summaryrefslogtreecommitdiffstats
path: root/arch/x86/events
Commit message (Collapse)AuthorAgeFilesLines
* Merge tag 'perf-urgent-2022-06-05' of ↵Linus Torvalds2022-06-051-1/+1
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull perf fixes from Thomas Gleixner: - Make the ICL event constraints match reality - Remove a unused local variable * tag 'perf-urgent-2022-06-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: perf/core: Remove unused local variable perf/x86/intel: Fix event constraints for ICL
| * perf/x86/intel: Fix event constraints for ICLKan Liang2022-05-251-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | According to the latest event list, the event encoding 0x55 INST_DECODED.DECODERS and 0x56 UOPS_DECODED.DEC0 are only available on the first 4 counters. Add them into the event constraints table. Fixes: 6017608936c1 ("perf/x86/intel: Add Icelake support") Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220525133952.1660658-1-kan.liang@linux.intel.com
* | perf/x86/Kconfig: Fix indentation in the Kconfig fileJuerg Haefliger2022-05-251-6/+6
|/ | | | | | | | | | The convention for indentation seems to be a single tab. Help text is further indented by an additional two whitespaces. Fix the lines that violate these rules. Signed-off-by: Juerg Haefliger <juerg.haefliger@canonical.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20220525133949.53730-1-juerg.haefliger@canonical.com
* perf/x86/amd/core: Fix reloading events for SVMSandipan Das2022-05-191-4/+20
| | | | | | | | | | | | | | | | | | | | Commit 1018faa6cf23 ("perf/x86/kvm: Fix Host-Only/Guest-Only counting with SVM disabled") addresses an issue in which the Host-Only bit in the counter control registers needs to be masked off when SVM is not enabled. The events need to be reloaded whenever SVM is enabled or disabled for a CPU and this requires the PERF_CTL registers to be reprogrammed using {enable,disable}_all(). However, PerfMonV2 variants of these functions do not reprogram the PERF_CTL registers. Hence, the legacy enable_all() function should also be called. Fixes: 9622e67e3980 ("perf/x86/amd/core: Add PerfMonV2 counter control") Reported-by: Like Xu <likexu@tencent.com> Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20220518084327.464005-1-sandipan.das@amd.com
* perf/x86/amd: Run AMD BRS code only on supported hwBorislav Petkov2022-05-181-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This fires on a Fam16h machine here: unchecked MSR access error: WRMSR to 0xc000010f (tried to write 0x0000000000000018) \ at rIP: 0xffffffff81007db1 (amd_brs_reset+0x11/0x50) Call Trace: <TASK> amd_pmu_cpu_starting ? x86_pmu_dead_cpu x86_pmu_starting_cpu cpuhp_invoke_callback ? x86_pmu_starting_cpu ? x86_pmu_dead_cpu cpuhp_issue_call ? x86_pmu_starting_cpu __cpuhp_setup_state_cpuslocked ? x86_pmu_dead_cpu ? x86_pmu_starting_cpu __cpuhp_setup_state ? map_vsyscall init_hw_perf_events ? map_vsyscall do_one_initcall ? _raw_spin_unlock_irqrestore ? try_to_wake_up kernel_init_freeable ? rest_init kernel_init ret_from_fork because that CPU hotplug callback gets executed on any AMD CPU - not only on the BRS-enabled ones. Check the BRS feature bit properly. Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-By: Stephane Eranian <eranian@google.com> Link: https://lkml.kernel.org/r/20220516154838.7044-1-bp@alien8.de
* perf/x86/amd: Fix AMD BRS period adjustmentPeter Zijlstra2022-05-183-25/+13
| | | | | | | | | | | | | | | | There's two problems with the current amd_brs_adjust_period() code: - it isn't in fact AMD specific and wil always adjust the period; - it adjusts the period, while it should only adjust the event count, resulting in repoting a short period. Fix this by using x86_pmu.limit_period, this makes it specific to the AMD BRS case and ensures only the event count is adjusted while the reported period is unmodified. Fixes: ba2fe7500845 ("perf/x86/amd: Add AMD branch sampling period adjustment") Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
* perf/x86/amd: Remove unused variable 'hwc'Zucheng Zheng2022-05-121-3/+0
| | | | | | | | 'hwc' is never used in amd_pmu_enable_all(), so remove it. Signed-off-by: Zucheng Zheng <zhengzucheng@huawei.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20220421111031.174698-1-zhengzucheng@huawei.com
* perf/amd/ibs: Advertise zen4_ibs_extensions as pmu capability attributeRavi Bangoria2022-05-111-0/+21
