diff options
Diffstat (limited to 'tools')
21 files changed, 1027 insertions, 141 deletions
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 8073c9e4fe46..cccf62ea2b8f 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -63,6 +63,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_DELTA_VELOCITY] = "deltavelocity", [IIO_COLORTEMP] = "colortemp", [IIO_CHROMATICITY] = "chromaticity", + [IIO_ATTENTION] = "attention", }; static const char * const iio_ev_type_text[] = { @@ -183,6 +184,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_DELTA_VELOCITY: case IIO_COLORTEMP: case IIO_CHROMATICITY: + case IIO_ATTENTION: break; default: return false; @@ -449,6 +451,7 @@ error_free_chrdev_name: enable_events(dev_dir_name, 0); free(chrdev_name); + free(dev_dir_name); return ret; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f7586f82b967..4ce176ad411f 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -4573,6 +4573,8 @@ static int validate_ibt(struct objtool_file *file) !strcmp(sec->name, "__jump_table") || !strcmp(sec->name, "__mcount_loc") || !strcmp(sec->name, ".kcfi_traps") || + !strcmp(sec->name, ".llvm.call-graph-profile") || + !strcmp(sec->name, ".llvm_bb_addr_map") || !strcmp(sec->name, "__tracepoints") || strstr(sec->name, "__patchable_function_entries")) continue; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 3d27983dc908..6f64d611faea 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -224,12 +224,17 @@ int find_symbol_hole_containing(const struct section *sec, unsigned long offset) if (n) return 0; /* not a hole */ - /* didn't find a symbol for which @offset is after it */ - if (!hole.sym) - return 0; /* not a hole */ + /* + * @offset >= sym->offset + sym->len, find symbol after it. + * When hole.sym is empty, use the first node to compute the hole. + * If there is no symbol in the section, the first node will be NULL, + * in which case, -1 is returned to skip the whole section. + */ + if (hole.sym) + n = rb_next(&hole.sym->node); + else + n = rb_first_cached(&sec->symbol_tree); - /* @offset >= sym->offset + sym->len, find symbol after it */ - n = rb_next(&hole.sym->node); if (!n) return -1; /* until end of address space */ diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 067717bce1d4..a7f7ed01421c 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -33,6 +33,9 @@ name as necessary to disambiguate it from others is necessary. Note that option msr0xXXX is a hex offset, eg. msr0x10 /sys/path... is an absolute path to a sysfs attribute <device> is a perf device from /sys/bus/event_source/devices/<device> eg. cstate_core + On Intel hybrid platforms, instead of one "cpu" perf device there are two, "cpu_core" and "cpu_atom" devices for P and E cores respectively. + Turbostat, in this case, allow user to use "cpu" device and will automatically detect the type of a CPU and translate it to "cpu_core" and "cpu_atom" accordingly. + For a complete example see "ADD PERF COUNTER EXAMPLE #2 (using virtual "cpu" device)". <event> is a perf event for given device from /sys/bus/event_source/devices/<device>/events/<event> eg. c1-residency perf/cstate_core/c1-residency would then use /sys/bus/event_source/devices/cstate_core/events/c1-residency @@ -187,6 +190,8 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. .PP +\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). Disabled by default. Enable with --enable SysWatt. +.PP \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. .PP \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM. @@ -387,6 +392,28 @@ CPU pCPU%c1 CPU%c1 .fi +.SH ADD PERF COUNTER EXAMPLE #2 (using virtual cpu device) +Here we run on hybrid, Raptor Lake platform. +We limit turbostat to show output for just cpu0 (pcore) and cpu12 (ecore). +We add a counter showing number of L3 cache misses, using virtual "cpu" device, +labeling it with the column header, "VCMISS". +We add a counter showing number of L3 cache misses, using virtual "cpu_core" device, +labeling it with the column header, "PCMISS". This will fail on ecore cpu12. +We add a counter showing number of L3 cache misses, using virtual "cpu_atom" device, +labeling it with the column header, "ECMISS". This will fail on pcore cpu0. +We display it only once, after the conclusion of 0.1 second sleep. +.nf +sudo ./turbostat --quiet --cpu 0,12 --show CPU --add perf/cpu/cache-misses,cpu,delta,raw,VCMISS --add perf/cpu_core/cache-misses,cpu,delta,raw,PCMISS --add perf/cpu_atom/cache-misses,cpu,delta,raw,ECMISS sleep .1 +turbostat: added_perf_counters_init_: perf/cpu_atom/cache-misses: failed to open counter on cpu0 +turbostat: added_perf_counters_init_: perf/cpu_core/cache-misses: failed to open counter on cpu12 +0.104630 sec +CPU ECMISS PCMISS VCMISS +- 0x0000000000000000 0x0000000000000000 0x0000000000000000 +0 0x0000000000000000 0x0000000000007951 0x0000000000007796 +12 0x000000000001137a 0x0000000000000000 0x0000000000011392 + +.fi + .SH ADD PMT COUNTER EXAMPLE Here we limit turbostat to showing just the CPU number 0. We add two counters, showing crystal clock count and the DC6 residency. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 089220aaa5c9..58a487c225a7 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -31,6 +31,9 @@ ) // end copied section +#define CPUID_LEAF_MODEL_ID 0x1A +#define CPUID_LEAF_MODEL_ID_CORE_TYPE_SHIFT 24 + #define X86_VENDOR_INTEL 0 #include INTEL_FAMILY_HEADER @@ -89,6 +92,9 @@ #define PERF_DEV_NAME_BYTES 32 #define PERF_EVT_NAME_BYTES 32 +#define INTEL_ECORE_TYPE 0x20 +#define INTEL_PCORE_TYPE 0x40 + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE }; @@ -194,6 +200,8 @@ struct msr_counter bic[] = { { 0x0, "SAMMHz", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "SAMAMHz", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "SysWatt", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "Sys_J", NULL, 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -256,6 +264,8 @@ struct msr_counter bic[] = { #define BIC_SAMMHz (1ULL << 56) #define BIC_SAMACTMHz (1ULL << 57) #define BIC_Diec6 (1ULL << 58) +#define BIC_SysWatt (1ULL << 59) +#define BIC_Sys_J (1ULL << 60) #define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) #define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) @@ -263,7 +273,7 @@ struct msr_counter bic[] = { #define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) #define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_SysWatt | BIC_Sys_J) unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; @@ -370,7 +380,6 @@ enum gfx_sysfs_idx { }; struct gfx_sysfs_info { - const char *path; FILE *fp; unsigned int val; unsigned long long val_ull; @@ -502,12 +511,15 @@ enum rapl_msrs { RAPL_AMD_PWR_UNIT = BIT(14), /* 0xc0010299 MSR_AMD_RAPL_POWER_UNIT */ RAPL_AMD_CORE_ENERGY_STAT = BIT(15), /* 0xc001029a MSR_AMD_CORE_ENERGY_STATUS */ RAPL_AMD_PKG_ENERGY_STAT = BIT(16), /* 0xc001029b MSR_AMD_PKG_ENERGY_STATUS */ + RAPL_PLATFORM_ENERGY_LIMIT = BIT(17), /* 0x64c MSR_PLATFORM_ENERGY_LIMIT */ + RAPL_PLATFORM_ENERGY_STATUS = BIT(18), /* 0x64d MSR_PLATFORM_ENERGY_STATUS */ }; #define RAPL_PKG (RAPL_PKG_ENERGY_STATUS | RAPL_PKG_POWER_LIMIT) #define RAPL_DRAM (RAPL_DRAM_ENERGY_STATUS | RAPL_DRAM_POWER_LIMIT) #define RAPL_CORE (RAPL_CORE_ENERGY_STATUS | RAPL_CORE_POWER_LIMIT) #define RAPL_GFX (RAPL_GFX_POWER_LIMIT | RAPL_GFX_ENERGY_STATUS) +#define RAPL_PSYS (RAPL_PLATFORM_ENERGY_STATUS | RAPL_PLATFORM_ENERGY_LIMIT) #define RAPL_PKG_ALL (RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO) #define RAPL_DRAM_ALL (RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_DRAM_POWER_INFO) @@ -708,7 +720,7 @@ static const struct platform_features skl_features = { .has_ext_cst_msrs = 1, .trl_msrs = TRL_BASE, .