As Alexei noted, get_perf_callchain() return values may be reused
if a task is preempted after the BPF program enters migrate disable
mode. Drawing on the per-cpu design of bpf_perf_callchain_entries,
stack-allocated memory of bpf_perf_callchain_entry is used here.
Signed-off-by: Tao Chen <chen.dylane@linux.dev>
---
kernel/bpf/stackmap.c | 19 +++++++++++--------
1 file changed, 11 insertions(+), 8 deletions(-)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index e6e40f22826..1a51a2ea159 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -31,6 +31,11 @@ struct bpf_stack_map {
struct stack_map_bucket *buckets[] __counted_by(n_buckets);
};
+struct bpf_perf_callchain_entry {
+ u64 nr;
+ u64 ip[PERF_MAX_STACK_DEPTH];
+};
+
static inline bool stack_map_use_build_id(struct bpf_map *map)
{
return (map->map_flags & BPF_F_STACK_BUILD_ID);
@@ -305,6 +310,7 @@ 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;
+ struct bpf_perf_callchain_entry entry = { 0 };
if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
@@ -314,12 +320,8 @@ 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, NULL, 0, kernel, user, max_depth,
- false, false);
-
- if (unlikely(!trace))
- /* couldn't fetch the stack trace */
- return -EFAULT;
+ trace = get_perf_callchain(regs, (struct perf_callchain_entry *)&entry, 0,
+ kernel, user, max_depth, false, false);
return __bpf_get_stackid(map, trace, flags);
}
@@ -412,6 +414,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
bool user = flags & BPF_F_USER_STACK;
struct perf_callchain_entry *trace;
+ struct bpf_perf_callchain_entry entry = { 0 };
bool kernel = !user;
int err = -EINVAL;
u64 *ips;
@@ -451,8 +454,8 @@ 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, NULL, 0, kernel, user, max_depth,
- crosstask, false);
+ trace = get_perf_callchain(regs, (struct perf_callchain_entry *)&entry, 0,
+ kernel, user, max_depth, crosstask, false);
if (unlikely(!trace) || trace->nr < skip) {
if (may_fault)
--
2.48.1