| | | | | | | | | | | | | | | | PMU driver can advertise certain feature via capability attribute('caps' sysfs directory) which can be consumed by userspace tools like perf. Add zen4_ibs_extensions capability attribute for IBS pmus. This attribute will be enabled when CPUID_Fn8000001B_EAX[11] is set. With patch on Zen4: $ ls /sys/bus/event_source/devices/ibs_op/caps zen4_ibs_extensions Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220509044914.1473-5-ravi.bangoria@amd.com
* perf/amd/ibs: Add support for L3 miss filteringRavi Bangoria2022-05-111-7/+60
| | | | | | | | | | | | | | | | | | | IBS L3 miss filtering works by tagging an instruction on IBS counter overflow and generating an NMI if the tagged instruction causes an L3 miss. Samples without an L3 miss are discarded and counter is reset with random value (between 1-15 for fetch pmu and 1-127 for op pmu). This helps in reducing sampling overhead when user is interested only in such samples. One of the use case of such filtered samples is to feed data to page-migration daemon in tiered memory systems. Add support for L3 miss filtering in IBS driver via new pmu attribute "l3missonly". Example usage: # perf record -a -e ibs_op/l3missonly=1/ --raw-samples sleep 5 Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220509044914.1473-4-ravi.bangoria@amd.com
* perf/amd/ibs: Use ->is_visible callback for dynamic attributesRavi Bangoria2022-05-111-24/+54
| | | | | | | | | | | | | | Currently, some attributes are added at build time whereas others at boot time depending on IBS pmu capabilities. Instead, we can just add all attribute groups at build time but hide individual group at boot time using more appropriate ->is_visible() callback. Also, struct perf_ibs has bunch of fields for pmu attributes which just pass on the pointer, does not do anything else. Remove them. Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220509044914.1473-3-ravi.bangoria@amd.com
* perf/amd/ibs: Cascade pmu init functions' return valueRavi Bangoria2022-05-111-8/+29
| | | | | | | | | IBS pmu initialization code ignores return value provided by callee functions. Fix it. Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220509044914.1473-2-ravi.bangoria@amd.com
* perf/x86/uncore: Add new Alder Lake and Raptor Lake supportKan Liang2022-05-112-0/+54
| | | | | | | | | | | From the perspective of the uncore PMU, there is nothing changed for the new Alder Lake N and Raptor Lake P. Add new PCIIDs of IMC. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220504194413.1003071-5-kan.liang@linux.intel.com
* perf/x86/uncore: Clean up uncore_pci_ids[]Kan Liang2022-05-111-316/+86
| | | | | | | | | The initialization code to assign PCI IDs for different platforms is similar. Add the new macros to reduce the redundant code. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220504194413.1003071-4-kan.liang@linux.intel.com
* perf/x86/cstate: Add new Alder Lake and Raptor Lake supportKan Liang2022-05-111-0/+2
| | | | | | | | | From the perspective of Intel cstate residency counters, there is nothing changed for the new Alder Lake N and Raptor Lake P. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220504194413.1003071-3-kan.liang@linux.intel.com
* perf/x86/msr: Add new Alder Lake and Raptor Lake supportKan Liang2022-05-111-0/+2
| | | | | | | | | The new Alder Lake N and Raptor Lake P also support PPERF and SMI_COUNT MSRs. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220504194413.1003071-2-kan.liang@linux.intel.com
* perf/x86: Add new Alder Lake and Raptor Lake supportKan Liang2022-05-111-0/+2
| | | | | | | | | From PMU's perspective, there is no difference for the new Alder Lake N and Raptor Lake P. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220504194413.1003071-1-kan.liang@linux.intel.com
* Merge branch 'v5.18-rc5'Peter Zijlstra2022-05-115-12/+42
|\ | | | | | | | | | | Obtain the new INTEL_FAM6 stuff required. Signed-off-by: Peter Zijlstra <peterz@infradead.org>
| * perf/x86/cstate: Add SAPPHIRERAPIDS_X CPU supportZhang Rui2022-04-191-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | From the perspective of Intel cstate residency counters, SAPPHIRERAPIDS_X is the same as ICELAKE_X. Share the code with it. And update the comments for SAPPHIRERAPIDS_X. Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Link: https://lkml.kernel.org/r/20220415104520.2737004-1-rui.zhang@intel.com
| * perf/x86/intel: Update the FRONTEND MSR mask on Sapphire RapidsKan Liang2022-04-051-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | On Sapphire Rapids, the FRONTEND_RETIRED.MS_FLOWS event requires the FRONTEND MSR value 0x8. However, the current FRONTEND MSR mask doesn't support it. Update intel_spr_extra_regs[] to support it. Fixes: 61b985e3e775 ("perf/x86/intel: Add perf core PMU support for Sapphire Rapids") Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1648482543-14923-2-git-send-email-kan.liang@linux.intel.com
