x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 163 insertions, 0 deletions

diff --git a/lib/lockref.c b/lib/lockref.c
new file mode 100644
index 000000000..9b3dd688d
--- /dev/null
+++ b/lib/lockref.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/lockref.h>
+
+#if USE_CMPXCHG_LOCKREF
+
+/*
+ * Note that the "cmpxchg()" reloads the "old" value for the
+ * failure case.
+ */
+#define CMPXCHG_LOOP(CODE, SUCCESS) do {					\
+	int retry = 100;							\
+	struct lockref old;							\
+	BUILD_BUG_ON(sizeof(old) != 8);						\
+	old.lock_count = READ_ONCE(lockref->lock_count);			\
+	while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) {  	\
+		struct lockref new = old;					\
+		CODE								\
+		if (likely(try_cmpxchg64_relaxed(&lockref->lock_count,		\
+						 &old.lock_count,		\
+						 new.lock_count))) {		\
+			SUCCESS;						\
+		}								\
+		if (!--retry)							\
+			break;							\
+	}									\
+} while (0)
+
+#else
+
+#define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0)
+
+#endif
+
+/**
+ * lockref_get - Increments reference count unconditionally
+ * @lockref: pointer to lockref structure
+ *
+ * This operation is only valid if you already hold a reference
+ * to the object, so you know the count cannot be zero.
+ */
+void lockref_get(struct lockref *lockref)
+{
+	CMPXCHG_LOOP(
+		new.count++;
+	,
+		return;
+	);
+
+	spin_lock(&lockref->lock);
+	lockref->count++;
+	spin_unlock(&lockref->lock);
+}
+EXPORT_SYMBOL(lockref_get);
+
+/**
+ * lockref_get_not_zero - Increments count unless the count is 0 or dead
+ * @lockref: pointer to lockref structure
+ * Return: 1 if count updated successfully or 0 if count was zero
+ */
+bool lockref_get_not_zero(struct lockref *lockref)
+{
+	bool retval = false;
+
+	CMPXCHG_LOOP(
+		new.count++;
+		if (old.count <= 0)
+			return false;
+	,
+		return true;
+	);
+
+	spin_lock(&lockref->lock);
+	if (lockref->count > 0) {
+		lockref->count++;
+		retval = true;
+	}
+	spin_unlock(&lockref->lock);
+	return retval;
+}
+EXPORT_SYMBOL(lockref_get_not_zero);
+
+/**
+ * lockref_put_return - Decrement reference count if possible
+ * @lockref: pointer to lockref structure
+ *
+ * Decrement the reference count and return the new value.
+ * If the lockref was dead or locked, return -1.
+ */
+int lockref_put_return(struct lockref *lockref)
+{
+	CMPXCHG_LOOP(
+		new.count--;
+		if (old.count <= 0)
+			return -1;
+	,
+		return new.count;
+	);
+	return -1;
+}
+EXPORT_SYMBOL(lockref_put_return);
+
+/**
+ * lockref_put_or_lock - decrements count unless count <= 1 before decrement
+ * @lockref: pointer to lockref structure
+ * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken
+ */
+bool lockref_put_or_lock(struct lockref *lockref)
+{
+	CMPXCHG_LOOP(
+		new.count--;
+		if (old.count <= 1)
+			break;
+	,
+		return true;
+	);
+
+	spin_lock(&lockref->lock);
+	if (lockref->count <= 1)
+		return false;
+	lockref->count--;
+	spin_unlock(&lockref->lock);
+	return true;
+}
+EXPORT_SYMBOL(lockref_put_or_lock);
+
+/**
+ * lockref_mark_dead - mark lockref dead
+ * @lockref: pointer to lockref structure
+ */
+void lockref_mark_dead(struct lockref *lockref)
+{
+	assert_spin_locked(&lockref->lock);
+	lockref->count = __LOCKREF_DEAD_VAL;
+}
+EXPORT_SYMBOL(lockref_mark_dead);
+
+/**
+ * lockref_get_not_dead - Increments count unless the ref is dead
+ * @lockref: pointer to lockref structure
+ * Return: 1 if count updated successfully or 0 if lockref was dead
+ */
+bool lockref_get_not_dead(struct lockref *lockref)
+{
+	bool retval = false;
+
+	CMPXCHG_LOOP(
+		new.count++;
+		if (old.count < 0)
+			return false;
+	,
+		return true;
+	);
+
+	spin_lock(&lockref->lock);
+	if (lockref->count >= 0) {
+		lockref->count++;
+		retval = true;
+	}
+	spin_unlock(&lockref->lock);
+	return retval;
+}
+EXPORT_SYMBOL(lockref_get_not_dead);