xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'rcu-next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Browse Source 
Pull the latest RCU tree from Paul E. McKenney:

 - Additional cleanups after RCU flavor consolidation
 - Grace-period forward-progress cleanups and improvements
 - Documentation updates
 - Miscellaneous fixes
 - spin_is_locked() conversions to lockdep
 - SPDX changes to RCU source and header files
 - SRCU updates
 - Torture-test updates, including nolibc updates and moving
   nolibc to tools/include

Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar
2019-02-13 08:36:18 +01:00
parent aa0c38cf39 e7ffb4eb9a
commit cae45e1c6c
63 changed files with 1396 additions and 1269 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
kernel/locking/locktorture.c
View File

@@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* Module-based torture test facility for locking
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2014
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
* Davidlohr Bueso <dave@stgolabs.net>
* Based on kernel/rcu/torture.c.
*/
@@ -45,7 +32,7 @@
#include <linux/torture.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
torture_param(int, nwriters_stress, -1,
"Number of write-locking stress-test threads");
@@ -970,7 +957,7 @@ static int __init lock_torture_init(void)
/* Prepare torture context. */
if (onoff_interval > 0) {
firsterr = torture_onoff_init(onoff_holdoff * HZ,
onoff_interval * HZ);
onoff_interval * HZ, NULL);
if (firsterr)
goto unwind;
}

21
kernel/rcu/rcu.h
View File

@@ -1,23 +1,10 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update definitions shared among RCU implementations.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2011
*
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
* Author: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#ifndef __LINUX_RCU_H
@@ -30,7 +17,7 @@
#define RCU_TRACE(stmt)
#endif /* #else #ifdef CONFIG_RCU_TRACE */
/* Offset to allow for unmatched rcu_irq_{enter,exit}(). */
/* Offset to allow distinguishing irq vs. task-based idle entry/exit. */
#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1)
@@ -462,8 +449,6 @@ void rcu_request_urgent_qs_task(struct task_struct *t);
enum rcutorture_type {
RCU_FLAVOR,
RCU_BH_FLAVOR,
RCU_SCHED_FLAVOR,
RCU_TASKS_FLAVOR,
SRCU_FLAVOR,
INVALID_RCU_FLAVOR

17
kernel/rcu/rcu_segcblist.c
View File

@@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* RCU segmented callback lists, function definitions
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2017
*
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/types.h>

17
kernel/rcu/rcu_segcblist.h
View File

@@ -1,23 +1,10 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* RCU segmented callback lists, internal-to-rcu header file
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2017
*
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/rcu_segcblist.h>

27
kernel/rcu/rcuperf.c
View File

@@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update module-based performance-test facility
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2015
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#define pr_fmt(fmt) fmt
@@ -54,7 +41,7 @@
#include "rcu.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
#define PERF_FLAG "-perf:"
#define PERFOUT_STRING(s) \
@@ -83,13 +70,19 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
* Various other use cases may of course be specified.
*/
#ifdef MODULE
# define RCUPERF_SHUTDOWN 0
#else
# define RCUPERF_SHUTDOWN 1
#endif
torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
torture_param(int, nreaders, -1, "Number of RCU reader threads");
torture_param(int, nwriters, -1, "Number of RCU updater threads");
torture_param(bool, shutdown, !IS_ENABLED(MODULE),
torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
"Shutdown at end of performance tests.");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");

59
kernel/rcu/rcutorture.c
View File

@@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update module-based torture test facility
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2005, 2006
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
* Josh Triplett <josh@joshtriplett.org>
*
* See also: Documentation/RCU/torture.txt
@@ -61,7 +48,7 @@
#include "rcu.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
/* Bits for ->extendables field, extendables param, and related definitions. */
@@ -1630,21 +1617,34 @@ static bool rcu_fwd_emergency_stop;
#define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */
#define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */
#define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */
static long n_launders_hist[2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)];
struct rcu_launder_hist {
long n_launders;
unsigned long launder_gp_seq;
};
#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
static unsigned long rcu_launder_gp_seq_start;
static void rcu_torture_fwd_cb_hist(void)
{
unsigned long gps;
unsigned long gps_old;
int i;
int j;
for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
if (n_launders_hist[i] > 0)
if (n_launders_hist[i].n_launders > 0)
break;
pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
__func__, jiffies - rcu_fwd_startat);
for (j = 0; j <= i; j++)
pr_cont(" %ds/%d: %ld",
j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j]);
gps_old = rcu_launder_gp_seq_start;
for (j = 0; j <= i; j++) {
gps = n_launders_hist[j].launder_gp_seq;
pr_cont(" %ds/%d: %ld:%ld",
j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders,
rcutorture_seq_diff(gps, gps_old));
gps_old = gps;
}
pr_cont("\n");
}
@@ -1666,7 +1666,8 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
if (i >= ARRAY_SIZE(n_launders_hist))
i = ARRAY_SIZE(n_launders_hist) - 1;
n_launders_hist[i]++;
n_launders_hist[i].n_launders++;
n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
spin_unlock_irqrestore(&rcu_fwd_lock, flags);
}
@@ -1786,9 +1787,10 @@ static void rcu_torture_fwd_prog_cr(void)
n_max_cbs = 0;
n_max_gps = 0;
for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
n_launders_hist[i] = 0;
n_launders_hist[i].n_launders = 0;
cver = READ_ONCE(rcu_torture_current_version);
gps = cur_ops->get_gp_seq();
rcu_launder_gp_seq_start = gps;
while (time_before(jiffies, stopat) &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
rfcp = READ_ONCE(rcu_fwd_cb_head);
@@ -2228,6 +2230,14 @@ static void rcu_test_debug_objects(void)
#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
}
static void rcutorture_sync(void)
{
static unsigned long n;
if (cur_ops->sync && !(++n & 0xfff))
cur_ops->sync();
}
static int __init
rcu_torture_init(void)
{
@@ -2389,7 +2399,8 @@ rcu_torture_init(void)
firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
if (firsterr)
goto unwind;
firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval,
rcutorture_sync);
if (firsterr)
goto unwind;
firsterr = rcu_torture_stall_init();

17
kernel/rcu/srcutiny.c
View File

@@ -1,24 +1,11 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion,
* tiny version for non-preemptible single-CPU use.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2017
*
* Author: Paul McKenney <paulmck@us.ibm.com>
* Author: Paul McKenney <paulmck@linux.ibm.com>
*/
#include <linux/export.h>

