The patch titled
poll: avoid extra wakeups in select/poll
has been added to the -mm tree. Its filename is
poll-avoid-extra-wakeups-in-select-poll.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: poll: avoid extra wakeups in select/poll
From: Eric Dumazet <dada1@xxxxxxxxxxxxx>
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@xxxxxxxxxxxxx>
Acked-by: David S. Miller <davem@xxxxxxxxxxxxx>
Acked-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Acked-by: Ingo Molnar <mingo@xxxxxxx>
Acked-by: Davide Libenzi <davidel@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/select.c | 40 ++++++++++++++++++++++++++++++++++++----
include/linux/poll.h | 3 +++
2 files changed, 39 insertions(+), 4 deletions(-)
diff -puN fs/select.c~poll-avoid-extra-wakeups-in-select-poll fs/select.c
--- a/fs/select.c~poll-avoid-extra-wakeups-in-select-poll
+++ a/fs/select.c
@@ -168,7 +168,7 @@ static struct poll_table_entry *poll_get
return table->entry++;
}
-static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
struct poll_wqueues *pwq = wait->private;
DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task);
@@ -194,6 +194,16 @@ static int pollwake(wait_queue_t *wait,
return default_wake_function(&dummy_wait, mode, sync, key);
}
+static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+ struct poll_table_entry *entry;
+
+ entry = container_of(wait, struct poll_table_entry, wait);
+ if (key && !((unsigned long)key & entry->key))
+ return 0;
+ return __pollwake(wait, mode, sync, key);
+}
+
/* Add a new entry */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
poll_table *p)
@@ -205,6 +215,7 @@ static void __pollwait(struct file *filp
get_file(filp);
entry->filp = filp;
entry->wait_address = wait_address;
+ entry->key = p->key;
init_waitqueue_func_entry(&entry->wait, pollwake);
entry->wait.private = pwq;
add_wait_queue(wait_address, &entry->wait);
@@ -362,6 +373,18 @@ get_max:
#define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR)
#define POLLEX_SET (POLLPRI)
+static inline void wait_key_set(poll_table *wait, unsigned long in,
+ unsigned long out, unsigned long bit)
+{
+ if (wait) {
+ wait->key = POLLEX_SET;
+ if (in & bit)
+ wait->key |= POLLIN_SET;
+ if (out & bit)
+ wait->key |= POLLOUT_SET;
+ }
+}
+
int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
{
ktime_t expire, *to = NULL;
@@ -418,20 +441,25 @@ int do_select(int n, fd_set_bits *fds, s
if (file) {
f_op = file->f_op;
mask = DEFAULT_POLLMASK;
- if (f_op && f_op->poll)
- mask = (*f_op->poll)(file, retval ? NULL : wait);
+ if (f_op && f_op->poll) {
+ wait_key_set(wait, in, out, bit);
+ mask = (*f_op->poll)(file, wait);
+ }
fput_light(file, fput_needed);
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
retval++;
+ wait = NULL;
}
if ((mask & POLLOUT_SET) && (out & bit)) {
res_out |= bit;
retval++;
+ wait = NULL;
}
if ((mask & POLLEX_SET) && (ex & bit)) {
res_ex |= bit;
retval++;
+ wait = NULL;
}
}
}
@@ -685,8 +713,12 @@ static inline unsigned int do_pollfd(str
mask = POLLNVAL;
if (file != NULL) {
mask = DEFAULT_POLLMASK;
- if (file->f_op && file->f_op->poll)
+ if (file->f_op && file->f_op->poll) {
+ if (pwait)
+ pwait->key = pollfd->events |
+ POLLERR | POLLHUP;
mask = file->f_op->poll(file, pwait);
+ }
/* Mask out unneeded events. */
mask &= pollfd->events | POLLERR | POLLHUP;
fput_light(file, fput_needed);
diff -puN include/linux/poll.h~poll-avoid-extra-wakeups-in-select-poll include/linux/poll.h
--- a/include/linux/poll.h~poll-avoid-extra-wakeups-in-select-poll
+++ a/include/linux/poll.h
@@ -32,6 +32,7 @@ typedef void (*poll_queue_proc)(struct f
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)
@@ -43,10 +44,12 @@ static inline void poll_wait(struct file
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;
};
_
Patches currently in -mm which might be from dada1@xxxxxxxxxxxxx are
origin.patch
linux-next.patch
poll-avoid-extra-wakeups-in-select-poll.patch
softirq-introduce-statistics-for-softirq.patch
proc-export-statistics-for-softirq-to-proc.patch
proc-update-document-for-proc-softirqs-and-proc-stat.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
