From 9999e48639b3cecb08ffb37358bcba3b48161b29 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 08:50:17 +0000
Subject: [PATCH] add ax88772_rst
---
kernel/kernel/rcu/tree.c | 4074 +++++++++++++++++++++++++++++++++--------------------------
1 files changed, 2,250 insertions(+), 1,824 deletions(-)
diff --git a/kernel/kernel/rcu/tree.c b/kernel/kernel/rcu/tree.c
index 1c5a4ee..eec8e2f 100644
--- a/kernel/kernel/rcu/tree.c
+++ b/kernel/kernel/rcu/tree.c
@@ -1,27 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * Read-Copy Update mechanism for mutual exclusion
- *
- * 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.
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
*
* Copyright IBM Corporation, 2008
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
- * Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
+ * Paul E. McKenney <paulmck@linux.ibm.com>
*
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
@@ -56,11 +43,24 @@
#include <uapi/linux/sched/types.h>
#include <linux/prefetch.h>
#include <linux/delay.h>
-#include <linux/stop_machine.h>
#include <linux/random.h>
#include <linux/trace_events.h>
#include <linux/suspend.h>
#include <linux/ftrace.h>
+#include <linux/tick.h>
+#include <linux/sysrq.h>
+#include <linux/kprobes.h>
+#include <linux/gfp.h>
+#include <linux/oom.h>
+#include <linux/smpboot.h>
+#include <linux/jiffies.h>
+#include <linux/slab.h>
+#include <linux/sched/isolation.h>
+#include <linux/sched/clock.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/kasan.h>
+#include "../time/tick-internal.h"
#include "tree.h"
#include "rcu.h"
@@ -73,49 +73,35 @@
/* Data structures. */
/*
- * In order to export the rcu_state name to the tracing tools, it
- * needs to be added in the __tracepoint_string section.
- * This requires defining a separate variable tp_<sname>_varname
- * that points to the string being used, and this will allow
- * the tracing userspace tools to be able to decipher the string
- * address to the matching string.
+ * Steal a bit from the bottom of ->dynticks for idle entry/exit
+ * control. Initially this is for TLB flushing.
*/
-#ifdef CONFIG_TRACING
-# define DEFINE_RCU_TPS(sname) \
-static char sname##_varname[] = #sname; \
-static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname;
-# define RCU_STATE_NAME(sname) sname##_varname
-#else
-# define DEFINE_RCU_TPS(sname)
-# define RCU_STATE_NAME(sname) __stringify(sname)
-#endif
+#define RCU_DYNTICK_CTRL_MASK 0x1
+#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1)
-#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
-DEFINE_RCU_TPS(sname) \
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
-struct rcu_state sname##_state = { \
- .level = { &sname##_state.node[0] }, \
- .rda = &sname##_data, \
- .call = cr, \
- .gp_state = RCU_GP_IDLE, \
- .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \
- .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
- .name = RCU_STATE_NAME(sname), \
- .abbr = sabbr, \
- .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \
- .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \
- .ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \
-}
-
-RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
-RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
-
-static struct rcu_state *const rcu_state_p;
-LIST_HEAD(rcu_struct_flavors);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
+ .dynticks_nesting = 1,
+ .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
+ .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
+};
+static struct rcu_state rcu_state = {
+ .level = { &rcu_state.node[0] },
+ .gp_state = RCU_GP_IDLE,
+ .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT,
+ .barrier_mutex = __MUTEX_INITIALIZER(rcu_state.barrier_mutex),
+ .name = RCU_NAME,
+ .abbr = RCU_ABBR,
+ .exp_mutex = __MUTEX_INITIALIZER(rcu_state.exp_mutex),
+ .exp_wake_mutex = __MUTEX_INITIALIZER(rcu_state.exp_wake_mutex),
+ .ofl_lock = __RAW_SPIN_LOCK_UNLOCKED(rcu_state.ofl_lock),
+};
/* Dump rcu_node combining tree at boot to verify correct setup. */
static bool dump_tree;
module_param(dump_tree, bool, 0444);
+/* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
+static bool use_softirq = true;
+module_param(use_softirq, bool, 0444);
/* Control rcu_node-tree auto-balancing at boot time. */
static bool rcu_fanout_exact;
module_param(rcu_fanout_exact, bool, 0444);
@@ -126,9 +112,6 @@
/* Number of rcu_nodes at specified level. */
int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
-/* panic() on RCU Stall sysctl. */
-int sysctl_panic_on_rcu_stall __read_mostly = CONFIG_BOOTPARAM_RCU_STALL_PANIC_VALUE;
-ATOMIC_NOTIFIER_HEAD(rcu_stall_notifier_list);
/*
* The rcu_scheduler_active variable is initialized to the value
@@ -159,21 +142,19 @@
*/
static int rcu_scheduler_fully_active __read_mostly;
-static void
-rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
- struct rcu_node *rnp, unsigned long gps, unsigned long flags);
+static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
+ unsigned long gps, unsigned long flags);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
-static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
-static void rcu_report_exp_rdp(struct rcu_state *rsp,
- struct rcu_data *rdp, bool wake);
+static void rcu_report_exp_rdp(struct rcu_data *rdp);
static void sync_sched_exp_online_cleanup(int cpu);
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
/* rcuc/rcub kthread realtime priority */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
-module_param(kthread_prio, int, 0644);
+module_param(kthread_prio, int, 0444);
/* Delay in jiffies for grace-period initialization delays, debug only. */
@@ -184,7 +165,22 @@
static int gp_cleanup_delay;
module_param(gp_cleanup_delay, int, 0444);
-/* Retreive RCU kthreads priority for rcutorture */
+// Add delay to rcu_read_unlock() for strict grace periods.
+static int rcu_unlock_delay;
+#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
+module_param(rcu_unlock_delay, int, 0444);
+#endif
+
+/*
+ * This rcu parameter is runtime-read-only. It reflects
+ * a minimum allowed number of objects which can be cached
+ * per-CPU. Object size is equal to one page. This value
+ * can be changed at boot time.
+ */
+static int rcu_min_cached_objs = 5;
+module_param(rcu_min_cached_objs, int, 0444);
+
+/* Retrieve RCU kthreads priority for rcutorture */
int rcu_get_gp_kthreads_prio(void)
{
return kthread_prio;
@@ -208,7 +204,7 @@
* held, but the bit corresponding to the current CPU will be stable
* in most contexts.
*/
-unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
+static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
return READ_ONCE(rnp->qsmaskinitnext);
}
@@ -218,67 +214,39 @@
* permit this function to be invoked without holding the root rcu_node
* structure's ->lock, but of course results can be subject to change.
*/
-static int rcu_gp_in_progress(struct rcu_state *rsp)
+static int rcu_gp_in_progress(void)
{
- return rcu_seq_state(rcu_seq_current(&rsp->gp_seq));
+ return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq));
}
/*
- * Note a quiescent state. Because we do not need to know
- * how many quiescent states passed, just if there was at least
- * one since the start of the grace period, this just sets a flag.
- * The caller must have disabled preemption.
+ * Return the number of callbacks queued on the specified CPU.
+ * Handles both the nocbs and normal cases.
*/
-void rcu_sched_qs(void)
+static long rcu_get_n_cbs_cpu(int cpu)
{
- RCU_LOCKDEP_WARN(preemptible(), "rcu_sched_qs() invoked with preemption enabled!!!");
- if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
- return;
- trace_rcu_grace_period(TPS("rcu_sched"),
- __this_cpu_read(rcu_sched_data.gp_seq),
- TPS("cpuqs"));
- __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
- if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
- return;
- __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
- rcu_report_exp_rdp(&rcu_sched_state,
- this_cpu_ptr(&rcu_sched_data), true);
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+ if (rcu_segcblist_is_enabled(&rdp->cblist))
+ return rcu_segcblist_n_cbs(&rdp->cblist);
+ return 0;
}
-void rcu_bh_qs(void)
+void rcu_softirq_qs(void)
{
- RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
- if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
- trace_rcu_grace_period(TPS("rcu_bh"),
- __this_cpu_read(rcu_bh_data.gp_seq),
- TPS("cpuqs"));
- __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
- }
+ rcu_qs();
+ rcu_preempt_deferred_qs(current);
}
-
-/*
- * Steal a bit from the bottom of ->dynticks for idle entry/exit
- * control. Initially this is for TLB flushing.
- */
-#define RCU_DYNTICK_CTRL_MASK 0x1
-#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1)
-#ifndef rcu_eqs_special_exit
-#define rcu_eqs_special_exit() do { } while (0)
-#endif
-
-static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
- .dynticks_nesting = 1,
- .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
- .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
-};
/*
* Record entry into an extended quiescent state. This is only to be
- * called when not already in an extended quiescent state.
+ * called when not already in an extended quiescent state, that is,
+ * RCU is watching prior to the call to this function and is no longer
+ * watching upon return.
*/
-static void rcu_dynticks_eqs_enter(void)
+static noinstr void rcu_dynticks_eqs_enter(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
int seq;
/*
@@ -286,8 +254,9 @@
* critical sections, and we also must force ordering with the
* next idle sojourn.
*/
- seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
- /* Better be in an extended quiescent state! */
+ rcu_dynticks_task_trace_enter(); // Before ->dynticks update!
+ seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+ // RCU is no longer watching. Better be in extended quiescent state!
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
(seq & RCU_DYNTICK_CTRL_CTR));
/* Better not have special action (TLB flush) pending! */
@@ -297,11 +266,12 @@
/*
* Record exit from an extended quiescent state. This is only to be
- * called from an extended quiescent state.
+ * called from an extended quiescent state, that is, RCU is not watching
+ * prior to the call to this function and is watching upon return.
*/
-static void rcu_dynticks_eqs_exit(void)
+static noinstr void rcu_dynticks_eqs_exit(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
int seq;
/*
@@ -309,14 +279,14 @@
* and we also must force ordering with the next RCU read-side
* critical section.
*/
- seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+ // RCU is now watching. Better not be in an extended quiescent state!
+ rcu_dynticks_task_trace_exit(); // After ->dynticks update!
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!(seq & RCU_DYNTICK_CTRL_CTR));
if (seq & RCU_DYNTICK_CTRL_MASK) {
- atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdtp->dynticks);
+ arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
smp_mb__after_atomic(); /* _exit after clearing mask. */
- /* Prefer duplicate flushes to losing a flush. */
- rcu_eqs_special_exit();
}
}
@@ -332,11 +302,11 @@
*/
static void rcu_dynticks_eqs_online(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
- if (atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR)
+ if (atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR)
return;
- atomic_add(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ atomic_add(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
}
/*
@@ -344,20 +314,20 @@
*
* No ordering, as we are sampling CPU-local information.
*/
-bool rcu_dynticks_curr_cpu_in_eqs(void)
+static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
- return !(atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+ return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
}
/*
* Snapshot the ->dynticks counter with full ordering so as to allow
* stable comparison of this counter with past and future snapshots.
*/
-int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+static int rcu_dynticks_snap(struct rcu_data *rdp)
{
- int snap = atomic_add_return(0, &rdtp->dynticks);
+ int snap = atomic_add_return(0, &rdp->dynticks);
return snap & ~RCU_DYNTICK_CTRL_MASK;
}
@@ -372,13 +342,35 @@
}
/*
- * Return true if the CPU corresponding to the specified rcu_dynticks
+ * Return true if the CPU corresponding to the specified rcu_data
* structure has spent some time in an extended quiescent state since
* rcu_dynticks_snap() returned the specified snapshot.
*/
-static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
+static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
{
- return snap != rcu_dynticks_snap(rdtp);
+ return snap != rcu_dynticks_snap(rdp);
+}
+
+/*
+ * Return true if the referenced integer is zero while the specified
+ * CPU remains within a single extended quiescent state.
+ */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
+{
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ int snap;
+
+ // If not quiescent, force back to earlier extended quiescent state.
+ snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK |
+ RCU_DYNTICK_CTRL_CTR);
+
+ smp_rmb(); // Order ->dynticks and *vp reads.
+ if (READ_ONCE(*vp))
+ return false; // Non-zero, so report failure;
+ smp_rmb(); // Order *vp read and ->dynticks re-read.
+
+ // If still in the same extended quiescent state, we are good!
+ return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK);
}
/*
@@ -392,14 +384,17 @@
{
int old;
int new;
- struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+ int new_old;
+ struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+ new_old = atomic_read(&rdp->dynticks);
do {
- old = atomic_read(&rdtp->dynticks);
+ old = new_old;
if (old & RCU_DYNTICK_CTRL_CTR)
return false;
new = old | RCU_DYNTICK_CTRL_MASK;
- } while (atomic_cmpxchg(&rdtp->dynticks, old, new) != old);
+ new_old = atomic_cmpxchg(&rdp->dynticks, old, new);
+ } while (new_old != old);
return true;
}
@@ -414,105 +409,128 @@
*
* The caller must have disabled interrupts and must not be idle.
*/
-static void rcu_momentary_dyntick_idle(void)
+notrace void rcu_momentary_dyntick_idle(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
int special;
- raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
- special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ raw_cpu_write(rcu_data.rcu_need_heavy_qs, false);
+ special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
+ &this_cpu_ptr(&rcu_data)->dynticks);
/* It is illegal to call this from idle state. */
WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
+ rcu_preempt_deferred_qs(current);
}
+EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
-/*
- * Note a context switch. This is a quiescent state for RCU-sched,
- * and requires special handling for preemptible RCU.
- * The caller must have disabled interrupts.
- */
-void rcu_note_context_switch(bool preempt)
-{
- barrier(); /* Avoid RCU read-side critical sections leaking down. */
- trace_rcu_utilization(TPS("Start context switch"));
- rcu_sched_qs();
- rcu_preempt_note_context_switch(preempt);
- /* Load rcu_urgent_qs before other flags. */
- if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs)))
- goto out;
- this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
- if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs)))
- rcu_momentary_dyntick_idle();
- this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
- if (!preempt)
- rcu_tasks_qs(current);
-out:
- trace_rcu_utilization(TPS("End context switch"));
- barrier(); /* Avoid RCU read-side critical sections leaking up. */
-}
-EXPORT_SYMBOL_GPL(rcu_note_context_switch);
-
-/*
- * Register a quiescent state for all RCU flavors. If there is an
- * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight
- * dyntick-idle quiescent state visible to other CPUs (but only for those
- * RCU flavors in desperate need of a quiescent state, which will normally
- * be none of them). Either way, do a lightweight quiescent state for
- * all RCU flavors.
+/**
+ * rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle
*
- * The barrier() calls are redundant in the common case when this is
- * called externally, but just in case this is called from within this
- * file.
+ * If the current CPU is idle and running at a first-level (not nested)
+ * interrupt, or directly, from idle, return true.
*
+ * The caller must have at least disabled IRQs.
*/
-void rcu_all_qs(void)
+static int rcu_is_cpu_rrupt_from_idle(void)
{
- unsigned long flags;
+ long nesting;
- if (!raw_cpu_read(rcu_dynticks.rcu_urgent_qs))
- return;
- preempt_disable();
- /* Load rcu_urgent_qs before other flags. */
- if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) {
- preempt_enable();
- return;
- }
- this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
- barrier(); /* Avoid RCU read-side critical sections leaking down. */
- if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs))) {
- local_irq_save(flags);
- rcu_momentary_dyntick_idle();
- local_irq_restore(flags);
- }
- if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)))
- rcu_sched_qs();
- this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
- barrier(); /* Avoid RCU read-side critical sections leaking up. */
- preempt_enable();
+ /*
+ * Usually called from the tick; but also used from smp_function_call()
+ * for expedited grace periods. This latter can result in running from
+ * the idle task, instead of an actual IPI.
+ */
+ lockdep_assert_irqs_disabled();
+
+ /* Check for counter underflows */
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0,
+ "RCU dynticks_nesting counter underflow!");
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 0,
+ "RCU dynticks_nmi_nesting counter underflow/zero!");
+
+ /* Are we at first interrupt nesting level? */
+ nesting = __this_cpu_read(rcu_data.dynticks_nmi_nesting);
+ if (nesting > 1)
+ return false;
+
+ /*
+ * If we're not in an interrupt, we must be in the idle task!
+ */
+ WARN_ON_ONCE(!nesting && !is_idle_task(current));
+
+ /* Does CPU appear to be idle from an RCU standpoint? */
+ return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
}
-EXPORT_SYMBOL_GPL(rcu_all_qs);
-#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */
+#define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10)
+ // Maximum callbacks per rcu_do_batch ...
+#define DEFAULT_MAX_RCU_BLIMIT 10000 // ... even during callback flood.
static long blimit = DEFAULT_RCU_BLIMIT;
-#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */
+#define DEFAULT_RCU_QHIMARK 10000 // If this many pending, ignore blimit.
static long qhimark = DEFAULT_RCU_QHIMARK;
-#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */
+#define DEFAULT_RCU_QLOMARK 100 // Once only this many pending, use blimit.
static long qlowmark = DEFAULT_RCU_QLOMARK;
+#define DEFAULT_RCU_QOVLD_MULT 2
+#define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK)
+static long qovld = DEFAULT_RCU_QOVLD; // If this many pending, hammer QS.
+static long qovld_calc = -1; // No pre-initialization lock acquisitions!
module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);
+module_param(qovld, long, 0444);
-static ulong jiffies_till_first_fqs = ULONG_MAX;
+static ulong jiffies_till_first_fqs = IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 0 : ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
static bool rcu_kick_kthreads;
+static int rcu_divisor = 7;
+module_param(rcu_divisor, int, 0644);
+
+/* Force an exit from rcu_do_batch() after 3 milliseconds. */
+static long rcu_resched_ns = 3 * NSEC_PER_MSEC;
+module_param(rcu_resched_ns, long, 0644);
+
+/*
+ * How long the grace period must be before we start recruiting
+ * quiescent-state help from rcu_note_context_switch().
+ */
+static ulong jiffies_till_sched_qs = ULONG_MAX;
+module_param(jiffies_till_sched_qs, ulong, 0444);
+static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */
+module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */
+
+/*
+ * Make sure that we give the grace-period kthread time to detect any
+ * idle CPUs before taking active measures to force quiescent states.
+ * However, don't go below 100 milliseconds, adjusted upwards for really
+ * large systems.
+ */
+static void adjust_jiffies_till_sched_qs(void)
+{
+ unsigned long j;
+
+ /* If jiffies_till_sched_qs was specified, respect the request. */
+ if (jiffies_till_sched_qs != ULONG_MAX) {
+ WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs);
+ return;
+ }
+ /* Otherwise, set to third fqs scan, but bound below on large system. */
+ j = READ_ONCE(jiffies_till_first_fqs) +
+ 2 * READ_ONCE(jiffies_till_next_fqs);
+ if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV)
+ j = HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
+ pr_info("RCU calculated value of scheduler-enlistment delay is %ld jiffies.\n", j);
+ WRITE_ONCE(jiffies_to_sched_qs, j);
+}
static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
{
ulong j;
int ret = kstrtoul(val, 0, &j);
- if (!ret)
+ if (!ret) {
WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
+ adjust_jiffies_till_sched_qs();
+ }
return ret;
}
@@ -521,8 +539,10 @@
ulong j;
int ret = kstrtoul(val, 0, &j);
- if (!ret)
+ if (!ret) {
WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
+ adjust_jiffies_till_sched_qs();
+ }
return ret;
}
@@ -540,43 +560,17 @@
module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
module_param(rcu_kick_kthreads, bool, 0644);
-/*
- * How long the grace period must be before we start recruiting
- * quiescent-state help from rcu_note_context_switch().
- */
-static ulong jiffies_till_sched_qs = HZ / 10;
-module_param(jiffies_till_sched_qs, ulong, 0444);
-
-static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp));
-static void force_quiescent_state(struct rcu_state *rsp);
-static int rcu_pending(void);
+static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
+static int rcu_pending(int user);
/*
* Return the number of RCU GPs completed thus far for debug & stats.
*/
unsigned long rcu_get_gp_seq(void)
{
- return READ_ONCE(rcu_state_p->gp_seq);
+ return READ_ONCE(rcu_state.gp_seq);
}
EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
-
-/*
- * Return the number of RCU-sched GPs completed thus far for debug & stats.
- */
-unsigned long rcu_sched_get_gp_seq(void)
-{
- return READ_ONCE(rcu_sched_state.gp_seq);
-}
-EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
-
-/*
- * Return the number of RCU-bh GPs completed thus far for debug & stats.
- */
-unsigned long rcu_bh_get_gp_seq(void)
-{
- return READ_ONCE(rcu_bh_state.gp_seq);
-}
-EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq);
/*
* Return the number of RCU expedited batches completed thus far for
@@ -586,82 +580,17 @@
*/
unsigned long rcu_exp_batches_completed(void)
{
- return rcu_state_p->expedited_sequence;
+ return rcu_state.expedited_sequence;
}
EXPORT_SYMBOL_GPL(rcu_exp_batches_completed);
/*
- * Return the number of RCU-sched expedited batches completed thus far
- * for debug & stats. Similar to rcu_exp_batches_completed().
+ * Return the root node of the rcu_state structure.
*/
-unsigned long rcu_exp_batches_completed_sched(void)
+static struct rcu_node *rcu_get_root(void)
{
- return rcu_sched_state.expedited_sequence;
+ return &rcu_state.node[0];
}
-EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched);
-
-/*
- * Force a quiescent state.
- */
-void rcu_force_quiescent_state(void)
-{
- force_quiescent_state(rcu_state_p);
-}
-EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
-
-/*
- * Force a quiescent state for RCU BH.
- */
-void rcu_bh_force_quiescent_state(void)
-{
- force_quiescent_state(&rcu_bh_state);
-}
-EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
-
-/*
- * Force a quiescent state for RCU-sched.
