linux/kernel/rcu/tree.c
Linus Torvalds d2d8b14604 The major changes in this tracing update includes:
- Removing of non-DYNAMIC_FTRACE from 32bit x86
 
  - Removing of mcount support from x86
 
  - Emulating a call from int3 on x86_64, fixes live kernel patching
 
  - Consolidated Tracing Error logs file
 
 Minor updates:
 
  - Removal of klp_check_compiler_support()
 
  - kdb ftrace dumping output changes
 
  - Accessing and creating ftrace instances from inside the kernel
 
  - Clean up of #define if macro
 
  - Introduction of TRACE_EVENT_NOP() to disable trace events based on config
    options
 
 And other minor fixes and clean ups
 -----BEGIN PGP SIGNATURE-----
 
 iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCXNxMZxQccm9zdGVkdEBn
 b29kbWlzLm9yZwAKCRAp5XQQmuv6qq4PAP44kP6VbwL8CHyI2A3xuJ6Hwxd+2Z2r
 ip66RtzyJ+2iCgEA2QCuWUlEt2bLpF9a8IQ4N9tWenSeW2i7gunPb+tioQw=
 =RVQo
 -----END PGP SIGNATURE-----

Merge tag 'trace-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "The major changes in this tracing update includes:

   - Removal of non-DYNAMIC_FTRACE from 32bit x86

   - Removal of mcount support from x86

   - Emulating a call from int3 on x86_64, fixes live kernel patching

   - Consolidated Tracing Error logs file

  Minor updates:

   - Removal of klp_check_compiler_support()

   - kdb ftrace dumping output changes

   - Accessing and creating ftrace instances from inside the kernel

   - Clean up of #define if macro

   - Introduction of TRACE_EVENT_NOP() to disable trace events based on
     config options

  And other minor fixes and clean ups"

* tag 'trace-v5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (44 commits)
  x86: Hide the int3_emulate_call/jmp functions from UML
  livepatch: Remove klp_check_compiler_support()
  ftrace/x86: Remove mcount support
  ftrace/x86_32: Remove support for non DYNAMIC_FTRACE
  tracing: Simplify "if" macro code
  tracing: Fix documentation about disabling options using trace_options
  tracing: Replace kzalloc with kcalloc
  tracing: Fix partial reading of trace event's id file
  tracing: Allow RCU to run between postponed startup tests
  tracing: Fix white space issues in parse_pred() function
  tracing: Eliminate const char[] auto variables
  ring-buffer: Fix mispelling of Calculate
  tracing: probeevent: Fix to make the type of $comm string
  tracing: probeevent: Do not accumulate on ret variable
  tracing: uprobes: Re-enable $comm support for uprobe events
  ftrace/x86_64: Emulate call function while updating in breakpoint handler
  x86_64: Allow breakpoints to emulate call instructions
  x86_64: Add gap to int3 to allow for call emulation
  tracing: kdb: Allow ftdump to skip all but the last few entries
  tracing: Add trace_total_entries() / trace_total_entries_cpu()
  ...
2019-05-15 16:05:47 -07:00

