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/proc_namespace.c | 337 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 337 insertions(+) create mode 100644 fs/proc_namespace.c (limited to 'fs/proc_namespace.c') diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c new file mode 100644 index 000000000..036356c0a --- /dev/null +++ b/fs/proc_namespace.c @@ -0,0 +1,337 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fs/proc_namespace.c - handling of /proc//{mounts,mountinfo,mountstats} + * + * In fact, that's a piece of procfs; it's *almost* isolated from + * the rest of fs/proc, but has rather close relationships with + * fs/namespace.c, thus here instead of fs/proc + * + */ +#include +#include +#include +#include +#include + +#include "proc/internal.h" /* only for get_proc_task() in ->open() */ + +#include "pnode.h" +#include "internal.h" + +static __poll_t mounts_poll(struct file *file, poll_table *wait) +{ + struct seq_file *m = file->private_data; + struct proc_mounts *p = m->private; + struct mnt_namespace *ns = p->ns; + __poll_t res = EPOLLIN | EPOLLRDNORM; + int event; + + poll_wait(file, &p->ns->poll, wait); + + event = READ_ONCE(ns->event); + if (m->poll_event != event) { + m->poll_event = event; + res |= EPOLLERR | EPOLLPRI; + } + + return res; +} + +struct proc_fs_opts { + int flag; + const char *str; +}; + +static int show_sb_opts(struct seq_file *m, struct super_block *sb) +{ + static const struct proc_fs_opts fs_opts[] = { + { SB_SYNCHRONOUS, ",sync" }, + { SB_DIRSYNC, ",dirsync" }, + { SB_MANDLOCK, ",mand" }, + { SB_LAZYTIME, ",lazytime" }, + { 0, NULL } + }; + const struct proc_fs_opts *fs_infop; + + for (fs_infop = fs_opts; fs_infop->flag; fs_infop++) { + if (sb->s_flags & fs_infop->flag) + seq_puts(m, fs_infop->str); + } + + return security_sb_show_options(m, sb); +} + +static void show_vfsmnt_opts(struct seq_file *m, struct vfsmount *mnt) +{ + static const struct proc_fs_opts mnt_opts[] = { + { MNT_NOSUID, ",nosuid" }, + { MNT_NODEV, ",nodev" }, + { MNT_NOEXEC, ",noexec" }, + { MNT_NOATIME, ",noatime" }, + { MNT_NODIRATIME, ",nodiratime" }, + { MNT_RELATIME, ",relatime" }, + { MNT_NOSYMFOLLOW, ",nosymfollow" }, + { 0, NULL } + }; + const struct proc_fs_opts *fs_infop; + + for (fs_infop = mnt_opts; fs_infop->flag; fs_infop++) { + if (mnt->mnt_flags & fs_infop->flag) + seq_puts(m, fs_infop->str); + } + + if (is_idmapped_mnt(mnt)) + seq_puts(m, ",idmapped"); +} + +static inline void mangle(struct seq_file *m, const char *s) +{ + seq_escape(m, s, " \t\n\\#"); +} + +static void show_type(struct seq_file *m, struct super_block *sb) +{ + mangle(m, sb->s_type->name); + if (sb->s_subtype) { + seq_putc(m, '.'); + mangle(m, sb->s_subtype); + } +} + +static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) +{ + struct proc_mounts *p = m->private; + struct mount *r = real_mount(mnt); + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + struct super_block *sb = mnt_path.dentry->d_sb; + int err; + + if (sb->s_op->show_devname) { + err = sb->s_op->show_devname(m, mnt_path.dentry); + if (err) + goto out; + } else { + mangle(m, r->mnt_devname); + } + seq_putc(m, ' '); + /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ + err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\"); + if (err) + goto out; + seq_putc(m, ' '); + show_type(m, sb); + seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw"); + err = show_sb_opts(m, sb); + if (err) + goto out; + show_vfsmnt_opts(m, mnt); + if (sb->s_op->show_options) + err = sb->s_op->show_options(m, mnt_path.dentry); + seq_puts(m, " 0 0\n"); +out: + return err; +} + +static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) +{ + struct proc_mounts *p = m->private; + struct mount *r = real_mount(mnt); + struct super_block *sb = mnt->mnt_sb; + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + int err; + + seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id, + MAJOR(sb->s_dev), MINOR(sb->s_dev)); + err = show_path(m, mnt->mnt_root); + if (err) + goto out; + seq_putc(m, ' '); + + /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ + err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\"); + if (err) + goto out; + + seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw"); + show_vfsmnt_opts(m, mnt); + + /* Tagged fields ("foo:X" or "bar") */ + if (IS_MNT_SHARED(r)) + seq_printf(m, " shared:%i", r->mnt_group_id); + if (IS_MNT_SLAVE(r)) { + int master = r->mnt_master->mnt_group_id; + int dom = get_dominating_id(r, &p->root); + seq_printf(m, " master:%i", master); + if (dom && dom != master) + seq_printf(m, " propagate_from:%i", dom); + } + if (IS_MNT_UNBINDABLE(r)) + seq_puts(m, " unbindable"); + + /* Filesystem specific data */ + seq_puts(m, " - "); + show_type(m, sb); + seq_putc(m, ' '); + if (sb->s_op->show_devname) { + err = sb->s_op->show_devname(m, mnt->mnt_root); + if (err) + goto out; + } else { + mangle(m, r->mnt_devname); + } + seq_puts(m, sb_rdonly(sb) ? " ro" : " rw"); + err = show_sb_opts(m, sb); + if (err) + goto out; + if (sb->s_op->show_options) + err = sb->s_op->show_options(m, mnt->mnt_root); + seq_putc(m, '\n'); +out: + return err; +} + +static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) +{ + struct proc_mounts *p = m->private; + struct mount *r = real_mount(mnt); + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + struct super_block *sb = mnt_path.dentry->d_sb; + int err; + + /* device */ + seq_puts(m, "device "); + if (sb->s_op->show_devname) { + err = sb->s_op->show_devname(m, mnt_path.dentry); + if (err) + goto out; + } else { + mangle(m, r->mnt_devname); + } + + /* mount point */ + seq_puts(m, " mounted on "); + /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ + err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\"); + if (err) + goto out; + seq_putc(m, ' '); + + /* file system type */ + seq_puts(m, "with fstype "); + show_type(m, sb); + + /* optional statistics */ + if (sb->s_op->show_stats) { + seq_putc(m, ' '); + err = sb->s_op->show_stats(m, mnt_path.dentry); + } + + seq_putc(m, '\n'); +out: + return err; +} + +static int mounts_open_common(struct inode *inode, struct file *file, + int (*show)(struct seq_file *, struct vfsmount *)) +{ + struct task_struct *task = get_proc_task(inode); + struct nsproxy *nsp; + struct mnt_namespace *ns = NULL; + struct path root; + struct proc_mounts *p; + struct seq_file *m; + int ret = -EINVAL; + + if (!task) + goto err; + + task_lock(task); + nsp = task->nsproxy; + if (!nsp || !nsp->mnt_ns) { + task_unlock(task); + put_task_struct(task); + goto err; + } + ns = nsp->mnt_ns; + get_mnt_ns(ns); + if (!task->real_fs) { + task_unlock(task); + put_task_struct(task); + ret = -ENOENT; + goto err_put_ns; + } + get_fs_root(task->real_fs, &root); + task_unlock(task); + put_task_struct(task); + + ret = seq_open_private(file, &mounts_op, sizeof(struct proc_mounts)); + if (ret) + goto err_put_path; + + m = file->private_data; + m->poll_event = ns->event; + + p = m->private; + p->ns = ns; + p->root = root; + p->show = show; + + return 0; + + err_put_path: + path_put(&root); + err_put_ns: + put_mnt_ns(ns); + err: + return ret; +} + +static int mounts_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct proc_mounts *p = m->private; + path_put(&p->root); + put_mnt_ns(p->ns); + return seq_release_private(inode, file); +} + +static int mounts_open(struct inode *inode, struct file *file) +{ + return mounts_open_common(inode, file, show_vfsmnt); +} + +static int mountinfo_open(struct inode *inode, struct file *file) +{ + return mounts_open_common(inode, file, show_mountinfo); +} + +static int mountstats_open(struct inode *inode, struct file *file) +{ + return mounts_open_common(inode, file, show_vfsstat); +} + +const struct file_operations proc_mounts_operations = { + .open = mounts_open, + .read_iter = seq_read_iter, + .splice_read = copy_splice_read, + .llseek = seq_lseek, + .release = mounts_release, + .poll = mounts_poll, +}; + +const struct file_operations proc_mountinfo_operations = { + .open = mountinfo_open, + .read_iter = seq_read_iter, + .splice_read = copy_splice_read, + .llseek = seq_lseek, + .release = mounts_release, + .poll = mounts_poll, +}; + +const struct file_operations proc_mountstats_operations = { + .open = mountstats_open, + .read_iter = seq_read_iter, + .splice_read = copy_splice_read, + .llseek = seq_lseek, + .release = mounts_release, +}; -- cgit v1.3.1