From: Kan Liang <[email protected]> The type of task_ctx is hardcoded as struct x86_perf_task_context, which doesn't apply for Architecture LBR. For example, Architecture LBR doesn't have the TOS MSR. The number of LBR entries is variable. A new struct will be introduced for Architecture LBR. Perf has to determine the type of task_ctx at run time.
The type of task_ctx pointer is changed to 'void *', which will be determined at run time. The generic LBR optimization can be shared between Architecture LBR and model-specific LBR. Both need to access the structure for the generic LBR optimization. A helper task_context_opt() is introduced to retrieve the pointer of the structure at run time. Signed-off-by: Kan Liang <[email protected]> --- arch/x86/events/intel/lbr.c | 58 ++++++++++++++++++++------------------------ arch/x86/events/perf_event.h | 7 +++++- 2 files changed, 32 insertions(+), 33 deletions(-) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f220a4c..1c253ab 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -351,17 +351,17 @@ void intel_pmu_lbr_restore(void *ctx) wrmsrl(x86_pmu.lbr_tos, tos); } -static bool lbr_is_reset_in_cstate(struct x86_perf_task_context *task_ctx) +static bool lbr_is_reset_in_cstate(void *ctx) { - return !rdlbr_from(task_ctx->tos); + return !rdlbr_from(((struct x86_perf_task_context *)ctx)->tos); } -static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) +static void __intel_pmu_lbr_restore(void *ctx) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (task_ctx->opt.lbr_callstack_users == 0 || - task_ctx->opt.lbr_stack_state == LBR_NONE) { + if (task_context_opt(ctx)->lbr_callstack_users == 0 || + task_context_opt(ctx)->lbr_stack_state == LBR_NONE) { intel_pmu_lbr_reset(); return; } @@ -371,16 +371,16 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) * - No one else touched them, and * - Was not cleared in Cstate */ - if ((task_ctx == cpuc->last_task_ctx) && - (task_ctx->opt.log_id == cpuc->last_log_id) && - !lbr_is_reset_in_cstate(task_ctx)) { - task_ctx->opt.lbr_stack_state = LBR_NONE; + if ((ctx == cpuc->last_task_ctx) && + (task_context_opt(ctx)->log_id == cpuc->last_log_id) && + !lbr_is_reset_in_cstate(ctx)) { + task_context_opt(ctx)->lbr_stack_state = LBR_NONE; return; } - x86_pmu.lbr_restore(task_ctx); + x86_pmu.lbr_restore(ctx); - task_ctx->opt.lbr_stack_state = LBR_NONE; + task_context_opt(ctx)->lbr_stack_state = LBR_NONE; } void intel_pmu_lbr_save(void *ctx) @@ -406,27 +406,27 @@ void intel_pmu_lbr_save(void *ctx) task_ctx->tos = tos; } -static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) +static void __intel_pmu_lbr_save(void *ctx) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (task_ctx->opt.lbr_callstack_users == 0) { - task_ctx->opt.lbr_stack_state = LBR_NONE; + if (task_context_opt(ctx)->lbr_callstack_users == 0) { + task_context_opt(ctx)->lbr_stack_state = LBR_NONE; return; } - x86_pmu.lbr_save(task_ctx); + x86_pmu.lbr_save(ctx); - task_ctx->opt.lbr_stack_state = LBR_VALID; + task_context_opt(ctx)->lbr_stack_state = LBR_VALID; - cpuc->last_task_ctx = task_ctx; - cpuc->last_log_id = ++task_ctx->opt.log_id; + cpuc->last_task_ctx = ctx; + cpuc->last_log_id = ++task_context_opt(ctx)->log_id; } void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev, struct perf_event_context *next) { - struct x86_perf_task_context *prev_ctx_data, *next_ctx_data; + void *prev_ctx_data, *next_ctx_data; swap(prev->task_ctx_data, next->task_ctx_data); @@ -442,14 +442,14 @@ void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev, if (!prev_ctx_data || !next_ctx_data) return; - swap(prev_ctx_data->opt.lbr_callstack_users, - next_ctx_data->opt.lbr_callstack_users); + swap(task_context_opt(prev_ctx_data)->lbr_callstack_users, + task_context_opt(next_ctx_data)->lbr_callstack_users); } void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct x86_perf_task_context *task_ctx; + void *task_ctx; if (!cpuc->lbr_users) return; @@ -486,17 +486,14 @@ static inline bool branch_user_callstack(unsigned br_sel) void intel_pmu_lbr_add(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct x86_perf_task_context *task_ctx; if (!x86_pmu.lbr_nr) return; cpuc->br_sel = event->hw.branch_reg.reg; - if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) { - task_ctx = event->ctx->task_ctx_data; - task_ctx->opt.lbr_callstack_users++; - } + if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) + task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users++; /* * Request pmu::sched_task() callback, which will fire inside the @@ -527,16 +524,13 @@ void intel_pmu_lbr_add(struct perf_event *event) void intel_pmu_lbr_del(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct x86_perf_task_context *task_ctx; if (!x86_pmu.lbr_nr) return; if (branch_user_callstack(cpuc->br_sel) && - event->ctx->task_ctx_data) { - task_ctx = event->ctx->task_ctx_data; - task_ctx->opt.lbr_callstack_users--; - } + event->ctx->task_ctx_data) + task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users--; if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) cpuc->lbr_pebs_users--; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index fd73c6c..e33d348 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -246,7 +246,7 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; u64 br_sel; - struct x86_perf_task_context *last_task_ctx; + void *last_task_ctx; int last_log_id; /* @@ -798,6 +798,11 @@ static struct perf_pmu_events_ht_attr event_attr_##v = { \ struct pmu *x86_get_pmu(void); extern struct x86_pmu x86_pmu __read_mostly; +static inline struct x86_perf_task_context_opt *task_context_opt(void *ctx) +{ + return &((struct x86_perf_task_context *)ctx)->opt; +} + static inline bool x86_pmu_has_lbr_callstack(void) { return x86_pmu.lbr_sel_map && -- 2.7.4