| * perf/x86/intel: Don't extend the pseudo-encoding to GP countersKan Liang2022-04-051-1/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The INST_RETIRED.PREC_DIST event (0x0100) doesn't count on SPR. perf stat -e cpu/event=0xc0,umask=0x0/,cpu/event=0x0,umask=0x1/ -C0 Performance counter stats for 'CPU(s) 0': 607,246 cpu/event=0xc0,umask=0x0/ 0 cpu/event=0x0,umask=0x1/ The encoding for INST_RETIRED.PREC_DIST is pseudo-encoding, which doesn't work on the generic counters. However, current perf extends its mask to the generic counters. The pseudo event-code for a fixed counter must be 0x00. Check and avoid extending the mask for the fixed counter event which using the pseudo-encoding, e.g., ref-cycles and PREC_DIST event. With the patch, perf stat -e cpu/event=0xc0,umask=0x0/,cpu/event=0x0,umask=0x1/ -C0 Performance counter stats for 'CPU(s) 0': 583,184 cpu/event=0xc0,umask=0x0/ 583,048 cpu/event=0x0,umask=0x1/ Fixes: 2de71ee153ef ("perf/x86/intel: Fix ICL/SPR INST_RETIRED.PREC_DIST encodings") Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1648482543-14923-1-git-send-email-kan.liang@linux.intel.com
| * perf/x86/uncore: Add Raptor Lake uncore supportKan Liang2022-04-052-0/+21
| | | | | | | | | | | | | | | | | | The uncore PMU of the Raptor Lake is the same as Alder Lake. Add new PCIIDs of IMC for Raptor Lake. Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/1647366360-82824-4-git-send-email-kan.liang@linux.intel.com
| * perf/x86/msr: Add Raptor Lake CPU supportKan Liang2022-04-051-0/+1
| | | | | | | | | | | | | | | | | | Raptor Lake is Intel's successor to Alder lake. PPERF and SMI_COUNT MSRs are also supported. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/1647366360-82824-3-git-send-email-kan.liang@linux.intel.com
| * perf/x86/cstate: Add Raptor Lake supportKan Liang2022-04-051-10/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | Raptor Lake is Intel's successor to Alder lake. From the perspective of Intel cstate residency counters, there is nothing changed compared with Alder lake. Share adl_cstates with Alder lake. Update the comments for Raptor Lake. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/1647366360-82824-2-git-send-email-kan.liang@linux.intel.com
| * perf/x86: Add Intel Raptor Lake supportKan Liang2022-04-051-0/+1
| | | | | | | | | | | | | | | | | | | | From PMU's perspective, Raptor Lake is the same as the Alder Lake. The only difference is the event list, which will be supported in the perf tool later. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/1647366360-82824-1-git-send-email-kan.liang@linux.intel.com
* | perf/amd/ibs: Use interrupt regs ip for stack unwindingRavi Bangoria2022-05-101-0/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | IbsOpRip is recorded when IBS interrupt is triggered. But there is a skid from the time IBS interrupt gets triggered to the time the interrupt is presented to the core. Meanwhile processor would have moved ahead and thus IbsOpRip will be inconsistent with rsp and rbp recorded as part of the interrupt regs. This causes issues while unwinding stack using the ORC unwinder as it needs consistent rip, rsp and rbp. Fix this by using rip from interrupt regs instead of IbsOpRip for stack unwinding. Fixes: ee9f8fce99640 ("x86/unwind: Add the ORC unwinder") Reported-by: Dmitry Monakhov <dmtrmonakhov@yandex-team.ru> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20220429051441.14251-1-ravi.bangoria@amd.com
* | perf/x86/amd/core: Add PerfMonV2 overflow handlingSandipan Das2022-05-041-11/+133
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If AMD Performance Monitoring Version 2 (PerfMonV2) is supported, use a new scheme to process Core PMC overflows in the NMI handler using the new global control and status registers. This will be bypassed on unsupported hardware (x86_pmu.version < 2). In x86_pmu_handle_irq(), overflows are detected by testing the contents of the PERF_CTR register for each active PMC in a loop. The new scheme instead inspects the overflow bits of the global status register. The Performance Counter Global Status (PerfCntrGlobalStatus) register has overflow (PerfCntrOvfl) bits for each PMC. This is, however, a read-only MSR. To acknowledge that overflows have been processed, the NMI handler must clear the bits by writing to the PerfCntrGlobalStatusClr register. In x86_pmu_handle_irq(), PMCs counting the same event that are started and stopped at the same time record slightly different counts due to delays in between reads from the PERF_CTR registers. This is fixed by stopping and starting the PMCs at the same before and with a single write to the Performance Counter Global Control (PerfCntrGlobalCtl) upon entering and before exiting the NMI handler. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/f20b7e4da0b0a83bdbe05857f354146623bc63ab.1650515382.git.sandipan.das@amd.com
