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, 72 insertions, 0 deletions

diff --git a/drivers/hwspinlock/hwspinlock_internal.h b/drivers/hwspinlock/hwspinlock_internal.h
new file mode 100644
index 000000000..f298fc0ee
--- /dev/null
+++ b/drivers/hwspinlock/hwspinlock_internal.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Hardware spinlocks internal header
+ *
+ * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Contact: Ohad Ben-Cohen <ohad@wizery.com>
+ */
+
+#ifndef __HWSPINLOCK_HWSPINLOCK_H
+#define __HWSPINLOCK_HWSPINLOCK_H
+
+#include <linux/spinlock.h>
+#include <linux/device.h>
+
+struct hwspinlock_device;
+
+/**
+ * struct hwspinlock_ops - platform-specific hwspinlock handlers
+ *
+ * @trylock: make a single attempt to take the lock. returns 0 on
+ *	     failure and true on success. may _not_ sleep.
+ * @unlock:  release the lock. always succeed. may _not_ sleep.
+ * @bust:    optional, platform-specific bust handler, called by hwspinlock
+ *	     core to bust a specific lock.
+ * @relax:   optional, platform-specific relax handler, called by hwspinlock
+ *	     core while spinning on a lock, between two successive
+ *	     invocations of @trylock. may _not_ sleep.
+ */
+struct hwspinlock_ops {
+	int (*trylock)(struct hwspinlock *lock);
+	void (*unlock)(struct hwspinlock *lock);
+	int (*bust)(struct hwspinlock *lock, unsigned int id);
+	void (*relax)(struct hwspinlock *lock);
+};
+
+/**
+ * struct hwspinlock - this struct represents a single hwspinlock instance
+ * @bank: the hwspinlock_device structure which owns this lock
+ * @lock: initialized and used by hwspinlock core
+ * @priv: private data, owned by the underlying platform-specific hwspinlock drv
+ */
+struct hwspinlock {
+	struct hwspinlock_device *bank;
+	spinlock_t lock;
+	void *priv;
+};
+
+/**
+ * struct hwspinlock_device - a device which usually spans numerous hwspinlocks
+ * @dev: underlying device, will be used to invoke runtime PM api
+ * @ops: platform-specific hwspinlock handlers
+ * @base_id: id index of the first lock in this device
+ * @num_locks: number of locks in this device
+ * @lock: dynamically allocated array of 'struct hwspinlock'
+ */
+struct hwspinlock_device {
+	struct device *dev;
+	const struct hwspinlock_ops *ops;
+	int base_id;
+	int num_locks;
+	struct hwspinlock lock[];
+};
+
+static inline int hwlock_to_id(struct hwspinlock *hwlock)
+{
+	int local_id = hwlock - &hwlock->bank->lock[0];
+
+	return hwlock->bank->base_id + local_id;
+}
+
+#endif /* __HWSPINLOCK_HWSPINLOCK_H */