2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* linux/kernel/softirq.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1992 Linus Torvalds
|
|
|
|
*
|
2008-01-30 07:30:00 -05:00
|
|
|
* Distribute under GPLv2.
|
|
|
|
*
|
|
|
|
* Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
|
2008-09-24 01:15:57 -04:00
|
|
|
*
|
|
|
|
* Remote softirq infrastructure is by Jens Axboe.
|
2005-04-16 18:20:36 -04:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/kernel_stat.h>
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/notifier.h>
|
|
|
|
#include <linux/percpu.h>
|
|
|
|
#include <linux/cpu.h>
|
2007-07-17 07:03:35 -04:00
|
|
|
#include <linux/freezer.h>
|
2005-04-16 18:20:36 -04:00
|
|
|
#include <linux/kthread.h>
|
|
|
|
#include <linux/rcupdate.h>
|
2006-03-22 03:08:16 -05:00
|
|
|
#include <linux/smp.h>
|
2007-02-16 04:28:03 -05:00
|
|
|
#include <linux/tick.h>
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
#include <asm/irq.h>
|
|
|
|
/*
|
|
|
|
- No shared variables, all the data are CPU local.
|
|
|
|
- If a softirq needs serialization, let it serialize itself
|
|
|
|
by its own spinlocks.
|
|
|
|
- Even if softirq is serialized, only local cpu is marked for
|
|
|
|
execution. Hence, we get something sort of weak cpu binding.
|
|
|
|
Though it is still not clear, will it result in better locality
|
|
|
|
or will not.
|
|
|
|
|
|
|
|
Examples:
|
|
|
|
- NET RX softirq. It is multithreaded and does not require
|
|
|
|
any global serialization.
|
|
|
|
- NET TX softirq. It kicks software netdevice queues, hence
|
|
|
|
it is logically serialized per device, but this serialization
|
|
|
|
is invisible to common code.
|
|
|
|
- Tasklets: serialized wrt itself.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef __ARCH_IRQ_STAT
|
|
|
|
irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
|
|
|
|
EXPORT_SYMBOL(irq_stat);
|
|
|
|
#endif
|
|
|
|
|
2008-09-06 14:04:36 -04:00
|
|
|
static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* we cannot loop indefinitely here to avoid userspace starvation,
|
|
|
|
* but we also don't want to introduce a worst case 1/HZ latency
|
|
|
|
* to the pending events, so lets the scheduler to balance
|
|
|
|
* the softirq load for us.
|
|
|
|
*/
|
|
|
|
static inline void wakeup_softirqd(void)
|
|
|
|
{
|
|
|
|
/* Interrupts are disabled: no need to stop preemption */
|
|
|
|
struct task_struct *tsk = __get_cpu_var(ksoftirqd);
|
|
|
|
|
|
|
|
if (tsk && tsk->state != TASK_RUNNING)
|
|
|
|
wake_up_process(tsk);
|
|
|
|
}
|
|
|
|
|
2006-07-03 03:24:42 -04:00
|
|
|
/*
|
|
|
|
* This one is for softirq.c-internal use,
|
|
|
|
* where hardirqs are disabled legitimately:
|
|
|
|
*/
|
2006-07-30 06:04:02 -04:00
|
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
2006-07-03 03:24:42 -04:00
|
|
|
static void __local_bh_disable(unsigned long ip)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
WARN_ON_ONCE(in_irq());
|
|
|
|
|
|
|
|
raw_local_irq_save(flags);
|
|
|
|
add_preempt_count(SOFTIRQ_OFFSET);
|
|
|
|
/*
|
|
|
|
* Were softirqs turned off above:
|
|
|
|
*/
|
|
|
|
if (softirq_count() == SOFTIRQ_OFFSET)
|
|
|
|
trace_softirqs_off(ip);
|
|
|
|
raw_local_irq_restore(flags);
|
|
|
|
}
|
2006-07-30 06:04:02 -04:00
|
|
|
#else /* !CONFIG_TRACE_IRQFLAGS */
|
|
|
|
static inline void __local_bh_disable(unsigned long ip)
|
|
|
|
{
|
|
|
|
add_preempt_count(SOFTIRQ_OFFSET);
|
|
|
|
barrier();
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_TRACE_IRQFLAGS */
|
2006-07-03 03:24:42 -04:00
|
|
|
|
|
|
|
void local_bh_disable(void)
|
|
|
|
{
|
|
|
|
__local_bh_disable((unsigned long)__builtin_return_address(0));
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(local_bh_disable);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Special-case - softirqs can safely be enabled in
|
|
|
|
* cond_resched_softirq(), or by __do_softirq(),
|
|
|
|
* without processing still-pending softirqs:
|
|
|
|
*/
|
|
|
|
void _local_bh_enable(void)
|
|
|
|
{
|
|
|
|
WARN_ON_ONCE(in_irq());
|
|
|
|
WARN_ON_ONCE(!irqs_disabled());
|
|
|
|
|
|
|
|
if (softirq_count() == SOFTIRQ_OFFSET)
|
|
|
|
trace_softirqs_on((unsigned long)__builtin_return_address(0));
|
|
|
|
sub_preempt_count(SOFTIRQ_OFFSET);
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(_local_bh_enable);
|
|
|
|
|
2008-06-18 03:29:37 -04:00
|
|
|
static inline void _local_bh_enable_ip(unsigned long ip)
|
2006-07-03 03:24:42 -04:00
|
|
|
{
|
2008-06-18 03:29:37 -04:00
|
|
|
WARN_ON_ONCE(in_irq() || irqs_disabled());
|
2006-07-30 06:04:02 -04:00
|
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
2008-06-18 03:29:37 -04:00
|
|
|
local_irq_disable();
|
2006-07-30 06:04:02 -04:00
|
|
|
#endif
|
2006-07-03 03:24:42 -04:00
|
|
|
/*
|
|
|
|
* Are softirqs going to be turned on now:
|
|
|
|
*/
|
|
|
|
if (softirq_count() == SOFTIRQ_OFFSET)
|
2008-06-18 03:29:37 -04:00
|
|
|
trace_softirqs_on(ip);
|
2006-07-03 03:24:42 -04:00
|
|
|
/*
|
|
|
|
* Keep preemption disabled until we are done with
|
|
|
|
* softirq processing:
|
|
|
|
*/
|
|
|
|
sub_preempt_count(SOFTIRQ_OFFSET - 1);
|
|
|
|
|
|
|
|
if (unlikely(!in_interrupt() && local_softirq_pending()))
|
|
|
|
do_softirq();
|
|
|
|
|
|
|
|
dec_preempt_count();
|
2006-07-30 06:04:02 -04:00
|
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
2008-06-18 03:29:37 -04:00
|
|
|
local_irq_enable();
|
2006-07-30 06:04:02 -04:00
|
|
|
#endif
|
2006-07-03 03:24:42 -04:00
|
|
|
preempt_check_resched();
|
|
|
|
}
|
2008-06-18 03:29:37 -04:00
|
|
|
|
|
|
|
void local_bh_enable(void)
|
|
|
|
{
|
|
|
|
_local_bh_enable_ip((unsigned long)__builtin_return_address(0));
|
|
|
|
}
|
2006-07-03 03:24:42 -04:00
|
|
|
EXPORT_SYMBOL(local_bh_enable);
|
|
|
|
|
|
|
|
void local_bh_enable_ip(unsigned long ip)
|
|
|
|
{
|
2008-06-18 03:29:37 -04:00
|
|
|
_local_bh_enable_ip(ip);
|
2006-07-03 03:24:42 -04:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(local_bh_enable_ip);
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* We restart softirq processing MAX_SOFTIRQ_RESTART times,
|
|
|
|
* and we fall back to softirqd after that.