* | perf/x86/amd/core: Add PerfMonV2 counter controlSandipan Das2022-05-041-5/+45
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If AMD Performance Monitoring Version 2 (PerfMonV2) is supported, use a new scheme to manage the Core PMCs using the new global control and status registers. This will be bypassed on unsupported hardware (x86_pmu.version < 2). Currently, all PMCs have dedicated control (PERF_CTL) and counter (PERF_CTR) registers. For a given PMC, the enable (En) bit of its PERF_CTL register is used to start or stop counting. The Performance Counter Global Control (PerfCntrGlobalCtl) register has enable (PerfCntrEn) bits for each PMC. For a PMC to start counting, both PERF_CTL and PerfCntrGlobalCtl enable bits must be set. If either of those are cleared, the PMC stops counting. In x86_pmu_{en,dis}able_all(), the PERF_CTL registers of all active PMCs are written to in a loop. Ideally, PMCs counting the same event that were started and stopped at the same time should record the same counts. Due to delays in between writes to the PERF_CTL registers across loop iterations, the PMCs cannot be enabled or disabled at the same instant and hence, record slightly different counts. This is fixed by enabling or disabling all active PMCs at the same time with a single write to the PerfCntrGlobalCtl register. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/dfe8e934074aaabc6ba748dfaccd0a77c974bb82.1650515382.git.sandipan.das@amd.com
* | perf/x86/amd/core: Detect available countersSandipan Das2022-05-041-0/+6
| | | | | | | | | | | | | | | | | | | | | | If AMD Performance Monitoring Version 2 (PerfMonV2) is supported, use CPUID leaf 0x80000022 EBX to detect the number of Core PMCs. This offers more flexibility if the counts change in later processor families. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/68a6d9688df189267db26530378870edd34f7b06.1650515382.git.sandipan.das@amd.com
* | perf/x86/amd/core: Detect PerfMonV2 supportSandipan Das2022-05-041-0/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | AMD Performance Monitoring Version 2 (PerfMonV2) introduces some new Core PMU features such as detection of the number of available PMCs and managing PMCs using global registers namely, PerfCntrGlobalCtl and PerfCntrGlobalStatus. Clearing PerfCntrGlobalCtl and PerfCntrGlobalStatus ensures that all PMCs are inactive and have no pending overflows when CPUs are onlined or offlined. The PMU version (x86_pmu.version) now indicates PerfMonV2 support and will be used to bypass the new features on unsupported processors. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/dc8672ecbddff394e088ca8abf94b089b8ecc2e7.1650515382.git.sandipan.das@amd.com
* | perf/x86: Unify format of events sysfs showYang Jihong2022-04-051-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Sysfs show formats of files in /sys/devices/cpu/events/ are not unified, some end with "\n", and some do not. Modify sysfs show format of events defined by EVENT_ATTR_STR to end with "\n". Before: $ ls /sys/devices/cpu/events/* | xargs -i sh -c 'echo -n "{}: "; cat -A {}; echo' branch-instructions: event=0xc4$ branch-misses: event=0xc5$ bus-cycles: event=0x3c,umask=0x01$ cache-misses: event=0x2e,umask=0x41$ cache-references: event=0x2e,umask=0x4f$ cpu-cycles: event=0x3c$ instructions: event=0xc0$ ref-cycles: event=0x00,umask=0x03$ slots: event=0x00,umask=0x4 topdown-bad-spec: event=0x00,umask=0x81 topdown-be-bound: event=0x00,umask=0x83 topdown-fe-bound: event=0x00,umask=0x82 topdown-retiring: event=0x00,umask=0x80 After: $ ls /sys/devices/cpu/events/* | xargs -i sh -c 'echo -n "{}: "; cat -A {}; echo' /sys/devices/cpu/events/branch-instructions: event=0xc4$ /sys/devices/cpu/events/branch-misses: event=0xc5$ /sys/devices/cpu/events/bus-cycles: event=0x3c,umask=0x01$ /sys/devices/cpu/events/cache-misses: event=0x2e,umask=0x41$ /sys/devices/cpu/events/cache-references: event=0x2e,umask=0x4f$ /sys/devices/cpu/events/cpu-cycles: event=0x3c$ /sys/devices/cpu/events/instructions: event=0xc0$ /sys/devices/cpu/events/ref-cycles: event=0x00,umask=0x03$ /sys/devices/cpu/events/slots: event=0x00,umask=0x4$ Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20220324031957.135595-1-yangjihong1@huawei.com
* | perf/x86/amd: Add idle hooks for branch samplingStephane Eranian2022-04-053-0/+38
