mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-11-01 17:08:10 +00:00
4938d7e023
After introduction of keyed wakeups Davide Libenzi did on epoll, we are able to avoid spurious wakeups in poll()/select() code too. For example, typical use of poll()/select() is to wait for incoming network frames on many sockets. But TX completion for UDP/TCP frames call sock_wfree() which in turn schedules thread. When scheduled, thread does a full scan of all polled fds and can sleep again, because nothing is really available. If number of fds is large, this cause significant load. This patch makes select()/poll() aware of keyed wakeups and useless wakeups are avoided. This reduces number of context switches by about 50% on some setups, and work performed by sofirq handlers. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
139 lines
3.5 KiB
C
139 lines
3.5 KiB
C
#ifndef _LINUX_POLL_H
|
|
#define _LINUX_POLL_H
|
|
|
|
#include <asm/poll.h>
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/string.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/sched.h>
|
|
#include <asm/uaccess.h>
|
|
|
|
/* ~832 bytes of stack space used max in sys_select/sys_poll before allocating
|
|
additional memory. */
|
|
#define MAX_STACK_ALLOC 832
|
|
#define FRONTEND_STACK_ALLOC 256
|
|
#define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC
|
|
#define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC
|
|
#define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC)
|
|
#define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry))
|
|
|
|
#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM)
|
|
|
|
struct poll_table_struct;
|
|
|
|
/*
|
|
* structures and helpers for f_op->poll implementations
|
|
*/
|
|
typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *);
|
|
|
|
typedef struct poll_table_struct {
|
|
poll_queue_proc qproc;
|
|
unsigned long key;
|
|
} poll_table;
|
|
|
|
static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
|
|
{
|
|
if (p && wait_address)
|
|
p->qproc(filp, wait_address, p);
|
|
}
|
|
|
|
static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
|
|
{
|
|
pt->qproc = qproc;
|
|
pt->key = ~0UL; /* all events enabled */
|
|
}
|
|
|
|
struct poll_table_entry {
|
|
struct file *filp;
|
|
unsigned long key;
|
|
wait_queue_t wait;
|
|
wait_queue_head_t *wait_address;
|
|
};
|
|
|
|
/*
|
|
* Structures and helpers for sys_poll/sys_poll
|
|
*/
|
|
struct poll_wqueues {
|
|
poll_table pt;
|
|
struct poll_table_page *table;
|
|
struct task_struct *polling_task;
|
|
int triggered;
|
|
int error;
|
|
int inline_index;
|
|
struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES];
|
|
};
|
|
|
|
extern void poll_initwait(struct poll_wqueues *pwq);
|
|
extern void poll_freewait(struct poll_wqueues *pwq);
|
|
extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
|
|
ktime_t *expires, unsigned long slack);
|
|
|
|
static inline int poll_schedule(struct poll_wqueues *pwq, int state)
|
|
{
|
|
return poll_schedule_timeout(pwq, state, NULL, 0);
|
|
}
|
|
|
|
/*
|
|
* Scaleable version of the fd_set.
|
|
*/
|
|
|
|
typedef struct {
|
|
unsigned long *in, *out, *ex;
|
|
unsigned long *res_in, *res_out, *res_ex;
|
|
} fd_set_bits;
|
|
|
|
/*
|
|
* How many longwords for "nr" bits?
|
|
*/
|
|
#define FDS_BITPERLONG (8*sizeof(long))
|
|
#define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG)
|
|
#define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long))
|
|
|
|
/*
|
|
* We do a VERIFY_WRITE here even though we are only reading this time:
|
|
* we'll write to it eventually..
|
|
*
|
|
* Use "unsigned long" accesses to let user-mode fd_set's be long-aligned.
|
|
*/
|
|
static inline
|
|
int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
|
|
{
|
|
nr = FDS_BYTES(nr);
|
|
if (ufdset)
|
|
return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0;
|
|
|
|
memset(fdset, 0, nr);
|
|
return 0;
|
|
}
|
|
|
|
static inline unsigned long __must_check
|
|
set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
|
|
{
|
|
if (ufdset)
|
|
return __copy_to_user(ufdset, fdset, FDS_BYTES(nr));
|
|
return 0;
|
|
}
|
|
|
|
static inline
|
|
void zero_fd_set(unsigned long nr, unsigned long *fdset)
|
|
{
|
|
memset(fdset, 0, FDS_BYTES(nr));
|
|
}
|
|
|
|
#define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
|
|
|
|
extern int do_select(int n, fd_set_bits *fds, struct timespec *end_time);
|
|
extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
|
|
struct timespec *end_time);
|
|
extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
|
|
fd_set __user *exp, struct timespec *end_time);
|
|
|
|
extern int poll_select_set_timeout(struct timespec *to, long sec, long nsec);
|
|
|
|
#endif /* KERNEL */
|
|
|
|
#endif /* _LINUX_POLL_H */
|