1 files changed, 280 insertions, 470 deletions

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index a36ad3c75cf..b7f268eb5f4 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -12,9 +12,11 @@
 #include <linux/time.h>
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
+#include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/printk.h>
 #include <linux/mount.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/idr.h>
 #include <linux/namei.h>
@@ -27,206 +29,13 @@
 
 DEFINE_SPINLOCK(proc_subdir_lock);
 
-static int proc_match(int len, const char *name, struct proc_dir_entry *de)
+static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
 {
 	if (de->namelen != len)
 		return 0;
 	return !memcmp(name, de->name, len);
 }
 
-/* buffer size is one page but our output routines use some slack for overruns */
-#define PROC_BLOCK_SIZE	(PAGE_SIZE - 1024)
-
-static ssize_t
-proc_file_read(struct file *file, char __user *buf, size_t nbytes,
-	       loff_t *ppos)
-{
-	struct inode * inode = file->f_path.dentry->d_inode;
-	char 	*page;
-	ssize_t	retval=0;
-	int	eof=0;
-	ssize_t	n, count;
-	char	*start;
-	struct proc_dir_entry * dp;
-	unsigned long long pos;
-
-	/*
-	 * Gaah, please just use "seq_file" instead. The legacy /proc
-	 * interfaces cut loff_t down to off_t for reads, and ignore
-	 * the offset entirely for writes..
-	 */
-	pos = *ppos;
-	if (pos > MAX_NON_LFS)
-		return 0;
-	if (nbytes > MAX_NON_LFS - pos)
-		nbytes = MAX_NON_LFS - pos;
-
-	dp = PDE(inode);
-	if (!(page = (char*) __get_free_page(GFP_TEMPORARY)))
-		return -ENOMEM;
-
-	while ((nbytes > 0) && !eof) {
-		count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);
-
-		start = NULL;
-		if (dp->get_info) {
-			/* Handle old net routines */
-			n = dp->get_info(page, &start, *ppos, count);
-			if (n < count)
-				eof = 1;
-		} else if (dp->read_proc) {
-			/*
-			 * How to be a proc read function
-			 * ------------------------------
-			 * Prototype:
-			 *    int f(char *buffer, char **start, off_t offset,
-			 *          int count, int *peof, void *dat)
-			 *
-			 * Assume that the buffer is "count" bytes in size.
-			 *
-			 * If you know you have supplied all the data you
-			 * have, set *peof.
-			 *
-			 * You have three ways to return data:
-			 * 0) Leave *start = NULL.  (This is the default.)
-			 *    Put the data of the requested offset at that
-			 *    offset within the buffer.  Return the number (n)
-			 *    of bytes there are from the beginning of the
-			 *    buffer up to the last byte of data.  If the
-			 *    number of supplied bytes (= n - offset) is 
-			 *    greater than zero and you didn't signal eof
-			 *    and the reader is prepared to take more data
-			 *    you will be called again with the requested
-			 *    offset advanced by the number of bytes 
-			 *    absorbed.  This interface is useful for files
-			 *    no larger than the buffer.
-			 * 1) Set *start = an unsigned long value less than
-			 *    the buffer address but greater than zero.
-			 *    Put the data of the requested offset at the
-			 *    beginning of the buffer.  Return the number of
-			 *    bytes of data placed there.  If this number is
-			 *    greater than zero and you didn't signal eof
-			 *    and the reader is prepared to take more data
-			 *    you will be called again with the requested
-			 *    offset advanced by *start.  This interface is
-			 *    useful when you have a large file consisting
-			 *    of a series of blocks which you want to count
-			 *    and return as wholes.
-			 *    (Hack by Paul.Russell@rustcorp.com.au)
-			 * 2) Set *start = an address within the buffer.
-			 *    Put the data of the requested offset at *start.
-			 *    Return the number of bytes of data placed there.
-			 *    If this number is greater than zero and you
-			 *    didn't signal eof and the reader is prepared to
-			 *    take more data you will be called again with the
-			 *    requested offset advanced by the number of bytes
-			 *    absorbed.
-			 */
-			n = dp->read_proc(page, &start, *ppos,
-					  count, &eof, dp->data);
-		} else
-			break;
-
-		if (n == 0)   /* end of file */
-			break;
-		if (n < 0) {  /* error */
-			if (retval == 0)
-				retval = n;
-			break;
-		}
-
-		if (start == NULL) {
-			if (n > PAGE_SIZE) {
-				printk(KERN_ERR
-				       "proc_file_read: Apparent buffer overflow!\n");
-				n = PAGE_SIZE;
-			}
-			n -= *ppos;
-			if (n <= 0)
-				break;
-			if (n > count)
-				n = count;
-			start = page + *ppos;
-		} else if (start < page) {
-			if (n > PAGE_SIZE) {
-				printk(KERN_ERR
-				       "proc_file_read: Apparent buffer overflow!\n");
-				n = PAGE_SIZE;
-			}
-			if (n > count) {
-				/*
-				 * Don't reduce n because doing so might
-				 * cut off part of a data block.
-				 */
-				printk(KERN_WARNING
-				       "proc_file_read: Read count exceeded\n");
-			}
-		} else /* start >= page */ {
-			unsigned long startoff = (unsigned long)(start - page);
-			if (n > (PAGE_SIZE - startoff)) {
-				printk(KERN_ERR
-				       "proc_file_read: Apparent buffer overflow!\n");
-				n = PAGE_SIZE - startoff;
-			}
-			if (n > count)
-				n = count;
-		}
-		
- 		n -= copy_to_user(buf, start < page ? page : start, n);
-		if (n == 0) {
-			if (retval == 0)
-				retval = -EFAULT;
-			break;
-		}
-
-		*ppos += start < page ? (unsigned long)start : n;
-		nbytes -= n;
-		buf += n;
-		retval += n;
-	}
-	free_page((unsigned long) page);
-	return retval;
-}
-
-static ssize_t
-proc_file_write(struct file *file, const char __user *buffer,
-		size_t count, loff_t *ppos)
-{
-	struct inode *inode = file->f_path.dentry->d_inode;
-	struct proc_dir_entry * dp;
-	
-	dp = PDE(inode);
-
-	if (!dp->write_proc)
-		return -EIO;
-
-	/* FIXME: does this routine need ppos?  probably... */
-	return dp->write_proc(file, buffer, count, dp->data);
-}
-
-
-static loff_t
-proc_file_lseek(struct file *file, loff_t offset, int orig)
-{
-	loff_t retval = -EINVAL;
-	switch (orig) {
-	case 1:
-		offset += file->f_pos;
-	/* fallthrough */
-	case 0:
-		if (offset < 0 || offset > MAX_NON_LFS)
-			break;
-		file->f_pos = retval = offset;
-	}
-	return retval;
-}
-
-static const struct file_operations proc_file_operations = {
-	.llseek		= proc_file_lseek,
-	.read		= proc_file_read,
-	.write		= proc_file_write,
-};
-
 static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = dentry->d_inode;
@@ -235,17 +44,14 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
 