|
|
|
|
*
|
|
|
|
* This number has been established via experimentation.
|
|
|
|
* The two things to balance is latency against fairness -
|
|
|
|
* we want to handle softirqs as soon as possible, but they
|
|
|
|
* should not be able to lock up the box.
|
|
|
|
*/
|
|
|
|
#define MAX_SOFTIRQ_RESTART 10
|
|
|
|
|
|
|
|
asmlinkage void __do_softirq(void)
|
|
|
|
{
|
|
|
|
struct softirq_action *h;
|
|
|
|
__u32 pending;
|
|
|
|
int max_restart = MAX_SOFTIRQ_RESTART;
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
pending = local_softirq_pending();
|
2006-07-03 03:25:40 -04:00
|
|
|
account_system_vtime(current);
|
|
|
|
|
2006-07-03 03:24:42 -04:00
|
|
|
__local_bh_disable((unsigned long)__builtin_return_address(0));
|
|
|
|
trace_softirq_enter();
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
cpu = smp_processor_id();
|
|
|
|
restart:
|
|
|
|
/* Reset the pending bitmask before enabling irqs */
|
2005-09-12 12:49:24 -04:00
|
|
|
set_softirq_pending(0);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
2005-07-30 13:22:49 -04:00
|
|
|
local_irq_enable();
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
h = softirq_vec;
|
|
|
|
|
|
|
|
do {
|
|
|
|
if (pending & 1) {
|
2008-10-02 04:50:53 -04:00
|
|
|
int prev_count = preempt_count();
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
h->action(h);
|
2008-10-02 04:50:53 -04:00
|
|
|
|
|
|
|
if (unlikely(prev_count != preempt_count())) {
|
2008-10-16 18:32:46 -04:00
|
|
|
printk(KERN_ERR "huh, entered softirq %td %p"
|
2008-10-02 04:50:53 -04:00
|
|
|
"with preempt_count %08x,"
|
|
|
|
" exited with %08x?\n", h - softirq_vec,
|
|
|
|
h->action, prev_count, preempt_count());
|
|
|
|
preempt_count() = prev_count;
|
|
|
|
}
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
rcu_bh_qsctr_inc(cpu);
|
|
|
|
}
|
|
|
|
h++;
|
|
|
|
pending >>= 1;
|
|
|
|
} while (pending);
|
|
|
|
|
2005-07-30 13:22:49 -04:00
|
|
|
local_irq_disable();
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
pending = local_softirq_pending();
|
|
|
|
if (pending && --max_restart)
|
|
|
|
goto restart;
|
|
|
|
|
|
|
|
if (pending)
|
|
|
|
wakeup_softirqd();
|
|
|
|
|
2006-07-03 03:24:42 -04:00
|
|
|
trace_softirq_exit();
|
2006-07-03 03:25:40 -04:00
|
|
|
|
|
|
|
account_system_vtime(current);
|
2006-07-03 03:24:42 -04:00
|
|
|
_local_bh_enable();
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifndef __ARCH_HAS_DO_SOFTIRQ
|
|
|
|
|
|
|
|
asmlinkage void do_softirq(void)
|
|
|
|
{
|
|
|
|
__u32 pending;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
if (in_interrupt())
|
|
|
|
return;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
|
|
|
|
pending = local_softirq_pending();
|
|
|
|
|
|
|
|
if (pending)
|
|
|
|
__do_softirq();
|
|
|
|
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
2007-02-16 04:27:45 -05:00
|
|
|
/*
|
|
|
|
* Enter an interrupt context.
|
|
|
|
*/
|
|
|
|
void irq_enter(void)
|
|
|
|
{
|
2008-01-30 07:30:04 -05:00
|
|
|
int cpu = smp_processor_id();
|
2008-10-17 03:59:47 -04:00
|
|
|
|
"Tree RCU": scalable classic RCU implementation
This patch fixes a long-standing performance bug in classic RCU that
results in massive internal-to-RCU lock contention on systems with
more than a few hundred CPUs. Although this patch creates a separate
flavor of RCU for ease of review and patch maintenance, it is intended
to replace classic RCU.
This patch still handles stress better than does mainline, so I am still
calling it ready for inclusion. This patch is against the -tip tree.
Nevertheless, experience on an actual 1000+ CPU machine would still be
most welcome.
Most of the changes noted below were found while creating an rcutiny
(which should permit ejecting the current rcuclassic) and while doing
detailed line-by-line documentation.
Updates from v9 (http://lkml.org/lkml/2008/12/2/334):
o Fixes from remainder of line-by-line code walkthrough,
including comment spelling, initialization, undesirable
narrowing due to type conversion, removing redundant memory
barriers, removing redundant local-variable initialization,
and removing redundant local variables.
I do not believe that any of these fixes address the CPU-hotplug
issues that Andi Kleen was seeing, but please do give it a whirl
in case the machine is smarter than I am.
A writeup from the walkthrough may be found at the following
URL, in case you are suffering from terminal insomnia or
masochism:
http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf
o Made rcutree tracing use seq_file, as suggested some time
ago by Lai Jiangshan.
o Added a .csv variant of the rcudata debugfs trace file, to allow
people having thousands of CPUs to drop the data into
a spreadsheet. Tested with oocalc and gnumeric. Updated
documentation to suit.
