mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-17 18:26:40 +07:00
d6cffbbe9a
Currently unregistering sysctl table does not prune its dentries. Stale dentries could slowdown sysctl operations significantly. For example, command: # for i in {1..100000} ; do unshare -n -- sysctl -a &> /dev/null ; done creates a millions of stale denties around sysctls of loopback interface: # sysctl fs.dentry-state fs.dentry-state = 25812579 24724135 45 0 0 0 All of them have matching names thus lookup have to scan though whole hash chain and call d_compare (proc_sys_compare) which checks them under system-wide spinlock (sysctl_lock). # time sysctl -a > /dev/null real 1m12.806s user 0m0.016s sys 1m12.400s Currently only memory reclaimer could remove this garbage. But without significant memory pressure this never happens. This patch collects sysctl inodes into list on sysctl table header and prunes all their dentries once that table unregisters. Konstantin Khlebnikov <khlebnikov@yandex-team.ru> writes: > On 10.02.2017 10:47, Al Viro wrote: >> how about >> the matching stats *after* that patch? > > dcache size doesn't grow endlessly, so stats are fine > > # sysctl fs.dentry-state > fs.dentry-state = 92712 58376 45 0 0 0 > > # time sysctl -a &>/dev/null > > real 0m0.013s > user 0m0.004s > sys 0m0.008s Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Suggested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
229 lines
7.0 KiB
C
229 lines
7.0 KiB
C
/*
|
|
* sysctl.h: General linux system control interface
|
|
*
|
|
* Begun 24 March 1995, Stephen Tweedie
|
|
*
|
|
****************************************************************
|
|
****************************************************************
|
|
**
|
|
** WARNING:
|
|
** The values in this file are exported to user space via
|
|
** the sysctl() binary interface. Do *NOT* change the
|
|
** numbering of any existing values here, and do not change
|
|
** any numbers within any one set of values. If you have to
|
|
** redefine an existing interface, use a new number for it.
|
|
** The kernel will then return -ENOTDIR to any application using
|
|
** the old binary interface.
|
|
**
|
|
****************************************************************
|
|
****************************************************************
|
|
*/
|
|
#ifndef _LINUX_SYSCTL_H
|
|
#define _LINUX_SYSCTL_H
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/uidgid.h>
|
|
#include <uapi/linux/sysctl.h>
|
|
|
|
/* For the /proc/sys support */
|
|
struct completion;
|
|
struct ctl_table;
|
|
struct nsproxy;
|
|
struct ctl_table_root;
|
|
struct ctl_table_header;
|
|
struct ctl_dir;
|
|
|
|
typedef int proc_handler (struct ctl_table *ctl, int write,
|
|
void __user *buffer, size_t *lenp, loff_t *ppos);
|
|
|
|
extern int proc_dostring(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_dointvec(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_douintvec(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_dointvec_minmax(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_dointvec_jiffies(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_dointvec_ms_jiffies(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_doulongvec_minmax(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_do_large_bitmap(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
|
|
/*
|
|
* Register a set of sysctl names by calling register_sysctl_table
|
|
* with an initialised array of struct ctl_table's. An entry with
|
|
* NULL procname terminates the table. table->de will be
|
|
* set up by the registration and need not be initialised in advance.
|
|
*
|
|
* sysctl names can be mirrored automatically under /proc/sys. The
|
|
* procname supplied controls /proc naming.
|
|
*
|
|
* The table's mode will be honoured both for sys_sysctl(2) and
|
|
* proc-fs access.
|
|
*
|
|
* Leaf nodes in the sysctl tree will be represented by a single file
|
|
* under /proc; non-leaf nodes will be represented by directories. A
|
|
* null procname disables /proc mirroring at this node.
|
|
*
|
|
* sysctl(2) can automatically manage read and write requests through
|
|
* the sysctl table. The data and maxlen fields of the ctl_table
|
|
* struct enable minimal validation of the values being written to be
|
|
* performed, and the mode field allows minimal authentication.
|
|
*
|
|
* There must be a proc_handler routine for any terminal nodes
|
|
* mirrored under /proc/sys (non-terminals are handled by a built-in
|
|
* directory handler). Several default handlers are available to
|
|
* cover common cases.
