linux/fs/proc/internal.h

300 lines
8.2 KiB
C
Raw Normal View History

/* Internal procfs definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/binfmts.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
struct ctl_table_header;
struct mempolicy;
/*
* 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.
*
* parent/subdir are used for the directory structure (every /proc file has a
* parent, but "subdir" is empty for all non-directory entries).
* subdir_node is used to build the rb tree "subdir" of the parent.
*/
struct proc_dir_entry {
unsigned int low_ino;
umode_t mode;
nlink_t nlink;
kuid_t uid;
kgid_t gid;
loff_t size;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
struct proc_dir_entry *parent;
struct rb_root subdir;
struct rb_node subdir_node;
void *data;
atomic_t count; /* use count */
atomic_t in_use; /* number of callers into module in progress; */
/* negative -> it's going away RSN */
struct completion *pde_unload_completion;
struct list_head pde_openers; /* who did ->open, but not ->release */
spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
u8 namelen;
char name[];
} __randomize_layout;
union proc_op {
int (*proc_get_link)(struct dentry *, struct path *);
int (*proc_show)(struct seq_file *m,
struct pid_namespace *ns, struct pid *pid,
struct task_struct *task);
};
struct proc_inode {
struct pid *pid;
unsigned int fd;
union proc_op op;
struct proc_dir_entry *pde;
struct ctl_table_header *sysctl;
struct ctl_table *sysctl_entry;
proc: Fix proc_sys_prune_dcache to hold a sb reference Andrei Vagin writes: FYI: This bug has been reproduced on 4.11.7 > BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo} still in use (1) [unmount of proc proc] > ------------[ cut here ]------------ > WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80 > CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1 > Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015 > Workqueue: events proc_cleanup_work > Call Trace: > dump_stack+0x63/0x86 > __warn+0xcb/0xf0 > warn_slowpath_null+0x1d/0x20 > umount_check+0x6e/0x80 > d_walk+0xc6/0x270 > ? dentry_free+0x80/0x80 > do_one_tree+0x26/0x40 > shrink_dcache_for_umount+0x2d/0x90 > generic_shutdown_super+0x1f/0xf0 > kill_anon_super+0x12/0x20 > proc_kill_sb+0x40/0x50 > deactivate_locked_super+0x43/0x70 > deactivate_super+0x5a/0x60 > cleanup_mnt+0x3f/0x90 > mntput_no_expire+0x13b/0x190 > kern_unmount+0x3e/0x50 > pid_ns_release_proc+0x15/0x20 > proc_cleanup_work+0x15/0x20 > process_one_work+0x197/0x450 > worker_thread+0x4e/0x4a0 > kthread+0x109/0x140 > ? process_one_work+0x450/0x450 > ? kthread_park+0x90/0x90 > ret_from_fork+0x2c/0x40 > ---[ end trace e1c109611e5d0b41 ]--- > VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds. Have a nice day... > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: _raw_spin_lock+0xc/0x30 > PGD 0 Fix this by taking a reference to the super block in proc_sys_prune_dcache. The superblock reference is the core of the fix however the sysctl_inodes list is converted to a hlist so that hlist_del_init_rcu may be used. This allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while not causing problems for proc_sys_evict_inode when if it later choses to remove the inode from the sysctl_inodes list. Removing inodes from the sysctl_inodes list allows proc_sys_prune_dcache to have a progress guarantee, while still being able to drop all locks. The fact that head->unregistering is set in start_unregistering ensures that no more inodes will be added to the the sysctl_inodes list. Previously the code did a dance where it delayed calling iput until the next entry in the list was being considered to ensure the inode remained on the sysctl_inodes list until the next entry was walked to. The structure of the loop in this patch does not need that so is much easier to understand and maintain. Cc: stable@vger.kernel.org Reported-by: Andrei Vagin <avagin@gmail.com> Tested-by: Andrei Vagin <avagin@openvz.org> Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.") Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering") Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2017-07-06 21:41:06 +08:00
struct hlist_node sysctl_inodes;
const struct proc_ns_operations *ns_ops;
struct inode vfs_inode;
} __randomize_layout;
/*
* General functions
*/
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 void *__PDE_DATA(const struct inode *inode)
{
return PDE(inode)->data;
}
static inline struct pid *proc_pid(struct inode *inode)
{
return PROC_I(inode)->pid;
}
static inline struct task_struct *get_proc_task(struct inode *inode)
{
return get_pid_task(proc_pid(inode), PIDTYPE_PID);
}
void task_dump_owner(struct task_struct *task, mode_t mode,
kuid_t *ruid, kgid_t *rgid);
static inline unsigned name_to_int(const struct qstr *qstr)
{
const char *name = qstr->name;
int len = qstr->len;
unsigned n = 0;
if (len > 1 && *name == '0')
goto out;
while (len-- > 0) {
unsigned c = *name++ - '0';
if (c > 9)
goto out;
if (n >= (~0U-9)/10)
goto out;
n *= 10;
n += c;
}
return n;
out:
return ~0U;
}
/*
* 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
/*
* array.c
*/
extern const struct file_operations proc_tid_children_operations;
extern int proc_tid_stat(struct seq_file *, struct pid_namespace *,
struct pid *, struct task_struct *);
extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *,
struct pid *, struct task_struct *);
extern int proc_pid_status(struct seq_file *, struct pid_namespace *,
struct pid *, struct task_struct *);
extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
struct pid *, struct task_struct *);
/*
* base.c
*/
extern const struct dentry_operations pid_dentry_operations;
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern int proc_setattr(struct dentry *, struct iattr *);
extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
extern int pid_revalidate(struct dentry *, unsigned int);
extern int pid_delete_dentry(const struct dentry *);
extern int proc_pid_readdir(struct file *, struct dir_context *);
extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int);
extern loff_t mem_lseek(struct file *, loff_t, int);
/* Lookups */
typedef int instantiate_t(struct inode *, struct dentry *,
struct task_struct *, const void *);
extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int,
instantiate_t, struct task_struct *, const void *);
/*
* generic.c
*/
extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *,
struct dentry *);
extern int proc_readdir(struct file *, struct dir_context *);
extern int proc_readdir_de(struct proc_dir_entry *, struct file *, struct dir_context *);
static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
{
atomic_inc(&pde->count);
return pde;
}
extern void pde_put(struct proc_dir_entry *);
static inline bool is_empty_pde(const struct proc_dir_entry *pde)
{
return S_ISDIR(pde->mode) && !pde->proc_iops;
}
/*
* inode.c
*/
struct pde_opener {
struct file *file;
struct list_head lh;
bool closing;
struct completion *c;
};
extern const struct inode_operations proc_link_inode_operations;
extern const struct inode_operations proc_pid_link_inode_operations;
extern void proc_init_inodecache(void);
void set_proc_pid_nlink(void);
extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
extern int proc_fill_super(struct super_block *, void *data, int flags);
extern void proc_entry_rundown(struct proc_dir_entry *);
/*
* proc_namespaces.c
*/
extern const struct inode_operations proc_ns_dir_inode_operations;
extern const struct file_operations proc_ns_dir_operations;
/*
* proc_net.c
*/
extern const struct file_operations proc_net_operations;
extern const struct inode_operations proc_net_inode_operations;
#ifdef CONFIG_NET
extern int proc_net_init(void);
#else
static inline int proc_net_init(void) { return 0; }
#endif
/*
* proc_self.c
*/
extern int proc_setup_self(struct super_block *);
/*
* proc_thread_self.c
*/
extern int proc_setup_thread_self(struct super_block *);
extern void proc_thread_self_init(void);
/*
* proc_sysctl.c
*/
#ifdef CONFIG_PROC_SYSCTL
extern int proc_sys_init(void);
extern void proc_sys_evict_inode(struct inode *inode,
struct ctl_table_header *head);
#else
static inline void proc_sys_init(void) { }
static inline void proc_sys_evict_inode(struct inode *inode,
struct ctl_table_header *head) { }
#endif
/*
* proc_tty.c
*/
#ifdef CONFIG_TTY
extern void proc_tty_init(void);
#else
static inline void proc_tty_init(void) {}
#endif
/*
* root.c
*/
extern struct proc_dir_entry proc_root;
extern int proc_parse_options(char *options, struct pid_namespace *pid);
extern void proc_self_init(void);
extern int proc_remount(struct super_block *, int *, char *);
/*
* task_[no]mmu.c
*/
struct proc_maps_private {
struct inode *inode;
struct task_struct *task;
fs/proc/task_mmu.c: shift mm_access() from m_start() to proc_maps_open() A simple test-case from Kirill Shutemov cat /proc/self/maps >/dev/null chmod +x /proc/self/net/packet exec /proc/self/net/packet makes lockdep unhappy, cat/exec take seq_file->lock + cred_guard_mutex in the opposite order. It's a false positive and probably we should not allow "chmod +x" on proc files. Still I think that we should avoid mm_access() and cred_guard_mutex in sys_read() paths, security checking should happen at open time. Besides, this doesn't even look right if the task changes its ->mm between m_stop() and m_start(). Add the new "mm_struct *mm" member into struct proc_maps_private and change proc_maps_open() to initialize it using proc_mem_open(). Change m_start() to use priv->mm if atomic_inc_not_zero(mm_users) succeeds or return NULL (eof) otherwise. The only complication is that proc_maps_open() users should additionally do mmdrop() in fop->release(), add the new proc_map_release() helper for that. Note: this is the user-visible change, if the task execs after open("maps") the new ->mm won't be visible via this file. I hope this is fine, and this matches /proc/pid/mem bahaviour. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reported-by: "Kirill A. Shutemov" <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 06:25:26 +08:00
struct mm_struct *mm;
#ifdef CONFIG_MMU
struct vm_area_struct *tail_vma;
#endif
#ifdef CONFIG_NUMA
struct mempolicy *task_mempolicy;
#endif
} __randomize_layout;
struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
extern const struct file_operations proc_pid_maps_operations;
extern const struct file_operations proc_tid_maps_operations;
extern const struct file_operations proc_pid_numa_maps_operations;
extern const struct file_operations proc_tid_numa_maps_operations;
extern const struct file_operations proc_pid_smaps_operations;
extern const struct file_operations proc_tid_smaps_operations;
extern const struct file_operations proc_clear_refs_operations;
extern const struct file_operations proc_pagemap_operations;
extern unsigned long task_vsize(struct mm_struct *);
extern unsigned long task_statm(struct mm_struct *,
unsigned long *, unsigned long *,
unsigned long *, unsigned long *);
extern void task_mem(struct seq_file *, struct mm_struct *);