#include "../../util/kvm-stat.h" #include #include #include define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS); static struct kvm_events_ops exit_events = { .is_begin_event = exit_event_begin, .is_end_event = exit_event_end, .decode_key = exit_event_decode_key, .name = "VM-EXIT" }; const char *vcpu_id_str = "vcpu_id"; const int decode_str_len = 20; const char *kvm_exit_reason = "exit_reason"; const char *kvm_entry_trace = "kvm:kvm_entry"; const char *kvm_exit_trace = "kvm:kvm_exit"; /* * For the mmio events, we treat: * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). */ static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) { key->key = perf_evsel__intval(evsel, sample, "gpa"); key->info = perf_evsel__intval(evsel, sample, "type"); } #define KVM_TRACE_MMIO_READ_UNSATISFIED 0 #define KVM_TRACE_MMIO_READ 1 #define KVM_TRACE_MMIO_WRITE 2 static bool mmio_event_begin(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO read begin event in kernel. */ if (kvm_exit_event(evsel)) return true; /* MMIO write begin event in kernel. */ if (!strcmp(evsel->name, "kvm:kvm_mmio") && perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { mmio_event_get_key(evsel, sample, key); return true; } return false; } static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO write end event in kernel. */ if (kvm_entry_event(evsel)) return true; /* MMIO read end event in kernel.*/ if (!strcmp(evsel->name, "kvm:kvm_mmio") && perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { mmio_event_get_key(evsel, sample, key); return true; } return false; } static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { scnprintf(decode, decode_str_len, "%#lx:%s", (unsigned long)key->key, key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); } static struct kvm_events_ops mmio_events = { .is_begin_event = mmio_event_begin, .is_end_event = mmio_event_end, .decode_key = mmio_event_decode_key, .name = "MMIO Access" }; /* The time of emulation pio access is from kvm_pio to kvm_entry. */ static void ioport_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) { key->key = perf_evsel__intval(evsel, sample, "port"); key->info = perf_evsel__intval(evsel, sample, "rw"); } static bool ioport_event_begin(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) { if (!strcmp(evsel->name, "kvm:kvm_pio")) { ioport_event_get_key(evsel, sample, key); return true; } return false; } static bool ioport_event_end(struct perf_evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { return kvm_entry_event(evsel); } static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { scnprintf(decode, decode_str_len, "%#llx:%s", (unsigned long long)key->key, key->info ? "POUT" : "PIN"); } static struct kvm_events_ops ioport_events = { .is_begin_event = ioport_event_begin, .is_end_event = ioport_event_end, .decode_key = ioport_event_decode_key, .name = "IO Port Access" }; const char *kvm_events_tp[] = { "kvm:kvm_entry", "kvm:kvm_exit", "kvm:kvm_mmio", "kvm:kvm_pio", NULL, }; struct kvm_reg_events_ops kvm_reg_events_ops[] = { { .name = "vmexit", .ops = &exit_events }, { .name = "mmio", .ops = &mmio_events }, { .name = "ioport", .ops = &ioport_events }, { NULL, NULL }, }; const char * const kvm_skip_events[] = { "HLT", NULL, }; int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) { if (strstr(cpuid, "Intel")) { kvm->exit_reasons = vmx_exit_reasons; kvm->exit_reasons_isa = "VMX"; } else if (strstr(cpuid, "AMD")) { kvm->exit_reasons = svm_exit_reasons; kvm->exit_reasons_isa = "SVM"; } else return -ENOTSUP; return 0; } d>space:mode:
authorSrinivas Pandruvada <srinivas.pandruvada@linux.intel.com>2017-02-03 14:18:39 -0800
committerRafael J. Wysocki <rafael.j.wysocki@intel.com>2017-02-04 00:11:08 +0100
commit6e978b22efa1db9f6e71b24440b5f1d93e968ee3 (patch)
treec666f7a26b860674848949e39a610222b0723f89 /net/vmw_vsock/Makefile
parent3c223c19aea85d3dda1416c187915f4a30b04b1f (diff)
cpufreq: intel_pstate: Disable energy efficiency optimization
Some Kabylake desktop processors may not reach max turbo when running in HWP mode, even if running under sustained 100% utilization. This occurs when the HWP.EPP (Energy Performance Preference) is set to "balance_power" (0x80) -- the default on most systems. It occurs because the platform BIOS may erroneously enable an energy-efficiency setting -- MSR_IA32_POWER_CTL BIT-EE, which is not recommended to be enabled on this SKU. On the failing systems, this BIOS issue was not discovered when the desktop motherboard was tested with Windows, because the BIOS also neglects to provide the ACPI/CPPC table, that Windows requires to enable HWP, and so Windows runs in legacy P-state mode, where this setting has no effect. Linux' intel_pstate driver does not require ACPI/CPPC to enable HWP, and so it runs in HWP mode, exposing this incorrect BIOS configuration. There are several ways to address this problem. First, Linux can also run in legacy P-state mode on this system. As intel_pstate is how Linux enables HWP, booting with "intel_pstate=disable" will run in acpi-cpufreq/ondemand legacy p-state mode. Or second, the "performance" governor can be used with intel_pstate, which will modify HWP.EPP to 0. Or third, starting in 4.10, the /sys/devices/system/cpu/cpufreq/policy*/energy_performance_preference attribute in can be updated from "balance_power" to "performance". Or fourth, apply this patch, which fixes the erroneous setting of MSR_IA32_POWER_CTL BIT_EE on this model, allowing the default configuration to function as designed. Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Reviewed-by: Len Brown <len.brown@intel.com> Cc: 4.6+ <stable@vger.kernel.org> # 4.6+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Diffstat (limited to 'net/vmw_vsock/Makefile')