linux/fs/ramfs/inode.c

324 lines
7.2 KiB
C
Raw Normal View History

/*
* 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 <linux/parser.h>
#include <asm/uaccess.h>
#include "internal.h"
/* some random number */
#define RAMFS_MAGIC 0x858458f6
#define RAMFS_DEFAULT_MODE 0755
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_mapping->a_ops = &ramfs_aops;
inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated It is often known at allocation time whether a page may be migrated or not. This patch adds a flag called __GFP_MOVABLE and a new mask called GFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated using the page migration mechanism or reclaimed by syncing with backing storage and discarding. An API function very similar to alloc_zeroed_user_highpage() is added for __GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The flags used by alloc_zeroed_user_highpage() are not changed because it would change the semantics of an existing API. After this patch is applied there are no in-kernel users of alloc_zeroed_user_highpage() so it probably should be marked deprecated if this patch is merged. Note that this patch includes a minor cleanup to the use of __GFP_ZERO in shmem.c to keep all flag modifications to inode->mapping in the shmem_dir_alloc() helper function. This clean-up suggestion is courtesy of Hugh Dickens. Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the concept. Credit to Hugh Dickens for catching issues with shmem swap vector and ramfs allocations. [akpm@linux-foundation.org: build fix] [hugh@veritas.com: __GFP_ZERO cleanup] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:05 +08:00
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
Ramfs and Ram Disk pages are unevictable Christoph Lameter pointed out that ram disk pages also clutter the LRU lists. When vmscan finds them dirty and tries to clean them, the ram disk writeback function just redirties the page so that it goes back onto the active list. Round and round she goes... With the ram disk driver [rd.c] replaced by the newer 'brd.c', this is no longer the case, as ram disk pages are no longer maintained on the lru. [This makes them unmigratable for defrag or memory hot remove, but that can be addressed by a separate patch series.] However, the ramfs pages behave like ram disk pages used to, so: Define new address_space flag [shares address_space flags member with mapping's gfp mask] to indicate that the address space contains all unevictable pages. This will provide for efficient testing of ramfs pages in page_evictable(). Also provide wrapper functions to set/test the unevictable state to minimize #ifdefs in ramfs driver and any other users of this facility. Set the unevictable state on address_space structures for new ramfs inodes. Test the unevictable state in page_evictable() to cull unevictable pages. These changes depend on [CONFIG_]UNEVICTABLE_LRU. [riel@redhat.com: undo the brd.c part] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Debugged-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:42 +08:00
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,
.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_parse_options(char *data, struct ramfs_mount_opts *opts)
{
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;
}
static int ramfs_fill_super(struct super_block * sb, void * data, int silent)
{
struct ramfs_fs_info *fsi;
struct inode *inode = NULL;
struct dentry *root;
int err;
save_mount_options(sb, data);
fsi = kzalloc(sizeof(struct ramfs_fs_info), GFP_KERNEL);
sb->s_fs_info = fsi;
if (!fsi) {
err = -ENOMEM;
goto fail;
}
err = ramfs_parse_options(data, &fsi->mount_opts);
if (err)
goto fail;
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 | fsi->mount_opts.mode, 0);
if (!inode) {
err = -ENOMEM;
goto fail;
}
root = d_alloc_root(inode);
sb->s_root = root;
if (!root) {
err = -ENOMEM;
goto fail;
}
return 0;
fail:
kfree(fsi);
sb->s_fs_info = NULL;
iput(inode);
return err;
}
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
int ramfs_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
return get_sb_nodev(fs_type, flags, data, ramfs_fill_super, mnt);
}
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
static int rootfs_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
return get_sb_nodev(fs_type, flags|MS_NOUSER, data, ramfs_fill_super,
mnt);
}
static void ramfs_kill_sb(struct super_block *sb)
{
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 = ramfs_kill_sb,
};
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");