Initial commit: Linux kernel 4.19 for Unplugged OS

This commit is contained in:
ziv committed 2025-10-06 13:52:42 +00:00
commit d30235b04c
80519 files changed
+35800681

No files matched your search

+241
View File
@@ -0,0 +1,241 @@
#
# RCU-related configuration options
#
menu "RCU Subsystem"
config TREE_RCU
bool
default y if !PREEMPT && SMP
help
This option selects the RCU implementation that is
designed for very large SMP system with hundreds or
thousands of CPUs. It also scales down nicely to
smaller systems.
config PREEMPT_RCU
bool
default y if PREEMPT
help
This option selects the RCU implementation that is
designed for very large SMP systems with hundreds or
thousands of CPUs, but for which real-time response
is also required. It also scales down nicely to
smaller systems.
Select this option if you are unsure.
config TINY_RCU
bool
default y if !PREEMPT && !SMP
help
This option selects the RCU implementation that is
designed for UP systems from which real-time response
is not required. This option greatly reduces the
memory footprint of RCU.
config RCU_EXPERT
bool "Make expert-level adjustments to RCU configuration"
default n
help
This option needs to be enabled if you wish to make
expert-level adjustments to RCU configuration. By default,
no such adjustments can be made, which has the often-beneficial
side-effect of preventing "make oldconfig" from asking you all
sorts of detailed questions about how you would like numerous
obscure RCU options to be set up.
Say Y if you need to make expert-level adjustments to RCU.
Say N if you are unsure.
config SRCU
bool
help
This option selects the sleepable version of RCU. This version
permits arbitrary sleeping or blocking within RCU read-side critical
sections.
config TINY_SRCU
bool
default y if SRCU && TINY_RCU
help
This option selects the single-CPU non-preemptible version of SRCU.
config TREE_SRCU
bool
default y if SRCU && !TINY_RCU
help
This option selects the full-fledged version of SRCU.
config TASKS_RCU
def_bool PREEMPT
select SRCU
help
This option enables a task-based RCU implementation that uses
only voluntary context switch (not preemption!), idle, and
user-mode execution as quiescent states.
config RCU_STALL_COMMON
def_bool ( TREE_RCU || PREEMPT_RCU )
help
This option enables RCU CPU stall code that is common between
the TINY and TREE variants of RCU. The purpose is to allow
the tiny variants to disable RCU CPU stall warnings, while
making these warnings mandatory for the tree variants.
config RCU_NEED_SEGCBLIST
def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU )
config CONTEXT_TRACKING
bool
config CONTEXT_TRACKING_FORCE
bool "Force context tracking"
depends on CONTEXT_TRACKING
default y if !NO_HZ_FULL
help
The major pre-requirement for full dynticks to work is to
support the context tracking subsystem. But there are also
other dependencies to provide in order to make the full
dynticks working.
This option stands for testing when an arch implements the
context tracking backend but doesn't yet fullfill all the
requirements to make the full dynticks feature working.
Without the full dynticks, there is no way to test the support
for context tracking and the subsystems that rely on it: RCU
userspace extended quiescent state and tickless cputime
accounting. This option copes with the absence of the full
dynticks subsystem by forcing the context tracking on all
CPUs in the system.
Say Y only if you're working on the development of an
architecture backend for the context tracking.
Say N otherwise, this option brings an overhead that you
don't want in production.
config RCU_FANOUT
int "Tree-based hierarchical RCU fanout value"
range 2 64 if 64BIT
range 2 32 if !64BIT
depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
default 64 if 64BIT
default 32 if !64BIT
help
This option controls the fanout of hierarchical implementations
of RCU, allowing RCU to work efficiently on machines with
large numbers of CPUs. This value must be at least the fourth
root of NR_CPUS, which allows NR_CPUS to be insanely large.
The default value of RCU_FANOUT should be used for production
systems, but if you are stress-testing the RCU implementation
itself, small RCU_FANOUT values allow you to test large-system
code paths on small(er) systems.
Select a specific number if testing RCU itself.
Take the default if unsure.
config RCU_FANOUT_LEAF
int "Tree-based hierarchical RCU leaf-level fanout value"
range 2 64 if 64BIT
range 2 32 if !64BIT
depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
default 16
help
This option controls the leaf-level fanout of hierarchical
implementations of RCU, and allows trading off cache misses
against lock contention. Systems that synchronize their
scheduling-clock interrupts for energy-efficiency reasons will
want the default because the smaller leaf-level fanout keeps
lock contention levels acceptably low. Very large systems
(hundreds or thousands of CPUs) will instead want to set this
value to the maximum value possible in order to reduce the
number of cache misses incurred during RCU's grace-period
initialization. These systems tend to run CPU-bound, and thus
are not helped by synchronized interrupts, and thus tend to
skew them, which reduces lock contention enough that large
leaf-level fanouts work well. That said, setting leaf-level
fanout to a large number will likely cause problematic
lock contention on the leaf-level rcu_node structures unless
you boot with the skew_tick kernel parameter.
Select a specific number if testing RCU itself.
Select the maximum permissible value for large systems, but
please understand that you may also need to set the skew_tick
kernel boot parameter to avoid contention on the rcu_node
structure's locks.
Take the default if unsure.
config RCU_FAST_NO_HZ
bool "Accelerate last non-dyntick-idle CPU's grace periods"
depends on NO_HZ_COMMON && SMP && RCU_EXPERT
default n
help
This option permits CPUs to enter dynticks-idle state even if
they have RCU callbacks queued, and prevents RCU from waking
these CPUs up more than roughly once every four jiffies (by
default, you can adjust this using the rcutree.rcu_idle_gp_delay
parameter), thus improving energy efficiency. On the other
hand, this option increases the duration of RCU grace periods,
for example, slowing down synchronize_rcu().
Say Y if energy efficiency is critically important, and you
don't care about increased grace-period durations.
Say N if you are unsure.
config RCU_BOOST
bool "Enable RCU priority boosting"
depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
default n
help
This option boosts the priority of preempted RCU readers that
block the current preemptible RCU grace period for too long.
This option also prevents heavy loads from blocking RCU
callback invocation for all flavors of RCU.
Say Y here if you are working with real-time apps or heavy loads
Say N here if you are unsure.
config RCU_BOOST_DELAY
int "Milliseconds to delay boosting after RCU grace-period start"
range 0 3000
depends on RCU_BOOST
default 500
help
This option specifies the time to wait after the beginning of
a given grace period before priority-boosting preempted RCU
readers blocking that grace period. Note that any RCU reader
blocking an expedited RCU grace period is boosted immediately.
Accept the default if unsure.
config RCU_NOCB_CPU
bool "Offload RCU callback processing from boot-selected CPUs"
depends on TREE_RCU || PREEMPT_RCU
depends on RCU_EXPERT || NO_HZ_FULL
default n
help
Use this option to reduce OS jitter for aggressive HPC or
real-time workloads. It can also be used to offload RCU
callback invocation to energy-efficient CPUs in battery-powered
asymmetric multiprocessors.
This option offloads callback invocation from the set of
CPUs specified at boot time by the rcu_nocbs parameter.
For each such CPU, a kthread ("rcuox/N") will be created to
invoke callbacks, where the "N" is the CPU being offloaded,
and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
"s" for RCU-sched. Nothing prevents this kthread from running
on the specified CPUs, but (1) the kthreads may be preempted
between each callback, and (2) affinity or cgroups can be used
to force the kthreads to run on whatever set of CPUs is desired.
Say Y here if you want to help to debug reduced OS jitter.
Say N here if you are unsure.
endmenu # "RCU Subsystem"
+82
View File
@@ -0,0 +1,82 @@
#
# RCU-related debugging configuration options
#
menu "RCU Debugging"
config PROVE_RCU
def_bool PROVE_LOCKING
config TORTURE_TEST
tristate
default n
config RCU_PERF_TEST
tristate "performance tests for RCU"
depends on DEBUG_KERNEL
select TORTURE_TEST
select SRCU
select TASKS_RCU
default n
help
This option provides a kernel module that runs performance
tests on the RCU infrastructure. The kernel module may be built
after the fact on the running kernel to be tested, if desired.
Say Y here if you want RCU performance tests to be built into
the kernel.
Say M if you want the RCU performance tests to build as a module.
Say N if you are unsure.
config RCU_TORTURE_TEST
tristate "torture tests for RCU"
depends on DEBUG_KERNEL
select TORTURE_TEST
select SRCU
select TASKS_RCU
default n
help
This option provides a kernel module that runs torture tests
on the RCU infrastructure. The kernel module may be built
after the fact on the running kernel to be tested, if desired.
Say Y here if you want RCU torture tests to be built into
the kernel.
Say M if you want the RCU torture tests to build as a module.
Say N if you are unsure.
config RCU_CPU_STALL_TIMEOUT
int "RCU CPU stall timeout in seconds"
depends on RCU_STALL_COMMON
range 3 300
default 21
help
If a given RCU grace period extends more than the specified
number of seconds, a CPU stall warning is printed. If the
RCU grace period persists, additional CPU stall warnings are
printed at more widely spaced intervals.
config RCU_TRACE
bool "Enable tracing for RCU"
depends on DEBUG_KERNEL
default y if TREE_RCU
select TRACE_CLOCK
help
This option enables additional tracepoints for ftrace-style
event tracing.
Say Y here if you want to enable RCU tracing
Say N if you are unsure.
config RCU_EQS_DEBUG
bool "Provide debugging asserts for adding NO_HZ support to an arch"
depends on DEBUG_KERNEL
help
This option provides consistency checks in RCU's handling of
NO_HZ. These checks have proven quite helpful in detecting
bugs in arch-specific NO_HZ code.
Say N here if you need ultimate kernel/user switch latencies
Say Y if you are unsure
endmenu # "RCU Debugging"
+14
View File
@@ -0,0 +1,14 @@
# SPDX-License-Identifier: GPL-2.0
# Any varying coverage in these files is non-deterministic
# and is generally not a function of system call inputs.
KCOV_INSTRUMENT := n
obj-y += update.o sync.o
obj-$(CONFIG_TREE_SRCU) += srcutree.o
obj-$(CONFIG_TINY_SRCU) += srcutiny.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
obj-$(CONFIG_TREE_RCU) += tree.o
obj-$(CONFIG_PREEMPT_RCU) += tree.o
obj-$(CONFIG_TINY_RCU) += tiny.o
obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o
+559
View File
@@ -0,0 +1,559 @@
/*
* Read-Copy Update definitions shared among RCU implementations.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2011
*
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#ifndef __LINUX_RCU_H
#define __LINUX_RCU_H
#include <linux/interrupt.h>
#include <trace/events/rcu.h>
#ifdef CONFIG_RCU_TRACE
#define RCU_TRACE(stmt) stmt
#else /* #ifdef CONFIG_RCU_TRACE */
#define RCU_TRACE(stmt)
#endif /* #else #ifdef CONFIG_RCU_TRACE */
/* Offset to allow for unmatched rcu_irq_{enter,exit}(). */
#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1)
/*
* Grace-period counter management.
*/
#define RCU_SEQ_CTR_SHIFT 2
#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1)
/*
* Return the counter portion of a sequence number previously returned
* by rcu_seq_snap() or rcu_seq_current().
*/
static inline unsigned long rcu_seq_ctr(unsigned long s)
{
return s >> RCU_SEQ_CTR_SHIFT;
}
/*
* Return the state portion of a sequence number previously returned
* by rcu_seq_snap() or rcu_seq_current().
*/
static inline int rcu_seq_state(unsigned long s)
{
return s & RCU_SEQ_STATE_MASK;
}
/*
* Set the state portion of the pointed-to sequence number.
* The caller is responsible for preventing conflicting updates.
*/
static inline void rcu_seq_set_state(unsigned long *sp, int newstate)
{
WARN_ON_ONCE(newstate & ~RCU_SEQ_STATE_MASK);
WRITE_ONCE(*sp, (*sp & ~RCU_SEQ_STATE_MASK) + newstate);
}
/* Adjust sequence number for start of update-side operation. */
static inline void rcu_seq_start(unsigned long *sp)
{
WRITE_ONCE(*sp, *sp + 1);
smp_mb(); /* Ensure update-side operation after counter increment. */
WARN_ON_ONCE(rcu_seq_state(*sp) != 1);
}
/* Compute the end-of-grace-period value for the specified sequence number. */
static inline unsigned long rcu_seq_endval(unsigned long *sp)
{
return (*sp | RCU_SEQ_STATE_MASK) + 1;
}
/* Adjust sequence number for end of update-side operation. */
static inline void rcu_seq_end(unsigned long *sp)
{
smp_mb(); /* Ensure update-side operation before counter increment. */
WARN_ON_ONCE(!rcu_seq_state(*sp));
WRITE_ONCE(*sp, rcu_seq_endval(sp));
}
/*
* rcu_seq_snap - Take a snapshot of the update side's sequence number.
*
* This function returns the earliest value of the grace-period sequence number
* that will indicate that a full grace period has elapsed since the current
* time. Once the grace-period sequence number has reached this value, it will
* be safe to invoke all callbacks that have been registered prior to the
* current time. This value is the current grace-period number plus two to the
* power of the number of low-order bits reserved for state, then rounded up to
* the next value in which the state bits are all zero.
*/
static inline unsigned long rcu_seq_snap(unsigned long *sp)
{
unsigned long s;
s = (READ_ONCE(*sp) + 2 * RCU_SEQ_STATE_MASK + 1) & ~RCU_SEQ_STATE_MASK;
smp_mb(); /* Above access must not bleed into critical section. */
return s;
}
/* Return the current value the update side's sequence number, no ordering. */
static inline unsigned long rcu_seq_current(unsigned long *sp)
{
return READ_ONCE(*sp);
}
/*
* Given a snapshot from rcu_seq_snap(), determine whether or not the
* corresponding update-side operation has started.
*/
static inline bool rcu_seq_started(unsigned long *sp, unsigned long s)
{
return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp));
}
/*
* Given a snapshot from rcu_seq_snap(), determine whether or not a
* full update-side operation has occurred.
*/
static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
{
return ULONG_CMP_GE(READ_ONCE(*sp), s);
}
/*
* Has a grace period completed since the time the old gp_seq was collected?
*/
static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
{
return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK);
}
/*
* Has a grace period started since the time the old gp_seq was collected?
*/
static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
{
return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK,
new);
}
/*
* Roughly how many full grace periods have elapsed between the collection
* of the two specified grace periods?
*/
static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
{
unsigned long rnd_diff;
if (old == new)
return 0;
/*
* Compute the number of grace periods (still shifted up), plus
* one if either of new and old is not an exact grace period.
*/
rnd_diff = (new & ~RCU_SEQ_STATE_MASK) -
((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) +
((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK));
if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff))
return 1; /* Definitely no grace period has elapsed. */
return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2;
}
/*
* debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
* by call_rcu() and rcu callback execution, and are therefore not part of the
* RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
*/
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
# define STATE_RCU_HEAD_READY 0
# define STATE_RCU_HEAD_QUEUED 1
extern struct debug_obj_descr rcuhead_debug_descr;
static inline int debug_rcu_head_queue(struct rcu_head *head)
{
int r1;
r1 = debug_object_activate(head, &rcuhead_debug_descr);
debug_object_active_state(head, &rcuhead_debug_descr,
STATE_RCU_HEAD_READY,
STATE_RCU_HEAD_QUEUED);
return r1;
}
static inline void debug_rcu_head_unqueue(struct rcu_head *head)
{
debug_object_active_state(head, &rcuhead_debug_descr,
STATE_RCU_HEAD_QUEUED,
STATE_RCU_HEAD_READY);
debug_object_deactivate(head, &rcuhead_debug_descr);
}
#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
static inline int debug_rcu_head_queue(struct rcu_head *head)
{
return 0;
}
static inline void debug_rcu_head_unqueue(struct rcu_head *head)
{
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
void kfree(const void *);
/*
* Reclaim the specified callback, either by invoking it (non-lazy case)
* or freeing it directly (lazy case). Return true if lazy, false otherwise.
*/
static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
{
unsigned long offset = (unsigned long)head->func;
unsigned long long ts = 0;
rcu_lock_acquire(&rcu_callback_map);
if (__is_kfree_rcu_offset(offset)) {
RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset);)
check_start_time(ts);
kfree((void *)head - offset);
check_process_time("rcu_reclaim free memory", ts);
rcu_lock_release(&rcu_callback_map);
return true;
} else {
rcu_callback_t f = head->func;
RCU_TRACE(trace_rcu_invoke_callback(rn, head);)
check_start_time(ts);
f(head);
check_process_time("rcu_reclaim %ps", ts, f);
rcu_lock_release(&rcu_callback_map);
return false;
}
}
#ifdef CONFIG_RCU_STALL_COMMON
extern int rcu_cpu_stall_suppress;
int rcu_jiffies_till_stall_check(void);
#define rcu_ftrace_dump_stall_suppress() \
do { \
if (!rcu_cpu_stall_suppress) \
rcu_cpu_stall_suppress = 3; \
} while (0)
#define rcu_ftrace_dump_stall_unsuppress() \
do { \
if (rcu_cpu_stall_suppress == 3) \
rcu_cpu_stall_suppress = 0; \
} while (0)
#else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */
#define rcu_ftrace_dump_stall_suppress()
#define rcu_ftrace_dump_stall_unsuppress()
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
/*
* Strings used in tracepoints need to be exported via the
* tracing system such that tools like perf and trace-cmd can
* translate the string address pointers to actual text.