 	error = inode_change_ok(inode, iattr);
 	if (error)
-		goto out;
+		return error;
 
-	error = inode_setattr(inode, iattr);
-	if (error)
-		goto out;
-	
-	de->uid = inode->i_uid;
-	de->gid = inode->i_gid;
+	setattr_copy(inode, iattr);
+	mark_inode_dirty(inode);
+
+	proc_set_user(de, inode->i_uid, inode->i_gid);
 	de->mode = inode->i_mode;
-out:
-	return error;
+	return 0;
 }
 
 static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -254,7 +60,7 @@ static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	struct inode *inode = dentry->d_inode;
 	struct proc_dir_entry *de = PROC_I(inode)->pde;
 	if (de && de->nlink)
-		inode->i_nlink = de->nlink;
+		set_nlink(inode, de->nlink);
 
 	generic_fillattr(inode, stat);
 	return 0;
@@ -269,16 +75,17 @@ static const struct inode_operations proc_file_inode_operations = {
  * returns the struct proc_dir_entry for "/proc/tty/driver", and
  * returns "serial" in residual.
  */
-static int xlate_proc_name(const char *name,
-			   struct proc_dir_entry **ret, const char **residual)
+static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+			     const char **residual)
 {
 	const char     		*cp = name, *next;
 	struct proc_dir_entry	*de;
-	int			len;
-	int 			rtn = 0;
+	unsigned int		len;
+
+	de = *ret;
+	if (!de)
+		de = &proc_root;
 
