linux/fs/proc/internal.h

302 lines
8.5 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/* Internal procfs definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
#include <linux/refcount.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 {
fs/proc/internal.h: rearrange struct proc_dir_entry struct proc_dir_entry became bit messy over years: * move 16-bit ->mode_t before namelen to get rid of padding * make ->in_use first field: it seems to be most used resulting in smaller code on x86_64 (defconfig): add/remove: 0/0 grow/shrink: 7/13 up/down: 24/-67 (-43) Function old new delta proc_readdir_de 451 455 +4 proc_get_inode 282 286 +4 pde_put 65 69 +4 remove_proc_subtree 294 297 +3 remove_proc_entry 297 300 +3 proc_register 295 298 +3 proc_notify_change 94 97 +3 unuse_pde 27 26 -1 proc_reg_write 89 85 -4 proc_reg_unlocked_ioctl 85 81 -4 proc_reg_read 89 85 -4 proc_reg_llseek 87 83 -4 proc_reg_get_unmapped_area 123 119 -4 proc_entry_rundown 139 135 -4 proc_reg_poll 91 85 -6 proc_reg_mmap 79 73 -6 proc_get_link 55 49 -6 proc_reg_release 108 101 -7 proc_reg_open 298 291 -7 close_pdeo 228 218 -10 * move writeable fields together to a first cacheline (on x86_64), those include * ->in_use: reference count, taken every open/read/write/close etc * ->count: reference count, taken at readdir on every entry * ->pde_openers: tracks (nearly) every open, dirtied * ->pde_unload_lock: spinlock protecting ->pde_openers * ->proc_iops, ->proc_fops, ->data: writeonce fields, used right together with previous group. * other rarely written fields go into 1st/2nd and 2nd/3rd cacheline on 32-bit and 64-bit respectively. Additionally on 32-bit, ->subdir, ->subdir_node, ->namelen, ->name go fully into 2nd cacheline, separated from writeable fields. They are all used during lookup. Link: http://lkml.kernel.org/r/20171220215914.GA7877@avx2 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-06 23:37:18 +00:00
/*
* number of callers into module in progress;
* negative -> it's going away RSN
*/
atomic_t in_use;
refcount_t refcnt;
fs/proc/internal.h: rearrange struct proc_dir_entry struct proc_dir_entry became bit messy over years: * move 16-bit ->mode_t before namelen to get rid of padding * make ->in_use first field: it seems to be most used resulting in smaller code on x86_64 (defconfig): add/remove: 0/0 grow/shrink: 7/13 up/down: 24/-67 (-43) Function old new delta proc_readdir_de 451 455 +4 proc_get_inode 282 286 +4 pde_put 65 69 +4 remove_proc_subtree 294 297 +3 remove_proc_entry 297 300 +3 proc_register 295 298 +3 proc_notify_change 94 97 +3 unuse_pde 27 26 -1 proc_reg_write 89 85 -4 proc_reg_unlocked_ioctl 85 81 -4 proc_reg_read 89 85 -4 proc_reg_llseek 87 83 -4 proc_reg_get_unmapped_area 123 119 -4 proc_entry_rundown 139 135 -4 proc_reg_poll 91 85 -6 proc_reg_mmap 79 73 -6 proc_get_link 55 49 -6 proc_reg_release 108 101 -7 proc_reg_open 298 291 -7 close_pdeo 228 218 -10 * move writeable fields together to a first cacheline (on x86_64), those include * ->in_use: reference count, taken every open/read/write/close etc * ->count: reference count, taken at readdir on every entry * ->pde_openers: tracks (nearly) every open, dirtied * ->pde_unload_lock: spinlock protecting ->pde_openers * ->proc_iops, ->proc_fops, ->data: writeonce fields, used right together with previous group. * other rarely written fields go into 1st/2nd and 2nd/3rd cacheline on 32-bit and 64-bit respectively. Additionally on 32-bit, ->subdir, ->subdir_node, ->namelen, ->name go fully into 2nd cacheline, separated from writeable fields. They are all used during lookup. Link: http://lkml.kernel.org/r/20171220215914.GA7877@avx2 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-06 23:37:18 +00:00
struct list_head pde_openers; /* who did ->open, but not ->release */
/* protects ->pde_openers and all struct pde_opener instances */
spinlock_t pde_unload_lock;
