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 --- fs/squashfs/id.c | 115 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 115 insertions(+) create mode 100644 fs/squashfs/id.c (limited to 'fs/squashfs/id.c') diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c new file mode 100644 index 000000000..ea5387679 --- /dev/null +++ b/fs/squashfs/id.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher + * + * id.c + */ + +/* + * This file implements code to handle uids and gids. + * + * For space efficiency regular files store uid and gid indexes, which are + * converted to 32-bit uids/gids using an id look up table. This table is + * stored compressed into metadata blocks. A second index table is used to + * locate these. This second index table for speed of access (and because it + * is small) is read at mount time and cached in memory. + */ + +#include +#include +#include + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" + +/* + * Map uid/gid index into real 32-bit uid/gid using the id look up table + */ +int squashfs_get_id(struct super_block *sb, unsigned int index, + unsigned int *id) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int block = SQUASHFS_ID_BLOCK(index); + int offset = SQUASHFS_ID_BLOCK_OFFSET(index); + u64 start_block; + __le32 disk_id; + int err; + + if (index >= msblk->ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->id_table[block]); + + err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset, + sizeof(disk_id)); + if (err < 0) + return err; + + *id = le32_to_cpu(disk_id); + return 0; +} + + +/* + * Read uncompressed id lookup table indexes from disk into memory + */ +__le64 *squashfs_read_id_index_table(struct super_block *sb, + u64 id_table_start, u64 next_table, unsigned short no_ids) +{ + unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids); + unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids); + int n; + __le64 *table; + u64 start, end; + + TRACE("In read_id_index_table, length %d\n", length); + + /* Sanity check values */ + + /* there should always be at least one id */ + if (no_ids == 0) + return ERR_PTR(-EINVAL); + + /* + * The computed size of the index table (length bytes) should exactly + * match the table start and end points + */ + if (length != (next_table - id_table_start)) + return ERR_PTR(-EINVAL); + + table = squashfs_read_table(sb, id_table_start, length); + if (IS_ERR(table)) + return table; + + /* + * table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than id_table_start, and again the difference + * should be SQUASHFS_METADATA_SIZE or less + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + + return table; +} -- cgit v1.3.1