- */
-void rcu_sched_force_quiescent_state(void)
-{
- force_quiescent_state(&rcu_sched_state);
-}
-EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
-
-/*
- * Show the state of the grace-period kthreads.
- */
-void show_rcu_gp_kthreads(void)
-{
- int cpu;
- struct rcu_data *rdp;
- struct rcu_node *rnp;
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp) {
- pr_info("%s: wait state: %d ->state: %#lx\n",
- rsp->name, rsp->gp_state, rsp->gp_kthread->state);
- rcu_for_each_node_breadth_first(rsp, rnp) {
- if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed))
- continue;
- pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
- rnp->grplo, rnp->grphi, rnp->gp_seq,
- rnp->gp_seq_needed);
- if (!rcu_is_leaf_node(rnp))
- continue;
- for_each_leaf_node_possible_cpu(rnp, cpu) {
- rdp = per_cpu_ptr(rsp->rda, cpu);
- if (rdp->gpwrap ||
- ULONG_CMP_GE(rsp->gp_seq,
- rdp->gp_seq_needed))
- continue;
- pr_info("\tcpu %d ->gp_seq_needed %lu\n",
- cpu, rdp->gp_seq_needed);
- }
- }
- /* sched_show_task(rsp->gp_kthread); */
- }
-}
-EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
/*
* Send along grace-period-related data for rcutorture diagnostics.
@@ -669,35 +598,16 @@
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
unsigned long *gp_seq)
{
- struct rcu_state *rsp = NULL;
-
switch (test_type) {
case RCU_FLAVOR:
- rsp = rcu_state_p;
- break;
- case RCU_BH_FLAVOR:
- rsp = &rcu_bh_state;
- break;
- case RCU_SCHED_FLAVOR:
- rsp = &rcu_sched_state;
+ *flags = READ_ONCE(rcu_state.gp_flags);
+ *gp_seq = rcu_seq_current(&rcu_state.gp_seq);
break;
default:
break;
}
- if (rsp == NULL)
- return;
- *flags = READ_ONCE(rsp->gp_flags);
- *gp_seq = rcu_seq_current(&rsp->gp_seq);
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
-
-/*
- * Return the root node of the specified rcu_state structure.
- */
-static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
-{
- return &rsp->node[0];
-}
/*
* Enter an RCU extended quiescent state, which can be either the
@@ -707,31 +617,36 @@
* the possibility of usermode upcalls having messed up our count
* of interrupt nesting level during the prior busy period.
*/
-static void rcu_eqs_enter(bool user)
+static noinstr void rcu_eqs_enter(bool user)
{
- struct rcu_state *rsp;
- struct rcu_data *rdp;
- struct rcu_dynticks *rdtp;
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
- rdtp = this_cpu_ptr(&rcu_dynticks);
- WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0);
+ WARN_ON_ONCE(rdp->dynticks_nmi_nesting != DYNTICK_IRQ_NONIDLE);
+ WRITE_ONCE(rdp->dynticks_nmi_nesting, 0);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
- rdtp->dynticks_nesting == 0);
- if (rdtp->dynticks_nesting != 1) {
- rdtp->dynticks_nesting--;
+ rdp->dynticks_nesting == 0);
+ if (rdp->dynticks_nesting != 1) {
+ // RCU will still be watching, so just do accounting and leave.
+ rdp->dynticks_nesting--;
return;
}
lockdep_assert_irqs_disabled();
- trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0, rdtp->dynticks);
+ instrumentation_begin();
+ trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
- for_each_rcu_flavor(rsp) {
- rdp = this_cpu_ptr(rsp->rda);
- do_nocb_deferred_wakeup(rdp);
- }
+ rdp = this_cpu_ptr(&rcu_data);
rcu_prepare_for_idle();
- WRITE_ONCE(rdtp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
+ rcu_preempt_deferred_qs(current);
+
+ // instrumentation for the noinstr rcu_dynticks_eqs_enter()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
+ instrumentation_end();
+ WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
+ // RCU is watching here ...
rcu_dynticks_eqs_enter();
+ // ... but is no longer watching here.
rcu_dynticks_task_enter();
}
@@ -751,6 +666,7 @@
lockdep_assert_irqs_disabled();
rcu_eqs_enter(false);
}
+EXPORT_SYMBOL_GPL(rcu_idle_enter);
#ifdef CONFIG_NO_HZ_FULL
/**
@@ -764,9 +680,16 @@
* If you add or remove a call to rcu_user_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_user_enter(void)
+noinstr void rcu_user_enter(void)
{
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
lockdep_assert_irqs_disabled();
+
+ instrumentation_begin();
+ do_nocb_deferred_wakeup(rdp);
+ instrumentation_end();
+
rcu_eqs_enter(true);
}
#endif /* CONFIG_NO_HZ_FULL */
@@ -775,40 +698,56 @@
* rcu_nmi_exit - inform RCU of exit from NMI context
*
* If we are returning from the outermost NMI handler that interrupted an
- * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
+ * RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
* to let the RCU grace-period handling know that the CPU is back to
* being RCU-idle.
*
* If you add or remove a call to rcu_nmi_exit(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_nmi_exit(void)
+noinstr void rcu_nmi_exit(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+ instrumentation_begin();
/*
* Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
* (We are exiting an NMI handler, so RCU better be paying attention
* to us!)
*/
- WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
+ WARN_ON_ONCE(rdp->dynticks_nmi_nesting <= 0);
WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
/*
* If the nesting level is not 1, the CPU wasn't RCU-idle, so
* leave it in non-RCU-idle state.
*/
- if (rdtp->dynticks_nmi_nesting != 1) {
- trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nmi_nesting, rdtp->dynticks_nmi_nesting - 2, rdtp->dynticks);
- WRITE_ONCE(rdtp->dynticks_nmi_nesting, /* No store tearing. */
- rdtp->dynticks_nmi_nesting - 2);
+ if (rdp->dynticks_nmi_nesting != 1) {
+ trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
+ atomic_read(&rdp->dynticks));
+ WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
+ rdp->dynticks_nmi_nesting - 2);
+ instrumentation_end();
return;
}
/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
- trace_rcu_dyntick(TPS("Startirq"), rdtp->dynticks_nmi_nesting, 0, rdtp->dynticks);
- WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
+ trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
+ WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
+
+ if (!in_nmi())
+ rcu_prepare_for_idle();
+
+ // instrumentation for the noinstr rcu_dynticks_eqs_enter()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+ instrumentation_end();
+
+ // RCU is watching here ...
rcu_dynticks_eqs_enter();
+ // ... but is no longer watching here.
+
+ if (!in_nmi())
+ rcu_dynticks_task_enter();
}
/**
@@ -830,17 +769,51 @@
* If you add or remove a call to rcu_irq_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_irq_exit(void)
+void noinstr rcu_irq_exit(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
-
lockdep_assert_irqs_disabled();
- if (rdtp->dynticks_nmi_nesting == 1)
- rcu_prepare_for_idle();
rcu_nmi_exit();
- if (rdtp->dynticks_nmi_nesting == 0)
- rcu_dynticks_task_enter();
}
+
+/**
+ * rcu_irq_exit_preempt - Inform RCU that current CPU is exiting irq
+ * towards in kernel preemption
+ *
+ * Same as rcu_irq_exit() but has a sanity check that scheduling is safe
+ * from RCU point of view. Invoked from return from interrupt before kernel
+ * preemption.
+ */
+void rcu_irq_exit_preempt(void)
+{
+ lockdep_assert_irqs_disabled();
+ rcu_nmi_exit();
+
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+ "RCU dynticks_nesting counter underflow/zero!");
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+ DYNTICK_IRQ_NONIDLE,
+ "Bad RCU dynticks_nmi_nesting counter\n");
+ RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+ "RCU in extended quiescent state!");
+}
+
+#ifdef CONFIG_PROVE_RCU
+/**
+ * rcu_irq_exit_check_preempt - Validate that scheduling is possible
+ */
+void rcu_irq_exit_check_preempt(void)
+{
+ lockdep_assert_irqs_disabled();
+
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+ "RCU dynticks_nesting counter underflow/zero!");
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+ DYNTICK_IRQ_NONIDLE,
+ "Bad RCU dynticks_nmi_nesting counter\n");
+ RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+ "RCU in extended quiescent state!");
+}
+#endif /* #ifdef CONFIG_PROVE_RCU */
/*
* Wrapper for rcu_irq_exit() where interrupts are enabled.
@@ -865,26 +838,36 @@
* allow for the possibility of usermode upcalls messing up our count of
* interrupt nesting level during the busy period that is just now starting.
*/
-static void rcu_eqs_exit(bool user)
+static void noinstr rcu_eqs_exit(bool user)
{
- struct rcu_dynticks *rdtp;
+ struct rcu_data *rdp;
long oldval;
lockdep_assert_irqs_disabled();
- rdtp = this_cpu_ptr(&rcu_dynticks);
- oldval = rdtp->dynticks_nesting;
+ rdp = this_cpu_ptr(&rcu_data);
+ oldval = rdp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
if (oldval) {
- rdtp->dynticks_nesting++;
+ // RCU was already watching, so just do accounting and leave.
+ rdp->dynticks_nesting++;
return;
}
rcu_dynticks_task_exit();
+ // RCU is not watching here ...
rcu_dynticks_eqs_exit();
+ // ... but is watching here.
+ instrumentation_begin();
+
+ // instrumentation for the noinstr rcu_dynticks_eqs_exit()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
rcu_cleanup_after_idle();
- trace_rcu_dyntick(TPS("End"), rdtp->dynticks_nesting, 1, rdtp->dynticks);
+ trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
- WRITE_ONCE(rdtp->dynticks_nesting, 1);
- WRITE_ONCE(rdtp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
+ WRITE_ONCE(rdp->dynticks_nesting, 1);
+ WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
+ WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
+ instrumentation_end();
}
/**
@@ -904,6 +887,7 @@
rcu_eqs_exit(false);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_idle_exit);
#ifdef CONFIG_NO_HZ_FULL
/**
@@ -915,17 +899,79 @@
* If you add or remove a call to rcu_user_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_user_exit(void)
+void noinstr rcu_user_exit(void)
{
rcu_eqs_exit(1);
}
+
+/**
+ * __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it.
+ *
+ * The scheduler tick is not normally enabled when CPUs enter the kernel
+ * from nohz_full userspace execution. After all, nohz_full userspace
+ * execution is an RCU quiescent state and the time executing in the kernel
+ * is quite short. Except of course when it isn't. And it is not hard to
+ * cause a large system to spend tens of seconds or even minutes looping
+ * in the kernel, which can cause a number of problems, include RCU CPU
+ * stall warnings.
+ *
+ * Therefore, if a nohz_full CPU fails to report a quiescent state
+ * in a timely manner, the RCU grace-period kthread sets that CPU's
+ * ->rcu_urgent_qs flag with the expectation that the next interrupt or
+ * exception will invoke this function, which will turn on the scheduler
+ * tick, which will enable RCU to detect that CPU's quiescent states,
+ * for example, due to cond_resched() calls in CONFIG_PREEMPT=n kernels.
+ * The tick will be disabled once a quiescent state is reported for
+ * this CPU.
+ *
+ * Of course, in carefully tuned systems, there might never be an
+ * interrupt or exception. In that case, the RCU grace-period kthread
+ * will eventually cause one to happen. However, in less carefully
+ * controlled environments, this function allows RCU to get what it
+ * needs without creating otherwise useless interruptions.
+ */
+void __rcu_irq_enter_check_tick(void)
+{
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+ // If we're here from NMI there's nothing to do.
+ if (in_nmi())
+ return;
+
+ RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+ "Illegal rcu_irq_enter_check_tick() from extended quiescent state");
+
+ if (!tick_nohz_full_cpu(rdp->cpu) ||
+ !READ_ONCE(rdp->rcu_urgent_qs) ||
+ READ_ONCE(rdp->rcu_forced_tick)) {
+ // RCU doesn't need nohz_full help from this CPU, or it is
+ // already getting that help.
+ return;
+ }
+
+ // We get here only when not in an extended quiescent state and
+ // from interrupts (as opposed to NMIs). Therefore, (1) RCU is
+ // already watching and (2) The fact that we are in an interrupt
+ // handler and that the rcu_node lock is an irq-disabled lock
+ // prevents self-deadlock. So we can safely recheck under the lock.
+ // Note that the nohz_full state currently cannot change.
+ raw_spin_lock_rcu_node(rdp->mynode);
+ if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+ // A nohz_full CPU is in the kernel and RCU needs a
+ // quiescent state. Turn on the tick!
+ WRITE_ONCE(rdp->rcu_forced_tick, true);
+ tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+ }
+ raw_spin_unlock_rcu_node(rdp->mynode);
+}
+NOKPROBE_SYMBOL(__rcu_irq_enter_check_tick);
#endif /* CONFIG_NO_HZ_FULL */
/**
* rcu_nmi_enter - inform RCU of entry to NMI context
*
- * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and
- * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know
+ * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
+ * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know
* that the CPU is active. This implementation permits nested NMIs, as
* long as the nesting level does not overflow an int. (You will probably
* run out of stack space first.)
@@ -933,13 +979,13 @@
* If you add or remove a call to rcu_nmi_enter(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_nmi_enter(void)
+noinstr void rcu_nmi_enter(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
long incby = 2;
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
/* Complain about underflow. */
- WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0);
+ WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0);
/*
* If idle from RCU viewpoint, atomically increment ->dynticks
@@ -950,14 +996,40 @@
* period (observation due to Andy Lutomirski).
*/
if (rcu_dynticks_curr_cpu_in_eqs()) {
+
+ if (!in_nmi())
+ rcu_dynticks_task_exit();
+
+ // RCU is not watching here ...
rcu_dynticks_eqs_exit();
+ // ... but is watching here.
+
+ if (!in_nmi()) {
+ instrumentation_begin();
+ rcu_cleanup_after_idle();
+ instrumentation_end();
+ }
+
+ instrumentation_begin();
+ // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
+ instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
+ // instrumentation for the noinstr rcu_dynticks_eqs_exit()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
incby = 1;
+ } else if (!in_nmi()) {
+ instrumentation_begin();
+ rcu_irq_enter_check_tick();
+ } else {
+ instrumentation_begin();
}
+
trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
- rdtp->dynticks_nmi_nesting,
- rdtp->dynticks_nmi_nesting + incby, rdtp->dynticks);
- WRITE_ONCE(rdtp->dynticks_nmi_nesting, /* Prevent store tearing. */
- rdtp->dynticks_nmi_nesting + incby);
+ rdp->dynticks_nmi_nesting,
+ rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
+ instrumentation_end();
+ WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
+ rdp->dynticks_nmi_nesting + incby);
barrier();
}
@@ -983,16 +1055,10 @@
* If you add or remove a call to rcu_irq_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_irq_enter(void)
+noinstr void rcu_irq_enter(void)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
-
lockdep_assert_irqs_disabled();
- if (rdtp->dynticks_nmi_nesting == 0)
- rcu_dynticks_task_exit();
rcu_nmi_enter();
- if (rdtp->dynticks_nmi_nesting == 1)
- rcu_cleanup_after_idle();
}
/*
@@ -1010,15 +1076,34 @@
local_irq_restore(flags);
}
+/*
+ * If any sort of urgency was applied to the current CPU (for example,
+ * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
+ * to get to a quiescent state, disable it.
+ */
+static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
+{
+ raw_lockdep_assert_held_rcu_node(rdp->mynode);
+ WRITE_ONCE(rdp->rcu_urgent_qs, false);
+ WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
+ if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
+ tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+ WRITE_ONCE(rdp->rcu_forced_tick, false);
+ }
+}
+
/**
- * rcu_is_watching - see if RCU thinks that the current CPU is idle
+ * rcu_is_watching - see if RCU thinks that the current CPU is not idle
*
* Return true if RCU is watching the running CPU, which means that this
* CPU can safely enter RCU read-side critical sections. In other words,
- * if the current CPU is in its idle loop and is neither in an interrupt
- * or NMI handler, return true.
+ * if the current CPU is not in its idle loop or is in an interrupt or
+ * NMI handler, return true.
+ *
+ * Make notrace because it can be called by the internal functions of
+ * ftrace, and making this notrace removes unnecessary recursion calls.
*/
-bool notrace rcu_is_watching(void)
+notrace bool rcu_is_watching(void)
{
bool ret;
@@ -1044,7 +1129,7 @@
cpu = task_cpu(t);
if (!task_curr(t))
return; /* This task is not running on that CPU. */
- smp_store_release(per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, cpu), true);
+ smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true);
}
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
@@ -1055,11 +1140,7 @@
* Disable preemption to avoid false positives that could otherwise
* happen due to the current CPU number being sampled, this task being
* preempted, its old CPU being taken offline, resuming on some other CPU,
- * then determining that its old CPU is now offline. Because there are
- * multiple flavors of RCU, and because this function can be called in the
- * midst of updating the flavors while a given CPU coming online or going
- * offline, it is necessary to check all flavors. If any of the flavors
- * believe that given CPU is online, it is considered to be online.
+ * then determining that its old CPU is now offline.
*
* Disable checking if in an NMI handler because we cannot safely
* report errors from NMI handlers anyway. In addition, it is OK to use
@@ -1070,38 +1151,21 @@
{
struct rcu_data *rdp;
struct rcu_node *rnp;
- struct rcu_state *rsp;
+ bool ret = false;
if (in_nmi() || !rcu_scheduler_fully_active)
return true;
- preempt_disable();
- for_each_rcu_flavor(rsp) {
- rdp = this_cpu_ptr(rsp->rda);
- rnp = rdp->mynode;
- if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) {
- preempt_enable();
- return true;
- }
- }
- preempt_enable();
- return false;
+ preempt_disable_notrace();
+ rdp = this_cpu_ptr(&rcu_data);
+ rnp = rdp->mynode;
+ if (rdp->grpmask & rcu_rnp_online_cpus(rnp) || READ_ONCE(rnp->ofl_seq) & 0x1)
+ ret = true;
+ preempt_enable_notrace();
+ return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */
-
-/**
- * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
- *
- * If the current CPU is idle or running at a first-level (not nested)
- * interrupt from idle, return true. The caller must have at least
- * disabled preemption.
- */
-static int rcu_is_cpu_rrupt_from_idle(void)
-{
- return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 0 &&
- __this_cpu_read(rcu_dynticks.dynticks_nmi_nesting) <= 1;
-}
/*
* We are reporting a quiescent state on behalf of some other CPU, so
@@ -1127,34 +1191,13 @@
*/
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
- rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
+ rdp->dynticks_snap = rcu_dynticks_snap(rdp);
if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
+ trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rdp->mynode, rdp);
return 1;
}
return 0;
-}
-
-/*
- * Handler for the irq_work request posted when a grace period has
- * gone on for too long, but not yet long enough for an RCU CPU
- * stall warning. Set state appropriately, but just complain if
- * there is unexpected state on entry.
- */
-static void rcu_iw_handler(struct irq_work *iwp)
-{
- struct rcu_data *rdp;
- struct rcu_node *rnp;
-
- rdp = container_of(iwp, struct rcu_data, rcu_iw);
- rnp = rdp->mynode;
- raw_spin_lock_rcu_node(rnp);
- if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
- rdp->rcu_iw_gp_seq = rnp->gp_seq;
- rdp->rcu_iw_pending = false;
- }
- raw_spin_unlock_rcu_node(rnp);
}
/*
@@ -1178,39 +1221,34 @@
* read-side critical section that started before the beginning
* of the current RCU grace period.
*/
- if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
- rdp->dynticks_fqs++;
+ if (rcu_dynticks_in_eqs_since(rdp, rdp->dynticks_snap)) {
+ trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rnp, rdp);
return 1;
}
/*
- * Has this CPU encountered a cond_resched() since the beginning
- * of the grace period? For this to be the case, the CPU has to
- * have noticed the current grace period. This might not be the
- * case for nohz_full CPUs looping in the kernel.
+ * Complain if a CPU that is considered to be offline from RCU's
+ * perspective has not yet reported a quiescent state. After all,
+ * the offline CPU should have reported a quiescent state during
+ * the CPU-offline process, or, failing that, by rcu_gp_init()
+ * if it ran concurrently with either the CPU going offline or the
+ * last task on a leaf rcu_node structure exiting its RCU read-side
+ * critical section while all CPUs corresponding to that structure
+ * are offline. This added warning detects bugs in any of these
+ * code paths.
+ *
+ * The rcu_node structure's ->lock is held here, which excludes
+ * the relevant portions the CPU-hotplug code, the grace-period
+ * initialization code, and the rcu_read_unlock() code paths.
+ *
+ * For more detail, please refer to the "Hotplug CPU" section
+ * of RCU's Requirements documentation.
*/
- jtsq = jiffies_till_sched_qs;
- ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
- if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
- READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
- rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc"));
- rcu_gpnum_ovf(rnp, rdp);
- return 1;
- } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) {
- /* Load rcu_qs_ctr before store to rcu_urgent_qs. */
- smp_store_release(ruqp, true);
- }
-
- /* If waiting too long on an offline CPU, complain. */
- if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
- time_after(jiffies, rdp->rsp->gp_start + HZ)) {
+ if (WARN_ON_ONCE(!(rdp->grpmask & rcu_rnp_online_cpus(rnp)))) {
bool onl;
struct rcu_node *rnp1;
- WARN_ON(1); /* Offline CPUs are supposed to report QS! */
pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
__func__, rnp->grplo, rnp->grphi, rnp->level,
(long)rnp->gp_seq, (long)rnp->completedqs);
@@ -1227,43 +1265,63 @@
/*
* A CPU running for an extended time within the kernel can
- * delay RCU grace periods. When the CPU is in NO_HZ_FULL mode,
- * even context-switching back and forth between a pair of
- * in-kernel CPU-bound tasks cannot advance grace periods.