fs/proc/internal.h: rearrange struct proc_dir_entry struct proc_dir_entry became bit messy over years: * move 16-bit ->mode_t before namelen to get rid of padding * make ->in_use first field: it seems to be most used resulting in smaller code on x86_64 (defconfig): add/remove: 0/0 grow/shrink: 7/13 up/down: 24/-67 (-43) Function old new delta proc_readdir_de 451 455 +4 proc_get_inode 282 286 +4 pde_put 65 69 +4 remove_proc_subtree 294 297 +3 remove_proc_entry 297 300 +3 proc_register 295 298 +3 proc_notify_change 94 97 +3 unuse_pde 27 26 -1 proc_reg_write 89 85 -4 proc_reg_unlocked_ioctl 85 81 -4 proc_reg_read 89 85 -4 proc_reg_llseek 87 83 -4 proc_reg_get_unmapped_area 123 119 -4 proc_entry_rundown 139 135 -4 proc_reg_poll 91 85 -6 proc_reg_mmap 79 73 -6 proc_get_link 55 49 -6 proc_reg_release 108 101 -7 proc_reg_open 298 291 -7 close_pdeo 228 218 -10 * move writeable fields together to a first cacheline (on x86_64), those include * ->in_use: reference count, taken every open/read/write/close etc * ->count: reference count, taken at readdir on every entry * ->pde_openers: tracks (nearly) every open, dirtied * ->pde_unload_lock: spinlock protecting ->pde_openers * ->proc_iops, ->proc_fops, ->data: writeonce fields, used right together with previous group. * other rarely written fields go into 1st/2nd and 2nd/3rd cacheline on 32-bit and 64-bit respectively. Additionally on 32-bit, ->subdir, ->subdir_node, ->namelen, ->name go fully into 2nd cacheline, separated from writeable fields. They are all used during lookup. Link: http://lkml.kernel.org/r/20171220215914.GA7877@avx2 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-06 23:37:18 +00:00
struct completion *pde_unload_completion;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
const struct dentry_operations *proc_dops;
union {
const struct seq_operations *seq_ops;
int (*single_show)(struct seq_file *, void *);
};
proc_write_t write;
fs/proc/internal.h: rearrange struct proc_dir_entry struct proc_dir_entry became bit messy over years: * move 16-bit ->mode_t before namelen to get rid of padding * make ->in_use first field: it seems to be most used resulting in smaller code on x86_64 (defconfig): add/remove: 0/0 grow/shrink: 7/13 up/down: 24/-67 (-43) Function old new delta proc_readdir_de 451 455 +4 proc_get_inode 282 286 +4 pde_put 65 69 +4 remove_proc_subtree 294 297 +3 remove_proc_entry 297 300 +3 proc_register 295 298 +3 proc_notify_change 94 97 +3 unuse_pde 27 26 -1 proc_reg_write 89 85 -4 proc_reg_unlocked_ioctl 85 81 -4 proc_reg_read 89 85 -4 proc_reg_llseek 87 83 -4 proc_reg_get_unmapped_area 123 119 -4 proc_entry_rundown 139 135 -4 proc_reg_poll 91 85 -6 proc_reg_mmap 79 73 -6 proc_get_link 55 49 -6 proc_reg_release 108 101 -7 proc_reg_open 298 291 -7 close_pdeo 228 218 -10 * move writeable fields together to a first cacheline (on x86_64), those include * ->in_use: reference count, taken every open/read/write/close etc * ->count: reference count, taken at readdir on every entry * ->pde_openers: tracks (nearly) every open, dirtied * ->pde_unload_lock: spinlock protecting ->pde_openers * ->proc_iops, ->proc_fops, ->data: writeonce fields, used right together with previous group. * other rarely written fields go into 1st/2nd and 2nd/3rd cacheline on 32-bit and 64-bit respectively. Additionally on 32-bit, ->subdir, ->subdir_node, ->namelen, ->name go fully into 2nd cacheline, separated from writeable fields. They are all used during lookup. Link: http://lkml.kernel.org/r/20171220215914.GA7877@avx2 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-06 23:37:18 +00:00
void *data;
unsigned int state_size;
unsigned int low_ino;
nlink_t nlink;
kuid_t uid;
kgid_t gid;
loff_t size;
struct proc_dir_entry *parent;
struct rb_root subdir;
struct rb_node subdir_node;
char *name;
fs/proc/internal.h: rearrange struct proc_dir_entry struct proc_dir_entry became bit messy over years: * move 16-bit ->mode_t before namelen to get rid of padding * make ->in_use first field: it seems to be most used resulting in smaller code on x86_64 (defconfig): add/remove: 0/0 grow/shrink: 7/13 up/down: 24/-67 (-43) Function old new delta proc_readdir_de 451 455 +4 proc_get_inode 282 286 +4 pde_put 65 69 +4 remove_proc_subtree 294 297 +3 remove_proc_entry 297 300 +3 proc_register 295 298 +3 proc_notify_change 94 97 +3 unuse_pde 27 26 -1 proc_reg_write 89 85 -4 proc_reg_unlocked_ioctl 85 81 -4 proc_reg_read 89 85 -4 proc_reg_llseek 87 83 -4 proc_reg_get_unmapped_area 123 119 -4 proc_entry_rundown 139 135 -4 proc_reg_poll 91 85 -6 proc_reg_mmap 79 73 -6 proc_get_link 55 49 -6 proc_reg_release 108 101 -7 proc_reg_open 298 291 -7 close_pdeo 228 218 -10 * move writeable fields together to a first cacheline (on x86_64), those include * ->in_use: reference count, taken