tracing: Fix race condition in kprobe initialization causing NULL pointer dereference

There is a critical race condition in kprobe initialization that can lead to
NULL pointer dereference and kernel crash.

[1135630.084782] Unable to handle kernel paging request at virtual address 0000710a04630000
...
[1135630.260314] pstate: 404003c9 (nZcv DAIF +PAN -UAO)
[1135630.269239] pc : kprobe_perf_func+0x30/0x260
[1135630.277643] lr : kprobe_dispatcher+0x44/0x60
[1135630.286041] sp : ffffaeff4977fa40
[1135630.293441] x29: ffffaeff4977fa40 x28: ffffaf015340e400
[1135630.302837] x27: 0000000000000000 x26: 0000000000000000
[1135630.312257] x25: ffffaf029ed108a8 x24: ffffaf015340e528
[1135630.321705] x23: ffffaeff4977fc50 x22: ffffaeff4977fc50
[1135630.331154] x21: 0000000000000000 x20: ffffaeff4977fc50
[1135630.340586] x19: ffffaf015340e400 x18: 0000000000000000
[1135630.349985] x17: 0000000000000000 x16: 0000000000000000
[1135630.359285] x15: 0000000000000000 x14: 0000000000000000
[1135630.368445] x13: 0000000000000000 x12: 0000000000000000
[1135630.377473] x11: 0000000000000000 x10: 0000000000000000
[1135630.386411] x9 : 0000000000000000 x8 : 0000000000000000
[1135630.395252] x7 : 0000000000000000 x6 : 0000000000000000
[1135630.403963] x5 : 0000000000000000 x4 : 0000000000000000
[1135630.412545] x3 : 0000710a04630000 x2 : 0000000000000006
[1135630.421021] x1 : ffffaeff4977fc50 x0 : 0000710a04630000
[1135630.429410] Call trace:
[1135630.434828]  kprobe_perf_func+0x30/0x260
[1135630.441661]  kprobe_dispatcher+0x44/0x60
[1135630.448396]  aggr_pre_handler+0x70/0xc8
[1135630.454959]  kprobe_breakpoint_handler+0x140/0x1e0
[1135630.462435]  brk_handler+0xbc/0xd8
[1135630.468437]  do_debug_exception+0x84/0x138
[1135630.475074]  el1_dbg+0x18/0x8c
[1135630.480582]  security_file_permission+0x0/0xd0
[1135630.487426]  vfs_write+0x70/0x1c0
[1135630.493059]  ksys_write+0x5c/0xc8
[1135630.498638]  __arm64_sys_write+0x24/0x30
[1135630.504821]  el0_svc_common+0x78/0x130
[1135630.510838]  el0_svc_handler+0x38/0x78
[1135630.516834]  el0_svc+0x8/0x1b0

kernel/trace/trace_kprobe.c: 1308
0xffff3df8995039ec <kprobe_perf_func+0x2c>:     ldr     x21, [x24,torvalds#120]
include/linux/compiler.h: 294
0xffff3df8995039f0 <kprobe_perf_func+0x30>:     ldr     x1, [x21,x0]

kernel/trace/trace_kprobe.c
1308: head = this_cpu_ptr(call->perf_events);
1309: if (hlist_empty(head))
1310: 	return 0;

crash> struct trace_event_call -o
struct trace_event_call {
  ...
  [120] struct hlist_head *perf_events;  //(call->perf_event)
  ...
}

crash> struct trace_event_call ffffaf015340e528
struct trace_event_call {
  ...
  perf_events = 0xffff0ad5fa89f088, //this value is correct, but x21 = 0
  ...
}

Race Condition Analysis:

The race occurs between kprobe activation and perf_events initialization:

  CPU0                                    CPU1
  ====                                    ====
  perf_kprobe_init
    perf_trace_event_init
      tp_event->perf_events = list;(1)
      tp_event->class->reg (2)← KPROBE ACTIVE
                                          Debug exception triggers
                                          ...
                                          kprobe_dispatcher
                                            kprobe_perf_func (tk->tp.flags & TP_FLAG_PROFILE)
                                              head = this_cpu_ptr(call->perf_events)(3)
                                              (perf_events is still NULL)

Problem:
1. CPU0 executes (1) assigning tp_event->perf_events = list
2. CPU0 executes (2) enabling kprobe functionality via class->reg()
3. CPU1 triggers and reaches kprobe_dispatcher
4. CPU1 checks TP_FLAG_PROFILE - condition passes (step 2 completed)
5. CPU1 calls kprobe_perf_func() and crashes at (3) because
   call->perf_events is still NULL

CPU1 sees that kprobe functionality is enabled but does not see that
perf_events has been assigned.