74
kernel/rcu/srcutree.c
View File

@@ -1,24 +1,11 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* Sleepable 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.
*
* Copyright (C) IBM Corporation, 2006
* Copyright (C) Fujitsu, 2012
*
* Author: Paul McKenney <paulmck@us.ibm.com>
* Author: Paul McKenney <paulmck@linux.ibm.com>
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
@@ -58,6 +45,7 @@ static bool __read_mostly srcu_init_done;
static void srcu_invoke_callbacks(struct work_struct *work);
static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
static void process_srcu(struct work_struct *work);
static void srcu_delay_timer(struct timer_list *t);
/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
#define spin_lock_rcu_node(p) \
@@ -156,7 +144,8 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp, bool is_static)
snp->grphi = cpu;
}
sdp->cpu = cpu;
INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
INIT_WORK(&sdp->work, srcu_invoke_callbacks);
timer_setup(&sdp->delay_work, srcu_delay_timer, 0);
sdp->ssp = ssp;
sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
if (is_static)
@@ -386,13 +375,19 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
} else {
flush_delayed_work(&ssp->work);
}
for_each_possible_cpu(cpu)
for_each_possible_cpu(cpu) {
struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
if (quiesced) {
if (WARN_ON(delayed_work_pending(&per_cpu_ptr(ssp->sda, cpu)->work)))
if (WARN_ON(timer_pending(&sdp->delay_work)))
return; /* Just leak it! */
if (WARN_ON(work_pending(&sdp->work)))
return; /* Just leak it! */
} else {
flush_delayed_work(&per_cpu_ptr(ssp->sda, cpu)->work);
del_timer_sync(&sdp->delay_work);
flush_work(&sdp->work);
}
}
if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(ssp))) {
pr_info("%s: Active srcu_struct %p state: %d\n",
@@ -463,39 +458,23 @@ static void srcu_gp_start(struct srcu_struct *ssp)
WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}
/*
* Track online CPUs to guide callback workqueue placement.
*/
DEFINE_PER_CPU(bool, srcu_online);
void srcu_online_cpu(unsigned int cpu)
static void srcu_delay_timer(struct timer_list *t)
{
WRITE_ONCE(per_cpu(srcu_online, cpu), true);
struct srcu_data *sdp = container_of(t, struct srcu_data, delay_work);
queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
}
void srcu_offline_cpu(unsigned int cpu)
{
WRITE_ONCE(per_cpu(srcu_online, cpu), false);
}
/*
* Place the workqueue handler on the specified CPU if online, otherwise
* just run it whereever. This is useful for placing workqueue handlers
* that are to invoke the specified CPU's callbacks.
*/
static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork,
static void srcu_queue_delayed_work_on(struct srcu_data *sdp,
unsigned long delay)
{
bool ret;
if (!delay) {
queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
return;
}
preempt_disable();
if (READ_ONCE(per_cpu(srcu_online, cpu)))
ret = queue_delayed_work_on(cpu, wq, dwork, delay);
else
ret = queue_delayed_work(wq, dwork, delay);
preempt_enable();
return ret;
timer_reduce(&sdp->delay_work, jiffies + delay);
}
/*
@@ -504,7 +483,7 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
*/
static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
{
srcu_queue_delayed_work_on(sdp->cpu, rcu_gp_wq, &sdp->work, delay);
srcu_queue_delayed_work_on(sdp, delay);
}
/*
@@ -1186,7 +1165,8 @@ static void srcu_invoke_callbacks(struct work_struct *work)
struct srcu_data *sdp;
struct srcu_struct *ssp;
sdp = container_of(work, struct srcu_data, work.work);
sdp = container_of(work, struct srcu_data, work);
ssp = sdp->ssp;
rcu_cblist_init(&ready_cbs);
spin_lock_irq_rcu_node(sdp);

15
kernel/rcu/sync.c
View File

@@ -1,20 +1,7 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* RCU-based infrastructure for lightweight reader-writer locking
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (c) 2015, Red Hat, Inc.
*
* Author: Oleg Nesterov <oleg@redhat.com>

19
kernel/rcu/tiny.c
View File

@@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
* Author: Paul E. McKenney <paulmck@linux.ibm.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
@@ -76,7 +63,7 @@ void rcu_qs(void)
* be called from hardirq context. It is normally called from the
* scheduling-clock interrupt.
*/
void rcu_check_callbacks(int user)
void rcu_sched_clock_irq(int user)
{
if (user) {
rcu_qs();