- * So if the grace period is old enough, make the CPU pay attention.
- * Note that the unsynchronized assignments to the per-CPU
- * rcu_need_heavy_qs variable are safe. Yes, setting of
- * bits can be lost, but they will be set again on the next
- * force-quiescent-state pass. So lost bit sets do not result
- * in incorrect behavior, merely in a grace period lasting
- * a few jiffies longer than it might otherwise. Because
- * there are at most four threads involved, and because the
- * updates are only once every few jiffies, the probability of
- * lossage (and thus of slight grace-period extension) is
- * quite low.
+ * delay RCU grace periods: (1) At age jiffies_to_sched_qs,
+ * set .rcu_urgent_qs, (2) At age 2*jiffies_to_sched_qs, set
+ * both .rcu_need_heavy_qs and .rcu_urgent_qs. Note that the
+ * unsynchronized assignments to the per-CPU rcu_need_heavy_qs
+ * variable are safe because the assignments are repeated if this
+ * CPU failed to pass through a quiescent state. This code
+ * also checks .jiffies_resched in case jiffies_to_sched_qs
+ * is set way high.
*/
- rnhqp = &per_cpu(rcu_dynticks.rcu_need_heavy_qs, rdp->cpu);
+ jtsq = READ_ONCE(jiffies_to_sched_qs);
+ ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu);
+ rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu);
if (!READ_ONCE(*rnhqp) &&
- (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
- time_after(jiffies, rdp->rsp->jiffies_resched))) {
+ (time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
+ time_after(jiffies, rcu_state.jiffies_resched) ||
+ rcu_state.cbovld)) {
WRITE_ONCE(*rnhqp, true);
/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
smp_store_release(ruqp, true);
- rdp->rsp->jiffies_resched += jtsq; /* Re-enable beating. */
+ } else if (time_after(jiffies, rcu_state.gp_start + jtsq)) {
+ WRITE_ONCE(*ruqp, true);
}
/*
- * If more than halfway to RCU CPU stall-warning time, do a
- * resched_cpu() to try to loosen things up a bit. Also check to
- * see if the CPU is getting hammered with interrupts, but only
- * once per grace period, just to keep the IPIs down to a dull roar.
+ * NO_HZ_FULL CPUs can run in-kernel without rcu_sched_clock_irq!
+ * The above code handles this, but only for straight cond_resched().
+ * And some in-kernel loops check need_resched() before calling
+ * cond_resched(), which defeats the above code for CPUs that are
+ * running in-kernel with scheduling-clock interrupts disabled.
+ * So hit them over the head with the resched_cpu() hammer!
*/
- if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) {
+ if (tick_nohz_full_cpu(rdp->cpu) &&
+ (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
+ rcu_state.cbovld)) {
+ WRITE_ONCE(*ruqp, true);
resched_cpu(rdp->cpu);
+ WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+ }
+
+ /*
+ * If more than halfway to RCU CPU stall-warning time, invoke
+ * resched_cpu() more frequently to try to loosen things up a bit.
+ * Also check to see if the CPU is getting hammered with interrupts,
+ * but only once per grace period, just to keep the IPIs down to
+ * a dull roar.
+ */
+ if (time_after(jiffies, rcu_state.jiffies_resched)) {
+ if (time_after(jiffies,
+ READ_ONCE(rdp->last_fqs_resched) + jtsq)) {
+ resched_cpu(rdp->cpu);
+ WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+ }
if (IS_ENABLED(CONFIG_IRQ_WORK) &&
!rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
+ atomic_set(&rdp->rcu_iw.flags, IRQ_WORK_HARD_IRQ);
rdp->rcu_iw_pending = true;
rdp->rcu_iw_gp_seq = rnp->gp_seq;
irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
@@ -1273,317 +1331,13 @@
return 0;
}
-static void record_gp_stall_check_time(struct rcu_state *rsp)
-{
- unsigned long j = jiffies;
- unsigned long j1;
-
- rsp->gp_start = j;
- j1 = rcu_jiffies_till_stall_check();
- /* Record ->gp_start before ->jiffies_stall. */
- smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */
- rsp->jiffies_resched = j + j1 / 2;
- rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
-}
-
-/*
- * Convert a ->gp_state value to a character string.
- */
-static const char *gp_state_getname(short gs)
-{
- if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
- return "???";
- return gp_state_names[gs];
-}
-
-/*
- * Complain about starvation of grace-period kthread.
- */
-static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
-{
- unsigned long gpa;
- unsigned long j;
-
- j = jiffies;
- gpa = READ_ONCE(rsp->gp_activity);
- if (j - gpa > 2 * HZ) {
- pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
- rsp->name, j - gpa,
- (long)rcu_seq_current(&rsp->gp_seq),
- rsp->gp_flags,
- gp_state_getname(rsp->gp_state), rsp->gp_state,
- rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
- rsp->gp_kthread ? task_cpu(rsp->gp_kthread) : -1);
- if (rsp->gp_kthread) {
- pr_err("RCU grace-period kthread stack dump:\n");
- sched_show_task(rsp->gp_kthread);
- wake_up_process(rsp->gp_kthread);
- }
- }
-}
-
-/*
- * Dump stacks of all tasks running on stalled CPUs. First try using
- * NMIs, but fall back to manual remote stack tracing on architectures
- * that don't support NMI-based stack dumps. The NMI-triggered stack
- * traces are more accurate because they are printed by the target CPU.
- */
-static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
-{
- int cpu;
- unsigned long flags;
- struct rcu_node *rnp;
-
- rcu_for_each_leaf_node(rsp, rnp) {
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- for_each_leaf_node_possible_cpu(rnp, cpu)
- if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
- if (!trigger_single_cpu_backtrace(cpu))
- dump_cpu_task(cpu);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
-}
-
-/*
- * If too much time has passed in the current grace period, and if
- * so configured, go kick the relevant kthreads.
- */
-static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
-{
- unsigned long j;
-
- if (!rcu_kick_kthreads)
- return;
- j = READ_ONCE(rsp->jiffies_kick_kthreads);
- if (time_after(jiffies, j) && rsp->gp_kthread &&
- (rcu_gp_in_progress(rsp) || READ_ONCE(rsp->gp_flags))) {
- WARN_ONCE(1, "Kicking %s grace-period kthread\n", rsp->name);
- rcu_ftrace_dump(DUMP_ALL);
- wake_up_process(rsp->gp_kthread);
- WRITE_ONCE(rsp->jiffies_kick_kthreads, j + HZ);
- }
-}
-
-static void panic_on_rcu_stall(void)
-{
- if (sysctl_panic_on_rcu_stall)
- panic("RCU Stall\n");
-}
-
-static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
-{
- int cpu;
- unsigned long flags;
- unsigned long gpa;
- unsigned long j;
- int ndetected = 0;
- struct rcu_node *rnp = rcu_get_root(rsp);
- long totqlen = 0;
-
- /* Kick and suppress, if so configured. */
- rcu_stall_kick_kthreads(rsp);
- if (rcu_cpu_stall_suppress)
- return;
-
- /*
- * OK, time to rat on our buddy...
- * See Documentation/RCU/stallwarn.txt for info on how to debug
- * RCU CPU stall warnings.
- */
- pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name);
- print_cpu_stall_info_begin();
- rcu_for_each_leaf_node(rsp, rnp) {
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- ndetected += rcu_print_task_stall(rnp);
- if (rnp->qsmask != 0) {
- for_each_leaf_node_possible_cpu(rnp, cpu)
- if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
- print_cpu_stall_info(rsp, cpu);
- ndetected++;
- }
- }
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
-
- print_cpu_stall_info_end();
- for_each_possible_cpu(cpu)
- totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
- cpu)->cblist);
- pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
- smp_processor_id(), (long)(jiffies - rsp->gp_start),
- (long)rcu_seq_current(&rsp->gp_seq), totqlen);
- if (ndetected) {
- rcu_dump_cpu_stacks(rsp);
-
- /* Complain about tasks blocking the grace period. */
- rcu_print_detail_task_stall(rsp);
- } else {
- if (rcu_seq_current(&rsp->gp_seq) != gp_seq) {
- pr_err("INFO: Stall ended before state dump start\n");
- } else {
- j = jiffies;
- gpa = READ_ONCE(rsp->gp_activity);
- pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
- rsp->name, j - gpa, j, gpa,
- jiffies_till_next_fqs,
- rcu_get_root(rsp)->qsmask);
- /* In this case, the current CPU might be at fault. */
- sched_show_task(current);
- }
- }
- /* Rewrite if needed in case of slow consoles. */
- if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
- WRITE_ONCE(rsp->jiffies_stall,
- jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-
- rcu_check_gp_kthread_starvation(rsp);
-
- atomic_notifier_call_chain(&rcu_stall_notifier_list, 0, NULL);
-
- panic_on_rcu_stall();
-
- force_quiescent_state(rsp); /* Kick them all. */
-}
-
-static void print_cpu_stall(struct rcu_state *rsp)
-{
- int cpu;
- unsigned long flags;
- struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- struct rcu_node *rnp = rcu_get_root(rsp);
- long totqlen = 0;
-
- /* Kick and suppress, if so configured. */
- rcu_stall_kick_kthreads(rsp);
- if (rcu_cpu_stall_suppress)
- return;
-
- /*
- * OK, time to rat on ourselves...
- * See Documentation/RCU/stallwarn.txt for info on how to debug
- * RCU CPU stall warnings.
- */
- pr_err("INFO: %s self-detected stall on CPU", rsp->name);
- print_cpu_stall_info_begin();
- raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
- print_cpu_stall_info(rsp, smp_processor_id());
- raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
- print_cpu_stall_info_end();
- for_each_possible_cpu(cpu)
- totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
- cpu)->cblist);
- pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
- jiffies - rsp->gp_start,
- (long)rcu_seq_current(&rsp->gp_seq), totqlen);
-
- rcu_check_gp_kthread_starvation(rsp);
-
- rcu_dump_cpu_stacks(rsp);
-
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- /* Rewrite if needed in case of slow consoles. */
- if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
- WRITE_ONCE(rsp->jiffies_stall,
- jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
- panic_on_rcu_stall();
-
- /*
- * Attempt to revive the RCU machinery by forcing a context switch.
- *
- * A context switch would normally allow the RCU state machine to make
- * progress and it could be we're stuck in kernel space without context
- * switches for an entirely unreasonable amount of time.
- */
- resched_cpu(smp_processor_id());
-}
-
-static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- unsigned long gs1;
- unsigned long gs2;
- unsigned long gps;
- unsigned long j;
- unsigned long jn;
- unsigned long js;
- struct rcu_node *rnp;
-
- if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
- !rcu_gp_in_progress(rsp))
- return;
- rcu_stall_kick_kthreads(rsp);
- j = jiffies;
-
- /*
- * Lots of memory barriers to reject false positives.
- *
- * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall,
- * then rsp->gp_start, and finally another copy of rsp->gp_seq.
- * These values are updated in the opposite order with memory
- * barriers (or equivalent) during grace-period initialization
- * and cleanup. Now, a false positive can occur if we get an new
- * value of rsp->gp_start and a old value of rsp->jiffies_stall.
- * But given the memory barriers, the only way that this can happen
- * is if one grace period ends and another starts between these
- * two fetches. This is detected by comparing the second fetch
- * of rsp->gp_seq with the previous fetch from rsp->gp_seq.
- *
- * Given this check, comparisons of jiffies, rsp->jiffies_stall,
- * and rsp->gp_start suffice to forestall false positives.
- */
- gs1 = READ_ONCE(rsp->gp_seq);
- smp_rmb(); /* Pick up ->gp_seq first... */
- js = READ_ONCE(rsp->jiffies_stall);
- smp_rmb(); /* ...then ->jiffies_stall before the rest... */
- gps = READ_ONCE(rsp->gp_start);
- smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
- gs2 = READ_ONCE(rsp->gp_seq);
- if (gs1 != gs2 ||
- ULONG_CMP_LT(j, js) ||
- ULONG_CMP_GE(gps, js))
- return; /* No stall or GP completed since entering function. */
- rnp = rdp->mynode;
- jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
- if (rcu_gp_in_progress(rsp) &&
- (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
- cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
-
- /* We haven't checked in, so go dump stack. */
- print_cpu_stall(rsp);
-
- } else if (rcu_gp_in_progress(rsp) &&
- ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
- cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
-
- /* They had a few time units to dump stack, so complain. */
- print_other_cpu_stall(rsp, gs2);
- }
-}
-
-/**
- * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
- *
- * Set the stall-warning timeout way off into the future, thus preventing
- * any RCU CPU stall-warning messages from appearing in the current set of
- * RCU grace periods.
- *
- * The caller must disable hard irqs.
- */
-void rcu_cpu_stall_reset(void)
-{
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp)
- WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
-}
-
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long gp_seq_req, const char *s)
{
- trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req,
- rnp->level, rnp->grplo, rnp->grphi, s);
+ trace_rcu_future_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+ gp_seq_req, rnp->level,
+ rnp->grplo, rnp->grphi, s);
}
/*
@@ -1606,7 +1360,6 @@
unsigned long gp_seq_req)
{
bool ret = false;
- struct rcu_state *rsp = rdp->rsp;
struct rcu_node *rnp;
/*
@@ -1631,7 +1384,7 @@
TPS("Prestarted"));
goto unlock_out;
}
- rnp->gp_seq_needed = gp_seq_req;
+ WRITE_ONCE(rnp->gp_seq_needed, gp_seq_req);
if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
/*
* We just marked the leaf or internal node, and a
@@ -1650,24 +1403,24 @@
}
/* If GP already in progress, just leave, otherwise start one. */
- if (rcu_gp_in_progress(rsp)) {
+ if (rcu_gp_in_progress()) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
goto unlock_out;
}
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
- WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
- rsp->gp_req_activity = jiffies;
- if (!rsp->gp_kthread) {
+ WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT);
+ WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+ if (!READ_ONCE(rcu_state.gp_kthread)) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
goto unlock_out;
}
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
+ trace_rcu_grace_period(rcu_state.name, data_race(rcu_state.gp_seq), TPS("newreq"));
ret = true; /* Caller must wake GP kthread. */
unlock_out:
/* Push furthest requested GP to leaf node and rcu_data structure. */
if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
- rnp_start->gp_seq_needed = rnp->gp_seq_needed;
- rdp->gp_seq_needed = rnp->gp_seq_needed;
+ WRITE_ONCE(rnp_start->gp_seq_needed, rnp->gp_seq_needed);
+ WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
}
if (rnp != rnp_start)
raw_spin_unlock_rcu_node(rnp);
@@ -1678,10 +1431,10 @@
* Clean up any old requests for the just-ended grace period. Also return
* whether any additional grace periods have been requested.
*/
-static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
{
bool needmore;
- struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
if (!needmore)
@@ -1692,12 +1445,13 @@
}
/*
- * Awaken the grace-period kthread. Don't do a self-awaken (unless in
- * an interrupt or softirq handler), and don't bother awakening when there
- * is nothing for the grace-period kthread to do (as in several CPUs raced
- * to awaken, and we lost), and finally don't try to awaken a kthread that
- * has not yet been created. If all those checks are passed, track some
- * debug information and awaken.
+ * Awaken the grace-period kthread. Don't do a self-awaken (unless in an
+ * interrupt or softirq handler, in which case we just might immediately
+ * sleep upon return, resulting in a grace-period hang), and don't bother
+ * awakening when there is nothing for the grace-period kthread to do
+ * (as in several CPUs raced to awaken, we lost), and finally don't try
+ * to awaken a kthread that has not yet been created. If all those checks
+ * are passed, track some debug information and awaken.
*
* So why do the self-wakeup when in an interrupt or softirq handler
* in the grace-period kthread's context? Because the kthread might have
@@ -1705,14 +1459,16 @@
* pre-sleep check of the awaken condition. In this case, a wakeup really
* is required, and is therefore supplied.
*/
-static void rcu_gp_kthread_wake(struct rcu_state *rsp)
+static void rcu_gp_kthread_wake(void)
{
- if ((current == rsp->gp_kthread &&
- !in_interrupt() && !in_serving_softirq()) ||
- !READ_ONCE(rsp->gp_flags) ||
- !rsp->gp_kthread)
+ struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
+
+ if ((current == t && !in_irq() && !in_serving_softirq()) ||
+ !READ_ONCE(rcu_state.gp_flags) || !t)
return;
- swake_up_one(&rsp->gp_wq);
+ WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
+ WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
+ swake_up_one(&rcu_state.gp_wq);
}
/*
@@ -1727,12 +1483,12 @@
*
* The caller must hold rnp->lock with interrupts disabled.
*/
-static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp)
+static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
{
unsigned long gp_seq_req;
bool ret = false;
+ rcu_lockdep_assert_cblist_protected(rdp);
raw_lockdep_assert_held_rcu_node(rnp);
/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
@@ -1749,15 +1505,16 @@
* accelerating callback invocation to an earlier grace-period
* number.
*/
- gp_seq_req = rcu_seq_snap(&rsp->gp_seq);
+ gp_seq_req = rcu_seq_snap(&rcu_state.gp_seq);
if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
- trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB"));
+ trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccWaitCB"));
else
- trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB"));
+ trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB"));
+
return ret;
}
@@ -1768,25 +1525,24 @@
* that a new grace-period request be made, invokes rcu_accelerate_cbs()
* while holding the leaf rcu_node structure's ->lock.
*/
-static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp,
- struct rcu_node *rnp,
+static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp,
struct rcu_data *rdp)
{
unsigned long c;
bool needwake;
- lockdep_assert_irqs_disabled();
- c = rcu_seq_snap(&rsp->gp_seq);
- if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+ rcu_lockdep_assert_cblist_protected(rdp);
+ c = rcu_seq_snap(&rcu_state.gp_seq);
+ if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
/* Old request still live, so mark recent callbacks. */
(void)rcu_segcblist_accelerate(&rdp->cblist, c);
return;
}
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
- needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ needwake = rcu_accelerate_cbs(rnp, rdp);
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
if (needwake)
- rcu_gp_kthread_wake(rsp);
+ rcu_gp_kthread_wake();
}
/*
@@ -1799,9 +1555,9 @@
*
* The caller must hold rnp->lock with interrupts disabled.
*/
-static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp)
+static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
{
+ rcu_lockdep_assert_cblist_protected(rdp);
raw_lockdep_assert_held_rcu_node(rnp);
/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
@@ -1815,7 +1571,36 @@
rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
/* Classify any remaining callbacks. */
- return rcu_accelerate_cbs(rsp, rnp, rdp);
+ return rcu_accelerate_cbs(rnp, rdp);
+}
+
+/*
+ * Move and classify callbacks, but only if doing so won't require
+ * that the RCU grace-period kthread be awakened.
+ */
+static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
+ struct rcu_data *rdp)
+{
+ rcu_lockdep_assert_cblist_protected(rdp);
+ if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp))
+ return;
+ // The grace period cannot end while we hold the rcu_node lock.
+ if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
+ WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+ raw_spin_unlock_rcu_node(rnp);
+}
+
+/*
+ * In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, attempt to generate a
+ * quiescent state. This is intended to be invoked when the CPU notices
+ * a new grace period.
+ */
+static void rcu_strict_gp_check_qs(void)
+{
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
+ rcu_read_lock();
+ rcu_read_unlock();
+ }
}
/*
@@ -1824,11 +1609,12 @@
* structure corresponding to the current CPU, and must have irqs disabled.
* Returns true if the grace-period kthread needs to be awakened.
*/
-static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp)
+static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
{
- bool ret;
- bool need_gp;
+ bool ret = false;
+ bool need_qs;
+ const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+ rcu_segcblist_is_offloaded(&rdp->cblist);
raw_lockdep_assert_held_rcu_node(rnp);
@@ -1838,10 +1624,15 @@
/* Handle the ends of any preceding grace periods first. */
if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
unlikely(READ_ONCE(rdp->gpwrap))) {
- ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */
- trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend"));
+ if (!offloaded)
+ ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */
+ rdp->core_needs_qs = false;
+ trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend"));
} else {
- ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */
+ if (!offloaded)
+ ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */
+ if (rdp->core_needs_qs)
+ rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
}
/* Now handle the beginnings of any new-to-this-CPU grace periods. */
@@ -1852,22 +1643,21 @@
* set up to detect a quiescent state, otherwise don't
* go looking for one.
