linux/kernel/rcu/tiny.c
Linus Torvalds 3ba7dfb8da RCU pull request for v6.15
This pull request contains the following branches:
 
 docs.2025.02.04a:
  - Add broken-timing possibility to stallwarn.rst.
  - Improve discussion of this_cpu_ptr(), add raw_cpu_ptr().
  - Document self-propagating callbacks.
  - Point call_srcu() to call_rcu() for detailed memory ordering.
  - Add CONFIG_RCU_LAZY delays to call_rcu() kernel-doc header.
  - Clarify RCU_LAZY and RCU_LAZY_DEFAULT_OFF help text.
  - Remove references to old grace-period-wait primitives.
 
 srcu.2025.02.05a:
  - Introduce srcu_read_{un,}lock_fast(), which is similar to
    srcu_read_{un,}lock_lite(): avoid smp_mb()s in lock and unlock at the
    cost of calling synchronize_rcu() in synchronize_srcu(). Moreover, by
    returning the percpu offset of the counter at srcu_read_lock_fast()
    time, srcu_read_unlock_fast() can save extra pointer dereferencing,
    which makes it faster than srcu_read_{un,}lock_lite().
    srcu_read_{un,}lock_fast() are intended to replace
    rcu_read_{un,}lock_trace() if possible.
 
 torture.2025.02.05a:
  - Add get_torture_init_jiffies() to return the start time of the test.
  - Add a test_boost_holdoff module parameter to allow delaying boosting
    tests when building rcutorture as built-in.
  - Add grace period sequence number logging at the beginning and end of
    failure/close-call results.
  - Switch to hexadecimal for the expedited grace period sequence number
    in the rcu_exp_grace_period trace point.
  - Make cur_ops->format_gp_seqs take buffer length.
  - Move RCU_TORTURE_TEST_{CHK_RDR_STATE,LOG_CPU} to bool.
  - Complain when invalid SRCU reader_flavor is specified.
  - Add FORCE_NEED_SRCU_NMI_SAFE Kconfig for testing, which forces SRCU
    uses atomics even when percpu ops are NMI safe, and use the Kconfig
    for SRCU lockdep testing.
 
 misc.2025.03.04a:
  - Split rcu_report_exp_cpu_mult() mask parameter and use for tracing.
  - Remove READ_ONCE() for rdp->gpwrap access in __note_gp_changes().
  - Fix get_state_synchronize_rcu_full() GP-start detection.
  - Move RCU Tasks self-tests to core_initcall().
  - Print segment lengths in show_rcu_nocb_gp_state().
  - Make RCU watch ct_kernel_exit_state() warning.
  - Flush console log from kernel_power_off().
  - rcutorture: Allow a negative value for nfakewriters.
  - rcu: Update TREE05.boot to test normal synchronize_rcu().
  - rcu: Use _full() API to debug synchronize_rcu().
 
 lazypreempt.2025.03.04a: Make RCU handle PREEMPT_LAZY better:
  - Fix header guard for rcu_all_qs().
  - rcu: Rename PREEMPT_AUTO to PREEMPT_LAZY.
  - Update __cond_resched comment about RCU quiescent states.
  - Handle unstable rdp in rcu_read_unlock_strict().
  - Handle quiescent states for PREEMPT_RCU=n, PREEMPT_COUNT=y.
  - osnoise: Provide quiescent states.
  - Adjust rcutorture with possible PREEMPT_RCU=n && PREEMPT_COUNT=y
    combination.
  - Limit PREEMPT_RCU configurations.
  - Make rcutorture senario TREE07 and senario TREE10 use PREEMPT_LAZY=y.
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEj5IosQTPz8XU1wRHSXnow7UH+rgFAmfeBLQACgkQSXnow7UH
 +rh11Qf/Rt6IZJ/YT/V9Sd+8hMx4O0BMh779pr9cD6mbAG+FDk2Yeva1m8vIdFOb
 qId6oc8K/ef2JfFjSn0oHMzQP2D3XUyiJWPNbBDHv/D8Os8GZgjzu8dkxVkSbdbY
 OxtvIflbcqFN1JDJfGKZnTEW0/YxGqfnS9b6R7iyyA7SOGQ/WubGOE5qNCqPufc9
 zJiP+qTUFYQzCIiPlEJul39o9KboPogbt3QAAQjWmi3utd77ehJnm/15FvAjyau4
 uhC2cnGfMY535rQaiaQeBQ/IHIowKripCq0JQFvcUNdyArZM3HOI2x79+2II6ft7
 mjHskNODOIJHfW2o1RzQ0yRYAywFIg==
 =J+mH
 -----END PGP SIGNATURE-----