267
kernel/rcu/tree.c
View File

@@ -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.
*
* 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> Hierarchical version
*
* 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 -
@@ -62,6 +49,7 @@
#include <linux/suspend.h>
#include <linux/ftrace.h>
#include <linux/tick.h>
#include <linux/sysrq.h>
#include "tree.h"
#include "rcu.h"
@@ -115,6 +103,9 @@ 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;
/* Commandeer a sysrq key to dump RCU's tree. */
static bool sysrq_rcu;
module_param(sysrq_rcu, bool, 0444);
/*
* The rcu_scheduler_active variable is initialized to the value
@@ -479,7 +470,6 @@ module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next
module_param(rcu_kick_kthreads, bool, 0644);
static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
static void force_quiescent_state(void);
static int rcu_pending(void);
/*
@@ -504,13 +494,12 @@ unsigned long rcu_exp_batches_completed(void)
EXPORT_SYMBOL_GPL(rcu_exp_batches_completed);
/*
* Force a quiescent state.
* Return the root node of the rcu_state structure.
*/
void rcu_force_quiescent_state(void)
static struct rcu_node *rcu_get_root(void)
{
force_quiescent_state();
return &rcu_state.node[0];
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
* Convert a ->gp_state value to a character string.
@@ -529,19 +518,30 @@ void show_rcu_gp_kthreads(void)
{
int cpu;
unsigned long j;
unsigned long ja;
unsigned long jr;
unsigned long jw;
struct rcu_data *rdp;
struct rcu_node *rnp;
j = jiffies - READ_ONCE(rcu_state.gp_activity);
pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n",
j = jiffies;
ja = j - READ_ONCE(rcu_state.gp_activity);
jr = j - READ_ONCE(rcu_state.gp_req_activity);
jw = j - READ_ONCE(rcu_state.gp_wake_time);
pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
rcu_state.gp_state, rcu_state.gp_kthread->state, j);
rcu_state.gp_state,
rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
(long)READ_ONCE(rcu_state.gp_seq),
(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
READ_ONCE(rcu_state.gp_flags));
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(rcu_state.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);
pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
(long)rnp->gp_seq_needed);
if (!rcu_is_leaf_node(rnp))
continue;
for_each_leaf_node_possible_cpu(rnp, cpu) {
@@ -550,14 +550,35 @@ void show_rcu_gp_kthreads(void)
ULONG_CMP_GE(rcu_state.gp_seq,
rdp->gp_seq_needed))
continue;
pr_info("\tcpu %d ->gp_seq_needed %lu\n",
cpu, rdp->gp_seq_needed);
pr_info("\tcpu %d ->gp_seq_needed %ld\n",
cpu, (long)rdp->gp_seq_needed);
}
}
/* sched_show_task(rcu_state.gp_kthread); */
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
/* Dump grace-period-request information due to commandeered sysrq. */
static void sysrq_show_rcu(int key)
{
show_rcu_gp_kthreads();
}
static struct sysrq_key_op sysrq_rcudump_op = {
.handler = sysrq_show_rcu,
.help_msg = "show-rcu(y)",
.action_msg = "Show RCU tree",
.enable_mask = SYSRQ_ENABLE_DUMP,
};
static int __init rcu_sysrq_init(void)
{
if (sysrq_rcu)
return register_sysrq_key('y', &sysrq_rcudump_op);
return 0;
}
early_initcall(rcu_sysrq_init);
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
@@ -566,8 +587,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
{
switch (test_type) {
case RCU_FLAVOR:
case RCU_BH_FLAVOR:
case RCU_SCHED_FLAVOR:
*flags = READ_ONCE(rcu_state.gp_flags);
*gp_seq = rcu_seq_current(&rcu_state.gp_seq);
break;
@@ -577,14 +596,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
/*
* Return the root node of the rcu_state structure.
*/
static struct rcu_node *rcu_get_root(void)
{
return &rcu_state.node[0];
}
/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
@@ -701,7 +712,6 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
/**
* rcu_nmi_exit - inform RCU of exit from NMI context
* @irq: Is this call from rcu_irq_exit?
*
* If you add or remove a call to rcu_nmi_exit(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
@@ -1115,7 +1125,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
}
/*
* NO_HZ_FULL CPUs can run in-kernel without rcu_check_callbacks!
* 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
@@ -1181,7 +1191,7 @@ static void rcu_check_gp_kthread_starvation(void)
pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
rcu_state.name, j,
(long)rcu_seq_current(&rcu_state.gp_seq),
rcu_state.gp_flags,
READ_ONCE(rcu_state.gp_flags),
gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
if (gpk) {
@@ -1310,7 +1320,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
panic_on_rcu_stall();
force_quiescent_state(); /* Kick them all. */
rcu_force_quiescent_state(); /* Kick them all. */
}
static void print_cpu_stall(void)
@@ -1557,17 +1567,28 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
}
/*
* Awaken the grace-period kthread. Don't do a self-awaken, 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.
* 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.
*
* 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
* been interrupted just as it was going to sleep, and just after the final
* 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(void)
{
if (current == rcu_state.gp_kthread ||
if ((current == rcu_state.gp_kthread &&
!in_interrupt() && !in_serving_softirq()) ||
!READ_ONCE(rcu_state.gp_flags) ||
!rcu_state.gp_kthread)
return;
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);
}
@@ -1711,7 +1732,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
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)
if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
rdp->gp_seq_needed = rnp->gp_seq_needed;
WRITE_ONCE(rdp->gpwrap, false);
rcu_gpnum_ovf(rnp, rdp);
@@ -1939,7 +1960,7 @@ static void rcu_gp_fqs_loop(void)
if (!ret) {
rcu_state.jiffies_force_qs = jiffies + j;
WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
jiffies + 3 * j);
jiffies + (j ? 3 * j : 2));
}
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
@@ -2497,14 +2518,14 @@ static void rcu_do_batch(struct rcu_data *rdp)
}
/*
* 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"));
raw_cpu_inc(rcu_data.ticks_this_gp);
@@ -2517,7 +2538,7 @@ void rcu_check_callbacks(int user)
}
__this_cpu_write(rcu_data.rcu_urgent_qs, false);
}
rcu_flavor_check_callbacks(user);
rcu_flavor_sched_clock_irq(user);
if (rcu_pending())
invoke_rcu_core();
@@ -2578,7 +2599,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
* Force quiescent states on reluctant CPUs, and also detect which
* CPUs are in dyntick-idle mode.
*/
static void force_quiescent_state(void)
void rcu_force_quiescent_state(void)
{
unsigned long flags;
bool ret;
@@ -2610,6 +2631,7 @@ static void force_quiescent_state(void)
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
rcu_gp_kthread_wake();
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
* This function checks for grace-period requests that fail to motivate
@@ -2657,16 +2679,11 @@ rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
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(rcu_state.gp_seq),
(long)READ_ONCE(rnp_root->gp_seq_needed),
j - rcu_state.gp_req_activity, j - rcu_state.gp_activity,
rcu_state.gp_flags, rcu_state.gp_state, rcu_state.name,
rcu_state.gp_kthread ? rcu_state.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);
show_rcu_gp_kthreads();
}
/*
@@ -2711,12 +2728,8 @@ void rcu_fwd_progress_check(unsigned long j)
}
EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
/*
* This does the RCU core processing work for the specified rcu_data
* structures. This may be called only from the CPU to whom the rdp
* belongs.
*/
static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(struct softirq_action *unused)
{
unsigned long flags;
struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
@@ -2801,9 +2814,9 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
/*
* 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) >
@@ -2820,7 +2833,7 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
rdp->blimit = LONG_MAX;
if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
force_quiescent_state();
rcu_force_quiescent_state();
rdp->n_force_qs_snap = rcu_state.n_force_qs;
rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
@@ -2889,9 +2902,6 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
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(rcu_state.name, head,
(unsigned long)func,
@@ -2961,6 +2971,79 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
}
EXPORT_SYMBOL_GPL(kfree_call_rcu);
/*
* During early boot, any blocking grace-period wait automatically
* implies a grace period. Later on, this is never the case for PREEMPT.
*
* Howevr, because a context switch is a grace period for !PREEMPT, 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.
*/
static int rcu_blocking_is_gp(void)
{
int ret;
if (IS_ENABLED(CONFIG_PREEMPT))
return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
might_sleep(); /* Check for RCU read-side critical section. */
preempt_disable();
ret = num_online_cpus() <= 1;
preempt_enable();
return ret;
}
/**
* synchronize_rcu - wait until a grace period has elapsed.
*
* 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_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_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_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_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_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_rcu() in RCU read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/**
* get_state_synchronize_rcu - Snapshot current RCU state
*
@@ -3048,28 +3131,6 @@ static int rcu_pending(void)
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;
rdp = this_cpu_ptr(&rcu_data);
if (!rcu_segcblist_empty(&rdp->cblist)) {
hc = true;
if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist))
al = false;
}
if (all_lazy)
*all_lazy = al;
return hc;
}
/*
* Helper function for rcu_barrier() tracing. If tracing is disabled,
* the compiler is expected to optimize this away.
@@ -3299,7 +3360,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_prepare_kthreads(cpu);
rcu_spawn_all_nocb_kthreads(cpu);
rcu_spawn_cpu_nocb_kthread(cpu);
return 0;
}
@@ -3329,8 +3390,6 @@ int rcutree_online_cpu(unsigned int cpu)
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);
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return 0; /* Too early in boot for scheduler work. */
sync_sched_exp_online_cleanup(cpu);
@@ -3355,8 +3414,6 @@ int rcutree_offline_cpu(unsigned int cpu)
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcutree_affinity_setting(cpu, cpu);
if (IS_ENABLED(CONFIG_TREE_SRCU))
srcu_offline_cpu(cpu);
return 0;
}
@@ -3777,7 +3834,7 @@ void __init rcu_init(void)
rcu_init_one();
if (dump_tree)
rcu_dump_rcu_node_tree();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
open_softirq(RCU_SOFTIRQ, rcu_core);
/*
* We don't need protection against CPU-hotplug here because