Updates from v8 (http://lkml.org/lkml/2008/11/15/139):
o Fix a theoretical race between grace-period initialization and
force_quiescent_state() that could occur if more than three
jiffies were required to carry out the grace-period
initialization. Which it might, if you had enough CPUs.
o Apply Ingo's printk-standardization patch.
o Substitute local variables for repeated accesses to global
variables.
o Fix comment misspellings and redundant (but harmless) increments
of ->n_rcu_pending (this latter after having explicitly added it).
o Apply checkpatch fixes.
Updates from v7 (http://lkml.org/lkml/2008/10/10/291):
o Fixed a number of problems noted by Gautham Shenoy, including
the cpu-stall-detection bug that he was having difficulty
convincing me was real. ;-)
o Changed cpu-stall detection to wait for ten seconds rather than
three in order to reduce false positive, as suggested by Ingo
Molnar.
o Produced a design document (http://lwn.net/Articles/305782/).
The act of writing this document uncovered a number of both
theoretical and "here and now" bugs as noted below.
o Fix dynticks_nesting accounting confusion, simplify WARN_ON()
condition, fix kerneldoc comments, and add memory barriers
in dynticks interface functions.
o Add more data to tracing.
o Remove unused "rcu_barrier" field from rcu_data structure.
o Count calls to rcu_pending() from scheduling-clock interrupt
to use as a surrogate timebase should jiffies stop counting.
o Fix a theoretical race between force_quiescent_state() and
grace-period initialization. Yes, initialization does have to
go on for some jiffies for this race to occur, but given enough
CPUs...
Updates from v6 (http://lkml.org/lkml/2008/9/23/448):
o Fix a number of checkpatch.pl complaints.
o Apply review comments from Ingo Molnar and Lai Jiangshan
on the stall-detection code.
o Fix several bugs in !CONFIG_SMP builds.
o Fix a misspelled config-parameter name so that RCU now announces
at boot time if stall detection is configured.
o Run tests on numerous combinations of configurations parameters,
which after the fixes above, now build and run correctly.
Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line):
o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a
changeset some time ago, and finally got around to retesting
this option).
o Fix some tracing bugs in rcupreempt that caused incorrect
totals to be printed.
o I now test with a more brutal random-selection online/offline
script (attached). Probably more brutal than it needs to be
on the people reading it as well, but so it goes.
o A number of optimizations and usability improvements:
o Make rcu_pending() ignore the grace-period timeout when
there is no grace period in progress.
o Make force_quiescent_state() avoid going for a global
lock in the case where there is no grace period in
progress.
o Rearrange struct fields to improve struct layout.
o Make call_rcu() initiate a grace period if RCU was
idle, rather than waiting for the next scheduling
clock interrupt.
o Invoke rcu_irq_enter() and rcu_irq_exit() only when
idle, as suggested by Andi Kleen. I still don't
completely trust this change, and might back it out.
o Make CONFIG_RCU_TRACE be the single config variable
manipulated for all forms of RCU, instead of the prior
confusion.
o Document tracing files and formats for both rcupreempt
and rcutree.
Updates from v4 for those missing v5 given its bad subject line:
o Separated dynticks interface so that NMIs and irqs call separate
functions, greatly simplifying it. In particular, this code
no longer requires a proof of correctness. ;-)
o Separated dynticks state out into its own per-CPU structure,
avoiding the duplicated accounting.
o The case where a dynticks-idle CPU runs an irq handler that
invokes call_rcu() is now correctly handled, forcing that CPU
out of dynticks-idle mode.
o Review comments have been applied (thank you all!!!).
For but one example, fixed the dynticks-ordering issue that
Manfred pointed out, saving me much debugging. ;-)
o Adjusted rcuclassic and rcupreempt to handle dynticks changes.
Attached is an updated patch to Classic RCU that applies a hierarchy,
greatly reducing the contention on the top-level lock for large machines.
This passes 10-hour concurrent rcutorture and online-offline testing on
128-CPU ppc64 without dynticks enabled, and exposes some timekeeping
bugs in presence of dynticks (exciting working on a system where
"sleep 1" hangs until interrupted...), which were fixed in the
2.6.27 kernel. It is getting more reliable than mainline by some
measures, so the next version will be against -tip for inclusion.
See also Manfred Spraul's recent patches (or his earlier work from
2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2).
We will converge onto a common patch in the fullness of time, but are
currently exploring different regions of the design space. That said,
I have already gratefully stolen quite a few of Manfred's ideas.
This patch provides CONFIG_RCU_FANOUT, which controls the bushiness
of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on
64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT,
there is no hierarchy. By default, the RCU initialization code will
adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA
architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable
this balancing, allowing the hierarchy to be exactly aligned to the
underlying hardware. Up to two levels of hierarchy are permitted
(in addition to the root node), allowing up to 16,384 CPUs on 32-bit
systems and up to 262,144 CPUs on 64-bit systems. I just know that I
am going to regret saying this, but this seems more than sufficient
for the foreseeable future. (Some architectures might wish to set
CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs.
If this becomes a real problem, additional levels can be added, but I
doubt that it will make a significant difference on real hardware.)
In the common case, a given CPU will manipulate its private rcu_data
structure and the rcu_node structure that it shares with its immediate
neighbors. This can reduce both lock and memory contention by multiple
orders of magnitude, which should eliminate the need for the strange
manipulations that are reported to be required when running Linux on
very large systems.
Some shortcomings:
o More bugs will probably surface as a result of an ongoing
line-by-line code inspection.
Patches will be provided as required.
o There are probably hangs, rcutorture failures, &c. Seems
quite stable on a 128-CPU machine, but that is kind of small
compared to 4096 CPUs. However, seems to do better than
mainline.
Patches will be provided as required.
o The memory footprint of this version is several KB larger
than rcuclassic.
A separate UP-only rcutiny patch will be provided, which will
reduce the memory footprint significantly, even compared
to the old rcuclassic. One such patch passes light testing,
and has a memory footprint smaller even than rcuclassic.
Initial reaction from various embedded guys was "it is not
worth it", so am putting it aside.
