package/die\n"); - fprintf(stderr, - "\tClos Enable: Specify priority type with [--priority|-p]\n"); - fprintf(stderr, "\t\t 0: Proportional, 1: Ordered\n"); + if (enable) { + fprintf(stderr, + "Enable core-power for a package/die\n"); + fprintf(stderr, + "\tClos Enable: Specify priority type with [--priority|-p]\n"); + fprintf(stderr, "\t\t 0: Proportional, 1: Ordered\n"); + } else { + fprintf(stderr, + "Disable core-power: [No command arguments are required]\n"); + } exit(0); } - if (cpufreq_sysfs_present()) { + if (enable && cpufreq_sysfs_present()) { fprintf(stderr, "cpufreq subsystem and core-power enable will interfere with each other!\n"); } @@ -1068,30 +1692,10 @@ static void set_clos_enable(void) isst_ctdp_display_information_start(outf); if (max_target_cpus) for_each_online_target_cpu_in_set(enable_clos_qos_config, NULL, - NULL, NULL, &status); + NULL, NULL, &enable); else for_each_online_package_in_set(enable_clos_qos_config, NULL, - NULL, NULL, &status); - isst_ctdp_display_information_end(outf); -} - -static void set_clos_disable(void) -{ - int status = 0; - - if (cmd_help) { - fprintf(stderr, - "Disable core-power: [No command arguments are required]\n"); - exit(0); - } - - isst_ctdp_display_information_start(outf); - if (max_target_cpus) - for_each_online_target_cpu_in_set(enable_clos_qos_config, NULL, - NULL, NULL, &status); - else - for_each_online_package_in_set(enable_clos_qos_config, NULL, - NULL, NULL, &status); + NULL, NULL, &enable); isst_ctdp_display_information_end(outf); } @@ -1109,7 +1713,7 @@ static void dump_clos_config_for_cpu(int cpu, void *arg1, void *arg2, &clos_config); } -static void dump_clos_config(void) +static void dump_clos_config(int arg) { if (cmd_help) { fprintf(stderr, @@ -1145,7 +1749,7 @@ static void get_clos_info_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, isst_clos_display_clos_information(cpu, outf, enable, prio_type); } -static void dump_clos_info(void) +static void dump_clos_info(int arg) { if (cmd_help) { fprintf(stderr, @@ -1188,7 +1792,7 @@ static void set_clos_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, isst_display_result(cpu, outf, "core-power", "config", ret); } -static void set_clos_config(void) +static void set_clos_config(int arg) { if (cmd_help) { fprintf(stderr, @@ -1198,9 +1802,9 @@ static void set_clos_config(void) fprintf(stderr, "\tSpecify clos EPP with [--epp|-e]\n"); fprintf(stderr, "\tSpecify clos Proportional Priority [--weight|-w]\n"); - fprintf(stderr, "\tSpecify clos min with [--min|-n]\n"); - fprintf(stderr, "\tSpecify clos max with [--max|-m]\n"); - fprintf(stderr, "\tSpecify clos desired with [--desired|-d]\n"); + fprintf(stderr, "\tSpecify clos min in MHz with [--min|-n]\n"); + fprintf(stderr, "\tSpecify clos max in MHz with [--max|-m]\n"); + fprintf(stderr, "\tSpecify clos desired in MHz with [--desired|-d]\n"); exit(0); } @@ -1222,7 +1826,7 @@ static void set_clos_config(void) clos_min = 0; } if (clos_max < 0) { - fprintf(stderr, "clos max is not specified, default: 0xff\n"); + fprintf(stderr, "clos max is not specified, default: 25500 MHz\n"); clos_max = 0xff; } if (clos_desired < 0) { @@ -1252,7 +1856,7 @@ static void set_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, isst_display_result(cpu, outf, "core-power", "assoc", ret); } -static void set_clos_assoc(void) +static void set_clos_assoc(int arg) { if (cmd_help) { fprintf(stderr, "Associate a clos id to a CPU\n"); @@ -1286,7 +1890,7 @@ static void get_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, isst_clos_display_assoc_information(cpu, outf, clos); } -static void get_clos_assoc(void) +static void get_clos_assoc(int arg) { if (cmd_help) { fprintf(stderr, "Get associate clos id to a CPU\n"); @@ -1306,27 +1910,36 @@ static void get_clos_assoc(void) isst_ctdp_display_information_end(outf); } +static struct process_cmd_struct clx_n_cmds[] = { + { "perf-profile", "info", dump_isst_config, 0 }, + { "base-freq", "info", dump_pbf_config, 0 }, + { "base-freq", "enable", set_pbf_enable, 1 }, + { "base-freq", "disable", set_pbf_enable, 0 }, + { NULL, NULL, NULL, 0 } +}; + static struct process_cmd_struct isst_cmds[] = { - { "perf-profile", "get-lock-status", get_tdp_locked }, - { "perf-profile", "get-config-levels", get_tdp_levels }, - { "perf-profile", "get-config-version", get_tdp_version }, - { "perf-profile", "get-config-enabled", get_tdp_enabled }, - { "perf-profile", "get-config-current-level", get_tdp_current_level }, - { "perf-profile", "set-config-level", set_tdp_level }, - { "perf-profile", "info", dump_isst_config }, - { "base-freq", "info", dump_pbf_config }, - { "base-freq", "enable", set_pbf_enable }, - { "base-freq", "disable", set_pbf_disable }, - { "turbo-freq", "info", dump_fact_config }, - { "turbo-freq", "enable", set_fact_enable }, - { "turbo-freq", "disable", set_fact_disable }, - { "core-power", "info", dump_clos_info }, - { "core-power", "enable", set_clos_enable }, - { "core-power", "disable", set_clos_disable }, - { "core-power", "config", set_clos_config }, - { "core-power", "get-config", dump_clos_config }, - { "core-power", "assoc", set_clos_assoc }, - { "core-power", "get-assoc", get_clos_assoc }, + { "perf-profile", "get-lock-status", get_tdp_locked, 0 }, + { "perf-profile", "get-config-levels", get_tdp_levels, 0 }, + { "perf-profile", "get-config-version", get_tdp_version, 0 }, + { "perf-profile", "get-config-enabled", get_tdp_enabled, 0 }, + { "perf-profile", "get-config-current-level", get_tdp_current_level, + 0 }, + { "perf-profile", "set-config-level", set_tdp_level, 0 }, + { "perf-profile", "info", dump_isst_config, 0 }, + { "base-freq", "info", dump_pbf_config, 0 }, + { "base-freq", "enable", set_pbf_enable, 1 }, + { "base-freq", "disable", set_pbf_enable, 0 }, + { "turbo-freq", "info", dump_fact_config, 0 }, + { "turbo-freq", "enable", set_fact_enable, 1 }, + { "turbo-freq", "disable", set_fact_enable, 0 }, + { "core-power", "info", dump_clos_info, 0 }, + { "core-power", "enable", set_clos_enable, 1 }, + { "core-power", "disable", set_clos_enable, 0 }, + { "core-power", "config", set_clos_config, 0 }, + { "core-power", "get-config", dump_clos_config, 0 }, + { "core-power", "assoc", set_clos_assoc, 0 }, + { "core-power", "get-assoc", get_clos_assoc, 0 }, { NULL, NULL, NULL } }; @@ -1417,15 +2030,19 @@ static void parse_cmd_args(int argc, int start, char **argv) { "max", required_argument, 0, 'm' }, { "priority", required_argument, 0, 'p' }, { "weight", required_argument, 0, 'w' }, + { "auto", no_argument, 0, 'a' }, { 0, 0, 0, 0 } }; option_index = start; optind = start + 1; - while ((opt = getopt_long(argc, argv, "b:l:t:c:d:e:n:m:p:w:ho", + while ((opt = getopt_long(argc, argv, "b:l:t:c:d:e:n:m:p:w:hoa", long_options, &option_index)) != -1) { switch (opt) { + case 'a': + auto_mode = 1; + break; case 'b': fact_bucket = atoi(optarg); break; @@ -1459,15 +2076,18 @@ static void parse_cmd_args(int argc, int start, char **argv) break; case 'd': clos_desired = atoi(optarg); + clos_desired /= DISP_FREQ_MULTIPLIER; break; case 'e': clos_epp = atoi(optarg); break; case 'n': clos_min = atoi(optarg); + clos_min /= DISP_FREQ_MULTIPLIER; break; case 'm': clos_max = atoi(optarg); + clos_max /= DISP_FREQ_MULTIPLIER; break; case 'p': clos_priority_type = atoi(optarg); @@ -1489,12 +2109,15 @@ static void isst_help(void) TDP, etc.\n"); printf("\nCommands : For feature=perf-profile\n"); printf("\tinfo\n"); - printf("\tget-lock-status\n"); - printf("\tget-config-levels\n"); - printf("\tget-config-version\n"); - printf("\tget-config-enabled\n"); - printf("\tget-config-current-level\n"); - printf("\tset-config-level\n"); + + if (!is_clx_n_platform()) { + printf("\tget-lock-status\n"); + printf("\tget-config-levels\n"); + printf("\tget-config-version\n"); + printf("\tget-config-enabled\n"); + printf("\tget-config-current-level\n"); + printf("\tset-config-level\n"); + } } static void pbf_help(void) @@ -1544,7 +2167,15 @@ static struct process_cmd_help_struct isst_help_cmds[] = { { NULL, NULL } }; -void process_command(int argc, char **argv) +static struct process_cmd_help_struct clx_n_help_cmds[] = { + { "perf-profile", isst_help }, + { "base-freq", pbf_help }, + { NULL, NULL } +}; + +void process_command(int argc, char **argv, + struct process_cmd_help_struct *help_cmds, + struct process_cmd_struct *cmds) { int i = 0, matched = 0; char *feature = argv[optind]; @@ -1555,23 +2186,24 @@ void process_command(int argc, char **argv) debug_printf("feature name [%s] command [%s]\n", feature, cmd); if (!strcmp(cmd, "-h") || !strcmp(cmd, "--help")) { - while (isst_help_cmds[i].feature) { - if (!strcmp(isst_help_cmds[i].feature, feature)) { - isst_help_cmds[i].process_fn(); + while (help_cmds[i].feature) { + if (!strcmp(help_cmds[i].feature, feature)) { + help_cmds[i].process_fn(); exit(0); } ++i; } } - create_cpu_map(); + if (!is_clx_n_platform()) + create_cpu_map(); i = 0; - while (isst_cmds[i].feature) { - if (!strcmp(isst_cmds[i].feature, feature) && - !strcmp(isst_cmds[i].command, cmd)) { + while (cmds[i].feature) { + if (!strcmp(cmds[i].feature, feature) && + !strcmp(cmds[i].command, cmd)) { parse_cmd_args(argc, optind + 1, argv); - isst_cmds[i].process_fn(); + cmds[i].process_fn(cmds[i].arg); matched = 1; break; } @@ -1682,17 +2314,23 @@ static void cmdline(int argc, char **argv) fprintf(stderr, "Feature name and|or command not specified\n"); exit(0); } - update_cpu_model(); + ret = update_cpu_model(); + if (ret) + err(-1, "Invalid CPU model (%d)\n", cpu_model); printf("Intel(R) Speed Select Technology\n"); printf("Executing on CPU model:%d[0x%x]\n", cpu_model, cpu_model); set_max_cpu_num(); set_cpu_present_cpu_mask(); set_cpu_target_cpu_mask(); - ret = isst_fill_platform_info(); - if (ret) - goto out; - process_command(argc, argv); + if (!is_clx_n_platform()) { + ret = isst_fill_platform_info(); + if (ret) + goto out; + process_command(argc, argv, isst_help_cmds, isst_cmds); + } else { + process_command(argc, argv, clx_n_help_cmds, clx_n_cmds); + } out: free_cpu_set(present_cpumask); free_cpu_set(target_cpumask); diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c index 6dee5332c9d3..d14c7bcd327a 100644 --- a/tools/power/x86/intel-speed-select/isst-core.c +++ b/tools/power/x86/intel-speed-select/isst-core.c @@ -13,8 +13,14 @@ int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev) ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_LEVELS_INFO, 0, 0, &resp); - if (ret) - return ret; + if (ret) { + pkg_dev->levels = 0; + pkg_dev->locked = 1; + pkg_dev->current_level = 0; + pkg_dev->version = 0; + pkg_dev->enabled = 0; + return 0; + } debug_printf("cpu:%d CONFIG_TDP_GET_LEVELS_INFO resp:%x\n", cpu, resp); @@ -95,6 +101,69 @@ int isst_get_pwr_info(int cpu, int config_index, return 0; } +void isst_get_uncore_p0_p1_info(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int ret; + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_GET_UNCORE_P0_P1_INFO, 0, + config_index, &resp); + if (ret) { + ctdp_level->uncore_p0 = 0; + ctdp_level->uncore_p1 = 0; + return; + } + + ctdp_level->uncore_p0 = resp & GENMASK(7, 0); + ctdp_level->uncore_p1 = (resp & GENMASK(15, 8)) >> 8; + debug_printf( + "cpu:%d ctdp:%d CONFIG_TDP_GET_UNCORE_P0_P1_INFO resp:%x uncore p0:%d uncore p1:%d\n", + cpu, config_index, resp, ctdp_level->uncore_p0, + ctdp_level->uncore_p1); +} + +void isst_get_p1_info(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int ret; + ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_P1_INFO, 0, + config_index, &resp); + if (ret) { + ctdp_level->sse_p1 = 0; + ctdp_level->avx2_p1 = 0; + ctdp_level->avx512_p1 = 0; + return; + } + + ctdp_level->sse_p1 = resp & GENMASK(7, 0); + ctdp_level->avx2_p1 = (resp & GENMASK(15, 8)) >> 8; + ctdp_level->avx512_p1 = (resp & GENMASK(23, 16)) >> 16; + debug_printf( + "cpu:%d ctdp:%d CONFIG_TDP_GET_P1_INFO resp:%x sse_p1:%d avx2_p1:%d avx512_p1:%d\n", + cpu, config_index, resp, ctdp_level->sse_p1, + ctdp_level->avx2_p1, ctdp_level->avx512_p1); +} + +void isst_get_uncore_mem_freq(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int ret; + ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_MEM_FREQ, + 0, config_index, &resp); + if (ret) { + ctdp_level->mem_freq = 0; + return; + } + + ctdp_level->mem_freq = resp & GENMASK(7, 0); + debug_printf( + "cpu:%d ctdp:%d CONFIG_TDP_GET_MEM_FREQ resp:%x uncore mem_freq:%d\n", + cpu, config_index, resp, ctdp_level->mem_freq); +} + int isst_get_tjmax_info(int cpu, int config_index, struct isst_pkg_ctdp_level_info *ctdp_level) { @@ -149,6 +218,27 @@ int isst_get_coremask_info(int cpu, int config_index, return 0; } +int isst_get_get_trl_from_msr(int cpu, int *trl) +{ + unsigned long long msr_trl; + int ret; + + ret = isst_send_msr_command(cpu, 0x1AD, 0, &msr_trl); + if (ret) + return ret; + + trl[0] = msr_trl & GENMASK(7, 0); + trl[1] = (msr_trl & GENMASK(15, 8)) >> 8; + trl[2] = (msr_trl & GENMASK(23, 16)) >> 16; + trl[3] = (msr_trl & GENMASK(31, 24)) >> 24; + trl[4] = (msr_trl & GENMASK(39, 32)) >> 32; + trl[5] = (msr_trl & GENMASK(47, 40)) >> 40; + trl[6] = (msr_trl & GENMASK(55, 48)) >> 48; + trl[7] = (msr_trl & GENMASK(63, 56)) >> 56; + + return 0; +} + int isst_get_get_trl(int cpu, int level, int avx_level, int *trl) { unsigned int req, resp; @@ -245,12 +335,15 @@ int isst_set_tdp_level(int cpu, int tdp_level) int isst_get_pbf_info(int cpu, int level, struct isst_pbf_info *pbf_info) { + int i, ret, core_cnt, max; unsigned int req, resp; - int i, ret; pbf_info->core_cpumask_size = alloc_cpu_set(&pbf_info->core_cpumask); - for (i = 0; i < 2; ++i) { + core_cnt = get_core_count(get_physical_package_id(cpu), get_physical_die_id(cpu)); + max = core_cnt > 32 ? 