diff options
Diffstat (limited to 'tools')
111 files changed, 3648 insertions, 1251 deletions
diff --git a/tools/arch/arm64/vdso b/tools/arch/arm64/vdso new file mode 120000 index 000000000000..233c7a26f6e5 --- /dev/null +++ b/tools/arch/arm64/vdso @@ -0,0 +1 @@ +../../../arch/arm64/kernel/vdso
\ No newline at end of file diff --git a/tools/arch/loongarch/vdso b/tools/arch/loongarch/vdso new file mode 120000 index 000000000000..ebda43a82db7 --- /dev/null +++ b/tools/arch/loongarch/vdso @@ -0,0 +1 @@ +../../../arch/loongarch/vdso
\ No newline at end of file diff --git a/tools/arch/powerpc/vdso b/tools/arch/powerpc/vdso new file mode 120000 index 000000000000..4e676d1d1cb4 --- /dev/null +++ b/tools/arch/powerpc/vdso @@ -0,0 +1 @@ +../../../arch/powerpc/kernel/vdso
\ No newline at end of file diff --git a/tools/arch/s390/vdso b/tools/arch/s390/vdso new file mode 120000 index 000000000000..6cf4c1cebdcd --- /dev/null +++ b/tools/arch/s390/vdso @@ -0,0 +1 @@ +../../../arch/s390/kernel/vdso64
\ No newline at end of file diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv index e0c25b75327e..d751eb8585d0 100644 --- a/tools/arch/x86/kcpuid/cpuid.csv +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -1,451 +1,1053 @@ -# The basic row format is: -# LEAF, SUBLEAF, register_name, bits, short_name, long_description - -# Leaf 00H - 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs - -# Leaf 01H - 1, 0, EAX, 3:0, stepping, Stepping ID - 1, 0, EAX, 7:4, model, Model - 1, 0, EAX, 11:8, family, Family ID - 1, 0, EAX, 13:12, processor, Processor Type - 1, 0, EAX, 19:16, model_ext, Extended Model ID - 1, 0, EAX, 27:20, family_ext, Extended Family ID - - 1, 0, EBX, 7:0, brand, Brand Index - 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes - 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package - 1, 0, EBX, 31:24, apic_id, Initial APIC ID - - 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) - 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported - 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout - 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported - 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL - 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported - 1, 0, ECX, 6, smx, Safer Mode Extension supported - 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology - 1, 0, ECX, 8, tm2, Thermal Monitor 2 - 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) - 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) - 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported - 1, 0, ECX, 12, fma, FMA extensions using YMM state supported - 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported - 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported - 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present - 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present - 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported - 1, 0, ECX, 19, sse4_1, SSE4.1 feature present - 1, 0, ECX, 20, sse4_2, SSE4.2 feature present - 1, 0, ECX, 21, x2apic, x2APIC supported - 1, 0, ECX, 22, movbe, MOVBE instruction supported - 1, 0, ECX, 23, popcnt, POPCNT instruction supported - 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value - 1, 0, ECX, 25, aesni, AESNI instruction supported - 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) - 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 - 1, 0, ECX, 28, avx, AVX instruction supported - 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported - 1, 0, ECX, 30, rdrand, RDRAND instruction supported - - 1, 0, EDX, 0, fpu, x87 FPU on chip - 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement - 1, 0, EDX, 2, de, Debugging Extensions - 1, 0, EDX, 3, pse, Page Size Extensions - 1, 0, EDX, 4, tsc, Time Stamp Counter - 1, 0, EDX, 5, msr, RDMSR and WRMSR Support - 1, 0, EDX, 6, pae, Physical Address Extensions - 1, 0, EDX, 7, mce, Machine Check Exception - 1, 0, EDX, 8, cx8, CMPXCHG8B instr - 1, 0, EDX, 9, apic, APIC on Chip - 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs - 1, 0, EDX, 12, mtrr, Memory Type Range Registers - 1, 0, EDX, 13, pge, Page Global Bit - 1, 0, EDX, 14, mca, Machine Check Architecture - 1, 0, EDX, 15, cmov, Conditional Move Instrs - 1, 0, EDX, 16, pat, Page Attribute Table - 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension - 1, 0, EDX, 18, psn, Processor Serial Number - 1, 0, EDX, 19, clflush, CLFLUSH instr -# 1, 0, EDX, 20, - 1, 0, EDX, 21, ds, Debug Store - 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities - 1, 0, EDX, 23, mmx, Intel MMX Technology - 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs - 1, 0, EDX, 25, sse, SSE - 1, 0, EDX, 26, sse2, SSE2 - 1, 0, EDX, 27, ss, Self Snoop - 1, 0, EDX, 28, hit, Max APIC IDs - 1, 0, EDX, 29, tm, Thermal Monitor -# 1, 0, EDX, 30, - 1, 0, EDX, 31, pbe, Pending Break Enable - -# Leaf 02H -# cache and TLB descriptor info - -# Leaf 03H -# Precessor Serial Number, introduced on Pentium III, not valid for -# latest models - -# Leaf 04H -# thread/core and cache topology - 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified - 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) - 4, 0, EAX, 8, cache_self_init, Cache Self Initialization - 4, 0, EAX, 9, fully_associate, Fully Associative cache -# 4, 0, EAX, 13:10, resvd, resvd - 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache - 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package - - 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes - 4, 0, EBX, 21:12, cache_partition, Physical Line partitions - 4, 0, EBX, 31:22, cache_ways, Ways of associativity - 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 - 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache - 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level - 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing - -# Leaf 05H -# MONITOR/MWAIT - 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes - 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes - 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported - 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes - 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT - 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT - 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT - 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT - 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT - 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT - 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT - 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT - -# Leaf 06H -# Thermal & Power Management - - 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported - 6, 0, EAX, 1, turbo, Intel Turbo Boost - 6, 0, EAX, 2, arat, Always running APIC timer -# 6, 0, EAX, 3, resv, Reserved - 6, 0, EAX, 4, pln, Power limit notifications supported - 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported - 6, 0, EAX, 6, ptm, Package thermal management supported - 6, 0, EAX, 7, hwp, HWP base register - 6, 0, EAX, 8, hwp_notify, HWP notification - 6, 0, EAX, 9, hwp_act_window, HWP activity window - 6, 0, EAX, 10, hwp_energy, HWP energy performance preference - 6, 0, EAX, 11, hwp_pkg_req, HWP package level request -# 6, 0, EAX, 12, resv, Reserved - 6, 0, EAX, 13, hdc, HDC base registers supported - 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 - 6, 0, EAX, 15, hwp_cap, Highest Performance change supported - 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported - 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported - 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported -# 6, 0, EAX, 19, resv, Reserved - 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported - - 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor - 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF - 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported - -# Leaf 07H -# ECX == 0 -# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 -# XXX: Do we really need to enumerate each and every AVX512 sub features - - 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported - 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported - 7, 0, EBX, 2, sgx, Software Guard Extensions - 7, 0, EBX, 3, bmi1, BMI1 - 7, 0, EBX, 4, hle, Hardware Lock Elision - 7, 0, EBX, 5, avx2, AVX2 -# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions - 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention - 7, 0, EBX, 8, bmi2, BMI2 - 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB - 7, 0, EBX, 10, invpcid, INVPCID instruction - 7, 0, EBX, 11, rtm, Restricted Transactional Memory - 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability - 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS - 7, 0, EBX, 14, mpx, Memory Protection Extensions - 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability - 7, 0, EBX, 16, avx512f, AVX512 Foundation instr - 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr - 7, 0, EBX, 18, rdseed, RDSEED instr - 7, 0, EBX, 19, adx, ADX instr - 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention - 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add -# 7, 0, EBX, 22, resvd, resvd - 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr - 7, 0, EBX, 24, clwb, CLWB instr - 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr - 7, 0, EBX, 26, avx512pf, Prefetch - 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr - 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr - 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr - 7, 0, EBX, 30, avx512bw, AVX512 Byte & Word instr - 7, 0, EBX, 31, avx512vl, AVX512 Vector Length Extentions (VL) - 7, 0, ECX, 0, prefetchwt1, X - 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions - 7, 0, ECX, 2, umip, User-mode Instruction Prevention - - 7, 0, ECX, 3, pku, Protection Keys for User-mode pages - 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys -# 7, 0, ECX, 16:5, resvd, resvd - 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode - 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX -# 7, 0, ECX, 29:23, resvd, resvd - 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration -# 7, 0, ECX, 31, resvd, resvd - -# Leaf 08H -# - - -# Leaf 09H -# Direct Cache Access (DCA) information - 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP +# SPDX-License-Identifier: CC0-1.0 +# Generator: x86-cpuid-db v1.0 -# Leaf 0AH -# Architectural Performance Monitoring # -# Do we really need to print out the PMU related stuff? -# Does normal user really care about it? +# Auto-generated file. +# Please submit all updates and bugfixes to https://x86-cpuid.org # - 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version - 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU - 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter - 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events - - 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available - 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available - 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available - 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available - 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available - 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available - 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available - - 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version - 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU - -# Leaf 0BH -# Extended Topology Enumeration Leaf -# - - 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type - 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type - 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core - 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor - - -# Leaf 0DH -# Processor Extended State - 0xD, 0, EAX, 0, x87, X87 state - 0xD, 0, EAX, 1, sse, SSE state - 0xD, 0, EAX, 2, avx, AVX state - 0xD, 0, EAX, 4:3, mpx, MPX state - 0xD, 0, EAX, 7:5, avx512, AVX-512 state - 0xD, 0, EAX, 9, pkru, PKRU state - - 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 - 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area - - 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available - 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported - 0xD, 1, EAX, 2, xgetbv, XGETBV supported - 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported - - 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 - 0xD, 1, ECX, 8, pt, PT state - 0xD, 1, ECX, 11, cet_usr, CET user state - 0xD, 1, ECX, 12, cet_supv, CET supervisor state - 0xD, 1, ECX, 13, hdc, HDC state - 0xD, 1, ECX, 16, hwp, HWP state - -# Leaf 0FH -# Intel RDT Monitoring - - 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types - 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported - - 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types - 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported - 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported - 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported +# The basic row format is: +# LEAF, SUBLEAVES, reg, bits, short_name , long_description + +# Leaf 0H +# Maximum standard leaf number + CPU vendor string + + 0, 0, eax, 31:0, max_std_leaf , Highest cpuid standard leaf supported + 0, 0, ebx, 31:0, cpu_vendorid_0 , CPU vendor ID string bytes 0 - 3 + 0, 0, ecx, 31:0, cpu_vendorid_2 , CPU vendor ID string bytes 8 - 11 + 0, 0, edx, 31:0, cpu_vendorid_1 , CPU vendor ID string bytes 4 - 7 + +# Leaf 1H +# CPU FMS (Family/Model/Stepping) + standard feature flags + + 1, 0, eax, 3:0, stepping , Stepping ID + 1, 0, eax, 7:4, base_model , Base CPU model ID + 1, 0, eax, 11:8, base_family_id , Base CPU family ID + 1, 0, eax, 13:12, cpu_type , CPU type + 1, 0, eax, 19:16, ext_model , Extended CPU model ID + 1, 0, eax, 27:20, ext_family , Extended CPU family ID + 1, 0, ebx, 7:0, brand_id , Brand index + 1, 0, ebx, 15:8, clflush_size , CLFLUSH instruction cache line size + 1, 0, ebx, 23:16, n_logical_cpu , Logical CPU (HW threads) count + 1, 0, ebx, 31:24, local_apic_id , Initial local APIC physical ID + 1, 0, ecx, 0, pni , Streaming SIMD Extensions 3 (SSE3) + 1, 0, ecx, 1, pclmulqdq , PCLMULQDQ instruction support + 1, 0, ecx, 2, dtes64 , 64-bit DS save area + 1, 0, ecx, 3, monitor , MONITOR/MWAIT support + 1, 0, ecx, 4, ds_cpl , CPL Qualified Debug Store + 1, 0, ecx, 5, vmx , Virtual Machine Extensions + 1, 0, ecx, 6, smx , Safer Mode Extensions + 1, 0, ecx, 7, est , Enhanced Intel SpeedStep + 1, 0, ecx, 8, tm2 , Thermal Monitor 2 + 1, 0, ecx, 9, ssse3 , Supplemental SSE3 + 1, 0, ecx, 10, cid , L1 Context ID + 1, 0, ecx, 11, sdbg , Sillicon Debug + 1, 0, ecx, 12, fma , FMA extensions using YMM state + 1, 0, ecx, 13, cx16 , CMPXCHG16B instruction support + 1, 0, ecx, 14, xtpr , xTPR Update Control + 1, 0, ecx, 15, pdcm , Perfmon and Debug Capability + 1, 0, ecx, 17, pcid , Process-context identifiers + 1, 0, ecx, 18, dca , Direct Cache Access + 1, 0, ecx, 19, sse4_1 , SSE4.1 + 1, 0, ecx, 20, sse4_2 , SSE4.2 + 1, 0, ecx, 21, x2apic , X2APIC support + 1, 0, ecx, 22, movbe , MOVBE instruction support + 1, 0, ecx, 23, popcnt , POPCNT instruction support + 1, 0, ecx, 24, tsc_deadline_timer , APIC timer one-shot operation + 1, 0, ecx, 25, aes , AES instructions + 1, 0, ecx, 26, xsave , XSAVE (and related instructions) support + 1, 0, ecx, 27, osxsave , XSAVE (and related instructions) are enabled by OS + 1, 0, ecx, 28, avx , AVX instructions support + 1, 0, ecx, 29, f16c , Half-precision floating-point conversion support + 1, 0, ecx, 30, rdrand , RDRAND instruction support + 1, 0, ecx, 31, guest_status , System is running as guest; (para-)virtualized system + 1, 0, edx, 0, fpu , Floating-Point Unit on-chip (x87) + 1, 0, edx, 1, vme , Virtual-8086 Mode Extensions + 1, 0, edx, 2, de , Debugging Extensions + 1, 0, edx, 3, pse , Page Size Extension + 1, 0, edx, 4, tsc , Time Stamp Counter + 1, 0, edx, 5, msr , Model-Specific Registers (RDMSR and WRMSR support) + 1, 0, edx, 6, pae , Physical Address Extensions + 1, 0, edx, 7, mce , Machine Check Exception + 1, 0, edx, 8, cx8 , CMPXCHG8B instruction + 1, 0, edx, 9, apic , APIC on-chip + 1, 0, edx, 11, sep , SYSENTER, SYSEXIT, and associated MSRs + 1, 0, edx, 12, mtrr , Memory Type Range Registers + 1, 0, edx, 13, pge , Page Global Extensions + 1, 0, edx, 14, mca , Machine Check Architecture + 1, 0, edx, 15, cmov , Conditional Move Instruction + 1, 0, edx, 16, pat , Page Attribute Table + 1, 0, edx, 17, pse36 , Page Size Extension (36-bit) + 1, 0, edx, 18, pn , Processor Serial Number + 1, 0, edx, 19, clflush , CLFLUSH instruction + 1, 0, edx, 21, dts , Debug Store + 1, 0, edx, 22, acpi , Thermal monitor and clock control + 1, 0, edx, 23, mmx , MMX instructions + 1, 0, edx, 24, fxsr , FXSAVE and FXRSTOR instructions + 1, 0, edx, 25, sse , SSE instructions + 1, 0, edx, 26, sse2 , SSE2 instructions + 1, 0, edx, 27, ss , Self Snoop + 1, 0, edx, 28, ht , Hyper-threading + 1, 0, edx, 29, tm , Thermal Monitor + 1, 0, edx, 30, ia64 , Legacy IA-64 (Itanium) support bit, now resreved + 1, 0, edx, 31, pbe , Pending Break Enable + +# Leaf 2H +# Intel cache and TLB information one-byte descriptors + + 2, 0, eax, 7:0, iteration_count , Number of times this CPUD leaf must be queried + 2, 0, eax, 15:8, desc1 , Descriptor #1 + 2, 0, eax, 23:16, desc2 , Descriptor #2 + 2, 0, eax, 30:24, desc3 , Descriptor #3 + 2, 0, eax, 31, eax_invalid , Descriptors 1-3 are invalid if set + 2, 0, ebx, 7:0, desc4 , Descriptor #4 + 2, 0, ebx, 15:8, desc5 , Descriptor #5 + 2, 0, ebx, 23:16, desc6 , Descriptor #6 + 2, 0, ebx, 30:24, desc7 , Descriptor #7 + 2, 0, ebx, 31, ebx_invalid , Descriptors 4-7 are invalid if set + 2, 0, ecx, 7:0, desc8 , Descriptor #8 + 2, 0, ecx, 15:8, desc9 , Descriptor #9 + 2, 0, ecx, 23:16, desc10 , Descriptor #10 + 2, 0, ecx, 30:24, desc11 , Descriptor #11 + 2, 0, ecx, 31, ecx_invalid , Descriptors 8-11 are invalid if set + 2, 0, edx, 7:0, desc12 , Descriptor #12 + 2, 0, edx, 15:8, desc13 , Descriptor #13 + 2, 0, edx, 23:16, desc14 , Descriptor #14 + 2, 0, edx, 30:24, desc15 , Descriptor #15 + 2, 0, edx, 31, edx_invalid , Descriptors 12-15 are invalid if set + +# Leaf 4H +# Intel deterministic cache parameters + + 4, 31:0, eax, 4:0, cache_type , Cache type field + 4, 31:0, eax, 7:5, cache_level , Cache level (1-based) + 4, 31:0, eax, 8, cache_self_init , Self-initialializing cache level + 4, 31:0, eax, 9, fully_associative , Fully-associative cache + 4, 31:0, eax, 25:14, num_threads_sharing , Number logical CPUs sharing this cache + 4, 31:0, eax, 31:26, num_cores_on_die , Number of cores in the physical package + 4, 31:0, ebx, 11:0, cache_linesize , System coherency line size (0-based) + 4, 31:0, ebx, 21:12, cache_npartitions , Physical line partitions (0-based) + 4, 31:0, ebx, 31:22, cache_nways , Ways of associativity (0-based) + 4, 31:0, ecx, 30:0, cache_nsets , Cache number of sets (0-based) + 4, 31:0, edx, 0, wbinvd_rll_no_guarantee, WBINVD/INVD not guaranteed for Remote Lower-Level caches + 4, 31:0, edx, 1, ll_inclusive , Cache is inclusive of Lower-Level caches + 4, 31:0, edx, 2, complex_indexing , Not a direct-mapped cache (complex function) + +# Leaf 5H +# MONITOR/MWAIT instructions enumeration + + 5, 0, eax, 15:0, min_mon_size , Smallest monitor-line size, in bytes + 5, 0, ebx, 15:0, max_mon_size , Largest monitor-line size, in bytes + 5, 0, ecx, 0, mwait_ext , Enumeration of MONITOR/MWAIT extensions is supported + 5, 0, ecx, 1, mwait_irq_break , Interrupts as a break-event for MWAIT is supported + 5, 0, edx, 3:0, n_c0_substates , Number of C0 sub C-states supported using MWAIT + 5, 0, edx, 7:4, n_c1_substates , Number of C1 sub C-states supported using MWAIT + 5, 0, edx, 11:8, n_c2_substates , Number of C2 sub C-states supported using MWAIT + 5, 0, edx, 15:12, n_c3_substates , Number of C3 sub C-states supported using MWAIT + 5, 0, edx, 19:16, n_c4_substates , Number of C4 sub C-states supported using MWAIT + 5, 0, edx, 23:20, n_c5_substates , Number of C5 sub C-states supported using MWAIT + 5, 0, edx, 27:24, n_c6_substates , Number of C6 sub C-states supported using MWAIT + 5, 0, edx, 31:28, n_c7_substates , Number of C7 sub C-states supported using MWAIT + +# Leaf 6H +# Thermal and Power Management enumeration + + 6, 0, eax, 0, dtherm , Digital temprature sensor + 6, 0, eax, 1, turbo_boost , Intel Turbo Boost + 6, 0, eax, 2, arat , Always-Running APIC Timer (not affected by p-state) + 6, 0, eax, 4, pln , Power Limit Notification (PLN) event + 6, 0, eax, 5, ecmd , Clock modulation duty cycle extension + 6, 0, eax, 6, pts , Package thermal management + 6, 0, eax, 7, hwp , HWP (Hardware P-states) base registers are supported + 6, 0, eax, 8, hwp_notify , HWP notification (IA32_HWP_INTERRUPT MSR) + 6, 0, eax, 9, hwp_act_window , HWP activity window (IA32_HWP_REQUEST[bits 41:32]) supported + 6, 0, eax, 10, hwp_epp , HWP Energy Performance Preference + 6, 0, eax, 11, hwp_pkg_req , HWP Package Level Request + 6, 0, eax, 13, hdc_base_regs , HDC base registers are supported + 6, 0, eax, 14, turbo_boost_3_0 , Intel Turbo Boost Max 3.0 + 6, 0, eax, 15, hwp_capabilities , HWP Highest Performance change + 6, 0, eax, 16, hwp_peci_override , HWP PECI override + 6, 0, eax, 17, hwp_flexible , Flexible HWP + 6, 0, eax, 18, hwp_fast , IA32_HWP_REQUEST MSR fast access mode + 6, 0, eax, 19, hfi , HW_FEEDBACK MSRs supported + 6, 0, eax, 20, hwp_ignore_idle , Ignoring idle logical CPU HWP req is supported + 6, 0, eax, 23, thread_director , Intel thread director support + 6, 0, eax, 24, therm_interrupt_bit25 , IA32_THERM_INTERRUPT MSR bit 25 is supported + 6, 0, ebx, 3:0, n_therm_thresholds , Digital thermometer thresholds + 6, 0, ecx, 0, aperfmperf , MPERF/APERF MSRs (effective frequency interface) + 6, 0, ecx, 3, epb , IA32_ENERGY_PERF_BIAS MSR support + 6, 0, ecx, 15:8, thrd_director_nclasses , Number of classes, Intel thread director + 6, 0, edx, 0, perfcap_reporting , Performance capability reporting + 6, 0, edx, 1, encap_reporting , Energy efficiency capability reporting + 6, 0, edx, 11:8, feedback_sz , HW feedback interface struct size, in 4K pages + 6, 0, edx, 31:16, this_lcpu_hwfdbk_idx , This logical CPU index @ HW feedback struct, 0-based + +# Leaf 7H +# Extended CPU features enumeration + + 7, 0, eax, 31:0, leaf7_n_subleaves , Number of cpuid 0x7 subleaves + 7, 0, ebx, 0, fsgsbase , FSBASE/GSBASE read/write support + 7, 0, ebx, 1, tsc_adjust , IA32_TSC_ADJUST MSR supported + 7, 0, ebx, 2, sgx , Intel SGX (Software Guard Extensions) + 7, 0, ebx, 3, bmi1 , Bit manipulation extensions group 1 + 7, 0, ebx, 4, hle , Hardware Lock Elision + 7, 0, ebx, 5, avx2 , AVX2 instruction set + 7, 0, ebx, 6, fdp_excptn_only , FPU Data Pointer updated only on x87 exceptions + 7, 0, ebx, 7, smep , Supervisor Mode Execution Protection + 7, 0, ebx, 8, bmi2 , Bit manipulation extensions group 2 + 7, 0, ebx, 9, erms , Enhanced REP MOVSB/STOSB + 7, 0, ebx, 10, invpcid , INVPCID instruction (Invalidate Processor Context ID) + 7, 0, ebx, 11, rtm , Intel restricted transactional memory + 7, 0, ebx, 12, cqm , Intel RDT-CMT / AMD Platform-QoS cache monitoring + 7, 0, ebx, 13, zero_fcs_fds , Deprecated FPU CS/DS (stored as zero) + 7, 0, ebx, 14, mpx , Intel memory protection extensions + 7, 0, ebx, 15, rdt_a , Intel RDT / AMD Platform-QoS Enforcemeent + 7, 0, ebx, 16, avx512f , AVX-512 foundation instructions + 7, 0, ebx, 17, avx512dq , AVX-512 double/quadword instructions + 7, 0, ebx, 18, rdseed , RDSEED instruction + 7, 0, ebx, 19, adx , ADCX/ADOX instructions + 7, 0, ebx, 20, smap , Supervisor mode access prevention + 7, 0, ebx, 21, avx512ifma , AVX-512 integer fused multiply add + 7, 0, ebx, 23, clflushopt , CLFLUSHOPT instruction + 7, 0, ebx, 24, clwb , CLWB instruction + 7, 0, ebx, 25, intel_pt , Intel processor trace + 7, 0, ebx, 26, avx512pf , AVX-512 prefetch instructions + 7, 0, ebx, 27, avx512er , AVX-512 exponent/reciprocal instrs + 7, 0, ebx, 28, avx512cd , AVX-512 conflict detection instrs + 7, 0, ebx, 29, sha_ni , SHA/SHA256 instructions + 7, 0, ebx, 30, avx512bw , AVX-512 BW (byte/word granular) instructions + 7, 0, ebx, 31, avx512vl , AVX-512 VL (128/256 vector length) extensions + 7, 0, ecx, 0, prefetchwt1 , PREFETCHWT1 (Intel Xeon Phi only) + 7, 0, ecx, 1, avx512vbmi , AVX-512 Vector byte manipulation instrs + 7, 0, ecx, 2, umip , User mode instruction protection + 7, 0, ecx, 3, pku , Protection keys for user-space + 7, 0, ecx, 4, ospke , OS protection keys enable + 7, 0, ecx, 5, waitpkg , WAITPKG instructions + 7, 0, ecx, 6, avx512_vbmi2 , AVX-512 vector byte manipulation instrs group 2 + 7, 0, ecx, 7, cet_ss , CET shadow stack features + 7, 0, ecx, 8, gfni , Galois field new instructions + 7, 0, ecx, 9, vaes , Vector AES instrs + 7, 0, ecx, 10, vpclmulqdq , VPCLMULQDQ 256-bit instruction support + 7, 0, ecx, 11, avx512_vnni , Vector neural network instructions + 7, 0, ecx, 12, avx512_bitalg , AVX-512 bit count/shiffle + 7, 0, ecx, 13, tme , Intel total memory encryption + 7, 0, ecx, 14, avx512_vpopcntdq , AVX-512: POPCNT for vectors of DW/QW + 7, 0, ecx, 16, la57 , 57-bit linear addreses (five-level paging) + 7, 0, ecx, 21:17, mawau_val_lm , BNDLDX/BNDSTX MAWAU value in 64-bit mode + 7, 0, ecx, 22, rdpid , RDPID instruction + 7, 0, ecx, 23, key_locker , Intel key locker support + 7, 0, ecx, 24, bus_lock_detect , OS bus-lock detection + 7, 0, ecx, 25, cldemote , CLDEMOTE instruction + 7, 0, ecx, 27, movdiri , MOVDIRI instruction + 7, 0, ecx, 28, movdir64b , MOVDIR64B instruction + 7, 0, ecx, 29, enqcmd , Enqueue stores supported (ENQCMD{,S}) + 7, 0, ecx, 30, sgx_lc , Intel SGX launch configuration + 7, 0, ecx, 31, pks , Protection keys for supervisor-mode pages + 7, 0, edx, 1, sgx_keys , Intel SGX attestation services + 7, 0, edx, 2, avx512_4vnniw , AVX-512 neural network instructions + 7, 0, edx, 3, avx512_4fmaps , AVX-512 multiply accumulation single precision + 7, 0, edx, 4, fsrm , Fast short REP MOV + 7, 0, edx, 5, uintr , CPU supports user interrupts + 7, 0, edx, 8, avx512_vp2intersect , VP2INTERSECT{D,Q} instructions + 7, 0, edx, 9, srdbs_ctrl , SRBDS mitigation MSR available + 7, 0, edx, 10, md_clear , VERW MD_CLEAR microcode support + 7, 0, edx, 11, rtm_always_abort , XBEGIN (RTM transaction) always aborts + 7, 0, edx, 13, tsx_force_abort , MSR TSX_FORCE_ABORT, RTM_ABORT bit, supported + 7, 0, edx, 14, serialize , SERIALIZE instruction + 7, 0, edx, 15, hybrid_cpu , The CPU is identified as a 'hybrid part' + 7, 0, edx, 16, tsxldtrk , TSX suspend/resume load address tracking + 7, 0, edx, 18, pconfig , PCONFIG instruction + 7, 0, edx, 19, arch_lbr , Intel architectural LBRs + 7, 0, edx, 20, ibt , CET indirect branch tracking + 7, 0, edx, 22, amx_bf16 , AMX-BF16: tile bfloat16 support + 7, 0, edx, 23, avx512_fp16 , AVX-512 FP16 instructions + 7, 0, edx, 24, amx_tile , AMX-TILE: tile architecture support + 7, 0, edx, 25, amx_int8 , AMX-INT8: tile 8-bit integer support + 7, 0, edx, 26, spec_ctrl , Speculation Control (IBRS/IBPB: indirect branch restrictions) + 7, 0, edx, 27, intel_stibp , Single thread indirect branch predictors + 7, 0, edx, 28, flush_l1d , FLUSH L1D cache: IA32_FLUSH_CMD MSR + 7, 0, edx, 29, arch_capabilities , Intel IA32_ARCH_CAPABILITIES MSR + 7, 0, edx, 30, core_capabilities , IA32_CORE_CAPABILITIES MSR + 7, 0, edx, 31, spec_ctrl_ssbd , Speculative store bypass disable + 7, 1, eax, 4, avx_vnni , AVX-VNNI instructions + 7, 1, eax, 5, avx512_bf16 , AVX-512 bFloat16 instructions + 7, 1, eax, 6, lass , Linear address space separation + 7, 1, eax, 7, cmpccxadd , CMPccXADD instructions + 7, 1, eax, 8, arch_perfmon_ext , ArchPerfmonExt: CPUID leaf 0x23 is supported + 7, 1, eax, 10, fzrm , Fast zero-length REP MOVSB + 7, 1, eax, 11, fsrs , Fast short REP STOSB + 7, 1, eax, 12, fsrc , Fast Short REP CMPSB/SCASB + 7, 1, eax, 17, fred , FRED: Flexible return and event delivery transitions + 7, 1, eax, 18, lkgs , LKGS: Load 'kernel' (userspace) GS + 7, 1, eax, 19, wrmsrns , WRMSRNS instr (WRMSR-non-serializing) + 7, 1, eax, 21, amx_fp16 , AMX-FP16: FP16 tile operations + 7, 1, eax, 22, hreset , History reset support + 7, 1, eax, 23, avx_ifma , Integer fused multiply add + 7, 1, eax, 26, lam , Linear address masking + 7, 1, eax, 27, rd_wr_msrlist , RDMSRLIST/WRMSRLIST instructions + 7, 1, ebx, 0, intel_ppin , Protected processor inventory number (PPIN{,_CTL} MSRs) + 7, 1, edx, 4, avx_vnni_int8 , AVX-VNNI-INT8 instructions + 7, 1, edx, 5, avx_ne_convert , AVX-NE-CONVERT instructions + 7, 1, edx, 8, amx_complex , AMX-COMPLEX instructions (starting from Granite Rapids) + 7, 1, edx, 14, prefetchit_0_1 , PREFETCHIT0/1 instructions + 7, 1, edx, 18, cet_sss , CET supervisor shadow stacks safe to use + 7, 2, edx, 0, intel_psfd , Intel predictive store forward disable + 7, 2, edx, 1, ipred_ctrl , MSR bits IA32_SPEC_CTRL.IPRED_DIS_{U,S} + 7, 2, edx, 2, rrsba_ctrl , MSR bits IA32_SPEC_CTRL.RRSBA_DIS_{U,S} + 7, 2, edx, 3, ddp_ctrl , MSR bit