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, 81 insertions, 0 deletions

diff --git a/drivers/pci/mmap.c b/drivers/pci/mmap.c
new file mode 100644
index 000000000..8da3347a9
--- /dev/null
+++ b/drivers/pci/mmap.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Generic PCI resource mmap helper
+ *
+ * Copyright © 2017 Amazon.com, Inc. or its affiliates.
+ *
+ * Author: David Woodhouse <dwmw2@infradead.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+
+#include "pci.h"
+
+#ifdef ARCH_GENERIC_PCI_MMAP_RESOURCE
+
+static const struct vm_operations_struct pci_phys_vm_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+	.access = generic_access_phys,
+#endif
+};
+
+int pci_mmap_resource_range(struct pci_dev *pdev, int bar,
+			    struct vm_area_struct *vma,
+			    enum pci_mmap_state mmap_state, int write_combine)
+{
+	unsigned long size;
+	int ret;
+
+	size = ((pci_resource_len(pdev, bar) - 1) >> PAGE_SHIFT) + 1;
+	if (vma->vm_pgoff + vma_pages(vma) > size)
+		return -EINVAL;
+
+	if (write_combine)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_device(vma->vm_page_prot);
+
+	if (mmap_state == pci_mmap_io) {
+		ret = pci_iobar_pfn(pdev, bar, vma);
+		if (ret)
+			return ret;
+	} else
+		vma->vm_pgoff += (pci_resource_start(pdev, bar) >> PAGE_SHIFT);
+
+	vma->vm_ops = &pci_phys_vm_ops;
+
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				  vma->vm_end - vma->vm_start,
+				  vma->vm_page_prot);
+}
+
+#endif
+
+#if (defined(CONFIG_SYSFS) || defined(CONFIG_PROC_FS)) && \
+    (defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE))
+
+int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma,
+		  enum pci_mmap_api mmap_api)
+{
+	resource_size_t pci_start = 0, pci_end;
+	unsigned long nr, start, size;
+
+	if (pci_resource_len(pdev, resno) == 0)
+		return 0;
+	nr = vma_pages(vma);
+	start = vma->vm_pgoff;
+	size = ((pci_resource_len(pdev, resno) - 1) >> PAGE_SHIFT) + 1;
+	if (mmap_api == PCI_MMAP_PROCFS) {
+		pci_resource_to_user(pdev, resno, &pdev->resource[resno],
+				     &pci_start, &pci_end);
+		pci_start >>= PAGE_SHIFT;
+	}
+	if (start >= pci_start && start < pci_start + size &&
+	    start + nr <= pci_start + size)
+		return 1;
+	return 0;
+}
+
+#endif