-	spin_lock(&proc_subdir_lock);
-	de = &proc_root;
 	while (1) {
 		next = strchr(cp, '/');
 		if (!next)
@@ -290,65 +97,74 @@ static int xlate_proc_name(const char *name,
 				break;
 		}
 		if (!de) {
-			rtn = -ENOENT;
-			goto out;
+			WARN(1, "name '%s'\n", name);
+			return -ENOENT;
 		}
 		cp += len + 1;
 	}
 	*residual = cp;
 	*ret = de;
-out:
+	return 0;
+}
+
+static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+			   const char **residual)
+{
+	int rv;
+
+	spin_lock(&proc_subdir_lock);
+	rv = __xlate_proc_name(name, ret, residual);
 	spin_unlock(&proc_subdir_lock);
-	return rtn;
+	return rv;
 }
 
-static DEFINE_IDR(proc_inum_idr);
+static DEFINE_IDA(proc_inum_ida);
 static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
 
-#define PROC_DYNAMIC_FIRST 0xF0000000UL
+#define PROC_DYNAMIC_FIRST 0xF0000000U
 
 /*
  * Return an inode number between PROC_DYNAMIC_FIRST and
  * 0xffffffff, or zero on failure.
  */
-static unsigned int get_inode_number(void)
+int proc_alloc_inum(unsigned int *inum)
 {
-	int i, inum = 0;
+	unsigned int i;
 	int error;
 
 retry:
-	if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0)
-		return 0;
+	if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
+		return -ENOMEM;
 
-	spin_lock(&proc_inum_lock);
-	error = idr_get_new(&proc_inum_idr, NULL, &i);
-	spin_unlock(&proc_inum_lock);
+	spin_lock_irq(&proc_inum_lock);
+	error = ida_get_new(&proc_inum_ida, &i);
+	spin_unlock_irq(&proc_inum_lock);
 	if (error == -EAGAIN)
 		goto retry;
 	else if (error)
-		return 0;
+		return error;
 
-	inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST;
-
-	/* inum will never be more than 0xf0ffffff, so no check
-	 * for overflow.
-	 */
-
-	return inum;
+	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
+		spin_lock_irq(&proc_inum_lock);
+		ida_remove(&proc_inum_ida, i);
+		spin_unlock_irq(&proc_inum_lock);
+		return -ENOSPC;
+	}
+	*inum = PROC_DYNAMIC_FIRST + i;
+	return 0;
 }
 
-static void release_inode_number(unsigned int inum)
+void proc_free_inum(unsigned int inum)
 {
-	int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK;
-
-	spin_lock(&proc_inum_lock);
-	idr_remove(&proc_inum_idr, id);
-	spin_unlock(&proc_inum_lock);
+	unsigned long flags;
+	spin_lock_irqsave(&proc_inum_lock, flags);
+	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
+	spin_unlock_irqrestore(&proc_inum_lock, flags);
 }
 
 static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
-	nd_set_link(nd, PDE(dentry->d_inode)->data);
+	nd_set_link(nd, __PDE_DATA(dentry->d_inode));
 	return NULL;
 }
 
@@ -358,64 +174,35 @@ static const struct inode_operations proc_link_inode_operations = {
 };
 
 /*
- * As some entries in /proc are volatile, we want to 
- * get rid of unused dentries.  This could be made 
- * smarter: we could keep a "volatile" flag in the 
- * inode to indicate which ones to keep.
- */
-static int proc_delete_dentry(struct dentry * dentry)
-{
-	return 1;
-}
-
-static struct dentry_operations proc_dentry_operations =
-{
-	.d_delete	= proc_delete_dentry,
-};
-
-/*
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
  */
 struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 		struct dentry *dentry)
 {
-	struct inode *inode = NULL;
-	int error = -ENOENT;
+	struct inode *inode;
 
