1 files changed, 369 insertions, 125 deletions

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 6573f31f1fd..0adbc02d60e 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -7,164 +7,409 @@
 #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/smp_lock.h>
+#include <linux/sysctl.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/magic.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
 
-static inline struct proc_dir_entry * de_get(struct proc_dir_entry *de)
-{
-	if (de)
-		atomic_inc(&de->count);
-	return de;
-}
-
-/*
- * Decrements the use count and checks for deferred deletion.
- */
-static 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();
-	}
-}
-
-/*
- * Decrement the use count of the proc_dir_entry.
- */
-static void proc_delete_inode(struct inode *inode)
+static void proc_evict_inode(struct inode *inode)
 {
 	struct proc_dir_entry *de;
-	struct task_struct *tsk;
+	struct ctl_table_header *head;
+	const struct proc_ns_operations *ns_ops;
+	void *ns;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
 
-	/* Let go of any associated process */
-	tsk = PROC_I(inode)->task;
-	if (tsk)
-		put_task_struct(tsk);
+	/* Stop tracking associated processes */
+	put_pid(PROC_I(inode)->pid);
 
 	/* Let go of any associated proc directory entry */
 	de = PROC_I(inode)->pde;
-	if (de) {
-		if (de->owner)
-			module_put(de->owner);
-		de_put(de);
+	if (de)
+		pde_put(de);
+	head = PROC_I(inode)->sysctl;
+	if (head) {
+		RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL);
+		sysctl_head_put(head);
 	}
-	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;
+	/* Release any associated namespace */
+	ns_ops = PROC_I(inode)->ns.ns_ops;
+	ns = PROC_I(inode)->ns.ns;
+	if (ns_ops && ns)
+		ns_ops->put(ns);
 }
 
-static kmem_cache_t * proc_inode_cachep;
+static struct kmem_cache * proc_inode_cachep;
 
 static struct inode *proc_alloc_inode(struct super_block *sb)
 {
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, SLAB_KERNEL);
+	ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
-	ei->task = NULL;
-	ei->type = 0;
+	ei->pid = NULL;
+	ei->fd = 0;
 	ei->op.proc_get_link = NULL;
 	ei->pde = NULL;
+	ei->sysctl = NULL;
+	ei->sysctl_entry = NULL;
+	ei->ns.ns = NULL;
+	ei->ns.ns_ops = NULL;
 	inode = &ei->vfs_inode;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	return inode;
 }
 
-static void proc_destroy_inode(struct inode *inode)
+static void proc_i_callback(struct rcu_head *head)
 {
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
 }
 
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static void proc_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, proc_i_callback);
+}
+
+static void init_once(void *foo)
 {
 	struct proc_inode *ei = (struct proc_inode *) foo;
 
-	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
-	    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,
-					     init_once, NULL);
-	if (proc_inode_cachep == NULL)
-		return -ENOMEM;
-	return 0;
+					     0, (SLAB_RECLAIM_ACCOUNT|
+						SLAB_MEM_SPREAD|SLAB_PANIC),
+					     init_once);
 }
 
-static int proc_remount(struct super_block *sb, int *flags, char *data)
+static int proc_show_options(struct seq_file *seq, struct dentry *root)
 {
-	*flags |= MS_NODIRATIME;
+	struct super_block *sb = root->d_sb;
+	struct pid_namespace *pid = sb->s_fs_info;
+
+	if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
+		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
+	if (pid->hide_pid != 0)
+		seq_printf(seq, ",hidepid=%u", pid->hide_pid);
+
 	return 0;
 }
 
-static struct super_operations proc_sops = { 
+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,
+	.evict_inode	= proc_evict_inode,
 	.statfs		= simple_statfs,
 	.remount_fs	= proc_remount,
+	.show_options	= proc_show_options,
 };
 
-struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
-				struct proc_dir_entry *de)
+enum {BIAS = -1U<<31};
+
+static inline int use_pde(struct proc_dir_entry *pde)
+{
+	return atomic_inc_unless_negative(&pde->in_use);
+}
+
+static void unuse_pde(struct proc_dir_entry *pde)
+{
+	if (atomic_dec_return(&pde->in_use) == BIAS)
+		complete(pde->pde_unload_completion);
+}
+
+/* pde is locked */
+static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
+{
+	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);
+		spin_lock(&pde->pde_unload_lock);
+	} else {
+		struct file *file;
+		pdeo->closing = 1;
+		spin_unlock(&pde->pde_unload_lock);
+		file = pdeo->file;
+		pde->proc_fops->release(file_inode(file), file);
+		spin_lock(&pde->pde_unload_lock);
+		list_del_init(&pdeo->lh);
+		if (pdeo->c)
+			complete(pdeo->c);
+		kfree(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);
+
+	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_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 (use_pde(pde)) {
+		loff_t (*llseek)(struct file *, loff_t, int);
+		llseek = pde->proc_fops->llseek;
+		if (!llseek)
+			llseek = default_llseek;
+		rv = llseek(file, offset, whence);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+	if (use_pde(pde)) {
+		read = pde->proc_fops->read;
+		if (read)
+			rv = read(file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+	if (use_pde(pde)) {
+		write = pde->proc_fops->write;
+		if (write)
+			rv = write(file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
 {
-	struct inode * inode;
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	unsigned int rv = DEFAULT_POLLMASK;
+	unsigned int (*poll)(struct file *, struct poll_table_struct *);
+	if (use_pde(pde)) {
+		poll = pde->proc_fops->poll;
+		if (poll)
+			rv = poll(file, pts);
+		unuse_pde(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_inode(file));
+	long rv = -ENOTTY;
+	long (*ioctl)(struct file *, unsigned int, unsigned long);
+	if (use_pde(pde)) {
+		ioctl = pde->proc_fops->unlocked_ioctl;
+		if (ioctl)
+			rv = ioctl(file, cmd, arg);
+		unuse_pde(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_inode(file));
+	long rv = -ENOTTY;
+	long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
+	if (use_pde(pde)) {
+		compat_ioctl = pde->proc_fops->compat_ioctl;
+		if (compat_ioctl)
+			rv = compat_ioctl(file, cmd, arg);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+#endif
+
+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;
+	int (*mmap)(struct file *, struct vm_area_struct *);
+	if (use_pde(pde)) {
+		mmap = pde->proc_fops->mmap;
+		if (mmap)
+			rv = mmap(file, vma);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+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 (use_pde(pde)) {
+		typeof(proc_reg_get_unmapped_area) *get_area;
+
+		get_area = pde->proc_fops->get_unmapped_area;
+#ifdef CONFIG_MMU
+		if (!get_area)
+			get_area = current->mm->get_unmapped_area;
+#endif
+
+		if (get_area)
+			rv = get_area(file, orig_addr, len, pgoff, flags);
+		else
+			rv = orig_addr;
+		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;
+	int (*open)(struct inode *, struct file *);
+	int (*release)(struct inode *, struct file *);
+	struct pde_opener *pdeo;
 
 	/*
-	 * Increment the use count so the dir entry can't disappear.
+	 * 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.
 	 */
-	de_get(de);
+	pdeo = kzalloc(sizeof(struct pde_opener), GFP_KERNEL);
+	if (!pdeo)
+		return -ENOMEM;
 
-	WARN_ON(de && de->deleted);
+	if (!use_pde(pde)) {
+		kfree(pdeo);
+		return -ENOENT;
+	}
+	open = pde->proc_fops->open;
+	release = pde->proc_fops->release;
 
-	if (de != NULL && !try_module_get(de->owner))
-		goto out_mod;
+	if (open)
+		rv = open(inode, file);
 
-	inode = iget(sb, ino);
-	if (!inode)
-		goto out_ino;
+	if (rv == 0 && release) {
+		/* To know what to release. */
+		pdeo->file = file;
+		/* Strictly for "too late" ->release in proc_reg_release(). */
+		spin_lock(&pde->pde_unload_lock);
+		list_add(&pdeo->lh, &pde->pde_openers);
+		spin_unlock(&pde->pde_unload_lock);
+	} else
+		kfree(pdeo);
+
+	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;
+	spin_lock(&pde->pde_unload_lock);
+	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+		if (pdeo->file == file) {
+			close_pdeo(pde, pdeo);
+			break;
+		}
+	}
+	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,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= proc_reg_compat_ioctl,
+#endif
+	.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_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,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+#endif
+
+struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
+{
+	struct inode *inode = new_inode_pseudo(sb);
+
+	if (inode) {
+		inode->i_ino = de->low_ino;
+		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		PROC_I(inode)->pde = de;
 
-	PROC_I(inode)->pde = de;
-	if (de) {
 		if (de->mode) {
 			inode->i_mode = de->mode;
 			inode->i_uid = de->uid;
@@ -173,51 +418,50 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
 		if (de->size)
 			inode->i_size = de->size;
 		if (de->nlink)
-			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;
-	}
-
+			set_nlink(inode, de->nlink);
+		WARN_ON(!de->proc_iops);
+		inode->i_op = de->proc_iops;
+		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;
+			}
+		}
+	} else
+	       pde_put(de);
 	return inode;
+}
 
-out_ino:
-	if (de != NULL)
-		module_put(de->owner);
-out_mod:
-	de_put(de);
-	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;
+	struct inode *root_inode;
 
-	s->s_flags |= MS_NODIRATIME;
+	s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
 	s->s_blocksize = 1024;
 	s->s_blocksize_bits = 10;
 	s->s_magic = PROC_SUPER_MAGIC;
 	s->s_op = &proc_sops;
 	s->s_time_gran = 1;
 	
-	root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root);
-	if (!root_inode)
-		goto out_no_root;
-	/*
-	 * Fixup the root inode's nlink value
-	 */
-	root_inode->i_nlink += nr_processes();
-	root_inode->i_uid = 0;
-	root_inode->i_gid = 0;
-	s->s_root = d_alloc_root(root_inode);
-	if (!s->s_root)
-		goto out_no_root;
-	return 0;
+	pde_get(&proc_root);
+	root_inode = proc_get_inode(s, &proc_root);
+	if (!root_inode) {
+		pr_err("proc_fill_super: get root inode failed\n");
+		return -ENOMEM;
+	}
+
+	s->s_root = d_make_root(root_inode);
+	if (!s->s_root) {
+		pr_err("proc_fill_super: allocate dentry failed\n");
+		return -ENOMEM;
+	}
 
-out_no_root:
-	printk("proc_read_super: get root inode failed\n");
-	iput(root_inode);
-	return -ENOMEM;
+	return proc_setup_self(s);
 }
-MODULE_LICENSE("GPL");