perf: Use extern perf_callchain_entry for get_perf_callchain

From bpf stack map, we want to use our own buffers to avoid unnecessary
copy, so let us pass it directly. BPF will use this in the next patch.

Signed-off-by: Tao Chen <[email protected]>

Author: Tao Chen

include/linux/perf_event.h

@@ -1719,8 +1719,8 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
 extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern struct perf_callchain_entry *
-get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
-		   u32 max_stack, bool crosstask, bool add_mark);
+get_perf_callchain(struct pt_regs *regs, struct perf_callchain_entry *external_entry,
+		   bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 extern struct perf_callchain_entry *get_callchain_entry(int *rctx);

kernel/bpf/stackmap.c

@@ -314,7 +314,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	if (max_depth > sysctl_perf_event_max_stack)
 		max_depth = sysctl_perf_event_max_stack;
 
-	trace = get_perf_callchain(regs, kernel, user, max_depth,
+	trace = get_perf_callchain(regs, NULL, kernel, user, max_depth,
 				   false, false);
 
 	if (unlikely(!trace))
@@ -451,7 +451,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	else if (kernel && task)
 		trace = get_callchain_entry_for_task(task, max_depth);
 	else
-		trace = get_perf_callchain(regs, kernel, user, max_depth,
+		trace = get_perf_callchain(regs, NULL, kernel, user, max_depth,
 					   crosstask, false);
 
 	if (unlikely(!trace) || trace->nr < skip) {

kernel/events/callchain.c

@@ -217,8 +217,8 @@ static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entr
 }
 
 struct perf_callchain_entry *
-get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
-		   u32 max_stack, bool crosstask, bool add_mark)
+get_perf_callchain(struct pt_regs *regs, struct perf_callchain_entry *external_entry,
+		   bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark)
 {
 	struct perf_callchain_entry *entry;
 	struct perf_callchain_entry_ctx ctx;
@@ -228,7 +228,11 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 	if (crosstask && user && !kernel)
 		return NULL;
 
-	entry = get_callchain_entry(&rctx);
+	if (external_entry)
+		entry = external_entry;
+	else
+		entry = get_callchain_entry(&rctx);
+
 	if (!entry)
 		return NULL;
 
@@ -260,7 +264,8 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 	}
 
 exit_put:
-	put_callchain_entry(rctx);
+	if (!external_entry)
+		put_callchain_entry(rctx);
 
 	return entry;
 }

kernel/events/core.c

@@ -8217,7 +8217,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	if (!kernel && !user)
 		return &__empty_callchain;
 
-	callchain = get_perf_callchain(regs, kernel, user,
+	callchain = get_perf_callchain(regs, NULL, kernel, user,
 				       max_stack, crosstask, true);
 	return callchain ?: &__empty_callchain;
 }