Merge tag 'rcu-next-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux

Pull RCU updates from Boqun Feng:
 "Documentation:
   - Add broken-timing possibility to stallwarn.rst
   - Improve discussion of this_cpu_ptr(), add raw_cpu_ptr()
   - Document self-propagating callbacks
   - Point call_srcu() to call_rcu() for detailed memory ordering
   - Add CONFIG_RCU_LAZY delays to call_rcu() kernel-doc header
   - Clarify RCU_LAZY and RCU_LAZY_DEFAULT_OFF help text
   - Remove references to old grace-period-wait primitives

  srcu:
   - Introduce srcu_read_{un,}lock_fast(), which is similar to
     srcu_read_{un,}lock_lite(): avoid smp_mb()s in lock and unlock
     at the cost of calling synchronize_rcu() in synchronize_srcu()

     Moreover, by returning the percpu offset of the counter at
     srcu_read_lock_fast() time, srcu_read_unlock_fast() can avoid
     extra pointer dereferencing, which makes it faster than
     srcu_read_{un,}lock_lite()

     srcu_read_{un,}lock_fast() are intended to replace
     rcu_read_{un,}lock_trace() if possible

  RCU torture:
   - Add get_torture_init_jiffies() to return the start time of the test
   - Add a test_boost_holdoff module parameter to allow delaying
     boosting tests when building rcutorture as built-in
   - Add grace period sequence number logging at the beginning and end
     of failure/close-call results
   - Switch to hexadecimal for the expedited grace period sequence
     number in the rcu_exp_grace_period trace point
   - Make cur_ops->format_gp_seqs take buffer length
   - Move RCU_TORTURE_TEST_{CHK_RDR_STATE,LOG_CPU} to bool
   - Complain when invalid SRCU reader_flavor is specified
   - Add FORCE_NEED_SRCU_NMI_SAFE Kconfig for testing, which forces SRCU
     uses atomics even when percpu ops are NMI safe, and use the Kconfig
     for SRCU lockdep testing

  Misc:
   - Split rcu_report_exp_cpu_mult() mask parameter and use for tracing
   - Remove READ_ONCE() for rdp->gpwrap access in __note_gp_changes()
   - Fix get_state_synchronize_rcu_full() GP-start detection
   - Move RCU Tasks self-tests to core_initcall()
   - Print segment lengths in show_rcu_nocb_gp_state()
   - Make RCU watch ct_kernel_exit_state() warning
   - Flush console log from kernel_power_off()
   - rcutorture: Allow a negative value for nfakewriters
   - rcu: Update TREE05.boot to test normal synchronize_rcu()
   - rcu: Use _full() API to debug synchronize_rcu()

  Make RCU handle PREEMPT_LAZY better:
   - Fix header guard for rcu_all_qs()
   - rcu: Rename PREEMPT_AUTO to PREEMPT_LAZY
   - Update __cond_resched comment about RCU quiescent states
   - Handle unstable rdp in rcu_read_unlock_strict()
   - Handle quiescent states for PREEMPT_RCU=n, PREEMPT_COUNT=y
   - osnoise: Provide quiescent states
   - Adjust rcutorture with possible PREEMPT_RCU=n && PREEMPT_COUNT=y
     combination
   - Limit PREEMPT_RCU configurations
   - Make rcutorture senario TREE07 and senario TREE10 use
     PREEMPT_LAZY=y"