Add pairing read and write memory barriers to guarantee that if CPU1
sees that kprobe functionality is enabled, it must also see that
perf_events has been assigned.

v1->v2: Fix race analysis (per Masami) - kprobe arms in class->reg().
v2->v3: Adopt RELEASE/ACQUIRE semantics per Peter/John's suggestions,
        aligning with Steven's clarification on barrier purposes.
v3->v4: Introduce load_flag() (Masami) and optimize barrier usage in
        checks/clear (Peter).

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

Author: chenyuan0001

kernel/trace/trace_fprobe.c

@@ -522,13 +522,14 @@ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip,
 			     void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+	unsigned int flags = trace_probe_load_flag(&tf->tp);
 	int ret = 0;
 
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
+	if (flags & TP_FLAG_TRACE)
 		fentry_trace_func(tf, entry_ip, fregs);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret = fentry_perf_func(tf, entry_ip, fregs);
 #endif
 	return ret;
@@ -540,11 +541,12 @@ static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip,
 			     void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+	unsigned int flags = trace_probe_load_flag(&tf->tp);
 
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
+	if (flags & TP_FLAG_TRACE)
 		fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		fexit_perf_func(tf, entry_ip, ret_ip, fregs, entry_data);
 #endif
 }

kernel/trace/trace_kprobe.c

@@ -1815,14 +1815,15 @@ static int kprobe_register(struct trace_event_call *event,
 static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
+	unsigned int flags = trace_probe_load_flag(&tk->tp);
 	int ret = 0;
 
 	raw_cpu_inc(*tk->nhit);
 
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
+	if (flags & TP_FLAG_TRACE)
 		kprobe_trace_func(tk, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret = kprobe_perf_func(tk, regs);
 #endif
 	return ret;
@@ -1834,6 +1835,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	struct kretprobe *rp = get_kretprobe(ri);
 	struct trace_kprobe *tk;
+	unsigned int flags;
 
 	/*
 	 * There is a small chance that get_kretprobe(ri) returns NULL when
@@ -1846,10 +1848,11 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 	tk = container_of(rp, struct trace_kprobe, rp);
 	raw_cpu_inc(*tk->nhit);
 
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tk->tp);
+	if (flags & TP_FLAG_TRACE)
 		kretprobe_trace_func(tk, ri, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		kretprobe_perf_func(tk, ri, regs);
 #endif
 	return 0;	/* We don't tweak kernel, so just return 0 */

kernel/trace/trace_probe.h

@@ -271,16 +271,21 @@ struct event_file_link {
 	struct list_head		list;
 };
 
+static inline unsigned int trace_probe_load_flag(struct trace_probe *tp)
+{
+	return smp_load_acquire(&tp->event->flags);
+}
+
 static inline bool trace_probe_test_flag(struct trace_probe *tp,
 					 unsigned int flag)
 {
-	return !!(tp->event->flags & flag);
+	return !!(trace_probe_load_flag(tp) & flag);
 }
 
 static inline void trace_probe_set_flag(struct trace_probe *tp,
 					unsigned int flag)
 {
-	tp->event->flags |= flag;
+	smp_store_release(&tp->event->flags, tp->event->flags | flag);
 }
 
 static inline void trace_probe_clear_flag(struct trace_probe *tp,

kernel/trace/trace_uprobe.c

@@ -1529,6 +1529,7 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs,
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
 	struct uprobe_cpu_buffer *ucb = NULL;
+	unsigned int flags;
 	int ret = 0;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
@@ -1543,11 +1544,12 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs,
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tu->tp);
+	if (flags & TP_FLAG_TRACE)
 		ret |= uprobe_trace_func(tu, regs, &ucb);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret |= uprobe_perf_func(tu, regs, &ucb);
 #endif
 	uprobe_buffer_put(ucb);
@@ -1561,6 +1563,7 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
 	struct uprobe_cpu_buffer *ucb = NULL;
+	unsigned int flags;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
 
@@ -1572,11 +1575,12 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tu->tp);
+	if (flags & TP_FLAG_TRACE)
 		uretprobe_trace_func(tu, func, regs, &ucb);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		uretprobe_perf_func(tu, func, regs, &ucb);
 #endif
 	uprobe_buffer_put(ucb);