[PATCH 4.4 073/135] kretprobe: Prevent triggering kretprobe from within kprobe_flush_task

From: Sasha Levin
Date: Mon Jun 29 2020 - 17:10:38 EST


From: Jiri Olsa <jolsa@xxxxxxxxxx>

[ Upstream commit 9b38cc704e844e41d9cf74e647bff1d249512cb3 ]

Ziqian reported lockup when adding retprobe on _raw_spin_lock_irqsave.
My test was also able to trigger lockdep output:

============================================
WARNING: possible recursive locking detected
5.6.0-rc6+ #6 Not tainted
--------------------------------------------
sched-messaging/2767 is trying to acquire lock:
ffffffff9a492798 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_hash_lock+0x52/0xa0

but task is already holding lock:
ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50

other info that might help us debug this:
Possible unsafe locking scenario:

CPU0
----
lock(&(kretprobe_table_locks[i].lock));
lock(&(kretprobe_table_locks[i].lock));

*** DEADLOCK ***

May be due to missing lock nesting notation

1 lock held by sched-messaging/2767:
#0: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50

stack backtrace:
CPU: 3 PID: 2767 Comm: sched-messaging Not tainted 5.6.0-rc6+ #6
Call Trace:
dump_stack+0x96/0xe0
__lock_acquire.cold.57+0x173/0x2b7
? native_queued_spin_lock_slowpath+0x42b/0x9e0
? lockdep_hardirqs_on+0x590/0x590
? __lock_acquire+0xf63/0x4030
lock_acquire+0x15a/0x3d0
? kretprobe_hash_lock+0x52/0xa0
_raw_spin_lock_irqsave+0x36/0x70
? kretprobe_hash_lock+0x52/0xa0
kretprobe_hash_lock+0x52/0xa0
trampoline_handler+0xf8/0x940
? kprobe_fault_handler+0x380/0x380
? find_held_lock+0x3a/0x1c0
kretprobe_trampoline+0x25/0x50
? lock_acquired+0x392/0xbc0
? _raw_spin_lock_irqsave+0x50/0x70
? __get_valid_kprobe+0x1f0/0x1f0
? _raw_spin_unlock_irqrestore+0x3b/0x40
? finish_task_switch+0x4b9/0x6d0
? __switch_to_asm+0x34/0x70
? __switch_to_asm+0x40/0x70

The code within the kretprobe handler checks for probe reentrancy,
so we won't trigger any _raw_spin_lock_irqsave probe in there.

The problem is in outside kprobe_flush_task, where we call:

kprobe_flush_task
kretprobe_table_lock
raw_spin_lock_irqsave
_raw_spin_lock_irqsave

where _raw_spin_lock_irqsave triggers the kretprobe and installs
kretprobe_trampoline handler on _raw_spin_lock_irqsave return.

The kretprobe_trampoline handler is then executed with already
locked kretprobe_table_locks, and first thing it does is to
lock kretprobe_table_locks ;-) the whole lockup path like:

kprobe_flush_task
kretprobe_table_lock
raw_spin_lock_irqsave
_raw_spin_lock_irqsave ---> probe triggered, kretprobe_trampoline installed

---> kretprobe_table_locks locked

kretprobe_trampoline
trampoline_handler
kretprobe_hash_lock(current, &head, &flags); <--- deadlock

Adding kprobe_busy_begin/end helpers that mark code with fake
probe installed to prevent triggering of another kprobe within
this code.

Using these helpers in kprobe_flush_task, so the probe recursion
protection check is hit and the probe is never set to prevent
above lockup.

Link: http://lkml.kernel.org/r/158927059835.27680.7011202830041561604.stgit@devnote2

Fixes: ef53d9c5e4da ("kprobes: improve kretprobe scalability with hashed locking")
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "Gustavo A . R . Silva" <gustavoars@xxxxxxxxxx>
Cc: Anders Roxell <anders.roxell@xxxxxxxxxx>
Cc: "Naveen N . Rao" <naveen.n.rao@xxxxxxxxxxxxx>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@xxxxxxxxx>
Cc: David Miller <davem@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Reported-by: "Ziqian SUN (Zamir)" <zsun@xxxxxxxxxx>
Acked-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
arch/x86/kernel/kprobes/core.c | 16 +++-------------
include/linux/kprobes.h | 4 ++++
kernel/kprobes.c | 24 ++++++++++++++++++++++++
3 files changed, 31 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 7d2e2e40bbba3..5a6cb30b1c621 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -736,16 +736,11 @@ static void __used kretprobe_trampoline_holder(void)
NOKPROBE_SYMBOL(kretprobe_trampoline_holder);
NOKPROBE_SYMBOL(kretprobe_trampoline);

-static struct kprobe kretprobe_kprobe = {
- .addr = (void *)kretprobe_trampoline,
-};
-
/*
* Called from kretprobe_trampoline
*/
__visible __used void *trampoline_handler(struct pt_regs *regs)
{
- struct kprobe_ctlblk *kcb;
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
struct hlist_node *tmp;
@@ -755,16 +750,12 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
void *frame_pointer;
bool skipped = false;

- preempt_disable();
-
/*
* Set a dummy kprobe for avoiding kretprobe recursion.
* Since kretprobe never run in kprobe handler, kprobe must not
* be running at this point.
*/
- kcb = get_kprobe_ctlblk();
- __this_cpu_write(current_kprobe, &kretprobe_kprobe);
- kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+ kprobe_busy_begin();

INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
@@ -843,7 +834,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
__this_cpu_write(current_kprobe, &ri->rp->kp);
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
- __this_cpu_write(current_kprobe, &kretprobe_kprobe);
+ __this_cpu_write(current_kprobe, &kprobe_busy);
}

recycle_rp_inst(ri, &empty_rp);
@@ -859,8 +850,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)

kretprobe_hash_unlock(current, &flags);

- __this_cpu_write(current_kprobe, NULL);
- preempt_enable();
+ kprobe_busy_end();

hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index cb527c78de9fd..4db62045f01ae 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -366,6 +366,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
return this_cpu_ptr(&kprobe_ctlblk);
}

+extern struct kprobe kprobe_busy;
+void kprobe_busy_begin(void);
+void kprobe_busy_end(void);
+
int register_kprobe(struct kprobe *p);
void unregister_kprobe(struct kprobe *p);
int register_kprobes(struct kprobe **kps, int num);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 430baa19e48c3..5bda113a3116c 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1150,6 +1150,26 @@ __releases(hlist_lock)
}
NOKPROBE_SYMBOL(kretprobe_table_unlock);

+struct kprobe kprobe_busy = {
+ .addr = (void *) get_kprobe,
+};
+
+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;
+}
+
+void kprobe_busy_end(void)
+{
+ __this_cpu_write(current_kprobe, NULL);
+ preempt_enable();
+}
+
/*
* This function is called from finish_task_switch when task tk becomes dead,
* so that we can recycle any function-return probe instances associated
@@ -1167,6 +1187,8 @@ void kprobe_flush_task(struct task_struct *tk)
/* Early boot. kretprobe_table_locks not yet initialized. */
return;

+ kprobe_busy_begin();
+
INIT_HLIST_HEAD(&empty_rp);
hash = hash_ptr(tk, KPROBE_HASH_BITS);
head = &kretprobe_inst_table[hash];
@@ -1180,6 +1202,8 @@ void kprobe_flush_task(struct task_struct *tk)
hlist_del(&ri->hlist);
kfree(ri);
}
+
+ kprobe_busy_end();
}
NOKPROBE_SYMBOL(kprobe_flush_task);

--
2.25.1