3383 lines
108 KiB
C

// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion
*
* Copyright IBM Corporation, 2008
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
* Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical version
*
* Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#define pr_fmt(fmt) "rcu: " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate_wait.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/nmi.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/export.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/time.h>
#include <linux/kernel_stat.h>
#include <linux/wait.h>
#include <linux/kthread.h>
#include <uapi/linux/sched/types.h>
#include <linux/prefetch.h>
#include <linux/delay.h>
#include <linux/stop_machine.h>
#include <linux/random.h>
#include <linux/trace_events.h>
#include <linux/suspend.h>
#include <linux/ftrace.h>
#include <linux/tick.h>
#include <linux/sysrq.h>
#include <linux/kprobes.h>
#include "tree.h"
#include "rcu.h"
#ifdef MODULE_PARAM_PREFIX
#undef MODULE_PARAM_PREFIX
#endif
#define MODULE_PARAM_PREFIX "rcutree."
/* Data structures. */
/*
* Steal a bit from the bottom of ->dynticks for idle entry/exit
* control. Initially this is for TLB flushing.
*/
#define RCU_DYNTICK_CTRL_MASK 0x1
#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1)
#ifndef rcu_eqs_special_exit
#define rcu_eqs_special_exit() do { } while (0)
#endif
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
.dynticks_nesting = 1,
.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
.dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
};
struct rcu_state rcu_state = {
.level = { &rcu_state.node[0] },
.gp_state = RCU_GP_IDLE,
.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT,
.barrier_mutex = __MUTEX_INITIALIZER(rcu_state.barrier_mutex),
.name = RCU_NAME,
.abbr = RCU_ABBR,
.exp_mutex = __MUTEX_INITIALIZER(rcu_state.exp_mutex),
.exp_wake_mutex = __MUTEX_INITIALIZER(rcu_state.exp_wake_mutex),
.ofl_lock = __RAW_SPIN_LOCK_UNLOCKED(rcu_state.ofl_lock),
};
/* Dump rcu_node combining tree at boot to verify correct setup. */
static bool dump_tree;
module_param(dump_tree, bool, 0444);
/* Control rcu_node-tree auto-balancing at boot time. */
static bool rcu_fanout_exact;
module_param(rcu_fanout_exact, bool, 0444);
/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
/* Number of rcu_nodes at specified level. */
int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
/*
* The rcu_scheduler_active variable is initialized to the value
* RCU_SCHEDULER_INACTIVE and transitions RCU_SCHEDULER_INIT just before the
* first task is spawned. So when this variable is RCU_SCHEDULER_INACTIVE,
* RCU can assume that there is but one task, allowing RCU to (for example)
* optimize synchronize_rcu() to a simple barrier(). When this variable
* is RCU_SCHEDULER_INIT, RCU must actually do all the hard work required
* to detect real grace periods. This variable is also used to suppress
* boot-time false positives from lockdep-RCU error checking. Finally, it
* transitions from RCU_SCHEDULER_INIT to RCU_SCHEDULER_RUNNING after RCU
* is fully initialized, including all of its kthreads having been spawned.
*/
int rcu_scheduler_active __read_mostly;
EXPORT_SYMBOL_GPL(rcu_scheduler_active);
/*
* The rcu_scheduler_fully_active variable transitions from zero to one
* during the early_initcall() processing, which is after the scheduler
* is capable of creating new tasks. So RCU processing (for example,
* creating tasks for RCU priority boosting) must be delayed until after
* rcu_scheduler_fully_active transitions from zero to one. We also
* currently delay invocation of any RCU callbacks until after this point.
*
* It might later prove better for people registering RCU callbacks during
* early boot to take responsibility for these callbacks, but one step at
* a time.
*/
static int rcu_scheduler_fully_active __read_mostly;
static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
unsigned long gps, unsigned long flags);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_data *rdp);
static void rcu_report_exp_rdp(struct rcu_data *rdp);
static void sync_sched_exp_online_cleanup(int cpu);
/* rcuc/rcub kthread realtime priority */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
module_param(kthread_prio, int, 0444);
/* Delay in jiffies for grace-period initialization delays, debug only. */
static int gp_preinit_delay;
module_param(gp_preinit_delay, int, 0444);
static int gp_init_delay;
module_param(gp_init_delay, int, 0444);
static int gp_cleanup_delay;
module_param(gp_cleanup_delay, int, 0444);
/* Retrieve RCU kthreads priority for rcutorture */
int rcu_get_gp_kthreads_prio(void)
{
return kthread_prio;
}
EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
/*
* Number of grace periods between delays, normalized by the duration of
* the delay. The longer the delay, the more the grace periods between
* each delay. The reason for this normalization is that it means that,
* for non-zero delays, the overall slowdown of grace periods is constant
* regardless of the duration of the delay. This arrangement balances
* the need for long delays to increase some race probabilities with the
* need for fast grace periods to increase other race probabilities.
*/
#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */
/*
* Compute the mask of online CPUs for the specified rcu_node structure.
* This will not be stable unless the rcu_node structure's ->lock is
* held, but the bit corresponding to the current CPU will be stable
* in most contexts.
*/
unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
return READ_ONCE(rnp->qsmaskinitnext);
}
/*
* Return true if an RCU grace period is in progress. The READ_ONCE()s
* permit this function to be invoked without holding the root rcu_node
* structure's ->lock, but of course results can be subject to change.
*/
static int rcu_gp_in_progress(void)
{
return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq));
}
/*
* Return the number of callbacks queued on the specified CPU.
* Handles both the nocbs and normal cases.
*/
static long rcu_get_n_cbs_cpu(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
if (rcu_segcblist_is_enabled(&rdp->cblist)) /* Online normal CPU? */
return rcu_segcblist_n_cbs(&rdp->cblist);
return rcu_get_n_cbs_nocb_cpu(rdp); /* Works for offline, too. */
}
void rcu_softirq_qs(void)
{
rcu_qs();
rcu_preempt_deferred_qs(current);
}
/*
* Record entry into an extended quiescent state. This is only to be
* called when not already in an extended quiescent state.
*/
static void rcu_dynticks_eqs_enter(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
int seq;
/*
* CPUs seeing atomic_add_return() must see prior RCU read-side
* critical sections, and we also must force ordering with the
* next idle sojourn.
*/
seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
/* Better be in an extended quiescent state! */
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
(seq & RCU_DYNTICK_CTRL_CTR));
/* Better not have special action (TLB flush) pending! */
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
(seq & RCU_DYNTICK_CTRL_MASK));
}
/*
* Record exit from an extended quiescent state. This is only to be
* called from an extended quiescent state.
*/
static void rcu_dynticks_eqs_exit(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
int seq;
/*
* CPUs seeing atomic_add_return() must see prior idle sojourns,
* and we also must force ordering with the next RCU read-side
* critical section.
*/
seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!(seq & RCU_DYNTICK_CTRL_CTR));
if (seq & RCU_DYNTICK_CTRL_MASK) {
atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
smp_mb__after_atomic(); /* _exit after clearing mask. */
/* Prefer duplicate flushes to losing a flush. */
rcu_eqs_special_exit();
}
}
/*
* Reset the current CPU's ->dynticks counter to indicate that the
* newly onlined CPU is no longer in an extended quiescent state.
* This will either leave the counter unchanged, or increment it
* to the next non-quiescent value.
*
* The non-atomic test/increment sequence works because the upper bits
* of the ->dynticks counter are manipulated only by the corresponding CPU,
* or when the corresponding CPU is offline.
*/
static void rcu_dynticks_eqs_online(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
if (atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR)
return;
atomic_add(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
}
/*
* Is the current CPU in an extended quiescent state?
*
* No ordering, as we are sampling CPU-local information.
*/
bool rcu_dynticks_curr_cpu_in_eqs(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
}
/*
* Snapshot the ->dynticks counter with full ordering so as to allow
* stable comparison of this counter with past and future snapshots.
*/
int rcu_dynticks_snap(struct rcu_data *rdp)
{
int snap = atomic_add_return(0, &rdp->dynticks);
return snap & ~RCU_DYNTICK_CTRL_MASK;
}
/*
* Return true if the snapshot returned from rcu_dynticks_snap()
* indicates that RCU is in an extended quiescent state.
*/
static bool rcu_dynticks_in_eqs(int snap)
{
return !(snap & RCU_DYNTICK_CTRL_CTR);
}
/*
* Return true if the CPU corresponding to the specified rcu_data
* structure has spent some time in an extended quiescent state since
* rcu_dynticks_snap() returned the specified snapshot.
*/
static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
{
return snap != rcu_dynticks_snap(rdp);
}
/*
* Set the special (bottom) bit of the specified CPU so that it
* will take special action (such as flushing its TLB) on the
* next exit from an extended quiescent state. Returns true if
* the bit was successfully set, or false if the CPU was not in
* an extended quiescent state.
*/
bool rcu_eqs_special_set(int cpu)
{
int old;
int new;
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
do {
old = atomic_read(&rdp->dynticks);
if (old & RCU_DYNTICK_CTRL_CTR)
return false;
new = old | RCU_DYNTICK_CTRL_MASK;
} while (atomic_cmpxchg(&rdp->dynticks, old, new) != old);
return true;
}
/*
* Let the RCU core know that this CPU has gone through the scheduler,
* which is a quiescent state. This is called when the need for a
* quiescent state is urgent, so we burn an atomic operation and full
* memory barriers to let the RCU core know about it, regardless of what
* this CPU might (or might not) do in the near future.
*
* We inform the RCU core by emulating a zero-duration dyntick-idle period.
*
* The caller must have disabled interrupts and must not be idle.
*/
static void __maybe_unused rcu_momentary_dyntick_idle(void)
{
int special;
raw_cpu_write(rcu_data.rcu_need_heavy_qs, false);
special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
&this_cpu_ptr(&rcu_data)->dynticks);
/* It is illegal to call this from idle state. */
WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
rcu_preempt_deferred_qs(current);
}
/**
* rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
*
* If the current CPU is idle or running at a first-level (not nested)
* interrupt from idle, return true. The caller must have at least
* disabled preemption.
*/
static int rcu_is_cpu_rrupt_from_idle(void)
{
return __this_cpu_read(rcu_data.dynticks_nesting) <= 0 &&
__this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 1;
}
#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */
static long blimit = DEFAULT_RCU_BLIMIT;
#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */
static long qhimark = DEFAULT_RCU_QHIMARK;
#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */
static long qlowmark = DEFAULT_RCU_QLOMARK;
module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);
static ulong jiffies_till_first_fqs = ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
static bool rcu_kick_kthreads;
/*
* How long the grace period must be before we start recruiting
* quiescent-state help from rcu_note_context_switch().
*/
static ulong jiffies_till_sched_qs = ULONG_MAX;
module_param(jiffies_till_sched_qs, ulong, 0444);
static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */
module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */
/*
* Make sure that we give the grace-period kthread time to detect any
* idle CPUs before taking active measures to force quiescent states.
* However, don't go below 100 milliseconds, adjusted upwards for really
* large systems.
*/
static void adjust_jiffies_till_sched_qs(void)
{
unsigned long j;
/* If jiffies_till_sched_qs was specified, respect the request. */
if (jiffies_till_sched_qs != ULONG_MAX) {
WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs);
return;
}
/* Otherwise, set to third fqs scan, but bound below on large system. */
j = READ_ONCE(jiffies_till_first_fqs) +
2 * READ_ONCE(jiffies_till_next_fqs);
if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV)
j = HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
pr_info("RCU calculated value of scheduler-enlistment delay is %ld jiffies.\n", j);
WRITE_ONCE(jiffies_to_sched_qs, j);
}
static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
{
ulong j;
int ret = kstrtoul(val, 0, &j);
if (!ret) {
WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
adjust_jiffies_till_sched_qs();
}
return ret;
}
static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp)
{
ulong j;
int ret = kstrtoul(val, 0, &j);
if (!ret) {
WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
adjust_jiffies_till_sched_qs();
}
return ret;
}
static struct kernel_param_ops first_fqs_jiffies_ops = {
.set = param_set_first_fqs_jiffies,
.get = param_get_ulong,
};
static struct kernel_param_ops next_fqs_jiffies_ops = {
.set = param_set_next_fqs_jiffies,
.get = param_get_ulong,
};
module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644);
module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
module_param(rcu_kick_kthreads, bool, 0644);
static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
static int rcu_pending(void);
/*
