5 files changed, 464 insertions, 96 deletions

diff --git a/fs/ramfs/Makefile b/fs/ramfs/Makefile
index f096f300709..c71e65dcad2 100644
--- a/fs/ramfs/Makefile
+++ b/fs/ramfs/Makefile
@@ -2,6 +2,8 @@
 # Makefile for the linux ramfs routines.
 #
 
-obj-$(CONFIG_RAMFS) += ramfs.o
+obj-y += ramfs.o
 
-ramfs-objs := inode.o
+file-mmu-y := file-nommu.o
+file-mmu-$(CONFIG_MMU) := file-mmu.o
+ramfs-objs += inode.o $(file-mmu-y)
diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c
new file mode 100644
index 00000000000..4f56de822d2
--- /dev/null
+++ b/fs/ramfs/file-mmu.c
@@ -0,0 +1,48 @@
+/* file-mmu.c: ramfs MMU-based file operations
+ *
+ * Resizable simple ram filesystem for Linux.
+ *
+ * Copyright (C) 2000 Linus Torvalds.
+ *               2000 Transmeta Corp.
+ *
+ * Usage limits added by David Gibson, Linuxcare Australia.
+ * This file is released under the GPL.
+ */
+
+/*
+ * NOTE! This filesystem is probably most useful
+ * not as a real filesystem, but as an example of
+ * how virtual filesystems can be written.
+ *
+ * It doesn't get much simpler than this. Consider
+ * that this file implements the full semantics of
+ * a POSIX-compliant read-write filesystem.
+ *
+ * Note in particular how the filesystem does not
+ * need to implement any data structures of its own
+ * to keep track of the virtual data: using the VFS
+ * caches is sufficient.
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/ramfs.h>
+
+#include "internal.h"
+
+const struct file_operations ramfs_file_operations = {
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
+	.mmap		= generic_file_mmap,
+	.fsync		= noop_fsync,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
+	.llseek		= generic_file_llseek,
+};
+
+const struct inode_operations ramfs_file_inode_operations = {
+	.setattr	= simple_setattr,
+	.getattr	= simple_getattr,
+};
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
new file mode 100644
index 00000000000..dda012ad420
--- /dev/null
+++ b/fs/ramfs/file-nommu.c
@@ -0,0 +1,266 @@
+/* file-nommu.c: no-MMU version of ramfs
+ *
+ * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/backing-dev.h>
+#include <linux/ramfs.h>
+#include <linux/pagevec.h>
+#include <linux/mman.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static int ramfs_nommu_setattr(struct dentry *, struct iattr *);
+static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
+						   unsigned long addr,
+						   unsigned long len,
+						   unsigned long pgoff,
+						   unsigned long flags);
+static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
+
+const struct file_operations ramfs_file_operations = {
+	.mmap			= ramfs_nommu_mmap,
+	.get_unmapped_area	= ramfs_nommu_get_unmapped_area,
+	.read			= new_sync_read,
+	.read_iter		= generic_file_read_iter,
+	.write			= new_sync_write,
+	.write_iter		= generic_file_write_iter,
+	.fsync			= noop_fsync,
+	.splice_read		= generic_file_splice_read,
+	.splice_write		= iter_file_splice_write,
+	.llseek			= generic_file_llseek,
+};
+
+const struct inode_operations ramfs_file_inode_operations = {
+	.setattr		= ramfs_nommu_setattr,
+	.getattr		= simple_getattr,
+};
+
+/*****************************************************************************/
+/*
+ * add a contiguous set of pages into a ramfs inode when it's truncated from
+ * size 0 on the assumption that it's going to be used for an mmap of shared
+ * memory
+ */
+int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
+{
+	unsigned long npages, xpages, loop;
+	struct page *pages;
+	unsigned order;
+	void *data;
+	int ret;
+
+	/* make various checks */
+	order = get_order(newsize);
+	if (unlikely(order >= MAX_ORDER))
+		return -EFBIG;
+
+	ret = inode_newsize_ok(inode, newsize);
+	if (ret)
+		return ret;
+
+	i_size_write(inode, newsize);
+
+	/* allocate enough contiguous pages to be able to satisfy the
+	 * request */
+	pages = alloc_pages(mapping_gfp_mask(inode->i_mapping), order);
+	if (!pages)
+		return -ENOMEM;
+
+	/* split the high-order page into an array of single pages */
+	xpages = 1UL << order;
+	npages = (newsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	split_page(pages, order);
+
+	/* trim off any pages we don't actually require */
+	for (loop = npages; loop < xpages; loop++)
+		__free_page(pages + loop);
+
+	/* clear the memory we allocated */
+	newsize = PAGE_SIZE * npages;
+	data = page_address(pages);
+	memset(data, 0, newsize);
+
+	/* attach all the pages to the inode's address space */