every open/read/write/close etc * ->count: reference count, taken at readdir on every entry * ->pde_openers: tracks (nearly) every open, dirtied * ->pde_unload_lock: spinlock protecting ->pde_openers * ->proc_iops, ->proc_fops, ->data: writeonce fields, used right together with previous group. * other rarely written fields go into 1st/2nd and 2nd/3rd cacheline on 32-bit and 64-bit respectively. Additionally on 32-bit, ->subdir, ->subdir_node, ->namelen, ->name go fully into 2nd cacheline, separated from writeable fields. They are all used during lookup. Link: http://lkml.kernel.org/r/20171220215914.GA7877@avx2 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-06 23:37:18 +00:00
umode_t mode;
u8 namelen;
char inline_name[];
} __randomize_layout;
#define SIZEOF_PDE ( \
sizeof(struct proc_dir_entry) < 128 ? 128 : \
sizeof(struct proc_dir_entry) < 192 ? 192 : \
sizeof(struct proc_dir_entry) < 256 ? 256 : \
sizeof(struct proc_dir_entry) < 512 ? 512 : \
0)
#define SIZEOF_PDE_INLINE_NAME (SIZEOF_PDE - sizeof(struct proc_dir_entry))
extern struct kmem_cache *proc_dir_entry_cache;
void pde_free(struct proc_dir_entry *pde);
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);
const char *lsm;
};
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 13:41:06 +00:00
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(const struct inode *inode)
{
return PROC_I(inode)->pid;
}
static inline struct task_struct *get_proc_task(const struct inode *inode)
{
return get_pid_task(proc_pid(inode), PIDTYPE_PID);
}
void task_dump_owner(struct task_struct *task, umode_t mode,
kuid_t *ruid, kgid_t *rgid);
unsigned name_to_int(const struct qstr *qstr);
/*
* 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 void proc_task_name(struct seq_file *m, struct task_struct *p,
bool escape);
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>
2017-01-31 16:46:22 +00:00
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 void pid_update_inode(struct task_struct *, struct inode *);
extern int pid_delete_dentry(const struct dentry *);
extern int proc_pid_readdir(struct file *, struct dir_context *);
struct dentry *proc_pid_lookup(struct dentry *, unsigned int);
extern loff_t mem_lseek(struct file *, loff_t, int);
/* Lookups */
typedef struct dentry *instantiate_t(struct dentry *,
struct task_struct *, const void *);
bool proc_fill_cache(struct file *, struct dir_context *, const char *, unsigned int,
instantiate_t, struct task_struct *, const void *);
/*
* generic.c
*/
struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
struct proc_dir_entry **parent, void *data);
struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
struct proc_dir_entry *dp);
extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *);
extern int proc_readdir(struct file *, struct dir_context *);
int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *);
static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
{
refcount_inc(&pde->refcnt);
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;
}
extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, loff_t *);
/*
* inode.c
*/
struct pde_opener {
struct file *file;
struct list_head lh;
bool closing;
struct completion *c;
} __randomize_layout;
extern const struct inode_operations proc_link_inode_operations;
extern const struct inode_operations proc_pid_link_inode_operations;
extern const struct super_operations proc_sops;
void proc_init_kmemcache(void);
void set_proc_pid_nlink(void);
extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
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 void proc_self_init(void);
/*
* task_[no]mmu.c
*/
mm: add /proc/pid/smaps_rollup /proc/pid/smaps_rollup is a new proc file that improves the performance of user programs that determine aggregate memory statistics (e.g., total PSS) of a process. Android regularly "samples" the memory usage of various processes in order to balance its memory pool sizes. This sampling process involves opening /proc/pid/smaps and summing certain fields. For very large processes, sampling memory use this way can take several hundred milliseconds, due mostly to the overhead of the seq_printf calls in task_mmu.c. smaps_rollup improves the situation. It contains most of the fields of /proc/pid/smaps, but instead of a set of fields for each VMA, smaps_rollup instead contains