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/inode.c | 680 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 680 insertions(+) create mode 100644 fs/proc/inode.c (limited to 'fs/proc/inode.c') diff --git a/fs/proc/inode.c b/fs/proc/inode.c new file mode 100644 index 000000000..b7634f975 --- /dev/null +++ b/fs/proc/inode.c @@ -0,0 +1,680 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/proc/inode.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +static void proc_evict_inode(struct inode *inode) +{ + struct ctl_table_header *head; + struct proc_inode *ei = PROC_I(inode); + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); + + /* Stop tracking associated processes */ + if (ei->pid) + proc_pid_evict_inode(ei); + + head = ei->sysctl; + if (head) { + WRITE_ONCE(ei->sysctl, NULL); + proc_sys_evict_inode(inode, head); + } +} + +static struct kmem_cache *proc_inode_cachep __ro_after_init; +static struct kmem_cache *pde_opener_cache __ro_after_init; + +static struct inode *proc_alloc_inode(struct super_block *sb) +{ + struct proc_inode *ei; + + ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL); + if (!ei) + return NULL; + ei->pid = NULL; + ei->fd = 0; + ei->op.proc_get_link = NULL; + ei->pde = NULL; + ei->sysctl = NULL; + ei->sysctl_entry = NULL; + INIT_HLIST_NODE(&ei->sibling_inodes); + ei->ns_ops = NULL; + return &ei->vfs_inode; +} + +static void proc_free_inode(struct inode *inode) +{ + struct proc_inode *ei = PROC_I(inode); + + if (ei->pid) + put_pid(ei->pid); + /* Let go of any associated proc directory entry */ + if (ei->pde) + pde_put(ei->pde); + kmem_cache_free(proc_inode_cachep, PROC_I(inode)); +} + +static void init_once(void *foo) +{ + struct proc_inode *ei = (struct proc_inode *) foo; + + inode_init_once(&ei->vfs_inode); +} + +void __init proc_init_kmemcache(void) +{ + proc_inode_cachep = kmem_cache_create("proc_inode_cache", + sizeof(struct proc_inode), + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_ACCOUNT| + SLAB_PANIC), + init_once); + pde_opener_cache = + kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0, + SLAB_ACCOUNT|SLAB_PANIC, NULL); + proc_dir_entry_cache = kmem_cache_create_usercopy( + "proc_dir_entry", SIZEOF_PDE, 0, SLAB_PANIC, + offsetof(struct proc_dir_entry, inline_name), + SIZEOF_PDE_INLINE_NAME, NULL); + BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE); +} + +void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock) +{ + struct hlist_node *node; + struct super_block *old_sb = NULL; + + rcu_read_lock(); + while ((node = hlist_first_rcu(inodes))) { + struct proc_inode *ei = hlist_entry(node, struct proc_inode, sibling_inodes); + struct super_block *sb; + struct inode *inode; + + spin_lock(lock); + hlist_del_init_rcu(&ei->sibling_inodes); + spin_unlock(lock); + + inode = &ei->vfs_inode; + sb = inode->i_sb; + if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active)) + continue; + inode = igrab(inode); + rcu_read_unlock(); + if (sb != old_sb) { + if (old_sb) + deactivate_super(old_sb); + old_sb = sb; + } + if (unlikely(!inode)) { + rcu_read_lock(); + continue; + } + + if (S_ISDIR(inode->i_mode)) { + struct dentry *dir = d_find_any_alias(inode); + if (dir) { + d_invalidate(dir); + dput(dir); + } + } else { + struct dentry *dentry; + while ((dentry = d_find_alias(inode))) { + d_invalidate(dentry); + dput(dentry); + } + } + iput(inode); + + rcu_read_lock(); + } + rcu_read_unlock(); + if (old_sb) + deactivate_super(old_sb); +} + +static inline const char *hidepid2str(enum proc_hidepid v) +{ + switch (v) { + case HIDEPID_OFF: return "off"; + case HIDEPID_NO_ACCESS: return "noaccess"; + case HIDEPID_INVISIBLE: return "invisible"; + case HIDEPID_NOT_PTRACEABLE: return "ptraceable"; + } + WARN_ONCE(1, "bad hide_pid value: %d\n", v); + return "unknown"; +} + +static int proc_show_options(struct seq_file *seq, struct dentry *root) +{ + struct proc_fs_info *fs_info = proc_sb_info(root->d_sb); + + if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid)); + if (fs_info->hide_pid != HIDEPID_OFF) + seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid)); + if (fs_info->pidonly != PROC_PIDONLY_OFF) + seq_printf(seq, ",subset=pid"); + + return 0; +} + +const struct super_operations proc_sops = { + .alloc_inode = proc_alloc_inode, + .free_inode = proc_free_inode, + .drop_inode = inode_just_drop, + .evict_inode = proc_evict_inode, + .statfs = simple_statfs, + .show_options = proc_show_options, +}; + +enum {BIAS = -1U<<31}; + +static inline int use_pde(struct proc_dir_entry *pde) +{ + return likely(atomic_inc_unless_negative(&pde->in_use)); +} + +static void unuse_pde(struct proc_dir_entry *pde) +{ + if (unlikely(atomic_dec_return(&pde->in_use) == BIAS)) + complete(pde->pde_unload_completion); +} + +/* + * At most 2 contexts can enter this function: the one doing the last + * close on the descriptor and whoever is deleting PDE itself. + * + * First to enter calls ->proc_release hook and signals its completion + * to the second one which waits and then does nothing. + * + * PDE is locked on entry, unlocked on exit. + */ +static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) + __releases(&pde->pde_unload_lock) +{ + /* + * close() (proc_reg_release()) can't delete an entry and proceed: + * ->release hook needs to be available at the right moment. + * + * rmmod (remove_proc_entry() et al) can't delete an entry and proceed: + * "struct file" needs to be available at the right moment. + */ + if (pdeo->closing) { + /* somebody else is doing that, just wait */ + DECLARE_COMPLETION_ONSTACK(c); + pdeo->c = &c; + spin_unlock(&pde->pde_unload_lock); + wait_for_completion(&c); + } else { + struct file *file; + struct completion *c; + + pdeo->closing = true; + spin_unlock(&pde->pde_unload_lock); + + file = pdeo->file; + pde->proc_ops->proc_release(file_inode(file), file); + + spin_lock(&pde->pde_unload_lock); + /* Strictly after ->proc_release, see above. */ + list_del(&pdeo->lh); + c = pdeo->c; + spin_unlock(&pde->pde_unload_lock); + if (unlikely(c)) + complete(c); + kmem_cache_free(pde_opener_cache, pdeo); + } +} + +void proc_entry_rundown(struct proc_dir_entry *de) +{ + DECLARE_COMPLETION_ONSTACK(c); + /* Wait until all existing callers into module are done. */ + de->pde_unload_completion = &c; + if (atomic_add_return(BIAS, &de->in_use) != BIAS) + wait_for_completion(&c); + + /* ->pde_openers list can't grow from now on. */ + + spin_lock(&de->pde_unload_lock); + while (!list_empty(&de->pde_openers)) { + struct pde_opener *pdeo; + pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh); + close_pdeo(de, pdeo); + spin_lock(&de->pde_unload_lock); + } + spin_unlock(&de->pde_unload_lock); +} + +static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + loff_t rv = -EINVAL; + + if (pde_is_permanent(pde)) { + return pde->proc_ops->proc_lseek(file, offset, whence); + } else if (use_pde(pde)) { + rv = pde->proc_ops->proc_lseek(file, offset, whence); + unuse_pde(pde); + } + return rv; +} + +static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp)); + ssize_t ret; + + if (pde_is_permanent(pde)) + return pde->proc_ops->proc_read_iter(iocb, iter); + + if (!use_pde(pde)) + return -EIO; + ret = pde->proc_ops->proc_read_iter(iocb, iter); + unuse_pde(pde); + return ret; +} + +static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + const auto read = pde->proc_ops->proc_read; + if (read) + return read(file, buf, count, ppos); + return -EIO; +} + +static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + ssize_t rv = -EIO; + + if (pde_is_permanent(pde)) { + return pde_read(pde, file, buf, count, ppos); + } else if (use_pde(pde)) { + rv = pde_read(pde, file, buf, count, ppos); + unuse_pde(pde); + } + return rv; +} + +static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + const auto write = pde->proc_ops->proc_write; + if (write) + return write(file, buf, count, ppos); + return -EIO; +} + +static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + ssize_t rv = -EIO; + + if (pde_is_permanent(pde)) { + return pde_write(pde, file, buf, count, ppos); + } else if (use_pde(pde)) { + rv = pde_write(pde, file, buf, count, ppos); + unuse_pde(pde); + } + return rv; +} + +static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts) +{ + const auto poll = pde->proc_ops->proc_poll; + if (poll) + return poll(file, pts); + return DEFAULT_POLLMASK; +} + +static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + __poll_t rv = DEFAULT_POLLMASK; + + if (pde_is_permanent(pde)) { + return pde_poll(pde, file, pts); + } else if (use_pde(pde)) { + rv = pde_poll(pde, file, pts); + unuse_pde(pde); + } + return rv; +} + +static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) +{ + const auto ioctl = pde->proc_ops->proc_ioctl; + if (ioctl) + return ioctl(file, cmd, arg); + return -ENOTTY; +} + +static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + long rv = -ENOTTY; + + if (pde_is_permanent(pde)) { + return pde_ioctl(pde, file, cmd, arg); + } else if (use_pde(pde)) { + rv = pde_ioctl(pde, file, cmd, arg); + unuse_pde(pde); + } + return rv; +} + +#ifdef CONFIG_COMPAT +static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) +{ + const auto compat_ioctl = pde->proc_ops->proc_compat_ioctl; + if (compat_ioctl) + return compat_ioctl(file, cmd, arg); + return -ENOTTY; +} + +static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + long rv = -ENOTTY; + if (pde_is_permanent(pde)) { + return pde_compat_ioctl(pde, file, cmd, arg); + } else if (use_pde(pde)) { + rv = pde_compat_ioctl(pde, file, cmd, arg); + unuse_pde(pde); + } + return rv; +} +#endif + +static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma) +{ + const auto mmap = pde->proc_ops->proc_mmap; + if (mmap) + return mmap(file, vma); + return -EIO; +} + +static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + int rv = -EIO; + + if (pde_is_permanent(pde)) { + return pde_mmap(pde, file, vma); + } else if (use_pde(pde)) { + rv = pde_mmap(pde, file, vma); + unuse_pde(pde); + } + return rv; +} + +static unsigned long +pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + if (pde->proc_ops->proc_get_unmapped_area) + return pde->proc_ops->proc_get_unmapped_area(file, orig_addr, len, pgoff, flags); + +#ifdef CONFIG_MMU + return mm_get_unmapped_area(file, orig_addr, len, pgoff, flags); +#endif + + return orig_addr; +} + +static unsigned long +proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + unsigned long rv = -EIO; + + if (pde_is_permanent(pde)) { + return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); + } else if (use_pde(pde)) { + rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); + unuse_pde(pde); + } + return rv; +} + +static int proc_reg_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *pde = PDE(inode); + int rv = 0; + typeof_member(struct proc_ops, proc_open) open; + struct pde_opener *pdeo; + + if (!pde_has_proc_lseek(pde)) + file->f_mode &= ~FMODE_LSEEK; + + if (pde_is_permanent(pde)) { + open = pde->proc_ops->proc_open; + if (open) + rv = open(inode, file); + return rv; + } + + /* + * Ensure that + * 1) PDE's ->release hook will be called no matter what + * either normally by close()/->release, or forcefully by + * rmmod/remove_proc_entry. + * + * 2) rmmod isn't blocked by opening file in /proc and sitting on + * the descriptor (including "rmmod foo release hook. + */ + if (!use_pde(pde)) + return -ENOENT; + + const auto release = pde->proc_ops->proc_release; + if (release) { + pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); + if (!pdeo) { + rv = -ENOMEM; + goto out_unuse; + } + } + + open = pde->proc_ops->proc_open; + if (open) + rv = open(inode, file); + + if (release) { + if (rv == 0) { + /* To know what to release. */ + pdeo->file = file; + pdeo->closing = false; + pdeo->c = NULL; + spin_lock(&pde->pde_unload_lock); + list_add(&pdeo->lh, &pde->pde_openers); + spin_unlock(&pde->pde_unload_lock); + } else + kmem_cache_free(pde_opener_cache, pdeo); + } + +out_unuse: + unuse_pde(pde); + return rv; +} + +static int proc_reg_release(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *pde = PDE(inode); + struct pde_opener *pdeo; + + if (pde_is_permanent(pde)) { + const auto release = pde->proc_ops->proc_release; + if (release) + return release(inode, file); + return 0; + } + + spin_lock(&pde->pde_unload_lock); + list_for_each_entry(pdeo, &pde->pde_openers, lh) { + if (pdeo->file == file) { + close_pdeo(pde, pdeo); + return 0; + } + } + spin_unlock(&pde->pde_unload_lock); + return 0; +} + +static const struct file_operations proc_reg_file_ops = { + .llseek = proc_reg_llseek, + .read = proc_reg_read, + .write = proc_reg_write, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, + .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, + .open = proc_reg_open, + .release = proc_reg_release, +}; + +static const struct file_operations proc_iter_file_ops = { + .llseek = proc_reg_llseek, + .read_iter = proc_reg_read_iter, + .write = proc_reg_write, + .splice_read = copy_splice_read, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, + .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, + .open = proc_reg_open, + .release = proc_reg_release, +}; + +#ifdef CONFIG_COMPAT +static const struct file_operations proc_reg_file_ops_compat = { + .llseek = proc_reg_llseek, + .read = proc_reg_read, + .write = proc_reg_write, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, + .compat_ioctl = proc_reg_compat_ioctl, + .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, + .open = proc_reg_open, + .release = proc_reg_release, +}; + +static const struct file_operations proc_iter_file_ops_compat = { + .llseek = proc_reg_llseek, + .read_iter = proc_reg_read_iter, + .splice_read = copy_splice_read, + .write = proc_reg_write, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, + .compat_ioctl = proc_reg_compat_ioctl, + .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, + .open = proc_reg_open, + .release = proc_reg_release, +}; +#endif + +static void proc_put_link(void *p) +{ + unuse_pde(p); +} + +static const char *proc_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) +{ + struct proc_dir_entry *pde = PDE(inode); + if (!use_pde(pde)) + return ERR_PTR(-EINVAL); + set_delayed_call(done, proc_put_link, pde); + return pde->data; +} + +const struct inode_operations proc_link_inode_operations = { + .get_link = proc_get_link, +}; + +struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) +{ + struct inode *inode = new_inode(sb); + + if (!inode) { + pde_put(de); + return NULL; + } + + inode->i_private = de->data; + inode->i_ino = de->low_ino; + simple_inode_init_ts(inode); + PROC_I(inode)->pde = de; + if (is_empty_pde(de)) { + make_empty_dir_inode(inode); + return inode; + } + + if (de->mode) { + inode->i_mode = de->mode; + inode->i_uid = de->uid; + inode->i_gid = de->gid; + } + if (de->size) + inode->i_size = de->size; + if (de->nlink) + set_nlink(inode, de->nlink); + + if (S_ISREG(inode->i_mode)) { + inode->i_op = de->proc_iops; + if (pde_has_proc_read_iter(de)) + inode->i_fop = &proc_iter_file_ops; + else + inode->i_fop = &proc_reg_file_ops; +#ifdef CONFIG_COMPAT + if (pde_has_proc_compat_ioctl(de)) { + if (pde_has_proc_read_iter(de)) + inode->i_fop = &proc_iter_file_ops_compat; + else + inode->i_fop = &proc_reg_file_ops_compat; + } +#endif + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = de->proc_dir_ops; + } else if (S_ISLNK(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = NULL; + } else { + BUG(); + } + return inode; +} -- cgit v1.3.1