* Return the number of RCU GPs completed thus far for debug & stats.
*/
unsigned long rcu_get_gp_seq(void)
{
return READ_ONCE(rcu_state.gp_seq);
}
EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
/*
* Return the number of RCU expedited batches completed thus far for
* debug & stats. Odd numbers mean that a batch is in progress, even
* numbers mean idle. The value returned will thus be roughly double
* the cumulative batches since boot.
*/
unsigned long rcu_exp_batches_completed(void)
{
return rcu_state.expedited_sequence;
}
EXPORT_SYMBOL_GPL(rcu_exp_batches_completed);
/*
* Return the root node of the rcu_state structure.
*/
static struct rcu_node *rcu_get_root(void)
{
return &rcu_state.node[0];
}
/*
* Convert a ->gp_state value to a character string.
*/
static const char *gp_state_getname(short gs)
{
if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
return "???";
return gp_state_names[gs];
}
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
unsigned long *gp_seq)
{
switch (test_type) {
case RCU_FLAVOR:
*flags = READ_ONCE(rcu_state.gp_flags);
*gp_seq = rcu_seq_current(&rcu_state.gp_seq);
break;
default:
break;
}
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*
* We crowbar the ->dynticks_nmi_nesting field to zero to allow for
* the possibility of usermode upcalls having messed up our count
* of interrupt nesting level during the prior busy period.
*/
static void rcu_eqs_enter(bool user)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
WARN_ON_ONCE(rdp->dynticks_nmi_nesting != DYNTICK_IRQ_NONIDLE);
WRITE_ONCE(rdp->dynticks_nmi_nesting, 0);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdp->dynticks_nesting == 0);
if (rdp->dynticks_nesting != 1) {
rdp->dynticks_nesting--;
return;
}
lockdep_assert_irqs_disabled();
trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, rdp->dynticks);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
rdp = this_cpu_ptr(&rcu_data);
do_nocb_deferred_wakeup(rdp);
rcu_prepare_for_idle();
rcu_preempt_deferred_qs(current);
WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
rcu_dynticks_eqs_enter();
rcu_dynticks_task_enter();
}
/**
* rcu_idle_enter - inform RCU that current CPU is entering idle
*
* Enter idle mode, in other words, -leave- the mode in which RCU
* read-side critical sections can occur. (Though RCU read-side
* critical sections can occur in irq handlers in idle, a possibility
* handled by irq_enter() and irq_exit().)
*
* If you add or remove a call to rcu_idle_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_idle_enter(void)
{
lockdep_assert_irqs_disabled();
rcu_eqs_enter(false);
}
#ifdef CONFIG_NO_HZ_FULL
/**
* rcu_user_enter - inform RCU that we are resuming userspace.
*
* Enter RCU idle mode right before resuming userspace. No use of RCU
* is permitted between this call and rcu_user_exit(). This way the
* CPU doesn't need to maintain the tick for RCU maintenance purposes
* when the CPU runs in userspace.
*
* If you add or remove a call to rcu_user_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_user_enter(void)
{
lockdep_assert_irqs_disabled();
rcu_eqs_enter(true);
}
#endif /* CONFIG_NO_HZ_FULL */
/*
* If we are returning from the outermost NMI handler that interrupted an
* RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
* to let the RCU grace-period handling know that the CPU is back to
* being RCU-idle.
*
* If you add or remove a call to rcu_nmi_exit_common(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
static __always_inline void rcu_nmi_exit_common(bool irq)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
/*
* Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
* (We are exiting an NMI handler, so RCU better be paying attention
* to us!)
*/
WARN_ON_ONCE(rdp->dynticks_nmi_nesting <= 0);
WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
/*
* If the nesting level is not 1, the CPU wasn't RCU-idle, so
* leave it in non-RCU-idle state.
*/
if (rdp->dynticks_nmi_nesting != 1) {
trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks);
WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
rdp->dynticks_nmi_nesting - 2);
return;
}
/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, rdp->dynticks);
WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
if (irq)
rcu_prepare_for_idle();
rcu_dynticks_eqs_enter();
if (irq)
rcu_dynticks_task_enter();
}
/**
* rcu_nmi_exit - inform RCU of exit from NMI context
*
* If you add or remove a call to rcu_nmi_exit(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_nmi_exit(void)
{
rcu_nmi_exit_common(false);
}
/**
* rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
*
* Exit from an interrupt handler, which might possibly result in entering
* idle mode, in other words, leaving the mode in which read-side critical
* sections can occur. The caller must have disabled interrupts.
*
* This code assumes that the idle loop never does anything that might
* result in unbalanced calls to irq_enter() and irq_exit(). If your
* architecture's idle loop violates this assumption, RCU will give you what
* you deserve, good and hard. But very infrequently and irreproducibly.
*
* Use things like work queues to work around this limitation.
*
* You have been warned.
*
* If you add or remove a call to rcu_irq_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_exit(void)
{
lockdep_assert_irqs_disabled();
rcu_nmi_exit_common(true);
}
/*
* Wrapper for rcu_irq_exit() where interrupts are enabled.
*
* If you add or remove a call to rcu_irq_exit_irqson(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_exit_irqson(void)
{
unsigned long flags;
local_irq_save(flags);
rcu_irq_exit();
local_irq_restore(flags);
}
/*
* Exit an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*
* We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE to
* allow for the possibility of usermode upcalls messing up our count of
* interrupt nesting level during the busy period that is just now starting.
*/
static void rcu_eqs_exit(bool user)
{
struct rcu_data *rdp;
long oldval;
lockdep_assert_irqs_disabled();
rdp = this_cpu_ptr(&rcu_data);
oldval = rdp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
if (oldval) {
rdp->dynticks_nesting++;
return;
}
rcu_dynticks_task_exit();
rcu_dynticks_eqs_exit();
rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, rdp->dynticks);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
WRITE_ONCE(rdp->dynticks_nesting, 1);
WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
}
/**
* rcu_idle_exit - inform RCU that current CPU is leaving idle
*
* Exit idle mode, in other words, -enter- the mode in which RCU
* read-side critical sections can occur.
*
* If you add or remove a call to rcu_idle_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_idle_exit(void)
{
unsigned long flags;
local_irq_save(flags);
rcu_eqs_exit(false);
local_irq_restore(flags);
}
#ifdef CONFIG_NO_HZ_FULL
/**
* rcu_user_exit - inform RCU that we are exiting userspace.
*
* Exit RCU idle mode while entering the kernel because it can
* run a RCU read side critical section anytime.
*
* If you add or remove a call to rcu_user_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_user_exit(void)
{
rcu_eqs_exit(1);
}
#endif /* CONFIG_NO_HZ_FULL */
/**
* rcu_nmi_enter_common - inform RCU of entry to NMI context
* @irq: Is this call from rcu_irq_enter?
*
* If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
* rdp->dynticks_nmi_nesting to let the RCU grace-period handling know
* that the CPU is active. This implementation permits nested NMIs, as
* long as the nesting level does not overflow an int. (You will probably
* run out of stack space first.)
*
* If you add or remove a call to rcu_nmi_enter_common(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
static __always_inline void rcu_nmi_enter_common(bool irq)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
long incby = 2;
/* Complain about underflow. */
WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0);
/*
* If idle from RCU viewpoint, atomically increment ->dynticks
* to mark non-idle and increment ->dynticks_nmi_nesting by one.
* Otherwise, increment ->dynticks_nmi_nesting by two. This means
* if ->dynticks_nmi_nesting is equal to one, we are guaranteed
* to be in the outermost NMI handler that interrupted an RCU-idle
* period (observation due to Andy Lutomirski).
*/
if (rcu_dynticks_curr_cpu_in_eqs()) {
if (irq)
rcu_dynticks_task_exit();
rcu_dynticks_eqs_exit();
if (irq)
rcu_cleanup_after_idle();
incby = 1;
}
trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
rdp->dynticks_nmi_nesting,
rdp->dynticks_nmi_nesting + incby, rdp->dynticks);
WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
rdp->dynticks_nmi_nesting + incby);
barrier();
}
/**
* rcu_nmi_enter - inform RCU of entry to NMI context
*/
void rcu_nmi_enter(void)
{
rcu_nmi_enter_common(false);
}
NOKPROBE_SYMBOL(rcu_nmi_enter);
/**
* rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
*
* Enter an interrupt handler, which might possibly result in exiting
* idle mode, in other words, entering the mode in which read-side critical
* sections can occur. The caller must have disabled interrupts.
*
* Note that the Linux kernel is fully capable of entering an interrupt
* handler that it never exits, for example when doing upcalls to user mode!
* This code assumes that the idle loop never does upcalls to user mode.
* If your architecture's idle loop does do upcalls to user mode (or does
* anything else that results in unbalanced calls to the irq_enter() and
* irq_exit() functions), RCU will give you what you deserve, good and hard.
* But very infrequently and irreproducibly.
*
* Use things like work queues to work around this limitation.
*
* You have been warned.
*
* If you add or remove a call to rcu_irq_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_enter(void)
{
lockdep_assert_irqs_disabled();
rcu_nmi_enter_common(true);
}
/*
* Wrapper for rcu_irq_enter() where interrupts are enabled.
*
* If you add or remove a call to rcu_irq_enter_irqson(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_enter_irqson(void)
{
unsigned long flags;
local_irq_save(flags);
rcu_irq_enter();
local_irq_restore(flags);
}
/**
* rcu_is_watching - see if RCU thinks that the current CPU is not idle
*
* Return true if RCU is watching the running CPU, which means that this
* CPU can safely enter RCU read-side critical sections. In other words,
* if the current CPU is not in its idle loop or is in an interrupt or
* NMI handler, return true.
*/
bool notrace rcu_is_watching(void)
{
bool ret;
preempt_disable_notrace();
ret = !rcu_dynticks_curr_cpu_in_eqs();
preempt_enable_notrace();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_is_watching);
/*
* If a holdout task is actually running, request an urgent quiescent
* state from its CPU. This is unsynchronized, so migrations can cause
* the request to go to the wrong CPU. Which is OK, all that will happen
* is that the CPU's next context switch will be a bit slower and next
* time around this task will generate another request.
*/
void rcu_request_urgent_qs_task(struct task_struct *t)
{
int cpu;
barrier();
cpu = task_cpu(t);
if (!task_curr(t))
return; /* This task is not running on that CPU. */
smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true);
}
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
* Is the current CPU online as far as RCU is concerned?
*
* Disable preemption to avoid false positives that could otherwise
* happen due to the current CPU number being sampled, this task being
* preempted, its old CPU being taken offline, resuming on some other CPU,
* then determining that its old CPU is now offline.
*
* Disable checking if in an NMI handler because we cannot safely
* report errors from NMI handlers anyway. In addition, it is OK to use
* RCU on an offline processor during initial boot, hence the check for
* rcu_scheduler_fully_active.
*/
bool rcu_lockdep_current_cpu_online(void)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
bool ret = false;
if (in_nmi() || !rcu_scheduler_fully_active)
return true;
preempt_disable();
rdp = this_cpu_ptr(&rcu_data);
rnp = rdp->mynode;
if (rdp->grpmask & rcu_rnp_online_cpus(rnp))
ret = true;
preempt_enable();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */
/*
* We are reporting a quiescent state on behalf of some other CPU, so
* it is our responsibility to check for and handle potential overflow
* of the rcu_node ->gp_seq counter with respect to the rcu_data counters.
* After all, the CPU might be in deep idle state, and thus executing no
* code whatsoever.
*/
static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
{
raw_lockdep_assert_held_rcu_node(rnp);
if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
rnp->gp_seq))
WRITE_ONCE(rdp->gpwrap, true);
if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
}
/*
* Snapshot the specified CPU's dynticks counter so that we can later
* credit them with an implicit quiescent state. Return 1 if this CPU
* is in dynticks idle mode, which is an extended quiescent state.
*/
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
rdp->dynticks_snap = rcu_dynticks_snap(rdp);
if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rdp->mynode, rdp);
return 1;
}
return 0;
}
/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
* idle state since the last call to dyntick_save_progress_counter()
* for this same CPU, or by virtue of having been offline.
*/
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
unsigned long jtsq;
bool *rnhqp;
bool *ruqp;
struct rcu_node *rnp = rdp->mynode;
/*
* If the CPU passed through or entered a dynticks idle phase with
* no active irq/NMI handlers, then we can safely pretend that the CPU
* already acknowledged the request to pass through a quiescent
* state. Either way, that CPU cannot possibly be in an RCU
* read-side critical section that started before the beginning
* of the current RCU grace period.
*/
if (rcu_dynticks_in_eqs_since(rdp, rdp->dynticks_snap)) {
trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rnp, rdp);
return 1;
}
/* If waiting too long on an offline CPU, complain. */
if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
time_after(jiffies, rcu_state.gp_start + HZ)) {
bool onl;
struct rcu_node *rnp1;
WARN_ON(1); /* Offline CPUs are supposed to report QS! */
pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
__func__, rnp->grplo, rnp->grphi, rnp->level,
(long)rnp->gp_seq, (long)rnp->completedqs);
for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
__func__, rdp->cpu, ".o"[onl],
(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
return 1; /* Break things loose after complaining. */
}
/*
* A CPU running for an extended time within the kernel can
* delay RCU grace periods: (1) At age jiffies_to_sched_qs,
* set .rcu_urgent_qs, (2) At age 2*jiffies_to_sched_qs, set
* both .rcu_need_heavy_qs and .rcu_urgent_qs. Note that the
* unsynchronized assignments to the per-CPU rcu_need_heavy_qs
* variable are safe because the assignments are repeated if this
* CPU failed to pass through a quiescent state. This code
* also checks .jiffies_resched in case jiffies_to_sched_qs
* is set way high.
*/
jtsq = READ_ONCE(jiffies_to_sched_qs);
ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu);
rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu);
if (!READ_ONCE(*rnhqp) &&
(time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
time_after(jiffies, rcu_state.jiffies_resched))) {
WRITE_ONCE(*rnhqp, true);
/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
smp_store_release(ruqp, true);
} else if (time_after(jiffies, rcu_state.gp_start + jtsq)) {
WRITE_ONCE(*ruqp, true);
}
/*
* NO_HZ_FULL CPUs can run in-kernel without rcu_sched_clock_irq!
* The above code handles this, but only for straight cond_resched().
* And some in-kernel loops check need_resched() before calling
* cond_resched(), which defeats the above code for CPUs that are
* running in-kernel with scheduling-clock interrupts disabled.
* So hit them over the head with the resched_cpu() hammer!
*/
if (tick_nohz_full_cpu(rdp->cpu) &&
time_after(jiffies,
READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) {
resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
/*
* If more than halfway to RCU CPU stall-warning time, invoke
* resched_cpu() more frequently to try to loosen things up a bit.
* Also check to see if the CPU is getting hammered with interrupts,
* but only once per grace period, just to keep the IPIs down to
* a dull roar.
*/
if (time_after(jiffies, rcu_state.jiffies_resched)) {
if (time_after(jiffies,
READ_ONCE(rdp->last_fqs_resched) + jtsq)) {
resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
if (IS_ENABLED(CONFIG_IRQ_WORK) &&
!rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
rdp->rcu_iw_pending = true;
rdp->rcu_iw_gp_seq = rnp->gp_seq;
irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
}
}
return 0;
}
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long gp_seq_req, const char *s)
{
trace_rcu_future_grace_period(rcu_state.name, rnp->gp_seq, gp_seq_req,
rnp->level, rnp->grplo, rnp->grphi, s);
}
/*
* rcu_start_this_gp - Request the start of a particular grace period
* @rnp_start: The leaf node of the CPU from which to start.
* @rdp: The rcu_data corresponding to the CPU from which to start.
* @gp_seq_req: The gp_seq of the grace period to start.
*
* Start the specified grace period, as needed to handle newly arrived
* callbacks. The required future grace periods are recorded in each
* rcu_node structure's ->gp_seq_needed field. Returns true if there
* is reason to awaken the grace-period kthread.
*
* The caller must hold the specified rcu_node structure's ->lock, which
* is why the caller is responsible for waking the grace-period kthread.
*
* Returns true if the GP thread needs to be awakened else false.
*/
static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
unsigned long gp_seq_req)
{
bool ret = false;
struct rcu_node *rnp;
/*
* Use funnel locking to either acquire the root rcu_node
* structure's lock or bail out if the need for this grace period
* has already been recorded -- or if that grace period has in
* fact already started. If there is already a grace period in
* progress in a non-leaf node, no recording is needed because the
* end of the grace period will scan the leaf rcu_node structures.
* Note that rnp_start->lock must not be released.
*/
raw_lockdep_assert_held_rcu_node(rnp_start);
trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf"));
for (rnp = rnp_start; 1; rnp = rnp->parent) {
if (rnp != rnp_start)
raw_spin_lock_rcu_node(rnp);
if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) ||
rcu_seq_started(&rnp->gp_seq, gp_seq_req) ||
(rnp != rnp_start &&
rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req,
TPS("Prestarted"));
goto unlock_out;
}
rnp->gp_seq_needed = gp_seq_req;
if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
/*
* We just marked the leaf or internal node, and a
* grace period is in progress, which means that
* rcu_gp_cleanup() will see the marking. Bail to
* reduce contention.
*/
trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
TPS("Startedleaf"));
goto unlock_out;
}
if (rnp != rnp_start && rnp->parent != NULL)
raw_spin_unlock_rcu_node(rnp);
if (!rnp->parent)
break; /* At root, and perhaps also leaf. */
}
/* If GP already in progress, just leave, otherwise start one. */
if (rcu_gp_in_progress()) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
goto unlock_out;
}
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT);
rcu_state.gp_req_activity = jiffies;
if (!rcu_state.gp_kthread) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
goto unlock_out;
}
trace_rcu_grace_period(rcu_state.name, READ_ONCE(rcu_state.gp_seq), TPS("newreq"));
ret = true; /* Caller must wake GP kthread. */
unlock_out:
/* Push furthest requested GP to leaf node and rcu_data structure. */
if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
rnp_start->gp_seq_needed = rnp->gp_seq_needed;
rdp->gp_seq_needed = rnp->gp_seq_needed;
}
if (rnp != rnp_start)
raw_spin_unlock_rcu_node(rnp);
return ret;
}
/*
* Clean up any old requests for the just-ended grace period. Also return
* whether any additional grace periods have been requested.
*/
static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
{
bool needmore;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
if (!needmore)
rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
trace_rcu_this_gp(rnp, rdp, rnp->gp_seq,
needmore ? TPS("CleanupMore") : TPS("Cleanup"));
return needmore;
}
/*
* Awaken the grace-period kthread. Don't do a self-awaken (unless in
* an interrupt or softirq handler), and don't bother awakening when there
* is nothing for the grace-period kthread to do (as in several CPUs raced
* to awaken, and we lost), and finally don't try to awaken a kthread that
* has not yet been created. If all those checks are passed, track some
* debug information and awaken.
*
* So why do the self-wakeup when in an interrupt or softirq handler
* in the grace-period kthread's context? Because the kthread might have
* been interrupted just as it was going to sleep, and just after the final
* pre-sleep check of the awaken condition. In this case, a wakeup really
* is required, and is therefore supplied.
*/
static void rcu_gp_kthread_wake(void)
{
if ((current == rcu_state.gp_kthread &&
!in_irq() && !in_serving_softirq()) ||
!READ_ONCE(rcu_state.gp_flags) ||
!rcu_state.gp_kthread)
return;
WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
swake_up_one(&rcu_state.gp_wq);
}
/*
* If there is room, assign a ->gp_seq number to any callbacks on this
* CPU that have not already been assigned. Also accelerate any callbacks
* that were previously assigned a ->gp_seq number that has since proven
* to be too conservative, which can happen if callbacks get assigned a
* ->gp_seq number while RCU is idle, but with reference to a non-root
* rcu_node structure. This function is idempotent, so it does not hurt
* to call it repeatedly. Returns an flag saying that we should awaken
* the RCU grace-period kthread.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
{
unsigned long gp_seq_req;
bool ret = false;
raw_lockdep_assert_held_rcu_node(rnp);
/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
/*
* Callbacks are often registered with incomplete grace-period
* information. Something about the fact that getting exact
* information requires acquiring a global lock... RCU therefore
* makes a conservative estimate of the grace period number at which
* a given callback will become ready to invoke. The following
* code checks this estimate and improves it when possible, thus
* accelerating callback invocation to an earlier grace-period
* number.
*/
gp_seq_req = rcu_seq_snap(&rcu_state.gp_seq);
if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccWaitCB"));
else
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccReadyCB"));
return ret;
}
/*
* Similar to rcu_accelerate_cbs(), but does not require that the leaf
* rcu_node structure's ->lock be held. It consults the cached value
* of ->gp_seq_needed in the rcu_data structure, and if that indicates
* that a new grace-period request be made, invokes rcu_accelerate_cbs()
* while holding the leaf rcu_node structure's ->lock.
*/
static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp,
struct rcu_data *rdp)
{
unsigned long c;
bool needwake;
lockdep_assert_irqs_disabled();
c = rcu_seq_snap(&rcu_state.gp_seq);
if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
/* Old request still live, so mark recent callbacks. */
(void)rcu_segcblist_accelerate(&rdp->cblist, c);
return;
}
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
needwake = rcu_accelerate_cbs(rnp, rdp);
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
if (needwake)
rcu_gp_kthread_wake();
}
/*
* Move any callbacks whose grace period has completed to the
* RCU_DONE_TAIL sublist, then compact the remaining sublists and
* assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL
* sublist. This function is idempotent, so it does not hurt to
* invoke it repeatedly. As long as it is not invoked -too- often...
* Returns true if the RCU grace-period kthread needs to be awakened.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
{
raw_lockdep_assert_held_rcu_node(rnp);
/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
/*
* Find all callbacks whose ->gp_seq numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
*/
rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
/* Classify any remaining callbacks. */
return rcu_accelerate_cbs(rnp, rdp);
}
/*
* Update CPU-local rcu_data state to record the beginnings and ends of
* grace periods. The caller must hold the ->lock of the leaf rcu_node
* structure corresponding to the current CPU, and must have irqs disabled.
* Returns true if the grace-period kthread needs to be awakened.
*/
static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
{
bool ret;
bool need_gp;
raw_lockdep_assert_held_rcu_node(rnp);
if (rdp->gp_seq == rnp->gp_seq)
return false; /* Nothing to do. */
/* Handle the ends of any preceding grace periods first. */
if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
unlikely(READ_ONCE(rdp->gpwrap))) {
ret = rcu_advance_cbs(rnp, rdp); /* Advance callbacks. */
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend"));
} else {
ret = rcu_accelerate_cbs(rnp, rdp); /* Recent callbacks. */
}
/* Now handle the beginnings of any new-to-this-CPU grace periods. */
if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
unlikely(READ_ONCE(rdp->gpwrap))) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
* go looking for one.
*/
trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart"));
need_gp = !!(rnp->qsmask & rdp->grpmask);
rdp->cpu_no_qs.b.norm = need_gp;
rdp->core_needs_qs = need_gp;
zero_cpu_stall_ticks(rdp);
}
rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
rdp->gp_seq_needed = rnp->gp_seq_needed;
WRITE_ONCE(rdp->gpwrap, false);
rcu_gpnum_ovf(rnp, rdp);
return ret;
}
static void note_gp_changes(struct rcu_data *rdp)
{
unsigned long flags;
bool needwake;
struct rcu_node *rnp;
local_irq_save(flags);
rnp = rdp->mynode;
if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) &&
!unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
!raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
local_irq_restore(flags);
return;
}
needwake = __note_gp_changes(rnp, rdp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (needwake)
rcu_gp_kthread_wake();
}
static void rcu_gp_slow(int delay)
{
if (delay > 0 &&
!(rcu_seq_ctr(rcu_state.gp_seq) %
(rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
schedule_timeout_uninterruptible(delay);
}
/*
* Initialize a new grace period. Return false if no grace period required.
*/
static bool rcu_gp_init(void)
{
unsigned long flags;
unsigned long oldmask;
unsigned long mask;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
if (!READ_ONCE(rcu_state.gp_flags)) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq_rcu_node(rnp);
return false;
}
WRITE_ONCE(rcu_state.gp_flags, 0); /* Clear all flags: New GP. */
if (WARN_ON_ONCE(rcu_gp_in_progress())) {
/*
* Grace period already in progress, don't start another.
* Not supposed to be able to happen.
*/
raw_spin_unlock_irq_rcu_node(rnp);
return false;
}
/* Advance to a new grace period and initialize state. */
record_gp_stall_check_time();
/* Record GP times before starting GP, hence rcu_seq_start(). */
rcu_seq_start(&rcu_state.gp_seq);
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
raw_spin_unlock_irq_rcu_node(rnp);
/*
* Apply per-leaf buffered online and offline operations to the
* rcu_node tree. Note that this new grace period need not wait
* for subsequent online CPUs, and that quiescent-state forcing
* will handle subsequent offline CPUs.
*/
rcu_state.gp_state = RCU_GP_ONOFF;
rcu_for_each_leaf_node(rnp) {
