linux/kernel/rcu/tree.h

510 lines
21 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions.
*
* Copyright IBM Corporation, 2008
*
* Author: Ingo Molnar <mingo@elte.hu>
* Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/cache.h>
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 08:35:27 +08:00
#include <linux/kthread.h>
#include <linux/spinlock.h>
#include <linux/rtmutex.h>
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/seqlock.h>
rcu: Use simple wait queues where possible in rcutree As of commit dae6e64d2bcfd ("rcu: Introduce proper blocking to no-CBs kthreads GP waits") the RCU subsystem started making use of wait queues. Here we convert all additions of RCU wait queues to use simple wait queues, since they don't need the extra overhead of the full wait queue features. Originally this was done for RT kernels[1], since we would get things like... BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 in_atomic(): 1, irqs_disabled(): 1, pid: 8, name: rcu_preempt Pid: 8, comm: rcu_preempt Not tainted Call Trace: [<ffffffff8106c8d0>] __might_sleep+0xd0/0xf0 [<ffffffff817d77b4>] rt_spin_lock+0x24/0x50 [<ffffffff8106fcf6>] __wake_up+0x36/0x70 [<ffffffff810c4542>] rcu_gp_kthread+0x4d2/0x680 [<ffffffff8105f910>] ? __init_waitqueue_head+0x50/0x50 [<ffffffff810c4070>] ? rcu_gp_fqs+0x80/0x80 [<ffffffff8105eabb>] kthread+0xdb/0xe0 [<ffffffff8106b912>] ? finish_task_switch+0x52/0x100 [<ffffffff817e0754>] kernel_thread_helper+0x4/0x10 [<ffffffff8105e9e0>] ? __init_kthread_worker+0x60/0x60 [<ffffffff817e0750>] ? gs_change+0xb/0xb ...and hence simple wait queues were deployed on RT out of necessity (as simple wait uses a raw lock), but mainline might as well take advantage of the more streamline support as well. [1] This is a carry forward of work from v3.10-rt; the original conversion was by Thomas on an earlier -rt version, and Sebastian extended it to additional post-3.10 added RCU waiters; here I've added a commit log and unified the RCU changes into one, and uprev'd it to match mainline RCU. Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-rt-users@vger.kernel.org Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1455871601-27484-6-git-send-email-wagi@monom.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-02-19 16:46:41 +08:00
#include <linux/swait.h>
#include <linux/rcu_node_tree.h>
#include "rcu_segcblist.h"
/* Communicate arguments to a workqueue handler. */
struct rcu_exp_work {
unsigned long rew_s;
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 08:35:27 +08:00
#ifdef CONFIG_RCU_EXP_KTHREAD
struct kthread_work rew_work;
#else
struct work_struct rew_work;
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 08:35:27 +08:00
#endif /* CONFIG_RCU_EXP_KTHREAD */
};
/* RCU's kthread states for tracing. */
#define RCU_KTHREAD_STOPPED 0
#define RCU_KTHREAD_RUNNING 1
#define RCU_KTHREAD_WAITING 2
#define RCU_KTHREAD_OFFCPU 3
#define RCU_KTHREAD_YIELDING 4
#define RCU_KTHREAD_MAX 4
/*
* Definition for node within the RCU grace-period-detection hierarchy.
*/
struct rcu_node {
raw_spinlock_t __private lock; /* Root rcu_node's lock protects */
/* some rcu_state fields as well as */
/* following. */
unsigned long gp_seq; /* Track rsp->gp_seq. */
unsigned long gp_seq_needed; /* Track furthest future GP request. */
unsigned long completedqs; /* All QSes done for this node. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
/* In leaf rcu_node, each bit corresponds to */
/* an rcu_data structure, otherwise, each */
/* bit corresponds to a child rcu_node */
/* structure. */
unsigned long rcu_gp_init_mask; /* Mask of offline CPUs at GP init. */
unsigned long qsmaskinit;
/* Per-GP initial value for qsmask. */
rcu: Process offlining and onlining only at grace-period start Races between CPU hotplug and grace periods can be difficult to resolve, so the ->onoff_mutex is used to exclude the two events. Unfortunately, this means that it is impossible for an outgoing CPU to perform the last bits of its offlining from its last pass through the idle loop, because sleeplocks cannot be acquired in that context. This commit avoids these problems by buffering online and offline events in a new ->qsmaskinitnext field in the leaf rcu_node structures. When a grace period starts, the events accumulated in this mask are applied to the ->qsmaskinit field, and, if needed, up the rcu_node tree. The special case of all CPUs corresponding to a given leaf rcu_node structure being offline while there are still elements in that structure's ->blkd_tasks list is handled using a new ->wait_blkd_tasks field. In this case, propagating the offline bits up the tree is deferred until the beginning of the grace period after all of the tasks have exited their RCU read-side critical sections and removed themselves from the list, at which point the ->wait_blkd_tasks flag is cleared. If one of that leaf rcu_node structure's CPUs comes back online before the list empties, then the ->wait_blkd_tasks flag is simply cleared. This of course means that RCU's notion of which CPUs are offline can be out of date. This is OK because RCU need only wait on CPUs that were online at the time that the grace period started. In addition, RCU's force-quiescent-state actions will handle the case where a CPU goes offline after the grace period starts. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2015-01-24 13:52:37 +08:00
/* Initialized from ->qsmaskinitnext at the */
/* beginning of each grace period. */
unsigned long qsmaskinitnext;
unsigned long expmask; /* CPUs or groups that need to check in */
/* to allow the current expedited GP */
/* to complete. */
unsigned long expmaskinit;
/* Per-GP initial values for expmask. */
/* Initialized from ->expmaskinitnext at the */
/* beginning of each expedited GP. */
unsigned long expmaskinitnext;
/* Online CPUs for next expedited GP. */
/* Any CPU that has ever been online will */
/* have its bit set. */
unsigned long cbovldmask;
/* CPUs experiencing callback overload. */
unsigned long ffmask; /* Fully functional CPUs. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
/* Only one bit will be set in this mask. */
int grplo; /* lowest-numbered CPU here. */
int grphi; /* highest-numbered CPU here. */
u8 grpnum; /* group number for next level up. */
u8 level; /* root is at level 0. */
rcu: Process offlining and onlining only at grace-period start Races between CPU hotplug and grace periods can be difficult to resolve, so the ->onoff_mutex is used to exclude the two events. Unfortunately, this means that it is impossible for an outgoing CPU to perform the last bits of its offlining from its last pass through the idle loop, because sleeplocks cannot be acquired in that context. This commit avoids these problems by buffering online and offline events in a new ->qsmaskinitnext field in the leaf rcu_node structures. When a grace period starts, the events accumulated in this mask are applied to the ->qsmaskinit field, and, if needed, up the rcu_node tree. The special case of all CPUs corresponding to a given leaf rcu_node structure being offline while there are still elements in that structure's ->blkd_tasks list is handled using a new ->wait_blkd_tasks field. In this case, propagating the offline bits up the tree is deferred until the beginning of the grace period after all of the tasks have exited their RCU read-side critical sections and removed themselves from the list, at which point the ->wait_blkd_tasks flag is cleared. If one of that leaf rcu_node structure's CPUs comes back online before the list empties, then the ->wait_blkd_tasks flag is simply cleared. This of course means that RCU's notion of which CPUs are offline can be out of date. This is OK because RCU need only wait on CPUs that were online at the time that the grace period started. In addition, RCU's force-quiescent-state actions will handle the case where a CPU goes offline after the grace period starts. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2015-01-24 13:52:37 +08:00
bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
/* exit RCU read-side critical sections */
/* before propagating offline up the */
/* rcu_node tree? */
struct rcu_node *parent;
struct list_head blkd_tasks;
/* Tasks blocked in RCU read-side critical */
/* section. Tasks are placed at the head */
/* of this list and age towards the tail. */
struct list_head *gp_tasks;
/* Pointer to the first task blocking the */
/* current grace period, or NULL if there */
/* is no such task. */
struct list_head *exp_tasks;
/* Pointer to the first task blocking the */
/* current expedited grace period, or NULL */
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there can cannot be any such task. */
struct list_head *boost_tasks;
/* Pointer to first task that needs to be */
/* priority boosted, or NULL if no priority */
/* boosting is needed for this rcu_node */
/* structure. If there are no tasks */
/* queued on this rcu_node structure that */
/* are blocking the current grace period, */
/* there can be no such task. */
struct rt_mutex boost_mtx;
/* Used only for the priority-boosting */
/* side effect, not as a lock. */
unsigned long boost_time;
/* When to start boosting (jiffies). */
struct mutex boost_kthread_mutex;
/* Exclusion for thread spawning and affinity */
/* manipulation. */
struct task_struct *boost_kthread_task;
/* kthread that takes care of priority */
/* boosting for this rcu_node structure. */
unsigned int boost_kthread_status;
/* State of boost_kthread_task for tracing. */
unsigned long n_boosts; /* Number of boosts for this rcu_node structure. */
#ifdef CONFIG_RCU_NOCB_CPU