53
kernel/rcu/tree.h
View File

@@ -1,25 +1,12 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
* Author: Ingo Molnar <mingo@elte.hu>
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
* Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/cache.h>
@@ -36,7 +23,6 @@
/* Communicate arguments to a workqueue handler. */
struct rcu_exp_work {
smp_call_func_t rew_func;
unsigned long rew_s;
struct work_struct rew_work;
};
@@ -194,10 +180,7 @@ struct rcu_data {
bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */
bool rcu_urgent_qs; /* GP old need light quiescent state. */
#ifdef CONFIG_RCU_FAST_NO_HZ
bool all_lazy; /* Are all CPU's CBs lazy? */
unsigned long nonlazy_posted; /* # times non-lazy CB posted to CPU. */
unsigned long nonlazy_posted_snap;
/* Nonlazy_posted snapshot. */
bool all_lazy; /* All CPU's CBs lazy at idle start? */
unsigned long last_accelerate; /* Last jiffy CBs were accelerated. */
unsigned long last_advance_all; /* Last jiffy CBs were all advanced. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
@@ -234,7 +217,13 @@ struct rcu_data {
/* Leader CPU takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/* 6) Diagnostic data, including RCU CPU stall warnings. */
/* 6) RCU priority boosting. */
struct task_struct *rcu_cpu_kthread_task;
/* rcuc per-CPU kthread or NULL. */
unsigned int rcu_cpu_kthread_status;
char rcu_cpu_has_work;
/* 7) Diagnostic data, including RCU CPU stall warnings. */
unsigned int softirq_snap; /* Snapshot of softirq activity. */
/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
struct irq_work rcu_iw; /* Check for non-irq activity. */
@@ -303,6 +292,8 @@ struct rcu_state {
struct swait_queue_head gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
short gp_state; /* GP kthread sleep state. */
unsigned long gp_wake_time; /* Last GP kthread wake. */
unsigned long gp_wake_seq; /* ->gp_seq at ^^^. */
/* End of fields guarded by root rcu_node's lock. */
@@ -402,13 +393,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
int rcu_dynticks_snap(struct rcu_data *rdp);
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DECLARE_PER_CPU(char, rcu_cpu_has_work);
#endif /* #ifdef CONFIG_RCU_BOOST */
/* Forward declarations for rcutree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_qs(void);
@@ -420,7 +404,7 @@ static void rcu_print_detail_task_stall(void);
static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
static void rcu_flavor_check_callbacks(int user);
static void rcu_flavor_sched_clock_irq(int user);
void call_rcu(struct rcu_head *head, rcu_callback_t func);
static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
@@ -431,7 +415,6 @@ static void __init rcu_spawn_boost_kthreads(void);
static void rcu_prepare_kthreads(int cpu);
static void rcu_cleanup_after_idle(void);
static void rcu_prepare_for_idle(void);
static void rcu_idle_count_callbacks_posted(void);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
static void rcu_preempt_deferred_qs(struct task_struct *t);
@@ -451,7 +434,7 @@ static bool rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_all_nocb_kthreads(int cpu);
static void rcu_spawn_cpu_nocb_kthread(int cpu);
static void __init rcu_spawn_nocb_kthreads(void);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(void);
@@ -462,11 +445,3 @@ static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
#ifdef CONFIG_SRCU
void srcu_online_cpu(unsigned int cpu);
void srcu_offline_cpu(unsigned int cpu);
#else /* #ifdef CONFIG_SRCU */
void srcu_online_cpu(unsigned int cpu) { }
void srcu_offline_cpu(unsigned int cpu) { }
#endif /* #else #ifdef CONFIG_SRCU */