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On AMD Fam19h Zen3, the branch sampling (BRS) feature must be disabled before entering low power and re-enabled (if was active) when returning from low power. Otherwise, the NMI interrupt may be held up for too long and cause problems. Stopping BRS will cause the NMI to be delivered if it was held up. Define a perf_amd_brs_lopwr_cb() callback to stop/restart BRS. The callback is protected by a jump label which is enabled only when AMD BRS is detected. In all other cases, the callback is never called. Signed-off-by: Stephane Eranian <eranian@google.com> [peterz: static_call() and build fixes] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322221517.2510440-10-eranian@google.com
* | perf/x86/amd: Make Zen3 branch sampling opt-inStephane Eranian2022-04-053-11/+49
| | | | | | | | | | | | | | | | | | | | Add a kernel config option CONFIG_PERF_EVENTS_AMD_BRS to make the support for AMD Zen3 Branch Sampling (BRS) an opt-in compile time option. Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322221517.2510440-8-eranian@google.com
* | perf/x86/amd: Add AMD branch sampling period adjustmentStephane Eranian2022-04-052-0/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add code to adjust the sampling event period when used with the Branch Sampling feature (BRS). Given the depth of the BRS (16), the period is reduced by that depth such that in the best case scenario, BRS saturates at the desired sampling period. In practice, though, the processor may execute more branches. Given a desired period P and a depth D, the kernel programs the actual period at P - D. After P occurrences of the sampling event, the counter overflows. It then may take X branches (skid) before the NMI is caught and held by the hardware and BRS activates. Then, after D branches, BRS saturates and the NMI is delivered. With no skid, the effective period would be (P - D) + D = P. In practice, however, it will likely be (P - D) + X + D. There is no way to eliminate X or predict X. Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322221517.2510440-7-eranian@google.com
* | perf/x86/amd: Enable branch sampling priv level filteringStephane Eranian2022-04-051-6/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The AMD Branch Sampling features does not provide hardware filtering by privilege level. The associated PMU counter does but not the branch sampling by itself. Given how BRS operates there is a possibility that BRS captures kernel level branches even though the event is programmed to count only at the user level. Implement a workaround in software by removing the branches which belong to the wrong privilege level. The privilege level is evaluated on the target of the branch and not the source so as to be compatible with other architectures. As a consequence of this patch, the number of entries in the PERF_RECORD_BRANCH_STACK buffer may be less than the maximum (16). It could even be zero. Another consequence is that consecutive entries in the branch stack may not reflect actual code path and may have discontinuities, in case kernel branches were suppressed. But this is no different than what happens on other architectures. Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322221517.2510440-6-eranian@google.com
* | perf/x86/amd: Add branch-brs helper event for Fam19h BRSStephane Eranian2022-04-051-0/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Add a pseudo event called branch-brs to help use the FAM Fam19h Branch Sampling feature (BRS). BRS samples taken branches, so it is best used when sampling on a retired taken branch event (0xc4) which is what BRS captures. Instead of trying to remember the event code or actual event name, users can simply do: $ perf record -b -e cpu/branch-brs/ -c 1000037 ..... Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322221517.2510440-5-eranian@google.com
* | perf/x86/amd: Add AMD Fam19h Branch Sampling supportStephane Eranian2022-04-055-22/+641