+	for (loop = 0; loop < npages; loop++) {
+		struct page *page = pages + loop;
+
+		ret = add_to_page_cache_lru(page, inode->i_mapping, loop,
+					GFP_KERNEL);
+		if (ret < 0)
+			goto add_error;
+
+		/* prevent the page from being discarded on memory pressure */
+		SetPageDirty(page);
+		SetPageUptodate(page);
+
+		unlock_page(page);
+		put_page(page);
+	}
+
+	return 0;
+
+add_error:
+	while (loop < npages)
+		__free_page(pages + loop++);
+	return ret;
+}
+
+/*****************************************************************************/
+/*
+ *
+ */
+static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size)
+{
+	int ret;
+
+	/* assume a truncate from zero size is going to be for the purposes of
+	 * shared mmap */
+	if (size == 0) {
+		if (unlikely(newsize >> 32))
+			return -EFBIG;
+
+		return ramfs_nommu_expand_for_mapping(inode, newsize);
+	}
+
+	/* check that a decrease in size doesn't cut off any shared mappings */
+	if (newsize < size) {
+		ret = nommu_shrink_inode_mappings(inode, size, newsize);
+		if (ret < 0)
+			return ret;
+	}
+
+	truncate_setsize(inode, newsize);
+	return 0;
+}
+
+/*****************************************************************************/
+/*
+ * handle a change of attributes
+ * - we're specifically interested in a change of size
+ */
+static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia)
+{
+	struct inode *inode = dentry->d_inode;
+	unsigned int old_ia_valid = ia->ia_valid;
+	int ret = 0;
+
+	/* POSIX UID/GID verification for setting inode attributes */
+	ret = inode_change_ok(inode, ia);
+	if (ret)
+		return ret;
+
+	/* pick out size-changing events */
+	if (ia->ia_valid & ATTR_SIZE) {
+		loff_t size = inode->i_size;
+
+		if (ia->ia_size != size) {
+			ret = ramfs_nommu_resize(inode, ia->ia_size, size);
+			if (ret < 0 || ia->ia_valid == ATTR_SIZE)
+				goto out;
+		} else {
+			/* we skipped the truncate but must still update
+			 * timestamps
+			 */
+			ia->ia_valid |= ATTR_MTIME|ATTR_CTIME;
+		}
+	}
+
+	setattr_copy(inode, ia);
+ out:
+	ia->ia_valid = old_ia_valid;
+	return ret;
+}
+
+/*****************************************************************************/
+/*
+ * try to determine where a shared mapping can be made
+ * - we require that:
+ *   - the pages to be mapped must exist
+ *   - the pages be physically contiguous in sequence
+ */
+static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
+					    unsigned long addr, unsigned long len,
+					    unsigned long pgoff, unsigned long flags)
+{
+	unsigned long maxpages, lpages, nr, loop, ret;
+	struct inode *inode = file_inode(file);
+	struct page **pages = NULL, **ptr, *page;
+	loff_t isize;
+
+	if (!(flags & MAP_SHARED))
+		return addr;
+
+	/* the mapping mustn't extend beyond the EOF */
+	lpages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	isize = i_size_read(inode);
+
+	ret = -EINVAL;
+	maxpages = (isize + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (pgoff >= maxpages)
+		goto out;
+
+	if (maxpages - pgoff < lpages)
+		goto out;
+
+	/* gang-find the pages */
+	ret = -ENOMEM;
+	pages = kzalloc(lpages * sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		goto out_free;
+
+	nr = find_get_pages(inode->i_mapping, pgoff, lpages, pages);
+	if (nr != lpages)
+		goto out_free_pages; /* leave if some pages were missing */
+
+	/* check the pages for physical adjacency */
+	ptr = pages;
+	page = *ptr++;
+	page++;
+	for (loop = lpages; loop > 1; loop--)
+		if (*ptr++ != page++)
+			goto out_free_pages;
+
+	/* okay - all conditions fulfilled */
+	ret = (unsigned long) page_address(pages[0]);
+
+out_free_pages:
+	ptr = pages;
+	for (loop = nr; loop > 0; loop--)
+		put_page(*ptr++);
+out_free:
+	kfree(pages);
+out:
+	return ret;
+}
+
+/*****************************************************************************/
+/*
+ * set up a mapping for shared memory segments
+ */
+static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return -ENOSYS;
+
+	file_accessed(file);
+	vma->vm_ops = &generic_file_vm_ops;
+	return 0;
+}
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 0a88917605a..d365b1c4eb3 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -23,45 +23,53 @@
  * caches is sufficient.
  */
 
-#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
+#include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/backing-dev.h>
 #include <linux/ramfs.h>
-
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
+#include "internal.h"
+
+#define RAMFS_DEFAULT_MODE	0755
 
