Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681// SPDX-License-Identifier: GPL-2.0/* * linux/fs/proc/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds */
#include <linux/cache.h>#include <linux/time.h>#include <linux/proc_fs.h>#include <linux/kernel.h>#include <linux/pid_namespace.h>#include <linux/mm.h>#include <linux/string.h>#include <linux/stat.h>#include <linux/completion.h>#include <linux/poll.h>#include <linux/printk.h>#include <linux/file.h>#include <linux/limits.h>#include <linux/init.h>#include <linux/module.h>#include <linux/sysctl.h>#include <linux/seq_file.h>#include <linux/slab.h>#include <linux/mount.h>#include <linux/bug.h>
#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_COMPATstatic 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 longpde_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 longproc_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 </proc/foo" scenario). * * Save every "struct file" with custom ->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_COMPATstatic 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;}