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add support for the AMD Fam19h 16-deep branch sampling feature as described in the AMD PPR Fam19h Model 01h Revision B1. This is a model specific extension. It is not an architected AMD feature. The Branch Sampling (BRS) operates with a 16-deep saturating buffer in MSR registers. There is no branch type filtering. All control flow changes are captured. BRS relies on specific programming of the core PMU of Fam19h. In particular, the following requirements must be met: - the sampling period be greater than 16 (BRS depth) - the sampling period must use a fixed and not frequency mode BRS interacts with the NMI interrupt as well. Because enabling BRS is expensive, it is only activated after P event occurrences, where P is the desired sampling period. At P occurrences of the event, the counter overflows, the CPU catches the interrupt, activates BRS for 16 branches until it saturates, and then delivers the NMI to the kernel. Between the overflow and the time BRS activates more branches may be executed skewing the period. All along, the sampling event keeps counting. The skid may be attenuated by reducing the sampling period by 16 (subsequent patch). BRS is integrated into perf_events seamlessly via the same PERF_RECORD_BRANCH_STACK sample format. BRS generates perf_branch_entry records in the sampling buffer. No prediction information is supported. The branches are stored in reverse order of execution. The most recent branch is the first entry in each record. No modification to the perf tool is necessary. BRS can be used with any sampling event. However, it is recommended to use the RETIRED_BRANCH_INSTRUCTIONS event because it matches what the BRS captures. $ perf record -b -c 1000037 -e cpu/event=0xc2,name=ret_br_instructions/ test $ perf report -D 56531696056126 0x193c000 [0x1a8]: PERF_RECORD_SAMPLE(IP, 0x2): 18122/18230: 0x401d24 period: 1000037 addr: 0 ... branch stack: nr:16 ..... 0: 0000000000401d24 -> 0000000000401d5a 0 cycles 0 ..... 1: 0000000000401d5c -> 0000000000401d24 0 cycles 0 ..... 2: 0000000000401d22 -> 0000000000401d5c 0 cycles 0 ..... 3: 0000000000401d5e -> 0000000000401d22 0 cycles 0 ..... 4: 0000000000401d20 -> 0000000000401d5e 0 cycles 0 ..... 5: 0000000000401d3e -> 0000000000401d20 0 cycles 0 ..... 6: 0000000000401d42 -> 0000000000401d3e 0 cycles 0 ..... 7: 0000000000401d3c -> 0000000000401d42 0 cycles 0 ..... 8: 0000000000401d44 -> 0000000000401d3c 0 cycles 0 ..... 9: 0000000000401d3a -> 0000000000401d44 0 cycles 0 ..... 10: 0000000000401d46 -> 0000000000401d3a 0 cycles 0 ..... 11: 0000000000401d38 -> 0000000000401d46 0 cycles 0 ..... 12: 0000000000401d48 -> 0000000000401d38 0 cycles 0 ..... 13: 0000000000401d36 -> 0000000000401d48 0 cycles 0 ..... 14: 0000000000401d4a -> 0000000000401d36 0 cycles 0 ..... 15: 0000000000401d34 -> 0000000000401d4a 0 cycles 0 ... thread: test:18230 ...... dso: test Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322221517.2510440-4-eranian@google.com
* | perf/core: Add perf_clear_branch_entry_bitfields() helperStephane Eranian2022-04-051-19/+17
|/ | | | | | | | | | | | Make it simpler to reset all the info fields on the perf_branch_entry by adding a helper inline function. The goal is to centralize the initialization to avoid missing a field in case more are added. Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322221517.2510440-2-eranian@google.com
* Merge tag 'asm-generic-5.18' of ↵Linus Torvalds2022-03-231-1/+1
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic Pull asm-generic updates from Arnd Bergmann: "There are three sets of updates for 5.18 in the asm-generic tree: - The set_fs()/get_fs() infrastructure gets removed for good. This was already gone from all major architectures, but now we can finally remove it everywhere, which loses some particularly tricky and error-prone code. There is a small merge conflict against a parisc cleanup, the solution is to use their new version. - The nds32 architecture ends its tenure in the Linux kernel. The hardware is still used and the code is in reasonable shape, but the mainline port is not actively maintained any more, as all remaining users are thought to run vendor kernels that would never be updated to a future release. - A series from Masahiro Yamada cleans up some of the uapi header files to pass the compile-time checks" * tag 'asm-generic-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic: (27 commits) nds32: Remove the architecture uaccess: remove CONFIG_SET_FS ia64: remove CONFIG_SET_FS support sh: remove CONFIG_SET_FS support sparc64: remove CONFIG_SET_FS support lib/test_lockup: fix kernel pointer check for separate address spaces uaccess: generalize access_ok() uaccess: fix type mismatch warnings from access_ok() arm64: simplify access_ok() m68k: fix access_ok for coldfire MIPS: use simpler access_ok() MIPS: Handle address errors for accesses above CPU max virtual user address uaccess: add generic __{get,put}_kernel_nofault nios2: drop access_ok() check from __put_user() x86: use more conventional access_ok() definition x86: remove __range_not_ok() sparc64: add __{get,put}_kernel_nofault() nds32: fix access_ok() checks in get/put_user uaccess: fix nios2 and microblaze get_user_8() sparc64: fix building assembly files ...