rcu: Use simple wait queues where possible in rcutree As of commit dae6e64d2bcfd ("rcu: Introduce proper blocking to no-CBs kthreads GP waits") the RCU subsystem started making use of wait queues. Here we convert all additions of RCU wait queues to use simple wait queues, since they don't need the extra overhead of the full wait queue features. Originally this was done for RT kernels[1], since we would get things like... BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 in_atomic(): 1, irqs_disabled(): 1, pid: 8, name: rcu_preempt Pid: 8, comm: rcu_preempt Not tainted Call Trace: [<ffffffff8106c8d0>] __might_sleep+0xd0/0xf0 [<ffffffff817d77b4>] rt_spin_lock+0x24/0x50 [<ffffffff8106fcf6>] __wake_up+0x36/0x70 [<ffffffff810c4542>] rcu_gp_kthread+0x4d2/0x680 [<ffffffff8105f910>] ? __init_waitqueue_head+0x50/0x50 [<ffffffff810c4070>] ? rcu_gp_fqs+0x80/0x80 [<ffffffff8105eabb>] kthread+0xdb/0xe0 [<ffffffff8106b912>] ? finish_task_switch+0x52/0x100 [<ffffffff817e0754>] kernel_thread_helper+0x4/0x10 [<ffffffff8105e9e0>] ? __init_kthread_worker+0x60/0x60 [<ffffffff817e0750>] ? gs_change+0xb/0xb ...and hence simple wait queues were deployed on RT out of necessity (as simple wait uses a raw lock), but mainline might as well take advantage of the more streamline support as well. [1] This is a carry forward of work from v3.10-rt; the original conversion was by Thomas on an earlier -rt version, and Sebastian extended it to additional post-3.10 added RCU waiters; here I've added a commit log and unified the RCU changes into one, and uprev'd it to match mainline RCU. Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-rt-users@vger.kernel.org Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1455871601-27484-6-git-send-email-wagi@monom.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-02-19 16:46:41 +08:00
struct swait_queue_head nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
unsigned long exp_seq_rq;
wait_queue_head_t exp_wq[4];
struct rcu_exp_work rew;
bool exp_need_flush; /* Need to flush workitem? */
raw_spinlock_t exp_poll_lock;
/* Lock and data for polled expedited grace periods. */
unsigned long exp_seq_poll_rq;
struct work_struct exp_poll_wq;
} ____cacheline_internodealigned_in_smp;
rcu: Correctly handle sparse possible cpus In many cases in the RCU tree code, we iterate over the set of cpus for a leaf node described by rcu_node::grplo and rcu_node::grphi, checking per-cpu data for each cpu in this range. However, if the set of possible cpus is sparse, some cpus described in this range are not possible, and thus no per-cpu region will have been allocated (or initialised) for them by the generic percpu code. Erroneous accesses to a per-cpu area for these !possible cpus may fault or may hit other data depending on the addressed generated when the erroneous per cpu offset is applied. In practice, both cases have been observed on arm64 hardware (the former being silent, but detectable with additional patches). To avoid issues resulting from this, we must iterate over the set of *possible* cpus for a given leaf node. This patch add a new helper, for_each_leaf_node_possible_cpu, to enable this. As iteration is often intertwined with rcu_node local bitmask manipulation, a new leaf_node_cpu_bit helper is added to make this simpler and more consistent. The RCU tree code is made to use both of these where appropriate. Without this patch, running reboot at a shell can result in an oops like: [ 3369.075979] Unable to handle kernel paging request at virtual address ffffff8008b21b4c [ 3369.083881] pgd = ffffffc3ecdda000 [ 3369.087270] [ffffff8008b21b4c] *pgd=00000083eca48003, *pud=00000083eca48003, *pmd=0000000000000000 [ 3369.096222] Internal error: Oops: 96000007 [#1] PREEMPT SMP [ 3369.101781] Modules linked in: [ 3369.104825] CPU: 2 PID: 1817 Comm: NetworkManager Tainted: G W 4.6.0+ #3 [ 3369.121239] task: ffffffc0fa13e000 ti: ffffffc3eb940000 task.ti: ffffffc3eb940000 [ 3369.128708] PC is at sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.134094] LR is at sync_rcu_exp_select_cpus+0x104/0x510 [ 3369.139479] pc : [<ffffff80081109a8>] lr : [<ffffff8008110924>] pstate: 200001c5 [ 3369.146860] sp : ffffffc3eb9435a0 [ 3369.150162] x29: ffffffc3eb9435a0 x28: ffffff8008be4f88 [ 3369.155465] x27: ffffff8008b66c80 x26: ffffffc3eceb2600 [ 3369.160767] x25: 0000000000000001 x24: ffffff8008be4f88 [ 3369.166070] x23: ffffff8008b51c3c x22: ffffff8008b66c80 [ 3369.171371] x21: 0000000000000001 x20: ffffff8008b21b40 [ 3369.176673] x19: ffffff8008b66c80 x18: 0000000000000000 [ 3369.181975] x17: 0000007fa951a010 x16: ffffff80086a30f0 [ 3369.187278] x15: 0000007fa9505590 x14: 0000000000000000 [ 3369.192580] x13: ffffff8008b51000 x12: ffffffc3eb940000 [ 3369.197882] x11: 0000000000000006 x10: ffffff8008b51b78 [ 3369.203184] x9 : 0000000000000001 x8 : ffffff8008be4000 [ 3369.208486] x7 : ffffff8008b21b40 x6 : 0000000000001003 [ 3369.213788] x5 : 0000000000000000 x4 : ffffff8008b27280 [ 3369.219090] x3 : ffffff8008b21b4c x2 : 0000000000000001 [ 3369.224406] x1 : 0000000000000001 x0 : 0000000000000140 ... [ 3369.972257] [<ffffff80081109a8>] sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.978685] [<ffffff80081128b4>] synchronize_rcu_expedited+0x64/0xa8 [ 3369.985026] [<ffffff80086b987c>] synchronize_net+0x24/0x30 [ 3369.990499] [<ffffff80086ddb54>] dev_deactivate_many+0x28c/0x298 [ 3369.996493] [<ffffff80086b6bb8>] __dev_close_many+0x60/0xd0 [ 3370.002052] [<ffffff80086b6d48>] __dev_close+0x28/0x40 [ 3370.007178] [<ffffff80086bf62c>] __dev_change_flags+0x8c/0x158 [ 3370.012999] [<ffffff80086bf718>] dev_change_flags+0x20/0x60 [ 3370.018558] [<ffffff80086cf7f0>] do_setlink+0x288/0x918 [ 3370.023771] [<ffffff80086d0798>] rtnl_newlink+0x398/0x6a8 [ 3370.029158] [<ffffff80086cee84>] rtnetlink_rcv_msg+0xe4/0x220 [ 3370.034891] [<ffffff80086e274c>] netlink_rcv_skb+0xc4/0xf8 [ 3370.040364] [<ffffff80086ced8c>] rtnetlink_rcv+0x2c/0x40 [ 3370.045663] [<ffffff80086e1fe8>] netlink_unicast+0x160/0x238 [ 3370.051309] [<ffffff80086e24b8>] netlink_sendmsg+0x2f0/0x358 [ 3370.056956] [<ffffff80086a0070>] sock_sendmsg+0x18/0x30 [ 3370.062168] [<ffffff80086a21cc>] ___sys_sendmsg+0x26c/0x280 [ 3370.067728] [<ffffff80086a30ac>] __sys_sendmsg+0x44/0x88 [ 3370.073027] [<ffffff80086a3100>] SyS_sendmsg+0x10/0x20 [ 3370.078153] [<ffffff8008085e70>] el0_svc_naked+0x24/0x28 Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reported-by: Dennis Chen <dennis.chen@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Steve Capper <steve.capper@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2016-06-03 22:20:04 +08:00
/*
* Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
* are indexed relative to this interval rather than the global CPU ID space.
* This generates the bit for a CPU in node-local masks.
*/
#define leaf_node_cpu_bit(rnp, cpu) (BIT((cpu) - (rnp)->grplo))
rcu: Correctly handle sparse possible cpus In many cases in the RCU tree code, we iterate over the set of cpus for a leaf node described by rcu_node::grplo and rcu_node::grphi, checking per-cpu data for each cpu in this range. However, if the set of possible cpus is sparse, some cpus described in this range are not possible, and thus no per-cpu region will have been allocated (or initialised) for them by the generic percpu code. Erroneous accesses to a per-cpu area for these !possible cpus may fault or may hit other data depending on the addressed generated when the erroneous per cpu offset is applied. In practice, both cases have been observed on arm64 hardware (the former being silent, but detectable with additional patches). To avoid issues resulting from this, we must iterate over the set of *possible* cpus for a given leaf node. This patch add a new helper, for_each_leaf_node_possible_cpu, to enable this. As iteration is often intertwined with rcu_node local bitmask manipulation, a new leaf_node_cpu_bit helper is added to make this simpler and more consistent. The RCU tree code is made to use both of these where appropriate. Without this patch, running reboot at a shell can result in an oops like: [ 3369.075979] Unable to handle kernel paging request at virtual address ffffff8008b21b4c [ 3369.083881] pgd = ffffffc3ecdda000 [ 3369.087270] [ffffff8008b21b4c] *pgd=00000083eca48003, *pud=00000083eca48003, *pmd=0000000000000000 [ 3369.096222] Internal error: Oops: 96000007 [#1] PREEMPT SMP [ 3369.101781] Modules linked in: [ 3369.104825] CPU: 2 PID: 1817 Comm: NetworkManager Tainted: G W 4.6.0+ #3 [ 3369.121239] task: ffffffc0fa13e000 ti: ffffffc3eb940000 task.ti: ffffffc3eb940000 [ 3369.128708] PC is at sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.134094] LR is at sync_rcu_exp_select_cpus+0x104/0x510 [ 3369.139479] pc : [<ffffff80081109a8>] lr : [<ffffff8008110924>] pstate: 200001c5 [ 3369.146860] sp : ffffffc3eb9435a0 [ 3369.150162] x29: ffffffc3eb9435a0 x28: ffffff8008be4f88 [ 3369.155465] x27: ffffff8008b66c80 x26: ffffffc3eceb2600 [ 3369.160767] x25: 0000000000000001 x24: ffffff8008be4f88 [ 3369.166070] x23: ffffff8008b51c3c x22: ffffff8008b66c80 [ 3369.171371] x21: 0000000000000001 x20: ffffff8008b21b40 [ 3369.176673] x19: ffffff8008b66c80 x18: 0000000000000000 [ 3369.181975] x17: 0000007fa951a010 x16: ffffff80086a30f0 [ 3369.187278] x15: 0000007fa9505590 x14: 0000000000000000 [ 3369.192580] x13: ffffff8008b51000 x12: ffffffc3eb940000 [ 3369.197882] x11: 0000000000000006 x10: ffffff8008b51b78 [ 3369.203184] x9 : 0000000000000001 x8 : ffffff8008be4000 [ 3369.208486] x7 : ffffff8008b21b40 x6 : 0000000000001003 [ 3369.213788] x5 : 0000000000000000 x4 : ffffff8008b27280 [ 3369.219090] x3 : ffffff8008b21b4c x2 : 0000000000000001 [ 3369.224406] x1 : 0000000000000001 x0 : 0000000000000140 ... [ 3369.972257] [<ffffff80081109a8>] sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.978685] [<ffffff80081128b4>] synchronize_rcu_expedited+0x64/0xa8 [ 3369.985026] [<ffffff80086b987c>] synchronize_net+0x24/0x30 [ 3369.990499] [<ffffff80086ddb54>] dev_deactivate_many+0x28c/0x298 [ 3369.996493] [<ffffff80086b6bb8>] __dev_close_many+0x60/0xd0 [ 3370.002052] [<ffffff80086b6d48>] __dev_close+0x28/0x40 [ 3370.007178] [<ffffff80086bf62c>] __dev_change_flags+0x8c/0x158 [ 3370.012999] [<ffffff80086bf718>] dev_change_flags+0x20/0x60 [ 3370.018558] [<ffffff80086cf7f0>] do_setlink+0x288/0x918 [ 3370.023771] [<ffffff80086d0798>] rtnl_newlink+0x398/0x6a8 [ 3370.029158] [<ffffff80086cee84>] rtnetlink_rcv_msg+0xe4/0x220 [ 3370.034891] [<ffffff80086e274c>] netlink_rcv_skb+0xc4/0xf8 [ 3370.040364] [<ffffff80086ced8c>] rtnetlink_rcv+0x2c/0x40 [ 3370.045663] [<ffffff80086e1fe8>] netlink_unicast+0x160/0x238 [ 3370.051309] [<ffffff80086e24b8>] netlink_sendmsg+0x2f0/0x358 [ 3370.056956] [<ffffff80086a0070>] sock_sendmsg+0x18/0x30 [ 3370.062168] [<ffffff80086a21cc>] ___sys_sendmsg+0x26c/0x280 [ 3370.067728] [<ffffff80086a30ac>] __sys_sendmsg+0x44/0x88 [ 3370.073027] [<ffffff80086a3100>] SyS_sendmsg+0x10/0x20 [ 3370.078153] [<ffffff8008085e70>] el0_svc_naked+0x24/0x28 Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reported-by: Dennis Chen <dennis.chen@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Steve Capper <steve.capper@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2016-06-03 22:20:04 +08:00
/*
* Union to allow "aggregate OR" operation on the need for a quiescent
* state by the normal and expedited grace periods.