-/* some random number */
-#define RAMFS_MAGIC	0x858458f6
+static const struct super_operations ramfs_ops;
+static const struct inode_operations ramfs_dir_inode_operations;
 
-static struct super_operations ramfs_ops;
-static struct address_space_operations ramfs_aops;
-static struct inode_operations ramfs_file_inode_operations;
-static struct inode_operations ramfs_dir_inode_operations;
+static const struct address_space_operations ramfs_aops = {
+	.readpage	= simple_readpage,
+	.write_begin	= simple_write_begin,
+	.write_end	= simple_write_end,
+	.set_page_dirty	= __set_page_dirty_no_writeback,
+};
 
 static struct backing_dev_info ramfs_backing_dev_info = {
+	.name		= "ramfs",
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK |
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK |
 			  BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
 			  BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP,
 };
 
-struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
+struct inode *ramfs_get_inode(struct super_block *sb,
+				const struct inode *dir, umode_t mode, dev_t dev)
 {
 	struct inode * inode = new_inode(sb);
 
 	if (inode) {
-		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
-		inode->i_blksize = PAGE_CACHE_SIZE;
-		inode->i_blocks = 0;
+		inode->i_ino = get_next_ino();
+		inode_init_owner(inode, dir, mode);
 		inode->i_mapping->a_ops = &ramfs_aops;
 		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
+		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+		mapping_set_unevictable(inode->i_mapping);
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		switch (mode & S_IFMT) {
 		default:
@@ -76,7 +84,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
 			inode->i_fop = &simple_dir_operations;
 
 			/* directory inodes start off with i_nlink == 2 (for "." entry) */
-			inode->i_nlink++;
+			inc_nlink(inode);
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
@@ -91,33 +99,29 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
  */
 /* SMP-safe */
 static int
-ramfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
+ramfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
 {
-	struct inode * inode = ramfs_get_inode(dir->i_sb, mode, dev);
+	struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev);
 	int error = -ENOSPC;
 
 	if (inode) {
-		if (dir->i_mode & S_ISGID) {
-			inode->i_gid = dir->i_gid;
-			if (S_ISDIR(mode))
-				inode->i_mode |= S_ISGID;
-		}
 		d_instantiate(dentry, inode);
 		dget(dentry);	/* Extra count - pin the dentry in core */
 		error = 0;
+		dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	}
 	return error;
 }
 
-static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 {
 	int retval = ramfs_mknod(dir, dentry, mode | S_IFDIR, 0);
 	if (!retval)
-		dir->i_nlink++;
+		inc_nlink(dir);
 	return retval;
 }
 
-static int ramfs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd)
+static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
 {
 	return ramfs_mknod(dir, dentry, mode | S_IFREG, 0);
 }
@@ -127,41 +131,21 @@ static int ramfs_symlink(struct inode * dir, struct dentry *dentry, const char *
 	struct inode *inode;
 	int error = -ENOSPC;
 
-	inode = ramfs_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
+	inode = ramfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
 	if (inode) {
 		int l = strlen(symname)+1;
 		error = page_symlink(inode, symname, l);
 		if (!error) {
-			if (dir->i_mode & S_ISGID)
-				inode->i_gid = dir->i_gid;
 			d_instantiate(dentry, inode);
 			dget(dentry);
+			dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 		} else
 			iput(inode);
 	}
 	return error;
 }
 
-static struct address_space_operations ramfs_aops = {
-	.readpage	= simple_readpage,
-	.prepare_write	= simple_prepare_write,
-	.commit_write	= simple_commit_write
-};
-
-struct file_operations ramfs_file_operations = {
-	.read		= generic_file_read,
-	.write		= generic_file_write,
-	.mmap		= generic_file_mmap,
-	.fsync		= simple_sync_file,
-	.sendfile	= generic_file_sendfile,
-	.llseek		= generic_file_llseek,
-};
-
-static struct inode_operations ramfs_file_inode_operations = {
-	.getattr	= simple_getattr,
-};
-
-static struct inode_operations ramfs_dir_inode_operations = {
+static const struct inode_operations ramfs_dir_inode_operations = {
 	.create		= ramfs_create,
 	.lookup		= simple_lookup,
 	.link		= simple_link,
@@ -173,74 +157,129 @@ static struct inode_operations ramfs_dir_inode_operations = {
 	.rename		= simple_rename,
 };
 
-static struct super_operations ramfs_ops = {
+static const struct super_operations ramfs_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
+	.show_options	= generic_show_options,
+};
+
+struct ramfs_mount_opts {
+	umode_t mode;
+};
+
+enum {
+	Opt_mode,
+	Opt_err
+};
+
+static const match_table_t tokens = {
+	{Opt_mode, "mode=%o"},
+	{Opt_err, NULL}
+};
+
+struct ramfs_fs_info {
+	struct ramfs_mount_opts mount_opts;
 };
 
