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, 77 insertions, 0 deletions

diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
new file mode 100644
index 000000000..706842573
--- /dev/null
+++ b/fs/ntfs/malloc.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * malloc.h - NTFS kernel memory handling. Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2005 Anton Altaparmakov
+ */
+
+#ifndef _LINUX_NTFS_MALLOC_H
+#define _LINUX_NTFS_MALLOC_H
+
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+
+/**
+ * __ntfs_malloc - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ * @gfp_mask:	extra flags for the allocator
+ *
+ * Internal function.  You probably want ntfs_malloc_nofs()...
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ * Depending on @gfp_mask the allocation may be guaranteed to succeed.
+ */
+static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)
+{
+	if (likely(size <= PAGE_SIZE)) {
+		BUG_ON(!size);
+		/* kmalloc() has per-CPU caches so is faster for now. */
+		return kmalloc(PAGE_SIZE, gfp_mask & ~__GFP_HIGHMEM);
+		/* return (void *)__get_free_page(gfp_mask); */
+	}
+	if (likely((size >> PAGE_SHIFT) < totalram_pages()))
+		return __vmalloc(size, gfp_mask);
+	return NULL;
+}
+
+/**
+ * ntfs_malloc_nofs - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ */
+static inline void *ntfs_malloc_nofs(unsigned long size)
+{
+	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM);
+}
+
+/**
+ * ntfs_malloc_nofs_nofail - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * This function guarantees that the allocation will succeed.  It will sleep
+ * for as long as it takes to complete the allocation.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ */
+static inline void *ntfs_malloc_nofs_nofail(unsigned long size)
+{
+	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM | __GFP_NOFAIL);
+}
+
+static inline void ntfs_free(void *addr)
+{
+	kvfree(addr);
+}
+
+#endif /* _LINUX_NTFS_MALLOC_H */