1 files changed, 148 insertions, 155 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index eacc3702654d..f79fd8b87f75 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -380,7 +380,6 @@ enum event_type_t {
 
 /*
  * perf_sched_events : >0 events exist
- * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
 
 static void perf_sched_delayed(struct work_struct *work);
@@ -389,7 +388,6 @@ static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed);
 static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
-static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -844,9 +842,16 @@ static void perf_cgroup_switch(struct task_struct *task)
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
 	struct perf_cgroup *cgrp;
 
-	cgrp = perf_cgroup_from_task(task, NULL);
+	/*
+	 * cpuctx->cgrp is set when the first cgroup event enabled,
+	 * and is cleared when the last cgroup event disabled.
+	 */
+	if (READ_ONCE(cpuctx->cgrp) == NULL)
+		return;
 
 	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+
+	cgrp = perf_cgroup_from_task(task, NULL);
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
 		return;
 
@@ -3631,8 +3636,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	 * to check if we have to switch out PMU state.
 	 * cgroup event are system-wide mode only
 	 */
-	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_switch(next);
+	perf_cgroup_switch(next);
 }
 
 static bool perf_less_group_idx(const void *l, const void *r)
@@ -4809,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 
 		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
 		epc = &cpc->epc;
-
+		raw_spin_lock_irq(&ctx->lock);
 		if (!epc->ctx) {
 			atomic_set(&epc->refcount, 1);
 			epc->embedded = 1;
-			raw_spin_lock_irq(&ctx->lock);
 			list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
 			epc->ctx = ctx;
-			raw_spin_unlock_irq(&ctx->lock);
 		} else {
 			WARN_ON_ONCE(epc->ctx != ctx);
 			atomic_inc(&epc->refcount);
 		}
-
+		raw_spin_unlock_irq(&ctx->lock);
 		return epc;
 	}
 
@@ -4892,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head)
 
 static void put_pmu_ctx(struct perf_event_pmu_context *epc)
 {
+	struct perf_event_context *ctx = epc->ctx;
 	unsigned long flags;
 
-	if (!atomic_dec_and_test(&epc->refcount))
+	/*
+	 * XXX
+	 *
+	 * lockdep_assert_held(&ctx->mutex);
+	 *
+	 * can't because of the call-site in _free_event()/put_event()
+	 * which isn't always called under ctx->mutex.
+	 */
+	if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags))
 		return;
 
-	if (epc->ctx) {
-		struct perf_event_context *ctx = epc->ctx;
-
-		/*
-		 * XXX
-		 *
-		 * lockdep_assert_held(&ctx->mutex);
-		 *
-		 * can't because of the call-site in _free_event()/put_event()
-		 * which isn't always called under ctx->mutex.
-		 */
+	WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
 
-		WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
-		raw_spin_lock_irqsave(&ctx->lock, flags);
-		list_del_init(&epc->pmu_ctx_entry);
-		epc->ctx = NULL;
-		raw_spin_unlock_irqrestore(&ctx->lock, flags);
-	}
+	list_del_init(&epc->pmu_ctx_entry);
+	epc->ctx = NULL;
 
 	WARN_ON_ONCE(!list_empty(&epc->pinned_active));
 	WARN_ON_ONCE(!list_empty(&epc->flexible_active));
 
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
 	if (epc->embedded)
 		return;
 
@@ -4974,15 +4973,6 @@ static void unaccount_pmu_sb_event(struct perf_event *event)
 		detach_sb_event(event);
 }
 
-static void unaccount_event_cpu(struct perf_event *event, int cpu)
-{
-	if (event->parent)
-		return;
-
-	if (is_cgroup_event(event))
-		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
-}
-
 #ifdef CONFIG_NO_HZ_FULL
 static DEFINE_SPINLOCK(nr_freq_lock);
 #endif
@@ -5048,8 +5038,6 @@ static void unaccount_event(struct perf_event *event)
 			schedule_delayed_work(&perf_sched_work, HZ);
 	}
 
-	unaccount_event_cpu(event, event->cpu);
-
 	unaccount_pmu_sb_event(event);
 }
 
@@ -6580,7 +6568,7 @@ aux_unlock:
 	 * Since pinned accounting is per vm we cannot allow fork() to copy our
 	 * vma.
 	 */
-	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
+	vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
 	vma->vm_ops = &perf_mmap_vmops;
 
 	if (event->pmu->event_mapped)
@@ -7053,13 +7041,20 @@ out_put:
 	ring_buffer_put(rb);
 }
 