IA32_SPEC_CTRL.DDPD_U + 7, 2, edx, 4, bhi_ctrl , MSR bit IA32_SPEC_CTRL.BHI_DIS_S + 7, 2, edx, 5, mcdt_no , MCDT mitigation not needed + 7, 2, edx, 6, uclock_disable , UC-lock disable is supported + +# Leaf 9H +# Intel DCA (Direct Cache Access) enumeration + + 9, 0, eax, 0, dca_enabled_in_bios , DCA is enabled in BIOS + +# Leaf AH +# Intel PMU (Performance Monitoring Unit) enumeration + + 0xa, 0, eax, 7:0, pmu_version , Performance monitoring unit version ID + 0xa, 0, eax, 15:8, pmu_n_gcounters , Number of general PMU counters per logical CPU + 0xa, 0, eax, 23:16, pmu_gcounters_nbits , Bitwidth of PMU general counters + 0xa, 0, eax, 31:24, pmu_cpuid_ebx_bits , Length of cpuid leaf 0xa EBX bit vector + 0xa, 0, ebx, 0, no_core_cycle_evt , Core cycle event not available + 0xa, 0, ebx, 1, no_insn_retired_evt , Instruction retired event not available + 0xa, 0, ebx, 2, no_refcycle_evt , Reference cycles event not available + 0xa, 0, ebx, 3, no_llc_ref_evt , LLC-reference event not available + 0xa, 0, ebx, 4, no_llc_miss_evt , LLC-misses event not available + 0xa, 0, ebx, 5, no_br_insn_ret_evt , Branch instruction retired event not available + 0xa, 0, ebx, 6, no_br_mispredict_evt , Branch mispredict retired event not available + 0xa, 0, ebx, 7, no_td_slots_evt , Topdown slots event not available + 0xa, 0, ecx, 31:0, pmu_fcounters_bitmap , Fixed-function PMU counters support bitmap + 0xa, 0, edx, 4:0, pmu_n_fcounters , Number of fixed PMU counters + 0xa, 0, edx, 12:5, pmu_fcounters_nbits , Bitwidth of PMU fixed counters + 0xa, 0, edx, 15, anythread_depr , AnyThread deprecation + +# Leaf BH +# CPUs v1 extended topology enumeration + + 0xb, 1:0, eax, 4:0, x2apic_id_shift , Bit width of this level (previous levels inclusive) + 0xb, 1:0, ebx, 15:0, domain_lcpus_count , Logical CPUs count across all instances of this domain + 0xb, 1:0, ecx, 7:0, domain_nr , This domain level (subleaf ID) + 0xb, 1:0, ecx, 15:8, domain_type , This domain type + 0xb, 1:0, edx, 31:0, x2apic_id , x2APIC ID of current logical CPU + +# Leaf DH +# Processor extended state enumeration + + 0xd, 0, eax, 0, xcr0_x87 , XCR0.X87 (bit 0) supported + 0xd, 0, eax, 1, xcr0_sse , XCR0.SEE (bit 1) supported + 0xd, 0, eax, 2, xcr0_avx , XCR0.AVX (bit 2) supported + 0xd, 0, eax, 3, xcr0_mpx_bndregs , XCR0.BNDREGS (bit 3) supported (MPX BND0-BND3 regs) + 0xd, 0, eax, 4, xcr0_mpx_bndcsr , XCR0.BNDCSR (bit 4) supported (MPX BNDCFGU/BNDSTATUS regs) + 0xd, 0, eax, 5, xcr0_avx512_opmask , XCR0.OPMASK (bit 5) supported (AVX-512 k0-k7 regs) + 0xd, 0, eax, 6, xcr0_avx512_zmm_hi256 , XCR0.ZMM_Hi256 (bit 6) supported (AVX-512 ZMM0->ZMM7/15 regs) + 0xd, 0, eax, 7, xcr0_avx512_hi16_zmm , XCR0.HI16_ZMM (bit 7) supported (AVX-512 ZMM16->ZMM31 regs) + 0xd, 0, eax, 9, xcr0_pkru , XCR0.PKRU (bit 9) supported (XSAVE PKRU reg) + 0xd, 0, eax, 11, xcr0_cet_u , AMD XCR0.CET_U (bit 11) supported (CET supervisor state) + 0xd, 0, eax, 12, xcr0_cet_s , AMD XCR0.CET_S (bit 12) support (CET user state) + 0xd, 0, eax, 17, xcr0_tileconfig , XCR0.TILECONFIG (bit 17) supported (AMX can manage TILECONFIG) + 0xd, 0, eax, 18, xcr0_tiledata , XCR0.TILEDATA (bit 18) supported (AMX can manage TILEDATA) + 0xd, 0, ebx, 31:0, xsave_sz_xcr0_enabled , XSAVE/XRSTR area byte size, for XCR0 enabled features + 0xd, 0, ecx, 31:0, xsave_sz_max , XSAVE/XRSTR area max byte size, all CPU features + 0xd, 0, edx, 30, xcr0_lwp , AMD XCR0.LWP (bit 62) supported (Light-weight Profiling) + 0xd, 1, eax, 0, xsaveopt , XSAVEOPT instruction + 0xd, 1, eax, 1, xsavec , XSAVEC instruction + 0xd, 1, eax, 2, xgetbv1 , XGETBV instruction with ECX = 1 + 0xd, 1, eax, 3, xsaves , XSAVES/XRSTORS instructions (and XSS MSR) + 0xd, 1, eax, 4, xfd , Extended feature disable support + 0xd, 1, ebx, 31:0, xsave_sz_xcr0_xmms_enabled, XSAVE area size, all XCR0 and XMMS features enabled + 0xd, 1, ecx, 8, xss_pt , PT state, supported + 0xd, 1, ecx, 10, xss_pasid , PASID state, supported + 0xd, 1, ecx, 11, xss_cet_u , CET user state, supported + 0xd, 1, ecx, 12, xss_cet_p , CET supervisor state, supported + 0xd, 1, ecx, 13, xss_hdc , HDC state, supported + 0xd, 1, ecx, 14, xss_uintr , UINTR state, supported + 0xd, 1, ecx, 15, xss_lbr , LBR state, supported + 0xd, 1, ecx, 16, xss_hwp , HWP state, supported + 0xd, 63:2, eax, 31:0, xsave_sz , Size of save area for subleaf-N feature, in bytes + 0xd, 63:2, ebx, 31:0, xsave_offset , Offset of save area for subleaf-N feature, in bytes + 0xd, 63:2, ecx, 0, is_xss_bit , Subleaf N describes an XSS bit, otherwise XCR0 bit + 0xd, 63:2, ecx, 1, compacted_xsave_64byte_aligned, When compacted, subleaf-N feature xsave area is 64-byte aligned + +# Leaf FH +# Intel RDT / AMD PQoS resource monitoring + + 0xf, 0, ebx, 31:0, core_rmid_max , RMID max, within this core, all types (0-based) + 0xf, 0, edx, 1, cqm_llc , LLC QoS-monitoring supported + 0xf, 1, eax, 7:0, l3c_qm_bitwidth , L3 QoS-monitoring counter bitwidth (24-based) + 0xf, 1, eax, 8, l3c_qm_overflow_bit , QM_CTR MSR bit 61 is an overflow bit + 0xf, 1, ebx, 31:0, l3c_qm_conver_factor , QM_CTR MSR conversion factor to bytes + 0xf, 1, ecx, 31:0, l3c_qm_rmid_max , L3 QoS-monitoring max RMID + 0xf, 1, edx, 0, cqm_occup_llc , L3 QoS occupancy monitoring supported + 0xf, 1, edx, 1, cqm_mbm_total , L3 QoS total bandwidth monitoring supported + 0xf, 1, edx, 2, cqm_mbm_local , L3 QoS local bandwidth monitoring supported # Leaf 10H -# Intel RDT Allocation - - 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported - 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported - 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported - +# Intel RDT / AMD PQoS allocation enumeration + + 0x10, 0, ebx, 1, cat_l3 , L3 Cache Allocation Technology supported + 0x10, 0, ebx, 2, cat_l2 , L2 Cache Allocation Technology supported + 0x10, 0, ebx, 3, mba , Memory Bandwidth Allocation supported + 0x10, 2:1, eax, 4:0, cat_cbm_len , L3/L2_CAT capacity bitmask length, minus-one notation + 0x10, 2:1, ebx, 31:0, cat_units_bitmap , L3/L2_CAT bitmap of allocation units + 0x10, 2:1, ecx, 1, l3_cat_cos_infreq_updates, L3_CAT COS updates should be infrequent + 0x10, 2:1, ecx, 2, cdp_l3 , L3/L2_CAT CDP (Code and Data Prioritization) + 0x10, 2:1, ecx, 3, cat_sparse_1s , L3/L2_CAT non-contiguous 1s value supported + 0x10, 2:1, edx, 15:0, cat_cos_max , L3/L2_CAT max COS (Class of Service) supported + 0x10, 3, eax, 11:0, mba_max_delay , Max MBA throttling value; minus-one notation + 0x10, 3, ecx, 0, per_thread_mba , Per-thread MBA controls are supported + 0x10, 3, ecx, 2, mba_delay_linear , Delay values are linear + 0x10, 3, edx, 15:0, mba_cos_max , MBA max Class of Service supported # Leaf 12H -# SGX Capability -# -# Some detailed SGX features not added yet - - 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported - 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported - +# Intel Software Guard Extensions (SGX) enumeration + + 0x12, 0, eax, 0, sgx1 , SGX1 leaf functions supported + 0x12, 0, eax, 1, sgx2 , SGX2 leaf functions supported + 0x12, 0, eax, 5, enclv_leaves , ENCLV leaves (E{INC,DEC}VIRTCHILD, ESETCONTEXT) supported + 0x12, 0, eax, 6, encls_leaves , ENCLS leaves (ENCLS ETRACKC, ERDINFO, ELDBC, ELDUC) supported + 0x12, 0, eax, 7, enclu_everifyreport2 , ENCLU leaf EVERIFYREPORT2 supported + 0x12, 0, eax, 10, encls_eupdatesvn , ENCLS leaf EUPDATESVN supported + 0x12, 0, eax, 11, sgx_edeccssa , ENCLU leaf EDECCSSA supported + 0x12, 0, ebx, 0, miscselect_exinfo , SSA.MISC frame: reporting #PF and #GP exceptions inside enclave supported + 0x12, 0, ebx, 1, miscselect_cpinfo , SSA.MISC frame: reporting #CP exceptions inside enclave supported + 0x12, 0, edx, 7:0, max_enclave_sz_not64 , Maximum enclave size in non-64-bit mode (log2) + 0x12, 0, edx, 15:8, max_enclave_sz_64 , Maximum enclave size in 64-bit mode (log2) + 0x12, 1, eax, 0, secs_attr_init , ATTRIBUTES.INIT supported (enclave initialized by EINIT) + 0x12, 1, eax, 1, secs_attr_debug , ATTRIBUTES.DEBUG supported (enclave permits debugger read/write) + 0x12, 1, eax, 2, secs_attr_mode64bit , ATTRIBUTES.MODE64BIT supported (enclave runs in 64-bit mode) + 0x12, 1, eax, 4, secs_attr_provisionkey , ATTRIBUTES.PROVISIONKEY supported (provisioning key available) + 0x12, 1, eax, 5, secs_attr_einittoken_key, ATTRIBUTES.EINITTOKEN_KEY supported (EINIT token key available) + 0x12, 1, eax, 6, secs_attr_cet , ATTRIBUTES.CET supported (enable CET attributes) + 0x12, 1, eax, 7, secs_attr_kss , ATTRIBUTES.KSS supported (Key Separation and Sharing enabled) + 0x12, 1, eax, 10, secs_attr_aexnotify , ATTRIBUTES.AEXNOTIFY supported (enclave threads may get AEX notifications + 0x12, 1, ecx, 0, xfrm_x87 , Enclave XFRM.X87 (bit 0) supported + 0x12, 1, ecx, 1, xfrm_sse , Enclave XFRM.SEE (bit 1) supported + 0x12, 1, ecx, 2, xfrm_avx , Enclave XFRM.AVX (bit 2) supported + 0x12, 1, ecx, 3, xfrm_mpx_bndregs , Enclave XFRM.BNDREGS (bit 3) supported (MPX BND0-BND3 regs) + 0x12, 1, ecx, 4, xfrm_mpx_bndcsr , Enclave XFRM.BNDCSR (bit 4) supported (MPX BNDCFGU/BNDSTATUS regs) + 0x12, 1, ecx, 5, xfrm_avx512_opmask , Enclave XFRM.OPMASK (bit 5) supported (AVX-512 k0-k7 regs) + 0x12, 1, ecx, 6, xfrm_avx512_zmm_hi256 , Enclave XFRM.ZMM_Hi256 (bit 6) supported (AVX-512 ZMM0->ZMM7/15 regs) + 0x12, 1, ecx, 7, xfrm_avx512_hi16_zmm , Enclave XFRM.HI16_ZMM (bit 7) supported (AVX-512 ZMM16->ZMM31 regs) + 0x12, 1, ecx, 9, xfrm_pkru , Enclave XFRM.PKRU (bit 9) supported (XSAVE PKRU reg) + 0x12, 1, ecx, 17, xfrm_tileconfig , Enclave XFRM.TILECONFIG (bit 17) supported (AMX can manage TILECONFIG) + 0x12, 1, ecx, 18, xfrm_tiledata , Enclave XFRM.TILEDATA (bit 18) supported (AMX can manage TILEDATA) + 0x12, 31:2, eax, 3:0, subleaf_type , Subleaf type (dictates output layout) + 0x12, 31:2, eax, 31:12, epc_sec_base_addr_0 , EPC section base addr, bits[12:31] + 0x12, 31:2, ebx, 19:0, epc_sec_base_addr_1 , EPC section base addr, bits[32:51] + 0x12, 31:2, ecx, 3:0, epc_sec_type , EPC section type / property encoding + 0x12, 31:2, ecx, 31:12, epc_sec_size_0 , EPC section size, bits[12:31] + 0x12, 31:2, edx, 19:0, epc_sec_size_1 , EPC section size, bits[32:51] # Leaf 14H -# Intel Processor Tracer -# +# Intel Processor Trace enumeration + + 0x14, 0, eax, 31:0, pt_max_subleaf , Max cpuid 0x14 subleaf + 0x14, 0, ebx, 0, cr3_filtering , IA32_RTIT_CR3_MATCH is accessible + 0x14, 0, ebx, 1, psb_cyc , Configurable PSB and cycle-accurate mode + 0x14, 0, ebx, 2, ip_filtering , IP/TraceStop filtering; Warm-reset PT MSRs preservation + 0x14, 0, ebx, 3, mtc_timing , MTC timing packet; COFI-based packets suppression + 0x14, 0, ebx, 4, ptwrite , PTWRITE support + 0x14, 0, ebx, 5, power_event_trace , Power Event Trace support + 0x14, 0, ebx, 6, psb_pmi_preserve , PSB and PMI preservation support + 0x14, 0, ebx, 7, event_trace , Event Trace packet generation through IA32_RTIT_CTL.EventEn + 0x14, 0, ebx, 8, tnt_disable , TNT packet generation disable through IA32_RTIT_CTL.DisTNT + 0x14, 0, ecx, 0, topa_output , ToPA output scheme support + 0x14, 0, ecx, 1, topa_multiple_entries , ToPA tables can hold multiple entries + 0x14, 0, ecx, 2, single_range_output , Single-range output scheme supported + 0x14, 0, ecx, 3, trance_transport_output, Trace Transport subsystem output support + 0x14, 0, ecx, 31, ip_payloads_lip , IP payloads have LIP values (CS base included) + 0x14, 1, eax, 2:0, num_address_ranges , Filtering number of configurable Address Ranges + 0x14, 1, eax, 31:16, mtc_periods_bmp , Bitmap of supported MTC period encodings + 0x14, 1, ebx, 15:0, cycle_thresholds_bmp , Bitmap of supported Cycle Threshold encodings + 0x14, 1, ebx, 31:16, psb_periods_bmp , Bitmap of supported Configurable PSB frequency encodings # Leaf 15H -# Time Stamp Counter and Nominal Core Crystal Clock Information +# Intel TSC (Time Stamp Counter) enumeration - 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio - 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio - 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + 0x15, 0, eax, 31:0, tsc_denominator , Denominator of the TSC/'core crystal clock' ratio + 0x15, 0, ebx, 31:0, tsc_numerator , Numerator of the TSC/'core crystal clock' ratio + 0x15, 0, ecx, 31:0, cpu_crystal_hz , Core crystal clock nominal frequency, in Hz # Leaf 16H -# Processor Frequency Information +# Intel processor fequency enumeration - 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz - 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz - 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + 0x16, 0, eax, 15:0, cpu_base_mhz , Processor base frequency, in MHz + 0x16, 0, ebx, 15:0, cpu_max_mhz , Processor max frequency, in MHz + 0x16, 0, ecx, 15:0, bus_mhz , Bus reference frequency, in MHz # Leaf 17H -# System-On-Chip Vendor Attribute - - 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf - 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID - 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme - 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor - 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID +# Intel SoC vendor attributes enumeration + + 0x17, 0, eax, 31:0, soc_max_subleaf , Max cpuid leaf 0x17 subleaf + 0x17, 0, ebx, 15:0, soc_vendor_id , SoC vendor ID + 0x17, 0, ebx, 16, is_vendor_scheme , Assigned by industry enumaeratoion scheme (not Intel) + 0x17, 0, ecx, 31:0, soc_proj_id , SoC project ID, assigned by vendor + 0x17, 0, edx, 31:0, soc_stepping_id , Soc project stepping ID, assigned by vendor + 0x17, 3:1, eax, 31:0, vendor_brand_a , Vendor Brand ID string, bytes subleaf_nr * (0 -> 3) + 0x17, 3:1, ebx, 31:0, vendor_brand_b , Vendor Brand ID string, bytes subleaf_nr * (4 -> 7) + 0x17, 3:1, ecx, 31:0, vendor_brand_c , Vendor Brand ID string, bytes subleaf_nr * (8 -> 11) + 0x17, 3:1, edx, 31:0, vendor_brand_d , Vendor Brand ID string, bytes subleaf_nr * (12 -> 15) # Leaf 18H -# Deterministic Address Translation Parameters - +# Intel determenestic address translation (TLB) parameters + + 0x18, 31:0, eax, 31:0, tlb_max_subleaf , Max cpuid 0x18 subleaf + 0x18, 31:0, ebx, 0, tlb_4k_page , TLB 4KB-page entries supported + 0x18, 31:0, ebx, 1, tlb_2m_page , TLB 2MB-page entries supported + 0x18, 31:0, ebx, 2, tlb_4m_page , TLB 4MB-page entries supported + 0x18, 31:0, ebx, 3, tlb_1g_page , TLB 1GB-page entries supported + 0x18, 31:0, ebx, 10:8, hard_partitioning , (Hard/Soft) partitioning between logical CPUs sharing this struct + 0x18, 31:0, ebx, 31:16, n_way_associative , Ways of associativity + 0x18, 31:0, ecx, 31:0, n_sets , Number of sets + 0x18, 31:0, edx, 4:0, tlb_type , Translation cache type (TLB type) + 0x18, 31:0, edx, 7:5, tlb_cache_level , Translation cache level (1-based) + 0x18, 31:0, edx, 8, is_fully_associative , Fully-associative structure + 0x18, 31:0, edx, 25:14, tlb_max_addressible_ids, Max num of addressible IDs for logical CPUs sharing this TLB - 1 # Leaf 19H -# Key Locker Leaf +# Intel Key Locker enumeration + 0x19, 0, eax, 0, kl_cpl0_only , CPL0-only key Locker restriction supported + 0x19, 0, eax, 1, kl_no_encrypt , No-encrypt key locker restriction supported + 0x19, 0, eax, 2, kl_no_decrypt , No-decrypt key locker restriction supported + 0x19, 0, ebx, 0, aes_keylocker , AES key locker instructions supported + 0x19, 0, ebx, 2, aes_keylocker_wide , AES wide key locker instructions supported + 0x19, 0, ebx, 4, kl_msr_iwkey , Key locker MSRs and IWKEY backups supported + 0x19, 0, ecx, 0, loadiwkey_no_backup , LOADIWKEY NoBackup parameter supported + 0x19, 0, ecx, 1, iwkey_rand , IWKEY randomization (KeySource encoding 1) supported # Leaf 1AH -# Hybrid Information - - 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core - +# Intel hybrid CPUs identification (e.g. Atom, Core) + + 0x1a, 0, eax, 23:0, core_native_model , This core's native model ID + 0x1a, 0, eax, 31:24, core_type , This core's type + +# Leaf 1BH +# Intel PCONFIG (Platform configuration) enumeration + + 0x1b, 31:0, eax, 11:0, pconfig_subleaf_type , CPUID 0x1b subleaf type + 0x1b, 31:0, ebx, 31:0, pconfig_target_id_x , A supported PCONFIG target ID + 0x1b, 31:0, ecx, 31:0, pconfig_target_id_y , A supported PCONFIG target ID + 0x1b, 31:0, edx, 31:0, pconfig_target_id_z , A supported PCONFIG target ID + +# Leaf 1CH +# Intel LBR (Last Branch Record) enumeration + + 0x1c, 0, eax, 0, lbr_depth_8 , Max stack depth (number of LBR entries) = 8 + 0x1c, 0, eax, 1, lbr_depth_16 , Max stack depth (number of LBR entries) = 16 + 0x1c, 0, eax, 2, lbr_depth_24 , Max stack depth (number of LBR entries) = 24 + 0x1c, 0, eax, 3, lbr_depth_32 , Max stack depth (number of LBR entries) = 32 + 0x1c, 0, eax, 4, lbr_depth_40 , Max stack depth (number of LBR entries) = 40 + 0x1c, 0, eax, 5, lbr_depth_48 , Max stack depth (number of LBR entries) = 48 + 0x1c, 0, eax, 6, lbr_depth_56 , Max stack depth (number of LBR entries) = 56 + 0x1c, 0, eax, 7, lbr_depth_64 , Max stack depth (number of LBR entries) = 64 + 0x1c, 0, eax, 30, lbr_deep_c_reset , LBRs maybe cleared on MWAIT C-state > C1 + 0x1c, 0, eax, 31, lbr_ip_is_lip , LBR IP contain Last IP, otherwise effective IP + 0x1c, 0, ebx, 0, lbr_cpl , CPL filtering (non-zero IA32_LBR_CTL[2:1]) supported + 0x1c, 0, ebx, 1, lbr_branch_filter , Branch filtering (non-zero IA32_LBR_CTL[22:16]) supported + 0x1c, 0, ebx, 2, lbr_call_stack , Call-stack mode (IA32_LBR_CTL[3] = 1) supported + 0x1c, 0, ecx, 0, lbr_mispredict , Branch misprediction bit supported (IA32_LBR_x_INFO[63]) + 0x1c, 0, ecx, 1, lbr_timed_lbr , Timed LBRs (CPU cycles since last LBR entry) supported + 0x1c, 0, ecx, 2, lbr_branch_type , Branch type field (IA32_LBR_INFO_x[59:56]) supported + 0x1c, 0, ecx, 19:16, lbr_events_gpc_bmp , LBR PMU-events logging support; bitmap for first 4 GP (general-purpose) Counters + +# Leaf 1DH +# Intel AMX (Advanced Matrix Extensions) tile information + + 0x1d, 0, eax, 31:0, amx_max_palette , Highest palette ID / subleaf ID + 0x1d, 1, eax, 15:0, amx_palette_size , AMX palette total tiles size, in bytes + 0x1d, 1, eax, 31:16, amx_tile_size , AMX single tile's size, in bytes + 0x1d, 1, ebx, 15:0, amx_tile_row_size , AMX tile single row's size, in bytes + 0x1d, 1, ebx, 31:16, amx_palette_nr_tiles , AMX palette number of tiles + 0x1d, 1, ecx, 15:0, amx_tile_nr_rows , AMX tile max number of rows + +# Leaf 1EH +# Intel AMX, TMUL (Tile-matrix MULtiply) accelerator unit enumeration + + 0x1e, 0, ebx, 7:0, tmul_maxk , TMUL unit maximum height, K (rows or columns) + 0x1e, 0, ebx, 23:8, tmul_maxn , TMUL unit maxiumum SIMD dimension, N (column bytes) # Leaf 1FH -# V2 Extended Topology - A preferred superset to leaf 0BH - - -# According to SDM -# 40000000H - 4FFFFFFFH is invalid range +# Intel extended topology enumeration v2 + + 0x1f, 5:0, eax, 4:0, x2apic_id_shift , Bit width of this level (previous levels inclusive) + 0x1f, 5:0, ebx, 15:0, domain_lcpus_count , Logical CPUs count across all instances of this domain + 0x1f, 5:0, ecx, 7:0, domain_level , This domain level (subleaf ID) + 0x1f, 5:0, ecx, 15:8, domain_type , This domain type + 0x1f, 5:0, edx, 31:0, x2apic_id , x2APIC ID of current logical CPU + +# Leaf 20H +# Intel HRESET (History Reset) enumeration + + 0x20, 0, eax, 31:0, hreset_nr_subleaves , CPUID 0x20 max subleaf + 1 + 0x20, 0, ebx, 0, hreset_thread_director , HRESET of Intel thread director is supported + +# Leaf 21H +# Intel TD (Trust Domain) guest execution environment enumeration + + 0x21, 0, ebx, 31:0, tdx_vendorid_0 , TDX vendor ID string bytes 0 - 3 + 0x21, 0, ecx, 31:0, tdx_vendorid_2 , CPU vendor ID string bytes 8 - 11 + 0x21, 0, edx, 31:0, tdx_vendorid_1 , CPU vendor ID string bytes 4 - 7 + +# Leaf 23H +# Intel Architectural Performance Monitoring Extended (ArchPerfmonExt) + + 0x23, 0, eax, 1, subleaf_1_counters , Subleaf 1, PMU counters bitmaps, is valid + 0x23, 0, eax, 3, subleaf_3_events , Subleaf 3, PMU events bitmaps, is valid + 0x23, 0, ebx, 0, unitmask2 , IA32_PERFEVTSELx MSRs UnitMask2 is supported + 0x23, 0, ebx, 1, zbit , IA32_PERFEVTSELx MSRs Z-bit is supported + 0x23, 1, eax, 31:0, pmu_gp_counters_bitmap , General-purpose PMU counters bitmap + 0x23, 1, ebx, 31:0, pmu_f_counters_bitmap , Fixed PMU counters bitmap + 0x23, 3, eax, 0, core_cycles_evt , Core cycles event supported + 0x23, 3, eax, 1, insn_retired_evt , Instructions retired event supported + 0x23, 3, eax, 2, ref_cycles_evt , Reference cycles event supported + 0x23, 3, eax, 3, llc_refs_evt , Last-level cache references event supported + 0x23, 3, eax, 4, llc_misses_evt , Last-level cache misses event supported + 0x23, 3, eax, 5, br_insn_ret_evt , Branch instruction retired event supported + 0x23, 3, eax, 6, br_mispr_evt , Branch mispredict retired event supported + 0x23, 3, eax, 7, td_slots_evt , Topdown slots event supported + 0x23, 3, eax, 8, td_backend_bound_evt , Topdown backend bound event supported + 0x23, 3, eax, 9, td_bad_spec_evt , Topdown bad speculation event supported + 0x23, 3, eax, 10, td_frontend_bound_evt , Topdown frontend bound event supported + 0x23, 3, eax, 11, td_retiring_evt , Topdown retiring event support + +# Leaf 40000000H +# Maximum hypervisor standard leaf + hypervisor vendor string + +0x40000000, 0, eax, 31:0, max_hyp_leaf , Maximum hypervisor standard leaf number +0x40000000, 0, ebx, 31:0, hypervisor_id_0 , Hypervisor ID string bytes 0 - 3 +0x40000000, 0, ecx, 31:0, hypervisor_id_1 , Hypervisor ID string bytes 4 - 7 +0x40000000, 0, edx, 31:0, hypervisor_id_2 , Hypervisor ID string bytes 8 - 11 + +# Leaf 80000000H +# Maximum extended leaf number + CPU vendor string (AMD) + +0x80000000, 0, eax, 31:0, max_ext_leaf , Maximum extended cpuid leaf supported +0x80000000, 0, ebx, 31:0, cpu_vendorid_0 , Vendor ID string bytes 0 - 3 +0x80000000, 0, ecx, 31:0, cpu_vendorid_2 , Vendor ID string bytes 8 - 11 +0x80000000, 0, edx, 31:0, cpu_vendorid_1 , Vendor ID string bytes 4 - 7 # Leaf 80000001H -# Extended Processor Signature and Feature Bits - -0x80000001, 0, EAX, 27:20, extfamily, Extended family -0x80000001, 0, EAX, 19:16, extmodel, Extended model -0x80000001, 0, EAX, 11:8, basefamily, Description of Family -0x80000001, 0, EAX, 11:8, basemodel, Model numbers vary with product -0x80000001, 0, EAX, 3:0, stepping, Processor stepping (revision) for a specific model - -0x80000001, 0, EBX, 31:28, pkgtype, Specifies the package type - -0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode -0x80000001, 0, ECX, 1, cmplegacy, Core multi-processing legacy mode -0x80000001, 0, ECX, 2, svm, Indicates support for: VMRUN, VMLOAD, VMSAVE, CLGI, VMMCALL, and INVLPGA -0x80000001, 0, ECX, 3, extapicspace, Extended APIC register space -0x80000001, 0, ECX, 4, altmovecr8, Indicates support for LOCK MOV CR0 means MOV CR8 -0x80000001, 0, ECX, 5, lzcnt, LZCNT -0x80000001, 0, ECX, 6, sse4a, EXTRQ, INSERTQ, MOVNTSS, and MOVNTSD instruction support -0x80000001, 0, ECX, 7, misalignsse, Misaligned SSE Mode -0x80000001, 0, ECX, 8, prefetchw, PREFETCHW -0x80000001, 0, ECX, 9, osvw, OS Visible Work-around support -0x80000001, 0, ECX, 10, ibs, Instruction Based Sampling -0x80000001, 0, ECX, 11, xop, Extended operation support -0x80000001, 0, ECX, 12, skinit, SKINIT and STGI support -0x80000001, 0, ECX, 13, wdt, Watchdog timer support -0x80000001, 0, ECX, 15, lwp, Lightweight profiling support -0x80000001, 0, ECX, 16, fma4, Four-operand FMA instruction support -0x80000001, 0, ECX, 17, tce, Translation cache extension -0x80000001, 0, ECX, 22, TopologyExtensions, Indicates support for Core::X86::Cpuid::CachePropEax0 and Core::X86::Cpuid::ExtApicId -0x80000001, 0, ECX, 23, perfctrextcore, Indicates support for Core::X86::Msr::PERF_CTL0 - 5 and Core::X86::Msr::PERF_CTR -0x80000001, 0, ECX, 24, perfctrextdf, Indicates support for Core::X86::Msr::DF_PERF_CTL and Core::X86::Msr::DF_PERF_CTR -0x80000001, 0, ECX, 26, databreakpointextension, Indicates data breakpoint support for Core::X86::Msr::DR0_ADDR_MASK, Core::X86::Msr::DR1_ADDR_MASK, Core::X86::Msr::DR2_ADDR_MASK and Core::X86::Msr::DR3_ADDR_MASK -0x80000001, 0, ECX, 27, perftsc, Performance time-stamp counter supported -0x80000001, 0, ECX, 28, perfctrextllc, Indicates support for L3 performance counter extensions -0x80000001, 0, ECX, 29, mwaitextended, MWAITX and MONITORX capability is supported -0x80000001, 0, ECX, 30, admskextn, Indicates support for address mask extension (to 32 bits and to all 4 DRs) for instruction breakpoints - -0x80000001, 0, EDX, 0, fpu, x87 floating point unit on-chip -0x80000001, 0, EDX, 1, vme, Virtual-mode enhancements -0x80000001, 0, EDX, 2, de, Debugging extensions, IO breakpoints, CR4.DE -0x80000001, 0, EDX, 3, pse, Page-size extensions (4 MB pages) -0x80000001, 0, EDX, 4, tsc, Time stamp counter, RDTSC/RDTSCP instructions, CR4.TSD -0x80000001, 0, EDX, 5, msr, Model-specific registers (MSRs), with RDMSR and WRMSR instructions -0x80000001, 0, EDX, 6, pae, Physical-address extensions (PAE) -0x80000001, 0, EDX, 7, mce, Machine Check Exception, CR4.MCE -0x80000001, 0, EDX, 8, cmpxchg8b, CMPXCHG8B instruction -0x80000001, 0, EDX, 9, apic, advanced programmable interrupt controller (APIC) exists and is enabled -0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported -0x80000001, 0, EDX, 12, mtrr, Memory-type range registers -0x80000001, 0, EDX, 13, pge, Page global extension, CR4.PGE -0x80000001, 0, EDX, 14, mca, Machine check architecture, MCG_CAP -0x80000001, 0, EDX, 15, cmov, Conditional move instructions, CMOV, FCOMI, FCMOV -0x80000001, 0, EDX, 16, pat, Page attribute table -0x80000001, 0, EDX, 17, pse36, Page-size extensions -0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available -0x80000001, 0, EDX, 22, mmxext, AMD extensions to MMX instructions -0x80000001, 0, EDX, 23, mmx, MMX instructions -0x80000001, 0, EDX, 24, fxsr, FXSAVE and FXRSTOR instructions -0x80000001, 0, EDX, 25, ffxsr, FXSAVE and FXRSTOR instruction optimizations -0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported -0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available -0x80000001, 0, EDX, 29, lm, 64b Architecture supported -0x80000001, 0, EDX, 30, threednowext, AMD extensions to 3DNow! instructions -0x80000001, 0, EDX, 31, threednow, 3DNow! instructions - -# Leaf 80000002H/80000003H/80000004H -# Processor Brand String +# Extended CPU feature identifiers + +0x80000001, 0, eax, 3:0, e_stepping_id , Stepping ID +0x80000001, 0, eax, 7:4, e_base_model , Base processor model +0x80000001, 0, eax, 11:8, e_base_family , Base processor family +0x80000001, 0, eax, 19:16, e_ext_model , Extended processor model +0x80000001, 0, eax, 27:20, e_ext_family , Extended processor family +0x80000001, 0, ebx, 15:0, brand_id , Brand ID +0x80000001, 0, ebx, 31:28, pkg_type , Package type +0x80000001, 0, ecx, 0, lahf_lm , LAHF and SAHF in 64-bit mode +0x80000001, 0, ecx, 1, cmp_legacy , Multi-processing legacy mode (No HT) +0x80000001, 0, ecx, 2, svm , Secure Virtual Machine +0x80000001, 0, ecx, 3, extapic , Extended APIC space +0x80000001, 0, ecx, 4, cr8_legacy , LOCK MOV CR0 means MOV CR8 +0x80000001, 0, ecx, 5, abm , LZCNT advanced bit manipulation +0x80000001, 0, ecx, 6, sse4a , SSE4A support +0x80000001, 0, ecx, 7, misalignsse , Misaligned SSE mode +0x80000001, 0, ecx, 8, 3dnowprefetch , 3DNow PREFETCH/PREFETCHW support +0x80000001, 0, ecx, 9, osvw , OS visible workaround +0x80000001, 0, ecx, 10, ibs , Instruction based sampling +0x80000001, 0, ecx, 11, xop , XOP: extended operation (AVX instructions) +0x80000001, 0, ecx, 12, skinit , SKINIT/STGI support +0x80000001, 0, ecx, 13, wdt , Watchdog timer support +0x80000001, 0, ecx, 15, lwp , Lightweight profiling +0x80000001, 0, ecx, 16, fma4 , 4-operand FMA instruction +0x80000001, 0, ecx, 17, tce , Translation cache extension +0x80000001, 0, ecx, 19, nodeid_msr , NodeId MSR (0xc001100c) +0x80000001, 0, ecx, 21, tbm , Trailing bit manipulations +0x80000001, 0, ecx, 22, topoext , Topology Extensions (cpuid leaf 0x8000001d) +0x80000001, 0, ecx, 23, perfctr_core , Core performance counter extensions +0x80000001, 0, ecx, 24, perfctr_nb , NB/DF performance counter extensions +0x80000001, 0, ecx, 26, bpext , Data access breakpoint extension +0x80000001, 0, ecx, 27, ptsc , Performance time-stamp counter +0x80000001, 0, ecx, 28, perfctr_llc , LLC (L3) performance counter extensions +0x80000001, 0, ecx, 29, mwaitx , MWAITX/MONITORX support +0x80000001, 0, ecx, 30, addr_mask_ext , Breakpoint address mask extension (to bit 31) +0x80000001, 0, edx, 0, e_fpu , Floating-Point Unit on-chip (x87) +0x80000001, 0, edx, 1, e_vme , Virtual-8086 Mode Extensions +0x80000001, 0, edx, 2, e_de , Debugging Extensions +0x80000001, 0, edx, 3, e_pse , Page Size Extension +0x80000001, 0, edx, 4, e_tsc , Time Stamp Counter +0x80000001, 0, edx, 5, e_msr , Model-Specific Registers (RDMSR and WRMSR support) +0x80000001, 0, edx, 6, pae , Physical Address Extensions +0x80000001, 0, edx, 7, mce , Machine Check Exception +0x80000001, 0, edx, 8, cx8 , CMPXCHG8B instruction +0x80000001, 0, edx, 9, apic , APIC on-chip +0x80000001, 0, edx, 11, syscall , SYSCALL and SYSRET instructions +0x80000001, 0, edx, 12, mtrr , Memory Type Range Registers +0x80000001, 0, edx, 13, pge , Page Global Extensions +0x80000001, 0, edx, 14, mca , Machine Check Architecture +0x80000001, 0, edx, 15, cmov , Conditional Move Instruction +0x80000001, 0, edx, 16, pat , Page Attribute Table +0x80000001, 0, edx, 17, pse36 , Page Size Extension (36-bit) +0x80000001, 0, edx, 19, mp , Out-of-spec AMD Multiprocessing bit +0x80000001, 0, edx, 20, nx , No-execute page protection +0x80000001, 0, edx, 22, mmxext , AMD MMX extensions +0x80000001, 0, edx, 24, e_fxsr , FXSAVE and FXRSTOR instructions +0x80000001, 0, edx, 25, fxsr_opt , FXSAVE and FXRSTOR optimizations +0x80000001, 0, edx, 26, pdpe1gb , 1-GB large page support +0x80000001, 0, edx, 27, rdtscp , RDTSCP instruction +0x80000001, 0, edx, 29, lm , Long mode (x86-64, 64-bit support) +0x80000001, 0, edx, 30, 3dnowext , AMD 3DNow extensions +0x80000001, 0, edx, 31, 3dnow , 3DNow instructions + +# Leaf 80000002H +# CPU brand ID string, bytes 0 - 15 + +0x80000002, 0, eax, 31:0, cpu_brandid_0 , CPU brand ID string, bytes 0 - 3 +0x80000002, 0, ebx, 31:0, cpu_brandid_1 , CPU brand ID string, bytes 4 - 7 +0x80000002, 0, ecx, 31:0, cpu_brandid_2 , CPU brand ID string, bytes 8 - 11 +0x80000002, 0, edx, 31:0, cpu_brandid_3 , CPU brand ID string, bytes 12 - 15 + +# Leaf 80000003H +# CPU brand ID string, bytes 16 - 31 + +0x80000003, 0, eax, 31:0, cpu_brandid_4 , CPU brand ID string bytes, 16 - 19 +0x80000003, 0, ebx, 31:0, cpu_brandid_5 , CPU brand ID string bytes, 20 - 23 +0x80000003, 0, ecx, 31:0, cpu_brandid_6 , CPU brand ID string bytes, 24 - 27 +0x80000003, 0, edx, 31:0, cpu_brandid_7 , CPU brand ID string bytes, 28 - 31 + +# Leaf 80000004H +# CPU brand ID string, bytes 32 - 47 + +0x80000004, 0, eax, 31:0, cpu_brandid_8 , CPU brand ID string, bytes 32 - 35 +0x80000004, 0, ebx, 31:0, cpu_brandid_9 , CPU brand ID string, bytes 36 - 39 +0x80000004, 0, ecx, 31:0, cpu_brandid_10 , CPU brand ID string, bytes 40 - 43 +0x80000004, 0, edx, 31:0, cpu_brandid_11 , CPU brand ID string, bytes 44 - 47 # Leaf 80000005H -# Reserved +# AMD L1 cache and L1 TLB enumeration + +0x80000005, 0, eax, 7:0, l1_itlb_2m_4m_nentries , L1 ITLB #entires, 2M and 4M pages +0x80000005, 0, eax, 15:8, l1_itlb_2m_4m_assoc , L1 ITLB associativity, 2M and 4M pages +0x80000005, 0, eax, 23:16, l1_dtlb_2m_4m_nentries , L1 DTLB #entires, 2M and 4M pages +0x80000005, 0, eax, 31:24, l1_dtlb_2m_4m_assoc , L1 DTLB associativity, 2M and 4M pages +0x80000005, 0, ebx, 7:0, l1_itlb_4k_nentries , L1 ITLB #entries, 4K pages +0x80000005, 0, ebx, 15:8, l1_itlb_4k_assoc , L1 ITLB associativity, 4K pages +0x80000005, 0, ebx, 23:16, l1_dtlb_4k_nentries , L1 DTLB #entries, 4K pages +0x80000005, 0, ebx, 31:24, l1_dtlb_4k_assoc , L1 DTLB associativity, 4K pages +0x80000005, 0, ecx, 7:0, l1_dcache_line_size , L1 dcache line size, in bytes +0x80000005, 0, ecx, 15:8, l1_dcache_nlines , L1 dcache lines per tag +0x80000005, 0, ecx, 23:16, l1_dcache_assoc , L1 dcache associativity +0x80000005, 0, ecx, 31:24, l1_dcache_size_kb , L1 dcache size, in KB +0x80000005, 0, edx, 7:0, l1_icache_line_size , L1 icache line size, in bytes +0x80000005, 0, edx, 15:8, l1_icache_nlines , L1 icache lines per tag +0x80000005, 0, edx, 23:16, l1_icache_assoc , L1 icache associativity +0x80000005, 0, edx, 31:24, l1_icache_size_kb , L1 icache size, in KB # Leaf 80000006H -# Extended L2 Cache Features - -0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes -0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity -0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units - +# (Mostly AMD) L2 TLB, L2 cache, and L3 cache enumeration + +0x80000006, 0, eax, 11:0, l2_itlb_2m_4m_nentries , L2 iTLB #entries, 2M and 4M pages +0x80000006, 0, eax, 15:12, l2_itlb_2m_4m_assoc , L2 iTLB associativity, 2M and 4M pages +0x80000006, 0, eax, 27:16, l2_dtlb_2m_4m_nentries , L2 dTLB #entries, 2M and 4M pages +0x80000006, 0, eax, 31:28, l2_dtlb_2m_4m_assoc , L2 dTLB associativity, 2M and 4M pages +0x80000006, 0, ebx, 11:0, l2_itlb_4k_nentries , L2 iTLB #entries, 4K pages +0x80000006, 0, ebx, 15:12, l2_itlb_4k_assoc , L2 iTLB associativity, 4K pages +0x80000006, 0, ebx, 27:16, l2_dtlb_4k_nentries , L2 dTLB #entries, 4K pages +0x80000006, 0, ebx, 31:28, l2_dtlb_4k_assoc , L2 dTLB associativity, 4K pages +0x80000006, 0, ecx, 7:0, l2_line_size , L2 cache line size, in bytes +0x80000006, 0, ecx, 11:8, l2_nlines , L2 cache number of lines per tag +0x80000006, 0, ecx, 15:12, l2_assoc , L2 cache associativity +0x80000006, 0, ecx, 31:16, l2_size_kb , L2 cache size, in KB +0x80000006, 0, edx, 7:0, l3_line_size , L3 cache line size, in bytes +0x80000006, 0, edx, 11:8, l3_nlines , L3 cache number of lines per tag +0x80000006, 0, edx, 15:12, l3_assoc , L3 cache associativity +0x80000006, 0, edx, 31:18, l3_size_range , L3 cache size range # Leaf 80000007H - -0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available - +# CPU power management (mostly AMD) and AMD RAS enumeration + +0x80000007, 0, ebx, 0, overflow_recov , MCA overflow conditions not fatal +0x80000007, 0, ebx, 1, succor , Software containment of UnCORRectable errors +0x80000007, 0, ebx, 2, hw_assert , Hardware assert MSRs +0x80000007, 0, ebx, 3, smca , Scalable MCA (MCAX MSRs) +0x80000007, 0, ecx, 31:0, cpu_pwr_sample_ratio , CPU power sample time ratio +0x80000007, 0, edx, 0, digital_temp , Digital temprature sensor +0x80000007, 0, edx, 1, powernow_freq_id , PowerNOW! frequency scaling +0x80000007, 0, edx, 2, powernow_volt_id , PowerNOW! voltage scaling +0x80000007, 0, edx, 3, thermal_trip , THERMTRIP (Thermal Trip) +0x80000007, 0, edx, 4, hw_thermal_control , Hardware thermal control +0x80000007, 0, edx, 5, sw_thermal_control , Software thermal control +0x80000007, 0, edx, 6, 100mhz_steps , 100 MHz multiplier control +0x80000007, 0, edx, 7, hw_pstate , Hardware P-state control +0x80000007, 0, edx, 8, constant_tsc , TSC ticks at constant rate across all P and C states +0x80000007, 0, edx, 9, cpb , Core performance boost +0x80000007, 0, edx, 10, eff_freq_ro , Read-only effective frequency interface +0x80000007, 0, edx, 11, proc_feedback , Processor feedback interface (deprecated) +0x80000007, 0, edx, 12, acc_power , Processor power reporting interface +0x80000007, 0, edx, 13, connected_standby , CPU Connected Standby support +0x80000007, 0, edx, 14, rapl , Runtime Average Power Limit interface # Leaf 80000008H - -0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits -0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits -0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD - -# 0x8000001E -# EAX: Extended APIC ID -0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID -# EBX: Core Identifiers -0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID -0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 -# ECX: Node Identifiers -0x8000001E, 0, ECX, 7:0, node_id, Node ID -0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } - -# 8000001F: AMD Secure Encryption -0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption -0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization -0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR -0x8000001F, 0, EAX, 3, seves, SEV Encrypted State -0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption -0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled -0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest -0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest +# CPU capacity parameters and extended feature flags (mostly AMD) + +0x80000008, 0, eax, 7:0, phys_addr_bits , Max physical address bits +0x80000008, 0, eax, 15:8, virt_addr_bits , Max virtual address bits +0x80000008, 0, eax, 23:16, guest_phys_addr_bits , Max nested-paging guest physical address bits +0x80000008, 0, ebx, 0, clzero , CLZERO supported +0x80000008, 0, ebx, 1, irperf , Instruction retired counter MSR +0x80000008, 0, ebx, 2, xsaveerptr , XSAVE/XRSTOR always saves/restores FPU error pointers +0x80000008, 0, ebx, 3, invlpgb , INVLPGB broadcasts a TLB invalidate to all threads +0x80000008, 0, ebx, 4, rdpru , RDPRU (Read Processor Register at User level) supported +0x80000008, 0, ebx, 6, mba , Memory Bandwidth Allocation (AMD bit) +0x80000008, 0, ebx, 8, mcommit , MCOMMIT (Memory commit) supported +0x80000008, 0, ebx, 9, wbnoinvd , WBNOINVD supported +0x80000008, 0, ebx, 12, amd_ibpb , Indirect Branch Prediction Barrier +0x80000008, 0, ebx, 13, wbinvd_int , Interruptible WBINVD/WBNOINVD +0x80000008, 0, ebx, 14, amd_ibrs , Indirect Branch Restricted Speculation +0x80000008, 0, ebx, 15, amd_stibp , Single Thread Indirect Branch Prediction mode +0x80000008, 0, ebx, 16, ibrs_always_on , IBRS always-on preferred +0x80000008, 0, ebx, 17, amd_stibp_always_on , STIBP always-on preferred +0x80000008, 0, ebx, 18, ibrs_fast , IBRS is preferred over software solution +0x80000008, 0, ebx, 19, ibrs_same_mode , IBRS provides same mode protection +0x80000008, 0, ebx, 20, no_efer_lmsle , EFER[LMSLE] bit (Long-Mode Segment Limit Enable) unsupported +0x80000008, 0, ebx, 21, tlb_flush_nested , INVLPGB RAX[5] bit can be set (nested translations) +0x80000008, 0, ebx, 23, amd_ppin , Protected Processor Inventory Number +0x80000008, 0, ebx, 24, amd_ssbd , Speculative Store Bypass Disable +0x80000008, 0, ebx, 25, virt_ssbd , virtualized SSBD (Speculative Store Bypass Disable) +0x80000008, 0, ebx, 26, amd_ssb_no , SSBD not needed (fixed in HW) +0x80000008, 0, ebx, 27, cppc , Collaborative Processor Performance Control +0x80000008, 0, ebx, 28, amd_psfd , Predictive Store Forward Disable +0x80000008, 0, ebx, 29, btc_no , CPU not affected by Branch Type Confusion +0x80000008, 0, ebx, 30, ibpb_ret , IBPB clears RSB/RAS too +0x80000008, 0, ebx, 31, brs , Branch Sampling supported +0x80000008, 0, ecx, 7:0, cpu_nthreads , Number of physical threads - 1 +0x80000008, 0, ecx, 15:12, apicid_coreid_len , Number of thread core ID bits (shift) in APIC ID +0x80000008, 0, ecx, 17:16, perf_tsc_len , Performance time-stamp counter size +0x80000008, 0, edx, 15:0, invlpgb_max_pages , INVLPGB maximum page count +0x80000008, 0, edx, 31:16, rdpru_max_reg_id , RDPRU max register ID (ECX input) + +# Leaf 8000000AH +# AMD SVM (Secure Virtual Machine) enumeration + +0x8000000a, 0, eax, 7:0, svm_version , SVM revision number +0x8000000a, 0, ebx, 31:0, svm_nasid , Number of address space identifiers (ASID) +0x8000000a, 0, edx, 0, npt , Nested paging +0x8000000a, 0, edx, 1, lbrv , LBR virtualization +0x8000000a, 0, edx, 2, svm_lock , SVM lock +0x8000000a, 0, edx, 3, nrip_save , NRIP save support on #VMEXIT +0x8000000a, 0, edx, 4, tsc_scale , MSR based TSC rate control +0x8000000a, 0, edx, 5, vmcb_clean , VMCB clean bits support +0x8000000a, 0, edx, 6, flushbyasid , Flush by ASID + Extended VMCB TLB_Control +0x8000000a, 0, edx, 7, decodeassists , Decode Assists support +0x8000000a, 0, edx, 10, pausefilter , Pause intercept filter +0x8000000a, 0, edx, 12, pfthreshold , Pause filter threshold +0x8000000a, 0, edx, 13, avic , Advanced virtual interrupt controller +0x8000000a, 0, edx, 15, v_vmsave_vmload , Virtual VMSAVE/VMLOAD (nested virt) +0x8000000a, 0, edx, 16, vgif , Virtualize the Global Interrupt Flag +0x8000000a, 0, edx, 17, gmet , Guest mode execution trap +0x8000000a, 0, edx, 18, x2avic , Virtual x2APIC +0x8000000a, 0, edx, 19, sss_check , Supervisor Shadow Stack restrictions +0x8000000a, 0, edx, 20, v_spec_ctrl , Virtual SPEC_CTRL +0x8000000a, 0, edx, 21, ro_gpt , Read-Only guest page table support +0x8000000a, 0, edx, 23, h_mce_override , Host MCE override +0x8000000a, 0, edx, 24, tlbsync_int , TLBSYNC intercept + INVLPGB/TLBSYNC in VMCB +0x8000000a, 0, edx, 25, vnmi , NMI virtualization +0x8000000a, 0, edx, 26, ibs_virt , IBS Virtualization +0x8000000a, 0, edx, 27, ext_lvt_off_chg , Extended LVT offset fault change +0x8000000a, 0, edx, 28, svme_addr_chk , Guest SVME addr check + +# Leaf 80000019H +# AMD TLB 1G-pages enumeration + +0x80000019, 0, eax, 11:0, l1_itlb_1g_nentries , L1 iTLB #entries, 1G pages +0x80000019, 0, eax, 15:12, l1_itlb_1g_assoc , L1 iTLB associativity, 1G pages +0x80000019, 0, eax, 27:16, l1_dtlb_1g_nentries , L1 dTLB #entries, 1G pages +0x80000019, 0, eax, 31:28, l1_dtlb_1g_assoc , L1 dTLB associativity, 1G pages +0x80000019, 0, ebx, 11:0, l2_itlb_1g_nentries , L2 iTLB #entries, 1G pages +0x80000019, 0, ebx, 15:12, l2_itlb_1g_assoc , L2 iTLB associativity, 1G pages +0x80000019, 0, ebx, 27:16, l2_dtlb_1g_nentries , L2 dTLB #entries, 1G pages +0x80000019, 0, ebx, 31:28, l2_dtlb_1g_assoc , L2 dTLB associativity, 1G pages + +# Leaf 8000001AH +# AMD instruction optimizations enumeration + +0x8000001a, 0, eax, 0, fp_128 , Internal FP/SIMD exec data path is 128-bits wide +0x8000001a, 0, eax, 1, movu_preferred , SSE: MOVU* better than MOVL*/MOVH* +0x8000001a, 0, eax, 2, fp_256 , internal FP/SSE exec data path is 256-bits wide + +# Leaf 8000001BH +# AMD IBS (Instruction-Based Sampling) enumeration + +0x8000001b, 0, eax, 0, ibs_flags_valid , IBS feature flags valid +0x8000001b, 0, eax, 1, ibs_fetch_sampling , IBS fetch sampling supported +0x8000001b, 0, eax, 2, ibs_op_sampling , IBS execution sampling supported +0x8000001b, 0, eax, 3, ibs_rdwr_op_counter , IBS read/write of op counter supported +0x8000001b, 0, eax, 4, ibs_op_count , IBS OP counting mode supported +0x8000001b, 0, eax, 5, ibs_branch_target , IBS branch target address reporting supported +0x8000001b, 0, eax, 6, ibs_op_counters_ext , IBS IbsOpCurCnt/IbsOpMaxCnt extend by 7 bits +0x8000001b, 0, eax, 7, ibs_rip_invalid_chk , IBS invalid RIP indication supported +0x8000001b, 0, eax, 8, ibs_op_branch_fuse , IBS fused branch micro-op indication supported +0x8000001b, 0, eax, 9, ibs_fetch_ctl_ext , IBS Fetch Control Extended MSR (0xc001103c) supported +0x8000001b, 0, eax, 10, ibs_op_data_4 , IBS op data 4 MSR supported +0x8000001b, 0, eax, 11, ibs_l3_miss_filter , IBS L3-miss filtering supported (Zen4+) + +# Leaf 8000001CH +# AMD LWP (Lightweight Profiling) + +0x8000001c, 0, eax, 0, os_lwp_avail , LWP is available to application programs (supported by OS) +0x8000001c, 0, eax, 1, os_lpwval , LWPVAL instruction (EventId=1) is supported by OS +0x8000001c, 0, eax, 2, os_lwp_ire , Instructions Retired Event (EventId=2) is supported by OS +0x8000001c, 0, eax, 3, os_lwp_bre , Branch Retired Event (EventId=3) is supported by OS +0x8000001c, 0, eax, 4, os_lwp_dme , DCache Miss Event (EventId=4) is supported by OS +0x8000001c, 0, eax, 5, os_lwp_cnh , CPU Clocks Not Halted event (EventId=5) is supported by OS +0x8000001c, 0, eax, 6, os_lwp_rnh , CPU Reference clocks Not Halted event (EventId=6) is supported by OS +0x8000001c, 0, eax, 29, os_lwp_cont , LWP sampling in continuous mode is supported by OS +0x8000001c, 0, eax, 30, os_lwp_ptsc , Performance Time Stamp Counter in event records is supported by OS +0x8000001c, 0, eax, 31, os_lwp_int , Interrupt on threshold overflow is supported by OS +0x8000001c, 0, ebx, 7:0, lwp_lwpcb_sz , LWP Control Block size, in quadwords +0x8000001c, 0, ebx, 15:8, lwp_event_sz , LWP event record size, in bytes +0x8000001c, 0, ebx, 23:16, lwp_max_events , LWP max supported EventId value (EventID 255 not included) +0x8000001c, 0, ebx, 31:24, lwp_event_offset , LWP events area offset in the LWP Control Block +0x8000001c, 0, ecx, 4:0, lwp_latency_max , Num of bits in cache latency counters (10 to 31) +0x8000001c, 0, ecx, 5, lwp_data_adddr , Cache miss events report the data address of the reference +0x8000001c, 0, ecx, 8:6, lwp_latency_rnd , Amount by which cache latency is rounded +0x8000001c, 0, ecx, 15:9, lwp_version , LWP implementation version +0x8000001c, 0, ecx, 23:16, lwp_buf_min_sz , LWP event ring buffer min size, in units of 32 event records +0x8000001c, 0, ecx, 28, lwp_branch_predict , Branches Retired events can be filtered +0x8000001c, 0, ecx, 29, lwp_ip_filtering , IP filtering (IPI, IPF, BaseIP, and LimitIP @ LWPCP) supported +0x8000001c, 0, ecx, 30, lwp_cache_levels , Cache-related events can be filtered by cache level +0x8000001c, 0, ecx, 31, lwp_cache_latency , Cache-related events can be filtered by latency +0x8000001c, 0, edx, 0, hw_lwp_avail , LWP is available in Hardware +0x8000001c, 0, edx, 1, hw_lpwval , LWPVAL instruction (EventId=1) is available in HW +0x8000001c, 0, edx, 2, hw_lwp_ire , Instructions Retired Event (EventId=2) is available in HW +0x8000001c, 0, edx, 3, hw_lwp_bre , Branch Retired Event (EventId=3) is available in HW +0x8000001c, 0, edx, 4, hw_lwp_dme , DCache Miss Event (EventId=4) is available in HW +0x8000001c, 0, edx, 5, hw_lwp_cnh , CPU Clocks Not Halted event (EventId=5) is available in HW +0x8000001c, 0, edx, 6, hw_lwp_rnh , CPU Reference clocks Not Halted event (EventId=6) is available in HW +0x8000001c, 0, edx, 29, hw_lwp_cont , LWP sampling in continuous mode is available in HW +0x8000001c, 0, edx, 30, hw_lwp_ptsc , Performance Time Stamp Counter in event records is available in HW +0x8000001c, 0, edx, 31, hw_lwp_int , Interrupt on threshold overflow is available in HW + +# Leaf 8000001DH +# AMD deterministic cache parameters + +0x8000001d, 31:0, eax, 4:0, cache_type , Cache type field +0x8000001d, 31:0, eax, 7:5, cache_level , Cache level (1-based) +0x8000001d, 31:0, eax, 8, cache_self_init , Self-initializing cache level +0x8000001d, 31:0, eax, 9, fully_associative , Fully-associative cache +0x8000001d, 31:0, eax, 25:14, num_threads_sharing , Number of logical CPUs sharing cache +0x8000001d, 31:0, ebx, 11:0, cache_linesize , System coherency line size (0-based) +0x8000001d, 31:0, ebx, 21:12, cache_npartitions , Physical line partitions (0-based) +0x8000001d, 31:0, ebx, 31:22, cache_nways , Ways of associativity (0-based) +0x8000001d, 31:0, ecx, 30:0, cache_nsets , Cache number of sets (0-based) +0x8000001d, 31:0, edx, 0, wbinvd_rll_no_guarantee, WBINVD/INVD not guaranteed for Remote Lower-Level caches +0x8000001d, 31:0, edx, 1, ll_inclusive , Cache is inclusive of Lower-Level caches + +# Leaf 8000001EH +# AMD CPU topology enumeration + +0x8000001e, 0, eax, 31:0, ext_apic_id , Extended APIC ID +0x8000001e, 0, ebx, 7:0, core_id , Unique per-socket logical core unit ID +0x8000001e, 0, ebx, 15:8, core_nthreas , #Threads per core (zero-based) +0x8000001e, 0, ecx, 7:0, node_id , Node (die) ID of invoking logical CPU +0x8000001e, 0, ecx, 10:8, nnodes_per_socket , #nodes in invoking logical CPU's package/socket + +# Leaf 8000001FH +# AMD encrypted memory capabilities enumeration (SME/SEV) + +0x8000001f, 0, eax, 0, sme , Secure Memory Encryption supported +0x8000001f, 0, eax, 1, sev , Secure Encrypted Virtualization supported +0x8000001f, 0, eax, 2, vm_page_flush , VM Page Flush MSR (0xc001011e) available +0x8000001f, 0, eax, 3, sev_es , SEV Encrypted State supported +0x8000001f, 0, eax, 4, sev_nested_paging , SEV secure nested paging supported +0x8000001f, 0, eax, 5, vm_permission_levels , VMPL supported +0x8000001f, 0, eax, 6, rpmquery , RPMQUERY instruction supported +0x8000001f, 0, eax, 7, vmpl_sss , VMPL supervisor shadwo stack supported +0x8000001f, 0, eax, 8, secure_tsc , Secure TSC supported +0x8000001f, 0, eax, 9, v_tsc_aux , Hardware virtualizes TSC_AUX +0x8000001f, 0, eax, 10, sme_coherent , HW enforces cache coherency across encryption domains +0x8000001f, 0, eax, 11, req_64bit_hypervisor , SEV guest mandates 64-bit hypervisor +0x8000001f, 0, eax, 12, restricted_injection , Restricted Injection supported +0x8000001f, 0, eax, 13, alternate_injection , Alternate Injection supported +0x8000001f, 0, eax, 14, debug_swap , SEV-ES: full debug state swap is supported +0x8000001f, 0, eax, 15, disallow_host_ibs , SEV-ES: Disallowing IBS use by the host is supported +0x8000001f, 0, eax, 16, virt_transparent_enc , Virtual Transparent Encryption +0x8000001f, 0, eax, 17, vmgexit_paremeter , VmgexitParameter is supported in SEV_FEATURES +0x8000001f, 0, eax, 18, virt_tom_msr , Virtual TOM MSR is supported +0x8000001f, 0, eax, 19, virt_ibs , IBS state virtualization is supported for SEV-ES guests +0x8000001f, 0, eax, 24, vmsa_reg_protection , VMSA register protection is supported +0x8000001f, 0, eax, 25, smt_protection , SMT protection is supported +0x8000001f, 0, eax, 28, svsm_page_msr , SVSM communication page MSR (0xc001f000h) is supported +0x8000001f, 0, eax, 29, nested_virt_snp_msr , VIRT_RMPUPDATE/VIRT_PSMASH MSRs are supported +0x8000001f, 0, ebx, 5:0, pte_cbit_pos , PTE bit number used to enable memory encryption +0x8000001f, 0, ebx, 11:6, phys_addr_reduction_nbits, Reduction of phys address space when encryption is enabled, in bits +0x8000001f, 0, ebx, 15:12, vmpl_count , Number of VM permission levels (VMPL) supported +0x8000001f, 0, ecx, 31:0, enc_guests_max , Max supported number of simultaneous encrypted guests +0x8000001f, 0, edx, 31:0, min_sev_asid_no_sev_es , Mininum ASID for SEV-enabled SEV-ES-disabled guest + +# Leaf 80000020H +# AMD Platform QoS extended feature IDs + +0x80000020, 0, ebx, 1, mba , Memory Bandwidth Allocation support +0x80000020, 0, ebx, 2, smba , Slow Memory Bandwidth Allocation support +0x80000020, 0, ebx, 3, bmec , Bandwidth Monitoring Event Configuration support +0x80000020, 0, ebx, 4, l3rr , L3 Range Reservation support +0x80000020, 1, eax, 31:0, mba_limit_len , MBA enforcement limit size +0x80000020, 1, edx, 31:0, mba_cos_max , MBA max Class of Service number (zero-based) +0x80000020, 2, eax, 31:0, smba_limit_len , SMBA enforcement limit size +0x80000020, 2, edx, 31:0, smba_cos_max , SMBA max Class of Service number (zero-based) +0x80000020, 3, ebx, 7:0, bmec_num_events , BMEC number of bandwidth events available +0x80000020, 3, ecx, 0, bmec_local_reads , Local NUMA reads can be tracked +0x80000020, 3, ecx, 1, bmec_remote_reads , Remote NUMA reads can be tracked +0x80000020, 3, ecx, 2, bmec_local_nontemp_wr , Local NUMA non-temporal writes can be tracked +0x80000020, 3, ecx, 3, bmec_remote_nontemp_wr , Remote NUMA non-temporal writes can be tracked +0x80000020, 3, ecx, 4, bmec_local_slow_mem_rd , Local NUMA slow-memory reads can be tracked +0x80000020, 3, ecx, 5, bmec_remote_slow_mem_rd, Remote NUMA slow-memory reads can be tracked +0x80000020, 3, ecx, 6, bmec_all_dirty_victims , Dirty QoS victims to all types of memory can be tracked + +# Leaf 80000021H +# AMD extended features enumeration 2 + +0x80000021, 0, eax, 0, no_nested_data_bp , No nested data breakpoints +0x80000021, 0, eax, 1, fsgs_non_serializing , WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing +0x80000021, 0, eax, 2, lfence_rdtsc , LFENCE always serializing / synchronizes RDTSC +0x80000021, 0, eax, 3, smm_page_cfg_lock , SMM paging configuration lock is supported +0x80000021, 0, eax, 6, null_sel_clr_base , Null selector clears base +0x80000021, 0, eax, 7, upper_addr_ignore , EFER MSR Upper Address Ignore Enable bit supported +0x80000021, 0, eax, 8, autoibrs , EFER MSR Automatic IBRS enable bit supported +0x80000021, 0, eax, 9, no_smm_ctl_msr , SMM_CTL MSR (0xc0010116) is not present +0x80000021, 0, eax, 10, fsrs_supported , Fast Short Rep Stosb (FSRS) is supported +0x80000021, 0, eax, 11, fsrc_supported , Fast Short Repe Cmpsb (FSRC) is supported +0x80000021, 0, eax, 13, prefetch_ctl_msr , Prefetch control MSR is supported +0x80000021, 0, eax, 17, user_cpuid_disable , #GP when executing CPUID at CPL > 0 is supported +0x80000021, 0, eax, 18, epsf_supported , Enhanced Predictive Store Forwarding (EPSF) is supported +0x80000021, 0, ebx, 11:0, microcode_patch_size , Size of microcode patch, in 16-byte units + +# Leaf 80000022H +# AMD Performance Monitoring v2 enumeration + +0x80000022, 0, eax, 0, perfmon_v2 , Performance monitoring v2 supported +0x80000022, 0, eax, 1, lbr_v2 , Last Branch Record v2 extensions (LBR Stack) +0x80000022, 0, eax, 2, lbr_pmc_freeze , Freezing core performance counters / LBR Stack supported +0x80000022, 0, ebx, 3:0, n_pmc_core , Number of core perfomance counters +0x80000022, 0, ebx, 9:4, lbr_v2_stack_size , Number of available LBR stack entries +0x80000022, 0, ebx, 15:10, n_pmc_northbridge , Number of available northbridge (data fabric) performance counters +0x80000022, 0, ebx, 21:16, n_pmc_umc , Number of available UMC performance counters +0x80000022, 0, ecx, 31:0, active_umc_bitmask , Active UMCs bitmask + +# Leaf 80000023H +# AMD Secure Multi-key Encryption enumeration + +0x80000023, 0, eax, 0, mem_hmk_mode , MEM-HMK encryption mode is supported +0x80000023, 0, ebx, 15:0, mem_hmk_avail_keys , MEM-HMK mode: total num of available encryption keys + +# Leaf 80000026H +# AMD extended topology enumeration v2 + +0x80000026, 3:0, eax, 4:0, x2apic_id_shift , Bit width of this level (previous levels inclusive) +0x80000026, 3:0, eax, 29, core_has_pwreff_ranking, This core has a power efficiency ranking +0x80000026, 3:0, eax, 30, domain_has_hybrid_cores, This domain level has hybrid (E, P) cores +0x80000026, 3:0, eax, 31, domain_core_count_asymm, The 'Core' domain has asymmetric cores count +0x80000026, 3:0, ebx, 15:0, domain_lcpus_count , Number of logical CPUs at this domain instance +0x80000026, 3:0, ebx, 23:16, core_pwreff_ranking , This core's static power efficiency ranking +0x80000026, 3:0, ebx, 27:24, core_native_model_id , This core's native model ID +0x80000026, 3:0, ebx, 31:28, core_type , This core's type +0x80000026, 3:0, ecx, 7:0, domain_level , This domain level (subleaf ID) +0x80000026, 3:0, ecx, 15:8, domain_type , This domain type +0x80000026, 3:0, edx, 31:0, x2apic_id , x2APIC ID of current logical CPU diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c index 24b7d017ec2c..1b25c0a95d3f 100644 --- a/tools/arch/x86/kcpuid/kcpuid.c +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -7,7 +7,8 @@ #include <string.h> #include <getopt.h> -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#define min(a, b) (((a) < (b)) ? (a) : (b)) typedef unsigned int u32; typedef unsigned long long u64; @@ -76,7 +77,6 @@ struct cpuid_range { */ struct cpuid_range *leafs_basic, *leafs_ext; -static int num_leafs; static bool is_amd; static bool show_details; static bool show_raw; @@ -98,27 +98,17 @@ static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) static inline bool has_subleafs(u32 f) { - if (f == 0x7 || f == 0xd) - return true; - - if (is_amd) { - if (f == 0x8000001d) + u32 with_subleaves[] = { + 0x4, 0x7, 0xb, 0xd, 0xf, 0x10, 0x12, + 0x14, 0x17, 0x18, 0x1b, 0x1d, 0x1f, 0x23, + 0x8000001d, 0x80000020, 0x80000026, + }; + + for (unsigned i = 0; i < ARRAY_SIZE(with_subleaves); i++) + if (f == with_subleaves[i]) return true; - return false; - } - switch (f) { - case 0x4: - case 0xb: - case 0xf: - case 0x10: - case 0x14: - case 0x18: - case 0x1f: - return true; - default: - return false; - } + return false; } static void leaf_print_raw(struct subleaf *leaf) @@ -204,15 +194,12 @@ static void raw_dump_range(struct cpuid_range *range) } } -#define MAX_SUBLEAF_NUM 32 +#define MAX_SUBLEAF_NUM 64 struct cpuid_range *setup_cpuid_range(u32 input_eax) { - u32 max_func, idx_func; - int subleaf; + u32 max_func, idx_func, subleaf, max_subleaf; + u32 eax, ebx, ecx, edx, f = input_eax; struct cpuid_range *range; - u32 eax, ebx, ecx, edx; - u32 f = input_eax; - int max_subleaf; bool allzero; eax = input_eax; @@ -246,7 +233,6 @@ struct cpuid_range *setup_cpuid_range(u32 input_eax) allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); if (allzero) continue; - num_leafs++; if (!has_subleafs(f)) continue; @@ -257,11 +243,18 @@ struct cpuid_range *setup_cpuid_range(u32 input_eax) * Some can provide the exact number of subleafs, * others have to be tried (0xf) */ - if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) - max_subleaf = (eax & 0xff) + 1; - + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18 || f == 0x1d) + max_subleaf = min((eax & 0xff) + 1, max_subleaf); if (f == 0xb) max_subleaf = 2; + if (f == 0x1f) + max_subleaf = 6; + if (f == 0x23) + max_subleaf = 4; + if (f == 0x80000020) + max_subleaf = 4; + if (f == 0x80000026) + max_subleaf = 5; for (subleaf = 1; subleaf < max_subleaf; subleaf++) { eax = f; @@ -272,7 +265,6 @@ struct cpuid_range *setup_cpuid_range(u32 input_eax) eax, ebx, ecx, edx); if (allzero) continue; - num_leafs++; } } @@ -313,6 +305,8 @@ static int parse_line(char *line) struct bits_desc *bdesc; int reg_index; char *start, *end; + u32 subleaf_start, subleaf_end; + unsigned bit_start, bit_end; /* Skip comments and NULL line */ if (line[0] == '#' || line[0] == '\n') @@ -351,13 +345,25 @@ static int parse_line(char *line) return 0; /* subleaf */ - sub = strtoul(tokens[1], NULL, 0); - if ((int)sub > func->nr) - return -1; + buf = tokens[1]; + end = strtok(buf, ":"); + start = strtok(NULL, ":"); + subleaf_end = strtoul(end, NULL, 0); + + /* A subleaf range is given? */ + if (start) { + subleaf_start = strtoul(start, NULL, 0); + subleaf_end = min(subleaf_end, (u32)(func->nr - 1)); + if (subleaf_start > subleaf_end) + return 0; + } else { + subleaf_start = subleaf_end; + if (subleaf_start > (u32)(func->nr - 1)) + return 0; + } - leaf = &func->leafs[sub]; + /* register */ buf = tokens[2]; - if (strcasestr(buf, "EAX")) reg_index = R_EAX; else if (strcasestr(buf, "EBX")) @@ -369,23 +375,23 @@ static int parse_line(char *line) else goto err_exit; - reg = &leaf->info[reg_index]; - bdesc = ®->descs[reg->nr++]; - /* bit flag or bits field */ buf = tokens[3]; - end = strtok(buf, ":"); - bdesc->end = strtoul(end, NULL, 0); - bdesc->start = bdesc->end; - - /* start != NULL means it is bit fields */ start = strtok(NULL, ":"); - if (start) - bdesc->start = strtoul(start, NULL, 0); - - strcpy(bdesc->simp, tokens[4]); - strcpy(bdesc->detail, tokens[5]); + bit_end = strtoul(end, NULL, 0); + bit_start = (start) ? strtoul(start, NULL, 0) : bit_end; + + for (sub = subleaf_start; sub <= subleaf_end; sub++) { + leaf = &func->leafs[sub]; + reg = &leaf->info[reg_index]; + bdesc = ®->descs[reg->nr++]; + + bdesc->end = bit_end; + bdesc->start = bit_start; + strcpy(bdesc->simp, strtok(tokens[4], " \t")); + strcpy(bdesc->detail, tokens[5]); + } return 0; err_exit: @@ -452,8 +458,9 @@ static void decode_bits(u32 value, struct reg_desc *rdesc, enum cpuid_reg reg) if (start == end) { /* single bit flag */ if (value & (1 << start)) - printf("\t%-20s %s%s\n", + printf("\t%-20s %s%s%s\n", bdesc->simp, + show_flags_only ? "" : "\t\t\t", show_details ? "-" : "", show_details ? bdesc->detail : "" ); diff --git a/tools/arch/x86/vdso b/tools/arch/x86/vdso new file mode 120000 index 000000000000..7eb962fd3454 --- /dev/null +++ b/tools/arch/x86/vdso @@ -0,0 +1 @@ +../../../arch/x86/entry/vdso/