*/
- trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart"));
- need_gp = !!(rnp->qsmask & rdp->grpmask);
- rdp->cpu_no_qs.b.norm = need_gp;
- rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
- rdp->core_needs_qs = need_gp;
+ trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart"));
+ need_qs = !!(rnp->qsmask & rdp->grpmask);
+ rdp->cpu_no_qs.b.norm = need_qs;
+ rdp->core_needs_qs = need_qs;
zero_cpu_stall_ticks(rdp);
}
rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
- if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
- rdp->gp_seq_needed = rnp->gp_seq_needed;
+ if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
+ WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
WRITE_ONCE(rdp->gpwrap, false);
rcu_gpnum_ovf(rnp, rdp);
return ret;
}
-static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
+static void note_gp_changes(struct rcu_data *rdp)
{
unsigned long flags;
bool needwake;
@@ -1881,41 +1671,77 @@
local_irq_restore(flags);
return;
}
- needwake = __note_gp_changes(rsp, rnp, rdp);
+ needwake = __note_gp_changes(rnp, rdp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ rcu_strict_gp_check_qs();
if (needwake)
- rcu_gp_kthread_wake(rsp);
+ rcu_gp_kthread_wake();
}
-static void rcu_gp_slow(struct rcu_state *rsp, int delay)
+static void rcu_gp_slow(int delay)
{
if (delay > 0 &&
- !(rcu_seq_ctr(rsp->gp_seq) %
+ !(rcu_seq_ctr(rcu_state.gp_seq) %
(rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
- schedule_timeout_uninterruptible(delay);
+ schedule_timeout_idle(delay);
+}
+
+static unsigned long sleep_duration;
+
+/* Allow rcutorture to stall the grace-period kthread. */
+void rcu_gp_set_torture_wait(int duration)
+{
+ if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST) && duration > 0)
+ WRITE_ONCE(sleep_duration, duration);
+}
+EXPORT_SYMBOL_GPL(rcu_gp_set_torture_wait);
+
+/* Actually implement the aforementioned wait. */
+static void rcu_gp_torture_wait(void)
+{
+ unsigned long duration;
+
+ if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST))
+ return;
+ duration = xchg(&sleep_duration, 0UL);
+ if (duration > 0) {
+ pr_alert("%s: Waiting %lu jiffies\n", __func__, duration);
+ schedule_timeout_idle(duration);
+ pr_alert("%s: Wait complete\n", __func__);
+ }
+}
+
+/*
+ * Handler for on_each_cpu() to invoke the target CPU's RCU core
+ * processing.
+ */
+static void rcu_strict_gp_boundary(void *unused)
+{
+ invoke_rcu_core();
}
/*
* Initialize a new grace period. Return false if no grace period required.
*/
-static bool rcu_gp_init(struct rcu_state *rsp)
+static bool rcu_gp_init(void)
{
+ unsigned long firstseq;
unsigned long flags;
unsigned long oldmask;
unsigned long mask;
struct rcu_data *rdp;
- struct rcu_node *rnp = rcu_get_root(rsp);
+ struct rcu_node *rnp = rcu_get_root();
- WRITE_ONCE(rsp->gp_activity, jiffies);
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
- if (!READ_ONCE(rsp->gp_flags)) {
+ if (!READ_ONCE(rcu_state.gp_flags)) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq_rcu_node(rnp);
return false;
}
- WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
+ WRITE_ONCE(rcu_state.gp_flags, 0); /* Clear all flags: New GP. */
- if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
+ if (WARN_ON_ONCE(rcu_gp_in_progress())) {
/*
* Grace period already in progress, don't start another.
* Not supposed to be able to happen.
@@ -1925,27 +1751,37 @@
}
/* Advance to a new grace period and initialize state. */
- record_gp_stall_check_time(rsp);
+ record_gp_stall_check_time();
/* Record GP times before starting GP, hence rcu_seq_start(). */
- rcu_seq_start(&rsp->gp_seq);
- trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start"));
+ rcu_seq_start(&rcu_state.gp_seq);
+ ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
raw_spin_unlock_irq_rcu_node(rnp);
/*
- * Apply per-leaf buffered online and offline operations to the
- * rcu_node tree. Note that this new grace period need not wait
- * for subsequent online CPUs, and that quiescent-state forcing
- * will handle subsequent offline CPUs.
+ * Apply per-leaf buffered online and offline operations to
+ * the rcu_node tree. Note that this new grace period need not
+ * wait for subsequent online CPUs, and that RCU hooks in the CPU
+ * offlining path, when combined with checks in this function,
+ * will handle CPUs that are currently going offline or that will
+ * go offline later. Please also refer to "Hotplug CPU" section
+ * of RCU's Requirements documentation.
*/
- rsp->gp_state = RCU_GP_ONOFF;
- rcu_for_each_leaf_node(rsp, rnp) {
- spin_lock(&rsp->ofl_lock);
+ rcu_state.gp_state = RCU_GP_ONOFF;
+ rcu_for_each_leaf_node(rnp) {
+ smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
+ firstseq = READ_ONCE(rnp->ofl_seq);
+ if (firstseq & 0x1)
+ while (firstseq == READ_ONCE(rnp->ofl_seq))
+ schedule_timeout_idle(1); // Can't wake unless RCU is watching.
+ smp_mb(); // Pair with barriers used when updating ->ofl_seq to even values.
+ raw_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irq_rcu_node(rnp);
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
!rnp->wait_blkd_tasks) {
/* Nothing to do on this leaf rcu_node structure. */
raw_spin_unlock_irq_rcu_node(rnp);
- spin_unlock(&rsp->ofl_lock);
+ raw_spin_unlock(&rcu_state.ofl_lock);
continue;
}
@@ -1981,46 +1817,50 @@
}
raw_spin_unlock_irq_rcu_node(rnp);
- spin_unlock(&rsp->ofl_lock);
+ raw_spin_unlock(&rcu_state.ofl_lock);
}
- rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */
+ rcu_gp_slow(gp_preinit_delay); /* Races with CPU hotplug. */
/*
* Set the quiescent-state-needed bits in all the rcu_node
- * structures for all currently online CPUs in breadth-first order,
- * starting from the root rcu_node structure, relying on the layout
- * of the tree within the rsp->node[] array. Note that other CPUs
- * will access only the leaves of the hierarchy, thus seeing that no
- * grace period is in progress, at least until the corresponding
- * leaf node has been initialized.
+ * structures for all currently online CPUs in breadth-first
+ * order, starting from the root rcu_node structure, relying on the
+ * layout of the tree within the rcu_state.node[] array. Note that
+ * other CPUs will access only the leaves of the hierarchy, thus
+ * seeing that no grace period is in progress, at least until the
+ * corresponding leaf node has been initialized.
*
* The grace period cannot complete until the initialization
* process finishes, because this kthread handles both.
*/
- rsp->gp_state = RCU_GP_INIT;
- rcu_for_each_node_breadth_first(rsp, rnp) {
- rcu_gp_slow(rsp, gp_init_delay);
+ rcu_state.gp_state = RCU_GP_INIT;
+ rcu_for_each_node_breadth_first(rnp) {
+ rcu_gp_slow(gp_init_delay);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rdp = this_cpu_ptr(rsp->rda);
- rcu_preempt_check_blocked_tasks(rsp, rnp);
+ rdp = this_cpu_ptr(&rcu_data);
+ rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
- WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
+ WRITE_ONCE(rnp->gp_seq, rcu_state.gp_seq);
if (rnp == rdp->mynode)
- (void)__note_gp_changes(rsp, rnp, rdp);
+ (void)__note_gp_changes(rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
- trace_rcu_grace_period_init(rsp->name, rnp->gp_seq,
+ trace_rcu_grace_period_init(rcu_state.name, rnp->gp_seq,
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
/* Quiescent states for tasks on any now-offline CPUs. */
mask = rnp->qsmask & ~rnp->qsmaskinitnext;
rnp->rcu_gp_init_mask = mask;
if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
else
raw_spin_unlock_irq_rcu_node(rnp);
cond_resched_tasks_rcu_qs();
- WRITE_ONCE(rsp->gp_activity, jiffies);
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
}
+
+ // If strict, make all CPUs aware of new grace period.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
return true;
}
@@ -2029,16 +1869,20 @@
* Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
* time.
*/
-static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
+static bool rcu_gp_fqs_check_wake(int *gfp)
{
- struct rcu_node *rnp = rcu_get_root(rsp);
+ struct rcu_node *rnp = rcu_get_root();
- /* Someone like call_rcu() requested a force-quiescent-state scan. */
- *gfp = READ_ONCE(rsp->gp_flags);
+ // If under overload conditions, force an immediate FQS scan.
+ if (*gfp & RCU_GP_FLAG_OVLD)
+ return true;
+
+ // Someone like call_rcu() requested a force-quiescent-state scan.
+ *gfp = READ_ONCE(rcu_state.gp_flags);
if (*gfp & RCU_GP_FLAG_FQS)
return true;
- /* The current grace period has completed. */
+ // The current grace period has completed.
if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
return true;
@@ -2048,45 +1892,117 @@
/*
* Do one round of quiescent-state forcing.
*/
-static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time)
+static void rcu_gp_fqs(bool first_time)
{
- struct rcu_node *rnp = rcu_get_root(rsp);
+ struct rcu_node *rnp = rcu_get_root();
- WRITE_ONCE(rsp->gp_activity, jiffies);
- rsp->n_force_qs++;
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
+ WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
if (first_time) {
/* Collect dyntick-idle snapshots. */
- force_qs_rnp(rsp, dyntick_save_progress_counter);
+ force_qs_rnp(dyntick_save_progress_counter);
} else {
/* Handle dyntick-idle and offline CPUs. */
- force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
+ force_qs_rnp(rcu_implicit_dynticks_qs);
}
/* Clear flag to prevent immediate re-entry. */
- if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+ if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq_rcu_node(rnp);
- WRITE_ONCE(rsp->gp_flags,
- READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
+ WRITE_ONCE(rcu_state.gp_flags,
+ READ_ONCE(rcu_state.gp_flags) & ~RCU_GP_FLAG_FQS);
raw_spin_unlock_irq_rcu_node(rnp);
+ }
+}
+
+/*
+ * Loop doing repeated quiescent-state forcing until the grace period ends.
+ */
+static void rcu_gp_fqs_loop(void)
+{
+ bool first_gp_fqs;
+ int gf = 0;
+ unsigned long j;
+ int ret;
+ struct rcu_node *rnp = rcu_get_root();
+
+ first_gp_fqs = true;
+ j = READ_ONCE(jiffies_till_first_fqs);
+ if (rcu_state.cbovld)
+ gf = RCU_GP_FLAG_OVLD;
+ ret = 0;
+ for (;;) {
+ if (!ret) {
+ rcu_state.jiffies_force_qs = jiffies + j;
+ WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
+ jiffies + (j ? 3 * j : 2));
+ }
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
+ TPS("fqswait"));
+ rcu_state.gp_state = RCU_GP_WAIT_FQS;
+ ret = swait_event_idle_timeout_exclusive(
+ rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
+ rcu_gp_torture_wait();
+ rcu_state.gp_state = RCU_GP_DOING_FQS;
+ /* Locking provides needed memory barriers. */
+ /* If grace period done, leave loop. */
+ if (!READ_ONCE(rnp->qsmask) &&
+ !rcu_preempt_blocked_readers_cgp(rnp))
+ break;
+ /* If time for quiescent-state forcing, do it. */
+ if (!time_after(rcu_state.jiffies_force_qs, jiffies) ||
+ (gf & (RCU_GP_FLAG_FQS | RCU_GP_FLAG_OVLD))) {
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
+ TPS("fqsstart"));
+ rcu_gp_fqs(first_gp_fqs);
+ gf = 0;
+ if (first_gp_fqs) {
+ first_gp_fqs = false;
+ gf = rcu_state.cbovld ? RCU_GP_FLAG_OVLD : 0;
+ }
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
+ TPS("fqsend"));
+ cond_resched_tasks_rcu_qs();
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
+ ret = 0; /* Force full wait till next FQS. */
+ j = READ_ONCE(jiffies_till_next_fqs);
+ } else {
+ /* Deal with stray signal. */
+ cond_resched_tasks_rcu_qs();
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
+ WARN_ON(signal_pending(current));
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
+ TPS("fqswaitsig"));
+ ret = 1; /* Keep old FQS timing. */
+ j = jiffies;
+ if (time_after(jiffies, rcu_state.jiffies_force_qs))
+ j = 1;
+ else
+ j = rcu_state.jiffies_force_qs - j;
+ gf = 0;
+ }
}
}
/*
* Clean up after the old grace period.
*/
-static void rcu_gp_cleanup(struct rcu_state *rsp)
+static void rcu_gp_cleanup(void)
{
- unsigned long gp_duration;
+ int cpu;
bool needgp = false;
+ unsigned long gp_duration;
unsigned long new_gp_seq;
+ bool offloaded;
struct rcu_data *rdp;
- struct rcu_node *rnp = rcu_get_root(rsp);
+ struct rcu_node *rnp = rcu_get_root();
struct swait_queue_head *sq;
- WRITE_ONCE(rsp->gp_activity, jiffies);
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
- gp_duration = jiffies - rsp->gp_start;
- if (gp_duration > rsp->gp_max)
- rsp->gp_max = gp_duration;
+ rcu_state.gp_end = jiffies;
+ gp_duration = rcu_state.gp_end - rcu_state.gp_start;
+ if (gp_duration > rcu_state.gp_max)
+ rcu_state.gp_max = gp_duration;
/*
* We know the grace period is complete, but to everyone else
@@ -2107,165 +2023,123 @@
* the rcu_node structures before the beginning of the next grace
* period is recorded in any of the rcu_node structures.
*/
- new_gp_seq = rsp->gp_seq;
+ new_gp_seq = rcu_state.gp_seq;
rcu_seq_end(&new_gp_seq);
- rcu_for_each_node_breadth_first(rsp, rnp) {
+ rcu_for_each_node_breadth_first(rnp) {
raw_spin_lock_irq_rcu_node(rnp);
if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
- dump_blkd_tasks(rsp, rnp, 10);
+ dump_blkd_tasks(rnp, 10);
WARN_ON_ONCE(rnp->qsmask);
WRITE_ONCE(rnp->gp_seq, new_gp_seq);
- rdp = this_cpu_ptr(rsp->rda);
+ rdp = this_cpu_ptr(&rcu_data);
if (rnp == rdp->mynode)
- needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
+ needgp = __note_gp_changes(rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
- needgp = rcu_future_gp_cleanup(rsp, rnp) || needgp;
+ needgp = rcu_future_gp_cleanup(rnp) || needgp;
+ // Reset overload indication for CPUs no longer overloaded
+ if (rcu_is_leaf_node(rnp))
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->cbovldmask) {
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ check_cb_ovld_locked(rdp, rnp);
+ }
sq = rcu_nocb_gp_get(rnp);
raw_spin_unlock_irq_rcu_node(rnp);
rcu_nocb_gp_cleanup(sq);
cond_resched_tasks_rcu_qs();
- WRITE_ONCE(rsp->gp_activity, jiffies);
- rcu_gp_slow(rsp, gp_cleanup_delay);
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
+ rcu_gp_slow(gp_cleanup_delay);
}
- rnp = rcu_get_root(rsp);
- raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */
+ rnp = rcu_get_root();
+ raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */
- /* Declare grace period done. */
- rcu_seq_end(&rsp->gp_seq);
- trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end"));
- rsp->gp_state = RCU_GP_IDLE;
+ /* Declare grace period done, trace first to use old GP number. */
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
+ rcu_seq_end(&rcu_state.gp_seq);
+ ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
+ rcu_state.gp_state = RCU_GP_IDLE;
/* Check for GP requests since above loop. */
- rdp = this_cpu_ptr(rsp->rda);
+ rdp = this_cpu_ptr(&rcu_data);
if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
TPS("CleanupMore"));
needgp = true;
}
/* Advance CBs to reduce false positives below. */
- if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
- WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
- rsp->gp_req_activity = jiffies;
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq),
+ offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+ rcu_segcblist_is_offloaded(&rdp->cblist);
+ if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
+ WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
+ WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+ trace_rcu_grace_period(rcu_state.name,
+ rcu_state.gp_seq,
TPS("newreq"));
} else {
- WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
+ WRITE_ONCE(rcu_state.gp_flags,
+ rcu_state.gp_flags & RCU_GP_FLAG_INIT);
}
raw_spin_unlock_irq_rcu_node(rnp);
+
+ // If strict, make all CPUs aware of the end of the old grace period.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
}
/*
* Body of kthread that handles grace periods.
*/
-static int __noreturn rcu_gp_kthread(void *arg)
+static int __noreturn rcu_gp_kthread(void *unused)
{
- bool first_gp_fqs;
- int gf;
- unsigned long j;
- int ret;
- struct rcu_state *rsp = arg;
- struct rcu_node *rnp = rcu_get_root(rsp);
-
rcu_bind_gp_kthread();
for (;;) {
/* Handle grace-period start. */
for (;;) {
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gp_seq),
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("reqwait"));
- rsp->gp_state = RCU_GP_WAIT_GPS;
- swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
- RCU_GP_FLAG_INIT);
- rsp->gp_state = RCU_GP_DONE_GPS;
+ rcu_state.gp_state = RCU_GP_WAIT_GPS;
+ swait_event_idle_exclusive(rcu_state.gp_wq,
+ READ_ONCE(rcu_state.gp_flags) &
+ RCU_GP_FLAG_INIT);
+ rcu_gp_torture_wait();
+ rcu_state.gp_state = RCU_GP_DONE_GPS;
/* Locking provides needed memory barrier. */
- if (rcu_gp_init(rsp))
+ if (rcu_gp_init())
break;
cond_resched_tasks_rcu_qs();
- WRITE_ONCE(rsp->gp_activity, jiffies);
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
WARN_ON(signal_pending(current));
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gp_seq),
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
- first_gp_fqs = true;
- j = jiffies_till_first_fqs;
- ret = 0;
- for (;;) {
- if (!ret) {
- rsp->jiffies_force_qs = jiffies + j;
- WRITE_ONCE(rsp->jiffies_kick_kthreads,
- jiffies + 3 * j);
- }
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gp_seq),
- TPS("fqswait"));
- rsp->gp_state = RCU_GP_WAIT_FQS;
- ret = swait_event_idle_timeout_exclusive(rsp->gp_wq,
- rcu_gp_fqs_check_wake(rsp, &gf), j);
- rsp->gp_state = RCU_GP_DOING_FQS;
- /* Locking provides needed memory barriers. */
- /* If grace period done, leave loop. */
- if (!READ_ONCE(rnp->qsmask) &&
- !rcu_preempt_blocked_readers_cgp(rnp))
- break;
- /* If time for quiescent-state forcing, do it. */
- if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
- (gf & RCU_GP_FLAG_FQS)) {
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gp_seq),
- TPS("fqsstart"));
- rcu_gp_fqs(rsp, first_gp_fqs);
- first_gp_fqs = false;
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gp_seq),
- TPS("fqsend"));
- cond_resched_tasks_rcu_qs();
- WRITE_ONCE(rsp->gp_activity, jiffies);
- ret = 0; /* Force full wait till next FQS. */
- j = jiffies_till_next_fqs;
- } else {
- /* Deal with stray signal. */
- cond_resched_tasks_rcu_qs();
- WRITE_ONCE(rsp->gp_activity, jiffies);
- WARN_ON(signal_pending(current));
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gp_seq),
- TPS("fqswaitsig"));
- ret = 1; /* Keep old FQS timing. */
- j = jiffies;
- if (time_after(jiffies, rsp->jiffies_force_qs))
- j = 1;
- else
- j = rsp->jiffies_force_qs - j;
- }
- }
+ rcu_gp_fqs_loop();
/* Handle grace-period end. */
- rsp->gp_state = RCU_GP_CLEANUP;
- rcu_gp_cleanup(rsp);
- rsp->gp_state = RCU_GP_CLEANED;
+ rcu_state.gp_state = RCU_GP_CLEANUP;
+ rcu_gp_cleanup();
+ rcu_state.gp_state = RCU_GP_CLEANED;
}
}
/*
- * Report a full set of quiescent states to the specified rcu_state data
- * structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period
- * kthread if another grace period is required. Whether we wake
- * the grace-period kthread or it awakens itself for the next round
- * of quiescent-state forcing, that kthread will clean up after the
- * just-completed grace period. Note that the caller must hold rnp->lock,
- * which is released before return.
+ * Report a full set of quiescent states to the rcu_state data structure.
+ * Invoke rcu_gp_kthread_wake() to awaken the grace-period kthread if
+ * another grace period is required. Whether we wake the grace-period
+ * kthread or it awakens itself for the next round of quiescent-state
+ * forcing, that kthread will clean up after the just-completed grace
+ * period. Note that the caller must hold rnp->lock, which is released
+ * before return.
*/
-static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
- __releases(rcu_get_root(rsp)->lock)
+static void rcu_report_qs_rsp(unsigned long flags)
+ __releases(rcu_get_root()->lock)
{
- raw_lockdep_assert_held_rcu_node(rcu_get_root(rsp));
- WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
- WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
- raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
- rcu_gp_kthread_wake(rsp);
+ raw_lockdep_assert_held_rcu_node(rcu_get_root());
+ WARN_ON_ONCE(!rcu_gp_in_progress());
+ WRITE_ONCE(rcu_state.gp_flags,
+ READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS);
+ raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(), flags);
+ rcu_gp_kthread_wake();
}
/*
@@ -2282,9 +2156,8 @@
* disabled. This allows propagating quiescent state due to resumed tasks
* during grace-period initialization.
*/
-static void
-rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
- struct rcu_node *rnp, unsigned long gps, unsigned long flags)
+static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
+ unsigned long gps, unsigned long flags)
__releases(rnp->lock)
{
unsigned long oldmask = 0;
@@ -2306,8 +2179,8 @@
WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
- rnp->qsmask &= ~mask;
- trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq,
+ WRITE_ONCE(rnp->qsmask, rnp->qsmask & ~mask);
+ trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq,
mask, rnp->qsmask, rnp->level,
rnp->grplo, rnp->grphi,
!!rnp->gp_tasks);
@@ -2329,7 +2202,7 @@
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- oldmask = rnp_c->qsmask;
+ oldmask = READ_ONCE(rnp_c->qsmask);
}
/*
@@ -2337,19 +2210,18 @@
* state for this grace period. Invoke rcu_report_qs_rsp()
* to clean up and start the next grace period if one is needed.
*/
- rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
+ rcu_report_qs_rsp(flags); /* releases rnp->lock. */
}
/*
* Record a quiescent state for all tasks that were previously queued
* on the specified rcu_node structure and that were blocking the current
- * RCU grace period. The caller must hold the specified rnp->lock with
+ * RCU grace period. The caller must hold the corresponding rnp->lock with
* irqs disabled, and this lock is released upon return, but irqs remain
* disabled.
