linux_dsm_epyc7002/fs/configfs/mount.c

181 lines
4.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* mount.c - operations for initializing and mounting configfs.
*
* Based on sysfs:
* sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
*
* configfs Copyright (C) 2005 Oracle. All rights reserved.
*/
#include <linux/fs.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/fs_context.h>
#include <linux/pagemap.h>
#include <linux/init.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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/configfs.h>
#include "configfs_internal.h"
/* Random magic number */
#define CONFIGFS_MAGIC 0x62656570
static struct vfsmount *configfs_mount = NULL;
struct kmem_cache *configfs_dir_cachep;
static int configfs_mnt_count = 0;
static void configfs_free_inode(struct inode *inode)
{
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
free_inode_nonrcu(inode);
}
static const struct super_operations configfs_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.free_inode = configfs_free_inode,
};
static struct config_group configfs_root_group = {
.cg_item = {
.ci_namebuf = "root",
.ci_name = configfs_root_group.cg_item.ci_namebuf,
},
};
int configfs_is_root(struct config_item *item)
{
return item == &configfs_root_group.cg_item;
}
static struct configfs_dirent configfs_root = {
.s_sibling = LIST_HEAD_INIT(configfs_root.s_sibling),
.s_children = LIST_HEAD_INIT(configfs_root.s_children),
.s_element = &configfs_root_group.cg_item,
.s_type = CONFIGFS_ROOT,
.s_iattr = NULL,
};
static int configfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
struct dentry *root;
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 19:29:47 +07:00
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = CONFIGFS_MAGIC;
sb->s_op = &configfs_ops;
sb->s_time_gran = 1;
inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
&configfs_root, sb);
if (inode) {
inode->i_op = &configfs_root_inode_operations;
inode->i_fop = &configfs_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
} else {
pr_debug("could not get root inode\n");
return -ENOMEM;
}
root = d_make_root(inode);
if (!root) {
pr_debug("%s: could not get root dentry!\n",__func__);
return -ENOMEM;
}
config_group_init(&configfs_root_group);
configfs_root_group.cg_item.ci_dentry = root;
root->d_fsdata = &configfs_root;
sb->s_root = root;
sb->s_d_op = &configfs_dentry_ops; /* the rest get that */
return 0;
}
static int configfs_get_tree(struct fs_context *fc)
{
return get_tree_single(fc, configfs_fill_super);
}
static const struct fs_context_operations configfs_context_ops = {
.get_tree = configfs_get_tree,
};
static int configfs_init_fs_context(struct fs_context *fc)
{
fc->ops = &configfs_context_ops;
return 0;
}
static struct file_system_type configfs_fs_type = {
.owner = THIS_MODULE,
.name = "configfs",
.init_fs_context = configfs_init_fs_context,
.kill_sb = kill_litter_super,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 10:39:14 +07:00
MODULE_ALIAS_FS("configfs");
struct dentry *configfs_pin_fs(void)
{
int err = simple_pin_fs(&configfs_fs_type, &configfs_mount,
&configfs_mnt_count);
return err ? ERR_PTR(err) : configfs_mount->mnt_root;
}
void configfs_release_fs(void)
{
simple_release_fs(&configfs_mount, &configfs_mnt_count);
}
static int __init configfs_init(void)
{
int err = -ENOMEM;
configfs_dir_cachep = kmem_cache_create("configfs_dir_cache",
sizeof(struct configfs_dirent),
0, 0, NULL);
if (!configfs_dir_cachep)
goto out;
err = sysfs_create_mount_point(kernel_kobj, "config");
if (err)
goto out2;
err = register_filesystem(&configfs_fs_type);
if (err)
goto out3;
return 0;
out3:
pr_err("Unable to register filesystem!\n");
sysfs_remove_mount_point(kernel_kobj, "config");
out2:
kmem_cache_destroy(configfs_dir_cachep);
configfs_dir_cachep = NULL;
out:
return err;
}
static void __exit configfs_exit(void)
{
unregister_filesystem(&configfs_fs_type);
sysfs_remove_mount_point(kernel_kobj, "config");
kmem_cache_destroy(configfs_dir_cachep);
configfs_dir_cachep = NULL;
}
MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");
MODULE_VERSION("0.0.2");
MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration.");
core_initcall(configfs_init);
module_exit(configfs_exit);