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, 117 insertions, 0 deletions

diff --git a/drivers/acpi/arm64/amba.c b/drivers/acpi/arm64/amba.c
new file mode 100644
index 000000000..1350083bc
--- /dev/null
+++ b/drivers/acpi/arm64/amba.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * ACPI support for platform bus type.
+ *
+ * Copyright (C) 2015, Linaro Ltd
+ * Author: Graeme Gregory <graeme.gregory@linaro.org>
+ */
+
+#include <linux/acpi.h>
+#include <linux/amba/bus.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "init.h"
+
+static const struct acpi_device_id amba_id_list[] = {
+	{"ARMH0061", 0}, /* PL061 GPIO Device */
+	{"ARMH0330", 0}, /* ARM DMA Controller DMA-330 */
+	{"", 0},
+};
+
+static void amba_register_dummy_clk(void)
+{
+	struct clk *amba_dummy_clk;
+
+	amba_dummy_clk = clk_register_fixed_rate(NULL, "apb_pclk", NULL, 0, 0);
+	clk_register_clkdev(amba_dummy_clk, "apb_pclk", NULL);
+}
+
+static int amba_handler_attach(struct acpi_device *adev,
+				const struct acpi_device_id *id)
+{
+	struct acpi_device *parent = acpi_dev_parent(adev);
+	struct amba_device *dev;
+	struct resource_entry *rentry;
+	struct list_head resource_list;
+	bool address_found = false;
+	int irq_no = 0;
+	int ret;
+
+	/* If the ACPI node already has a physical device attached, skip it. */
+	if (adev->physical_node_count)
+		return 0;
+
+	dev = amba_device_alloc(dev_name(&adev->dev), 0, 0);
+	if (!dev) {
+		dev_err(&adev->dev, "%s(): amba_device_alloc() failed\n",
+			__func__);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
+	if (ret < 0)
+		goto err_free;
+
+	list_for_each_entry(rentry, &resource_list, node) {
+		switch (resource_type(rentry->res)) {
+		case IORESOURCE_MEM:
+			if (!address_found) {
+				dev->res = *rentry->res;
+				dev->res.name = dev_name(&dev->dev);
+				address_found = true;
+			}
+			break;
+		case IORESOURCE_IRQ:
+			if (irq_no < AMBA_NR_IRQS)
+				dev->irq[irq_no++] = rentry->res->start;
+			break;
+		default:
+			dev_warn(&adev->dev, "Invalid resource\n");
+			break;
+		}
+	}
+
+	acpi_dev_free_resource_list(&resource_list);
+
+	/*
+	 * If the ACPI node has a parent and that parent has a physical device
+	 * attached to it, that physical device should be the parent of
+	 * the amba device we are about to create.
+	 */
+	if (parent)
+		dev->dev.parent = acpi_get_first_physical_node(parent);
+
+	device_set_node(&dev->dev, acpi_fwnode_handle(adev));
+
+	ret = amba_device_add(dev, &iomem_resource);
+	if (ret) {
+		dev_err(&adev->dev, "%s(): amba_device_add() failed (%d)\n",
+		       __func__, ret);
+		goto err_free;
+	}
+
+	return 1;
+
+err_free:
+	amba_device_put(dev);
+	return ret;
+}
+
+static struct acpi_scan_handler amba_handler = {
+	.ids = amba_id_list,
+	.attach = amba_handler_attach,
+};
+
+void __init acpi_amba_init(void)
+{
+	amba_register_dummy_clk();
+	acpi_scan_add_handler(&amba_handler);
+}