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX | RAPL_PSYS, .enable_tsc_tweak = 1, }; @@ -725,42 +737,44 @@ static const struct platform_features cnl_features = { .has_ext_cst_msrs = 1, .trl_msrs = TRL_BASE, .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX | RAPL_PSYS, .enable_tsc_tweak = 1, }; +/* Copied from cnl_features, with PC7/PC9 removed */ static const struct platform_features adl_features = { - .has_msr_misc_feature_control = 1, - .has_msr_misc_pwr_mgmt = 1, - .has_nhm_msrs = 1, - .has_config_tdp = 1, - .bclk_freq = BCLK_100MHZ, - .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC8 | PC10, - .cst_limit = CST_LIMIT_HSW, - .has_irtl_msrs = 1, - .has_msr_core_c1_res = 1, - .has_ext_cst_msrs = 1, - .trl_msrs = TRL_BASE, - .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, - .enable_tsc_tweak = 1, + .has_msr_misc_feature_control = cnl_features.has_msr_misc_feature_control, + .has_msr_misc_pwr_mgmt = cnl_features.has_msr_misc_pwr_mgmt, + .has_nhm_msrs = cnl_features.has_nhm_msrs, + .has_config_tdp = cnl_features.has_config_tdp, + .bclk_freq = cnl_features.bclk_freq, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC8 | PC10, + .cst_limit = cnl_features.cst_limit, + .has_irtl_msrs = cnl_features.has_irtl_msrs, + .has_msr_core_c1_res = cnl_features.has_msr_core_c1_res, + .has_ext_cst_msrs = cnl_features.has_ext_cst_msrs, + .trl_msrs = cnl_features.trl_msrs, + .tcc_offset_bits = cnl_features.tcc_offset_bits, + .rapl_msrs = cnl_features.rapl_msrs, + .enable_tsc_tweak = cnl_features.enable_tsc_tweak, }; -static const struct platform_features arl_features = { - .has_msr_misc_feature_control = 1, - .has_msr_misc_pwr_mgmt = 1, - .has_nhm_msrs = 1, - .has_config_tdp = 1, - .bclk_freq = BCLK_100MHZ, - .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC10, - .cst_limit = CST_LIMIT_HSW, - .has_irtl_msrs = 1, - .has_msr_core_c1_res = 1, - .has_ext_cst_msrs = 1, - .trl_msrs = TRL_BASE, - .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, - .enable_tsc_tweak = 1, +/* Copied from adl_features, with PC3/PC8 removed */ +static const struct platform_features lnl_features = { + .has_msr_misc_feature_control = adl_features.has_msr_misc_feature_control, + .has_msr_misc_pwr_mgmt = adl_features.has_msr_misc_pwr_mgmt, + .has_nhm_msrs = adl_features.has_nhm_msrs, + .has_config_tdp = adl_features.has_config_tdp, + .bclk_freq = adl_features.bclk_freq, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC6 | PC10, + .cst_limit = adl_features.cst_limit, + .has_irtl_msrs = adl_features.has_irtl_msrs, + .has_msr_core_c1_res = adl_features.has_msr_core_c1_res, + .has_ext_cst_msrs = adl_features.has_ext_cst_msrs, + .trl_msrs = adl_features.trl_msrs, + .tcc_offset_bits = adl_features.tcc_offset_bits, + .rapl_msrs = adl_features.rapl_msrs, + .enable_tsc_tweak = adl_features.enable_tsc_tweak, }; static const struct platform_features skx_features = { @@ -790,7 +804,7 @@ static const struct platform_features icx_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, .has_fixed_rapl_unit = 1, }; @@ -806,7 +820,7 @@ static const struct platform_features spr_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; static const struct platform_features srf_features = { @@ -822,7 +836,7 @@ static const struct platform_features srf_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; static const struct platform_features grr_features = { @@ -838,7 +852,7 @@ static const struct platform_features grr_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; static const struct platform_features slv_features = { @@ -997,18 +1011,19 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_SAPPHIRERAPIDS_X, &spr_features }, { INTEL_EMERALDRAPIDS_X, &spr_features }, { INTEL_GRANITERAPIDS_X, &spr_features }, + { INTEL_GRANITERAPIDS_D, &spr_features }, { INTEL_LAKEFIELD, &cnl_features }, { INTEL_ALDERLAKE, &adl_features }, { INTEL_ALDERLAKE_L, &adl_features }, { INTEL_RAPTORLAKE, &adl_features }, { INTEL_RAPTORLAKE_P, &adl_features }, { INTEL_RAPTORLAKE_S, &adl_features }, - { INTEL_METEORLAKE, &cnl_features }, - { INTEL_METEORLAKE_L, &cnl_features }, - { INTEL_ARROWLAKE_H, &arl_features }, - { INTEL_ARROWLAKE_U, &arl_features }, - { INTEL_ARROWLAKE, &arl_features }, - { INTEL_LUNARLAKE_M, &arl_features }, + { INTEL_METEORLAKE, &adl_features }, + { INTEL_METEORLAKE_L, &adl_features }, + { INTEL_ARROWLAKE_H, &adl_features }, + { INTEL_ARROWLAKE_U, &adl_features }, + { INTEL_ARROWLAKE, &adl_features }, + { INTEL_LUNARLAKE_M, &lnl_features }, { INTEL_ATOM_SILVERMONT, &slv_features }, { INTEL_ATOM_SILVERMONT_D, &slvd_features }, { INTEL_ATOM_AIRMONT, &amt_features }, @@ -1100,6 +1115,7 @@ enum rapl_rci_index { RAPL_RCI_INDEX_PKG_PERF_STATUS = 4, RAPL_RCI_INDEX_DRAM_PERF_STATUS = 5, RAPL_RCI_INDEX_CORE_ENERGY = 6, + RAPL_RCI_INDEX_ENERGY_PLATFORM = 7, NUM_RAPL_COUNTERS, }; @@ -1126,6 +1142,7 @@ struct rapl_counter_info_t { struct rapl_counter_info_t *rapl_counter_info_perdomain; unsigned int rapl_counter_info_perdomain_size; +#define RAPL_COUNTER_FLAG_PLATFORM_COUNTER (1u << 0) #define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1) struct rapl_counter_arch_info { @@ -1247,6 +1264,19 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .compat_scale = 1.0, .flags = 0, }, + { + .feature_mask = RAPL_PSYS, + .perf_subsys = "power", + .perf_name = "energy-psys", + .msr = MSR_PLATFORM_ENERGY_STATUS, + .msr_mask = 0x00000000FFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM, + .bic = BIC_SysWatt | BIC_Sys_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_PLATFORM_COUNTER | RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, }; struct rapl_counter { @@ -1674,6 +1704,7 @@ enum { IDX_PP1_ENERGY, IDX_PKG_PERF, IDX_DRAM_PERF, + IDX_PSYS_ENERGY, IDX_COUNT, }; @@ -1718,6 +1749,9 @@ off_t idx_to_offset(int idx) case IDX_DRAM_PERF: offset = MSR_DRAM_PERF_STATUS; break; + case IDX_PSYS_ENERGY: + offset = MSR_PLATFORM_ENERGY_STATUS; + break; default: offset = -1; } @@ -1748,6 +1782,9 @@ int offset_to_idx(off_t offset) case MSR_DRAM_PERF_STATUS: idx = IDX_DRAM_PERF; break; + case MSR_PLATFORM_ENERGY_STATUS: + idx = IDX_PSYS_ENERGY; + break; default: