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

5 files changed, 403 insertions, 0 deletions

diff --git a/arch/csky/lib/Makefile b/arch/csky/lib/Makefile
new file mode 100644
index 000000000..d0ce6e2d7
--- /dev/null
+++ b/arch/csky/lib/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+lib-y  := usercopy.o delay.o
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_STRING_OPS), y)
+lib-y  += string.o
+endif
diff --git a/arch/csky/lib/delay.c b/arch/csky/lib/delay.c
new file mode 100644
index 000000000..f5db31731
--- /dev/null
+++ b/arch/csky/lib/delay.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+
+void __aligned(8) __delay(unsigned long loops)
+{
+	asm volatile (
+		"mov r0, r0\n"
+		"1:declt %0\n"
+		"bf	1b"
+		: "=r"(loops)
+		: "0"(loops));
+}
+EXPORT_SYMBOL(__delay);
+
+void __const_udelay(unsigned long xloops)
+{
+	unsigned long long loops;
+
+	loops = (unsigned long long)xloops * loops_per_jiffy * HZ;
+
+	__delay(loops >> 32);
+}
+EXPORT_SYMBOL(__const_udelay);
+
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long nsecs)
+{
+	__const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */
+}
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/csky/lib/error-inject.c b/arch/csky/lib/error-inject.c
new file mode 100644
index 000000000..c15fb36fe
--- /dev/null
+++ b/arch/csky/lib/error-inject.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	instruction_pointer_set(regs, regs->lr);
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/csky/lib/string.c b/arch/csky/lib/string.c
new file mode 100644
index 000000000..d65626fca
--- /dev/null
+++ b/arch/csky/lib/string.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * String functions optimized for hardware which doesn't
+ * handle unaligned memory accesses efficiently.
+ *
+ * Copyright (C) 2021 Matteo Croce
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+
+/* Minimum size for a word copy to be convenient */
+#define BYTES_LONG	sizeof(long)
+#define WORD_MASK	(BYTES_LONG - 1)
+#define MIN_THRESHOLD	(BYTES_LONG * 2)
+
+/* convenience union to avoid cast between different pointer types */
+union types {
+	u8 *as_u8;
+	unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+union const_types {
+	const u8 *as_u8;
+	unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+void *memcpy(void *dest, const void *src, size_t count)
+{
+	union const_types s = { .as_u8 = src };
+	union types d = { .as_u8 = dest };
+	int distance = 0;
+
+	if (count < MIN_THRESHOLD)
+		goto copy_remainder;
+
+	/* Copy a byte at time until destination is aligned. */
+	for (; d.as_uptr & WORD_MASK; count--)
+		*d.as_u8++ = *s.as_u8++;
+
+	distance = s.as_uptr & WORD_MASK;
+
+	if (distance) {
+		unsigned long last, next;
+
+		/*
+		 * s is distance bytes ahead of d, and d just reached
+		 * the alignment boundary. Move s backward to word align it
+		 * and shift data to compensate for distance, in order to do
+		 * word-by-word copy.
+		 */
+		s.as_u8 -= distance;
+
+		next = s.as_ulong[0];
+		for (; count >= BYTES_LONG; count -= BYTES_LONG) {
+			last = next;
+			next = s.as_ulong[1];
+
+			d.as_ulong[0] = last >> (distance * 8) |
+				next << ((BYTES_LONG - distance) * 8);
+
+			d.as_ulong++;
+			s.as_ulong++;
+		}
+
+		/* Restore s with the original offset. */
+		s.as_u8 += distance;
+	} else {
+		/*
+		 * If the source and dest lower bits are the same, do a simple
+		 * 32/64 bit wide copy.
+		 */
+		for (; count >= BYTES_LONG; count -= BYTES_LONG)
+			*d.as_ulong++ = *s.as_ulong++;
+	}
+
+copy_remainder:
+	while (count--)
+		*d.as_u8++ = *s.as_u8++;
+
+	return dest;
+}
+EXPORT_SYMBOL(memcpy);
+
+/*
+ * Simply check if the buffer overlaps an call memcpy() in case,
+ * otherwise do a simple one byte at time backward copy.