*/
#define TPS(x) tracepoint_string(x)
/*
* Dump the ftrace buffer, but only one time per callsite per boot.
*/
#define rcu_ftrace_dump(oops_dump_mode) \
do { \
static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \
\
if (!atomic_read(&___rfd_beenhere) && \
!atomic_xchg(&___rfd_beenhere, 1)) { \
tracing_off(); \
rcu_ftrace_dump_stall_suppress(); \
ftrace_dump(oops_dump_mode); \
rcu_ftrace_dump_stall_unsuppress(); \
} \
} while (0)
void rcu_early_boot_tests(void);
void rcu_test_sync_prims(void);
/*
* This function really isn't for public consumption, but RCU is special in
* that context switches can allow the state machine to make progress.
*/
extern void resched_cpu(int cpu);
#if defined(SRCU) || !defined(TINY_RCU)
#include <linux/rcu_node_tree.h>
extern int rcu_num_lvls;
extern int num_rcu_lvl[];
extern int rcu_num_nodes;
static bool rcu_fanout_exact;
static int rcu_fanout_leaf;
/*
* Compute the per-level fanout, either using the exact fanout specified
* or balancing the tree, depending on the rcu_fanout_exact boot parameter.
*/
static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
{
int i;
if (rcu_fanout_exact) {
levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
for (i = rcu_num_lvls - 2; i >= 0; i--)
levelspread[i] = RCU_FANOUT;
} else {
int ccur;
int cprv;
cprv = nr_cpu_ids;
for (i = rcu_num_lvls - 1; i >= 0; i--) {
ccur = levelcnt[i];
levelspread[i] = (cprv + ccur - 1) / ccur;
cprv = ccur;
}
}
}
/* Returns first leaf rcu_node of the specified RCU flavor. */
#define rcu_first_leaf_node(rsp) ((rsp)->level[rcu_num_lvls - 1])
/* Is this rcu_node a leaf? */
#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
/* Is this rcu_node the last leaf? */
#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
*/
#define rcu_for_each_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
* Do a breadth-first scan of the non-leaf rcu_node structures for the
* specified rcu_state structure. Note that if there is a singleton
* rcu_node tree with but one rcu_node structure, this loop is a no-op.
*/
#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; !rcu_is_leaf_node(rsp, rnp); (rnp)++)
/*
* Scan the leaves of the rcu_node hierarchy for the specified rcu_state
* structure. Note that if there is a singleton rcu_node tree with but
* one rcu_node structure, this loop -will- visit the rcu_node structure.
* It is still a leaf node, even if it is also the root node.
*/
#define rcu_for_each_leaf_node(rsp, rnp) \
for ((rnp) = rcu_first_leaf_node(rsp); \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
* Iterate over all possible CPUs in a leaf RCU node.
*/
#define for_each_leaf_node_possible_cpu(rnp, cpu) \
for ((cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
(cpu) <= rnp->grphi; \
(cpu) = cpumask_next((cpu), cpu_possible_mask))
/*
* Iterate over all CPUs in a leaf RCU node's specified mask.
*/
#define rcu_find_next_bit(rnp, cpu, mask) \
((rnp)->grplo + find_next_bit(&(mask), BITS_PER_LONG, (cpu)))
#define for_each_leaf_node_cpu_mask(rnp, cpu, mask) \
for ((cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
(cpu) <= rnp->grphi; \
(cpu) = rcu_find_next_bit((rnp), (cpu) + 1 - (rnp->grplo), (mask)))
/*
* Wrappers for the rcu_node::lock acquire and release.
*
* Because the rcu_nodes form a tree, the tree traversal locking will observe
* different lock values, this in turn means that an UNLOCK of one level
* followed by a LOCK of another level does not imply a full memory barrier;
* and most importantly transitivity is lost.
*
* In order to restore full ordering between tree levels, augment the regular
* lock acquire functions with smp_mb__after_unlock_lock().
*
* As ->lock of struct rcu_node is a __private field, therefore one should use
* these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock.
*/
#define raw_spin_lock_rcu_node(p) \
do { \
raw_spin_lock(&ACCESS_PRIVATE(p, lock)); \
smp_mb__after_unlock_lock(); \
} while (0)
#define raw_spin_unlock_rcu_node(p) raw_spin_unlock(&ACCESS_PRIVATE(p, lock))
#define raw_spin_lock_irq_rcu_node(p) \
do { \
raw_spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \
smp_mb__after_unlock_lock(); \
} while (0)
#define raw_spin_unlock_irq_rcu_node(p) \
raw_spin_unlock_irq(&ACCESS_PRIVATE(p, lock))
#define raw_spin_lock_irqsave_rcu_node(p, flags) \
do { \
raw_spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \
smp_mb__after_unlock_lock(); \
} while (0)
#define raw_spin_unlock_irqrestore_rcu_node(p, flags) \
raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)
#define raw_spin_trylock_rcu_node(p) \
({ \
bool ___locked = raw_spin_trylock(&ACCESS_PRIVATE(p, lock)); \
\
if (___locked) \
smp_mb__after_unlock_lock(); \
___locked; \
})
#define raw_lockdep_assert_held_rcu_node(p) \
lockdep_assert_held(&ACCESS_PRIVATE(p, lock))
#endif /* #if defined(SRCU) || !defined(TINY_RCU) */
#ifdef CONFIG_TINY_RCU
/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */
static inline bool rcu_gp_is_normal(void) { return true; }
static inline bool rcu_gp_is_expedited(void) { return false; }
static inline void rcu_expedite_gp(void) { }
static inline void rcu_unexpedite_gp(void) { }
static inline void rcu_request_urgent_qs_task(struct task_struct *t) { }
#else /* #ifdef CONFIG_TINY_RCU */
bool rcu_gp_is_normal(void); /* Internal RCU use. */
bool rcu_gp_is_expedited(void); /* Internal RCU use. */
void rcu_expedite_gp(void);
void rcu_unexpedite_gp(void);
void rcupdate_announce_bootup_oddness(void);
void rcu_request_urgent_qs_task(struct task_struct *t);
#endif /* #else #ifdef CONFIG_TINY_RCU */
#define RCU_SCHEDULER_INACTIVE 0
#define RCU_SCHEDULER_INIT 1
#define RCU_SCHEDULER_RUNNING 2
enum rcutorture_type {
RCU_FLAVOR,
RCU_BH_FLAVOR,
RCU_SCHED_FLAVOR,
RCU_TASKS_FLAVOR,
SRCU_FLAVOR,
INVALID_RCU_FLAVOR
};
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
unsigned long *gp_seq);
void rcutorture_record_progress(unsigned long vernum);
void do_trace_rcu_torture_read(const char *rcutorturename,
struct rcu_head *rhp,
unsigned long secs,
unsigned long c_old,
unsigned long c);
#else
static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
int *flags, unsigned long *gp_seq)
{
*flags = 0;
*gp_seq = 0;
}
static inline void rcutorture_record_progress(unsigned long vernum) { }
#ifdef CONFIG_RCU_TRACE
void do_trace_rcu_torture_read(const char *rcutorturename,
struct rcu_head *rhp,
unsigned long secs,
unsigned long c_old,
unsigned long c);
#else
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
do { } while (0)
#endif
#endif
#ifdef CONFIG_TINY_SRCU
static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
unsigned long *gp_seq)
{
if (test_type != SRCU_FLAVOR)
return;
*flags = 0;
*gp_seq = sp->srcu_idx;
}
#elif defined(CONFIG_TREE_SRCU)
void srcutorture_get_gp_data(enum rcutorture_type test_type,
struct srcu_struct *sp, int *flags,
unsigned long *gp_seq);
#endif
#ifdef CONFIG_TINY_RCU
static inline unsigned long rcu_get_gp_seq(void) { return 0; }
static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; }
static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; }
static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
static inline unsigned long
srcu_batches_completed(struct srcu_struct *sp) { return 0; }
static inline void rcu_force_quiescent_state(void) { }
static inline void rcu_bh_force_quiescent_state(void) { }
static inline void rcu_sched_force_quiescent_state(void) { }
static inline void show_rcu_gp_kthreads(void) { }
static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
#else /* #ifdef CONFIG_TINY_RCU */
unsigned long rcu_get_gp_seq(void);
unsigned long rcu_bh_get_gp_seq(void);
unsigned long rcu_sched_get_gp_seq(void);
unsigned long rcu_exp_batches_completed(void);
unsigned long rcu_exp_batches_completed_sched(void);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
void show_rcu_gp_kthreads(void);
int rcu_get_gp_kthreads_prio(void);
void rcu_force_quiescent_state(void);
void rcu_bh_force_quiescent_state(void);
void rcu_sched_force_quiescent_state(void);
extern struct workqueue_struct *rcu_gp_wq;
extern struct workqueue_struct *rcu_par_gp_wq;
#endif /* #else #ifdef CONFIG_TINY_RCU */
#ifdef CONFIG_RCU_NOCB_CPU
bool rcu_is_nocb_cpu(int cpu);
#else
static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
#endif
#endif /* __LINUX_RCU_H */
+428
View File
@@ -0,0 +1,428 @@
/*
* RCU segmented callback lists, function definitions
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2017
*
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/rcupdate.h>
#include "rcu_segcblist.h"
/* Initialize simple callback list. */
void rcu_cblist_init(struct rcu_cblist *rclp)
{
rclp->head = NULL;
rclp->tail = &rclp->head;
rclp->len = 0;
rclp->len_lazy = 0;
}
/*
* Dequeue the oldest rcu_head structure from the specified callback
* list. This function assumes that the callback is non-lazy, but
* the caller can later invoke rcu_cblist_dequeued_lazy() if it
* finds otherwise (and if it cares about laziness). This allows
* different users to have different ways of determining laziness.
*/
struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
{
struct rcu_head *rhp;
rhp = rclp->head;
if (!rhp)
return NULL;
rclp->len--;
rclp->head = rhp->next;
if (!rclp->head)
rclp->tail = &rclp->head;
return rhp;
}
/*
* Initialize an rcu_segcblist structure.
*/
void rcu_segcblist_init(struct rcu_segcblist *rsclp)
{
int i;
BUILD_BUG_ON(RCU_NEXT_TAIL + 1 != ARRAY_SIZE(rsclp->gp_seq));
BUILD_BUG_ON(ARRAY_SIZE(rsclp->tails) != ARRAY_SIZE(rsclp->gp_seq));
rsclp->head = NULL;
for (i = 0; i < RCU_CBLIST_NSEGS; i++)
rsclp->tails[i] = &rsclp->head;
rsclp->len = 0;
rsclp->len_lazy = 0;
}
/*
* Disable the specified rcu_segcblist structure, so that callbacks can
* no longer be posted to it. This structure must be empty.
*/
void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
{
WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
rsclp->tails[RCU_NEXT_TAIL] = NULL;
}
/*
* Does the specified rcu_segcblist structure contain callbacks that
* are ready to be invoked?
*/
bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
{
return rcu_segcblist_is_enabled(rsclp) &&
&rsclp->head != rsclp->tails[RCU_DONE_TAIL];
}
/*
* Does the specified rcu_segcblist structure contain callbacks that
* are still pending, that is, not yet ready to be invoked?
*/
bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp)
{
return rcu_segcblist_is_enabled(rsclp) &&
!rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL);
}
/*
* Return a pointer to the first callback in the specified rcu_segcblist
* structure. This is useful for diagnostics.
*/
struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp)
{
if (rcu_segcblist_is_enabled(rsclp))
return rsclp->head;
return NULL;
}
/*
* Return a pointer to the first pending callback in the specified
* rcu_segcblist structure. This is useful just after posting a given
* callback -- if that callback is the first pending callback, then
* you cannot rely on someone else having already started up the required
* grace period.
*/
struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp)
{
if (rcu_segcblist_is_enabled(rsclp))
return *rsclp->tails[RCU_DONE_TAIL];
return NULL;
}
/*
* Enqueue the specified callback onto the specified rcu_segcblist
* structure, updating accounting as needed. Note that the ->len
* field may be accessed locklessly, hence the WRITE_ONCE().
* The ->len field is used by rcu_barrier() and friends to determine
* if it must post a callback on this structure, and it is OK
* for rcu_barrier() to sometimes post callbacks needlessly, but
* absolutely not OK for it to ever miss posting a callback.
*/
void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
struct rcu_head *rhp, bool lazy)
{
WRITE_ONCE(rsclp->len, rsclp->len + 1); /* ->len sampled locklessly. */
if (lazy)
rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is enqueued. */
rhp->next = NULL;
*rsclp->tails[RCU_NEXT_TAIL] = rhp;
rsclp->tails[RCU_NEXT_TAIL] = &rhp->next;
}
/*
* Entrain the specified callback onto the specified rcu_segcblist at
* the end of the last non-empty segment. If the entire rcu_segcblist
* is empty, make no change, but return false.
*
* This is intended for use by rcu_barrier()-like primitives, -not-
* for normal grace-period use. IMPORTANT: The callback you enqueue
* will wait for all prior callbacks, NOT necessarily for a grace
* period. You have been warned.
*/
bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
struct rcu_head *rhp, bool lazy)
{
int i;
if (rcu_segcblist_n_cbs(rsclp) == 0)
return false;
WRITE_ONCE(rsclp->len, rsclp->len + 1);
if (lazy)
rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is entrained. */
rhp->next = NULL;
for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
if (rsclp->tails[i] != rsclp->tails[i - 1])
break;
*rsclp->tails[i] = rhp;
for (; i <= RCU_NEXT_TAIL; i++)
rsclp->tails[i] = &rhp->next;
return true;
}
/*
* Extract only the counts from the specified rcu_segcblist structure,
* and place them in the specified rcu_cblist structure. This function
* supports both callback orphaning and invocation, hence the separation
* of counts and callbacks. (Callbacks ready for invocation must be
* orphaned and adopted separately from pending callbacks, but counts
* apply to all callbacks. Locking must be used to make sure that
* both orphaned-callbacks lists are consistent.)
*/
void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
rclp->len_lazy += rsclp->len_lazy;
rclp->len += rsclp->len;
rsclp->len_lazy = 0;
WRITE_ONCE(rsclp->len, 0); /* ->len sampled locklessly. */
}
/*
* Extract only those callbacks ready to be invoked from the specified
* rcu_segcblist structure and place them in the specified rcu_cblist
* structure.
*/
void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
int i;
if (!rcu_segcblist_ready_cbs(rsclp))
return; /* Nothing to do. */
*rclp->tail = rsclp->head;
rsclp->head = *rsclp->tails[RCU_DONE_TAIL];
*rsclp->tails[RCU_DONE_TAIL] = NULL;
rclp->tail = rsclp->tails[RCU_DONE_TAIL];
for (i = RCU_CBLIST_NSEGS - 1; i >= RCU_DONE_TAIL; i--)
if (rsclp->tails[i] == rsclp->tails[RCU_DONE_TAIL])
rsclp->tails[i] = &rsclp->head;
}
/*
* Extract only those callbacks still pending (not yet ready to be
* invoked) from the specified rcu_segcblist structure and place them in
* the specified rcu_cblist structure. Note that this loses information
* about any callbacks that might have been partway done waiting for
* their grace period. Too bad! They will have to start over.
*/
void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
int i;
if (!rcu_segcblist_pend_cbs(rsclp))
return; /* Nothing to do. */
*rclp->tail = *rsclp->tails[RCU_DONE_TAIL];
rclp->tail = rsclp->tails[RCU_NEXT_TAIL];
*rsclp->tails[RCU_DONE_TAIL] = NULL;
for (i = RCU_DONE_TAIL + 1; i < RCU_CBLIST_NSEGS; i++)
rsclp->tails[i] = rsclp->tails[RCU_DONE_TAIL];
}
/*
* Insert counts from the specified rcu_cblist structure in the
* specified rcu_segcblist structure.
*/
void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
rsclp->len_lazy += rclp->len_lazy;
/* ->len sampled locklessly. */
WRITE_ONCE(rsclp->len, rsclp->len + rclp->len);
rclp->len_lazy = 0;
rclp->len = 0;
}
/*
* Move callbacks from the specified rcu_cblist to the beginning of the
* done-callbacks segment of the specified rcu_segcblist.
*/
void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
int i;
if (!rclp->head)
return; /* No callbacks to move. */
*rclp->tail = rsclp->head;
rsclp->head = rclp->head;
for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++)
if (&rsclp->head == rsclp->tails[i])
rsclp->tails[i] = rclp->tail;
else
break;
rclp->head = NULL;
rclp->tail = &rclp->head;
}
/*
* Move callbacks from the specified rcu_cblist to the end of the
* new-callbacks segment of the specified rcu_segcblist.
*/
void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
if (!rclp->head)
return; /* Nothing to do. */
*rsclp->tails[RCU_NEXT_TAIL] = rclp->head;
rsclp->tails[RCU_NEXT_TAIL] = rclp->tail;
rclp->head = NULL;
rclp->tail = &rclp->head;
}
/*
* Advance the callbacks in the specified rcu_segcblist structure based
* on the current value passed in for the grace-period counter.
*/
void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq)
{
int i, j;
WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
return;
/*
* Find all callbacks whose ->gp_seq numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL segment.
