From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions 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) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- lib/crypto/mpi/mpi-inline.h | 109 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) create mode 100644 lib/crypto/mpi/mpi-inline.h (limited to 'lib/crypto/mpi/mpi-inline.h') diff --git a/lib/crypto/mpi/mpi-inline.h b/lib/crypto/mpi/mpi-inline.h new file mode 100644 index 000000000..980b6b940 --- /dev/null +++ b/lib/crypto/mpi/mpi-inline.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* mpi-inline.h - Internal to the Multi Precision Integers + * Copyright (C) 1994, 1996, 1998, 1999 Free Software Foundation, Inc. + * + * This file is part of GnuPG. + * + * Note: This code is heavily based on the GNU MP Library. + * Actually it's the same code with only minor changes in the + * way the data is stored; this is to support the abstraction + * of an optional secure memory allocation which may be used + * to avoid revealing of sensitive data due to paging etc. + * The GNU MP Library itself is published under the LGPL; + * however I decided to publish this code under the plain GPL. + */ + +#ifndef G10_MPI_INLINE_H +#define G10_MPI_INLINE_H + +#ifndef G10_MPI_INLINE_DECL +#define G10_MPI_INLINE_DECL static inline +#endif + +G10_MPI_INLINE_DECL mpi_limb_t +mpihelp_add_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, + mpi_size_t s1_size, mpi_limb_t s2_limb) +{ + mpi_limb_t x; + + x = *s1_ptr++; + s2_limb += x; + *res_ptr++ = s2_limb; + if (s2_limb < x) { /* sum is less than the left operand: handle carry */ + while (--s1_size) { + x = *s1_ptr++ + 1; /* add carry */ + *res_ptr++ = x; /* and store */ + if (x) /* not 0 (no overflow): we can stop */ + goto leave; + } + return 1; /* return carry (size of s1 to small) */ + } + +leave: + if (res_ptr != s1_ptr) { /* not the same variable */ + mpi_size_t i; /* copy the rest */ + for (i = 0; i < s1_size - 1; i++) + res_ptr[i] = s1_ptr[i]; + } + return 0; /* no carry */ +} + +G10_MPI_INLINE_DECL mpi_limb_t +mpihelp_add(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size, + mpi_ptr_t s2_ptr, mpi_size_t s2_size) +{ + mpi_limb_t cy = 0; + + if (s2_size) + cy = mpihelp_add_n(res_ptr, s1_ptr, s2_ptr, s2_size); + + if (s1_size - s2_size) + cy = mpihelp_add_1(res_ptr + s2_size, s1_ptr + s2_size, + s1_size - s2_size, cy); + return cy; +} + +G10_MPI_INLINE_DECL mpi_limb_t +mpihelp_sub_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, + mpi_size_t s1_size, mpi_limb_t s2_limb) +{ + mpi_limb_t x; + + x = *s1_ptr++; + s2_limb = x - s2_limb; + *res_ptr++ = s2_limb; + if (s2_limb > x) { + while (--s1_size) { + x = *s1_ptr++; + *res_ptr++ = x - 1; + if (x) + goto leave; + } + return 1; + } + +leave: + if (res_ptr != s1_ptr) { + mpi_size_t i; + for (i = 0; i < s1_size - 1; i++) + res_ptr[i] = s1_ptr[i]; + } + return 0; +} + +G10_MPI_INLINE_DECL mpi_limb_t +mpihelp_sub(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size, + mpi_ptr_t s2_ptr, mpi_size_t s2_size) +{ + mpi_limb_t cy = 0; + + if (s2_size) + cy = mpihelp_sub_n(res_ptr, s1_ptr, s2_ptr, s2_size); + + if (s1_size - s2_size) + cy = mpihelp_sub_1(res_ptr + s2_size, s1_ptr + s2_size, + s1_size - s2_size, cy); + return cy; +} + +#endif /*G10_MPI_INLINE_H */ -- cgit v1.3.1