one synthetic smaps-format entry representing the whole process. In the single smaps_rollup synthetic entry, each field is the summation of the corresponding field in all of the real-smaps VMAs. Using a common format for smaps_rollup and smaps allows userspace parsers to repurpose parsers meant for use with non-rollup smaps for smaps_rollup, and it allows userspace to switch between smaps_rollup and smaps at runtime (say, based on the availability of smaps_rollup in a given kernel) with minimal fuss. By using smaps_rollup instead of smaps, a caller can avoid the significant overhead of formatting, reading, and parsing each of a large process's potentially very numerous memory mappings. For sampling system_server's PSS in Android, we measured a 12x speedup, representing a savings of several hundred milliseconds. One alternative to a new per-process proc file would have been including PSS information in /proc/pid/status. We considered this option but thought that PSS would be too expensive (by a few orders of magnitude) to collect relative to what's already emitted as part of /proc/pid/status, and slowing every user of /proc/pid/status for the sake of readers that happen to want PSS feels wrong. The code itself works by reusing the existing VMA-walking framework we use for regular smaps generation and keeping the mem_size_stats structure around between VMA walks instead of using a fresh one for each VMA. In this way, summation happens automatically. We let seq_file walk over the VMAs just as it does for regular smaps and just emit nothing to the seq_file until we hit the last VMA. Benchmarks: using smaps: iterations:1000 pid:1163 pss:220023808 0m29.46s real 0m08.28s user 0m20.98s system using smaps_rollup: iterations:1000 pid:1163 pss:220702720 0m04.39s real 0m00.03s user 0m04.31s system We're using the PSS samples we collect asynchronously for system-management tasks like fine-tuning oom_adj_score, memory use tracking for debugging, application-level memory-use attribution, and deciding whether we want to kill large processes during system idle maintenance windows. Android has been using PSS for these purposes for a long time; as the average process VMA count has increased and and devices become more efficiency-conscious, PSS-collection inefficiency has started to matter more. IMHO, it'd be a lot safer to optimize the existing PSS-collection model, which has been fine-tuned over the years, instead of changing the memory tracking approach entirely to work around smaps-generation inefficiency. Tim said: : There are two main reasons why Android gathers PSS information: : : 1. Android devices can show the user the amount of memory used per : application via the settings app. This is a less important use case. : : 2. We log PSS to help identify leaks in applications. We have found : an enormous number of bugs (in the Android platform, in Google's own : apps, and in third-party applications) using this data. : : To do this, system_server (the main process in Android userspace) will : sample the PSS of a process three seconds after it changes state (for : example, app is launched and becomes the foreground application) and about : every ten minutes after that. The net result is that PSS collection is : regularly running on at least one process in the system (usually a few : times a minute while the screen is on, less when screen is off due to : suspend). PSS of a process is an incredibly useful stat to track, and we : aren't going to get rid of it. We've looked at some very hacky approaches : using RSS ("take the RSS of the target process, subtract the RSS of the : zygote process that is the parent of all Android apps") to reduce the : accounting time, but it regularly overestimated the memory used by 20+ : percent. Accordingly, I don't think that there's a good alternative to : using PSS. : : We started looking into PSS collection performance after we noticed random : frequency spikes while a phone's screen was off; occasionally, one of the : CPU clusters would ramp to a high frequency because there was 200-300ms of : constant CPU work from a single thread in the main Android userspace : process. The work causing the spike (which is reasonable governor : behavior given the amount of CPU time needed) was always PSS collection. : As a result, Android is burning