raw_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irq_rcu_node(rnp);
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
!rnp->wait_blkd_tasks) {
/* Nothing to do on this leaf rcu_node structure. */
raw_spin_unlock_irq_rcu_node(rnp);
raw_spin_unlock(&rcu_state.ofl_lock);
continue;
}
/* Record old state, apply changes to ->qsmaskinit field. */
oldmask = rnp->qsmaskinit;
rnp->qsmaskinit = rnp->qsmaskinitnext;
/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
if (!oldmask != !rnp->qsmaskinit) {
if (!oldmask) { /* First online CPU for rcu_node. */
if (!rnp->wait_blkd_tasks) /* Ever offline? */
rcu_init_new_rnp(rnp);
} else if (rcu_preempt_has_tasks(rnp)) {
rnp->wait_blkd_tasks = true; /* blocked tasks */
} else { /* Last offline CPU and can propagate. */
rcu_cleanup_dead_rnp(rnp);
}
}
/*
* If all waited-on tasks from prior grace period are
* done, and if all this rcu_node structure's CPUs are
* still offline, propagate up the rcu_node tree and
* clear ->wait_blkd_tasks. Otherwise, if one of this
* rcu_node structure's CPUs has since come back online,
* simply clear ->wait_blkd_tasks.
*/
if (rnp->wait_blkd_tasks &&
(!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) {
rnp->wait_blkd_tasks = false;
if (!rnp->qsmaskinit)
rcu_cleanup_dead_rnp(rnp);
}
raw_spin_unlock_irq_rcu_node(rnp);
raw_spin_unlock(&rcu_state.ofl_lock);
}
rcu_gp_slow(gp_preinit_delay); /* Races with CPU hotplug. */
/*
* Set the quiescent-state-needed bits in all the rcu_node
* structures for all currently online CPUs in breadth-first
* order, starting from the root rcu_node structure, relying on the
* layout of the tree within the rcu_state.node[] array. Note that
* other CPUs will access only the leaves of the hierarchy, thus
* seeing that no grace period is in progress, at least until the
* corresponding leaf node has been initialized.
*
* The grace period cannot complete until the initialization
* process finishes, because this kthread handles both.
*/
rcu_state.gp_state = RCU_GP_INIT;
rcu_for_each_node_breadth_first(rnp) {
rcu_gp_slow(gp_init_delay);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp = this_cpu_ptr(&rcu_data);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
WRITE_ONCE(rnp->gp_seq, rcu_state.gp_seq);
if (rnp == rdp->mynode)
(void)__note_gp_changes(rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
trace_rcu_grace_period_init(rcu_state.name, rnp->gp_seq,
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
/* Quiescent states for tasks on any now-offline CPUs. */
mask = rnp->qsmask & ~rnp->qsmaskinitnext;
rnp->rcu_gp_init_mask = mask;
if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
else
raw_spin_unlock_irq_rcu_node(rnp);
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
}
return true;
}
/*
* Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
* time.
*/
static bool rcu_gp_fqs_check_wake(int *gfp)
{
struct rcu_node *rnp = rcu_get_root();
/* Someone like call_rcu() requested a force-quiescent-state scan. */
*gfp = READ_ONCE(rcu_state.gp_flags);
if (*gfp & RCU_GP_FLAG_FQS)
return true;
/* The current grace period has completed. */
if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
return true;
return false;
}
/*
* Do one round of quiescent-state forcing.
*/
static void rcu_gp_fqs(bool first_time)
{
struct rcu_node *rnp = rcu_get_root();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
rcu_state.n_force_qs++;
if (first_time) {
/* Collect dyntick-idle snapshots. */
force_qs_rnp(dyntick_save_progress_counter);
} else {
/* Handle dyntick-idle and offline CPUs. */
force_qs_rnp(rcu_implicit_dynticks_qs);
}
/* Clear flag to prevent immediate re-entry. */
if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq_rcu_node(rnp);
WRITE_ONCE(rcu_state.gp_flags,
READ_ONCE(rcu_state.gp_flags) & ~RCU_GP_FLAG_FQS);
raw_spin_unlock_irq_rcu_node(rnp);
}
}
/*
* Loop doing repeated quiescent-state forcing until the grace period ends.
*/
static void rcu_gp_fqs_loop(void)
{
bool first_gp_fqs;
int gf;
unsigned long j;
int ret;
struct rcu_node *rnp = rcu_get_root();
first_gp_fqs = true;
j = READ_ONCE(jiffies_till_first_fqs);
ret = 0;
for (;;) {
if (!ret) {
rcu_state.jiffies_force_qs = jiffies + j;
WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
jiffies + (j ? 3 * j : 2));
}
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
TPS("fqswait"));
rcu_state.gp_state = RCU_GP_WAIT_FQS;
ret = swait_event_idle_timeout_exclusive(
rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
rcu_state.gp_state = RCU_GP_DOING_FQS;
/* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
if (!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
break;
/* If time for quiescent-state forcing, do it. */
if (ULONG_CMP_GE(jiffies, rcu_state.jiffies_force_qs) ||
(gf & RCU_GP_FLAG_FQS)) {
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
TPS("fqsstart"));
rcu_gp_fqs(first_gp_fqs);
first_gp_fqs = false;
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
TPS("fqsend"));
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
ret = 0; /* Force full wait till next FQS. */
j = READ_ONCE(jiffies_till_next_fqs);
} else {
/* Deal with stray signal. */
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
TPS("fqswaitsig"));
ret = 1; /* Keep old FQS timing. */
j = jiffies;
if (time_after(jiffies, rcu_state.jiffies_force_qs))
j = 1;
else
j = rcu_state.jiffies_force_qs - j;
}
}
}
/*
* Clean up after the old grace period.
*/
static void rcu_gp_cleanup(void)
{
unsigned long gp_duration;
bool needgp = false;
unsigned long new_gp_seq;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root();
struct swait_queue_head *sq;
WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
rcu_state.gp_end = jiffies;
gp_duration = rcu_state.gp_end - rcu_state.gp_start;
if (gp_duration > rcu_state.gp_max)
rcu_state.gp_max = gp_duration;
/*
* We know the grace period is complete, but to everyone else
* it appears to still be ongoing. But it is also the case
* that to everyone else it looks like there is nothing that
* they can do to advance the grace period. It is therefore
* safe for us to drop the lock in order to mark the grace
* period as completed in all of the rcu_node structures.
*/
raw_spin_unlock_irq_rcu_node(rnp);
/*
* Propagate new ->gp_seq value to rcu_node structures so that
* other CPUs don't have to wait until the start of the next grace
* period to process their callbacks. This also avoids some nasty
* RCU grace-period initialization races by forcing the end of
* the current grace period to be completely recorded in all of
* the rcu_node structures before the beginning of the next grace
* period is recorded in any of the rcu_node structures.
*/
new_gp_seq = rcu_state.gp_seq;
rcu_seq_end(&new_gp_seq);
rcu_for_each_node_breadth_first(rnp) {
raw_spin_lock_irq_rcu_node(rnp);
if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
dump_blkd_tasks(rnp, 10);
WARN_ON_ONCE(rnp->qsmask);
WRITE_ONCE(rnp->gp_seq, new_gp_seq);
rdp = this_cpu_ptr(&rcu_data);
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
needgp = rcu_future_gp_cleanup(rnp) || needgp;
sq = rcu_nocb_gp_get(rnp);
raw_spin_unlock_irq_rcu_node(rnp);
rcu_nocb_gp_cleanup(sq);
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
rcu_gp_slow(gp_cleanup_delay);
}
rnp = rcu_get_root();
raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */
/* Declare grace period done, trace first to use old GP number. */
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
rcu_seq_end(&rcu_state.gp_seq);
rcu_state.gp_state = RCU_GP_IDLE;
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(&rcu_data);
if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
TPS("CleanupMore"));
needgp = true;
}
/* Advance CBs to reduce false positives below. */
if (!rcu_accelerate_cbs(rnp, rdp) && needgp) {
WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
rcu_state.gp_req_activity = jiffies;
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
TPS("newreq"));
} else {
WRITE_ONCE(rcu_state.gp_flags,
rcu_state.gp_flags & RCU_GP_FLAG_INIT);
}
raw_spin_unlock_irq_rcu_node(rnp);
}
/*
* Body of kthread that handles grace periods.
*/
static int __noreturn rcu_gp_kthread(void *unused)
{
rcu_bind_gp_kthread();
for (;;) {
/* Handle grace-period start. */
for (;;) {
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
TPS("reqwait"));
rcu_state.gp_state = RCU_GP_WAIT_GPS;
swait_event_idle_exclusive(rcu_state.gp_wq,
READ_ONCE(rcu_state.gp_flags) &
RCU_GP_FLAG_INIT);
rcu_state.gp_state = RCU_GP_DONE_GPS;
/* Locking provides needed memory barrier. */
if (rcu_gp_init())
break;
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rcu_state.name,
READ_ONCE(rcu_state.gp_seq),
TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
rcu_gp_fqs_loop();
/* Handle grace-period end. */
rcu_state.gp_state = RCU_GP_CLEANUP;
rcu_gp_cleanup();
rcu_state.gp_state = RCU_GP_CLEANED;
}
}
/*
* Report a full set of quiescent states to the rcu_state data structure.
* Invoke rcu_gp_kthread_wake() to awaken the grace-period kthread if
* another grace period is required. Whether we wake the grace-period
* kthread or it awakens itself for the next round of quiescent-state
* forcing, that kthread will clean up after the just-completed grace
* period. Note that the caller must hold rnp->lock, which is released
* before return.
*/
static void rcu_report_qs_rsp(unsigned long flags)
__releases(rcu_get_root()->lock)
{
raw_lockdep_assert_held_rcu_node(rcu_get_root());
WARN_ON_ONCE(!rcu_gp_in_progress());
WRITE_ONCE(rcu_state.gp_flags,
READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(), flags);
rcu_gp_kthread_wake();
}
/*
* Similar to rcu_report_qs_rdp(), for which it is a helper function.
* Allows quiescent states for a group of CPUs to be reported at one go
* to the specified rcu_node structure, though all the CPUs in the group
* must be represented by the same rcu_node structure (which need not be a
* leaf rcu_node structure, though it often will be). The gps parameter
* is the grace-period snapshot, which means that the quiescent states
* are valid only if rnp->gp_seq is equal to gps. That structure's lock
* must be held upon entry, and it is released before return.
*
* As a special case, if mask is zero, the bit-already-cleared check is
* disabled. This allows propagating quiescent state due to resumed tasks
* during grace-period initialization.
*/
static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
unsigned long gps, unsigned long flags)
__releases(rnp->lock)
{
unsigned long oldmask = 0;
struct rcu_node *rnp_c;
raw_lockdep_assert_held_rcu_node(rnp);
/* Walk up the rcu_node hierarchy. */
for (;;) {
if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) {
/*
* Our bit has already been cleared, or the
* relevant grace period is already over, so done.
*/
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
rnp->qsmask &= ~mask;
trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq,
mask, rnp->qsmask, rnp->level,
rnp->grplo, rnp->grphi,
!!rnp->gp_tasks);
if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
/* Other bits still set at this level, so done. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
rnp->completedqs = rnp->gp_seq;
mask = rnp->grpmask;
if (rnp->parent == NULL) {
/* No more levels. Exit loop holding root lock. */
break;
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
oldmask = rnp_c->qsmask;
}
/*
* Get here if we are the last CPU to pass through a quiescent
* state for this grace period. Invoke rcu_report_qs_rsp()
* to clean up and start the next grace period if one is needed.
*/
rcu_report_qs_rsp(flags); /* releases rnp->lock. */
}
/*
* Record a quiescent state for all tasks that were previously queued
* on the specified rcu_node structure and that were blocking the current
* RCU grace period. The caller must hold the corresponding rnp->lock with
* irqs disabled, and this lock is released upon return, but irqs remain
* disabled.
*/
static void __maybe_unused
rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
unsigned long gps;
unsigned long mask;
struct rcu_node *rnp_p;
raw_lockdep_assert_held_rcu_node(rnp);
if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)) ||
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
rnp->qsmask != 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return; /* Still need more quiescent states! */
}
rnp->completedqs = rnp->gp_seq;
rnp_p = rnp->parent;
if (rnp_p == NULL) {
/*
* Only one rcu_node structure in the tree, so don't
* try to report up to its nonexistent parent!
*/
rcu_report_qs_rsp(flags);
return;
}
/* Report up the rest of the hierarchy, tracking current ->gp_seq. */
gps = rnp->gp_seq;
mask = rnp->grpmask;
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */
rcu_report_qs_rnp(mask, rnp_p, gps, flags);
}
/*
* Record a quiescent state for the specified CPU to that CPU's rcu_data
* structure. This must be called from the specified CPU.
*/
static void
rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
{
unsigned long flags;
unsigned long mask;
bool needwake;
struct rcu_node *rnp;
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
rdp->gpwrap) {
/*
* The grace period in which this quiescent state was
* recorded has ended, so don't report it upwards.
* We will instead need a new quiescent state that lies
* within the current grace period.
*/
rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
mask = rdp->grpmask;
rdp->core_needs_qs = false;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
} else {
/*
* This GP can't end until cpu checks in, so all of our
* callbacks can be processed during the next GP.
*/
needwake = rcu_accelerate_cbs(rnp, rdp);
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
/* ^^^ Released rnp->lock */
if (needwake)
rcu_gp_kthread_wake();
}
}
/*
* Check to see if there is a new grace period of which this CPU
* is not yet aware, and if so, set up local rcu_data state for it.
* Otherwise, see if this CPU has just passed through its first