Credits:
o Manfred Spraul for ideas, review comments, and bugs spotted,
as well as some good friendly competition. ;-)
o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers,
Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton
for reviews and comments.
o Thomas Gleixner for much-needed help with some timer issues
(see patches below).
o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos,
Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton
Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines
alive despite my heavy abuse^Wtesting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-18 15:55:32 -05:00
|
|
|
rcu_irq_enter();
|
2008-11-07 05:06:00 -05:00
|
|
|
if (idle_cpu(cpu) && !in_interrupt()) {
|
|
|
|
__irq_enter();
|
2008-10-17 03:59:47 -04:00
|
|
|
tick_check_idle(cpu);
|
2008-11-07 05:06:00 -05:00
|
|
|
} else
|
|
|
|
__irq_enter();
|
2007-02-16 04:27:45 -05:00
|
|
|
}
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
|
|
|
|
# define invoke_softirq() __do_softirq()
|
|
|
|
#else
|
|
|
|
# define invoke_softirq() do_softirq()
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Exit an interrupt context. Process softirqs if needed and possible:
|
|
|
|
*/
|
|
|
|
void irq_exit(void)
|
|
|
|
{
|
|
|
|
account_system_vtime(current);
|
2006-07-03 03:24:42 -04:00
|
|
|
trace_hardirq_exit();
|
2005-04-16 18:20:36 -04:00
|
|
|
sub_preempt_count(IRQ_EXIT_OFFSET);
|
|
|
|
if (!in_interrupt() && local_softirq_pending())
|
|
|
|
invoke_softirq();
|
2007-02-16 04:28:03 -05:00
|
|
|
|
|
|
|
#ifdef CONFIG_NO_HZ
|
|
|
|
/* Make sure that timer wheel updates are propagated */
|
2008-02-29 12:46:50 -05:00
|
|
|
rcu_irq_exit();
|
"Tree RCU": scalable classic RCU implementation
This patch fixes a long-standing performance bug in classic RCU that
results in massive internal-to-RCU lock contention on systems with
more than a few hundred CPUs. Although this patch creates a separate
flavor of RCU for ease of review and patch maintenance, it is intended
to replace classic RCU.
This patch still handles stress better than does mainline, so I am still
calling it ready for inclusion. This patch is against the -tip tree.
Nevertheless, experience on an actual 1000+ CPU machine would still be
most welcome.
Most of the changes noted below were found while creating an rcutiny
(which should permit ejecting the current rcuclassic) and while doing
detailed line-by-line documentation.
Updates from v9 (http://lkml.org/lkml/2008/12/2/334):
o Fixes from remainder of line-by-line code walkthrough,
including comment spelling, initialization, undesirable
narrowing due to type conversion, removing redundant memory
barriers, removing redundant local-variable initialization,
and removing redundant local variables.
I do not believe that any of these fixes address the CPU-hotplug
issues that Andi Kleen was seeing, but please do give it a whirl
in case the machine is smarter than I am.
A writeup from the walkthrough may be found at the following
URL, in case you are suffering from terminal insomnia or
masochism:
http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf
o Made rcutree tracing use seq_file, as suggested some time
ago by Lai Jiangshan.
o Added a .csv variant of the rcudata debugfs trace file, to allow
people having thousands of CPUs to drop the data into
a spreadsheet. Tested with oocalc and gnumeric. Updated
documentation to suit.
Updates from v8 (http://lkml.org/lkml/2008/11/15/139):
o Fix a theoretical race between grace-period initialization and
force_quiescent_state() that could occur if more than three
jiffies were required to carry out the grace-period
initialization. Which it might, if you had enough CPUs.
o Apply Ingo's printk-standardization patch.
o Substitute local variables for repeated accesses to global
variables.
o Fix comment misspellings and redundant (but harmless) increments
of ->n_rcu_pending (this latter after having explicitly added it).
o Apply checkpatch fixes.
Updates from v7 (http://lkml.org/lkml/2008/10/10/291):
o Fixed a number of problems noted by Gautham Shenoy, including
the cpu-stall-detection bug that he was having difficulty
convincing me was real. ;-)
o Changed cpu-stall detection to wait for ten seconds rather than
three in order to reduce false positive, as suggested by Ingo
Molnar.
o Produced a design document (http://lwn.net/Articles/305782/).
The act of writing this document uncovered a number of both
theoretical and "here and now" bugs as noted below.
o Fix dynticks_nesting accounting confusion, simplify WARN_ON()
condition, fix kerneldoc comments, and add memory barriers
in dynticks interface functions.
o Add more data to tracing.
o Remove unused "rcu_barrier" field from rcu_data structure.
o Count calls to rcu_pending() from scheduling-clock interrupt
to use as a surrogate timebase should jiffies stop counting.
o Fix a theoretical race between force_quiescent_state() and
grace-period initialization. Yes, initialization does have to
go on for some jiffies for this race to occur, but given enough
CPUs...
Updates from v6 (http://lkml.org/lkml/2008/9/23/448):
o Fix a number of checkpatch.pl complaints.
o Apply review comments from Ingo Molnar and Lai Jiangshan
on the stall-detection code.
o Fix several bugs in !CONFIG_SMP builds.
o Fix a misspelled config-parameter name so that RCU now announces
at boot time if stall detection is configured.
o Run tests on numerous combinations of configurations parameters,
which after the fixes above, now build and run correctly.
Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line):
o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a
changeset some time ago, and finally got around to retesting
this option).
o Fix some tracing bugs in rcupreempt that caused incorrect
totals to be printed.
o I now test with a more brutal random-selection online/offline
script (attached). Probably more brutal than it needs to be
on the people reading it as well, but so it goes.
o A number of optimizations and usability improvements:
o Make rcu_pending() ignore the grace-period timeout when
there is no grace period in progress.
o Make force_quiescent_state() avoid going for a global
lock in the case where there is no grace period in
progress.
o Rearrange struct fields to improve struct layout.
o Make call_rcu() initiate a grace period if RCU was
idle, rather than waiting for the next scheduling
clock interrupt.
o Invoke rcu_irq_enter() and rcu_irq_exit() only when
idle, as suggested by Andi Kleen. I still don't
completely trust this change, and might back it out.
o Make CONFIG_RCU_TRACE be the single config variable
manipulated for all forms of RCU, instead of the prior
confusion.
o Document tracing files and formats for both rcupreempt
and rcutree.
Updates from v4 for those missing v5 given its bad subject line:
o Separated dynticks interface so that NMIs and irqs call separate
functions, greatly simplifying it. In particular, this code
no longer requires a proof of correctness. ;-)
o Separated dynticks state out into its own per-CPU structure,
avoiding the duplicated accounting.
o The case where a dynticks-idle CPU runs an irq handler that
invokes call_rcu() is now correctly handled, forcing that CPU
out of dynticks-idle mode.
o Review comments have been applied (thank you all!!!).
For but one example, fixed the dynticks-ordering issue that
Manfred pointed out, saving me much debugging. ;-)
o Adjusted rcuclassic and rcupreempt to handle dynticks changes.
Attached is an updated patch to Classic RCU that applies a hierarchy,
greatly reducing the contention on the top-level lock for large machines.
