[PATCH v3 1/1] kernel: kprobes: fix cur_kprobe corruption during re-entrant kprobe_busy_begin() calls

[Khaja Hussain Shaik Khaji]

Fix cur_kprobe corruption that occurs when kprobe_busy_begin() is called
re-entrantly during an active kprobe handler.

Previously, kprobe_busy_begin() unconditionally overwrites current_kprobe
with &kprobe_busy, and kprobe_busy_end() writes NULL. This approach works
correctly when no kprobe is active but fails during re-entrant calls.

On arm64, arm64_enter_el1_dbg() re-enables IRQs before invoking kprobe
handlers. This allows an IRQ during kretprobe entry_handler to trigger
kprobe_flush_task() via softirq, which calls kprobe_busy_begin/end and
corrupts cur_kprobe.

Problem flow: kretprobe entry_handler -> IRQ -> softirq ->
kprobe_flush_task -> kprobe_busy_begin/end -> cur_kprobe corruption.

This corruption causes two issues:
1. NULL cur_kprobe in setup_singlestep leading to panic in single-step
handler
2. kprobe_status overwritten with HIT_ACTIVE during execute-out-of-line
window

Implement a per-CPU re-entrancy tracking mechanism with:
- A depth counter to track nested calls
- Saved state for current_kprobe and kprobe_status
- Save state on first entry, restore on final exit
- Increment depth counter for nested calls only

This approach maintains compatibility with existing callers as
save/restore of NULL is a no-op.

Signed-off-by: Khaja Hussain Shaik Khaji <khaja.khaji@xxxxxxxxxxxxxxxx>
---
 kernel/kprobes.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e2cd01cf5968..47a4ae50ee6c 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -70,6 +70,15 @@ static bool kprobes_all_disarmed;
 static DEFINE_MUTEX(kprobe_mutex);
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance);
 
+/* Per-CPU re-entrancy state for kprobe_busy_begin/end.
+ * kprobe_busy_begin() may be called while a kprobe handler
+ * is active - e.g. kprobe_flush_task() via softirq during
+ * kretprobe entry_handler on arm64 where IRQs are re-enabled.
+ */
+static DEFINE_PER_CPU(int, kprobe_busy_depth);
+static DEFINE_PER_CPU(struct kprobe *, kprobe_busy_saved_current);
+static DEFINE_PER_CPU(unsigned long, kprobe_busy_saved_status);
+
 kprobe_opcode_t * __weak kprobe_lookup_name(const char *name,
 					unsigned int __unused)
 {
@@ -1307,14 +1316,31 @@ void kprobe_busy_begin(void)
 	struct kprobe_ctlblk *kcb;
 
 	preempt_disable();
-	__this_cpu_write(current_kprobe, &kprobe_busy);
-	kcb = get_kprobe_ctlblk();
-	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+	if (__this_cpu_read(kprobe_busy_depth) == 0) {
+		kcb = get_kprobe_ctlblk();
+		__this_cpu_write(kprobe_busy_saved_current,
+				 __this_cpu_read(current_kprobe));
+		__this_cpu_write(kprobe_busy_saved_status,
+				 kcb->kprobe_status);
+		__this_cpu_write(current_kprobe, &kprobe_busy);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+	}
+	__this_cpu_inc(kprobe_busy_depth);
 }
 
 void kprobe_busy_end(void)
 {
-	__this_cpu_write(current_kprobe, NULL);
+	struct kprobe_ctlblk *kcb;
+
+	__this_cpu_dec(kprobe_busy_depth);
+
+	if (__this_cpu_read(kprobe_busy_depth) == 0) {
+		kcb = get_kprobe_ctlblk();
+		__this_cpu_write(current_kprobe,
+				 __this_cpu_read(kprobe_busy_saved_current));
+		kcb->kprobe_status =
+				__this_cpu_read(kprobe_busy_saved_status);
+	}
 	preempt_enable();
 }
 
-- 
2.34.1