From 47e5abfb546a3ace23a77453dc2e9db92704c5ac Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 14 Jun 2018 10:01:52 +0200 Subject: [PATCH 01/14] PM / core: Fix supplier device runtime PM usage counter imbalance If a device link is added via device_link_add() by the driver of the link's consumer device, the supplier's runtime PM usage counter is going to be dropped by the pm_runtime_put_suppliers() call in driver_probe_device(). However, in that case it is not incremented unless the supplier driver is already present and the link is not stateless. That leads to a runtime PM usage counter imbalance for the supplier device in a few cases. To prevent that from happening, bump up the supplier runtime PM usage counter in device_link_add() for all links with the DL_FLAG_PM_RUNTIME flag set that are added at the consumer probe time. Use pm_runtime_get_noresume() for that as the callers of device_link_add() who want the supplier to be resumed by it are expected to pass DL_FLAG_RPM_ACTIVE in flags to it anyway, but additionally resume the supplier if the link is added during consumer driver probe to retain the existing behavior for the callers depending on it. Fixes: 21d5c57b3726 (PM / runtime: Use device links) Reported-by: Ulf Hansson Reviewed-by: Ulf Hansson Tested-by: Marek Szyprowski Cc: 4.10+ # 4.10+ Signed-off-by: Rafael J. Wysocki --- drivers/base/core.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 36622b52e419..df3e1a44707a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -236,6 +236,13 @@ struct device_link *device_link_add(struct device *consumer, link->rpm_active = true; } pm_runtime_new_link(consumer); + /* + * If the link is being added by the consumer driver at probe + * time, balance the decrementation of the supplier's runtime PM + * usage counter after consumer probe in driver_probe_device(). + */ + if (consumer->links.status == DL_DEV_PROBING) + pm_runtime_get_noresume(supplier); } get_device(supplier); link->supplier = supplier; @@ -255,12 +262,12 @@ struct device_link *device_link_add(struct device *consumer, switch (consumer->links.status) { case DL_DEV_PROBING: /* - * Balance the decrementation of the supplier's - * runtime PM usage counter after consumer probe - * in driver_probe_device(). + * Some callers expect the link creation during + * consumer driver probe to resume the supplier + * even without DL_FLAG_RPM_ACTIVE. */ if (flags & DL_FLAG_PM_RUNTIME) - pm_runtime_get_sync(supplier); + pm_runtime_resume(supplier); link->status = DL_STATE_CONSUMER_PROBE; break; From ee3dbcf963c17775417d2fdf74e60f0c1b563dda Mon Sep 17 00:00:00 2001 From: Ilia Lin Date: Sun, 17 Jun 2018 21:58:42 +0200 Subject: [PATCH 02/14] cpufreq: kryo: Fix possible error code dereference In event of error returned by the nvmem_cell_read() non-pointer value may be dereferenced. Fix this with error handling. Additionally free the allocated speedbin buffer, as per the API. Fixes: 9ce36edd1a52 (cpufreq: Add Kryo CPU scaling driver) Signed-off-by: Ilia Lin Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/qcom-cpufreq-kryo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index d049fe4b80c4..74b9b93d511b 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -115,6 +115,8 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) speedbin = nvmem_cell_read(speedbin_nvmem, &len); nvmem_cell_put(speedbin_nvmem); + if (IS_ERR(speedbin)) + return PTR_ERR(speedbin); switch (msm8996_version) { case MSM8996_V3: @@ -127,6 +129,7 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) BUG(); break; } + kfree(speedbin); for_each_possible_cpu(cpu) { cpu_dev = get_cpu_device(cpu); From 5ad7346b4ae2d59cfee106ec8e40ee2561476d47 Mon Sep 17 00:00:00 2001 From: Ilia Lin Date: Sun, 17 Jun 2018 22:01:46 +0200 Subject: [PATCH 03/14] cpufreq: kryo: Add module remove and exit Add device remove and module exit code to make the driver functioning as a loadable module. Fixes: ac28927659be (cpufreq: kryo: allow building as a loadable module) Signed-off-by: Ilia Lin Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/qcom-cpufreq-kryo.