2 : 1; + + for (i = 0; i < max; ++i) { unsigned long long mask; int count; @@ -258,7 +351,7 @@ int isst_get_pbf_info(int cpu, int level, struct isst_pbf_info *pbf_info) CONFIG_TDP_PBF_GET_CORE_MASK_INFO, 0, (i << 8) | level, &resp); if (ret) - return ret; + break; debug_printf( "cpu:%d CONFIG_TDP_PBF_GET_CORE_MASK_INFO resp:%x\n", @@ -323,7 +416,7 @@ int isst_set_pbf_fact_status(int cpu, int pbf, int enable) ret = isst_get_ctdp_levels(cpu, &pkg_dev); if (ret) - return ret; + debug_printf("cpu:%d No support for dynamic ISST\n", cpu); current_level = pkg_dev.current_level; @@ -553,7 +646,6 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev) i); ctdp_level = &pkg_dev->ctdp_level[i]; - ctdp_level->processed = 1; ctdp_level->level = i; ctdp_level->control_cpu = cpu; ctdp_level->pkg_id = get_physical_package_id(cpu); @@ -561,7 +653,37 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev) ret = isst_get_ctdp_control(cpu, i, ctdp_level); if (ret) - return ret; + continue; + + pkg_dev->processed = 1; + ctdp_level->processed = 1; + + if (ctdp_level->pbf_support) { + ret = isst_get_pbf_info(cpu, i, &ctdp_level->pbf_info); + if (!ret) + ctdp_level->pbf_found = 1; + } + + if (ctdp_level->fact_support) { + ret = isst_get_fact_info(cpu, i, + &ctdp_level->fact_info); + if (ret) + return ret; + } + + if (!pkg_dev->enabled) { + int freq; + + freq = get_cpufreq_base_freq(cpu); + if (freq > 0) { + ctdp_level->sse_p1 = freq / 100000; + ctdp_level->tdp_ratio = ctdp_level->sse_p1; + } + + isst_get_get_trl_from_msr(cpu, ctdp_level->trl_sse_active_cores); + isst_get_trl_bucket_info(cpu, &ctdp_level->buckets_info); + continue; + } ret = isst_get_tdp_info(cpu, i, ctdp_level); if (ret) @@ -600,22 +722,11 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev) if (ret) return ret; - if (ctdp_level->pbf_support) { - ret = isst_get_pbf_info(cpu, i, &ctdp_level->pbf_info); - if (!ret) - ctdp_level->pbf_found = 1; - } - - if (ctdp_level->fact_support) { - ret = isst_get_fact_info(cpu, i, - &ctdp_level->fact_info); - if (ret) - return ret; - } + isst_get_uncore_p0_p1_info(cpu, i, ctdp_level); + isst_get_p1_info(cpu, i, ctdp_level); + isst_get_uncore_mem_freq(cpu, i, ctdp_level); } - pkg_dev->processed = 1; - return 0; } @@ -649,6 +760,27 @@ int isst_pm_qos_config(int cpu, int enable_clos, int priority_type) unsigned int req, resp; int ret; + if (!enable_clos) { + struct isst_pkg_ctdp pkg_dev; + struct isst_pkg_ctdp_level_info ctdp_level; + + ret = isst_get_ctdp_levels(cpu, &pkg_dev); + if (ret) { + debug_printf("isst_get_ctdp_levels\n"); + return ret; + } + + ret = isst_get_ctdp_control(cpu, pkg_dev.current_level, + &ctdp_level); + if (ret) + return ret; + + if (ctdp_level.fact_enabled) { + debug_printf("Turbo-freq feature must be disabled first\n"); + return -EINVAL; + } + } + ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_QOS_CONFIG, 0, 0, &resp); if (ret) diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c index 40346d534f78..040dd09d5eee 100644 --- a/tools/power/x86/intel-speed-select/isst-display.c +++ b/tools/power/x86/intel-speed-select/isst-display.c @@ -6,8 +6,6 @@ #include "isst.h" -#define DISP_FREQ_MULTIPLIER 100 - static void printcpulist(int str_len, char *str, int mask_size, cpu_set_t *cpu_mask) { @@ -204,6 +202,9 @@ static void _isst_pbf_display_information(int cpu, FILE *outf, int level, pbf_info->p1_low * DISP_FREQ_MULTIPLIER); format_and_print(outf, disp_level + 1, header, value); + if (is_clx_n_platform()) + return; + snprintf(header, sizeof(header), "tjunction-temperature(C)"); snprintf(value, sizeof(value), "%d", pbf_info->t_prochot); format_and_print(outf, disp_level + 1, header, value); @@ -314,7 +315,8 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, char value[256]; int i, base_level = 1; - print_package_info(cpu, outf); + if (pkg_dev->processed) + print_package_info(cpu, outf); for (i = 0; i <= pkg_dev->levels; ++i) { struct isst_pkg_ctdp_level_info *ctdp_level; @@ -334,27 +336,66 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, snprintf(value, sizeof(value), "%d", j); format_and_print(outf, base_level + 4, header, value); - snprintf(header, sizeof(header), "enable-cpu-mask"); - printcpumask(sizeof(value), value, - ctdp_level->core_cpumask_size, - ctdp_level->core_cpumask); - format_and_print(outf, base_level + 4, header, value); - - snprintf(header, sizeof(header), "enable-cpu-list"); - printcpulist(sizeof(value), value, - ctdp_level->core_cpumask_size, - ctdp_level->core_cpumask); - format_and_print(outf, base_level + 4, header, value); + if (ctdp_level->core_cpumask_size) { + snprintf(header, sizeof(header), "enable-cpu-mask"); + printcpumask(sizeof(value), value, + ctdp_level->core_cpumask_size, + ctdp_level->core_cpumask); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), "enable-cpu-list"); + printcpulist(sizeof(value), value, + ctdp_level->core_cpumask_size, + ctdp_level->core_cpumask); + format_and_print(outf, base_level + 4, header, value); + } snprintf(header, sizeof(header), "thermal-design-power-ratio"); snprintf(value, sizeof(value), "%d", ctdp_level->tdp_ratio); format_and_print(outf, base_level + 4, header, value); snprintf(header, sizeof(header), "base-frequency(MHz)"); + if (!ctdp_level->sse_p1) + ctdp_level->sse_p1 = ctdp_level->tdp_ratio; snprintf(value, sizeof(value), "%d", - ctdp_level->tdp_ratio * DISP_FREQ_MULTIPLIER); + ctdp_level->sse_p1 * DISP_FREQ_MULTIPLIER); format_and_print(outf, base_level + 4, header, value); + if (ctdp_level->avx2_p1) { + snprintf(header, sizeof(header), "base-frequency-avx2(MHz)"); + snprintf(value, sizeof(value), "%d", + ctdp_level->avx2_p1 * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 4, header, value); + } + + if (ctdp_level->avx512_p1) { + snprintf(header, sizeof(header), "base-frequency-avx512(MHz)"); + snprintf(value, sizeof(value), "%d", + ctdp_level->avx512_p1 * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 4, header, value); + } + + if (ctdp_level->uncore_p1) { + snprintf(header, sizeof(header), "uncore-frequency-min(MHz)"); + snprintf(value, sizeof(value), "%d", + ctdp_level->uncore_p1 * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 4, header, value); + } + + if (ctdp_level->uncore_p0) { + snprintf(header, sizeof(header), "uncore-frequency-max(MHz)"); + snprintf(value, sizeof(value), "%d", + ctdp_level->uncore_p0 * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 4, header, value); + } + + if (ctdp_level->mem_freq) { + snprintf(header, sizeof(header), "mem-frequency(MHz)"); + snprintf(value, sizeof(value), "%d", + ctdp_level->mem_freq * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 4, header, value); + } + snprintf(header, sizeof(header), "speed-select-turbo-freq"); if (ctdp_level->fact_support) { @@ -377,13 +418,26 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, snprintf(value, sizeof(value), "unsupported"); format_and_print(outf, base_level + 4, header, value); - snprintf(header, sizeof(header), "thermal-design-power(W)"); - snprintf(value, sizeof(value), "%d", ctdp_level->pkg_tdp); - format_and_print(outf, base_level + 4, header, value); + if (is_clx_n_platform()) { + if (ctdp_level->pbf_support) + _isst_pbf_display_information(cpu, outf, + tdp_level, + &ctdp_level->pbf_info, + base_level + 4); + continue; + } - snprintf(header, sizeof(header), "tjunction-max(C)"); - snprintf(value, sizeof(value), "%d", ctdp_level->t_proc_hot); - format_and_print(outf, base_level + 4, header, value); + if (ctdp_level->pkg_tdp) { + snprintf(header, sizeof(header), "thermal-design-power(W)"); + snprintf(value, sizeof(value), "%d", ctdp_level->pkg_tdp); + format_and_print(outf, base_level + 4, header, value); + } + + if (ctdp_level->t_proc_hot) { + snprintf(header, sizeof(header), "tjunction-max(C)"); + snprintf(value, sizeof(value), "%d", ctdp_level->t_proc_hot); + format_and_print(outf, base_level + 4, header, value); + } snprintf(header, sizeof(header), "turbo-ratio-limits-sse"); format_and_print(outf, base_level + 4, header, NULL); @@ -402,41 +456,41 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, DISP_FREQ_MULTIPLIER); format_and_print(outf, base_level + 6, header, value); } - snprintf(header, sizeof(header), "turbo-ratio-limits-avx"); - format_and_print(outf, base_level + 4, header, NULL); - for (j = 0; j < 8; ++j) { - snprintf(header, sizeof(header), "bucket-%d", j); - format_and_print(outf, base_level + 5, header, NULL); - snprintf(header, sizeof(header), "core-count"); - snprintf(value, sizeof(value), "%llu", (ctdp_level->buckets_info >> (j * 8)) & 0xff); - format_and_print(outf, base_level + 6, header, value); + if (ctdp_level->trl_avx_active_cores[0]) { + snprintf(header, sizeof(header), "turbo-ratio-limits-avx2"); + format_and_print(outf, base_level + 4, header, NULL); + for (j = 0; j < 8; ++j) { + snprintf(header, sizeof(header), "bucket-%d", j); + format_and_print(outf, base_level + 5, header, NULL); - snprintf(header, sizeof(header), - "max-turbo-frequency(MHz)"); - snprintf(value, sizeof(value), "%d", - ctdp_level->trl_avx_active_cores[j] * - DISP_FREQ_MULTIPLIER); - format_and_print(outf, base_level + 6, header, value); + snprintf(header, sizeof(header), "core-count"); + snprintf(value, sizeof(value), "%llu", (ctdp_level->buckets_info >> (j * 8)) & 0xff); + format_and_print(outf, base_level + 6, header, value); + + snprintf(header, sizeof(header), "max-turbo-frequency(MHz)"); + snprintf(value, sizeof(value), "%d", ctdp_level->trl_avx_active_cores[j] * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 6, header, value); + } } - snprintf(header, sizeof(header), "turbo-ratio-limits-avx512"); - format_and_print(outf, base_level + 4, header, NULL); - for (j = 0; j < 8; ++j) { - snprintf(header, sizeof(header), "bucket-%d", j); - format_and_print(outf, base_level + 5, header, NULL); + if (ctdp_level->trl_avx_512_active_cores[0]) { + snprintf(header, sizeof(header), "turbo-ratio-limits-avx512"); + format_and_print(outf, base_level + 4, header, NULL); + for (j = 0; j < 8; ++j) { + snprintf(header, sizeof(header), "bucket-%d", j); + format_and_print(outf, base_level + 5, header, NULL); - snprintf(header, sizeof(header), "core-count"); - snprintf(value, sizeof(value), "%llu", (ctdp_level->buckets_info >> (j * 8)) & 0xff); - format_and_print(outf, base_level + 6, header, value); + snprintf(header, sizeof(header), "core-count"); + snprintf(value, sizeof(value), "%llu", (ctdp_level->buckets_info >> (j * 8)) & 0xff); + format_and_print(outf, base_level + 6, header, value); - snprintf(header, sizeof(header), - "max-turbo-frequency(MHz)"); - snprintf(value, sizeof(value), "%d", - ctdp_level->trl_avx_512_active_cores[j] * - DISP_FREQ_MULTIPLIER); + snprintf(header, sizeof(header), "max-turbo-frequency(MHz)"); + snprintf(value, sizeof(value), "%d", ctdp_level->trl_avx_512_active_cores[j] * DISP_FREQ_MULTIPLIER); format_and_print(outf, base_level + 6, header, value); + } } + if (ctdp_level->pbf_support) _isst_pbf_display_information(cpu, outf, i, &ctdp_level->pbf_info, @@ -509,15 +563,15 @@ void isst_clos_display_information(int cpu, FILE *outf, int clos, format_and_print(outf, 5, header, value); snprintf(header, sizeof(header), "clos-min"); - snprintf(value, sizeof(value), "%d", clos_config->clos_min); + snprintf(value, sizeof(value), "%d MHz", clos_config->clos_min * DISP_FREQ_MULTIPLIER); format_and_print(outf, 5, header, value); snprintf(header, sizeof(header), "clos-max"); - snprintf(value, sizeof(value), "%d", clos_config->clos_max); + snprintf(value, sizeof(value), "%d MHz", clos_config->clos_max * DISP_FREQ_MULTIPLIER); format_and_print(outf, 5, header, value); snprintf(header, sizeof(header), "clos-desired"); - snprintf(value, sizeof(value), "%d", clos_config->clos_desired); + snprintf(value, sizeof(value), "%d MHz", clos_config->clos_desired * DISP_FREQ_MULTIPLIER); format_and_print(outf, 5, header, value); format_and_print(outf, 1, NULL, NULL); diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h index d280b27d600d..cdf0f8a6dbbf 100644 --- a/tools/power/x86/intel-speed-select/isst.h +++ b/tools/power/x86/intel-speed-select/isst.h @@ -69,6 +69,8 @@ #define PM_CLOS_OFFSET 0x08 #define PQR_ASSOC_OFFSET 0x20 +#define DISP_FREQ_MULTIPLIER 100 + struct isst_clos_config { int pkg_id; int die_id; @@ -161,6 +163,7 @@ struct isst_pkg_ctdp { extern int get_topo_max_cpus(void); extern int get_cpu_count(int pkg_id, int die_id); +extern int get_core_count(int pkg_id, int die_id); /* Common interfaces */ extern void debug_printf(const char *format, ...); @@ -237,4 +240,6 @@ extern void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd, extern int isst_clos_get_clos_information(int cpu, int *enable, int *type); extern void isst_clos_display_clos_information(int cpu, FILE *outf, int clos_enable, int type); +extern int is_clx_n_platform(void); +extern int get_cpufreq_base_freq(int cpu); #endif diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index efe06d621983..e59eb9e7f923 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -31,15 +31,12 @@ class KunitStatus(Enum): TEST_FAILURE = auto() def create_default_kunitconfig(): - if not os.path.exists(kunit_kernel.KUNITCONFIG_PATH): + if not os.path.exists(kunit_kernel.kunitconfig_path): shutil.copyfile('arch/um/configs/kunit_defconfig', - kunit_kernel.KUNITCONFIG_PATH) + kunit_kernel.kunitconfig_path) def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: - if request.defconfig: - create_default_kunitconfig() - config_start = time.time() success = linux.build_reconfig(request.build_dir) config_end = time.time() @@ -108,15 +105,22 @@ def main(argv, linux=None): run_parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' 'directory.', - type=str, default=None, metavar='build_dir') + type=str, default='', metavar='build_dir') run_parser.add_argument('--defconfig', - help='Uses a default kunitconfig.', + help='Uses a default .kunitconfig.', action='store_true') cli_args = parser.parse_args(argv) if cli_args.subcommand == 'run': + if cli_args.build_dir: + if not os.path.exists(cli_args.build_dir): + os.mkdir(cli_args.build_dir) + kunit_kernel.kunitconfig_path = os.path.join( + cli_args.build_dir, + kunit_kernel.kunitconfig_path) + if cli_args.defconfig: create_default_kunitconfig() diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index bf3876835331..cc5d844ecca1 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -14,7 +14,7 @@ import os import kunit_config KCONFIG_PATH = '.config' -KUNITCONFIG_PATH = 'kunitconfig' +kunitconfig_path = '.kunitconfig' class ConfigError(Exception): """Represents an error trying to configure the Linux kernel.""" @@ -82,7 +82,7 @@ class LinuxSourceTree(object): def __init__(self): self._kconfig = kunit_config.Kconfig() - self._kconfig.read_from_file(KUNITCONFIG_PATH) + self._kconfig.read_from_file(kunitconfig_path) self._ops = LinuxSourceTreeOperations() def clean(self): @@ -111,7 +111,7 @@ class LinuxSourceTree(object): return True def build_reconfig(self, build_dir): - """Creates a new .config if it is not a subset of the kunitconfig.""" + """Creates a new .config if it is not a subset of the .kunitconfig.""" kconfig_path = get_kconfig_path(build_dir) if os.path.exists(kconfig_path): existing_kconfig = kunit_config.Kconfig() @@ -140,10 +140,10 @@ class LinuxSourceTree(object): return False return True - def run_kernel(self, args=[], timeout=None, build_dir=None): + def run_kernel(self, args=[], timeout=None, build_dir=''): args.extend(['mem=256M']) process = self._ops.linux_bin(args, timeout, build_dir) - with open('test.log', 'w') as f: + with open(os.path.join(build_dir, 'test.log'), 'w') as f: for line in process.stdout: f.write(line.rstrip().decode('ascii') + '\n') yield line.rstrip().decode('ascii') diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 4a12baa0cd4e..cba97756ac4a 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -174,6 +174,7 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 assert self.linux_source_mock.run_kernel.call_count == 1 + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_passes_args_fail(self): @@ -199,7 +200,14 @@ class KUnitMainTest(unittest.TestCase): timeout = 3453 kunit.main(['run', '--timeout', str(timeout)], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 - self.linux_source_mock.run_kernel.assert_called_once_with(timeout=timeout) + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=timeout) + self.print_mock.assert_any_call(StrContains('Testing complete.')) + + def test_run_builddir(self): + build_dir = '.kunit' + kunit.main(['run', '--build_dir', build_dir], self.linux_source_mock) + assert self.linux_source_mock.build_reconfig.call_count == 1 + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir=build_dir, timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) if __name__ == '__main__': diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index c4a9196d794c..6aca8d5be159 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -5,6 +5,7 @@ ldflags-y += --wrap=devm_ioremap_nocache ldflags-y += --wrap=devm_memremap ldflags-y += --wrap=devm_memunmap ldflags-y += --wrap=ioremap_nocache +ldflags-y += --wrap=ioremap ldflags-y += --wrap=iounmap ldflags-y += --wrap=memunmap ldflags-y += --wrap=__devm_request_region diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 3f55f2f99112..6271ac757a4b 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -193,6 +193,12 @@ void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) } EXPORT_SYMBOL(__wrap_ioremap_nocache); +void __iomem *__wrap_ioremap(resource_size_t offset, unsigned long size) +{ + return __nfit_test_ioremap(offset, size, ioremap); +} +EXPORT_SYMBOL(__wrap_ioremap); + void __iomem *__wrap_ioremap_wc(resource_size_t offset, unsigned long size) { return __nfit_test_ioremap(offset, size, ioremap_wc); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 0fb95f25944d..b001c602414b 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -13,6 +13,7 @@ TARGETS += efivarfs TARGETS += exec TARGETS += filesystems TARGETS += filesystems/binderfs +TARGETS += filesystems/epoll TARGETS += firmware TARGETS += ftrace TARGETS += futex @@ -88,10 +89,10 @@ override LDFLAGS = endif ifneq ($(O),) - BUILD := $(abs_objtree) + BUILD := $(O) else ifneq ($(KBUILD_OUTPUT),) - BUILD := $(abs_objtree)/kselftest + BUILD := $(KBUILD_OUTPUT)/kselftest else BUILD := $(shell pwd) DEFAULT_INSTALL_HDR_PATH := 1 @@ -104,7 +105,6 @@ include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) export KSFT_KHDR_INSTALL_DONE := 1 export BUILD -#$(info abd_objtree = $(abs_objtree) BUILD = $(BUILD)) # build and run gpio when output directory is the src dir. # gpio has dependency on tools/gpio and builds tools/gpio diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 4865116b96c7..1ff0a9f49c01 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -37,5 +37,7 @@ libbpf.so.* test_hashmap test_btf_dump xdping +test_cpp /no_alu32 /bpf_gcc +bpf_helper_defs.h diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 085678d88ef8..e2fd6f8d579c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -71,7 +71,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \ # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ - test_lirc_mode2_user xdping + test_lirc_mode2_user xdping test_cpp TEST_CUSTOM_PROGS = urandom_read @@ -120,9 +120,9 @@ force: $(BPFOBJ): force $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ -BPF_HELPERS := $(BPFDIR)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) -$(BPFDIR)/bpf_helper_defs.h: - $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ bpf_helper_defs.h +BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) +$(OUTPUT)/bpf_helper_defs.h: + $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, @@ -317,6 +317,10 @@ verifier/tests.h: verifier/*.c $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) $(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ +# Make sure we are able to include and link libbpf against c++. +$(OUTPUT)/test_cpp: test_cpp.cpp $(BPFOBJ) + $(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@ + EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 15c7378362dd..b426bf2f97e4 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -2,25 +2,21 @@ /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#define PROG_CNT 3 - -void test_fexit_bpf2bpf(void) +static void test_fexit_bpf2bpf_common(const char *obj_file, + const char *target_obj_file, + int prog_cnt, + const char **prog_name) { - const char *prog_name[PROG_CNT] = { - "fexit/test_pkt_access", - "fexit/test_pkt_access_subprog1", - "fexit/test_pkt_access_subprog2", - }; struct bpf_object *obj = NULL, *pkt_obj; int err, pkt_fd, i; - struct bpf_link *link[PROG_CNT] = {}; - struct bpf_program *prog[PROG_CNT]; + struct bpf_link **link = NULL; + struct bpf_program **prog = NULL; __u32 duration, retval; struct bpf_map *data_map; const int zero = 0; - u64 result[PROG_CNT]; + u64 *result = NULL; - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_UNSPEC, + err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) return; @@ -28,7 +24,14 @@ void test_fexit_bpf2bpf(void) .attach_prog_fd = pkt_fd, ); - obj = bpf_object__open_file("./fexit_bpf2bpf.o", &opts); + link = calloc(sizeof(struct bpf_link *), prog_cnt); + prog = calloc(sizeof(struct bpf_program *), prog_cnt); + result = malloc(prog_cnt * sizeof(u64)); + if (CHECK(!link || !prog || !result, "alloc_memory", + "failed to alloc memory")) + goto close_prog; + + obj = bpf_object__open_file(obj_file, &opts); if (CHECK(IS_ERR_OR_NULL(obj), "obj_open", "failed to open fexit_bpf2bpf: %ld\n", PTR_ERR(obj))) @@ -38,7 +41,7 @@ void test_fexit_bpf2bpf(void) if (CHECK(err, "obj_load", "err %d\n", err)) goto close_prog; - for (i = 0; i < PROG_CNT; i++) { + for (i = 0; i < prog_cnt; i++) { prog[i] = bpf_object__find_program_by_title(obj, prog_name[i]); if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name[i])) goto close_prog; @@ -56,21 +59,54 @@ void test_fexit_bpf2bpf(void) "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result); + err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, result); if (CHECK(err, "get_result", "failed to get output data: %d\n", err)) goto close_prog; - for (i = 0; i < PROG_CNT; i++) + for (i = 0; i < prog_cnt; i++) if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %ld\n", result[i])) goto close_prog; close_prog: - for (i = 0; i < PROG_CNT; i++) + for (i = 0; i < prog_cnt; i++) if (!IS_ERR_OR_NULL(link[i])) bpf_link__destroy(link[i]); if (!IS_ERR_OR_NULL(obj)) bpf_object__close(obj); bpf_object__close(pkt_obj); + free(link); + free(prog); + free(result); +} + +static void test_target_no_callees(void) +{ + const char *prog_name[] = { + "fexit/test_pkt_md_access", + }; + test_fexit_bpf2bpf_common("./fexit_bpf2bpf_simple.o", + "./test_pkt_md_access.o", + ARRAY_SIZE(prog_name), + prog_name); +} + +static void test_target_yes_callees(void) +{ + const char *prog_name[] = { + "fexit/test_pkt_access", + "fexit/test_pkt_access_subprog1", + "fexit/test_pkt_access_subprog2", + }; + test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", + "./test_pkt_access.o", + ARRAY_SIZE(prog_name), + prog_name); +} + +void test_fexit_bpf2bpf(void) +{ + test_target_no_callees(); + test_target_yes_callees(); } diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index d2af9f039df5..615f7c6bca77 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -6,28 +6,28 @@ char _license[] SEC("license") = "GPL"; -static volatile __u64 test1_result; +__u64 test1_result = 0; BPF_TRACE_1("fentry/bpf_fentry_test1", test1, int, a) { test1_result = a == 1; return 0; } -static volatile __u64 test2_result; +__u64 test2_result = 0; BPF_TRACE_2("fentry/bpf_fentry_test2", test2, int, a, __u64, b) { test2_result = a == 2 && b == 3; return 0; } -static volatile __u64 test3_result; +__u64 test3_result = 0; BPF_TRACE_3("fentry/bpf_fentry_test3", test3, char, a, int, b, __u64, c) { test3_result = a == 4 && b == 5 && c == 6; return 0; } -static volatile __u64 test4_result; +__u64 test4_result = 0; BPF_TRACE_4("fentry/bpf_fentry_test4", test4, void *, a, char, b, int, c, __u64, d) { @@ -35,7 +35,7 @@ BPF_TRACE_4("fentry/bpf_fentry_test4", test4, return 0; } -static volatile __u64 test5_result; +__u64 test5_result = 0; BPF_TRACE_5("fentry/bpf_fentry_test5", test5, __u64, a, void *, b, short, c, int, d, __u64, e) { @@ -44,7 +44,7 @@ BPF_TRACE_5("fentry/bpf_fentry_test5", test5, return 0; } -static volatile __u64 test6_result; +__u64 test6_result = 0; BPF_TRACE_6("fentry/bpf_fentry_test6", test6, __u64, a, void *, b, short, c, int, d, void *, e, __u64, f) { diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c index 525d47d7b589..2d211ee98a1c 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -8,7 +8,7 @@ struct sk_buff { unsigned int len; }; -static volatile __u64 test_result; +__u64 test_result = 0; BPF_TRACE_2("fexit/test_pkt_access", test_main, struct sk_buff *, skb, int, ret) { @@ -23,7 +23,7 @@ BPF_TRACE_2("fexit/test_pkt_access", test_main, return 0; } -static volatile __u64 test_result_subprog1; +__u64 test_result_subprog1 = 0; BPF_TRACE_2("fexit/test_pkt_access_subprog1", test_subprog1, struct sk_buff *, skb, int, ret) { @@ -56,7 +56,7 @@ struct args_subprog2 { __u64 args[5]; __u64 ret; }; -static volatile __u64 test_result_subprog2; +__u64 test_result_subprog2 = 0; SEC("fexit/test_pkt_access_subprog2") int test_subprog2(struct args_subprog2 *ctx) { diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c new file mode 100644 index 000000000000..ebc0ab7f0f5c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_trace_helpers.h" + +struct sk_buff { + unsigned int len; +}; + +__u64 test_result = 0; +BPF_TRACE_2("fexit/test_pkt_md_access", test_main2, + struct sk_buff *, skb, int, ret) +{ + int len; + + __builtin_preserve_access_index(({ + len = skb->len; + })); + if (len != 74 || ret != 0) + return 0; + + test_result = 1; + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c index 2487e98edb34..86db0d60fb6e 100644 --- a/tools/testing/selftests/bpf/progs/fexit_test.c +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -6,28 +6,28 @@ char _license[] SEC("license") = "GPL"; -static volatile __u64 test1_result; +__u64 test1_result = 0; BPF_TRACE_2("fexit/bpf_fentry_test1", test1, int, a, int, ret) { test1_result = a == 1 && ret == 2; return 0; } -static volatile __u64 test2_result; +__u64 test2_result = 0; BPF_TRACE_3("fexit/bpf_fentry_test2", test2, int, a, __u64, b, int, ret) { test2_result = a == 2 && b == 3 && ret == 5; return 0; } -static volatile __u64 test3_result; +__u64 test3_result = 0; BPF_TRACE_4("fexit/bpf_fentry_test3", test3, char, a, int, b, __u64, c, int, ret) { test3_result = a == 4 && b == 5 && c == 6 && ret == 15; return 0; } -static volatile __u64 test4_result; +__u64 test4_result = 0; BPF_TRACE_5("fexit/bpf_fentry_test4", test4, void *, a, char, b, int, c, __u64, d, int, ret) { @@ -37,7 +37,7 @@ BPF_TRACE_5("fexit/bpf_fentry_test4", test4, return 0; } -static volatile __u64 test5_result; +__u64 test5_result = 0; BPF_TRACE_6("fexit/bpf_fentry_test5", test5, __u64, a, void *, b, short, c, int, d, __u64, e, int, ret) { @@ -46,7 +46,7 @@ BPF_TRACE_6("fexit/bpf_fentry_test5", test5, return 0; } -static volatile __u64 test6_result; +__u64 test6_result = 0; BPF_TRACE_7("fexit/bpf_fentry_test6", test6, __u64, a, void *, b, short, c, int, d, void *, e, __u64, f, int, ret) diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c index 0d2ec9fbcf61..e808791b7047 100644 --- a/tools/testing/selftests/bpf/progs/test_mmap.c +++ b/tools/testing/selftests/bpf/progs/test_mmap.c @@ -15,8 +15,8 @@ struct { __type(value, __u64); } data_map SEC(".maps"); -static volatile __u64 in_val; -static volatile __u64 out_val; +__u64 in_val = 0; +__u64 out_val = 0; SEC("raw_tracepoint/sys_enter") int test_mmap(void *ctx) diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 3d039e18bf82..1db2623021ad 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -27,8 +27,8 @@ int _version SEC("version") = 1; } #endif -SEC("test1") -int process(struct __sk_buff *skb) +SEC("classifier/test_pkt_md_access") +int test_pkt_md_access(struct __sk_buff *skb) { TEST_FIELD(__u8, len, 0xFF); TEST_FIELD(__u16, len, 0xFFFF); diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 2e233613d1fc..7fa4595d2b66 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -131,6 +131,7 @@ int bpf_testcb(struct bpf_sock_ops *skops) g.bytes_received = skops->bytes_received; g.bytes_acked = skops->bytes_acked; } + g.num_close_events++; bpf_map_update_elem(&global_map, &key, &g, BPF_ANY); } diff --git a/tools/lib/bpf/test_libbpf.c b/tools/testing/selftests/bpf/test_cpp.cpp index f0eb2727b766..f0eb2727b766 100644 --- a/tools/lib/bpf/test_libbpf.c +++ b/tools/testing/selftests/bpf/test_cpp.cpp diff --git a/tools/testing/selftests/bpf/test_ftrace.sh b/tools/testing/selftests/bpf/test_ftrace.sh new file mode 100755 index 000000000000..20de7bb873bc --- /dev/null +++ b/tools/testing/selftests/bpf/test_ftrace.sh @@ -0,0 +1,39 @@ +#!