*/
union rcu_noqs {
struct {
u8 norm;
u8 exp;
} b; /* Bits. */
u16 s; /* Set of bits, aggregate OR here. */
};
rcu: Add RCU stall diagnosis information Because RCU CPU stall warnings are driven from the scheduling-clock interrupt handler, a workload consisting of a very large number of short-duration hardware interrupts can result in misleading stall-warning messages. On systems supporting only a single level of interrupts, that is, where interrupts handlers cannot be interrupted, this can produce misleading diagnostics. The stack traces will show the innocent-bystander interrupted task, not the interrupts that are at the very least exacerbating the stall. This situation can be improved by displaying the number of interrupts and the CPU time that they have consumed. Diagnosing other types of stalls can be eased by also providing the count of softirqs and the CPU time that they consumed as well as the number of context switches and the task-level CPU time consumed. Consider the following output given this change: rcu: INFO: rcu_preempt self-detected stall on CPU rcu: 0-....: (1250 ticks this GP) <omitted> rcu: hardirqs softirqs csw/system rcu: number: 624 45 0 rcu: cputime: 69 1 2425 ==> 2500(ms) This output shows that the number of hard and soft interrupts is small, there are no context switches, and the system takes up a lot of time. This indicates that the current task is looping with preemption disabled. The impact on system performance is negligible because snapshot is recorded only once for all continuous RCU stalls. This added debugging information is suppressed by default and can be enabled by building the kernel with CONFIG_RCU_CPU_STALL_CPUTIME=y or by booting with rcupdate.rcu_cpu_stall_cputime=1. Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Reviewed-by: Mukesh Ojha <quic_mojha@quicinc.com> Reviewed-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-11-19 17:25:06 +08:00
/*
* Record the snapshot of the core stats at half of the first RCU stall timeout.
* The member gp_seq is used to ensure that all members are updated only once
* during the sampling period. The snapshot is taken only if this gp_seq is not
* equal to rdp->gp_seq.
*/
struct rcu_snap_record {
unsigned long gp_seq; /* Track rdp->gp_seq counter */
u64 cputime_irq; /* Accumulated cputime of hard irqs */
u64 cputime_softirq;/* Accumulated cputime of soft irqs */
u64 cputime_system; /* Accumulated cputime of kernel tasks */
unsigned long nr_hardirqs; /* Accumulated number of hard irqs */
unsigned int nr_softirqs; /* Accumulated number of soft irqs */
unsigned long long nr_csw; /* Accumulated number of task switches */
unsigned long jiffies; /* Track jiffies value */
};
/* Per-CPU data for read-copy update. */
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
unsigned long gp_seq; /* Track rsp->gp_seq counter. */
unsigned long gp_seq_needed; /* Track furthest future GP request. */
union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */
bool core_needs_qs; /* Core waits for quiescent state. */
bool beenonline; /* CPU online at least once. */
bool gpwrap; /* Possible ->gp_seq wrap. */
bool cpu_started; /* RCU watching this onlining CPU. */
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
unsigned long ticks_this_gp; /* The number of scheduling-clock */
/* ticks this CPU has handled */
/* during and after the last grace */
/* period it is aware of. */
struct irq_work defer_qs_iw; /* Obtain later scheduler attention. */
bool defer_qs_iw_pending; /* Scheduler attention pending? */
struct work_struct strict_work; /* Schedule readers for strict GPs. */
/* 2) batch handling */
struct rcu_segcblist cblist; /* Segmented callback list, with */
/* different callbacks waiting for */
/* different grace periods. */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* # callbacks invoked since boot. */
unsigned long n_force_qs_snap;
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
/* 3) dynticks interface. */
int dynticks_snap; /* Per-GP tracking for dynticks. */
bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */
bool rcu_urgent_qs; /* GP old need light quiescent state. */
bool rcu_forced_tick; /* Forced tick to provide QS. */
bool rcu_forced_tick_exp; /* ... provide QS to expedited GP. */
/* 4) rcu_barrier(), OOM callbacks, and expediting. */
unsigned long barrier_seq_snap; /* Snap of rcu_state.barrier_sequence. */
struct rcu_head barrier_head;
int exp_dynticks_snap; /* Double-check need for IPI. */
/* 5) Callback offloading. */
#ifdef CONFIG_RCU_NOCB_CPU
rcu/nocb: Provide separate no-CBs grace-period kthreads Currently, there is one no-CBs rcuo kthread per CPU, and these kthreads are divided into groups. The first rcuo kthread to come online in a given group is that group's leader, and the leader both waits for grace periods and invokes its CPU's callbacks. The non-leader rcuo kthreads only invoke callbacks. This works well in the real-time/embedded environments for which it was intended because such environments tend not to generate all that many callbacks. However, given huge floods of callbacks, it is possible for the leader kthread to be stuck invoking callbacks while its followers wait helplessly while their callbacks pile up. This is a good recipe for an OOM, and rcutorture's new callback-flood capability does generate such OOMs. One strategy would be to wait until such OOMs start happening in production, but similar OOMs have in fact happened starting in 2018. It would therefore be wise to take a more proactive approach. This commit therefore features per-CPU rcuo kthreads that do nothing but invoke callbacks. Instead of having one of these kthreads act as leader, each group has a separate rcog kthread that handles grace periods for its group. Because these rcuog kthreads do not invoke callbacks, callback floods on one CPU no longer block callbacks from reaching the rcuc callback-invocation kthreads on other CPUs. This change does introduce additional kthreads, however: 1. The number of additional kthreads is about the square root of the number of CPUs, so that a 4096-CPU system would have only about 64 additional kthreads. Note that recent changes decreased the number of rcuo kthreads by a factor of two (CONFIG_PREEMPT=n) or even three (CONFIG_PREEMPT=y), so this still represents a significant improvement on most systems. 2. The leading "rcuo" of the rcuog kthreads should allow existing scripting to affinity these additional kthreads as needed, the same as for the rcuop and rcuos kthreads. (There are no longer any rcuob kthreads.) 3. A state-machine approach was considered and rejected. Although this would allow the rcuo kthreads to continue their dual leader/follower roles, it complicates callback invocation and makes it more difficult to consolidate rcuo callback invocation with existing softirq callback invocation. The introduction of rcuog kthreads should thus be acceptable. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-03-30 07:43:51 +08:00
struct swait_queue_head nocb_cb_wq; /* For nocb kthreads to sleep on. */
struct swait_queue_head nocb_state_wq; /* For offloading state changes */
rcu/nocb: Provide separate no-CBs grace-period kthreads Currently, there is one no-CBs rcuo kthread per CPU, and these kthreads are divided into groups. The first rcuo kthread to come online in a given group is that group's leader, and the leader both waits for grace periods and invokes its CPU's callbacks. The non-leader rcuo kthreads only invoke callbacks. This works well in the real-time/embedded environments for which it was intended because such environments tend not to generate all that many callbacks. However, given huge floods of callbacks, it is possible for the leader kthread to be stuck invoking callbacks while its followers wait helplessly while their callbacks pile up. This is a good recipe for an OOM, and rcutorture's new callback-flood capability does generate such OOMs. One strategy would be to wait until such OOMs start happening in production, but similar OOMs have in fact happened starting in 2018. It would therefore be wise to take a more proactive approach. This commit therefore features per-CPU rcuo kthreads that do nothing but invoke callbacks. Instead of having one of these kthreads act as leader, each group has a separate rcog kthread that handles grace periods for its group. Because these rcuog kthreads do not invoke callbacks, callback floods on one CPU no longer block callbacks from reaching the rcuc callback-invocation kthreads on other CPUs. This change does introduce additional kthreads, however: 1. The number of additional kthreads is about the square root of the number of CPUs, so that a 4096-CPU system would have only about 64 additional kthreads. Note that recent changes decreased the number of rcuo kthreads by a factor of two (CONFIG_PREEMPT=n) or even three (CONFIG_PREEMPT=y), so this still represents a significant improvement on most systems. 2. The leading "rcuo" of the rcuog kthreads should allow existing scripting to affinity these additional kthreads as needed, the same as for the rcuop and rcuos kthreads. (There are no longer any rcuob kthreads.) 3. A state-machine approach was considered and rejected. Although this would allow the rcuo kthreads to continue their dual leader/follower roles, it complicates callback invocation and makes it more difficult to consolidate rcuo callback invocation with existing softirq callback invocation. The introduction of rcuog kthreads should thus be acceptable. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-03-30 07:43:51 +08:00