idx = -1; } @@ -1769,6 +1806,8 @@ int idx_valid(int idx) return platform->rapl_msrs & RAPL_PKG_PERF_STATUS; case IDX_DRAM_PERF: return platform->rapl_msrs & RAPL_DRAM_PERF_STATUS; + case IDX_PSYS_ENERGY: + return platform->rapl_msrs & RAPL_PSYS; default: return 0; } @@ -1840,6 +1879,10 @@ struct system_summary { struct pkg_data packages; } average; +struct platform_counters { + struct rapl_counter energy_psys; /* MSR_PLATFORM_ENERGY_STATUS */ +} platform_counters_odd, platform_counters_even; + struct cpu_topology { int physical_package_id; int die_id; @@ -1848,6 +1891,7 @@ struct cpu_topology { int logical_node_id; /* 0-based count within the package */ int physical_core_id; int thread_id; + int type; cpu_set_t *put_ids; /* Processing Unit/Thread IDs */ } *cpus; @@ -2291,7 +2335,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: - outp += sprintf(outp, "%s%s", delim, ppmt->name); + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2365,7 +2409,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: - outp += sprintf(outp, "%s%s", delim, ppmt->name); + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2496,13 +2540,18 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: - outp += sprintf(outp, "%s%s", delim, ppmt->name); + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } ppmt = ppmt->next; } + if (DO_BIC(BIC_SysWatt)) + outp += sprintf(outp, "%sSysWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_Sys_J)) + outp += sprintf(outp, "%sSys_J", (printed++ ? delim : "")); + outp += sprintf(outp, "\n"); } @@ -2510,6 +2559,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p { int i; struct msr_counter *mp; + struct platform_counters *pplat_cnt = p == package_odd ? &platform_counters_odd : &platform_counters_even; outp += sprintf(outp, "t %p, c %p, p %p\n", t, c, p); @@ -2581,6 +2631,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores.raw_value); outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx.raw_value); outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram.raw_value); + outp += sprintf(outp, "Joules PSYS: %0llX\n", pplat_cnt->energy_psys.raw_value); outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status.raw_value); outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status.raw_value); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); @@ -2619,6 +2670,9 @@ double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desir */ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { + static int count; + + struct platform_counters *pplat_cnt = NULL; double interval_float, tsc; char *fmt8; int i; @@ -2628,6 +2682,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data char *delim = "\t"; int printed = 0; + if (t == &average.threads) { + pplat_cnt = count & 1 ? &platform_counters_odd : &platform_counters_even; + ++count; + } + /* if showing only 1st thread in core and this isn't one, bail out */ if (show_core_only && !is_cpu_first_thread_in_core(t, c, p)) return 0; @@ -2788,6 +2847,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { + const unsigned long value_raw = t->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2799,9 +2860,6 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: - const unsigned long value_raw = t->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; } @@ -2869,6 +2927,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { + const unsigned long value_raw = c->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2880,9 +2940,6 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: - const unsigned long value_raw = c->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; } @@ -3068,6 +3125,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { + const unsigned long value_raw = p->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -3079,14 +3138,18 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: - const unsigned long value_raw = p->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; } } + if (DO_BIC(BIC_SysWatt) && (t == &average.threads)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&pplat_cnt->energy_psys, RAPL_UNIT_WATTS, interval_float)); + if (DO_BIC(BIC_Sys_J) && (t == &average.threads)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&pplat_cnt->energy_psys, RAPL_UNIT_JOULES, interval_float)); + done: if (*(outp - 1) != '\n') outp += sprintf(outp, "\n"); @@ -3394,6 +3457,11 @@ int delta_cpu(struct thread_data *t, struct core_data *c, return retval; } +void delta_platform(struct platform_counters *new, struct platform_counters *old) +{ + old->energy_psys.raw_value = new->energy_psys.raw_value - old->energy_psys.raw_value; +} + void rapl_counter_clear(struct rapl_counter *c) { c->raw_value = 0; @@ -4123,6 +4191,9 @@ static size_t cstate_counter_info_count_perf(const struct cstate_counter_info_t void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci, unsigned int idx) { + if (rci->source[idx] == COUNTER_SOURCE_NONE) + return; + rc->raw_value = rci->data[idx]; rc->unit = rci->unit[idx]; rc->scale = rci->scale[idx]; @@ -4130,6 +4201,7 @@ void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct pkg_data *p) { + struct platform_counters *pplat_cnt = p == package_odd ? &platform_counters_odd : &platform_counters_even; unsigned long long perf_data[NUM_RAPL_COUNTERS + 1]; struct rapl_counter_info_t *rci; @@ -4157,6 +4229,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) { switch (rci->source[i]) { case COUNTER_SOURCE_NONE: + rci->data[i] = 0; break; case COUNTER_SOURCE_PERF: @@ -4195,7 +4268,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct } } - BUILD_BUG_ON(NUM_RAPL_COUNTERS != 7); + BUILD_BUG_ON(NUM_RAPL_COUNTERS != 8); write_rapl_counter(&p->energy_pkg, rci, RAPL_RCI_INDEX_ENERGY_PKG); write_rapl_counter(&p->energy_cores, rci, RAPL_RCI_INDEX_ENERGY_CORES); write_rapl_counter(&p->energy_dram, rci, RAPL_RCI_INDEX_DRAM); @@ -4203,6 +4276,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct write_rapl_counter(&p->rapl_pkg_perf_status, rci, RAPL_RCI_INDEX_PKG_PERF_STATUS); write_rapl_counter(&p->rapl_dram_perf_status, rci, RAPL_RCI_INDEX_DRAM_PERF_STATUS); write_rapl_counter(&c->core_energy, rci, RAPL_RCI_INDEX_CORE_ENERGY); + write_rapl_counter(&pplat_cnt->energy_psys, rci, RAPL_RCI_INDEX_ENERGY_PLATFORM); return 0; } @@ -5385,6 +5459,9 @@ static int parse_cpu_str(char *cpu_str, cpu_set_t *cpu_set, int cpu_set_size) if (*next == '-') /* no negative cpu numbers */ return 1; + if (*next == '\0' || *next == '\n') + break; + start = strtoul(next, &next, 10); if (start >= CPU_SUBSET_MAXCPUS) @@ -5656,6 +5733,32 @@ int init_thread_id(int cpu) return 0; } +int set_my_cpu_type(void) +{ + unsigned int eax, ebx, ecx, edx; + unsigned int max_level; + + __cpuid(0, max_level, ebx, ecx, edx); + + if (max_level < CPUID_LEAF_MODEL_ID) + return 0; + + __cpuid(CPUID_LEAF_MODEL_ID, eax, ebx, ecx, edx); + + return (eax >> CPUID_LEAF_MODEL_ID_CORE_TYPE_SHIFT); +} + +int set_cpu_hybrid_type(int