\ No newline at end of file diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index d29c9c49e251..ed565eb52275 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -78,7 +78,7 @@ $(OUTPUT)gpio-watch: $(GPIO_WATCH_IN) clean: rm -f $(ALL_PROGRAMS) rm -f $(OUTPUT)include/linux/gpio.h - find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c index 54fdf59dd320..ba0866eb3581 100644 --- a/tools/gpio/gpio-hammer.c +++ b/tools/gpio/gpio-hammer.c @@ -54,7 +54,7 @@ int hammer_device(const char *device_name, unsigned int *lines, int num_lines, fprintf(stdout, "Hammer lines ["); for (i = 0; i < num_lines; i++) { - fprintf(stdout, "%d", lines[i]); + fprintf(stdout, "%u", lines[i]); if (i != (num_lines - 1)) fprintf(stdout, ", "); } @@ -89,7 +89,7 @@ int hammer_device(const char *device_name, unsigned int *lines, int num_lines, fprintf(stdout, "["); for (i = 0; i < num_lines; i++) { - fprintf(stdout, "%d: %d", lines[i], + fprintf(stdout, "%u: %d", lines[i], gpiotools_test_bit(values.bits, i)); if (i != (num_lines - 1)) fprintf(stdout, ", "); diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 3ce316cc9f97..7a00f3066a98 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -296,6 +296,13 @@ static int hv_fcopy_start(struct hv_start_fcopy *smsg_in) file_name = (char *)malloc(file_size * sizeof(char)); path_name = (char *)malloc(path_size * sizeof(char)); + if (!file_name || !path_name) { + free(file_name); + free(path_name); + syslog(LOG_ERR, "Can't allocate memory for file name and/or path name"); + return HV_E_FAIL; + } + wcstoutf8(file_name, (__u16 *)in_file_name, file_size); wcstoutf8(path_name, (__u16 *)in_path_name, path_size); diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index 7ce02a223732..8e548ac8f740 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -2,8 +2,18 @@ #ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H #define _TOOLS_ASM_ALTERNATIVE_ASM_H +#if defined(__s390x__) +#ifdef __ASSEMBLY__ +.macro ALTERNATIVE oldinstr, newinstr, feature + \oldinstr +.endm +#endif +#else + /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ #define ALTERNATIVE # #endif + +#endif diff --git a/tools/include/generated/asm-offsets.h b/tools/include/generated/asm-offsets.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/generated/asm-offsets.h diff --git a/tools/include/generated/asm/cpucap-defs.h b/tools/include/generated/asm/cpucap-defs.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/generated/asm/cpucap-defs.h diff --git a/tools/include/generated/asm/sysreg-defs.h b/tools/include/generated/asm/sysreg-defs.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/generated/asm/sysreg-defs.h diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 6f7f22ac9da5..4366da278033 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -2,6 +2,8 @@ #ifndef _TOOLS_LINUX_COMPILER_H_ #define _TOOLS_LINUX_COMPILER_H_ +#ifndef __ASSEMBLY__ + #include <linux/compiler_types.h> #ifndef __compiletime_error @@ -224,4 +226,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __asm__ ("" : "=r" (var) : "0" (var)) #endif +#endif /* __ASSEMBLY__ */ + #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h index bc763d500262..a48ff086899c 100644 --- a/tools/include/linux/linkage.h +++ b/tools/include/linux/linkage.h @@ -1,4 +1,8 @@ #ifndef _TOOLS_INCLUDE_LINUX_LINKAGE_H #define _TOOLS_INCLUDE_LINUX_LINKAGE_H +#define SYM_FUNC_START(x) .globl x; x: + +#define SYM_FUNC_END(x) + #endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */ diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile index e69c26abe1ea..a1f55fb24bb3 100644 --- a/tools/include/nolibc/Makefile +++ b/tools/include/nolibc/Makefile @@ -35,6 +35,7 @@ all_files := \ stackprotector.h \ std.h \ stdarg.h \ + stdbool.h \ stdint.h \ stdlib.h \ string.h \ diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h index b23ac1f04035..06fdef7b291a 100644 --- a/tools/include/nolibc/arch-aarch64.h +++ b/tools/include/nolibc/arch-aarch64.h @@ -142,13 +142,13 @@ }) /* startup code */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { __asm__ volatile ( "mov x0, sp\n" /* save stack pointer to x0, as arg1 of _start_c */ "and sp, x0, -16\n" /* sp must be 16-byte aligned in the callee */ "bl _start_c\n" /* transfer to c runtime */ ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #endif /* _NOLIBC_ARCH_AARCH64_H */ diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h index cae4afa7c1c7..6180ff99ab43 100644 --- a/tools/include/nolibc/arch-arm.h +++ b/tools/include/nolibc/arch-arm.h @@ -185,15 +185,15 @@ }) /* startup code */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { __asm__ volatile ( - "mov %r0, sp\n" /* save stack pointer to %r0, as arg1 of _start_c */ - "and ip, %r0, #-8\n" /* sp must be 8-byte aligned in the callee */ + "mov r0, sp\n" /* save stack pointer to %r0, as arg1 of _start_c */ + "and ip, r0, #-8\n" /* sp must be 8-byte aligned in the callee */ "mov sp, ip\n" "bl _start_c\n" /* transfer to c runtime */ ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #endif /* _NOLIBC_ARCH_ARM_H */ diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h index 28c26a00a762..ff5afc35bbd8 100644 --- a/tools/include/nolibc/arch-i386.h +++ b/tools/include/nolibc/arch-i386.h @@ -162,7 +162,7 @@ * 2) The deepest stack frame should be set to zero * */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { __asm__ volatile ( "xor %ebp, %ebp\n" /* zero the stack frame */ @@ -174,7 +174,7 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ "call _start_c\n" /* transfer to c runtime */ "hlt\n" /* ensure it does not return */ ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #endif /* _NOLIBC_ARCH_I386_H */ diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h index 3f8ef8f86c0f..fb519545959e 100644 --- a/tools/include/nolibc/arch-loongarch.h +++ b/tools/include/nolibc/arch-loongarch.h @@ -149,14 +149,14 @@ #endif /* startup code */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { __asm__ volatile ( "move $a0, $sp\n" /* save stack pointer to $a0, as arg1 of _start_c */ LONG_BSTRINS " $sp, $zero, 3, 0\n" /* $sp must be 16-byte aligned */ "bl _start_c\n" /* transfer to c runtime */ ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #endif /* _NOLIBC_ARCH_LOONGARCH_H */ diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index 62cc50ef3288..1791a8ce58da 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -179,7 +179,7 @@ }) /* startup code, note that it's called __start on MIPS */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector __start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector __start(void) { __asm__ volatile ( ".set push\n" @@ -194,11 +194,13 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ "li $t0, -8\n" "and $sp, $sp, $t0\n" /* $sp must be 8-byte aligned */ "addiu $sp, $sp, -16\n" /* the callee expects to save a0..a3 there */ - "jal _start_c\n" /* transfer to c runtime */ + "lui $t9, %hi(_start_c)\n" /* ABI requires current function address in $t9 */ + "ori $t9, %lo(_start_c)\n" + "jalr $t9\n" /* transfer to c runtime */ " nop\n" /* delayed slot */ ".set pop\n" ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #endif /* _NOLIBC_ARCH_MIPS_H */ diff --git a/tools/include/nolibc/arch-powerpc.h b/tools/include/nolibc/arch-powerpc.h index ac212e6185b2..ee2fdb8d601d 100644 --- a/tools/include/nolibc/arch-powerpc.h +++ b/tools/include/nolibc/arch-powerpc.h @@ -172,7 +172,7 @@ _ret; \ }) -#ifndef __powerpc64__ +#if !defined(__powerpc64__) && !defined(__clang__) /* FIXME: For 32-bit PowerPC, with newer gcc compilers (e.g. gcc 13.1.0), * "omit-frame-pointer" fails with __attribute__((no_stack_protector)) but * works with __attribute__((__optimize__("-fno-stack-protector"))) @@ -184,7 +184,7 @@ #endif /* !__powerpc64__ */ /* startup code */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { #ifdef __powerpc64__ #if _CALL_ELF == 2 @@ -215,7 +215,7 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ "bl _start_c\n" /* transfer to c runtime */ ); #endif - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #endif /* _NOLIBC_ARCH_POWERPC_H */ diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index 1927c643c739..8827bf936212 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -140,7 +140,7 @@ }) /* startup code */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { __asm__ volatile ( ".option push\n" @@ -151,7 +151,7 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ "andi sp, a0, -16\n" /* sp must be 16-byte aligned */ "call _start_c\n" /* transfer to c runtime */ ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #endif /* _NOLIBC_ARCH_RISCV_H */ diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h index 5d60fd43f883..2ec13d8b9a2d 100644 --- a/tools/include/nolibc/arch-s390.h +++ b/tools/include/nolibc/arch-s390.h @@ -139,7 +139,7 @@ }) /* startup code */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { __asm__ volatile ( "lgr %r2, %r15\n" /* save stack pointer to %r2, as arg1 of _start_c */ @@ -147,7 +147,7 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ "xc 0(8,%r15), 0(%r15)\n" /* clear backchain */ "brasl %r14, _start_c\n" /* transfer to c runtime */ ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } struct s390_mmap_arg_struct { diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h index 68609f421934..1e40620a2b33 100644 --- a/tools/include/nolibc/arch-x86_64.h +++ b/tools/include/nolibc/arch-x86_64.h @@ -161,7 +161,7 @@ * 2) The deepest stack frame should be zero (the %rbp). * */ -void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void) +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) { __asm__ volatile ( "xor %ebp, %ebp\n" /* zero the stack frame */ @@ -170,7 +170,7 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ "call _start_c\n" /* transfer to c runtime */ "hlt\n" /* ensure it does not return */ ); - __builtin_unreachable(); + __nolibc_entrypoint_epilogue(); } #define NOLIBC_ARCH_HAS_MEMMOVE @@ -193,10 +193,10 @@ __asm__ ( "movq %rdi, %rdx\n\t" "subq %rsi, %rdx\n\t" "cmpq %rcx, %rdx\n\t" - "jb .Lbackward_copy\n\t" + "jb 1f\n\t" "rep movsb\n\t" "retq\n" -".Lbackward_copy:" +"1:" /* backward copy */ "leaq -1(%rdi, %rcx, 1), %rdi\n\t" "leaq -1(%rsi, %rcx, 1), %rsi\n\t" "std\n\t" diff --git a/tools/include/nolibc/compiler.h b/tools/include/nolibc/compiler.h index beddc3665d69..9bc6a706a332 100644 --- a/tools/include/nolibc/compiler.h +++ b/tools/include/nolibc/compiler.h @@ -6,20 +6,30 @@ #ifndef _NOLIBC_COMPILER_H #define _NOLIBC_COMPILER_H +#if defined(__has_attribute) +# define __nolibc_has_attribute(attr) __has_attribute(attr) +#else +# define __nolibc_has_attribute(attr) 0 +#endif + +#if __nolibc_has_attribute(naked) +# define __nolibc_entrypoint __attribute__((naked)) +# define __nolibc_entrypoint_epilogue() +#else +# define __nolibc_entrypoint __attribute__((optimize("Os", "omit-frame-pointer"))) +# define __nolibc_entrypoint_epilogue() __builtin_unreachable() +#endif /* __nolibc_has_attribute(naked) */ + #if defined(__SSP__) || defined(__SSP_STRONG__) || defined(__SSP_ALL__) || defined(__SSP_EXPLICIT__) #define _NOLIBC_STACKPROTECTOR #endif /* defined(__SSP__) ... */ -#if defined(__has_attribute) -# if __has_attribute(no_stack_protector) -# define __no_stack_protector __attribute__((no_stack_protector)) -# else -# define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) -# endif +#if __nolibc_has_attribute(no_stack_protector) +# define __no_stack_protector __attribute__((no_stack_protector)) #else # define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) -#endif /* defined(__has_attribute) */ +#endif /* __nolibc_has_attribute(no_stack_protector) */ #endif /* _NOLIBC_COMPILER_H */ diff --git a/tools/include/nolibc/crt.h b/tools/include/nolibc/crt.h index 43b551468c2a..bbcd5fd09806 100644 --- a/tools/include/nolibc/crt.h +++ b/tools/include/nolibc/crt.h @@ -13,23 +13,24 @@ const unsigned long *_auxv __attribute__((weak)); static void __stack_chk_init(void); static void exit(int); -extern void (*const __preinit_array_start[])(void) __attribute__((weak)); -extern void (*const __preinit_array_end[])(void) __attribute__((weak)); +extern void (*const __preinit_array_start[])(int, char **, char**) __attribute__((weak)); +extern void (*const __preinit_array_end[])(int, char **, char**) __attribute__((weak)); -extern void (*const __init_array_start[])(void) __attribute__((weak)); -extern void (*const __init_array_end[])(void) __attribute__((weak)); +extern void (*const __init_array_start[])(int, char **, char**) __attribute__((weak)); +extern void (*const __init_array_end[])(int, char **, char**) __attribute__((weak)); extern void (*const __fini_array_start[])(void) __attribute__((weak)); extern void (*const __fini_array_end[])(void) __attribute__((weak)); -__attribute__((weak)) +__attribute__((weak,used)) void _start_c(long *sp) { long argc; char **argv; char **envp; int exitcode; - void (* const *func)(void); + void (* const *ctor_func)(int, char **, char **); + void (* const *dtor_func)(void); const unsigned long *auxv; /* silence potential warning: conflicting types for 'main' */ int _nolibc_main(int, char **, char **) __asm__ ("main"); @@ -66,16 +67,16 @@ void _start_c(long *sp) ; _auxv = auxv; - for (func = __preinit_array_start; func < __preinit_array_end; func++) - (*func)(); - for (func = __init_array_start; func < __init_array_end; func++) - (*func)(); + for (ctor_func = __preinit_array_start; ctor_func < __preinit_array_end; ctor_func++) + (*ctor_func)(argc, argv, envp); + for (ctor_func = __init_array_start; ctor_func < __init_array_end; ctor_func++) + (*ctor_func)(argc, argv, envp); /* go to application */ exitcode = _nolibc_main(argc, argv, envp); - for (func = __fini_array_end; func > __fini_array_start;) - (*--func)(); + for (dtor_func = __fini_array_end; dtor_func > __fini_array_start;) + (*--dtor_func)(); exit(exitcode); } diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index 989e707263a4..92436b1e4441 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -74,7 +74,8 @@ * -I../nolibc -o hello hello.c -lgcc * * The available standard (but limited) include files are: - * ctype.h, errno.h, signal.h, stdarg.h, stdio.h, stdlib.h, string.h, time.h + * ctype.h, errno.h, signal.h, stdarg.h, stdbool.h stdio.h, stdlib.h, + * string.h, time.h * * In addition, the following ones are expected to be provided by the compiler: * float.h, stddef.h diff --git a/tools/include/nolibc/stackprotector.h b/tools/include/nolibc/stackprotector.h index 13f1d0e60387..1d0d5259ec41 100644 --- a/tools/include/nolibc/stackprotector.h +++ b/tools/include/nolibc/stackprotector.h @@ -18,7 +18,7 @@ * triggering stack protector errors themselves */ -__attribute__((weak,noreturn,section(".text.nolibc_stack_chk"))) +__attribute__((weak,used,noreturn,section(".text.nolibc_stack_chk"))) void __stack_chk_fail(void) { pid_t pid; @@ -34,7 +34,7 @@ void __stack_chk_fail_local(void) __stack_chk_fail(); } -__attribute__((weak,section(".data.nolibc_stack_chk"))) +__attribute__((weak,used,section(".data.nolibc_stack_chk"))) uintptr_t __stack_chk_guard; static __no_stack_protector void __stack_chk_init(void) diff --git a/tools/include/nolibc/stdbool.h b/tools/include/nolibc/stdbool.h new file mode 100644 index 000000000000..60feece22f17 --- /dev/null +++ b/tools/include/nolibc/stdbool.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Boolean types support for NOLIBC + * Copyright (C) 2024 Thomas Weißschuh <linux@weissschuh.net> + */ + +#ifndef _NOLIBC_STDBOOL_H +#define _NOLIBC_STDBOOL_H + +#define bool _Bool +#define true 1 +#define false 0 + +#define __bool_true_false_are_defined 1 + +#endif /* _NOLIBC_STDBOOL_H */ diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index f9ab28421e6d..9ec9c24f38c0 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -7,6 +7,7 @@ #ifndef _NOLIBC_STRING_H #define _NOLIBC_STRING_H +#include "arch.h" #include "std.h" static void *malloc(size_t len); diff --git a/tools/memory-model/Documentation/README b/tools/memory-model/Documentation/README index 304162743a5b..9999c1effdb6 100644 --- a/tools/memory-model/Documentation/README +++ b/tools/memory-model/Documentation/README @@ -9,6 +9,8 @@ depending on what you know and what you would like to learn. Please note that the documents later in this list assume that the reader understands the material provided by documents earlier in this list. +If LKMM-specific terms lost you, glossary.txt might help you. + o You are new to Linux-kernel concurrency: simple.txt o You have some background in Linux-kernel concurrency, and would @@ -21,6 +23,9 @@ o You are familiar with the Linux-kernel concurrency primitives that you need, and just want to get started with LKMM litmus tests: litmus-tests.txt +o You would like to access lock-protected shared variables without + having their corresponding locks held: locking.txt + o You are familiar with Linux-kernel concurrency, and would like a detailed intuitive understanding of LKMM, including situations involving more than two threads: recipes.txt @@ -28,12 +33,18 @@ o You are familiar with Linux-kernel concurrency, and would o You would like a detailed understanding of what your compiler can and cannot do to control dependencies: control-dependencies.txt +o You would like to mark concurrent normal accesses to shared + variables so that intentional "racy" accesses can be properly + documented, especially when you are responding to complaints + from KCSAN: access-marking.txt + o You are familiar with Linux-kernel concurrency and the use of LKMM, and would like a quick reference: cheatsheet.txt o You are familiar with Linux-kernel concurrency and the use of LKMM, and would like to learn about LKMM's requirements, - rationale, and implementation: explanation.txt + rationale, and implementation: explanation.txt and + herd-representation.txt o You are interested in the publications related to LKMM, including hardware manuals, academic literature, standards-committee @@ -61,10 +72,21 @@ control-dependencies.txt explanation.txt Detailed description of the memory model. +glossary.txt + Brief definitions of LKMM-related terms. + +herd-representation.txt + The (abstract) representation of the Linux-kernel concurrency + primitives in terms of events. + litmus-tests.txt The format, features, capabilities, and limitations of the litmus tests that LKMM can evaluate. +locking.txt + Rules for accessing lock-protected shared variables outside of + their corresponding critical sections. + ordering.txt Overview of the Linux kernel's low-level memory-ordering primitives by category. diff --git a/tools/memory-model/Documentation/herd-representation.txt b/tools/memory-model/Documentation/herd-representation.txt new file mode 100644 index 000000000000..ed988906f2b7 --- /dev/null +++ b/tools/memory-model/Documentation/herd-representation.txt @@ -0,0 +1,110 @@ +# +# Legend: +# R, a Load event +# W, a Store event +# F, a Fence event +# LKR, a Lock-Read event +# LKW, a Lock-Write event +# UL, an Unlock event +# LF, a Lock-Fail event +# RL, a Read-Locked event +# RU, a Read-Unlocked event +# R*, a Load event included in RMW +# W*, a Store event included in RMW +# SRCU, a Sleepable-Read-Copy-Update event +# +# po, a Program-Order link +# rmw, a Read-Modify-Write link - every rmw link is a po link +# +# By convention, a blank line in a cell means "same as the preceding line". +# +# Disclaimer. The table includes representations of "add" and "and" operations; +# corresponding/identical representations of "sub", "inc", "dec" and "or", "xor", +# "andnot" operations are omitted. +# + ------------------------------------------------------------------------------ + | C macro | Events | + ------------------------------------------------------------------------------ + | Non-RMW ops | | + ------------------------------------------------------------------------------ + | READ_ONCE | R[once] | + | atomic_read | | + | WRITE_ONCE | W[once] | + | atomic_set | | + | smp_load_acquire | R[acquire] | + | atomic_read_acquire | | + | smp_store_release | W[release] | + | atomic_set_release | | + | smp_store_mb | W[once] ->po F[mb] | + | smp_mb | F[mb] | + | smp_rmb | F[rmb] | + | smp_wmb | F[wmb] | + | smp_mb__before_atomic | F[before-atomic] | + | smp_mb__after_atomic | F[after-atomic] | + | spin_unlock | UL | + | spin_is_locked | On success: RL | + | | On failure: RU | + | smp_mb__after_spinlock | F[after-spinlock] | + | smp_mb__after_unlock_lock | F[after-unlock-lock] | + | rcu_read_lock | F[rcu-lock] | + | rcu_read_unlock | F[rcu-unlock] | + | synchronize_rcu | F[sync-rcu] | + | rcu_dereference | R[once] | + | rcu_assign_pointer | W[release] | + | srcu_read_lock | R[srcu-lock] | + | srcu_down_read | | + | srcu_read_unlock | W[srcu-unlock] | + | srcu_up_read | | + | synchronize_srcu | SRCU[sync-srcu] | + | smp_mb__after_srcu_read_unlock | F[after-srcu-read-unlock] | + ------------------------------------------------------------------------------ + | RMW ops w/o return value | | + ------------------------------------------------------------------------------ + | atomic_add | R*[noreturn] ->rmw W*[once] | + | atomic_and | | + | spin_lock | LKR ->po LKW | + ------------------------------------------------------------------------------ + | RMW ops w/ return value | | + ------------------------------------------------------------------------------ + | atomic_add_return | F[mb] ->po R*[once] | + | | ->rmw W*[once] ->po F[mb] | + | atomic_fetch_add | | + | atomic_fetch_and | | + | atomic_xchg | | + | xchg | | + | atomic_add_negative | | + | atomic_add_return_relaxed | R*[once] ->rmw W*[once] | + | atomic_fetch_add_relaxed | | + | atomic_fetch_and_relaxed | | + | atomic_xchg_relaxed | | + | xchg_relaxed | | + | atomic_add_negative_relaxed | | + | atomic_add_return_acquire | R*[acquire] ->rmw W*[once] | + | atomic_fetch_add_acquire | | + | atomic_fetch_and_acquire | | + | atomic_xchg_acquire | | + | xchg_acquire | | + | atomic_add_negative_acquire | | + | atomic_add_return_release | R*[once] ->rmw W*[release] | + | atomic_fetch_add_release | | + | atomic_fetch_and_release | | + | atomic_xchg_release | | + | xchg_release | | + | atomic_add_negative_release | | + ------------------------------------------------------------------------------ + | Conditional RMW ops | | + ------------------------------------------------------------------------------ + | atomic_cmpxchg | On success: F[mb] ->po R*[once] | + | | ->rmw W*[once] ->po F[mb] | + | | On failure: R*[once] | + | cmpxchg | | + | atomic_add_unless | | + | atomic_cmpxchg_relaxed | On success: R*[once] ->rmw W*[once] | + | | On failure: R*[once] | + | atomic_cmpxchg_acquire | On success: R*[acquire] ->rmw W*[once] | + | | On failure: R*[once] | + | atomic_cmpxchg_release | On success: R*[once] ->rmw W*[release] | + | | On failure: R*[once] | + | spin_trylock | On success: LKR ->po LKW | + | | On failure: LF | + ------------------------------------------------------------------------------ diff --git a/tools/memory-model/Documentation/simple.txt b/tools/memory-model/Documentation/simple.txt index 4c789ec8334f..21f06c1d1b70 100644 --- a/tools/memory-model/Documentation/simple.txt +++ b/tools/memory-model/Documentation/simple.txt @@ -266,5 +266,5 @@ More complex use cases ====================== If the alternatives above do not do what you need, please look at the -recipes-pairs.txt file to peel off the next layer of the memory-ordering +recipes.txt file to peel off the next layer of the memory-ordering onion. diff --git a/tools/rcu/rcu-updaters.sh b/tools/rcu/rcu-updaters.sh index 4ef1397927bb..8a5df3f22550 100755 --- a/tools/rcu/rcu-updaters.sh +++ b/tools/rcu/rcu-updaters.sh @@ -21,12 +21,10 @@ fi bpftrace -e 'kprobe:kvfree_call_rcu, kprobe:call_rcu, kprobe:call_rcu_tasks, - kprobe:call_rcu_tasks_rude, kprobe:call_rcu_tasks_trace, kprobe:call_srcu, kprobe:rcu_barrier, kprobe:rcu_barrier_tasks, - kprobe:rcu_barrier_tasks_rude, kprobe:rcu_barrier_tasks_trace, kprobe:srcu_barrier, kprobe:synchronize_rcu, diff --git a/tools/sound/dapm-graph b/tools/sound/dapm-graph index 57d78f6df041..f14bdfedee8f 100755 --- a/tools/sound/dapm-graph +++ b/tools/sound/dapm-graph @@ -8,6 +8,8 @@ set -eu +STYLE_COMPONENT_ON="color=dodgerblue;style=bold" +STYLE_COMPONENT_OFF="color=gray40;style=filled;fillcolor=gray90" STYLE_NODE_ON="shape=box,style=bold,color=green4" STYLE_NODE_OFF="shape=box,style=filled,color=gray30,fillcolor=gray95" @@ -132,11 +134,17 @@ process_dapm_widget() # Collect any links. We could use "in" links or "out" links, # let's use "in" links if echo "${line}" | grep -q '^in '; then + local w_route=$(echo "$line" | awk -F\" '{print $2}') local w_src=$(echo "$line" | awk -F\" '{print $6 "_" $4}' | sed 's/^(null)_/ROOT_/') dbg_echo " - Input route from: ${w_src}" - echo " \"${w_src}\" -> \"$w_tag\"" >> "${links_file}" + dbg_echo " - Route: ${w_route}" + local w_edge_attrs="" + if [ "${w_route}" != "static" ]; then + w_edge_attrs=" [label=\"${w_route}\"]" + fi + echo " \"${w_src}\" -> \"$w_tag\"${w_edge_attrs}" >> "${links_file}" fi done @@ -150,16 +158,20 @@ process_dapm_widget() # # $1 = temporary work dir # $2 = component directory -# $3 = forced component name (extracted for path if empty) +# $3 = "ROOT" for the root card directory, empty otherwise process_dapm_component() { local tmp_dir="${1}" local c_dir="${2}" local c_name="${3}" + local is_component=0 local dot_file="${tmp_dir}/main.dot" local links_file="${tmp_dir}/links.dot" + local c_attribs="" if [ -z "${c_name}" ]; then + is_component=1 + # Extract directory name into component name: # "./cs42l51.0-004a/dapm" -> "cs42l51.0-004a" c_name="$(basename $(dirname "${c_dir}"))" @@ -167,11 +179,23 @@ process_dapm_component() dbg_echo " * Component: ${c_name}" - echo "" >> "${dot_file}" - echo " subgraph \"${c_name}\" {" >> "${dot_file}" - echo " cluster = true" >> "${dot_file}" - echo " label = \"${c_name}\"" >> "${dot_file}" - echo " color=dodgerblue" >> "${dot_file}" + if [ ${is_component} = 1 ]; then + if [ -f "${c_dir}/bias_level" ]; then + c_onoff=$(sed -n -e 1p "${c_dir}/bias_level" | awk '{print $1}') + dbg_echo " - bias_level: ${c_onoff}" + if [ "$c_onoff" = "On" ]; then + c_attribs="${STYLE_COMPONENT_ON}" + elif [ "$c_onoff" = "Off" ]; then + c_attribs="${STYLE_COMPONENT_OFF}" + fi + fi + + echo "" >> "${dot_file}" + echo " subgraph \"${c_name}\" {" >> "${dot_file}" + echo " cluster = true" >> "${dot_file}" + echo " label = \"${c_name}\"" >> "${dot_file}" + echo " ${c_attribs}" >> "${dot_file}" + fi # Create empty file to ensure it will exist in all cases >"${links_file}" @@ -181,7 +205,9 @@ process_dapm_component() process_dapm_widget "${tmp_dir}" "${c_name}" "${w_file}" done - echo " }" >> "${dot_file}" + if [ ${is_component} = 1 ]; then + echo " }" >> "${dot_file}" + fi cat "${links_file}" >> "${dot_file}" } @@ -200,7 +226,7 @@ process_dapm_tree() echo "digraph G {" > "${dot_file}" echo " fontname=\"sans-serif\"" >> "${dot_file}" echo " node [fontname=\"sans-serif\"]" >> "${dot_file}" - + echo " edge [fontname=\"sans-serif\"]" >> "${dot_file}" # Process root directory (no component) process_dapm_component "${tmp_dir}" "${dapm_dir}/dapm" "ROOT" diff --git a/tools/spi/spidev_fdx.c b/tools/spi/spidev_fdx.c index 7d2a867cd4ae..bc9c4f6c3ba8 100644 --- a/tools/spi/spidev_fdx.c +++ b/tools/spi/spidev_fdx.c @@ -99,7 +99,7 @@ static void dumpstat(const char *name, int fd) return; } - printf("%s: spi mode 0x%x, %d bits %sper word, %d Hz max\n", + printf("%s: spi mode 0x%x, %d bits %sper word, %u Hz max\n", name, mode, bits, lsb ? "(lsb first) " : "", speed); } diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 7254c110ff23..61931c4926fd 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -72,7 +72,8 @@ class LinuxSourceTreeOperations: raise ConfigError(e.output.decode()) def make(self, jobs: int, build_dir: str, make_options: Optional[List[str]]) -> None: - command = ['make', 'ARCH=' + self._linux_arch, 'O=' + build_dir, '--jobs=' + str(jobs)] + command = ['make', 'all', 'compile_commands.json', 'ARCH=' + self._linux_arch, + 'O=' + build_dir, '--jobs=' + str(jobs)] if make_options: command.extend(make_options) if self._cross_compile: diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 3b7df5477317..b38199965f99 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +TARGETS += acct TARGETS += alsa TARGETS += amd-pstate TARGETS += arm64 @@ -109,7 +110,6 @@ TARGETS += tmpfs TARGETS += tpm2 TARGETS += tty TARGETS += uevent -TARGETS += user TARGETS += user_events TARGETS += vDSO TARGETS += mm diff --git a/tools/testing/selftests/acct/.gitignore b/tools/testing/selftests/acct/.gitignore new file mode 100644 index 000000000000..7e78aac19038 --- /dev/null +++ b/tools/testing/selftests/acct/.gitignore @@ -0,0 +1,3 @@ +acct_syscall +config +process_log