-	lock_kernel();
 	spin_lock(&proc_subdir_lock);
-	if (de) {
-		for (de = de->subdir; de ; de = de->next) {
-			if (de->namelen != dentry->d_name.len)
-				continue;
-			if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
-				unsigned int ino;
-
-				ino = de->low_ino;
-				de_get(de);
-				spin_unlock(&proc_subdir_lock);
-				error = -EINVAL;
-				inode = proc_get_inode(dir->i_sb, ino, de);
-				goto out_unlock;
-			}
+	for (de = de->subdir; de ; de = de->next) {
+		if (de->namelen != dentry->d_name.len)
+			continue;
+		if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
+			pde_get(de);
+			spin_unlock(&proc_subdir_lock);
+			inode = proc_get_inode(dir->i_sb, de);
+			if (!inode)
+				return ERR_PTR(-ENOMEM);
+			d_set_d_op(dentry, &simple_dentry_operations);
+			d_add(dentry, inode);
+			return NULL;
 		}
 	}
 	spin_unlock(&proc_subdir_lock);
-out_unlock:
-	unlock_kernel();
-
-	if (inode) {
-		dentry->d_op = &proc_dentry_operations;
-		d_add(dentry, inode);
-		return NULL;
-	}
-	de_put(de);
-	return ERR_PTR(error);
+	return ERR_PTR(-ENOENT);
 }
 
 struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
-		struct nameidata *nd)
+		unsigned int flags)
 {
 	return proc_lookup_de(PDE(dir), dir, dentry);
 }
@@ -429,82 +216,52 @@ struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
  * value of the readdir() call, as long as it's non-negative
  * for success..
  */
-int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
-		filldir_t filldir)
+int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
+		    struct dir_context *ctx)
 {
-	unsigned int ino;
 	int i;
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	int ret = 0;
-
-	lock_kernel();
 
-	ino = inode->i_ino;
-	if (!de) {
-		ret = -EINVAL;
-		goto out;
-	}
-	i = filp->f_pos;
-	switch (i) {
-		case 0:
-			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
-				goto out;
-			i++;
-			filp->f_pos++;
-			/* fall through */
-		case 1:
-			if (filldir(dirent, "..", 2, i,
-				    parent_ino(filp->f_path.dentry),
-				    DT_DIR) < 0)
-				goto out;
-			i++;
-			filp->f_pos++;
-			/* fall through */
-		default:
-			spin_lock(&proc_subdir_lock);
-			de = de->subdir;
-			i -= 2;
-			for (;;) {
-				if (!de) {
-					ret = 1;
-					spin_unlock(&proc_subdir_lock);
-					goto out;
-				}
-				if (!i)
-					break;
-				de = de->next;
-				i--;
-			}
+	if (!dir_emit_dots(file, ctx))
+		return 0;
 
-			do {
-				struct proc_dir_entry *next;
-
-				/* filldir passes info to user space */
-				de_get(de);
-				spin_unlock(&proc_subdir_lock);
-				if (filldir(dirent, de->name, de->namelen, filp->f_pos,
-					    de->low_ino, de->mode >> 12) < 0) {
-					de_put(de);
-					goto out;
-				}
-				spin_lock(&proc_subdir_lock);
-				filp->f_pos++;
-				next = de->next;
-				de_put(de);
-				de = next;
-			} while (de);
+	spin_lock(&proc_subdir_lock);
+	de = de->subdir;
+	i = ctx->pos - 2;
+	for (;;) {
+		if (!de) {
 			spin_unlock(&proc_subdir_lock);
+			return 0;
+		}
+		if (!i)
+			break;
+		de = de->next;
+		i--;
 	}
-	ret = 1;
-out:	unlock_kernel();
-	return ret;	
+
+	do {
+		struct proc_dir_entry *next;
+		pde_get(de);
+		spin_unlock(&proc_subdir_lock);
+		if (!dir_emit(ctx, de->name, de->namelen,
+			    de->low_ino, de->mode >> 12)) {
+			pde_put(de);
+			return 0;
+		}
+		spin_lock(&proc_subdir_lock);
+		ctx->pos++;
+		next = de->next;
+		pde_put(de);
+		de = next;
+	} while (de);
+	spin_unlock(&proc_subdir_lock);
+	return 1;
 }
 
-int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
+int proc_readdir(struct file *file, struct dir_context *ctx)
 {
-	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(file);
 
-	return proc_readdir_de(PDE(inode), filp, dirent, filldir);
+	return proc_readdir_de(PDE(inode), file, ctx);
 }
 
