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, 170 insertions, 0 deletions

diff --git a/drivers/mfd/altera-a10sr.c b/drivers/mfd/altera-a10sr.c
new file mode 100644
index 000000000..9c0262228
--- /dev/null
+++ b/drivers/mfd/altera-a10sr.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Altera Arria10 DevKit System Resource MFD Driver
+ *
+ * Author: Thor Thayer <tthayer@opensource.altera.com>
+ *
+ * Copyright Intel Corporation (C) 2014-2016. All Rights Reserved
+ *
+ * SPI access for Altera Arria10 MAX5 System Resource Chip
+ *
+ * Adapted from DA9052
+ */
+
+#include <linux/mfd/altera-a10sr.h>
+#include <linux/mfd/core.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+static const struct mfd_cell altr_a10sr_subdev_info[] = {
+	{
+		.name = "altr_a10sr_gpio",
+		.of_compatible = "altr,a10sr-gpio",
+	},
+	{
+		.name = "altr_a10sr_reset",
+		.of_compatible = "altr,a10sr-reset",
+	},
+};
+
+static bool altr_a10sr_reg_readable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_VERSION_READ:
+	case ALTR_A10SR_LED_REG:
+	case ALTR_A10SR_PBDSW_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_PWR_GOOD1_REG:
+	case ALTR_A10SR_PWR_GOOD2_REG:
+	case ALTR_A10SR_PWR_GOOD3_REG:
+	case ALTR_A10SR_FMCAB_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_USB_QSPI_REG:
+	case ALTR_A10SR_SFPA_REG:
+	case ALTR_A10SR_SFPB_REG:
+	case ALTR_A10SR_I2C_M_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool altr_a10sr_reg_writeable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_LED_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_FMCAB_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_USB_QSPI_REG:
+	case ALTR_A10SR_SFPA_REG:
+	case ALTR_A10SR_SFPB_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool altr_a10sr_reg_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_PBDSW_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_PWR_GOOD1_REG:
+	case ALTR_A10SR_PWR_GOOD2_REG:
+	case ALTR_A10SR_PWR_GOOD3_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_I2C_M_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config altr_a10sr_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.cache_type = REGCACHE_NONE,
+
+	.use_single_read = true,
+	.use_single_write = true,
+	.read_flag_mask = 1,
+	.write_flag_mask = 0,
+
+	.max_register = ALTR_A10SR_WR_KEY_REG,
+	.readable_reg = altr_a10sr_reg_readable,
+	.writeable_reg = altr_a10sr_reg_writeable,
+	.volatile_reg = altr_a10sr_reg_volatile,
+
+};
+
+static int altr_a10sr_spi_probe(struct spi_device *spi)
+{
+	int ret;
+	struct altr_a10sr *a10sr;
+
+	a10sr = devm_kzalloc(&spi->dev, sizeof(*a10sr),
+			     GFP_KERNEL);
+	if (!a10sr)
+		return -ENOMEM;
+
+	spi->mode = SPI_MODE_3;
+	spi->bits_per_word = 8;
+	spi_setup(spi);
+
+	a10sr->dev = &spi->dev;
+
+	spi_set_drvdata(spi, a10sr);
+
+	a10sr->regmap = devm_regmap_init_spi(spi, &altr_a10sr_regmap_config);
+	if (IS_ERR(a10sr->regmap)) {
+		ret = PTR_ERR(a10sr->regmap);
+		dev_err(&spi->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = devm_mfd_add_devices(a10sr->dev, PLATFORM_DEVID_AUTO,
+				   altr_a10sr_subdev_info,
+				   ARRAY_SIZE(altr_a10sr_subdev_info),
+				   NULL, 0, NULL);
+	if (ret)
+		dev_err(a10sr->dev, "Failed to register sub-devices: %d\n",
+			ret);
+
+	return ret;
+}
+
+static const struct of_device_id altr_a10sr_spi_of_match[] = {
+	{ .compatible = "altr,a10sr" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, altr_a10sr_spi_of_match);
+
+static const struct spi_device_id altr_a10sr_spi_ids[] = {
+	{ .name = "a10sr" },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, altr_a10sr_spi_ids);
+
+static struct spi_driver altr_a10sr_spi_driver = {
+	.probe = altr_a10sr_spi_probe,
+	.driver = {
+		.name = "altr_a10sr",
+		.of_match_table = altr_a10sr_spi_of_match,
+	},
+	.id_table = altr_a10sr_spi_ids,
+};
+builtin_driver(altr_a10sr_spi_driver, spi_register_driver)