-static void __perf_event_header__init_id(struct perf_event_header *header,
-					 struct perf_sample_data *data,
+/*
+ * A set of common sample data types saved even for non-sample records
+ * when event->attr.sample_id_all is set.
+ */
+#define PERF_SAMPLE_ID_ALL  (PERF_SAMPLE_TID | PERF_SAMPLE_TIME |	\
+			     PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
+			     PERF_SAMPLE_CPU | PERF_SAMPLE_IDENTIFIER)
+
+static void __perf_event_header__init_id(struct perf_sample_data *data,
 					 struct perf_event *event,
 					 u64 sample_type)
 {
 	data->type = event->attr.sample_type;
-	header->size += event->id_header_size;
+	data->sample_flags |= data->type & PERF_SAMPLE_ID_ALL;
 
 	if (sample_type & PERF_SAMPLE_TID) {
 		/* namespace issues */
@@ -7086,8 +7081,10 @@ void perf_event_header__init_id(struct perf_event_header *header,
 				struct perf_sample_data *data,
 				struct perf_event *event)
 {
-	if (event->attr.sample_id_all)
-		__perf_event_header__init_id(header, data, event, event->attr.sample_type);
+	if (event->attr.sample_id_all) {
+		header->size += event->id_header_size;
+		__perf_event_header__init_id(data, event, event->attr.sample_type);
+	}
 }
 
 static void __perf_event__output_id_sample(struct perf_output_handle *handle,
@@ -7317,7 +7314,7 @@ void perf_output_sample(struct perf_output_handle *handle,
 	}
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
-		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
+		if (data->br_stack) {
 			size_t size;
 
 			size = data->br_stack->nr
@@ -7561,83 +7558,68 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	return callchain ?: &__empty_callchain;
 }
 
-void perf_prepare_sample(struct perf_event_header *header,
-			 struct perf_sample_data *data,
+static __always_inline u64 __cond_set(u64 flags, u64 s, u64 d)
+{
+	return d * !!(flags & s);
+}
+
+void perf_prepare_sample(struct perf_sample_data *data,
 			 struct perf_event *event,
 			 struct pt_regs *regs)
 {
 	u64 sample_type = event->attr.sample_type;
 	u64 filtered_sample_type;
 
-	header->type = PERF_RECORD_SAMPLE;
-	header->size = sizeof(*header) + event->header_size;
-
-	header->misc = 0;
-	header->misc |= perf_misc_flags(regs);
-
 	/*
-	 * Clear the sample flags that have already been done by the
-	 * PMU driver.
+	 * Add the sample flags that are dependent to others.  And clear the
+	 * sample flags that have already been done by the PMU driver.
 	 */
-	filtered_sample_type = sample_type & ~data->sample_flags;
-	__perf_event_header__init_id(header, data, event, filtered_sample_type);
-
-	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
-		data->ip = perf_instruction_pointer(regs);
+	filtered_sample_type = sample_type;
+	filtered_sample_type |= __cond_set(sample_type, PERF_SAMPLE_CODE_PAGE_SIZE,
+					   PERF_SAMPLE_IP);
+	filtered_sample_type |= __cond_set(sample_type, PERF_SAMPLE_DATA_PAGE_SIZE |
+					   PERF_SAMPLE_PHYS_ADDR, PERF_SAMPLE_ADDR);
+	filtered_sample_type |= __cond_set(sample_type, PERF_SAMPLE_STACK_USER,
+					   PERF_SAMPLE_REGS_USER);
+	filtered_sample_type &= ~data->sample_flags;
 
-	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-		int size = 1;
-
-		if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN)
-			data->callchain = perf_callchain(event, regs);
-
-		size += data->callchain->nr;
-
-		header->size += size * sizeof(u64);
+	if (filtered_sample_type == 0) {
+		/* Make sure it has the correct data->type for output */
+		data->type = event->attr.sample_type;
+		return;
 	}
 
-	if (sample_type & PERF_SAMPLE_RAW) {
-		struct perf_raw_record *raw = data->raw;
-		int size;
-
-		if (raw && (data->sample_flags & PERF_SAMPLE_RAW)) {
-			struct perf_raw_frag *frag = &raw->frag;
-			u32 sum = 0;
+	__perf_event_header__init_id(data, event, filtered_sample_type);
 
