linux-stable/fs/proc/internal.h

321 lines
9.1 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;
union {
const struct proc_ops *proc_ops;
const struct file_operations *proc_dir_ops;
};
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;
proc: faster open/read/close with "permanent" files Now that "struct proc_ops" exist we can start putting there stuff which could not fly with VFS "struct file_operations"... Most of fs/proc/inode.c file is dedicated to make open/read/.../close reliable in the event of disappearing /proc entries which usually happens if module is getting removed. Files like /proc/cpuinfo which never disappear simply do not need such protection. Save 2 atomic ops, 1 allocation, 1 free per open/read/close sequence for such "permanent" files. Enable "permanent" flag for /proc/cpuinfo /proc/kmsg /proc/modules /proc/slabinfo /proc/stat /proc/sysvipc/* /proc/swaps More will come once I figure out foolproof way to prevent out module authors from marking their stuff "permanent" for performance reasons when it is not. This should help with scalability: benchmark is "read /proc/cpuinfo R times by N threads scattered over the system". N R t, s (before) t, s (after) ----------------------------------------------------- 64 4096 1.582458 1.530502 -3.2% 256 4096 6.371926 6.125168 -3.9% 1024 4096 25.64888 24.47528 -4.6% Benchmark source: #include <chrono> #include <iostream> #include <thread> #include <vector> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> const int NR_CPUS = sysconf(_SC_NPROCESSORS_ONLN); int N; const char *filename; int R; int xxx = 0; int glue(int n) { cpu_set_t m; CPU_ZERO(&m); CPU_SET(n, &m); return sched_setaffinity(0, sizeof(cpu_set_t), &m); } void f(int n) { glue(n % NR_CPUS); while (*(volatile int *)&xxx == 0) { } for (int i = 0; i < R; i++) { int fd = open(filename, O_RDONLY); char buf[4096]; ssize_t rv = read(fd, buf, sizeof(buf)); asm volatile ("" :: "g" (rv)); close(fd); } } int main(int argc, char *argv[]) { if (argc < 4) { std::cerr << "usage: " << argv[0] << ' ' << "N /proc/filename R "; return 1; } N = atoi(argv[1]); filename = argv[2]; R = atoi(argv[3]); for (int i = 0; i < NR_CPUS; i++) { if (glue(i) == 0) break; } std::vector<std::thread> T; T.reserve(N); for (int i = 0; i < N; i++) { T.emplace_back(f, i); } auto t0 = std::chrono::system_clock::now(); { *(volatile int *)&xxx = 1; for (auto& t: T) { t.join(); } } auto t1 = std::chrono::system_clock::now(); std::chrono::duration<double> dt = t1 - t0; std::cout << dt.count() << ' '; return 0; } P.S.: Explicit randomization marker is added because adding non-function pointer will silently disable structure layout randomization. [akpm@linux-foundation.org: coding style fixes] Reported-by: kbuild test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Link: http://lkml.kernel.org/r/20200222201539.GA22576@avx2 Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 03:09:01 +00:00
u8 flags;
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))
proc: faster open/read/close with "permanent" files Now that "struct proc_ops" exist we can start putting there stuff which could not fly with VFS "struct file_operations"... Most of fs/proc/inode.c file is dedicated to make open/read/.../close reliable in the event of disappearing /proc entries which usually happens if module is getting removed. Files like /proc/cpuinfo which never disappear simply do not need such protection. Save 2 atomic ops, 1 allocation, 1 free per open/read/close sequence for such "permanent" files. Enable "permanent" flag for /proc/cpuinfo /proc/kmsg /proc/modules /proc/slabinfo /proc/stat /proc/sysvipc/* /proc/swaps More will come once I figure out foolproof way to prevent out module authors from marking their stuff "permanent" for performance reasons when it is not. This should help with scalability: benchmark is "read /proc/cpuinfo R times by N threads scattered over the system". N R t, s (before) t, s (after) ----------------------------------------------------- 64 4096 1.582458 1.530502 -3.2% 256 4096 6.371926 6.125168 -3.9% 1024 4096 25.64888 24.47528 -4.6% Benchmark source: #include <chrono> #include <iostream> #include <thread> #include <vector> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> const int NR_CPUS = sysconf(_SC_NPROCESSORS_ONLN); int N; const char *filename; int R; int xxx = 0; int glue(int n) { cpu_set_t m; CPU_ZERO(&m); CPU_SET(n, &m); return sched_setaffinity(0, sizeof(cpu_set_t), &m); } void f(int n) { glue(n % NR_CPUS); while (*(volatile int *)&xxx == 0) { } for (int i = 0; i < R; i++) { int fd = open(filename, O_RDONLY); char buf[4096]; ssize_t rv = read(fd, buf, sizeof(buf)); asm volatile ("" :: "g" (rv)); close(fd); } } int main(int argc, char *argv[]) { if (argc < 4) { std::cerr << "usage: " << argv[0] << ' ' << "N /proc/filename R "; return 1; } N = atoi(argv[1]); filename = argv[2]; R = atoi(argv[3]); for (int i = 0; i < NR_CPUS; i++) { if (glue(i) == 0) break; } std::vector<std::thread> T; T.reserve(N); for (int i = 0; i < N; i++) { T.emplace_back(f, i); } auto t0 = std::chrono::system_clock::now(); { *(volatile int *)&xxx = 1; for (auto& t: T) { t.join(); } } auto t1 = std::chrono::system_clock::now(); std::chrono::duration<double> dt = t1 - t0; std::cout << dt.count() << ' '; return 0; } P.S.: Explicit randomization marker is added because adding non-function pointer will silently disable structure layout randomization. [akpm@linux-foundation.org: coding style fixes] Reported-by: kbuild test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Joe Perches <joe@perches.com> Link: http://lkml.kernel.org/r/20200222201539.GA22576@avx2 Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 03:09:01 +00:00
static inline bool pde_is_permanent(const struct proc_dir_entry *pde)
{
return pde->flags & PROC_ENTRY_PERMANENT;
}
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;
struct hlist_node sibling_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;
extern int pid_getattr(struct user_namespace *, const struct path *,
struct kstat *, u32, unsigned int);
extern int proc_setattr(struct user_namespace *, struct dentry *,
struct iattr *);
proc: Use a list of inodes to flush from proc Rework the flushing of proc to use a list of directory inodes that need to be flushed. The list is kept on struct pid not on struct task_struct, as there is a fixed connection between proc inodes and pids but at least for the case of de_thread the pid of a task_struct changes. This removes the dependency on proc_mnt which allows for different mounts of proc having different mount options even in the same pid namespace and this allows for the removal of proc_mnt which will trivially the first mount of proc to honor it's mount options. This flushing remains an optimization. The functions pid_delete_dentry and pid_revalidate ensure that ordinary dcache management will not attempt to use dentries past the point their respective task has died. When unused the shrinker will eventually be able to remove these dentries. There is a case in de_thread where proc_flush_pid can be called early for a given pid. Which winds up being safe (if suboptimal) as this is just an optiimization. Only pid directories are put on the list as the other per pid files are children of those directories and d_invalidate on the directory will get them as well. So that the pid can be used during flushing it's reference count is taken in release_task and dropped in proc_flush_pid. Further the call of proc_flush_pid is moved after the tasklist_lock is released in release_task so that it is certain that the pid has already been unhashed when flushing it taking place. This removes a small race where a dentry could recreated. As struct pid is supposed to be small and I need a per pid lock I reuse the only lock that currently exists in struct pid the the wait_pidfd.lock. The net result is that this adds all of this functionality with just a little extra list management overhead and a single extra pointer in struct pid. v2: Initialize pid->inodes. I somehow failed to get that initialization into the initial version of the patch. A boot failure was reported by "kernel test robot <lkp@intel.com>", and failure to initialize that pid->inodes matches all of the reported symptoms. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2020-02-20 00:22:26 +00:00
extern void proc_pid_evict_inode(struct proc_inode *);
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 void pde_get(struct proc_dir_entry *pde)
{
refcount_inc(&pde->refcnt);
}
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 list_head lh;
struct file *file;
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 proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock);
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 *);
extern const struct dentry_operations proc_net_dentry_ops;
static inline void pde_force_lookup(struct proc_dir_entry *pde)
{
/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
pde->proc_dops = &proc_net_dentry_ops;
}