From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- 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