![Alexey Dobriyan](/assets/img/avatar_default.png)
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>
183 lines
7.1 KiB
C
183 lines
7.1 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* The proc filesystem constants/structures
|
|
*/
|
|
#ifndef _LINUX_PROC_FS_H
|
|
#define _LINUX_PROC_FS_H
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/types.h>
|
|
#include <linux/fs.h>
|
|
|
|
struct proc_dir_entry;
|
|
struct seq_file;
|
|
struct seq_operations;
|
|
|
|
enum {
|
|
/*
|
|
* All /proc entries using this ->proc_ops instance are never removed.
|
|
*
|
|
* If in doubt, ignore this flag.
|
|
*/
|
|
#ifdef MODULE
|
|
PROC_ENTRY_PERMANENT = 0U,
|
|
#else
|
|
PROC_ENTRY_PERMANENT = 1U << 0,
|
|
#endif
|
|
};
|
|
|
|
struct proc_ops {
|
|
unsigned int proc_flags;
|
|
int (*proc_open)(struct inode *, struct file *);
|
|
ssize_t (*proc_read)(struct file *, char __user *, size_t, loff_t *);
|
|
ssize_t (*proc_write)(struct file *, const char __user *, size_t, loff_t *);
|
|
loff_t (*proc_lseek)(struct file *, loff_t, int);
|
|
int (*proc_release)(struct inode *, struct file *);
|
|
__poll_t (*proc_poll)(struct file *, struct poll_table_struct *);
|
|
long (*proc_ioctl)(struct file *, unsigned int, unsigned long);
|
|
#ifdef CONFIG_COMPAT
|
|
long (*proc_compat_ioctl)(struct file *, unsigned int, unsigned long);
|
|
#endif
|
|
int (*proc_mmap)(struct file *, struct vm_area_struct *);
|
|
unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
|
|
} __randomize_layout;
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
typedef int (*proc_write_t)(struct file *, char *, size_t);
|
|
|
|
extern void proc_root_init(void);
|
|
extern void proc_flush_pid(struct pid *);
|
|
|
|
extern struct proc_dir_entry *proc_symlink(const char *,
|
|
struct proc_dir_entry *, const char *);
|
|
extern struct proc_dir_entry *proc_mkdir(const char *, struct proc_dir_entry *);
|
|
extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t,
|
|
struct proc_dir_entry *, void *);
|
|
extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t,
|
|
struct proc_dir_entry *);
|
|
struct proc_dir_entry *proc_create_mount_point(const char *name);
|
|
|
|
struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
|
|
struct proc_dir_entry *parent, const struct seq_operations *ops,
|
|
unsigned int state_size, void *data);
|
|
#define proc_create_seq_data(name, mode, parent, ops, data) \
|
|
proc_create_seq_private(name, mode, parent, ops, 0, data)
|
|
#define proc_create_seq(name, mode, parent, ops) \
|
|
proc_create_seq_private(name, mode, parent, ops, 0, NULL)
|
|
struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
|
|
struct proc_dir_entry *parent,
|
|
int (*show)(struct seq_file *, void *), void *data);
|
|
#define proc_create_single(name, mode, parent, show) \
|
|
proc_create_single_data(name, mode, parent, show, NULL)
|
|
|
|
extern struct proc_dir_entry *proc_create_data(const char *, umode_t,
|
|
struct proc_dir_entry *,
|
|
const struct proc_ops *,
|
|
void *);
|
|
|
|
struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops);
|
|
extern void proc_set_size(struct proc_dir_entry *, loff_t);
|
|
extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t);
|
|
extern void *PDE_DATA(const struct inode *);
|
|
extern void *proc_get_parent_data(const struct inode *);
|
|
extern void proc_remove(struct proc_dir_entry *);
|
|
extern void remove_proc_entry(const char *, struct proc_dir_entry *);
|
|
extern int remove_proc_subtree(const char *, struct proc_dir_entry *);
|
|
|
|
struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
|
|
struct proc_dir_entry *parent, const struct seq_operations *ops,
|
|
unsigned int state_size, void *data);
|
|
#define proc_create_net(name, mode, parent, ops, state_size) \
|
|
proc_create_net_data(name, mode, parent, ops, state_size, NULL)
|
|
struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
|
|
struct proc_dir_entry *parent,
|
|
int (*show)(struct seq_file *, void *), void *data);
|
|
struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode,
|
|
struct proc_dir_entry *parent,
|
|
const struct seq_operations *ops,
|
|
proc_write_t write,
|
|
unsigned int state_size, void *data);
|
|
struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode,
|
|
struct proc_dir_entry *parent,
|
|
int (*show)(struct seq_file *, void *),
|
|
proc_write_t write,
|
|
void *data);
|
|
extern struct pid *tgid_pidfd_to_pid(const struct file *file);
|
|
|
|
#ifdef CONFIG_PROC_PID_ARCH_STATUS
|
|
/*
|
|
* The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must
|
|
* provide proc_pid_arch_status() definition.
