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, 119 insertions, 0 deletions

diff --git a/drivers/mfd/menf21bmc.c b/drivers/mfd/menf21bmc.c
new file mode 100644
index 000000000..0f24de516
--- /dev/null
+++ b/drivers/mfd/menf21bmc.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  MEN 14F021P00 Board Management Controller (BMC) MFD Core Driver.
+ *
+ *  Copyright (C) 2014 MEN Mikro Elektronik Nuernberg GmbH
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+
+#define BMC_CMD_WDT_EXIT_PROD	0x18
+#define BMC_CMD_WDT_PROD_STAT	0x19
+#define BMC_CMD_REV_MAJOR	0x80
+#define BMC_CMD_REV_MINOR	0x81
+#define BMC_CMD_REV_MAIN	0x82
+
+static struct mfd_cell menf21bmc_cell[] = {
+	{ .name = "menf21bmc_wdt", },
+	{ .name = "menf21bmc_led", },
+	{ .name = "menf21bmc_hwmon", }
+};
+
+static int menf21bmc_wdt_exit_prod_mode(struct i2c_client *client)
+{
+	int val, ret;
+
+	val = i2c_smbus_read_byte_data(client, BMC_CMD_WDT_PROD_STAT);
+	if (val < 0)
+		return val;
+
+	/*
+	 * Production mode should be not active after delivery of the Board.
+	 * To be sure we check it, inform the user and exit the mode
+	 * if active.
+	 */
+	if (val == 0x00) {
+		dev_info(&client->dev,
+			"BMC in production mode. Exit production mode\n");
+
+		ret = i2c_smbus_write_byte(client, BMC_CMD_WDT_EXIT_PROD);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+menf21bmc_probe(struct i2c_client *client)
+{
+	int rev_major, rev_minor, rev_main;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA |
+						      I2C_FUNC_SMBUS_WORD_DATA |
+						      I2C_FUNC_SMBUS_BYTE))
+		return -ENODEV;
+
+	rev_major = i2c_smbus_read_word_data(client, BMC_CMD_REV_MAJOR);
+	if (rev_major < 0) {
+		dev_err(&client->dev, "failed to get BMC major revision\n");
+		return rev_major;
+	}
+
+	rev_minor = i2c_smbus_read_word_data(client, BMC_CMD_REV_MINOR);
+	if (rev_minor < 0) {
+		dev_err(&client->dev, "failed to get BMC minor revision\n");
+		return rev_minor;
+	}
+
+	rev_main = i2c_smbus_read_word_data(client, BMC_CMD_REV_MAIN);
+	if (rev_main < 0) {
+		dev_err(&client->dev, "failed to get BMC main revision\n");
+		return rev_main;
+	}
+
+	dev_info(&client->dev, "FW Revision: %02d.%02d.%02d\n",
+		 rev_major, rev_minor, rev_main);
+
+	/*
+	 * We have to exit the Production Mode of the BMC to activate the
+	 * Watchdog functionality and the BIOS life sign monitoring.
+	 */
+	ret = menf21bmc_wdt_exit_prod_mode(client);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed to leave production mode\n");
+		return ret;
+	}
+
+	ret = devm_mfd_add_devices(&client->dev, 0, menf21bmc_cell,
+				   ARRAY_SIZE(menf21bmc_cell), NULL, 0, NULL);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed to add BMC sub-devices\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct i2c_device_id menf21bmc_id_table[] = {
+	{ "menf21bmc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, menf21bmc_id_table);
+
+static struct i2c_driver menf21bmc_driver = {
+	.driver.name	= "menf21bmc",
+	.id_table	= menf21bmc_id_table,
+	.probe		= menf21bmc_probe,
+};
+
+module_i2c_driver(menf21bmc_driver);
+
+MODULE_DESCRIPTION("MEN 14F021P00 BMC mfd core driver");
+MODULE_AUTHOR("Andreas Werner <andreas.werner@men.de>");
+MODULE_LICENSE("GPL v2");