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, 127 insertions, 0 deletions

diff --git a/drivers/reset/reset-ath79.c b/drivers/reset/reset-ath79.c
new file mode 100644
index 000000000..1a2c0f8a5
--- /dev/null
+++ b/drivers/reset/reset-ath79.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AR71xx Reset Controller Driver
+ * Author: Alban Bedel
+ *
+ * Copyright (C) 2015 Alban Bedel <albeu@free.fr>
+ */
+
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/reset-controller.h>
+#include <linux/reboot.h>
+
+struct ath79_reset {
+	struct reset_controller_dev rcdev;
+	void __iomem *base;
+	spinlock_t lock;
+};
+
+#define FULL_CHIP_RESET 24
+
+static int ath79_reset_update(struct reset_controller_dev *rcdev,
+			unsigned long id, bool assert)
+{
+	struct ath79_reset *ath79_reset =
+		container_of(rcdev, struct ath79_reset, rcdev);
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&ath79_reset->lock, flags);
+	val = readl(ath79_reset->base);
+	if (assert)
+		val |= BIT(id);
+	else
+		val &= ~BIT(id);
+	writel(val, ath79_reset->base);
+	spin_unlock_irqrestore(&ath79_reset->lock, flags);
+
+	return 0;
+}
+
+static int ath79_reset_assert(struct reset_controller_dev *rcdev,
+			unsigned long id)
+{
+	return ath79_reset_update(rcdev, id, true);
+}
+
+static int ath79_reset_deassert(struct reset_controller_dev *rcdev,
+				unsigned long id)
+{
+	return ath79_reset_update(rcdev, id, false);
+}
+
+static int ath79_reset_status(struct reset_controller_dev *rcdev,
+			unsigned long id)
+{
+	struct ath79_reset *ath79_reset =
+		container_of(rcdev, struct ath79_reset, rcdev);
+	u32 val;
+
+	val = readl(ath79_reset->base);
+
+	return !!(val & BIT(id));
+}
+
+static const struct reset_control_ops ath79_reset_ops = {
+	.assert = ath79_reset_assert,
+	.deassert = ath79_reset_deassert,
+	.status = ath79_reset_status,
+};
+
+static int ath79_reset_restart_handler(struct sys_off_data *data)
+{
+	struct ath79_reset *ath79_reset = data->cb_data;
+
+	ath79_reset_assert(&ath79_reset->rcdev, FULL_CHIP_RESET);
+
+	return NOTIFY_DONE;
+}
+
+static int ath79_reset_probe(struct platform_device *pdev)
+{
+	struct ath79_reset *ath79_reset;
+	int err;
+
+	ath79_reset = devm_kzalloc(&pdev->dev,
+				sizeof(*ath79_reset), GFP_KERNEL);
+	if (!ath79_reset)
+		return -ENOMEM;
+
+	ath79_reset->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ath79_reset->base))
+		return PTR_ERR(ath79_reset->base);
+
+	spin_lock_init(&ath79_reset->lock);
+	ath79_reset->rcdev.ops = &ath79_reset_ops;
+	ath79_reset->rcdev.owner = THIS_MODULE;
+	ath79_reset->rcdev.of_node = pdev->dev.of_node;
+	ath79_reset->rcdev.of_reset_n_cells = 1;
+	ath79_reset->rcdev.nr_resets = 32;
+
+	err = devm_reset_controller_register(&pdev->dev, &ath79_reset->rcdev);
+	if (err)
+		return err;
+
+	err = devm_register_restart_handler(&pdev->dev, ath79_reset_restart_handler, ath79_reset);
+	if (err)
+		dev_warn(&pdev->dev, "Failed to register restart handler\n");
+
+	return 0;
+}
+
+static const struct of_device_id ath79_reset_dt_ids[] = {
+	{ .compatible = "qca,ar7100-reset", },
+	{ },
+};
+
+static struct platform_driver ath79_reset_driver = {
+	.probe	= ath79_reset_probe,
+	.driver = {
+		.name			= "ath79-reset",
+		.of_match_table		= ath79_reset_dt_ids,
+		.suppress_bind_attrs	= true,
+	},
+};
+builtin_platform_driver(ath79_reset_driver);