*/
static void __maybe_unused
-rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
- struct rcu_node *rnp, unsigned long flags)
+rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
unsigned long gps;
@@ -2357,8 +2229,7 @@
struct rcu_node *rnp_p;
raw_lockdep_assert_held_rcu_node(rnp);
- if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) ||
- WARN_ON_ONCE(rsp != rcu_state_p) ||
+ if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RCU)) ||
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
rnp->qsmask != 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2372,7 +2243,7 @@
* Only one rcu_node structure in the tree, so don't
* try to report up to its nonexistent parent!
*/
- rcu_report_qs_rsp(rsp, flags);
+ rcu_report_qs_rsp(flags);
return;
}
@@ -2381,7 +2252,7 @@
mask = rnp->grpmask;
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */
- rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags);
+ rcu_report_qs_rnp(mask, rnp_p, gps, flags);
}
/*
@@ -2389,13 +2260,16 @@
* structure. This must be called from the specified CPU.
*/
static void
-rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
+rcu_report_qs_rdp(struct rcu_data *rdp)
{
unsigned long flags;
unsigned long mask;
- bool needwake;
+ bool needwake = false;
+ const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+ rcu_segcblist_is_offloaded(&rdp->cblist);
struct rcu_node *rnp;
+ WARN_ON_ONCE(rdp->cpu != smp_processor_id());
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
@@ -2408,26 +2282,26 @@
* within the current grace period.
*/
rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */
- rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
mask = rdp->grpmask;
+ rdp->core_needs_qs = false;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
} else {
- rdp->core_needs_qs = false;
-
/*
* This GP can't end until cpu checks in, so all of our
* callbacks can be processed during the next GP.
*/
- needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ if (!offloaded)
+ needwake = rcu_accelerate_cbs(rnp, rdp);
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ rcu_disable_urgency_upon_qs(rdp);
+ rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
/* ^^^ Released rnp->lock */
if (needwake)
- rcu_gp_kthread_wake(rsp);
+ rcu_gp_kthread_wake();
}
}
@@ -2438,10 +2312,10 @@
* quiescent state for this grace period, and record that fact if so.
*/
static void
-rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
+rcu_check_quiescent_state(struct rcu_data *rdp)
{
/* Check for grace-period ends and beginnings. */
- note_gp_changes(rsp, rdp);
+ note_gp_changes(rdp);
/*
* Does this CPU still need to do its part for current grace period?
@@ -2461,24 +2335,26 @@
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
- rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
+ rcu_report_qs_rdp(rdp);
}
/*
- * Trace the fact that this CPU is going offline.
+ * Near the end of the offline process. Trace the fact that this CPU
+ * is going offline.
*/
-static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
+int rcutree_dying_cpu(unsigned int cpu)
{
- RCU_TRACE(bool blkd;)
- RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
- RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
+ bool blkd;
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+ struct rcu_node *rnp = rdp->mynode;
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
- return;
+ return 0;
- RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);)
- trace_rcu_grace_period(rsp->name, rnp->gp_seq,
+ blkd = !!(rnp->qsmask & rdp->grpmask);
+ trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
+ return 0;
}
/*
@@ -2532,35 +2408,44 @@
* There can only be one CPU hotplug operation at a time, so no need for
* explicit locking.
*/
-static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
+int rcutree_dead_cpu(unsigned int cpu)
{
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
- return;
+ return 0;
/* Adjust any no-longer-needed kthreads. */
rcu_boost_kthread_setaffinity(rnp, -1);
+ /* Do any needed no-CB deferred wakeups from this CPU. */
+ do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu));
+
+ // Stop-machine done, so allow nohz_full to disable tick.
+ tick_dep_clear(TICK_DEP_BIT_RCU);
+ return 0;
}
/*
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
*/
-static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
+static void rcu_do_batch(struct rcu_data *rdp)
{
+ int div;
unsigned long flags;
+ const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+ rcu_segcblist_is_offloaded(&rdp->cblist);
struct rcu_head *rhp;
struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
long bl, count;
+ long pending, tlimit = 0;
/* If no callbacks are ready, just return. */
if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
- trace_rcu_batch_start(rsp->name,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ trace_rcu_batch_start(rcu_state.name,
rcu_segcblist_n_cbs(&rdp->cblist), 0);
- trace_rcu_batch_end(rsp->name, 0,
+ trace_rcu_batch_end(rcu_state.name, 0,
!rcu_segcblist_empty(&rdp->cblist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
@@ -2573,32 +2458,76 @@
* callback counts, as rcu_barrier() needs to be conservative.
*/
local_irq_save(flags);
+ rcu_nocb_lock(rdp);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
- bl = rdp->blimit;
- trace_rcu_batch_start(rsp->name, rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ pending = rcu_segcblist_n_cbs(&rdp->cblist);
+ div = READ_ONCE(rcu_divisor);
+ div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
+ bl = max(rdp->blimit, pending >> div);
+ if (in_serving_softirq() && unlikely(bl > 100)) {
+ long rrn = READ_ONCE(rcu_resched_ns);
+
+ rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
+ tlimit = local_clock() + rrn;
+ }
+ trace_rcu_batch_start(rcu_state.name,
rcu_segcblist_n_cbs(&rdp->cblist), bl);
rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
- local_irq_restore(flags);
+ if (offloaded)
+ rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
+ rcu_nocb_unlock_irqrestore(rdp, flags);
/* Invoke callbacks. */
+ tick_dep_set_task(current, TICK_DEP_BIT_RCU);
rhp = rcu_cblist_dequeue(&rcl);
for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ rcu_callback_t f;
+
debug_rcu_head_unqueue(rhp);
- if (__rcu_reclaim(rsp->name, rhp))
- rcu_cblist_dequeued_lazy(&rcl);
+
+ rcu_lock_acquire(&rcu_callback_map);
+ trace_rcu_invoke_callback(rcu_state.name, rhp);
+
+ f = rhp->func;
+ WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
+ f(rhp);
+
+ rcu_lock_release(&rcu_callback_map);
+
/*
* Stop only if limit reached and CPU has something to do.
* Note: The rcl structure counts down from zero.
*/
- if (-rcl.len >= bl &&
- (need_resched() ||
- (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
- break;
+ if (in_serving_softirq()) {
+ if (-rcl.len >= bl && (need_resched() ||
+ (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
+ break;
+
+ /*
+ * Make sure we don't spend too much time here and deprive other
+ * softirq vectors of CPU cycles.
+ */
+ if (unlikely(tlimit)) {
+ /* only call local_clock() every 32 callbacks */
+ if (likely((-rcl.len & 31) || local_clock() < tlimit))
+ continue;
+ /* Exceeded the time limit, so leave. */
+ break;
+ }
+ } else {
+ local_bh_enable();
+ lockdep_assert_irqs_enabled();
+ cond_resched_tasks_rcu_qs();
+ lockdep_assert_irqs_enabled();
+ local_bh_disable();
+ }
}
local_irq_save(flags);
+ rcu_nocb_lock(rdp);
count = -rcl.len;
- trace_rcu_batch_end(rsp->name, count, !!rcl.head, need_resched(),
+ rdp->n_cbs_invoked += count;
+ trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
is_idle_task(current), rcu_is_callbacks_kthread());
/* Update counts and requeue any remaining callbacks. */
@@ -2608,13 +2537,13 @@
/* Reinstate batch limit if we have worked down the excess. */
count = rcu_segcblist_n_cbs(&rdp->cblist);
- if (rdp->blimit == LONG_MAX && count <= qlowmark)
+ if (rdp->blimit >= DEFAULT_MAX_RCU_BLIMIT && count <= qlowmark)
rdp->blimit = blimit;
/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
if (count == 0 && rdp->qlen_last_fqs_check != 0) {
rdp->qlen_last_fqs_check = 0;
- rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
} else if (count < rdp->qlen_last_fqs_check - qhimark)
rdp->qlen_last_fqs_check = count;
@@ -2622,94 +2551,72 @@
* The following usually indicates a double call_rcu(). To track
* this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.
*/
- WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != (count == 0));
+ WARN_ON_ONCE(count == 0 && !rcu_segcblist_empty(&rdp->cblist));
+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+ count != 0 && rcu_segcblist_empty(&rdp->cblist));
- local_irq_restore(flags);
+ rcu_nocb_unlock_irqrestore(rdp, flags);
/* Re-invoke RCU core processing if there are callbacks remaining. */
- if (rcu_segcblist_ready_cbs(&rdp->cblist))
+ if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_core();
+ tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
}
/*
- * Check to see if this CPU is in a non-context-switch quiescent state
- * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
- * Also schedule RCU core processing.
- *
- * This function must be called from hardirq context. It is normally
- * invoked from the scheduling-clock interrupt.
+ * This function is invoked from each scheduling-clock interrupt,
+ * and checks to see if this CPU is in a non-context-switch quiescent
+ * state, for example, user mode or idle loop. It also schedules RCU
+ * core processing. If the current grace period has gone on too long,
+ * it will ask the scheduler to manufacture a context switch for the sole
+ * purpose of providing a providing the needed quiescent state.
*/
-void rcu_check_callbacks(int user)
+void rcu_sched_clock_irq(int user)
{
trace_rcu_utilization(TPS("Start scheduler-tick"));
- increment_cpu_stall_ticks();
- if (user || rcu_is_cpu_rrupt_from_idle()) {
-
- /*
- * Get here if this CPU took its interrupt from user
- * mode or from the idle loop, and if this is not a
- * nested interrupt. In this case, the CPU is in
- * a quiescent state, so note it.
- *
- * No memory barrier is required here because both
- * rcu_sched_qs() and rcu_bh_qs() reference only CPU-local
- * variables that other CPUs neither access nor modify,
- * at least not while the corresponding CPU is online.
- */
-
- rcu_sched_qs();
- rcu_bh_qs();
- rcu_note_voluntary_context_switch(current);
-
- } else if (!in_softirq()) {
-
- /*
- * Get here if this CPU did not take its interrupt from
- * softirq, in other words, if it is not interrupting
- * a rcu_bh read-side critical section. This is an _bh
- * critical section, so note it.
- */
-
- rcu_bh_qs();
- }
- rcu_preempt_check_callbacks();
+ lockdep_assert_irqs_disabled();
+ raw_cpu_inc(rcu_data.ticks_this_gp);
/* The load-acquire pairs with the store-release setting to true. */
- if (smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) {
+ if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
/* Idle and userspace execution already are quiescent states. */
if (!rcu_is_cpu_rrupt_from_idle() && !user) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
- __this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
+ __this_cpu_write(rcu_data.rcu_urgent_qs, false);
}
- if (rcu_pending())
+ rcu_flavor_sched_clock_irq(user);
+ if (rcu_pending(user))
invoke_rcu_core();
+ lockdep_assert_irqs_disabled();
trace_rcu_utilization(TPS("End scheduler-tick"));
}
/*
- * Scan the leaf rcu_node structures, processing dyntick state for any that
- * have not yet encountered a quiescent state, using the function specified.
- * Also initiate boosting for any threads blocked on the root rcu_node.
- *
- * The caller must have suppressed start of new grace periods.
+ * Scan the leaf rcu_node structures. For each structure on which all
+ * CPUs have reported a quiescent state and on which there are tasks
+ * blocking the current grace period, initiate RCU priority boosting.
+ * Otherwise, invoke the specified function to check dyntick state for
+ * each CPU that has not yet reported a quiescent state.
*/
-static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
+static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
{
int cpu;
unsigned long flags;
unsigned long mask;
+ struct rcu_data *rdp;
struct rcu_node *rnp;
- rcu_for_each_leaf_node(rsp, rnp) {
+ rcu_state.cbovld = rcu_state.cbovldnext;
+ rcu_state.cbovldnext = false;
+ rcu_for_each_leaf_node(rnp) {
cond_resched_tasks_rcu_qs();
mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ rcu_state.cbovldnext |= !!rnp->cbovldmask;
if (rnp->qsmask == 0) {
- if (rcu_state_p == &rcu_sched_state ||
- rsp != rcu_state_p ||
- rcu_preempt_blocked_readers_cgp(rnp)) {
+ if (rcu_preempt_blocked_readers_cgp(rnp)) {
/*
* No point in scanning bits because they
* are all zero. But we might need to
@@ -2722,16 +2629,16 @@
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
continue;
}
- for_each_leaf_node_possible_cpu(rnp, cpu) {
- unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
- if ((rnp->qsmask & bit) != 0) {
- if (f(per_cpu_ptr(rsp->rda, cpu)))
- mask |= bit;
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) {
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (f(rdp)) {
+ mask |= rdp->grpmask;
+ rcu_disable_urgency_upon_qs(rdp);
}
}
if (mask != 0) {
/* Idle/offline CPUs, report (releases rnp->lock). */
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+ rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
} else {
/* Nothing to do here, so just drop the lock. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2743,7 +2650,7 @@
* Force quiescent states on reluctant CPUs, and also detect which
* CPUs are in dyntick-idle mode.
*/
-static void force_quiescent_state(struct rcu_state *rsp)
+void rcu_force_quiescent_state(void)
{
unsigned long flags;
bool ret;
@@ -2751,169 +2658,206 @@
struct rcu_node *rnp_old = NULL;
/* Funnel through hierarchy to reduce memory contention. */
- rnp = __this_cpu_read(rsp->rda->mynode);
+ rnp = raw_cpu_read(rcu_data.mynode);
for (; rnp != NULL; rnp = rnp->parent) {
- ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
- !raw_spin_trylock(&rnp->fqslock);
+ ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
+ !raw_spin_trylock(&rnp->fqslock);
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
if (ret)
return;
rnp_old = rnp;
}
- /* rnp_old == rcu_get_root(rsp), rnp == NULL. */
+ /* rnp_old == rcu_get_root(), rnp == NULL. */
/* Reached the root of the rcu_node tree, acquire lock. */
raw_spin_lock_irqsave_rcu_node(rnp_old, flags);
raw_spin_unlock(&rnp_old->fqslock);
- if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+ if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
return; /* Someone beat us to it. */
}
- WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
+ WRITE_ONCE(rcu_state.gp_flags,
+ READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
- rcu_gp_kthread_wake(rsp);
+ rcu_gp_kthread_wake();
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+
+// Workqueue handler for an RCU reader for kernels enforcing struct RCU
+// grace periods.
+static void strict_work_handler(struct work_struct *work)
+{
+ rcu_read_lock();
+ rcu_read_unlock();
}
-/*
- * This function checks for grace-period requests that fail to motivate
- * RCU to come out of its idle mode.
- */
-static void
-rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp)
-{
- const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
- unsigned long flags;
- unsigned long j;
- struct rcu_node *rnp_root = rcu_get_root(rsp);
- static atomic_t warned = ATOMIC_INIT(0);
-
- if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
- return;
- j = jiffies; /* Expensive access, and in common case don't get here. */
- if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
- time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
- atomic_read(&warned))
- return;
-
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- j = jiffies;
- if (rcu_gp_in_progress(rsp) ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
- time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
- time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
- atomic_read(&warned)) {
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- return;
- }
- /* Hold onto the leaf lock to make others see warned==1. */
-
- if (rnp_root != rnp)
- raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
- j = jiffies;
- if (rcu_gp_in_progress(rsp) ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
- time_before(j, rsp->gp_req_activity + gpssdelay) ||
- time_before(j, rsp->gp_activity + gpssdelay) ||
- atomic_xchg(&warned, 1)) {
- raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- return;
- }
- pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
- __func__, (long)READ_ONCE(rsp->gp_seq),
- (long)READ_ONCE(rnp_root->gp_seq_needed),
- j - rsp->gp_req_activity, j - rsp->gp_activity,
- rsp->gp_flags, rsp->gp_state, rsp->name,
- rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
- WARN_ON(1);
- if (rnp_root != rnp)
- raw_spin_unlock_rcu_node(rnp_root);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-}
-
-/*
- * This does the RCU core processing work for the specified rcu_state
- * and rcu_data structures. This may be called only from the CPU to
- * whom the rdp belongs.
- */
-static void
-__rcu_process_callbacks(struct rcu_state *rsp)
+/* Perform RCU core processing work for the current CPU. */
+static __latent_entropy void rcu_core(void)
{
unsigned long flags;
- struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
+ struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
-
- WARN_ON_ONCE(!rdp->beenonline);
-
- /* Update RCU state based on any recent quiescent states. */
- rcu_check_quiescent_state(rsp, rdp);
-
- /* No grace period and unregistered callbacks? */
- if (!rcu_gp_in_progress(rsp) &&
- rcu_segcblist_is_enabled(&rdp->cblist)) {
- local_irq_save(flags);
- if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
- rcu_accelerate_cbs_unlocked(rsp, rnp, rdp);
- local_irq_restore(flags);
- }
-
- rcu_check_gp_start_stall(rsp, rnp, rdp);
-
- /* If there are callbacks ready, invoke them. */
- if (rcu_segcblist_ready_cbs(&rdp->cblist))
- invoke_rcu_callbacks(rsp, rdp);
-
- /* Do any needed deferred wakeups of rcuo kthreads. */
- do_nocb_deferred_wakeup(rdp);
-}
-
-/*
- * Do RCU core processing for the current CPU.
- */
-static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
-{
- struct rcu_state *rsp;
+ const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+ rcu_segcblist_is_offloaded(&rdp->cblist);
if (cpu_is_offline(smp_processor_id()))
return;
trace_rcu_utilization(TPS("Start RCU core"));
- for_each_rcu_flavor(rsp)
- __rcu_process_callbacks(rsp);
+ WARN_ON_ONCE(!rdp->beenonline);
+
+ /* Report any deferred quiescent states if preemption enabled. */
+ if (!(preempt_count() & PREEMPT_MASK)) {
+ rcu_preempt_deferred_qs(current);
+ } else if (rcu_preempt_need_deferred_qs(current)) {
+ set_tsk_need_resched(current);
+ set_preempt_need_resched();
+ }
+
+ /* Update RCU state based on any recent quiescent states. */
+ rcu_check_quiescent_state(rdp);
+
+ /* No grace period and unregistered callbacks? */
+ if (!rcu_gp_in_progress() &&
+ rcu_segcblist_is_enabled(&rdp->cblist) && !offloaded) {
+ local_irq_save(flags);
+ if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
+ rcu_accelerate_cbs_unlocked(rnp, rdp);
+ local_irq_restore(flags);
+ }
+
+ rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
+
+ /* If there are callbacks ready, invoke them. */
+ if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist) &&
+ likely(READ_ONCE(rcu_scheduler_fully_active)))
+ rcu_do_batch(rdp);
+
+ /* Do any needed deferred wakeups of rcuo kthreads. */
+ do_nocb_deferred_wakeup(rdp);
trace_rcu_utilization(TPS("End RCU core"));
+
+ // If strict GPs, schedule an RCU reader in a clean environment.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work);
+}
+
+static void rcu_core_si(struct softirq_action *h)
+{
+ rcu_core();
+}
+
+static void rcu_wake_cond(struct task_struct *t, int status)
+{
+ /*
+ * If the thread is yielding, only wake it when this
+ * is invoked from idle
+ */
+ if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
+ wake_up_process(t);
+}
+
+static void invoke_rcu_core_kthread(void)
+{
+ struct task_struct *t;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
+ t = __this_cpu_read(rcu_data.rcu_cpu_kthread_task);
+ if (t != NULL && t != current)
+ rcu_wake_cond(t, __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
+ local_irq_restore(flags);
}
/*
- * Schedule RCU callback invocation. If the specified type of RCU
- * does not support RCU priority boosting, just do a direct call,
- * otherwise wake up the per-CPU kernel kthread. Note that because we
- * are running on the current CPU with softirqs disabled, the
- * rcu_cpu_kthread_task cannot disappear out from under us.
+ * Wake up this CPU's rcuc kthread to do RCU core processing.
*/
-static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
- return;
- if (likely(!rsp->boost)) {
- rcu_do_batch(rsp, rdp);
- return;
- }
- invoke_rcu_callbacks_kthread();
-}
-
static void invoke_rcu_core(void)
{
- if (cpu_online(smp_processor_id()))
+ if (!cpu_online(smp_processor_id()))
+ return;
+ if (use_softirq)
raise_softirq(RCU_SOFTIRQ);
+ else
+ invoke_rcu_core_kthread();
+}
+
+static void rcu_cpu_kthread_park(unsigned int cpu)
+{
+ per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+}
+
+static int rcu_cpu_kthread_should_run(unsigned int cpu)
+{
+ return __this_cpu_read(rcu_data.rcu_cpu_has_work);
+}
+
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks. This replaces
+ * the RCU softirq used in configurations of RCU that do not support RCU
+ * priority boosting.
+ */
+static void rcu_cpu_kthread(unsigned int cpu)
+{
+ unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
+ char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
+ int spincnt;
+
+ trace_rcu_utilization(TPS("Start CPU kthread@rcu_run"));
+ for (spincnt = 0; spincnt < 10; spincnt++) {
+ local_bh_disable();
+ *statusp = RCU_KTHREAD_RUNNING;
+ local_irq_disable();
+ work = *workp;
+ *workp = 0;
+ local_irq_enable();
+ if (work)
+ rcu_core();
+ local_bh_enable();
+ if (*workp == 0) {
+ trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
+ *statusp = RCU_KTHREAD_WAITING;
+ return;
+ }
+ }
+ *statusp = RCU_KTHREAD_YIELDING;
+ trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
+ schedule_timeout_idle(2);
+ trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
+ *statusp = RCU_KTHREAD_WAITING;
+}
+
+static struct smp_hotplug_thread rcu_cpu_thread_spec = {
+ .store = &rcu_data.rcu_cpu_kthread_task,
+ .thread_should_run = rcu_cpu_kthread_should_run,
+ .thread_fn = rcu_cpu_kthread,
+ .thread_comm = "rcuc/%u",
+ .setup = rcu_cpu_kthread_setup,
+ .park = rcu_cpu_kthread_park,
+};
+
+/*
+ * Spawn per-CPU RCU core processing kthreads.