/bin/bash + +TR=/sys/kernel/debug/tracing/ +clear_trace() { # reset trace output + echo > $TR/trace +} + +disable_tracing() { # stop trace recording + echo 0 > $TR/tracing_on +} + +enable_tracing() { # start trace recording + echo 1 > $TR/tracing_on +} + +reset_tracer() { # reset the current tracer + echo nop > $TR/current_tracer +} + +disable_tracing +clear_trace + +echo "" > $TR/set_ftrace_filter +echo '*printk* *console* *wake* *serial* *lock*' > $TR/set_ftrace_notrace + +echo "bpf_prog_test*" > $TR/set_graph_function +echo "" > $TR/set_graph_notrace + +echo function_graph > $TR/current_tracer + +enable_tracing +./test_progs -t fentry +./test_progs -t fexit +disable_tracing +clear_trace + +reset_tracer + +exit 0 diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c index 9220747c069d..356351c0ac28 100644 --- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c @@ -120,7 +120,7 @@ int check_ancestor_cgroup_ids(int prog_id) int err = 0; int map_fd; - expected_ids[0] = 0x100000001; /* root cgroup */ + expected_ids[0] = get_cgroup_id("/.."); /* root cgroup */ expected_ids[1] = get_cgroup_id(""); expected_ids[2] = get_cgroup_id(CGROUP_PATH); expected_ids[3] = 0; /* non-existent cgroup */ diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 3845144e2c91..4a851513c842 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -240,14 +240,14 @@ static int sockmap_init_sockets(int verbose) addr.sin_port = htons(S1_PORT); err = bind(s1, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0) { - perror("bind s1 failed()\n"); + perror("bind s1 failed()"); return errno; } addr.sin_port = htons(S2_PORT); err = bind(s2, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0) { - perror("bind s2 failed()\n"); + perror("bind s2 failed()"); return errno; } @@ -255,14 +255,14 @@ static int sockmap_init_sockets(int verbose) addr.sin_port = htons(S1_PORT); err = listen(s1, 32); if (err < 0) { - perror("listen s1 failed()\n"); + perror("listen s1 failed()"); return errno; } addr.sin_port = htons(S2_PORT); err = listen(s2, 32); if (err < 0) { - perror("listen s1 failed()\n"); + perror("listen s1 failed()"); return errno; } @@ -270,14 +270,14 @@ static int sockmap_init_sockets(int verbose) addr.sin_port = htons(S1_PORT); err = connect(c1, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0 && errno != EINPROGRESS) { - perror("connect c1 failed()\n"); + perror("connect c1 failed()"); return errno; } addr.sin_port = htons(S2_PORT); err = connect(c2, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0 && errno != EINPROGRESS) { - perror("connect c2 failed()\n"); + perror("connect c2 failed()"); return errno; } else if (err < 0) { err = 0; @@ -286,13 +286,13 @@ static int sockmap_init_sockets(int verbose) /* Accept Connecrtions */ p1 = accept(s1, NULL, NULL); if (p1 < 0) { - perror("accept s1 failed()\n"); + perror("accept s1 failed()"); return errno; } p2 = accept(s2, NULL, NULL); if (p2 < 0) { - perror("accept s1 failed()\n"); + perror("accept s1 failed()"); return errno; } @@ -332,6 +332,10 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, int i, fp; file = fopen(".sendpage_tst.tmp", "w+"); + if (!file) { + perror("create file for sendpage"); + return 1; + } for (i = 0; i < iov_length * cnt; i++, k++) fwrite(&k, sizeof(char), 1, file); fflush(file); @@ -339,12 +343,17 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, fclose(file); fp = open(".sendpage_tst.tmp", O_RDONLY); + if (fp < 0) { + perror("reopen file for sendpage"); + return 1; + } + clock_gettime(CLOCK_MONOTONIC, &s->start); for (i = 0; i < cnt; i++) { int sent = sendfile(fd, fp, NULL, iov_length); if (!drop && sent < 0) { - perror("send loop error:"); + perror("send loop error"); close(fp); return sent; } else if (drop && sent >= 0) { @@ -463,7 +472,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, int sent = sendmsg(fd, &msg, flags); if (!drop && sent < 0) { - perror("send loop error:"); + perror("send loop error"); goto out_errno; } else if (drop && sent >= 0) { printf("send loop error expected: %i\n", sent); @@ -499,7 +508,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, total_bytes -= txmsg_pop_total; err = clock_gettime(CLOCK_MONOTONIC, &s->start); if (err < 0) - perror("recv start time: "); + perror("recv start time"); while (s->bytes_recvd < total_bytes) { if (txmsg_cork) { timeout.tv_sec = 0; @@ -543,7 +552,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, if (recv < 0) { if (errno != EWOULDBLOCK) { clock_gettime(CLOCK_MONOTONIC, &s->end); - perror("recv failed()\n"); + perror("recv failed()"); goto out_errno; } } @@ -557,7 +566,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, errno = msg_verify_data(&msg, recv, chunk_sz); if (errno) { - perror("data verify msg failed\n"); + perror("data verify msg failed"); goto out_errno; } if (recvp) { @@ -565,7 +574,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, recvp, chunk_sz); if (errno) { - perror("data verify msg_peek failed\n"); + perror("data verify msg_peek failed"); goto out_errno; } } @@ -654,7 +663,7 @@ static int sendmsg_test(struct sockmap_options *opt) err = 0; exit(err ? 1 : 0); } else if (rxpid == -1) { - perror("msg_loop_rx: "); + perror("msg_loop_rx"); return errno; } @@ -681,7 +690,7 @@ static int sendmsg_test(struct sockmap_options *opt) s.bytes_recvd, recvd_Bps, recvd_Bps/giga); exit(err ? 1 : 0); } else if (txpid == -1) { - perror("msg_loop_tx: "); + perror("msg_loop_tx"); return errno; } @@ -715,7 +724,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt) /* Ping/Pong data from client to server */ sc = send(c1, buf, sizeof(buf), 0); if (sc < 0) { - perror("send failed()\n"); + perror("send failed()"); return sc; } @@ -748,7 +757,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt) rc = recv(i, buf, sizeof(buf), 0); if (rc < 0) { if (errno != EWOULDBLOCK) { - perror("recv failed()\n"); + perror("recv failed()"); return rc; } } @@ -760,7 +769,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt) sc = send(i, buf, rc, 0); if (sc < 0) { - perror("send failed()\n"); + perror("send failed()"); return sc; } } diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h index 7bcfa6207005..6220b95cbd02 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf.h +++ b/tools/testing/selftests/bpf/test_tcpbpf.h @@ -13,5 +13,6 @@ struct tcpbpf_globals { __u64 bytes_received; __u64 bytes_acked; __u32 num_listen; + __u32 num_close_events; }; #endif diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 716b4e3be581..3ae127620463 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -16,6 +16,9 @@ #include "test_tcpbpf.h" +/* 3 comes from one listening socket + both ends of the connection */ +#define EXPECTED_CLOSE_EVENTS 3 + #define EXPECT_EQ(expected, actual, fmt) \ do { \ if ((expected) != (actual)) { \ @@ -23,13 +26,14 @@ " Actual: %" fmt "\n" \ " Expected: %" fmt "\n", \ (actual), (expected)); \ - goto err; \ + ret--; \ } \ } while (0) int verify_result(const struct tcpbpf_globals *result) { __u32 expected_events; + int ret = 0; expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) | (1 << BPF_SOCK_OPS_RWND_INIT) | @@ -48,15 +52,15 @@ int verify_result(const struct tcpbpf_globals *result) EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32); EXPECT_EQ(0, result->good_cb_test_rv, PRIu32); EXPECT_EQ(1, result->num_listen, PRIu32); + EXPECT_EQ(EXPECTED_CLOSE_EVENTS, result->num_close_events, PRIu32); - return 0; -err: - return -1; + return ret; } int verify_sockopt_result(int sock_map_fd) { __u32 key = 0; + int ret = 0; int res; int rv; @@ -69,9 +73,7 @@ int verify_sockopt_result(int sock_map_fd) rv = bpf_map_lookup_elem(sock_map_fd, &key, &res); EXPECT_EQ(0, rv, "d"); EXPECT_EQ(1, res, "d"); - return 0; -err: - return -1; + return ret; } static int bpf_find_map(const char *test, struct bpf_object *obj, @@ -96,6 +98,7 @@ int main(int argc, char **argv) int error = EXIT_FAILURE; struct bpf_object *obj; int cg_fd = -1; + int retry = 10; __u32 key = 0; int rv; @@ -134,12 +137,20 @@ int main(int argc, char **argv) if (sock_map_fd < 0) goto err; +retry_lookup: rv = bpf_map_lookup_elem(map_fd, &key, &g); if (rv != 0) { printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); goto err; } + if (g.num_close_events != EXPECTED_CLOSE_EVENTS && retry--) { + printf("Unexpected number of close events (%d), retrying!\n", + g.num_close_events); + usleep(100); + goto retry_lookup; + } + if (verify_result(&g)) { printf("FAILED: Wrong stats\n"); goto err; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index d27fd929abb9..87eaa49609a0 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -408,10 +408,10 @@ static void update_map(int fd, int index) assert(!bpf_map_update_elem(fd, &index, &value, 0)); } -static int create_prog_dummy1(enum bpf_prog_type prog_type) +static int create_prog_dummy_simple(enum bpf_prog_type prog_type, int ret) { struct bpf_insn prog[] = { - BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_MOV64_IMM(BPF_REG_0, ret), BPF_EXIT_INSN(), }; @@ -419,14 +419,15 @@ static int create_prog_dummy1(enum bpf_prog_type prog_type) ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_dummy2(enum bpf_prog_type prog_type, int mfd, int idx) +static int create_prog_dummy_loop(enum bpf_prog_type prog_type, int mfd, + int idx, int ret) { struct bpf_insn prog[] = { BPF_MOV64_IMM(BPF_REG_3, idx), BPF_LD_MAP_FD(BPF_REG_2, mfd), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), - BPF_MOV64_IMM(BPF_REG_0, 41), + BPF_MOV64_IMM(BPF_REG_0, ret), BPF_EXIT_INSN(), }; @@ -435,10 +436,9 @@ static int create_prog_dummy2(enum bpf_prog_type prog_type, int mfd, int idx) } static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, - int p1key) + int p1key, int p2key, int p3key) { - int p2key = 1; - int mfd, p1fd, p2fd; + int mfd, p1fd, p2fd, p3fd; mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), sizeof(int), max_elem, 0); @@ -449,23 +449,24 @@ static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, return -1; } - p1fd = create_prog_dummy1(prog_type); - p2fd = create_prog_dummy2(prog_type, mfd, p2key); - if (p1fd < 0 || p2fd < 0) - goto out; + p1fd = create_prog_dummy_simple(prog_type, 42); + p2fd = create_prog_dummy_loop(prog_type, mfd, p2key, 41); + p3fd = create_prog_dummy_simple(prog_type, 24); + if (p1fd < 0 || p2fd < 0 || p3fd < 0) + goto err; if (bpf_map_update_elem(mfd, &p1key, &p1fd, BPF_ANY) < 0) - goto out; + goto err; if (bpf_map_update_elem(mfd, &p2key, &p2fd, BPF_ANY) < 0) - goto out; + goto err; + if (bpf_map_update_elem(mfd, &p3key, &p3fd, BPF_ANY) < 0) { +err: + close(mfd); + mfd = -1; + } + close(p3fd); close(p2fd); close(p1fd); - return mfd; -out: - close(p2fd); - close(p1fd); - close(mfd); - return -1; } static int create_map_in_map(void) @@ -684,7 +685,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } if (*fixup_prog1) { - map_fds[4] = create_prog_array(prog_type, 4, 0); + map_fds[4] = create_prog_array(prog_type, 4, 0, 1, 2); do { prog[*fixup_prog1].imm = map_fds[4]; fixup_prog1++; @@ -692,7 +693,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } if (*fixup_prog2) { - map_fds[5] = create_prog_array(prog_type, 8, 7); + map_fds[5] = create_prog_array(prog_type, 8, 7, 1, 2); do { prog[*fixup_prog2].imm = map_fds[5]; fixup_prog2++; diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index ebcbf154c460..604b46151736 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -455,7 +455,7 @@ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7), /* bpf_tail_call() */ - BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 3), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), @@ -478,7 +478,7 @@ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), BPF_EMIT_CALL(BPF_FUNC_sk_release), /* bpf_tail_call() */ - BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 3), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), @@ -497,7 +497,7 @@ BPF_SK_LOOKUP(sk_lookup_tcp), /* bpf_tail_call() */ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), - BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 3), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), diff --git a/tools/testing/selftests/bpf/verifier/runtime_jit.c b/tools/testing/selftests/bpf/verifier/runtime_jit.c index a9a8f620e71c..94c399d1faca 100644 --- a/tools/testing/selftests/bpf/verifier/runtime_jit.c +++ b/tools/testing/selftests/bpf/verifier/runtime_jit.c @@ -27,6 +27,19 @@ { "runtime/jit: tail_call within bounds, no prog", .insns = { + BPF_MOV64_IMM(BPF_REG_3, 3), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "runtime/jit: tail_call within bounds, key 2", + .insns = { BPF_MOV64_IMM(BPF_REG_3, 2), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), @@ -35,9 +48,147 @@ }, .fixup_prog1 = { 1 }, .