This passes 10-hour concurrent rcutorture and online-offline testing on
128-CPU ppc64 without dynticks enabled, and exposes some timekeeping
bugs in presence of dynticks (exciting working on a system where
"sleep 1" hangs until interrupted...), which were fixed in the
2.6.27 kernel. It is getting more reliable than mainline by some
measures, so the next version will be against -tip for inclusion.
See also Manfred Spraul's recent patches (or his earlier work from
2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2).
We will converge onto a common patch in the fullness of time, but are
currently exploring different regions of the design space. That said,
I have already gratefully stolen quite a few of Manfred's ideas.
This patch provides CONFIG_RCU_FANOUT, which controls the bushiness
of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on
64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT,
there is no hierarchy. By default, the RCU initialization code will
adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA
architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable
this balancing, allowing the hierarchy to be exactly aligned to the
underlying hardware. Up to two levels of hierarchy are permitted
(in addition to the root node), allowing up to 16,384 CPUs on 32-bit
systems and up to 262,144 CPUs on 64-bit systems. I just know that I
am going to regret saying this, but this seems more than sufficient
for the foreseeable future. (Some architectures might wish to set
CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs.
If this becomes a real problem, additional levels can be added, but I
doubt that it will make a significant difference on real hardware.)
In the common case, a given CPU will manipulate its private rcu_data
structure and the rcu_node structure that it shares with its immediate
neighbors. This can reduce both lock and memory contention by multiple
orders of magnitude, which should eliminate the need for the strange
manipulations that are reported to be required when running Linux on
very large systems.
Some shortcomings:
o More bugs will probably surface as a result of an ongoing
line-by-line code inspection.
Patches will be provided as required.
o There are probably hangs, rcutorture failures, &c. Seems
quite stable on a 128-CPU machine, but that is kind of small
compared to 4096 CPUs. However, seems to do better than
mainline.
Patches will be provided as required.
o The memory footprint of this version is several KB larger
than rcuclassic.
A separate UP-only rcutiny patch will be provided, which will
reduce the memory footprint significantly, even compared
to the old rcuclassic. One such patch passes light testing,
and has a memory footprint smaller even than rcuclassic.
Initial reaction from various embedded guys was "it is not
worth it", so am putting it aside.
Credits:
o Manfred Spraul for ideas, review comments, and bugs spotted,
as well as some good friendly competition. ;-)
o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers,
Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton
for reviews and comments.
o Thomas Gleixner for much-needed help with some timer issues
(see patches below).
o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos,
Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton
Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines
alive despite my heavy abuse^Wtesting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-18 15:55:32 -05:00
|
|
|
if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
|
|
|
|
tick_nohz_stop_sched_tick(0);
|
2007-02-16 04:28:03 -05:00
|
|
|
#endif
|
2005-04-16 18:20:36 -04:00
|
|
|
preempt_enable_no_resched();
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function must run with irqs disabled!
|
|
|
|
*/
|
2008-02-08 07:19:53 -05:00
|
|
|
inline void raise_softirq_irqoff(unsigned int nr)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
|
|
|
__raise_softirq_irqoff(nr);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we're in an interrupt or softirq, we're done
|
|
|
|
* (this also catches softirq-disabled code). We will
|
|
|
|
* actually run the softirq once we return from
|
|
|
|
* the irq or softirq.
|
|
|
|
*
|
|
|
|
* Otherwise we wake up ksoftirqd to make sure we
|
|
|
|
* schedule the softirq soon.
|
|
|
|
*/
|
|
|
|
if (!in_interrupt())
|
|
|
|
wakeup_softirqd();
|
|
|
|
}
|
|
|
|
|
2008-02-08 07:19:53 -05:00
|
|
|
void raise_softirq(unsigned int nr)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
raise_softirq_irqoff(nr);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
|
Remove argument from open_softirq which is always NULL
As git-grep shows, open_softirq() is always called with the last argument
being NULL
block/blk-core.c: open_softirq(BLOCK_SOFTIRQ, blk_done_softirq, NULL);
kernel/hrtimer.c: open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL);
kernel/rcuclassic.c: open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL);
kernel/rcupreempt.c: open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL);
kernel/sched.c: open_softirq(SCHED_SOFTIRQ, run_rebalance_domains, NULL);
kernel/softirq.c: open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
kernel/softirq.c: open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
kernel/timer.c: open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
net/core/dev.c: open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
net/core/dev.c: open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
This observation has already been made by Matthew Wilcox in June 2002
(http://www.cs.helsinki.fi/linux/linux-kernel/2002-25/0687.html)
"I notice that none of the current softirq routines use the data element
passed to them."
and the situation hasn't changed since them. So it appears we can safely
remove that extra argument to save 128 (54) bytes of kernel data (text).
