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, 89 insertions, 0 deletions

diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c
new file mode 100644
index 000000000..78ecc6336
--- /dev/null
+++ b/fs/udf/udftime.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: LGPL-2.0+
+/* Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Contributed by Paul Eggert (eggert@twinsun.com). */
+
+/*
+ * dgb 10/02/98: ripped this from glibc source to help convert timestamps
+ *               to unix time
+ *     10/04/98: added new table-based lookup after seeing how ugly
+ *               the gnu code is
+ * blf 09/27/99: ripped out all the old code and inserted new table from
+ *		 John Brockmeyer (without leap second corrections)
+ *		 rewrote udf_stamp_to_time and fixed timezone accounting in
+ *		 udf_time_to_stamp.
+ */
+
+/*
+ * We don't take into account leap seconds. This may be correct or incorrect.
+ * For more NIST information (especially dealing with leap seconds), see:
+ * http://www.boulder.nist.gov/timefreq/pubs/bulletin/leapsecond.htm
+ */
+
+#include "udfdecl.h"
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/time.h>
+
+void
+udf_disk_stamp_to_time(struct timespec64 *dest, struct timestamp src)
+{
+	u16 typeAndTimezone = le16_to_cpu(src.typeAndTimezone);
+	u16 year = le16_to_cpu(src.year);
+	uint8_t type = typeAndTimezone >> 12;
+	int16_t offset;
+
+	if (type == 1) {
+		offset = typeAndTimezone << 4;
+		/* sign extent offset */
+		offset = (offset >> 4);
+		if (offset == -2047) /* unspecified offset */
+			offset = 0;
+	} else
+		offset = 0;
+
+	dest->tv_sec = mktime64(year, src.month, src.day, src.hour, src.minute,
+			src.second);
+	dest->tv_sec -= offset * 60;
+
+	/*
+	 * Sanitize nanosecond field since reportedly some filesystems are
+	 * recorded with bogus sub-second values.
+	 */
+	if (src.centiseconds < 100 && src.hundredsOfMicroseconds < 100 &&
+	    src.microseconds < 100) {
+		dest->tv_nsec = 1000 * (src.centiseconds * 10000 +
+			src.hundredsOfMicroseconds * 100 + src.microseconds);
+	} else {
+		dest->tv_nsec = 0;
+	}
+}
+
+void
+udf_time_to_disk_stamp(struct timestamp *dest, struct timespec64 ts)
+{
+	time64_t seconds;
+	int16_t offset;
+	struct tm tm;
+
+	offset = -sys_tz.tz_minuteswest;
+
+	dest->typeAndTimezone = cpu_to_le16(0x1000 | (offset & 0x0FFF));
+
+	seconds = ts.tv_sec + offset * 60;
+	time64_to_tm(seconds, 0, &tm);
+	dest->year = cpu_to_le16(tm.tm_year + 1900);
+	dest->month = tm.tm_mon + 1;
+	dest->day = tm.tm_mday;
+	dest->hour = tm.tm_hour;
+	dest->minute = tm.tm_min;
+	dest->second = tm.tm_sec;
+	dest->centiseconds = ts.tv_nsec / 10000000;
+	dest->hundredsOfMicroseconds = (ts.tv_nsec / 1000 -
+					dest->centiseconds * 10000) / 100;
+	dest->microseconds = (ts.tv_nsec / 1000 - dest->centiseconds * 10000 -
+			      dest->hundredsOfMicroseconds * 100);
+}
+
+/* EOF */