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, 126 insertions, 0 deletions

diff --git a/drivers/reset/reset-brcmstb.c b/drivers/reset/reset-brcmstb.c
new file mode 100644
index 000000000..810fe7645
--- /dev/null
+++ b/drivers/reset/reset-brcmstb.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Broadcom STB generic reset controller for SW_INIT style reset controller
+ *
+ * Author: Florian Fainelli <f.fainelli@gmail.com>
+ * Copyright (C) 2018 Broadcom
+ */
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset-controller.h>
+#include <linux/types.h>
+
+struct brcmstb_reset {
+	void __iomem *base;
+	struct reset_controller_dev rcdev;
+};
+
+#define SW_INIT_SET		0x00
+#define SW_INIT_CLEAR		0x04
+#define SW_INIT_STATUS		0x08
+
+#define SW_INIT_BIT(id)		BIT((id) & 0x1f)
+#define SW_INIT_BANK(id)	((id) >> 5)
+
+/* A full bank contains extra registers that we are not utilizing but still
+ * qualify as a single bank.
+ */
+#define SW_INIT_BANK_SIZE	0x18
+
+static inline
+struct brcmstb_reset *to_brcmstb(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct brcmstb_reset, rcdev);
+}
+
+static int brcmstb_reset_assert(struct reset_controller_dev *rcdev,
+				unsigned long id)
+{
+	unsigned int off = SW_INIT_BANK(id) * SW_INIT_BANK_SIZE;
+	struct brcmstb_reset *priv = to_brcmstb(rcdev);
+
+	writel_relaxed(SW_INIT_BIT(id), priv->base + off + SW_INIT_SET);
+
+	return 0;
+}
+
+static int brcmstb_reset_deassert(struct reset_controller_dev *rcdev,
+				  unsigned long id)
+{
+	unsigned int off = SW_INIT_BANK(id) * SW_INIT_BANK_SIZE;
+	struct brcmstb_reset *priv = to_brcmstb(rcdev);
+
+	writel_relaxed(SW_INIT_BIT(id), priv->base + off + SW_INIT_CLEAR);
+	/* Maximum reset delay after de-asserting a line and seeing block
+	 * operation is typically 14us for the worst case, build some slack
+	 * here.
+	 */
+	usleep_range(100, 200);
+
+	return 0;
+}
+
+static int brcmstb_reset_status(struct reset_controller_dev *rcdev,
+				unsigned long id)
+{
+	unsigned int off = SW_INIT_BANK(id) * SW_INIT_BANK_SIZE;
+	struct brcmstb_reset *priv = to_brcmstb(rcdev);
+
+	return readl_relaxed(priv->base + off + SW_INIT_STATUS) &
+			     SW_INIT_BIT(id);
+}
+
+static const struct reset_control_ops brcmstb_reset_ops = {
+	.assert	= brcmstb_reset_assert,
+	.deassert = brcmstb_reset_deassert,
+	.status = brcmstb_reset_status,
+};
+
+static int brcmstb_reset_probe(struct platform_device *pdev)
+{
+	struct device *kdev = &pdev->dev;
+	struct brcmstb_reset *priv;
+	struct resource *res;
+
+	priv = devm_kzalloc(kdev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	dev_set_drvdata(kdev, priv);
+
+	priv->rcdev.owner = THIS_MODULE;
+	priv->rcdev.nr_resets = DIV_ROUND_DOWN_ULL(resource_size(res),
+						   SW_INIT_BANK_SIZE) * 32;
+	priv->rcdev.ops = &brcmstb_reset_ops;
+	priv->rcdev.of_node = kdev->of_node;
+	/* Use defaults: 1 cell and simple xlate function */
+
+	return devm_reset_controller_register(kdev, &priv->rcdev);
+}
+
+static const struct of_device_id brcmstb_reset_of_match[] = {
+	{ .compatible = "brcm,brcmstb-reset" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, brcmstb_reset_of_match);
+
+static struct platform_driver brcmstb_reset_driver = {
+	.probe	= brcmstb_reset_probe,
+	.driver	= {
+		.name = "brcmstb-reset",
+		.of_match_table = brcmstb_reset_of_match,
+	},
+};
+module_platform_driver(brcmstb_reset_driver);
+
+MODULE_AUTHOR("Broadcom");
+MODULE_DESCRIPTION("Broadcom STB reset controller");
+MODULE_LICENSE("GPL");