struct task_struct *nocb_gp_kthread;
raw_spinlock_t nocb_lock; /* Guard following pair of fields. */
atomic_t nocb_lock_contended; /* Contention experienced. */
int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
struct timer_list nocb_timer; /* Enforce finite deferral. */
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 07:03:33 +08:00
unsigned long nocb_gp_adv_time; /* Last call_rcu() CB adv (jiffies). */
struct mutex nocb_gp_kthread_mutex; /* Exclusion for nocb gp kthread */
/* spawning */
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 07:03:33 +08:00
/* The following fields are used by call_rcu, hence own cacheline. */
raw_spinlock_t nocb_bypass_lock ____cacheline_internodealigned_in_smp;
struct rcu_cblist nocb_bypass; /* Lock-contention-bypass CB list. */
unsigned long nocb_bypass_first; /* Time (jiffies) of first enqueue. */
unsigned long nocb_nobypass_last; /* Last ->cblist enqueue (jiffies). */
int nocb_nobypass_count; /* # ->cblist enqueues at ^^^ time. */
rcu: Parallelize and economize NOCB kthread wakeups An 80-CPU system with a context-switch-heavy workload can require so many NOCB kthread wakeups that the RCU grace-period kthreads spend several tens of percent of a CPU just awakening things. This clearly will not scale well: If you add enough CPUs, the RCU grace-period kthreads would get behind, increasing grace-period latency. To avoid this problem, this commit divides the NOCB kthreads into leaders and followers, where the grace-period kthreads awaken the leaders each of whom in turn awakens its followers. By default, the number of groups of kthreads is the square root of the number of CPUs, but this default may be overridden using the rcutree.rcu_nocb_leader_stride boot parameter. This reduces the number of wakeups done per grace period by the RCU grace-period kthread by the square root of the number of CPUs, but of course by shifting those wakeups to the leaders. In addition, because the leaders do grace periods on behalf of their respective followers, the number of wakeups of the followers decreases by up to a factor of two. Instead of being awakened once when new callbacks arrive and again at the end of the grace period, the followers are awakened only at the end of the grace period. For a numerical example, in a 4096-CPU system, the grace-period kthread would awaken 64 leaders, each of which would awaken its 63 followers at the end of the grace period. This compares favorably with the 79 wakeups for the grace-period kthread on an 80-CPU system. Reported-by: Rik van Riel <riel@redhat.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2014-06-25 00:26:11 +08:00
/* The following fields are used by GP kthread, hence own cacheline. */
raw_spinlock_t nocb_gp_lock ____cacheline_internodealigned_in_smp;
u8 nocb_gp_sleep; /* Is the nocb GP thread asleep? */
u8 nocb_gp_bypass; /* Found a bypass on last scan? */
u8 nocb_gp_gp; /* GP to wait for on last scan? */
unsigned long nocb_gp_seq; /* If so, ->gp_seq to wait for. */
unsigned long nocb_gp_loops; /* # passes through wait code. */
rcu/nocb: Provide separate no-CBs grace-period kthreads Currently, there is one no-CBs rcuo kthread per CPU, and these kthreads are divided into groups. The first rcuo kthread to come online in a given group is that group's leader, and the leader both waits for grace periods and invokes its CPU's callbacks. The non-leader rcuo kthreads only invoke callbacks. This works well in the real-time/embedded environments for which it was intended because such environments tend not to generate all that many callbacks. However, given huge floods of callbacks, it is possible for the leader kthread to be stuck invoking callbacks while its followers wait helplessly while their callbacks pile up. This is a good recipe for an OOM, and rcutorture's new callback-flood capability does generate such OOMs. One strategy would be to wait until such OOMs start happening in production, but similar OOMs have in fact happened starting in 2018. It would therefore be wise to take a more proactive approach. This commit therefore features per-CPU rcuo kthreads that do nothing but invoke callbacks. Instead of having one of these kthreads act as leader, each group has a separate rcog kthread that handles grace periods for its group. Because these rcuog kthreads do not invoke callbacks, callback floods on one CPU no longer block callbacks from reaching the rcuc callback-invocation kthreads on other CPUs. This change does introduce additional kthreads, however: 1. The number of additional kthreads is about the square root of the number of CPUs, so that a 4096-CPU system would have only about 64 additional kthreads. Note that recent changes decreased the number of rcuo kthreads by a factor of two (CONFIG_PREEMPT=n) or even three (CONFIG_PREEMPT=y), so this still represents a significant improvement on most systems. 2. The leading "rcuo" of the rcuog kthreads should allow existing scripting to affinity these additional kthreads as needed, the same as for the rcuop and rcuos kthreads. (There are no longer any rcuob kthreads.) 3. A state-machine approach was considered and rejected. Although this would allow the rcuo kthreads to continue their dual leader/follower roles, it complicates callback invocation and makes it more difficult to consolidate rcuo callback invocation with existing softirq callback invocation. The introduction of rcuog kthreads should thus be acceptable. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-03-30 07:43:51 +08:00
struct swait_queue_head nocb_gp_wq; /* For nocb kthreads to sleep on. */
bool nocb_cb_sleep; /* Is the nocb CB thread asleep? */
rcu/nocb: Provide separate no-CBs grace-period kthreads Currently, there is one no-CBs rcuo kthread per CPU, and these kthreads are divided into groups. The first rcuo kthread to come online in a given group is that group's leader, and the leader both waits for grace periods and invokes its CPU's callbacks. The non-leader rcuo kthreads only invoke callbacks. This works well in the real-time/embedded environments for which it was intended because such environments tend not to generate all that many callbacks. However, given huge floods of callbacks, it is possible for the leader kthread to be stuck invoking callbacks while its followers wait helplessly while their callbacks pile up. This is a good recipe for an OOM, and rcutorture's new callback-flood capability does generate such OOMs. One strategy would be to wait until such OOMs start happening in production, but similar OOMs have in fact happened starting in 2018. It would therefore be wise to take a more proactive approach. This commit therefore features per-CPU rcuo kthreads that do nothing but invoke callbacks. Instead of having one of these kthreads act as leader, each group has a separate rcog kthread that handles grace periods for its group. Because these rcuog kthreads do not invoke callbacks, callback floods on one CPU no longer block callbacks from reaching the rcuc callback-invocation kthreads on other CPUs. This change does introduce additional kthreads, however: 1. The number of additional kthreads is about the square root of the number of CPUs, so that a 4096-CPU system would have only about 64 additional kthreads. Note that recent changes decreased the number of rcuo kthreads by a factor of two (CONFIG_PREEMPT=n) or even three (CONFIG_PREEMPT=y), so this still represents a significant improvement on most systems. 2. The leading "rcuo" of the rcuog kthreads should allow existing scripting to affinity these additional kthreads as needed, the same as for the rcuop and rcuos kthreads. (There are no longer any rcuob kthreads.) 3. A state-machine approach was considered and rejected. Although this would allow the rcuo kthreads to continue their dual leader/follower roles, it complicates callback invocation and makes it more difficult to consolidate rcuo callback invocation with existing softirq callback invocation. The introduction of rcuog kthreads should thus be acceptable. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-03-30 07:43:51 +08:00
struct task_struct *nocb_cb_kthread;
struct list_head nocb_head_rdp; /*
* Head of rcu_data list in wakeup chain,
* if rdp_gp.
