2008-06-26 16:21:34 +07:00
|
|
|
/*
|
|
|
|
* Generic helpers for smp ipi calls
|
|
|
|
*
|
|
|
|
* (C) Jens Axboe <jens.axboe@oracle.com> 2008
|
|
|
|
*/
|
|
|
|
#include <linux/rcupdate.h>
|
2008-07-16 04:02:33 +07:00
|
|
|
#include <linux/rculist.h>
|
2009-03-13 16:47:34 +07:00
|
|
|
#include <linux/kernel.h>
|
2011-05-24 01:51:41 +07:00
|
|
|
#include <linux/export.h>
|
2009-02-25 22:52:11 +07:00
|
|
|
#include <linux/percpu.h>
|
|
|
|
#include <linux/init.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
|
|
|
#include <linux/gfp.h>
|
2008-06-26 16:21:34 +07:00
|
|
|
#include <linux/smp.h>
|
2009-02-25 19:59:47 +07:00
|
|
|
#include <linux/cpu.h>
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2012-04-21 07:08:50 +07:00
|
|
|
#include "smpboot.h"
|
|
|
|
|
2008-06-26 16:21:34 +07:00
|
|
|
enum {
|
2009-02-25 19:59:48 +07:00
|
|
|
CSD_FLAG_LOCK = 0x01,
|
2013-05-17 14:58:43 +07:00
|
|
|
CSD_FLAG_WAIT = 0x02,
|
2008-06-26 16:21:34 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
struct call_function_data {
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
struct call_single_data __percpu *csd;
|
2009-02-25 22:52:11 +07:00
|
|
|
cpumask_var_t cpumask;
|
2008-06-26 16:21:34 +07:00
|
|
|
};
|
|
|
|
|
2010-01-18 09:00:51 +07:00
|
|
|
static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
|
|
|
|
|
2014-01-31 06:45:47 +07:00
|
|
|
static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
|
2009-02-25 19:59:47 +07:00
|
|
|
|
|
|
|
static int
|
|
|
|
hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
|
|
|
|
{
|
|
|
|
long cpu = (long)hcpu;
|
|
|
|
struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
|
|
|
|
|
|
|
|
switch (action) {
|
|
|
|
case CPU_UP_PREPARE:
|
|
|
|
case CPU_UP_PREPARE_FROZEN:
|
2009-06-07 04:51:36 +07:00
|
|
|
if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
|
2009-02-25 19:59:47 +07:00
|
|
|
cpu_to_node(cpu)))
|
2010-05-27 04:43:32 +07:00
|
|
|
return notifier_from_errno(-ENOMEM);
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
cfd->csd = alloc_percpu(struct call_single_data);
|
|
|
|
if (!cfd->csd) {
|
|
|
|
free_cpumask_var(cfd->cpumask);
|
|
|
|
return notifier_from_errno(-ENOMEM);
|
|
|
|
}
|
2009-02-25 19:59:47 +07:00
|
|
|
break;
|
|
|
|
|
2009-08-07 05:07:29 +07:00
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
2009-02-25 19:59:47 +07:00
|
|
|
case CPU_UP_CANCELED:
|
|
|
|
case CPU_UP_CANCELED_FROZEN:
|
|
|
|
|
|
|
|
case CPU_DEAD:
|
|
|
|
case CPU_DEAD_FROZEN:
|
|
|
|
free_cpumask_var(cfd->cpumask);
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
free_percpu(cfd->csd);
|
2009-02-25 19:59:47 +07:00
|
|
|
break;
|
|
|
|
#endif
|
|
|
|
};
|
|
|
|
|
|
|
|
return NOTIFY_OK;
|
|
|
|
}
|
|
|
|
|
2013-06-20 01:53:51 +07:00
|
|
|
static struct notifier_block hotplug_cfd_notifier = {
|
2009-02-25 22:52:11 +07:00
|
|
|
.notifier_call = hotplug_cfd,
|
2009-02-25 19:59:47 +07:00
|
|
|
};
|
|
|
|
|
2011-03-29 23:35:04 +07:00
|
|
|
void __init call_function_init(void)
|
2008-06-26 16:21:34 +07:00
|
|
|
{
|
2009-02-25 19:59:47 +07:00
|
|
|
void *cpu = (void *)(long)smp_processor_id();
|
2008-06-26 16:21:34 +07:00
|
|
|
int i;
|
|
|
|
|
2014-01-31 06:45:47 +07:00
|
|
|
for_each_possible_cpu(i)
|
|
|
|
init_llist_head(&per_cpu(call_single_queue, i));
|
2009-02-25 19:59:47 +07:00
|
|
|
|
|
|
|
hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
|
|
|
|
register_cpu_notifier(&hotplug_cfd_notifier);
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
|
|
|
|
2009-02-25 19:59:47 +07:00
|
|
|
/*
|
|
|
|
* csd_lock/csd_unlock used to serialize access to per-cpu csd resources
|
|
|
|
*
|
2009-02-25 22:52:11 +07:00
|
|
|
* For non-synchronous ipi calls the csd can still be in use by the
|
|
|
|
* previous function call. For multi-cpu calls its even more interesting
|
|
|
|
* as we'll have to ensure no other cpu is observing our csd.