-static int ramfs_fill_super(struct super_block * sb, void * data, int silent)
+static int ramfs_parse_options(char *data, struct ramfs_mount_opts *opts)
 {
-	struct inode * inode;
-	struct dentry * root;
-
-	sb->s_maxbytes = MAX_LFS_FILESIZE;
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
-	sb->s_magic = RAMFS_MAGIC;
-	sb->s_op = &ramfs_ops;
-	sb->s_time_gran = 1;
-	inode = ramfs_get_inode(sb, S_IFDIR | 0755, 0);
-	if (!inode)
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	int token;
+	char *p;
+
+	opts->mode = RAMFS_DEFAULT_MODE;
+
+	while ((p = strsep(&data, ",")) != NULL) {
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_mode:
+			if (match_octal(&args[0], &option))
+				return -EINVAL;
+			opts->mode = option & S_IALLUGO;
+			break;
+		/*
+		 * We might like to report bad mount options here;
+		 * but traditionally ramfs has ignored all mount options,
+		 * and as it is used as a !CONFIG_SHMEM simple substitute
+		 * for tmpfs, better continue to ignore other mount options.
+		 */
+		}
+	}
+
+	return 0;
+}
+
+int ramfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct ramfs_fs_info *fsi;
+	struct inode *inode;
+	int err;
+
+	save_mount_options(sb, data);
+
+	fsi = kzalloc(sizeof(struct ramfs_fs_info), GFP_KERNEL);
+	sb->s_fs_info = fsi;
+	if (!fsi)
 		return -ENOMEM;
 
-	root = d_alloc_root(inode);
-	if (!root) {
-		iput(inode);
+	err = ramfs_parse_options(data, &fsi->mount_opts);
+	if (err)
+		return err;
+
+	sb->s_maxbytes		= MAX_LFS_FILESIZE;
+	sb->s_blocksize		= PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits	= PAGE_CACHE_SHIFT;
+	sb->s_magic		= RAMFS_MAGIC;
+	sb->s_op		= &ramfs_ops;
+	sb->s_time_gran		= 1;
+
+	inode = ramfs_get_inode(sb, NULL, S_IFDIR | fsi->mount_opts.mode, 0);
+	sb->s_root = d_make_root(inode);
+	if (!sb->s_root)
 		return -ENOMEM;
-	}
-	sb->s_root = root;
+
 	return 0;
 }
 
-struct super_block *ramfs_get_sb(struct file_system_type *fs_type,
+struct dentry *ramfs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
-	return get_sb_nodev(fs_type, flags, data, ramfs_fill_super);
+	return mount_nodev(fs_type, flags, data, ramfs_fill_super);
 }
 
-static struct super_block *rootfs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static void ramfs_kill_sb(struct super_block *sb)
 {
-	return get_sb_nodev(fs_type, flags|MS_NOUSER, data, ramfs_fill_super);
+	kfree(sb->s_fs_info);
+	kill_litter_super(sb);
 }
 
 static struct file_system_type ramfs_fs_type = {
 	.name		= "ramfs",
-	.get_sb		= ramfs_get_sb,
-	.kill_sb	= kill_litter_super,
-};
-static struct file_system_type rootfs_fs_type = {
-	.name		= "rootfs",
-	.get_sb		= rootfs_get_sb,
-	.kill_sb	= kill_litter_super,
+	.mount		= ramfs_mount,
+	.kill_sb	= ramfs_kill_sb,
+	.fs_flags	= FS_USERNS_MOUNT,
 };
 
-static int __init init_ramfs_fs(void)
+int __init init_ramfs_fs(void)
 {
-	return register_filesystem(&ramfs_fs_type);
-}
+	static unsigned long once;
+	int err;
 
-static void __exit exit_ramfs_fs(void)
-{
-	unregister_filesystem(&ramfs_fs_type);
-}
+	if (test_and_set_bit(0, &once))
+		return 0;
 
-module_init(init_ramfs_fs)
-module_exit(exit_ramfs_fs)
+	err = bdi_init(&ramfs_backing_dev_info);
+	if (err)
+		return err;
 
-int __init init_rootfs(void)
-{
-	return register_filesystem(&rootfs_fs_type);
-}
+	err = register_filesystem(&ramfs_fs_type);
+	if (err)
+		bdi_destroy(&ramfs_backing_dev_info);
 
-MODULE_LICENSE("GPL");
+	return err;
+}
+fs_initcall(init_ramfs_fs);
diff --git a/fs/ramfs/internal.h b/fs/ramfs/internal.h
new file mode 100644
index 00000000000..a9d8ae88fa1
--- /dev/null
+++ b/fs/ramfs/internal.h
@@ -0,0 +1,13 @@
+/* internal.h: ramfs internal definitions
+ *
+ * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+extern const struct inode_operations ramfs_file_inode_operations;