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index 74b9b93d511b..01bddacf5c3b 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -42,6 +42,8 @@ enum _msm8996_version { NUM_OF_MSM8996_VERSIONS, }; +struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev; + static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void) { size_t len; @@ -74,7 +76,6 @@ static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void) static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) { struct opp_table *opp_tables[NR_CPUS] = {0}; - struct platform_device *cpufreq_dt_pdev; enum _msm8996_version msm8996_version; struct nvmem_cell *speedbin_nvmem; struct device_node *np; @@ -165,8 +166,15 @@ free_opp: return ret; } +static int qcom_cpufreq_kryo_remove(struct platform_device *pdev) +{ + platform_device_unregister(cpufreq_dt_pdev); + return 0; +} + static struct platform_driver qcom_cpufreq_kryo_driver = { .probe = qcom_cpufreq_kryo_probe, + .remove = qcom_cpufreq_kryo_remove, .driver = { .name = "qcom-cpufreq-kryo", }, @@ -201,8 +209,9 @@ static int __init qcom_cpufreq_kryo_init(void) if (unlikely(ret < 0)) return ret; - ret = PTR_ERR_OR_ZERO(platform_device_register_simple( - "qcom-cpufreq-kryo", -1, NULL, 0)); + kryo_cpufreq_pdev = platform_device_register_simple( + "qcom-cpufreq-kryo", -1, NULL, 0); + ret = PTR_ERR_OR_ZERO(kryo_cpufreq_pdev); if (0 == ret) return 0; @@ -211,5 +220,12 @@ static int __init qcom_cpufreq_kryo_init(void) } module_init(qcom_cpufreq_kryo_init); +static void __init qcom_cpufreq_kryo_exit(void) +{ + platform_device_unregister(kryo_cpufreq_pdev); + platform_driver_unregister(&qcom_cpufreq_kryo_driver); +} +module_exit(qcom_cpufreq_kryo_exit); + MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver"); MODULE_LICENSE("GPL v2"); From ff7c9917143b3a6cf2fa61212a32d67cf259bf9c Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Mon, 18 Jun 2018 12:47:45 -0700 Subject: [PATCH 04/14] cpufreq: intel_pstate: Fix scaling max/min limits with Turbo 3.0 When scaling max/min settings are changed, internally they are converted to a ratio using the max turbo 1 core turbo frequency. This works fine when 1 core max is same irrespective of the core. But under Turbo 3.0, this will not be the case. For example: Core 0: max turbo pstate: 43 (4.3GHz) Core 1: max turbo pstate: 45 (4.5GHz) In this case 1 core turbo ratio will be maximum of all, so it will be 45 (4.5GHz). Suppose scaling max is set to 4GHz (ratio 40) for all cores ,then on core one it will be = max_state * policy->max / max_freq; = 43 * (4000000/4500000) = 38 (3.8GHz) = 38 which is 200MHz less than the desired. On core2, it will be correctly set to ratio 40 (4GHz). Same holds true for scaling min frequency limit. So this requires usage of correct turbo max frequency for core one, which in this case is 4.3GHz. So we need to adjust per CPU cpu->pstate.turbo_freq using the maximum HWP ratio of that core. This change uses the HWP capability of a core to adjust max turbo frequency. But since Broadwell HWP doesn't use ratios in the HWP capabilities, we have to use legacy max 1 core turbo ratio. This is not a problem as the HWP capabilities don't differ among cores in Broadwell. We need to check for non Broadwell CPU model for applying this change, though. Signed-off-by: Srinivas Pandruvada Cc: 4.6+ # 4.6+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1de5ec8d5ea3..ece120da3353 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -294,6 +294,7 @@ struct pstate_funcs { static struct pstate_funcs pstate_funcs __read_mostly; static int hwp_active __read_mostly; +static int hwp_mode_bdw __read_mostly; static bool per_cpu_limits __read_mostly; static bool hwp_boost __read_mostly; @@ -1413,7 +1414,15 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); cpu->pstate.scaling = pstate_funcs.get_scaling(); cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; - cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + + if (hwp_active && !hwp_mode_bdw) { + unsigned int phy_max, current_max; + + intel_pstate_get_hwp_max(cpu->cpu, &phy_max, ¤t_max); + cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling; + } else { + cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + } if (pstate_funcs.get_aperf_mperf_shift) cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift(); @@ -2467,28 +2476,36 @@ static inline bool intel_pstate_has_acpi_ppc(void) { return false; } static inline void intel_pstate_request_control_from_smm(void) {} #endif /* CONFIG_ACPI */ +#define INTEL_PSTATE_HWP_BROADWELL 0x01 + +#define ICPU_HWP(model, hwp_mode) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_HWP, hwp_mode } + static const struct x86_cpu_id hwp_support_ids[] __initconst = { - { X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP }, + ICPU_HWP(INTEL_FAM6_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL), + ICPU_HWP(INTEL_FAM6_BROADWELL_XEON_D, INTEL_PSTATE_HWP_BROADWELL), + ICPU_HWP(X86_MODEL_ANY, 0), {} }; static int __init intel_pstate_init(void) { + const struct x86_cpu_id *id; int rc; if (no_load) return -ENODEV; - if (x86_match_cpu(hwp_support_ids)) { + id = x86_match_cpu(hwp_support_ids); + if (id) { copy_cpu_funcs(&core_funcs); if (!no_hwp) { hwp_active++; + hwp_mode_bdw = id->driver_data; intel_pstate.attr = hwp_cpufreq_attrs; goto hwp_cpu_matched; } } else { - const struct x86_cpu_id *id; - id = x86_match_cpu(intel_pstate_cpu_ids); if (!id) return -ENODEV; From c5c2a97b3ac7d1ec19e7cff9e38caca6afefc3de Mon Sep 17 00:00:00 2001 From: Waldemar Rymarkiewicz Date: Thu, 14 Jun 2018 15:56:08 +0200 Subject: [PATCH 05/14] PM / OPP: Update voltage in case freq == old_freq This commit fixes a rare but possible case when the clk rate is updated without update of the regulator voltage. At boot up, CPUfreq checks if the system is running at the right freq. This is a sanity check in case a bootloader set clk rate that is outside of freq table present with cpufreq core. In such cases system can be unstable so better to change it to a freq that is preset in freq-table. The CPUfreq takes next freq that is >= policy->cur and this is our target_freq that needs to be set now. dev_pm_opp_set_rate(dev, target_freq) checks the target_freq and the old_freq (a current rate). If these are equal it returns early. If not, it searches for OPP (old_opp) that fits best to old_freq (not listed in the table) and updates old_freq (!). Here, we can end up with old_freq = old_opp.rate = target_freq, which is not handled in _generic_set_opp_regulator(). It's supposed to update voltage only when freq > old_freq || freq > old_freq. if (freq > old_freq) { ret = _set_opp_voltage(dev, reg, new_supply); [...] if (freq < old_freq) { ret = _set_opp_voltage(dev, reg, new_supply); if (ret) It results in, no voltage update while clk rate is updated. Example: freq-table = { 1000MHz 1.15V 666MHZ 1.10V 333MHz 1.05V } boot-up-freq = 800MHz # not listed in freq-table freq = target_freq = 1GHz old_freq = 800Mhz old_opp = _find_freq_ceil(opp_table, &old_freq); #(old_freq is modified!) old_freq = 1GHz Fixes: 6a0712f6f199 ("PM / OPP: Add dev_pm_opp_set_rate()") Cc: 4.6+ # v4.6+ Signed-off-by: Waldemar Rymarkiewicz Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/opp/core.c b/drivers/opp/core.c index ab2f3fead6b1..31ff03dbeb83 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -598,7 +598,7 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table, } /* Scaling up? Scale voltage before frequency */ - if (freq > old_freq) { + if (freq >= old_freq) { ret = _set_opp_voltage(dev, reg, new_supply); if (ret) goto restore_voltage; From bdd5ae3aa51939bb1fd26cd9fe7af07ca8c60397 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 6 Jun 2018 17:18:36 -0400 Subject: [PATCH 06/14] tools/power turbostat: fix show/hide issues resulting from mis-merge The --show and --hide options failed on "Node", which was listed as "Node%". The --show and --hide options were generally fouled-up do due to come content merges that scrambled the list of column name indexes. Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 106 +++++++++++++------------- 1 file changed, 54 insertions(+), 52 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d6cff3070ebd..f09a272941a1 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -381,19 +381,23 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) } /* - * Each string in this array is compared in --show and --hide cmdline. - * Thus, strings that are proper sub-sets must follow their more specific peers. + * This list matches the column headers, except + * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time + * 2. Core and CPU are moved to the end, we can't have strings that contain them + * matching on them for --show and --hide. */ struct msr_counter bic[] = { { 0x0, "usec" }, { 0x0, "Time_Of_Day_Seconds" }, { 0x0, "Package" }, + { 0x0, "Node" }, { 0x0, "Avg_MHz" }, + { 0x0, "Busy%" }, { 0x0, "Bzy_MHz" }, { 0x0, "TSC_MHz" }, { 0x0, "IRQ" }, { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL}, - { 0x0, "Busy%" }, + { 0x0, "sysfs" }, { 0x0, "CPU%c1" }, { 0x0, "CPU%c3" }, { 0x0, "CPU%c6" }, @@ -424,15 +428,13 @@ struct msr_counter bic[] = { { 0x0, "Cor_J" }, { 0x0, "GFX_J" }, { 0x0, "RAM_J" }, - { 0x0, "Core" }, - { 0x0, "CPU" }, { 0x0, "Mod%c6" }, - { 0x0, "sysfs" }, { 0x0, "Totl%C0" }, { 0x0, "Any%C0" }, { 0x0, "GFX%C0" }, { 0x0, "CPUGFX%" }, - { 0x0, "Node%" }, + { 0x0, "Core" }, + { 0x0, "CPU" }, }; @@ -441,51 +443,51 @@ struct msr_counter bic[] = { #define BIC_USEC (1ULL << 0) #define BIC_TOD (1ULL << 1) #define BIC_Package (1ULL << 2) -#define BIC_Avg_MHz (1ULL << 3) -#define BIC_Bzy_MHz (1ULL << 4) -#define BIC_TSC_MHz (1ULL << 5) -#define BIC_IRQ (1ULL << 6) -#define BIC_SMI (1ULL << 7) -#define BIC_Busy (1ULL << 8) -#define BIC_CPU_c1 (1ULL << 9) -#define BIC_CPU_c3 (1ULL << 10) -#define BIC_CPU_c6 (1ULL << 11) -#define BIC_CPU_c7 (1ULL << 12) -#define BIC_ThreadC (1ULL << 13) -#define BIC_CoreTmp (1ULL << 14) -#define BIC_CoreCnt (1ULL << 15) -#define BIC_PkgTmp (1ULL << 16) -#define BIC_GFX_rc6 (1ULL << 17) -#define BIC_GFXMHz (1ULL << 18) -#define BIC_Pkgpc2 (1ULL << 19) -#define BIC_Pkgpc3 (1ULL << 20) -#define BIC_Pkgpc6 (1ULL << 21) -#define BIC_Pkgpc7 (1ULL << 22) -#define BIC_Pkgpc8 (1ULL << 23) -#define BIC_Pkgpc9 (1ULL << 24) -#define BIC_Pkgpc10 (1ULL << 25) -#define BIC_CPU_LPI (1ULL << 26) -#define BIC_SYS_LPI (1ULL << 27) -#define BIC_PkgWatt (1ULL << 26) -#define BIC_CorWatt (1ULL << 27) -#define BIC_GFXWatt (1ULL << 28) -#define BIC_PkgCnt (1ULL << 29) -#define BIC_RAMWatt (1ULL << 30) -#define BIC_PKG__ (1ULL << 31) -#define BIC_RAM__ (1ULL << 32) -#define BIC_Pkg_J (1ULL << 33) -#define BIC_Cor_J (1ULL << 34) -#define BIC_GFX_J (1ULL << 35) -#define BIC_RAM_J (1ULL << 36) -#define BIC_Core (1ULL << 37) -#define BIC_CPU (1ULL << 38) -#define BIC_Mod_c6 (1ULL << 39) -#define BIC_sysfs (1ULL << 40) -#define BIC_Totl_c0 (1ULL << 41) -#define BIC_Any_c0 (1ULL << 42) -#define BIC_GFX_c0 (1ULL << 43) -#define BIC_CPUGFX (1ULL << 44) -#define BIC_Node (1ULL << 45) +#define BIC_Node (1ULL << 3) +#define BIC_Avg_MHz (1ULL << 4) +#define BIC_Busy (1ULL << 5) +#define BIC_Bzy_MHz (1ULL << 6) +#define BIC_TSC_MHz (1ULL << 7) +#define BIC_IRQ (1ULL << 8) +#define BIC_SMI (1ULL << 9) +#define BIC_sysfs (1ULL << 10) +#define BIC_CPU_c1 (1ULL << 11) +#define BIC_CPU_c3 (1ULL << 12) +#define BIC_CPU_c6 (1ULL << 13) +#define BIC_CPU_c7 (1ULL << 14) +#define BIC_ThreadC (1ULL << 15) +#define BIC_CoreTmp (1ULL << 16) +#define BIC_CoreCnt (1ULL << 17) +#define BIC_PkgTmp (1ULL << 18) +#define BIC_GFX_rc6 (1ULL << 19) +#define BIC_GFXMHz (1ULL << 20) +#define BIC_Pkgpc2 (1ULL << 21) +#define BIC_Pkgpc3 (1ULL << 22) +#define BIC_Pkgpc6 (1ULL << 23) +#define BIC_Pkgpc7 (1ULL << 24) +#define