#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
+#include <linux/completion.h>
+#include <linux/poll.h>
#include <linux/file.h>
#include <linux/limits.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/smp_lock.h>
+#include <linux/sysctl.h>
#include <asm/system.h>
#include <asm/uaccess.h>
struct proc_dir_entry *de_get(struct proc_dir_entry *de)
{
- if (de)
- atomic_inc(&de->count);
+ atomic_inc(&de->count);
return de;
}
*/
void de_put(struct proc_dir_entry *de)
{
- if (de) {
- lock_kernel();
- if (!atomic_read(&de->count)) {
- printk("de_put: entry %s already free!\n", de->name);
- unlock_kernel();
- return;
- }
-
- if (atomic_dec_and_test(&de->count)) {
- if (de->deleted) {
- printk("de_put: deferred delete of %s\n",
- de->name);
- free_proc_entry(de);
- }
- }
- unlock_kernel();
+ if (!atomic_read(&de->count)) {
+ printk("de_put: entry %s already free!\n", de->name);
+ return;
}
+
+ if (atomic_dec_and_test(&de->count))
+ free_proc_entry(de);
}
/*
module_put(de->owner);
de_put(de);
}
+ if (PROC_I(inode)->sysctl)
+ sysctl_head_put(PROC_I(inode)->sysctl);
clear_inode(inode);
}
struct vfsmount *proc_mnt;
-static void proc_read_inode(struct inode * inode)
-{
- inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-}
-
static struct kmem_cache * proc_inode_cachep;
static struct inode *proc_alloc_inode(struct super_block *sb)
ei->fd = 0;
ei->op.proc_get_link = NULL;
ei->pde = NULL;
+ ei->sysctl = NULL;
+ ei->sysctl_entry = NULL;
inode = &ei->vfs_inode;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
return inode;
kmem_cache_free(proc_inode_cachep, PROC_I(inode));
}
-static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
+static void init_once(void *foo)
{
struct proc_inode *ei = (struct proc_inode *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
-
-int __init proc_init_inodecache(void)
+
+void __init proc_init_inodecache(void)
{
proc_inode_cachep = kmem_cache_create("proc_inode_cache",
sizeof(struct proc_inode),
0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD),
- init_once, NULL);
- if (proc_inode_cachep == NULL)
- return -ENOMEM;
- return 0;
-}
-
-static int proc_remount(struct super_block *sb, int *flags, char *data)
-{
- *flags |= MS_NODIRATIME;
- return 0;
+ SLAB_MEM_SPREAD|SLAB_PANIC),
+ init_once);
}
static const struct super_operations proc_sops = {
.alloc_inode = proc_alloc_inode,
.destroy_inode = proc_destroy_inode,
- .read_inode = proc_read_inode,
.drop_inode = generic_delete_inode,
.delete_inode = proc_delete_inode,
.statfs = simple_statfs,
- .remount_fs = proc_remount,
};
+static void __pde_users_dec(struct proc_dir_entry *pde)
+{
+ pde->pde_users--;
+ if (pde->pde_unload_completion && pde->pde_users == 0)
+ complete(pde->pde_unload_completion);
+}
+
+static void pde_users_dec(struct proc_dir_entry *pde)
+{
+ spin_lock(&pde->pde_unload_lock);
+ __pde_users_dec(pde);
+ spin_unlock(&pde->pde_unload_lock);
+}
+
+static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ loff_t rv = -EINVAL;
+ loff_t (*llseek)(struct file *, loff_t, int);
+
+ spin_lock(&pde->pde_unload_lock);
+ /*
+ * remove_proc_entry() is going to delete PDE (as part of module
+ * cleanup sequence). No new callers into module allowed.
+ */
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ /*
+ * Bump refcount so that remove_proc_entry will wail for ->llseek to
+ * complete.
+ */
+ pde->pde_users++;
+ /*
+ * Save function pointer under lock, to protect against ->proc_fops
+ * NULL'ifying right after ->pde_unload_lock is dropped.
+ */
+ llseek = pde->proc_fops->llseek;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (!llseek)
+ llseek = default_llseek;
+ rv = llseek(file, offset, whence);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+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->f_path.dentry->d_inode);
+ ssize_t rv = -EIO;
+ ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ read = pde->proc_fops->read;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (read)
+ rv = read(file, buf, count, ppos);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+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->f_path.dentry->d_inode);
+ ssize_t rv = -EIO;
+ ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ write = pde->proc_fops->write;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (write)
+ rv = write(file, buf, count, ppos);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ unsigned int rv = DEFAULT_POLLMASK;
+ unsigned int (*poll)(struct file *, struct poll_table_struct *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ poll = pde->proc_fops->poll;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (poll)
+ rv = poll(file, pts);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ long rv = -ENOTTY;
+ long (*unlocked_ioctl)(struct file *, unsigned int, unsigned long);
+ int (*ioctl)(struct inode *, struct file *, unsigned int, unsigned long);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ unlocked_ioctl = pde->proc_fops->unlocked_ioctl;
+ ioctl = pde->proc_fops->ioctl;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (unlocked_ioctl) {
+ rv = unlocked_ioctl(file, cmd, arg);
+ if (rv == -ENOIOCTLCMD)
+ rv = -EINVAL;
+ } else if (ioctl) {
+ lock_kernel();
+ rv = ioctl(file->f_path.dentry->d_inode, file, cmd, arg);
+ unlock_kernel();
+ }
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+#ifdef CONFIG_COMPAT
+static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ long rv = -ENOTTY;
+ long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ compat_ioctl = pde->proc_fops->compat_ioctl;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (compat_ioctl)
+ rv = compat_ioctl(file, cmd, arg);
+
+ pde_users_dec(pde);
+ return rv;
+}
+#endif
+
+static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ int rv = -EIO;
+ int (*mmap)(struct file *, struct vm_area_struct *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ mmap = pde->proc_fops->mmap;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (mmap)
+ rv = mmap(file, vma);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static int proc_reg_open(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *pde = PDE(inode);
+ int rv = 0;
+ int (*open)(struct inode *, struct file *);
+ int (*release)(struct inode *, struct file *);
+ struct pde_opener *pdeo;
+
+ /*
+ * What for, you ask? Well, we can have open, rmmod, remove_proc_entry
+ * sequence. ->release won't be called because ->proc_fops will be
+ * cleared. Depending on complexity of ->release, consequences vary.