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 2 / key 2, first branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 13), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 2 / key 2, second branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 14), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 0 / key 2, first branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 13), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 0 / key 2, second branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 14), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 42, +}, +{ + "runtime/jit: tail_call within bounds, different maps, first branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 13), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5 }, + .fixup_prog2 = { 9 }, + .result_unpriv = REJECT, + .errstr_unpriv = "tail_call abusing map_ptr", + .result = ACCEPT, .retval = 1, }, { + "runtime/jit: tail_call within bounds, different maps, second branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 14), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5 }, + .fixup_prog2 = { 9 }, + .result_unpriv = REJECT, + .errstr_unpriv = "tail_call abusing map_ptr", + .result = ACCEPT, + .retval = 42, +}, +{ "runtime/jit: tail_call out of bounds", .insns = { BPF_MOV64_IMM(BPF_REG_3, 256), diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index d60a343b1371..842d9155d36c 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -45,7 +45,7 @@ static int get_stats(int fd, __u16 count, __u32 raddr) printf("\nXDP RTT data:\n"); if (bpf_map_lookup_elem(fd, &raddr, &pinginfo)) { - perror("bpf_map_lookup elem: "); + perror("bpf_map_lookup elem"); return 1; } diff --git a/tools/testing/selftests/filesystems/epoll/.gitignore b/tools/testing/selftests/filesystems/epoll/.gitignore new file mode 100644 index 000000000000..9ae8db44ec14 --- /dev/null +++ b/tools/testing/selftests/filesystems/epoll/.gitignore @@ -0,0 +1 @@ +epoll_wakeup_test diff --git a/tools/testing/selftests/filesystems/epoll/Makefile b/tools/testing/selftests/filesystems/epoll/Makefile new file mode 100644 index 000000000000..78ae4aaf7141 --- /dev/null +++ b/tools/testing/selftests/filesystems/epoll/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += -I../../../../../usr/include/ +LDLIBS += -lpthread +TEST_GEN_PROGS := epoll_wakeup_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c new file mode 100644 index 000000000000..37a04dab56f0 --- /dev/null +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -0,0 +1,3074 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <poll.h> +#include <unistd.h> +#include <signal.h> +#include <pthread.h> +#include <sys/epoll.h> +#include <sys/socket.h> +#include "../../kselftest_harness.h" + +struct epoll_mtcontext +{ + int efd[3]; + int sfd[4]; + int count; + + pthread_t main; + pthread_t waiter; +}; + +static void signal_handler(int signum) +{ +} + +static void kill_timeout(struct epoll_mtcontext *ctx) +{ + usleep(1000000); + pthread_kill(ctx->main, SIGUSR1); + pthread_kill(ctx->waiter, SIGUSR1); +} + +static void *waiter_entry1a(void *data) +{ + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + if (epoll_wait(ctx->efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx->count, 1); + + return NULL; +} + +static void *waiter_entry1ap(void *data) +{ + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + pfd.fd = ctx->efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx->efd[0], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx->count, 1); + } + + return NULL; +} + +static void *waiter_entry1o(void *data) +{ + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + if (epoll_wait(ctx->efd[0], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx->count, 1); + + return NULL; +} + +static void *waiter_entry1op(void *data) +{ + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + pfd.fd = ctx->efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx->efd[0], &e, 1, 0) > 0) + __sync_fetch_and_or(&ctx->count, 1); + } + + return NULL; +} + +static void *waiter_entry2a(void *data) +{ + struct epoll_event events[2]; + struct epoll_mtcontext *ctx = data; + + if (epoll_wait(ctx->efd[0], events, 2, -1) > 0) + __sync_fetch_and_add(&ctx->count, 1); + + return NULL; +} + +static void *waiter_entry2ap(void *data) +{ + struct pollfd pfd; + struct epoll_event events[2]; + struct epoll_mtcontext *ctx = data; + + pfd.fd = ctx->efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx->efd[0], events, 2, 0) > 0) + __sync_fetch_and_add(&ctx->count, 1); + } + + return NULL; +} + +static void *emitter_entry1(void *data) +{ + struct epoll_mtcontext *ctx = data; + + usleep(100000); + write(ctx->sfd[1], "w", 1); + + kill_timeout(ctx); + + return NULL; +} + +static void *emitter_entry2(void *data) +{ + struct epoll_mtcontext *ctx = data; + + usleep(100000); + write(ctx->sfd[1], "w", 1); + write(ctx->sfd[3], "w", 1); + + kill_timeout(ctx); + + return NULL; +} + +/* + * t0 + * | (ew) + * e0 + * | (lt) + * s0 + */ +TEST(epoll1) +{ + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (et) + * s0 + */ +TEST(epoll2) +{ + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ +TEST(epoll3) +{ + int efd; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (ew) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll4) +{ + int efd; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * | (lt) + * s0 + */ +TEST(epoll5) +{ + int efd; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 1); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 1); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (et) + * s0 + */ +TEST(epoll6) +{ + int efd; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 1); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 0); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ + +TEST(epoll7) +{ + int efd; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll8) +{ + int efd; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (lt) + * s0 + */ +TEST(epoll9) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (et) + * s0 + */ +TEST(epoll10) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ +TEST(epoll11) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry2a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 2, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll12) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (lt) + * s0 + */ +TEST(epoll13) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (et) + * s0 + */ +TEST(epoll14) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ +TEST(epoll15) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry2ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 2, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll16) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 + * | (ew) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll17) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll18) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll19) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll20) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll21) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll22) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll23) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll24) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll25) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll26) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll27) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll28) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll29) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll30) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll31) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll32) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll33) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll34) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll35) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll36) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll37) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll38) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_or(&ctx.count, 2); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll39) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll40) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_or(&ctx.count, 2); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll41) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll42) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll43) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll44) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll45) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll46) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll47) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll48) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll49) +{ + int efd[3]; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (ew) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll50) +{ + int efd[3]; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 0); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll51) +{ + int efd[3]; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll52) +{ + int efd[3]; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 0); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll53) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll54) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll55) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll56) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (p) \ / (p) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll57) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + pfd.fd = ctx.efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[0], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (p) \ / (p) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll58) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + pfd.fd = ctx.efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[0], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh index b879305a766d..5b8c0fedee76 100755 --- a/tools/testing/selftests/firmware/fw_lib.sh +++ b/tools/testing/selftests/firmware/fw_lib.sh @@ -34,6 +34,12 @@ test_modprobe() check_mods() { + local uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "skip all tests: must be run as root" >&2 + exit $ksft_skip + fi + trap "test_modprobe" EXIT if [ ! -d $DIR ]; then modprobe test_firmware diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc index 36fb59f886ea..1a52f2883fe0 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc @@ -3,6 +3,8 @@ # description: ftrace - stacktrace filter command # flags: instance +[ ! -f set_ftrace_filter ] && exit_unsupported + echo _do_fork:stacktrace >> set_ftrace_filter grep -q "_do_fork:stacktrace:unlimited" set_ftrace_filter diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc index 86a1f07ef2ca..71fa3f49e35e 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc @@ -15,6 +15,11 @@ if [ $NP -eq 1 ] ;then exit_unresolved fi +if ! grep -q "function" available_tracers ; then + echo "Function trace is not enabled" + exit_unsupported +fi + ORIG_CPUMASK=`cat tracing_cpumask` do_reset() { diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 86986c4bba54..5d4550591ff9 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -46,6 +46,9 @@ reset_events_filter() { # reset all current setting filters } reset_ftrace_filter() { # reset all triggers in set_ftrace_filter + if [ ! -f set_ftrace_filter ]; then + return 0 + fi echo > set_ftrace_filter grep -v '^#' set_ftrace_filter | while read t; do tr=`echo $t | cut -d: -f2` @@ -93,7 +96,7 @@ initialize_ftrace() { # Reset ftrace to initial-state disable_events [ -f set_event_pid ] && echo > set_event_pid [ -f set_ftrace_pid ] && echo > set_ftrace_pid - [ -f set_ftrace_filter ] && echo | tee set_ftrace_* + [ -f set_ftrace_notrace ] && echo > set_ftrace_notrace [ -f set_graph_function ] && echo | tee set_graph_* [ -f stack_trace_filter ] && echo > stack_trace_filter [ -f kprobe_events ] && echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index 5862eee91e1d..6e3dbe5f96b7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -20,9 +20,9 @@ while read i; do test $N -eq 256 && break done -L=`wc -l kprobe_events` -if [ $L -ne $N ]; then - echo "The number of kprobes events ($L) is not $N" +L=`cat kprobe_events | wc -l` +if [ $L -ne 256 ]; then + echo "The number of kprobes events ($L) is not 256" exit_fail fi diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc index 1221240f8cf6..3f2aee115f6e 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc @@ -21,10 +21,10 @@ grep -q "snapshot()" README || exit_unsupported # version issue echo "Test expected snapshot action failure" -echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail +echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> events/sched/sched_waking/trigger && exit_fail echo "Test expected save action failure" -echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail +echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> events/sched/sched_waking/trigger && exit_fail exit_xfail diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc index 064a284e4e75..c80007aa9f86 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc @@ -16,7 +16,7 @@ grep -q "onchange(var)" README || exit_unsupported # version issue echo "Test onchange action" -echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger +echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> events/sched/sched_waking/trigger ping $LOCALHOST -c 3 nice -n 1 ping $LOCALHOST -c 3 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc index 18fff69fc433..f546c1b66a9b 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc @@ -23,9 +23,9 @@ grep -q "snapshot()" README || exit_unsupported # version issue echo "Test snapshot action" -echo 1 > /sys/kernel/debug/tracing/events/sched/enable +echo 1 > events/sched/enable -echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger +echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> events/sched/sched_waking/trigger ping $LOCALHOST -c 3 nice -n 1 ping $LOCALHOST -c 3 diff --git a/tools/testing/selftests/kselftest/module.sh b/tools/testing/selftests/kselftest/module.sh index 18e1c7992d30..fb4733faff12 100755 --- a/tools/testing/selftests/kselftest/module.sh +++ b/tools/testing/selftests/kselftest/module.sh @@ -9,7 +9,7 @@ # # #!