201
kernel/rcu/tree_exp.h
View File

@@ -1,27 +1,16 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* RCU expedited grace periods
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2016
*
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/lockdep.h>
static void rcu_exp_handler(void *unused);
/*
* Record the start of an expedited grace period.
*/
@@ -344,7 +333,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
{
int cpu;
unsigned long flags;
smp_call_func_t func;
unsigned long mask_ofl_test;
unsigned long mask_ofl_ipi;
int ret;
@@ -352,7 +340,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
container_of(wp, struct rcu_exp_work, rew_work);
struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
func = rewp->rew_func;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
/* Each pass checks a CPU for identity, offline, and idle. */
@@ -396,7 +383,7 @@ retry_ipi:
mask_ofl_test |= mask;
continue;
}
ret = smp_call_function_single(cpu, func, NULL, 0);
ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
if (!ret) {
mask_ofl_ipi &= ~mask;
continue;
@@ -426,7 +413,7 @@ retry_ipi:
* Select the nodes that the upcoming expedited grace period needs
* to wait for.
*/
static void sync_rcu_exp_select_cpus(smp_call_func_t func)
static void sync_rcu_exp_select_cpus(void)
{
int cpu;
struct rcu_node *rnp;
@@ -440,7 +427,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
rnp->exp_need_flush = false;
if (!READ_ONCE(rnp->expmask))
continue; /* Avoid early boot non-existent wq. */
rnp->rew.rew_func = func;
if (!READ_ONCE(rcu_par_gp_wq) ||
rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
rcu_is_last_leaf_node(rnp)) {
@@ -449,7 +435,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
continue;
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
preempt_disable();
cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
/* If all offline, queue the work on an unbound CPU. */
if (unlikely(cpu > rnp->grphi - rnp->grplo))
@@ -457,7 +442,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
else
cpu += rnp->grplo;
queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
preempt_enable();
rnp->exp_need_flush = true;
}
@@ -580,10 +564,10 @@ static void rcu_exp_wait_wake(unsigned long s)
* Common code to drive an expedited grace period forward, used by
* workqueues and mid-boot-time tasks.
*/
static void rcu_exp_sel_wait_wake(smp_call_func_t func, unsigned long s)
static void rcu_exp_sel_wait_wake(unsigned long s)
{
/* Initialize the rcu_node tree in preparation for the wait. */
sync_rcu_exp_select_cpus(func);
sync_rcu_exp_select_cpus();
/* Wait and clean up, including waking everyone. */
rcu_exp_wait_wake(s);
@@ -597,52 +581,7 @@ static void wait_rcu_exp_gp(struct work_struct *wp)
struct rcu_exp_work *rewp;
rewp = container_of(wp, struct rcu_exp_work, rew_work);
rcu_exp_sel_wait_wake(rewp->rew_func, rewp->rew_s);
}
/*
* Given a smp_call_function() handler, kick off the specified
* implementation of expedited grace period.
*/
static void _synchronize_rcu_expedited(smp_call_func_t func)
{
struct rcu_data *rdp;
struct rcu_exp_work rew;
struct rcu_node *rnp;
unsigned long s;
/* If expedited grace periods are prohibited, fall back to normal. */
if (rcu_gp_is_normal()) {
wait_rcu_gp(call_rcu);
return;
}
/* Take a snapshot of the sequence number. */
s = rcu_exp_gp_seq_snap();
if (exp_funnel_lock(s))
return; /* Someone else did our work for us. */
/* Ensure that load happens before action based on it. */
if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
/* Direct call during scheduler init and early_initcalls(). */
rcu_exp_sel_wait_wake(func, s);
} else {
/* Marshall arguments & schedule the expedited grace period. */
rew.rew_func = func;
rew.rew_s = s;
INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
queue_work(rcu_gp_wq, &rew.rew_work);
}
/* Wait for expedited grace period to complete. */
rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
rnp = rcu_get_root();
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(s));
smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
mutex_unlock(&rcu_state.exp_mutex);
rcu_exp_sel_wait_wake(rewp->rew_s);
}
#ifdef CONFIG_PREEMPT_RCU
@@ -654,7 +593,7 @@ static void _synchronize_rcu_expedited(smp_call_func_t func)
* ->expmask fields in the rcu_node tree. Otherwise, immediately
* report the quiescent state.
*/
static void sync_rcu_exp_handler(void *unused)
static void rcu_exp_handler(void *unused)
{
unsigned long flags;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -697,6 +636,7 @@ static void sync_rcu_exp_handler(void *unused)
WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
/*
@@ -730,43 +670,10 @@ static void sync_sched_exp_online_cleanup(int cpu)
{
}
/**
* synchronize_rcu_expedited - Brute-force RCU grace period
*
* Wait for an RCU-preempt grace period, but expedite it. The basic
* idea is to IPI all non-idle non-nohz online CPUs. The IPI handler
* checks whether the CPU is in an RCU-preempt critical section, and
* if so, it sets a flag that causes the outermost rcu_read_unlock()
* to report the quiescent state. On the other hand, if the CPU is
* not in an RCU read-side critical section, the IPI handler reports
* the quiescent state immediately.
*
* Although this is a greate improvement over previous expedited
* implementations, it is still unfriendly to real-time workloads, so is
* thus not recommended for any sort of common-case code. In fact, if
* you are using synchronize_rcu_expedited() in a loop, please restructure
* your code to batch your updates, and then Use a single synchronize_rcu()
* instead.
*
* This has the same semantics as (but is more brutal than) synchronize_rcu().
*/
void synchronize_rcu_expedited(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_expedited() in RCU read-side critical section");
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return;
_synchronize_rcu_expedited(sync_rcu_exp_handler);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#else /* #ifdef CONFIG_PREEMPT_RCU */
/* Invoked on each online non-idle CPU for expedited quiescent state. */
static void sync_sched_exp_handler(void *unused)
static void rcu_exp_handler(void *unused)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
@@ -798,44 +705,78 @@ static void sync_sched_exp_online_cleanup(int cpu)
rnp = rdp->mynode;
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
return;
ret = smp_call_function_single(cpu, sync_sched_exp_handler, NULL, 0);
ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
WARN_ON_ONCE(ret);
}
/*
* Because a context switch is a grace period for !PREEMPT, 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.
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
/**
* synchronize_rcu_expedited - Brute-force RCU grace period
*
* Wait for an RCU grace period, but expedite it. The basic idea is to
* IPI all non-idle non-nohz online CPUs. The IPI handler checks whether
* the CPU is in an RCU critical section, and if so, it sets a flag that
* causes the outermost rcu_read_unlock() to report the quiescent state
* for RCU-preempt or asks the scheduler for help for RCU-sched. On the
* other hand, if the CPU is not in an RCU read-side critical section,
* the IPI handler reports the quiescent state immediately.
*
* Although this is a greate improvement over previous expedited
* implementations, it is still unfriendly to real-time workloads, so is
* thus not recommended for any sort of common-case code. In fact, if
* you are using synchronize_rcu_expedited() in a loop, please restructure
* your code to batch your updates, and then Use a single synchronize_rcu()
* instead.
*
* This has the same semantics as (but is more brutal than) synchronize_rcu().
*/
static int rcu_blocking_is_gp(void)
{
int ret;
might_sleep(); /* Check for RCU read-side critical section. */
preempt_disable();
ret = num_online_cpus() <= 1;
preempt_enable();
return ret;
}
/* PREEMPT=n implementation of synchronize_rcu_expedited(). */
void synchronize_rcu_expedited(void)
{
struct rcu_data *rdp;
struct rcu_exp_work rew;
struct rcu_node *rnp;
unsigned long s;
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_expedited() in RCU read-side critical section");
/* If only one CPU, this is automatically a grace period. */
/* Is the state is such that the call is a grace period? */
if (rcu_blocking_is_gp())
return;
_synchronize_rcu_expedited(sync_sched_exp_handler);
/* If expedited grace periods are prohibited, fall back to normal. */
if (rcu_gp_is_normal()) {
wait_rcu_gp(call_rcu);
return;
}
/* Take a snapshot of the sequence number. */
s = rcu_exp_gp_seq_snap();
if (exp_funnel_lock(s))
return; /* Someone else did our work for us. */
/* Ensure that load happens before action based on it. */
if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
/* Direct call during scheduler init and early_initcalls(). */
rcu_exp_sel_wait_wake(s);
} else {
/* Marshall arguments & schedule the expedited grace period. */
rew.rew_s = s;
INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
queue_work(rcu_gp_wq, &rew.rew_work);
}
/* Wait for expedited grace period to complete. */
rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
rnp = rcu_get_root();
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(s));
smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
mutex_unlock(&rcu_state.exp_mutex);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */

