#
598c2faf |
|
25-Mar-2024 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Use freeze based on availability Currently, the LBR code assumes that LBR Freeze is supported on all processors when X86_FEATURE_AMD_LBR_V2 is available i.e. CPUID leaf 0x80000022[EAX] bit 1 is set. This is incorrect as the availability of the feature is additionally dependent on CPUID leaf 0x80000022[EAX] bit 2 being set, which may not be set for all Zen 4 processors. Define a new feature bit for LBR and PMC freeze and set the freeze enable bit (FLBRI) in DebugCtl (MSR 0x1d9) conditionally. It should still be possible to use LBR without freeze for profile-guided optimization of user programs by using an user-only branch filter during profiling. When the user-only filter is enabled, branches are no longer recorded after the transition to CPL 0 upon PMI arrival. When branch entries are read in the PMI handler, the branch stack does not change. E.g. $ perf record -j any,u -e ex_ret_brn_tkn ./workload Since the feature bit is visible under flags in /proc/cpuinfo, it can be used to determine the feasibility of use-cases which require LBR Freeze to be supported by the hardware such as profile-guided optimization of kernels. Fixes: ca5b7c0d9621 ("perf/x86/amd/lbr: Add LbrExtV2 branch record support") Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/69a453c97cfd11c6f2584b19f937fe6df741510f.1711091584.git.sandipan.das@amd.com
|
#
29297fff |
|
29-Jan-2024 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Discard erroneous branch entries The Revision Guide for AMD Family 19h Model 10-1Fh processors declares Erratum 1452 which states that non-branch entries may erroneously be recorded in the Last Branch Record (LBR) stack with the valid and spec bits set. Such entries can be recognized by inspecting bit 61 of the corresponding LastBranchStackToIp register. This bit is currently reserved but if found to be set, the associated branch entry should be discarded. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://bugzilla.kernel.org/attachment.cgi?id=305518 Link: https://lore.kernel.org/r/3ad2aa305f7396d41a40e3f054f740d464b16b7f.1706526029.git.sandipan.das@amd.com
|
#
bd275681 |
|
08-Oct-2022 |
Peter Zijlstra <peterz@infradead.org> |
perf: Rewrite core context handling There have been various issues and limitations with the way perf uses (task) contexts to track events. Most notable is the single hardware PMU task context, which has resulted in a number of yucky things (both proposed and merged). Notably: - HW breakpoint PMU - ARM big.little PMU / Intel ADL PMU - Intel Branch Monitoring PMU - AMD IBS PMU - S390 cpum_cf PMU - PowerPC trace_imc PMU *Current design:* Currently we have a per task and per cpu perf_event_contexts: task_struct::perf_events_ctxp[] <-> perf_event_context <-> perf_cpu_context ^ | ^ | ^ `---------------------------------' | `--> pmu ---' v ^ perf_event ------' Each task has an array of pointers to a perf_event_context. Each perf_event_context has a direct relation to a PMU and a group of events for that PMU. The task related perf_event_context's have a pointer back to that task. Each PMU has a per-cpu pointer to a per-cpu perf_cpu_context, which includes a perf_event_context, which again has a direct relation to that PMU, and a group of events for that PMU. The perf_cpu_context also tracks which task context is currently associated with that CPU and includes a few other things like the hrtimer for rotation etc. Each perf_event is then associated with its PMU and one perf_event_context. *Proposed design:* New design proposed by this patch reduce to a single task context and a single CPU context but adds some intermediate data-structures: task_struct::perf_event_ctxp -> perf_event_context <- perf_cpu_context ^ | ^ ^ `---------------------------' | | | | perf_cpu_pmu_context <--. | `----. ^ | | | | | | v v | | ,--> perf_event_pmu_context | | | | | | | v v | perf_event ---> pmu ----------------' With the new design, perf_event_context will hold all events for all pmus in the (respective pinned/flexible) rbtrees. This can be achieved by adding pmu to rbtree key: {cpu, pmu, cgroup, group_index} Each perf_event_context carries a list of perf_event_pmu_context which is used to hold per-pmu-per-context state. For example, it keeps track of currently active events for that pmu, a pmu specific task_ctx_data, a flag to tell whether rotation is required or not etc. Additionally, perf_cpu_pmu_context is used to hold per-pmu-per-cpu state like hrtimer details to drive the event rotation, a pointer to perf_event_pmu_context of currently running task and some other ancillary information. Each perf_event is associated to it's pmu, perf_event_context and perf_event_pmu_context. Further optimizations to current implementation are possible. For example, ctx_resched() can be optimized to reschedule only single pmu events. Much thanks to Ravi for picking this up and pushing it towards completion. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Co-developed-by: Ravi Bangoria <ravi.bangoria@amd.com> Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20221008062424.313-1-ravi.bangoria@amd.com
|
#
3f9a1b35 |
|
28-Sep-2022 |
Stephane Eranian <eranian@google.com> |