 /*
@@ -513,8 +270,9 @@ int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
  * the /proc directory.
  */
 static const struct file_operations proc_dir_operations = {
+	.llseek			= generic_file_llseek,
 	.read			= generic_read_dir,
-	.readdir		= proc_readdir,
+	.iterate		= proc_readdir,
 };
 
 /*
@@ -528,37 +286,33 @@ static const struct inode_operations proc_dir_inode_operations = {
 
 static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
 {
-	unsigned int i;
 	struct proc_dir_entry *tmp;
+	int ret;
 	
-	i = get_inode_number();
-	if (i == 0)
-		return -EAGAIN;
-	dp->low_ino = i;
+	ret = proc_alloc_inum(&dp->low_ino);
+	if (ret)
+		return ret;
 
 	if (S_ISDIR(dp->mode)) {
-		if (dp->proc_iops == NULL) {
-			dp->proc_fops = &proc_dir_operations;
-			dp->proc_iops = &proc_dir_inode_operations;
-		}
+		dp->proc_fops = &proc_dir_operations;
+		dp->proc_iops = &proc_dir_inode_operations;
 		dir->nlink++;
 	} else if (S_ISLNK(dp->mode)) {
-		if (dp->proc_iops == NULL)
-			dp->proc_iops = &proc_link_inode_operations;
+		dp->proc_iops = &proc_link_inode_operations;
 	} else if (S_ISREG(dp->mode)) {
-		if (dp->proc_fops == NULL)
-			dp->proc_fops = &proc_file_operations;
-		if (dp->proc_iops == NULL)
-			dp->proc_iops = &proc_file_inode_operations;
+		BUG_ON(dp->proc_fops == NULL);
+		dp->proc_iops = &proc_file_inode_operations;
+	} else {
+		WARN_ON(1);
+		return -EINVAL;
 	}
 
 	spin_lock(&proc_subdir_lock);
 
 	for (tmp = dir->subdir; tmp; tmp = tmp->next)
 		if (strcmp(tmp->name, dp->name) == 0) {
-			printk(KERN_WARNING "proc_dir_entry '%s' already "
-					"registered\n", dp->name);
-			dump_stack();
+			WARN(1, "proc_dir_entry '%s/%s' already registered\n",
+				dir->name, dp->name);
 			break;
 		}
 
@@ -572,17 +326,18 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
 
 static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 					  const char *name,
-					  mode_t mode,
+					  umode_t mode,
 					  nlink_t nlink)
 {
 	struct proc_dir_entry *ent = NULL;
 	const char *fn = name;
-	int len;
+	unsigned int len;
 
 	/* make sure name is valid */
-	if (!name || !strlen(name)) goto out;
+	if (!name || !strlen(name))
+		goto out;
 
-	if (!(*parent) && xlate_proc_name(name, parent, &fn) != 0)
+	if (xlate_proc_name(name, parent, &fn) != 0)
 		goto out;
 
 	/* At this point there must not be any '/' characters beyond *fn */
@@ -591,20 +346,18 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 
 	len = strlen(fn);
 
-	ent = kmalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
-	if (!ent) goto out;
+	ent = kzalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
+	if (!ent)
+		goto out;
 
-	memset(ent, 0, sizeof(struct proc_dir_entry));
-	memcpy(((char *) ent) + sizeof(struct proc_dir_entry), fn, len + 1);
-	ent->name = ((char *) ent) + sizeof(*ent);
+	memcpy(ent->name, fn, len + 1);
 	ent->namelen = len;
 	ent->mode = mode;
 	ent->nlink = nlink;
 	atomic_set(&ent->count, 1);
-	ent->pde_users = 0;
 	spin_lock_init(&ent->pde_unload_lock);
-	ent->pde_unload_completion = NULL;
- out:
+	INIT_LIST_HEAD(&ent->pde_openers);
+out:
 	return ent;
 }
 
@@ -632,14 +385,19 @@ struct proc_dir_entry *proc_symlink(const char *name,
 	}
 	return ent;
 }
+EXPORT_SYMBOL(proc_symlink);
 
-struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
-		struct proc_dir_entry *parent)
+struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, void *data)
 {
 	struct proc_dir_entry *ent;
 