\ No newline at end of file diff --git a/tools/testing/selftests/acct/Makefile b/tools/testing/selftests/acct/Makefile new file mode 100644 index 000000000000..7e025099cf65 --- /dev/null +++ b/tools/testing/selftests/acct/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := acct_syscall +CFLAGS += -Wall + +include ../lib.mk
\ No newline at end of file diff --git a/tools/testing/selftests/acct/acct_syscall.c b/tools/testing/selftests/acct/acct_syscall.c new file mode 100644 index 000000000000..e44e8fe1f4a3 --- /dev/null +++ b/tools/testing/selftests/acct/acct_syscall.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* kselftest for acct() system call + * The acct() system call enables or disables process accounting. + */ + +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <sys/wait.h> + +#include "../kselftest.h" + +int main(void) +{ + char filename[] = "process_log"; + FILE *fp; + pid_t child_pid; + int sz; + + // Setting up kselftest framework + ksft_print_header(); + ksft_set_plan(1); + + // Check if test is run a root + if (geteuid()) { + ksft_test_result_skip("This test needs root to run!\n"); + return 1; + } + + // Create file to log closed processes + fp = fopen(filename, "w"); + + if (!fp) { + ksft_test_result_error("%s.\n", strerror(errno)); + ksft_finished(); + return 1; + } + + acct(filename); + + // Handle error conditions + if (errno) { + ksft_test_result_error("%s.\n", strerror(errno)); + fclose(fp); + ksft_finished(); + return 1; + } + + // Create child process and wait for it to terminate. + + child_pid = fork(); + + if (child_pid < 0) { + ksft_test_result_error("Creating a child process to log failed\n"); + acct(NULL); + return 1; + } else if (child_pid > 0) { + wait(NULL); + fseek(fp, 0L, SEEK_END); + sz = ftell(fp); + + acct(NULL); + + if (sz <= 0) { + ksft_test_result_fail("Terminated child process not logged\n"); + ksft_exit_fail(); + return 1; + } + + ksft_test_result_pass("Successfully logged terminated process.\n"); + fclose(fp); + ksft_exit_pass(); + return 0; + } + + return 1; +} diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index c1ce39874e2b..25be68025290 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -12,9 +12,9 @@ LDLIBS+=-lpthread OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS := mixer-test pcm-test test-pcmtest-driver +TEST_GEN_PROGS := mixer-test pcm-test test-pcmtest-driver utimer-test -TEST_GEN_PROGS_EXTENDED := libatest.so +TEST_GEN_PROGS_EXTENDED := libatest.so global-timer TEST_FILES := conf.d pcm-test.conf diff --git a/tools/testing/selftests/alsa/global-timer.c b/tools/testing/selftests/alsa/global-timer.c new file mode 100644 index 000000000000..c15ec0ba851a --- /dev/null +++ b/tools/testing/selftests/alsa/global-timer.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This tool is used by the utimer test, and it allows us to + * count the ticks of a global timer in a certain time frame + * (which is set by `timeout` parameter). + * + * Author: Ivan Orlov <ivan.orlov0322@gmail.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <alsa/asoundlib.h> +#include <time.h> + +static int ticked; +static void async_callback(snd_async_handler_t *ahandler) +{ + ticked++; +} + +static char timer_name[64]; +static void bind_to_timer(int device, int subdevice, int timeout) +{ + snd_timer_t *handle; + snd_timer_params_t *params; + snd_async_handler_t *ahandler; + + time_t end; + + sprintf(timer_name, "hw:CLASS=%d,SCLASS=%d,DEV=%d,SUBDEV=%d", + SND_TIMER_CLASS_GLOBAL, SND_TIMER_SCLASS_NONE, + device, subdevice); + + snd_timer_params_alloca(¶ms); + + if (snd_timer_open(&handle, timer_name, SND_TIMER_OPEN_NONBLOCK) < 0) { + perror("Can't open the timer"); + exit(EXIT_FAILURE); + } + + snd_timer_params_set_auto_start(params, 1); + snd_timer_params_set_ticks(params, 1); + if (snd_timer_params(handle, params) < 0) { + perror("Can't set timer params"); + exit(EXIT_FAILURE); + } + + if (snd_async_add_timer_handler(&ahandler, handle, async_callback, NULL) < 0) { + perror("Can't create a handler"); + exit(EXIT_FAILURE); + } + end = time(NULL) + timeout; + if (snd_timer_start(handle) < 0) { + perror("Failed to start the timer"); + exit(EXIT_FAILURE); + } + printf("Timer has started\n"); + while (time(NULL) <= end) { + /* + * Waiting for the timeout to elapse. Can't use sleep here, as it gets + * constantly interrupted by the signal from the timer (SIGIO) + */ + } + snd_timer_stop(handle); + snd_timer_close(handle); +} + +int main(int argc, char *argv[]) +{ + int device, subdevice, timeout; + + if (argc < 4) { + perror("Usage: %s <device> <subdevice> <timeout>"); + return EXIT_FAILURE; + } + + setlinebuf(stdout); + + device = atoi(argv[1]); + subdevice = atoi(argv[2]); + timeout = atoi(argv[3]); + + bind_to_timer(device, subdevice, timeout); + + printf("Total ticks count: %d\n", ticked); + + return EXIT_SUCCESS; +} diff --git a/tools/testing/selftests/alsa/utimer-test.c b/tools/testing/selftests/alsa/utimer-test.c new file mode 100644 index 000000000000..32ee3ce57721 --- /dev/null +++ b/tools/testing/selftests/alsa/utimer-test.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This test covers the functionality of userspace-driven ALSA timers. Such timers + * are purely virtual (so they don't directly depend on the hardware), and they could be + * created and triggered by userspace applications. + * + * Author: Ivan Orlov <ivan.orlov0322@gmail.com> + */ +#include "../kselftest_harness.h" +#include <sound/asound.h> +#include <unistd.h> +#include <fcntl.h> +#include <limits.h> +#include <sys/ioctl.h> +#include <stdlib.h> +#include <pthread.h> +#include <string.h> + +#define FRAME_RATE 8000 +#define PERIOD_SIZE 4410 +#define UTIMER_DEFAULT_ID -1 +#define UTIMER_DEFAULT_FD -1 +#define NANO 1000000000ULL +#define TICKS_COUNT 10 +#define TICKS_RECORDING_DELTA 5 +#define TIMER_OUTPUT_BUF_LEN 1024 +#define TIMER_FREQ_SEC 1 +#define RESULT_PREFIX_LEN strlen("Total ticks count: ") + +enum timer_app_event { + TIMER_APP_STARTED, + TIMER_APP_RESULT, + TIMER_NO_EVENT, +}; + +FIXTURE(timer_f) { + struct snd_timer_uinfo *utimer_info; +}; + +FIXTURE_SETUP(timer_f) { + int timer_dev_fd; + + if (geteuid()) + SKIP(return, "This test needs root to run!"); + + self->utimer_info = calloc(1, sizeof(*self->utimer_info)); + ASSERT_NE(NULL, self->utimer_info); + + /* Resolution is the time the period of frames takes in nanoseconds */ + self->utimer_info->resolution = (NANO / FRAME_RATE * PERIOD_SIZE); + + timer_dev_fd = open("/dev/snd/timer", O_RDONLY); + ASSERT_GE(timer_dev_fd, 0); + + ASSERT_EQ(ioctl(timer_dev_fd, SNDRV_TIMER_IOCTL_CREATE, self->utimer_info), 0); + ASSERT_GE(self->utimer_info->fd, 0); + + close(timer_dev_fd); +} + +FIXTURE_TEARDOWN(timer_f) { + close(self->utimer_info->fd); + free(self->utimer_info); +} + +static void *ticking_func(void *data) +{ + int i; + int *fd = (int *)data; + + for (i = 0; i < TICKS_COUNT; i++) { + /* Well, trigger the timer! */ + ioctl(*fd, SNDRV_TIMER_IOCTL_TRIGGER, NULL); + sleep(TIMER_FREQ_SEC); + } + + return NULL; +} + +static enum timer_app_event parse_timer_output(const char *s) +{ + if (strstr(s, "Timer has started")) + return TIMER_APP_STARTED; + if (strstr(s, "Total ticks count")) + return TIMER_APP_RESULT; + + return TIMER_NO_EVENT; +} + +static int parse_timer_result(const char *s) +{ + char *end; + long d; + + d = strtol(s + RESULT_PREFIX_LEN, &end, 10); + if (end == s + RESULT_PREFIX_LEN) + return -1; + + return d; +} + +/* + * This test triggers the timer and counts ticks at the same time. The amount + * of the timer trigger calls should be equal to the amount of ticks received. + */ +TEST_F(timer_f, utimer) { + char command[64]; + pthread_t ticking_thread; + int total_ticks = 0; + FILE *rfp; + char *buf = malloc(TIMER_OUTPUT_BUF_LEN); + + ASSERT_NE(buf, NULL); + + /* The timeout should be the ticks interval * count of ticks + some delta */ + sprintf(command, "./global-timer %d %d %d", SNDRV_TIMER_GLOBAL_UDRIVEN, + self->utimer_info->id, TICKS_COUNT * TIMER_FREQ_SEC + TICKS_RECORDING_DELTA); + + rfp = popen(command, "r"); + while (fgets(buf, TIMER_OUTPUT_BUF_LEN, rfp)) { + buf[TIMER_OUTPUT_BUF_LEN - 1] = 0; + switch (parse_timer_output(buf)) { + case TIMER_APP_STARTED: + /* global-timer waits for timer to trigger, so start the ticking thread */ + pthread_create(&ticking_thread, NULL, ticking_func, + &self->utimer_info->fd); + break; + case TIMER_APP_RESULT: + total_ticks = parse_timer_result(buf); + break; + case TIMER_NO_EVENT: + break; + } + } + pthread_join(ticking_thread, NULL); + ASSERT_EQ(total_ticks, TICKS_COUNT); + pclose(rfp); +} + +TEST(wrong_timers_test) { + int timer_dev_fd; + int utimer_fd; + size_t i; + struct snd_timer_uinfo wrong_timer = { + .resolution = 0, + .id = UTIMER_DEFAULT_ID, + .fd = UTIMER_DEFAULT_FD, + }; + + timer_dev_fd = open("/dev/snd/timer", O_RDONLY); + ASSERT_GE(timer_dev_fd, 0); + + utimer_fd = ioctl(timer_dev_fd, SNDRV_TIMER_IOCTL_CREATE, &wrong_timer); + ASSERT_LT(utimer_fd, 0); + /* Check that id was not updated */ + ASSERT_EQ(wrong_timer.id, UTIMER_DEFAULT_ID); + + /* Test the NULL as an argument is processed correctly */ + ASSERT_LT(ioctl(timer_dev_fd, SNDRV_TIMER_IOCTL_CREATE, NULL), 0); + + close(timer_dev_fd); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index a32771da4293..22807fd78fe6 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -434,7 +434,7 @@ uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func, struct testmod_uprobe { struct path path; - loff_t offset; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -448,25 +448,25 @@ static int testmod_register_uprobe(loff_t offset) { int err = -EBUSY; - if (uprobe.offset) + if (uprobe.uprobe) return -EBUSY; mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) + if (uprobe.uprobe) goto out; err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path); if (err) goto out; - err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry), - offset, 0, &uprobe.consumer); - if (err) + uprobe.uprobe = uprobe_register(d_real_inode(uprobe.path.dentry), + offset, 0, &uprobe.consumer); + if (IS_ERR(uprobe.uprobe)) { + err = PTR_ERR(uprobe.uprobe); path_put(&uprobe.path); - else - uprobe.offset = offset; - + uprobe.uprobe = NULL; + } out: mutex_unlock(&testmod_uprobe_mutex); return err; @@ -476,10 +476,11 @@ static void testmod_unregister_uprobe(void) { mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) { - uprobe_unregister(d_real_inode(uprobe.path.dentry), - uprobe.offset, &uprobe.consumer); - uprobe.offset = 0; + if (uprobe.uprobe) { + uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer); + uprobe_unregister_sync(); + path_put(&uprobe.path); + uprobe.uprobe = NULL; } mutex_unlock(&testmod_uprobe_mutex); diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 7c08cc153367..03c1bdaed2c3 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -84,6 +84,20 @@ echo member > test/cpuset.cpus.partition echo "" > test/cpuset.cpus [[ $RESULT -eq 0 ]] && skip_test "Child cgroups are using cpuset!" +# +# If isolated CPUs have been reserved at boot time (as shown in +# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7 +# that will be used by this script for testing purpose. If not, some of +# the tests may fail incorrectly. These isolated CPUs will also be removed +# before being compared with the expected results. +# +BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated) +if [[ -n "$BOOT_ISOLCPUS" ]] +then + [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] && + skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested" + echo "Pre-isolated CPUs: $BOOT_ISOLCPUS" +fi cleanup() { online_cpus @@ -321,7 +335,7 @@ TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # - # Incorrect change to cpuset.cpus invalidates partition root + # Incorrect change to cpuset.cpus[.exclusive] invalidates partition root # # Adding CPUs to partition root that are not in parent's # cpuset.cpus is allowed, but those extra CPUs are ignored. @@ -365,6 +379,16 @@ TEST_MATRIX=( # cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it " C0-3 . . C4-5 X5 . . . 0 A1:0-3,B1:4-5" + # Child partition root that try to take all CPUs from parent partition + # with tasks will remain invalid. + " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1" + " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1,A2:1-4 A1:P1,A2:P1" + " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1" + + # Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't + # affect cpuset.cpus.exclusive.effective. + " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4,XA2:3" + # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: @@ -632,7 +656,8 @@ check_cgroup_states() # Note that isolated CPUs from the sched/domains context include offline # CPUs as well as CPUs in non-isolated 1-CPU partition. Those CPUs may # not be included in the cpuset.cpus.isolated control file which contains -# only CPUs in isolated partitions. +# only CPUs in isolated partitions as well as those that are isolated at +# boot time. # # $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>} # <isolcpus1> - expected sched/domains value @@ -659,18 +684,21 @@ check_isolcpus() fi # - # Check the debug isolated cpumask, if present + # Check cpuset.cpus.isolated cpumask # - [[ -f $ISCPUS ]] && { + if [[ -z "$BOOT_ISOLCPUS" ]] + then + ISOLCPUS=$(cat $ISCPUS) + else + ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") + fi + [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { + # Take a 50ms pause and try again + pause 0.05 ISOLCPUS=$(cat $ISCPUS) - [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { - # Take a 50ms pause and try again - pause 0.05 - ISOLCPUS=$(cat $ISCPUS) - } - [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1 - ISOLCPUS= } + [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1 + ISOLCPUS= # # Use the sched domain in debugfs to check isolated CPUs, if available @@ -703,6 +731,9 @@ check_isolcpus() fi done [[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU + [[ -n "BOOT_ISOLCPUS" ]] && + ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") + [[ "$EXPECT_VAL" = "$ISOLCPUS" ]] } @@ -720,7 +751,8 @@ test_fail() } # -# Check to see if there are unexpected isolated CPUs left +# Check to see if there are unexpected isolated CPUs left beyond the boot +# time isolated ones. # null_isolcpus_check() { diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh new file mode 100755 index 000000000000..42a6628fb8bc --- /dev/null +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh @@ -0,0 +1,77 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Basc test for cpuset v1 interfaces write/read +# + +skip_test() { + echo "$1" + echo "Test SKIPPED" + exit 4 # ksft_skip +} + +write_test() { + dir=$1 + interface=$2 + value=$3 + original=$(cat $dir/$interface) + echo "testing $interface $value" + echo $value > $dir/$interface + new=$(cat $dir/$interface) + [[ $value -ne $(cat $dir/$interface) ]] && { + echo "$interface write $value failed: new:$new" + exit 1 + } +} + +[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!" + +# Find cpuset v1 mount point +CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk '{print $3}') +[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!" + +# +# Create a test cpuset, read write test +# +TDIR=test$$ +[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR + +ITF_MATRIX=( + #interface value expect root_only + 'cpuset.cpus 0-1 0-1 0' + 'cpuset.mem_exclusive 1 1 0' + 'cpuset.mem_exclusive 0 0 0' + 'cpuset.mem_hardwall 1 1 0' + 'cpuset.mem_hardwall 0 0 0' + 'cpuset.memory_migrate 1 1 0' + 'cpuset.memory_migrate 0 0 0' + 'cpuset.memory_spread_page 1 1 0' + 'cpuset.memory_spread_page 0 0 0' + 'cpuset.memory_spread_slab 1 1 0' + 'cpuset.memory_spread_slab 0 0 0' + 'cpuset.mems 0 0 0' + 'cpuset.sched_load_balance 1 1 0' + 'cpuset.sched_load_balance 0 0 0' + 'cpuset.sched_relax_domain_level 2 2 0' + 'cpuset.memory_pressure_enabled 1 1 1' + 'cpuset.memory_pressure_enabled 0 0 1' +) + +run_test() +{ + cnt="${ITF_MATRIX[@]}" + for i in "${ITF_MATRIX[@]}" ; do + args=($i) + root_only=${args[3]} + [[ $root_only -eq 1 ]] && { + write_test "$CPUSET" "${args[0]}" "${args[1]}" "${args[2]}" + continue + } + write_test "$CPUSET/$TDIR" "${args[0]}" "${args[1]}" "${args[2]}" + done +} + +run_test +rmdir $CPUSET/$TDIR +echo "Test PASSED" +exit 0 diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile index ce262d097269..8e99f87f5d7c 100644 --- a/tools/testing/selftests/core/Makefile +++ b/tools/testing/selftests/core/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -g $(KHDR_INCLUDES) -TEST_GEN_PROGS := close_range_test +TEST_GEN_PROGS := close_range_test unshare_test include ../lib.mk diff --git a/tools/testing/selftests/core/unshare_test.c b/tools/testing/selftests/core/unshare_test.c new file mode 100644 index 000000000000..7fec9dfb1b0e --- /dev/null +++ b/tools/testing/selftests/core/unshare_test.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/kernel.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <unistd.h> +#include <sys/resource.h> +#include <linux/close_range.h> + +#include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +TEST(unshare_EMFILE) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + int fd; + ssize_t n, n2; + static char buf[512], buf2[512]; + struct rlimit rlimit; + int nr_open; + + fd = open("/proc/sys/fs/nr_open", O_RDWR); + ASSERT_GE(fd, 0); + + n = read(fd, buf, sizeof(buf)); + ASSERT_GT(n, 0); + ASSERT_EQ(buf[n - 1], '\n'); + + ASSERT_EQ(sscanf(buf, "%d", &nr_open), 1); + + ASSERT_EQ(0, getrlimit(RLIMIT_NOFILE, &rlimit)); + + /* bump fs.nr_open */ + n2 = sprintf(buf2, "%d\n", nr_open + 1024); + lseek(fd, 0, SEEK_SET); + write(fd, buf2, n2); + + /* bump ulimit -n */ + rlimit.rlim_cur = nr_open + 1024; + rlimit.rlim_max = nr_open + 1024; + EXPECT_EQ(0, setrlimit(RLIMIT_NOFILE, &rlimit)) { + lseek(fd, 0, SEEK_SET); + write(fd, buf, n); + exit(EXIT_FAILURE); + } + + /* get a descriptor past the old fs.nr_open */ + EXPECT_GE(dup2(2, nr_open + 64), 0) { + lseek(fd, 0, SEEK_SET); + write(fd, buf, n); + exit(EXIT_FAILURE); + } + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + EXPECT_GE(pid, 0) { + lseek(fd, 0, SEEK_SET); + write(fd, buf, n); + exit(EXIT_FAILURE); + } + + if (pid == 0) { + int err; + + /* restore fs.nr_open */ + lseek(fd, 0, SEEK_SET); + write(fd, buf, n); + /* ... and now unshare(CLONE_FILES) must fail with EMFILE */ + err = unshare(CLONE_FILES); + EXPECT_EQ(err, -1) + exit(EXIT_FAILURE); + EXPECT_EQ(errno, EMFILE) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/cpufreq/cpufreq.sh b/tools/testing/selftests/cpufreq/cpufreq.sh index a8b1dbc0a3a5..e350c521b467 100755 --- a/tools/testing/selftests/cpufreq/cpufreq.sh +++ b/tools/testing/selftests/cpufreq/cpufreq.sh @@ -231,6 +231,21 @@ do_suspend() for i in `seq 1 $2`; do printf "Starting $1\n" + + if [ "$3" = "rtc" ]; then + if ! command -v rtcwake &> /dev/null; then + printf "rtcwake could not be found, please install it.\n" + return 1 + fi + + rtcwake -m $filename -s 15 + + if [ $? -ne 0 ]; then + printf "Failed to suspend using RTC wake alarm\n" + return 1 + fi + fi + echo $filename > $SYSFS/power/state printf "Came out of $1\n" diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh index a0eb84cf7167..f12ff7416e41 100755 --- a/tools/testing/selftests/cpufreq/main.sh +++ b/tools/testing/selftests/cpufreq/main.sh @@ -24,6 +24,8 @@ helpme() [-t <basic: Basic cpufreq testing suspend: suspend/resume, hibernate: hibernate/resume, + suspend_rtc: suspend/resume back using the RTC wakeup alarm, + hibernate_rtc: hibernate/resume back using the RTC wakeup alarm, modtest: test driver or governor modules. Only to be used with -d or -g options, sptest1: Simple governor switch to produce lockdep. sptest2: Concurrent governor switch to produce lockdep. @@ -76,7 +78,8 @@ parse_arguments() helpme ;; - t) # --func_type (Function to perform: basic, suspend, hibernate, modtest, sptest1/2/3/4 (default: basic)) + t) # --func_type (Function to perform: basic, suspend, hibernate, + # suspend_rtc, hibernate_rtc, modtest, sptest1/2/3/4 (default: basic)) FUNC=$OPTARG ;; @@ -121,6 +124,14 @@ do_test() do_suspend "hibernate" 1 ;; + "suspend_rtc") + do_suspend "suspend" 1 rtc + ;; + + "hibernate_rtc") + do_suspend "hibernate" 1 rtc + ;; + "modtest") # Do we have modules in place? if [ -z $DRIVER_MOD ] && [ -z $GOVERNOR_MOD ]; then diff --git a/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c b/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c index ea0cdc37b44f..7ee7492138c6 100644 --- a/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c +++ b/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c @@ -257,12 +257,6 @@ TEST_F(attest_fixture, att_inval_addr) att_inval_addr_test(&self->uvio_attest.meas_addr, _metadata, self); } -static void __attribute__((constructor)) __constructor_order_last(void) -{ - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; -} - int main(int argc, char **argv) { int fd = open(UV_PATH, O_ACCMODE); diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh index 2d7e70c5ad2d..5e3f42ef249e 100755 --- a/tools/testing/selftests/dt/test_unprobed_devices.sh +++ b/tools/testing/selftests/dt/test_unprobed_devices.sh @@ -34,8 +34,21 @@ nodes_compatible=$( # Check if node is available if [[ -e "${node}"/status ]]; then status=$(tr -d '\000' < "${node}"/status) - [[ "${status}" != "okay" && "${status}" != "ok" ]] && continue + if [[ "${status}" != "okay" && "${status}" != "ok" ]]; then + if [ -n "${disabled_nodes_regex}" ]; then + disabled_nodes_regex="${disabled_nodes_regex}|${node}" + else + disabled_nodes_regex="${node}" + fi + continue + fi fi + + # Ignore this node if one of its ancestors was disabled + if [ -n "${disabled_nodes_regex}" ]; then + echo "${node}" | grep -q -E "${disabled_nodes_regex}" && continue + fi + echo "${node}" | sed -e 's|\/proc\/device-tree||' done | sort ) diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c index 6418ded40bdd..071e03532cba 100644 --- a/tools/testing/selftests/exec/execveat.c +++ b/tools/testing/selftests/exec/execveat.c @@ -117,7 +117,7 @@ static int check_execveat_invoked_rc(int fd, const char *path, int flags, } if ((WEXITSTATUS(status) != expected_rc) && (WEXITSTATUS(status) != expected_rc2)) { - ksft_print_msg("child %d exited with %d not %d nor %d\n", + ksft_print_msg("child %d exited with %d neither %d nor %d\n", child, WEXITSTATUS(status), expected_rc, expected_rc2); ksft_test_result_fail("%s\n", test_name); diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c index e044f5fc57fd..70cb0c8b21cf 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c @@ -319,8 +319,11 @@ static void test_listmount_ns(void) * Tell our parent how many mounts we have, and then wait for it * to tell us we're done. */ - write(child_ready_pipe[1], &nr_mounts, sizeof(nr_mounts)); - read(parent_ready_pipe[0], &cval, sizeof(cval)); + if (write(child_ready_pipe[1], &nr_mounts, sizeof(nr_mounts)) != + sizeof(nr_mounts)) + ret = NSID_ERROR; + if (read(parent_ready_pipe[0], &cval, sizeof(cval)) != sizeof(cval)) + ret = NSID_ERROR; exit(NSID_PASS); } diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc index c45094d1e1d2..094419e190c2 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc @@ -6,6 +6,18 @@ original_group=`stat -c "%g" .` original_owner=`stat -c "%u" .` mount_point=`stat -c '%m' .` + +# If stat -c '%m' does not work (e.g. busybox) or failed, try to use the +# current working directory (which should be a tracefs) as the mount point. +if [ ! -d "$mount_point" ]; then + if mount | grep -qw $PWD ; then + mount_point=$PWD + else + # If PWD doesn't work, that is an environmental problem. + exit_unresolved + fi +fi + mount_options=`mount | grep "$mount_point" | sed -e 's/.*(\(.*\)).*/\1/'` # find another owner and group that is not the original @@ -83,32 +95,38 @@ run_tests() { done } -mount -o remount,"$new_options" . +# Run the tests twice as leftovers can cause issues +for loop in 1 2 ; do -run_tests + echo "Running iteration $loop" -mount -o remount,"$mount_options" . + mount -o remount,"$new_options" . -for d in "." "events" "events/sched" "events/sched/sched_switch" "events/sched/sched_switch/enable" $canary; do - test "$d" $original_group -done + run_tests + + mount -o remount,"$mount_options" . + + for d in "." "events" "events/sched" "events/sched/sched_switch" "events/sched/sched_switch/enable" $canary; do + test "$d" $original_group + done # check instances as well -chgrp $other_group instances + chgrp $other_group instances -instance="$(mktemp -u test-XXXXXX)" + instance="$(mktemp -u test-XXXXXX)" -mkdir instances/$instance + mkdir instances/$instance -cd instances/$instance + cd instances/$instance -run_tests + run_tests -cd ../.. + cd ../.. -rmdir instances/$instance + rmdir instances/$instance -chgrp $original_group instances + chgrp $original_group instances +done exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc new file mode 100644 index 000000000000..a275decdc880 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc @@ -0,0 +1,26 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Generic dynamic event - add/remove/test uprobe events +# requires: uprobe_events + +echo 0 > events/enable +echo > dynamic_events + +echo 'cat /proc/$$/maps' | /bin/sh | \ + grep "r-xp .*/bin/.