|
2009-02-25 19:59:47 +07:00
|
|
|
*/
|
2013-05-01 05:27:28 +07:00
|
|
|
static void csd_lock_wait(struct call_single_data *csd)
|
2009-02-25 19:59:47 +07:00
|
|
|
{
|
2013-05-01 05:27:28 +07:00
|
|
|
while (csd->flags & CSD_FLAG_LOCK)
|
2009-02-25 19:59:47 +07:00
|
|
|
cpu_relax();
|
2009-02-25 19:59:48 +07:00
|
|
|
}
|
|
|
|
|
2013-05-01 05:27:28 +07:00
|
|
|
static void csd_lock(struct call_single_data *csd)
|
2009-02-25 19:59:48 +07:00
|
|
|
{
|
2013-05-01 05:27:28 +07:00
|
|
|
csd_lock_wait(csd);
|
|
|
|
csd->flags |= CSD_FLAG_LOCK;
|
2009-02-25 19:59:47 +07:00
|
|
|
|
|
|
|
/*
|
2009-02-25 22:52:11 +07:00
|
|
|
* prevent CPU from reordering the above assignment
|
|
|
|
* to ->flags with any subsequent assignments to other
|
|
|
|
* fields of the specified call_single_data structure:
|
2009-02-25 19:59:47 +07:00
|
|
|
*/
|
|
|
|
smp_mb();
|
|
|
|
}
|
|
|
|
|
2013-05-01 05:27:28 +07:00
|
|
|
static void csd_unlock(struct call_single_data *csd)
|
2009-02-25 19:59:47 +07:00
|
|
|
{
|
2013-05-17 14:58:43 +07:00
|
|
|
WARN_ON((csd->flags & CSD_FLAG_WAIT) && !(csd->flags & CSD_FLAG_LOCK));
|
2009-02-25 22:52:11 +07:00
|
|
|
|
2009-02-25 19:59:47 +07:00
|
|
|
/*
|
2009-02-25 22:52:11 +07:00
|
|
|
* ensure we're all done before releasing data:
|
2009-02-25 19:59:47 +07:00
|
|
|
*/
|
|
|
|
smp_mb();
|
2009-02-25 22:52:11 +07:00
|
|
|
|
2013-05-01 05:27:28 +07:00
|
|
|
csd->flags &= ~CSD_FLAG_LOCK;
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
|
|
|
|
2014-02-24 22:39:58 +07:00
|
|
|
static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
|
|
|
|
|
2008-06-26 16:21:34 +07:00
|
|
|
/*
|
2009-02-25 22:52:11 +07:00
|
|
|
* Insert a previously allocated call_single_data element
|
|
|
|
* for execution on the given CPU. data must already have
|
|
|
|
* ->func, ->info, and ->flags set.
|
2008-06-26 16:21:34 +07:00
|
|
|
*/
|
2014-02-24 22:39:58 +07:00
|
|
|
static int generic_exec_single(int cpu, struct call_single_data *csd,
|
|
|
|
smp_call_func_t func, void *info, int wait)
|
2008-06-26 16:21:34 +07:00
|
|
|
{
|
2014-02-24 22:39:58 +07:00
|
|
|
struct call_single_data csd_stack = { .flags = 0 };
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
|
|
|
|
if (cpu == smp_processor_id()) {
|
|
|
|
local_irq_save(flags);
|
|
|
|
func(info);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))
|
|
|
|
return -ENXIO;
|
|
|
|
|
|
|
|
|
|
|
|
if (!csd) {
|
|
|
|
csd = &csd_stack;
|
|
|
|
if (!wait)
|
|
|
|
csd = &__get_cpu_var(csd_data);
|
|
|
|
}
|
|
|
|
|
|
|
|
csd_lock(csd);
|
|
|
|
|
|
|
|
csd->func = func;
|
|
|
|
csd->info = info;
|
|
|
|
|
2013-05-17 14:58:43 +07:00
|
|
|
if (wait)
|
|
|
|
csd->flags |= CSD_FLAG_WAIT;
|
|
|
|
|
2008-10-31 00:28:41 +07:00
|
|
|
/*
|
generic IPI: simplify barriers and locking
Simplify the barriers in generic remote function call interrupt
code.
