Initial import of modified Linux 2.6.28 tree

Original upstream URL:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git | branch linux-2.6.28.y

5 files changed, 622 insertions, 0 deletions

diff --git a/fs/ramfs/Makefile b/fs/ramfs/Makefile
new file mode 100644
index 0000000..c71e65d
--- /dev/null
+++ b/fs/ramfs/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for the linux ramfs routines.
+#
+
+obj-y += ramfs.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 0000000..78f613c
--- /dev/null
+++ b/fs/ramfs/file-mmu.c
@@ -0,0 +1,54 @@
+/* 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 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,
+};
+
+const struct file_operations ramfs_file_operations = {
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= generic_file_aio_write,
+	.mmap		= generic_file_mmap,
+	.fsync		= simple_sync_file,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+	.llseek		= generic_file_llseek,
+};
+
+const struct inode_operations ramfs_file_inode_operations = {
+	.getattr	= simple_getattr,
+};
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
new file mode 100644
index 0000000..76acdbc
--- /dev/null
+++ b/fs/ramfs/file-nommu.c
@@ -0,0 +1,305 @@
+/* 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/quotaops.h>
+#include <linux/pagevec.h>
+#include <linux/mman.h>
+
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static int ramfs_nommu_setattr(struct dentry *, struct iattr *);
+
+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,
+};
+
+const struct file_operations ramfs_file_operations = {
+	.mmap			= ramfs_nommu_mmap,
+	.get_unmapped_area	= ramfs_nommu_get_unmapped_area,
+	.read			= do_sync_read,
+	.aio_read		= generic_file_aio_read,
+	.write			= do_sync_write,
+	.aio_write		= generic_file_aio_write,
+	.fsync			= simple_sync_file,
+	.splice_read		= generic_file_splice_read,
+	.splice_write		= generic_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)
+{
+	struct pagevec lru_pvec;
+	unsigned long npages, xpages, loop, limit;
+	struct page *pages;
+	unsigned order;
+	void *data;
+	int ret;
+
+	/* make various checks */
+	order = get_order(newsize);
+	if (unlikely(order >= MAX_ORDER))
+		goto too_big;
+
+	limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+	if (limit != RLIM_INFINITY && newsize > limit)
+		goto fsize_exceeded;
+
+	if (newsize > inode->i_sb->s_maxbytes)
+		goto too_big;
+
+	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 */
+	pagevec_init(&lru_pvec, 0);
+	for (loop = 0; loop < npages; loop++) {
+		struct page *page = pages + loop;
+
+		ret = add_to_page_cache(page, inode->i_mapping, loop, GFP_KERNEL);
+		if (ret < 0)
+			goto add_error;
+
+		if (!pagevec_add(&lru_pvec, page))
+			__pagevec_lru_add_file(&lru_pvec);
+
+		unlock_page(page);
+	}
+
+	pagevec_lru_add_file(&lru_pvec);
+	return 0;
+
+ fsize_exceeded:
+	send_sig(SIGXFSZ, current, 0);
+ too_big:
+	return -EFBIG;
+
+ add_error:
+	page_cache_release(pages + loop);
+	for (loop++; loop < npages; loop++)
+		__free_page(pages + loop);
+	return ret;
+}
+
+/*****************************************************************************/
+/*
+ * check that file shrinkage doesn't leave any VMAs dangling in midair
+ */
+static int ramfs_nommu_check_mappings(struct inode *inode,
+				      size_t newsize, size_t size)
+{
+	struct vm_area_struct *vma;
+	struct prio_tree_iter iter;
+
+	/* search for VMAs that fall within the dead zone */
+	vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+			      newsize >> PAGE_SHIFT,
+			      (size + PAGE_SIZE - 1) >> PAGE_SHIFT
+			      ) {
+		/* found one - only interested if it's shared out of the page
+		 * cache */
+		if (vma->vm_flags & VM_SHARED)
+			return -ETXTBSY; /* not quite true, but near enough */
+	}
+
+	return 0;
+}
+
+/*****************************************************************************/
+/*
+ *
+ */
+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 = ramfs_nommu_check_mappings(inode, newsize, size);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = vmtruncate(inode, newsize);
+
+	return ret;
+}
+
+/*****************************************************************************/
+/*
+ * 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;
+
+	/* by providing our own setattr() method, we skip this quotaism */
+	if ((old_ia_valid & ATTR_UID && ia->ia_uid != inode->i_uid) ||
+	    (old_ia_valid & ATTR_GID && ia->ia_gid != inode->i_gid))
+		ret = DQUOT_TRANSFER(inode, ia) ? -EDQUOT : 0;
+
+	/* pick out size-changing events */
+	if (ia->ia_valid & ATTR_SIZE) {
+		loff_t size = i_size_read(inode);
+		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;
+		}
+	}
+