*sh$" | \ + awk '{printf "p:myevent %s:0x%s\n", $6,$3 }' >> uprobe_events + +grep -q myevent uprobe_events +test -d events/uprobes/myevent + +echo 1 > events/uprobes/myevent/enable +echo 'ls' | /bin/sh > /dev/null +echo 0 > events/uprobes/myevent/enable +grep -q myevent trace + +echo "-:myevent" >> uprobe_events +! grep -q myevent uprobe_events + +echo > uprobe_events + +clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc index 073a748b9380..263f6b798c85 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -19,7 +19,14 @@ fail() { # mesg FILTER=set_ftrace_filter FUNC1="schedule" -FUNC2="sched_tick" +if grep '^sched_tick\b' available_filter_functions; then + FUNC2="sched_tick" +elif grep '^scheduler_tick\b' available_filter_functions; then + FUNC2="scheduler_tick" +else + exit_unresolved +fi + ALL_FUNCS="#### all functions enabled ####" diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc index e21c9c27ece4..77f4c07cdcb8 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Kprobe event char type argument -# requires: kprobe_events +# requires: kprobe_events available_filter_functions case `uname -m` in x86_64) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index 93217d459556..39001073f7ed 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Kprobe event string type argument -# requires: kprobe_events +# requires: kprobe_events available_filter_functions case `uname -m` in x86_64) diff --git a/tools/testing/selftests/hid/.gitignore b/tools/testing/selftests/hid/.gitignore index 995af0670f69..746c62361f77 100644 --- a/tools/testing/selftests/hid/.gitignore +++ b/tools/testing/selftests/hid/.gitignore @@ -2,4 +2,5 @@ bpftool *.skel.h /tools hid_bpf +hidraw results diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 2b5ea18bde38..72be55ac4bdf 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -32,7 +32,7 @@ CFLAGS += -Wno-unused-command-line-argument endif # Order correspond to 'make run_tests' order -TEST_GEN_PROGS = hid_bpf +TEST_GEN_PROGS = hid_bpf hidraw # Emit succinct information message describing current building step # $1 - generic step name (e.g., CC, LINK, etc); diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index 75b7b4ef6cfa..86f4d66379f7 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -1,93 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2022 Red Hat */ +/* Copyright (c) 2022-2024 Red Hat */ #include "hid.skel.h" - -#include "../kselftest_harness.h" - +#include "hid_common.h" #include <bpf/bpf.h> -#include <fcntl.h> -#include <fnmatch.h> -#include <dirent.h> -#include <poll.h> -#include <pthread.h> -#include <stdbool.h> -#include <linux/hidraw.h> -#include <linux/uhid.h> - -#define SHOW_UHID_DEBUG 0 - -#define min(a, b) \ - ({ __typeof__(a) _a = (a); \ - __typeof__(b) _b = (b); \ - _a < _b ? _a : _b; }) - -static unsigned char rdesc[] = { - 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ - 0x09, 0x21, /* Usage (Vendor Usage 0x21) */ - 0xa1, 0x01, /* COLLECTION (Application) */ - 0x09, 0x01, /* Usage (Vendor Usage 0x01) */ - 0xa1, 0x00, /* COLLECTION (Physical) */ - 0x85, 0x02, /* REPORT_ID (2) */ - 0x19, 0x01, /* USAGE_MINIMUM (1) */ - 0x29, 0x08, /* USAGE_MAXIMUM (3) */ - 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ - 0x25, 0xff, /* LOGICAL_MAXIMUM (255) */ - 0x95, 0x08, /* REPORT_COUNT (8) */ - 0x75, 0x08, /* REPORT_SIZE (8) */ - 0x81, 0x02, /* INPUT (Data,Var,Abs) */ - 0xc0, /* END_COLLECTION */ - 0x09, 0x01, /* Usage (Vendor Usage 0x01) */ - 0xa1, 0x00, /* COLLECTION (Physical) */ - 0x85, 0x01, /* REPORT_ID (1) */ - 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ - 0x19, 0x01, /* USAGE_MINIMUM (1) */ - 0x29, 0x03, /* USAGE_MAXIMUM (3) */ - 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ - 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ - 0x95, 0x03, /* REPORT_COUNT (3) */ - 0x75, 0x01, /* REPORT_SIZE (1) */ - 0x81, 0x02, /* INPUT (Data,Var,Abs) */ - 0x95, 0x01, /* REPORT_COUNT (1) */ - 0x75, 0x05, /* REPORT_SIZE (5) */ - 0x81, 0x01, /* INPUT (Cnst,Var,Abs) */ - 0x05, 0x01, /* USAGE_PAGE (Generic Desktop) */ - 0x09, 0x30, /* USAGE (X) */ - 0x09, 0x31, /* USAGE (Y) */ - 0x15, 0x81, /* LOGICAL_MINIMUM (-127) */ - 0x25, 0x7f, /* LOGICAL_MAXIMUM (127) */ - 0x75, 0x10, /* REPORT_SIZE (16) */ - 0x95, 0x02, /* REPORT_COUNT (2) */ - 0x81, 0x06, /* INPUT (Data,Var,Rel) */ - - 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ - 0x19, 0x01, /* USAGE_MINIMUM (1) */ - 0x29, 0x03, /* USAGE_MAXIMUM (3) */ - 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ - 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ - 0x95, 0x03, /* REPORT_COUNT (3) */ - 0x75, 0x01, /* REPORT_SIZE (1) */ - 0x91, 0x02, /* Output (Data,Var,Abs) */ - 0x95, 0x01, /* REPORT_COUNT (1) */ - 0x75, 0x05, /* REPORT_SIZE (5) */ - 0x91, 0x01, /* Output (Cnst,Var,Abs) */ - - 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ - 0x19, 0x06, /* USAGE_MINIMUM (6) */ - 0x29, 0x08, /* USAGE_MAXIMUM (8) */ - 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ - 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ - 0x95, 0x03, /* REPORT_COUNT (3) */ - 0x75, 0x01, /* REPORT_SIZE (1) */ - 0xb1, 0x02, /* Feature (Data,Var,Abs) */ - 0x95, 0x01, /* REPORT_COUNT (1) */ - 0x75, 0x05, /* REPORT_SIZE (5) */ - 0x91, 0x01, /* Output (Cnst,Var,Abs) */ - - 0xc0, /* END_COLLECTION */ - 0xc0, /* END_COLLECTION */ -}; - -static __u8 feature_data[] = { 1, 2 }; struct attach_prog_args { int prog_fd; @@ -105,354 +20,6 @@ struct hid_hw_request_syscall_args { __u8 request_type; }; -#define ASSERT_OK(data) ASSERT_FALSE(data) -#define ASSERT_OK_PTR(ptr) ASSERT_NE(NULL, ptr) - -#define UHID_LOG(fmt, ...) do { \ - if (SHOW_UHID_DEBUG) \ - TH_LOG(fmt, ##__VA_ARGS__); \ -} while (0) - -static pthread_mutex_t uhid_started_mtx = PTHREAD_MUTEX_INITIALIZER; -static pthread_cond_t uhid_started = PTHREAD_COND_INITIALIZER; - -static pthread_mutex_t uhid_output_mtx = PTHREAD_MUTEX_INITIALIZER; -static pthread_cond_t uhid_output_cond = PTHREAD_COND_INITIALIZER; -static unsigned char output_report[10]; - -/* no need to protect uhid_stopped, only one thread accesses it */ -static bool uhid_stopped; - -static int uhid_write(struct __test_metadata *_metadata, int fd, const struct uhid_event *ev) -{ - ssize_t ret; - - ret = write(fd, ev, sizeof(*ev)); - if (ret < 0) { - TH_LOG("Cannot write to uhid: %m"); - return -errno; - } else if (ret != sizeof(*ev)) { - TH_LOG("Wrong size written to uhid: %zd != %zu", - ret, sizeof(ev)); - return -EFAULT; - } else { - return 0; - } -} - -static int uhid_create(struct __test_metadata *_metadata, int fd, int rand_nb) -{ - struct uhid_event ev; - char buf[25]; - - sprintf(buf, "test-uhid-device-%d", rand_nb); - - memset(&ev, 0, sizeof(ev)); - ev.type = UHID_CREATE; - strcpy((char *)ev.u.create.name, buf); - ev.u.create.rd_data = rdesc; - ev.u.create.rd_size = sizeof(rdesc); - ev.u.create.bus = BUS_USB; - ev.u.create.vendor = 0x0001; - ev.u.create.product = 0x0a37; - ev.u.create.version = 0; - ev.u.create.country = 0; - - sprintf(buf, "%d", rand_nb); - strcpy((char *)ev.u.create.phys, buf); - - return uhid_write(_metadata, fd, &ev); -} - -static void uhid_destroy(struct __test_metadata *_metadata, int fd) -{ - struct uhid_event ev; - - memset(&ev, 0, sizeof(ev)); - ev.type = UHID_DESTROY; - - uhid_write(_metadata, fd, &ev); -} - -static int uhid_event(struct __test_metadata *_metadata, int fd) -{ - struct uhid_event ev, answer; - ssize_t ret; - - memset(&ev, 0, sizeof(ev)); - ret = read(fd, &ev, sizeof(ev)); - if (ret == 0) { - UHID_LOG("Read HUP on uhid-cdev"); - return -EFAULT; - } else if (ret < 0) { - UHID_LOG("Cannot read uhid-cdev: %m"); - return -errno; - } else if (ret != sizeof(ev)) { - UHID_LOG("Invalid size read from uhid-dev: %zd != %zu", - ret, sizeof(ev)); - return -EFAULT; - } - - switch (ev.type) { - case UHID_START: - pthread_mutex_lock(&uhid_started_mtx); - pthread_cond_signal(&uhid_started); - pthread_mutex_unlock(&uhid_started_mtx); - - UHID_LOG("UHID_START from uhid-dev"); - break; - case UHID_STOP: - uhid_stopped = true; - - UHID_LOG("UHID_STOP from uhid-dev"); - break; - case UHID_OPEN: - UHID_LOG("UHID_OPEN from uhid-dev"); - break; - case UHID_CLOSE: - UHID_LOG("UHID_CLOSE from uhid-dev"); - break; - case UHID_OUTPUT: - UHID_LOG("UHID_OUTPUT from uhid-dev"); - - pthread_mutex_lock(&uhid_output_mtx); - memcpy(output_report, - ev.u.output.data, - min(ev.u.output.size, sizeof(output_report))); - pthread_cond_signal(&uhid_output_cond); - pthread_mutex_unlock(&uhid_output_mtx); - break; - case UHID_GET_REPORT: - UHID_LOG("UHID_GET_REPORT from uhid-dev"); - - answer.type = UHID_GET_REPORT_REPLY; - answer.u.get_report_reply.id = ev.u.get_report.id; - answer.u.get_report_reply.err = ev.u.get_report.rnum == 1 ? 0 : -EIO; - answer.u.get_report_reply.size = sizeof(feature_data); - memcpy(answer.u.get_report_reply.data, feature_data, sizeof(feature_data)); - - uhid_write(_metadata, fd, &answer); - - break; - case UHID_SET_REPORT: - UHID_LOG("UHID_SET_REPORT from uhid-dev"); - break; - default: - TH_LOG("Invalid event from uhid-dev: %u", ev.type); - } - - return 0; -} - -struct uhid_thread_args { - int fd; - struct __test_metadata *_metadata; -}; -static void *uhid_read_events_thread(void *arg) -{ - struct uhid_thread_args *args = (struct uhid_thread_args *)arg; - struct __test_metadata *_metadata = args->_metadata; - struct pollfd pfds[1]; - int fd = args->fd; - int ret = 0; - - pfds[0].fd = fd; - pfds[0].events = POLLIN; - - uhid_stopped = false; - - while (!uhid_stopped) { - ret = poll(pfds, 1, 100); - if (ret < 0) { - TH_LOG("Cannot poll for fds: %m"); - break; - } - if (pfds[0].revents & POLLIN) { - ret = uhid_event(_metadata, fd); - if (ret) - break; - } - } - - return (void *)(long)ret; -} - -static int uhid_start_listener(struct __test_metadata *_metadata, pthread_t *tid, int uhid_fd) -{ - struct uhid_thread_args args = { - .fd = uhid_fd, - ._metadata = _metadata, - }; - int err; - - pthread_mutex_lock(&uhid_started_mtx); - err = pthread_create(tid, NULL, uhid_read_events_thread, (void *)&args); - ASSERT_EQ(0, err) { - TH_LOG("Could not start the uhid thread: %d", err); - pthread_mutex_unlock(&uhid_started_mtx); - close(uhid_fd); - return -EIO; - } - pthread_cond_wait(&uhid_started, &uhid_started_mtx); - pthread_mutex_unlock(&uhid_started_mtx); - - return 0; -} - -static int uhid_send_event(struct __test_metadata *_metadata, int fd, __u8 *buf, size_t size) -{ - struct uhid_event ev; - - if (size > sizeof(ev.u.input.data)) - return -E2BIG; - - memset(&ev, 0, sizeof(ev)); - ev.type = UHID_INPUT2; - ev.u.input2.size = size; - - memcpy(ev.u.input2.data, buf, size); - - return uhid_write(_metadata, fd, &ev); -} - -static int setup_uhid(struct __test_metadata *_metadata, int rand_nb) -{ - int fd; - const char *path = "/dev/uhid"; - int ret; - - fd = open(path, O_RDWR | O_CLOEXEC); - ASSERT_GE(fd, 0) TH_LOG("open uhid-cdev failed; %d", fd); - - ret = uhid_create(_metadata, fd, rand_nb); - ASSERT_EQ(0, ret) { - TH_LOG("create uhid device failed: %d", ret); - close(fd); - } - - return fd; -} - -static bool match_sysfs_device(int dev_id, const char *workdir, struct dirent *dir) -{ - const char *target = "0003:0001:0A37.*"; - char phys[512]; - char uevent[1024]; - char temp[512]; - int fd, nread; - bool found = false; - - if (fnmatch(target, dir->d_name, 0)) - return false; - - /* we found the correct VID/PID, now check for phys */ - sprintf(uevent, "%s/%s/uevent", workdir, dir->d_name); - - fd = open(uevent, O_RDONLY | O_NONBLOCK); - if (fd < 0) - return false; - - sprintf(phys, "PHYS=%d", dev_id); - - nread = read(fd, temp, ARRAY_SIZE(temp)); - if (nread > 0 && (strstr(temp, phys)) != NULL) - found = true; - - close(fd); - - return found; -} - -static int get_hid_id(int dev_id) -{ - const char *workdir = "/sys/devices/virtual/misc/uhid"; - const char *str_id; - DIR *d; - struct dirent *dir; - int found = -1, attempts = 3; - - /* it would be nice to be able to use nftw, but the no_alu32 target doesn't support it */ - - while (found < 0 && attempts > 0) { - attempts--; - d = opendir(workdir); - if (d) { - while ((dir = readdir(d)) != NULL) { - if (!match_sysfs_device(dev_id, workdir, dir)) - continue; - - str_id = dir->d_name + sizeof("0003:0001:0A37."); - found = (int)strtol(str_id, NULL, 16); - - break; - } - closedir(d); - } - if (found < 0) - usleep(100000); - } - - return found; -} - -static int get_hidraw(int dev_id) -{ - const char *workdir = "/sys/devices/virtual/misc/uhid"; - char sysfs[1024]; - DIR *d, *subd; - struct dirent *dir, *subdir; - int i, found = -1; - - /* retry 5 times in case the system is loaded */ - for (i = 5; i > 0; i--) { - usleep(10); - d = opendir(workdir); - - if (!d) - continue; - - while ((dir = readdir(d)) != NULL) { - if (!match_sysfs_device(dev_id, workdir, dir)) - continue; - - sprintf(sysfs, "%s/%s/hidraw", workdir, dir->d_name); - - subd = opendir(sysfs); - if (!subd) - continue; - - while ((subdir = readdir(subd)) != NULL) { - if (fnmatch("hidraw*", subdir->d_name, 0)) - continue; - - found = atoi(subdir->d_name + strlen("hidraw")); - } - - closedir(subd); - - if (found > 0) - break; - } - closedir(d); - } - - return found; -} - -static int open_hidraw(int dev_id) -{ - int hidraw_number; - char hidraw_path[64] = { 0 }; - - hidraw_number = get_hidraw(dev_id); - if (hidraw_number < 0) - return hidraw_number; - - /* open hidraw node to check the other side of the pipe */ - sprintf(hidraw_path, "/dev/hidraw%d", hidraw_number); - return open(hidraw_path, O_RDWR | O_NONBLOCK); -} - FIXTURE(hid_bpf) { int dev_id; int uhid_fd; @@ -1357,12 +924,6 @@ static int libbpf_print_fn(enum libbpf_print_level level, return 0; } -static void __attribute__((constructor)) __constructor_order_last(void) -{ - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; -} - int main(int argc, char **argv) { /* Use libbpf 1.0 API mode */ diff --git a/tools/testing/selftests/hid/hid_common.h b/tools/testing/selftests/hid/hid_common.h new file mode 100644 index 000000000000..f151f151a1ed --- /dev/null +++ b/tools/testing/selftests/hid/hid_common.h @@ -0,0 +1,436 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2022-2024 Red Hat */ + +#include "../kselftest_harness.h" + +#include <fcntl.h> +#include <fnmatch.h> +#include <dirent.h> +#include <poll.h> +#include <pthread.h> +#include <stdbool.h> +#include <linux/hidraw.h> +#include <linux/uhid.h> + +#define SHOW_UHID_DEBUG 0 + +#define min(a, b) \ + ({ __typeof__(a) _a = (a); \ + __typeof__(b) _b = (b); \ + _a < _b ? _a : _b; }) + +static unsigned char rdesc[] = { + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x09, 0x21, /* Usage (Vendor Usage 0x21) */ + 0xa1, 0x01, /* COLLECTION (Application) */ + 0x09, 0x01, /* Usage (Vendor Usage 0x01) */ + 0xa1, 0x00, /* COLLECTION (Physical) */ + 0x85, 0x02, /* REPORT_ID (2) */ + 0x19, 0x01, /* USAGE_MINIMUM (1) */ + 0x29, 0x08, /* USAGE_MAXIMUM (3) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0xff, /* LOGICAL_MAXIMUM (255) */ + 0x95, 0x08, /* REPORT_COUNT (8) */ + 0x75, 0x08, /* REPORT_SIZE (8) */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ + 0xc0, /* END_COLLECTION */ + 0x09, 0x01, /* Usage (Vendor Usage 0x01) */ + 0xa1, 0x00, /* COLLECTION (Physical) */ + 0x85, 0x01, /* REPORT_ID (1) */ + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x01, /* USAGE_MINIMUM (1) */ + 0x29, 0x03, /* USAGE_MAXIMUM (3) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x81, 0x01, /* INPUT (Cnst,Var,Abs) */ + 0x05, 0x01, /* USAGE_PAGE (Generic Desktop) */ + 0x09, 0x30, /* USAGE (X) */ + 0x09, 0x31, /* USAGE (Y) */ + 0x15, 0x81, /* LOGICAL_MINIMUM (-127) */ + 0x25, 0x7f, /* LOGICAL_MAXIMUM (127) */ + 0x75, 0x10, /* REPORT_SIZE (16) */ + 0x95, 0x02, /* REPORT_COUNT (2) */ + 0x81, 0x06, /* INPUT (Data,Var,Rel) */ + + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x01, /* USAGE_MINIMUM (1) */ + 0x29, 0x03, /* USAGE_MAXIMUM (3) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0x91, 0x02, /* Output (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x91, 0x01, /* Output (Cnst,Var,Abs) */ + + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x06, /* USAGE_MINIMUM (6) */ + 0x29, 0x08, /* USAGE_MAXIMUM (8) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0xb1, 0x02, /* Feature (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x91, 0x01, /* Output (Cnst,Var,Abs) */ + + 0xc0, /* END_COLLECTION */ + 0xc0, /* END_COLLECTION */ +}; + +static __u8 feature_data[] = { 1, 2 }; + +#define ASSERT_OK(data) ASSERT_FALSE(data) +#define ASSERT_OK_PTR(ptr) ASSERT_NE(NULL, ptr) + +#define UHID_LOG(fmt, ...) do { \ + if (SHOW_UHID_DEBUG) \ + TH_LOG(fmt, ##__VA_ARGS__); \ +} while (0) + +static pthread_mutex_t uhid_started_mtx = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t uhid_started = PTHREAD_COND_INITIALIZER; + +static pthread_mutex_t uhid_output_mtx = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t uhid_output_cond = PTHREAD_COND_INITIALIZER; +static unsigned char output_report[10]; + +/* no need to protect uhid_stopped, only one thread accesses it */ +static bool uhid_stopped; + +static int uhid_write(struct __test_metadata *_metadata, int fd, const struct uhid_event *ev) +{ + ssize_t ret; + + ret = write(fd, ev, sizeof(*ev)); + if (ret < 0) { + TH_LOG("Cannot write to uhid: %m"); + return -errno; + } else if (ret != sizeof(*ev)) { + TH_LOG("Wrong size written to uhid: %zd != %zu", + ret, sizeof(ev)); + return -EFAULT; + } else { + return 0; + } +} + +static int uhid_create(struct __test_metadata *_metadata, int fd, int rand_nb) +{ + struct uhid_event ev; + char buf[25]; + + sprintf(buf, "test-uhid-device-%d", rand_nb); + + memset(&ev, 0, sizeof(ev)); + ev.type = UHID_CREATE; + strcpy((char *)ev.u.create.name, buf); + ev.u.create.rd_data = rdesc; + ev.u.create.rd_size = sizeof(rdesc); + ev.u.create.bus = BUS_USB; + ev.u.create.vendor = 0x0001; + ev.u.create.product = 0x0a37; + ev.u.create.version = 0; + ev.u.create.country = 0; + + sprintf(buf, "%d", rand_nb); + strcpy((char *)ev.u.create.phys, buf); + + return uhid_write(_metadata, fd, &ev); +} + +static void uhid_destroy(struct __test_metadata *_metadata, int fd) +{ + struct uhid_event ev; + + memset(&ev, 0, sizeof(ev)); + ev.type = UHID_DESTROY; + + uhid_write(_metadata, fd, &ev); +} + +static int uhid_event(struct __test_metadata *_metadata, int fd) +{ + struct uhid_event ev, answer; + ssize_t ret; + + memset(&ev, 0, sizeof(ev)); + ret = read(fd, &ev, sizeof(ev)); + if (ret == 0) { + UHID_LOG("Read HUP on uhid-cdev"); + return -EFAULT; + } else if (ret < 0) { + UHID_LOG("Cannot read uhid-cdev: %m"); + return -errno; + } else if (ret != sizeof(ev)) { + UHID_LOG("Invalid size read from uhid-dev: %zd != %zu", + ret, sizeof(ev)); + return -EFAULT; + } + + switch (ev.type) { + case UHID_START: + pthread_mutex_lock(&uhid_started_mtx); + pthread_cond_signal(&uhid_started); + pthread_mutex_unlock(&uhid_started_mtx); + + UHID_LOG("UHID_START from uhid-dev"); + break; + case UHID_STOP: + uhid_stopped = true; + + UHID_LOG("UHID_STOP from uhid-dev"); + break; + case UHID_OPEN: + UHID_LOG("UHID_OPEN from uhid-dev"); + break; + case UHID_CLOSE: + UHID_LOG("UHID_CLOSE from uhid-dev"); + break; + case UHID_OUTPUT: + UHID_LOG("UHID_OUTPUT from uhid-dev"); + + pthread_mutex_lock(&uhid_output_mtx); + memcpy(output_report, + ev.u.output.data, + min(ev.u.output.size, sizeof(output_report))); + pthread_cond_signal(&uhid_output_cond); + pthread_mutex_unlock(&uhid_output_mtx); + break; + case UHID_GET_REPORT: + UHID_LOG("UHID_GET_REPORT from uhid-dev"); + + answer.type = UHID_GET_REPORT_REPLY; + answer.u.get_report_reply.id = ev.u.get_report.id; + answer.u.get_report_reply.err = ev.u.get_report.rnum == 1 ? 0 : -EIO; + answer.u.get_report_reply.size = sizeof(feature_data); + memcpy(answer.u.get_report_reply.data, feature_data, sizeof(feature_data)); + + uhid_write(_metadata, fd, &answer); + + break; + case UHID_SET_REPORT: + UHID_LOG("UHID_SET_REPORT from uhid-dev"); + break; + default: + TH_LOG("Invalid event from uhid-dev: %u", ev.type); + } + + return 0; +} + +struct uhid_thread_args { + int fd; + struct __test_metadata *_metadata; +}; +static void *uhid_read_events_thread(void *arg) +{ + struct uhid_thread_args *args = (struct uhid_thread_args *)arg; + struct __test_metadata *_metadata = args->_metadata; + struct pollfd pfds[1]; + int fd = args->fd; + int ret = 0; + + pfds[0].fd = fd; + pfds[0].events = POLLIN; + + uhid_stopped = false; + + while (!uhid_stopped) { + ret = poll(pfds, 1, 100); + if (ret < 0) { + TH_LOG("Cannot poll for fds: %m"); + break; + } + if (pfds[0].revents & POLLIN) { + ret = uhid_event(_metadata, fd); + if (ret) + break; + } + } + + return (void *)(long)ret; +} + +static int uhid_start_listener(struct __test_metadata *_metadata, pthread_t *tid, int uhid_fd) +{ + struct uhid_thread_args args = { + .fd = uhid_fd, + ._metadata = _metadata, + }; + int err; + + pthread_mutex_lock(&uhid_started_mtx); + err = pthread_create(tid, NULL, uhid_read_events_thread, (void *)&args); + ASSERT_EQ(0, err) { + TH_LOG("Could not start the uhid thread: %d", err); + pthread_mutex_unlock(&uhid_started_mtx); + close(uhid_fd); + return -EIO; + } + pthread_cond_wait(&uhid_started, &uhid_started_mtx); + pthread_mutex_unlock(&uhid_started_mtx); + + return 0; +} + +static int uhid_send_event(struct __test_metadata *_metadata, int fd, __u8 *buf, size_t size) +{ + struct uhid_event ev; + + if (size > sizeof(ev.u.input.data)) + return -E2BIG; + + memset(&ev, 0, sizeof(ev)); + ev.type = UHID_INPUT2; + ev.u.input2.size = size; + + memcpy(ev.u.input2.data, buf, size); + + return uhid_write(_metadata, fd, &ev); +} + +static int setup_uhid(struct __test_metadata *_metadata, int rand_nb) +{ + int fd; + const char *path = "/dev/uhid"; + int ret; + + fd = open(path, O_RDWR | O_CLOEXEC); + ASSERT_GE(fd, 0) TH_LOG("open uhid-cdev failed; %d", fd); + + ret = uhid_create(_metadata, fd, rand_nb); + ASSERT_EQ(0, ret) { + TH_LOG("create uhid device failed: %d", ret); + close(fd); + } + + return fd; +} + +static bool match_sysfs_device(int dev_id, const char *workdir, struct dirent *dir) +{ + const char *target = "0003:0001:0A37.*"; + char phys[512]; + char uevent[1024]; + char temp[512]; + int fd, nread; + bool found = false; + + if (fnmatch(target, dir->d_name, 0)) + return false; + + /* we found the correct VID/PID, now check for phys */ + sprintf(uevent, "%s/%s/uevent", workdir, dir->d_name); + + fd = open(uevent, O_RDONLY | O_NONBLOCK); + if (fd < 0) + return false; + + sprintf(phys, "PHYS=%d", dev_id); + + nread = read(fd, temp, ARRAY_SIZE(temp)); + if (nread > 0 && (strstr(temp, phys)) != NULL) + found = true; + + close(fd); + + return found; +} + +static int get_hid_id(int dev_id) +{ + const char *workdir = "/sys/devices/virtual/misc/uhid"; + const char *str_id; + DIR *d; + struct dirent *dir; + int found = -1, attempts = 3; + + /* it would be nice to be able to use nftw, but the no_alu32 target doesn't support it */ + + while (found < 0 && attempts > 0) { + attempts--; + d = opendir(workdir); + if (d) { + while ((dir = readdir(d)) != NULL) { + if (!match_sysfs_device(dev_id, workdir, dir)) + continue; + + str_id = dir->d_name + sizeof("0003:0001:0A37."); + found = (int)strtol(str_id, NULL, 16); + + break; + } + closedir(d); + } + if (found < 0) + usleep(100000); + } + + return found; +} + +static int get_hidraw(int dev_id) +{ + const char *workdir = "/sys/devices/virtual/misc/uhid"; + char sysfs[1024]; + DIR *d, *subd; + struct dirent *dir, *subdir; + int i, found = -1; + + /* retry 5 times in case the system is loaded */ + for (i = 5; i > 0; i--) { + usleep(10); + d = opendir(workdir); + + if (!d) + continue; + + while ((dir = readdir(d)) != NULL) { + if (!match_sysfs_device(dev_id, workdir, dir)) + continue; + + sprintf(sysfs, "%s/%s/hidraw", workdir, dir->d_name); + + subd = opendir(sysfs); + if (!subd) + continue; + + while ((subdir = readdir(subd)) != NULL) { + if (fnmatch("hidraw*", subdir->d_name, 0)) + continue; + + found = atoi(subdir->d_name + strlen("hidraw")); + } + + closedir(subd); + + if (found > 0) + break; + } + closedir(d); + } + + return found; +} + +static int open_hidraw(int dev_id) +{ + int hidraw_number; + char hidraw_path[64] = { 0 }; + + hidraw_number = get_hidraw(dev_id); + if (hidraw_number < 0) + return hidraw_number; + + /* open hidraw node to check the other side of the pipe */ + sprintf(hidraw_path, "/dev/hidraw%d", hidraw_number); + return open(hidraw_path, O_RDWR | O_NONBLOCK); +} diff --git a/tools/testing/selftests/hid/hidraw.c b/tools/testing/selftests/hid/hidraw.c new file mode 100644 index 000000000000..f8b4f7ff292c --- /dev/null +++ b/tools/testing/selftests/hid/hidraw.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022-2024 Red Hat */ + +#include "hid_common.h" + +/* for older kernels */ +#ifndef HIDIOCREVOKE +#define HIDIOCREVOKE _IOW('H', 0x0D, int) /* Revoke device access */ +#endif /* HIDIOCREVOKE */ + +FIXTURE(hidraw) { + int dev_id; + int uhid_fd; + int hidraw_fd; + int hid_id; + pthread_t tid; +}; +static void close_hidraw(FIXTURE_DATA(hidraw) * self) +{ + if (self->hidraw_fd) + close(self->hidraw_fd); + self->hidraw_fd = 0; +} + +FIXTURE_TEARDOWN(hidraw) { + void *uhid_err; + + uhid_destroy(_metadata, self->uhid_fd); + + close_hidraw(self); + pthread_join(self->tid, &uhid_err); +} +#define TEARDOWN_LOG(fmt, ...) do { \ + TH_LOG(fmt, ##__VA_ARGS__); \ + hidraw_teardown(_metadata, self, variant); \ +} while (0) + +FIXTURE_SETUP(hidraw) +{ + time_t t; + int err; + + /* initialize random number generator */ + srand((unsigned int)time(&t)); + + self->dev_id = rand() % 1024; + + self->uhid_fd = setup_uhid(_metadata, self->dev_id); + + /* locate the uev, self, variant);ent file of the created device */ + self->hid_id = get_hid_id(self->dev_id); + ASSERT_GT(self->hid_id, 0) + TEARDOWN_LOG("Could not locate uhid device id: %d", self->hid_id); + + err = uhid_start_listener(_metadata, &self->tid, self->uhid_fd); + ASSERT_EQ(0, err) TEARDOWN_LOG("could not start udev listener: %d", err); + + self->hidraw_fd = open_hidraw(self->dev_id); + ASSERT_GE(self->hidraw_fd, 0) TH_LOG("open_hidraw"); +} + +/* + * A simple test to see if the fixture is working fine. + * If this fails, none of the other tests will pass. + */ +TEST_F(hidraw, test_create_uhid) +{ +} + +/* + * Inject one event in the uhid device, + * check that we get the same data through hidraw + */ +TEST_F(hidraw, raw_event) +{ + __u8 buf[10] = {0}; + int err; + + /* inject one event */ + buf[0] = 1; + buf[1] = 42; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[0], 1); + ASSERT_EQ(buf[1], 42); +} + +/* + * After initial opening/checks of hidraw, revoke the hidraw + * node and check that we can not read any more data. + */ +TEST_F(hidraw, raw_event_revoked) +{ + __u8 buf[10] = {0}; + int err; + + /* inject one event */ + buf[0] = 1; + buf[1] = 42; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[0], 1); + ASSERT_EQ(buf[1], 42); + + /* call the revoke ioctl */ + err = ioctl(self->hidraw_fd, HIDIOCREVOKE, NULL); + ASSERT_OK(err) TH_LOG("couldn't revoke the hidraw fd"); + + /* inject one other event */ + buf[0] = 1; + buf[1] = 43; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, -1) TH_LOG("read_hidraw"); + ASSERT_EQ(errno, ENODEV) TH_LOG("unexpected error code while reading the hidraw node: %d", + errno); +} + +/* + * Revoke the hidraw node and check that we can not do any ioctl. + */ +TEST_F(hidraw, ioctl_revoked) +{ + int err, desc_size = 0; + + /* call the revoke ioctl */ + err = ioctl(self->hidraw_fd, HIDIOCREVOKE, NULL); + ASSERT_OK(err) TH_LOG("couldn't revoke the hidraw fd"); + + /* do an ioctl */ + err = ioctl(self->hidraw_fd, HIDIOCGRDESCSIZE, &desc_size); + ASSERT_EQ(err, -1) TH_LOG("ioctl_hidraw"); + ASSERT_EQ(errno, ENODEV) TH_LOG("unexpected error code while doing an ioctl: %d", + errno); +} + +/* + * Setup polling of the fd, and check that revoke works properly. + */ +TEST_F(hidraw, poll_revoked) +{ + struct pollfd pfds[1]; + __u8 buf[10] = {0}; + int err, ready; + + /* setup polling */ + pfds[0].fd = self->hidraw_fd; + pfds[0].events = POLLIN; + + /* inject one event */ + buf[0] = 1; + buf[1] = 42; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + while (true) { + ready = poll(pfds, 1, 5000); + ASSERT_EQ(ready, 1) TH_LOG("poll return value"); + + if (pfds[0].revents & POLLIN) { + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[0], 1); + ASSERT_EQ(buf[1], 42); + + /* call the revoke ioctl */ + err = ioctl(self->hidraw_fd, HIDIOCREVOKE, NULL); + ASSERT_OK(err) TH_LOG("couldn't revoke the hidraw fd"); + } else { + break; + } + } + + ASSERT_TRUE(pfds[0].revents & POLLHUP); +} + +/* + * After initial opening/checks of hidraw, revoke the hidraw + * node and check that we can not read any more data. + */ +TEST_F(hidraw, write_event_revoked) +{ + struct timespec time_to_wait; + __u8 buf[10] = {0}; + int err; + + /* inject one event from hidraw */ + buf[0] = 1; /* report ID */ + buf[1] = 2; + buf[2] = 42; + + pthread_mutex_lock(&uhid_output_mtx); + + memset(output_report, 0, sizeof(output_report)); + clock_gettime(CLOCK_REALTIME, &time_to_wait); + time_to_wait.tv_sec += 2; + + err = write(self->hidraw_fd, buf, 3); + ASSERT_EQ(err, 3) TH_LOG("unexpected error while writing to hidraw node: %d", err); + + err = pthread_cond_timedwait(&uhid_output_cond, &uhid_output_mtx, &time_to_wait); + ASSERT_OK(err) TH_LOG("error while calling waiting for the condition"); + + ASSERT_EQ(output_report[0], 1); + ASSERT_EQ(output_report[1], 2); + ASSERT_EQ(output_report[2], 42); + + /* call the revoke ioctl */ + err = ioctl(self->hidraw_fd, HIDIOCREVOKE, NULL); + ASSERT_OK(err) TH_LOG("couldn't revoke the hidraw fd"); + + /* inject one other event */ + buf[0] = 1; + buf[1] = 43; + err = write(self->hidraw_fd, buf, 3); + ASSERT_LT(err, 0) TH_LOG("unexpected success while writing to hidraw node: %d", err); + ASSERT_EQ(errno, ENODEV) TH_LOG("unexpected error code while writing to hidraw node: %d", + errno); + + pthread_mutex_unlock(&uhid_output_mtx); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index b8967b6e29d5..29fedf609611 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -61,6 +61,7 @@ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #endif +#if defined(__i386__) || defined(__x86_64__) /* arch */ /* * gcc cpuid.h provides __cpuid_count() since v4.4. * Clang/LLVM cpuid.h provides __cpuid_count() since v3.4.0. @@ -75,6 +76,7 @@ : "=a" (a), "=b" (b), "=c" (c), "=d" (d) \ : "0" (level), "2" (count)) #endif +#endif /* end arch */ /* define kselftest exit codes */ #define KSFT_PASS 0 @@ -371,15 +373,7 @@ static inline __noreturn __printf(1, 2) void ksft_exit_fail_msg(const char *msg, static inline __noreturn void ksft_exit_fail_perror(const char *msg) { -#ifndef NOLIBC ksft_exit_fail_msg("%s: %s (%d)\n", msg, strerror(errno), errno); -#else - /* - * nolibc doesn't provide strerror() and it seems - * inappropriate to add one, just print the errno. - */ - ksft_exit_fail_msg("%s: %d)\n", msg, errno); -#endif } static inline __noreturn void ksft_exit_xfail(void) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 40723a6a083f..a5a72415e37b 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -488,12 +488,6 @@ * Use once to append a main() to the test file. */ #define TEST_HARNESS_MAIN \ - static void __attribute__((constructor)) \ - __constructor_order_last(void) \ - { \ - if (!