diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 0bebb5c348b8268eff6135f24f1635c0adf2dbb1..d36f68b08acc1fc95c0df5867df545ac2976d0d6 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -595,7 +595,7 @@ extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
 extern void *perf_trace_buf_prepare(int size, unsigned short type,
-				    struct pt_regs *regs, int *rctxp);
+				    struct pt_regs **regs, int *rctxp);
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4f7a61ca4b393dc837cb4ad278c4a66306247cbd..3a7bd80b4db8b5f8f74f94bfdad17e76389aff77 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -665,6 +665,7 @@ static inline int is_software_event(struct perf_event *event)
 
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
+extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
 extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
 
 #ifndef perf_arch_fetch_caller_regs
@@ -689,14 +690,25 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
-	struct pt_regs hot_regs;
+	if (static_key_false(&perf_swevent_enabled[event_id]))
+		__perf_sw_event(event_id, nr, regs, addr);
+}
+
+DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
 
+/*
+ * 'Special' version for the scheduler, it hard assumes no recursion,
+ * which is guaranteed by us not actually scheduling inside other swevents
+ * because those disable preemption.
+ */
+static __always_inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
+{
 	if (static_key_false(&perf_swevent_enabled[event_id])) {
-		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs);
-			regs = &hot_regs;
-		}
-		__perf_sw_event(event_id, nr, regs, addr);
+		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+		perf_fetch_caller_regs(regs);
+		___perf_sw_event(event_id, nr, regs, addr);
 	}
 }
 
@@ -712,7 +724,7 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
 static inline void perf_event_task_sched_out(struct task_struct *prev,
 					     struct task_struct *next)
 {
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
+	perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
 
 	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_out(prev, next);
@@ -823,6 +835,8 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh)
 static inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)	{ }
 static inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)			{ }
+static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
 static inline int perf_register_guest_info_callbacks
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 139b5067345b2ecb2daa1881d8b484ad76cf382a..27609dfcce25916120521b23215dd473fab0051a 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -763,7 +763,7 @@ perf_trace_##call(void *__data, proto)					\
 	struct ftrace_event_call *event_call = __data;			\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
-	struct pt_regs __regs;						\
+	struct pt_regs *__regs;						\
 	u64 __addr = 0, __count = 1;					\
 	struct task_struct *__task = NULL;				\
 	struct hlist_head *head;					\
@@ -782,18 +782,19 @@ perf_trace_##call(void *__data, proto)					\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	perf_fetch_caller_regs(&__regs);				\
 	entry = perf_trace_buf_prepare(__entry_size,			\
 			event_call->event.type, &__regs, &rctx);	\
 	if (!entry)							\
 		return;							\
 									\
+	perf_fetch_caller_regs(__regs);					\
+									\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
-		__count, &__regs, head, __task);			\
+		__count, __regs, head, __task);				\
 }
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 882f835a0d859e011848069ed6ee716f3def4dee..c10124b772c44bbf1131c294fb5feaa0bb659a96 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5889,6 +5889,8 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
 	rcu_read_unlock();
 }
 
+DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]);
+
 int perf_swevent_get_recursion_context(void)
 {
 	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
@@ -5904,21 +5906,30 @@ inline void perf_swevent_put_recursion_context(int rctx)
 	put_recursion_context(swhash->recursion, rctx);
 }
 
-void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
+void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
 	struct perf_sample_data data;
-	int rctx;
 
-	preempt_disable_notrace();
-	rctx = perf_swevent_get_recursion_context();
-	if (rctx < 0)
+	if (WARN_ON_ONCE(!regs))
 		return;
 
 	perf_sample_data_init(&data, addr, 0);
-
 	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs);
+}
+
+void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
+{
+	int rctx;
+
+	preempt_disable_notrace();
+	rctx = perf_swevent_get_recursion_context();
+	if (unlikely(rctx < 0))
+		goto fail;
+
+	___perf_sw_event(event_id, nr, regs, addr);
 
 	perf_swevent_put_recursion_context(rctx);
+fail:
 	preempt_enable_notrace();
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c0accc00566eb774a022870635c60e63da6ee198..d22fb16a715397eadcf76a5f42c15cea37985e93 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1082,7 +1082,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
-		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
 	}
 
 	__set_task_cpu(p, new_cpu);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 4b9c114ee9de87d10edd154239c7cb18d237af00..6fa484de2ba1811ada052f451d1bc147e7241068 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -261,7 +261,7 @@ void perf_trace_del(struct perf_event *p_event, int flags)
 }
 
 void *perf_trace_buf_prepare(int size, unsigned short type,
-			     struct pt_regs *regs, int *rctxp)
+			     struct pt_regs **regs, int *rctxp)
 {
 	struct trace_entry *entry;
 	unsigned long flags;
@@ -280,6 +280,8 @@ void *perf_trace_buf_prepare(int size, unsigned short type,
 	if (*rctxp < 0)
 		return NULL;
 
+	if (regs)
+		*regs = this_cpu_ptr(&__perf_regs[*rctxp]);
 	raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
 
 	/* zero the dead bytes from align to not leak stack to user */
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5edb518be3458a01096351f0562fb84ce5f9b231..296079ae658300123e157d3265fe9e0f5a352bcf 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1148,7 +1148,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		return;
 
@@ -1179,7 +1179,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		return;
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index c6ee36fcbf9071a22e4b86d7ba4b3da3bd047a32..f97f6e3a676ce35b1606b58fc9da694e38d83204 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -574,7 +574,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	size -= sizeof(u32);
 
 	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
-				sys_data->enter_event->event.type, regs, &rctx);
+				sys_data->enter_event->event.type, NULL, &rctx);
 	if (!rec)
 		return;
 
@@ -647,7 +647,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	size -= sizeof(u32);
 
 	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
-				sys_data->exit_event->event.type, regs, &rctx);
+				sys_data->exit_event->event.type, NULL, &rctx);
 	if (!rec)
 		return;
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8520acc34b185f7cb05fcbc4a2a30685dce0ef13..b11441321e7a473a6e7086f28d791dcd44b8a6f3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1111,7 +1111,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	if (hlist_empty(head))
 		goto out;
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		goto out;