/bin/sh # SPDX-License-Identifier: GPL-2.0+ -# $(dirname $0)/../kselftest_module.sh "description" module_name +# $(dirname $0)/../kselftest/module.sh "description" module_name # # Example: tools/testing/selftests/lib/printf.sh diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl index ec7e48118183..31f7c2a0a8bd 100755 --- a/tools/testing/selftests/kselftest/prefix.pl +++ b/tools/testing/selftests/kselftest/prefix.pl @@ -3,6 +3,7 @@ # Prefix all lines with "# ", unbuffered. Command being piped in may need # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd". use strict; +use IO::Handle; binmode STDIN; binmode STDOUT; diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 84de7bc74f2c..a8d20cbb711c 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -79,6 +79,7 @@ run_one() if [ $rc -eq $skip_rc ]; then \ echo "not ok $test_num $TEST_HDR_MSG # SKIP" elif [ $rc -eq $timeout_rc ]; then \ + echo "#" echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT" else echo "not ok $test_num $TEST_HDR_MSG # exit=$rc" diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index 31eb09e38729..a6e3d5517a6f 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -7,6 +7,9 @@ MAX_RETRIES=600 RETRY_INTERVAL=".1" # seconds +# Kselftest framework requirement - SKIP code is 4 +ksft_skip=4 + # log(msg) - write message to kernel log # msg - insightful words function log() { @@ -18,7 +21,16 @@ function log() { function skip() { log "SKIP: $1" echo "SKIP: $1" >&2 - exit 4 + exit $ksft_skip +} + +# root test +function is_root() { + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "skip all tests: must be run as root" >&2 + exit $ksft_skip + fi } # die(msg) - game over, man @@ -62,6 +74,7 @@ function set_ftrace_enabled() { # for verbose livepatching output and turn on # the ftrace_enabled sysctl. function setup_config() { + is_root push_config set_dynamic_debug set_ftrace_enabled 1 diff --git a/tools/testing/selftests/livepatch/test-state.sh b/tools/testing/selftests/livepatch/test-state.sh index dc2908c22c26..a08212708115 100755 --- a/tools/testing/selftests/livepatch/test-state.sh +++ b/tools/testing/selftests/livepatch/test-state.sh @@ -8,8 +8,7 @@ MOD_LIVEPATCH=test_klp_state MOD_LIVEPATCH2=test_klp_state2 MOD_LIVEPATCH3=test_klp_state3 -set_dynamic_debug - +setup_config # TEST: Loading and removing a module that modifies the system state diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index c67d32eeb668..334a7eea2004 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -290,6 +290,40 @@ static void mfd_assert_read_shared(int fd) munmap(p, mfd_def_size); } +static void mfd_assert_fork_private_write(int fd) +{ + int *p; + pid_t pid; + + p = mmap(NULL, + mfd_def_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + p[0] = 22; + + pid = fork(); + if (pid == 0) { + p[0] = 33; + exit(0); + } else { + waitpid(pid, NULL, 0); + + if (p[0] != 22) { + printf("MAP_PRIVATE copy-on-write failed: %m\n"); + abort(); + } + } + + munmap(p, mfd_def_size); +} + static void mfd_assert_write(int fd) { ssize_t l; @@ -760,6 +794,8 @@ static void test_seal_future_write(void) mfd_assert_read_shared(fd2); mfd_fail_write(fd2); + mfd_assert_fork_private_write(fd); + munmap(p, mfd_def_size); close(fd2); close(fd); diff --git a/tools/testing/selftests/net/forwarding/loopback.sh b/tools/testing/selftests/net/forwarding/loopback.sh index 6e4626ae71b0..8f4057310b5b 100755 --- a/tools/testing/selftests/net/forwarding/loopback.sh +++ b/tools/testing/selftests/net/forwarding/loopback.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ALL_TESTS="loopback_test" NUM_NETIFS=2 source tc_common.sh @@ -72,6 +75,11 @@ setup_prepare() h1_create h2_create + + if ethtool -k $h1 | grep loopback | grep -q fixed; then + log_test "SKIP: dev $h1 does not support loopback feature" + exit $ksft_skip + fi } cleanup() diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index fef88eb4b873..fa6a88c50750 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -36,7 +36,7 @@ h2_destroy() { ip -6 route del 2001:db8:1::/64 vrf v$h2 ip -4 route del 192.0.2.0/28 vrf v$h2 - simple_if_fini $h2 192.0.2.130/28 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 } router_create() diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index d93589bd4d1d..64f652633585 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -3,16 +3,42 @@ CHECK_TC="yes" +# Can be overridden by the configuration file. See lib.sh +TC_HIT_TIMEOUT=${TC_HIT_TIMEOUT:=1000} # ms + +__tc_check_packets() +{ + local id=$1 + local handle=$2 + local count=$3 + local operator=$4 + + start_time="$(date -u +%s%3N)" + while true + do + cmd_jq "tc -j -s filter show $id" \ + ".[] | select(.options.handle == $handle) | \ + select(.options.actions[0].stats.packets $operator $count)" \ + &> /dev/null + ret=$? + if [[ $ret -eq 0 ]]; then + return $ret + fi + current_time="$(date -u +%s%3N)" + diff=$(expr $current_time - $start_time) + if [ "$diff" -gt "$TC_HIT_TIMEOUT" ]; then + return 1 + fi + done +} + tc_check_packets() { local id=$1 local handle=$2 local count=$3 - cmd_jq "tc -j -s filter show $id" \ - ".[] | select(.options.handle == $handle) | \ - select(.options.actions[0].stats.packets == $count)" \ - &> /dev/null + __tc_check_packets "$id" "$handle" "$count" "==" } tc_check_packets_hitting() @@ -20,8 +46,5 @@ tc_check_packets_hitting() local id=$1 local handle=$2 - cmd_jq "tc -j -s filter show $id" \ - ".[] | select(.options.handle == $handle) | \ - select(.options.actions[0].stats.packets > 0)" \ - &> /dev/null + __tc_check_packets "$id" "$handle" 0 ">" } diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index ab367e75f095..71a62e7e35b1 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -11,9 +11,9 @@ # R1 and R2 (also implemented with namespaces), with different MTUs: # # segment a_r1 segment b_r1 a_r1: 2000 -# .--------------R1--------------. a_r2: 1500 -# A B a_r3: 2000 -# '--------------R2--------------' a_r4: 1400 +# .--------------R1--------------. b_r1: 1400 +# A B a_r2: 2000 +# '--------------R2--------------' b_r2: 1500 # segment a_r2 segment b_r2 # # Check that PMTU exceptions with the correct PMTU are created. Then @@ -1249,8 +1249,7 @@ test_list_flush_ipv4_exception() { done run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dst2}" - # Each exception is printed as two lines - if [ "$(${ns_a} ip route list cache | wc -l)" -ne 202 ]; then + if [ "$(${ns_a} ip -oneline route list cache | wc -l)" -ne 101 ]; then err " can't list cached exceptions" fail=1 fi @@ -1300,7 +1299,7 @@ test_list_flush_ipv6_exception() { run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst_prefix1}${i}" done run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst2}" - if [ "$(${ns_a} ip -6 route list cache | wc -l)" -ne 101 ]; then + if [ "$(${ns_a} ip -oneline -6 route list cache | wc -l)" -ne 101 ]; then err " can't list cached exceptions" fail=1 fi diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 1c8f194d6556..0ea44d975b6c 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,10 +25,6 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 -#ifndef ENOTSUPP -#define ENOTSUPP 524 -#endif - FIXTURE(tls_basic) { int fd, cfd; @@ -268,6 +264,38 @@ TEST_F(tls, sendmsg_single) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +#define MAX_FRAGS 64 +#define SEND_LEN 13 +TEST_F(tls, sendmsg_fragmented) +{ + char const *test_str = "test_sendmsg"; + char buf[SEND_LEN * MAX_FRAGS]; + struct iovec vec[MAX_FRAGS]; + struct msghdr msg; + int i, frags; + + for (frags = 1; frags <= MAX_FRAGS; frags++) { + for (i = 0; i < frags; i++) { + vec[i].iov_base = (char *)test_str; + vec[i].iov_len = SEND_LEN; + } + + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = vec; + msg.msg_iovlen = frags; + + EXPECT_EQ(sendmsg(self->fd, &msg, 0), SEND_LEN * frags); + EXPECT_EQ(recv(self->cfd, buf, SEND_LEN * frags, MSG_WAITALL), + SEND_LEN * frags); + + for (i = 0; i < frags; i++) + EXPECT_EQ(memcmp(buf + SEND_LEN * i, + test_str, SEND_LEN), 0); + } +} +#undef MAX_FRAGS +#undef SEND_LEN + TEST_F(tls, sendmsg_large) { void *mem = malloc(16384); @@ -1145,11 +1173,11 @@ TEST(non_established) { /* TLS ULP not supported */ if (errno == ENOENT) return; - EXPECT_EQ(errno, ENOTSUPP); + EXPECT_EQ(errno, ENOTCONN); ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); EXPECT_EQ(ret, -1); - EXPECT_EQ(errno, ENOTSUPP); + EXPECT_EQ(errno, ENOTCONN); ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 16571ac1dab4..d3e0809ab368 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -226,17 +226,19 @@ check_transfer() return 0 } -test_tcp_forwarding() +test_tcp_forwarding_ip() { local nsa=$1 local nsb=$2 + local dstip=$3 + local dstport=$4 local lret=0 ip netns exec $nsb nc -w 5 -l -p 12345 < "$ns2in" > "$ns2out" & lpid=$! sleep 1 - ip netns exec $nsa nc -w 4 10.0.2.99 12345 < "$ns1in" > "$ns1out" & + ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$ns1in" > "$ns1out" & cpid=$! sleep 3 @@ -258,6 +260,28 @@ test_tcp_forwarding() return $lret } +test_tcp_forwarding() +{ + test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + + return $? +} + +test_tcp_forwarding_nat() +{ + local lret + + test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + lret=$? + + if [ $lret -eq 0 ] ; then + test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666 + lret=$? + fi + + return $lret +} + make_file "$ns1in" "ns1" make_file "$ns2in" "ns2" @@ -283,14 +307,19 @@ ip -net ns2 route add 192.168.10.1 via 10.0.2.1 # Same, but with NAT enabled. ip netns exec nsr1 nft -f - <<EOF table ip nat { + chain prerouting { + type nat hook prerouting priority 0; policy accept; + meta iif "veth0" ip daddr 10.6.6.6 tcp dport 1666 counter dnat ip to 10.0.2.99:12345 + } + chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oifname "veth1" masquerade + meta oifname "veth1" counter masquerade } } EOF -test_tcp_forwarding ns1 ns2 +test_tcp_forwarding_nat ns1 ns2 if [ $? -eq 0 ] ;then echo "PASS: flow offloaded for ns1/ns2 with NAT" @@ -313,7 +342,7 @@ fi ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null -test_tcp_forwarding ns1 ns2 +test_tcp_forwarding_nat ns1 ns2 if [ $? -eq 0 ] ;then echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery" else diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 1be55e705780..d7e07f4c3d7f 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -8,9 +8,14 @@ ksft_skip=4 ret=0 test_inet_nat=true +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" +ns2="ns2-$sfx" + cleanup() { - for i in 0 1 2; do ip netns del ns$i;done + for i in 0 1 2; do ip netns del ns$i-"$sfx";done } nft --version > /dev/null 2>&1 @@ -25,40 +30,49 @@ if [ $? -ne 0 ];then exit $ksft_skip fi -ip netns add ns0 +ip netns add "$ns0" if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace" + echo "SKIP: Could not create net namespace $ns0" exit $ksft_skip fi trap cleanup EXIT -ip netns add ns1 -ip netns add ns2 +ip netns add "$ns1" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns1" + exit $ksft_skip +fi + +ip netns add "$ns2" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns2" + exit $ksft_skip +fi -ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 > /dev/null 2>&1 +ip link add veth0 netns "$ns0" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: No virtual ethernet pair device support in kernel" exit $ksft_skip fi -ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 +ip link add veth1 netns "$ns0" type veth peer name eth0 netns "$ns2" -ip -net ns0 link set lo up -ip -net ns0 link set veth0 up -ip -net ns0 addr add 10.0.1.1/24 dev veth0 -ip -net ns0 addr add dead:1::1/64 dev veth0 +ip -net "$ns0" link set lo up +ip -net "$ns0" link set veth0 up +ip -net "$ns0" addr add 10.0.1.1/24 dev veth0 +ip -net "$ns0" addr add dead:1::1/64 dev veth0 -ip -net ns0 link set veth1 up -ip -net ns0 addr add 10.0.2.1/24 dev veth1 -ip -net ns0 addr add dead:2::1/64 dev veth1 +ip -net "$ns0" link set veth1 up +ip -net "$ns0" addr add 10.0.2.1/24 dev veth1 +ip -net "$ns0" addr add dead:2::1/64 dev veth1 for i in 1 2; do - ip -net ns$i link set lo up - ip -net ns$i link set eth0 up - ip -net ns$i addr add 10.0.$i.99/24 dev eth0 - ip -net ns$i route add default via 10.0.$i.1 - ip -net ns$i addr add dead:$i::99/64 dev eth0 - ip -net ns$i route add default via dead:$i::1 + ip -net ns$i-$sfx link set lo up + ip -net ns$i-$sfx link set eth0 up + ip -net ns$i-$sfx addr add 10.0.$i.99/24 dev eth0 + ip -net ns$i-$sfx route add default via 10.0.