BIC_Pkgpc8 (1ULL << 25) +#define BIC_Pkgpc9 (1ULL << 26) +#define BIC_Pkgpc10 (1ULL << 27) +#define BIC_CPU_LPI (1ULL << 28) +#define BIC_SYS_LPI (1ULL << 29) +#define BIC_PkgWatt (1ULL << 30) +#define BIC_CorWatt (1ULL << 31) +#define BIC_GFXWatt (1ULL << 32) +#define BIC_PkgCnt (1ULL << 33) +#define BIC_RAMWatt (1ULL << 34) +#define BIC_PKG__ (1ULL << 35) +#define BIC_RAM__ (1ULL << 36) +#define BIC_Pkg_J (1ULL << 37) +#define BIC_Cor_J (1ULL << 38) +#define BIC_GFX_J (1ULL << 39) +#define BIC_RAM_J (1ULL << 40) +#define BIC_Mod_c6 (1ULL << 41) +#define BIC_Totl_c0 (1ULL << 42) +#define BIC_Any_c0 (1ULL << 43) +#define BIC_GFX_c0 (1ULL << 44) +#define BIC_CPUGFX (1ULL << 45) +#define BIC_Core (1ULL << 46) +#define BIC_CPU (1ULL << 47) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD) From d9d226ffadbf4a8e60f5b8fc866aaa5028c7e479 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 6 Jun 2018 15:47:36 -0400 Subject: [PATCH 07/14] tools/power turbostat: decode cpuid.1.HT eg. the "HT" here: CPUID(1): SSE3 MONITOR - EIST TM2 TSC MSR ACPI-TM HT TM Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index f09a272941a1..b0f294bf89c3 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -4394,7 +4394,7 @@ void process_cpuid() if (!quiet) { fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", max_level, family, model, stepping, family, model, stepping); - fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n", + fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", ecx & (1 << 0) ? "SSE3" : "-", ecx & (1 << 3) ? "MONITOR" : "-", ecx & (1 << 6) ? "SMX" : "-", @@ -4403,6 +4403,7 @@ void process_cpuid() edx & (1 << 4) ? "TSC" : "-", edx & (1 << 5) ? "MSR" : "-", edx & (1 << 22) ? "ACPI-TM" : "-", + edx & (1 << 28) ? "HT" : "-", edx & (1 << 29) ? "TM" : "-"); } From 4c2122d42116ebaa1665ad0fbef2c558fdc0e3c6 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 6 Jun 2018 17:44:48 -0400 Subject: [PATCH 08/14] tools/power turbostat: add optional APIC X2APIC columns Add APIC and X2APIC columns to the topology section. They are disabled-by-default -- enable like so: --debug or --enable APIC,X2APIC Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.8 | 2 +- tools/power/x86/turbostat/turbostat.c | 75 ++++++++++++++++++++++++--- 2 files changed, 68 insertions(+), 9 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index ca9ef7017624..d39e4ff7d0bf 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -56,7 +56,7 @@ name as necessary to disambiguate it from others is necessary. Note that option .PP \fB--hide column\fP do not show the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group. .PP -\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds". +\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec", "Time_Of_Day_Seconds", "APIC" and "X2APIC". The column name "all" can be used to enable all disabled-by-default built-in counters. .PP \fB--show column\fP show only the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index b0f294bf89c3..3bc2c9d94739 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -109,6 +109,7 @@ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int has_misc_feature_control; +unsigned int first_counter_read = 1; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -170,6 +171,8 @@ struct thread_data { unsigned long long irq_count; unsigned int smi_count; unsigned int cpu_id; + unsigned int apic_id; + unsigned int x2apic_id; unsigned int flags; #define CPU_IS_FIRST_THREAD_IN_CORE 0x2 #define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4 @@ -435,10 +438,10 @@ struct msr_counter bic[] = { { 0x0, "CPUGFX%" }, { 0x0, "Core" }, { 0x0, "CPU" }, + { 0x0, "APIC" }, + { 0x0, "X2APIC" }, }; - - #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) #define BIC_USEC (1ULL << 0) #define BIC_TOD (1ULL << 1) @@ -488,11 +491,13 @@ struct msr_counter bic[] = { #define BIC_CPUGFX (1ULL << 45) #define BIC_Core (1ULL << 46) #define BIC_CPU (1ULL << 47) +#define BIC_APIC (1ULL << 48) +#define BIC_X2APIC (1ULL << 49) -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD) +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); -unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs; +unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) #define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) @@ -603,6 +608,10 @@ void print_header(char *delim) outp += sprintf(outp, "%sCore", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU)) outp += sprintf(outp, "%sCPU", (printed++ ? delim : "")); + if (DO_BIC(BIC_APIC)) + outp += sprintf(outp, "%sAPIC", (printed++ ? delim : "")); + if (DO_BIC(BIC_X2APIC)) + outp += sprintf(outp, "%sX2APIC", (printed++ ? delim : "")); if (DO_BIC(BIC_Avg_MHz)) outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : "")); if (DO_BIC(BIC_Busy)) @@ -882,6 +891,10 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_APIC)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_X2APIC)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } else { if (DO_BIC(BIC_Package)) { if (p) @@ -906,6 +919,10 @@ int format_counters(struct thread_data *t, struct core_data *c, } if (DO_BIC(BIC_CPU)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id); + if (DO_BIC(BIC_APIC)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->apic_id); + if (DO_BIC(BIC_X2APIC)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->x2apic_id); } if (DO_BIC(BIC_Avg_MHz)) @@ -1233,6 +1250,12 @@ delta_thread(struct thread_data *new, struct thread_data *old, int i; struct msr_counter *mp; + /* we run cpuid just the 1st time, copy the results */ + if (DO_BIC(BIC_APIC)) + new->apic_id = old->apic_id; + if (DO_BIC(BIC_X2APIC)) + new->x2apic_id = old->x2apic_id; + /* * the timestamps from start of measurement interval are in "old" * the timestamp from end of measurement interval are in "new" @@ -1395,6 +1418,12 @@ int sum_counters(struct thread_data *t, struct core_data *c, int i; struct msr_counter *mp; + /* copy un-changing apic_id's */ + if (DO_BIC(BIC_APIC)) + average.threads.apic_id = t->apic_id; + if (DO_BIC(BIC_X2APIC)) + average.threads.x2apic_id = t->x2apic_id; + /* remember first tv_begin */ if (average.threads.tv_begin.tv_sec == 0) average.threads.tv_begin = t->tv_begin; @@ -1621,6 +1650,34 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) return 0; } +void get_apic_id(struct thread_data *t) +{ + unsigned int eax, ebx, ecx, edx, max_level; + + eax = ebx = ecx = edx = 0; + + if (!genuine_intel) + return; + + __cpuid(0, max_level, ebx, ecx, edx); + + __cpuid(1, eax, ebx, ecx, edx); + t->apic_id = (ebx >> 24) & 0xf; + + if (max_level < 0xb) + return; + + if (!DO_BIC(BIC_X2APIC)) + return; + + ecx = 0; + __cpuid(0xb, eax, ebx, ecx, edx); + t->x2apic_id = edx; + + if (debug && (t->apic_id != t->x2apic_id)) + fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); +} + /* * get_counters(...) * migrate to cpu @@ -1634,7 +1691,6 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) struct msr_counter *mp; int i; - gettimeofday(&t->tv_begin, (struct timezone *)NULL); if (cpu_migrate(cpu)) { @@ -1642,6 +1698,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -1; } + if (first_counter_read) + get_apic_id(t); retry: t->tsc = rdtsc(); /* we are running on local CPU of interest */ @@ -2881,6 +2939,7 @@ void do_sleep(void) } } + void turbostat_loop() { int retval; @@ -2894,6 +2953,7 @@ restart: snapshot_proc_sysfs_files(); retval = for_all_cpus(get_counters, EVEN_COUNTERS); + first_counter_read = 0; if (retval < -1) { exit(retval); } else if (retval == -1) { @@ -4655,7 +4715,6 @@ void process_cpuid() return; } - /* * in /dev/cpu/ return success for names that are numbers * ie. filter out ".", "..", "microcode". @@ -4949,6 +5008,7 @@ int fork_it(char **argv) snapshot_proc_sysfs_files(); status = for_all_cpus(get_counters, EVEN_COUNTERS); + first_counter_read = 0; if (status) exit(status); /* clear affinity side-effect of get_counters() */ @@ -5384,7 +5444,7 @@ void cmdline(int argc, char **argv) break; case 'e': /* --enable specified counter */ - bic_enabled |= bic_lookup(optarg, SHOW_LIST); + bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST); break; case 'd': debug++; @@ -5468,7 +5528,6 @@ void cmdline(int argc, char **argv) int main(int argc, char **argv) { outf = stderr; - cmdline(argc, argv); if (!quiet) From 42dd45209201edb222de5f9eadc1c8f93700ef28 Mon Sep 17 00:00:00 2001 From: Nathan Ciobanu Date: Fri, 8 Jun 2018 15:15:12 -0700 Subject: [PATCH 09/14] tools/power turbostat: fix segfault on 'no node' machines Running turbostat on machines that don't expose nodes in sysfs (no /sys/bus/node) causes a segfault or a -nan value diesplayed in the log. This is caused by physical_node_id being reported as -1 and logical_node_id being calculated as a negative number resulting in the new GET_THREAD/GET_CORE returning an incorrect address. Signed-off-by: Nathan Ciobanu Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 3bc2c9d94739..97cc00a9c763 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2492,6 +2492,12 @@ void set_node_data(void) if (pni[pkg].count > topo.nodes_per_pkg) topo.nodes_per_pkg = pni[0].count; + /* Fake 1 node per pkg for machines that don't + * expose nodes and thus avoid -nan results + */ + if (topo.nodes_per_pkg == 0) + topo.nodes_per_pkg = 1; + for (cpu = 0; cpu < topo.num_cpus; cpu++) { pkg = cpus[cpu].physical_package_id; node = cpus[cpu].physical_node_id; @@ -4904,6 +4910,13 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base, struct core_data *c; struct pkg_data *p; + + /* Workaround for systems where physical_node_id==-1 + * and logical_node_id==(-1 - topo.num_cpus) + */ + if (node_id < 0) + node_id = 0; + t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id); c = GET_CORE(core_base, core_id, node_id, pkg_id); p = GET_PKG(pkg_base, pkg_id); From 2ee19bdea1bbc04a06606b5c9681a07d005ecbaf Mon Sep 17 00:00:00 2001 From: Nathan Ciobanu Date: Wed, 13 Jun 2018 19:51:32 -0700 Subject: [PATCH 10/14] tools/power turbostat: alphabetize the help output Sort the command line arguments output of help() in alphabetical order in line with other linux tools. Signed-off-by: Nathan Ciobanu Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 97cc00a9c763..d33b655299ba 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -528,12 +528,12 @@ void help(void) " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" "--cpu cpu-set limit output to summary plus cpu-set:\n" " {core | package | j,k,l..m,n-p }\n" - "--quiet skip decoding system configuration header\n" "--interval sec.subsec Override default 5-second measurement interval\n" - "--help print this help message\n" "--list list column headers only\n" "--num_iterations num number of the measurement iterations\n" "--out file create or truncate \"file\" for all output\n" + "--quiet skip decoding system configuration header\n" + "--help print this help message\n" "--version print version information\n" "\n" "For more help, run \"man turbostat\"\n"); From cc4816503f835c7cea184776fe8ae5bb3f505083 Mon Sep 17 00:00:00 2001 From: Nathan Ciobanu Date: Wed, 13 Jun 2018 19:51:33 -0700 Subject: [PATCH 11/14] tools/power turbostat: add single character tokens to help Improve the help() output by adding the single character tokens (e.g -a). Signed-off-by: Nathan Ciobanu Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d33b655299ba..2dcc05f3ee6f 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -524,17 +524,20 @@ void help(void) "when COMMAND completes.\n" "If no COMMAND is specified, turbostat wakes every 5-seconds\n" "to print statistics, until interrupted.