__constructor_order) \ - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; \ - } \ int main(int argc, char **argv) { \ return test_harness_run(argc, argv); \ } @@ -824,7 +818,7 @@ item->prev = item; \ return; \ } \ - if (__constructor_order == _CONSTRUCTOR_ORDER_FORWARD) { \ + if (__constructor_order_forward) { \ item->next = NULL; \ item->prev = head->prev; \ item->prev->next = item; \ @@ -888,10 +882,7 @@ struct __test_xfail { } static struct __fixture_metadata *__fixture_list = &_fixture_global; -static int __constructor_order; - -#define _CONSTRUCTOR_ORDER_FORWARD 1 -#define _CONSTRUCTOR_ORDER_BACKWARD -1 +static bool __constructor_order_forward; static inline void __register_fixture(struct __fixture_metadata *f) { @@ -942,7 +933,7 @@ static inline bool __test_passed(struct __test_metadata *metadata) * list so tests are run in source declaration order. * https://gcc.gnu.org/onlinedocs/gccint/Initialization.html * However, it seems not all toolchains do this correctly, so use - * __constructor_order to detect which direction is called first + * __constructor_order_foward to detect which direction is called first * and adjust list building logic to get things running in the right * direction. */ @@ -1337,8 +1328,7 @@ static int test_harness_run(int argc, char **argv) static void __attribute__((constructor)) __constructor_order_first(void) { - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_FORWARD; + __constructor_order_forward = true; } #endif /* __KSELFTEST_HARNESS_H */ diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile index ee71fc99d5b5..c52fe3ad8e98 100644 --- a/tools/testing/selftests/lib/Makefile +++ b/tools/testing/selftests/lib/Makefile @@ -4,6 +4,5 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh scanf.sh strscpy.sh - +TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh scanf.sh include ../lib.mk diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config index 645839b50b0a..dc15aba8d0a3 100644 --- a/tools/testing/selftests/lib/config +++ b/tools/testing/selftests/lib/config @@ -2,5 +2,4 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_PRIME_NUMBERS=m -CONFIG_TEST_STRSCPY=m CONFIG_TEST_BITOPS=m diff --git a/tools/testing/selftests/lib/strscpy.sh b/tools/testing/selftests/lib/strscpy.sh deleted file mode 100755 index be60ef6e1a7f..000000000000 --- a/tools/testing/selftests/lib/strscpy.sh +++ /dev/null @@ -1,3 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0+ -$(dirname $0)/../kselftest/module.sh "strscpy*" test_strscpy diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 5f2ca591c956..e10b87376fde 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -90,6 +90,7 @@ CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_pr CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) VMTARGETS := protection_keys +VMTARGETS += pkey_sighandler_tests BINARIES_32 := $(VMTARGETS:%=%_32) BINARIES_64 := $(VMTARGETS:%=%_64) diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index 15608350fc01..9ab6a3ee153b 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -79,7 +79,18 @@ extern void abort_hooks(void); } \ } while (0) -__attribute__((noinline)) int read_ptr(int *ptr); +#define barrier() __asm__ __volatile__("": : :"memory") +#ifndef noinline +# define noinline __attribute__((noinline)) +#endif + +noinline int read_ptr(int *ptr) +{ + /* Keep GCC from optimizing this away somehow */ + barrier(); + return *ptr; +} + void expected_pkey_fault(int pkey); int sys_pkey_alloc(unsigned long flags, unsigned long init_val); int sys_pkey_free(unsigned long pkey); diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c new file mode 100644 index 000000000000..a8088b645ad6 --- /dev/null +++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tests Memory Protection Keys (see Documentation/core-api/protection-keys.rst) + * + * The testcases in this file exercise various flows related to signal handling, + * using an alternate signal stack, with the default pkey (pkey 0) disabled. + * + * Compile with: + * gcc -mxsave -o pkey_sighandler_tests -O2 -g -std=gnu99 -pthread -Wall pkey_sighandler_tests.c -I../../../../tools/include -lrt -ldl -lm + * gcc -mxsave -m32 -o pkey_sighandler_tests -O2 -g -std=gnu99 -pthread -Wall pkey_sighandler_tests.c -I../../../../tools/include -lrt -ldl -lm + */ +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ +#include <errno.h> +#include <sys/syscall.h> +#include <string.h> +#include <stdio.h> +#include <stdint.h> +#include <stdbool.h> +#include <signal.h> +#include <assert.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <pthread.h> +#include <limits.h> + +#include "pkey-helpers.h" + +#define STACK_SIZE PTHREAD_STACK_MIN + +void expected_pkey_fault(int pkey) {} + +pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER; +pthread_cond_t cond = PTHREAD_COND_INITIALIZER; +siginfo_t siginfo = {0}; + +/* + * We need to use inline assembly instead of glibc's syscall because glibc's + * syscall will attempt to access the PLT in order to call a library function + * which is protected by MPK 0 which we don't have access to. + */ +static inline __always_inline +long syscall_raw(long n, long a1, long a2, long a3, long a4, long a5, long a6) +{ + unsigned long ret; +#ifdef __x86_64__ + register long r10 asm("r10") = a4; + register long r8 asm("r8") = a5; + register long r9 asm("r9") = a6; + asm volatile ("syscall" + : "=a"(ret) + : "a"(n), "D"(a1), "S"(a2), "d"(a3), "r"(r10), "r"(r8), "r"(r9) + : "rcx", "r11", "memory"); +#elif defined __i386__ + asm volatile ("int $0x80" + : "=a"(ret) + : "a"(n), "b"(a1), "c"(a2), "d"(a3), "S"(a4), "D"(a5) + : "memory"); +#else +# error syscall_raw() not implemented +#endif + return ret; +} + +static void sigsegv_handler(int signo, siginfo_t *info, void *ucontext) +{ + pthread_mutex_lock(&mutex); + + memcpy(&siginfo, info, sizeof(siginfo_t)); + + pthread_cond_signal(&cond); + pthread_mutex_unlock(&mutex); + + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); +} + +static void sigusr1_handler(int signo, siginfo_t *info, void *ucontext) +{ + pthread_mutex_lock(&mutex); + + memcpy(&siginfo, info, sizeof(siginfo_t)); + + pthread_cond_signal(&cond); + pthread_mutex_unlock(&mutex); +} + +static void sigusr2_handler(int signo, siginfo_t *info, void *ucontext) +{ + /* + * pkru should be the init_pkru value which enabled MPK 0 so + * we can use library functions. + */ + printf("%s invoked.\n", __func__); +} + +static void raise_sigusr2(void) +{ + pid_t tid = 0; + + tid = syscall_raw(SYS_gettid, 0, 0, 0, 0, 0, 0); + + syscall_raw(SYS_tkill, tid, SIGUSR2, 0, 0, 0, 0); + + /* + * We should return from the signal handler here and be able to + * return to the interrupted thread. + */ +} + +static void *thread_segv_with_pkey0_disabled(void *ptr) +{ + /* Disable MPK 0 (and all others too) */ + __write_pkey_reg(0x55555555); + + /* Segfault (with SEGV_MAPERR) */ + *(int *) (0x1) = 1; + return NULL; +} + +static void *thread_segv_pkuerr_stack(void *ptr) +{ + /* Disable MPK 0 (and all others too) */ + __write_pkey_reg(0x55555555); + + /* After we disable MPK 0, we can't access the stack to return */ + return NULL; +} + +static void *thread_segv_maperr_ptr(void *ptr) +{ + stack_t *stack = ptr; + int *bad = (int *)1; + + /* + * Setup alternate signal stack, which should be pkey_mprotect()ed by + * MPK 0. The thread's stack cannot be used for signals because it is + * not accessible by the default init_pkru value of 0x55555554. + */ + syscall_raw(SYS_sigaltstack, (long)stack, 0, 0, 0, 0, 0); + + /* Disable MPK 0. Only MPK 1 is enabled. */ + __write_pkey_reg(0x55555551); + + /* Segfault */ + *bad = 1; + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + return NULL; +} + +/* + * Verify that the sigsegv handler is invoked when pkey 0 is disabled. + * Note that the new thread stack and the alternate signal stack is + * protected by MPK 0. + */ +static void test_sigsegv_handler_with_pkey0_disabled(void) +{ + struct sigaction sa; + pthread_attr_t attr; + pthread_t thr; + + sa.sa_flags = SA_SIGINFO; + + sa.sa_sigaction = sigsegv_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + memset(&siginfo, 0, sizeof(siginfo)); + + pthread_attr_init(&attr); + pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); + + pthread_create(&thr, &attr, thread_segv_with_pkey0_disabled, NULL); + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + ksft_test_result(siginfo.si_signo == SIGSEGV && + siginfo.si_code == SEGV_MAPERR && + siginfo.si_addr == (void *)1, + "%s\n", __func__); +} + +/* + * Verify that the sigsegv handler is invoked when pkey 0 is disabled. + * Note that the new thread stack and the alternate signal stack is + * protected by MPK 0, which renders them inaccessible when MPK 0 + * is disabled. So just the return from the thread should cause a + * segfault with SEGV_PKUERR. + */ +static void test_sigsegv_handler_cannot_access_stack(void) +{ + struct sigaction sa; + pthread_attr_t attr; + pthread_t thr; + + sa.sa_flags = SA_SIGINFO; + + sa.sa_sigaction = sigsegv_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + memset(&siginfo, 0, sizeof(siginfo)); + + pthread_attr_init(&attr); + pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); + + pthread_create(&thr, &attr, thread_segv_pkuerr_stack, NULL); + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + ksft_test_result(siginfo.si_signo == SIGSEGV && + siginfo.si_code == SEGV_PKUERR, + "%s\n", __func__); +} + +/* + * Verify that the sigsegv handler that uses an alternate signal stack + * is correctly invoked for a thread which uses a non-zero MPK to protect + * its own stack, and disables all other MPKs (including 0). + */ +static void test_sigsegv_handler_with_different_pkey_for_stack(void) +{ + struct sigaction sa; + static stack_t sigstack; + void *stack; + int pkey; + int parent_pid = 0; + int child_pid = 0; + + sa.sa_flags = SA_SIGINFO | SA_ONSTACK; + + sa.sa_sigaction = sigsegv_handler; + + sigemptyset(&sa.sa_mask); + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + stack = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + assert(stack != MAP_FAILED); + + /* Allow access to MPK 0 and MPK 1 */ + __write_pkey_reg(0x55555550); + + /* Protect the new stack with MPK 1 */ + pkey = pkey_alloc(0, 0); + pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + + /* Set up alternate signal stack that will use the default MPK */ + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + sigstack.ss_flags = 0; + sigstack.ss_size = STACK_SIZE; + + memset(&siginfo, 0, sizeof(siginfo)); + + /* Use clone to avoid newer glibcs using rseq on new threads */ + long ret = syscall_raw(SYS_clone, + CLONE_VM | CLONE_FS | CLONE_FILES | + CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | + CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | + CLONE_DETACHED, + (long) ((char *)(stack) + STACK_SIZE), + (long) &parent_pid, + (long) &child_pid, 0, 0); + + if (ret < 0) { + errno = -ret; + perror("clone"); + } else if (ret == 0) { + thread_segv_maperr_ptr(&sigstack); + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + } + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + ksft_test_result(siginfo.si_signo == SIGSEGV && + siginfo.si_code == SEGV_MAPERR && + siginfo.si_addr == (void *)1, + "%s\n", __func__); +} + +/* + * Verify that the PKRU value set by the application is correctly + * restored upon return from signal handling. + */ +static void test_pkru_preserved_after_sigusr1(void) +{ + struct sigaction sa; + unsigned long pkru = 0x45454544; + + sa.sa_flags = SA_SIGINFO; + + sa.sa_sigaction = sigusr1_handler; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + memset(&siginfo, 0, sizeof(siginfo)); + + __write_pkey_reg(pkru); + + raise(SIGUSR1); + + pthread_mutex_lock(&mutex); + while (siginfo.si_signo == 0) + pthread_cond_wait(&cond, &mutex); + pthread_mutex_unlock(&mutex); + + /* Ensure the pkru value is the same after returning from signal. */ + ksft_test_result(pkru == __read_pkey_reg() && + siginfo.si_signo == SIGUSR1, + "%s\n", __func__); +} + +static noinline void *thread_sigusr2_self(void *ptr) +{ + /* + * A const char array like "Resuming after SIGUSR2" won't be stored on + * the stack and the code could access it via an offset from the program + * counter. This makes sure it's on the function's stack frame. + */ + char str[] = {'R', 'e', 's', 'u', 'm', 'i', 'n', 'g', ' ', + 'a', 'f', 't', 'e', 'r', ' ', + 'S', 'I', 'G', 'U', 'S', 'R', '2', + '.', '.', '.', '\n', '\0'}; + stack_t *stack = ptr; + + /* + * Setup alternate signal stack, which should be pkey_mprotect()ed by + * MPK 0. The thread's stack cannot be used for signals because it is + * not accessible by the default init_pkru value of 0x55555554. + */ + syscall(SYS_sigaltstack, (long)stack, 0, 0, 0, 0, 0); + + /* Disable MPK 0. Only MPK 2 is enabled. */ + __write_pkey_reg(0x55555545); + + raise_sigusr2(); + + /* Do something, to show the thread resumed execution after the signal */ + syscall_raw(SYS_write, 1, (long) str, sizeof(str) - 1, 0, 0, 0); + + /* + * We can't return to test_pkru_sigreturn because it + * will attempt to use a %rbp value which is on the stack + * of the main thread. + */ + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + return NULL; +} + +/* + * Verify that sigreturn is able to restore altstack even if the thread had + * disabled pkey 0. + */ +static void test_pkru_sigreturn(void) +{ + struct sigaction sa = {0}; + static stack_t sigstack; + void *stack; + int pkey; + int parent_pid = 0; + int child_pid = 0; + + sa.sa_handler = SIG_DFL; + sa.sa_flags = 0; + sigemptyset(&sa.sa_mask); + + /* + * For this testcase, we do not want to handle SIGSEGV. Reset handler + * to default so that the application can crash if it receives SIGSEGV. + */ + if (sigaction(SIGSEGV, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + sa.sa_flags = SA_SIGINFO | SA_ONSTACK; + sa.sa_sigaction = sigusr2_handler; + sigemptyset(&sa.sa_mask); + + if (sigaction(SIGUSR2, &sa, NULL) == -1) { + perror("sigaction"); + exit(EXIT_FAILURE); + } + + stack = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + assert(stack != MAP_FAILED); + + /* + * Allow access to MPK 0 and MPK 2. The child thread (to be created + * later in this flow) will have its stack protected by MPK 2, whereas + * the current thread's stack is protected by the default MPK 0. Hence + * both need to be enabled. + */ + __write_pkey_reg(0x55555544); + + /* Protect the stack with MPK 2 */ + pkey = pkey_alloc(0, 0); + pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + + /* Set up alternate signal stack that will use the default MPK */ + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + sigstack.ss_flags = 0; + sigstack.ss_size = STACK_SIZE; + + /* Use clone to avoid newer glibcs using rseq on new threads */ + long ret = syscall_raw(SYS_clone, + CLONE_VM | CLONE_FS | CLONE_FILES | + CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | + CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | + CLONE_DETACHED, + (long) ((char *)(stack) + STACK_SIZE), + (long) &parent_pid, + (long) &child_pid, 0, 0); + + if (ret < 0) { + errno = -ret; + perror("clone"); + } else if (ret == 0) { + thread_sigusr2_self(&sigstack); + syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); + } + + child_pid = ret; + /* Check that thread exited */ + do { + sched_yield(); + ret = syscall_raw(SYS_tkill, child_pid, 0, 0, 0, 0, 0); + } while (ret != -ESRCH && ret != -EINVAL); + + ksft_test_result_pass("%s\n", __func__); +} + +static void (*pkey_tests[])(void) = { + test_sigsegv_handler_with_pkey0_disabled, + test_sigsegv_handler_cannot_access_stack, + test_sigsegv_handler_with_different_pkey_for_stack, + test_pkru_preserved_after_sigusr1, + test_pkru_sigreturn +}; + +int main(int argc, char *argv[]) +{ + int i; + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(pkey_tests)); + + for (i = 0; i < ARRAY_SIZE(pkey_tests); i++) + (*pkey_tests[i])(); + + ksft_finished(); + return 0; +} diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 0789981b72b9..4990f7ab4cb7 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -954,16 +954,6 @@ void close_test_fds(void) nr_test_fds = 0; } -#define barrier() __asm__ __volatile__("": : :"memory") -__attribute__((noinline)) int read_ptr(int *ptr) -{ - /* - * Keep GCC from optimizing this away somehow - */ - barrier(); - return *ptr; -} - void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) { int i, err; diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 3fbabab46958..8de98ea7af80 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -1,19 +1,21 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for nolibc tests -include ../../../scripts/Makefile.include -include ../../../scripts/utilities.mak -# We need this for the "cc-option" macro. -include ../../../build/Build.include +# we're in ".../tools/testing/selftests/nolibc" +ifeq ($(srctree),) +srctree := $(patsubst %/tools/testing/selftests/,%,$(dir $(CURDIR))) +endif + +include $(srctree)/tools/scripts/utilities.mak +# We need this for the "__cc-option" macro. +include $(srctree)/scripts/Makefile.compiler ifneq ($(O),) ifneq ($(call is-absolute,$(O)),y) $(error Only absolute O= parameters are supported) endif -endif - -# we're in ".../tools/testing/selftests/nolibc" -ifeq ($(srctree),) -srctree := $(patsubst %/tools/testing/selftests/,%,$(dir $(CURDIR))) +objtree := $(O) +else +objtree ?= $(srctree) endif ifeq ($(ARCH),) @@ -21,7 +23,7 @@ include $(srctree)/scripts/subarch.include ARCH = $(SUBARCH) endif -objtree ?= $(srctree) +cc-option = $(call __cc-option, $(CC),$(CLANG_CROSS_FLAGS),$(1),$(2)) # XARCH extends the kernel's ARCH with a few variants of the same # architecture that only differ by the configuration, the toolchain @@ -155,9 +157,22 @@ CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wex $(CFLAGS_$(XARCH)) $(CFLAGS_STACKPROTECTOR) $(CFLAGS_EXTRA) LDFLAGS := +LIBGCC := -lgcc + +ifneq ($(LLVM),) +# Not needed for clang +LIBGCC := +endif + +# Modify CFLAGS based on LLVM= +include $(srctree)/tools/scripts/Makefile.include + +# GCC uses "s390", clang "systemz" +CLANG_CROSS_FLAGS := $(subst --target=s390-linux,--target=systemz-linux,$(CLANG_CROSS_FLAGS)) + REPORT ?= awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{if (!f) printf("\n"); f++; print;} /\[SKIPPED\][\r]*$$/{s++} \ END{ printf("\n%3d test(s): %3d passed, %3d skipped, %3d failed => status: ", p+s+f, p, s, f); \ - if (f) printf("failure\n"); else if (s) printf("warning\n"); else printf("success\n");; \ + if (f || !p) printf("failure\n"); else if (s) printf("warning\n"); else printf("success\n");; \ printf("\nSee all results in %s\n", ARGV[1]); }' help: @@ -204,11 +219,11 @@ sysroot/$(ARCH)/include: ifneq ($(NOLIBC_SYSROOT),0) nolibc-test: nolibc-test.c nolibc-test-linkage.c sysroot/$(ARCH)/include $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ - -nostdlib -nostdinc -static -Isysroot/$(ARCH)/include nolibc-test.c nolibc-test-linkage.c -lgcc + -nostdlib -nostdinc -static -Isysroot/$(ARCH)/include nolibc-test.c nolibc-test-linkage.c $(LIBGCC) else nolibc-test: nolibc-test.c nolibc-test-linkage.c $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ - -nostdlib -static -include $(srctree)/tools/include/nolibc/nolibc.h nolibc-test.c nolibc-test-linkage.c -lgcc + -nostdlib -static -include $(srctree)/tools/include/nolibc/nolibc.h nolibc-test.c nolibc-test-linkage.c $(LIBGCC) endif libc-test: nolibc-test.c nolibc-test-linkage.c diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 093d0512f4c5..6fba7025c5e3 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -542,7 +542,7 @@ int expect_strzr(const char *expr, int llen) { int ret = 0; - llen += printf(" = <%s> ", expr); + llen += printf(" = <%s> ", expr ? expr : "(null)"); if (expr) { ret = 1; result(llen, FAIL); @@ -561,7 +561,7 @@ int expect_strnz(const char *expr, int llen) { int ret = 0; - llen += printf(" = <%s> ", expr); + llen += printf(" = <%s> ", expr ? expr : "(null)"); if (!expr) { ret = 1; result(llen, FAIL); @@ -686,9 +686,10 @@ static void constructor1(void) } __attribute__((constructor)) -static void constructor2(void) +static void constructor2(int argc, char **argv, char **envp) { - constructor_test_value *= 2; + if (argc && argv && envp) + constructor_test_value *= 2; } int run_startup(int min, int max) diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index 0446e6326a40..e7ecda4ae796 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -15,10 +15,11 @@ download_location="${cache_dir}/crosstools/" build_location="$(realpath "${cache_dir}"/nolibc-tests/)" perform_download=0 test_mode=system -CFLAGS_EXTRA="-Werror" +werror=1 +llvm= archs="i386 x86_64 arm64 arm mips32le mips32be ppc ppc64 ppc64le riscv s390 loongarch" -TEMP=$(getopt -o 'j:d:c:b:a:m:peh' -n "$0" -- "$@") +TEMP=$(getopt -o 'j:d:c:b:a:m:pelh' -n "$0" -- "$@") eval set -- "$TEMP" unset TEMP @@ -42,6 +43,7 @@ Options: -b [DIR] Build location (default: ${build_location}) -m [MODE] Test mode user/system (default: ${test_mode}) -e Disable -Werror + -l Build with LLVM/clang EOF } @@ -69,7 +71,10 @@ while true; do test_mode="$2" shift 2; continue ;; '-e') - CFLAGS_EXTRA="" + werror=0 + shift; continue ;; + '-l') + llvm=1 shift; continue ;; '-h') print_usage @@ -140,7 +145,10 @@ test_arch() { ct_abi=$(crosstool_abi "$1") cross_compile=$(realpath "${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}/bin/${ct_arch}-${ct_abi}-") build_dir="${build_location}/${arch}" - MAKE=(make -j"${nproc}" XARCH="${arch}" CROSS_COMPILE="${cross_compile}" O="${build_dir}") + if [ "$werror" -ne 0 ]; then + CFLAGS_EXTRA="$CFLAGS_EXTRA -Werror" + fi + MAKE=(make -j"${nproc}" XARCH="${arch}" CROSS_COMPILE="${cross_compile}" LLVM="${llvm}" O="${build_dir}") mkdir -p "$build_dir" if [ "$test_mode" = "system" ] && [ ! -f "${build_dir}/.config" ]; then diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index 1321922038d0..ca4483c238b9 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -18,4 +18,4 @@ $(OUTPUT)/context_switch: LDLIBS += -lpthread $(OUTPUT)/fork: LDLIBS += -lpthread -$(OUTPUT)/exec_target: CFLAGS += -static -nostartfiles +$(OUTPUT)/exec_target: CFLAGS += -nostartfiles diff --git a/tools/testing/selftests/powerpc/benchmarks/exec_target.c b/tools/testing/selftests/powerpc/benchmarks/exec_target.c index c14b0fc1edde..a6408d3f26cd 100644 --- a/tools/testing/selftests/powerpc/benchmarks/exec_target.c +++ b/tools/testing/selftests/powerpc/benchmarks/exec_target.c @@ -7,10 +7,22 @@ */ #define _GNU_SOURCE -#include <unistd.h> #include <sys/syscall.h> void _start(void) { - syscall(SYS_exit, 0); + asm volatile ( + "li %%r0, %[sys_exit];" + "li %%r3, 0;" + "sc;" + : + : [sys_exit] "i" (SYS_exit) + /* + * "sc" will clobber r0, r3-r13, cr0, ctr, xer and memory. + * Even though sys_exit never returns, handle clobber + * registers. + */ + : "r0", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", + "r11", "r12", "r13", "cr0", "ctr", "xer", "memory" + ); } diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index b33cd8753689..ad79784e552d 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -68,6 +68,8 @@ config_override_param "--gdb options" KcList "$TORTURE_KCONFIG_GDB_ARG" config_override_param "--kasan options" KcList "$TORTURE_KCONFIG_KASAN_ARG" config_override_param "--kcsan options" KcList "$TORTURE_KCONFIG_KCSAN_ARG" config_override_param "--kconfig argument" KcList "$TORTURE_KCONFIG_ARG" +config_override_param "$config_dir/CFcommon.$(uname -m)" KcList \ + "`cat $config_dir/CFcommon.$(uname -m) 2> /dev/null`" cp $T/KcList $resdir/ConfigFragment base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'` diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index 990d24696fd3..0447c4a00cc4 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -19,10 +19,10 @@ PATH=${RCUTORTURE}/bin:$PATH; export PATH TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" MAKE_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS*2)) -HALF_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS/2)) -if test "$HALF_ALLOTED_CPUS" -lt 1 +SCALE_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS/2)) +if test "$SCALE_ALLOTED_CPUS" -lt 1 then - HALF_ALLOTED_CPUS=1 + SCALE_ALLOTED_CPUS=1 fi VERBOSE_BATCH_CPUS=$((TORTURE_ALLOTED_CPUS/16)) if test "$VERBOSE_BATCH_CPUS" -lt 2 @@ -90,6 +90,7 @@ usage () { echo " --do-scftorture / --do-no-scftorture / --no-scftorture" echo " --do-srcu-lockdep / --do-no-srcu-lockdep / --no-srcu-lockdep" echo " --duration [ <minutes> | <hours>h | <days>d ]" + echo " --guest-cpu-limit N" echo " --kcsan-kmake-arg kernel-make-arguments" exit 1 } @@ -203,6 +204,21 @@ do duration_base=$(($ts*mult)) shift ;; + --guest-cpu-limit|--guest-cpu-lim) + checkarg --guest-cpu-limit "(number)" "$#" "$2" '^[0-9]*$' '^--' + if (("$2" <= "$TORTURE_ALLOTED_CPUS" / 2)) + then + SCALE_ALLOTED_CPUS="$2" + VERBOSE_BATCH_CPUS="$((SCALE_ALLOTED_CPUS/8))" + if (("$VERBOSE_BATCH_CPUS" < 2)) + then + VERBOSE_BATCH_CPUS=0 + fi + else + echo "Ignoring value of $2 for --guest-cpu-limit which is greater than (("$TORTURE_ALLOTED_CPUS" / 2))." + fi + shift + ;; --kcsan-kmake-arg|--kcsan-kmake-args) checkarg --kcsan-kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' kcsan_kmake_args="`echo "$kcsan_kmake_args $2" | sed -e 's/^ *//' -e 's/ *$//'`" @@ -425,9 +441,9 @@ fi if test "$do_scftorture" = "yes" then # Scale memory based on the number of CPUs. - scfmem=$((3+HALF_ALLOTED_CPUS/16)) - torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1" - torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory ${scfmem}G --trust-make + scfmem=$((3+SCALE_ALLOTED_CPUS/16)) + torture_bootargs="scftorture.nthreads=$SCALE_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1" + torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --memory ${scfmem}G --trust-make fi if test "$do_rt" = "yes" @@ -471,8 +487,8 @@ for prim in $primlist do if test -n "$firsttime" then - torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "refscale.verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make + torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$SCALE_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --bootargs "refscale.verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make mv $T/last-resdir-nodebug $T/first-resdir-nodebug || : if test -f "$T/last-resdir-kasan" then @@ -520,8 +536,8 @@ for prim in $primlist do if test -n "$firsttime" then - torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make + torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$SCALE_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --trust-make mv $T/last-resdir-nodebug $T/first-resdir-nodebug || : if test -f "$T/last-resdir-kasan" then @@ -559,7 +575,7 @@ do_kcsan="$do_kcsan_save" if test "$do_kvfree" = "yes" then torture_bootargs="rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot" - torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration $duration_rcutorture --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make + torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration $duration_rcutorture --kconfig "CONFIG_NR_CPUS=$SCALE_ALLOTED_CPUS" --memory 2G --trust-make fi if test "$do_clocksourcewd" = "yes" diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon index 0e92d85313aa..217597e84905 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon @@ -1,7 +1,5 @@ CONFIG_RCU_TORTURE_TEST=y CONFIG_PRINTK_TIME=y -CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y -CONFIG_KVM_GUEST=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.i686 b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.i686 new file mode 100644 index 000000000000..d8b2f555686f --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.i686 @@ -0,0 +1,2 @@ +CONFIG_HYPERVISOR_GUEST=y +CONFIG_KVM_GUEST=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.ppc64le b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.ppc64le new file mode 100644 index 000000000000..133da04247ee --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.ppc64le @@ -0,0 +1 @@ +CONFIG_KVM_GUEST=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.x86_64 b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.x86_64 new file mode 100644 index 000000000000..d8b2f555686f --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon.x86_64 @@ -0,0 +1,2 @@ +CONFIG_HYPERVISOR_GUEST=y +CONFIG_KVM_GUEST=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot index 979edbf4c820..55ce305b2a3d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot @@ -2,3 +2,4 @@ nohz_full=2-9 rcutorture.stall_cpu=14 rcutorture.stall_cpu_holdoff=90 rcutorture.fwd_progress=0 +rcutree.nohz_full_patience_delay=1000 diff --git a/tools/testing/selftests/rcutorture/configs/refscale/TINY b/tools/testing/selftests/rcutorture/configs/refscale/TINY new file mode 100644 index 000000000000..759343980b80 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/TINY @@ -0,0 +1,20 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n +#CHECK#CONFIG_PREEMPT_RCU=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 742782438ca3..94cfdba5308d 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -290,12 +290,12 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param static bool arch_supports_noncont_cat(const struct resctrl_test *test) { - unsigned int eax, ebx, ecx, edx; - /* AMD always supports non-contiguous CBM. */ if (get_vendor() == ARCH_AMD) return true; +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax, ebx, ecx, edx; /* Intel support for non-contiguous CBM needs to be discovered. */ if (!strcmp(test->resource, "L3")) __cpuid_count(0x10, 1, eax, ebx, ecx, edx); @@ -305,6 +305,9 @@ static bool arch_supports_noncont_cat(const struct resctrl_test *test) return false; return ((ecx >> 3) & 1); +#endif /* end arch */ + + return false; } static int noncont_cat_run_test(const struct resctrl_test *test, diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index 63ce02d1d5cc..9647b14b47c5 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -410,13 +410,6 @@ TEST_F_TIMEOUT(rtc, alarm_wkalm_set_minute, 65) { ASSERT_EQ(new, secs); } -static void __attribute__((constructor)) -__constructor_order_last(void) -{ - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; -} - int main(int argc, char **argv) { switch (argc) { diff --git a/tools/testing/selftests/rust/config b/tools/testing/selftests/rust/config index b4002acd40bc..5f942b5c8c17 100644 --- a/tools/testing/selftests/rust/config +++ b/tools/testing/selftests/rust/config @@ -1,5 +1,6 @@ +# CONFIG_GCC_PLUGINS is not set CONFIG_RUST=y CONFIG_SAMPLES=y CONFIG_SAMPLES_RUST=y CONFIG_SAMPLE_RUST_MINIMAL=m -CONFIG_SAMPLE_RUST_PRINT=m