perf/x86/amd/lbr: Adjust LBR regardless of filtering In case of fused compare and taken branch instructions, the AMD LBR points to the compare instruction instead of the branch. Users of LBR usually expects the from address to point to a branch instruction. The kernel has code to adjust the from address via get_branch_type_fused(). However this correction is only applied when a branch filter is applied. That means that if no filter is present, the quality of the data is lower. Fix the problem by applying the adjustment regardless of the filter setting, bringing the AMD LBR to the same level as other LBR implementations. Fixes: 245268c19f70 ("perf/x86/amd/lbr: Use fusion-aware branch classifier") Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Sandipan Das <sandipan.das@amd.com> Link: https://lore.kernel.org/r/20220928184043.408364-3-eranian@google.com
|
#
0bc3be5b |
|
11-Aug-2022 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Add LbrExtV2 branch speculation info support Provide branch speculation information captured via AMD Last Branch Record Extension Version 2 (LbrExtV2) by setting the speculation info in branch records. The info is based on the "valid" and "spec" bits in the Branch To registers. Suggested-by: Stephane Eranian <eranian@google.com> Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/ddc02f6320464cad0e3ff5bdb2314531568a91bc.1660211399.git.sandipan.das@amd.com
|
#
245268c1 |
|
11-Aug-2022 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Use fusion-aware branch classifier AMD Last Branch Record Extension Version 2 (LbrExtV2) can report a branch from address that points to an instruction preceding the actual branch by several bytes due to branch fusion and further optimizations in Zen4 processors. In such cases, software should move forward sequentially in the instruction stream from the reported address and the address of the first branch encountered should be used instead. Hence, use the fusion-aware branch classifier to determine the correct branch type and get the offset for adjusting the branch from address. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/c324d2d0a9c3976da30b9563d09e50bfee0f264d.1660211399.git.sandipan.das@amd.com
|
#
f9c73224 |
|
11-Aug-2022 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Add LbrExtV2 software branch filter support With AMD Last Branch Record Extension Version 2 (LbrExtV2), it is necessary to process the branch records further as hardware filtering is not granular enough for identifying certain types of branches. E.g. to record system calls, one should record far branches. The filter captures both far calls and far returns but the irrelevant records are filtered out based on the branch type as seen by the branch classifier. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/e51de057517f77788abd393c832e8dea616d489c.1660211399.git.sandipan.das@amd.com
|
#
f4f925da |
|
11-Aug-2022 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Add LbrExtV2 hardware branch filter support If AMD Last Branch Record Extension Version 2 (LbrExtV2) is detected, convert the requested branch filter (PERF_SAMPLE_BRANCH_* flags) to the corresponding hardware filter value and stash it in the event data when a branch stack is requested. The hardware filter value is also saved in per-CPU areas for use during event scheduling. Hardware filtering is provided by the LBR Branch Select register. It has bits which when set, suppress recording of the following types of branches: * CPL = 0 (Kernel only) * CPL > 0 (Userspace only) * Conditional Branches * Near Relative Calls * Near Indirect Calls * Near Returns * Near Indirect Jumps (excluding Near Indirect Calls and Near Returns) * Near Relative Jumps (excluding Near Relative Calls) * Far Branches Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/9336af5c9785b8e14c62220fc0e6cfb10ab97de3.1660211399.git.sandipan.das@amd.com
|
#
ca5b7c0d |
|
11-Aug-2022 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Add LbrExtV2 branch record support If AMD Last Branch Record Extension Version 2 (LbrExtV2) is detected, enable it alongside LBR Freeze on PMI when an event requests branch stack i.e. PERF_SAMPLE_BRANCH_STACK. Each branch record is represented by a pair of registers, LBR From and LBR To. The freeze feature prevents any updates to these registers once a PMC overflows. The contents remain unchanged until the freeze bit is cleared by the PMI handler. The branch records are read and copied to sample data before unfreezing. However, only valid entries are copied. There is no additional register to denote which of the register pairs represent the top of the stack (TOS) since internal register renaming always ensures that the first pair (i.e. index 0) is the one representing the most recent branch and so on. The LBR registers are per-thread resources and are cleared explicitly whenever a new task is scheduled in. There are no special implications on the contents of these registers when transitioning to deep C-states. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/d3b8500a3627a0d4d0259b005891ee248f248d91.1660211399.git.sandipan.das@amd.com
|
#
703fb765 |
|
11-Aug-2022 |
Sandipan Das <sandipan.das@amd.com> |
perf/x86/amd/lbr: Detect LbrExtV2 support AMD Last Branch Record Extension Version 2 (LbrExtV2) is driven by Core PMC overflows. It records recently taken branches up to the moment when the PMC overflow occurs. Detect the feature during PMU initialization and set the branch stack depth using CPUID leaf 0x80000022 EBX. Signed-off-by: Sandipan Das <sandipan.das@amd.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/fc6e45378ada258f1bab79b0de6e05c393a8f1dd.1660211399.git.sandipan.das@amd.com
|