linux/fs/proc/internal.h
Alexey Dobriyan d919b33daf 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 10:43:42 -07:00

313 lines
8.8 KiB
C

/* 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 {
/*
* number of callers into module in progress;
* negative -> it's going away RSN
*/
atomic_t in_use;
refcount_t refcnt;
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;
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;
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;
umode_t mode;
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))
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(const struct path *, struct kstat *, u32, unsigned int);
extern int proc_setattr(struct dentry *, struct iattr *);
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 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 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
*/
struct mem_size_stats;
struct proc_maps_private {
struct inode *inode;
struct task_struct *task;
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;
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 *);