|
|
*/
|
|
|
|
/* Support for userspace poll() to watch for changes */
|
|
struct ctl_table_poll {
|
|
atomic_t event;
|
|
wait_queue_head_t wait;
|
|
};
|
|
|
|
static inline void *proc_sys_poll_event(struct ctl_table_poll *poll)
|
|
{
|
|
return (void *)(unsigned long)atomic_read(&poll->event);
|
|
}
|
|
|
|
#define __CTL_TABLE_POLL_INITIALIZER(name) { \
|
|
.event = ATOMIC_INIT(0), \
|
|
.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait) }
|
|
|
|
#define DEFINE_CTL_TABLE_POLL(name) \
|
|
struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name)
|
|
|
|
/* A sysctl table is an array of struct ctl_table: */
|
|
struct ctl_table
|
|
{
|
|
const char *procname; /* Text ID for /proc/sys, or zero */
|
|
void *data;
|
|
int maxlen;
|
|
umode_t mode;
|
|
struct ctl_table *child; /* Deprecated */
|
|
proc_handler *proc_handler; /* Callback for text formatting */
|
|
struct ctl_table_poll *poll;
|
|
void *extra1;
|
|
void *extra2;
|
|
};
|
|
|
|
struct ctl_node {
|
|
struct rb_node node;
|
|
struct ctl_table_header *header;
|
|
};
|
|
|
|
/* struct ctl_table_header is used to maintain dynamic lists of
|
|
struct ctl_table trees. */
|
|
struct ctl_table_header
|
|
{
|
|
union {
|
|
struct {
|
|
struct ctl_table *ctl_table;
|
|
int used;
|
|
int count;
|
|
int nreg;
|
|
};
|
|
struct rcu_head rcu;
|
|
};
|
|
struct completion *unregistering;
|
|
struct ctl_table *ctl_table_arg;
|
|
struct ctl_table_root *root;
|
|
struct ctl_table_set *set;
|
|
struct ctl_dir *parent;
|
|
struct ctl_node *node;
|
|
struct list_head inodes; /* head for proc_inode->sysctl_inodes */
|
|
};
|
|
|
|
struct ctl_dir {
|
|
/* Header must be at the start of ctl_dir */
|
|
struct ctl_table_header header;
|
|
struct rb_root root;
|
|
};
|
|
|
|
struct ctl_table_set {
|
|
int (*is_seen)(struct ctl_table_set *);
|
|
struct ctl_dir dir;
|
|
};
|
|
|
|
struct ctl_table_root {
|
|
struct ctl_table_set default_set;
|
|
struct ctl_table_set *(*lookup)(struct ctl_table_root *root);
|
|
void (*set_ownership)(struct ctl_table_header *head,
|
|
struct ctl_table *table,
|
|
kuid_t *uid, kgid_t *gid);
|
|
int (*permissions)(struct ctl_table_header *head, struct ctl_table *table);
|
|
};
|
|
|
|
/* struct ctl_path describes where in the hierarchy a table is added */
|
|
struct ctl_path {
|
|
const char *procname;
|
|
};
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
|
|
void proc_sys_poll_notify(struct ctl_table_poll *poll);
|
|
|
|
extern void setup_sysctl_set(struct ctl_table_set *p,
|
|
struct ctl_table_root *root,
|
|
int (*is_seen)(struct ctl_table_set *));
|
|
extern void retire_sysctl_set(struct ctl_table_set *set);
|
|
|
|
void register_sysctl_root(struct ctl_table_root *root);
|
|
struct ctl_table_header *__register_sysctl_table(
|
|
struct ctl_table_set *set,
|
|
const char *path, struct ctl_table *table);
|
|
struct ctl_table_header *__register_sysctl_paths(
|
|
struct ctl_table_set *set,
|
|
const struct ctl_path *path, struct ctl_table *table);
|
|
struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table);
|
|
struct ctl_table_header *register_sysctl_table(struct ctl_table * table);
|
|
struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
|
|
struct ctl_table *table);
|
|
|
|
void unregister_sysctl_table(struct ctl_table_header * table);
|
|
|
|
extern int sysctl_init(void);
|
|
|
|
extern struct ctl_table sysctl_mount_point[];
|
|
|
|
#else /* CONFIG_SYSCTL */
|
|
static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct ctl_table_header *register_sysctl_paths(
|
|
const struct ctl_path *path, struct ctl_table *table)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void unregister_sysctl_table(struct ctl_table_header * table)
|
|
{
|
|
}
|
|
|
|
static inline void setup_sysctl_set(struct ctl_table_set *p,
|
|
struct ctl_table_root *root,
|
|
int (*is_seen)(struct ctl_table_set *))
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_SYSCTL */
|
|
|
|
int sysctl_max_threads(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp, loff_t *ppos);
|
|
|
|
#endif /* _LINUX_SYSCTL_H */
|