-			do {
-				sum += frag->size;
-				if (perf_raw_frag_last(frag))
-					break;
-				frag = frag->next;
-			} while (1);
+	if (filtered_sample_type & PERF_SAMPLE_IP) {
+		data->ip = perf_instruction_pointer(regs);
+		data->sample_flags |= PERF_SAMPLE_IP;
+	}
 
-			size = round_up(sum + sizeof(u32), sizeof(u64));
-			raw->size = size - sizeof(u32);
-			frag->pad = raw->size - sum;
-		} else {
-			size = sizeof(u64);
-			data->raw = NULL;
-		}
+	if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(data, event, regs);
 
-		header->size += size;
+	if (filtered_sample_type & PERF_SAMPLE_RAW) {
+		data->raw = NULL;
+		data->dyn_size += sizeof(u64);
+		data->sample_flags |= PERF_SAMPLE_RAW;
 	}
 
-	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
-		int size = sizeof(u64); /* nr */
-		if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) {
-			if (branch_sample_hw_index(event))
-				size += sizeof(u64);
-
-			size += data->br_stack->nr
-			      * sizeof(struct perf_branch_entry);
-		}
-		header->size += size;
+	if (filtered_sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		data->br_stack = NULL;
+		data->dyn_size += sizeof(u64);
+		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 	}
 
-	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
+	if (filtered_sample_type & PERF_SAMPLE_REGS_USER)
 		perf_sample_regs_user(&data->regs_user, regs);
 
-	if (sample_type & PERF_SAMPLE_REGS_USER) {
+	/*
+	 * It cannot use the filtered_sample_type here as REGS_USER can be set
+	 * by STACK_USER (using __cond_set() above) and we don't want to update
+	 * the dyn_size if it's not requested by users.
+	 */
+	if ((sample_type & ~data->sample_flags) & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);
 
@@ -7646,10 +7628,11 @@ void perf_prepare_sample(struct perf_event_header *header,
 			size += hweight64(mask) * sizeof(u64);
 		}
 
-		header->size += size;
+		data->dyn_size += size;
+		data->sample_flags |= PERF_SAMPLE_REGS_USER;
 	}
 
-	if (sample_type & PERF_SAMPLE_STACK_USER) {
+	if (filtered_sample_type & PERF_SAMPLE_STACK_USER) {
 		/*
 		 * Either we need PERF_SAMPLE_STACK_USER bit to be always
 		 * processed as the last one or have additional check added
@@ -7657,9 +7640,10 @@ void perf_prepare_sample(struct perf_event_header *header,
 		 * up the rest of the sample size.
 		 */
 		u16 stack_size = event->attr.sample_stack_user;
+		u16 header_size = perf_sample_data_size(data, event);
 		u16 size = sizeof(u64);
 
-		stack_size = perf_sample_ustack_size(stack_size, header->size,
+		stack_size = perf_sample_ustack_size(stack_size, header_size,
 						     data->regs_user.regs);
 
 		/*
@@ -7671,24 +7655,31 @@ void perf_prepare_sample(struct perf_event_header *header,
 			size += sizeof(u64) + stack_size;
 
 		data->stack_user_size = stack_size;
-		header->size += size;
+		data->dyn_size += size;
+		data->sample_flags |= PERF_SAMPLE_STACK_USER;
 	}
 
-	if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+	if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
 		data->weight.full = 0;
+		data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
+	}
 
-	if (filtered_sample_type & PERF_SAMPLE_DATA_SRC)
+	if (filtered_sample_type & PERF_SAMPLE_DATA_SRC) {
 		data->data_src.val = PERF_MEM_NA;
+		data->sample_flags |= PERF_SAMPLE_DATA_SRC;
+	}
 
-	if (filtered_sample_type & PERF_SAMPLE_TRANSACTION)
+	if (filtered_sample_type & PERF_SAMPLE_TRANSACTION) {
 		data->txn = 0;
+		data->sample_flags |= PERF_SAMPLE_TRANSACTION;
+	}
 
-	if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_DATA_PAGE_SIZE)) {
-		if (filtered_sample_type & PERF_SAMPLE_ADDR)
-			data->addr = 0;
+	if (filtered_sample_type & PERF_SAMPLE_ADDR) {
+		data->addr = 0;
+		data->sample_flags |= PERF_SAMPLE_ADDR;
 	}
 
