3708983452
The only valid use of preempt_enable_no_resched() is if the very next line is schedule() or if we know preemption cannot actually be enabled by that statement due to known more preempt_count 'refs'. This busy_poll stuff looks to be completely and utterly broken, sched_clock() can return utter garbage with interrupts enabled (rare but still) and it can drift unbounded between CPUs. This means that if you get preempted/migrated and your new CPU is years behind on the previous CPU we get to busy spin for a _very_ long time. There is a _REASON_ sched_clock() warns about preemptability - papering over it with a preempt_disable()/preempt_enable_no_resched() is just terminal brain damage on so many levels. Replace sched_clock() usage with local_clock() which has a bounded drift between CPUs (<2 jiffies). There is a further problem with the entire busy wait poll thing in that the spin time is additive to the syscall timeout, not inclusive. Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: rui.zhang@intel.com Cc: jacob.jun.pan@linux.intel.com Cc: Mike Galbraith <bitbucket@online.de> Cc: hpa@zytor.com Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: lenb@kernel.org Cc: rjw@rjwysocki.net Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131119151338.GF3694@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
170 lines
4.0 KiB
C
170 lines
4.0 KiB
C
/*
|
|
* net busy poll support
|
|
* Copyright(c) 2013 Intel Corporation.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program; if not, write to the Free Software Foundation, Inc.,
|
|
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
|
|
*
|
|
* Author: Eliezer Tamir
|
|
*
|
|
* Contact Information:
|
|
* e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
|
|
*/
|
|
|
|
#ifndef _LINUX_NET_BUSY_POLL_H
|
|
#define _LINUX_NET_BUSY_POLL_H
|
|
|
|
#include <linux/netdevice.h>
|
|
#include <net/ip.h>
|
|
|
|
#ifdef CONFIG_NET_RX_BUSY_POLL
|
|
|
|
struct napi_struct;
|
|
extern unsigned int sysctl_net_busy_read __read_mostly;
|
|
extern unsigned int sysctl_net_busy_poll __read_mostly;
|
|
|
|
/* return values from ndo_ll_poll */
|
|
#define LL_FLUSH_FAILED -1
|
|
#define LL_FLUSH_BUSY -2
|
|
|
|
static inline bool net_busy_loop_on(void)
|
|
{
|
|
return sysctl_net_busy_poll;
|
|
}
|
|
|
|
static inline u64 busy_loop_us_clock(void)
|
|
{
|
|
return local_clock() >> 10;
|
|
}
|
|
|
|
static inline unsigned long sk_busy_loop_end_time(struct sock *sk)
|
|
{
|
|
return busy_loop_us_clock() + ACCESS_ONCE(sk->sk_ll_usec);
|
|
}
|
|
|
|
/* in poll/select we use the global sysctl_net_ll_poll value */
|
|
static inline unsigned long busy_loop_end_time(void)
|
|
{
|
|
return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll);
|
|
}
|
|
|
|
static inline bool sk_can_busy_loop(struct sock *sk)
|
|
{
|
|
return sk->sk_ll_usec && sk->sk_napi_id &&
|
|
!need_resched() && !signal_pending(current);
|
|
}
|
|
|
|
|
|
static inline bool busy_loop_timeout(unsigned long end_time)
|
|
{
|
|
unsigned long now = busy_loop_us_clock();
|
|
|
|
return time_after(now, end_time);
|
|
}
|
|
|
|
/* when used in sock_poll() nonblock is known at compile time to be true
|
|
* so the loop and end_time will be optimized out
|
|
*/
|
|
static inline bool sk_busy_loop(struct sock *sk, int nonblock)
|
|
{
|
|
unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
|
|
const struct net_device_ops *ops;
|
|
struct napi_struct *napi;
|
|
int rc = false;
|
|
|
|
/*
|
|
* rcu read lock for napi hash
|
|
* bh so we don't race with net_rx_action
|
|
*/
|
|
rcu_read_lock_bh();
|
|
|
|
napi = napi_by_id(sk->sk_napi_id);
|
|
if (!napi)
|
|
goto out;
|
|
|
|
ops = napi->dev->netdev_ops;
|
|
if (!ops->ndo_busy_poll)
|
|
goto out;
|
|
|
|
do {
|
|
rc = ops->ndo_busy_poll(napi);
|
|
|
|
if (rc == LL_FLUSH_FAILED)
|
|
break; /* permanent failure */
|
|
|
|
if (rc > 0)
|
|
/* local bh are disabled so it is ok to use _BH */
|
|
NET_ADD_STATS_BH(sock_net(sk),
|
|
LINUX_MIB_BUSYPOLLRXPACKETS, rc);
|
|
cpu_relax();
|
|
|
|
} while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) &&
|
|
!need_resched() && !busy_loop_timeout(end_time));
|
|
|
|
rc = !skb_queue_empty(&sk->sk_receive_queue);
|
|
out:
|
|
rcu_read_unlock_bh();
|
|
return rc;
|
|
}
|
|
|
|
/* used in the NIC receive handler to mark the skb */
|
|
static inline void skb_mark_napi_id(struct sk_buff *skb,
|
|
struct napi_struct *napi)
|
|
{
|
|
skb->napi_id = napi->napi_id;
|
|
}
|
|
|
|
/* used in the protocol hanlder to propagate the napi_id to the socket */
|
|
static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
sk->sk_napi_id = skb->napi_id;
|
|
}
|
|
|
|
#else /* CONFIG_NET_RX_BUSY_POLL */
|
|
static inline unsigned long net_busy_loop_on(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline unsigned long busy_loop_end_time(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool sk_can_busy_loop(struct sock *sk)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void skb_mark_napi_id(struct sk_buff *skb,
|
|
struct napi_struct *napi)
|
|
{
|
|
}
|
|
|
|
static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
}
|
|
|
|
static inline bool busy_loop_timeout(unsigned long end_time)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline bool sk_busy_loop(struct sock *sk, int nonblock)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_NET_RX_BUSY_POLL */
|
|
#endif /* _LINUX_NET_BUSY_POLL_H */
|