| * x86: remove __range_not_ok()Arnd Bergmann2022-02-251-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The __range_not_ok() helper is an x86 (and sparc64) specific interface that does roughly the same thing as __access_ok(), but with different calling conventions. Change this to use the normal interface in order for consistency as we clean up all access_ok() implementations. This changes the limit from TASK_SIZE to TASK_SIZE_MAX, which Al points out is the right thing do do here anyway. The callers have to use __access_ok() instead of the normal access_ok() though, because on x86 that contains a WARN_ON_IN_IRQ() check that cannot be used inside of NMI context while tracing. The check in copy_code() is not needed any more, because this one is already done by copy_from_user_nmi(). Suggested-by: Al Viro <viro@zeniv.linux.org.uk> Suggested-by: Christoph Hellwig <hch@infradead.org> Link: https://lore.kernel.org/lkml/YgsUKcXGR7r4nINj@zeniv-ca.linux.org.uk/ Signed-off-by: Arnd Bergmann <arnd@arndb.de>
* | Merge tag 'perf-core-2022-03-21' of ↵Linus Torvalds2022-03-226-26/+121
|\ \ | |/ |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 perf event updates from Ingo Molnar: - Fix address filtering for Intel/PT,ARM/CoreSight - Enable Intel/PEBS format 5 - Allow more fixed-function counters for x86 - Intel/PT: Enable not recording Taken-Not-Taken packets - Add a few branch-types * tag 'perf-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: perf/x86/intel/uncore: Fix the build on !CONFIG_PHYS_ADDR_T_64BIT perf: Add irq and exception return branch types perf/x86/intel/uncore: Make uncore_discovery clean for 64 bit addresses perf/x86/intel/pt: Add a capability and config bit for disabling TNTs perf/x86/intel/pt: Add a capability and config bit for event tracing perf/x86/intel: Increase max number of the fixed counters KVM: x86: use the KVM side max supported fixed counter perf/x86/intel: Enable PEBS format 5 perf/core: Allow kernel address filter when not filtering the kernel perf/x86/intel/pt: Fix address filter config for 32-bit kernel perf/core: Fix address filter parser for multiple filters x86: Share definition of __is_canonical_address() perf/x86/intel/pt: Relax address filter validation
| * perf/x86/intel/uncore: Fix the build on !CONFIG_PHYS_ADDR_T_64BITIngo Molnar2022-03-031-1/+3
| | | | | | | | | | | | | | | | 'val2' is unused if !CONFIG_PHYS_ADDR_T_64BIT: arch/x86/events/intel/uncore_discovery.c:213:18: error: unused variable ‘val2’ [-Werror=unused-variable] Signed-off-by: Ingo Molnar <mingo@kernel.org>
| * perf: Add irq and exception return branch typesAnshuman Khandual2022-03-011-2/+2
| | | | | | | | | | | | | | | | | | | | | | This expands generic branch type classification by adding two more entries there in i.e irq and exception return. Also updates the x86 implementation to process X86_BR_IRET and X86_BR_IRQ records as appropriate. This changes branch types reported to user space on x86 platform but it should not be a problem. The possible scenarios and impacts are enumerated here. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/1645681014-3346-1-git-send-email-anshuman.khandual@arm.com
| * perf/x86/intel/uncore: Make uncore_discovery clean for 64 bit addressesSteve Wahl2022-03-012-7/+11
| | | | | | | | | | | | | | | | | | | | Support 64-bit BAR size for discovery, and do not truncate return from generic_uncore_mmio_box_ctl() to 32 bits. Signed-off-by: Steve Wahl <steve.wahl@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Link: https://lore.kernel.org/r/20220218175418.421268-1-steve.wahl@hpe.com
| * perf/x86/intel/pt: Add a capability and config bit for disabling TNTsAlexander Shishkin2022-02-151-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | As of Intel SDM (https://www.intel.com/sdm) version 076, there is a new Intel PT feature called TNT-Disable which is enabled config bit 55. TNT-Disable disables Taken-Not-Taken packets to reduce the tracing overhead, but with the result that exact control flow information is lost. Add a capability and config bit for TNT-Disable. Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Adrian Hunter <adrian.hunter@intel.com> Link: https://lore.kernel.org/r/20220126104815.2807416-3-adrian.hunter@intel.com