238
kernel/rcu/tree_plugin.h
View File

@@ -1,27 +1,14 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions that provide either classic
* or preemptible semantics.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright Red Hat, 2009
* Copyright IBM Corporation, 2009
*
* Author: Ingo Molnar <mingo@elte.hu>
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
* Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/delay.h>
@@ -34,17 +21,7 @@
#include "../time/tick-internal.h"
#ifdef CONFIG_RCU_BOOST
#include "../locking/rtmutex_common.h"
/*
* Control variables for per-CPU and per-rcu_node kthreads.
*/
static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DEFINE_PER_CPU(char, rcu_cpu_has_work);
#else /* #ifdef CONFIG_RCU_BOOST */
/*
@@ -307,7 +284,7 @@ static void rcu_qs(void)
__this_cpu_read(rcu_data.gp_seq),
TPS("cpuqs"));
__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
barrier(); /* Coordinate with rcu_flavor_check_callbacks(). */
barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */
current->rcu_read_unlock_special.b.need_qs = false;
}
}
@@ -788,13 +765,13 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
}
/*
* Check for a quiescent state from the current CPU. When a task blocks,
* the task is recorded in the corresponding CPU's rcu_node structure,
* which is checked elsewhere.
*
* Caller must disable hard irqs.
* Check for a quiescent state from the current CPU, including voluntary
* context switches for Tasks RCU. When a task blocks, the task is
* recorded in the corresponding CPU's rcu_node structure, which is checked
* elsewhere, hence this function need only check for quiescent states
* related to the current CPU, not to those related to tasks.
*/
static void rcu_flavor_check_callbacks(int user)
static void rcu_flavor_sched_clock_irq(int user)
{
struct task_struct *t = current;
@@ -825,54 +802,6 @@ static void rcu_flavor_check_callbacks(int user)
t->rcu_read_unlock_special.b.need_qs = true;
}
/**
* synchronize_rcu - wait until a grace period has elapsed.
*
* 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_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_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_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_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_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_rcu() in RCU read-side critical section");
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return;
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/*
* Check for a task exiting while in a preemptible-RCU read-side
* critical section, clean up if so. No need to issue warnings,
@@ -1088,14 +1017,10 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
}
/*
* 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.
* Check to see if this CPU is in a non-context-switch quiescent state,
* namely user mode and idle loop.
*/
static void rcu_flavor_check_callbacks(int user)
static void rcu_flavor_sched_clock_irq(int user)
{
if (user || rcu_is_cpu_rrupt_from_idle()) {
@@ -1115,22 +1040,6 @@ static void rcu_flavor_check_callbacks(int user)
}
}
/* PREEMPT=n implementation of synchronize_rcu(). */
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_rcu() in RCU read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/*
* Because preemptible RCU does not exist, tasks cannot possibly exit
* while in preemptible RCU read-side critical sections.
@@ -1307,11 +1216,11 @@ static void invoke_rcu_callbacks_kthread(void)
unsigned long flags;
local_irq_save(flags);
__this_cpu_write(rcu_cpu_has_work, 1);
if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
current != __this_cpu_read(rcu_cpu_kthread_task)) {
rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task),
__this_cpu_read(rcu_cpu_kthread_status));
__this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
if (__this_cpu_read(rcu_data.rcu_cpu_kthread_task) != NULL &&
current != __this_cpu_read(rcu_data.rcu_cpu_kthread_task)) {
rcu_wake_cond(__this_cpu_read(rcu_data.rcu_cpu_kthread_task),
__this_cpu_read(rcu_data.rcu_cpu_kthread_status));
}
local_irq_restore(flags);
}
@@ -1322,7 +1231,7 @@ static void invoke_rcu_callbacks_kthread(void)
*/
static bool rcu_is_callbacks_kthread(void)
{
return __this_cpu_read(rcu_cpu_kthread_task) == current;
return __this_cpu_read(rcu_data.rcu_cpu_kthread_task) == current;
}
#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
@@ -1369,11 +1278,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
return 0;
}
static void rcu_kthread_do_work(void)
{
rcu_do_batch(this_cpu_ptr(&rcu_data));
}
static void rcu_cpu_kthread_setup(unsigned int cpu)
{
struct sched_param sp;
@@ -1384,12 +1288,12 @@ static void rcu_cpu_kthread_setup(unsigned int cpu)
static void rcu_cpu_kthread_park(unsigned int cpu)
{
per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
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_cpu_has_work);
return __this_cpu_read(rcu_data.rcu_cpu_has_work);
}
/*
@@ -1399,21 +1303,20 @@ static int rcu_cpu_kthread_should_run(unsigned int cpu)
*/
static void rcu_cpu_kthread(unsigned int cpu)
{
unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
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;
for (spincnt = 0; spincnt < 10; spincnt++) {
trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
local_bh_disable();
*statusp = RCU_KTHREAD_RUNNING;
this_cpu_inc(rcu_cpu_kthread_loops);
local_irq_disable();
work = *workp;
*workp = 0;
local_irq_enable();
if (work)
rcu_kthread_do_work();
rcu_do_batch(this_cpu_ptr(&rcu_data));
local_bh_enable();
if (*workp == 0) {
trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
@@ -1459,7 +1362,7 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
}
static struct smp_hotplug_thread rcu_cpu_thread_spec = {
.store = &rcu_cpu_kthread_task,
.store = &rcu_data.rcu_cpu_kthread_task,
.thread_should_run = rcu_cpu_kthread_should_run,
.thread_fn = rcu_cpu_kthread,
.thread_comm = "rcuc/%u",
@@ -1476,7 +1379,7 @@ static void __init rcu_spawn_boost_kthreads(void)
int cpu;
for_each_possible_cpu(cpu)
per_cpu(rcu_cpu_has_work, cpu) = 0;
per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__))
return;
rcu_for_each_leaf_node(rnp)
@@ -1543,7 +1446,7 @@ static void rcu_prepare_kthreads(int cpu)
int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
*nextevt = KTIME_MAX;
return rcu_cpu_has_callbacks(NULL);
return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist);
}
/*
@@ -1562,14 +1465,6 @@ static void rcu_prepare_for_idle(void)
{
}
/*
* Don't bother keeping a running count of the number of RCU callbacks
* posted because CONFIG_RCU_FAST_NO_HZ=n.
*/
static void rcu_idle_count_callbacks_posted(void)
{
}
#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
/*