*/
for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
if (ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
break;
rsclp->tails[RCU_DONE_TAIL] = rsclp->tails[i];
}
/* If no callbacks moved, nothing more need be done. */
if (i == RCU_WAIT_TAIL)
return;
/* Clean up tail pointers that might have been misordered above. */
for (j = RCU_WAIT_TAIL; j < i; j++)
rsclp->tails[j] = rsclp->tails[RCU_DONE_TAIL];
/*
* Callbacks moved, so clean up the misordered ->tails[] pointers
* that now point into the middle of the list of ready-to-invoke
* callbacks. The overall effect is to copy down the later pointers
* into the gap that was created by the now-ready segments.
*/
for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL])
break; /* No more callbacks. */
rsclp->tails[j] = rsclp->tails[i];
rsclp->gp_seq[j] = rsclp->gp_seq[i];
}
}
/*
* "Accelerate" callbacks based on more-accurate grace-period information.
* The reason for this is that RCU does not synchronize the beginnings and
* ends of grace periods, and that callbacks are posted locally. This in
* turn means that the callbacks must be labelled conservatively early
* on, as getting exact information would degrade both performance and
* scalability. When more accurate grace-period information becomes
* available, previously posted callbacks can be "accelerated", marking
* them to complete at the end of the earlier grace period.
*
* This function operates on an rcu_segcblist structure, and also the
* grace-period sequence number seq at which new callbacks would become
* ready to invoke. Returns true if there are callbacks that won't be
* ready to invoke until seq, false otherwise.
*/
bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
{
int i;
WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
return false;
/*
* Find the segment preceding the oldest segment of callbacks
* whose ->gp_seq[] completion is at or after that passed in via
* "seq", skipping any empty segments. This oldest segment, along
* with any later segments, can be merged in with any newly arrived
* callbacks in the RCU_NEXT_TAIL segment, and assigned "seq"
* as their ->gp_seq[] grace-period completion sequence number.
*/
for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--)
if (rsclp->tails[i] != rsclp->tails[i - 1] &&
ULONG_CMP_LT(rsclp->gp_seq[i], seq))
break;
/*
* If all the segments contain callbacks that correspond to
* earlier grace-period sequence numbers than "seq", leave.
* Assuming that the rcu_segcblist structure has enough
* segments in its arrays, this can only happen if some of
* the non-done segments contain callbacks that really are
* ready to invoke. This situation will get straightened
* out by the next call to rcu_segcblist_advance().
*
* Also advance to the oldest segment of callbacks whose
* ->gp_seq[] completion is at or after that passed in via "seq",
* skipping any empty segments.
*/
if (++i >= RCU_NEXT_TAIL)
return false;
/*
* Merge all later callbacks, including newly arrived callbacks,
* into the segment located by the for-loop above. Assign "seq"
* as the ->gp_seq[] value in order to correctly handle the case
* where there were no pending callbacks in the rcu_segcblist
* structure other than in the RCU_NEXT_TAIL segment.
*/
for (; i < RCU_NEXT_TAIL; i++) {
rsclp->tails[i] = rsclp->tails[RCU_NEXT_TAIL];
rsclp->gp_seq[i] = seq;
}
return true;
}
/*
* Merge the source rcu_segcblist structure into the destination
* rcu_segcblist structure, then initialize the source. Any pending
* callbacks from the source get to start over. It is best to
* advance and accelerate both the destination and the source
* before merging.
*/
void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
struct rcu_segcblist *src_rsclp)
{
struct rcu_cblist donecbs;
struct rcu_cblist pendcbs;
rcu_cblist_init(&donecbs);
rcu_cblist_init(&pendcbs);
rcu_segcblist_extract_count(src_rsclp, &donecbs);
rcu_segcblist_extract_done_cbs(src_rsclp, &donecbs);
rcu_segcblist_extract_pend_cbs(src_rsclp, &pendcbs);
rcu_segcblist_insert_count(dst_rsclp, &donecbs);
rcu_segcblist_insert_done_cbs(dst_rsclp, &donecbs);
rcu_segcblist_insert_pend_cbs(dst_rsclp, &pendcbs);
rcu_segcblist_init(src_rsclp);
}
+138
View File
@@ -0,0 +1,138 @@
/*
* RCU segmented callback lists, internal-to-rcu header file
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2017
*
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#include <linux/rcu_segcblist.h>
/*
* Account for the fact that a previously dequeued callback turned out
* to be marked as lazy.
*/
static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
{
rclp->len_lazy--;
}
void rcu_cblist_init(struct rcu_cblist *rclp);
struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp);
/*
* Is the specified rcu_segcblist structure empty?
*
* But careful! The fact that the ->head field is NULL does not
* necessarily imply that there are no callbacks associated with
* this structure. When callbacks are being invoked, they are
* removed as a group. If callback invocation must be preempted,
* the remaining callbacks will be added back to the list. Either
* way, the counts are updated later.
*
* So it is often the case that rcu_segcblist_n_cbs() should be used
* instead.
*/
static inline bool rcu_segcblist_empty(struct rcu_segcblist *rsclp)
{
return !rsclp->head;
}
/* Return number of callbacks in segmented callback list. */
static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
{
return READ_ONCE(rsclp->len);
}
/* Return number of lazy callbacks in segmented callback list. */
static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
{
return rsclp->len_lazy;
}
/* Return number of lazy callbacks in segmented callback list. */
static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
{
return rsclp->len - rsclp->len_lazy;
}
/*
* Is the specified rcu_segcblist enabled, for example, not corresponding
* to an offline or callback-offloaded CPU?
*/
static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
{
return !!rsclp->tails[RCU_NEXT_TAIL];
}
/*
* Are all segments following the specified segment of the specified
* rcu_segcblist structure empty of callbacks? (The specified
* segment might well contain callbacks.)
*/
static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
{
return !*rsclp->tails[seg];
}
/*
* Interim function to return rcu_segcblist head pointer. Longer term, the
* rcu_segcblist will be used more pervasively, removing the need for this
* function.
*/
static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp)
{
return rsclp->head;
}
/*
* Interim function to return rcu_segcblist head pointer. Longer term, the
* rcu_segcblist will be used more pervasively, removing the need for this
* function.
*/
static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
{
WARN_ON_ONCE(rcu_segcblist_empty(rsclp));
return rsclp->tails[RCU_NEXT_TAIL];
}
void rcu_segcblist_init(struct rcu_segcblist *rsclp);
void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
struct rcu_head *rhp, bool lazy);
bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
struct rcu_head *rhp, bool lazy);
void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
struct rcu_segcblist *src_rsclp);
+761
View File
@@ -0,0 +1,761 @@
/*
* Read-Copy Update module-based performance-test facility
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2015
*
* Authors: Paul E. McKenney <paulmck@us.ibm.com>
*/
#define pr_fmt(fmt) fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <uapi/linux/sched/types.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/freezer.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/stat.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <asm/byteorder.h>
#include <linux/torture.h>
#include <linux/vmalloc.h>
#include "rcu.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
#define PERF_FLAG "-perf:"
#define PERFOUT_STRING(s) \
pr_alert("%s" PERF_FLAG " %s\n", perf_type, s)
#define VERBOSE_PERFOUT_STRING(s) \
do { if (verbose) pr_alert("%s" PERF_FLAG " %s\n", perf_type, s); } while (0)
#define VERBOSE_PERFOUT_ERRSTRING(s) \
do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0)
/*
* The intended use cases for the nreaders and nwriters module parameters
* are as follows:
*
* 1. Specify only the nr_cpus kernel boot parameter. This will
* set both nreaders and nwriters to the value specified by
* nr_cpus for a mixed reader/writer test.
*
* 2. Specify the nr_cpus kernel boot parameter, but set
* rcuperf.nreaders to zero. This will set nwriters to the
* value specified by nr_cpus for an update-only test.
*
* 3. Specify the nr_cpus kernel boot parameter, but set
* rcuperf.nwriters to zero. This will set nreaders to the
* value specified by nr_cpus for a read-only test.
*
* Various other use cases may of course be specified.
*/
torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
torture_param(int, nreaders, -1, "Number of RCU reader threads");
torture_param(int, nwriters, -1, "Number of RCU updater threads");
torture_param(bool, shutdown, !IS_ENABLED(MODULE),
"Shutdown at end of performance tests.");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
static char *perf_type = "rcu";
module_param(perf_type, charp, 0444);
MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)");
static int nrealreaders;
static int nrealwriters;
static struct task_struct **writer_tasks;
static struct task_struct **reader_tasks;
static struct task_struct *shutdown_task;
static u64 **writer_durations;
static int *writer_n_durations;
static atomic_t n_rcu_perf_reader_started;
static atomic_t n_rcu_perf_writer_started;
static atomic_t n_rcu_perf_writer_finished;
static wait_queue_head_t shutdown_wq;
static u64 t_rcu_perf_writer_started;
static u64 t_rcu_perf_writer_finished;
static unsigned long b_rcu_perf_writer_started;
static unsigned long b_rcu_perf_writer_finished;
static DEFINE_PER_CPU(atomic_t, n_async_inflight);
static int rcu_perf_writer_state;
#define RTWS_INIT 0
#define RTWS_ASYNC 1
#define RTWS_BARRIER 2
#define RTWS_EXP_SYNC 3
#define RTWS_SYNC 4
#define RTWS_IDLE 5
#define RTWS_STOPPING 6
#define MAX_MEAS 10000
#define MIN_MEAS 100
/*
* Operations vector for selecting different types of tests.
*/
struct rcu_perf_ops {
int ptype;
void (*init)(void);
void (*cleanup)(void);
int (*readlock)(void);
void (*readunlock)(int idx);
unsigned long (*get_gp_seq)(void);
unsigned long (*gp_diff)(unsigned long new, unsigned long old);
unsigned long (*exp_completed)(void);
void (*async)(struct rcu_head *head, rcu_callback_t func);
void (*gp_barrier)(void);
void (*sync)(void);
void (*exp_sync)(void);
const char *name;
};
static struct rcu_perf_ops *cur_ops;
/*
* Definitions for rcu perf testing.
*/
static int rcu_perf_read_lock(void) __acquires(RCU)
{
rcu_read_lock();
return 0;
}
static void rcu_perf_read_unlock(int idx) __releases(RCU)
{
rcu_read_unlock();
}
static unsigned long __maybe_unused rcu_no_completed(void)
{
return 0;
}
static void rcu_sync_perf_init(void)
{
}
static struct rcu_perf_ops rcu_ops = {
.ptype = RCU_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = rcu_perf_read_lock,
.readunlock = rcu_perf_read_unlock,
.get_gp_seq = rcu_get_gp_seq,
.gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed,
.async = call_rcu,
.gp_barrier = rcu_barrier,
.sync = synchronize_rcu,
.exp_sync = synchronize_rcu_expedited,
.name = "rcu"
};
/*
* Definitions for rcu_bh perf testing.
*/
static int rcu_bh_perf_read_lock(void) __acquires(RCU_BH)
{
rcu_read_lock_bh();
return 0;
}
static void rcu_bh_perf_read_unlock(int idx) __releases(RCU_BH)
{
rcu_read_unlock_bh();
}
static struct rcu_perf_ops rcu_bh_ops = {
.ptype = RCU_BH_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = rcu_bh_perf_read_lock,
.readunlock = rcu_bh_perf_read_unlock,
.get_gp_seq = rcu_bh_get_gp_seq,
.gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_bh,
.gp_barrier = rcu_barrier_bh,
.sync = synchronize_rcu_bh,
.exp_sync = synchronize_rcu_bh_expedited,
.name = "rcu_bh"
};
/*
* Definitions for srcu perf testing.
*/
DEFINE_STATIC_SRCU(srcu_ctl_perf);
static struct srcu_struct *srcu_ctlp = &srcu_ctl_perf;
static int srcu_perf_read_lock(void) __acquires(srcu_ctlp)
{
return srcu_read_lock(srcu_ctlp);
}
static void srcu_perf_read_unlock(int idx) __releases(srcu_ctlp)
{
srcu_read_unlock(srcu_ctlp, idx);
}
static unsigned long srcu_perf_completed(void)
{
return srcu_batches_completed(srcu_ctlp);
}
static void srcu_call_rcu(struct rcu_head *head, rcu_callback_t func)
{
call_srcu(srcu_ctlp, head, func);
}
static void srcu_rcu_barrier(void)
{
srcu_barrier(srcu_ctlp);
}
static void srcu_perf_synchronize(void)
{
synchronize_srcu(srcu_ctlp);
}
static void srcu_perf_synchronize_expedited(void)
{
synchronize_srcu_expedited(srcu_ctlp);
}
static struct rcu_perf_ops srcu_ops = {
.ptype = SRCU_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = srcu_perf_read_lock,
.readunlock = srcu_perf_read_unlock,
.get_gp_seq = srcu_perf_completed,
.gp_diff = rcu_seq_diff,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
.sync = srcu_perf_synchronize,
.exp_sync = srcu_perf_synchronize_expedited,
.name = "srcu"
};
static struct srcu_struct srcud;
static void srcu_sync_perf_init(void)
{
srcu_ctlp = &srcud;
init_srcu_struct(srcu_ctlp);
}
static void srcu_sync_perf_cleanup(void)
{
cleanup_srcu_struct(srcu_ctlp);
}
static struct rcu_perf_ops srcud_ops = {
.ptype = SRCU_FLAVOR,
.init = srcu_sync_perf_init,
.cleanup = srcu_sync_perf_cleanup,
.readlock = srcu_perf_read_lock,
.readunlock = srcu_perf_read_unlock,
.get_gp_seq = srcu_perf_completed,
.gp_diff = rcu_seq_diff,
.exp_completed = srcu_perf_completed,
.async = srcu_call_rcu,
.gp_barrier = srcu_rcu_barrier,
.sync = srcu_perf_synchronize,
.exp_sync = srcu_perf_synchronize_expedited,
.name = "srcud"
};
/*
* Definitions for sched perf testing.
*/
static int sched_perf_read_lock(void)
{
preempt_disable();
return 0;
}
static void sched_perf_read_unlock(int idx)
{
preempt_enable();
}
static struct rcu_perf_ops sched_ops = {
.ptype = RCU_SCHED_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = sched_perf_read_lock,
.readunlock = sched_perf_read_unlock,
.get_gp_seq = rcu_sched_get_gp_seq,
.gp_diff = rcu_seq_diff,
.exp_completed = rcu_exp_batches_completed_sched,
.async = call_rcu_sched,
.gp_barrier = rcu_barrier_sched,
.sync = synchronize_sched,
.exp_sync = synchronize_sched_expedited,
.name = "sched"
};
/*
* Definitions for RCU-tasks perf testing.
*/
static int tasks_perf_read_lock(void)
{
return 0;
}
static void tasks_perf_read_unlock(int idx)
{
}
static struct rcu_perf_ops tasks_ops = {
.ptype = RCU_TASKS_FLAVOR,
.init = rcu_sync_perf_init,
.readlock = tasks_perf_read_lock,
.readunlock = tasks_perf_read_unlock,
.get_gp_seq = rcu_no_completed,
.gp_diff = rcu_seq_diff,
.async = call_rcu_tasks,
.gp_barrier = rcu_barrier_tasks,
.sync = synchronize_rcu_tasks,
.exp_sync = synchronize_rcu_tasks,
.name = "tasks"
};
static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
{
if (!cur_ops->gp_diff)
return new - old;
return cur_ops->gp_diff(new, old);
}
/*
* If performance tests complete, wait for shutdown to commence.
*/
static void rcu_perf_wait_shutdown(void)
{
cond_resched_tasks_rcu_qs();
if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters)
return;
while (!torture_must_stop())
schedule_timeout_uninterruptible(1);
}
/*
* RCU perf reader kthread. Repeatedly does empty RCU read-side
* critical section, minimizing update-side interference.
*/
static int
rcu_perf_reader(void *arg)
{
unsigned long flags;
int idx;
long me = (long)arg;
VERBOSE_PERFOUT_STRING("rcu_perf_reader task started");
set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
set_user_nice(current, MAX_NICE);
atomic_inc(&n_rcu_perf_reader_started);
do {
local_irq_save(flags);
idx = cur_ops->readlock();
cur_ops->readunlock(idx);
local_irq_restore(flags);
rcu_perf_wait_shutdown();
} while (!torture_must_stop());
torture_kthread_stopping("rcu_perf_reader");
return 0;
}
/*
* Callback function for asynchronous grace periods from rcu_perf_writer().
*/
static void rcu_perf_async_cb(struct rcu_head *rhp)
{
atomic_dec(this_cpu_ptr(&n_async_inflight));
kfree(rhp);
}
/*
* RCU perf writer kthread. Repeatedly does a grace period.
