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, 157 insertions, 0 deletions

diff --git a/drivers/nvmem/snvs_lpgpr.c b/drivers/nvmem/snvs_lpgpr.c
new file mode 100644
index 000000000..89c271123
--- /dev/null
+++ b/drivers/nvmem/snvs_lpgpr.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2015 Pengutronix, Steffen Trumtrar <kernel@pengutronix.de>
+ * Copyright (c) 2017 Pengutronix, Oleksij Rempel <kernel@pengutronix.de>
+ */
+
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#define IMX6Q_SNVS_HPLR		0x00
+#define IMX6Q_SNVS_LPLR		0x34
+#define IMX6Q_SNVS_LPGPR	0x68
+
+#define IMX7D_SNVS_HPLR		0x00
+#define IMX7D_SNVS_LPLR		0x34
+#define IMX7D_SNVS_LPGPR	0x90
+
+#define IMX_GPR_SL		BIT(5)
+#define IMX_GPR_HL		BIT(5)
+
+struct snvs_lpgpr_cfg {
+	int offset;
+	int offset_hplr;
+	int offset_lplr;
+	int size;
+};
+
+struct snvs_lpgpr_priv {
+	struct device_d			*dev;
+	struct regmap			*regmap;
+	struct nvmem_config		cfg;
+	const struct snvs_lpgpr_cfg	*dcfg;
+};
+
+static const struct snvs_lpgpr_cfg snvs_lpgpr_cfg_imx6q = {
+	.offset		= IMX6Q_SNVS_LPGPR,
+	.offset_hplr	= IMX6Q_SNVS_HPLR,
+	.offset_lplr	= IMX6Q_SNVS_LPLR,
+	.size		= 4,
+};
+
+static const struct snvs_lpgpr_cfg snvs_lpgpr_cfg_imx7d = {
+	.offset		= IMX7D_SNVS_LPGPR,
+	.offset_hplr	= IMX7D_SNVS_HPLR,
+	.offset_lplr	= IMX7D_SNVS_LPLR,
+	.size		= 16,
+};
+
+static int snvs_lpgpr_write(void *context, unsigned int offset, void *val,
+			    size_t bytes)
+{
+	struct snvs_lpgpr_priv *priv = context;
+	const struct snvs_lpgpr_cfg *dcfg = priv->dcfg;
+	unsigned int lock_reg;
+	int ret;
+
+	ret = regmap_read(priv->regmap, dcfg->offset_hplr, &lock_reg);
+	if (ret < 0)
+		return ret;
+
+	if (lock_reg & IMX_GPR_SL)
+		return -EPERM;
+
+	ret = regmap_read(priv->regmap, dcfg->offset_lplr, &lock_reg);
+	if (ret < 0)
+		return ret;
+
+	if (lock_reg & IMX_GPR_HL)
+		return -EPERM;
+
+	return regmap_bulk_write(priv->regmap, dcfg->offset + offset, val,
+				bytes / 4);
+}
+
+static int snvs_lpgpr_read(void *context, unsigned int offset, void *val,
+			   size_t bytes)
+{
+	struct snvs_lpgpr_priv *priv = context;
+	const struct snvs_lpgpr_cfg *dcfg = priv->dcfg;
+
+	return regmap_bulk_read(priv->regmap, dcfg->offset + offset,
+			       val, bytes / 4);
+}
+
+static int snvs_lpgpr_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *node = dev->of_node;
+	struct device_node *syscon_node;
+	struct snvs_lpgpr_priv *priv;
+	struct nvmem_config *cfg;
+	struct nvmem_device *nvmem;
+	const struct snvs_lpgpr_cfg *dcfg;
+
+	if (!node)
+		return -ENOENT;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dcfg = of_device_get_match_data(dev);
+	if (!dcfg)
+		return -EINVAL;
+
+	syscon_node = of_get_parent(node);
+	if (!syscon_node)
+		return -ENODEV;
+
+	priv->regmap = syscon_node_to_regmap(syscon_node);
+	of_node_put(syscon_node);
+	if (IS_ERR(priv->regmap))
+		return PTR_ERR(priv->regmap);
+
+	priv->dcfg = dcfg;
+
+	cfg = &priv->cfg;
+	cfg->priv = priv;
+	cfg->name = dev_name(dev);
+	cfg->dev = dev;
+	cfg->stride = 4;
+	cfg->word_size = 4;
+	cfg->size = dcfg->size;
+	cfg->owner = THIS_MODULE;
+	cfg->reg_read  = snvs_lpgpr_read;
+	cfg->reg_write = snvs_lpgpr_write;
+
+	nvmem = devm_nvmem_register(dev, cfg);
+
+	return PTR_ERR_OR_ZERO(nvmem);
+}
+
+static const struct of_device_id snvs_lpgpr_dt_ids[] = {
+	{ .compatible = "fsl,imx6q-snvs-lpgpr", .data = &snvs_lpgpr_cfg_imx6q },
+	{ .compatible = "fsl,imx6ul-snvs-lpgpr",
+	  .data = &snvs_lpgpr_cfg_imx6q },
+	{ .compatible = "fsl,imx7d-snvs-lpgpr",	.data = &snvs_lpgpr_cfg_imx7d },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, snvs_lpgpr_dt_ids);
+
+static struct platform_driver snvs_lpgpr_driver = {
+	.probe	= snvs_lpgpr_probe,
+	.driver = {
+		.name	= "snvs_lpgpr",
+		.of_match_table = snvs_lpgpr_dt_ids,
+	},
+};
+module_platform_driver(snvs_lpgpr_driver);
+
+MODULE_AUTHOR("Oleksij Rempel <o.rempel@pengutronix.de>");
+MODULE_DESCRIPTION("Low Power General Purpose Register in i.MX6 and i.MX7 Secure Non-Volatile Storage");
+MODULE_LICENSE("GPL v2");