$i.1 + ip -net ns$i-$sfx addr add dead:$i::99/64 dev eth0 + ip -net ns$i-$sfx route add default via dead:$i::1 done bad_counter() @@ -66,8 +80,9 @@ bad_counter() local ns=$1 local counter=$2 local expect=$3 + local tag=$4 - echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2 + echo "ERROR: $counter counter in $ns has unexpected value (expected $expect) at $tag" 1>&2 ip netns exec $ns nft list counter inet filter $counter 1>&2 } @@ -78,24 +93,24 @@ check_counters() cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84") if [ $? -ne 0 ]; then - bad_counter $ns ns0in "packets 1 bytes 84" + bad_counter $ns ns0in "packets 1 bytes 84" "check_counters 1" lret=1 fi cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84") if [ $? -ne 0 ]; then - bad_counter $ns ns0out "packets 1 bytes 84" + bad_counter $ns ns0out "packets 1 bytes 84" "check_counters 2" lret=1 fi expect="packets 1 bytes 104" cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter $ns ns0in6 "$expect" + bad_counter $ns ns0in6 "$expect" "check_counters 3" lret=1 fi cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter $ns ns0out6 "$expect" + bad_counter $ns ns0out6 "$expect" "check_counters 4" lret=1 fi @@ -107,41 +122,41 @@ check_ns0_counters() local ns=$1 local lret=0 - cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0in "packets 0 bytes 0" + bad_counter "$ns0" ns0in "packets 0 bytes 0" "check_ns0_counters 1" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0in6 "packets 0 bytes 0" + bad_counter "$ns0" ns0in6 "packets 0 bytes 0" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0out "packets 0 bytes 0" + bad_counter "$ns0" ns0out "packets 0 bytes 0" "check_ns0_counters 2" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0out6 "packets 0 bytes 0" + bad_counter "$ns0" ns0out6 "packets 0 bytes 0" "check_ns0_counters3 " lret=1 fi for dir in "in" "out" ; do expect="packets 1 bytes 84" - cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 $ns$dir "$expect" + bad_counter "$ns0" $ns$dir "$expect" "check_ns0_counters 4" lret=1 fi expect="packets 1 bytes 104" - cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 $ns$dir6 "$expect" + bad_counter "$ns0" $ns$dir6 "$expect" "check_ns0_counters 5" lret=1 fi done @@ -152,7 +167,7 @@ check_ns0_counters() reset_counters() { for i in 0 1 2;do - ip netns exec ns$i nft reset counters inet > /dev/null + ip netns exec ns$i-$sfx nft reset counters inet > /dev/null done } @@ -166,7 +181,7 @@ test_local_dnat6() IPF="ip6" fi -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain output { type nat hook output priority 0; policy accept; @@ -180,7 +195,7 @@ EOF fi # ping netns1, expect rewrite to netns2 - ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 dead:1::99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping6 failed" @@ -189,18 +204,18 @@ EOF expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat6 1" lret=1 fi done expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat6 2" lret=1 fi done @@ -208,9 +223,9 @@ EOF # expect 0 count in ns1 expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat6 3" lret=1 fi done @@ -218,15 +233,15 @@ EOF # expect 1 packet in ns2 expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns0$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat6 4" lret=1 fi done - test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was $family NATted to ns2" - ip netns exec ns0 nft flush chain ip6 nat output + test $lret -eq 0 && echo "PASS: ipv6 ping to $ns1 was $family NATted to $ns2" + ip netns exec "$ns0" nft flush chain ip6 nat output return $lret } @@ -241,7 +256,7 @@ test_local_dnat() IPF="ip" fi -ip netns exec ns0 nft -f - <<EOF 2>/dev/null +ip netns exec "$ns0" nft -f /dev/stdin <<EOF 2>/dev/null table $family nat { chain output { type nat hook output priority 0; policy accept; @@ -260,7 +275,7 @@ EOF fi # ping netns1, expect rewrite to netns2 - ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping failed" @@ -269,18 +284,18 @@ EOF expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat 1" lret=1 fi done expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 2" lret=1 fi done @@ -288,9 +303,9 @@ EOF # expect 0 count in ns1 expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat 3" lret=1 fi done @@ -298,19 +313,19 @@ EOF # expect 1 packet in ns2 expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns0$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 4" lret=1 fi done - test $lret -eq 0 && echo "PASS: ping to ns1 was $family NATted to ns2" + test $lret -eq 0 && echo "PASS: ping to $ns1 was $family NATted to $ns2" - ip netns exec ns0 nft flush chain $family nat output + ip netns exec "$ns0" nft flush chain $family nat output reset_counters - ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping failed" @@ -319,17 +334,17 @@ EOF expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns1$dir "$expect" + bad_counter "$ns1" ns1$dir "$expect" "test_local_dnat 5" lret=1 fi done expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 6" lret=1 fi done @@ -337,9 +352,9 @@ EOF # expect 1 count in ns1 expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns0$dir "$expect" + bad_counter "$ns0" ns0$dir "$expect" "test_local_dnat 7" lret=1 fi done @@ -347,14 +362,14 @@ EOF # expect 0 packet in ns2 expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns2$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 8" lret=1 fi done - test $lret -eq 0 && echo "PASS: ping to ns1 OK after $family nat output chain flush" + test $lret -eq 0 && echo "PASS: ping to $ns1 OK after $family nat output chain flush" return $lret } @@ -366,26 +381,26 @@ test_masquerade6() local natflags=$2 local lret=0 - ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 via ipv6" + echo "ERROR: cannot ping $ns1 from $ns2 via ipv6" return 1 lret=1 fi expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_masquerade6 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 2" lret=1 fi done @@ -393,7 +408,7 @@ test_masquerade6() reset_counters # add masquerading rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain postrouting { type nat hook postrouting priority 0; policy accept; @@ -406,24 +421,24 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active $family masquerade $natflags" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags" lret=1 fi # ns1 should have seen packets from ns0, due to masquerade expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 3" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 4" lret=1 fi done @@ -431,32 +446,32 @@ EOF # ns1 should not have seen packets from ns2, due to masquerade expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 5" lret=1 fi - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_masquerade6 6" lret=1 fi done - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + echo "ERROR: cannot ping $ns1 from $ns2 with active ipv6 masquerade $natflags (attempt 2)" lret=1 fi - ip netns exec ns0 nft flush chain $family nat postrouting + ip netns exec "$ns0" nft flush chain $family nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for $ns2" return $lret } @@ -467,26 +482,26 @@ test_masquerade() local natflags=$2 local lret=0 - ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null - ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$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 $natflags" + echo "ERROR: cannot ping $ns1 from "$ns2" $natflags" lret=1 fi expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_masquerade 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 2" lret=1 fi done @@ -494,7 +509,7 @@ test_masquerade() reset_counters # add masquerading rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain postrouting { type nat hook postrouting priority 0; policy accept; @@ -507,24 +522,24 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$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 active $family masquerade $natflags" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags" lret=1 fi # ns1 should have seen packets from ns0, due to masquerade expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 3" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 4" lret=1 fi done @@ -532,32 +547,32 @@ EOF # 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 "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 5" lret=1 fi - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_masquerade 6" lret=1 fi done - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + 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 active ip masquerade $natflags (attempt 2)" + echo "ERROR: cannot ping $ns1 from $ns2 with active ip masquerade $natflags (attempt 2)" lret=1 fi - ip netns exec ns0 nft flush chain $family nat postrouting + ip netns exec "$ns0" nft flush chain $family nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for ns2" + test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for $ns2" return $lret } @@ -567,25 +582,25 @@ test_redirect6() local family=$1 local lret=0 - ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannnot ping ns1 from ns2 via ipv6" + echo "ERROR: cannnot ping $ns1 from $ns2 via ipv6" lret=1 fi expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_redirect6 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_redirect6 2" lret=1 fi done @@ -593,7 +608,7 @@ test_redirect6() reset_counters # add redirect rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain prerouting { type nat hook prerouting priority 0; policy accept; @@ -606,18 +621,18 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 via ipv6 with active $family redirect" + echo "ERROR: cannot ping $ns1 from $ns2 via ipv6 with active $family redirect" lret=1 fi # ns1 should have seen no packets from ns2, due to redirection expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 3" lret=1 fi done @@ -625,20 +640,20 @@ EOF # ns0 should have seen packets from ns2, due to masquerade expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 4" lret=1 fi done - ip netns exec ns0 nft delete table $family nat + ip netns exec "$ns0" nft delete table $family nat if [ $? -ne 0 ]; then echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IPv6 redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 redirection for $ns2" return $lret } @@ -648,26 +663,26 @@ test_redirect() local family=$1 local lret=0 - ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null - ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$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" + echo "ERROR: cannot ping $ns1 from $ns2" lret=1 fi expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" $ns2$dir "$expect" "test_redirect 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_redirect 2" lret=1 fi done @@ -675,7 +690,7 @@ test_redirect() reset_counters # add redirect rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain prerouting { type nat hook prerouting priority 0; policy accept; @@ -688,9 +703,9 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$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 active $family ip redirect" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family ip redirect" lret=1 fi @@ -698,9 +713,9 @@ EOF expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect 3" lret=1 fi done @@ -708,28 +723,28 @@ EOF # ns0 should have seen packets from ns2, due to masquerade expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns0" ns0$dir "$expect" "test_redirect 4" lret=1 fi done - ip netns exec ns0 nft delete table $family nat + ip netns exec "$ns0" nft delete table $family nat if [ $? -ne 0 ]; then echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IP redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IP redirection for $ns2" return $lret } -# ip netns exec ns0 ping -c 1 -q 10.0.$i.99 +# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do -ip netns exec ns$i nft -f - <<EOF +ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF table inet filter { counter ns0in {} counter ns1in {} @@ -796,18 +811,18 @@ done sleep 3 # test basic connectivity for i in 1 2; do - ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null + ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 > /dev/null if [ $? -ne 0 ];then echo "ERROR: Could not reach other namespace(s)" 1>&2 ret=1 fi - ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null + ip netns exec "$ns0" ping -c 1 -q dead:$i::99 > /dev/null if [ $? -ne 0 ];then echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2 ret=1 fi - check_counters ns$i + check_counters ns$i-$sfx if [ $? -ne 0 ]; then ret=1 fi @@ -820,7 +835,7 @@ for i in 1 2; do done if [ $ret -eq 0 ];then - echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2" + echo "PASS: netns routing/connectivity: $ns0 can reach $ns1 and $ns2" fi reset_counters @@ -846,4 +861,9 @@ reset_counters $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet +if [ $ret -ne 0 ];then + echo -n "FAIL: " + nft --version +fi + exit $ret diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index eec2663261f2..e8a657a5f48a 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -15,7 +15,7 @@ #include <errno.h> #include <stddef.h> -static inline pid_t gettid(void) +static inline pid_t rseq_gettid(void) { return syscall(__NR_gettid); } @@ -373,11 +373,12 @@ void *test_percpu_spinlock_thread(void *arg) rseq_percpu_unlock(&data->lock, cpu); #ifndef BENCHMARK if (i != 0 && !(i % (reps / 10))) - printf_verbose("tid %d: count %lld\n", (int) gettid(), i); + printf_verbose("tid %d: count %lld\n", + (int) rseq_gettid(), i); #endif } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && thread_data->reg && rseq_unregister_current_thread()) abort(); @@ -454,11 +455,12 @@ void *test_percpu_inc_thread(void *arg) } while (rseq_unlikely(ret)); #ifndef BENCHMARK if (i != 0 && !