* tag 'rcu-next-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux: (59 commits)
  rcutorture: Make scenario TREE07 build CONFIG_PREEMPT_LAZY=y
  rcutorture: Make scenario TREE10 build CONFIG_PREEMPT_LAZY=y
  rcu: limit PREEMPT_RCU configurations
  rcutorture: Update ->extendables check for lazy preemption
  rcutorture: Update rcutorture_one_extend_check() for lazy preemption
  osnoise: provide quiescent states
  rcu: Use _full() API to debug synchronize_rcu()
  rcu: Update TREE05.boot to test normal synchronize_rcu()
  rcutorture: Allow a negative value for nfakewriters
  Flush console log from kernel_power_off()
  context_tracking: Make RCU watch ct_kernel_exit_state() warning
  rcu/nocb: Print segment lengths in show_rcu_nocb_gp_state()
  rcu-tasks: Move RCU Tasks self-tests to core_initcall()
  rcu: Fix get_state_synchronize_rcu_full() GP-start detection
  torture: Make SRCU lockdep testing use srcu_read_lock_nmisafe()
  srcu: Add FORCE_NEED_SRCU_NMI_SAFE Kconfig for testing
  rcutorture: Complain when invalid SRCU reader_flavor is specified
  rcutorture: Move RCU_TORTURE_TEST_{CHK_RDR_STATE,LOG_CPU} to bool
  rcutorture: Make cur_ops->format_gp_seqs take buffer length
  rcutorture: Add ftrace-compatible timestamp to GP# failure/close-call output
  ...
2025-03-24 19:41:37 -07:00