+ */
+static int __init rcu_spawn_core_kthreads(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
+ if (!IS_ENABLED(CONFIG_RCU_BOOST) && use_softirq)
+ return 0;
+ WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec),
+ "%s: Could not start rcuc kthread, OOM is now expected behavior\n", __func__);
+ return 0;
}
/*
* Handle any core-RCU processing required by a call_rcu() invocation.
*/
-static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
- struct rcu_head *head, unsigned long flags)
+static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
+ unsigned long flags)
{
/*
* If called from an extended quiescent state, invoke the RCU
@@ -2928,27 +2872,27 @@
/*
* Force the grace period if too many callbacks or too long waiting.
- * Enforce hysteresis, and don't invoke force_quiescent_state()
+ * Enforce hysteresis, and don't invoke rcu_force_quiescent_state()
* if some other CPU has recently done so. Also, don't bother
- * invoking force_quiescent_state() if the newly enqueued callback
+ * invoking rcu_force_quiescent_state() if the newly enqueued callback
* is the only one waiting for a grace period to complete.
*/
if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) >
rdp->qlen_last_fqs_check + qhimark)) {
/* Are we ignoring a completed grace period? */
- note_gp_changes(rsp, rdp);
+ note_gp_changes(rdp);
/* Start a new grace period if one not already started. */
- if (!rcu_gp_in_progress(rsp)) {
- rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp);
+ if (!rcu_gp_in_progress()) {
+ rcu_accelerate_cbs_unlocked(rdp->mynode, rdp);
} else {
/* Give the grace period a kick. */
- rdp->blimit = LONG_MAX;
- if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+ rdp->blimit = DEFAULT_MAX_RCU_BLIMIT;
+ if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap &&
rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
- force_quiescent_state(rsp);
- rdp->n_force_qs_snap = rsp->n_force_qs;
+ rcu_force_quiescent_state();
+ rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
}
@@ -2962,17 +2906,54 @@
}
/*
- * Helper function for call_rcu() and friends. The cpu argument will
- * normally be -1, indicating "currently running CPU". It may specify
- * a CPU only if that CPU is a no-CBs CPU. Currently, only _rcu_barrier()
- * is expected to specify a CPU.
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks. The caller must hold the leaf rcu_node
+ * structure's ->lock.
*/
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp)
+{
+ raw_lockdep_assert_held_rcu_node(rnp);
+ if (qovld_calc <= 0)
+ return; // Early boot and wildcard value set.
+ if (rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc)
+ WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask | rdp->grpmask);
+ else
+ WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask & ~rdp->grpmask);
+}
+
+/*
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks. No locks need be held, but the
+ * caller must have disabled interrupts.
+ *
+ * Note that this function ignores the possibility that there are a lot
+ * of callbacks all of which have already seen the end of their respective
+ * grace periods. This omission is due to the need for no-CBs CPUs to
+ * be holding ->nocb_lock to do this check, which is too heavy for a
+ * common-case operation.
+ */
+static void check_cb_ovld(struct rcu_data *rdp)
+{
+ struct rcu_node *const rnp = rdp->mynode;
+
+ if (qovld_calc <= 0 ||
+ ((rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc) ==
+ !!(READ_ONCE(rnp->cbovldmask) & rdp->grpmask)))
+ return; // Early boot wildcard value or already set correctly.
+ raw_spin_lock_rcu_node(rnp);
+ check_cb_ovld_locked(rdp, rnp);
+ raw_spin_unlock_rcu_node(rnp);
+}
+
+/* Helper function for call_rcu() and friends. */
static void
-__call_rcu(struct rcu_head *head, rcu_callback_t func,
- struct rcu_state *rsp, int cpu, bool lazy)
+__call_rcu(struct rcu_head *head, rcu_callback_t func)
{
unsigned long flags;
struct rcu_data *rdp;
+ bool was_alldone;
/* Misaligned rcu_head! */
WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
@@ -2983,7 +2964,7 @@
* Use rcu:rcu_callback trace event to find the previous
* time callback was passed to __call_rcu().
*/
- WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pF()!!!\n",
+ WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pS()!!!\n",
head, head->func);
WRITE_ONCE(head->func, rcu_leak_callback);
return;
@@ -2991,130 +2972,692 @@
head->func = func;
head->next = NULL;
local_irq_save(flags);
- rdp = this_cpu_ptr(rsp->rda);
+ kasan_record_aux_stack(head);
+ rdp = this_cpu_ptr(&rcu_data);
/* Add the callback to our list. */
- if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist)) || cpu != -1) {
- int offline;
-
- if (cpu != -1)
- rdp = per_cpu_ptr(rsp->rda, cpu);
- if (likely(rdp->mynode)) {
- /* Post-boot, so this should be for a no-CBs CPU. */
- offline = !__call_rcu_nocb(rdp, head, lazy, flags);
- WARN_ON_ONCE(offline);
- /* Offline CPU, _call_rcu() illegal, leak callback. */
- local_irq_restore(flags);
- return;
- }
- /*
- * Very early boot, before rcu_init(). Initialize if needed
- * and then drop through to queue the callback.
- */
- BUG_ON(cpu != -1);
+ if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist))) {
+ // This can trigger due to call_rcu() from offline CPU:
+ WARN_ON_ONCE(rcu_scheduler_active != RCU_SCHEDULER_INACTIVE);
WARN_ON_ONCE(!rcu_is_watching());
+ // Very early boot, before rcu_init(). Initialize if needed
+ // and then drop through to queue the callback.
if (rcu_segcblist_empty(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist);
}
- rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
- if (!lazy)
- rcu_idle_count_callbacks_posted();
- if (__is_kfree_rcu_offset((unsigned long)func))
- trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ check_cb_ovld(rdp);
+ if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
+ return; // Enqueued onto ->nocb_bypass, so just leave.
+ // If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
+ rcu_segcblist_enqueue(&rdp->cblist, head);
+ if (__is_kvfree_rcu_offset((unsigned long)func))
+ trace_rcu_kvfree_callback(rcu_state.name, head,
+ (unsigned long)func,
rcu_segcblist_n_cbs(&rdp->cblist));
else
- trace_rcu_callback(rsp->name, head,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ trace_rcu_callback(rcu_state.name, head,
rcu_segcblist_n_cbs(&rdp->cblist));
/* Go handle any RCU core processing required. */
- __call_rcu_core(rsp, rdp, head, flags);
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+ unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) {
+ __call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
+ } else {
+ __call_rcu_core(rdp, head, flags);
+ local_irq_restore(flags);
+ }
+}
+
+/**
+ * call_rcu() - Queue an RCU callback for invocation after a grace period.
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed. However, the callback function
+ * might well execute concurrently with RCU read-side critical sections
+ * that started after call_rcu() was invoked. RCU read-side critical
+ * sections are delimited by rcu_read_lock() and rcu_read_unlock(), and
+ * may be nested. In addition, regions of code across which interrupts,
+ * preemption, or softirqs have been disabled also serve as RCU read-side
+ * critical sections. This includes hardware interrupt handlers, softirq
+ * handlers, and NMI handlers.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing RCU read-side critical section. On systems with more
+ * than one CPU, this means that when "func()" is invoked, each CPU is
+ * guaranteed to have executed a full memory barrier since the end of its
+ * last RCU read-side critical section whose beginning preceded the call
+ * to call_rcu(). It also means that each CPU executing an RCU read-side
+ * critical section that continues beyond the start of "func()" must have
+ * executed a memory barrier after the call_rcu() but before the beginning
+ * of that RCU read-side critical section. Note that these guarantees
+ * include CPUs that are offline, idle, or executing in user mode, as
+ * well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting RCU callback function "func()", then both CPU A and CPU B are
+ * guaranteed to execute a full memory barrier during the time interval
+ * between the call to call_rcu() and the invocation of "func()" -- even
+ * if CPU A and CPU B are the same CPU (but again only if the system has
+ * more than one CPU).
+ */
+void call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+ __call_rcu(head, func);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+
+/* Maximum number of jiffies to wait before draining a batch. */
+#define KFREE_DRAIN_JIFFIES (HZ / 50)
+#define KFREE_N_BATCHES 2
+#define FREE_N_CHANNELS 2
+
+/**
+ * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers
+ * @nr_records: Number of active pointers in the array
+ * @next: Next bulk object in the block chain
+ * @records: Array of the kvfree_rcu() pointers
+ */
+struct kvfree_rcu_bulk_data {
+ unsigned long nr_records;
+ struct kvfree_rcu_bulk_data *next;
+ void *records[];
+};
+
+/*
+ * This macro defines how many entries the "records" array
+ * will contain. It is based on the fact that the size of
+ * kvfree_rcu_bulk_data structure becomes exactly one page.
+ */
+#define KVFREE_BULK_MAX_ENTR \
+ ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *))
+
+/**
+ * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
+ * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
+ * @head_free: List of kfree_rcu() objects waiting for a grace period
+ * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period
+ * @krcp: Pointer to @kfree_rcu_cpu structure
+ */
+
+struct kfree_rcu_cpu_work {
+ struct rcu_work rcu_work;
+ struct rcu_head *head_free;
+ struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS];
+ struct kfree_rcu_cpu *krcp;
+};
+
+/**
+ * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
+ * @head: List of kfree_rcu() objects not yet waiting for a grace period
+ * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
+ * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
+ * @lock: Synchronize access to this structure
+ * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
+ * @monitor_todo: Tracks whether a @monitor_work delayed work is pending
+ * @initialized: The @rcu_work fields have been initialized
+ * @count: Number of objects for which GP not started
+ * @bkvcache:
+ * A simple cache list that contains objects for reuse purpose.
+ * In order to save some per-cpu space the list is singular.
+ * Even though it is lockless an access has to be protected by the
+ * per-cpu lock.
+ * @page_cache_work: A work to refill the cache when it is empty
+ * @work_in_progress: Indicates that page_cache_work is running
+ * @hrtimer: A hrtimer for scheduling a page_cache_work
+ * @nr_bkv_objs: number of allocated objects at @bkvcache.
+ *
+ * This is a per-CPU structure. The reason that it is not included in
+ * the rcu_data structure is to permit this code to be extracted from
+ * the RCU files. Such extraction could allow further optimization of
+ * the interactions with the slab allocators.
+ */
+struct kfree_rcu_cpu {
+ struct rcu_head *head;
+ struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS];
+ struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
+ raw_spinlock_t lock;
+ struct delayed_work monitor_work;
+ bool monitor_todo;
+ bool initialized;
+ int count;
+
+ struct work_struct page_cache_work;
+ atomic_t work_in_progress;
+ struct hrtimer hrtimer;
+
+ struct llist_head bkvcache;
+ int nr_bkv_objs;
+};
+
+static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock),
+};
+
+static __always_inline void
+debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead)
+{
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+ int i;
+
+ for (i = 0; i < bhead->nr_records; i++)
+ debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
+#endif
+}
+
+static inline struct kfree_rcu_cpu *
+krc_this_cpu_lock(unsigned long *flags)
+{
+ struct kfree_rcu_cpu *krcp;
+
+ local_irq_save(*flags); // For safely calling this_cpu_ptr().
+ krcp = this_cpu_ptr(&krc);
+ raw_spin_lock(&krcp->lock);
+
+ return krcp;
+}
+
+static inline void
+krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
+{
+ raw_spin_unlock(&krcp->lock);
local_irq_restore(flags);
}
-/**
- * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_sched() assumes
- * that the read-side critical sections end on enabling of preemption
- * or on voluntary preemption.
- * RCU read-side critical sections are delimited by:
- *
- * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
- * - anything that disables preemption.
- *
- * These may be nested.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
+static inline struct kvfree_rcu_bulk_data *
+get_cached_bnode(struct kfree_rcu_cpu *krcp)
{
- __call_rcu(head, func, &rcu_sched_state, -1, 0);
-}
-EXPORT_SYMBOL_GPL(call_rcu_sched);
+ if (!krcp->nr_bkv_objs)
+ return NULL;
-/**
- * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_bh() assumes
- * that the read-side critical sections end on completion of a softirq
- * handler. This means that read-side critical sections in process
- * context must not be interrupted by softirqs. This interface is to be
- * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by:
- *
- * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context, OR
- * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
- *
- * These may be nested.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
-{
- __call_rcu(head, func, &rcu_bh_state, -1, 0);
+ krcp->nr_bkv_objs--;
+ return (struct kvfree_rcu_bulk_data *)
+ llist_del_first(&krcp->bkvcache);
}
-EXPORT_SYMBOL_GPL(call_rcu_bh);
+
+static inline bool
+put_cached_bnode(struct kfree_rcu_cpu *krcp,
+ struct kvfree_rcu_bulk_data *bnode)
+{
+ // Check the limit.
+ if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
+ return false;
+
+ llist_add((struct llist_node *) bnode, &krcp->bkvcache);
+ krcp->nr_bkv_objs++;
+ return true;
+
+}
/*
- * Queue an RCU callback for lazy invocation after a grace period.
- * This will likely be later named something like "call_rcu_lazy()",
- * but this change will require some way of tagging the lazy RCU
- * callbacks in the list of pending callbacks. Until then, this
- * function may only be called from __kfree_rcu().
+ * This function is invoked in workqueue context after a grace period.
+ * It frees all the objects queued on ->bhead_free or ->head_free.
*/
-void kfree_call_rcu(struct rcu_head *head,
- rcu_callback_t func)
+static void kfree_rcu_work(struct work_struct *work)
{
- __call_rcu(head, func, rcu_state_p, -1, 1);
+ unsigned long flags;
+ struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext;
+ struct rcu_head *head, *next;
+ struct kfree_rcu_cpu *krcp;
+ struct kfree_rcu_cpu_work *krwp;
+ int i, j;
+
+ krwp = container_of(to_rcu_work(work),
+ struct kfree_rcu_cpu_work, rcu_work);
+ krcp = krwp->krcp;
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ // Channels 1 and 2.
+ for (i = 0; i < FREE_N_CHANNELS; i++) {
+ bkvhead[i] = krwp->bkvhead_free[i];
+ krwp->bkvhead_free[i] = NULL;
+ }
+
+ // Channel 3.
+ head = krwp->head_free;
+ krwp->head_free = NULL;
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ // Handle two first channels.
+ for (i = 0; i < FREE_N_CHANNELS; i++) {
+ for (; bkvhead[i]; bkvhead[i] = bnext) {
+ bnext = bkvhead[i]->next;
+ debug_rcu_bhead_unqueue(bkvhead[i]);
+
+ rcu_lock_acquire(&rcu_callback_map);
+ if (i == 0) { // kmalloc() / kfree().
+ trace_rcu_invoke_kfree_bulk_callback(
+ rcu_state.name, bkvhead[i]->nr_records,
+ bkvhead[i]->records);
+
+ kfree_bulk(bkvhead[i]->nr_records,
+ bkvhead[i]->records);
+ } else { // vmalloc() / vfree().
+ for (j = 0; j < bkvhead[i]->nr_records; j++) {
+ trace_rcu_invoke_kvfree_callback(
+ rcu_state.name,
+ bkvhead[i]->records[j], 0);
+
+ vfree(bkvhead[i]->records[j]);
+ }
+ }
+ rcu_lock_release(&rcu_callback_map);
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (put_cached_bnode(krcp, bkvhead[i]))
+ bkvhead[i] = NULL;
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ if (bkvhead[i])
+ free_page((unsigned long) bkvhead[i]);
+
+ cond_resched_tasks_rcu_qs();
+ }
+ }
+
+ /*
+ * Emergency case only. It can happen under low memory
+ * condition when an allocation gets failed, so the "bulk"
+ * path can not be temporary maintained.
+ */
+ for (; head; head = next) {
+ unsigned long offset = (unsigned long)head->func;
+ void *ptr = (void *)head - offset;
+
+ next = head->next;
+ debug_rcu_head_unqueue((struct rcu_head *)ptr);
+ rcu_lock_acquire(&rcu_callback_map);
+ trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset);
+
+ if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
+ kvfree(ptr);
+
+ rcu_lock_release(&rcu_callback_map);
+ cond_resched_tasks_rcu_qs();
+ }
}
-EXPORT_SYMBOL_GPL(kfree_call_rcu);
+
+static bool
+need_offload_krc(struct kfree_rcu_cpu *krcp)
+{
+ int i;
+
+ for (i = 0; i < FREE_N_CHANNELS; i++)
+ if (krcp->bkvhead[i])
+ return true;
+
+ return !!krcp->head;
+}
+
+static bool
+need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp)
+{
+ int i;
+
+ for (i = 0; i < FREE_N_CHANNELS; i++)
+ if (krwp->bkvhead_free[i])
+ return true;
+
+ return !!krwp->head_free;
+}
/*
- * Because a context switch is a grace period for RCU-sched and RCU-bh,
- * any blocking grace-period wait automatically implies a grace period
- * if there is only one CPU online at any point time during execution
- * of either synchronize_sched() or synchronize_rcu_bh(). It is OK to
+ * Schedule the kfree batch RCU work to run in workqueue context after a GP.
+ *
+ * This function is invoked by kfree_rcu_monitor() when the KFREE_DRAIN_JIFFIES
+ * timeout has been reached.
+ */
+static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
+{
+ struct kfree_rcu_cpu_work *krwp;
+ bool repeat = false;
+ int i, j;
+
+ lockdep_assert_held(&krcp->lock);
+
+ for (i = 0; i < KFREE_N_BATCHES; i++) {
+ krwp = &(krcp->krw_arr[i]);
+
+ // Try to detach bulk_head or head and attach it, only when
+ // all channels are free. Any channel is not free means at krwp
+ // there is on-going rcu work to handle krwp's free business.
+ if (need_wait_for_krwp_work(krwp))
+ continue;
+
+ if (need_offload_krc(krcp)) {
+ // Channel 1 corresponds to SLAB ptrs.
+ // Channel 2 corresponds to vmalloc ptrs.
+ for (j = 0; j < FREE_N_CHANNELS; j++) {
+ if (!krwp->bkvhead_free[j]) {
+ krwp->bkvhead_free[j] = krcp->bkvhead[j];
+ krcp->bkvhead[j] = NULL;
+ }
+ }
+
+ // Channel 3 corresponds to emergency path.
+ if (!krwp->head_free) {
+ krwp->head_free = krcp->head;
+ krcp->head = NULL;
+ }
+
+ WRITE_ONCE(krcp->count, 0);
+
+ /*
+ * One work is per one batch, so there are three
+ * "free channels", the batch can handle. It can
+ * be that the work is in the pending state when
+ * channels have been detached following by each
+ * other.
+ */
+ queue_rcu_work(system_wq, &krwp->rcu_work);
+ }
+ }
+
+ // Repeat if any "free" corresponding channel is still busy.
+ if (need_offload_krc(krcp))
+ repeat = true;
+
+ return !repeat;
+}
+
+static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
+ unsigned long flags)
+{
+ // Attempt to start a new batch.
+ krcp->monitor_todo = false;
+ if (queue_kfree_rcu_work(krcp)) {
+ // Success! Our job is done here.
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+ return;
+ }
+
+ // Previous RCU batch still in progress, try again later.
+ krcp->monitor_todo = true;
+ schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+}
+
+/*
+ * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
+ * It invokes kfree_rcu_drain_unlock() to attempt to start another batch.
+ */
+static void kfree_rcu_monitor(struct work_struct *work)
+{
+ unsigned long flags;
+ struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu,
+ monitor_work.work);
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (krcp->monitor_todo)
+ kfree_rcu_drain_unlock(krcp, flags);
+ else
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+}
+
+static enum hrtimer_restart
+schedule_page_work_fn(struct hrtimer *t)
+{
+ struct kfree_rcu_cpu *krcp =
+ container_of(t, struct kfree_rcu_cpu, hrtimer);
+
+ queue_work(system_highpri_wq, &krcp->page_cache_work);
+ return HRTIMER_NORESTART;
+}
+
+static void fill_page_cache_func(struct work_struct *work)
+{
+ struct kvfree_rcu_bulk_data *bnode;
+ struct kfree_rcu_cpu *krcp =
+ container_of(work, struct kfree_rcu_cpu,
+ page_cache_work);
+ unsigned long flags;
+ bool pushed;
+ int i;
+
+ for (i = 0; i < rcu_min_cached_objs; i++) {
+ bnode = (struct kvfree_rcu_bulk_data *)
+ __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+
+ if (!bnode)
+ break;
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ pushed = put_cached_bnode(krcp, bnode);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ if (!pushed) {
+ free_page((unsigned long) bnode);
+ break;
+ }
+ }
+
+ atomic_set(&krcp->work_in_progress, 0);
+}
+
+static void
+run_page_cache_worker(struct kfree_rcu_cpu *krcp)
+{
+ if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
+ !atomic_xchg(&krcp->work_in_progress, 1)) {
+ hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL);
+ krcp->hrtimer.function = schedule_page_work_fn;
+ hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
+ }
+}
+
+static inline bool
+kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
+{
+ struct kvfree_rcu_bulk_data *bnode;
+ int idx;
+
+ if (unlikely(!krcp->initialized))
+ return false;
+
+ lockdep_assert_held(&krcp->lock);
+ idx = !!is_vmalloc_addr(ptr);
+
+ /* Check if a new block is required. */
+ if (!krcp->bkvhead[idx] ||
+ krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
+ bnode = get_cached_bnode(krcp);
+ /* Switch to emergency path. */
+ if (!bnode)
+ return false;
+
+ /* Initialize the new block. */
+ bnode->nr_records = 0;
+ bnode->next = krcp->bkvhead[idx];
+
+ /* Attach it to the head. */
+ krcp->bkvhead[idx] = bnode;
+ }
+
+ /* Finally insert. */
+ krcp->bkvhead[idx]->records
+ [krcp->bkvhead[idx]->nr_records++] = ptr;
+
+ return true;
+}
+
+/*
+ * Queue a request for lazy invocation of appropriate free routine after a
+ * grace period. Please note there are three paths are maintained, two are the
+ * main ones that use array of pointers interface and third one is emergency
+ * one, that is used only when the main path can not be maintained temporary,
+ * due to memory pressure.