*/
static int
rcu_perf_writer(void *arg)
{
int i = 0;
int i_max;
long me = (long)arg;
struct rcu_head *rhp = NULL;
struct sched_param sp;
bool started = false, done = false, alldone = false;
u64 t;
u64 *wdp;
u64 *wdpp = writer_durations[me];
VERBOSE_PERFOUT_STRING("rcu_perf_writer task started");
WARN_ON(!wdpp);
set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
sp.sched_priority = 1;
sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
if (holdoff)
schedule_timeout_uninterruptible(holdoff * HZ);
t = ktime_get_mono_fast_ns();
if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
t_rcu_perf_writer_started = t;
if (gp_exp) {
b_rcu_perf_writer_started =
cur_ops->exp_completed() / 2;
} else {
b_rcu_perf_writer_started = cur_ops->get_gp_seq();
}
}
do {
if (writer_holdoff)
udelay(writer_holdoff);
wdp = &wdpp[i];
*wdp = ktime_get_mono_fast_ns();
if (gp_async) {
retry:
if (!rhp)
rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
rcu_perf_writer_state = RTWS_ASYNC;
atomic_inc(this_cpu_ptr(&n_async_inflight));
cur_ops->async(rhp, rcu_perf_async_cb);
rhp = NULL;
} else if (!kthread_should_stop()) {
rcu_perf_writer_state = RTWS_BARRIER;
cur_ops->gp_barrier();
goto retry;
} else {
kfree(rhp); /* Because we are stopping. */
}
} else if (gp_exp) {
rcu_perf_writer_state = RTWS_EXP_SYNC;
cur_ops->exp_sync();
} else {
rcu_perf_writer_state = RTWS_SYNC;
cur_ops->sync();
}
rcu_perf_writer_state = RTWS_IDLE;
t = ktime_get_mono_fast_ns();
*wdp = t - *wdp;
i_max = i;
if (!started &&
atomic_read(&n_rcu_perf_writer_started) >= nrealwriters)
started = true;
if (!done && i >= MIN_MEAS) {
done = true;
sp.sched_priority = 0;
sched_setscheduler_nocheck(current,
SCHED_NORMAL, &sp);
pr_alert("%s%s rcu_perf_writer %ld has %d measurements\n",
perf_type, PERF_FLAG, me, MIN_MEAS);
if (atomic_inc_return(&n_rcu_perf_writer_finished) >=
nrealwriters) {
schedule_timeout_interruptible(10);
rcu_ftrace_dump(DUMP_ALL);
PERFOUT_STRING("Test complete");
t_rcu_perf_writer_finished = t;
if (gp_exp) {
b_rcu_perf_writer_finished =
cur_ops->exp_completed() / 2;
} else {
b_rcu_perf_writer_finished =
cur_ops->get_gp_seq();
}
if (shutdown) {
smp_mb(); /* Assign before wake. */
wake_up(&shutdown_wq);
}
}
}
if (done && !alldone &&
atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters)
alldone = true;
if (started && !alldone && i < MAX_MEAS - 1)
i++;
rcu_perf_wait_shutdown();
} while (!torture_must_stop());
if (gp_async) {
rcu_perf_writer_state = RTWS_BARRIER;
cur_ops->gp_barrier();
}
rcu_perf_writer_state = RTWS_STOPPING;
writer_n_durations[me] = i_max;
torture_kthread_stopping("rcu_perf_writer");
return 0;
}
static void
rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
{
pr_alert("%s" PERF_FLAG
"--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
perf_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
}
static void
rcu_perf_cleanup(void)
{
int i;
int j;
int ngps = 0;
u64 *wdp;
u64 *wdpp;
/*
* Would like warning at start, but everything is expedited
* during the mid-boot phase, so have to wait till the end.
*/
if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
if (rcu_gp_is_normal() && gp_exp)
VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
if (gp_exp && gp_async)
VERBOSE_PERFOUT_ERRSTRING("No expedited async GPs, so went with async!");
if (torture_cleanup_begin())
return;
if (!cur_ops) {
torture_cleanup_end();
return;
}
if (reader_tasks) {
for (i = 0; i < nrealreaders; i++)
torture_stop_kthread(rcu_perf_reader,
reader_tasks[i]);
kfree(reader_tasks);
}
if (writer_tasks) {
for (i = 0; i < nrealwriters; i++) {
torture_stop_kthread(rcu_perf_writer,
writer_tasks[i]);
if (!writer_n_durations)
continue;
j = writer_n_durations[i];
pr_alert("%s%s writer %d gps: %d\n",
perf_type, PERF_FLAG, i, j);
ngps += j;
}
pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n",
perf_type, PERF_FLAG,
t_rcu_perf_writer_started, t_rcu_perf_writer_finished,
t_rcu_perf_writer_finished -
t_rcu_perf_writer_started,
ngps,
rcuperf_seq_diff(b_rcu_perf_writer_finished,
b_rcu_perf_writer_started));
for (i = 0; i < nrealwriters; i++) {
if (!writer_durations)
break;
if (!writer_n_durations)
continue;
wdpp = writer_durations[i];
if (!wdpp)
continue;
for (j = 0; j <= writer_n_durations[i]; j++) {
wdp = &wdpp[j];
pr_alert("%s%s %4d writer-duration: %5d %llu\n",
perf_type, PERF_FLAG,
i, j, *wdp);
if (j % 100 == 0)
schedule_timeout_uninterruptible(1);
}
kfree(writer_durations[i]);
}
kfree(writer_tasks);
kfree(writer_durations);
kfree(writer_n_durations);
}
/* Do flavor-specific cleanup operations. */
if (cur_ops->cleanup != NULL)
cur_ops->cleanup();
torture_cleanup_end();
}
/*
* Return the number if non-negative. If -1, the number of CPUs.
* If less than -1, that much less than the number of CPUs, but
* at least one.
*/
static int compute_real(int n)
{
int nr;
if (n >= 0) {
nr = n;
} else {
nr = num_online_cpus() + 1 + n;
if (nr <= 0)
nr = 1;
}
return nr;
}
/*
* RCU perf shutdown kthread. Just waits to be awakened, then shuts
* down system.
*/
static int
rcu_perf_shutdown(void *arg)
{
do {
wait_event(shutdown_wq,
atomic_read(&n_rcu_perf_writer_finished) >=
nrealwriters);
} while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters);
smp_mb(); /* Wake before output. */
rcu_perf_cleanup();
kernel_power_off();
return -EINVAL;
}
static int __init
rcu_perf_init(void)
{
long i;
int firsterr = 0;
static struct rcu_perf_ops *perf_ops[] = {
&rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops,
&tasks_ops,
};
if (!torture_init_begin(perf_type, verbose))
return -EBUSY;
/* Process args and tell the world that the perf'er is on the job. */
for (i = 0; i < ARRAY_SIZE(perf_ops); i++) {
cur_ops = perf_ops[i];
if (strcmp(perf_type, cur_ops->name) == 0)
break;
}
if (i == ARRAY_SIZE(perf_ops)) {
pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
pr_alert("rcu-perf types:");
for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
pr_cont(" %s", perf_ops[i]->name);
pr_cont("\n");
firsterr = -EINVAL;
cur_ops = NULL;
goto unwind;
}
if (cur_ops->init)
cur_ops->init();
nrealwriters = compute_real(nwriters);
nrealreaders = compute_real(nreaders);
atomic_set(&n_rcu_perf_reader_started, 0);
atomic_set(&n_rcu_perf_writer_started, 0);
atomic_set(&n_rcu_perf_writer_finished, 0);
rcu_perf_print_module_parms(cur_ops, "Start of test");
/* Start up the kthreads. */
if (shutdown) {
init_waitqueue_head(&shutdown_wq);
firsterr = torture_create_kthread(rcu_perf_shutdown, NULL,
shutdown_task);
if (firsterr)
goto unwind;
schedule_timeout_uninterruptible(1);
}
reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
GFP_KERNEL);
if (reader_tasks == NULL) {
VERBOSE_PERFOUT_ERRSTRING("out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nrealreaders; i++) {
firsterr = torture_create_kthread(rcu_perf_reader, (void *)i,
reader_tasks[i]);
if (firsterr)
goto unwind;
}
while (atomic_read(&n_rcu_perf_reader_started) < nrealreaders)
schedule_timeout_uninterruptible(1);
writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]),
GFP_KERNEL);
writer_durations = kcalloc(nrealwriters, sizeof(*writer_durations),
GFP_KERNEL);
writer_n_durations =
kcalloc(nrealwriters, sizeof(*writer_n_durations),
GFP_KERNEL);
if (!writer_tasks || !writer_durations || !writer_n_durations) {
VERBOSE_PERFOUT_ERRSTRING("out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nrealwriters; i++) {
writer_durations[i] =
kcalloc(MAX_MEAS, sizeof(*writer_durations[i]),
GFP_KERNEL);
if (!writer_durations[i]) {
firsterr = -ENOMEM;
goto unwind;
}
firsterr = torture_create_kthread(rcu_perf_writer, (void *)i,
writer_tasks[i]);
if (firsterr)
goto unwind;
}
torture_init_end();
return 0;
unwind:
torture_init_end();
rcu_perf_cleanup();
return firsterr;
}
module_init(rcu_perf_init);
module_exit(rcu_perf_cleanup);
File diff suppressed because it is too large. Load diff
+206
View File
@@ -0,0 +1,206 @@
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion,
* tiny version for non-preemptible single-CPU use.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2017
*
* Author: Paul McKenney <paulmck@us.ibm.com>
*/
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/preempt.h>
#include <linux/rcupdate_wait.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/srcu.h>
#include <linux/rcu_node_tree.h>
#include "rcu_segcblist.h"
#include "rcu.h"
int rcu_scheduler_active __read_mostly;
static int init_srcu_struct_fields(struct srcu_struct *sp)
{
sp->srcu_lock_nesting[0] = 0;
sp->srcu_lock_nesting[1] = 0;
init_swait_queue_head(&sp->srcu_wq);
sp->srcu_cb_head = NULL;
sp->srcu_cb_tail = &sp->srcu_cb_head;
sp->srcu_gp_running = false;
sp->srcu_gp_waiting = false;
sp->srcu_idx = 0;
INIT_WORK(&sp->srcu_work, srcu_drive_gp);
return 0;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
int __init_srcu_struct(struct srcu_struct *sp, const char *name,
struct lock_class_key *key)
{
/* Don't re-initialize a lock while it is held. */
debug_check_no_locks_freed((void *)sp, sizeof(*sp));
lockdep_init_map(&sp->dep_map, name, key, 0);
return init_srcu_struct_fields(sp);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
* init_srcu_struct - initialize a sleep-RCU structure
* @sp: structure to initialize.
*
* Must invoke this on a given srcu_struct before passing that srcu_struct
* to any other function. Each srcu_struct represents a separate domain
* of SRCU protection.
*/
int init_srcu_struct(struct srcu_struct *sp)
{
return init_srcu_struct_fields(sp);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
* @sp: structure to clean up.
*
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
{
WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
if (quiesced)
WARN_ON(work_pending(&sp->srcu_work));
else
flush_work(&sp->srcu_work);
WARN_ON(sp->srcu_gp_running);
WARN_ON(sp->srcu_gp_waiting);
WARN_ON(sp->srcu_cb_head);
WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail);
}
EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
/*
* Removes the count for the old reader from the appropriate element of
* the srcu_struct.
*/
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
int newval = sp->srcu_lock_nesting[idx] - 1;
WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
if (!newval && READ_ONCE(sp->srcu_gp_waiting))
swake_up_one(&sp->srcu_wq);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
/*
* Workqueue handler to drive one grace period and invoke any callbacks
* that become ready as a result. Single-CPU and !PREEMPT operation
* means that we get away with murder on synchronization. ;-)
*/
void srcu_drive_gp(struct work_struct *wp)
{
int idx;
struct rcu_head *lh;
struct rcu_head *rhp;
struct srcu_struct *sp;
sp = container_of(wp, struct srcu_struct, srcu_work);
if (sp->srcu_gp_running || !READ_ONCE(sp->srcu_cb_head))
return; /* Already running or nothing to do. */
/* Remove recently arrived callbacks and wait for readers. */
WRITE_ONCE(sp->srcu_gp_running, true);
local_irq_disable();
lh = sp->srcu_cb_head;
sp->srcu_cb_head = NULL;
sp->srcu_cb_tail = &sp->srcu_cb_head;
local_irq_enable();
idx = sp->srcu_idx;
WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
/* Invoke the callbacks we removed above. */
while (lh) {
rhp = lh;
lh = lh->next;
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
}
/*
* Enable rescheduling, and if there are more callbacks,
* reschedule ourselves. This can race with a call_srcu()
* at interrupt level, but the ->srcu_gp_running checks will
* straighten that out.
*/
WRITE_ONCE(sp->srcu_gp_running, false);
if (READ_ONCE(sp->srcu_cb_head))
schedule_work(&sp->srcu_work);
}
EXPORT_SYMBOL_GPL(srcu_drive_gp);
/*
* Enqueue an SRCU callback on the specified srcu_struct structure,
* initiating grace-period processing if it is not already running.
*/
void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
rcu_callback_t func)
{
unsigned long flags;
rhp->func = func;
rhp->next = NULL;
local_irq_save(flags);
*sp->srcu_cb_tail = rhp;
sp->srcu_cb_tail = &rhp->next;
local_irq_restore(flags);
if (!READ_ONCE(sp->srcu_gp_running))
schedule_work(&sp->srcu_work);
}
EXPORT_SYMBOL_GPL(call_srcu);
/*
* synchronize_srcu - wait for prior SRCU read-side critical-section completion
*/
void synchronize_srcu(struct srcu_struct *sp)
{
struct rcu_synchronize rs;
init_rcu_head_on_stack(&rs.head);
init_completion(&rs.completion);
call_srcu(sp, &rs.head, wakeme_after_rcu);
wait_for_completion(&rs.completion);
destroy_rcu_head_on_stack(&rs.head);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
/* Lockdep diagnostics. */
void __init rcu_scheduler_starting(void)
{
rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
}
File diff suppressed because it is too large. Load diff
+240
View File
@@ -0,0 +1,240 @@
/*
* RCU-based infrastructure for lightweight reader-writer locking
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (c) 2015, Red Hat, Inc.
*
* Author: Oleg Nesterov <oleg@redhat.com>
*/
#include <linux/rcu_sync.h>
#include <linux/sched.h>
#ifdef CONFIG_PROVE_RCU
#define __INIT_HELD(func) .held = func,
#else
#define __INIT_HELD(func)
#endif
static const struct {
void (*sync)(void);
void (*call)(struct rcu_head *, void (*)(struct rcu_head *));
void (*wait)(void);
#ifdef CONFIG_PROVE_RCU
int (*held)(void);
#endif
} gp_ops[] = {
[RCU_SYNC] = {
.sync = synchronize_rcu,
.call = call_rcu,
.wait = rcu_barrier,
__INIT_HELD(rcu_read_lock_held)
},
[RCU_SCHED_SYNC] = {
.sync = synchronize_sched,
.call = call_rcu_sched,
.wait = rcu_barrier_sched,
__INIT_HELD(rcu_read_lock_sched_held)
},
[RCU_BH_SYNC] = {
.sync = synchronize_rcu_bh,
.call = call_rcu_bh,
.wait = rcu_barrier_bh,
__INIT_HELD(rcu_read_lock_bh_held)
},
};
enum { GP_IDLE = 0, GP_PENDING, GP_PASSED };
enum { CB_IDLE = 0, CB_PENDING, CB_REPLAY };
#define rss_lock gp_wait.lock
#ifdef CONFIG_PROVE_RCU
void rcu_sync_lockdep_assert(struct rcu_sync *rsp)
{
RCU_LOCKDEP_WARN(!gp_ops[rsp->gp_type].held(),
"suspicious rcu_sync_is_idle() usage");
}
EXPORT_SYMBOL_GPL(rcu_sync_lockdep_assert);
#endif
/**
* rcu_sync_init() - Initialize an rcu_sync structure
* @rsp: Pointer to rcu_sync structure to be initialized
* @type: Flavor of RCU with which to synchronize rcu_sync structure
*/
void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type)
{
memset(rsp, 0, sizeof(*rsp));
init_waitqueue_head(&rsp->gp_wait);
rsp->gp_type = type;
}
/**
* rcu_sync_enter_start - Force readers onto slow path for multiple updates
* @rsp: Pointer to rcu_sync structure to use for synchronization
*
* Must be called after rcu_sync_init() and before first use.
*
* Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
* pairs turn into NO-OPs.
*/
void rcu_sync_enter_start(struct rcu_sync *rsp)
{
rsp->gp_count++;
rsp->gp_state = GP_PASSED;
}
/**
* rcu_sync_enter() - Force readers onto slowpath
* @rsp: Pointer to rcu_sync structure to use for synchronization
*
* This function is used by updaters who need readers to make use of
* a slowpath during the update. After this function returns, all
* subsequent calls to rcu_sync_is_idle() will return false, which
* tells readers to stay off their fastpaths. A later call to
* rcu_sync_exit() re-enables reader slowpaths.
*
* When called in isolation, rcu_sync_enter() must wait for a grace
* period, however, closely spaced calls to rcu_sync_enter() can
* optimize away the grace-period wait via a state machine implemented
* by rcu_sync_enter(), rcu_sync_exit(), and rcu_sync_func().
*/
void rcu_sync_enter(struct rcu_sync *rsp)
{
bool need_wait, need_sync;
spin_lock_irq(&rsp->rss_lock);
need_wait = rsp->gp_count++;
need_sync = rsp->gp_state == GP_IDLE;
if (need_sync)
rsp->gp_state = GP_PENDING;
spin_unlock_irq(&rsp->rss_lock);
BUG_ON(need_wait && need_sync);
if (need_sync) {
gp_ops[rsp->gp_type].sync();
rsp->gp_state = GP_PASSED;
wake_up_all(&rsp->gp_wait);
} else if (need_wait) {
wait_event(rsp->gp_wait, rsp->gp_state == GP_PASSED);
} else {
/*
* Possible when there's a pending CB from a rcu_sync_exit().
* Nobody has yet been allowed the 'fast' path and thus we can
* avoid doing any sync(). The callback will get 'dropped'.
*/
BUG_ON(rsp->gp_state != GP_PASSED);
}
}
/**
* rcu_sync_func() - Callback function managing reader access to fastpath
* @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization
*
* This function is passed to one of the call_rcu() functions by
* rcu_sync_exit(), so that it is invoked after a grace period following the
* that invocation of rcu_sync_exit(). It takes action based on events that
* have taken place in the meantime, so that closely spaced rcu_sync_enter()
* and rcu_sync_exit() pairs need not wait for a grace period.