*/
struct list_head nocb_entry_rdp; /* rcu_data node in wakeup chain. */
rcu/nocb: Add/del rdp to iterate from rcuog itself NOCB rdp's are part of a group whose list is iterated by the corresponding rdp leader. This list is RCU traversed because an rdp can be either added or deleted concurrently. Upon addition, a new iteration to the list after a synchronization point (a pair of LOCK/UNLOCK ->nocb_gp_lock) is forced to make sure: 1) we didn't miss a new element added in the middle of an iteration 2) we didn't ignore a whole subset of the list due to an element being quickly deleted and then re-added. 3) we prevent from probably other surprises... Although this layout is expected to be safe, it doesn't help anybody to sleep well. Simplify instead the nocb state toggling with moving the list modification from the nocb (de-)offloading workqueue to the rcuog kthreads instead. Whenever the rdp leader is expected to (re-)set the SEGCBLIST_KTHREAD_GP flag of a target rdp, the latter is queued so that the leader handles the flag flip along with adding or deleting the target rdp to the list to iterate. This way the list modification and iteration happen from the same kthread and those operations can't race altogether. As a bonus, the flags for each rdp don't need to be checked locklessly before each iteration, which is one less opportunity to produce nightmares. Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Cc: Neeraj Upadhyay <quic_neeraju@quicinc.com> Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Uladzislau Rezki <uladzislau.rezki@sony.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Zqiang <qiang1.zhang@intel.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Reviewed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
2022-04-19 20:23:18 +08:00
struct rcu_data *nocb_toggling_rdp; /* rdp queued for (de-)offloading */
rcu: Parallelize and economize NOCB kthread wakeups An 80-CPU system with a context-switch-heavy workload can require so many NOCB kthread wakeups that the RCU grace-period kthreads spend several tens of percent of a CPU just awakening things. This clearly will not scale well: If you add enough CPUs, the RCU grace-period kthreads would get behind, increasing grace-period latency. To avoid this problem, this commit divides the NOCB kthreads into leaders and followers, where the grace-period kthreads awaken the leaders each of whom in turn awakens its followers. By default, the number of groups of kthreads is the square root of the number of CPUs, but this default may be overridden using the rcutree.rcu_nocb_leader_stride boot parameter. This reduces the number of wakeups done per grace period by the RCU grace-period kthread by the square root of the number of CPUs, but of course by shifting those wakeups to the leaders. In addition, because the leaders do grace periods on behalf of their respective followers, the number of wakeups of the followers decreases by up to a factor of two. Instead of being awakened once when new callbacks arrive and again at the end of the grace period, the followers are awakened only at the end of the grace period. For a numerical example, in a 4096-CPU system, the grace-period kthread would awaken 64 leaders, each of which would awaken its 63 followers at the end of the grace period. This compares favorably with the 79 wakeups for the grace-period kthread on an 80-CPU system. Reported-by: Rik van Riel <riel@redhat.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2014-06-25 00:26:11 +08:00
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 07:03:33 +08:00
/* The following fields are used by CB kthread, hence new cacheline. */
struct rcu_data *nocb_gp_rdp ____cacheline_internodealigned_in_smp;
/* GP rdp takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/* 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;
unsigned long rcuc_activity;
/* 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. */
bool rcu_iw_pending; /* Is ->rcu_iw pending? */
unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */
unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */
short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */
unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */
short rcu_onl_gp_flags; /* ->gp_flags at last online. */
unsigned long last_fqs_resched; /* Time of last rcu_resched(). */
unsigned long last_sched_clock; /* Jiffies of last rcu_sched_clock_irq(). */
rcu: Add RCU stall diagnosis information Because RCU CPU stall warnings are driven from the scheduling-clock interrupt handler, a workload consisting of a very large number of short-duration hardware interrupts can result in misleading stall-warning messages. On systems supporting only a single level of interrupts, that is, where interrupts handlers cannot be interrupted, this can produce misleading diagnostics. The stack traces will show the innocent-bystander interrupted task, not the interrupts that are at the very least exacerbating the stall. This situation can be improved by displaying the number of interrupts and the CPU time that they have consumed. Diagnosing other types of stalls can be eased by also providing the count of softirqs and the CPU time that they consumed as well as the number of context switches and the task-level CPU time consumed. Consider the following output given this change: rcu: INFO: rcu_preempt self-detected stall on CPU rcu: 0-....: (1250 ticks this GP) <omitted> rcu: hardirqs softirqs csw/system rcu: number: 624 45 0 rcu: cputime: 69 1 2425 ==> 2500(ms) This output shows that the number of hard and soft interrupts is small, there are no context switches, and the system takes up a lot of time. This indicates that the current task is looping with preemption disabled. The impact on system performance is negligible because snapshot is recorded only once for all continuous RCU stalls. This added debugging information is suppressed by default and can be enabled by building the kernel with CONFIG_RCU_CPU_STALL_CPUTIME=y or by booting with rcupdate.rcu_cpu_stall_cputime=1. Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Reviewed-by: Mukesh Ojha <quic_mojha@quicinc.com> Reviewed-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-11-19 17:25:06 +08:00
struct rcu_snap_record snap_record; /* Snapshot of core stats at half of */
/* the first RCU stall timeout */
long lazy_len; /* Length of buffered lazy callbacks. */
int cpu;
};
/* Values for nocb_defer_wakeup field in struct rcu_data. */
#define RCU_NOCB_WAKE_NOT 0
#define RCU_NOCB_WAKE_BYPASS 1
#define RCU_NOCB_WAKE_LAZY 2
#define RCU_NOCB_WAKE 3
#define RCU_NOCB_WAKE_FORCE 4
#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
/* For jiffies_till_first_fqs and */
/* and jiffies_till_next_fqs. */
#define RCU_JIFFIES_FQS_DIV 256 /* Very large systems need more */
/* delay between bouts of */
/* quiescent-state forcing. */
#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time to take */
/* at least one scheduling clock */
/* irq before ratting on them. */
#define rcu_wait(cond) \
do { \
for (;;) { \
set_current_state(TASK_INTERRUPTIBLE); \
if (cond) \
break; \
schedule(); \
} \
__set_current_state(TASK_RUNNING); \
} while (0)
/*
* RCU global state, including node hierarchy. This hierarchy is
* represented in "heap" form in a dense array. The root (first level)
* of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
* level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
* and the third level in ->node[m+1] and following (->node[m+1] referenced
* by ->level[2]). The number of levels is determined by the number of
* CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy"
* consisting of a single rcu_node.
*/
struct rcu_state {
struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */
struct rcu_node *level[RCU_NUM_LVLS + 1];
/* Hierarchy levels (+1 to */
/* shut bogus gcc warning) */
int ncpus; /* # CPUs seen so far. */
rcu: Fix single-CPU check in rcu_blocking_is_gp() Currently, for CONFIG_PREEMPTION=n kernels, rcu_blocking_is_gp() uses num_online_cpus() to determine whether there is only one CPU online. When there is only a single CPU online, the simple fact that synchronize_rcu() could be legally called implies that a full grace period has elapsed. Therefore, in the single-CPU case, synchronize_rcu() simply returns immediately. Unfortunately, num_online_cpus() is unreliable while a CPU-hotplug operation is transitioning to or from single-CPU operation because: 1. num_online_cpus() uses atomic_read(&__num_online_cpus) to locklessly sample the number of online CPUs. The hotplug locks are not held, which means that an incoming CPU can concurrently update this count. This in turn means that an RCU read-side critical section on the incoming CPU might observe updates prior to the grace period, but also that this critical section might extend beyond the end of the optimized synchronize_rcu(). This breaks RCU's fundamental guarantee. 2. In addition, num_online_cpus() does no ordering, thus providing another way that RCU's fundamental guarantee can be broken by the current code. 3. The most probable failure mode happens on outgoing CPUs. The outgoing CPU updates the count of online CPUs in the CPUHP_TEARDOWN_CPU stop-machine handler, which is fine in and of itself due to preemption being disabled at the call to num_online_cpus(). Unfortunately, after that stop-machine handler returns, the CPU takes one last trip through the scheduler (which has RCU readers) and, after the resulting context switch, one final dive into the idle loop. During this time, RCU needs to keep track of two CPUs, but num_online_cpus() will say that there is only one, which in turn means that the surviving CPU will incorrectly ignore the outgoing CPU's RCU read-side critical sections. This problem is illustrated by the following litmus test in which P0() corresponds to synchronize_rcu() and P1() corresponds to the incoming CPU. The herd7 tool confirms that the "exists" clause can be satisfied, thus demonstrating that this breakage can happen according to the Linux kernel memory model. { int x = 0; atomic_t numonline = ATOMIC_INIT(1); } P0(int *x, atomic_t *numonline) { int r0; WRITE_ONCE(*x, 1); r0 = atomic_read(numonline); if (r0 == 1) { smp_mb(); } else { synchronize_rcu(); } WRITE_ONCE(*x, 2); } P1(int *x, atomic_t *numonline) { int r0; int r1; atomic_inc(numonline); smp_mb(); rcu_read_lock(); r0 = READ_ONCE(*x); smp_rmb(); r1 = READ_ONCE(*x); rcu_read_unlock(); } locations [x;numonline;] exists (1:r0=0 /\ 1:r1=2) It is important to note that these problems arise only when the system is transitioning to or from single-CPU operation. One solution would be to hold the CPU-hotplug locks while sampling num_online_cpus(), which was in fact the intent of the (redundant) preempt_disable() and preempt_enable() surrounding this call to num_online_cpus(). Actually blocking CPU hotplug would not only result in excessive overhead, but would also unnecessarily impede CPU-hotplug operations. This commit therefore follows long-standing RCU tradition by maintaining a separate RCU-specific set of CPU-hotplug books. This separate set of books is implemented by a new ->n_online_cpus field in the rcu_state structure that maintains RCU's count of the online CPUs. This count is incremented early in the CPU-online process, so that the critical transition away from single-CPU operation will occur when there is only a single CPU. Similarly for the critical transition to single-CPU operation, the counter is decremented late in the CPU-offline process, again while there is only a single CPU. Because there is only ever a single CPU when the ->n_online_cpus field undergoes the critical 1->2 and 2->1 transitions, full memory ordering and mutual exclusion is provided implicitly and, better yet, for free. In the case where the CPU is coming online, nothing will happen until the current CPU helps it come online. Therefore, the new CPU will see all accesses prior to the optimized grace period, which means that RCU does not need to further delay this new CPU. In the case where the CPU is going offline, the outgoing CPU is totally out of the picture before the optimized grace period starts, which means that this outgoing CPU cannot see any of the accesses following that grace period. Again, RCU needs no further interaction with the outgoing CPU. This does mean that synchronize_rcu() will unnecessarily do a few grace periods the hard way just before the second CPU comes online and just after the second-to-last CPU goes offline, but it is not worth optimizing this uncommon case. Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Neeraj Upadhyay <neeraju@codeaurora.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-09-23 15:29:33 +08:00