@@ -1652,11 +1547,8 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
lockdep_assert_irqs_disabled();
/* Snapshot to detect later posting of non-lazy callback. */
rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
/* If no callbacks, RCU doesn't need the CPU. */
if (!rcu_cpu_has_callbacks(&rdp->all_lazy)) {
if (rcu_segcblist_empty(&rdp->cblist)) {
*nextevt = KTIME_MAX;
return 0;
}
@@ -1670,11 +1562,12 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
rdp->last_accelerate = jiffies;
/* Request timer delay depending on laziness, and round. */
if (!rdp->all_lazy) {
rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist);
if (rdp->all_lazy) {
dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
} else {
dj = round_up(rcu_idle_gp_delay + jiffies,
rcu_idle_gp_delay) - jiffies;
} else {
dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
}
*nextevt = basemono + dj * TICK_NSEC;
return 0;
@@ -1704,7 +1597,7 @@ static void rcu_prepare_for_idle(void)
/* Handle nohz enablement switches conservatively. */
tne = READ_ONCE(tick_nohz_active);
if (tne != rdp->tick_nohz_enabled_snap) {
if (rcu_cpu_has_callbacks(NULL))
if (!rcu_segcblist_empty(&rdp->cblist))
invoke_rcu_core(); /* force nohz to see update. */
rdp->tick_nohz_enabled_snap = tne;
return;
@@ -1717,10 +1610,8 @@ static void rcu_prepare_for_idle(void)
* callbacks, invoke RCU core for the side-effect of recalculating
* idle duration on re-entry to idle.
*/
if (rdp->all_lazy &&
rdp->nonlazy_posted != rdp->nonlazy_posted_snap) {
if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) {
rdp->all_lazy = false;
rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
invoke_rcu_core();
return;
}
@@ -1756,19 +1647,6 @@ static void rcu_cleanup_after_idle(void)
invoke_rcu_core();
}
/*
* Keep a running count of the number of non-lazy callbacks posted
* on this CPU. This running counter (which is never decremented) allows
* rcu_prepare_for_idle() to detect when something out of the idle loop
* posts a callback, even if an equal number of callbacks are invoked.
* Of course, callbacks should only be posted from within a trace event
* designed to be called from idle or from within RCU_NONIDLE().
*/
static void rcu_idle_count_callbacks_posted(void)
{
__this_cpu_add(rcu_data.nonlazy_posted, 1);
}
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
#ifdef CONFIG_RCU_FAST_NO_HZ
@@ -1776,13 +1654,12 @@ static void rcu_idle_count_callbacks_posted(void)
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
unsigned long nlpd = rdp->nonlazy_posted - rdp->nonlazy_posted_snap;
sprintf(cp, "last_accelerate: %04lx/%04lx, nonlazy_posted: %ld, %c%c",
sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
rdp->last_accelerate & 0xffff, jiffies & 0xffff,
ulong2long(nlpd),
rdp->all_lazy ? 'L' : '.',
rdp->tick_nohz_enabled_snap ? '.' : 'D');
".l"[rdp->all_lazy],
".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
".D"[!rdp->tick_nohz_enabled_snap]);
}
#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
@@ -1868,22 +1745,24 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp)
/*
* Offload callback processing from the boot-time-specified set of CPUs
* specified by rcu_nocb_mask. For each CPU in the set, there is a
* kthread created that pulls the callbacks from the corresponding CPU,
* waits for a grace period to elapse, and invokes the callbacks.
* The no-CBs CPUs do a wake_up() on their kthread when they insert
* a callback into any empty list, unless the rcu_nocb_poll boot parameter
* has been specified, in which case each kthread actively polls its
* CPU. (Which isn't so great for energy efficiency, but which does
* reduce RCU's overhead on that CPU.)
* specified by rcu_nocb_mask. For the CPUs in the set, there are kthreads
* created that pull the callbacks from the corresponding CPU, wait for
* a grace period to elapse, and invoke the callbacks. These kthreads
* are organized into leaders, which manage incoming callbacks, wait for
* grace periods, and awaken followers, and the followers, which only
* invoke callbacks. Each leader is its own follower. The no-CBs CPUs
* do a wake_up() on their kthread when they insert a callback into any
* empty list, unless the rcu_nocb_poll boot parameter has been specified,
* in which case each kthread actively polls its CPU. (Which isn't so great
* for energy efficiency, but which does reduce RCU's overhead on that CPU.)
*
* This is intended to be used in conjunction with Frederic Weisbecker's
* adaptive-idle work, which would seriously reduce OS jitter on CPUs
* running CPU-bound user-mode computations.
*
* Offloading of callback processing could also in theory be used as
* an energy-efficiency measure because CPUs with no RCU callbacks
* queued are more aggressive about entering dyntick-idle mode.
* Offloading of callbacks can also be used as an energy-efficiency
* measure because CPUs with no RCU callbacks queued are more aggressive
* about entering dyntick-idle mode.
*/
@@ -1987,10 +1866,7 @@ static void wake_nocb_leader_defer(struct rcu_data *rdp, int waketype,
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
}
/*
* Does the specified CPU need an RCU callback for this invocation
* of rcu_barrier()?
*/
/* Does rcu_barrier need to queue an RCU callback on the specified CPU? */
static bool rcu_nocb_cpu_needs_barrier(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -2006,8 +1882,8 @@ static bool rcu_nocb_cpu_needs_barrier(int cpu)
* callbacks would be posted. In the worst case, the first
* barrier in rcu_barrier() suffices (but the caller cannot
* necessarily rely on this, not a substitute for the caller
* getting the concurrency design right!). There must also be
* a barrier between the following load an posting of a callback
* getting the concurrency design right!). There must also be a
* barrier between the following load and posting of a callback
* (if a callback is in fact needed). This is associated with an
* atomic_inc() in the caller.
*/
@@ -2517,9 +2393,9 @@ static void rcu_spawn_one_nocb_kthread(int cpu)
/*
* If the specified CPU is a no-CBs CPU that does not already have its
* rcuo kthreads, spawn them.
* rcuo kthread, spawn it.
*/
static void rcu_spawn_all_nocb_kthreads(int cpu)
static void rcu_spawn_cpu_nocb_kthread(int cpu)
{
if (rcu_scheduler_fully_active)
rcu_spawn_one_nocb_kthread(cpu);
@@ -2536,7 +2412,7 @@ static void __init rcu_spawn_nocb_kthreads(void)
int cpu;
for_each_online_cpu(cpu)
rcu_spawn_all_nocb_kthreads(cpu);
rcu_spawn_cpu_nocb_kthread(cpu);
}
/* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */
@@ -2670,7 +2546,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
{
}
static void rcu_spawn_all_nocb_kthreads(int cpu)
static void rcu_spawn_cpu_nocb_kthread(int cpu)
{
}

