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, 79 insertions, 0 deletions

diff --git a/drivers/power/reset/axxia-reset.c b/drivers/power/reset/axxia-reset.c
new file mode 100644
index 000000000..797bf6773
--- /dev/null
+++ b/drivers/power/reset/axxia-reset.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Reset driver for Axxia devices
+ *
+ * Copyright (C) 2014 LSI
+ */
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/regmap.h>
+
+#define SC_CRIT_WRITE_KEY	0x1000
+#define SC_LATCH_ON_RESET	0x1004
+#define SC_RESET_CONTROL	0x1008
+#define   RSTCTL_RST_ZERO	(1<<3)
+#define   RSTCTL_RST_FAB	(1<<2)
+#define   RSTCTL_RST_CHIP	(1<<1)
+#define   RSTCTL_RST_SYS	(1<<0)
+#define SC_EFUSE_INT_STATUS	0x180c
+#define   EFUSE_READ_DONE	(1<<31)
+
+static int axxia_restart_handler(struct sys_off_data *data)
+{
+	struct regmap *syscon = data->cb_data;
+
+	/* Access Key (0xab) */
+	regmap_write(syscon, SC_CRIT_WRITE_KEY, 0xab);
+	/* Select internal boot from 0xffff0000 */
+	regmap_write(syscon, SC_LATCH_ON_RESET, 0x00000040);
+	/* Assert ResetReadDone (to avoid hanging in boot ROM) */
+	regmap_write(syscon, SC_EFUSE_INT_STATUS, EFUSE_READ_DONE);
+	/* Assert chip reset */
+	regmap_update_bits(syscon, SC_RESET_CONTROL,
+			   RSTCTL_RST_CHIP, RSTCTL_RST_CHIP);
+
+	return NOTIFY_DONE;
+}
+
+static int axxia_reset_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct regmap *syscon;
+	int err;
+
+	syscon = syscon_regmap_lookup_by_phandle(dev->of_node, "syscon");
+	if (IS_ERR(syscon)) {
+		pr_err("%pOFn: syscon lookup failed\n", dev->of_node);
+		return PTR_ERR(syscon);
+	}
+
+	err = devm_register_sys_off_handler(&pdev->dev, SYS_OFF_MODE_RESTART,
+					    128, axxia_restart_handler, syscon);
+	if (err)
+		dev_err(dev, "cannot register restart handler (err=%d)\n", err);
+
+	return err;
+}
+
+static const struct of_device_id of_axxia_reset_match[] = {
+	{ .compatible = "lsi,axm55xx-reset", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_axxia_reset_match);
+
+static struct platform_driver axxia_reset_driver = {
+	.probe = axxia_reset_probe,
+	.driver = {
+		.name = "axxia-reset",
+		.of_match_table = of_match_ptr(of_axxia_reset_match),
+	},
+};
+builtin_platform_driver(axxia_reset_driver);