cpu) +{ + if (cpu_migrate(cpu)) + return -1; + + int type = set_my_cpu_type(); + + cpus[cpu].type = type; + return 0; +} + /* * snapshot_proc_interrupts() * @@ -5728,28 +5831,21 @@ int snapshot_proc_interrupts(void) */ int snapshot_graphics(int idx) { - FILE *fp; int retval; + rewind(gfx_info[idx].fp); + switch (idx) { case GFX_rc6: case SAM_mc6: - fp = fopen_or_die(gfx_info[idx].path, "r"); - retval = fscanf(fp, "%lld", &gfx_info[idx].val_ull); + retval = fscanf(gfx_info[idx].fp, "%lld", &gfx_info[idx].val_ull); if (retval != 1) err(1, "rc6"); - fclose(fp); return 0; case GFX_MHz: case GFX_ACTMHz: case SAM_MHz: case SAM_ACTMHz: - if (gfx_info[idx].fp == NULL) { - gfx_info[idx].fp = fopen_or_die(gfx_info[idx].path, "r"); - } else { - rewind(gfx_info[idx].fp); - fflush(gfx_info[idx].fp); - } retval = fscanf(gfx_info[idx].fp, "%d", &gfx_info[idx].val); if (retval != 1) err(1, "MHz"); @@ -6116,6 +6212,7 @@ restart: re_initialize(); goto restart; } + delta_platform(&platform_counters_odd, &platform_counters_even); compute_average(EVEN_COUNTERS); format_all_counters(EVEN_COUNTERS); flush_output_stdout(); @@ -6139,6 +6236,7 @@ restart: re_initialize(); goto restart; } + delta_platform(&platform_counters_even, &platform_counters_odd); compute_average(ODD_COUNTERS); format_all_counters(ODD_COUNTERS); flush_output_stdout(); @@ -6442,14 +6540,25 @@ static void probe_intel_uncore_frequency(void) probe_intel_uncore_frequency_legacy(); } +static void set_graphics_fp(char *path, int idx) +{ + if (!access(path, R_OK)) + gfx_info[idx].fp = fopen_or_die(path, "r"); +} + +/* Enlarge this if there are /sys/class/drm/card2 ... */ +#define GFX_MAX_CARDS 2 + static void probe_graphics(void) { + char path[PATH_MAX]; + int i; + /* Xe graphics sysfs knobs */ if (!access("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", R_OK)) { FILE *fp; char buf[8]; bool gt0_is_gt; - int idx; fp = fopen("/sys/class/drm/card0/device/tile0/gt0/gtidle/name", "r"); if (!fp) @@ -6468,81 +6577,76 @@ static void probe_graphics(void) else goto next; - idx = gt0_is_gt ? GFX_rc6 : SAM_mc6; - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", gt0_is_gt ? GFX_rc6 : SAM_mc6); - idx = gt0_is_gt ? GFX_MHz : SAM_MHz; - if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", gt0_is_gt ? GFX_MHz : SAM_MHz); - idx = gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz; - if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz); - idx = gt0_is_gt ? SAM_mc6 : GFX_rc6; - if (!access("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", gt0_is_gt ? SAM_mc6 : GFX_rc6); - idx = gt0_is_gt ? SAM_MHz : GFX_MHz; - if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", gt0_is_gt ? SAM_MHz : GFX_MHz); - idx = gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz; - if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz); goto end; } next: /* New i915 graphics sysfs knobs */ - if (!access("/sys/class/drm/card0/gt/gt0/rc6_residency_ms", R_OK)) { - gfx_info[GFX_rc6].path = "/sys/class/drm/card0/gt/gt0/rc6_residency_ms"; + for (i = 0; i < GFX_MAX_CARDS; i++) { + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rc6_residency_ms", i); + if (!access(path, R_OK)) + break; + } - if (!access("/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz", R_OK)) - gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz"; + if (i == GFX_MAX_CARDS) + goto legacy_i915; - if (!access("/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz", R_OK)) - gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rc6_residency_ms", i); + set_graphics_fp(path, GFX_rc6); - if (!access("/sys/class/drm/card0/gt/gt1/rc6_residency_ms", R_OK)) - gfx_info[SAM_mc6].path = "/sys/class/drm/card0/gt/gt1/rc6_residency_ms"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rps_cur_freq_mhz", i); + set_graphics_fp(path, GFX_MHz); - if (!access("/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz", R_OK)) - gfx_info[SAM_MHz].path = "/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rps_act_freq_mhz", i); + set_graphics_fp(path, GFX_ACTMHz); - if (!access("/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz", R_OK)) - gfx_info[SAM_ACTMHz].path = "/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt1/rc6_residency_ms", i); + set_graphics_fp(path, SAM_mc6); - goto end; - } + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt1/rps_cur_freq_mhz", i); + set_graphics_fp(path, SAM_MHz); + + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt1/rps_act_freq_mhz", i); + set_graphics_fp(path, SAM_ACTMHz); + goto end; + +legacy_i915: /* Fall back to traditional i915 graphics sysfs knobs */ - if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) - gfx_info[GFX_rc6].path = "/sys/class/drm/card0/power/rc6_residency_ms"; + set_graphics_fp("/sys/class/drm/card0/power/rc6_residency_ms", GFX_rc6); - if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK)) - gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt_cur_freq_mhz"; - else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) - gfx_info[GFX_MHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz"; + set_graphics_fp("/sys/class/drm/card0/gt_cur_freq_mhz", GFX_MHz); + if (!gfx_info[GFX_MHz].fp) + set_graphics_fp("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", GFX_MHz); - if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK)) - gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt_act_freq_mhz"; - else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) - gfx_info[GFX_ACTMHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz"; + set_graphics_fp("/sys/class/drm/card0/gt_act_freq_mhz", GFX_ACTMHz); + if (!gfx_info[GFX_ACTMHz].fp) + set_graphics_fp("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", GFX_ACTMHz); end: - if (gfx_info[GFX_rc6].path) + if (gfx_info[GFX_rc6].fp) BIC_PRESENT(BIC_GFX_rc6); - if (gfx_info[GFX_MHz].path) + if (gfx_info[GFX_MHz].fp) BIC_PRESENT(BIC_GFXMHz); - if (gfx_info[GFX_ACTMHz].path) + if (gfx_info[GFX_ACTMHz].fp) BIC_PRESENT(BIC_GFXACTMHz); - if (gfx_info[SAM_mc6].path) + if (gfx_info[SAM_mc6].fp) BIC_PRESENT(BIC_SAM_mc6); - if (gfx_info[SAM_MHz].path) + if (gfx_info[SAM_MHz].fp) BIC_PRESENT(BIC_SAMMHz); - if (gfx_info[SAM_ACTMHz].path) + if (gfx_info[SAM_ACTMHz].fp) BIC_PRESENT(BIC_SAMACTMHz); } @@ -6911,8 +7015,8 @@ void rapl_probe_intel(void) unsigned long long msr; unsigned int time_unit; double tdp; - const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt; - const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J; + const unsigned long long bic_watt_bits = BIC_SysWatt | BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt; + const unsigned long long bic_joules_bits = BIC_Sys_J | BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J; if (rapl_joules) bic_enabled &= ~bic_watt_bits; @@ -7572,6 +7676,9 @@ void rapl_perf_init(void) domain_visited[next_domain] = 1; + if ((cai->flags & RAPL_COUNTER_FLAG_PLATFORM_COUNTER) && (cpu != base_cpu)) + continue; + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[next_domain]; /* Check if the counter is enabled and accessible */ @@ -8196,7 +8303,7 @@ void topology_probe(bool startup) set_max_cpu_num(); topo.num_cpus = 0; for_all_proc_cpus(count_cpus); - if (!summary_only && topo.num_cpus > 1) + if (!summary_only) BIC_PRESENT(BIC_CPU); if (debug > 1) @@ -8284,6 +8391,8 @@ void topology_probe(bool startup) for_all_proc_cpus(init_thread_id); + for_all_proc_cpus(set_cpu_hybrid_type); + /* * For online cpus * find max_core_id, max_package_id @@ -8332,7 +8441,7 @@ void topology_probe(bool startup) topo.cores_per_node = max_core_id + 1; if (debug > 1) fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_node); - if (!summary_only && topo.cores_per_node > 1) + if (!summary_only) BIC_PRESENT(BIC_Core); topo.num_die = topo.max_die_id + 1; @@ -8548,6 +8657,35 @@ void check_perf_access(void) bic_enabled &= ~BIC_IPC; } +bool perf_has_hybrid_devices(void) +{ + /* + * 0: unknown + * 1: has separate perf device for p and e core + * -1: doesn't have separate perf device for p and e core + */ + static int cached; + + if (cached > 0) + return true; + + if (cached < 0) + return false; + + if (access("/sys/bus/event_source/devices/cpu_core", F_OK)) { + cached = -1; + return false; + } + + if (access("/sys/bus/event_source/devices/cpu_atom", F_OK)) { + cached = -1; + return false; + } + + cached = 1; + return true; +} + int added_perf_counters_init_(struct perf_counter_info *pinfo) { size_t num_domains = 0; @@ -8604,29 +8742,56 @@ int added_perf_counters_init_(struct perf_counter_info *pinfo) if (domain_visited[next_domain]) continue; - perf_type = read_perf_type(pinfo->device); + /* + * Intel hybrid platforms expose different perf devices for P and E cores. + * Instead of one, "/sys/bus/event_source/devices/cpu" device, there are + * "/sys/bus/event_source/devices/{cpu_core,cpu_atom}". + * + * This makes it more complicated to the user, because most of the counters + * are available on both and have to be handled manually, otherwise. + * + * Code below, allow user to use the old "cpu" name, which is translated accordingly. + */ + const char *perf_device = pinfo->device; + + if (strcmp(perf_device, "cpu") == 0 && perf_has_hybrid_devices()) { + switch (cpus[cpu].type) { + case INTEL_PCORE_TYPE: + perf_device = "cpu_core"; + break; + + case INTEL_ECORE_TYPE: + perf_device = "cpu_atom"; + break; + + default: /* Don't change, we will probably fail and report a problem soon. */ + break; + } + } + + perf_type = read_perf_type(perf_device); if (perf_type == (unsigned int)-1) { warnx("%s: perf/%s/%s: failed to read %s", - __func__, pinfo->device, pinfo->event, "type"); + __func__, perf_device, pinfo->event, "type"); continue; } - perf_config = read_perf_config(pinfo->device, pinfo->event); + perf_config = read_perf_config(perf_device, pinfo->event); if (perf_config == (unsigned int)-1) { warnx("%s: perf/%s/%s: failed to read %s", - __func__, pinfo->device, pinfo->event, "config"); + __func__, perf_device, pinfo->event, "config"); continue; } /* Scale is not required, some counters just don't have it. */ - perf_scale = read_perf_scale(pinfo->device, pinfo->event); + perf_scale = read_perf_scale(perf_device, pinfo->event); if (perf_scale == 0.0) perf_scale = 1.0; fd_perf = open_perf_counter(cpu, perf_type, perf_config, -1, 0); if (fd_perf == -1) { warnx("%s: perf/%s/%s: failed to open counter on cpu%d", - __func__, pinfo->device, pinfo->event, cpu); + __func__, perf_device, pinfo->event, cpu); continue; } @@ -8636,7 +8801,7 @@ int added_perf_counters_init_(struct perf_counter_info *pinfo) if (debug) fprintf(stderr, "Add perf/%s/%s cpu%d: %d\n", - pinfo->device, pinfo->event, cpu, pinfo->fd_perf_per_domain[next_domain]); + perf_device, pinfo->event, cpu, pinfo->fd_perf_per_domain[next_domain]); } pinfo = pinfo->next; @@ -9071,7 +9236,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2024.07.26 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2024.11.30 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -9781,7 +9946,7 @@ void cmdline(int argc, char **argv) * Parse some options early, because they may make other options invalid, * like adding the MSR counter with --add and at the same time using --no-msr. */ - while ((opt = getopt_long_only(argc, argv, "MPn:", long_options, &option_index)) != -1) { + while ((opt = getopt_long_only(argc, argv, "+MPn:", long_options, &option_index)) != -1) { switch (opt) { case 'M': no_msr = 1; @@ -9805,6 +9970,12 @@ void cmdline(int argc, char **argv) break; case 'D': dump_only++; + /* + * Force the no_perf early to prevent using it as a source. + * User asks for raw values, but perf returns them relative + * to the opening of the file descriptor. + */ + no_perf = 1; break; case 'e': /* --enable specified counter */ diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore index 12dc3fcd3456..3dd8e1176b89 100644 --- a/tools/testing/selftests/alsa/.gitignore +++ b/tools/testing/selftests/alsa/.gitignore @@ -1,3 +1,5 @@ +global-timer mixer-test pcm-test test-pcmtest-driver +utimer-test diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py index db84000fc75b..79fde603cbbc 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py @@ -218,5 +218,5 @@ class LinkConfig: json_data = process[0] """Check if the field exist in the json data""" if field not in json_data: - raise KsftSkipEx(f"Field {field} does not exist in the output of interface {json_data["ifname"]}") + raise KsftSkipEx(f'Field {field} does not exist in the output of interface {json_data["ifname"]}') return json_data[field] diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 319567f0fae1..81db85a5cc16 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -57,7 +57,6 @@ static int __do_binderfs_test(struct __test_metadata *_metadata) { int fd, ret, saved_errno, result = 1; size_t len; - ssize_t wret; struct binderfs_device device = { 0 }; struct binder_version version = { 0 }; char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX", diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 8e34f7fa44e9..4bc1051848e5 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -41,10 +41,14 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_I: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_M: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_V: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMNPM: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSCOFPMF: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSNPM: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVADE: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVADU: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: @@ -414,10 +418,14 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(I), KVM_ISA_EXT_ARR(M), KVM_ISA_EXT_ARR(V), + KVM_ISA_EXT_ARR(SMNPM), KVM_ISA_EXT_ARR(SMSTATEEN), KVM_ISA_EXT_ARR(SSAIA), KVM_ISA_EXT_ARR(SSCOFPMF), + KVM_ISA_EXT_ARR(SSNPM), KVM_ISA_EXT_ARR(SSTC), + KVM_ISA_EXT_ARR(SVADE), + KVM_ISA_EXT_ARR(SVADU), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), @@ -946,9 +954,13 @@ KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA); KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F); KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D); KVM_ISA_EXT_SIMPLE_CONFIG(h, H); +KVM_ISA_EXT_SIMPLE_CONFIG(smnpm, SMNPM); KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN); KVM_ISA_EXT_SIMPLE_CONFIG(sscofpmf, SSCOFPMF); +KVM_ISA_EXT_SIMPLE_CONFIG(ssnpm, SSNPM); KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC); +KVM_ISA_EXT_SIMPLE_CONFIG(svade, SVADE); +KVM_ISA_EXT_SIMPLE_CONFIG(svadu, SVADU); KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); @@ -1009,9 +1021,13 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_fp_f, &config_fp_d, &config_h, + &config_smnpm, &config_smstateen, &config_sscofpmf, + &config_ssnpm, &config_sstc, + &config_svade, + &config_svadu, &config_svinval, &config_svnapot, &config_svpbmt, diff --git a/tools/testing/selftests/module/Makefile b/tools/testing/selftests/module/Makefile new file mode 100644 index 000000000000..6132d7ddb08b --- /dev/null +++ b/tools/testing/selftests/module/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Makefile for module loading selftests + +# No binaries, but make sure arg-less "make" doesn't trigger "run_tests" +all: + +TEST_PROGS := find_symbol.sh + +include ../lib.mk + +# Nothing to clean up. +clean: diff --git a/tools/testing/selftests/module/config b/tools/testing/selftests/module/config new file mode 100644 index 000000000000..b0c206b1ad47 --- /dev/null +++ b/tools/testing/selftests/module/config @@ -0,0 +1,3 @@ +CONFIG_TEST_RUNTIME=y +CONFIG_TEST_RUNTIME_MODULE=y +CONFIG_TEST_KALLSYMS=m diff --git a/tools/testing/selftests/module/find_symbol.sh b/tools/testing/selftests/module/find_symbol.sh new file mode 100755 index 000000000000..2c56805c9b6e --- /dev/null +++ b/tools/testing/selftests/module/find_symbol.sh @@ -0,0 +1,81 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1 +# Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org> +# +# This is a stress test script for kallsyms through find_symbol() + +set -e + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +test_reqs() +{ + if ! which modprobe 2> /dev/null > /dev/null; then + echo "$0: You need modprobe installed" >&2 + exit $ksft_skip + fi + + if ! which kmod 2> /dev/null > /dev/null; then + echo "$0: You need kmod installed" >&2 + exit $ksft_skip + fi + + if ! which perf 2> /dev/null > /dev/null; then + echo "$0: You need perf installed" >&2 + exit $ksft_skip + fi + + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo $msg must be run as root >&2 + exit $ksft_skip + fi +} + +load_mod() +{ + local STATS="-e duration_time" + STATS="$STATS -e user_time" + STATS="$STATS -e system_time" + STATS="$STATS -e page-faults" + local MOD=$1 + + local ARCH="$(uname -m)" + case "${ARCH}" in + x86_64) + perf stat $STATS $MODPROBE $MOD + ;; + *) + time $MODPROBE $MOD + exit 1 + ;; + esac +} + +remove_all() +{ + $MODPROBE -r test_kallsyms_b + for i in a b c d; do + $MODPROBE -r test_kallsyms_$i + done +} +test_reqs + +MODPROBE=$(</proc/sys/kernel/modprobe) + +remove_all +load_mod test_kallsyms_b +remove_all + +# Now pollute the namespace +$MODPROBE test_kallsyms_c +load_mod test_kallsyms_b + +# Now pollute the namespace with twice the number of symbols than the last time +remove_all +$MODPROBE test_kallsyms_c +$MODPROBE test_kallsyms_d +load_mod test_kallsyms_b + +exit 0 diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 68801e1a9ec2..70f65eb320a7 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1026,7 +1026,7 @@ FIXTURE_SETUP(mount_setattr_idmapped) "size=100000,mode=700"), 0); ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV, - "size=100000,mode=700"), 0); + "size=2m,mode=700"), 0); ASSERT_EQ(mkdir("/mnt/A", 0777), 0); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3d487b03c4a0..cb2fc601de66 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -78,7 +78,6 @@ TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash -TEST_GEN_PROGS += netlink-dumps TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_GEN_PROGS += sk_so_peek_off @@ -101,7 +100,7 @@ TEST_PROGS += ipv6_route_update_soft_lockup.sh TEST_PROGS += busy_poll_test.sh # YNL files, must be before "include ..lib.mk" -YNL_GEN_FILES := busy_poller +YNL_GEN_FILES := busy_poller netlink-dumps TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_FILES := settings diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 84e29b7dffb6..07423f256f96 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -12,11 +12,140 @@ #include <unistd.h> #include <linux/genetlink.h> +#include <linux/neighbour.h> +#include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/mqueue.h> +#include <linux/rtnetlink.h> #include "../kselftest_harness.h" +#include <ynl.h> + +struct ext_ack { + int err; + + __u32 attr_offs; + __u32 miss_type; + __u32 miss_nest; + const char *str; +}; + +/* 0: no done, 1: done found, 2: extack found, -1: error */ +static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea) +{ + const struct nlmsghdr *nlh; + const struct nlattr *attr; + ssize_t rem; + + for (rem = n; rem > 0; NLMSG_NEXT(nlh, rem)) { + nlh = (struct nlmsghdr *)&buf[n - rem]; + if (!NLMSG_OK(nlh, rem)) + return -1; + + if (nlh->nlmsg_type != NLMSG_DONE) + continue; + + ea->err = -*(int *)NLMSG_DATA(nlh); + + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 1; + + ynl_attr_for_each(attr, nlh, sizeof(int)) { + switch (ynl_attr_type(attr)) { + case NLMSGERR_ATTR_OFFS: + ea->attr_offs = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_TYPE: + ea->miss_type = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_NEST: + ea->miss_nest = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MSG: + ea->str = ynl_attr_get_str(attr); + break; + } + } + + return 2; + } + + return 0; +} + +static const struct { + struct nlmsghdr nlhdr; + struct ndmsg ndm; + struct nlattr ahdr; + __u32 val; +} dump_neigh_bad = { + .nlhdr = { + .nlmsg_len = sizeof(dump_neigh_bad), + .nlmsg_type = RTM_GETNEIGH, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + .nlmsg_seq = 1, + }, + .ndm = { + .ndm_family = 123, + }, + .ahdr = { + .nla_len = 4 + 4, + .nla_type = NDA_FLAGS_EXT, + }, + .val = -1, // should fail MASK validation +}; + +TEST(dump_extack) +{ + int netlink_sock; + char buf[8192]; + int one = 1; + int i, cnt; + ssize_t n; + + netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + ASSERT_GE(netlink_sock, 0); + + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_CAP_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_GET_STRICT_CHK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + + /* Dump so many times we fill up the buffer */ + cnt = 64; + for (i = 0; i < cnt; i++) { + n = send(netlink_sock, &dump_neigh_bad, + sizeof(dump_neigh_bad), 