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, 240 insertions, 0 deletions

diff --git a/lib/test_static_keys.c b/lib/test_static_keys.c
new file mode 100644
index 000000000..00c715f30
--- /dev/null
+++ b/lib/test_static_keys.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Kernel module for testing static keys.
+ *
+ * Copyright 2015 Akamai Technologies Inc. All Rights Reserved
+ *
+ * Authors:
+ *      Jason Baron       <jbaron@akamai.com>
+ */
+
+#include <linux/module.h>
+#include <linux/jump_label.h>
+
+/* old keys */
+struct static_key old_true_key	= STATIC_KEY_INIT_TRUE;
+struct static_key old_false_key	= STATIC_KEY_INIT_FALSE;
+
+/* new api */
+DEFINE_STATIC_KEY_TRUE(true_key);
+DEFINE_STATIC_KEY_FALSE(false_key);
+
+/* external */
+extern struct static_key base_old_true_key;
+extern struct static_key base_inv_old_true_key;
+extern struct static_key base_old_false_key;
+extern struct static_key base_inv_old_false_key;
+
+/* new api */
+extern struct static_key_true base_true_key;
+extern struct static_key_true base_inv_true_key;
+extern struct static_key_false base_false_key;
+extern struct static_key_false base_inv_false_key;
+
+
+struct test_key {
+	bool			init_state;
+	struct static_key	*key;
+	bool			(*test_key)(void);
+};
+
+#define test_key_func(key, branch)	\
+static bool key ## _ ## branch(void)	\
+{					\
+	return branch(&key);		\
+}
+
+static void invert_key(struct static_key *key)
+{
+	if (static_key_enabled(key))
+		static_key_disable(key);
+	else
+		static_key_enable(key);
+}
+
+static void invert_keys(struct test_key *keys, int size)
+{
+	struct static_key *previous = NULL;
+	int i;
+
+	for (i = 0; i < size; i++) {
+		if (previous != keys[i].key) {
+			invert_key(keys[i].key);
+			previous = keys[i].key;
+		}
+	}
+}
+
+static int verify_keys(struct test_key *keys, int size, bool invert)
+{
+	int i;
+	bool ret, init;
+
+	for (i = 0; i < size; i++) {
+		ret = static_key_enabled(keys[i].key);
+		init = keys[i].init_state;
+		if (ret != (invert ? !init : init))
+			return -EINVAL;
+		ret = keys[i].test_key();
+		if (static_key_enabled(keys[i].key)) {
+			if (!ret)
+				return -EINVAL;
+		} else {
+			if (ret)
+				return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+test_key_func(old_true_key, static_key_true)
+test_key_func(old_false_key, static_key_false)
+test_key_func(true_key, static_branch_likely)
+test_key_func(true_key, static_branch_unlikely)
+test_key_func(false_key, static_branch_likely)
+test_key_func(false_key, static_branch_unlikely)
+test_key_func(base_old_true_key, static_key_true)
+test_key_func(base_inv_old_true_key, static_key_true)
+test_key_func(base_old_false_key, static_key_false)
+test_key_func(base_inv_old_false_key, static_key_false)
+test_key_func(base_true_key, static_branch_likely)
+test_key_func(base_true_key, static_branch_unlikely)
+test_key_func(base_inv_true_key, static_branch_likely)
+test_key_func(base_inv_true_key, static_branch_unlikely)
+test_key_func(base_false_key, static_branch_likely)
+test_key_func(base_false_key, static_branch_unlikely)
+test_key_func(base_inv_false_key, static_branch_likely)
+test_key_func(base_inv_false_key, static_branch_unlikely)
+
+static int __init test_static_key_init(void)
+{
+	int ret;
+	int size;
+
+	struct test_key static_key_tests[] = {
+		/* internal keys - old keys */
+		{
+			.init_state	= true,
+			.key		= &old_true_key,
+			.test_key	= &old_true_key_static_key_true,
+		},
+		{
+			.init_state	= false,
+			.key		= &old_false_key,
+			.test_key	= &old_false_key_static_key_false,
+		},
+		/* internal keys - new keys */
+		{
+			.init_state	= true,
+			.key		= &true_key.key,
+			.test_key	= &true_key_static_branch_likely,
+		},
+		{
+			.init_state	= true,
+			.key		= &true_key.key,
+			.test_key	= &true_key_static_branch_unlikely,
+		},
+		{
+			.init_state	= false,
+			.key		= &false_key.key,
+			.test_key	= &false_key_static_branch_likely,
+		},
+		{
+			.init_state	= false,
+			.key		= &false_key.key,
+			.test_key	= &false_key_static_branch_unlikely,
+		},
+		/* external keys - old keys */
+		{
+			.init_state	= true,
+			.key		= &base_old_true_key,
+			.test_key	= &base_old_true_key_static_key_true,
+		},
+		{
+			.init_state	= false,
+			.key		= &base_inv_old_true_key,
+			.test_key	= &base_inv_old_true_key_static_key_true,
+		},
+		{
+			.init_state	= false,
+			.key		= &base_old_false_key,
+			.test_key	= &base_old_false_key_static_key_false,
+		},
+		{
+			.init_state	= true,
+			.key		= &base_inv_old_false_key,
+			.test_key	= &base_inv_old_false_key_static_key_false,
+		},
+		/* external keys - new keys */
+		{
+			.init_state	= true,
+			.key		= &base_true_key.key,
+			.test_key	= &base_true_key_static_branch_likely,
+		},
+		{
+			.init_state	= true,
+			.key		= &base_true_key.key,
+			.test_key	= &base_true_key_static_branch_unlikely,
+		},
+		{
+			.init_state	= false,
+			.key		= &base_inv_true_key.key,
+			.test_key	= &base_inv_true_key_static_branch_likely,
+		},
+		{
+			.init_state	= false,
+			.key		= &base_inv_true_key.key,
+			.test_key	= &base_inv_true_key_static_branch_unlikely,
+		},
+		{
+			.init_state	= false,
+			.key		= &base_false_key.key,
+			.test_key	= &base_false_key_static_branch_likely,
+		},
+		{
+			.init_state	= false,
+			.key		= &base_false_key.key,
+			.test_key	= &base_false_key_static_branch_unlikely,
+		},
+		{
+			.init_state	= true,
+			.key		= &base_inv_false_key.key,
+			.test_key	= &base_inv_false_key_static_branch_likely,
+		},
+		{
+			.init_state	= true,
+			.key		= &base_inv_false_key.key,
+			.test_key	= &base_inv_false_key_static_branch_unlikely,
+		},
+	};
+
+	size = ARRAY_SIZE(static_key_tests);
+
+	ret = verify_keys(static_key_tests, size, false);
+	if (ret)
+		goto out;
+
+	invert_keys(static_key_tests, size);
+	ret = verify_keys(static_key_tests, size, true);
+	if (ret)
+		goto out;
+
+	invert_keys(static_key_tests, size);
+	ret = verify_keys(static_key_tests, size, false);
+	if (ret)
+		goto out;
+	return 0;
+out:
+	return ret;
+}
+
+static void __exit test_static_key_exit(void)
+{
+}
+
+module_init(test_static_key_init);
+module_exit(test_static_key_exit);
+
+MODULE_AUTHOR("Jason Baron <jbaron@akamai.com>");
+MODULE_DESCRIPTION("Kernel module for testing static keys");
+MODULE_LICENSE("GPL");