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, 177 insertions, 0 deletions

diff --git a/lib/crypto/mpi/mpi-bit.c b/lib/crypto/mpi/mpi-bit.c
new file mode 100644
index 000000000..b3d0e7ddb
--- /dev/null
+++ b/lib/crypto/mpi/mpi-bit.c
@@ -0,0 +1,177 @@
+/* mpi-bit.c  -  MPI bit level functions
+ * Copyright (C) 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ */
+
+#include <linux/export.h>
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+#define A_LIMB_1 ((mpi_limb_t) 1)
+
+/****************
+ * Sometimes we have MSL (most significant limbs) which are 0;
+ * this is for some reasons not good, so this function removes them.
+ */
+void mpi_normalize(MPI a)
+{
+	for (; a->nlimbs && !a->d[a->nlimbs - 1]; a->nlimbs--)
+		;
+}
+
+/****************
+ * Return the number of bits in A.
+ */
+unsigned mpi_get_nbits(MPI a)
+{
+	unsigned n;
+
+	mpi_normalize(a);
+
+	if (a->nlimbs) {
+		mpi_limb_t alimb = a->d[a->nlimbs - 1];
+		if (alimb)
+			n = count_leading_zeros(alimb);
+		else
+			n = BITS_PER_MPI_LIMB;
+		n = BITS_PER_MPI_LIMB - n + (a->nlimbs - 1) * BITS_PER_MPI_LIMB;
+	} else
+		n = 0;
+	return n;
+}
+EXPORT_SYMBOL_GPL(mpi_get_nbits);
+
+/****************
+ * Test whether bit N is set.
+ */
+int mpi_test_bit(MPI a, unsigned int n)
+{
+	unsigned int limbno, bitno;
+	mpi_limb_t limb;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs)
+		return 0; /* too far left: this is a 0 */
+	limb = a->d[limbno];
+	return (limb & (A_LIMB_1 << bitno)) ? 1 : 0;
+}
+EXPORT_SYMBOL_GPL(mpi_test_bit);
+
+/****************
+ * Set bit N of A.
+ */
+int mpi_set_bit(MPI a, unsigned int n)
+{
+	unsigned int i, limbno, bitno;
+	int err;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs) {
+		for (i = a->nlimbs; i < a->alloced; i++)
+			a->d[i] = 0;
+		err = mpi_resize(a, limbno+1);
+		if (err)
+			return err;
+		a->nlimbs = limbno+1;
+	}
+	a->d[limbno] |= (A_LIMB_1<<bitno);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_set_bit);
+
+/*
+ * Shift A by N bits to the right.
+ */
+int mpi_rshift(MPI x, MPI a, unsigned int n)
+{
+	mpi_size_t xsize;
+	unsigned int i;
+	unsigned int nlimbs = (n/BITS_PER_MPI_LIMB);
+	unsigned int nbits = (n%BITS_PER_MPI_LIMB);
+	int err;
+
+	if (x == a) {
+		/* In-place operation.  */
+		if (nlimbs >= x->nlimbs) {
+			x->nlimbs = 0;
+			return 0;
+		}
+
+		if (nlimbs) {
+			for (i = 0; i < x->nlimbs - nlimbs; i++)
+				x->d[i] = x->d[i+nlimbs];
+			x->d[i] = 0;
+			x->nlimbs -= nlimbs;
+		}
+		if (x->nlimbs && nbits)
+			mpihelp_rshift(x->d, x->d, x->nlimbs, nbits);
+	} else if (nlimbs) {
+		/* Copy and shift by more or equal bits than in a limb. */
+		xsize = a->nlimbs;
+		x->sign = a->sign;
+		err = RESIZE_IF_NEEDED(x, xsize);
+		if (err)
+			return err;
+		x->nlimbs = xsize;
+		for (i = 0; i < a->nlimbs; i++)
+			x->d[i] = a->d[i];
+		x->nlimbs = i;
+
+		if (nlimbs >= x->nlimbs) {
+			x->nlimbs = 0;
+			return 0;
+		}
+
+		for (i = 0; i < x->nlimbs - nlimbs; i++)
+			x->d[i] = x->d[i+nlimbs];
+		x->d[i] = 0;
+		x->nlimbs -= nlimbs;
+
+		if (x->nlimbs && nbits)
+			mpihelp_rshift(x->d, x->d, x->nlimbs, nbits);
+	} else {
+		/* Copy and shift by less than bits in a limb.  */
+		xsize = a->nlimbs;
+		x->sign = a->sign;
+		err = RESIZE_IF_NEEDED(x, xsize);
+		if (err)
+			return err;
+		x->nlimbs = xsize;
+
+		if (xsize) {
+			if (nbits)
+				mpihelp_rshift(x->d, a->d, x->nlimbs, nbits);
+			else {
+				/* The rshift helper function is not specified for
+				 * NBITS==0, thus we do a plain copy here.
+				 */
+				for (i = 0; i < x->nlimbs; i++)
+					x->d[i] = a->d[i];
+			}
+		}
+	}
+	MPN_NORMALIZE(x->d, x->nlimbs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_rshift);