+ */
+void *memmove(void *dest, const void *src, size_t count)
+{
+	if (dest < src || src + count <= dest)
+		return memcpy(dest, src, count);
+
+	if (dest > src) {
+		const char *s = src + count;
+		char *tmp = dest + count;
+
+		while (count--)
+			*--tmp = *--s;
+	}
+	return dest;
+}
+EXPORT_SYMBOL(memmove);
+
+void *memset(void *s, int c, size_t count)
+{
+	union types dest = { .as_u8 = s };
+
+	if (count >= MIN_THRESHOLD) {
+		unsigned long cu = (unsigned long)c;
+
+		/* Compose an ulong with 'c' repeated 4/8 times */
+		cu |= cu << 8;
+		cu |= cu << 16;
+		/* Suppress warning on 32 bit machines */
+		cu |= (cu << 16) << 16;
+
+		for (; count && dest.as_uptr & WORD_MASK; count--)
+			*dest.as_u8++ = c;
+
+		/* Copy using the largest size allowed */
+		for (; count >= BYTES_LONG; count -= BYTES_LONG)
+			*dest.as_ulong++ = cu;
+	}
+
+	/* copy the remainder */
+	while (count--)
+		*dest.as_u8++ = c;
+
+	return s;
+}
+EXPORT_SYMBOL(memset);
diff --git a/arch/csky/lib/usercopy.c b/arch/csky/lib/usercopy.c
new file mode 100644
index 000000000..3c01c5442
--- /dev/null
+++ b/arch/csky/lib/usercopy.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/uaccess.h>
+#include <linux/types.h>
+
+unsigned long raw_copy_from_user(void *to, const void *from,
+			unsigned long n)
+{
+	int tmp, nsave;
+
+	__asm__ __volatile__(
+	"0:     cmpnei  %1, 0           \n"
+	"       bf      7f              \n"
+	"       mov     %3, %1          \n"
+	"       or      %3, %2          \n"
+	"       andi    %3, 3           \n"
+	"       cmpnei  %3, 0           \n"
+	"       bf      1f              \n"
+	"       br      5f              \n"
+	"1:     cmplti  %0, 16          \n"
+	"       bt      3f              \n"
+	"2:     ldw     %3, (%2, 0)     \n"
+	"10:    ldw     %4, (%2, 4)     \n"
+	"       stw     %3, (%1, 0)     \n"
+	"       stw     %4, (%1, 4)     \n"
+	"11:    ldw     %3, (%2, 8)     \n"
+	"12:    ldw     %4, (%2, 12)    \n"
+	"       stw     %3, (%1, 8)     \n"
+	"       stw     %4, (%1, 12)    \n"
+	"       addi    %2, 16          \n"
+	"       addi    %1, 16          \n"
+	"       subi    %0, 16          \n"
+	"       br      1b              \n"
+	"3:     cmplti  %0, 4           \n"
+	"       bt      5f              \n"
+	"4:     ldw     %3, (%2, 0)     \n"
+	"       stw     %3, (%1, 0)     \n"
+	"       addi    %2, 4           \n"
+	"       addi    %1, 4           \n"
+	"       subi    %0, 4           \n"
+	"       br      3b              \n"
+	"5:     cmpnei  %0, 0           \n"
+	"       bf      7f              \n"
+	"6:     ldb     %3, (%2, 0)     \n"
+	"       stb     %3, (%1, 0)     \n"
+	"       addi    %2,  1          \n"
+	"       addi    %1,  1          \n"
+	"       subi    %0,  1          \n"
+	"       br      5b              \n"
+	"8:     stw     %3, (%1, 0)     \n"
+	"       subi    %0, 4           \n"
+	"       bf      7f              \n"
+	"9:     subi    %0, 8           \n"
+	"       bf      7f              \n"
+	"13:    stw     %3, (%1, 8)     \n"
+	"       subi    %0, 12          \n"
+	"       bf      7f              \n"
+	".section __ex_table, \"a\"     \n"
+	".align   2                     \n"
+	".long    2b, 7f                \n"
+	".long    4b, 7f                \n"
+	".long    6b, 7f                \n"
+	".long   10b, 8b                \n"
+	".long   11b, 9b                \n"
+	".long   12b,13b                \n"
+	".previous                      \n"
+	"7:                             \n"
+	: "=r"(n), "=r"(to), "=r"(from), "=r"(nsave),
+	  "=r"(tmp)
+	: "0"(n), "1"(to), "2"(from)
+	: "memory");
+
+	return n;
+}
+EXPORT_SYMBOL(raw_copy_from_user);
+
+unsigned long raw_copy_to_user(void *to, const void *from,
+			unsigned long n)
+{
+	int w0, w1, w2, w3;
+
+	__asm__ __volatile__(
+	"0:     cmpnei  %1, 0           \n"
+	"       bf      8f              \n"
+	"       mov     %3, %1          \n"
+	"       or      %3, %2          \n"
+	"       andi    %3, 3           \n"
+	"       cmpnei  %3, 0           \n"
+	"       bf      1f              \n"
+	"       br      5f              \n"
