linux_dsm_epyc7002/include/linux/proc_fs.h
Denis V. Lunev 59b7435149 proc: introduce proc_create_data to setup de->data
This set of patches fixes an proc ->open'less usage due to ->proc_fops flip in
the most part of the kernel code.  The original OOPS is described in the
commit 2d3a4e3666:

    Typical PDE creation code looks like:

    	pde = create_proc_entry("foo", 0, NULL);
    	if (pde)
    		pde->proc_fops = &foo_proc_fops;

    Notice that PDE is first created, only then ->proc_fops is set up to
    final value. This is a problem because right after creation
    a) PDE is fully visible in /proc , and
    b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's
       possible to ->read without ->open (see one class of oopses below).

    The fix is new API called proc_create() which makes sure ->proc_fops are
    set up before gluing PDE to main tree. Typical new code looks like:

    	pde = proc_create("foo", 0, NULL, &foo_proc_fops);
    	if (!pde)
    		return -ENOMEM;

    Fix most networking users for a start.

    In the long run, create_proc_entry() for regular files will go.

In addition to this, proc_create_data is introduced to fix reading from
proc without PDE->data. The race is basically the same as above.

create_proc_entries is replaced in the entire kernel code as new method
is also simply better.

This patch:

The problem is the same as for de->proc_fops.  Right now PDE becomes visible
without data set.  So, the entry could be looked up without data.  This, in
most cases, will simply OOPS.

proc_create_data call is created to address this issue.  proc_create now
becomes a wrapper around it.

Signed-off-by: Denis V. Lunev <den@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Chris Mason <chris.mason@oracle.com>
Acked-by: David Howells <dhowells@redhat.com>
Cc: Dmitry Torokhov <dtor@mail.ru>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Grant Grundler <grundler@parisc-linux.org>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Cc: Haavard Skinnemoen <hskinnemoen@atmel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Jaroslav Kysela <perex@suse.cz>
Cc: Jeff Garzik <jgarzik@pobox.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Karsten Keil <kkeil@suse.de>
Cc: Kyle McMartin <kyle@parisc-linux.org>
Cc: Len Brown <lenb@kernel.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Nadia Derbey <Nadia.Derbey@bull.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Osterlund <petero2@telia.com>
Cc: Pierre Peiffer <peifferp@gmail.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 08:06:20 -07:00