+	ret = inode_setattr(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
+ */
+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->f_path.dentry->d_inode;
+	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;
+
+	nr = find_get_pages(inode->i_mapping, pgoff, lpages, pages);
+	if (nr != lpages)
+		goto out; /* 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;
+
+	/* okay - all conditions fulfilled */
+	ret = (unsigned long) page_address(pages[0]);
+
+ out:
+	if (pages) {
+		ptr = pages;
+		for (loop = lpages; loop > 0; loop--)
+			put_page(*ptr++);
+		kfree(pages);
+	}
+
+	return ret;
+}
+
+/*****************************************************************************/
+/*
+ * set up a mapping for shared memory segments
+ */
+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
new file mode 100644
index 0000000..f031d1c
--- /dev/null
+++ b/fs/ramfs/inode.c
@@ -0,0 +1,240 @@
+/*
+ * 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/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/backing-dev.h>
+#include <linux/ramfs.h>
+#include <linux/sched.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+/* 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 backing_dev_info ramfs_backing_dev_info = {
+	.ra_pages	= 0,	/* No readahead */
+	.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 * inode = new_inode(sb);
+
+	if (inode) {
+		inode->i_mode = mode;
+		inode->i_uid = current->fsuid;
+		inode->i_gid = current->fsgid;
+		inode->i_blocks = 0;
+		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:
+			init_special_inode(inode, mode, dev);
+			break;
+		case S_IFREG:
+			inode->i_op = &ramfs_file_inode_operations;
+			inode->i_fop = &ramfs_file_operations;
+			break;
+		case S_IFDIR:
+			inode->i_op = &ramfs_dir_inode_operations;
+			inode->i_fop = &simple_dir_operations;
+
+			/* directory inodes start off with i_nlink == 2 (for "." entry) */
+			inc_nlink(inode);
+			break;
+		case S_IFLNK:
+			inode->i_op = &page_symlink_inode_operations;
+			break;
+		}
+	}
+	return inode;
+}
+
+/*
+ * File creation. Allocate an inode, and we're done..
+ */
+/* SMP-safe */
+static int
+ramfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
+{
+	struct inode * inode = ramfs_get_inode(dir->i_sb, 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)
+{
+	int retval = ramfs_mknod(dir, dentry, mode | S_IFDIR, 0);
+	if (!retval)
+		inc_nlink(dir);
+	return retval;
+}
+
+static int ramfs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd)
+{
+	return ramfs_mknod(dir, dentry, mode | S_IFREG, 0);
+}
+
+static int ramfs_symlink(struct inode * dir, struct dentry *dentry, const char * symname)
+{
+	struct inode *inode;
+	int error = -ENOSPC;
+
+	inode = ramfs_get_inode(dir->i_sb, 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 const struct inode_operations ramfs_dir_inode_operations = {
+	.create		= ramfs_create,
+	.lookup		= simple_lookup,
+	.link		= simple_link,
+	.unlink		= simple_unlink,
+	.symlink	= ramfs_symlink,
+	.mkdir		= ramfs_mkdir,
+	.rmdir		= simple_rmdir,
+	.mknod		= ramfs_mknod,
+	.rename		= simple_rename,
+};
+
+static const struct super_operations ramfs_ops = {
+	.statfs		= simple_statfs,
+	.drop_inode	= generic_delete_inode,
+};
+
+static int ramfs_fill_super(struct super_block * sb, void * data, int silent)
+{
+	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)
+		return -ENOMEM;
+
+	root = d_alloc_root(inode);
+	if (!root) {
+		iput(inode);
+		return -ENOMEM;
+	}
+	sb->s_root = root;
+	return 0;
+}
+
+int ramfs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	return get_sb_nodev(fs_type, flags, data, ramfs_fill_super, mnt);
+}
+
+static int rootfs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	return get_sb_nodev(fs_type, flags|MS_NOUSER, data, ramfs_fill_super,
+			    mnt);
+}
+
+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,
+};
+
+static int __init init_ramfs_fs(void)
+{
+	return register_filesystem(&ramfs_fs_type);
+}
+
+static void __exit exit_ramfs_fs(void)
+{
+	unregister_filesystem(&ramfs_fs_type);
+}
+
+module_init(init_ramfs_fs)
+module_exit(exit_ramfs_fs)
+
+int __init init_rootfs(void)
+{
+	int err;
+
+	err = bdi_init(&ramfs_backing_dev_info);
+	if (err)
+		return err;
+
+	err = register_filesystem(&rootfs_fs_type);
+	if (err)
+		bdi_destroy(&ramfs_backing_dev_info);
+
+	return err;
+}
+
+MODULE_LICENSE("GPL");
diff --git a/fs/ramfs/internal.h b/fs/ramfs/internal.h
new file mode 100644
index 0000000..6b33063
--- /dev/null
+++ b/fs/ramfs/internal.h
@@ -0,0 +1,14 @@
+/* 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 address_space_operations ramfs_aops;
+extern const struct inode_operations ramfs_file_inode_operations;