+ *
+ * Each kvfree_call_rcu() request is added to a batch. The batch will be drained
+ * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
+ * be free'd in workqueue context. This allows us to: batch requests together to
+ * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
+ */
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+ unsigned long flags;
+ struct kfree_rcu_cpu *krcp;
+ bool success;
+ void *ptr;
+
+ if (head) {
+ ptr = (void *) head - (unsigned long) func;
+ } else {
+ /*
+ * Please note there is a limitation for the head-less
+ * variant, that is why there is a clear rule for such
+ * objects: it can be used from might_sleep() context
+ * only. For other places please embed an rcu_head to
+ * your data.
+ */
+ might_sleep();
+ ptr = (unsigned long *) func;
+ }
+
+ krcp = krc_this_cpu_lock(&flags);
+
+ // Queue the object but don't yet schedule the batch.
+ if (debug_rcu_head_queue(ptr)) {
+ // Probable double kfree_rcu(), just leak.
+ WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
+ __func__, head);
+
+ // Mark as success and leave.
+ success = true;
+ goto unlock_return;
+ }
+
+ success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+ if (!success) {
+ run_page_cache_worker(krcp);
+
+ if (head == NULL)
+ // Inline if kvfree_rcu(one_arg) call.
+ goto unlock_return;
+
+ head->func = func;
+ head->next = krcp->head;
+ krcp->head = head;
+ success = true;
+ }
+
+ WRITE_ONCE(krcp->count, krcp->count + 1);
+
+ // Set timer to drain after KFREE_DRAIN_JIFFIES.
+ if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
+ !krcp->monitor_todo) {
+ krcp->monitor_todo = true;
+ schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+ }
+
+unlock_return:
+ krc_this_cpu_unlock(krcp, flags);
+
+ /*
+ * Inline kvfree() after synchronize_rcu(). We can do
+ * it from might_sleep() context only, so the current
+ * CPU can pass the QS state.
+ */
+ if (!success) {
+ debug_rcu_head_unqueue((struct rcu_head *) ptr);
+ synchronize_rcu();
+ kvfree(ptr);
+ }
+}
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
+
+static unsigned long
+kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ int cpu;
+ unsigned long count = 0;
+
+ /* Snapshot count of all CPUs */
+ for_each_possible_cpu(cpu) {
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ count += READ_ONCE(krcp->count);
+ }
+
+ return count;
+}
+
+static unsigned long
+kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ int cpu, freed = 0;
+ unsigned long flags;
+
+ for_each_possible_cpu(cpu) {
+ int count;
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ count = krcp->count;
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (krcp->monitor_todo)
+ kfree_rcu_drain_unlock(krcp, flags);
+ else
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ sc->nr_to_scan -= count;
+ freed += count;
+
+ if (sc->nr_to_scan <= 0)
+ break;
+ }
+
+ return freed == 0 ? SHRINK_STOP : freed;
+}
+
+static struct shrinker kfree_rcu_shrinker = {
+ .count_objects = kfree_rcu_shrink_count,
+ .scan_objects = kfree_rcu_shrink_scan,
+ .batch = 0,
+ .seeks = DEFAULT_SEEKS,
+};
+
+void __init kfree_rcu_scheduler_running(void)
+{
+ int cpu;
+ unsigned long flags;
+
+ for_each_possible_cpu(cpu) {
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (!krcp->head || krcp->monitor_todo) {
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+ continue;
+ }
+ krcp->monitor_todo = true;
+ schedule_delayed_work_on(cpu, &krcp->monitor_work,
+ KFREE_DRAIN_JIFFIES);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+ }
+}
+
+/*
+ * During early boot, any blocking grace-period wait automatically
+ * implies a grace period. Later on, this is never the case for PREEMPTION.
+ *
+ * Howevr, because a context switch is a grace period for !PREEMPTION, any
+ * blocking grace-period wait automatically implies a grace period if
+ * there is only one CPU online at any point time during execution of
+ * either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to
* occasionally incorrectly indicate that there are multiple CPUs online
- * when there was in fact only one the whole time, as this just adds
- * some overhead: RCU still operates correctly.
+ * when there was in fact only one the whole time, as this just adds some
+ * overhead: RCU still operates correctly.
*/
static int rcu_blocking_is_gp(void)
{
int ret;
+ if (IS_ENABLED(CONFIG_PREEMPTION))
+ return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
might_sleep(); /* Check for RCU read-side critical section. */
preempt_disable();
ret = num_online_cpus() <= 1;
@@ -3123,81 +3666,52 @@
}
/**
- * synchronize_sched - wait until an rcu-sched grace period has elapsed.
+ * synchronize_rcu - wait until a grace period has elapsed.
*
- * Control will return to the caller some time after a full rcu-sched
- * grace period has elapsed, in other words after all currently executing
- * rcu-sched read-side critical sections have completed. These read-side
- * critical sections are delimited by rcu_read_lock_sched() and
- * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(),
- * local_irq_disable(), and so on may be used in place of
- * rcu_read_lock_sched().
- *
- * This means that all preempt_disable code sequences, including NMI and
- * non-threaded hardware-interrupt handlers, in progress on entry will
- * have completed before this primitive returns. However, this does not
- * guarantee that softirq handlers will have completed, since in some
- * kernels, these handlers can run in process context, and can block.
+ * Control will return to the caller some time after a full grace
+ * period has elapsed, in other words after all currently executing RCU
+ * read-side critical sections have completed. Note, however, that
+ * upon return from synchronize_rcu(), the caller might well be executing
+ * concurrently with new RCU read-side critical sections that began while
+ * synchronize_rcu() was waiting. RCU read-side critical sections are
+ * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
+ * In addition, regions of code across which interrupts, preemption, or
+ * softirqs have been disabled also serve as RCU read-side critical
+ * sections. This includes hardware interrupt handlers, softirq handlers,
+ * and NMI handlers.
*
* Note that this guarantee implies further memory-ordering guarantees.
- * On systems with more than one CPU, when synchronize_sched() returns,
- * each CPU is guaranteed to have executed a full memory barrier since the
- * end of its last RCU-sched read-side critical section whose beginning
- * preceded the call to synchronize_sched(). In addition, each CPU having
+ * On systems with more than one CPU, when synchronize_rcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last RCU read-side critical section whose beginning
+ * preceded the call to synchronize_rcu(). In addition, each CPU having
* an RCU read-side critical section that extends beyond the return from
- * synchronize_sched() is guaranteed to have executed a full memory barrier
- * after the beginning of synchronize_sched() and before the beginning of
+ * synchronize_rcu() is guaranteed to have executed a full memory barrier
+ * after the beginning of synchronize_rcu() and before the beginning of
* that RCU read-side critical section. Note that these guarantees include
* CPUs that are offline, idle, or executing in user mode, as well as CPUs
* that are executing in the kernel.
*
- * Furthermore, if CPU A invoked synchronize_sched(), which returned
+ * Furthermore, if CPU A invoked synchronize_rcu(), which returned
* to its caller on CPU B, then both CPU A and CPU B are guaranteed
* to have executed a full memory barrier during the execution of
- * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but
+ * synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but
* again only if the system has more than one CPU).
*/
-void synchronize_sched(void)
+void synchronize_rcu(void)
{
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_sched() in RCU-sched read-side critical section");
+ "Illegal synchronize_rcu() in RCU read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
- synchronize_sched_expedited();
+ synchronize_rcu_expedited();
else
- wait_rcu_gp(call_rcu_sched);
+ wait_rcu_gp(call_rcu);
}
-EXPORT_SYMBOL_GPL(synchronize_sched);
-
-/**
- * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu_bh grace
- * period has elapsed, in other words after all currently executing rcu_bh
- * read-side critical sections have completed. RCU read-side critical
- * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
- * and may be nested.
- *
- * See the description of synchronize_sched() for more detailed information
- * on memory ordering guarantees.
- */
-void synchronize_rcu_bh(void)
-{
- RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
- lock_is_held(&rcu_lock_map) ||
- lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
- if (rcu_blocking_is_gp())
- return;
- if (rcu_gp_is_expedited())
- synchronize_rcu_bh_expedited();
- else
- wait_rcu_gp(call_rcu_bh);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+EXPORT_SYMBOL_GPL(synchronize_rcu);
/**
* get_state_synchronize_rcu - Snapshot current RCU state
@@ -3213,7 +3727,7 @@
* before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
- return rcu_seq_snap(&rcu_state_p->gp_seq);
+ return rcu_seq_snap(&rcu_state.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
@@ -3233,74 +3747,42 @@
*/
void cond_synchronize_rcu(unsigned long oldstate)
{
- if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate))
+ if (!rcu_seq_done(&rcu_state.gp_seq, oldstate))
synchronize_rcu();
else
smp_mb(); /* Ensure GP ends before subsequent accesses. */
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
-/**
- * get_state_synchronize_sched - Snapshot current RCU-sched state
- *
- * Returns a cookie that is used by a later call to cond_synchronize_sched()
- * to determine whether or not a full grace period has elapsed in the
- * meantime.
- */
-unsigned long get_state_synchronize_sched(void)
-{
- /*
- * Any prior manipulation of RCU-protected data must happen
- * before the load from ->gp_seq.
- */
- smp_mb(); /* ^^^ */
- return rcu_seq_snap(&rcu_sched_state.gp_seq);
-}
-EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
-
-/**
- * cond_synchronize_sched - Conditionally wait for an RCU-sched grace period
- *
- * @oldstate: return value from earlier call to get_state_synchronize_sched()
- *
- * If a full RCU-sched grace period has elapsed since the earlier call to
- * get_state_synchronize_sched(), just return. Otherwise, invoke
- * synchronize_sched() to wait for a full grace period.
- *
- * Yes, this function does not take counter wrap into account. But
- * counter wrap is harmless. If the counter wraps, we have waited for
- * more than 2 billion grace periods (and way more on a 64-bit system!),
- * so waiting for one additional grace period should be just fine.
- */
-void cond_synchronize_sched(unsigned long oldstate)
-{
- if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate))
- synchronize_sched();
- else
- smp_mb(); /* Ensure GP ends before subsequent accesses. */
-}
-EXPORT_SYMBOL_GPL(cond_synchronize_sched);
-
/*
- * Check to see if there is any immediate RCU-related work to be done
- * by the current CPU, for the specified type of RCU, returning 1 if so.
- * The checks are in order of increasing expense: checks that can be
- * carried out against CPU-local state are performed first. However,
- * we must check for CPU stalls first, else we might not get a chance.
+ * Check to see if there is any immediate RCU-related work to be done by
+ * the current CPU, returning 1 if so and zero otherwise. The checks are
+ * in order of increasing expense: checks that can be carried out against
+ * CPU-local state are performed first. However, we must check for CPU
+ * stalls first, else we might not get a chance.
*/
-static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
+static int rcu_pending(int user)
{
+ bool gp_in_progress;
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
- /* Check for CPU stalls, if enabled. */
- check_cpu_stall(rsp, rdp);
+ lockdep_assert_irqs_disabled();
- /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
- if (rcu_nohz_full_cpu(rsp))
+ /* Check for CPU stalls, if enabled. */
+ check_cpu_stall(rdp);
+
+ /* Does this CPU need a deferred NOCB wakeup? */
+ if (rcu_nocb_need_deferred_wakeup(rdp))
+ return 1;
+
+ /* Is this a nohz_full CPU in userspace or idle? (Ignore RCU if so.) */
+ if ((user || rcu_is_cpu_rrupt_from_idle()) && rcu_nohz_full_cpu())
return 0;
/* Is the RCU core waiting for a quiescent state from this CPU? */
- if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm)
+ gp_in_progress = rcu_gp_in_progress();
+ if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm && gp_in_progress)
return 1;
/* Does this CPU have callbacks ready to invoke? */
@@ -3308,8 +3790,9 @@
return 1;
/* Has RCU gone idle with this CPU needing another grace period? */
- if (!rcu_gp_in_progress(rsp) &&
- rcu_segcblist_is_enabled(&rdp->cblist) &&
+ if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
+ (!IS_ENABLED(CONFIG_RCU_NOCB_CPU) ||
+ !rcu_segcblist_is_offloaded(&rdp->cblist)) &&
!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return 1;
@@ -3318,141 +3801,106 @@
unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
return 1;
- /* Does this CPU need a deferred NOCB wakeup? */
- if (rcu_nocb_need_deferred_wakeup(rdp))
- return 1;
-
/* nothing to do */
return 0;
}
/*
- * Check to see if there is any immediate RCU-related work to be done
- * by the current CPU, returning 1 if so. This function is part of the
- * RCU implementation; it is -not- an exported member of the RCU API.
- */
-static int rcu_pending(void)
-{
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp)
- if (__rcu_pending(rsp, this_cpu_ptr(rsp->rda)))
- return 1;
- return 0;
-}
-
-/*
- * Return true if the specified CPU has any callback. If all_lazy is
- * non-NULL, store an indication of whether all callbacks are lazy.
- * (If there are no callbacks, all of them are deemed to be lazy.)
- */
-static bool rcu_cpu_has_callbacks(bool *all_lazy)
-{
- bool al = true;
- bool hc = false;
- struct rcu_data *rdp;
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp) {
- rdp = this_cpu_ptr(rsp->rda);
- if (rcu_segcblist_empty(&rdp->cblist))
- continue;
- hc = true;
- if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist) || !all_lazy) {
- al = false;
- break;
- }
- }
- if (all_lazy)
- *all_lazy = al;
- return hc;
-}
-
-/*
- * Helper function for _rcu_barrier() tracing. If tracing is disabled,
+ * Helper function for rcu_barrier() tracing. If tracing is disabled,
* the compiler is expected to optimize this away.
*/
-static void _rcu_barrier_trace(struct rcu_state *rsp, const char *s,
- int cpu, unsigned long done)
+static void rcu_barrier_trace(const char *s, int cpu, unsigned long done)
{
- trace_rcu_barrier(rsp->name, s, cpu,
- atomic_read(&rsp->barrier_cpu_count), done);
+ trace_rcu_barrier(rcu_state.name, s, cpu,
+ atomic_read(&rcu_state.barrier_cpu_count), done);
}
/*
- * RCU callback function for _rcu_barrier(). If we are last, wake
- * up the task executing _rcu_barrier().
+ * RCU callback function for rcu_barrier(). If we are last, wake
+ * up the task executing rcu_barrier().
+ *
+ * Note that the value of rcu_state.barrier_sequence must be captured
+ * before the atomic_dec_and_test(). Otherwise, if this CPU is not last,
+ * other CPUs might count the value down to zero before this CPU gets
+ * around to invoking rcu_barrier_trace(), which might result in bogus
+ * data from the next instance of rcu_barrier().
*/
static void rcu_barrier_callback(struct rcu_head *rhp)
{
- struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head);
- struct rcu_state *rsp = rdp->rsp;
+ unsigned long __maybe_unused s = rcu_state.barrier_sequence;
- if (atomic_dec_and_test(&rsp->barrier_cpu_count)) {
- _rcu_barrier_trace(rsp, TPS("LastCB"), -1,
- rsp->barrier_sequence);
- complete(&rsp->barrier_completion);
+ if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
+ rcu_barrier_trace(TPS("LastCB"), -1, s);
+ complete(&rcu_state.barrier_completion);
} else {
- _rcu_barrier_trace(rsp, TPS("CB"), -1, rsp->barrier_sequence);
+ rcu_barrier_trace(TPS("CB"), -1, s);
}
}
/*
* Called with preemption disabled, and from cross-cpu IRQ context.
*/
-static void rcu_barrier_func(void *type)
+static void rcu_barrier_func(void *cpu_in)
{
- struct rcu_state *rsp = type;
- struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
+ uintptr_t cpu = (uintptr_t)cpu_in;
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
- _rcu_barrier_trace(rsp, TPS("IRQ"), -1, rsp->barrier_sequence);
+ rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence);
rdp->barrier_head.func = rcu_barrier_callback;
debug_rcu_head_queue(&rdp->barrier_head);
- if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) {
- atomic_inc(&rsp->barrier_cpu_count);
+ rcu_nocb_lock(rdp);
+ WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+ if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
+ atomic_inc(&rcu_state.barrier_cpu_count);
} else {
debug_rcu_head_unqueue(&rdp->barrier_head);
- _rcu_barrier_trace(rsp, TPS("IRQNQ"), -1,
- rsp->barrier_sequence);
+ rcu_barrier_trace(TPS("IRQNQ"), -1,
+ rcu_state.barrier_sequence);
}
+ rcu_nocb_unlock(rdp);
}
-/*
- * Orchestrate the specified type of RCU barrier, waiting for all
- * RCU callbacks of the specified type to complete.
+/**
+ * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ *
+ * Note that this primitive does not necessarily wait for an RCU grace period
+ * to complete. For example, if there are no RCU callbacks queued anywhere
+ * in the system, then rcu_barrier() is within its rights to return
+ * immediately, without waiting for anything, much less an RCU grace period.
*/
-static void _rcu_barrier(struct rcu_state *rsp)
+void rcu_barrier(void)
{
- int cpu;
+ uintptr_t cpu;
struct rcu_data *rdp;
- unsigned long s = rcu_seq_snap(&rsp->barrier_sequence);
+ unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
- _rcu_barrier_trace(rsp, TPS("Begin"), -1, s);
+ rcu_barrier_trace(TPS("Begin"), -1, s);
/* Take mutex to serialize concurrent rcu_barrier() requests. */
- mutex_lock(&rsp->barrier_mutex);
+ mutex_lock(&rcu_state.barrier_mutex);
/* Did someone else do our work for us? */
- if (rcu_seq_done(&rsp->barrier_sequence, s)) {
- _rcu_barrier_trace(rsp, TPS("EarlyExit"), -1,
- rsp->barrier_sequence);
+ if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
+ rcu_barrier_trace(TPS("EarlyExit"), -1,
+ rcu_state.barrier_sequence);
smp_mb(); /* caller's subsequent code after above check. */
- mutex_unlock(&rsp->barrier_mutex);
+ mutex_unlock(&rcu_state.barrier_mutex);
return;
}
/* Mark the start of the barrier operation. */
- rcu_seq_start(&rsp->barrier_sequence);
- _rcu_barrier_trace(rsp, TPS("Inc1"), -1, rsp->barrier_sequence);
+ rcu_seq_start(&rcu_state.barrier_sequence);
+ rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence);
/*
- * Initialize the count to one rather than to zero in order to
- * avoid a too-soon return to zero in case of a short grace period
- * (or preemption of this task). Exclude CPU-hotplug operations
- * to ensure that no offline CPU has callbacks queued.
+ * Initialize the count to two rather than to zero in order
+ * to avoid a too-soon return to zero in case of an immediate
+ * invocation of the just-enqueued callback (or preemption of
+ * this task). Exclude CPU-hotplug operations to ensure that no
+ * offline non-offloaded CPU has callbacks queued.
*/
- init_completion(&rsp->barrier_completion);
- atomic_set(&rsp->barrier_cpu_count, 1);
+ init_completion(&rcu_state.barrier_completion);
+ atomic_set(&rcu_state.barrier_cpu_count, 2);
get_online_cpus();
/*
@@ -3461,28 +3909,27 @@
* corresponding CPU's preceding callbacks have been invoked.
*/
for_each_possible_cpu(cpu) {
- if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu))
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (cpu_is_offline(cpu) &&
+ !rcu_segcblist_is_offloaded(&rdp->cblist))
continue;
- rdp = per_cpu_ptr(rsp->rda, cpu);
- if (rcu_is_nocb_cpu(cpu)) {
- if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
- _rcu_barrier_trace(rsp, TPS("OfflineNoCB"), cpu,
- rsp->barrier_sequence);
- } else {
- _rcu_barrier_trace(rsp, TPS("OnlineNoCB"), cpu,
- rsp->barrier_sequence);
- smp_mb__before_atomic();
- atomic_inc(&rsp->barrier_cpu_count);
- __call_rcu(&rdp->barrier_head,
- rcu_barrier_callback, rsp, cpu, 0);
- }
- } else if (rcu_segcblist_n_cbs(&rdp->cblist)) {
- _rcu_barrier_trace(rsp, TPS("OnlineQ"), cpu,
- rsp->barrier_sequence);
- smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
+ if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
+ rcu_barrier_trace(TPS("OnlineQ"), cpu,
+ rcu_state.barrier_sequence);
+ smp_call_function_single(cpu, rcu_barrier_func, (void *)cpu, 1);
+ } else if (rcu_segcblist_n_cbs(&rdp->cblist) &&
+ cpu_is_offline(cpu)) {
+ rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu,
+ rcu_state.barrier_sequence);
+ local_irq_disable();
+ rcu_barrier_func((void *)cpu);
+ local_irq_enable();
+ } else if (cpu_is_offline(cpu)) {
+ rcu_barrier_trace(TPS("OfflineNoCBNoQ"), cpu,
+ rcu_state.barrier_sequence);
} else {
- _rcu_barrier_trace(rsp, TPS("OnlineNQ"), cpu,
- rsp->barrier_sequence);
+ rcu_barrier_trace(TPS("OnlineNQ"), cpu,
+ rcu_state.barrier_sequence);
}
}
put_online_cpus();
@@ -3491,37 +3938,20 @@
* Now that we have an rcu_barrier_callback() callback on each
* CPU, and thus each counted, remove the initial count.
