perf: Clean up pmu specific data

The pmu specific data is saved in task_struct now. Remove it from event
context structure.

Remove swap_task_ctx() as well.

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/20250314172700.438923-7-kan.liang@linux.intel.com

Author: Kan Liang

include/linux/perf_event.h

@@ -501,16 +501,6 @@ struct pmu {
 	 */
 	struct kmem_cache		*task_ctx_cache;
 
-	/*
-	 * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
-	 * can be synchronized using this function. See Intel LBR callstack support
-	 * implementation and Perf core context switch handling callbacks for usage
-	 * examples.
-	 */
-	void (*swap_task_ctx)		(struct perf_event_pmu_context *prev_epc,
-					 struct perf_event_pmu_context *next_epc);
-					/* optional */
-
 	/*
 	 * Set up pmu-private data structures for an AUX area
 	 */
@@ -933,7 +923,6 @@ struct perf_event_pmu_context {
 	atomic_t			refcount; /* event <-> epc */
 	struct rcu_head			rcu_head;
 
-	void				*task_ctx_data; /* pmu specific data */
 	/*
 	 * Set when one or more (plausibly active) event can't be scheduled
 	 * due to pmu overcommit or pmu constraints, except tolerant to
@@ -981,7 +970,6 @@ struct perf_event_context {
 	int				nr_user;
 	int				is_active;
 
-	int				nr_task_data;
 	int				nr_stat;
 	int				nr_freq;
 	int				rotate_disable;

kernel/events/core.c

@@ -1254,20 +1254,6 @@ static void get_ctx(struct perf_event_context *ctx)
 	refcount_inc(&ctx->refcount);
 }
 
-static void *alloc_task_ctx_data(struct pmu *pmu)
-{
-	if (pmu->task_ctx_cache)
-		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
-
-	return NULL;
-}
-
-static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
-{
-	if (pmu->task_ctx_cache && task_ctx_data)
-		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
-}
-
 static void free_ctx(struct rcu_head *head)
 {
 	struct perf_event_context *ctx;
@@ -3577,42 +3563,6 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
 	}
 }
 
-#define double_list_for_each_entry(pos1, pos2, head1, head2, member)	\
-	for (pos1 = list_first_entry(head1, typeof(*pos1), member),	\
-	     pos2 = list_first_entry(head2, typeof(*pos2), member);	\
-	     !list_entry_is_head(pos1, head1, member) &&		\
-	     !list_entry_is_head(pos2, head2, member);			\
-	     pos1 = list_next_entry(pos1, member),			\
-	     pos2 = list_next_entry(pos2, member))
-
-static void perf_event_swap_task_ctx_data(struct perf_event_context *prev_ctx,
-					  struct perf_event_context *next_ctx)
-{
-	struct perf_event_pmu_context *prev_epc, *next_epc;
-
-	if (!prev_ctx->nr_task_data)
-		return;
-
-	double_list_for_each_entry(prev_epc, next_epc,
-				   &prev_ctx->pmu_ctx_list, &next_ctx->pmu_ctx_list,
-				   pmu_ctx_entry) {
-
-		if (WARN_ON_ONCE(prev_epc->pmu != next_epc->pmu))
-			continue;
-
-		/*
-		 * PMU specific parts of task perf context can require
-		 * additional synchronization. As an example of such
-		 * synchronization see implementation details of Intel
-		 * LBR call stack data profiling;
-		 */
-		if (prev_epc->pmu->swap_task_ctx)
-			prev_epc->pmu->swap_task_ctx(prev_epc, next_epc);
-		else
-			swap(prev_epc->task_ctx_data, next_epc->task_ctx_data);
-	}
-}
-
 static void perf_ctx_sched_task_cb(struct perf_event_context *ctx,
 				   struct task_struct *task, bool sched_in)
 {
@@ -3687,16 +3637,15 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
 			WRITE_ONCE(next_ctx->task, task);
 
 			perf_ctx_sched_task_cb(ctx, task, false);
-			perf_event_swap_task_ctx_data(ctx, next_ctx);
 
 			perf_ctx_enable(ctx, false);
 
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not
 			 * modified the ctx and the above modification of
-			 * ctx->task and ctx->task_ctx_data are immaterial
-			 * since those values are always verified under
-			 * ctx->lock which we're now holding.
+			 * ctx->task is immaterial since this value is
+			 * always verified under ctx->lock which we're now
+			 * holding.
 			 */
 			RCU_INIT_POINTER(task->perf_event_ctxp, next_ctx);
 			RCU_INIT_POINTER(next->perf_event_ctxp, ctx);
@@ -5005,7 +4954,6 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 		     struct perf_event *event)
 {
 	struct perf_event_pmu_context *new = NULL, *pos = NULL, *epc;
-	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
 		/*
@@ -5038,14 +4986,6 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 	if (!new)
 		return ERR_PTR(-ENOMEM);
 
-	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
-		task_ctx_data = alloc_task_ctx_data(pmu);
-		if (!task_ctx_data) {
-			kfree(new);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-
 	__perf_init_event_pmu_context(new, pmu);
 
 	/*
@@ -5080,14 +5020,7 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 	epc->ctx = ctx;
 
 found_epc:
-	if (task_ctx_data && !epc->task_ctx_data) {
-		epc->task_ctx_data = task_ctx_data;
-		task_ctx_data = NULL;
-		ctx->nr_task_data++;
-	}
 	raw_spin_unlock_irq(&ctx->lock);
-
-	free_task_ctx_data(pmu, task_ctx_data);
 	kfree(new);
 
 	return epc;
@@ -5103,15 +5036,13 @@ static void free_cpc_rcu(struct rcu_head *head)
 	struct perf_cpu_pmu_context *cpc =
 		container_of(head, typeof(*cpc), epc.rcu_head);
 
-	kfree(cpc->epc.task_ctx_data);
 	kfree(cpc);
 }
 
 static void free_epc_rcu(struct rcu_head *head)
 {
 	struct perf_event_pmu_context *epc = container_of(head, typeof(*epc), rcu_head);
 
-	kfree(epc->task_ctx_data);
 	kfree(epc);
 }
 
@@ -14103,7 +14034,6 @@ inherit_event(struct perf_event *parent_event,
 	if (is_orphaned_event(parent_event) ||
 	    !atomic_long_inc_not_zero(&parent_event->refcount)) {
 		mutex_unlock(&parent_event->child_mutex);
-		/* task_ctx_data is freed with child_ctx */
 		free_event(child_event);
 		return NULL;
 	}