more power than we should be on PSS : collection. : : The other issue (and why I'm less sure about improving smaps as a : long-term solution) is that the number of VMAs per process has increased : significantly from release to release. After trying to figure out why we : were seeing these 200-300ms PSS collection times on Android O but had not : noticed it in previous versions, we found that the number of VMAs in the : main system process increased by 50% from Android N to Android O (from : ~1800 to ~2700) and varying increases in every userspace process. Android : M to N also had an increase in the number of VMAs, although not as much. : I'm not sure why this is increasing so much over time, but thinking about : ASLR and ways to make ASLR better, I expect that this will continue to : increase going forward. I would not be surprised if we hit 5000 VMAs on : the main Android process (system_server) by 2020. : : If we assume that the number of VMAs is going to increase over time, then : doing anything we can do to reduce the overhead of each VMA during PSS : collection seems like the right way to go, and that means outputting an : aggregate statistic (to avoid whatever overhead there is per line in : writing smaps and in reading each line from userspace). Link: http://lkml.kernel.org/r/20170812022148.178293-1-dancol@google.com Signed-off-by: Daniel Colascione <dancol@google.com> Cc: Tim Murray <timmurray@google.com> Cc: Joel Fernandes <joelaf@google.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Sonny Rao <sonnyrao@chromium.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-06 23:25:08 +00:00
struct mem_size_stats;
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>
2014-10-09 22:25:26 +00:00
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_pid_numa_maps_operations;
extern const struct file_operations proc_pid_smaps_operations;
mm: add /proc/pid/smaps_rollup /proc/pid/smaps_rollup is a new proc file that improves the performance of user programs that determine aggregate memory statistics (e.g., total PSS) of a process. Android regularly "samples" the memory usage of various processes in order to balance its memory pool sizes. This sampling process involves opening /proc/pid/smaps and summing certain fields. For very large processes, sampling memory use this way can take several hundred milliseconds, due mostly to the overhead of the seq_printf calls in task_mmu.c. smaps_rollup improves the situation. It contains most of the fields of /proc/pid/smaps, but instead of a set of fields for each VMA, smaps_rollup instead contains one synthetic smaps-format entry representing the whole process. In the single smaps_rollup synthetic entry, each field is the summation of the corresponding field in all of the real-smaps VMAs. Using a common format for smaps_rollup and smaps allows userspace parsers to repurpose parsers meant for use with non-rollup smaps for smaps_rollup, and it allows userspace to switch between smaps_rollup and smaps at runtime (say, based on the availability of smaps_rollup in a given kernel) with minimal fuss. By using smaps_rollup instead of smaps, a caller can avoid the significant overhead of formatting, reading, and parsing each of a large process's potentially very numerous memory mappings. For sampling system_server's PSS in Android, we measured a 12x speedup, representing a savings of several hundred milliseconds. One alternative to a new per-process proc file would have been including PSS information in /proc/pid/status. We considered this option but thought that PSS would be too expensive (by a few orders of magnitude) to collect relative to what's already emitted as part of /proc/pid/status, and slowing every user of /proc/pid/status for the sake of readers that happen to want PSS feels wrong. The code itself works by reusing the existing VMA-walking framework we use for regular smaps generation and keeping the mem_size_stats structure around between VMA walks instead of using a fresh one for each VMA. In this way, summation happens automatically. We let seq_file walk over the VMAs just as it does for regular smaps and just emit nothing to the seq_file until we hit the last VMA. Benchmarks: using smaps: iterations:1000 pid:1163 pss:220023808 0m29.46s real 0m08.28s user 0m20.98s system using smaps_rollup: iterations:1000 