Firstly, just unconditionally take the lock and check the list
in the generic_call_function_single_interrupt IPI handler. As
we've just taken an IPI here, the chances are fairly high that
there will be work on the list for us, so do the locking
unconditionally. This removes the tricky lockless list_empty
check and dubious barriers. The change looks bigger than it is
because it is just removing an outer loop.
Secondly, clarify architecture specific IPI locking rules.
Generic code has no tools to impose any sane ordering on IPIs if
they go outside normal cache coherency, ergo the arch code must
make them appear to obey cache coherency as a "memory operation"
to initiate an IPI, and a "memory operation" to receive one.
This way at least they can be reasoned about in generic code,
and smp_mb used to provide ordering.
The combination of these two changes means that explict barriers
can be taken out of queue handling for the single case -- shared
data is explicitly locked, and ipi ordering must conform to
that, so no barriers needed. An extra barrier is needed in the
many handler, so as to ensure we load the list element after the
IPI is received.
Does any architecture actually *need* these barriers? For the
initiator I could see it, but for the handler I would be
surprised. So the other thing we could do for simplicity is just
to require that, rather than just matching with cache coherency,
we just require a full barrier before generating an IPI, and
after receiving an IPI. In which case, the smp_mb()s can go
away. But just for now, we'll be on the safe side and use the
barriers (they're in the slow case anyway).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linux-arch@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-25 12:22:45 +07:00
|
|
|
* The list addition should be visible before sending the IPI
|
|
|
|
* handler locks the list to pull the entry off it because of
|
|
|
|
* normal cache coherency rules implied by spinlocks.
|
|
|
|
*
|
|
|
|
* If IPIs can go out of order to the cache coherency protocol
|
|
|
|
* in an architecture, sufficient synchronisation should be added
|
|
|
|
* to arch code to make it appear to obey cache coherency WRT
|
2009-02-25 22:52:11 +07:00
|
|
|
* locking and barrier primitives. Generic code isn't really
|
|
|
|
* equipped to do the right thing...
|
2008-10-31 00:28:41 +07:00
|
|
|
*/
|
2014-01-31 06:45:47 +07:00
|
|
|
if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
|
2008-06-26 16:21:34 +07:00
|
|
|
arch_send_call_function_single_ipi(cpu);
|
|
|
|
|
|
|
|
if (wait)
|
2013-05-01 05:27:28 +07:00
|
|
|
csd_lock_wait(csd);
|
2014-02-24 22:39:58 +07:00
|
|
|
|
|
|
|
return 0;
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2009-02-25 22:52:11 +07:00
|
|
|
* Invoked by arch to handle an IPI for call function single. Must be
|
|
|
|
* called from the arch with interrupts disabled.
|
2008-06-26 16:21:34 +07:00
|
|
|
*/
|
|
|
|
void generic_smp_call_function_single_interrupt(void)
|
|
|
|
{
|
2014-02-24 22:39:55 +07:00
|
|
|
struct llist_node *entry;
|
|
|
|
struct call_single_data *csd, *csd_next;
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2009-08-20 08:05:35 +07:00
|
|
|
/*
|
|
|
|
* Shouldn't receive this interrupt on a cpu that is not yet online.
|
|
|
|
*/
|
|
|
|
WARN_ON_ONCE(!cpu_online(smp_processor_id()));
|
|
|
|
|
2014-01-31 06:45:47 +07:00
|
|
|
entry = llist_del_all(&__get_cpu_var(call_single_queue));
|
|
|
|
entry = llist_reverse_order(entry);
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2014-02-24 22:39:55 +07:00
|
|
|
llist_for_each_entry_safe(csd, csd_next, entry, llist) {
|
2013-05-01 05:27:28 +07:00
|
|
|
csd->func(csd->info);
|
2013-07-30 10:06:09 +07:00
|
|
|
csd_unlock(csd);
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* smp_call_function_single - Run a function on a specific CPU
|
|
|
|
* @func: The function to run. This must be fast and non-blocking.
|
|
|
|
* @info: An arbitrary pointer to pass to the function.
|
|
|
|
* @wait: If true, wait until function has completed on other CPUs.
|
|
|
|
*
|
2009-10-22 18:19:34 +07:00
|
|
|
* Returns 0 on success, else a negative status code.