*
* If another rcu_sync_enter() is invoked before the grace period
* ended, reset state to allow the next rcu_sync_exit() to let the
* readers back onto their fastpaths (after a grace period). If both
* another rcu_sync_enter() and its matching rcu_sync_exit() are invoked
* before the grace period ended, re-invoke call_rcu() on behalf of that
* rcu_sync_exit(). Otherwise, set all state back to idle so that readers
* can again use their fastpaths.
*/
static void rcu_sync_func(struct rcu_head *rhp)
{
struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
unsigned long flags;
BUG_ON(rsp->gp_state != GP_PASSED);
BUG_ON(rsp->cb_state == CB_IDLE);
spin_lock_irqsave(&rsp->rss_lock, flags);
if (rsp->gp_count) {
/*
* A new rcu_sync_begin() has happened; drop the callback.
*/
rsp->cb_state = CB_IDLE;
} else if (rsp->cb_state == CB_REPLAY) {
/*
* A new rcu_sync_exit() has happened; requeue the callback
* to catch a later GP.
*/
rsp->cb_state = CB_PENDING;
gp_ops[rsp->gp_type].call(&rsp->cb_head, rcu_sync_func);
} else {
/*
* We're at least a GP after rcu_sync_exit(); eveybody will now
* have observed the write side critical section. Let 'em rip!.
*/
rsp->cb_state = CB_IDLE;
rsp->gp_state = GP_IDLE;
}
spin_unlock_irqrestore(&rsp->rss_lock, flags);
}
/**
* rcu_sync_exit() - Allow readers back onto fast patch after grace period
* @rsp: Pointer to rcu_sync structure to use for synchronization
*
* This function is used by updaters who have completed, and can therefore
* now allow readers to make use of their fastpaths after a grace period
* has elapsed. After this grace period has completed, all subsequent
* calls to rcu_sync_is_idle() will return true, which tells readers that
* they can once again use their fastpaths.
*/
void rcu_sync_exit(struct rcu_sync *rsp)
{
spin_lock_irq(&rsp->rss_lock);
if (!--rsp->gp_count) {
if (rsp->cb_state == CB_IDLE) {
rsp->cb_state = CB_PENDING;
gp_ops[rsp->gp_type].call(&rsp->cb_head, rcu_sync_func);
} else if (rsp->cb_state == CB_PENDING) {
rsp->cb_state = CB_REPLAY;
}
}
spin_unlock_irq(&rsp->rss_lock);
}
/**
* rcu_sync_dtor() - Clean up an rcu_sync structure
* @rsp: Pointer to rcu_sync structure to be cleaned up
*/
void rcu_sync_dtor(struct rcu_sync *rsp)
{
int cb_state;
BUG_ON(rsp->gp_count);
spin_lock_irq(&rsp->rss_lock);
if (rsp->cb_state == CB_REPLAY)
rsp->cb_state = CB_PENDING;
cb_state = rsp->cb_state;
spin_unlock_irq(&rsp->rss_lock);
if (cb_state != CB_IDLE) {
gp_ops[rsp->gp_type].wait();
BUG_ON(rsp->cb_state != CB_IDLE);
}
}
+239
View File
@@ -0,0 +1,239 @@
/*
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*
* 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 "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. */
};
/* Definition for rcupdate control block. */
static struct rcu_ctrlblk rcu_sched_ctrlblk = {
.donetail = &rcu_sched_ctrlblk.rcucblist,
.curtail = &rcu_sched_ctrlblk.rcucblist,
};
static struct rcu_ctrlblk rcu_bh_ctrlblk = {
.donetail = &rcu_bh_ctrlblk.rcucblist,
.curtail = &rcu_bh_ctrlblk.rcucblist,
};
void rcu_barrier_bh(void)
{
wait_rcu_gp(call_rcu_bh);
}
EXPORT_SYMBOL(rcu_barrier_bh);
void rcu_barrier_sched(void)
{
wait_rcu_gp(call_rcu_sched);
}
EXPORT_SYMBOL(rcu_barrier_sched);
/*
* Helper function for rcu_sched_qs() and rcu_bh_qs().
* Also irqs are disabled to avoid confusion due to interrupt handlers
* invoking call_rcu().
*/
static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
{
if (rcp->donetail != rcp->curtail) {
rcp->donetail = rcp->curtail;
return 1;
}
return 0;
}
/*
* Record an rcu quiescent state. And an rcu_bh quiescent state while we
* are at it, given that any rcu quiescent state is also an rcu_bh
* quiescent state. Use "+" instead of "||" to defeat short circuiting.
*/
void rcu_sched_qs(void)
{
unsigned long flags;
local_irq_save(flags);
if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
rcu_qsctr_help(&rcu_bh_ctrlblk))
raise_softirq(RCU_SOFTIRQ);
local_irq_restore(flags);
}
/*
* Record an rcu_bh quiescent state.
*/
void rcu_bh_qs(void)
{
unsigned long flags;
local_irq_save(flags);
if (rcu_qsctr_help(&rcu_bh_ctrlblk))
raise_softirq(RCU_SOFTIRQ);
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_check_callbacks(int user)
{
if (user)
rcu_sched_qs();
if (user || !in_softirq())
rcu_bh_qs();
}
/*
* Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
* whose grace period has elapsed.
*/
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
struct rcu_head *next, *list;
unsigned long flags;
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
if (rcp->donetail == &rcp->rcucblist) {
/* No callbacks ready, so just leave. */
local_irq_restore(flags);
return;
}
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;
*rcp->donetail = NULL;
if (rcp->curtail == rcp->donetail)
rcp->curtail = &rcp->rcucblist;
rcp->donetail = &rcp->rcucblist;
local_irq_restore(flags);
/* Invoke the callbacks on the local list. */
while (list) {
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
local_bh_disable();
__rcu_reclaim("", list);
local_bh_enable();
list = next;
}
}
static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
{
__rcu_process_callbacks(&rcu_sched_ctrlblk);
__rcu_process_callbacks(&rcu_bh_ctrlblk);
}
/*
* Wait for a grace period to elapse. But it is illegal to invoke
* synchronize_sched() from within an RCU read-side critical section.
* Therefore, any legal call to synchronize_sched() is a quiescent
* state, and so on a UP system, synchronize_sched() need do nothing.
* Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the
* benefits of doing might_sleep() to reduce latency.)
*
* Cool, huh? (Due to Josh Triplett.)
*/
void synchronize_sched(void)
{
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_sched() in RCU read-side critical section");
}
EXPORT_SYMBOL_GPL(synchronize_sched);
/*
* Helper function for call_rcu() and call_rcu_bh().
*/
static void __call_rcu(struct rcu_head *head,
rcu_callback_t func,
struct rcu_ctrlblk *rcp)
{
unsigned long flags;
debug_rcu_head_queue(head);
head->func = func;
head->next = NULL;
local_irq_save(flags);
*rcp->curtail = head;
rcp->curtail = &head->next;
local_irq_restore(flags);
if (unlikely(is_idle_task(current))) {
/* force scheduling for rcu_sched_qs() */
resched_cpu(0);
}
}
/*
* Post an RCU callback to be invoked after the end of an RCU-sched grace
* period. But since we have but one CPU, that would be after any
* quiescent state.
*/
void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
{
__call_rcu(head, func, &rcu_sched_ctrlblk);
}
EXPORT_SYMBOL_GPL(call_rcu_sched);
/*
* Post an RCU bottom-half callback to be invoked after any subsequent
* quiescent state.
*/
void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
{
__call_rcu(head, func, &rcu_bh_ctrlblk);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
rcu_early_boot_tests();
}
+4189
View File
File diff suppressed because it is too large. Load diff
+500
View File
@@ -0,0 +1,500 @@
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
* Author: Ingo Molnar <mingo@elte.hu>
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#include <linux/cache.h>
#include <linux/spinlock.h>
#include <linux/rtmutex.h>
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/seqlock.h>
#include <linux/swait.h>
#include <linux/stop_machine.h>
#include <linux/rcu_node_tree.h>
#include "rcu_segcblist.h"
/*
* Dynticks per-CPU state.
*/
struct rcu_dynticks {
long dynticks_nesting; /* Track process nesting level. */
long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */
atomic_t dynticks; /* Even value for idle, else odd. */
bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */
unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */
bool rcu_urgent_qs; /* GP old need light quiescent state. */
#ifdef CONFIG_RCU_FAST_NO_HZ
bool all_lazy; /* Are all CPU's CBs lazy? */
unsigned long nonlazy_posted;
/* # times non-lazy CBs posted to CPU. */
unsigned long nonlazy_posted_snap;
/* idle-period nonlazy_posted snapshot. */
unsigned long last_accelerate;
/* Last jiffy CBs were accelerated. */
unsigned long last_advance_all;
/* Last jiffy CBs were all advanced. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
};
/* Communicate arguments to a workqueue handler. */
struct rcu_exp_work {
smp_call_func_t rew_func;
struct rcu_state *rew_rsp;
unsigned long rew_s;
struct work_struct rew_work;
};
/* RCU's kthread states for tracing. */
#define RCU_KTHREAD_STOPPED 0
#define RCU_KTHREAD_RUNNING 1
#define RCU_KTHREAD_WAITING 2
#define RCU_KTHREAD_OFFCPU 3
#define RCU_KTHREAD_YIELDING 4
#define RCU_KTHREAD_MAX 4
/*
* Definition for node within the RCU grace-period-detection hierarchy.
*/
struct rcu_node {
raw_spinlock_t __private lock; /* Root rcu_node's lock protects */
/* some rcu_state fields as well as */
/* following. */
unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */
unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
unsigned long completedqs; /* All QSes done for this node. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
/* In leaf rcu_node, each bit corresponds to */
/* an rcu_data structure, otherwise, each */
/* bit corresponds to a child rcu_node */
/* structure. */
unsigned long rcu_gp_init_mask; /* Mask of offline CPUs at GP init. */
unsigned long qsmaskinit;
/* Per-GP initial value for qsmask. */
/* Initialized from ->qsmaskinitnext at the */
/* beginning of each grace period. */
unsigned long qsmaskinitnext;
/* Online CPUs for next grace period. */
unsigned long expmask; /* CPUs or groups that need to check in */
/* to allow the current expedited GP */
/* to complete. */
unsigned long expmaskinit;
/* Per-GP initial values for expmask. */
/* Initialized from ->expmaskinitnext at the */
/* beginning of each expedited GP. */
unsigned long expmaskinitnext;
/* Online CPUs for next expedited GP. */
/* Any CPU that has ever been online will */
/* have its bit set. */
unsigned long ffmask; /* Fully functional CPUs. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
/* Only one bit will be set in this mask. */
int grplo; /* lowest-numbered CPU or group here. */
int grphi; /* highest-numbered CPU or group here. */
u8 grpnum; /* CPU/group number for next level up. */
u8 level; /* root is at level 0. */
bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
/* exit RCU read-side critical sections */
/* before propagating offline up the */
/* rcu_node tree? */
struct rcu_node *parent;
struct list_head blkd_tasks;
/* Tasks blocked in RCU read-side critical */
/* section. Tasks are placed at the head */
/* of this list and age towards the tail. */
struct list_head *gp_tasks;
/* Pointer to the first task blocking the */
/* current grace period, or NULL if there */
/* is no such task. */
struct list_head *exp_tasks;
/* Pointer to the first task blocking the */
/* current expedited grace period, or NULL */
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there can cannot be any such task. */
struct list_head *boost_tasks;
/* Pointer to first task that needs to be */
/* priority boosted, or NULL if no priority */
/* boosting is needed for this rcu_node */
/* structure. If there are no tasks */
/* queued on this rcu_node structure that */
/* are blocking the current grace period, */
/* there can be no such task. */
struct rt_mutex boost_mtx;
/* Used only for the priority-boosting */
/* side effect, not as a lock. */
unsigned long boost_time;
/* When to start boosting (jiffies). */
struct task_struct *boost_kthread_task;
/* kthread that takes care of priority */
/* boosting for this rcu_node structure. */
unsigned int boost_kthread_status;
/* State of boost_kthread_task for tracing. */
#ifdef CONFIG_RCU_NOCB_CPU
struct swait_queue_head nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
unsigned long exp_seq_rq;
wait_queue_head_t exp_wq[4];
struct rcu_exp_work rew;
bool exp_need_flush; /* Need to flush workitem? */
} ____cacheline_internodealigned_in_smp;
/*
* Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
* are indexed relative to this interval rather than the global CPU ID space.
* This generates the bit for a CPU in node-local masks.
*/
#define leaf_node_cpu_bit(rnp, cpu) (1UL << ((cpu) - (rnp)->grplo))
/*
* Union to allow "aggregate OR" operation on the need for a quiescent
* state by the normal and expedited grace periods.
*/
union rcu_noqs {
struct {
u8 norm;
u8 exp;
} b; /* Bits. */
u16 s; /* Set of bits, aggregate OR here. */
};
/* Per-CPU data for read-copy update. */
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */
unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */
unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
/* for rcu_all_qs() invocations. */
union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */
bool core_needs_qs; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
bool gpwrap; /* Possible ->gp_seq wrap. */
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
unsigned long ticks_this_gp; /* The number of scheduling-clock */
/* ticks this CPU has handled */
/* during and after the last grace */
/* period it is aware of. */
/* 2) batch handling */
struct rcu_segcblist cblist; /* Segmented callback list, with */
/* different callbacks waiting for */
/* different grace periods. */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_force_qs_snap;
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
/* 3) dynticks interface. */
struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */
int dynticks_snap; /* Per-GP tracking for dynticks. */
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
unsigned long cond_resched_completed;
/* Grace period that needs help */
/* from cond_resched(). */
/* 5) _rcu_barrier(), OOM callbacks, and expediting. */
struct rcu_head barrier_head;
#ifdef CONFIG_RCU_FAST_NO_HZ
struct rcu_head oom_head;
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
int exp_dynticks_snap; /* Double-check need for IPI. */
/* 6) Callback offloading. */
#ifdef CONFIG_RCU_NOCB_CPU
struct rcu_head *nocb_head; /* CBs waiting for kthread. */
struct rcu_head **nocb_tail;
atomic_long_t nocb_q_count; /* # CBs waiting for nocb */
atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */
struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
struct rcu_head **nocb_follower_tail;
struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */
struct task_struct *nocb_kthread;
raw_spinlock_t nocb_lock; /* Guard following pair of fields. */
int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
struct timer_list nocb_timer; /* Enforce finite deferral. */
/* The following fields are used by the leader, hence own cacheline. */
struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
/* CBs waiting for GP. */
struct rcu_head **nocb_gp_tail;
bool nocb_leader_sleep; /* Is the nocb leader thread asleep? */
struct rcu_data *nocb_next_follower;
/* Next follower in wakeup chain. */
/* The following fields are used by the follower, hence new cachline. */
struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp;
/* Leader CPU takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/* 7) Diagnostic data, including RCU CPU stall warnings. */
unsigned int softirq_snap; /* Snapshot of softirq activity. */
/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
struct irq_work rcu_iw; /* Check for non-irq activity. */
bool rcu_iw_pending; /* Is ->rcu_iw pending? */
unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */
unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */
short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */
unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */
short rcu_onl_gp_flags; /* ->gp_flags at last online. */
int cpu;
struct rcu_state *rsp;
};
/* Values for nocb_defer_wakeup field in struct rcu_data. */
#define RCU_NOCB_WAKE_NOT 0
#define RCU_NOCB_WAKE 1
#define RCU_NOCB_WAKE_FORCE 2
#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
/* For jiffies_till_first_fqs and */
/* and jiffies_till_next_fqs. */
#define RCU_JIFFIES_FQS_DIV 256 /* Very large systems need more */
/* delay between bouts of */
/* quiescent-state forcing. */
#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time to take */
/* at least one scheduling clock */
/* irq before ratting on them. */
#define rcu_wait(cond) \
do { \
for (;;) { \
set_current_state(TASK_INTERRUPTIBLE); \
if (cond) \
break; \
schedule(); \
} \
__set_current_state(TASK_RUNNING); \
} while (0)
/*
* RCU global state, including node hierarchy. This hierarchy is
* represented in "heap" form in a dense array. The root (first level)
* of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
* level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
* and the third level in ->node[m+1] and following (->node[m+1] referenced
* by ->level[2]). The number of levels is determined by the number of
* CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy"
* consisting of a single rcu_node.
