mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 21:30:54 +07:00
bb73c52bad
Because preempt_disable() maps to barrier() for non-debug builds, it forces the compiler to spill and reload registers. Because Tree RCU and Tiny RCU now only appear in CONFIG_PREEMPT=n builds, these barrier() instances generate needless extra code for each instance of rcu_read_lock() and rcu_read_unlock(). This extra code slows down Tree RCU and bloats Tiny RCU. This commit therefore removes the preempt_disable() and preempt_enable() from the non-preemptible implementations of __rcu_read_lock() and __rcu_read_unlock(), respectively. However, for debug purposes, preempt_disable() and preempt_enable() are still invoked if CONFIG_PREEMPT_COUNT=y, because this allows detection of sleeping inside atomic sections in non-preemptible kernels. However, Tiny and Tree RCU operates by coalescing all RCU read-side critical sections on a given CPU that lie between successive quiescent states. It is therefore necessary to compensate for removing barriers from __rcu_read_lock() and __rcu_read_unlock() by adding them to a couple of the RCU functions invoked during quiescent states, namely to rcu_all_qs() and rcu_note_context_switch(). However, note that the latter is more paranoia than necessity, at least until link-time optimizations become more aggressive. This is based on an earlier patch by Paul E. McKenney, fixing a bug encountered in kernels built with CONFIG_PREEMPT=n and CONFIG_PREEMPT_COUNT=y. Signed-off-by: Boqun Feng <boqun.feng@gmail.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
223 lines
4.3 KiB
C
223 lines
4.3 KiB
C
/*
|
|
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that 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, you can access it online at
|
|
* http://www.gnu.org/licenses/gpl-2.0.html.
|
|
*
|
|
* Copyright IBM Corporation, 2008
|
|
*
|
|
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
*
|
|
* For detailed explanation of Read-Copy Update mechanism see -
|
|
* Documentation/RCU
|
|
*/
|
|
#ifndef __LINUX_TINY_H
|
|
#define __LINUX_TINY_H
|
|
|
|
#include <linux/cache.h>
|
|
|
|
static inline unsigned long get_state_synchronize_rcu(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void cond_synchronize_rcu(unsigned long oldstate)
|
|
{
|
|
might_sleep();
|
|
}
|
|
|
|
static inline unsigned long get_state_synchronize_sched(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void cond_synchronize_sched(unsigned long oldstate)
|
|
{
|
|
might_sleep();
|
|
}
|
|
|
|
static inline void rcu_barrier_bh(void)
|
|
{
|
|
wait_rcu_gp(call_rcu_bh);
|
|
}
|
|
|
|
static inline void rcu_barrier_sched(void)
|
|
{
|
|
wait_rcu_gp(call_rcu_sched);
|
|
}
|
|
|
|
static inline void synchronize_rcu_expedited(void)
|
|
{
|
|
synchronize_sched(); /* Only one CPU, so pretty fast anyway!!! */
|
|
}
|
|
|
|
static inline void rcu_barrier(void)
|
|
{
|
|
rcu_barrier_sched(); /* Only one CPU, so only one list of callbacks! */
|
|
}
|
|
|
|
static inline void synchronize_rcu_bh(void)
|
|
{
|
|
synchronize_sched();
|
|
}
|
|
|
|
static inline void synchronize_rcu_bh_expedited(void)
|
|
{
|
|
synchronize_sched();
|
|
}
|
|
|
|
static inline void synchronize_sched_expedited(void)
|
|
{
|
|
synchronize_sched();
|
|
}
|
|
|
|
static inline void kfree_call_rcu(struct rcu_head *head,
|
|
rcu_callback_t func)
|
|
{
|
|
call_rcu(head, func);
|
|
}
|
|
|
|
static inline void rcu_note_context_switch(void)
|
|
{
|
|
rcu_sched_qs();
|
|
}
|
|
|
|
/*
|
|
* Take advantage of the fact that there is only one CPU, which
|
|
* allows us to ignore virtualization-based context switches.
|
|
*/
|
|
static inline void rcu_virt_note_context_switch(int cpu)
|
|
{
|
|
}
|
|
|
|
/*
|
|
* Return the number of grace periods started.
|
|
*/
|
|
static inline unsigned long rcu_batches_started(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Return the number of bottom-half grace periods started.
|
|
*/
|
|
static inline unsigned long rcu_batches_started_bh(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Return the number of sched grace periods started.
|
|
*/
|
|
static inline unsigned long rcu_batches_started_sched(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Return the number of grace periods completed.
|
|
*/
|
|
static inline unsigned long rcu_batches_completed(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Return the number of bottom-half grace periods completed.
|
|
*/
|
|
static inline unsigned long rcu_batches_completed_bh(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Return the number of sched grace periods completed.
|
|
*/
|
|
static inline unsigned long rcu_batches_completed_sched(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void rcu_force_quiescent_state(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_bh_force_quiescent_state(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_sched_force_quiescent_state(void)
|
|
{
|
|
}
|
|
|
|
static inline void show_rcu_gp_kthreads(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_cpu_stall_reset(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_idle_enter(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_idle_exit(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_irq_enter(void)
|
|
{
|
|
}
|
|
|
|
static inline void rcu_irq_exit(void)
|
|
{
|
|
}
|
|
|
|
static inline void exit_rcu(void)
|
|
{
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
extern int rcu_scheduler_active __read_mostly;
|
|
void rcu_scheduler_starting(void);
|
|
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
|
|
static inline void rcu_scheduler_starting(void)
|
|
{
|
|
}
|
|
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
|
|
|
|
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
|
|
|
|
static inline bool rcu_is_watching(void)
|
|
{
|
|
return __rcu_is_watching();
|
|
}
|
|
|
|
#else /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
|
|
|
|
static inline bool rcu_is_watching(void)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
|
|
|
|
static inline void rcu_all_qs(void)
|
|
{
|
|
barrier(); /* Avoid RCU read-side critical sections leaking across. */
|
|
}
|
|
|
|
#endif /* __LINUX_RCUTINY_H */
|