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, 128 insertions, 0 deletions

diff --git a/drivers/misc/altera-stapl/altera-comp.c b/drivers/misc/altera-stapl/altera-comp.c
new file mode 100644
index 000000000..4a63f51cc
--- /dev/null
+++ b/drivers/misc/altera-stapl/altera-comp.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * altera-comp.c
+ *
+ * altera FPGA driver
+ *
+ * Copyright (C) Altera Corporation 1998-2001
+ * Copyright (C) 2010 NetUP Inc.
+ * Copyright (C) 2010 Igor M. Liplianin <liplianin@netup.ru>
+ */
+
+#include <linux/kernel.h>
+#include "altera-exprt.h"
+
+#define	SHORT_BITS		16
+#define	CHAR_BITS		8
+#define	DATA_BLOB_LENGTH	3
+#define	MATCH_DATA_LENGTH	8192
+#define ALTERA_REQUEST_SIZE	1024
+#define ALTERA_BUFFER_SIZE	(MATCH_DATA_LENGTH + ALTERA_REQUEST_SIZE)
+
+static u32 altera_bits_req(u32 n)
+{
+	u32 result = SHORT_BITS;
+
+	if (n == 0)
+		result = 1;
+	else {
+		/* Look for the highest non-zero bit position */
+		while ((n & (1 << (SHORT_BITS - 1))) == 0) {
+			n <<= 1;
+			--result;
+		}
+	}
+
+	return result;
+}
+
+static u32 altera_read_packed(u8 *buffer, u32 bits, u32 *bits_avail,
+							u32 *in_index)
+{
+	u32 result = 0;
+	u32 shift = 0;
+	u32 databyte = 0;
+
+	while (bits > 0) {
+		databyte = buffer[*in_index];
+		result |= (((databyte >> (CHAR_BITS - *bits_avail))
+			& (0xff >> (CHAR_BITS - *bits_avail))) << shift);
+
+		if (bits <= *bits_avail) {
+			result &= (0xffff >> (SHORT_BITS - (bits + shift)));
+			*bits_avail -= bits;
+			bits = 0;
+		} else {
+			++(*in_index);
+			shift += *bits_avail;
+			bits -= *bits_avail;
+			*bits_avail = CHAR_BITS;
+		}
+	}
+
+	return result;
+}
+
+u32 altera_shrink(u8 *in, u32 in_length, u8 *out, u32 out_length, s32 version)
+{
+	u32 i, j, data_length = 0L;
+	u32 offset, length;
+	u32 match_data_length = MATCH_DATA_LENGTH;
+	u32 bits_avail = CHAR_BITS;
+	u32 in_index = 0L;
+
+	if (version > 0)
+		--match_data_length;
+
+	for (i = 0; i < out_length; ++i)
+		out[i] = 0;
+
+	/* Read number of bytes in data. */
+	for (i = 0; i < sizeof(in_length); ++i) {
+		data_length = data_length | (
+			altera_read_packed(in,
+					CHAR_BITS,
+					&bits_avail,
+					&in_index) << (i * CHAR_BITS));
+	}
+
+	if (data_length > out_length) {
+		data_length = 0L;
+		return data_length;
+	}
+
+	i = 0;
+	while (i < data_length) {
+		/* A 0 bit indicates literal data. */
+		if (altera_read_packed(in, 1, &bits_avail,
+						&in_index) == 0) {
+			for (j = 0; j < DATA_BLOB_LENGTH; ++j) {
+				if (i < data_length) {
+					out[i] = (u8)altera_read_packed(in,
+							CHAR_BITS,
+							&bits_avail,
+							&in_index);
+					i++;
+				}
+			}
+		} else {
+			/* A 1 bit indicates offset/length to follow. */
+			offset = altera_read_packed(in, altera_bits_req((s16)
+					(i > match_data_length ?
+						match_data_length : i)),
+					&bits_avail,
+					&in_index);
+			length = altera_read_packed(in, CHAR_BITS,
+					&bits_avail,
+					&in_index);
+			for (j = 0; j < length; ++j) {
+				if (i < data_length) {
+					out[i] = out[i - offset];
+					i++;
+				}
+			}
+		}
+	}
+
+	return data_length;
+}