int n_online_cpus; /* # CPUs online for RCU. */
/* The following fields are guarded by the root rcu_node's lock. */
unsigned long gp_seq ____cacheline_internodealigned_in_smp;
/* Grace-period sequence #. */
unsigned long gp_max; /* Maximum GP duration in */
/* jiffies. */
struct task_struct *gp_kthread; /* Task for grace periods. */
rcu: Use simple wait queues where possible in rcutree As of commit dae6e64d2bcfd ("rcu: Introduce proper blocking to no-CBs kthreads GP waits") the RCU subsystem started making use of wait queues. Here we convert all additions of RCU wait queues to use simple wait queues, since they don't need the extra overhead of the full wait queue features. Originally this was done for RT kernels[1], since we would get things like... BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 in_atomic(): 1, irqs_disabled(): 1, pid: 8, name: rcu_preempt Pid: 8, comm: rcu_preempt Not tainted Call Trace: [<ffffffff8106c8d0>] __might_sleep+0xd0/0xf0 [<ffffffff817d77b4>] rt_spin_lock+0x24/0x50 [<ffffffff8106fcf6>] __wake_up+0x36/0x70 [<ffffffff810c4542>] rcu_gp_kthread+0x4d2/0x680 [<ffffffff8105f910>] ? __init_waitqueue_head+0x50/0x50 [<ffffffff810c4070>] ? rcu_gp_fqs+0x80/0x80 [<ffffffff8105eabb>] kthread+0xdb/0xe0 [<ffffffff8106b912>] ? finish_task_switch+0x52/0x100 [<ffffffff817e0754>] kernel_thread_helper+0x4/0x10 [<ffffffff8105e9e0>] ? __init_kthread_worker+0x60/0x60 [<ffffffff817e0750>] ? gs_change+0xb/0xb ...and hence simple wait queues were deployed on RT out of necessity (as simple wait uses a raw lock), but mainline might as well take advantage of the more streamline support as well. [1] This is a carry forward of work from v3.10-rt; the original conversion was by Thomas on an earlier -rt version, and Sebastian extended it to additional post-3.10 added RCU waiters; here I've added a commit log and unified the RCU changes into one, and uprev'd it to match mainline RCU. Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-rt-users@vger.kernel.org Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1455871601-27484-6-git-send-email-wagi@monom.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-02-19 16:46:41 +08:00
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 ^^^. */
unsigned long gp_seq_polled; /* GP seq for polled API. */
unsigned long gp_seq_polled_snap; /* ->gp_seq_polled at normal GP start. */
rcu: Make polled grace-period API account for expedited grace periods Currently, this code could splat: oldstate = get_state_synchronize_rcu(); synchronize_rcu_expedited(); WARN_ON_ONCE(!poll_state_synchronize_rcu(oldstate)); This situation is counter-intuitive and user-unfriendly. After all, there really was a perfectly valid full grace period right after the call to get_state_synchronize_rcu(), so why shouldn't poll_state_synchronize_rcu() know about it? This commit therefore makes the polled grace-period API aware of expedited grace periods in addition to the normal grace periods that it is already aware of. With this change, the above code is guaranteed not to splat. Please note that the above code can still splat due to counter wrap on the one hand and situations involving partially overlapping normal/expedited grace periods on the other. On 64-bit systems, the second is of course much more likely than the first. It is possible to modify this approach to prevent overlapping grace periods from causing splats, but only at the expense of greatly increasing the probability of counter wrap, as in within milliseconds on 32-bit systems and within minutes on 64-bit systems. This commit is in preparation for polled expedited grace periods. Link: https://lore.kernel.org/all/20220121142454.1994916-1-bfoster@redhat.com/ Link: https://docs.google.com/document/d/1RNKWW9jQyfjxw2E8dsXVTdvZYh0HnYeSHDKog9jhdN8/edit?usp=sharing Cc: Brian Foster <bfoster@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ian Kent <raven@themaw.net> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-14 21:56:35 +08:00
unsigned long gp_seq_polled_exp_snap; /* ->gp_seq_polled at expedited GP start. */
/* End of fields guarded by root rcu_node's lock. */
struct mutex barrier_mutex; /* Guards barrier fields. */
atomic_t barrier_cpu_count; /* # CPUs waiting on. */
struct completion barrier_completion; /* Wake at barrier end. */
unsigned long barrier_sequence; /* ++ at start and end of */
/* rcu_barrier(). */
/* End of fields guarded by barrier_mutex. */
rcu: Make rcu_barrier() no longer block CPU-hotplug operations This commit removes the cpus_read_lock() and cpus_read_unlock() calls from rcu_barrier(), thus allowing CPUs to come and go during the course of rcu_barrier() execution. Posting of the ->barrier_head callbacks does synchronize with portions of RCU's CPU-hotplug notifiers, but these locks are held for short time periods on both sides. Thus, full CPU-hotplug operations could both start and finish during the execution of a given rcu_barrier() invocation. Additional synchronization is provided by a global ->barrier_lock. Since the ->barrier_lock is only used during rcu_barrier() execution and during onlining/offlining a CPU, the contention for this lock should be low. It might be tempting to make use of a per-CPU lock just on general principles, but straightforward attempts to do this have the problems shown below. Initial state: 3 CPUs present, CPU 0 and CPU1 do not have any callback and CPU2 has callbacks. 1. CPU0 calls rcu_barrier(). 2. CPU1 starts offlining for CPU2. CPU1 calls rcutree_migrate_callbacks(). rcu_barrier_entrain() is called from rcutree_migrate_callbacks(), with CPU2's rdp->barrier_lock. It does not entrain ->barrier_head for CPU2, as rcu_barrier() on CPU0 hasn't started the barrier sequence (by calling rcu_seq_start(&rcu_state.barrier_sequence)) yet. 3. CPU0 starts new barrier sequence. It iterates over CPU0 and CPU1, after acquiring their per-cpu ->barrier_lock and finds 0 segcblist length. It updates ->barrier_seq_snap for CPU0 and CPU1 and continues loop iteration to CPU2. for_each_possible_cpu(cpu) { raw_spin_lock_irqsave(&rdp->barrier_lock, flags); if (!rcu_segcblist_n_cbs(&rdp->cblist)) { WRITE_ONCE(rdp->barrier_seq_snap, gseq); raw_spin_unlock_irqrestore(&rdp->barrier_lock, flags); rcu_barrier_trace(TPS("NQ"), cpu, rcu_state.barrier_sequence); continue; } 4. rcutree_migrate_callbacks() completes execution on CPU1. Segcblist len for CPU2 becomes 0. 5. The loop iteration on CPU0, checks rcu_segcblist_n_cbs(&rdp->cblist) for CPU2 and completes the loop iteration after setting ->barrier_seq_snap. 6. As there isn't any ->barrier_head callback entrained; at this point, rcu_barrier() in CPU0 returns. 7. The callbacks, which migrated from CPU2 to CPU1, execute. Straightforward per-CPU locking is also subject to the following race condition noted by Boqun Feng: 1. CPU0 calls rcu_barrier(), starting a new barrier sequence by invoking rcu_seq_start() and init_completion(), but does not yet initialize rcu_state.barrier_cpu_count. 2. CPU1 starts offlining for CPU2, calling rcutree_migrate_callbacks(), which in turn calls rcu_barrier_entrain() holding CPU2's. rdp->barrier_lock. It then entrains ->barrier_head for CPU2 and atomically increments rcu_state.barrier_cpu_count, which is unfortunately not yet initialized to the value 2. 3. The just-entrained RCU callback is invoked. It atomically decrements rcu_state.barrier_cpu_count and sees that it is now zero. This callback therefore invokes complete(). 4. CPU0 continues executing rcu_barrier(), but is not blocked by its call to wait_for_completion(). This results in rcu_barrier() returning before all pre-existing callbacks have been invoked, which is a bug. Therefore, synchronization is provided by rcu_state.barrier_lock, which is also held across the initialization sequence, especially the rcu_seq_start() and the atomic_set() that sets rcu_state.barrier_cpu_count to the value 2. In addition, this lock is held when entraining the rcu_barrier() callback, when deciding whether or not a CPU has callbacks that rcu_barrier() must wait on, when setting the ->qsmaskinitnext for incoming CPUs, and when migrating callbacks from a CPU that is going offline. Reviewed-by: Frederic Weisbecker <frederic@kernel.org> Co-developed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com> Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2021-12-15 05:35:17 +08:00
raw_spinlock_t barrier_lock; /* Protects ->barrier_seq_snap. */
struct mutex exp_mutex; /* Serialize expedited GP. */
struct mutex exp_wake_mutex; /* Serialize wakeup. */
unsigned long expedited_sequence; /* Take a ticket. */
atomic_t expedited_need_qs; /* # CPUs left to check in. */
rcu: Use simple wait queues where possible in rcutree As of commit dae6e64d2bcfd ("rcu: Introduce proper blocking to no-CBs kthreads GP waits") the RCU subsystem started making use of wait queues. Here we convert all additions of RCU wait queues to use simple wait queues, since they don't need the extra overhead of the full wait queue features. Originally this was done for RT kernels[1], since we would get things like... BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 in_atomic(): 1, irqs_disabled(): 1, pid: 8, name: rcu_preempt Pid: 8, comm: rcu_preempt Not tainted Call Trace: [<ffffffff8106c8d0>] __might_sleep+0xd0/0xf0 [<ffffffff817d77b4>] rt_spin_lock+0x24/0x50 [<ffffffff8106fcf6>] __wake_up+0x36/0x70 [<ffffffff810c4542>] rcu_gp_kthread+0x4d2/0x680 [<ffffffff8105f910>] ? __init_waitqueue_head+0x50/0x50 [<ffffffff810c4070>] ? rcu_gp_fqs+0x80/0x80 [<ffffffff8105eabb>] kthread+0xdb/0xe0 [<ffffffff8106b912>] ? finish_task_switch+0x52/0x100 [<ffffffff817e0754>] kernel_thread_helper+0x4/0x10 [<ffffffff8105e9e0>] ? __init_kthread_worker+0x60/0x60 [<ffffffff817e0750>] ? gs_change+0xb/0xb ...and hence simple wait queues were deployed on RT out of necessity (as simple wait uses a raw lock), but mainline might as well take advantage of the more streamline support as well. [1] This is a carry forward of work from v3.10-rt; the original conversion was by Thomas on an earlier -rt version, and Sebastian extended it to additional post-3.10 added RCU waiters; here I've added a commit log and unified the RCU changes into one, and uprev'd it to match mainline RCU. Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-rt-users@vger.kernel.org Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1455871601-27484-6-git-send-email-wagi@monom.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-02-19 16:46:41 +08:00