-	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+	if (filtered_sample_type & PERF_SAMPLE_REGS_INTR) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);
 
@@ -7700,20 +7691,23 @@ void perf_prepare_sample(struct perf_event_header *header,
 			size += hweight64(mask) * sizeof(u64);
 		}
 
-		header->size += size;
+		data->dyn_size += size;
+		data->sample_flags |= PERF_SAMPLE_REGS_INTR;
 	}
 
-	if (sample_type & PERF_SAMPLE_PHYS_ADDR &&
-	    filtered_sample_type & PERF_SAMPLE_PHYS_ADDR)
+	if (filtered_sample_type & PERF_SAMPLE_PHYS_ADDR) {
 		data->phys_addr = perf_virt_to_phys(data->addr);
+		data->sample_flags |= PERF_SAMPLE_PHYS_ADDR;
+	}
 
 #ifdef CONFIG_CGROUP_PERF
-	if (sample_type & PERF_SAMPLE_CGROUP) {
+	if (filtered_sample_type & PERF_SAMPLE_CGROUP) {
 		struct cgroup *cgrp;
 
 		/* protected by RCU */
 		cgrp = task_css_check(current, perf_event_cgrp_id, 1)->cgroup;
 		data->cgroup = cgroup_id(cgrp);
+		data->sample_flags |= PERF_SAMPLE_CGROUP;
 	}
 #endif
 
@@ -7722,16 +7716,21 @@ void perf_prepare_sample(struct perf_event_header *header,
 	 * require PERF_SAMPLE_ADDR, kernel implicitly retrieve the data->addr,
 	 * but the value will not dump to the userspace.
 	 */
-	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+	if (filtered_sample_type & PERF_SAMPLE_DATA_PAGE_SIZE) {
 		data->data_page_size = perf_get_page_size(data->addr);
+		data->sample_flags |= PERF_SAMPLE_DATA_PAGE_SIZE;
+	}
 
-	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+	if (filtered_sample_type & PERF_SAMPLE_CODE_PAGE_SIZE) {
 		data->code_page_size = perf_get_page_size(data->ip);
+		data->sample_flags |= PERF_SAMPLE_CODE_PAGE_SIZE;
+	}
 
-	if (sample_type & PERF_SAMPLE_AUX) {
+	if (filtered_sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
+		u16 header_size = perf_sample_data_size(data, event);
 
-		header->size += sizeof(u64); /* size */
+		header_size += sizeof(u64); /* size */
 
 		/*
 		 * Given the 16bit nature of header::size, an AUX sample can
@@ -7739,14 +7738,26 @@ void perf_prepare_sample(struct perf_event_header *header,
 		 * Make sure this doesn't happen by using up to U16_MAX bytes
 		 * per sample in total (rounded down to 8 byte boundary).
 		 */
-		size = min_t(size_t, U16_MAX - header->size,
+		size = min_t(size_t, U16_MAX - header_size,
 			     event->attr.aux_sample_size);
 		size = rounddown(size, 8);
 		size = perf_prepare_sample_aux(event, data, size);
 
-		WARN_ON_ONCE(size + header->size > U16_MAX);
-		header->size += size;
+		WARN_ON_ONCE(size + header_size > U16_MAX);
+		data->dyn_size += size + sizeof(u64); /* size above */
+		data->sample_flags |= PERF_SAMPLE_AUX;
 	}
+}
+
+void perf_prepare_header(struct perf_event_header *header,
+			 struct perf_sample_data *data,
+			 struct perf_event *event,
+			 struct pt_regs *regs)
+{
+	header->type = PERF_RECORD_SAMPLE;
+	header->size = perf_sample_data_size(data, event);
+	header->misc = perf_misc_flags(regs);
+
 	/*
 	 * If you're adding more sample types here, you likely need to do
 	 * something about the overflowing header::size, like repurpose the
@@ -7774,7 +7785,8 @@ __perf_event_output(struct perf_event *event,
 	/* protect the callchain buffers */
 	rcu_read_lock();
 
