linux/fs/ramfs/inode.c

300 lines
7.1 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/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 <linux/magic.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/seq_file.h>
#include "internal.h"
struct ramfs_mount_opts {
umode_t mode;
};
struct ramfs_fs_info {
struct ramfs_mount_opts mount_opts;
};
#define RAMFS_DEFAULT_MODE 0755
static const struct super_operations ramfs_ops;
static const struct inode_operations ramfs_dir_inode_operations;
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_ino = get_next_ino();
inode_init_owner(&init_user_ns, inode, dir, mode);
inode->i_mapping->a_ops = &ram_aops;
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(inode);
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;
inode_nohighmem(inode);
break;
}
}
return inode;
}
/*
* File creation. Allocate an inode, and we're done..
*/
/* SMP-safe */
static int
ramfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev);
int error = -ENOSPC;
if (inode) {
d_instantiate(dentry, inode);
dget(dentry); /* Extra count - pin the dentry in core */
error = 0;
dir->i_mtime = dir->i_ctime = current_time(dir);
}
return error;
}
static int ramfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
int retval = ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0);
if (!retval)
inc_nlink(dir);
return retval;
}
static int ramfs_create(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
return ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
}
static int ramfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, const char *symname)
{
struct inode *inode;
int error = -ENOSPC;
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) {
d_instantiate(dentry, inode);
dget(dentry);
dir->i_mtime = dir->i_ctime = current_time(dir);
} else
iput(inode);
}
return error;
}
static int ramfs_tmpfile(struct user_namespace *mnt_userns,
struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct inode *inode;
inode = ramfs_get_inode(dir->i_sb, dir, mode, 0);
if (!inode)
return -ENOSPC;
d_tmpfile(dentry, inode);
return 0;
}
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,
.tmpfile = ramfs_tmpfile,
};
/*
* Display the mount options in /proc/mounts.
*/
static int ramfs_show_options(struct seq_file *m, struct dentry *root)
{
struct ramfs_fs_info *fsi = root->d_sb->s_fs_info;
if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE)
seq_printf(m, ",mode=%o", fsi->mount_opts.mode);
return 0;
}
static const struct super_operations ramfs_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = ramfs_show_options,
};
enum ramfs_param {
Opt_mode,
};
const struct fs_parameter_spec ramfs_fs_parameters[] = {
fsparam_u32oct("mode", Opt_mode),
{}
};
static int ramfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct fs_parse_result result;
struct ramfs_fs_info *fsi = fc->s_fs_info;
int opt;
opt = fs_parse(fc, ramfs_fs_parameters, param, &result);
if (opt == -ENOPARAM) {
opt = vfs_parse_fs_param_source(fc, param);
if (opt != -ENOPARAM)
return opt;
/*
* 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;
}
if (opt < 0)
return opt;
switch (opt) {
case Opt_mode:
fsi->mount_opts.mode = result.uint_32 & S_IALLUGO;
break;
}
return 0;
}
static int ramfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct ramfs_fs_info *fsi = sb->s_fs_info;
struct inode *inode;
sb->s_maxbytes = MAX_LFS_FILESIZE;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_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;
return 0;
}
static int ramfs_get_tree(struct fs_context *fc)
{
return get_tree_nodev(fc, ramfs_fill_super);
}
static void ramfs_free_fc(struct fs_context *fc)
{
kfree(fc->s_fs_info);
}
static const struct fs_context_operations ramfs_context_ops = {
.free = ramfs_free_fc,
.parse_param = ramfs_parse_param,
.get_tree = ramfs_get_tree,
};
int ramfs_init_fs_context(struct fs_context *fc)
{
struct ramfs_fs_info *fsi;
fsi = kzalloc(sizeof(*fsi), GFP_KERNEL);
if (!fsi)
return -ENOMEM;
fsi->mount_opts.mode = RAMFS_DEFAULT_MODE;
fc->s_fs_info = fsi;
fc->ops = &ramfs_context_ops;
return 0;
}
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",
.init_fs_context = ramfs_init_fs_context,
.parameters = ramfs_fs_parameters,
.kill_sb = ramfs_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
static int __init init_ramfs_fs(void)
{
return register_filesystem(&ramfs_fs_type);
}
fs_initcall(init_ramfs_fs);