struct swait_queue_head expedited_wq; /* Wait for check-ins. */
int ncpus_snap; /* # CPUs seen last time. */
u8 cbovld; /* Callback overload now? */
u8 cbovldnext; /* ^ ^ next time? */
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
unsigned long jiffies_kick_kthreads; /* Time at which to kick */
/* kthreads, if configured. */
unsigned long n_force_qs; /* Number of calls to */
/* force_quiescent_state(). */
unsigned long gp_start; /* Time at which GP started, */
/* but in jiffies. */
unsigned long gp_end; /* Time last GP ended, again */
/* in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
unsigned long gp_req_activity; /* Time of last GP request */
/* in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
unsigned long jiffies_resched; /* Time at which to resched */
/* a reluctant CPU. */
unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */
/* GP start. */
const char *name; /* Name of structure. */
char abbr; /* Abbreviated name. */
rcu: Fix grace-period hangs due to race with CPU offline Without special fail-safe quiescent-state-propagation checks, grace-period hangs can result from the following scenario: 1. CPU 1 goes offline. 2. Because CPU 1 is the only CPU in the system blocking the current grace period, the grace period ends as soon as rcu_cleanup_dying_idle_cpu()'s call to rcu_report_qs_rnp() returns. 3. At this point, the leaf rcu_node structure's ->lock is no longer held: rcu_report_qs_rnp() has released it, as it must in order to awaken the RCU grace-period kthread. 4. At this point, that same leaf rcu_node structure's ->qsmaskinitnext field still records CPU 1 as being online. This is absolutely necessary because the scheduler uses RCU (in this case on the wake-up path while awakening RCU's grace-period kthread), and ->qsmaskinitnext contains RCU's idea as to which CPUs are online. Therefore, invoking rcu_report_qs_rnp() after clearing CPU 1's bit from ->qsmaskinitnext would result in a lockdep-RCU splat due to RCU being used from an offline CPU. 5. RCU's grace-period kthread awakens, sees that the old grace period has completed and that a new one is needed. It therefore starts a new grace period, but because CPU 1's leaf rcu_node structure's ->qsmaskinitnext field still shows CPU 1 as being online, this new grace period is initialized to wait for a quiescent state from the now-offline CPU 1. 6. Without the fail-safe force-quiescent-state checks, there would be no quiescent state from the now-offline CPU 1, which would eventually result in RCU CPU stall warnings and memory exhaustion. It would be good to get rid of the special fail-safe quiescent-state propagation checks, and thus it would be good to fix things so that the above scenario cannot happen. This commit therefore adds a new ->ofl_lock to the rcu_state structure. This lock is held by rcu_gp_init() across the applying of buffered online and offline operations to the rcu_node tree, and it is also held by rcu_cleanup_dying_idle_cpu() when buffering a new offline operation. This prevents rcu_gp_init() from acquiring the leaf rcu_node structure's lock during the interval between when rcu_cleanup_dying_idle_cpu() invokes rcu_report_qs_rnp(), which releases ->lock and the re-acquisition of that same lock. This in turn prevents the failure scenario outlined above, and will hopefully eventually allow removal of the offline-CPU checks from the force-quiescent-state code path. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2018-05-26 10:23:09 +08:00
arch_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
rcu: Fix grace-period hangs due to race with CPU offline Without special fail-safe quiescent-state-propagation checks, grace-period hangs can result from the following scenario: 1. CPU 1 goes offline. 2. Because CPU 1 is the only CPU in the system blocking the current grace period, the grace period ends as soon as rcu_cleanup_dying_idle_cpu()'s call to rcu_report_qs_rnp() returns. 3. At this point, the leaf rcu_node structure's ->lock is no longer held: rcu_report_qs_rnp() has released it, as it must in order to awaken the RCU grace-period kthread. 4. At this point, that same leaf rcu_node structure's ->qsmaskinitnext field still records CPU 1 as being online. This is absolutely necessary because the scheduler uses RCU (in this case on the wake-up path while awakening RCU's grace-period kthread), and ->qsmaskinitnext contains RCU's idea as to which CPUs are online. Therefore, invoking rcu_report_qs_rnp() after clearing CPU 1's bit from ->qsmaskinitnext would result in a lockdep-RCU splat due to RCU being used from an offline CPU. 5. RCU's grace-period kthread awakens, sees that the old grace period has completed and that a new one is needed. It therefore starts a new grace period, but because CPU 1's leaf rcu_node structure's ->qsmaskinitnext field still shows CPU 1 as being online, this new grace period is initialized to wait for a quiescent state from the now-offline CPU 1. 6. Without the fail-safe force-quiescent-state checks, there would be no quiescent state from the now-offline CPU 1, which would eventually result in RCU CPU stall warnings and memory exhaustion. It would be good to get rid of the special fail-safe quiescent-state propagation checks, and thus it would be good to fix things so that the above scenario cannot happen. This commit therefore adds a new ->ofl_lock to the rcu_state structure. This lock is held by rcu_gp_init() across the applying of buffered online and offline operations to the rcu_node tree, and it is also held by rcu_cleanup_dying_idle_cpu() when buffering a new offline operation. This prevents rcu_gp_init() from acquiring the leaf rcu_node structure's lock during the interval between when rcu_cleanup_dying_idle_cpu() invokes rcu_report_qs_rnp(), which releases ->lock and the re-acquisition of that same lock. This in turn prevents the failure scenario outlined above, and will hopefully eventually allow removal of the offline-CPU checks from the force-quiescent-state code path. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2018-05-26 10:23:09 +08:00
/* Synchronize offline with */
/* GP pre-initialization. */
int nocb_is_setup; /* nocb is setup from boot */
};
/* Values for rcu_state structure's gp_flags field. */
#define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */
#define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */
#define RCU_GP_FLAG_OVLD 0x4 /* Experiencing callback overload. */
/* Values for rcu_state structure's gp_state field. */
#define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */
#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */
#define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */
#define RCU_GP_ONOFF 3 /* Grace-period initialization hotplug. */
#define RCU_GP_INIT 4 /* Grace-period initialization. */
#define RCU_GP_WAIT_FQS 5 /* Wait for force-quiescent-state time. */
#define RCU_GP_DOING_FQS 6 /* Wait done for force-quiescent-state time. */
#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */
#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */
/*
* 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.
*/
#ifdef CONFIG_PREEMPT_RCU
#define RCU_ABBR 'p'
#define RCU_NAME_RAW "rcu_preempt"
#else /* #ifdef CONFIG_PREEMPT_RCU */
#define RCU_ABBR 's'
#define RCU_NAME_RAW "rcu_sched"
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
#ifndef CONFIG_TRACING
#define RCU_NAME RCU_NAME_RAW
#else /* #ifdef CONFIG_TRACING */
static char rcu_name[] = RCU_NAME_RAW;
static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
#define RCU_NAME rcu_name
#endif /* #else #ifdef CONFIG_TRACING */
/* Forward declarations for tree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_qs(void);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
rcu: Fix grace-period-stall bug on large systems with CPU hotplug When the last CPU of a given leaf rcu_node structure goes offline, all of the tasks queued on that leaf rcu_node structure (due to having blocked in their current RCU read-side critical sections) are requeued onto the root rcu_node structure. This requeuing is carried out by rcu_preempt_offline_tasks(). However, it is possible that these queued tasks are the only thing preventing the leaf rcu_node structure from reporting a quiescent state up the rcu_node hierarchy. Unfortunately, the old code would fail to do this reporting, resulting in a grace-period stall given the following sequence of events: 1. Kernel built for more than 32 CPUs on 32-bit systems or for more than 64 CPUs on 64-bit systems, so that there is more than one rcu_node structure. (Or CONFIG_RCU_FANOUT is artificially set to a number smaller than CONFIG_NR_CPUS.) 2. The kernel is built with CONFIG_TREE_PREEMPT_RCU. 3. A task running on a CPU associated with a given leaf rcu_node structure blocks while in an RCU read-side critical section -and- that CPU has not yet passed through a quiescent state for the current RCU grace period. This will cause the task to be queued on the leaf rcu_node's blocked_tasks[] array, in particular, on the element of this array corresponding to the current grace period. 4. Each of the remaining CPUs corresponding to this same leaf rcu_node structure pass through a quiescent state. However, the task is still in its RCU read-side critical section, so these quiescent states cannot be reported further up the rcu_node hierarchy. Nevertheless, all bits in the leaf rcu_node structure's ->qsmask field are now zero. 5. Each of the remaining CPUs go offline. (The events in step #4 and #5 can happen in any order as long as each CPU passes through a quiescent state before going offline.) 6. When the last CPU goes offline, __rcu_offline_cpu() will invoke rcu_preempt_offline_tasks(), which will move the task to the root rcu_node structure, but without reporting a quiescent state up the rcu_node hierarchy (and this failure to report a quiescent state is the bug). But because this leaf rcu_node structure's ->qsmask field is already zero and its ->block_tasks[] entries are all empty, force_quiescent_state() will skip this rcu_node structure. Therefore, grace periods are now hung. This patch abstracts some code out of rcu_read_unlock_special(), calling the result task_quiet() by analogy with cpu_quiet(), and invokes task_quiet() from both rcu_read_lock_special() and __rcu_offline_cpu(). Invoking task_quiet() from __rcu_offline_cpu() reports the quiescent state up the rcu_node hierarchy, fixing the bug. This ends up requiring a separate lock_class_key per level of the rcu_node hierarchy, which this patch also provides. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12589088301770-git-send-email-> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-23 00:53:48 +08:00
#ifdef CONFIG_HOTPLUG_CPU
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