*/
struct rcu_state {
struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */
struct rcu_node *level[RCU_NUM_LVLS + 1];
/* Hierarchy levels (+1 to */
/* shut bogus gcc warning) */
struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */
call_rcu_func_t call; /* call_rcu() flavor. */
int ncpus; /* # CPUs seen so far. */
/* The following fields are guarded by the root rcu_node's lock. */
u8 boost ____cacheline_internodealigned_in_smp;
/* Subject to priority boost. */
unsigned long gp_seq; /* Grace-period sequence #. */
struct task_struct *gp_kthread; /* Task for grace periods. */
struct swait_queue_head gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
short gp_state; /* GP kthread sleep state. */
/* End of fields guarded by root rcu_node's lock. */
struct mutex barrier_mutex; /* Guards barrier fields. */
atomic_t barrier_cpu_count; /* # CPUs waiting on. */
struct completion barrier_completion; /* Wake at barrier end. */
unsigned long barrier_sequence; /* ++ at start and end of */
/* _rcu_barrier(). */
/* End of fields guarded by barrier_mutex. */
struct mutex exp_mutex; /* Serialize expedited GP. */
struct mutex exp_wake_mutex; /* Serialize wakeup. */
unsigned long expedited_sequence; /* Take a ticket. */
atomic_t expedited_need_qs; /* # CPUs left to check in. */
struct swait_queue_head expedited_wq; /* Wait for check-ins. */
int ncpus_snap; /* # CPUs seen last time. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
unsigned long jiffies_kick_kthreads; /* Time at which to kick */
/* kthreads, if configured. */
unsigned long n_force_qs; /* Number of calls to */
/* force_quiescent_state(). */
unsigned long gp_start; /* Time at which GP started, */
/* but in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
unsigned long gp_req_activity; /* Time of last GP request */
/* in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
unsigned long jiffies_resched; /* Time at which to resched */
/* a reluctant CPU. */
unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */
/* GP start. */
unsigned long gp_max; /* Maximum GP duration in */
/* jiffies. */
const char *name; /* Name of structure. */
char abbr; /* Abbreviated name. */
struct list_head flavors; /* List of RCU flavors. */
spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
/* Synchronize offline with */
/* GP pre-initialization. */
};
/* Values for rcu_state structure's gp_flags field. */
#define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */
#define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */
/* Values for rcu_state structure's gp_state field. */
#define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */
#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */
#define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */
#define RCU_GP_ONOFF 3 /* Grace-period initialization hotplug. */
#define RCU_GP_INIT 4 /* Grace-period initialization. */
#define RCU_GP_WAIT_FQS 5 /* Wait for force-quiescent-state time. */
#define RCU_GP_DOING_FQS 6 /* Wait done for force-quiescent-state time. */
#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */
#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */
#ifndef RCU_TREE_NONCORE
static const char * const gp_state_names[] = {
"RCU_GP_IDLE",
"RCU_GP_WAIT_GPS",
"RCU_GP_DONE_GPS",
"RCU_GP_ONOFF",
"RCU_GP_INIT",
"RCU_GP_WAIT_FQS",
"RCU_GP_DOING_FQS",
"RCU_GP_CLEANUP",
"RCU_GP_CLEANED",
};
#endif /* #ifndef RCU_TREE_NONCORE */
extern struct list_head rcu_struct_flavors;
/* Sequence through rcu_state structures for each RCU flavor. */
#define for_each_rcu_flavor(rsp) \
list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
/*
* RCU implementation internal declarations:
*/
extern struct rcu_state rcu_sched_state;
extern struct rcu_state rcu_bh_state;
#ifdef CONFIG_PREEMPT_RCU
extern struct rcu_state rcu_preempt_state;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DECLARE_PER_CPU(char, rcu_cpu_has_work);
#endif /* #ifdef CONFIG_RCU_BOOST */
#ifndef RCU_TREE_NONCORE
/* Forward declarations for rcutree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_preempt_note_context_switch(bool preempt);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static void rcu_print_detail_task_stall(struct rcu_state *rsp);
static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
struct rcu_node *rnp);
static void rcu_preempt_check_callbacks(void);
void call_rcu(struct rcu_head *head, rcu_callback_t func);
static void __init __rcu_init_preempt(void);
static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static void invoke_rcu_callbacks_kthread(void);
static bool rcu_is_callbacks_kthread(void);
#ifdef CONFIG_RCU_BOOST
static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_BOOST */
static void __init rcu_spawn_boost_kthreads(void);
static void rcu_prepare_kthreads(int cpu);
static void rcu_cleanup_after_idle(void);
static void rcu_prepare_for_idle(void);
static void rcu_idle_count_callbacks_posted(void);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static void print_cpu_stall_info_begin(void);
static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static void increment_cpu_stall_ticks(void);
static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
static void rcu_init_one_nocb(struct rcu_node *rnp);
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
bool lazy, unsigned long flags);
static bool rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
struct rcu_data *rdp,
unsigned long flags);
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_all_nocb_kthreads(int cpu);
static void __init rcu_spawn_nocb_kthreads(void);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
static bool init_nocb_callback_list(struct rcu_data *rdp);
static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
#ifdef CONFIG_SRCU
void srcu_online_cpu(unsigned int cpu);
void srcu_offline_cpu(unsigned int cpu);
#else /* #ifdef CONFIG_SRCU */
void srcu_online_cpu(unsigned int cpu) { }
void srcu_offline_cpu(unsigned int cpu) { }
#endif /* #else #ifdef CONFIG_SRCU */
#endif /* #ifndef RCU_TREE_NONCORE */
+810
View File
@@ -0,0 +1,810 @@
/*
* RCU expedited grace periods
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2016
*
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#include <linux/lockdep.h>
/*
* Record the start of an expedited grace period.
*/
static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
{
rcu_seq_start(&rsp->expedited_sequence);
}
/*
* Return then value that expedited-grace-period counter will have
* at the end of the current grace period.
*/
static __maybe_unused unsigned long rcu_exp_gp_seq_endval(struct rcu_state *rsp)
{
return rcu_seq_endval(&rsp->expedited_sequence);
}
/*
* Record the end of an expedited grace period.
*/
static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
{
rcu_seq_end(&rsp->expedited_sequence);
smp_mb(); /* Ensure that consecutive grace periods serialize. */
}
/*
* Take a snapshot of the expedited-grace-period counter.
*/
static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
{
unsigned long s;
smp_mb(); /* Caller's modifications seen first by other CPUs. */
s = rcu_seq_snap(&rsp->expedited_sequence);
trace_rcu_exp_grace_period(rsp->name, s, TPS("snap"));
return s;
}
/*
* Given a counter snapshot from rcu_exp_gp_seq_snap(), return true
* if a full expedited grace period has elapsed since that snapshot
* was taken.
*/
static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
{
return rcu_seq_done(&rsp->expedited_sequence, s);
}
/*
* Reset the ->expmaskinit values in the rcu_node tree to reflect any
* recent CPU-online activity. Note that these masks are not cleared
* when CPUs go offline, so they reflect the union of all CPUs that have
* ever been online. This means that this function normally takes its
* no-work-to-do fastpath.
*/
static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
{
bool done;
unsigned long flags;
unsigned long mask;
unsigned long oldmask;
int ncpus = smp_load_acquire(&rsp->ncpus); /* Order against locking. */
struct rcu_node *rnp;
struct rcu_node *rnp_up;
/* If no new CPUs onlined since last time, nothing to do. */
if (likely(ncpus == rsp->ncpus_snap))
return;
rsp->ncpus_snap = ncpus;
/*
* Each pass through the following loop propagates newly onlined
* CPUs for the current rcu_node structure up the rcu_node tree.
*/
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->expmaskinit == rnp->expmaskinitnext) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
continue; /* No new CPUs, nothing to do. */
}
/* Update this node's mask, track old value for propagation. */
oldmask = rnp->expmaskinit;
rnp->expmaskinit = rnp->expmaskinitnext;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
/* If was already nonzero, nothing to propagate. */
if (oldmask)
continue;
/* Propagate the new CPU up the tree. */
mask = rnp->grpmask;
rnp_up = rnp->parent;
done = false;
while (rnp_up) {
raw_spin_lock_irqsave_rcu_node(rnp_up, flags);
if (rnp_up->expmaskinit)
done = true;
rnp_up->expmaskinit |= mask;
raw_spin_unlock_irqrestore_rcu_node(rnp_up, flags);
if (done)
break;
mask = rnp_up->grpmask;
rnp_up = rnp_up->parent;
}
}
}
/*
* Reset the ->expmask values in the rcu_node tree in preparation for
* a new expedited grace period.
*/
static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
{
unsigned long flags;
struct rcu_node *rnp;
sync_exp_reset_tree_hotplug(rsp);
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
WARN_ON_ONCE(rnp->expmask);
rnp->expmask = rnp->expmaskinit;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
/*
* Return non-zero if there is no RCU expedited grace period in progress
* for the specified rcu_node structure, in other words, if all CPUs and
* tasks covered by the specified rcu_node structure have done their bit
* for the current expedited grace period. Works only for preemptible
* RCU -- other RCU implementation use other means.
*
* Caller must hold the specificed rcu_node structure's ->lock
*/
static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
raw_lockdep_assert_held_rcu_node(rnp);
return rnp->exp_tasks == NULL &&
READ_ONCE(rnp->expmask) == 0;
}
/*
* Like sync_rcu_preempt_exp_done(), but this function assumes the caller
* doesn't hold the rcu_node's ->lock, and will acquire and release the lock
* itself
*/
static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
{
unsigned long flags;
bool ret;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
ret = sync_rcu_preempt_exp_done(rnp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return ret;
}
/*
* Report the exit from RCU read-side critical section for the last task
* that queued itself during or before the current expedited preemptible-RCU
* grace period. This event is reported either to the rcu_node structure on
* which the task was queued or to one of that rcu_node structure's ancestors,
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
*
* Caller must hold the specified rcu_node structure's ->lock.
*/
static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake, unsigned long flags)
__releases(rnp->lock)
{
unsigned long mask;
for (;;) {
if (!sync_rcu_preempt_exp_done(rnp)) {
if (!rnp->expmask)
rcu_initiate_boost(rnp, flags);
else
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
break;
}
if (rnp->parent == NULL) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (wake) {
smp_mb(); /* EGP done before wake_up(). */
swake_up_one(&rsp->expedited_wq);
}
break;
}
mask = rnp->grpmask;
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled */
rnp = rnp->parent;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
WARN_ON_ONCE(!(rnp->expmask & mask));
rnp->expmask &= ~mask;
}
}
/*
* Report expedited quiescent state for specified node. This is a
* lock-acquisition wrapper function for __rcu_report_exp_rnp().
*/
static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
struct rcu_node *rnp, bool wake)
{
unsigned long flags;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
__rcu_report_exp_rnp(rsp, rnp, wake, flags);
}
/*
* Report expedited quiescent state for multiple CPUs, all covered by the
* specified leaf rcu_node structure.
*/
static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
unsigned long mask, bool wake)
{
unsigned long flags;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (!(rnp->expmask & mask)) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
rnp->expmask &= ~mask;
__rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */
}
/*
* Report expedited quiescent state for specified rcu_data (CPU).
*/
static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
bool wake)
{
rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake);
}
/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s)
{
if (rcu_exp_gp_seq_done(rsp, s)) {
trace_rcu_exp_grace_period(rsp->name, s, TPS("done"));
/* Ensure test happens before caller kfree(). */
smp_mb__before_atomic(); /* ^^^ */
return true;
}
return false;
}
/*
* Funnel-lock acquisition for expedited grace periods. Returns true
* if some other task completed an expedited grace period that this task
* can piggy-back on, and with no mutex held. Otherwise, returns false
* with the mutex held, indicating that the caller must actually do the
* expedited grace period.
*/
static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
{
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
struct rcu_node *rnp = rdp->mynode;
struct rcu_node *rnp_root = rcu_get_root(rsp);
/* Low-contention fastpath. */
if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) &&
(rnp == rnp_root ||
ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) &&
mutex_trylock(&rsp->exp_mutex))
goto fastpath;
/*
* Each pass through the following loop works its way up
* the rcu_node tree, returning if others have done the work or
* otherwise falls through to acquire rsp->exp_mutex. The mapping
* from CPU to rcu_node structure can be inexact, as it is just
* promoting locality and is not strictly needed for correctness.
*/
for (; rnp != NULL; rnp = rnp->parent) {
if (sync_exp_work_done(rsp, s))
return true;
/* Work not done, either wait here or go up. */
spin_lock(&rnp->exp_lock);
if (ULONG_CMP_GE(rnp->exp_seq_rq, s)) {
/* Someone else doing GP, so wait for them. */
spin_unlock(&rnp->exp_lock);
trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
rnp->grplo, rnp->grphi,
TPS("wait"));
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(rsp, s));
return true;
}
rnp->exp_seq_rq = s; /* Followers can wait on us. */
spin_unlock(&rnp->exp_lock);
trace_rcu_exp_funnel_lock(rsp->name, rnp->level, rnp->grplo,
rnp->grphi, TPS("nxtlvl"));
}
mutex_lock(&rsp->exp_mutex);
fastpath:
if (sync_exp_work_done(rsp, s)) {
mutex_unlock(&rsp->exp_mutex);
return true;
}
rcu_exp_gp_seq_start(rsp);
trace_rcu_exp_grace_period(rsp->name, s, TPS("start"));
return false;
}
/* Invoked on each online non-idle CPU for expedited quiescent state. */
static void sync_sched_exp_handler(void *data)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
struct rcu_state *rsp = data;
rdp = this_cpu_ptr(rsp->rda);
rnp = rdp->mynode;
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
return;
if (rcu_is_cpu_rrupt_from_idle()) {
rcu_report_exp_rdp(&rcu_sched_state,
this_cpu_ptr(&rcu_sched_data), true);
return;
}
__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
/* Store .exp before .rcu_urgent_qs. */
smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
resched_cpu(smp_processor_id());
}
/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */
static void sync_sched_exp_online_cleanup(int cpu)
{
struct rcu_data *rdp;
int ret;
struct rcu_node *rnp;
struct rcu_state *rsp = &rcu_sched_state;
rdp = per_cpu_ptr(rsp->rda, cpu);
rnp = rdp->mynode;
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
return;
ret = smp_call_function_single(cpu, sync_sched_exp_handler, rsp, 0);
WARN_ON_ONCE(ret);
}
/*
* Select the CPUs within the specified rcu_node that the upcoming
* expedited grace period needs to wait for.
*/
static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
{
int cpu;
unsigned long flags;
smp_call_func_t func;
unsigned long mask_ofl_test;
unsigned long mask_ofl_ipi;
int ret;
struct rcu_exp_work *rewp =
container_of(wp, struct rcu_exp_work, rew_work);
struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
struct rcu_state *rsp = rewp->rew_rsp;
func = rewp->rew_func;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
/* Each pass checks a CPU for identity, offline, and idle. */
mask_ofl_test = 0;
for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
int snap;
if (raw_smp_processor_id() == cpu ||
!(rnp->qsmaskinitnext & mask)) {
mask_ofl_test |= mask;
} else {
snap = rcu_dynticks_snap(rdtp);
if (rcu_dynticks_in_eqs(snap))
mask_ofl_test |= mask;
else
rdp->exp_dynticks_snap = snap;
}
}
mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
/*
* Need to wait for any blocked tasks as well. Note that
* additional blocking tasks will also block the expedited GP
* until such time as the ->expmask bits are cleared.
*/
if (rcu_preempt_has_tasks(rnp))
rnp->exp_tasks = rnp->blkd_tasks.next;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
/* IPI the remaining CPUs for expedited quiescent state. */
for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
if (!(mask_ofl_ipi & mask))
continue;
retry_ipi:
if (rcu_dynticks_in_eqs_since(rdp->dynticks,
rdp->exp_dynticks_snap)) {
mask_ofl_test |= mask;
continue;
}
ret = smp_call_function_single(cpu, func, rsp, 0);
if (!ret) {
mask_ofl_ipi &= ~mask;
continue;
}
/* Failed, raced with CPU hotplug operation. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if ((rnp->qsmaskinitnext & mask) &&
(rnp->expmask & mask)) {
/* Online, so delay for a bit and try again. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
schedule_timeout_uninterruptible(1);
goto retry_ipi;
}
/* CPU really is offline, so we can ignore it. */
if (!(rnp->expmask & mask))
mask_ofl_ipi &= ~mask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/* Report quiescent states for those that went offline. */
mask_ofl_test |= mask_ofl_ipi;
if (mask_ofl_test)
rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
}
/*
* Select the nodes that the upcoming expedited grace period needs
* to wait for.