(i % (reps / 10))) - printf_verbose("tid %d: count %lld\n", (int) gettid(), i); + printf_verbose("tid %d: count %lld\n", + (int) rseq_gettid(), i); #endif } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && thread_data->reg && rseq_unregister_current_thread()) abort(); @@ -605,7 +607,7 @@ void *test_percpu_list_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); @@ -796,7 +798,7 @@ void *test_percpu_buffer_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); @@ -1011,7 +1013,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index d40d60e7499e..3f63eb362b92 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -149,11 +149,13 @@ static inline void rseq_clear_rseq_cs(void) /* * rseq_prepare_unload() should be invoked by each thread executing a rseq * critical section at least once between their last critical section and - * library unload of the library defining the rseq critical section - * (struct rseq_cs). This also applies to use of rseq in code generated by - * JIT: rseq_prepare_unload() should be invoked at least once by each - * thread executing a rseq critical section before reclaim of the memory - * holding the struct rseq_cs. + * library unload of the library defining the rseq critical section (struct + * rseq_cs) or the code referred to by the struct rseq_cs start_ip and + * post_commit_offset fields. This also applies to use of rseq in code + * generated by JIT: rseq_prepare_unload() should be invoked at least once by + * each thread executing a rseq critical section before reclaim of the memory + * holding the struct rseq_cs or reclaim of the code pointed to by struct + * rseq_cs start_ip and post_commit_offset fields. */ static inline void rseq_prepare_unload(void) { diff --git a/tools/testing/selftests/rseq/settings b/tools/testing/selftests/rseq/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/rseq/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/safesetid/Makefile b/tools/testing/selftests/safesetid/Makefile index 98da7a504737..fa02c4d5ec13 100644 --- a/tools/testing/selftests/safesetid/Makefile +++ b/tools/testing/selftests/safesetid/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for mount selftests. -CFLAGS = -Wall -lcap -O2 +CFLAGS = -Wall -O2 +LDLIBS = -lcap -TEST_PROGS := run_tests.sh +TEST_PROGS := safesetid-test.sh TEST_GEN_FILES := safesetid-test include ../lib.mk diff --git a/tools/testing/selftests/safesetid/safesetid-test.c b/tools/testing/selftests/safesetid/safesetid-test.c index 8f40c6ecdad1..0c4d50644c13 100644 --- a/tools/testing/selftests/safesetid/safesetid-test.c +++ b/tools/testing/selftests/safesetid/safesetid-test.c @@ -213,7 +213,8 @@ static void test_setuid(uid_t child_uid, bool expect_success) } if (cpid == 0) { /* Code executed by child */ - setuid(child_uid); + if (setuid(child_uid) < 0) + exit(EXIT_FAILURE); if (getuid() == child_uid) exit(EXIT_SUCCESS); else @@ -291,8 +292,10 @@ int main(int argc, char **argv) // First test to make sure we can write userns mappings from a user // that doesn't have any restrictions (as long as it has CAP_SETUID); - setuid(NO_POLICY_USER); - setgid(NO_POLICY_USER); + if (setuid(NO_POLICY_USER) < 0) + die("Error with set uid(%d)\n", NO_POLICY_USER); + if (setgid(NO_POLICY_USER) < 0) + die("Error with set gid(%d)\n", NO_POLICY_USER); // Take away all but setid caps drop_caps(true); @@ -306,8 +309,10 @@ int main(int argc, char **argv) die("test_userns failed when it should work\n"); } - setuid(RESTRICTED_PARENT); - setgid(RESTRICTED_PARENT); + if (setuid(RESTRICTED_PARENT) < 0) + die("Error with set uid(%d)\n", RESTRICTED_PARENT); + if (setgid(RESTRICTED_PARENT) < 0) + die("Error with set gid(%d)\n", RESTRICTED_PARENT); test_setuid(ROOT_USER, false); test_setuid(ALLOWED_CHILD1, true); diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 6944b898bb53..ee1b727ede04 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -3158,7 +3158,18 @@ TEST(user_notification_basic) EXPECT_GT(poll(&pollfd, 1, -1), 0); EXPECT_EQ(pollfd.revents, POLLIN); - EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + /* Test that we can't pass garbage to the kernel. */ + memset(&req, 0, sizeof(req)); + req.pid = -1; + errno = 0; + ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + if (ret) { + req.pid = 0; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + } pollfd.fd = listener; pollfd.events = POLLIN | POLLOUT; @@ -3278,6 +3289,7 @@ TEST(user_notification_signal) close(sk_pair[1]); + memset(&req, 0, sizeof(req)); EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); EXPECT_EQ(kill(pid, SIGUSR1), 0); @@ -3296,6 +3308,7 @@ TEST(user_notification_signal) EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1); EXPECT_EQ(errno, ENOENT); + memset(&req, 0, sizeof(req)); EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); resp.id = req.id; diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json index 76ae03a64506..2e361cea63bc 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json @@ -152,7 +152,7 @@ ] }, { - "id": "6f5e", + "id": "b99c", "name": "Add basic filter with cmp ematch u8/transport layer and default action", "category": [ "filter", diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index 0f89cd50a94b..8877f7b2b809 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -1,27 +1,5 @@ [ { - "id": "e9a3", - "name": "Add u32 with source match", - "category": [ - "filter", - "u32" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 u32 match ip src 127.0.0.1/32 flowid 1:1 action ok", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "match 7f000001/ffffffff at 12", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { "id": "2638", "name": "Add matchall and try to get it", "category": [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json new file mode 100644 index 000000000000..e09d3c0e307f --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -0,0 +1,205 @@ +[ + { + "id": "afa9", + "name": "Add u32 with source match", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.1/32 flowid 1:1 action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 1 u32 chain (0[ ]+$|0 fh 800: ht divisor 1|0 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1.*match 7f000001/ffffffff at 12)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "6aa7", + "name": "Add/Replace u32 with source match and invalid indev", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.1/32 indev notexist20 flowid 1:1 action ok", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 1 u32 chain 0", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "bc4d", + "name": "Replace valid u32 with source match and invalid indev", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.3/32 flowid 1:3 action ok" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.2/32 indev notexist20 flowid 1:2 action ok", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 1 u32 chain (0[ ]+$|0 fh 800: ht divisor 1|0 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:3.*match 7f000003/ffffffff at 12)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "648b", + "name": "Add u32 with custom hash table", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 99 handle 42: u32 divisor 256", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "pref 99 u32 chain (0[ ]+$|0 fh 42: ht divisor 256|0 fh 800: ht divisor 1)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "6658", + "name": "Add/Replace u32 with custom hash table and invalid handle", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress prio 99 handle 42:42 u32 divisor 256", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "pref 99 u32 chain 0", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "9d0a", + "name": "Replace valid u32 with custom hash table and invalid handle", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress prio 99 handle 42: u32 divisor 256" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress prio 99 handle 42:42 u32 divisor 128", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "pref 99 u32 chain (0[ ]+$|0 fh 42: ht divisor 256|0 fh 800: ht divisor 1)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "1644", + "name": "Add u32 filter that links to a custom hash table", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress prio 99 handle 43: u32 divisor 256" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol ip prio 98 u32 link 43: hashkey mask 0x0000ff00 at 12 match ip src 192.168.0.0/16", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 98 u32 chain (0[ ]+$|0 fh 801: ht divisor 1|0 fh 801::800 order 2048 key ht 801 bkt 0 link 43:.*match c0a80000/ffff0000 at 12.*hash mask 0000ff00 at 12)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "74c2", + "name": "Add/Replace u32 filter with invalid hash table id", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 20 u32 ht 47:47 action drop", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 20 u32 chain 0", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "1fe6", + "name": "Replace valid u32 filter with invalid hash table id", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress protocol ip prio 99 handle 43: u32 divisor 1", + "$TC filter add dev $DEV1 ingress protocol ip prio 98 u32 ht 43: match tcp src 22 FFFF classid 1:3" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 98 u32 ht 43:1 match tcp src 23 FFFF classid 1:4", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 99 u32 chain (0[ ]+$|0 fh (43|800): ht divisor 1|0 fh 43::800 order 2048 key ht 43 bkt 0 flowid 1:3.*match 00160000/ffff0000 at nexthdr\\+0)", + "matchCount": "4", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + } +] diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 80521d46220c..8155c2ea7ccb 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -2,3 +2,9 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) python -m unittest -v tpm2_tests.SmokeTest +python -m unittest -v tpm2_tests.AsyncTest + +CLEAR_CMD=$(which tpm2_clear) +if [ -n $CLEAR_CMD ]; then + tpm2_clear -T device +fi diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index 828c18584624..d0fcb66a88a6 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -6,8 +6,8 @@ import socket import struct import sys import unittest -from fcntl import ioctl - +import fcntl +import select TPM2_ST_NO_SESSIONS = 0x8001 TPM2_ST_SESSIONS = 0x8002 @@ -352,6 +352,7 @@ def hex_dump(d): class Client: FLAG_DEBUG = 0x01 FLAG_SPACE = 0x02 + FLAG_NONBLOCK = 0x04 TPM_IOC_NEW_SPACE = 0xa200 def __init__(self, flags = 0): @@ -362,13 +363,27 @@ class Client: else: self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0) + if (self.flags & Client.FLAG_NONBLOCK): + flags = fcntl.fcntl(self.tpm, fcntl.F_GETFL) + flags |= os.O_NONBLOCK + fcntl.fcntl(self.tpm, fcntl.F_SETFL, flags) + self.tpm_poll = select.poll() + def close(self): self.tpm.close() def send_cmd(self, cmd): self.tpm.write(cmd) + + if (self.flags & Client.FLAG_NONBLOCK): + self.tpm_poll.register(self.tpm, select.POLLIN) + self.tpm_poll.poll(10000) + rsp = self.tpm.read() + if (self.flags & Client.FLAG_NONBLOCK): + self.tpm_poll.unregister(self.tpm) + if (self.flags & Client.FLAG_DEBUG) != 0: sys.stderr.write('cmd' + os.linesep) sys.stderr.write(hex_dump(cmd) + os.linesep) diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index d4973be53493..728be7c69b76 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -288,3 +288,16 @@ class SpaceTest(unittest.TestCase): self.assertEqual(rc, tpm2.TPM2_RC_COMMAND_CODE | tpm2.TSS2_RESMGR_TPM_RC_LAYER) + +class AsyncTest(unittest.TestCase): + def setUp(self): + logging.basicConfig(filename='AsyncTest.log', level=logging.DEBUG) + + def test_async(self): + log = logging.getLogger(__name__) + log.debug(sys._getframe().f_code.co_name) + + async_client = tpm2.Client(tpm2.Client.FLAG_NONBLOCK) + 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() diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config index 1c0d76cb5adf..93b90a9b1eeb 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/vm/config @@ -1,2 +1,3 @@ CONFIG_SYSVIPC=y CONFIG_USERFAULTFD=y +CONFIG_TEST_VMALLOC=m diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c index 50ce6c3dd904..1063328e275c 100644 --- a/tools/testing/selftests/x86/single_step_syscall.c +++ b/tools/testing/selftests/x86/single_step_syscall.c @@ -43,7 +43,19 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), err(1, "sigaction"); } -static volatile sig_atomic_t sig_traps; +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static volatile sig_atomic_t sig_traps, sig_eflags; +sigjmp_buf jmpbuf; +static unsigned char altstack_data[SIGSTKSZ]; #ifdef __x86_64__ # define REG_IP REG_RIP @@ -90,6 +102,25 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) } } +static char const * const signames[] = { + [SIGSEGV] = "SIGSEGV", + [SIGBUS] = "SIBGUS", + [SIGTRAP] = "SIGTRAP", + [SIGILL] = "SIGILL", +}; + +static void print_and_longjmp(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = ctx_void; + + printf("\tGot %s with RIP=%lx, TF=%ld\n", signames[sig], + (unsigned long)ctx->uc_mcontext.gregs[REG_IP], + (unsigned long)ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_TF); + + sig_eflags = (unsigned long)ctx->uc_mcontext.gregs[REG_EFL]; + siglongjmp(jmpbuf, 1); +} + static void check_result(void) { unsigned long new_eflags = get_eflags(); @@ -109,6 +140,22 @@ static void check_result(void) sig_traps = 0; } +static void fast_syscall_no_tf(void) +{ + sig_traps = 0; + printf("[RUN]\tFast syscall with TF cleared\n"); + fflush(stdout); /* Force a syscall */ + if (get_eflags() & X86_EFLAGS_TF) { + printf("[FAIL]\tTF is now set\n"); + exit(1); + } + if (sig_traps) { + printf("[FAIL]\tGot SIGTRAP\n"); + exit(1); + } + printf("[OK]\tNothing unexpected happened\n"); +} + int main() { #ifdef CAN_BUILD_32 @@ -163,17 +210,46 @@ int main() check_result(); /* Now make sure that another fast syscall doesn't set TF again. */ - printf("[RUN]\tFast syscall with TF cleared\n"); - fflush(stdout); /* Force a syscall */ - if (get_eflags() & X86_EFLAGS_TF) { - printf("[FAIL]\tTF is now set\n"); - exit(1); + fast_syscall_no_tf(); + + /* + * And do a forced SYSENTER to make sure that this works even if + * fast syscalls don't use SYSENTER. + * + * Invoking SYSENTER directly breaks all the rules. Just handle + * the SIGSEGV. + */ + if (sigsetjmp(jmpbuf, 1) == 0) { + unsigned long nr = SYS_getpid; + printf("[RUN]\tSet TF and check SYSENTER\n"); + stack_t stack = { + .ss_sp = altstack_data, + .ss_size = SIGSTKSZ, + }; + if (sigaltstack(&stack, NULL) != 0) + err(1, "sigaltstack"); + sethandler(SIGSEGV, print_and_longjmp, + SA_RESETHAND | SA_ONSTACK); + sethandler(SIGILL, print_and_longjmp, SA_RESETHAND); + set_eflags(get_eflags() | X86_EFLAGS_TF); + /* Clear EBP first to make sure we segfault cleanly. */ + asm volatile ("xorl %%ebp, %%ebp; SYSENTER" : "+a" (nr) :: "flags", "rcx" +#ifdef __x86_64__ + , "r11" +#endif + ); + + /* We're unreachable here. SYSENTER forgets RIP. */ } - if (sig_traps) { - printf("[FAIL]\tGot SIGTRAP\n"); + clearhandler(SIGSEGV); + clearhandler(SIGILL); + if (!(sig_eflags & X86_EFLAGS_TF)) { + printf("[FAIL]\tTF was cleared\n"); exit(1); } - printf("[OK]\tNothing unexpected happened\n"); + + /* Now make sure that another fast syscall doesn't set TF again. */ + fast_syscall_no_tf(); return 0; } |