rcu: Fix grace-period-stall bug on large systems with CPU hotplug When the last CPU of a given leaf rcu_node structure goes offline, all of the tasks queued on that leaf rcu_node structure (due to having blocked in their current RCU read-side critical sections) are requeued onto the root rcu_node structure. This requeuing is carried out by rcu_preempt_offline_tasks(). However, it is possible that these queued tasks are the only thing preventing the leaf rcu_node structure from reporting a quiescent state up the rcu_node hierarchy. Unfortunately, the old code would fail to do this reporting, resulting in a grace-period stall given the following sequence of events: 1. Kernel built for more than 32 CPUs on 32-bit systems or for more than 64 CPUs on 64-bit systems, so that there is more than one rcu_node structure. (Or CONFIG_RCU_FANOUT is artificially set to a number smaller than CONFIG_NR_CPUS.) 2. The kernel is built with CONFIG_TREE_PREEMPT_RCU. 3. A task running on a CPU associated with a given leaf rcu_node structure blocks while in an RCU read-side critical section -and- that CPU has not yet passed through a quiescent state for the current RCU grace period. This will cause the task to be queued on the leaf rcu_node's blocked_tasks[] array, in particular, on the element of this array corresponding to the current grace period. 4. Each of the remaining CPUs corresponding to this same leaf rcu_node structure pass through a quiescent state. However, the task is still in its RCU read-side critical section, so these quiescent states cannot be reported further up the rcu_node hierarchy. Nevertheless, all bits in the leaf rcu_node structure's ->qsmask field are now zero. 5. Each of the remaining CPUs go offline. (The events in step #4 and #5 can happen in any order as long as each CPU passes through a quiescent state before going offline.) 6. When the last CPU goes offline, __rcu_offline_cpu() will invoke rcu_preempt_offline_tasks(), which will move the task to the root rcu_node structure, but without reporting a quiescent state up the rcu_node hierarchy (and this failure to report a quiescent state is the bug). But because this leaf rcu_node structure's ->qsmask field is already zero and its ->block_tasks[] entries are all empty, force_quiescent_state() will skip this rcu_node structure. Therefore, grace periods are now hung. This patch abstracts some code out of rcu_read_unlock_special(), calling the result task_quiet() by analogy with cpu_quiet(), and invokes task_quiet() from both rcu_read_lock_special() and __rcu_offline_cpu(). Invoking task_quiet() from __rcu_offline_cpu() reports the quiescent state up the rcu_node hierarchy, fixing the bug. This ends up requiring a separate lock_class_key per level of the rcu_node hierarchy, which this patch also provides. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12589088301770-git-send-email-> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-23 00:53:48 +08:00
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
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_sched_clock_irq(int user);
static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static bool rcu_is_callbacks_kthread(struct rcu_data *rdp);
static void rcu_cpu_kthread_setup(unsigned int cpu);
rcu: Make RCU priority boosting work on single-CPU rcu_node structures When any CPU comes online, it checks to see if an RCU-boost kthread has already been created for that CPU's leaf rcu_node structure, and if not, it creates one. Unfortunately, it also verifies that this leaf rcu_node structure actually has at least one online CPU, and if not, it declines to create the kthread. Although this behavior makes sense during early boot, especially on systems that claim far more CPUs than they actually have, it makes no sense for the first CPU to come online for a given rcu_node structure. There is no point in checking because we know there is a CPU on its way in. The problem is that timing differences can cause this incoming CPU to not yet be reflected in the various bit masks even at rcutree_online_cpu() time, and there is no chance at rcutree_prepare_cpu() time. Plus it would be better to create the RCU-boost kthread at rcutree_prepare_cpu() to handle the case where the CPU is involved in an RCU priority inversion very shortly after it comes online. This commit therefore moves the checking to rcu_prepare_kthreads(), which is called only at early boot, when the check is appropriate. In addition, it makes rcutree_prepare_cpu() invoke rcu_spawn_one_boost_kthread(), which no longer does any checking for online CPUs. With this change, RCU priority boosting tests now pass for short rcutorture runs, even with single-CPU leaf rcu_node structures. Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Scott Wood <swood@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2021-04-06 11:42:09 +08:00
static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
rcu: Process offlining and onlining only at grace-period start Races between CPU hotplug and grace periods can be difficult to resolve, so the ->onoff_mutex is used to exclude the two events. Unfortunately, this means that it is impossible for an outgoing CPU to perform the last bits of its offlining from its last pass through the idle loop, because sleeplocks cannot be acquired in that context. This commit avoids these problems by buffering online and offline events in a new ->qsmaskinitnext field in the leaf rcu_node structures. When a grace period starts, the events accumulated in this mask are applied to the ->qsmaskinit field, and, if needed, up the rcu_node tree. The special case of all CPUs corresponding to a given leaf rcu_node structure being offline while there are still elements in that structure's ->blkd_tasks list is handled using a new ->wait_blkd_tasks field. In this case, propagating the offline bits up the tree is deferred until the beginning of the grace period after all of the tasks have exited their RCU read-side critical sections and removed themselves from the list, at which point the ->wait_blkd_tasks flag is cleared. If one of that leaf rcu_node structure's CPUs comes back online before the list empties, then the ->wait_blkd_tasks flag is simply cleared. This of course means that RCU's notion of which CPUs are offline can be out of date. This is OK because RCU need only wait on CPUs that were online at the time that the grace period started. In addition, RCU's force-quiescent-state actions will handle the case where a CPU goes offline after the grace period starts. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2015-01-24 13:52:37 +08:00
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-22 03:50:01 +08:00
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
rcu: Use simple wait queues where possible in rcutree As of commit dae6e64d2bcfd ("rcu: Introduce proper blocking to no-CBs kthreads GP waits") the RCU subsystem started making use of wait queues. Here we convert all additions of RCU wait queues to use simple wait queues, since they don't need the extra overhead of the full wait queue features. Originally this was done for RT kernels[1], since we would get things like... BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 in_atomic(): 1, irqs_disabled(): 1, pid: 8, name: rcu_preempt Pid: 8, comm: rcu_preempt Not tainted Call Trace: [<ffffffff8106c8d0>] __might_sleep+0xd0/0xf0 [<ffffffff817d77b4>] rt_spin_lock+0x24/0x50 [<ffffffff8106fcf6>] __wake_up+0x36/0x70 [<ffffffff810c4542>] rcu_gp_kthread+0x4d2/0x680 [<ffffffff8105f910>] ? __init_waitqueue_head+0x50/0x50 [<ffffffff810c4070>] ? rcu_gp_fqs+0x80/0x80 [<ffffffff8105eabb>] kthread+0xdb/0xe0 [<ffffffff8106b912>] ? finish_task_switch+0x52/0x100 [<ffffffff817e0754>] kernel_thread_helper+0x4/0x10 [<ffffffff8105e9e0>] ? __init_kthread_worker+0x60/0x60 [<ffffffff817e0750>] ? gs_change+0xb/0xb ...and hence simple wait queues were deployed on RT out of necessity (as simple wait uses a raw lock), but mainline might as well take advantage of the more streamline support as well. [1] This is a carry forward of work from v3.10-rt; the original conversion was by Thomas on an earlier -rt version, and Sebastian extended it to additional post-3.10 added RCU waiters; here I've added a commit log and unified the RCU changes into one, and uprev'd it to match mainline RCU. Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-rt-users@vger.kernel.org Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1455871601-27484-6-git-send-email-wagi@monom.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-02-19 16:46:41 +08:00
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
static void rcu_init_one_nocb(struct rcu_node *rnp);
static bool wake_nocb_gp(struct rcu_data *rdp, bool force);
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 07:03:33 +08:00
static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
unsigned long j, bool lazy);
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 07:03:33 +08:00
static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
bool *was_alldone, unsigned long flags,
bool lazy);
static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
unsigned long flags);
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level);
static bool do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_cpu_nocb_kthread(int cpu);
static void show_rcu_nocb_state(struct rcu_data *rdp);
static void rcu_nocb_lock(struct rcu_data *rdp);
static void rcu_nocb_unlock(struct rcu_data *rdp);
static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
unsigned long flags);
rcu/nocb: Add bypass callback queueing Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs takes advantage of unrelated grace periods, thus reducing the memory footprint in the face of floods of call_rcu() invocations. However, the ->cblist field is a more-complex rcu_segcblist structure which must be protected via locking. Even though there are only three entities which can acquire this lock (the CPU invoking call_rcu(), the no-CBs grace-period kthread, and the no-CBs callbacks kthread), the contention on this lock is excessive under heavy stress. This commit therefore greatly reduces contention by provisioning an rcu_cblist structure field named ->nocb_bypass within the rcu_data structure. Each no-CBs CPU is permitted only a limited number of enqueues onto the ->cblist per jiffy, controlled by a new nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is exceeded, the CPU instead enqueues onto the new ->nocb_bypass. The ->nocb_bypass is flushed into the ->cblist every jiffy or when the number of callbacks on ->nocb_bypass exceeds qhimark, whichever happens first. During call_rcu() floods, this flushing is carried out by the CPU during the course of its call_rcu() invocations. However, a CPU could simply stop invoking call_rcu() at any time. The no-CBs grace-period kthread therefore carries out less-aggressive flushing (every few jiffies or when the number of callbacks on ->nocb_bypass exceeds (2 * qhimark), whichever comes first). This means that the no-CBs grace-period kthread cannot be permitted to do unbounded waits while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is used to provide the needed wakeups. [ paulmck: Apply Coverity feedback reported by Colin Ian King. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-07-03 07:03:33 +08:00
static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(void);
/*
* Disable IRQs before checking offloaded state so that local
* locking is safe against concurrent de-offloading.
*/
#define rcu_nocb_lock_irqsave(rdp, flags) \
do { \
local_irq_save(flags); \
if (rcu_segcblist_is_offloaded(&(rdp)->cblist)) \
raw_spin_lock(&(rdp)->nocb_lock); \
} while (0)
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
#define rcu_nocb_lock_irqsave(rdp, flags) local_irq_save(flags)
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);
/* Forward declarations for tree_stall.h */
static void record_gp_stall_check_time(void);
static void rcu_iw_handler(struct irq_work *iwp);
static void check_cpu_stall(struct rcu_data *rdp);
static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
const unsigned long gpssdelay);
/* Forward declarations for tree_exp.h. */
static void sync_rcu_do_polled_gp(struct work_struct *wp);