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 --- net/xdp/xsk_queue.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 net/xdp/xsk_queue.c (limited to 'net/xdp/xsk_queue.c') diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c new file mode 100644 index 000000000..d95b6d0d9 --- /dev/null +++ b/net/xdp/xsk_queue.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP user-space ring structure + * Copyright(c) 2018 Intel Corporation. + */ + +#include +#include +#include +#include +#include + +#include + +#include "xsk_queue.h" + +static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue) +{ + struct xdp_umem_ring *umem_ring; + struct xdp_rxtx_ring *rxtx_ring; + + if (umem_queue) + return struct_size(umem_ring, desc, q->nentries); + return struct_size(rxtx_ring, desc, q->nentries); +} + +static void *xskq_vmalloc_user(unsigned long size) +{ + return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL, + VM_USERMAP, NUMA_NO_NODE, + __builtin_return_address(0)); +} + +struct xsk_queue *xskq_create(u32 nentries, bool umem_queue) +{ + struct xsk_queue *q; + size_t size; + + q = kzalloc_obj(*q); + if (!q) + return NULL; + + q->nentries = nentries; + q->ring_mask = nentries - 1; + + size = xskq_get_ring_size(q, umem_queue); + + /* size which is overflowing or close to SIZE_MAX will become 0 in + * PAGE_ALIGN(), checking SIZE_MAX is enough due to the previous + * is_power_of_2(), the rest will be handled by vmalloc_user() + */ + if (unlikely(size == SIZE_MAX)) { + kfree(q); + return NULL; + } + + size = PAGE_ALIGN(size); + + q->ring = xskq_vmalloc_user(size); + if (!q->ring) { + kfree(q); + return NULL; + } + + q->ring_vmalloc_size = size; + return q; +} + +void xskq_destroy(struct xsk_queue *q) +{ + if (!q) + return; + + vfree(q->ring); + kfree(q); +} -- cgit v1.3.1