\n" - "--add add a counter\n" - " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" - "--cpu cpu-set limit output to summary plus cpu-set:\n" - " {core | package | j,k,l..m,n-p }\n" - "--interval sec.subsec Override default 5-second measurement interval\n" - "--list list column headers only\n" - "--num_iterations num number of the measurement iterations\n" - "--out file create or truncate \"file\" for all output\n" - "--quiet skip decoding system configuration header\n" - "--help print this help message\n" - "--version print version information\n" + " -a, --add add a counter\n" + " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" + " -c, --cpu cpu-set limit output to summary plus cpu-set:\n" + " {core | package | j,k,l..m,n-p }\n" + " -i, --interval sec.subsec\n" + " Override default 5-second measurement interval\n" + " -l, --list list column headers only\n" + " -n, --num_iterations num\n" + " number of the measurement iterations\n" + " -o, --out file\n" + " create or truncate \"file\" for all output\n" + " -q, --quiet skip decoding system configuration header\n" + " -h, --help print this help message\n" + " -v, --version print version information\n" "\n" "For more help, run \"man turbostat\"\n"); } From 9ce80578d5f5279545c272563851d059a2359f3e Mon Sep 17 00:00:00 2001 From: Nathan Ciobanu Date: Wed, 13 Jun 2018 19:51:34 -0700 Subject: [PATCH 12/14] tools/power turbostat: add the missing command line switches Document the missing command line tokens in the help() function. Signed-off-by: Nathan Ciobanu Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 2dcc05f3ee6f..108c3bf2a67c 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -528,14 +528,28 @@ void help(void) " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" " -c, --cpu cpu-set limit output to summary plus cpu-set:\n" " {core | package | j,k,l..m,n-p }\n" + " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n" + " -D, --Dump displays the raw counter values\n" + " -e, --enable [all | column]\n" + " shows all or the specified disabled column\n" + " -H, --hide [column|column,column,...]\n" + " hide the specified column(s)\n" " -i, --interval sec.subsec\n" " Override default 5-second measurement interval\n" + " -J, --Joules displays energy in Joules instead of Watts\n" " -l, --list list column headers only\n" " -n, --num_iterations num\n" " number of the measurement iterations\n" " -o, --out file\n" " create or truncate \"file\" for all output\n" " -q, --quiet skip decoding system configuration header\n" + " -s, --show [column|column,column,...]\n" + " show only the specified column(s)\n" + " -S, --Summary\n" + " limits output to 1-line system summary per interval\n" + " -T, --TCC temperature\n" + " sets the Thermal Control Circuit temperature in\n" + " degrees Celsius\n" " -h, --help print this help message\n" " -v, --version print version information\n" "\n" From 73780cd816e071b0fc0f74e204a9cb30fdb291c5 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 20 Jun 2018 13:55:29 -0400 Subject: [PATCH 13/14] tools/power turbostat: version 18.06.20 Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 108c3bf2a67c..4d14bbbf9b63 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -5102,7 +5102,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 18.06.01" + fprintf(outf, "turbostat version 18.06.20" " - Len Brown \n"); } From 7a0f9d1eb51ff25d119b48fe7cc6aa0433cd6621 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 20 Jun 2018 10:42:07 +0200 Subject: [PATCH 14/14] Documentation: intel_pstate: Fix typo Fix a typo in the intel_pstate admin-guide documentation. Signed-off-by: Rafael J. Wysocki --- Documentation/admin-guide/pm/intel_pstate.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index ab2fe0eda1d7..8b9164990956 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -410,7 +410,7 @@ argument is passed to the kernel in the command line. That only is supported in some configurations, though (for example, if the `HWP feature is enabled in the processor `_, the operation mode of the driver cannot be changed), and if it is not - supported in the current configuration, writes to this attribute with + supported in the current configuration, writes to this attribute will fail with an appropriate error. Interpretation of Policy Attributes