* quiescent state for this grace period, and record that fact if so.
*/
static void
rcu_check_quiescent_state(struct rcu_data *rdp)
{
/* Check for grace-period ends and beginnings. */
note_gp_changes(rdp);
/*
* Does this CPU still need to do its part for current grace period?
* If no, return and let the other CPUs do their part as well.
*/
if (!rdp->core_needs_qs)
return;
/*
* Was there a quiescent state since the beginning of the grace
* period? If no, then exit and wait for the next call.
*/
if (rdp->cpu_no_qs.b.norm)
return;
/*
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
rcu_report_qs_rdp(rdp->cpu, rdp);
}
/*
* Near the end of the offline process. Trace the fact that this CPU
* is going offline.
*/
int rcutree_dying_cpu(unsigned int cpu)
{
bool blkd;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return 0;
blkd = !!(rnp->qsmask & rdp->grpmask);
trace_rcu_grace_period(rcu_state.name, rnp->gp_seq,
blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
return 0;
}
/*
* All CPUs for the specified rcu_node structure have gone offline,
* and all tasks that were preempted within an RCU read-side critical
* section while running on one of those CPUs have since exited their RCU
* read-side critical section. Some other CPU is reporting this fact with
* the specified rcu_node structure's ->lock held and interrupts disabled.
* This function therefore goes up the tree of rcu_node structures,
* clearing the corresponding bits in the ->qsmaskinit fields. Note that
* the leaf rcu_node structure's ->qsmaskinit field has already been
* updated.
*
* This function does check that the specified rcu_node structure has
* all CPUs offline and no blocked tasks, so it is OK to invoke it
* prematurely. That said, invoking it after the fact will cost you
* a needless lock acquisition. So once it has done its work, don't
* invoke it again.
*/
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
{
long mask;
struct rcu_node *rnp = rnp_leaf;
raw_lockdep_assert_held_rcu_node(rnp_leaf);
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
return;
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (!rnp)
break;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rnp->qsmaskinit &= ~mask;
/* Between grace periods, so better already be zero! */
WARN_ON_ONCE(rnp->qsmask);
if (rnp->qsmaskinit) {
raw_spin_unlock_rcu_node(rnp);
/* irqs remain disabled. */
return;
}
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
}
}
/*
* The CPU has been completely removed, and some other CPU is reporting
* this fact from process context. Do the remainder of the cleanup.
* There can only be one CPU hotplug operation at a time, so no need for
* explicit locking.
*/
int rcutree_dead_cpu(unsigned int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return 0;
/* Adjust any no-longer-needed kthreads. */
rcu_boost_kthread_setaffinity(rnp, -1);
/* Do any needed no-CB deferred wakeups from this CPU. */
do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu));
return 0;
}
/*
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
*/
static void rcu_do_batch(struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_head *rhp;
struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
long bl, count;
/* If no callbacks are ready, just return. */
if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
trace_rcu_batch_start(rcu_state.name,
rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist), 0);
trace_rcu_batch_end(rcu_state.name, 0,
!rcu_segcblist_empty(&rdp->cblist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
return;
}
/*
* Extract the list of ready callbacks, disabling to prevent
* races with call_rcu() from interrupt handlers. Leave the
* callback counts, as rcu_barrier() needs to be conservative.
*/
local_irq_save(flags);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
bl = rdp->blimit;
trace_rcu_batch_start(rcu_state.name,
rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist), bl);
rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
local_irq_restore(flags);
/* Invoke callbacks. */
rhp = rcu_cblist_dequeue(&rcl);
for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
debug_rcu_head_unqueue(rhp);
if (__rcu_reclaim(rcu_state.name, rhp))
rcu_cblist_dequeued_lazy(&rcl);
/*
* Stop only if limit reached and CPU has something to do.
* Note: The rcl structure counts down from zero.
*/
if (-rcl.len >= bl &&
(need_resched() ||
(!is_idle_task(current) && !rcu_is_callbacks_kthread())))
break;
}
local_irq_save(flags);
count = -rcl.len;
trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
is_idle_task(current), rcu_is_callbacks_kthread());
/* Update counts and requeue any remaining callbacks. */
rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
smp_mb(); /* List handling before counting for rcu_barrier(). */
rcu_segcblist_insert_count(&rdp->cblist, &rcl);
/* Reinstate batch limit if we have worked down the excess. */
count = rcu_segcblist_n_cbs(&rdp->cblist);
if (rdp->blimit == LONG_MAX && count <= qlowmark)
rdp->blimit = blimit;
/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
if (count == 0 && rdp->qlen_last_fqs_check != 0) {
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rcu_state.n_force_qs;
} else if (count < rdp->qlen_last_fqs_check - qhimark)
rdp->qlen_last_fqs_check = count;
/*
* The following usually indicates a double call_rcu(). To track
* this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.
*/
WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != (count == 0));
local_irq_restore(flags);
/* Re-invoke RCU core processing if there are callbacks remaining. */
if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_core();
}
/*
* This function is invoked from each scheduling-clock interrupt,
* and checks to see if this CPU is in a non-context-switch quiescent
* state, for example, user mode or idle loop. It also schedules RCU
* core processing. If the current grace period has gone on too long,
* it will ask the scheduler to manufacture a context switch for the sole
* purpose of providing a providing the needed quiescent state.
*/
void rcu_sched_clock_irq(int user)
{
trace_rcu_utilization(TPS("Start scheduler-tick"));
raw_cpu_inc(rcu_data.ticks_this_gp);
/* The load-acquire pairs with the store-release setting to true. */
if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
/* Idle and userspace execution already are quiescent states. */
if (!rcu_is_cpu_rrupt_from_idle() && !user) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
__this_cpu_write(rcu_data.rcu_urgent_qs, false);
}
rcu_flavor_sched_clock_irq(user);
if (rcu_pending())
invoke_rcu_core();
trace_rcu_utilization(TPS("End scheduler-tick"));
}
/*
* Scan the leaf rcu_node structures. For each structure on which all
* CPUs have reported a quiescent state and on which there are tasks
* blocking the current grace period, initiate RCU priority boosting.
* Otherwise, invoke the specified function to check dyntick state for
* each CPU that has not yet reported a quiescent state.
*/
static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
{
int cpu;
unsigned long flags;
unsigned long mask;
struct rcu_node *rnp;
rcu_for_each_leaf_node(rnp) {
cond_resched_tasks_rcu_qs();
mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->qsmask == 0) {
if (!IS_ENABLED(CONFIG_PREEMPT) ||
rcu_preempt_blocked_readers_cgp(rnp)) {
/*
* No point in scanning bits because they
* are all zero. But we might need to
* priority-boost blocked readers.
*/
rcu_initiate_boost(rnp, flags);
/* rcu_initiate_boost() releases rnp->lock */
continue;
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
continue;
}
for_each_leaf_node_possible_cpu(rnp, cpu) {
unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
if ((rnp->qsmask & bit) != 0) {
if (f(per_cpu_ptr(&rcu_data, cpu)))
mask |= bit;
}
}
if (mask != 0) {
/* Idle/offline CPUs, report (releases rnp->lock). */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
} else {
/* Nothing to do here, so just drop the lock. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
}
/*
* Force quiescent states on reluctant CPUs, and also detect which
* CPUs are in dyntick-idle mode.
*/
void rcu_force_quiescent_state(void)
{
unsigned long flags;
bool ret;
struct rcu_node *rnp;
struct rcu_node *rnp_old = NULL;
/* Funnel through hierarchy to reduce memory contention. */
rnp = __this_cpu_read(rcu_data.mynode);
for (; rnp != NULL; rnp = rnp->parent) {
ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
!raw_spin_trylock(&rnp->fqslock);
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
if (ret)
return;
rnp_old = rnp;
}
/* rnp_old == rcu_get_root(), rnp == NULL. */
/* Reached the root of the rcu_node tree, acquire lock. */
raw_spin_lock_irqsave_rcu_node(rnp_old, flags);
raw_spin_unlock(&rnp_old->fqslock);
if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
return; /* Someone beat us to it. */
}
WRITE_ONCE(rcu_state.gp_flags,
READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
rcu_gp_kthread_wake();
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(struct softirq_action *unused)
{
unsigned long flags;
struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
if (cpu_is_offline(smp_processor_id()))
return;
trace_rcu_utilization(TPS("Start RCU core"));
WARN_ON_ONCE(!rdp->beenonline);
/* Report any deferred quiescent states if preemption enabled. */
if (!(preempt_count() & PREEMPT_MASK)) {
rcu_preempt_deferred_qs(current);
} else if (rcu_preempt_need_deferred_qs(current)) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rdp);
/* No grace period and unregistered callbacks? */
if (!rcu_gp_in_progress() &&
rcu_segcblist_is_enabled(&rdp->cblist)) {
local_irq_save(flags);
if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
rcu_accelerate_cbs_unlocked(rnp, rdp);
local_irq_restore(flags);
}
rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
/* If there are callbacks ready, invoke them. */
if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_callbacks(rdp);
/* Do any needed deferred wakeups of rcuo kthreads. */
do_nocb_deferred_wakeup(rdp);
trace_rcu_utilization(TPS("End RCU core"));
}
/*
* Schedule RCU callback invocation. If the running implementation of RCU
* does not support RCU priority boosting, just do a direct call, otherwise
* wake up the per-CPU kernel kthread. Note that because we are running
* on the current CPU with softirqs disabled, the rcu_cpu_kthread_task
* cannot disappear out from under us.
*/
static void invoke_rcu_callbacks(struct rcu_data *rdp)
{
if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
return;
if (likely(!rcu_state.boost)) {
rcu_do_batch(rdp);
return;
}
invoke_rcu_callbacks_kthread();
}
static void invoke_rcu_core(void)
{
if (cpu_online(smp_processor_id()))
raise_softirq(RCU_SOFTIRQ);
}
/*
* Handle any core-RCU processing required by a call_rcu() invocation.
*/
static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
unsigned long flags)
{
/*
* If called from an extended quiescent state, invoke the RCU
* core in order to force a re-evaluation of RCU's idleness.
*/
if (!rcu_is_watching())
invoke_rcu_core();
/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id()))
return;
/*
* Force the grace period if too many callbacks or too long waiting.
* Enforce hysteresis, and don't invoke rcu_force_quiescent_state()
* if some other CPU has recently done so. Also, don't bother
* invoking rcu_force_quiescent_state() if the newly enqueued callback
* is the only one waiting for a grace period to complete.
*/
if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) >
rdp->qlen_last_fqs_check + qhimark)) {
/* Are we ignoring a completed grace period? */
note_gp_changes(rdp);
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress()) {
rcu_accelerate_cbs_unlocked(rdp->mynode, rdp);
} else {
/* Give the grace period a kick. */
rdp->blimit = LONG_MAX;
if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
rcu_force_quiescent_state();
rdp->n_force_qs_snap = rcu_state.n_force_qs;
rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
}
}
/*
* RCU callback function to leak a callback.
*/
static void rcu_leak_callback(struct rcu_head *rhp)
{
}
/*
* Helper function for call_rcu() and friends. The cpu argument will
* normally be -1, indicating "currently running CPU". It may specify
* a CPU only if that CPU is a no-CBs CPU. Currently, only rcu_barrier()
* is expected to specify a CPU.
*/
static void
__call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
{
unsigned long flags;
struct rcu_data *rdp;
/* Misaligned rcu_head! */
WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
if (debug_rcu_head_queue(head)) {
/*
* Probable double call_rcu(), so leak the callback.
* Use rcu:rcu_callback trace event to find the previous
* time callback was passed to __call_rcu().
*/
WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pS()!!!\n",
head, head->func);
WRITE_ONCE(head->func, rcu_leak_callback);
return;
}
head->func = func;
head->next = NULL;
local_irq_save(flags);
rdp = this_cpu_ptr(&rcu_data);
/* Add the callback to our list. */
if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist)) || cpu != -1) {
int offline;
if (cpu != -1)
rdp = per_cpu_ptr(&rcu_data, cpu);
if (likely(rdp->mynode)) {
/* Post-boot, so this should be for a no-CBs CPU. */
offline = !__call_rcu_nocb(rdp, head, lazy, flags);
WARN_ON_ONCE(offline);
/* Offline CPU, _call_rcu() illegal, leak callback. */
local_irq_restore(flags);
return;
}
/*
* Very early boot, before rcu_init(). Initialize if needed
* and then drop through to queue the callback.
*/
WARN_ON_ONCE(cpu != -1);
WARN_ON_ONCE(!rcu_is_watching());
if (rcu_segcblist_empty(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist);
}
rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rcu_state.name, head,
(unsigned long)func,
rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist));
else
trace_rcu_callback(rcu_state.name, head,
rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist));
/* Go handle any RCU core processing required. */
