2005-04-17 02:20:36 +04:00
/*
* 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>
2006-02-25 00:04:23 +03:00
# include <linux/time.h>
2005-04-17 02:20:36 +04:00
# include <linux/init.h>
# include <linux/string.h>
# include <linux/backing-dev.h>
# include <linux/ramfs.h>
Detach sched.h from mm.h
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-21 01:22:52 +04:00
# include <linux/sched.h>
2009-04-01 02:24:34 +04:00
# include <linux/parser.h>
2005-04-17 02:20:36 +04:00
# include <asm/uaccess.h>
[PATCH] NOMMU: Provide shared-writable mmap support on ramfs
The attached patch makes ramfs support shared-writable mmaps by:
(1) Attempting to perform a contiguous block allocation to the requested size
when truncate attempts to increase the file from zero size, such as
happens when:
fd = shm_open("/file/on/ramfs", ...):
ftruncate(fd, size_requested);
addr = mmap(NULL, subsize, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_SHARED,
fd, offset);
(2) Permitting any shared-writable mapping over any contiguous set of extant
pages. get_unmapped_area() will return the address into the actual ramfs
pages. The mapping may start anywhere and be of any size, but may not go
over the end of file. Multiple mappings may overlap in any way.
(3) Not permitting a file to be shrunk if it would truncate any shared
mappings (private mappings are copied).
Thus this patch provides support for POSIX shared memory on NOMMU kernels,
with certain limitations such as there being a large enough block of pages
available to support the allocation and it only working on directly mappable
filesystems.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 11:11:41 +03:00
# include "internal.h"
2005-04-17 02:20:36 +04:00
/* some random number */
# define RAMFS_MAGIC 0x858458f6
2009-04-01 02:24:34 +04:00
# define RAMFS_DEFAULT_MODE 0755
2007-02-12 11:55:41 +03:00
static const struct super_operations ramfs_ops ;
2007-02-12 11:55:40 +03:00
static const struct inode_operations ramfs_dir_inode_operations ;
2005-04-17 02:20:36 +04:00
static struct backing_dev_info ramfs_backing_dev_info = {
. ra_pages = 0 , /* No readahead */
2008-04-30 11:54:37 +04:00
. capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK |
2005-04-17 02:20:36 +04:00
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 ;
2008-11-14 02:39:00 +03:00
inode - > i_uid = current_fsuid ( ) ;
inode - > i_gid = current_fsgid ( ) ;
2005-04-17 02:20:36 +04:00
inode - > i_mapping - > a_ops = & ramfs_aops ;
inode - > i_mapping - > backing_dev_info = & ramfs_backing_dev_info ;
2007-07-17 15:03:05 +04:00
mapping_set_gfp_mask ( inode - > i_mapping , GFP_HIGHUSER ) ;
2008-10-19 07:26:42 +04:00
mapping_set_unevictable ( inode - > i_mapping ) ;
2005-04-17 02:20:36 +04:00
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) */
2006-10-01 10:29:04 +04:00
inc_nlink ( inode ) ;
2005-04-17 02:20:36 +04:00
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 ;
2006-02-25 00:04:23 +03:00
dir - > i_mtime = dir - > i_ctime = CURRENT_TIME ;
2005-04-17 02:20:36 +04:00
}
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 )
2006-10-01 10:29:04 +04:00
inc_nlink ( dir ) ;
2005-04-17 02:20:36 +04:00
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 ) ;
2006-03-07 02:42:56 +03:00
dir - > i_mtime = dir - > i_ctime = CURRENT_TIME ;
2005-04-17 02:20:36 +04:00
} else
iput ( inode ) ;
}
return error ;
}
2007-02-12 11:55:40 +03:00
static const struct inode_operations ramfs_dir_inode_operations = {
2005-04-17 02:20:36 +04:00
. 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 ,
} ;
2007-02-12 11:55:41 +03:00
static const struct super_operations ramfs_ops = {
2005-04-17 02:20:36 +04:00
. statfs = simple_statfs ,
. drop_inode = generic_delete_inode ,
2009-04-01 02:24:34 +04:00
. 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 ;
2005-04-17 02:20:36 +04:00
} ;
2009-04-01 02:24:34 +04:00
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 ;
2009-06-15 01:56:48 +04:00
/*
* 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 .
*/
2009-04-01 02:24:34 +04:00
}
}
return 0 ;
}
2005-04-17 02:20:36 +04:00
static int ramfs_fill_super ( struct super_block * sb , void * data , int silent )
{
2009-04-01 02:24:34 +04:00
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 ) ;
2009-04-07 10:16:50 +04:00
sb - > s_fs_info = fsi ;
2009-04-01 02:24:34 +04:00
if ( ! fsi ) {
err = - ENOMEM ;
goto fail ;
}
err = ramfs_parse_options ( data , & fsi - > mount_opts ) ;
if ( err )
goto fail ;
2005-04-17 02:20:36 +04:00
2009-04-07 10:16:50 +04:00
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 ;
2009-04-01 02:24:34 +04:00
inode = ramfs_get_inode ( sb , S_IFDIR | fsi - > mount_opts . mode , 0 ) ;
if ( ! inode ) {
err = - ENOMEM ;
goto fail ;
}
2005-04-17 02:20:36 +04:00
root = d_alloc_root ( inode ) ;
2009-04-07 10:16:50 +04:00
sb - > s_root = root ;
2005-04-17 02:20:36 +04:00
if ( ! root ) {
2009-04-01 02:24:34 +04:00
err = - ENOMEM ;
goto fail ;
2005-04-17 02:20:36 +04:00
}
2009-04-07 10:16:50 +04:00
2005-04-17 02:20:36 +04:00
return 0 ;
2009-04-01 02:24:34 +04:00
fail :
kfree ( fsi ) ;
2009-04-07 10:16:50 +04:00
sb - > s_fs_info = NULL ;
2009-04-01 02:24:34 +04:00
iput ( inode ) ;
return err ;
2005-04-17 02:20:36 +04:00
}
[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 13:02:57 +04:00
int ramfs_get_sb ( struct file_system_type * fs_type ,
int flags , const char * dev_name , void * data , struct vfsmount * mnt )
2005-04-17 02:20:36 +04:00
{
[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 13:02:57 +04:00
return get_sb_nodev ( fs_type , flags , data , ramfs_fill_super , mnt ) ;
2005-04-17 02:20:36 +04:00
}
[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 13:02:57 +04:00
static int rootfs_get_sb ( struct file_system_type * fs_type ,
int flags , const char * dev_name , void * data , struct vfsmount * mnt )
2005-04-17 02:20:36 +04:00
{
[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 13:02:57 +04:00
return get_sb_nodev ( fs_type , flags | MS_NOUSER , data , ramfs_fill_super ,
mnt ) ;
2005-04-17 02:20:36 +04:00
}
2009-04-01 02:24:34 +04:00
static void ramfs_kill_sb ( struct super_block * sb )
{
kfree ( sb - > s_fs_info ) ;
kill_litter_super ( sb ) ;
}
2005-04-17 02:20:36 +04:00
static struct file_system_type ramfs_fs_type = {
. name = " ramfs " ,
. get_sb = ramfs_get_sb ,
2009-04-01 02:24:34 +04:00
. kill_sb = ramfs_kill_sb ,
2005-04-17 02:20:36 +04:00
} ;
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 )
{
2007-10-17 10:25:46 +04:00
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 ;
2005-04-17 02:20:36 +04:00
}
MODULE_LICENSE ( " GPL " ) ;