*/
- if (atomic_dec_and_test(&rsp->barrier_cpu_count))
- complete(&rsp->barrier_completion);
+ if (atomic_sub_and_test(2, &rcu_state.barrier_cpu_count))
+ complete(&rcu_state.barrier_completion);
/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
- wait_for_completion(&rsp->barrier_completion);
+ wait_for_completion(&rcu_state.barrier_completion);
/* Mark the end of the barrier operation. */
- _rcu_barrier_trace(rsp, TPS("Inc2"), -1, rsp->barrier_sequence);
- rcu_seq_end(&rsp->barrier_sequence);
+ rcu_barrier_trace(TPS("Inc2"), -1, rcu_state.barrier_sequence);
+ rcu_seq_end(&rcu_state.barrier_sequence);
/* Other rcu_barrier() invocations can now safely proceed. */
- mutex_unlock(&rsp->barrier_mutex);
+ mutex_unlock(&rcu_state.barrier_mutex);
}
-
-/**
- * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
- */
-void rcu_barrier_bh(void)
-{
- _rcu_barrier(&rcu_bh_state);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_bh);
-
-/**
- * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
- */
-void rcu_barrier_sched(void)
-{
- _rcu_barrier(&rcu_sched_state);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+EXPORT_SYMBOL_GPL(rcu_barrier);
/*
* Propagate ->qsinitmask bits up the rcu_node tree to account for the
@@ -3555,46 +3985,48 @@
* Do boot-time initialization of a CPU's per-CPU RCU data.
*/
static void __init
-rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
+rcu_boot_init_percpu_data(int cpu)
{
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
/* Set up local state, ensuring consistent view of global state. */
rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
- rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
- WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
- WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
- rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+ INIT_WORK(&rdp->strict_work, strict_work_handler);
+ WARN_ON_ONCE(rdp->dynticks_nesting != 1);
+ WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
+ rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;
rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
- rdp->rcu_onl_gp_seq = rsp->gp_seq;
+ rdp->rcu_onl_gp_seq = rcu_state.gp_seq;
rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
rdp->cpu = cpu;
- rdp->rsp = rsp;
rcu_boot_init_nocb_percpu_data(rdp);
}
/*
- * Initialize a CPU's per-CPU RCU data. Note that only one online or
+ * Invoked early in the CPU-online process, when pretty much all services
+ * are available. The incoming CPU is not present.
+ *
+ * Initializes a CPU's per-CPU RCU data. Note that only one online or
* offline event can be happening at a given time. Note also that we can
* accept some slop in the rsp->gp_seq access due to the fact that this
- * CPU cannot possibly have any RCU callbacks in flight yet.
+ * CPU cannot possibly have any non-offloaded RCU callbacks in flight yet.
+ * And any offloaded callbacks are being numbered elsewhere.
*/
-static void
-rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
+int rcutree_prepare_cpu(unsigned int cpu)
{
unsigned long flags;
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_node *rnp = rcu_get_root(rsp);
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ struct rcu_node *rnp = rcu_get_root();
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp->qlen_last_fqs_check = 0;
- rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
rdp->blimit = blimit;
if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */
- !init_nocb_callback_list(rdp))
+ !rcu_segcblist_is_offloaded(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */
- rdp->dynticks->dynticks_nesting = 1; /* CPU not up, no tearing. */
+ rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */
rcu_dynticks_eqs_online();
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
@@ -3606,30 +4038,16 @@
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rdp->beenonline = true; /* We have now been online. */
- rdp->gp_seq = rnp->gp_seq;
- rdp->gp_seq_needed = rnp->gp_seq;
+ rdp->gp_seq = READ_ONCE(rnp->gp_seq);
+ rdp->gp_seq_needed = rdp->gp_seq;
rdp->cpu_no_qs.b.norm = true;
- rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
rdp->core_needs_qs = false;
rdp->rcu_iw_pending = false;
- rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
- trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl"));
+ rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
+ trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-}
-
-/*
- * Invoked early in the CPU-online process, when pretty much all
- * services are available. The incoming CPU is not present.
- */
-int rcutree_prepare_cpu(unsigned int cpu)
-{
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp)
- rcu_init_percpu_data(cpu, rsp);
-
rcu_prepare_kthreads(cpu);
- rcu_spawn_all_nocb_kthreads(cpu);
+ rcu_spawn_cpu_nocb_kthread(cpu);
return 0;
}
@@ -3639,7 +4057,7 @@
*/
static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
{
- struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
rcu_boost_kthread_setaffinity(rdp->mynode, outgoing);
}
@@ -3653,21 +4071,19 @@
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
- struct rcu_state *rsp;
- for_each_rcu_flavor(rsp) {
- rdp = per_cpu_ptr(rsp->rda, cpu);
- rnp = rdp->mynode;
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rnp->ffmask |= rdp->grpmask;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
- if (IS_ENABLED(CONFIG_TREE_SRCU))
- srcu_online_cpu(cpu);
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ rnp = rdp->mynode;
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ rnp->ffmask |= rdp->grpmask;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return 0; /* Too early in boot for scheduler work. */
sync_sched_exp_online_cleanup(cpu);
rcutree_affinity_setting(cpu, -1);
+
+ // Stop-machine done, so allow nohz_full to disable tick.
+ tick_dep_clear(TICK_DEP_BIT_RCU);
return 0;
}
@@ -3680,49 +4096,19 @@
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
- struct rcu_state *rsp;
- for_each_rcu_flavor(rsp) {
- rdp = per_cpu_ptr(rsp->rda, cpu);
- rnp = rdp->mynode;
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rnp->ffmask &= ~rdp->grpmask;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ rnp = rdp->mynode;
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ rnp->ffmask &= ~rdp->grpmask;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcutree_affinity_setting(cpu, cpu);
- if (IS_ENABLED(CONFIG_TREE_SRCU))
- srcu_offline_cpu(cpu);
+
+ // nohz_full CPUs need the tick for stop-machine to work quickly
+ tick_dep_set(TICK_DEP_BIT_RCU);
return 0;
}
-
-/*
- * Near the end of the offline process. We do only tracing here.
- */
-int rcutree_dying_cpu(unsigned int cpu)
-{
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp)
- rcu_cleanup_dying_cpu(rsp);
- return 0;
-}
-
-/*
- * The outgoing CPU is gone and we are running elsewhere.
- */
-int rcutree_dead_cpu(unsigned int cpu)
-{
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp) {
- rcu_cleanup_dead_cpu(cpu, rsp);
- do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu));
- }
- return 0;
-}
-
-static DEFINE_PER_CPU(int, rcu_cpu_started);
/*
* Mark the specified CPU as being online so that subsequent grace periods
@@ -3739,74 +4125,46 @@
{
unsigned long flags;
unsigned long mask;
- int nbits;
- unsigned long oldmask;
struct rcu_data *rdp;
struct rcu_node *rnp;
- struct rcu_state *rsp;
+ bool newcpu;
- if (per_cpu(rcu_cpu_started, cpu))
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (rdp->cpu_started)
return;
+ rdp->cpu_started = true;
- per_cpu(rcu_cpu_started, cpu) = 1;
-
- for_each_rcu_flavor(rsp) {
- rdp = per_cpu_ptr(rsp->rda, cpu);
- rnp = rdp->mynode;
- mask = rdp->grpmask;
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rnp->qsmaskinitnext |= mask;
- oldmask = rnp->expmaskinitnext;
- rnp->expmaskinitnext |= mask;
- oldmask ^= rnp->expmaskinitnext;
- nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
- /* Allow lockless access for expedited grace periods. */
- smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
- rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
- rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
- rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
- if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
- /* Report QS -after- changing ->qsmaskinitnext! */
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
- } else {
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
- }
- smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function. We now remove it from the rcu_node tree's ->qsmaskinitnext
- * bit masks.
- */
-static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-{
- unsigned long flags;
- unsigned long mask;
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
-
- /* Remove outgoing CPU from mask in the leaf rcu_node structure. */
+ rnp = rdp->mynode;
mask = rdp->grpmask;
- spin_lock(&rsp->ofl_lock);
- raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
- rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
- rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
- if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
- /* Report quiescent state -before- changing ->qsmaskinitnext! */
- rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
+ newcpu = !(rnp->expmaskinitnext & mask);
+ rnp->expmaskinitnext |= mask;
+ /* Allow lockless access for expedited grace periods. */
+ smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */
+ ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus);
+ rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+ rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
+ rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
+ if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+ rcu_disable_urgency_upon_qs(rdp);
+ /* Report QS -after- changing ->qsmaskinitnext! */
+ rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
+ } else {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
- rnp->qsmaskinitnext &= ~mask;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- spin_unlock(&rsp->ofl_lock);
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(rnp->ofl_seq & 0x1);
+ smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
/*
* The outgoing function has no further need of RCU, so remove it from
- * the list of CPUs that RCU must track.
+ * the rcu_node tree's ->qsmaskinitnext bit masks.
*
* Note that this function is special in that it is invoked directly
* from the outgoing CPU rather than from the cpuhp_step mechanism.
@@ -3814,65 +4172,88 @@
*/
void rcu_report_dead(unsigned int cpu)
{
- struct rcu_state *rsp;
+ unsigned long flags;
+ unsigned long mask;
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
- /* QS for any half-done expedited RCU-sched GP. */
+ /* QS for any half-done expedited grace period. */
preempt_disable();
- rcu_report_exp_rdp(&rcu_sched_state,
- this_cpu_ptr(rcu_sched_state.rda), true);
+ rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
preempt_enable();
- for_each_rcu_flavor(rsp)
- rcu_cleanup_dying_idle_cpu(cpu, rsp);
+ rcu_preempt_deferred_qs(current);
- per_cpu(rcu_cpu_started, cpu) = 0;
+ /* Remove outgoing CPU from mask in the leaf rcu_node structure. */
+ mask = rdp->grpmask;
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+ raw_spin_lock(&rcu_state.ofl_lock);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+ rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
+ rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags);
+ if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
+ /* Report quiescent state -before- changing ->qsmaskinitnext! */
+ rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ }
+ WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ raw_spin_unlock(&rcu_state.ofl_lock);
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(rnp->ofl_seq & 0x1);
+
+ rdp->cpu_started = false;
}
-/* Migrate the dead CPU's callbacks to the current CPU. */
-static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The outgoing CPU has just passed through the dying-idle state, and we
+ * are being invoked from the CPU that was IPIed to continue the offline
+ * operation. Migrate the outgoing CPU's callbacks to the current CPU.
+ */
+void rcutree_migrate_callbacks(int cpu)
{
unsigned long flags;
struct rcu_data *my_rdp;
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+ struct rcu_node *my_rnp;
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
bool needwake;
- if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
+ if (rcu_segcblist_is_offloaded(&rdp->cblist) ||
+ rcu_segcblist_empty(&rdp->cblist))
return; /* No callbacks to migrate. */
local_irq_save(flags);
- my_rdp = this_cpu_ptr(rsp->rda);
- if (rcu_nocb_adopt_orphan_cbs(my_rdp, rdp, flags)) {
- local_irq_restore(flags);
- return;
- }
- raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+ my_rdp = this_cpu_ptr(&rcu_data);
+ my_rnp = my_rdp->mynode;
+ rcu_nocb_lock(my_rdp); /* irqs already disabled. */
+ WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies));
+ raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */
/* Leverage recent GPs and set GP for new callbacks. */
- needwake = rcu_advance_cbs(rsp, rnp_root, rdp) ||
- rcu_advance_cbs(rsp, rnp_root, my_rdp);
+ needwake = rcu_advance_cbs(my_rnp, rdp) ||
+ rcu_advance_cbs(my_rnp, my_rdp);
rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist);
+ needwake = needwake || rcu_advance_cbs(my_rnp, my_rdp);
+ rcu_segcblist_disable(&rdp->cblist);
WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
!rcu_segcblist_n_cbs(&my_rdp->cblist));
- raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags);
+ if (rcu_segcblist_is_offloaded(&my_rdp->cblist)) {
+ raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */
+ __call_rcu_nocb_wake(my_rdp, true, flags);
+ } else {
+ rcu_nocb_unlock(my_rdp); /* irqs remain disabled. */
+ raw_spin_unlock_irqrestore_rcu_node(my_rnp, flags);
+ }
if (needwake)
- rcu_gp_kthread_wake(rsp);
+ rcu_gp_kthread_wake();
+ lockdep_assert_irqs_enabled();
WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
!rcu_segcblist_empty(&rdp->cblist),
"rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
cpu, rcu_segcblist_n_cbs(&rdp->cblist),
rcu_segcblist_first_cb(&rdp->cblist));
-}
-
-/*
- * The outgoing CPU has just passed through the dying-idle state,
- * and we are being invoked from the CPU that was IPIed to continue the
- * offline operation. We need to migrate the outgoing CPU's callbacks.
- */
-void rcutree_migrate_callbacks(int cpu)
-{
- struct rcu_state *rsp;
-
- for_each_rcu_flavor(rsp)
- rcu_migrate_callbacks(cpu, rsp);
}
#endif
@@ -3886,13 +4267,11 @@
switch (action) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
- if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
- rcu_expedite_gp();
+ rcu_expedite_gp();
break;
case PM_POST_HIBERNATION:
case PM_POST_SUSPEND:
- if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
- rcu_unexpedite_gp();
+ rcu_unexpedite_gp();
break;
default:
break;
@@ -3901,14 +4280,13 @@
}
/*
- * Spawn the kthreads that handle each RCU flavor's grace periods.
+ * Spawn the kthreads that handle RCU's grace periods.
*/
static int __init rcu_spawn_gp_kthread(void)
{
unsigned long flags;
int kthread_prio_in = kthread_prio;
struct rcu_node *rnp;
- struct rcu_state *rsp;
struct sched_param sp;
struct task_struct *t;
@@ -3928,21 +4306,24 @@
kthread_prio, kthread_prio_in);
rcu_scheduler_fully_active = 1;
- for_each_rcu_flavor(rsp) {
- t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name);
- BUG_ON(IS_ERR(t));
- rnp = rcu_get_root(rsp);
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rsp->gp_kthread = t;
- if (kthread_prio) {
- sp.sched_priority = kthread_prio;
- sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
- }
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- wake_up_process(t);
+ t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name);
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__))
+ return 0;
+ if (kthread_prio) {
+ sp.sched_priority = kthread_prio;
+ sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
}
+ rnp = rcu_get_root();
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
+ WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+ // Reset .gp_activity and .gp_req_activity before setting .gp_kthread.
+ smp_store_release(&rcu_state.gp_kthread, t); /* ^^^ */
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ wake_up_process(t);
rcu_spawn_nocb_kthreads();
rcu_spawn_boost_kthreads();
+ rcu_spawn_core_kthreads();
return 0;
}
early_initcall(rcu_spawn_gp_kthread);
@@ -3967,9 +4348,9 @@
}
/*
- * Helper function for rcu_init() that initializes one rcu_state structure.
+ * Helper function for rcu_init() that initializes the rcu_state structure.
*/
-static void __init rcu_init_one(struct rcu_state *rsp)
+static void __init rcu_init_one(void)
{
static const char * const buf[] = RCU_NODE_NAME_INIT;
static const char * const fqs[] = RCU_FQS_NAME_INIT;
@@ -3991,14 +4372,15 @@
/* Initialize the level-tracking arrays. */
for (i = 1; i < rcu_num_lvls; i++)
- rsp->level[i] = rsp->level[i - 1] + num_rcu_lvl[i - 1];
+ rcu_state.level[i] =
+ rcu_state.level[i - 1] + num_rcu_lvl[i - 1];
rcu_init_levelspread(levelspread, num_rcu_lvl);
/* Initialize the elements themselves, starting from the leaves. */
for (i = rcu_num_lvls - 1; i >= 0; i--) {
cpustride *= levelspread[i];
- rnp = rsp->level[i];
+ rnp = rcu_state.level[i];
for (j = 0; j < num_rcu_lvl[i]; j++, rnp++) {
raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock));
lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock),
@@ -4006,9 +4388,9 @@
raw_spin_lock_init(&rnp->fqslock);
lockdep_set_class_and_name(&rnp->fqslock,
&rcu_fqs_class[i], fqs[i]);
- rnp->gp_seq = rsp->gp_seq;
- rnp->gp_seq_needed = rsp->gp_seq;
- rnp->completedqs = rsp->gp_seq;
+ rnp->gp_seq = rcu_state.gp_seq;
+ rnp->gp_seq_needed = rcu_state.gp_seq;
+ rnp->completedqs = rcu_state.gp_seq;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
rnp->grplo = j * cpustride;
@@ -4021,8 +4403,8 @@
rnp->parent = NULL;
} else {
rnp->grpnum = j % levelspread[i - 1];
- rnp->grpmask = 1UL << rnp->grpnum;
- rnp->parent = rsp->level[i - 1] +
+ rnp->grpmask = BIT(rnp->grpnum);
+ rnp->parent = rcu_state.level[i - 1] +
j / levelspread[i - 1];
}
rnp->level = i;
@@ -4036,16 +4418,15 @@
}
}
- init_swait_queue_head(&rsp->gp_wq);
- init_swait_queue_head(&rsp->expedited_wq);
- rnp = rcu_first_leaf_node(rsp);
+ init_swait_queue_head(&rcu_state.gp_wq);
+ init_swait_queue_head(&rcu_state.expedited_wq);
+ rnp = rcu_first_leaf_node();
for_each_possible_cpu(i) {
while (i > rnp->grphi)
rnp++;
- per_cpu_ptr(rsp->rda, i)->mynode = rnp;
- rcu_boot_init_percpu_data(i, rsp);
+ per_cpu_ptr(&rcu_data, i)->mynode = rnp;
+ rcu_boot_init_percpu_data(i);
}
- list_add(&rsp->flavors, &rcu_struct_flavors);
}
/*
@@ -4053,11 +4434,25 @@
* replace the definitions in tree.h because those are needed to size
* the ->node array in the rcu_state structure.
*/
-static void __init rcu_init_geometry(void)
+void rcu_init_geometry(void)
{
ulong d;
int i;
+ static unsigned long old_nr_cpu_ids;
int rcu_capacity[RCU_NUM_LVLS];
+ static bool initialized;
+
+ if (initialized) {
+ /*
+ * Warn if setup_nr_cpu_ids() had not yet been invoked,
+ * unless nr_cpus_ids == NR_CPUS, in which case who cares?
+ */
+ WARN_ON_ONCE(old_nr_cpu_ids != nr_cpu_ids);
+ return;
+ }
+
+ old_nr_cpu_ids = nr_cpu_ids;
+ initialized = true;
/*
* Initialize any unspecified boot parameters.
@@ -4071,6 +4466,7 @@
jiffies_till_first_fqs = d;
if (jiffies_till_next_fqs == ULONG_MAX)
jiffies_till_next_fqs = d;
+ adjust_jiffies_till_sched_qs();
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
@@ -4129,16 +4525,16 @@
/*
* Dump out the structure of the rcu_node combining tree associated
- * with the rcu_state structure referenced by rsp.
+ * with the rcu_state structure.
*/
-static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
+static void __init rcu_dump_rcu_node_tree(void)
{
int level = 0;
struct rcu_node *rnp;
pr_info("rcu_node tree layout dump\n");
pr_info(" ");
- rcu_for_each_node_breadth_first(rsp, rnp) {
+ rcu_for_each_node_breadth_first(rnp) {
if (rnp->level != level) {
pr_cont("\n");
pr_info(" ");
@@ -4152,20 +4548,41 @@
struct workqueue_struct *rcu_gp_wq;
struct workqueue_struct *rcu_par_gp_wq;
+static void __init kfree_rcu_batch_init(void)
+{
+ int cpu;
+ int i;
+
+ for_each_possible_cpu(cpu) {
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ for (i = 0; i < KFREE_N_BATCHES; i++) {
+ INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
+ krcp->krw_arr[i].krcp = krcp;
+ }
+
+ INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
+ INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
+ krcp->initialized = true;
+ }
+ if (register_shrinker(&kfree_rcu_shrinker))
+ pr_err("Failed to register kfree_rcu() shrinker!\n");
+}
+
void __init rcu_init(void)
{
int cpu;
rcu_early_boot_tests();
+ kfree_rcu_batch_init();
rcu_bootup_announce();
rcu_init_geometry();
- rcu_init_one(&rcu_bh_state);
- rcu_init_one(&rcu_sched_state);
+ rcu_init_one();
if (dump_tree)
- rcu_dump_rcu_node_tree(&rcu_sched_state);
- __rcu_init_preempt();
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+ rcu_dump_rcu_node_tree();
+ if (use_softirq)
+ open_softirq(RCU_SOFTIRQ, rcu_core_si);
/*
* We don't need protection against CPU-hotplug here because
@@ -4184,7 +4601,16 @@
WARN_ON(!rcu_gp_wq);
rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_par_gp_wq);
+ srcu_init();
+
+ /* Fill in default value for rcutree.qovld boot parameter. */
+ /* -After- the rcu_node ->lock fields are initialized! */
+ if (qovld < 0)
+ qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
+ else
+ qovld_calc = qovld;
}
+#include "tree_stall.h"
#include "tree_exp.h"
#include "tree_plugin.h"
--
Gitblit v1.6.2