linux/kernel/rcu/rcu_segcblist.h

159 lines
5.0 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0+ */
/*
* RCU segmented callback lists, internal-to-rcu header file
*
* Copyright IBM Corporation, 2017
*
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/rcu_segcblist.h>
/* Return number of callbacks in the specified callback list. */
static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp)
{
return READ_ONCE(rclp->len);
}
/* Return number of callbacks in segmented callback list by summing seglen. */
long rcu_segcblist_n_segment_cbs(struct rcu_segcblist *rsclp);
void rcu_cblist_init(struct rcu_cblist *rclp);
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 02:03:33 +03:00
void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp);
void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp,
struct rcu_cblist *srclp,
struct rcu_head *rhp);
struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp);
/*
* Is the specified rcu_segcblist structure empty?
*
* But careful! The fact that the ->head field is NULL does not
* necessarily imply that there are no callbacks associated with
* this structure. When callbacks are being invoked, they are
* removed as a group. If callback invocation must be preempted,
* the remaining callbacks will be added back to the list. Either
* way, the counts are updated later.
*
* So it is often the case that rcu_segcblist_n_cbs() should be used
* instead.
*/
static inline bool rcu_segcblist_empty(struct rcu_segcblist *rsclp)
{
return !READ_ONCE(rsclp->head);
}
/* Return number of callbacks in segmented callback list. */
static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
{
#ifdef CONFIG_RCU_NOCB_CPU
return atomic_long_read(&rsclp->len);
#else
return READ_ONCE(rsclp->len);
#endif
}
static inline void rcu_segcblist_set_flags(struct rcu_segcblist *rsclp,
int flags)
{
rsclp->flags |= flags;
}
static inline void rcu_segcblist_clear_flags(struct rcu_segcblist *rsclp,
int flags)
{
rsclp->flags &= ~flags;
}
static inline bool rcu_segcblist_test_flags(struct rcu_segcblist *rsclp,
int flags)
{
return READ_ONCE(rsclp->flags) & flags;
}
/*
* Is the specified rcu_segcblist enabled, for example, not corresponding
* to an offline CPU?
*/
static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
{
return rcu_segcblist_test_flags(rsclp, SEGCBLIST_ENABLED);
}
/* Is the specified rcu_segcblist offloaded? */
static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)
{
rcu/nocb: Provide basic callback offloading state machine bits Offloading and de-offloading RCU callback processes must be done carefully. There must never be a time at which callback processing is disabled because the task driving the offloading or de-offloading might be preempted or otherwise stalled at that point in time, which would result in OOM due to calbacks piling up indefinitely. This implies that there will be times during which a given CPU's callbacks might be concurrently invoked by both that CPU's RCU_SOFTIRQ handler (or, equivalently, that CPU's rcuc kthread) and by that CPU's rcuo kthread. This situation could fatally confuse both rcu_barrier() and the CPU-hotplug offlining process, so these must be excluded during any concurrent-callback-invocation period. In addition, during times of concurrent callback invocation, changes to ->cblist must be protected both as needed for RCU_SOFTIRQ and as needed for the rcuo kthread. This commit therefore defines and documents the states for a state machine that coordinates offloading and deoffloading. Cc: Josh Triplett <josh@joshtriplett.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Neeraj Upadhyay <neeraju@codeaurora.org> Cc: Thomas Gleixner <tglx@linutronix.de> Inspired-by: Paul E. McKenney <paulmck@kernel.org> Tested-by: Boqun Feng <boqun.feng@gmail.com> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-11-13 15:13:17 +03:00
if (IS_ENABLED(CONFIG_RCU_NOCB_CPU)) {
/*
* Complete de-offloading happens only when SEGCBLIST_SOFTIRQ_ONLY
* is set.
*/
if (!rcu_segcblist_test_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY))
return true;
}
return false;
}
static inline bool rcu_segcblist_completely_offloaded(struct rcu_segcblist *rsclp)
{
int flags = SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | SEGCBLIST_OFFLOADED;
if (IS_ENABLED(CONFIG_RCU_NOCB_CPU)) {
if ((rsclp->flags & flags) == flags)
return true;
}
return false;
}
/*
* Are all segments following the specified segment of the specified
* rcu_segcblist structure empty of callbacks? (The specified
* segment might well contain callbacks.)
*/
static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
{
return !READ_ONCE(*READ_ONCE(rsclp->tails[seg]));
}
/*
* Is the specified segment of the specified rcu_segcblist structure
* empty of callbacks?
*/
static inline bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg)
{
if (seg == RCU_DONE_TAIL)
return &rsclp->head == rsclp->tails[RCU_DONE_TAIL];
return rsclp->tails[seg - 1] == rsclp->tails[seg];
}
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 02:03:33 +03:00
void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp);
rcu/tree: Make rcu_do_batch count how many callbacks were executed The rcu_do_batch() function extracts the ready-to-invoke callbacks from the rcu_segcblist located in the ->cblist field of the current CPU's rcu_data structure. These callbacks are first moved to a local (unsegmented) rcu_cblist. The rcu_do_batch() function then uses this rcu_cblist's ->len field to count how many CBs it has invoked, but it does so by counting that field down from zero. Finally, this function negates the value in this ->len field (resulting in a positive number) and subtracts the result from the ->len field of the current CPU's ->cblist field. Except that it is sometimes necessary for rcu_do_batch() to stop invoking callbacks mid-stream, despite there being more ready to invoke, for example, if a high-priority task wakes up. In this case the remaining not-yet-invoked callbacks are requeued back onto the CPU's ->cblist, but remain in the ready-to-invoke segment of that list. As above, the negative of the local rcu_cblist's ->len field is still subtracted from the ->len field of the current CPU's ->cblist field. The design of counting down from 0 is confusing and error-prone, plus use of a positive count will make it easier to provide a uniform and consistent API to deal with the per-segment counts that are added later in this series. For example, rcu_segcblist_extract_done_cbs() can unconditionally populate the resulting unsegmented list's ->len field during extraction. This commit therefore explicitly counts how many callbacks were executed in rcu_do_batch() itself, counting up from zero, and then uses that to update the per-CPU segcb list's ->len field, without relying on the downcounting of rcl->len from zero. Reviewed-by: Frederic Weisbecker <frederic@kernel.org> Reviewed-by: Neeraj Upadhyay <neeraju@codeaurora.org> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-11-03 17:25:57 +03:00
void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v);
void rcu_segcblist_init(struct rcu_segcblist *rsclp);
void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload);
bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp);
void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
struct rcu_head *rhp);
bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
struct rcu_head *rhp);
void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
struct rcu_segcblist *src_rsclp);