pid:1163 pss:220702720 0m04.39s real 0m00.03s user 0m04.31s system We're using the PSS samples we collect asynchronously for system-management tasks like fine-tuning oom_adj_score, memory use tracking for debugging, application-level memory-use attribution, and deciding whether we want to kill large processes during system idle maintenance windows. Android has been using PSS for these purposes for a long time; as the average process VMA count has increased and and devices become more efficiency-conscious, PSS-collection inefficiency has started to matter more. IMHO, it'd be a lot safer to optimize the existing PSS-collection model, which has been fine-tuned over the years, instead of changing the memory tracking approach entirely to work around smaps-generation inefficiency. Tim said: : There are two main reasons why Android gathers PSS information: : : 1. Android devices can show the user the amount of memory used per : application via the settings app. This is a less important use case. : : 2. We log PSS to help identify leaks in applications. We have found : an enormous number of bugs (in the Android platform, in Google's own : apps, and in third-party applications) using this data. : : To do this, system_server (the main process in Android userspace) will : sample the PSS of a process three seconds after it changes state (for : example, app is launched and becomes the foreground application) and about : every ten minutes after that. The net result is that PSS collection is : regularly running on at least one process in the system (usually a few : times a minute while the screen is on, less when screen is off due to : suspend). PSS of a process is an incredibly useful stat to track, and we : aren't going to get rid of it. We've looked at some very hacky approaches : using RSS ("take the RSS of the target process, subtract the RSS of the : zygote process that is the parent of all Android apps") to reduce the : accounting time, but it regularly overestimated the memory used by 20+ : percent. Accordingly, I don't think that there's a good alternative to : using PSS. : : We started looking into PSS collection performance after we noticed random : frequency spikes while a phone's screen was off; occasionally, one of the : CPU clusters would ramp to a high frequency because there was 200-300ms of : constant CPU work from a single thread in the main Android userspace : process. The work causing the spike (which is reasonable governor : behavior given the amount of CPU time needed) was always PSS collection. : As a result, Android is burning more power than we should be on PSS : collection. : : The other issue (and why I'm less sure about improving smaps as a : long-term solution) is that the number of VMAs per process has increased : significantly from release to release. After trying to figure out why we : were seeing these 200-300ms PSS collection times on Android O but had not : noticed it in previous versions, we found that the number of VMAs in the : main system process increased by 50% from Android N to Android O (from : ~1800 to ~2700) and varying increases in every userspace process. Android : M to N also had an increase in the number of VMAs, although not as much. : I'm not sure why this is increasing so much over time, but thinking about : ASLR and ways to make ASLR better, I expect that this will continue to : increase going forward. I would not be surprised if we hit 5000 VMAs on : the main Android process (system_server) by 2020. : : If we assume that the number of VMAs is going to increase over time, then : doing anything we can do to reduce the overhead of each VMA during PSS : collection seems like the right way to go, and that means outputting an : aggregate statistic (to avoid whatever overhead there is per line in : writing smaps and in reading each line from userspace). Link: http://lkml.kernel.org/r/20170812022148.178293-1-dancol@google.com Signed-off-by: Daniel Colascione <dancol@google.com> Cc: Tim Murray <timmurray@google.com> Cc: Joel Fernandes <joelaf@google.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Sonny Rao <sonnyrao@chromium.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-06 23:25:08 +00:00
extern const struct file_operations proc_pid_smaps_rollup_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 *);