0); + ASSERT_EQ(n, sizeof(dump_neigh_bad)); + } + + /* Read out the ENOBUFS */ + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + EXPECT_EQ(n, -1); + EXPECT_EQ(errno, ENOBUFS); + + for (i = 0; i < cnt; i++) { + struct ext_ack ea = {}; + + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + if (n < 0) { + ASSERT_GE(i, 10); + break; + } + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); + + EXPECT_EQ(nl_get_extack(buf, n, &ea), 2); + EXPECT_EQ(ea.attr_offs, + sizeof(struct nlmsghdr) + sizeof(struct ndmsg)); + } +} + static const struct { struct nlmsghdr nlhdr; struct genlmsghdr genlhdr; diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile index 1803c39dbacb..612a7219990e 100644 --- a/tools/testing/selftests/net/rds/Makefile +++ b/tools/testing/selftests/net/rds/Makefile @@ -3,10 +3,9 @@ all: @echo mk_build_dir="$(shell pwd)" > include.sh -TEST_PROGS := run.sh \ - test.py +TEST_PROGS := run.sh -TEST_FILES := include.sh +TEST_FILES := include.sh test.py EXTRA_CLEAN := /tmp/rds_logs include.sh diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 7f05b5f9b76f..2e8243a65b50 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -29,6 +29,7 @@ ALL_TESTS=" kci_test_bridge_parent_id kci_test_address_proto kci_test_enslave_bonding + kci_test_mngtmpaddr " devdummy="test-dummy0" @@ -44,6 +45,7 @@ check_err() if [ $ret -eq 0 ]; then ret=$1 fi + [ -n "$2" ] && echo "$2" } # same but inverted -- used when command must fail for test to pass @@ -1239,6 +1241,99 @@ kci_test_enslave_bonding() ip netns del "$testns" } +# Called to validate the addresses on $IFNAME: +# +# 1. Every `temporary` address must have a matching `mngtmpaddr` +# 2. Every `mngtmpaddr` address must have some un`deprecated` `temporary` +# +# If the mngtmpaddr or tempaddr checking failed, return 0 and stop slowwait +validate_mngtmpaddr() +{ + local dev=$1 + local prefix="" + local addr_list=$(ip -j -n $testns addr show dev ${dev}) + local temp_addrs=$(echo ${addr_list} | \ + jq -r '.[].addr_info[] | select(.temporary == true) | .local') + local mng_prefixes=$(echo ${addr_list} | \ + jq -r '.[].addr_info[] | select(.mngtmpaddr == true) | .local' | \ + cut -d: -f1-4 | tr '\n' ' ') + local undep_prefixes=$(echo ${addr_list} | \ + jq -r '.[].addr_info[] | select(.temporary == true and .deprecated != true) | .local' | \ + cut -d: -f1-4 | tr '\n' ' ') + + # 1. All temporary addresses (temp and dep) must have a matching mngtmpaddr + for address in ${temp_addrs}; do + prefix=$(echo ${address} | cut -d: -f1-4) + if [[ ! " ${mng_prefixes} " =~ " $prefix " ]]; then + check_err 1 "FAIL: Temporary $address with no matching mngtmpaddr!"; + return 0 + fi + done + + # 2. All mngtmpaddr addresses must have a temporary address (not dep) + for prefix in ${mng_prefixes}; do + if [[ ! " ${undep_prefixes} " =~ " $prefix " ]]; then + check_err 1 "FAIL: No undeprecated temporary in $prefix!"; + return 0 + fi + done + + return 1 +} + +kci_test_mngtmpaddr() +{ + local ret=0 + + setup_ns testns + if [ $? -ne 0 ]; then + end_test "SKIP mngtmpaddr tests: cannot add net namespace $testns" + return $ksft_skip + fi + + # 1. Create a dummy Ethernet interface + run_cmd ip -n $testns link add ${devdummy} type dummy + run_cmd ip -n $testns link set ${devdummy} up + run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.use_tempaddr=1 + run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.temp_prefered_lft=10 + run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.temp_valid_lft=25 + run_cmd ip netns exec $testns sysctl -w net.ipv6.conf.${devdummy}.max_desync_factor=1 + + # 2. Create several mngtmpaddr addresses on that interface. + # with temp_*_lft configured to be pretty short (10 and 35 seconds + # for prefer/valid respectively) + for i in $(seq 1 9); do + run_cmd ip -n $testns addr add 2001:db8:7e57:${i}::1/64 mngtmpaddr dev ${devdummy} + done + + # 3. Confirm that a preferred temporary address exists for each mngtmpaddr + # address at all times, polling once per second for 30 seconds. + slowwait 30 validate_mngtmpaddr ${devdummy} + + # 4. Delete each mngtmpaddr address, one at a time (alternating between + # deleting and merely un-mngtmpaddr-ing), and confirm that the other + # mngtmpaddr addresses still have preferred temporaries. + for i in $(seq 1 9); do + (( $i % 4 == 0 )) && mng_flag="mngtmpaddr" || mng_flag="" + if (( $i % 2 == 0 )); then + run_cmd ip -n $testns addr del 2001:db8:7e57:${i}::1/64 $mng_flag dev ${devdummy} + else + run_cmd ip -n $testns addr change 2001:db8:7e57:${i}::1/64 dev ${devdummy} + fi + # the temp addr should be deleted + validate_mngtmpaddr ${devdummy} + done + + if [ $ret -ne 0 ]; then + end_test "FAIL: mngtmpaddr add/remove incorrect" + else + end_test "PASS: mngtmpaddr add/remove correctly" + fi + + ip netns del "$testns" + return $ret +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 7ce03d832b64..099b8c1f46f8 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= hwprobe vector mm sigreturn +RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/abi/.gitignore b/tools/testing/selftests/riscv/abi/.gitignore new file mode 100644 index 000000000000..b38358f91c4d --- /dev/null +++ b/tools/testing/selftests/riscv/abi/.gitignore @@ -0,0 +1 @@ +pointer_masking diff --git a/tools/testing/selftests/riscv/abi/Makefile b/tools/testing/selftests/riscv/abi/Makefile new file mode 100644 index 000000000000..ed82ff9c664e --- /dev/null +++ b/tools/testing/selftests/riscv/abi/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += -I$(top_srcdir)/tools/include + +TEST_GEN_PROGS := pointer_masking + +include ../../lib.mk + +$(OUTPUT)/pointer_masking: pointer_masking.c + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c new file mode 100644 index 000000000000..dee41b7ee3e3 --- /dev/null +++ b/tools/testing/selftests/riscv/abi/pointer_masking.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <errno.h> +#include <fcntl.