Signed-off-by: Carlos R. Mafra <crmafra@ift.unesp.br>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-15 10:15:37 -04:00
|
|
|
void open_softirq(int nr, void (*action)(struct softirq_action *))
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
|
|
|
softirq_vec[nr].action = action;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Tasklets */
|
|
|
|
struct tasklet_head
|
|
|
|
{
|
2008-03-04 18:23:25 -05:00
|
|
|
struct tasklet_struct *head;
|
|
|
|
struct tasklet_struct **tail;
|
2005-04-16 18:20:36 -04:00
|
|
|
};
|
|
|
|
|
2008-06-12 17:21:53 -04:00
|
|
|
static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
|
|
|
|
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
2008-02-08 07:19:53 -05:00
|
|
|
void __tasklet_schedule(struct tasklet_struct *t)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
2008-03-04 18:23:25 -05:00
|
|
|
t->next = NULL;
|
|
|
|
*__get_cpu_var(tasklet_vec).tail = t;
|
|
|
|
__get_cpu_var(tasklet_vec).tail = &(t->next);
|
2005-04-16 18:20:36 -04:00
|
|
|
raise_softirq_irqoff(TASKLET_SOFTIRQ);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(__tasklet_schedule);
|
|
|
|
|
2008-02-08 07:19:53 -05:00
|
|
|
void __tasklet_hi_schedule(struct tasklet_struct *t)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
2008-03-04 18:23:25 -05:00
|
|
|
t->next = NULL;
|
|
|
|
*__get_cpu_var(tasklet_hi_vec).tail = t;
|
|
|
|
__get_cpu_var(tasklet_hi_vec).tail = &(t->next);
|
2005-04-16 18:20:36 -04:00
|
|
|
raise_softirq_irqoff(HI_SOFTIRQ);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(__tasklet_hi_schedule);
|
|
|
|
|
|
|
|
static void tasklet_action(struct softirq_action *a)
|
|
|
|
{
|
|
|
|
struct tasklet_struct *list;
|
|
|
|
|
|
|
|
local_irq_disable();
|
2008-03-04 18:23:25 -05:00
|
|
|
list = __get_cpu_var(tasklet_vec).head;
|
|
|
|
__get_cpu_var(tasklet_vec).head = NULL;
|
|
|
|
__get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head;
|
2005-04-16 18:20:36 -04:00
|
|
|
local_irq_enable();
|
|
|
|
|
|
|
|
while (list) {
|
|
|
|
struct tasklet_struct *t = list;
|
|
|
|
|
|
|
|
list = list->next;
|
|
|
|
|
|
|
|
if (tasklet_trylock(t)) {
|
|
|
|
if (!atomic_read(&t->count)) {
|
|
|
|
if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
|
|
|
|
BUG();
|
|
|
|
t->func(t->data);
|
|
|
|
tasklet_unlock(t);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
tasklet_unlock(t);
|
|
|
|
}
|
|
|
|
|
|
|
|
local_irq_disable();
|
2008-03-04 18:23:25 -05:00
|
|
|
t->next = NULL;
|
|
|
|
*__get_cpu_var(tasklet_vec).tail = t;
|
|
|
|
__get_cpu_var(tasklet_vec).tail = &(t->next);
|
2005-04-16 18:20:36 -04:00
|
|
|
__raise_softirq_irqoff(TASKLET_SOFTIRQ);
|
|
|
|
local_irq_enable();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void tasklet_hi_action(struct softirq_action *a)
|
|
|
|
{
|
|
|
|
struct tasklet_struct *list;
|
|
|
|
|
|
|
|
local_irq_disable();
|
2008-03-04 18:23:25 -05:00
|
|
|
list = __get_cpu_var(tasklet_hi_vec).head;
|
|
|
|
__get_cpu_var(tasklet_hi_vec).head = NULL;
|
|
|
|
__get_cpu_var(tasklet_hi_vec).tail = &__get_cpu_var(tasklet_hi_vec).head;
|
2005-04-16 18:20:36 -04:00
|
|
|
local_irq_enable();
|
|
|
|
|
|
|
|
while (list) {
|
|
|
|
struct tasklet_struct *t = list;
|
|
|
|
|
|
|
|
list = list->next;
|
|
|
|
|
|
|
|
if (tasklet_trylock(t)) {
|
|
|
|
if (!atomic_read(&t->count)) {
|
|
|
|
if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
|
|
|
|
BUG();
|
|
|
|
t->func(t->data);
|
|
|
|
tasklet_unlock(t);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
tasklet_unlock(t);
|
|
|
|
}
|
|
|
|
|
|
|
|
local_irq_disable();
|
2008-03-04 18:23:25 -05:00
|
|
|
t->next = NULL;
|
|
|
|
*__get_cpu_var(tasklet_hi_vec).tail = t;
|
|
|
|
__get_cpu_var(tasklet_hi_vec).tail = &(t->next);
|
2005-04-16 18:20:36 -04:00
|
|
|
__raise_softirq_irqoff(HI_SOFTIRQ);
|
|
|
|
local_irq_enable();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
void tasklet_init(struct tasklet_struct *t,
|
|
|
|
void (*func)(unsigned long), unsigned long data)
|
|
|
|
{
|
|
|
|
t->next = NULL;
|
|
|
|
t->state = 0;
|
|
|
|
atomic_set(&t->count, 0);
|
|
|
|
t->func = func;
|
|
|
|
t->data = data;
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(tasklet_init);
|
|
|
|
|
|
|
|
void tasklet_kill(struct tasklet_struct *t)
|
|
|
|
{
|
|
|
|
if (in_interrupt())
|
|
|
|
printk("Attempt to kill tasklet from interrupt\n");
|
|
|
|
|
|
|
|
while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
|
|
|
|
do
|
|
|
|
yield();
|
|
|
|
while (test_bit(TASKLET_STATE_SCHED, &t->state));
|
|
|
|
}
|
|
|
|
tasklet_unlock_wait(t);
|
|
|
|
clear_bit(TASKLET_STATE_SCHED, &t->state);
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(tasklet_kill);
|
|
|
|
|
2008-09-24 01:15:57 -04:00
|
|
|
DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
|
|
|
|
EXPORT_PER_CPU_SYMBOL(softirq_work_list);
|
|
|
|
|
|
|
|
static void __local_trigger(struct call_single_data *cp, int softirq)
|
|
|
|
{
|
|
|
|
struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
|
|
|
|
|
|
|
|
list_add_tail(&cp->list, head);
|
|
|
|
|
|
|
|
/* Trigger the softirq only if the list was previously empty. */
|
|
|
|
if (head->next == &cp->list)
|
|
|
|
raise_softirq_irqoff(softirq);
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
|
|
|
|
static void remote_softirq_receive(void *data)
|
|
|
|
{
|
|
|
|
struct call_single_data *cp = data;
|
|
|
|
unsigned long flags;
|
|
|
|
int softirq;
|
|
|
|
|
|
|
|
softirq = cp->priv;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
__local_trigger(cp, softirq);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
|
|
|
|
{
|
|
|
|
if (cpu_online(cpu)) {
|
|
|
|
cp->func = remote_softirq_receive;
|
|
|
|
cp->info = cp;
|
|
|
|
cp->flags = 0;
|
|
|
|
cp->priv = softirq;
|
|
|
|
|
|
|
|
__smp_call_function_single(cpu, cp);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
|
|
|
|
static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/**
|
|
|
|
* __send_remote_softirq - try to schedule softirq work on a remote cpu
|
|
|
|
* @cp: private SMP call function data area
|
|
|
|
* @cpu: the remote cpu
|
|
|
|
* @this_cpu: the currently executing cpu
|
|
|
|
* @softirq: the softirq for the work
|
|
|
|
*
|
|
|
|
* Attempt to schedule softirq work on a remote cpu. If this cannot be
|
|
|
|
* done, the work is instead queued up on the local cpu.
|
|
|
|
*
|
|
|
|
* Interrupts must be disabled.
|
|
|
|
*/
|
|
|
|
void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
|
|
|
|
{
|
|
|
|
if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
|
|
|
|
__local_trigger(cp, softirq);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__send_remote_softirq);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* send_remote_softirq - try to schedule softirq work on a remote cpu
|
|
|
|
* @cp: private SMP call function data area
|
|
|
|
* @cpu: the remote cpu
|
|
|
|
* @softirq: the softirq for the work
|
|
|
|
*
|
|
|
|
* Like __send_remote_softirq except that disabling interrupts and
|
|
|
|
* computing the current cpu is done for the caller.
