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, 117 insertions, 0 deletions

diff --git a/drivers/base/power/qos-test.c b/drivers/base/power/qos-test.c
new file mode 100644
index 000000000..79fc6c441
--- /dev/null
+++ b/drivers/base/power/qos-test.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 NXP
+ */
+#include <kunit/test.h>
+#include <linux/pm_qos.h>
+
+/* Basic test for aggregating two "min" requests */
+static void freq_qos_test_min(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req1, req2;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req1, 0, sizeof(req1));
+	memset(&req2, 0, sizeof(req2));
+
+	ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MIN, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MIN, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000);
+
+	ret = freq_qos_remove_request(&req2);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000);
+
+	ret = freq_qos_remove_request(&req1);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+}
+
+/* Test that requests for MAX_DEFAULT_VALUE have no effect */
+static void freq_qos_test_maxdef(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req1, req2;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req1, 0, sizeof(req1));
+	memset(&req2, 0, sizeof(req2));
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX),
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+
+	ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MAX,
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+	ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MAX,
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+
+	/* Add max 1000 */
+	ret = freq_qos_update_request(&req1, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000);
+
+	/* Add max 2000, no impact */
+	ret = freq_qos_update_request(&req2, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000);
+
+	/* Remove max 1000, new max 2000 */
+	ret = freq_qos_remove_request(&req1);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 2000);
+}
+
+/*
+ * Test that a freq_qos_request can be added again after removal
+ *
+ * This issue was solved by commit 05ff1ba412fd ("PM: QoS: Invalidate frequency
+ * QoS requests after removal")
+ */
+static void freq_qos_test_readd(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req, 0, sizeof(req));
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+
+	/* Add */
+	ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000);
+
+	/* Remove */
+	ret = freq_qos_remove_request(&req);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+
+	/* Add again */
+	ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000);
+}
+
+static struct kunit_case pm_qos_test_cases[] = {
+	KUNIT_CASE(freq_qos_test_min),
+	KUNIT_CASE(freq_qos_test_maxdef),
+	KUNIT_CASE(freq_qos_test_readd),
+	{},
+};
+
+static struct kunit_suite pm_qos_test_module = {
+	.name = "qos-kunit-test",
+	.test_cases = pm_qos_test_cases,
+};
+kunit_test_suites(&pm_qos_test_module);