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, 136 insertions, 0 deletions

diff --git a/fs/jfs/jfs_unicode.h b/fs/jfs/jfs_unicode.h
new file mode 100644
index 000000000..b6a78d4ae
--- /dev/null
+++ b/fs/jfs/jfs_unicode.h
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *   Copyright (C) International Business Machines Corp., 2000-2002
+ *   Portions Copyright (C) Christoph Hellwig, 2001-2002
+ */
+#ifndef _H_JFS_UNICODE
+#define _H_JFS_UNICODE
+
+#include <linux/slab.h>
+#include <asm/byteorder.h>
+#include "../nls/nls_ucs2_data.h"
+#include "jfs_types.h"
+
+extern int get_UCSname(struct component_name *, struct dentry *);
+extern int jfs_strfromUCS_le(char *, const __le16 *, int, struct nls_table *);
+
+#define free_UCSname(COMP) kfree((COMP)->name)
+
+/*
+ * UniStrcpy:  Copy a string
+ */
+static inline wchar_t *UniStrcpy(wchar_t * ucs1, const wchar_t * ucs2)
+{
+	wchar_t *anchor = ucs1;	/* save the start of result string */
+
+	while ((*ucs1++ = *ucs2++));
+	return anchor;
+}
+
+
+
+/*
+ * UniStrncpy:  Copy length limited string with pad
+ */
+static inline __le16 *UniStrncpy_le(__le16 * ucs1, const __le16 * ucs2,
+				  size_t n)
+{
+	__le16 *anchor = ucs1;
+
+	while (n-- && *ucs2)	/* Copy the strings */
+		*ucs1++ = *ucs2++;
+
+	n++;
+	while (n--)		/* Pad with nulls */
+		*ucs1++ = 0;
+	return anchor;
+}
+
+/*
+ * UniStrncmp_le:  Compare length limited string - native to little-endian
+ */
+static inline int UniStrncmp_le(const wchar_t * ucs1, const __le16 * ucs2,
+				size_t n)
+{
+	if (!n)
+		return 0;	/* Null strings are equal */
+	while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) {
+		ucs1++;
+		ucs2++;
+	}
+	return (int) *ucs1 - (int) __le16_to_cpu(*ucs2);
+}
+
+/*
+ * UniStrncpy_to_le:  Copy length limited string with pad to little-endian
+ */
+static inline __le16 *UniStrncpy_to_le(__le16 * ucs1, const wchar_t * ucs2,
+				       size_t n)
+{
+	__le16 *anchor = ucs1;
+
+	while (n-- && *ucs2)	/* Copy the strings */
+		*ucs1++ = cpu_to_le16(*ucs2++);
+
+	n++;
+	while (n--)		/* Pad with nulls */
+		*ucs1++ = 0;
+	return anchor;
+}
+
+/*
+ * UniStrncpy_from_le:  Copy length limited string with pad from little-endian
+ */
+static inline wchar_t *UniStrncpy_from_le(wchar_t * ucs1, const __le16 * ucs2,
+					  size_t n)
+{
+	wchar_t *anchor = ucs1;
+
+	while (n-- && *ucs2)	/* Copy the strings */
+		*ucs1++ = __le16_to_cpu(*ucs2++);
+
+	n++;
+	while (n--)		/* Pad with nulls */
+		*ucs1++ = 0;
+	return anchor;
+}
+
+/*
+ * UniToupper:  Convert a unicode character to upper case
+ */
+static inline wchar_t UniToupper(wchar_t uc)
+{
+	const struct UniCaseRange *rp;
+
+	if (uc < sizeof(NlsUniUpperTable)) {	/* Latin characters */
+		return uc + NlsUniUpperTable[uc];	/* Use base tables */
+	} else {
+		rp = NlsUniUpperRange;	/* Use range tables */
+		while (rp->start) {
+			if (uc < rp->start)	/* Before start of range */
+				return uc;	/* Uppercase = input */
+			if (uc <= rp->end)	/* In range */
+				return uc + rp->table[uc - rp->start];
+			rp++;	/* Try next range */
+		}
+	}
+	return uc;		/* Past last range */
+}
+
+
+/*
+ * UniStrupr:  Upper case a unicode string
+ */
+static inline wchar_t *UniStrupr(wchar_t * upin)
+{
+	wchar_t *up;
+
+	up = upin;
+	while (*up) {		/* For all characters */
+		*up = UniToupper(*up);
+		up++;
+	}
+	return upin;		/* Return input pointer */
+}
+
+#endif				/* !_H_JFS_UNICODE */