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, 113 insertions, 0 deletions

diff --git a/drivers/base/auxiliary_sysfs.c b/drivers/base/auxiliary_sysfs.c
new file mode 100644
index 000000000..dea7f46f7
--- /dev/null
+++ b/drivers/base/auxiliary_sysfs.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES
+ */
+
+#include <linux/auxiliary_bus.h>
+#include <linux/slab.h>
+
+#define AUXILIARY_MAX_IRQ_NAME 11
+
+struct auxiliary_irq_info {
+	struct device_attribute sysfs_attr;
+	char name[AUXILIARY_MAX_IRQ_NAME];
+};
+
+static struct attribute *auxiliary_irq_attrs[] = {
+	NULL
+};
+
+static const struct attribute_group auxiliary_irqs_group = {
+	.name = "irqs",
+	.attrs = auxiliary_irq_attrs,
+};
+
+static int auxiliary_irq_dir_prepare(struct auxiliary_device *auxdev)
+{
+	int ret = 0;
+
+	guard(mutex)(&auxdev->sysfs.lock);
+	if (auxdev->sysfs.irq_dir_exists)
+		return 0;
+
+	ret = devm_device_add_group(&auxdev->dev, &auxiliary_irqs_group);
+	if (ret)
+		return ret;
+
+	auxdev->sysfs.irq_dir_exists = true;
+	xa_init(&auxdev->sysfs.irqs);
+	return 0;
+}
+
+/**
+ * auxiliary_device_sysfs_irq_add - add a sysfs entry for the given IRQ
+ * @auxdev: auxiliary bus device to add the sysfs entry.
+ * @irq: The associated interrupt number.
+ *
+ * This function should be called after auxiliary device have successfully
+ * received the irq.
+ * The driver is responsible to add a unique irq for the auxiliary device. The
+ * driver can invoke this function from multiple thread context safely for
+ * unique irqs of the auxiliary devices. The driver must not invoke this API
+ * multiple times if the irq is already added previously.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq)
+{
+	struct auxiliary_irq_info *info __free(kfree) = NULL;
+	struct device *dev = &auxdev->dev;
+	int ret;
+
+	ret = auxiliary_irq_dir_prepare(auxdev);
+	if (ret)
+		return ret;
+
+	info = kzalloc_obj(*info);
+	if (!info)
+		return -ENOMEM;
+
+	sysfs_attr_init(&info->sysfs_attr.attr);
+	snprintf(info->name, AUXILIARY_MAX_IRQ_NAME, "%d", irq);
+
+	ret = xa_insert(&auxdev->sysfs.irqs, irq, info, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	info->sysfs_attr.attr.name = info->name;
+	ret = sysfs_add_file_to_group(&dev->kobj, &info->sysfs_attr.attr,
+				      auxiliary_irqs_group.name);
+	if (ret)
+		goto sysfs_add_err;
+
+	xa_store(&auxdev->sysfs.irqs, irq, no_free_ptr(info), GFP_KERNEL);
+	return 0;
+
+sysfs_add_err:
+	xa_erase(&auxdev->sysfs.irqs, irq);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(auxiliary_device_sysfs_irq_add);
+
+/**
+ * auxiliary_device_sysfs_irq_remove - remove a sysfs entry for the given IRQ
+ * @auxdev: auxiliary bus device to add the sysfs entry.
+ * @irq: the IRQ to remove.
+ *
+ * This function should be called to remove an IRQ sysfs entry.
+ * The driver must invoke this API when IRQ is released by the device.
+ */
+void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq)
+{
+	struct auxiliary_irq_info *info __free(kfree) = xa_load(&auxdev->sysfs.irqs, irq);
+	struct device *dev = &auxdev->dev;
+
+	if (!info) {
+		dev_err(&auxdev->dev, "IRQ %d doesn't exist\n", irq);
+		return;
+	}
+	sysfs_remove_file_from_group(&dev->kobj, &info->sysfs_attr.attr,
+				     auxiliary_irqs_group.name);
+	xa_erase(&auxdev->sysfs.irqs, irq);
+}
+EXPORT_SYMBOL_GPL(auxiliary_device_sysfs_irq_remove);