__call_rcu_core(rdp, head, flags);
local_irq_restore(flags);
}
/**
* call_rcu() - Queue an RCU callback for invocation after a grace period.
* @head: structure to be used for queueing the RCU updates.
* @func: actual callback function to be invoked after the grace period
*
* The callback function will be invoked some time after a full grace
* period elapses, in other words after all pre-existing RCU read-side
* critical sections have completed. However, the callback function
* might well execute concurrently with RCU read-side critical sections
* that started after call_rcu() was invoked. RCU read-side critical
* sections are delimited by rcu_read_lock() and rcu_read_unlock(), and
* may be nested. In addition, regions of code across which interrupts,
* preemption, or softirqs have been disabled also serve as RCU read-side
* critical sections. This includes hardware interrupt handlers, softirq
* handlers, and NMI handlers.
*
* Note that all CPUs must agree that the grace period extended beyond
* all pre-existing RCU read-side critical section. On systems with more
* than one CPU, this means that when "func()" is invoked, each CPU is
* guaranteed to have executed a full memory barrier since the end of its
* last RCU read-side critical section whose beginning preceded the call
* to call_rcu(). It also means that each CPU executing an RCU read-side
* critical section that continues beyond the start of "func()" must have
* executed a memory barrier after the call_rcu() but before the beginning
* of that RCU read-side critical section. Note that these guarantees
* include CPUs that are offline, idle, or executing in user mode, as
* well as CPUs that are executing in the kernel.
*
* Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
* resulting RCU callback function "func()", then both CPU A and CPU B are
* guaranteed to execute a full memory barrier during the time interval
* between the call to call_rcu() and the invocation of "func()" -- even
* if CPU A and CPU B are the same CPU (but again only if the system has
* more than one CPU).
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
__call_rcu(head, func, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu);
/*
* Queue an RCU callback for lazy invocation after a grace period.
* This will likely be later named something like "call_rcu_lazy()",
* but this change will require some way of tagging the lazy RCU
* callbacks in the list of pending callbacks. Until then, this
* function may only be called from __kfree_rcu().
*/
void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
{
__call_rcu(head, func, -1, 1);
}
EXPORT_SYMBOL_GPL(kfree_call_rcu);
/*
* During early boot, any blocking grace-period wait automatically
* implies a grace period. Later on, this is never the case for PREEMPT.
*
* Howevr, because a context switch is a grace period for !PREEMPT, any
* blocking grace-period wait automatically implies a grace period if
* there is only one CPU online at any point time during execution of
* either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to
* occasionally incorrectly indicate that there are multiple CPUs online
* when there was in fact only one the whole time, as this just adds some
* overhead: RCU still operates correctly.
*/
static int rcu_blocking_is_gp(void)
{
int ret;
if (IS_ENABLED(CONFIG_PREEMPT))
return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
might_sleep(); /* Check for RCU read-side critical section. */
preempt_disable();
ret = num_online_cpus() <= 1;
preempt_enable();
return ret;
}
/**
* synchronize_rcu - wait until a grace period has elapsed.
*
* Control will return to the caller some time after a full grace
* period has elapsed, in other words after all currently executing RCU
* read-side critical sections have completed. Note, however, that
* upon return from synchronize_rcu(), the caller might well be executing
* concurrently with new RCU read-side critical sections that began while
* synchronize_rcu() was waiting. RCU read-side critical sections are
* delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
* In addition, regions of code across which interrupts, preemption, or
* softirqs have been disabled also serve as RCU read-side critical
* sections. This includes hardware interrupt handlers, softirq handlers,
* and NMI handlers.
*
* Note that this guarantee implies further memory-ordering guarantees.
* On systems with more than one CPU, when synchronize_rcu() returns,
* each CPU is guaranteed to have executed a full memory barrier since
* the end of its last RCU read-side critical section whose beginning
* preceded the call to synchronize_rcu(). In addition, each CPU having
* an RCU read-side critical section that extends beyond the return from
* synchronize_rcu() is guaranteed to have executed a full memory barrier
* after the beginning of synchronize_rcu() and before the beginning of
* that RCU read-side critical section. Note that these guarantees include
* CPUs that are offline, idle, or executing in user mode, as well as CPUs
* that are executing in the kernel.
*
* Furthermore, if CPU A invoked synchronize_rcu(), which returned
* to its caller on CPU B, then both CPU A and CPU B are guaranteed
* to have executed a full memory barrier during the execution of
* synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but
* again only if the system has more than one CPU).
*/
void synchronize_rcu(void)
{
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu() in RCU read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/**
* get_state_synchronize_rcu - Snapshot current RCU state
*
* Returns a cookie that is used by a later call to cond_synchronize_rcu()
* to determine whether or not a full grace period has elapsed in the
* meantime.
*/
unsigned long get_state_synchronize_rcu(void)
{
/*
* Any prior manipulation of RCU-protected data must happen
* before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
return rcu_seq_snap(&rcu_state.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
/**
* cond_synchronize_rcu - Conditionally wait for an RCU grace period
*
* @oldstate: return value from earlier call to get_state_synchronize_rcu()
*
* If a full RCU grace period has elapsed since the earlier call to
* get_state_synchronize_rcu(), just return. Otherwise, invoke
* synchronize_rcu() to wait for a full grace period.
*
* Yes, this function does not take counter wrap into account. But
* counter wrap is harmless. If the counter wraps, we have waited for
* more than 2 billion grace periods (and way more on a 64-bit system!),
* so waiting for one additional grace period should be just fine.
*/
void cond_synchronize_rcu(unsigned long oldstate)
{
if (!rcu_seq_done(&rcu_state.gp_seq, oldstate))
synchronize_rcu();
else
smp_mb(); /* Ensure GP ends before subsequent accesses. */
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
/*
* Check to see if there is any immediate RCU-related work to be done by
* the current CPU, returning 1 if so and zero otherwise. The checks are
* in order of increasing expense: checks that can be carried out against
* CPU-local state are performed first. However, we must check for CPU
* stalls first, else we might not get a chance.
*/
static int rcu_pending(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
/* Check for CPU stalls, if enabled. */
check_cpu_stall(rdp);
/* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
if (rcu_nohz_full_cpu())
return 0;
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm)
return 1;
/* Does this CPU have callbacks ready to invoke? */
if (rcu_segcblist_ready_cbs(&rdp->cblist))
return 1;
/* Has RCU gone idle with this CPU needing another grace period? */
if (!rcu_gp_in_progress() &&
rcu_segcblist_is_enabled(&rdp->cblist) &&
!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return 1;
/* Have RCU grace period completed or started? */
if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq ||
unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
return 1;
/* Does this CPU need a deferred NOCB wakeup? */
if (rcu_nocb_need_deferred_wakeup(rdp))
return 1;
/* nothing to do */
return 0;
}
/*
* Helper function for rcu_barrier() tracing. If tracing is disabled,
* the compiler is expected to optimize this away.
*/
static void rcu_barrier_trace(const char *s, int cpu, unsigned long done)
{
trace_rcu_barrier(rcu_state.name, s, cpu,
atomic_read(&rcu_state.barrier_cpu_count), done);
}
/*
* RCU callback function for rcu_barrier(). If we are last, wake
* up the task executing rcu_barrier().
*/
static void rcu_barrier_callback(struct rcu_head *rhp)
{
if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
rcu_barrier_trace(TPS("LastCB"), -1,
rcu_state.barrier_sequence);
complete(&rcu_state.barrier_completion);
} else {
rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence);
}
}
/*
* Called with preemption disabled, and from cross-cpu IRQ context.
*/
static void rcu_barrier_func(void *unused)
{
struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence);
rdp->barrier_head.func = rcu_barrier_callback;
debug_rcu_head_queue(&rdp->barrier_head);
if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) {
atomic_inc(&rcu_state.barrier_cpu_count);
} else {
debug_rcu_head_unqueue(&rdp->barrier_head);
rcu_barrier_trace(TPS("IRQNQ"), -1,
rcu_state.barrier_sequence);
}
}
/**
* rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
*
* Note that this primitive does not necessarily wait for an RCU grace period
* to complete. For example, if there are no RCU callbacks queued anywhere
* in the system, then rcu_barrier() is within its rights to return
* immediately, without waiting for anything, much less an RCU grace period.
*/
void rcu_barrier(void)
{
int cpu;
struct rcu_data *rdp;
unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
rcu_barrier_trace(TPS("Begin"), -1, s);
/* Take mutex to serialize concurrent rcu_barrier() requests. */
mutex_lock(&rcu_state.barrier_mutex);
/* Did someone else do our work for us? */
if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
rcu_barrier_trace(TPS("EarlyExit"), -1,
rcu_state.barrier_sequence);
smp_mb(); /* caller's subsequent code after above check. */
mutex_unlock(&rcu_state.barrier_mutex);
return;
}
/* Mark the start of the barrier operation. */
rcu_seq_start(&rcu_state.barrier_sequence);
rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence);
/*
* Initialize the count to one rather than to zero in order to
* avoid a too-soon return to zero in case of a short grace period
* (or preemption of this task). Exclude CPU-hotplug operations
* to ensure that no offline CPU has callbacks queued.
*/
init_completion(&rcu_state.barrier_completion);
atomic_set(&rcu_state.barrier_cpu_count, 1);
get_online_cpus();
/*
* Force each CPU with callbacks to register a new callback.
* When that callback is invoked, we will know that all of the
* corresponding CPU's preceding callbacks have been invoked.
*/
for_each_possible_cpu(cpu) {
if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu))
continue;
rdp = per_cpu_ptr(&rcu_data, cpu);
if (rcu_is_nocb_cpu(cpu)) {
if (!rcu_nocb_cpu_needs_barrier(cpu)) {
rcu_barrier_trace(TPS("OfflineNoCB"), cpu,
rcu_state.barrier_sequence);
} else {
rcu_barrier_trace(TPS("OnlineNoCB"), cpu,
rcu_state.barrier_sequence);
smp_mb__before_atomic();
atomic_inc(&rcu_state.barrier_cpu_count);
__call_rcu(&rdp->barrier_head,
rcu_barrier_callback, cpu, 0);
}
} else if (rcu_segcblist_n_cbs(&rdp->cblist)) {
rcu_barrier_trace(TPS("OnlineQ"), cpu,
rcu_state.barrier_sequence);
smp_call_function_single(cpu, rcu_barrier_func, NULL, 1);
} else {
rcu_barrier_trace(TPS("OnlineNQ"), cpu,
rcu_state.barrier_sequence);
}
}
put_online_cpus();
/*
* Now that we have an rcu_barrier_callback() callback on each
* CPU, and thus each counted, remove the initial count.
*/
if (atomic_dec_and_test(&rcu_state.barrier_cpu_count))
complete(&rcu_state.barrier_completion);
/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
wait_for_completion(&rcu_state.barrier_completion);
/* Mark the end of the barrier operation. */
rcu_barrier_trace(TPS("Inc2"), -1, rcu_state.barrier_sequence);
rcu_seq_end(&rcu_state.barrier_sequence);
/* Other rcu_barrier() invocations can now safely proceed. */
mutex_unlock(&rcu_state.barrier_mutex);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
/*
* Propagate ->qsinitmask bits up the rcu_node tree to account for the
* first CPU in a given leaf rcu_node structure coming online. The caller
* must hold the corresponding leaf rcu_node ->lock with interrrupts
* disabled.
*/
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
{
long mask;
long oldmask;
struct rcu_node *rnp = rnp_leaf;
raw_lockdep_assert_held_rcu_node(rnp_leaf);
WARN_ON_ONCE(rnp->wait_blkd_tasks);
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (rnp == NULL)
return;
raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
oldmask = rnp->qsmaskinit;
rnp->qsmaskinit |= mask;
raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
if (oldmask)
return;
}
}
/*
* Do boot-time initialization of a CPU's per-CPU RCU data.
*/
static void __init
rcu_boot_init_percpu_data(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
/* Set up local state, ensuring consistent view of global state. */
rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
WARN_ON_ONCE(rdp->dynticks_nesting != 1);
WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;
rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
rdp->rcu_onl_gp_seq = rcu_state.gp_seq;
rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
rdp->cpu = cpu;
rcu_boot_init_nocb_percpu_data(rdp);
}
/*
* Invoked early in the CPU-online process, when pretty much all services
* are available. The incoming CPU is not present.
*
* Initializes a CPU's per-CPU RCU data. Note that only one online or
* offline event can be happening at a given time. Note also that we can
* accept some slop in the rsp->gp_seq access due to the fact that this