+	"1:     cmplti  %0, 16          \n" /* 4W */
+	"       bt      3f              \n"
+	"       ldw     %3, (%2, 0)     \n"
+	"       ldw     %4, (%2, 4)     \n"
+	"       ldw     %5, (%2, 8)     \n"
+	"       ldw     %6, (%2, 12)    \n"
+	"2:     stw     %3, (%1, 0)     \n"
+	"9:     stw     %4, (%1, 4)     \n"
+	"10:    stw     %5, (%1, 8)     \n"
+	"11:    stw     %6, (%1, 12)    \n"
+	"       addi    %2, 16          \n"
+	"       addi    %1, 16          \n"
+	"       subi    %0, 16          \n"
+	"       br      1b              \n"
+	"3:     cmplti  %0, 4           \n" /* 1W */
+	"       bt      5f              \n"
+	"       ldw     %3, (%2, 0)     \n"
+	"4:     stw     %3, (%1, 0)     \n"
+	"       addi    %2, 4           \n"
+	"       addi    %1, 4           \n"
+	"       subi    %0, 4           \n"
+	"       br      3b              \n"
+	"5:     cmpnei  %0, 0           \n"  /* 1B */
+	"       bf      13f             \n"
+	"       ldb     %3, (%2, 0)     \n"
+	"6:     stb     %3, (%1, 0)     \n"
+	"       addi    %2,  1          \n"
+	"       addi    %1,  1          \n"
+	"       subi    %0,  1          \n"
+	"       br      5b              \n"
+	"7:     subi	%0,  4          \n"
+	"8:     subi	%0,  4          \n"
+	"12:    subi	%0,  4          \n"
+	"       br      13f             \n"
+	".section __ex_table, \"a\"     \n"
+	".align   2                     \n"
+	".long    2b, 13f               \n"
+	".long    4b, 13f               \n"
+	".long    6b, 13f               \n"
+	".long    9b, 12b               \n"
+	".long   10b, 8b                \n"
+	".long   11b, 7b                \n"
+	".previous                      \n"
+	"13:                            \n"
+	: "=r"(n), "=r"(to), "=r"(from), "=r"(w0),
+	  "=r"(w1), "=r"(w2), "=r"(w3)
+	: "0"(n), "1"(to), "2"(from)
+	: "memory");
+
+	return n;
+}
+EXPORT_SYMBOL(raw_copy_to_user);
+
+/*
+ * __clear_user: - Zero a block of memory in user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @n:    Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+unsigned long
+__clear_user(void __user *to, unsigned long n)
+{
+	int data, value, tmp;
+
+	__asm__ __volatile__(
+	"0:     cmpnei  %1, 0           \n"
+	"       bf      7f              \n"
+	"       mov     %3, %1          \n"
+	"       andi    %3, 3           \n"
+	"       cmpnei  %3, 0           \n"
+	"       bf      1f              \n"
+	"       br      5f              \n"
+	"1:     cmplti  %0, 32          \n" /* 4W */
+	"       bt      3f              \n"
+	"8:     stw     %2, (%1, 0)     \n"
+	"10:    stw     %2, (%1, 4)     \n"
+	"11:    stw     %2, (%1, 8)     \n"
+	"12:    stw     %2, (%1, 12)    \n"
+	"13:    stw     %2, (%1, 16)    \n"
+	"14:    stw     %2, (%1, 20)    \n"
+	"15:    stw     %2, (%1, 24)    \n"
+	"16:    stw     %2, (%1, 28)    \n"
+	"       addi    %1, 32          \n"
+	"       subi    %0, 32          \n"
+	"       br      1b              \n"
+	"3:     cmplti  %0, 4           \n" /* 1W */
+	"       bt      5f              \n"
+	"4:     stw     %2, (%1, 0)     \n"
+	"       addi    %1, 4           \n"
+	"       subi    %0, 4           \n"
+	"       br      3b              \n"
+	"5:     cmpnei  %0, 0           \n" /* 1B */
+	"9:     bf      7f              \n"
+	"6:     stb     %2, (%1, 0)     \n"
+	"       addi    %1,  1          \n"
+	"       subi    %0,  1          \n"
+	"       br      5b              \n"
+	".section __ex_table,\"a\"      \n"
+	".align   2                     \n"
+	".long    8b, 9b                \n"
+	".long    10b, 9b               \n"
+	".long    11b, 9b               \n"
+	".long    12b, 9b               \n"
+	".long    13b, 9b               \n"
+	".long    14b, 9b               \n"
+	".long    15b, 9b               \n"
+	".long    16b, 9b               \n"
+	".long    4b, 9b                \n"
+	".long    6b, 9b                \n"
+	".previous                      \n"
+	"7:                             \n"
+	: "=r"(n), "=r" (data), "=r"(value), "=r"(tmp)
+	: "0"(n), "1"(to), "2"(0)
+	: "memory");
+
+	return n;
+}
+EXPORT_SYMBOL(__clear_user);