\ No newline at end of file +CONFIG_SAMPLE_RUST_PRINT=m diff --git a/tools/testing/selftests/timers/change_skew.c b/tools/testing/selftests/timers/change_skew.c index 4421cd562c24..18e794a46c23 100644 --- a/tools/testing/selftests/timers/change_skew.c +++ b/tools/testing/selftests/timers/change_skew.c @@ -30,9 +30,6 @@ #include <time.h> #include "../kselftest.h" -#define NSEC_PER_SEC 1000000000LL - - int change_skew_test(int ppm) { struct timex tx; diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c index c8e6bffe4e0a..83450145fe65 100644 --- a/tools/testing/selftests/timers/skew_consistency.c +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -36,8 +36,6 @@ #include <sys/wait.h> #include "../kselftest.h" -#define NSEC_PER_SEC 1000000000LL - int main(int argc, char **argv) { struct timex tx; diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c index 76b38e41d9c7..d5564bbf0e50 100644 --- a/tools/testing/selftests/timers/threadtest.c +++ b/tools/testing/selftests/timers/threadtest.c @@ -38,10 +38,10 @@ struct timespec global_list[LISTSIZE]; int listcount = 0; -void checklist(struct timespec *list, int size) +void checklist(const struct timespec *list, int size) { int i, j; - struct timespec *a, *b; + const struct timespec *a, *b; /* scan the list */ for (i = 0; i < size-1; i++) { diff --git a/tools/testing/selftests/tpm2/test_async.sh b/tools/testing/selftests/tpm2/test_async.sh index 43bf5bd772fd..cf5a9c826097 100755 --- a/tools/testing/selftests/tpm2/test_async.sh +++ b/tools/testing/selftests/tpm2/test_async.sh @@ -7,4 +7,4 @@ ksft_skip=4 [ -e /dev/tpm0 ] || exit $ksft_skip [ -e /dev/tpmrm0 ] || exit $ksft_skip -python3 -m unittest -v tpm2_tests.AsyncTest +python3 -m unittest -v tpm2_tests.AsyncTest 2>&1 diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 58af963e5b55..168f4b166234 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -5,5 +5,7 @@ ksft_skip=4 [ -e /dev/tpm0 ] || exit $ksft_skip +read tpm_version < /sys/class/tpm/tpm0/tpm_version_major +[ "$tpm_version" == 2 ] || exit $ksft_skip -python3 -m unittest -v tpm2_tests.SmokeTest +python3 -m unittest -v tpm2_tests.SmokeTest 2>&1 diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index 04c47b13fe8a..93894cbc89a8 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -6,4 +6,4 @@ ksft_skip=4 [ -e /dev/tpmrm0 ] || exit $ksft_skip -python3 -m unittest -v tpm2_tests.SpaceTest +python3 -m unittest -v tpm2_tests.SpaceTest 2>&1 diff --git a/tools/testing/selftests/user/Makefile b/tools/testing/selftests/user/Makefile deleted file mode 100644 index 640a40f9b72b..000000000000 --- a/tools/testing/selftests/user/Makefile +++ /dev/null @@ -1,9 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# Makefile for user memory selftests - -# No binaries, but make sure arg-less "make" doesn't trigger "run_tests" -all: - -TEST_PROGS := test_user_copy.sh - -include ../lib.mk diff --git a/tools/testing/selftests/user/config b/tools/testing/selftests/user/config deleted file mode 100644 index 784ed8416324..000000000000 --- a/tools/testing/selftests/user/config +++ /dev/null @@ -1 +0,0 @@ -CONFIG_TEST_USER_COPY=m diff --git a/tools/testing/selftests/user/test_user_copy.sh b/tools/testing/selftests/user/test_user_copy.sh deleted file mode 100755 index f9b31a57439b..000000000000 --- a/tools/testing/selftests/user/test_user_copy.sh +++ /dev/null @@ -1,18 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# Runs copy_to/from_user infrastructure using test_user_copy kernel module - -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - -if ! /sbin/modprobe -q -n test_user_copy; then - echo "user: module test_user_copy is not found [SKIP]" - exit $ksft_skip -fi -if /sbin/modprobe -q test_user_copy; then - /sbin/modprobe -q -r test_user_copy - echo "user_copy: ok" -else - echo "user_copy: [FAIL]" - exit 1 -fi diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 3de8e7e052ae..af9cedbf5357 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -SODIUM := $(shell pkg-config --libs libsodium 2>/dev/null) +include ../../../scripts/Makefile.arch TEST_GEN_PROGS := vdso_test_gettimeofday TEST_GEN_PROGS += vdso_test_getcpu @@ -11,14 +9,12 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) TEST_GEN_PROGS += vdso_standalone_test_x86 endif TEST_GEN_PROGS += vdso_test_correctness -ifeq ($(uname_M),x86_64) +ifeq ($(ARCH)$(CONFIG_X86_32),$(filter $(ARCH)$(CONFIG_X86_32),x86 x86_64 loongarch arm64 powerpc s390)) TEST_GEN_PROGS += vdso_test_getrandom -ifneq ($(SODIUM),) TEST_GEN_PROGS += vdso_test_chacha endif -endif -CFLAGS := -std=gnu99 +CFLAGS := -std=gnu99 -O2 ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s @@ -38,11 +34,12 @@ $(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl $(OUTPUT)/vdso_test_getrandom: parse_vdso.c $(OUTPUT)/vdso_test_getrandom: CFLAGS += -isystem $(top_srcdir)/tools/include \ + $(KHDR_INCLUDES) \ -isystem $(top_srcdir)/include/uapi -$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/arch/$(ARCH)/entry/vdso/vgetrandom-chacha.S +$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/tools/arch/$(SRCARCH)/vdso/vgetrandom-chacha.S $(OUTPUT)/vdso_test_chacha: CFLAGS += -idirafter $(top_srcdir)/tools/include \ - -isystem $(top_srcdir)/arch/$(ARCH)/include \ - -isystem $(top_srcdir)/include \ - -D__ASSEMBLY__ -DBULID_VDSO -DCONFIG_FUNCTION_ALIGNMENT=0 \ - -Wa,--noexecstack $(SODIUM) + -idirafter $(top_srcdir)/tools/include/generated \ + -idirafter $(top_srcdir)/arch/$(SRCARCH)/include \ + -idirafter $(top_srcdir)/include \ + -D__ASSEMBLY__ -Wa,--noexecstack diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 4ae417372e9e..7dd5668ea8a6 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -36,6 +36,12 @@ #define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x) #define ELF(x) ELF_BITS_XFORM(ELF_BITS, x) +#ifdef __s390x__ +#define ELF_HASH_ENTRY ELF(Xword) +#else +#define ELF_HASH_ENTRY ELF(Word) +#endif + static struct vdso_info { bool valid; @@ -47,8 +53,8 @@ static struct vdso_info /* Symbol table */ ELF(Sym) *symtab; const char *symstrings; - ELF(Word) *bucket, *chain; - ELF(Word) nbucket, nchain; + ELF_HASH_ENTRY *bucket, *chain; + ELF_HASH_ENTRY nbucket, nchain; /* Version table */ ELF(Versym) *versym; @@ -115,7 +121,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) /* * Fish out the useful bits of the dynamic table. */ - ELF(Word) *hash = 0; + ELF_HASH_ENTRY *hash = 0; vdso_info.symstrings = 0; vdso_info.symtab = 0; vdso_info.versym = 0; @@ -133,7 +139,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) + vdso_info.load_offset); break; case DT_HASH: - hash = (ELF(Word) *) + hash = (ELF_HASH_ENTRY *) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; @@ -216,7 +222,8 @@ void *vdso_sym(const char *version, const char *name) ELF(Sym) *sym = &vdso_info.symtab[chain]; /* Check for a defined global or weak function w/ right name. */ - if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC && + ELF64_ST_TYPE(sym->st_info) != STT_NOTYPE) continue; if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && ELF64_ST_BIND(sym->st_info) != STB_WEAK) diff --git a/tools/testing/selftests/vDSO/vdso_call.h b/tools/testing/selftests/vDSO/vdso_call.h new file mode 100644 index 000000000000..bb237d771051 --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_call.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Macro to call vDSO functions + * + * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France + */ +#ifndef __VDSO_CALL_H__ +#define __VDSO_CALL_H__ + +#ifdef __powerpc__ + +#define LOADARGS_1(fn, __arg1) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ +} while (0) + +#define LOADARGS_2(fn, __arg1, __arg2) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ + _r4 = (long)__arg2; \ +} while (0) + +#define LOADARGS_3(fn, __arg1, __arg2, __arg3) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ + _r4 = (long)__arg2; \ + _r5 = (long)__arg3; \ +} while (0) + +#define LOADARGS_5(fn, __arg1, __arg2, __arg3, __arg4, __arg5) do { \ + _r0 = fn; \ + _r3 = (long)__arg1; \ + _r4 = (long)__arg2; \ + _r5 = (long)__arg3; \ + _r6 = (long)__arg4; \ + _r7 = (long)__arg5; \ +} while (0) + +#define VDSO_CALL(fn, nr, args...) ({ \ + register void *_r0 asm ("r0"); \ + register long _r3 asm ("r3"); \ + register long _r4 asm ("r4"); \ + register long _r5 asm ("r5"); \ + register long _r6 asm ("r6"); \ + register long _r7 asm ("r7"); \ + register long _r8 asm ("r8"); \ + register long _rval asm ("r3"); \ + \ + LOADARGS_##nr(fn, args); \ + \ + asm volatile( \ + " mtctr %0\n" \ + " bctrl\n" \ + " bns+ 1f\n" \ + " neg 3, 3\n" \ + "1:" \ + : "+r" (_r0), "=r" (_r3), "+r" (_r4), "+r" (_r5), \ + "+r" (_r6), "+r" (_r7), "+r" (_r8) \ + : "r" (_rval) \ + : "r9", "r10", "r11", "r12", "cr0", "cr1", "cr5", \ + "cr6", "cr7", "xer", "lr", "ctr", "memory" \ + ); \ + _rval; \ +}) + +#else +#define VDSO_CALL(fn, nr, args...) fn(args) +#endif + +#endif diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h index 7b543e7f04d7..722260f97561 100644 --- a/tools/testing/selftests/vDSO/vdso_config.h +++ b/tools/testing/selftests/vDSO/vdso_config.h @@ -18,18 +18,18 @@ #elif defined(__aarch64__) #define VDSO_VERSION 3 #define VDSO_NAMES 0 -#elif defined(__powerpc__) +#elif defined(__powerpc64__) #define VDSO_VERSION 1 #define VDSO_NAMES 0 -#define VDSO_32BIT 1 -#elif defined(__powerpc64__) +#elif defined(__powerpc__) #define VDSO_VERSION 1 #define VDSO_NAMES 0 -#elif defined (__s390__) +#define VDSO_32BIT 1 +#elif defined (__s390__) && !defined(__s390x__) #define VDSO_VERSION 2 #define VDSO_NAMES 0 #define VDSO_32BIT 1 -#elif defined (__s390X__) +#elif defined (__s390x__) #define VDSO_VERSION 2 #define VDSO_NAMES 0 #elif defined(__mips__) @@ -68,16 +68,15 @@ static const char *versions[7] = { "LINUX_5.10" }; -static const char *names[2][6] = { +static const char *names[2][7] = { { "__kernel_gettimeofday", "__kernel_clock_gettime", "__kernel_time", "__kernel_clock_getres", "__kernel_getcpu", -#if defined(VDSO_32BIT) "__kernel_clock_gettime64", -#endif + "__kernel_getrandom", }, { "__vdso_gettimeofday", @@ -85,9 +84,8 @@ static const char *names[2][6] = { "__vdso_time", "__vdso_clock_getres", "__vdso_getcpu", -#if defined(VDSO_32BIT) "__vdso_clock_gettime64", -#endif + "__vdso_getrandom", }, }; diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c index 96d32fd65b42..a54424e2336f 100644 --- a/tools/testing/selftests/vDSO/vdso_test_abi.c +++ b/tools/testing/selftests/vDSO/vdso_test_abi.c @@ -20,10 +20,8 @@ #include "../kselftest.h" #include "vdso_config.h" - -extern void *vdso_sym(const char *version, const char *name); -extern void vdso_init_from_sysinfo_ehdr(uintptr_t base); -extern void vdso_init_from_auxv(void *auxv); +#include "vdso_call.h" +#include "parse_vdso.h" static const char *version; static const char **name; @@ -61,7 +59,7 @@ static void vdso_test_gettimeofday(void) } struct timeval tv; - long ret = vdso_gettimeofday(&tv, 0); + long ret = VDSO_CALL(vdso_gettimeofday, 2, &tv, 0); if (ret == 0) { ksft_print_msg("The time is %lld.%06lld\n", @@ -86,7 +84,7 @@ static void vdso_test_clock_gettime(clockid_t clk_id) } struct timespec ts; - long ret = vdso_clock_gettime(clk_id, &ts); + long ret = VDSO_CALL(vdso_clock_gettime, 2, clk_id, &ts); if (ret == 0) { ksft_print_msg("The time is %lld.%06lld\n", @@ -111,7 +109,7 @@ static void vdso_test_time(void) return; } - long ret = vdso_time(NULL); + long ret = VDSO_CALL(vdso_time, 1, NULL); if (ret > 0) { ksft_print_msg("The time in hours since January 1, 1970 is %lld\n", @@ -138,7 +136,7 @@ static void vdso_test_clock_getres(clockid_t clk_id) } struct timespec ts, sys_ts; - long ret = vdso_clock_getres(clk_id, &ts); + long ret = VDSO_CALL(vdso_clock_getres, 2, clk_id, &ts); if (ret == 0) { ksft_print_msg("The vdso resolution is %lld %lld\n", diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c index e38f44e5f803..b1ea532c5996 100644 --- a/tools/testing/selftests/vDSO/vdso_test_chacha.c +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -3,23 +3,90 @@ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ -#include <sodium/crypto_stream_chacha20.h> +#include <tools/le_byteshift.h> #include <sys/random.h> +#include <sys/auxv.h> #include <string.h> #include <stdint.h> +#include <stdbool.h> #include "../kselftest.h" -extern void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint8_t *key, uint32_t *counter, size_t nblocks); +#if defined(__aarch64__) +static bool cpu_has_capabilities(void) +{ + return getauxval(AT_HWCAP) & HWCAP_ASIMD; +} +#elif defined(__s390x__) +static bool cpu_has_capabilities(void) +{ + return getauxval(AT_HWCAP) & HWCAP_S390_VXRS; +} +#else +static bool cpu_has_capabilities(void) +{ + return true; +} +#endif + +static uint32_t rol32(uint32_t word, unsigned int shift) +{ + return (word << (shift & 31)) | (word >> ((-shift) & 31)); +} + +static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, uint32_t *counter, size_t nblocks) +{ + uint32_t s[16] = { + 0x61707865U, 0x3320646eU, 0x79622d32U, 0x6b206574U, + key[0], key[1], key[2], key[3], key[4], key[5], key[6], key[7], + counter[0], counter[1], 0, 0 + }; + + while (nblocks--) { + uint32_t x[16]; + memcpy(x, s, sizeof(x)); + for (unsigned int r = 0; r < 20; r += 2) { + #define QR(a, b, c, d) ( \ + x[a] += x[b], \ + x[d] = rol32(x[d] ^ x[a], 16), \ + x[c] += x[d], \ + x[b] = rol32(x[b] ^ x[c], 12), \ + x[a] += x[b], \ + x[d] = rol32(x[d] ^ x[a], 8), \ + x[c] += x[d], \ + x[b] = rol32(x[b] ^ x[c], 7)) + + QR(0, 4, 8, 12); + QR(1, 5, 9, 13); + QR(2, 6, 10, 14); + QR(3, 7, 11, 15); + QR(0, 5, 10, 15); + QR(1, 6, 11, 12); + QR(2, 7, 8, 13); + QR(3, 4, 9, 14); + } + for (unsigned int i = 0; i < 16; ++i, dst_bytes += sizeof(uint32_t)) + put_unaligned_le32(x[i] + s[i], dst_bytes); + if (!++s[12]) + ++s[13]; + } + counter[0] = s[12]; + counter[1] = s[13]; +} + +typedef uint8_t u8; +typedef uint32_t u32; +typedef uint64_t u64; +#include <vdso/getrandom.h> int main(int argc, char *argv[]) { enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 }; - static const uint8_t nonce[8] = { 0 }; - uint32_t counter[2]; - uint8_t key[32]; + uint32_t key[8], counter1[2], counter2[2]; uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS]; ksft_print_header(); + if (!cpu_has_capabilities()) + ksft_exit_skip("Required CPU capabilities missing\n"); ksft_set_plan(1); for (unsigned int trial = 0; trial < TRIALS; ++trial) { @@ -27,17 +94,33 @@ int main(int argc, char *argv[]) printf("getrandom() failed!\n"); return KSFT_SKIP; } - crypto_stream_chacha20(output1, sizeof(output1), nonce, key); + memset(counter1, 0, sizeof(counter1)); + reference_chacha20_blocks(output1, key, counter1, BLOCKS); for (unsigned int split = 0; split < BLOCKS; ++split) { memset(output2, 'X', sizeof(output2)); - memset(counter, 0, sizeof(counter)); + memset(counter2, 0, sizeof(counter2)); if (split) - __arch_chacha20_blocks_nostack(output2, key, counter, split); - __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter, BLOCKS - split); - if (memcmp(output1, output2, sizeof(output1))) + __arch_chacha20_blocks_nostack(output2, key, counter2, split); + __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter2, BLOCKS - split); + if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) return KSFT_FAIL; } } + memset(counter1, 0, sizeof(counter1)); + counter1[0] = (uint32_t)-BLOCKS + 2; + memset(counter2, 0, sizeof(counter2)); + counter2[0] = (uint32_t)-BLOCKS + 2; + + reference_chacha20_blocks(output1, key, counter1, BLOCKS); + __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); + if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) + return KSFT_FAIL; + + reference_chacha20_blocks(output1, key, counter1, BLOCKS); + __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); + if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) + return KSFT_FAIL; + ksft_test_result_pass("chacha: PASS\n"); return KSFT_PASS; } diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index e691a3cf1491..5fb97ad67eea 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -20,6 +20,7 @@ #include <limits.h> #include "vdso_config.h" +#include "vdso_call.h" #include "../kselftest.h" static const char **name; @@ -114,6 +115,12 @@ static void fill_function_pointers() if (!vdso) vdso = dlopen("linux-gate.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-vdso32.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-vdso64.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); if (!vdso) { printf("[WARN]\tfailed to find vDSO\n"); return; @@ -180,7 +187,7 @@ static void test_getcpu(void) ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0); if (vdso_getcpu) - ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0); + ret_vdso = VDSO_CALL(vdso_getcpu, 3, &cpu_vdso, &node_vdso, 0); if (vgetcpu) ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0); @@ -263,7 +270,7 @@ static void test_one_clock_gettime(int clock, const char *name) if (sys_clock_gettime(clock, &start) < 0) { if (errno == EINVAL) { - vdso_ret = vdso_clock_gettime(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime, 2, clock, &vdso); if (vdso_ret == -EINVAL) { printf("[OK]\tNo such clock.\n"); } else { @@ -276,7 +283,7 @@ static void test_one_clock_gettime(int clock, const char *name) return; } - vdso_ret = vdso_clock_gettime(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime, 2, clock, &vdso); end_ret = sys_clock_gettime(clock, &end); if (vdso_ret != 0 || end_ret != 0) { @@ -325,7 +332,7 @@ static void test_one_clock_gettime64(int clock, const char *name) if (sys_clock_gettime64(clock, &start) < 0) { if (errno == EINVAL) { - vdso_ret = vdso_clock_gettime64(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime64, 2, clock, &vdso); if (vdso_ret == -EINVAL) { printf("[OK]\tNo such clock.\n"); } else { @@ -338,7 +345,7 @@ static void test_one_clock_gettime64(int clock, const char *name) return; } - vdso_ret = vdso_clock_gettime64(clock, &vdso); + vdso_ret = VDSO_CALL(vdso_clock_gettime64, 2, clock, &vdso); end_ret = sys_clock_gettime64(clock, &end); if (vdso_ret != 0 || end_ret != 0) { @@ -395,7 +402,7 @@ static void test_gettimeofday(void) return; } - vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz); + vdso_ret = VDSO_CALL(vdso_gettimeofday, 2, &vdso, &vdso_tz); end_ret = sys_gettimeofday(&end, NULL); if (vdso_ret != 0 || end_ret != 0) { @@ -425,7 +432,7 @@ static void test_gettimeofday(void) } /* And make sure that passing NULL for tz doesn't crash. */ - vdso_gettimeofday(&vdso, NULL); + VDSO_CALL(vdso_gettimeofday, 2, &vdso, NULL); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/vDSO/vdso_test_getcpu.c b/tools/testing/selftests/vDSO/vdso_test_getcpu.c index b758f68c6c9c..cdeaed45fb26 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getcpu.c +++ b/tools/testing/selftests/vDSO/vdso_test_getcpu.c @@ -14,6 +14,7 @@ #include "../kselftest.h" #include "parse_vdso.h" #include "vdso_config.h" +#include "vdso_call.h" struct getcpu_cache; typedef long (*getcpu_t)(unsigned int *, unsigned int *, @@ -42,7 +43,7 @@ int main(int argc, char **argv) return KSFT_SKIP; } - ret = get_cpu(&cpu, &node, 0); + ret = VDSO_CALL(get_cpu, 3, &cpu, &node, 0); if (ret == 0) { printf("Running on CPU %u node %u\n", cpu, node); } else { diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 05122425a873..72a1d9b43a84 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -16,11 +16,17 @@ #include <sys/mman.h> #include <sys/random.h> #include <sys/syscall.h> +#include <sys/ptrace.h> +#include <sys/wait.h> #include <sys/types.h> #include <linux/random.h> +#include <linux/compiler.h> +#include <linux/ptrace.h> #include "../kselftest.h" #include "parse_vdso.h" +#include "vdso_config.h" +#include "vdso_call.h" #ifndef timespecsub #define timespecsub(tsp, usp, vsp) \ @@ -38,50 +44,43 @@ static struct { pthread_mutex_t lock; void **states; size_t len, cap; -} grnd_allocator = { - .lock = PTHREAD_MUTEX_INITIALIZER -}; - -static struct { ssize_t(*fn)(void *, size_t, unsigned long, void *, size_t); - pthread_key_t key; - pthread_once_t initialized; struct vgetrandom_opaque_params params; -} grnd_ctx = { - .initialized = PTHREAD_ONCE_INIT +} vgrnd = { + .lock = PTHREAD_MUTEX_INITIALIZER }; static void *vgetrandom_get_state(void) { void *state = NULL; - pthread_mutex_lock(&grnd_allocator.lock); - if (!grnd_allocator.len) { + pthread_mutex_lock(&vgrnd.lock); + if (!vgrnd.len) { size_t page_size = getpagesize(); size_t new_cap; size_t alloc_size, num = sysconf(_SC_NPROCESSORS_ONLN); /* Just a decent heuristic. */ void *new_block, *new_states; - alloc_size = (num * grnd_ctx.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1)); - num = (page_size / grnd_ctx.params.size_of_opaque_state) * (alloc_size / page_size); - new_block = mmap(0, alloc_size, grnd_ctx.params.mmap_prot, grnd_ctx.params.mmap_flags, -1, 0); + alloc_size = (num * vgrnd.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1)); + num = (page_size / vgrnd.params.size_of_opaque_state) * (alloc_size / page_size); + new_block = mmap(0, alloc_size, vgrnd.params.mmap_prot, vgrnd.params.mmap_flags, -1, 0); if (new_block == MAP_FAILED) goto out; - new_cap = grnd_allocator.cap + num; - new_states = reallocarray(grnd_allocator.states, new_cap, sizeof(*grnd_allocator.states)); + new_cap = vgrnd.cap + num; + new_states = reallocarray(vgrnd.states, new_cap, sizeof(*vgrnd.states)); if (!new_states) goto unmap; - grnd_allocator.cap = new_cap; - grnd_allocator.states = new_states; + vgrnd.cap = new_cap; + vgrnd.states = new_states; for (size_t i = 0; i < num; ++i) { - if (((uintptr_t)new_block & (page_size - 1)) + grnd_ctx.params.size_of_opaque_state > page_size) + if (((uintptr_t)new_block & (page_size - 1)) + vgrnd.params.size_of_opaque_state > page_size) new_block = (void *)(((uintptr_t)new_block + page_size - 1) & (~(page_size - 1))); - grnd_allocator.states[i] = new_block; - new_block += grnd_ctx.params.size_of_opaque_state; + vgrnd.states[i] = new_block; + new_block += vgrnd.params.size_of_opaque_state; } - grnd_allocator.len = num; + vgrnd.len = num; goto success; unmap: @@ -89,10 +88,10 @@ static void *vgetrandom_get_state(void) goto out; } success: - state = grnd_allocator.states[--grnd_allocator.len]; + state = vgrnd.states[--vgrnd.len]; out: - pthread_mutex_unlock(&grnd_allocator.lock); + pthread_mutex_unlock(&vgrnd.lock); return state; } @@ -100,27 +99,33 @@ static void vgetrandom_put_state(void *state) { if (!state) return; - pthread_mutex_lock(&grnd_allocator.lock); - grnd_allocator.states[grnd_allocator.len++] = state; - pthread_mutex_unlock(&grnd_allocator.lock); + pthread_mutex_lock(&vgrnd.lock); + vgrnd.states[vgrnd.len++] = state; + pthread_mutex_unlock(&vgrnd.lock); } static void vgetrandom_init(void) { - if (pthread_key_create(&grnd_ctx.key, vgetrandom_put_state) != 0) - return; + const char *version = versions[VDSO_VERSION]; + const char *name = names[VDSO_NAMES][6]; unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); + size_t ret; + if (!sysinfo_ehdr) { printf("AT_SYSINFO_EHDR is not present!\n"); exit(KSFT_SKIP); } vdso_init_from_sysinfo_ehdr(sysinfo_ehdr); - grnd_ctx.fn = (__typeof__(grnd_ctx.fn))vdso_sym("LINUX_2.6", "__vdso_getrandom"); - if (!grnd_ctx.fn) { - printf("__vdso_getrandom is missing!\n"); + vgrnd.fn = (__typeof__(vgrnd.fn))vdso_sym(version, name); + if (!vgrnd.fn) { + printf("%s is missing!\n", name); exit(KSFT_FAIL); } - if (grnd_ctx.fn(NULL, 0, 0, &grnd_ctx.params, ~0UL) != 0) { + ret = VDSO_CALL(vgrnd.fn, 5, NULL, 0, 0, &vgrnd.params, ~0UL); + if (ret == -ENOSYS) { + printf("unsupported architecture\n"); + exit(KSFT_SKIP); + } else if (ret) { printf("failed to fetch vgetrandom params!\n"); exit(KSFT_FAIL); } @@ -128,27 +133,21 @@ static void vgetrandom_init(void) static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags) { - void *state; + static __thread void *state; - pthread_once(&grnd_ctx.initialized, vgetrandom_init); - state = pthread_getspecific(grnd_ctx.key); if (!state) { state = vgetrandom_get_state(); - if (pthread_setspecific(grnd_ctx.key, state) != 0) { - vgetrandom_put_state(state); - state = NULL; - } if (!state) { printf("vgetrandom_get_state failed!\n"); exit(KSFT_FAIL); } } - return grnd_ctx.fn(buf, len, flags, state, grnd_ctx.params.size_of_opaque_state); + return VDSO_CALL(vgrnd.fn, 5, buf, len, flags, state, vgrnd.params.size_of_opaque_state); } enum { TRIALS = 25000000, THREADS = 256 }; -static void *test_vdso_getrandom(void *) +static void *test_vdso_getrandom(void *ctx) { for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; @@ -158,7 +157,7 @@ static void *test_vdso_getrandom(void *) return NULL; } -static void *test_libc_getrandom(void *) +static void *test_libc_getrandom(void *ctx) { for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; @@ -168,7 +167,7 @@ static void *test_libc_getrandom(void *) return NULL; } -static void *test_syscall_getrandom(void *) +static void *test_syscall_getrandom(void *ctx) { for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; @@ -244,9 +243,10 @@ static void fill(void) static void kselftest(void) { uint8_t weird_size[1263]; + pid_t child; ksft_print_header(); - ksft_set_plan(1); + ksft_set_plan(2); for (size_t i = 0; i < 1000; ++i) { ssize_t ret = vgetrandom(weird_size, sizeof(weird_size), 0); @@ -255,6 +255,42 @@ static void kselftest(void) } ksft_test_result_pass("getrandom: PASS\n"); + + unshare(CLONE_NEWUSER); + assert(unshare(CLONE_NEWTIME) == 0); + child = fork(); + assert(child >= 0); + if (!child) { + vgetrandom_init(); + child = getpid(); + assert(ptrace(PTRACE_TRACEME, 0, NULL, NULL) == 0); + assert(kill(child, SIGSTOP) == 0); + assert(vgetrandom(weird_size, sizeof(weird_size), 0) == sizeof(weird_size)); + _exit(0); + } + for (;;) { + struct ptrace_syscall_info info = { 0 }; + int status, ret; + assert(waitpid(child, &status, 0) >= 0); + if (WIFEXITED(status)) { + if (WEXITSTATUS(status) != 0) + exit(KSFT_FAIL); + break; + } + assert(WIFSTOPPED(status)); + if (WSTOPSIG(status) == SIGSTOP) + assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACESYSGOOD) == 0); + else if (WSTOPSIG(status) == (SIGTRAP | 0x80)) { + assert(ptrace(PTRACE_GET_SYSCALL_INFO, child, sizeof(info), &info) > 0); + if (info.op == PTRACE_SYSCALL_INFO_ENTRY && info.entry.nr == __NR_getrandom && + info.entry.args[0] == (uintptr_t)weird_size && info.entry.args[1] == sizeof(weird_size)) + exit(KSFT_FAIL); + } + assert(ptrace(PTRACE_SYSCALL, child, 0, 0) == 0); + } + + ksft_test_result_pass("getrandom timens: PASS\n"); + exit(KSFT_PASS); } @@ -265,6 +301,8 @@ static void usage(const char *argv0) int main(int argc, char *argv[]) { + vgetrandom_init(); + if (argc == 1) { kselftest(); return 0; diff --git a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c index ee4f1ca56a71..e31b18ffae33 100644 --- a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c +++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c @@ -19,6 +19,7 @@ #include "../kselftest.h" #include "parse_vdso.h" #include "vdso_config.h" +#include "vdso_call.h" int main(int argc, char **argv) { @@ -43,7 +44,7 @@ int main(int argc, char **argv) } struct timeval tv; - long ret = gtod(&tv, 0); + long ret = VDSO_CALL(gtod, 2, &tv, 0); if (ret == 0) { printf("The time is %lld.%06lld\n", |