17
kernel/rcu/update.c
View File

@@ -1,26 +1,13 @@
// 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.
*
* Copyright IBM Corporation, 2001
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.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.
* Papers:
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf

4
kernel/sched/cpufreq.c
View File

@@ -48,8 +48,8 @@ EXPORT_SYMBOL_GPL(cpufreq_add_update_util_hook);
*
* Clear the update_util_data pointer for the given CPU.
*
* Callers must use RCU-sched callbacks to free any memory that might be
* accessed via the old update_util_data pointer or invoke synchronize_sched()
* Callers must use RCU callbacks to free any memory that might be
* accessed via the old update_util_data pointer or invoke synchronize_rcu()
* right after this function to avoid use-after-free.
*/
void cpufreq_remove_update_util_hook(int cpu)

2
kernel/sched/cpufreq_schedutil.c
View File

@@ -859,7 +859,7 @@ static void sugov_stop(struct cpufreq_policy *policy)
for_each_cpu(cpu, policy->cpus)
cpufreq_remove_update_util_hook(cpu);
synchronize_sched();
synchronize_rcu();
if (!policy->fast_switch_enabled) {
irq_work_sync(&sg_policy->irq_work);

2
kernel/sched/sched.h
View File

@@ -1260,7 +1260,7 @@ extern void sched_ttwu_pending(void);
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
* See detach_destroy_domains: synchronize_sched for details.
* See destroy_sched_domains: call_rcu for details.
*
* The domain tree of any CPU may only be accessed from within
* preempt-disabled sections.

4
kernel/sched/topology.c
View File

@@ -442,7 +442,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
raw_spin_unlock_irqrestore(&rq->lock, flags);
if (old_rd)
call_rcu_sched(&old_rd->rcu, free_rootdomain);
call_rcu(&old_rd->rcu, free_rootdomain);
}
void sched_get_rd(struct root_domain *rd)
@@ -455,7 +455,7 @@ void sched_put_rd(struct root_domain *rd)
if (!atomic_dec_and_test(&rd->refcount))
return;
call_rcu_sched(&rd->rcu, free_rootdomain);
call_rcu(&rd->rcu, free_rootdomain);
}
static int init_rootdomain(struct root_domain *rd)

2
kernel/time/timer.c
View File

@@ -1632,7 +1632,7 @@ void update_process_times(int user_tick)
/* Note: this timer irq context must be accounted for as well. */
account_process_tick(p, user_tick);
run_local_timers();
rcu_check_callbacks(user_tick);
rcu_sched_clock_irq(user_tick);
#ifdef CONFIG_IRQ_WORK
if (in_irq())
irq_work_tick();

25
kernel/torture.c
View File

@@ -1,23 +1,10 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* Common functions for in-kernel torture tests.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2014
*
* Author: Paul E. McKenney <paulmck@us.ibm.com>
* Author: Paul E. McKenney <paulmck@linux.ibm.com>
* Based on kernel/rcu/torture.c.
*/
@@ -53,7 +40,7 @@
#include "rcu/rcu.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
static char *torture_type;
static int verbose;
@@ -75,6 +62,7 @@ static DEFINE_MUTEX(fullstop_mutex);
static struct task_struct *onoff_task;
static long onoff_holdoff;
static long onoff_interval;
static torture_ofl_func *onoff_f;
static long n_offline_attempts;
static long n_offline_successes;
static unsigned long sum_offline;
@@ -118,6 +106,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
pr_alert("%s" TORTURE_FLAG
"torture_onoff task: offlined %d\n",
torture_type, cpu);
if (onoff_f)
onoff_f();
(*n_offl_successes)++;
delta = jiffies - starttime;
*sum_offl += delta;
@@ -243,11 +233,12 @@ stop:
/*
* Initiate online-offline handling.
*/
int torture_onoff_init(long ooholdoff, long oointerval)
int torture_onoff_init(long ooholdoff, long oointerval, torture_ofl_func *f)
{
#ifdef CONFIG_HOTPLUG_CPU
onoff_holdoff = ooholdoff;
onoff_interval = oointerval;
onoff_f = f;
if (onoff_interval <= 0)
return 0;
return torture_create_kthread(torture_onoff, NULL, onoff_task);