*/
static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
smp_call_func_t func)
{
int cpu;
struct rcu_node *rnp;
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
sync_exp_reset_tree(rsp);
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
/* Schedule work for each leaf rcu_node structure. */
rcu_for_each_leaf_node(rsp, rnp) {
rnp->exp_need_flush = false;
if (!READ_ONCE(rnp->expmask))
continue; /* Avoid early boot non-existent wq. */
rnp->rew.rew_func = func;
rnp->rew.rew_rsp = rsp;
if (!READ_ONCE(rcu_par_gp_wq) ||
rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
rcu_is_last_leaf_node(rsp, rnp)) {
/* No workqueues yet or last leaf, do direct call. */
sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
continue;
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
preempt_disable();
cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
/* If all offline, queue the work on an unbound CPU. */
if (unlikely(cpu > rnp->grphi))
cpu = WORK_CPU_UNBOUND;
queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
preempt_enable();
rnp->exp_need_flush = true;
}
/* Wait for workqueue jobs (if any) to complete. */
rcu_for_each_leaf_node(rsp, rnp)
if (rnp->exp_need_flush)
flush_work(&rnp->rew.rew_work);
}
static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
{
int cpu;
unsigned long jiffies_stall;
unsigned long jiffies_start;
unsigned long mask;
int ndetected;
struct rcu_node *rnp;
struct rcu_node *rnp_root = rcu_get_root(rsp);
int ret;
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("startwait"));
jiffies_stall = rcu_jiffies_till_stall_check();
jiffies_start = jiffies;
for (;;) {
ret = swait_event_timeout_exclusive(
rsp->expedited_wq,
sync_rcu_preempt_exp_done_unlocked(rnp_root),
jiffies_stall);
if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root))
return;
WARN_ON(ret < 0); /* workqueues should not be signaled. */
if (rcu_cpu_stall_suppress)
continue;
panic_on_rcu_stall();
pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
rsp->name);
ndetected = 0;
rcu_for_each_leaf_node(rsp, rnp) {
ndetected += rcu_print_task_exp_stall(rnp);
for_each_leaf_node_possible_cpu(rnp, cpu) {
struct rcu_data *rdp;
mask = leaf_node_cpu_bit(rnp, cpu);
if (!(rnp->expmask & mask))
continue;
ndetected++;
rdp = per_cpu_ptr(rsp->rda, cpu);
pr_cont(" %d-%c%c%c", cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rnp->expmaskinit)],
"N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
}
}
pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
jiffies - jiffies_start, rsp->expedited_sequence,
rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
if (ndetected) {
pr_err("blocking rcu_node structures:");
rcu_for_each_node_breadth_first(rsp, rnp) {
if (rnp == rnp_root)
continue; /* printed unconditionally */
if (sync_rcu_preempt_exp_done_unlocked(rnp))
continue;
pr_cont(" l=%u:%d-%d:%#lx/%c",
rnp->level, rnp->grplo, rnp->grphi,
rnp->expmask,
".T"[!!rnp->exp_tasks]);
}
pr_cont("\n");
}
rcu_for_each_leaf_node(rsp, rnp) {
for_each_leaf_node_possible_cpu(rnp, cpu) {
mask = leaf_node_cpu_bit(rnp, cpu);
if (!(rnp->expmask & mask))
continue;
dump_cpu_task(cpu);
}
}
jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
}
}
/*
* Wait for the current expedited grace period to complete, and then
* wake up everyone who piggybacked on the just-completed expedited
* grace period. Also update all the ->exp_seq_rq counters as needed
* in order to avoid counter-wrap problems.
*/
static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
{
struct rcu_node *rnp;
synchronize_sched_expedited_wait(rsp);
// Switch over to wakeup mode, allowing the next GP to proceed.
// End the previous grace period only after acquiring the mutex
// to ensure that only one GP runs concurrently with wakeups.
mutex_lock(&rsp->exp_wake_mutex);
rcu_exp_gp_seq_end(rsp);
trace_rcu_exp_grace_period(rsp->name, s, TPS("end"));
rcu_for_each_node_breadth_first(rsp, rnp) {
if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) {
spin_lock(&rnp->exp_lock);
/* Recheck, avoid hang in case someone just arrived. */
if (ULONG_CMP_LT(rnp->exp_seq_rq, s))
rnp->exp_seq_rq = s;
spin_unlock(&rnp->exp_lock);
}
smp_mb(); /* All above changes before wakeup. */
wake_up_all(&rnp->exp_wq[rcu_seq_ctr(s) & 0x3]);
}
trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
mutex_unlock(&rsp->exp_wake_mutex);
}
/*
* Common code to drive an expedited grace period forward, used by
* workqueues and mid-boot-time tasks.
*/
static void rcu_exp_sel_wait_wake(struct rcu_state *rsp,
smp_call_func_t func, unsigned long s)
{
/* Initialize the rcu_node tree in preparation for the wait. */
sync_rcu_exp_select_cpus(rsp, func);
/* Wait and clean up, including waking everyone. */
rcu_exp_wait_wake(rsp, s);
}
/*
* Work-queue handler to drive an expedited grace period forward.
*/
static void wait_rcu_exp_gp(struct work_struct *wp)
{
struct rcu_exp_work *rewp;
rewp = container_of(wp, struct rcu_exp_work, rew_work);
rcu_exp_sel_wait_wake(rewp->rew_rsp, rewp->rew_func, rewp->rew_s);
}
/*
* Given an rcu_state pointer and a smp_call_function() handler, kick
* off the specified flavor of expedited grace period.
*/
static void _synchronize_rcu_expedited(struct rcu_state *rsp,
smp_call_func_t func)
{
struct rcu_data *rdp;
struct rcu_exp_work rew;
struct rcu_node *rnp;
unsigned long s;
/* If expedited grace periods are prohibited, fall back to normal. */
if (rcu_gp_is_normal()) {
wait_rcu_gp(rsp->call);
return;
}
/* Take a snapshot of the sequence number. */
s = rcu_exp_gp_seq_snap(rsp);
if (exp_funnel_lock(rsp, s))
return; /* Someone else did our work for us. */
/* Ensure that load happens before action based on it. */
if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
/* Direct call during scheduler init and early_initcalls(). */
rcu_exp_sel_wait_wake(rsp, func, s);
} else {
/* Marshall arguments & schedule the expedited grace period. */
rew.rew_func = func;
rew.rew_rsp = rsp;
rew.rew_s = s;
INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
queue_work(rcu_gp_wq, &rew.rew_work);
}
/* Wait for expedited grace period to complete. */
rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
rnp = rcu_get_root(rsp);
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(rsp, s));
smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
mutex_unlock(&rsp->exp_mutex);
}
/**
* synchronize_sched_expedited - Brute-force RCU-sched grace period
*
* Wait for an RCU-sched grace period to elapse, but use a "big hammer"
* approach to force the grace period to end quickly. This consumes
* significant time on all CPUs and is unfriendly to real-time workloads,
* so is thus not recommended for any sort of common-case code. In fact,
* if you are using synchronize_sched_expedited() in a loop, please
* restructure your code to batch your updates, and then use a single
* synchronize_sched() instead.
*
* This implementation can be thought of as an application of sequence
* locking to expedited grace periods, but using the sequence counter to
* determine when someone else has already done the work instead of for
* retrying readers.
*/
void synchronize_sched_expedited(void)
{
struct rcu_state *rsp = &rcu_sched_state;
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_sched_expedited() in RCU read-side critical section");
/* If only one CPU, this is automatically a grace period. */
if (rcu_blocking_is_gp())
return;
_synchronize_rcu_expedited(rsp, sync_sched_exp_handler);
}
EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
#ifdef CONFIG_PREEMPT_RCU
/*
* Remote handler for smp_call_function_single(). If there is an
* RCU read-side critical section in effect, request that the
* next rcu_read_unlock() record the quiescent state up the
* ->expmask fields in the rcu_node tree. Otherwise, immediately
* report the quiescent state.
*/
static void sync_rcu_exp_handler(void *info)
{
struct rcu_data *rdp;
struct rcu_state *rsp = info;
struct task_struct *t = current;
/*
* Within an RCU read-side critical section, request that the next
* rcu_read_unlock() report. Unless this RCU read-side critical
* section has already blocked, in which case it is already set
* up for the expedited grace period to wait on it.
*/
if (t->rcu_read_lock_nesting > 0 &&
!t->rcu_read_unlock_special.b.blocked) {
t->rcu_read_unlock_special.b.exp_need_qs = true;
return;
}
/*
* We are either exiting an RCU read-side critical section (negative
* values of t->rcu_read_lock_nesting) or are not in one at all
* (zero value of t->rcu_read_lock_nesting). Or we are in an RCU
* read-side critical section that blocked before this expedited
* grace period started. Either way, we can immediately report
* the quiescent state.
*/
rdp = this_cpu_ptr(rsp->rda);
rcu_report_exp_rdp(rsp, rdp, true);
}
/**
* synchronize_rcu_expedited - Brute-force RCU grace period
*
* Wait for an RCU-preempt grace period, but expedite it. The basic
* idea is to IPI all non-idle non-nohz online CPUs. The IPI handler
* checks whether the CPU is in an RCU-preempt critical section, and
* if so, it sets a flag that causes the outermost rcu_read_unlock()
* to report the quiescent state. On the other hand, if the CPU is
* not in an RCU read-side critical section, the IPI handler reports
* the quiescent state immediately.
*
* Although this is a greate improvement over previous expedited
* implementations, it is still unfriendly to real-time workloads, so is
* thus not recommended for any sort of common-case code. In fact, if
* you are using synchronize_rcu_expedited() in a loop, please restructure
* your code to batch your updates, and then Use a single synchronize_rcu()
* instead.
*/
void synchronize_rcu_expedited(void)
{
struct rcu_state *rsp = rcu_state_p;
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu_expedited() in RCU read-side critical section");
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return;
_synchronize_rcu_expedited(rsp, sync_rcu_exp_handler);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#else /* #ifdef CONFIG_PREEMPT_RCU */
/*
* Wait for an rcu-preempt grace period, but make it happen quickly.
* But because preemptible RCU does not exist, map to rcu-sched.
*/
void synchronize_rcu_expedited(void)
{
synchronize_sched_expedited();
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
File diff suppressed because it is too large. Load diff
+977
View File
@@ -0,0 +1,977 @@
/*
* Read-Copy Update mechanism for mutual exclusion
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2001
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
*
* Based on the original work by Paul McKenney <paulmck@us.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
* Papers:
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
* http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
*
* For detailed explanation of Read-Copy Update mechanism see -
* http://lse.sourceforge.net/locking/rcupdate.html
*
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/export.h>
#include <linux/hardirq.h>
#include <linux/delay.h>
#include <linux/moduleparam.h>
#include <linux/kthread.h>
#include <linux/tick.h>
#include <linux/rcupdate_wait.h>
#include <linux/sched/isolation.h>
#include <linux/kprobes.h>
#define CREATE_TRACE_POINTS
#include "rcu.h"
#ifdef MODULE_PARAM_PREFIX
#undef MODULE_PARAM_PREFIX
#endif
#define MODULE_PARAM_PREFIX "rcupdate."
#ifndef CONFIG_TINY_RCU
extern int rcu_expedited; /* from sysctl */
module_param(rcu_expedited, int, 0);
extern int rcu_normal; /* from sysctl */
module_param(rcu_normal, int, 0);
static int rcu_normal_after_boot;
module_param(rcu_normal_after_boot, int, 0);
#endif /* #ifndef CONFIG_TINY_RCU */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
* rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
*
* If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
* RCU-sched read-side critical section. In absence of
* CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
* critical section unless it can prove otherwise. Note that disabling
* of preemption (including disabling irqs) counts as an RCU-sched
* read-side critical section. This is useful for debug checks in functions
* that required that they be called within an RCU-sched read-side
* critical section.
*
* Check debug_lockdep_rcu_enabled() to prevent false positives during boot
* and while lockdep is disabled.
*
* Note that if the CPU is in the idle loop from an RCU point of
* view (ie: that we are in the section between rcu_idle_enter() and
* rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
* did an rcu_read_lock(). The reason for this is that RCU ignores CPUs
* that are in such a section, considering these as in extended quiescent
* state, so such a CPU is effectively never in an RCU read-side critical
* section regardless of what RCU primitives it invokes. This state of
* affairs is required --- we need to keep an RCU-free window in idle
* where the CPU may possibly enter into low power mode. This way we can
* notice an extended quiescent state to other CPUs that started a grace
* period. Otherwise we would delay any grace period as long as we run in
* the idle task.
*
* Similarly, we avoid claiming an SRCU read lock held if the current
* CPU is offline.
*/
int rcu_read_lock_sched_held(void)
{
int lockdep_opinion = 0;
if (!debug_lockdep_rcu_enabled())
return 1;
if (!rcu_is_watching())
return 0;
if (!rcu_lockdep_current_cpu_online())
return 0;
if (debug_locks)
lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
return lockdep_opinion || !preemptible();
}
EXPORT_SYMBOL(rcu_read_lock_sched_held);
#endif
#ifndef CONFIG_TINY_RCU
/*
* Should expedited grace-period primitives always fall back to their
* non-expedited counterparts? Intended for use within RCU. Note
* that if the user specifies both rcu_expedited and rcu_normal, then
* rcu_normal wins. (Except during the time period during boot from
* when the first task is spawned until the rcu_set_runtime_mode()
* core_initcall() is invoked, at which point everything is expedited.)
*/
bool rcu_gp_is_normal(void)
{
return READ_ONCE(rcu_normal) &&
rcu_scheduler_active != RCU_SCHEDULER_INIT;
}
EXPORT_SYMBOL_GPL(rcu_gp_is_normal);
static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1);
/*
* Should normal grace-period primitives be expedited? Intended for
* use within RCU. Note that this function takes the rcu_expedited
* sysfs/boot variable and rcu_scheduler_active into account as well
* as the rcu_expedite_gp() nesting. So looping on rcu_unexpedite_gp()
* until rcu_gp_is_expedited() returns false is a -really- bad idea.
*/
bool rcu_gp_is_expedited(void)
{
return rcu_expedited || atomic_read(&rcu_expedited_nesting) ||
rcu_scheduler_active == RCU_SCHEDULER_INIT;
}
EXPORT_SYMBOL_GPL(rcu_gp_is_expedited);
/**
* rcu_expedite_gp - Expedite future RCU grace periods
*
* After a call to this function, future calls to synchronize_rcu() and
* friends act as the corresponding synchronize_rcu_expedited() function
* had instead been called.
*/
void rcu_expedite_gp(void)
{
atomic_inc(&rcu_expedited_nesting);
}
EXPORT_SYMBOL_GPL(rcu_expedite_gp);
/**
* rcu_unexpedite_gp - Cancel prior rcu_expedite_gp() invocation
*
* Undo a prior call to rcu_expedite_gp(). If all prior calls to
* rcu_expedite_gp() are undone by a subsequent call to rcu_unexpedite_gp(),
* and if the rcu_expedited sysfs/boot parameter is not set, then all
* subsequent calls to synchronize_rcu() and friends will return to
* their normal non-expedited behavior.
*/
void rcu_unexpedite_gp(void)
{
atomic_dec(&rcu_expedited_nesting);
}
EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
/*
* Inform RCU of the end of the in-kernel boot sequence.
*/
void rcu_end_inkernel_boot(void)
{
rcu_unexpedite_gp();
if (rcu_normal_after_boot)
WRITE_ONCE(rcu_normal, 1);
}
#endif /* #ifndef CONFIG_TINY_RCU */
/*
* Test each non-SRCU synchronous grace-period wait API. This is
* useful just after a change in mode for these primitives, and
* during early boot.
*/
void rcu_test_sync_prims(void)
{
if (!IS_ENABLED(CONFIG_PROVE_RCU))
return;
synchronize_rcu();
synchronize_rcu_bh();
synchronize_sched();
synchronize_rcu_expedited();
synchronize_rcu_bh_expedited();
synchronize_sched_expedited();
}
#if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU)
/*
* Switch to run-time mode once RCU has fully initialized.
*/
static int __init rcu_set_runtime_mode(void)
{
rcu_test_sync_prims();
rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
rcu_test_sync_prims();
return 0;
}
core_initcall(rcu_set_runtime_mode);
#endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
struct lockdep_map rcu_lock_map =
STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
EXPORT_SYMBOL_GPL(rcu_lock_map);
static struct lock_class_key rcu_bh_lock_key;
struct lockdep_map rcu_bh_lock_map =
STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);
EXPORT_SYMBOL_GPL(rcu_bh_lock_map);
static struct lock_class_key rcu_sched_lock_key;
struct lockdep_map rcu_sched_lock_map =
STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
static struct lock_class_key rcu_callback_key;
struct lockdep_map rcu_callback_map =
STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
EXPORT_SYMBOL_GPL(rcu_callback_map);
int notrace debug_lockdep_rcu_enabled(void)
{
return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks &&
current->lockdep_recursion == 0;
}
EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
/**
* rcu_read_lock_held() - might we be in RCU read-side critical section?
*
* If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
* read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
* this assumes we are in an RCU read-side critical section unless it can
* prove otherwise. This is useful for debug checks in functions that
* require that they be called within an RCU read-side critical section.
*
* Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
* and while lockdep is disabled.
*
* Note that rcu_read_lock() and the matching rcu_read_unlock() must
* occur in the same context, for example, it is illegal to invoke
* rcu_read_unlock() in process context if the matching rcu_read_lock()
* was invoked from within an irq handler.
*
* Note that rcu_read_lock() is disallowed if the CPU is either idle or
* offline from an RCU perspective, so check for those as well.
*/
int rcu_read_lock_held(void)
{
if (!debug_lockdep_rcu_enabled())
return 1;
if (!rcu_is_watching())
return 0;
if (!rcu_lockdep_current_cpu_online())
return 0;
return lock_is_held(&rcu_lock_map);
}
EXPORT_SYMBOL_GPL(rcu_read_lock_held);
/**
* rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
*
* Check for bottom half being disabled, which covers both the
* CONFIG_PROVE_RCU and not cases. Note that if someone uses
* rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled)
* will show the situation. This is useful for debug checks in functions
* that require that they be called within an RCU read-side critical
* section.
*
* Check debug_lockdep_rcu_enabled() to prevent false positives during boot.
*
* Note that rcu_read_lock() is disallowed if the CPU is either idle or
* offline from an RCU perspective, so check for those as well.
*/
int rcu_read_lock_bh_held(void)
{
if (!debug_lockdep_rcu_enabled())
return 1;
if (!rcu_is_watching())
return 0;
if (!rcu_lockdep_current_cpu_online())
return 0;
return in_softirq() || irqs_disabled();
}
EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/**
* wakeme_after_rcu() - Callback function to awaken a task after grace period
* @head: Pointer to rcu_head member within rcu_synchronize structure
*
* Awaken the corresponding task now that a grace period has elapsed.