|
|
|
|
*/
|
|
|
|
void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
int this_cpu;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
this_cpu = smp_processor_id();
|
|
|
|
__send_remote_softirq(cp, cpu, this_cpu, softirq);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(send_remote_softirq);
|
|
|
|
|
|
|
|
static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self,
|
|
|
|
unsigned long action, void *hcpu)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* If a CPU goes away, splice its entries to the current CPU
|
|
|
|
* and trigger a run of the softirq
|
|
|
|
*/
|
|
|
|
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
|
|
|
|
int cpu = (unsigned long) hcpu;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
local_irq_disable();
|
|
|
|
for (i = 0; i < NR_SOFTIRQS; i++) {
|
|
|
|
struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
|
|
|
|
struct list_head *local_head;
|
|
|
|
|
|
|
|
if (list_empty(head))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
local_head = &__get_cpu_var(softirq_work_list[i]);
|
|
|
|
list_splice_init(head, local_head);
|
|
|
|
raise_softirq_irqoff(i);
|
|
|
|
}
|
|
|
|
local_irq_enable();
|
|
|
|
}
|
|
|
|
|
|
|
|
return NOTIFY_OK;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct notifier_block __cpuinitdata remote_softirq_cpu_notifier = {
|
|
|
|
.notifier_call = remote_softirq_cpu_notify,
|
|
|
|
};
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
void __init softirq_init(void)
|
|
|
|
{
|
2008-03-04 18:23:25 -05:00
|
|
|
int cpu;
|
|
|
|
|
|
|
|
for_each_possible_cpu(cpu) {
|
2008-09-24 01:15:57 -04:00
|
|
|
int i;
|
|
|
|
|
2008-03-04 18:23:25 -05:00
|
|
|
per_cpu(tasklet_vec, cpu).tail =
|
|
|
|
&per_cpu(tasklet_vec, cpu).head;
|
|
|
|
per_cpu(tasklet_hi_vec, cpu).tail =
|
|
|
|
&per_cpu(tasklet_hi_vec, cpu).head;
|
2008-09-24 01:15:57 -04:00
|
|
|
for (i = 0; i < NR_SOFTIRQS; i++)
|
|
|
|
INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
|
2008-03-04 18:23:25 -05:00
|
|
|
}
|
|
|
|
|
2008-09-24 01:15:57 -04:00
|
|
|
register_hotcpu_notifier(&remote_softirq_cpu_notifier);
|
|
|
|
|
Remove argument from open_softirq which is always NULL
As git-grep shows, open_softirq() is always called with the last argument
being NULL
block/blk-core.c: open_softirq(BLOCK_SOFTIRQ, blk_done_softirq, NULL);
kernel/hrtimer.c: open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL);
kernel/rcuclassic.c: open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL);
kernel/rcupreempt.c: open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL);
kernel/sched.c: open_softirq(SCHED_SOFTIRQ, run_rebalance_domains, NULL);
kernel/softirq.c: open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
kernel/softirq.c: open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
kernel/timer.c: open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
net/core/dev.c: open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
net/core/dev.c: open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
This observation has already been made by Matthew Wilcox in June 2002
(http://www.cs.helsinki.fi/linux/linux-kernel/2002-25/0687.html)
"I notice that none of the current softirq routines use the data element
passed to them."
and the situation hasn't changed since them. So it appears we can safely
remove that extra argument to save 128 (54) bytes of kernel data (text).
Signed-off-by: Carlos R. Mafra <crmafra@ift.unesp.br>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-15 10:15:37 -04:00
|
|
|
open_softirq(TASKLET_SOFTIRQ, tasklet_action);
|
|
|
|
open_softirq(HI_SOFTIRQ, tasklet_hi_action);
|
2005-04-16 18:20:36 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
static int ksoftirqd(void * __bind_cpu)
|
|
|
|
{
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
|
|
|
|
while (!kthread_should_stop()) {
|
|
|
|
preempt_disable();
|
|
|
|
if (!local_softirq_pending()) {
|
|
|
|
preempt_enable_no_resched();
|
|
|
|
schedule();
|
|
|
|
preempt_disable();
|
|
|
|
}
|
|
|
|
|
|
|
|
__set_current_state(TASK_RUNNING);
|
|
|
|
|
|
|
|
while (local_softirq_pending()) {
|
|
|
|
/* Preempt disable stops cpu going offline.
|
|
|
|
If already offline, we'll be on wrong CPU:
|
|
|
|
don't process */
|
|
|
|
if (cpu_is_offline((long)__bind_cpu))
|
|
|
|
goto wait_to_die;
|
|
|
|
do_softirq();
|
|
|
|
preempt_enable_no_resched();
|
|
|
|
cond_resched();
|
|
|
|
preempt_disable();
|
|
|
|
}
|
|
|
|
preempt_enable();
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
}
|
|
|
|
__set_current_state(TASK_RUNNING);
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
wait_to_die:
|
|
|
|
preempt_enable();
|
|
|
|
/* Wait for kthread_stop */
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
while (!kthread_should_stop()) {
|
|
|
|
schedule();
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
}
|
|
|
|
__set_current_state(TASK_RUNNING);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
/*
|
|
|
|
* tasklet_kill_immediate is called to remove a tasklet which can already be
|
|
|
|
* scheduled for execution on @cpu.
|
|
|
|
*
|
|
|
|
* Unlike tasklet_kill, this function removes the tasklet
|
|
|
|
* _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
|
|
|
|
*
|
|
|
|
* When this function is called, @cpu must be in the CPU_DEAD state.
