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

1 files changed, 14 insertions, 16 deletions

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 332d2e6d8ae4..6a44aed7b100 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -811,7 +811,7 @@ struct x86_pmu {
 	void		(*cpu_dead)(int cpu);
 
 	void		(*check_microcode)(void);
-	void		(*sched_task)(struct perf_event_context *ctx,
+	void		(*sched_task)(struct perf_event_pmu_context *pmu_ctx,
 				      bool sched_in);
 
 	/*
@@ -894,12 +894,12 @@ struct x86_pmu {
 	int		num_topdown_events;
 
 	/*
-	 * perf task context (i.e. struct perf_event_context::task_ctx_data)
+	 * perf task context (i.e. struct perf_event_pmu_context::task_ctx_data)
 	 * switch helper to bridge calls from perf/core to perf/x86.
 	 * See struct pmu::swap_task_ctx() usage for examples;
 	 */
-	void		(*swap_task_ctx)(struct perf_event_context *prev,
-					 struct perf_event_context *next);
+	void		(*swap_task_ctx)(struct perf_event_pmu_context *prev_epc,
+					 struct perf_event_pmu_context *next_epc);
 
 	/*
 	 * AMD bits
@@ -925,7 +925,7 @@ struct x86_pmu {
 
 	int (*aux_output_match) (struct perf_event *event);
 
-	int (*filter_match)(struct perf_event *event);
+	void (*filter)(struct pmu *pmu, int cpu, bool *ret);
 	/*
 	 * Hybrid support
 	 *
@@ -1180,8 +1180,6 @@ int x86_pmu_handle_irq(struct pt_regs *regs);
 void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
 			  u64 intel_ctrl);
 
-void x86_pmu_update_cpu_context(struct pmu *pmu, int cpu);
-
 extern struct event_constraint emptyconstraint;
 
 extern struct event_constraint unconstrained;
@@ -1306,7 +1304,7 @@ void amd_pmu_lbr_reset(void);
 void amd_pmu_lbr_read(void);
 void amd_pmu_lbr_add(struct perf_event *event);
 void amd_pmu_lbr_del(struct perf_event *event);
-void amd_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
+void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 void amd_pmu_lbr_enable_all(void);
 void amd_pmu_lbr_disable_all(void);
 int amd_pmu_lbr_hw_config(struct perf_event *event);
@@ -1330,7 +1328,7 @@ static inline void amd_pmu_brs_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	perf_sched_cb_inc(event->ctx->pmu);
+	perf_sched_cb_inc(event->pmu);
 	cpuc->lbr_users++;
 	/*
 	 * No need to reset BRS because it is reset
@@ -1345,10 +1343,10 @@ static inline void amd_pmu_brs_del(struct perf_event *event)
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 
-	perf_sched_cb_dec(event->ctx->pmu);
+	perf_sched_cb_dec(event->pmu);
 }
 
-void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in);
+void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 #else
 static inline int amd_brs_init(void)
 {
@@ -1373,7 +1371,7 @@ static inline void amd_pmu_brs_del(struct perf_event *event)
 {
 }
 
-static inline void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in)
+static inline void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
 {
 }
 
@@ -1533,7 +1531,7 @@ void intel_pmu_pebs_enable_all(void);
 
 void intel_pmu_pebs_disable_all(void);
 
-void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 
 void intel_pmu_auto_reload_read(struct perf_event *event);
 
@@ -1541,10 +1539,10 @@ void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
 void intel_ds_init(void);
 
-void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
-				 struct perf_event_context *next);
+void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
+				 struct perf_event_pmu_context *next_epc);
 
-void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
+void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 
 u64 lbr_from_signext_quirk_wr(u64 val);