|
|
*/
|
|
int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
|
|
struct pid *pid, struct task_struct *task);
|
|
#endif /* CONFIG_PROC_PID_ARCH_STATUS */
|
|
|
|
#else /* CONFIG_PROC_FS */
|
|
|
|
static inline void proc_root_init(void)
|
|
{
|
|
}
|
|
|
|
static inline void proc_flush_pid(struct pid *pid)
|
|
{
|
|
}
|
|
|
|
static inline struct proc_dir_entry *proc_symlink(const char *name,
|
|
struct proc_dir_entry *parent,const char *dest) { return NULL;}
|
|
static inline struct proc_dir_entry *proc_mkdir(const char *name,
|
|
struct proc_dir_entry *parent) {return NULL;}
|
|
static inline struct proc_dir_entry *proc_create_mount_point(const char *name) { return NULL; }
|
|
static inline struct proc_dir_entry *proc_mkdir_data(const char *name,
|
|
umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; }
|
|
static inline struct proc_dir_entry *proc_mkdir_mode(const char *name,
|
|
umode_t mode, struct proc_dir_entry *parent) { return NULL; }
|
|
#define proc_create_seq_private(name, mode, parent, ops, size, data) ({NULL;})
|
|
#define proc_create_seq_data(name, mode, parent, ops, data) ({NULL;})
|
|
#define proc_create_seq(name, mode, parent, ops) ({NULL;})
|
|
#define proc_create_single(name, mode, parent, show) ({NULL;})
|
|
#define proc_create_single_data(name, mode, parent, show, data) ({NULL;})
|
|
#define proc_create(name, mode, parent, proc_ops) ({NULL;})
|
|
#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;})
|
|
|
|
static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {}
|
|
static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {}
|
|
static inline void *PDE_DATA(const struct inode *inode) {BUG(); return NULL;}
|
|
static inline void *proc_get_parent_data(const struct inode *inode) { BUG(); return NULL; }
|
|
|
|
static inline void proc_remove(struct proc_dir_entry *de) {}
|
|
#define remove_proc_entry(name, parent) do {} while (0)
|
|
static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; }
|
|
|
|
#define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;})
|
|
#define proc_create_net(name, mode, parent, state_size, ops) ({NULL;})
|
|
#define proc_create_net_single(name, mode, parent, show, data) ({NULL;})
|
|
|
|
static inline struct pid *tgid_pidfd_to_pid(const struct file *file)
|
|
{
|
|
return ERR_PTR(-EBADF);
|
|
}
|
|
|
|
#endif /* CONFIG_PROC_FS */
|
|
|
|
struct net;
|
|
|
|
static inline struct proc_dir_entry *proc_net_mkdir(
|
|
struct net *net, const char *name, struct proc_dir_entry *parent)
|
|
{
|
|
return proc_mkdir_data(name, 0, parent, net);
|
|
}
|
|
|
|
struct ns_common;
|
|
int open_related_ns(struct ns_common *ns,
|
|
struct ns_common *(*get_ns)(struct ns_common *ns));
|
|
|
|
/* get the associated pid namespace for a file in procfs */
|
|
static inline struct pid_namespace *proc_pid_ns(const struct inode *inode)
|
|
{
|
|
return inode->i_sb->s_fs_info;
|
|
}
|
|
|
|
#endif /* _LINUX_PROC_FS_H */
|