*/
void wakeme_after_rcu(struct rcu_head *head)
{
struct rcu_synchronize *rcu;
rcu = container_of(head, struct rcu_synchronize, head);
complete(&rcu->completion);
}
EXPORT_SYMBOL_GPL(wakeme_after_rcu);
void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
struct rcu_synchronize *rs_array)
{
int i;
int j;
/* Initialize and register callbacks for each flavor specified. */
for (i = 0; i < n; i++) {
if (checktiny &&
(crcu_array[i] == call_rcu ||
crcu_array[i] == call_rcu_bh)) {
might_sleep();
continue;
}
init_rcu_head_on_stack(&rs_array[i].head);
init_completion(&rs_array[i].completion);
for (j = 0; j < i; j++)
if (crcu_array[j] == crcu_array[i])
break;
if (j == i)
(crcu_array[i])(&rs_array[i].head, wakeme_after_rcu);
}
/* Wait for all callbacks to be invoked. */
for (i = 0; i < n; i++) {
if (checktiny &&
(crcu_array[i] == call_rcu ||
crcu_array[i] == call_rcu_bh))
continue;
for (j = 0; j < i; j++)
if (crcu_array[j] == crcu_array[i])
break;
if (j == i)
wait_for_completion(&rs_array[i].completion);
destroy_rcu_head_on_stack(&rs_array[i].head);
}
}
EXPORT_SYMBOL_GPL(__wait_rcu_gp);
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
void init_rcu_head(struct rcu_head *head)
{
debug_object_init(head, &rcuhead_debug_descr);
}
EXPORT_SYMBOL_GPL(init_rcu_head);
void destroy_rcu_head(struct rcu_head *head)
{
debug_object_free(head, &rcuhead_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_rcu_head);
static bool rcuhead_is_static_object(void *addr)
{
return true;
}
/**
* init_rcu_head_on_stack() - initialize on-stack rcu_head for debugobjects
* @head: pointer to rcu_head structure to be initialized
*
* This function informs debugobjects of a new rcu_head structure that
* has been allocated as an auto variable on the stack. This function
* is not required for rcu_head structures that are statically defined or
* that are dynamically allocated on the heap. This function has no
* effect for !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds.
*/
void init_rcu_head_on_stack(struct rcu_head *head)
{
debug_object_init_on_stack(head, &rcuhead_debug_descr);
}
EXPORT_SYMBOL_GPL(init_rcu_head_on_stack);
/**
* destroy_rcu_head_on_stack() - destroy on-stack rcu_head for debugobjects
* @head: pointer to rcu_head structure to be initialized
*
* This function informs debugobjects that an on-stack rcu_head structure
* is about to go out of scope. As with init_rcu_head_on_stack(), this
* function is not required for rcu_head structures that are statically
* defined or that are dynamically allocated on the heap. Also as with
* init_rcu_head_on_stack(), this function has no effect for
* !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds.
*/
void destroy_rcu_head_on_stack(struct rcu_head *head)
{
debug_object_free(head, &rcuhead_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
struct debug_obj_descr rcuhead_debug_descr = {
.name = "rcu_head",
.is_static_object = rcuhead_is_static_object,
};
EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
unsigned long secs,
unsigned long c_old, unsigned long c)
{
trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c);
}
EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
#else
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
do { } while (0)
#endif
#ifdef CONFIG_RCU_STALL_COMMON
#ifdef CONFIG_PROVE_RCU
#define RCU_STALL_DELAY_DELTA (5 * HZ)
#else
#define RCU_STALL_DELAY_DELTA 0
#endif
int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
module_param(rcu_cpu_stall_suppress, int, 0644);
module_param(rcu_cpu_stall_timeout, int, 0644);
int rcu_jiffies_till_stall_check(void)
{
int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
/*
* Limit check must be consistent with the Kconfig limits
* for CONFIG_RCU_CPU_STALL_TIMEOUT.
*/
if (till_stall_check < 3) {
WRITE_ONCE(rcu_cpu_stall_timeout, 3);
till_stall_check = 3;
} else if (till_stall_check > 300) {
WRITE_ONCE(rcu_cpu_stall_timeout, 300);
till_stall_check = 300;
}
return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
}
void rcu_sysrq_start(void)
{
if (!rcu_cpu_stall_suppress)
rcu_cpu_stall_suppress = 2;
}
void rcu_sysrq_end(void)
{
if (rcu_cpu_stall_suppress == 2)
rcu_cpu_stall_suppress = 0;
}
static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
{
rcu_cpu_stall_suppress = 1;
return NOTIFY_DONE;
}
static struct notifier_block rcu_panic_block = {
.notifier_call = rcu_panic,
};
static int __init check_cpu_stall_init(void)
{
atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
return 0;
}
early_initcall(check_cpu_stall_init);
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
#ifdef CONFIG_TASKS_RCU
/*
* Simple variant of RCU whose quiescent states are voluntary context
* switch, cond_resched_rcu_qs(), user-space execution, and idle.
* As such, grace periods can take one good long time. There are no
* read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
* because this implementation is intended to get the system into a safe
* state for some of the manipulations involved in tracing and the like.
* Finally, this implementation does not support high call_rcu_tasks()
* rates from multiple CPUs. If this is required, per-CPU callback lists
* will be needed.
*/
/* Global list of callbacks and associated lock. */
static struct rcu_head *rcu_tasks_cbs_head;
static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
/* Track exiting tasks in order to allow them to be waited for. */
DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */
#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
module_param(rcu_task_stall_timeout, int, 0644);
static struct task_struct *rcu_tasks_kthread_ptr;
/**
* call_rcu_tasks() - Queue an RCU for invocation task-based grace period
* @rhp: structure to be used for queueing the RCU updates.
* @func: actual callback function to be invoked after the grace period
*
* The callback function will be invoked some time after a full grace
* period elapses, in other words after all currently executing RCU
* read-side critical sections have completed. call_rcu_tasks() assumes
* that the read-side critical sections end at a voluntary context
* switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
* or transition to usermode execution. As such, there are no read-side
* primitives analogous to rcu_read_lock() and rcu_read_unlock() because
* this primitive is intended to determine that all tasks have passed
* through a safe state, not so much for data-strcuture synchronization.
*
* See the description of call_rcu() for more detailed information on
* memory ordering guarantees.
*/
void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
{
unsigned long flags;
bool needwake;
rhp->next = NULL;
rhp->func = func;
raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
needwake = !rcu_tasks_cbs_head;
*rcu_tasks_cbs_tail = rhp;
rcu_tasks_cbs_tail = &rhp->next;
raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
/* We can't create the thread unless interrupts are enabled. */
if (needwake && READ_ONCE(rcu_tasks_kthread_ptr))
wake_up(&rcu_tasks_cbs_wq);
}
EXPORT_SYMBOL_GPL(call_rcu_tasks);
/**
* synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
*
* Control will return to the caller some time after a full rcu-tasks
* grace period has elapsed, in other words after all currently
* executing rcu-tasks read-side critical sections have elapsed. These
* read-side critical sections are delimited by calls to schedule(),
* cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
* to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
*
* This is a very specialized primitive, intended only for a few uses in
* tracing and other situations requiring manipulation of function
* preambles and profiling hooks. The synchronize_rcu_tasks() function
* is not (yet) intended for heavy use from multiple CPUs.
*
* Note that this guarantee implies further memory-ordering guarantees.
* On systems with more than one CPU, when synchronize_rcu_tasks() returns,
* each CPU is guaranteed to have executed a full memory barrier since the
* end of its last RCU-tasks read-side critical section whose beginning
* preceded the call to synchronize_rcu_tasks(). In addition, each CPU
* having an RCU-tasks read-side critical section that extends beyond
* the return from synchronize_rcu_tasks() is guaranteed to have executed
* a full memory barrier after the beginning of synchronize_rcu_tasks()
* and before the beginning of that RCU-tasks 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_tasks(), 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_tasks() -- 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_tasks(void)
{
/* Complain if the scheduler has not started. */
RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
"synchronize_rcu_tasks called too soon");
/* Wait for the grace period. */
wait_rcu_gp(call_rcu_tasks);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
/**
* rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
*
* Although the current implementation is guaranteed to wait, it is not
* obligated to, for example, if there are no pending callbacks.
*/
void rcu_barrier_tasks(void)
{
/* There is only one callback queue, so this is easy. ;-) */
synchronize_rcu_tasks();
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
/* See if tasks are still holding out, complain if so. */
static void check_holdout_task(struct task_struct *t,
bool needreport, bool *firstreport)
{
int cpu;
if (!READ_ONCE(t->rcu_tasks_holdout) ||
t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
!READ_ONCE(t->on_rq) ||
(IS_ENABLED(CONFIG_NO_HZ_FULL) &&
!is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
WRITE_ONCE(t->rcu_tasks_holdout, false);
list_del_init(&t->rcu_tasks_holdout_list);
put_task_struct(t);
return;
}
rcu_request_urgent_qs_task(t);
if (!needreport)
return;
if (*firstreport) {
pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
*firstreport = false;
}
cpu = task_cpu(t);
pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
t, ".I"[is_idle_task(t)],
"N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
t->rcu_tasks_idle_cpu, cpu);
sched_show_task(t);
}
/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
static int __noreturn rcu_tasks_kthread(void *arg)
{
unsigned long flags;
struct task_struct *g, *t;
unsigned long lastreport;
struct rcu_head *list;
struct rcu_head *next;
LIST_HEAD(rcu_tasks_holdouts);
int fract;
/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
housekeeping_affine(current, HK_FLAG_RCU);
/*
* Each pass through the following loop makes one check for
* newly arrived callbacks, and, if there are some, waits for
* one RCU-tasks grace period and then invokes the callbacks.
* This loop is terminated by the system going down. ;-)
*/
for (;;) {
/* Pick up any new callbacks. */
raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
list = rcu_tasks_cbs_head;
rcu_tasks_cbs_head = NULL;
rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
/* If there were none, wait a bit and start over. */
if (!list) {
wait_event_interruptible(rcu_tasks_cbs_wq,
rcu_tasks_cbs_head);
if (!rcu_tasks_cbs_head) {
WARN_ON(signal_pending(current));
schedule_timeout_interruptible(HZ/10);
}
continue;
}
/*
* Wait for all pre-existing t->on_rq and t->nvcsw
* transitions to complete. Invoking synchronize_sched()
* suffices because all these transitions occur with
* interrupts disabled. Without this synchronize_sched(),
* a read-side critical section that started before the
* grace period might be incorrectly seen as having started
* after the grace period.
*
* This synchronize_sched() also dispenses with the
* need for a memory barrier on the first store to
* ->rcu_tasks_holdout, as it forces the store to happen
* after the beginning of the grace period.
*/
synchronize_sched();
/*
* There were callbacks, so we need to wait for an
* RCU-tasks grace period. Start off by scanning
* the task list for tasks that are not already
* voluntarily blocked. Mark these tasks and make
* a list of them in rcu_tasks_holdouts.
*/
rcu_read_lock();
for_each_process_thread(g, t) {
if (t != current && READ_ONCE(t->on_rq) &&
!is_idle_task(t)) {
get_task_struct(t);
t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
WRITE_ONCE(t->rcu_tasks_holdout, true);
list_add(&t->rcu_tasks_holdout_list,
&rcu_tasks_holdouts);
}
}
rcu_read_unlock();
/*
* Wait for tasks that are in the process of exiting.
* This does only part of the job, ensuring that all
* tasks that were previously exiting reach the point
* where they have disabled preemption, allowing the
* later synchronize_sched() to finish the job.
*/
synchronize_srcu(&tasks_rcu_exit_srcu);
/*
* Each pass through the following loop scans the list
* of holdout tasks, removing any that are no longer
* holdouts. When the list is empty, we are done.
*/
lastreport = jiffies;
/* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
fract = 10;
for (;;) {
bool firstreport;
bool needreport;
int rtst;
struct task_struct *t1;
if (list_empty(&rcu_tasks_holdouts))
break;
/* Slowly back off waiting for holdouts */
schedule_timeout_interruptible(HZ/fract);
if (fract > 1)
fract--;
rtst = READ_ONCE(rcu_task_stall_timeout);
needreport = rtst > 0 &&
time_after(jiffies, lastreport + rtst);
if (needreport)
lastreport = jiffies;
firstreport = true;
WARN_ON(signal_pending(current));
list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
rcu_tasks_holdout_list) {
check_holdout_task(t, needreport, &firstreport);
cond_resched();
}
}
/*
* Because ->on_rq and ->nvcsw are not guaranteed
* to have a full memory barriers prior to them in the
* schedule() path, memory reordering on other CPUs could
* cause their RCU-tasks read-side critical sections to
* extend past the end of the grace period. However,
* because these ->nvcsw updates are carried out with
* interrupts disabled, we can use synchronize_sched()
* to force the needed ordering on all such CPUs.
*
* This synchronize_sched() also confines all
* ->rcu_tasks_holdout accesses to be within the grace
* period, avoiding the need for memory barriers for
* ->rcu_tasks_holdout accesses.
*
* In addition, this synchronize_sched() waits for exiting
* tasks to complete their final preempt_disable() region
* of execution, cleaning up after the synchronize_srcu()
* above.
*/
synchronize_sched();
/* Invoke the callbacks. */
while (list) {
next = list->next;
local_bh_disable();
list->func(list);
local_bh_enable();
list = next;
cond_resched();
}
/* Paranoid sleep to keep this from entering a tight loop */
schedule_timeout_uninterruptible(HZ/10);
}
}
/* Spawn rcu_tasks_kthread() at core_initcall() time. */
static int __init rcu_spawn_tasks_kthread(void)
{
struct task_struct *t;
t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
BUG_ON(IS_ERR(t));
smp_mb(); /* Ensure others see full kthread. */
WRITE_ONCE(rcu_tasks_kthread_ptr, t);
return 0;
}
core_initcall(rcu_spawn_tasks_kthread);
/* Do the srcu_read_lock() for the above synchronize_srcu(). */
void exit_tasks_rcu_start(void)
{
preempt_disable();
current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
preempt_enable();
}
/* Do the srcu_read_unlock() for the above synchronize_srcu(). */
void exit_tasks_rcu_finish(void)
{
preempt_disable();
__srcu_read_unlock(&tasks_rcu_exit_srcu, current->rcu_tasks_idx);
preempt_enable();
}
#endif /* #ifdef CONFIG_TASKS_RCU */
#ifndef CONFIG_TINY_RCU
/*
* Print any non-default Tasks RCU settings.
*/
static void __init rcu_tasks_bootup_oddness(void)
{
#ifdef CONFIG_TASKS_RCU
if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
else
pr_info("\tTasks RCU enabled.\n");
#endif /* #ifdef CONFIG_TASKS_RCU */
}
#endif /* #ifndef CONFIG_TINY_RCU */
#ifdef CONFIG_PROVE_RCU
/*
* Early boot self test parameters, one for each flavor
*/
static bool rcu_self_test;
static bool rcu_self_test_bh;
static bool rcu_self_test_sched;
module_param(rcu_self_test, bool, 0444);
module_param(rcu_self_test_bh, bool, 0444);
module_param(rcu_self_test_sched, bool, 0444);
static int rcu_self_test_counter;
static void test_callback(struct rcu_head *r)
{
rcu_self_test_counter++;
pr_info("RCU test callback executed %d\n", rcu_self_test_counter);
}
static void early_boot_test_call_rcu(void)
{
static struct rcu_head head;
call_rcu(&head, test_callback);
}
static void early_boot_test_call_rcu_bh(void)
{
static struct rcu_head head;
call_rcu_bh(&head, test_callback);
}
static void early_boot_test_call_rcu_sched(void)
{
static struct rcu_head head;
call_rcu_sched(&head, test_callback);
}
void rcu_early_boot_tests(void)
{
pr_info("Running RCU self tests\n");
if (rcu_self_test)
early_boot_test_call_rcu();
if (rcu_self_test_bh)
early_boot_test_call_rcu_bh();
if (rcu_self_test_sched)
early_boot_test_call_rcu_sched();
rcu_test_sync_prims();
}
static int rcu_verify_early_boot_tests(void)
{
int ret = 0;
int early_boot_test_counter = 0;
if (rcu_self_test) {
early_boot_test_counter++;
rcu_barrier();
}
if (rcu_self_test_bh) {
early_boot_test_counter++;
rcu_barrier_bh();
}
if (rcu_self_test_sched) {
early_boot_test_counter++;
rcu_barrier_sched();
}
if (rcu_self_test_counter != early_boot_test_counter) {
WARN_ON(1);
ret = -1;
}
return ret;
}
late_initcall(rcu_verify_early_boot_tests);
#else
void rcu_early_boot_tests(void) {}
#endif /* CONFIG_PROVE_RCU */
#ifndef CONFIG_TINY_RCU
/*
* Print any significant non-default boot-time settings.
*/
void __init rcupdate_announce_bootup_oddness(void)
{
if (rcu_normal)
pr_info("\tNo expedited grace period (rcu_normal).\n");
else if (rcu_normal_after_boot)
pr_info("\tNo expedited grace period (rcu_normal_after_boot).\n");
else if (rcu_expedited)
pr_info("\tAll grace periods are expedited (rcu_expedited).\n");
if (rcu_cpu_stall_suppress)
pr_info("\tRCU CPU stall warnings suppressed (rcu_cpu_stall_suppress).\n");
if (rcu_cpu_stall_timeout != CONFIG_RCU_CPU_STALL_TIMEOUT)
pr_info("\tRCU CPU stall warnings timeout set to %d (rcu_cpu_stall_timeout).\n", rcu_cpu_stall_timeout);
rcu_tasks_bootup_oddness();
}
#endif /* #ifndef CONFIG_TINY_RCU */