-	perf_prepare_sample(&header, data, event, regs);
+	perf_prepare_sample(data, event, regs);
+	perf_prepare_header(&header, data, event, regs);
 
 	err = output_begin(&handle, data, event, header.size);
 	if (err)
@@ -9406,6 +9418,7 @@ void perf_report_aux_output_id(struct perf_event *event, u64 hw_id)
 
 	perf_output_end(&handle);
 }
+EXPORT_SYMBOL_GPL(perf_report_aux_output_id);
 
 static int
 __perf_event_account_interrupt(struct perf_event *event, int throttle)
@@ -10132,8 +10145,7 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 	};
 
 	perf_sample_data_init(&data, 0, 0);
-	data.raw = &raw;
-	data.sample_flags |= PERF_SAMPLE_RAW;
+	perf_sample_save_raw_data(&data, &raw);
 
 	perf_trace_buf_update(record, event_type);
 
@@ -10340,13 +10352,7 @@ static void bpf_overflow_handler(struct perf_event *event,
 	rcu_read_lock();
 	prog = READ_ONCE(event->prog);
 	if (prog) {
-		if (prog->call_get_stack &&
-		    (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
-		    !(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) {
-			data->callchain = perf_callchain(event, regs);
-			data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
-		}
-
+		perf_prepare_sample(data, event, regs);
 		ret = bpf_prog_run(prog, &ctx);
 	}
 	rcu_read_unlock();
@@ -11679,15 +11685,6 @@ static void account_pmu_sb_event(struct perf_event *event)
 		attach_sb_event(event);
 }
 
-static void account_event_cpu(struct perf_event *event, int cpu)
-{
-	if (event->parent)
-		return;
-
-	if (is_cgroup_event(event))
-		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
-}
-
 /* Freq events need the tick to stay alive (see perf_event_task_tick). */
 static void account_freq_event_nohz(void)
 {
@@ -11775,8 +11772,6 @@ static void account_event(struct perf_event *event)
 	}
 enabled:
 
-	account_event_cpu(event, event->cpu);
-
 	account_pmu_sb_event(event);
 }
 
@@ -12339,12 +12334,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
-	/* Do we allow access to perf_event_open(2) ? */
-	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
+	err = perf_copy_attr(attr_uptr, &attr);
 	if (err)
 		return err;
 
-	err = perf_copy_attr(attr_uptr, &attr);
+	/* Do we allow access to perf_event_open(2) ? */
+	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
 	if (err)
 		return err;
 
@@ -12689,7 +12684,8 @@ SYSCALL_DEFINE5(perf_event_open,
 	return event_fd;
 
 err_context:
-	/* event->pmu_ctx freed by free_event() */
+	put_pmu_ctx(event->pmu_ctx);
+	event->pmu_ctx = NULL; /* _free_event() */
 err_locked:
 	mutex_unlock(&ctx->mutex);
 	perf_unpin_context(ctx);
@@ -12802,6 +12798,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 err_pmu_ctx:
 	put_pmu_ctx(pmu_ctx);
+	event->pmu_ctx = NULL; /* _free_event() */
 err_unlock:
 	mutex_unlock(&ctx->mutex);
 	perf_unpin_context(ctx);
@@ -12822,13 +12819,11 @@ static void __perf_pmu_remove(struct perf_event_context *ctx,
 
 	perf_event_groups_for_cpu_pmu(event, groups, cpu, pmu) {
 		perf_remove_from_context(event, 0);
-		unaccount_event_cpu(event, cpu);
 		put_pmu_ctx(event->pmu_ctx);
 		list_add(&event->migrate_entry, events);
 
 		for_each_sibling_event(sibling, event) {
 			perf_remove_from_context(sibling, 0);
-			unaccount_event_cpu(sibling, cpu);
 			put_pmu_ctx(sibling->pmu_ctx);
 			list_add(&sibling->migrate_entry, events);
 		}
@@ -12847,7 +12842,6 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 
 	if (event->state >= PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_INACTIVE;
-	account_event_cpu(event, cpu);
 	perf_install_in_context(ctx, event, cpu);
 }
 
@@ -13231,7 +13225,7 @@ inherit_event(struct perf_event *parent_event,
 	pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
 	if (IS_ERR(pmu_ctx)) {
 		free_event(child_event);
-		return NULL;
+		return ERR_CAST(pmu_ctx);
 	}
 	child_event->pmu_ctx = pmu_ctx;
 
@@ -13742,8 +13736,7 @@ static int __perf_cgroup_move(void *info)
 	struct task_struct *task = info;
 
 	preempt_disable();
-	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_switch(task);
+	perf_cgroup_switch(task);
 	preempt_enable();
 
 	return 0;