* CPU cannot possibly have any RCU callbacks in flight yet.
*/
int rcutree_prepare_cpu(unsigned int cpu)
{
unsigned long flags;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rcu_get_root();
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rcu_state.n_force_qs;
rdp->blimit = blimit;
if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */
!init_nocb_callback_list(rdp))
rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */
rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */
rcu_dynticks_eqs_online();
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
/*
* Add CPU to leaf rcu_node pending-online bitmask. Any needed
* propagation up the rcu_node tree will happen at the beginning
* of the next grace period.
*/
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rdp->beenonline = true; /* We have now been online. */
rdp->gp_seq = rnp->gp_seq;
rdp->gp_seq_needed = rnp->gp_seq;
rdp->cpu_no_qs.b.norm = true;
rdp->core_needs_qs = false;
rdp->rcu_iw_pending = false;
rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_prepare_kthreads(cpu);
rcu_spawn_cpu_nocb_kthread(cpu);
return 0;
}
/*
* Update RCU priority boot kthread affinity for CPU-hotplug changes.
*/
static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
rcu_boost_kthread_setaffinity(rdp->mynode, outgoing);
}
/*
* Near the end of the CPU-online process. Pretty much all services
* enabled, and the CPU is now very much alive.
*/
int rcutree_online_cpu(unsigned int cpu)
{
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
rdp = per_cpu_ptr(&rcu_data, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rnp->ffmask |= rdp->grpmask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return 0; /* Too early in boot for scheduler work. */
sync_sched_exp_online_cleanup(cpu);
rcutree_affinity_setting(cpu, -1);
return 0;
}
/*
* Near the beginning of the process. The CPU is still very much alive
* with pretty much all services enabled.
*/
int rcutree_offline_cpu(unsigned int cpu)
{
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
rdp = per_cpu_ptr(&rcu_data, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rnp->ffmask &= ~rdp->grpmask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcutree_affinity_setting(cpu, cpu);
return 0;
}
static DEFINE_PER_CPU(int, rcu_cpu_started);
/*
* Mark the specified CPU as being online so that subsequent grace periods
* (both expedited and normal) will wait on it. Note that this means that
* incoming CPUs are not allowed to use RCU read-side critical sections
* until this function is called. Failing to observe this restriction
* will result in lockdep splats.
*
* Note that this function is special in that it is invoked directly
* from the incoming CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
*/
void rcu_cpu_starting(unsigned int cpu)
{
unsigned long flags;
unsigned long mask;
int nbits;
unsigned long oldmask;
struct rcu_data *rdp;
struct rcu_node *rnp;
if (per_cpu(rcu_cpu_started, cpu))
return;
per_cpu(rcu_cpu_started, cpu) = 1;
rdp = per_cpu_ptr(&rcu_data, cpu);
rnp = rdp->mynode;
mask = rdp->grpmask;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rnp->qsmaskinitnext |= mask;
oldmask = rnp->expmaskinitnext;
rnp->expmaskinitnext |= mask;
oldmask ^= rnp->expmaskinitnext;
nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
/* Allow lockless access for expedited grace periods. */
smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */
rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
/* Report QS -after- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
} else {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* The outgoing function has no further need of RCU, so remove it from
* the rcu_node tree's ->qsmaskinitnext bit masks.
*
* Note that this function is special in that it is invoked directly
* from the outgoing CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
*/
void rcu_report_dead(unsigned int cpu)
{
unsigned long flags;
unsigned long mask;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
/* QS for any half-done expedited grace period. */
preempt_disable();
rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
preempt_enable();
rcu_preempt_deferred_qs(current);
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
raw_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
/* Report quiescent state -before- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
rnp->qsmaskinitnext &= ~mask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
raw_spin_unlock(&rcu_state.ofl_lock);
per_cpu(rcu_cpu_started, cpu) = 0;
}
/*
* The outgoing CPU has just passed through the dying-idle state, and we
* are being invoked from the CPU that was IPIed to continue the offline
* operation. Migrate the outgoing CPU's callbacks to the current CPU.
*/
void rcutree_migrate_callbacks(int cpu)
{
unsigned long flags;
struct rcu_data *my_rdp;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp_root = rcu_get_root();
bool needwake;
if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
return; /* No callbacks to migrate. */
local_irq_save(flags);
my_rdp = this_cpu_ptr(&rcu_data);
if (rcu_nocb_adopt_orphan_cbs(my_rdp, rdp, flags)) {
local_irq_restore(flags);
return;
}
raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
/* Leverage recent GPs and set GP for new callbacks. */
needwake = rcu_advance_cbs(rnp_root, rdp) ||
rcu_advance_cbs(rnp_root, my_rdp);
rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist);
WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
!rcu_segcblist_n_cbs(&my_rdp->cblist));
raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags);
if (needwake)
rcu_gp_kthread_wake();
WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
!rcu_segcblist_empty(&rdp->cblist),
"rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
cpu, rcu_segcblist_n_cbs(&rdp->cblist),
rcu_segcblist_first_cb(&rdp->cblist));
}
#endif
/*
* On non-huge systems, use expedited RCU grace periods to make suspend
* and hibernation run faster.
*/
static int rcu_pm_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
switch (action) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
rcu_expedite_gp();
break;
case PM_POST_HIBERNATION:
case PM_POST_SUSPEND:
rcu_unexpedite_gp();
break;
default:
break;
}
return NOTIFY_OK;
}
/*
* Spawn the kthreads that handle RCU's grace periods.
*/
static int __init rcu_spawn_gp_kthread(void)
{
unsigned long flags;
int kthread_prio_in = kthread_prio;
struct rcu_node *rnp;
struct sched_param sp;
struct task_struct *t;
/* Force priority into range. */
if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2
&& IS_BUILTIN(CONFIG_RCU_TORTURE_TEST))
kthread_prio = 2;
else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
kthread_prio = 1;
else if (kthread_prio < 0)
kthread_prio = 0;
else if (kthread_prio > 99)
kthread_prio = 99;
if (kthread_prio != kthread_prio_in)
pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
kthread_prio, kthread_prio_in);
rcu_scheduler_fully_active = 1;
t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name);
if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__))
return 0;
rnp = rcu_get_root();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rcu_state.gp_kthread = t;
if (kthread_prio) {
sp.sched_priority = kthread_prio;
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
wake_up_process(t);
rcu_spawn_nocb_kthreads();
rcu_spawn_boost_kthreads();
return 0;
}
early_initcall(rcu_spawn_gp_kthread);
/*
* This function is invoked towards the end of the scheduler's
* initialization process. Before this is called, the idle task might
* contain synchronous grace-period primitives (during which time, this idle
* task is booting the system, and such primitives are no-ops). After this
* function is called, any synchronous grace-period primitives are run as
* expedited, with the requesting task driving the grace period forward.
* A later core_initcall() rcu_set_runtime_mode() will switch to full
* runtime RCU functionality.
*/
void rcu_scheduler_starting(void)
{
WARN_ON(num_online_cpus() != 1);
WARN_ON(nr_context_switches() > 0);
rcu_test_sync_prims();
rcu_scheduler_active = RCU_SCHEDULER_INIT;
rcu_test_sync_prims();
}
/*
* Helper function for rcu_init() that initializes the rcu_state structure.
*/
static void __init rcu_init_one(void)
{
static const char * const buf[] = RCU_NODE_NAME_INIT;
static const char * const fqs[] = RCU_FQS_NAME_INIT;
static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
int levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */
int cpustride = 1;
int i;
int j;
struct rcu_node *rnp;
BUILD_BUG_ON(RCU_NUM_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */
/* Silence gcc 4.8 false positive about array index out of range. */
if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
panic("rcu_init_one: rcu_num_lvls out of range");
/* Initialize the level-tracking arrays. */
for (i = 1; i < rcu_num_lvls; i++)
rcu_state.level[i] =
rcu_state.level[i - 1] + num_rcu_lvl[i - 1];
rcu_init_levelspread(levelspread, num_rcu_lvl);
/* Initialize the elements themselves, starting from the leaves. */
for (i = rcu_num_lvls - 1; i >= 0; i--) {
cpustride *= levelspread[i];
rnp = rcu_state.level[i];
for (j = 0; j < num_rcu_lvl[i]; j++, rnp++) {
raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock));
lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock),
&rcu_node_class[i], buf[i]);
raw_spin_lock_init(&rnp->fqslock);
lockdep_set_class_and_name(&rnp->fqslock,
&rcu_fqs_class[i], fqs[i]);
rnp->gp_seq = rcu_state.gp_seq;
rnp->gp_seq_needed = rcu_state.gp_seq;
rnp->completedqs = rcu_state.gp_seq;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
rnp->grplo = j * cpustride;
rnp->grphi = (j + 1) * cpustride - 1;
if (rnp->grphi >= nr_cpu_ids)
rnp->grphi = nr_cpu_ids - 1;
if (i == 0) {
rnp->grpnum = 0;
rnp->grpmask = 0;
rnp->parent = NULL;
} else {
rnp->grpnum = j % levelspread[i - 1];
rnp->grpmask = BIT(rnp->grpnum);
rnp->parent = rcu_state.level[i - 1] +
j / levelspread[i - 1];
}
rnp->level = i;
INIT_LIST_HEAD(&rnp->blkd_tasks);
rcu_init_one_nocb(rnp);
init_waitqueue_head(&rnp->exp_wq[0]);
init_waitqueue_head(&rnp->exp_wq[1]);
init_waitqueue_head(&rnp->exp_wq[2]);
init_waitqueue_head(&rnp->exp_wq[3]);
spin_lock_init(&rnp->exp_lock);
}
}
init_swait_queue_head(&rcu_state.gp_wq);
init_swait_queue_head(&rcu_state.expedited_wq);
rnp = rcu_first_leaf_node();
for_each_possible_cpu(i) {
while (i > rnp->grphi)
rnp++;
per_cpu_ptr(&rcu_data, i)->mynode = rnp;
rcu_boot_init_percpu_data(i);
}
}
/*
* Compute the rcu_node tree geometry from kernel parameters. This cannot
* replace the definitions in tree.h because those are needed to size
* the ->node array in the rcu_state structure.
*/
static void __init rcu_init_geometry(void)
{
ulong d;
int i;
int rcu_capacity[RCU_NUM_LVLS];
/*
* Initialize any unspecified boot parameters.
* The default values of jiffies_till_first_fqs and
* jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS
* value, which is a function of HZ, then adding one for each
* RCU_JIFFIES_FQS_DIV CPUs that might be on the system.
*/
d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
if (jiffies_till_first_fqs == ULONG_MAX)
jiffies_till_first_fqs = d;
if (jiffies_till_next_fqs == ULONG_MAX)
jiffies_till_next_fqs = d;
adjust_jiffies_till_sched_qs();
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
rcu_fanout_leaf, nr_cpu_ids);
/*
* The boot-time rcu_fanout_leaf parameter must be at least two
* and cannot exceed the number of bits in the rcu_node masks.
* Complain and fall back to the compile-time values if this
* limit is exceeded.
*/
if (rcu_fanout_leaf < 2 ||
rcu_fanout_leaf > sizeof(unsigned long) * 8) {
rcu_fanout_leaf = RCU_FANOUT_LEAF;
WARN_ON(1);
return;
}
/*
* Compute number of nodes that can be handled an rcu_node tree
* with the given number of levels.
*/
rcu_capacity[0] = rcu_fanout_leaf;
for (i = 1; i < RCU_NUM_LVLS; i++)
rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
/*
* The tree must be able to accommodate the configured number of CPUs.
* If this limit is exceeded, fall back to the compile-time values.
*/
if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1]) {
rcu_fanout_leaf = RCU_FANOUT_LEAF;
WARN_ON(1);
return;
}
/* Calculate the number of levels in the tree. */
for (i = 0; nr_cpu_ids > rcu_capacity[i]; i++) {
}
rcu_num_lvls = i + 1;
/* Calculate the number of rcu_nodes at each level of the tree. */
for (i = 0; i < rcu_num_lvls; i++) {
int cap = rcu_capacity[(rcu_num_lvls - 1) - i];
num_rcu_lvl[i] = DIV_ROUND_UP(nr_cpu_ids, cap);
}
/* Calculate the total number of rcu_node structures. */
rcu_num_nodes = 0;
for (i = 0; i < rcu_num_lvls; i++)
rcu_num_nodes += num_rcu_lvl[i];
}
/*
* Dump out the structure of the rcu_node combining tree associated
* with the rcu_state structure.
*/
static void __init rcu_dump_rcu_node_tree(void)
{
int level = 0;
struct rcu_node *rnp;
pr_info("rcu_node tree layout dump\n");
pr_info(" ");
rcu_for_each_node_breadth_first(rnp) {
if (rnp->level != level) {
pr_cont("\n");
pr_info(" ");
level = rnp->level;
}
pr_cont("%d:%d ^%d ", rnp->grplo, rnp->grphi, rnp->grpnum);
}
pr_cont("\n");
}
struct workqueue_struct *rcu_gp_wq;
struct workqueue_struct *rcu_par_gp_wq;
void __init rcu_init(void)
{
int cpu;
rcu_early_boot_tests();
rcu_bootup_announce();
rcu_init_geometry();
rcu_init_one();
if (dump_tree)
rcu_dump_rcu_node_tree();
open_softirq(RCU_SOFTIRQ, rcu_core);
/*
* We don't need protection against CPU-hotplug here because
* this is called early in boot, before either interrupts
* or the scheduler are operational.
*/
pm_notifier(rcu_pm_notify, 0);
for_each_online_cpu(cpu) {
rcutree_prepare_cpu(cpu);
rcu_cpu_starting(cpu);
rcutree_online_cpu(cpu);
}
/* Create workqueue for expedited GPs and for Tree SRCU. */
rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_gp_wq);
rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_par_gp_wq);
srcu_init();
}
#include "tree_stall.h"
#include "tree_exp.h"
#include "tree_plugin.h"