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, 160 insertions, 0 deletions

diff --git a/drivers/power/reset/syscon-reboot.c b/drivers/power/reset/syscon-reboot.c
new file mode 100644
index 000000000..60e855cae
--- /dev/null
+++ b/drivers/power/reset/syscon-reboot.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic Syscon Reboot Driver
+ *
+ * Copyright (c) 2013, Applied Micro Circuits Corporation
+ * Author: Feng Kan <fkan@apm.com>
+ */
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/notifier.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/regmap.h>
+
+struct reboot_mode_bits {
+	u32 offset;
+	u32 mask;
+	u32 value;
+	bool valid;
+};
+
+struct reboot_data {
+	struct reboot_mode_bits mode_bits[REBOOT_SOFT + 1];
+	struct reboot_mode_bits catchall;
+};
+
+struct syscon_reboot_context {
+	struct regmap *map;
+
+	const struct reboot_data *rd; /* from of match data, if any */
+	struct reboot_mode_bits catchall; /* from DT */
+
+	struct notifier_block restart_handler;
+};
+
+static int syscon_restart_handle(struct notifier_block *this,
+					unsigned long mode, void *cmd)
+{
+	struct syscon_reboot_context *ctx =
+			container_of(this, struct syscon_reboot_context,
+					restart_handler);
+	const struct reboot_mode_bits *mode_bits;
+
+	if (ctx->rd) {
+		if (mode < ARRAY_SIZE(ctx->rd->mode_bits) &&
+		    ctx->rd->mode_bits[mode].valid)
+			mode_bits = &ctx->rd->mode_bits[mode];
+		else
+			mode_bits = &ctx->rd->catchall;
+	} else {
+		mode_bits = &ctx->catchall;
+	}
+
+	/* Issue the reboot */
+	regmap_update_bits(ctx->map, mode_bits->offset, mode_bits->mask,
+			   mode_bits->value);
+
+	mdelay(1000);
+
+	pr_emerg("Unable to restart system\n");
+	return NOTIFY_DONE;
+}
+
+static int syscon_reboot_probe(struct platform_device *pdev)
+{
+	struct syscon_reboot_context *ctx;
+	struct device *dev = &pdev->dev;
+	u32 priority;
+	int err;
+
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->map = syscon_regmap_lookup_by_phandle(dev->of_node, "regmap");
+	if (IS_ERR(ctx->map)) {
+		ctx->map = syscon_node_to_regmap(dev->parent->of_node);
+		if (IS_ERR(ctx->map))
+			return PTR_ERR(ctx->map);
+	}
+
+	if (of_property_read_u32(pdev->dev.of_node, "priority", &priority))
+		priority = 192;
+
+	ctx->rd = of_device_get_match_data(dev);
+	if (!ctx->rd) {
+		int mask_err, value_err;
+
+		if (of_property_read_u32(pdev->dev.of_node, "offset",
+					 &ctx->catchall.offset) &&
+		    of_property_read_u32(pdev->dev.of_node, "reg",
+					 &ctx->catchall.offset))
+			return -EINVAL;
+
+		value_err = of_property_read_u32(pdev->dev.of_node, "value",
+						 &ctx->catchall.value);
+		mask_err = of_property_read_u32(pdev->dev.of_node, "mask",
+						&ctx->catchall.mask);
+		if (value_err && mask_err) {
+			dev_err(dev, "unable to read 'value' and 'mask'");
+			return -EINVAL;
+		}
+
+		if (value_err) {
+			/* support old binding */
+			ctx->catchall.value = ctx->catchall.mask;
+			ctx->catchall.mask = 0xFFFFFFFF;
+		} else if (mask_err) {
+			/* support value without mask */
+			ctx->catchall.mask = 0xFFFFFFFF;
+		}
+	}
+
+	ctx->restart_handler.notifier_call = syscon_restart_handle;
+	ctx->restart_handler.priority = priority;
+	err = register_restart_handler(&ctx->restart_handler);
+	if (err)
+		dev_err(dev, "can't register restart notifier (err=%d)\n", err);
+
+	return err;
+}
+
+static const struct reboot_data gs101_reboot_data = {
+	.mode_bits = {
+		[REBOOT_WARM] = {
+			.offset = 0x3a00, /* SYSTEM_CONFIGURATION */
+			.mask = 0x00000002, /* SWRESET_SYSTEM */
+			.value = 0x00000002,
+			.valid = true,
+		},
+		[REBOOT_SOFT] = {
+			.offset = 0x3a00, /* SYSTEM_CONFIGURATION */
+			.mask = 0x00000002, /* SWRESET_SYSTEM */
+			.value = 0x00000002,
+			.valid = true,
+		},
+	},
+	.catchall = {
+		.offset = 0x3e9c, /* PAD_CTRL_PWR_HOLD */
+		.mask = 0x00000100,
+		.value = 0x00000000,
+	},
+};
+
+static const struct of_device_id syscon_reboot_of_match[] = {
+	{ .compatible = "google,gs101-reboot", .data = &gs101_reboot_data  },
+	{ .compatible = "syscon-reboot" },
+	{}
+};
+
+static struct platform_driver syscon_reboot_driver = {
+	.probe = syscon_reboot_probe,
+	.driver = {
+		.name = "syscon-reboot",
+		.of_match_table = syscon_reboot_of_match,
+	},
+};
+builtin_platform_driver(syscon_reboot_driver);