+ *
+ * We can't wait for mercy when close will be done for real, it's
+ * deadlockable: rmmod foo </proc/foo . So, we're going to do ->release
+ * by hand in remove_proc_entry(). For this, save opener's credentials
+ * for later.
+ */
+ pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL);
+ if (!pdeo)
+ return -ENOMEM;
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ kfree(pdeo);
+ return -EINVAL;
+ }
+ pde->pde_users++;
+ open = pde->proc_fops->open;
+ release = pde->proc_fops->release;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (open)
+ rv = open(inode, file);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (rv == 0 && release) {
+ /* To know what to release. */
+ pdeo->inode = inode;
+ pdeo->file = file;
+ /* Strictly for "too late" ->release in proc_reg_release(). */
+ pdeo->release = release;
+ list_add(&pdeo->lh, &pde->pde_openers);
+ } else
+ kfree(pdeo);
+ __pde_users_dec(pde);
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+}
+
+static struct pde_opener *find_pde_opener(struct proc_dir_entry *pde,
+ struct inode *inode, struct file *file)
+{
+ struct pde_opener *pdeo;
+
+ list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+ if (pdeo->inode == inode && pdeo->file == file)
+ return pdeo;
+ }
+ return NULL;
+}
+
+static int proc_reg_release(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *pde = PDE(inode);
+ int rv = 0;
+ int (*release)(struct inode *, struct file *);
+ struct pde_opener *pdeo;
+
+ spin_lock(&pde->pde_unload_lock);
+ pdeo = find_pde_opener(pde, inode, file);
+ if (!pde->proc_fops) {
+ /*
+ * Can't simply exit, __fput() will think that everything is OK,
+ * and move on to freeing struct file. remove_proc_entry() will
+ * find slacker in opener's list and will try to do non-trivial
+ * things with struct file. Therefore, remove opener from list.
+ *
+ * But if opener is removed from list, who will ->release it?
+ */
+ if (pdeo) {
+ list_del(&pdeo->lh);
+ spin_unlock(&pde->pde_unload_lock);
+ rv = pdeo->release(inode, file);
+ kfree(pdeo);
+ } else
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ release = pde->proc_fops->release;
+ if (pdeo) {
+ list_del(&pdeo->lh);
+ kfree(pdeo);
+ }
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (release)
+ rv = release(inode, file);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+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,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = proc_reg_compat_ioctl,
+#endif
+ .mmap = proc_reg_mmap,
+ .open = proc_reg_open,
+ .release = proc_reg_release,
+};
+
+#ifdef CONFIG_COMPAT
+static const struct file_operations proc_reg_file_ops_no_compat = {
+ .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,
+ .open = proc_reg_open,
+ .release = proc_reg_release,
+};
+#endif
+
struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
struct proc_dir_entry *de)
{
struct inode * inode;
- if (de != NULL && !try_module_get(de->owner))
+ if (!try_module_get(de->owner))
goto out_mod;
- inode = iget(sb, ino);
+ inode = iget_locked(sb, ino);
if (!inode)
goto out_ino;
+ if (inode->i_state & I_NEW) {
+ inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ PROC_I(inode)->fd = 0;
+ PROC_I(inode)->pde = de;
- PROC_I(inode)->fd = 0;
- PROC_I(inode)->pde = de;
- if (de) {
if (de->mode) {
inode->i_mode = de->mode;
inode->i_uid = de->uid;
inode->i_nlink = de->nlink;
if (de->proc_iops)
inode->i_op = de->proc_iops;
- if (de->proc_fops)
- inode->i_fop = de->proc_fops;
+ if (de->proc_fops) {
+ if (S_ISREG(inode->i_mode)) {
+#ifdef CONFIG_COMPAT
+ if (!de->proc_fops->compat_ioctl)
+ inode->i_fop =
+ &proc_reg_file_ops_no_compat;
+ else
+#endif
+ inode->i_fop = &proc_reg_file_ops;
+ } else {
+ inode->i_fop = de->proc_fops;
+ }
+ }
+ unlock_new_inode(inode);
+ } else {
+ module_put(de->owner);
+ de_put(de);
}
-
return inode;
out_ino:
- if (de != NULL)
- module_put(de->owner);
+ module_put(de->owner);
out_mod:
return NULL;
}
-int proc_fill_super(struct super_block *s, void *data, int silent)
+int proc_fill_super(struct super_block *s)
{
struct inode * root_inode;
de_put(&proc_root);
return -ENOMEM;
}
-MODULE_LICENSE("GPL");