255 lines
6.7 KiB
C

// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
*
* Copyright IBM Corporation, 2008
*
* Author: Paul E. McKenney <paulmck@linux.ibm.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#include <linux/completion.h>
#include <linux/interrupt.h>
#include <linux/notifier.h>
#include <linux/rcupdate_wait.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/cpu.h>
#include <linux/prefetch.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include "rcu.h"
/* Global control variables for rcupdate callback mechanism. */
struct rcu_ctrlblk {
struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
struct rcu_head **curtail; /* ->next pointer of last CB. */
unsigned long gp_seq; /* Grace-period counter. */
};
/* Definition for rcupdate control block. */
static struct rcu_ctrlblk rcu_ctrlblk = {
.donetail = &rcu_ctrlblk.rcucblist,
.curtail = &rcu_ctrlblk.rcucblist,
.gp_seq = 0 - 300UL,
};
void rcu_barrier(void)
{
wait_rcu_gp(call_rcu_hurry);
}
EXPORT_SYMBOL(rcu_barrier);
/* Record an rcu quiescent state. */
void rcu_qs(void)
{
unsigned long flags;
local_irq_save(flags);
if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
raise_softirq_irqoff(RCU_SOFTIRQ);
}
WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
local_irq_restore(flags);
}
/*
* Check to see if the scheduling-clock interrupt came from an extended
* quiescent state, and, if so, tell RCU about it. This function must
* be called from hardirq context. It is normally called from the
* scheduling-clock interrupt.
*/
void rcu_sched_clock_irq(int user)
{
if (user) {
rcu_qs();
} else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
}
/*
* Reclaim the specified callback, either by invoking it for non-kfree cases or
* freeing it directly (for kfree). Return true if kfreeing, false otherwise.
*/
static inline bool rcu_reclaim_tiny(struct rcu_head *head)
{
rcu_callback_t f;
rcu_lock_acquire(&rcu_callback_map);
trace_rcu_invoke_callback("", head);
f = head->func;
debug_rcu_head_callback(head);
WRITE_ONCE(head->func, (rcu_callback_t)0L);
f(head);
rcu_lock_release(&rcu_callback_map);
return false;
}
/* Invoke the RCU callbacks whose grace period has elapsed. */
static __latent_entropy void rcu_process_callbacks(void)
{
struct rcu_head *next, *list;
unsigned long flags;
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
if (rcu_ctrlblk.donetail == &rcu_ctrlblk.rcucblist) {
/* No callbacks ready, so just leave. */
local_irq_restore(flags);
return;
}
list = rcu_ctrlblk.rcucblist;
rcu_ctrlblk.rcucblist = *rcu_ctrlblk.donetail;
*rcu_ctrlblk.donetail = NULL;
if (rcu_ctrlblk.curtail == rcu_ctrlblk.donetail)
rcu_ctrlblk.curtail = &rcu_ctrlblk.rcucblist;
rcu_ctrlblk.donetail = &rcu_ctrlblk.rcucblist;
local_irq_restore(flags);
/* Invoke the callbacks on the local list. */
while (list) {
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
rcu_reclaim_tiny(list);
list = next;
}
}
/*
* Wait for a grace period to elapse. But it is illegal to invoke
* synchronize_rcu() from within an RCU read-side critical section.
* Therefore, any legal call to synchronize_rcu() is a quiescent state,
* and so on a UP system, synchronize_rcu() need do nothing, other than
* let the polled APIs know that another grace period elapsed.
*
* (But Lai Jiangshan points out the benefits of doing might_sleep()
* to reduce latency.)
*
* Cool, huh? (Due to Josh Triplett.)
*/
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");
preempt_disable();
WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
preempt_enable();
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/*
* Post an RCU callback to be invoked after the end of an RCU grace
* period. But since we have but one CPU, that would be after any
* quiescent state.
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
static atomic_t doublefrees;
unsigned long flags;
if (debug_rcu_head_queue(head)) {
if (atomic_inc_return(&doublefrees) < 4) {
pr_err("%s(): Double-freed CB %p->%pS()!!! ", __func__, head, head->func);
mem_dump_obj(head);
}
return;
}
head->func = func;
head->next = NULL;
local_irq_save(flags);
*rcu_ctrlblk.curtail = head;
rcu_ctrlblk.curtail = &head->next;
local_irq_restore(flags);
if (unlikely(is_idle_task(current))) {
/* force scheduling for rcu_qs() */
resched_cpu(0);
}
}
EXPORT_SYMBOL_GPL(call_rcu);
/*
* Store a grace-period-counter "cookie". For more information,
* see the Tree RCU header comment.
*/
void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
{
rgosp->rgos_norm = RCU_GET_STATE_COMPLETED;
}
EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu_full);
/*
* Return a grace-period-counter "cookie". For more information,
* see the Tree RCU header comment.
*/
unsigned long get_state_synchronize_rcu(void)
{
return READ_ONCE(rcu_ctrlblk.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
/*
* Return a grace-period-counter "cookie" and ensure that a future grace
* period completes. For more information, see the Tree RCU header comment.
*/
unsigned long start_poll_synchronize_rcu(void)
{
unsigned long gp_seq = get_state_synchronize_rcu();
if (unlikely(is_idle_task(current))) {
/* force scheduling for rcu_qs() */
resched_cpu(0);
}
return gp_seq;
}
EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
/*
* Return true if the grace period corresponding to oldstate has completed
* and false otherwise. For more information, see the Tree RCU header
* comment.
*/
bool poll_state_synchronize_rcu(unsigned long oldstate)
{
return oldstate == RCU_GET_STATE_COMPLETED || READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
}
EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST)
unsigned long long rcutorture_gather_gp_seqs(void)
{
return READ_ONCE(rcu_ctrlblk.gp_seq) & 0xffffULL;
}
EXPORT_SYMBOL_GPL(rcutorture_gather_gp_seqs);
void rcutorture_format_gp_seqs(unsigned long long seqs, char *cp, size_t len)
{
snprintf(cp, len, "g%04llx", seqs & 0xffffULL);
}
EXPORT_SYMBOL_GPL(rcutorture_format_gp_seqs);
#endif
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
rcu_early_boot_tests();
tasks_cblist_init_generic();
}