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/9p/vfs_dir.c | 266 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 266 insertions(+) create mode 100644 fs/9p/vfs_dir.c (limited to 'fs/9p/vfs_dir.c') diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c new file mode 100644 index 000000000..323f85352 --- /dev/null +++ b/fs/9p/vfs_dir.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This file contains vfs directory ops for the 9P2000 protocol. + * + * Copyright (C) 2004 by Eric Van Hensbergen + * Copyright (C) 2002 by Ron Minnich + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "v9fs.h" +#include "v9fs_vfs.h" +#include "fid.h" + +/** + * struct p9_rdir - readdir accounting + * @head: start offset of current dirread buffer + * @tail: end offset of current dirread buffer + * @offset: file position the data at @head corresponds to + * @buf: dirread buffer + * + * private structure for keeping track of readdir + * allocated on demand + */ + +struct p9_rdir { + int head; + int tail; + loff_t offset; + uint8_t buf[]; +}; + +/** + * dt_type - return file type + * @mistat: mistat structure + * + */ + +static inline int dt_type(struct p9_wstat *mistat) +{ + unsigned long perm = mistat->mode; + int rettype = DT_REG; + + if (perm & P9_DMDIR) + rettype = DT_DIR; + if (perm & P9_DMSYMLINK) + rettype = DT_LNK; + + return rettype; +} + +/** + * v9fs_alloc_rdir_buf - Allocate buffer used for read and readdir + * @filp: opened file structure + * @buflen: Length in bytes of buffer to allocate + * + */ + +static struct p9_rdir *v9fs_alloc_rdir_buf(struct file *filp, int buflen) +{ + struct p9_fid *fid = filp->private_data; + + if (!fid->rdir) + fid->rdir = kvzalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL); + return fid->rdir; +} + +/** + * v9fs_dir_readdir - iterate through a directory + * @file: opened file structure + * @ctx: actor we feed the entries to + * + */ + +static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) +{ + bool over; + struct p9_wstat st; + int err = 0; + struct p9_fid *fid; + int buflen; + struct p9_rdir *rdir; + struct kvec kvec; + + p9_debug(P9_DEBUG_VFS, "name %pD\n", file); + fid = file->private_data; + + buflen = fid->clnt->msize - P9_IOHDRSZ; + + rdir = v9fs_alloc_rdir_buf(file, buflen); + if (!rdir) + return -ENOMEM; + kvec.iov_base = rdir->buf; + kvec.iov_len = buflen; + + if (rdir->head < rdir->tail && rdir->offset != ctx->pos) + rdir->head = rdir->tail = 0; + + while (1) { + if (rdir->tail == rdir->head) { + struct iov_iter to; + int n; + + iov_iter_kvec(&to, ITER_DEST, &kvec, 1, buflen); + n = p9_client_read(file->private_data, ctx->pos, &to, + &err); + if (err) + return err; + if (n == 0) + return 0; + + rdir->head = 0; + rdir->tail = n; + rdir->offset = ctx->pos; + } + while (rdir->head < rdir->tail) { + err = p9stat_read(fid->clnt, rdir->buf + rdir->head, + rdir->tail - rdir->head, &st); + if (err <= 0) { + p9_debug(P9_DEBUG_VFS, "returned %d\n", err); + return -EIO; + } + + over = !dir_emit(ctx, st.name, strlen(st.name), + QID2INO(&st.qid), dt_type(&st)); + p9stat_free(&st); + if (over) + return 0; + + rdir->head += err; + ctx->pos += err; + rdir->offset = ctx->pos; + } + } +} + +/** + * v9fs_dir_readdir_dotl - iterate through a directory + * @file: opened file structure + * @ctx: actor we feed the entries to + * + */ +static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx) +{ + int err = 0; + struct p9_fid *fid; + int buflen; + struct p9_rdir *rdir; + struct p9_dirent curdirent; + + p9_debug(P9_DEBUG_VFS, "name %pD\n", file); + fid = file->private_data; + + buflen = fid->clnt->msize - P9_READDIRHDRSZ; + + rdir = v9fs_alloc_rdir_buf(file, buflen); + if (!rdir) + return -ENOMEM; + + if (rdir->head < rdir->tail && rdir->offset != ctx->pos) + rdir->head = rdir->tail = 0; + + while (1) { + if (rdir->tail == rdir->head) { + err = p9_client_readdir(fid, rdir->buf, buflen, + ctx->pos); + if (err <= 0) + return err; + + rdir->head = 0; + rdir->tail = err; + rdir->offset = ctx->pos; + } + + while (rdir->head < rdir->tail) { + + err = p9dirent_read(fid->clnt, rdir->buf + rdir->head, + rdir->tail - rdir->head, + &curdirent); + if (err < 0) { + p9_debug(P9_DEBUG_VFS, "returned %d\n", err); + return -EIO; + } + + if (!dir_emit(ctx, curdirent.d_name, + strlen(curdirent.d_name), + QID2INO(&curdirent.qid), + curdirent.d_type)) + return 0; + + ctx->pos = curdirent.d_off; + rdir->head += err; + rdir->offset = ctx->pos; + } + } +} + + +/** + * v9fs_dir_release - close a directory or a file + * @inode: inode of the directory or file + * @filp: file pointer to a directory or file + * + */ + +int v9fs_dir_release(struct inode *inode, struct file *filp) +{ + struct v9fs_inode *v9inode = V9FS_I(inode); + struct p9_fid *fid; + __le32 version; + loff_t i_size; + int retval = 0, put_err; + + fid = filp->private_data; + p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n", + inode, filp, fid ? fid->fid : -1); + + if (fid) { + if ((S_ISREG(inode->i_mode)) && (filp->f_mode & FMODE_WRITE)) + retval = filemap_fdatawrite(inode->i_mapping); + + spin_lock(&inode->i_lock); + hlist_del(&fid->ilist); + spin_unlock(&inode->i_lock); + put_err = p9_fid_put(fid); + retval = retval < 0 ? retval : put_err; + } + + if ((filp->f_mode & FMODE_WRITE)) { + version = cpu_to_le32(v9inode->qid.version); + i_size = i_size_read(inode); + fscache_unuse_cookie(v9fs_inode_cookie(v9inode), + &version, &i_size); + } else { + fscache_unuse_cookie(v9fs_inode_cookie(v9inode), NULL, NULL); + } + return retval; +} + +const struct file_operations v9fs_dir_operations = { + .read = generic_read_dir, + .llseek = generic_file_llseek, + .iterate_shared = v9fs_dir_readdir, + .open = v9fs_file_open, + .release = v9fs_dir_release, +}; + +const struct file_operations v9fs_dir_operations_dotl = { + .read = generic_read_dir, + .llseek = generic_file_llseek, + .iterate_shared = v9fs_dir_readdir_dotl, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .fsync = v9fs_file_fsync_dotl, +}; -- cgit v1.3.1