|
|
|
|
*/
|
|
|
|
void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
|
|
|
|
{
|
|
|
|
struct tasklet_struct **i;
|
|
|
|
|
|
|
|
BUG_ON(cpu_online(cpu));
|
|
|
|
BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
|
|
|
|
|
|
|
|
if (!test_bit(TASKLET_STATE_SCHED, &t->state))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/* CPU is dead, so no lock needed. */
|
2008-03-04 18:23:25 -05:00
|
|
|
for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
|
2005-04-16 18:20:36 -04:00
|
|
|
if (*i == t) {
|
|
|
|
*i = t->next;
|
2008-03-04 18:23:25 -05:00
|
|
|
/* If this was the tail element, move the tail ptr */
|
|
|
|
if (*i == NULL)
|
|
|
|
per_cpu(tasklet_vec, cpu).tail = i;
|
2005-04-16 18:20:36 -04:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
|
|
|
static void takeover_tasklets(unsigned int cpu)
|
|
|
|
{
|
|
|
|
/* CPU is dead, so no lock needed. */
|
|
|
|
local_irq_disable();
|
|
|
|
|
|
|
|
/* Find end, append list for that CPU. */
|
2008-05-01 07:34:23 -04:00
|
|
|
if (&per_cpu(tasklet_vec, cpu).head != per_cpu(tasklet_vec, cpu).tail) {
|
|
|
|
*(__get_cpu_var(tasklet_vec).tail) = per_cpu(tasklet_vec, cpu).head;
|
|
|
|
__get_cpu_var(tasklet_vec).tail = per_cpu(tasklet_vec, cpu).tail;
|
|
|
|
per_cpu(tasklet_vec, cpu).head = NULL;
|
|
|
|
per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head;
|
|
|
|
}
|
2005-04-16 18:20:36 -04:00
|
|
|
raise_softirq_irqoff(TASKLET_SOFTIRQ);
|
|
|
|
|
2008-05-01 07:34:23 -04:00
|
|
|
if (&per_cpu(tasklet_hi_vec, cpu).head != per_cpu(tasklet_hi_vec, cpu).tail) {
|
|
|
|
*__get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).head;
|
|
|
|
__get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).tail;
|
|
|
|
per_cpu(tasklet_hi_vec, cpu).head = NULL;
|
|
|
|
per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head;
|
|
|
|
}
|
2005-04-16 18:20:36 -04:00
|
|
|
raise_softirq_irqoff(HI_SOFTIRQ);
|
|
|
|
|
|
|
|
local_irq_enable();
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
|
2006-07-30 06:03:35 -04:00
|
|
|
static int __cpuinit cpu_callback(struct notifier_block *nfb,
|
2005-04-16 18:20:36 -04:00
|
|
|
unsigned long action,
|
|
|
|
void *hcpu)
|
|
|
|
{
|
|
|
|
int hotcpu = (unsigned long)hcpu;
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
|
|
switch (action) {
|
|
|
|
case CPU_UP_PREPARE:
|
2007-05-09 05:35:10 -04:00
|
|
|
case CPU_UP_PREPARE_FROZEN:
|
2005-04-16 18:20:36 -04:00
|
|
|
p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
|
|
|
|
if (IS_ERR(p)) {
|
|
|
|
printk("ksoftirqd for %i failed\n", hotcpu);
|
|
|
|
return NOTIFY_BAD;
|
|
|
|
}
|
|
|
|
kthread_bind(p, hotcpu);
|
|
|
|
per_cpu(ksoftirqd, hotcpu) = p;
|
|
|
|
break;
|
|
|
|
case CPU_ONLINE:
|
2007-05-09 05:35:10 -04:00
|
|
|
case CPU_ONLINE_FROZEN:
|
2005-04-16 18:20:36 -04:00
|
|
|
wake_up_process(per_cpu(ksoftirqd, hotcpu));
|
|
|
|
break;
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
case CPU_UP_CANCELED:
|
2007-05-09 05:35:10 -04:00
|
|
|
case CPU_UP_CANCELED_FROZEN:
|
2006-06-25 08:49:10 -04:00
|
|
|
if (!per_cpu(ksoftirqd, hotcpu))
|
|
|
|
break;
|
2005-04-16 18:20:36 -04:00
|
|
|
/* Unbind so it can run. Fall thru. */
|
2005-11-07 03:58:38 -05:00
|
|
|
kthread_bind(per_cpu(ksoftirqd, hotcpu),
|
2008-12-31 18:42:23 -05:00
|
|
|
cpumask_any(cpu_online_mask));
|
2005-04-16 18:20:36 -04:00
|
|
|
case CPU_DEAD:
|
2007-07-16 02:39:48 -04:00
|
|
|
case CPU_DEAD_FROZEN: {
|
|
|
|
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
p = per_cpu(ksoftirqd, hotcpu);
|
|
|
|
per_cpu(ksoftirqd, hotcpu) = NULL;
|
2008-06-22 23:55:38 -04:00
|
|
|
sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
|
2005-04-16 18:20:36 -04:00
|
|
|
kthread_stop(p);
|
|
|
|
takeover_tasklets(hotcpu);
|
|
|
|
break;
|
2007-07-16 02:39:48 -04:00
|
|
|
}
|
2005-04-16 18:20:36 -04:00
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
}
|
|
|
|
return NOTIFY_OK;
|
|
|
|
}
|
|
|
|
|
2006-07-30 06:03:35 -04:00
|
|
|
static struct notifier_block __cpuinitdata cpu_nfb = {
|
2005-04-16 18:20:36 -04:00
|
|
|
.notifier_call = cpu_callback
|
|
|
|
};
|
|
|
|
|
2008-07-25 22:45:11 -04:00
|
|
|
static __init int spawn_ksoftirqd(void)
|
2005-04-16 18:20:36 -04:00
|
|
|
{
|
|
|
|
void *cpu = (void *)(long)smp_processor_id();
|
2006-09-29 05:00:22 -04:00
|
|
|
int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
|
|
|
|
|
|
|
|
BUG_ON(err == NOTIFY_BAD);
|
2005-04-16 18:20:36 -04:00
|
|
|
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
|
|
|
|
register_cpu_notifier(&cpu_nfb);
|
|
|
|
return 0;
|
|
|
|
}
|
2008-07-25 22:45:11 -04:00
|
|
|
early_initcall(spawn_ksoftirqd);
|
2006-03-22 03:08:16 -05:00
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
|
|
* Call a function on all processors
|
|
|
|
*/
|
2008-05-09 03:39:44 -04:00
|
|
|
int on_each_cpu(void (*func) (void *info), void *info, int wait)
|
2006-03-22 03:08:16 -05:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
preempt_disable();
|
2008-06-06 05:18:06 -04:00
|
|
|
ret = smp_call_function(func, info, wait);
|
2006-03-22 03:08:16 -05:00
|
|
|
local_irq_disable();
|
|
|
|
func(info);
|
|
|
|
local_irq_enable();
|
|
|
|
preempt_enable();
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(on_each_cpu);
|
|
|
|
#endif
|
2008-12-28 19:01:13 -05:00
|
|
|
|
|
|
|
/*
|
|
|
|
* [ These __weak aliases are kept in a separate compilation unit, so that
|
|
|
|
* GCC does not inline them incorrectly. ]
|
|
|
|
*/
|
|
|
|
|
|
|
|
int __init __weak early_irq_init(void)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int __init __weak arch_early_irq_init(void)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int __weak arch_init_chip_data(struct irq_desc *desc, int cpu)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|