[PATCH bpf-next v4 2/2] bpf: Hold the perf callchain entry until used completely

[Tao Chen <chen.dylane@linux.dev>]

As Alexei noted, get_perf_callchain() return values may be reused
if a task is preempted after the BPF program enters migrate disable
mode. The perf_callchain_entres has a small stack of entries, and
we can reuse it as follows:

1. get the perf callchain entry
2. BPF use...
3. put the perf callchain entry

Signed-off-by: Tao Chen <chen.dylane@linux.dev>
---
 kernel/bpf/stackmap.c | 61 ++++++++++++++++++++++++++++++++++---------
 1 file changed, 48 insertions(+), 13 deletions(-)

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index e28b35c7e0b..70d38249083 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -188,13 +188,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 }
 
 static struct perf_callchain_entry *
-get_callchain_entry_for_task(struct task_struct *task, u32 max_depth)
+get_callchain_entry_for_task(int *rctx, struct task_struct *task, u32 max_depth)
 {
 #ifdef CONFIG_STACKTRACE
 	struct perf_callchain_entry *entry;
-	int rctx;
 
-	entry = get_callchain_entry(&rctx);
+	entry = get_callchain_entry(rctx);
 
 	if (!entry)
 		return NULL;
@@ -216,8 +215,6 @@ get_callchain_entry_for_task(struct task_struct *task, u32 max_depth)
 			to[i] = (u64)(from[i]);
 	}
 
-	put_callchain_entry(rctx);
-
 	return entry;
 #else /* CONFIG_STACKTRACE */
 	return NULL;
@@ -297,6 +294,31 @@ static long __bpf_get_stackid(struct bpf_map *map,
 	return id;
 }
 
+static struct perf_callchain_entry *
+bpf_get_perf_callchain(int *rctx, struct pt_regs *regs, bool kernel, bool user,
+		       int max_stack, bool crosstask)
+{
+	struct perf_callchain_entry_ctx ctx;
+	struct perf_callchain_entry *entry;
+
+	entry = get_callchain_entry(rctx);
+	if (unlikely(!entry))
+		return NULL;
+
+	__init_perf_callchain_ctx(&ctx, entry, max_stack, false);
+	if (kernel)
+		__get_perf_callchain_kernel(&ctx, regs);
+	if (user && !crosstask)
+		__get_perf_callchain_user(&ctx, regs);
+
+	return entry;
+}
+
+static void bpf_put_callchain_entry(int rctx)
+{
+	put_callchain_entry(rctx);
+}
+
 BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags)
 {
@@ -305,6 +327,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	bool user = flags & BPF_F_USER_STACK;
 	struct perf_callchain_entry *trace;
 	bool kernel = !user;
+	int rctx, ret;
 
 	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
 			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
@@ -314,14 +337,15 @@ 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,
-				   false);
-
+	trace = bpf_get_perf_callchain(&rctx, regs, kernel, user, max_depth, false);
 	if (unlikely(!trace))
 		/* couldn't fetch the stack trace */
 		return -EFAULT;
 
-	return __bpf_get_stackid(map, trace, flags);
+	ret = __bpf_get_stackid(map, trace, flags);
+	bpf_put_callchain_entry(rctx);
+
+	return ret;
 }
 
 const struct bpf_func_proto bpf_get_stackid_proto = {
@@ -415,6 +439,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	bool kernel = !user;
 	int err = -EINVAL;
 	u64 *ips;
+	int rctx;
 
 	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
 			       BPF_F_USER_BUILD_ID)))
@@ -449,17 +474,24 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (trace_in)
 		trace = trace_in;
 	else if (kernel && task)
-		trace = get_callchain_entry_for_task(task, max_depth);
+		trace = get_callchain_entry_for_task(&rctx, task, max_depth);
 	else
-		trace = get_perf_callchain(regs, kernel, user, max_depth,
-					   crosstask);
+		trace = bpf_get_perf_callchain(&rctx, regs, kernel, user, max_depth, crosstask);
 
-	if (unlikely(!trace) || trace->nr < skip) {
+	if (unlikely(!trace)) {
 		if (may_fault)
 			rcu_read_unlock();
 		goto err_fault;
 	}
 
+	if (trace->nr < skip) {
+		if (may_fault)
+			rcu_read_unlock();
+		if (!trace_in)
+			bpf_put_callchain_entry(rctx);
+		goto err_fault;
+	}
+
 	trace_nr = trace->nr - skip;
 	trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
 	copy_len = trace_nr * elem_size;
@@ -479,6 +511,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (may_fault)
 		rcu_read_unlock();
 
+	if (!trace_in)
+		bpf_put_callchain_entry(rctx);
+
 	if (user_build_id)
 		stack_map_get_build_id_offset(buf, trace_nr, user, may_fault);
 
-- 
2.48.1