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 --- sound/soc/sof/sof-utils.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 sound/soc/sof/sof-utils.c (limited to 'sound/soc/sof/sof-utils.c') diff --git a/sound/soc/sof/sof-utils.c b/sound/soc/sof/sof-utils.c new file mode 100644 index 000000000..f70089317 --- /dev/null +++ b/sound/soc/sof/sof-utils.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +// +// This file is provided under a dual BSD/GPLv2 license. When using or +// redistributing this file, you may do so under either license. +// +// Copyright(c) 2018-2022 Intel Corporation +// +// Author: Keyon Jie +// + +#include +#include +#include +#include +#include +#include "sof-utils.h" + +/* + * Generic buffer page table creation. + * Take the each physical page address and drop the least significant unused + * bits from each (based on PAGE_SIZE). Then pack valid page address bits + * into compressed page table. + */ + +int snd_sof_create_page_table(struct device *dev, + struct snd_dma_buffer *dmab, + unsigned char *page_table, size_t size) +{ + int i, pages; + + pages = snd_sgbuf_aligned_pages(size); + + dev_dbg(dev, "generating page table for %p size 0x%zx pages %d\n", + dmab->area, size, pages); + + for (i = 0; i < pages; i++) { + /* + * The number of valid address bits for each page is 20. + * idx determines the byte position within page_table + * where the current page's address is stored + * in the compressed page_table. + * This can be calculated by multiplying the page number by 2.5. + */ + u32 idx = (5 * i) >> 1; + u32 pfn = snd_sgbuf_get_addr(dmab, i * PAGE_SIZE) >> PAGE_SHIFT; + u8 *pg_table; + + pg_table = (u8 *)(page_table + idx); + + /* + * pagetable compression: + * byte 0 byte 1 byte 2 byte 3 byte 4 byte 5 + * ___________pfn 0__________ __________pfn 1___________ _pfn 2... + * .... .... .... .... .... .... .... .... .... .... .... + * It is created by: + * 1. set current location to 0, PFN index i to 0 + * 2. put pfn[i] at current location in Little Endian byte order + * 3. calculate an intermediate value as + * x = (pfn[i+1] << 4) | (pfn[i] & 0xf) + * 4. put x at offset (current location + 2) in LE byte order + * 5. increment current location by 5 bytes, increment i by 2 + * 6. continue to (2) + */ + if (i & 1) + put_unaligned_le32((pg_table[0] & 0xf) | pfn << 4, + pg_table); + else + put_unaligned_le32(pfn, pg_table); + } + + return pages; +} +EXPORT_SYMBOL(snd_sof_create_page_table); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("SOF utils"); -- cgit v1.3.1