+	if (mode == 0)
+		mode = S_IRUGO | S_IXUGO;
+
 	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
 	if (ent) {
+		ent->data = data;
 		if (proc_register(parent, ent) < 0) {
 			kfree(ent);
 			ent = NULL;
@@ -647,64 +405,43 @@ struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
 	}
 	return ent;
 }
+EXPORT_SYMBOL_GPL(proc_mkdir_data);
 
-struct proc_dir_entry *proc_mkdir(const char *name,
-		struct proc_dir_entry *parent)
+struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
+				       struct proc_dir_entry *parent)
 {
-	return proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent);
+	return proc_mkdir_data(name, mode, parent, NULL);
 }
+EXPORT_SYMBOL(proc_mkdir_mode);
 
-struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
-					 struct proc_dir_entry *parent)
+struct proc_dir_entry *proc_mkdir(const char *name,
+		struct proc_dir_entry *parent)
 {
-	struct proc_dir_entry *ent;
-	nlink_t nlink;
-
-	if (S_ISDIR(mode)) {
-		if ((mode & S_IALLUGO) == 0)
-			mode |= S_IRUGO | S_IXUGO;
-		nlink = 2;
-	} else {
-		if ((mode & S_IFMT) == 0)
-			mode |= S_IFREG;
-		if ((mode & S_IALLUGO) == 0)
-			mode |= S_IRUGO;
-		nlink = 1;
-	}
-
-	ent = __proc_create(&parent, name, mode, nlink);
-	if (ent) {
-		if (proc_register(parent, ent) < 0) {
-			kfree(ent);
-			ent = NULL;
-		}
-	}
-	return ent;
+	return proc_mkdir_data(name, 0, parent, NULL);
 }
+EXPORT_SYMBOL(proc_mkdir);
 
-struct proc_dir_entry *proc_create(const char *name, mode_t mode,
-				   struct proc_dir_entry *parent,
-				   const struct file_operations *proc_fops)
+struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
+					struct proc_dir_entry *parent,
+					const struct file_operations *proc_fops,
+					void *data)
 {
 	struct proc_dir_entry *pde;
-	nlink_t nlink;
+	if ((mode & S_IFMT) == 0)
+		mode |= S_IFREG;
 
-	if (S_ISDIR(mode)) {
-		if ((mode & S_IALLUGO) == 0)
-			mode |= S_IRUGO | S_IXUGO;
-		nlink = 2;
-	} else {
-		if ((mode & S_IFMT) == 0)
-			mode |= S_IFREG;
-		if ((mode & S_IALLUGO) == 0)
-			mode |= S_IRUGO;
-		nlink = 1;
+	if (!S_ISREG(mode)) {
+		WARN_ON(1);	/* use proc_mkdir() */
+		return NULL;
 	}
 
-	pde = __proc_create(&parent, name, mode, nlink);
+	if ((mode & S_IALLUGO) == 0)
+		mode |= S_IRUGO;
+	pde = __proc_create(&parent, name, mode, 1);
 	if (!pde)
 		goto out;
 	pde->proc_fops = proc_fops;
+	pde->data = data;
 	if (proc_register(parent, pde) < 0)
 		goto out_free;
 	return pde;
@@ -713,76 +450,149 @@ out_free:
 out:
 	return NULL;
 }
-
-void free_proc_entry(struct proc_dir_entry *de)
+EXPORT_SYMBOL(proc_create_data);
+ 
+void proc_set_size(struct proc_dir_entry *de, loff_t size)
 {
-	unsigned int ino = de->low_ino;
+	de->size = size;
+}
+EXPORT_SYMBOL(proc_set_size);
 
-	if (ino < PROC_DYNAMIC_FIRST)
-		return;
+void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid)
+{
+	de->uid = uid;
+	de->gid = gid;
+}
+EXPORT_SYMBOL(proc_set_user);
 