| * perf/x86/intel/pt: Add a capability and config bit for event tracingAlexander Shishkin2022-02-151-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | As of Intel SDM (https://www.intel.com/sdm) version 076, there is a new Intel PT feature called Event Trace which is enabled config bit 31. Event Trace exposes details about asynchronous events such as interrupts and VM-Entry/Exit. Add a capability and config bit for Event Trace. Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Adrian Hunter <adrian.hunter@intel.com> Link: https://lore.kernel.org/r/20220126104815.2807416-2-adrian.hunter@intel.com
| * perf/x86/intel: Increase max number of the fixed countersKan Liang2022-02-021-1/+39
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The new PEBS format 5 implies that the number of the fixed counters can be up to 16. The current INTEL_PMC_MAX_FIXED is still 4. If the current kernel runs on a future platform which has more than 4 fixed counters, a warning will be triggered. The number of the fixed counters will be clipped to 4. Users have to upgrade the kernel to access the new fixed counters. Add a new default constraint for PerfMon v5 and up, which can support up to 16 fixed counters. The pseudo-encoding is applied for the fixed counters 4 and later. The user can have generic support for the new fixed counters on the future platfroms without updating the kernel. Increase the INTEL_PMC_MAX_FIXED to 16. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Andi Kleen <ak@linux.intel.com> Link: https://lkml.kernel.org/r/1643750603-100733-3-git-send-email-kan.liang@linux.intel.com
| * perf/x86/intel: Enable PEBS format 5Kan Liang2022-02-021-3/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The new PEBS Record Format 5 is similar to the PEBS Record Format 4. The only difference is the layout of the Counter Reset fields of the PEBS Config Buffer in the DS area. For the PEBS format 4, the Counter Reset fields allocation is for 8 general-purpose counters followed by 4 fixed-function counters. For the PEBS format 5, the Counter Reset fields allocation is for 32 general-purpose counters followed by 16 fixed-function counters. Extend the MAX_PEBS_EVENTS to 32. Add MAX_PEBS_EVENTS_FMT4 for the previous platform. Except for the DS auto-reload code, other places already assume 32 counters. Only check the PEBS_FMT in the DS auto-reload code. Extend the MAX_FIXED_PEBS_EVENTS to 16, which only impacts the size of struct debug_store and some local temporary variables. The size of struct debug_store increases 288B, which is small and should be acceptable. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/1643750603-100733-1-git-send-email-kan.liang@linux.intel.com
| * perf/x86/intel/pt: Fix address filter config for 32-bit kernelAdrian Hunter2022-02-021-1/+1
| | | | | | | | | | | | | | | | | | | | Change from shifting 'unsigned long' to 'u64' to prevent the config bits being lost on a 32-bit kernel. Fixes: eadf48cab4b6b0 ("perf/x86/intel/pt: Add support for address range filtering in PT") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220131072453.2839535-5-adrian.hunter@intel.com
| * x86: Share definition of __is_canonical_address()Adrian Hunter2022-02-021-12/+2
| | | | | | | | | | | | | | | | | | Reduce code duplication by moving canonical address code to a common header file. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220131072453.2839535-3-adrian.hunter@intel.com
| * perf/x86/intel/pt: Relax address filter validationAdrian Hunter2022-02-021-13/+50
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The requirement for 64-bit address filters is that they are canonical addresses. In other respects any address range is allowed which would include user space addresses. That can be useful for tracing virtual machine guests because address filtering can be used to advantage in place of current privilege level (CPL) filtering. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20220131072453.2839535-2-adrian.hunter@intel.com
generated by cgit v1.2.3-71-gd317 (git 2.46.0) at 2025-12-31 21:22:29 +0000