319 lines
9.3 KiB
C

#ifndef _LINUX_PROC_FS_H
#define _LINUX_PROC_FS_H
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/spinlock.h>
#include <linux/magic.h>
#include <asm/atomic.h>
struct net;
struct completion;
/*
* The proc filesystem constants/structures
*/
/*
* Offset of the first process in the /proc root directory..
*/
#define FIRST_PROCESS_ENTRY 256
/* Worst case buffer size needed for holding an integer. */
#define PROC_NUMBUF 13
/*
* We always define these enumerators
*/
enum {
PROC_ROOT_INO = 1,
};
/*
* This is not completely implemented yet. The idea is to
* create an in-memory tree (like the actual /proc filesystem
* tree) of these proc_dir_entries, so that we can dynamically
* add new files to /proc.
*
* The "next" pointer creates a linked list of one /proc directory,
* while parent/subdir create the directory structure (every
* /proc file has a parent, but "subdir" is NULL for all
* non-directory entries).
*
* "owner" is used to protect module
* from unloading while proc_dir_entry is in use
*/
typedef int (read_proc_t)(char *page, char **start, off_t off,
int count, int *eof, void *data);
typedef int (write_proc_t)(struct file *file, const char __user *buffer,
unsigned long count, void *data);
struct proc_dir_entry {
unsigned int low_ino;
unsigned short namelen;
const char *name;
mode_t mode;
nlink_t nlink;
uid_t uid;
gid_t gid;
loff_t size;
const struct inode_operations *proc_iops;
/*
* NULL ->proc_fops means "PDE is going away RSN" or
* "PDE is just created". In either case, e.g. ->read_proc won't be
* called because it's too late or too early, respectively.
*
* If you're allocating ->proc_fops dynamically, save a pointer
* somewhere.
*/
const struct file_operations *proc_fops;
struct module *owner;
struct proc_dir_entry *next, *parent, *subdir;
void *data;
read_proc_t *read_proc;
write_proc_t *write_proc;
atomic_t count; /* use count */
int pde_users; /* number of callers into module in progress */
spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
struct completion *pde_unload_completion;
};
struct kcore_list {
struct kcore_list *next;
unsigned long addr;
size_t size;
};
struct vmcore {
struct list_head list;
unsigned long long paddr;
unsigned long long size;
loff_t offset;
};
#ifdef CONFIG_PROC_FS
extern struct proc_dir_entry *proc_root_kcore;
extern spinlock_t proc_subdir_lock;
extern void proc_root_init(void);
extern void proc_misc_init(void);
struct mm_struct;
void proc_flush_task(struct task_struct *task);
struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
unsigned long task_vsize(struct mm_struct *);
int task_statm(struct mm_struct *, int *, int *, int *, int *);
void task_mem(struct seq_file *, struct mm_struct *);
void clear_refs_smap(struct mm_struct *mm);
struct proc_dir_entry *de_get(struct proc_dir_entry *de);
void de_put(struct proc_dir_entry *de);
extern struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
struct proc_dir_entry *parent);
struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
struct proc_dir_entry *parent,
const struct file_operations *proc_fops,
void *data);
extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent);
extern struct vfsmount *proc_mnt;
struct pid_namespace;
extern int proc_fill_super(struct super_block *);
extern struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *);
/*
* These are generic /proc routines that use the internal
* "struct proc_dir_entry" tree to traverse the filesystem.
*
* The /proc root directory has extended versions to take care
* of the /proc/<pid> subdirectories.
*/
extern int proc_readdir(struct file *, void *, filldir_t);
extern struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
extern const struct file_operations proc_kcore_operations;
extern const struct file_operations proc_kmsg_operations;
extern const struct file_operations ppc_htab_operations;
extern int pid_ns_prepare_proc(struct pid_namespace *ns);
extern void pid_ns_release_proc(struct pid_namespace *ns);
/*
* proc_tty.c
*/
struct tty_driver;
extern void proc_tty_init(void);
extern void proc_tty_register_driver(struct tty_driver *driver);
extern void proc_tty_unregister_driver(struct tty_driver *driver);
/*
* proc_devtree.c
*/
#ifdef CONFIG_PROC_DEVICETREE
struct device_node;
struct property;
extern void proc_device_tree_init(void);
extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *);
extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop);
extern void proc_device_tree_remove_prop(struct proc_dir_entry *pde,
struct property *prop);
extern void proc_device_tree_update_prop(struct proc_dir_entry *pde,
struct property *newprop,
struct property *oldprop);
#endif /* CONFIG_PROC_DEVICETREE */
extern struct proc_dir_entry *proc_symlink(const char *,
struct proc_dir_entry *, const char *);
extern struct proc_dir_entry *proc_mkdir(const char *,struct proc_dir_entry *);
extern struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
struct proc_dir_entry *parent);
static inline struct proc_dir_entry *proc_create(const char *name, mode_t mode,
struct proc_dir_entry *parent, const struct file_operations *proc_fops)
{
return proc_create_data(name, mode, parent, proc_fops, NULL);
}
static inline struct proc_dir_entry *create_proc_read_entry(const char *name,
mode_t mode, struct proc_dir_entry *base,
read_proc_t *read_proc, void * data)
{
struct proc_dir_entry *res=create_proc_entry(name,mode,base);
if (res) {
res->read_proc=read_proc;
res->data=data;
}
return res;
}
extern struct proc_dir_entry *proc_net_fops_create(struct net *net,
const char *name, mode_t mode, const struct file_operations *fops);
extern void proc_net_remove(struct net *net, const char *name);
extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
struct proc_dir_entry *parent);
/* While the {get|set|dup}_mm_exe_file functions are for mm_structs, they are
* only needed to implement /proc/<pid>|self/exe so we define them here. */
extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern struct file *get_mm_exe_file(struct mm_struct *mm);
extern void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm);
#else
#define proc_net_fops_create(net, name, mode, fops) ({ (void)(mode), NULL; })
static inline void proc_net_remove(struct net *net, const char *name) {}
static inline void proc_flush_task(struct task_struct *task)
{
}
static inline struct proc_dir_entry *create_proc_entry(const char *name,
mode_t mode, struct proc_dir_entry *parent) { return NULL; }
static inline struct proc_dir_entry *proc_create(const char *name,
mode_t mode, struct proc_dir_entry *parent,
const struct file_operations *proc_fops)
{
return NULL;
}
static inline struct proc_dir_entry *proc_create_data(const char *name,
mode_t mode, struct proc_dir_entry *parent,
const struct file_operations *proc_fops, void *data)
{
return NULL;
}
#define remove_proc_entry(name, parent) do {} while (0)
static inline struct proc_dir_entry *proc_symlink(const char *name,
struct proc_dir_entry *parent,const char *dest) {return NULL;}
static inline struct proc_dir_entry *proc_mkdir(const char *name,
struct proc_dir_entry *parent) {return NULL;}
static inline struct proc_dir_entry *create_proc_read_entry(const char *name,
mode_t mode, struct proc_dir_entry *base,
read_proc_t *read_proc, void * data) { return NULL; }
struct tty_driver;
static inline void proc_tty_register_driver(struct tty_driver *driver) {};
static inline void proc_tty_unregister_driver(struct tty_driver *driver) {};
static inline int pid_ns_prepare_proc(struct pid_namespace *ns)
{
return 0;
}
static inline void pid_ns_release_proc(struct pid_namespace *ns)
{
}
static inline void set_mm_exe_file(struct mm_struct *mm,
struct file *new_exe_file)
{}
static inline struct file *get_mm_exe_file(struct mm_struct *mm)
{
return NULL;
}
static inline void dup_mm_exe_file(struct mm_struct *oldmm,
struct mm_struct *newmm)
{}
#endif /* CONFIG_PROC_FS */
#if !defined(CONFIG_PROC_KCORE)
static inline void kclist_add(struct kcore_list *new, void *addr, size_t size)
{
}
#else
extern void kclist_add(struct kcore_list *, void *, size_t);
#endif
union proc_op {
int (*proc_get_link)(struct inode *, struct path *);
int (*proc_read)(struct task_struct *task, char *page);
int (*proc_show)(struct seq_file *m,
struct pid_namespace *ns, struct pid *pid,
struct task_struct *task);
};
struct proc_inode {
struct pid *pid;
int fd;
union proc_op op;
struct proc_dir_entry *pde;
struct inode vfs_inode;
};
static inline struct proc_inode *PROC_I(const struct inode *inode)
{
return container_of(inode, struct proc_inode, vfs_inode);
}
static inline struct proc_dir_entry *PDE(const struct inode *inode)
{
return PROC_I(inode)->pde;
}
static inline struct net *PDE_NET(struct proc_dir_entry *pde)
{
return pde->parent->data;
}
struct net *get_proc_net(const struct inode *inode);
struct proc_maps_private {
struct pid *pid;
struct task_struct *task;
#ifdef CONFIG_MMU
struct vm_area_struct *tail_vma;
#endif
};
#endif /* _LINUX_PROC_FS_H */