-	release_inode_number(ino);
+static void free_proc_entry(struct proc_dir_entry *de)
+{
+	proc_free_inum(de->low_ino);
 
 	if (S_ISLNK(de->mode))
 		kfree(de->data);
 	kfree(de);
 }
 
+void pde_put(struct proc_dir_entry *pde)
+{
+	if (atomic_dec_and_test(&pde->count))
+		free_proc_entry(pde);
+}
+
 /*
  * Remove a /proc entry and free it if it's not currently in use.
  */
 void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 {
 	struct proc_dir_entry **p;
-	struct proc_dir_entry *de;
+	struct proc_dir_entry *de = NULL;
 	const char *fn = name;
-	int len;
+	unsigned int len;
 
-	if (!parent && xlate_proc_name(name, &parent, &fn) != 0)
-		goto out;
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return;
+	}
 	len = strlen(fn);
 
-	spin_lock(&proc_subdir_lock);
 	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (!proc_match(len, fn, *p))
-			continue;
-		de = *p;
-		*p = de->next;
-		de->next = NULL;
-
-		spin_lock(&de->pde_unload_lock);
-		/*
-		 * Stop accepting new callers into module. If you're
-		 * dynamically allocating ->proc_fops, save a pointer somewhere.
-		 */
-		de->proc_fops = NULL;
-		/* Wait until all existing callers into module are done. */
-		if (de->pde_users > 0) {
-			DECLARE_COMPLETION_ONSTACK(c);
-
-			if (!de->pde_unload_completion)
-				de->pde_unload_completion = &c;
-
-			spin_unlock(&de->pde_unload_lock);
-			spin_unlock(&proc_subdir_lock);
+		if (proc_match(len, fn, *p)) {
+			de = *p;
+			*p = de->next;
+			de->next = NULL;
+			break;
+		}
+	}
+	spin_unlock(&proc_subdir_lock);
+	if (!de) {
+		WARN(1, "name '%s'\n", name);
+		return;
+	}
 
-			wait_for_completion(de->pde_unload_completion);
+	proc_entry_rundown(de);
 
-			spin_lock(&proc_subdir_lock);
-			goto continue_removing;
+	if (S_ISDIR(de->mode))
+		parent->nlink--;
+	de->nlink = 0;
+	WARN(de->subdir, "%s: removing non-empty directory "
+			 "'%s/%s', leaking at least '%s'\n", __func__,
+			 de->parent->name, de->name, de->subdir->name);
+	pde_put(de);
+}
+EXPORT_SYMBOL(remove_proc_entry);
+
+int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry **p;
+	struct proc_dir_entry *root = NULL, *de, *next;
+	const char *fn = name;
+	unsigned int len;
+
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	len = strlen(fn);
+
+	for (p = &parent->subdir; *p; p=&(*p)->next ) {
+		if (proc_match(len, fn, *p)) {
+			root = *p;
+			*p = root->next;
+			root->next = NULL;
+			break;
+		}
+	}
+	if (!root) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	de = root;
+	while (1) {
+		next = de->subdir;
+		if (next) {
+			de->subdir = next->next;
+			next->next = NULL;
+			de = next;
+			continue;
 		}
-		spin_unlock(&de->pde_unload_lock);
+		spin_unlock(&proc_subdir_lock);
 
-continue_removing:
+		proc_entry_rundown(de);
+		next = de->parent;
 		if (S_ISDIR(de->mode))
-			parent->nlink--;
+			next->nlink--;
 		de->nlink = 0;
-		WARN_ON(de->subdir);
-		if (atomic_dec_and_test(&de->count))
-			free_proc_entry(de);
-		break;
+		if (de == root)
+			break;
+		pde_put(de);
+
+		spin_lock(&proc_subdir_lock);
+		de = next;
 	}
-	spin_unlock(&proc_subdir_lock);
-out:
-	return;
+	pde_put(root);
+	return 0;
+}
+EXPORT_SYMBOL(remove_proc_subtree);
+
+void *proc_get_parent_data(const struct inode *inode)
+{
+	struct proc_dir_entry *de = PDE(inode);
+	return de->parent->data;
+}
+EXPORT_SYMBOL_GPL(proc_get_parent_data);
+
+void proc_remove(struct proc_dir_entry *de)
+{
+	if (de)
+		remove_proc_subtree(de->name, de->parent);
+}
+EXPORT_SYMBOL(proc_remove);
+
+void *PDE_DATA(const struct inode *inode)
+{
+	return __PDE_DATA(inode);
 }
+EXPORT_SYMBOL(PDE_DATA);