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, 310 insertions, 0 deletions

diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
new file mode 100644
index 000000000..51dc14b71
--- /dev/null
+++ b/arch/x86/boot/printf.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Oh, it's a waste of space, but oh-so-yummy for debugging.  This
+ * version of printf() does not include 64-bit support.  "Live with
+ * it."
+ *
+ */
+
+#include "boot.h"
+
+static int skip_atoi(const char **s)
+{
+	int i = 0;
+
+	while (isdigit(**s))
+		i = i * 10 + *((*s)++) - '0';
+	return i;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SMALL	32		/* Must be 32 == 0x20 */
+#define SPECIAL	64		/* 0x */
+
+#define __do_div(n, base) ({ \
+int __res; \
+__res = ((unsigned long) n) % (unsigned) base; \
+n = ((unsigned long) n) / (unsigned) base; \
+__res; })
+
+static char *number(char *str, long num, int base, int size, int precision,
+		    int type)
+{
+	/* we are called with base 8, 10 or 16, only, thus don't need "G..."  */
+	static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */
+
+	char tmp[66];
+	char c, sign, locase;
+	int i;
+
+	/* locase = 0 or 0x20. ORing digits or letters with 'locase'
+	 * produces same digits or (maybe lowercased) letters */
+	locase = (type & SMALL);
+	if (type & LEFT)
+		type &= ~ZEROPAD;
+	if (base < 2 || base > 16)
+		return NULL;
+	c = (type & ZEROPAD) ? '0' : ' ';
+	sign = 0;
+	if (type & SIGN) {
+		if (num < 0) {
+			sign = '-';
+			num = -num;
+			size--;
+		} else if (type & PLUS) {
+			sign = '+';
+			size--;
+		} else if (type & SPACE) {
+			sign = ' ';
+			size--;
+		}
+	}
+	if (type & SPECIAL) {
+		if (base == 16)
+			size -= 2;
+		else if (base == 8)
+			size--;
+	}
+	i = 0;
+	if (num == 0)
+		tmp[i++] = '0';
+	else
+		while (num != 0)
+			tmp[i++] = (digits[__do_div(num, base)] | locase);
+	if (i > precision)
+		precision = i;
+	size -= precision;
+	if (!(type & (ZEROPAD + LEFT)))
+		while (size-- > 0)
+			*str++ = ' ';
+	if (sign)
+		*str++ = sign;
+	if (type & SPECIAL) {
+		if (base == 8)
+			*str++ = '0';
+		else if (base == 16) {
+			*str++ = '0';
+			*str++ = ('X' | locase);
+		}
+	}
+	if (!(type & LEFT))
+		while (size-- > 0)
+			*str++ = c;
+	while (i < precision--)
+		*str++ = '0';
+	while (i-- > 0)
+		*str++ = tmp[i];
+	while (size-- > 0)
+		*str++ = ' ';
+	return str;
+}
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+	int len;
+	unsigned long num;
+	int i, base;
+	char *str;
+	const char *s;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/* min. # of digits for integers; max
+				   number of chars for from string */
+	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
+
+	for (str = buf; *fmt; ++fmt) {
+		if (*fmt != '%') {
+			*str++ = *fmt;
+			continue;
+		}
+
+		/* process flags */
+		flags = 0;
+	      repeat:
+		++fmt;		/* this also skips first '%' */
+		switch (*fmt) {
+		case '-':
+			flags |= LEFT;
+			goto repeat;
+		case '+':
+			flags |= PLUS;
+			goto repeat;
+		case ' ':
+			flags |= SPACE;
+			goto repeat;
+		case '#':
+			flags |= SPECIAL;
+			goto repeat;
+		case '0':
+			flags |= ZEROPAD;
+			goto repeat;
+		}
+
+		/* get field width */
+		field_width = -1;
+		if (isdigit(*fmt))
+			field_width = skip_atoi(&fmt);
+		else if (*fmt == '*') {
+			++fmt;
+			/* it's the next argument */
+			field_width = va_arg(args, int);
+			if (field_width < 0) {
+				field_width = -field_width;
+				flags |= LEFT;
+			}
+		}
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;
+			if (isdigit(*fmt))
+				precision = skip_atoi(&fmt);
+			else if (*fmt == '*') {
+				++fmt;
+				/* it's the next argument */
+				precision = va_arg(args, int);
+			}
+			if (precision < 0)
+				precision = 0;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L') {
+			qualifier = *fmt;
+			++fmt;
+		}
+
+		/* default base */
+		base = 10;
+
+		switch (*fmt) {
+		case 'c':
+			if (!(flags & LEFT))
+				while (--field_width > 0)
+					*str++ = ' ';
+			*str++ = (unsigned char)va_arg(args, int);
+			while (--field_width > 0)
+				*str++ = ' ';
+			continue;
+
+		case 's':
+			s = va_arg(args, char *);
+			len = strnlen(s, precision);
+
+			if (!(flags & LEFT))
+				while (len < field_width--)
+					*str++ = ' ';
+			for (i = 0; i < len; ++i)
+				*str++ = *s++;
+			while (len < field_width--)
+				*str++ = ' ';
+			continue;
+
+		case 'p':
+			if (field_width == -1) {
+				field_width = 2 * sizeof(void *);
+				flags |= ZEROPAD;
+			}
+			str = number(str,
+				     (unsigned long)va_arg(args, void *), 16,
+				     field_width, precision, flags);
+			continue;
+
+		case 'n':
+			if (qualifier == 'l') {
+				long *ip = va_arg(args, long *);
+				*ip = (str - buf);
+			} else {
+				int *ip = va_arg(args, int *);
+				*ip = (str - buf);
+			}
+			continue;
+
+		case '%':
+			*str++ = '%';
+			continue;
+
+			/* integer number formats - set up the flags and "break" */
+		case 'o':
+			base = 8;
+			break;
+
+		case 'x':
+			flags |= SMALL;
+			fallthrough;
+		case 'X':
+			base = 16;
+			break;
+
+		case 'd':
+		case 'i':
+			flags |= SIGN;
+			break;
+
+		case 'u':
+			break;
+
+		default:
+			*str++ = '%';
+			if (*fmt)
+				*str++ = *fmt;
+			else
+				--fmt;
+			continue;
+		}
+		if (qualifier == 'l')
+			num = va_arg(args, unsigned long);
+		else if (qualifier == 'h') {
+			num = (unsigned short)va_arg(args, int);
+			if (flags & SIGN)
+				num = (short)num;
+		} else if (flags & SIGN)
+			num = va_arg(args, int);
+		else
+			num = va_arg(args, unsigned int);
+		str = number(str, num, base, field_width, precision, flags);
+	}
+	*str = '\0';
+	return str - buf;
+}
+
+int sprintf(char *buf, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i = vsprintf(buf, fmt, args);
+	va_end(args);
+	return i;
+}
+
+int printf(const char *fmt, ...)
+{
+	char printf_buf[1024];
+	va_list args;
+	int printed;
+
+	va_start(args, fmt);
+	printed = vsprintf(printf_buf, fmt, args);
+	va_end(args);
+
+	puts(printf_buf);
+
+	return printed;
+}