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, 129 insertions, 0 deletions

diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
new file mode 100644
index 000000000..4a6574b67
--- /dev/null
+++ b/lib/strnlen_user.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <linux/bitops.h>
+
+#include <asm/word-at-a-time.h>
+
+/*
+ * Do a strnlen, return length of string *with* final '\0'.
+ * 'count' is the user-supplied count, while 'max' is the
+ * address space maximum.
+ *
+ * Return 0 for exceptions (which includes hitting the address
+ * space maximum), or 'count+1' if hitting the user-supplied
+ * maximum count.
+ *
+ * NOTE! We can sometimes overshoot the user-supplied maximum
+ * if it fits in a aligned 'long'. The caller needs to check
+ * the return value against "> max".
+ */
+static __always_inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
+{
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+	unsigned long align, res = 0;
+	unsigned long c;
+
+	/*
+	 * Do everything aligned. But that means that we
+	 * need to also expand the maximum..
+	 */
+	align = (sizeof(unsigned long) - 1) & (unsigned long)src;
+	src -= align;
+	max += align;
+
+	unsafe_get_user(c, (unsigned long __user *)src, efault);
+	c |= aligned_byte_mask(align);
+
+	for (;;) {
+		unsigned long data;
+		if (has_zero(c, &data, &constants)) {
+			data = prep_zero_mask(c, data, &constants);
+			data = create_zero_mask(data);
+			return res + find_zero(data) + 1 - align;
+		}
+		res += sizeof(unsigned long);
+		/* We already handled 'unsigned long' bytes. Did we do it all ? */
+		if (unlikely(max <= sizeof(unsigned long)))
+			break;
+		max -= sizeof(unsigned long);
+		unsafe_get_user(c, (unsigned long __user *)(src+res), efault);
+	}
+	res -= align;
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, return the marker for "too long".
+	 */
+	if (res >= count)
+		return count+1;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's 0.
+	 */
+efault:
+	return 0;
+}
+
+/**
+ * strnlen_user: - Get the size of a user string INCLUDING final NUL.
+ * @str: The string to measure.
+ * @count: Maximum count (including NUL character)
+ *
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * If the string is too long, returns a number larger than @count. User
+ * has to check the return value against "> count".
+ * On exception (or invalid count), returns 0.
+ *
+ * NOTE! You should basically never use this function. There is
+ * almost never any valid case for using the length of a user space
+ * string, since the string can be changed at any time by other
+ * threads. Use "strncpy_from_user()" instead to get a stable copy
+ * of the string.
+ */
+long strnlen_user(const char __user *str, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	if (can_do_masked_user_access()) {
+		long retval;
+
+		str = masked_user_read_access_begin(str);
+		retval = do_strnlen_user(str, count, count);
+		user_read_access_end();
+		return retval;
+	}
+
+	max_addr = TASK_SIZE_MAX;
+	src_addr = (unsigned long)untagged_addr(str);
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		long retval;
+
+		/*
+		 * Truncate 'max' to the user-specified limit, so that
+		 * we only have one limit we need to check in the loop
+		 */
+		if (max > count)
+			max = count;
+
+		if (user_read_access_begin(str, max)) {
+			retval = do_strnlen_user(str, count, max);
+			user_read_access_end();
+			return retval;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL(strnlen_user);