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../../kselftest.h" + +#ifndef PR_PMLEN_SHIFT +#define PR_PMLEN_SHIFT 24 +#endif +#ifndef PR_PMLEN_MASK +#define PR_PMLEN_MASK (0x7fUL << PR_PMLEN_SHIFT) +#endif + +static int dev_zero; + +static int pipefd[2]; + +static sigjmp_buf jmpbuf; + +static void sigsegv_handler(int sig) +{ + siglongjmp(jmpbuf, 1); +} + +static int min_pmlen; +static int max_pmlen; + +static inline bool valid_pmlen(int pmlen) +{ + return pmlen == 0 || pmlen == 7 || pmlen == 16; +} + +static void test_pmlen(void) +{ + ksft_print_msg("Testing available PMLEN values\n"); + + for (int request = 0; request <= 16; request++) { + int pmlen, ret; + + ret = prctl(PR_SET_TAGGED_ADDR_CTRL, request << PR_PMLEN_SHIFT, 0, 0, 0); + if (ret) + goto pr_set_error; + + ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0); + ksft_test_result(ret >= 0, "PMLEN=%d PR_GET_TAGGED_ADDR_CTRL\n", request); + if (ret < 0) + goto pr_get_error; + + pmlen = (ret & PR_PMLEN_MASK) >> PR_PMLEN_SHIFT; + ksft_test_result(pmlen >= request, "PMLEN=%d constraint\n", request); + ksft_test_result(valid_pmlen(pmlen), "PMLEN=%d validity\n", request); + + if (min_pmlen == 0) + min_pmlen = pmlen; + if (max_pmlen < pmlen) + max_pmlen = pmlen; + + continue; + +pr_set_error: + ksft_test_result_skip("PMLEN=%d PR_GET_TAGGED_ADDR_CTRL\n", request); +pr_get_error: + ksft_test_result_skip("PMLEN=%d constraint\n", request); + ksft_test_result_skip("PMLEN=%d validity\n", request); + } + + if (max_pmlen == 0) + ksft_exit_fail_msg("Failed to enable pointer masking\n"); +} + +static int set_tagged_addr_ctrl(int pmlen, bool tagged_addr_abi) +{ + int arg, ret; + + arg = pmlen << PR_PMLEN_SHIFT | tagged_addr_abi; + ret = prctl(PR_SET_TAGGED_ADDR_CTRL, arg, 0, 0, 0); + if (!ret) { + ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0); + if (ret == arg) + return 0; + } + + return ret < 0 ? -errno : -ENODATA; +} + +static void test_dereference_pmlen(int pmlen) +{ + static volatile int i; + volatile int *p; + int ret; + + ret = set_tagged_addr_ctrl(pmlen, false); + if (ret) + return ksft_test_result_error("PMLEN=%d setup (%d)\n", pmlen, ret); + + i = pmlen; + + if (pmlen) { + p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen)); + + /* These dereferences should succeed. */ + if (sigsetjmp(jmpbuf, 1)) + return ksft_test_result_fail("PMLEN=%d valid tag\n", pmlen); + if (*p != pmlen) + return ksft_test_result_fail("PMLEN=%d bad value\n", pmlen); + ++*p; + } + + p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen - 1)); + + /* These dereferences should raise SIGSEGV. */ + if (sigsetjmp(jmpbuf, 1)) + return ksft_test_result_pass("PMLEN=%d dereference\n", pmlen); + ++*p; + ksft_test_result_fail("PMLEN=%d invalid tag\n", pmlen); +} + +static void test_dereference(void) +{ + ksft_print_msg("Testing userspace pointer dereference\n"); + + signal(SIGSEGV, sigsegv_handler); + + test_dereference_pmlen(0); + test_dereference_pmlen(min_pmlen); + test_dereference_pmlen(max_pmlen); + + signal(SIGSEGV, SIG_DFL); +} + +static void execve_child_sigsegv_handler(int sig) +{ + exit(42); +} + +static int execve_child(void) +{ + static volatile int i; + volatile int *p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - 7)); + + signal(SIGSEGV, execve_child_sigsegv_handler); + + /* This dereference should raise SIGSEGV. */ + return *p; +} + +static void test_fork_exec(void) +{ + int ret, status; + + ksft_print_msg("Testing fork/exec behavior\n"); + + ret = set_tagged_addr_ctrl(min_pmlen, false); + if (ret) + return ksft_test_result_error("setup (%d)\n", ret); + + if (fork()) { + wait(&status); + ksft_test_result(WIFEXITED(status) && WEXITSTATUS(status) == 42, + "dereference after fork\n"); + } else { + static volatile int i = 42; + volatile int *p; + + p = (volatile int *)((uintptr_t)&i | 1UL << (__riscv_xlen - min_pmlen)); + + /* This dereference should succeed. */ + exit(*p); + } + + if (fork()) { + wait(&status); + ksft_test_result(WIFEXITED(status) && WEXITSTATUS(status) == 42, + "dereference after fork+exec\n"); + } else { + /* Will call execve_child(). */ + execve("/proc/self/exe", (char *const []) { "", NULL }, NULL); + } +} + +static void test_tagged_addr_abi_sysctl(void) +{ + char value; + int fd; + + ksft_print_msg("Testing tagged address ABI sysctl\n"); + + fd = open("/proc/sys/abi/tagged_addr_disabled", O_WRONLY); + if (fd < 0) { + ksft_test_result_skip("failed to open sysctl file\n"); + ksft_test_result_skip("failed to open sysctl file\n"); + return; + } + + value = '1'; + pwrite(fd, &value, 1, 0); + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, + "sysctl disabled\n"); + + value = '0'; + pwrite(fd, &value, 1, 0); + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, + "sysctl enabled\n"); + + set_tagged_addr_ctrl(0, false); + + close(fd); +} + +static void test_tagged_addr_abi_pmlen(int pmlen) +{ + int i, *p, ret; + + i = ~pmlen; + + if (pmlen) { + p = (int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen)); + + ret = set_tagged_addr_ctrl(pmlen, false); + if (ret) + return ksft_test_result_error("PMLEN=%d ABI disabled setup (%d)\n", + pmlen, ret); + + ret = write(pipefd[1], p, sizeof(*p)); + if (ret >= 0 || errno != EFAULT) + return ksft_test_result_fail("PMLEN=%d ABI disabled write\n", pmlen); + + ret = read(dev_zero, p, sizeof(*p)); + if (ret >= 0 || errno != EFAULT) + return ksft_test_result_fail("PMLEN=%d ABI disabled read\n", pmlen); + + if (i != ~pmlen) + return ksft_test_result_fail("PMLEN=%d ABI disabled value\n", pmlen); + + ret = set_tagged_addr_ctrl(pmlen, true); + if (ret) + return ksft_test_result_error("PMLEN=%d ABI enabled setup (%d)\n", + pmlen, ret); + + ret = write(pipefd[1], p, sizeof(*p)); + if (ret != sizeof(*p)) + return ksft_test_result_fail("PMLEN=%d ABI enabled write\n", pmlen); + + ret = read(dev_zero, p, sizeof(*p)); + if (ret != sizeof(*p)) + return ksft_test_result_fail("PMLEN=%d ABI enabled read\n", pmlen); + + if (i) + return ksft_test_result_fail("PMLEN=%d ABI enabled value\n", pmlen); + + i = ~pmlen; + } else { + /* The tagged address ABI cannot be enabled when PMLEN == 0. */ + ret = set_tagged_addr_ctrl(pmlen, true); + if (ret != -EINVAL) + return ksft_test_result_error("PMLEN=%d ABI setup (%d)\n", + pmlen, ret); + } + + p = (int *)((uintptr_t)&i | 1UL << (__riscv_xlen - pmlen - 1)); + + ret = write(pipefd[1], p, sizeof(*p)); + if (ret >= 0 || errno != EFAULT) + return ksft_test_result_fail("PMLEN=%d invalid tag write (%d)\n", pmlen, errno); + + ret = read(dev_zero, p, sizeof(*p)); + if (ret >= 0 || errno != EFAULT) + return ksft_test_result_fail("PMLEN=%d invalid tag read\n", pmlen); + + if (i != ~pmlen) + return ksft_test_result_fail("PMLEN=%d invalid tag value\n", pmlen); + + ksft_test_result_pass("PMLEN=%d tagged address ABI\n", pmlen); +} + +static void test_tagged_addr_abi(void) +{ + ksft_print_msg("Testing tagged address ABI\n"); + + test_tagged_addr_abi_pmlen(0); + test_tagged_addr_abi_pmlen(min_pmlen); + test_tagged_addr_abi_pmlen(max_pmlen); +} + +static struct test_info { + unsigned int nr_tests; + void (*test_fn)(void); +} tests[] = { + { .nr_tests = 17 * 3, test_pmlen }, + { .nr_tests = 3, test_dereference }, + { .nr_tests = 2, test_fork_exec }, + { .nr_tests = 2, test_tagged_addr_abi_sysctl }, + { .nr_tests = 3, test_tagged_addr_abi }, +}; + +int main(int argc, char **argv) +{ + unsigned int plan = 0; + int ret; + + /* Check if this is the child process after execve(). */ + if (!argv[0][0]) + return execve_child(); + + dev_zero = open("/dev/zero", O_RDWR); + if (dev_zero < 0) + return 1; + + /* Write to a pipe so the kernel must dereference the buffer pointer. */ + ret = pipe(pipefd); + if (ret) + return 1; + + ksft_print_header(); + + for (int i = 0; i < ARRAY_SIZE(tests); i++) + plan += tests[i].nr_tests; + + ksft_set_plan(plan); + + for (int i = 0; i < ARRAY_SIZE(tests); i++) + tests[i].test_fn(); + + ksft_finished(); +} |