|
2008-06-26 16:21:34 +07:00
|
|
|
*/
|
2010-10-27 23:28:36 +07:00
|
|
|
int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
|
2008-06-06 16:18:06 +07:00
|
|
|
int wait)
|
2008-06-26 16:21:34 +07:00
|
|
|
{
|
2009-02-25 22:52:11 +07:00
|
|
|
int this_cpu;
|
2014-02-24 22:39:58 +07:00
|
|
|
int err;
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2009-02-25 22:52:11 +07:00
|
|
|
/*
|
|
|
|
* prevent preemption and reschedule on another processor,
|
|
|
|
* as well as CPU removal
|
|
|
|
*/
|
|
|
|
this_cpu = get_cpu();
|
|
|
|
|
2009-08-20 08:05:35 +07:00
|
|
|
/*
|
|
|
|
* Can deadlock when called with interrupts disabled.
|
|
|
|
* We allow cpu's that are not yet online though, as no one else can
|
|
|
|
* send smp call function interrupt to this cpu and as such deadlocks
|
|
|
|
* can't happen.
|
|
|
|
*/
|
|
|
|
WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
|
|
|
|
&& !oops_in_progress);
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2014-02-24 22:39:58 +07:00
|
|
|
err = generic_exec_single(cpu, NULL, func, info, wait);
|
2008-06-26 16:21:34 +07:00
|
|
|
|
|
|
|
put_cpu();
|
2009-02-25 22:52:11 +07:00
|
|
|
|
2008-08-26 07:07:14 +07:00
|
|
|
return err;
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(smp_call_function_single);
|
|
|
|
|
2014-02-24 22:39:59 +07:00
|
|
|
/**
|
2014-02-24 22:40:02 +07:00
|
|
|
* smp_call_function_single_async(): Run an asynchronous function on a
|
|
|
|
* specific CPU.
|
2014-02-24 22:39:59 +07:00
|
|
|
* @cpu: The CPU to run on.
|
|
|
|
* @csd: Pre-allocated and setup data structure
|
|
|
|
*
|
2014-02-24 22:40:02 +07:00
|
|
|
* Like smp_call_function_single(), but the call is asynchonous and
|
|
|
|
* can thus be done from contexts with disabled interrupts.
|
|
|
|
*
|
|
|
|
* The caller passes his own pre-allocated data structure
|
|
|
|
* (ie: embedded in an object) and is responsible for synchronizing it
|
|
|
|
* such that the IPIs performed on the @csd are strictly serialized.
|
|
|
|
*
|
|
|
|
* NOTE: Be careful, there is unfortunately no current debugging facility to
|
|
|
|
* validate the correctness of this serialization.
|
2014-02-24 22:39:59 +07:00
|
|
|
*/
|
2014-02-24 22:40:02 +07:00
|
|
|
int smp_call_function_single_async(int cpu, struct call_single_data *csd)
|
2014-02-24 22:39:59 +07:00
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
|
2014-02-24 22:40:01 +07:00
|
|
|
preempt_disable();
|
|
|
|
err = generic_exec_single(cpu, csd, csd->func, csd->info, 0);
|
|
|
|
preempt_enable();
|
2014-02-24 22:39:59 +07:00
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
2014-02-24 22:40:02 +07:00
|
|
|
EXPORT_SYMBOL_GPL(smp_call_function_single_async);
|
2014-02-24 22:39:59 +07:00
|
|
|
|
2009-11-18 05:27:27 +07:00
|
|
|
/*
|
|
|
|
* smp_call_function_any - Run a function on any of the given cpus
|
|
|
|
* @mask: The mask of cpus it can run on.
|
|
|
|
* @func: The function to run. This must be fast and non-blocking.
|
|
|
|
* @info: An arbitrary pointer to pass to the function.
|
|
|
|
* @wait: If true, wait until function has completed.
|
|
|
|
*
|
|
|
|
* Returns 0 on success, else a negative status code (if no cpus were online).
|
|
|
|
*
|
|
|
|
* Selection preference:
|
|
|
|
* 1) current cpu if in @mask
|
|
|
|
* 2) any cpu of current node if in @mask
|
|
|
|
* 3) any other online cpu in @mask
|
|
|
|
*/
|
|
|
|
int smp_call_function_any(const struct cpumask *mask,
|
2010-10-27 23:28:36 +07:00
|
|
|
smp_call_func_t func, void *info, int wait)
|
2009-11-18 05:27:27 +07:00
|
|
|
{
|
|
|
|
unsigned int cpu;
|
|
|
|
const struct cpumask *nodemask;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
/* Try for same CPU (cheapest) */
|
|
|
|
cpu = get_cpu();
|
|
|
|
if (cpumask_test_cpu(cpu, mask))
|
|
|
|
goto call;
|
|
|
|
|
|
|
|
/* Try for same node. */
|
2010-01-16 08:01:23 +07:00
|
|
|
nodemask = cpumask_of_node(cpu_to_node(cpu));
|
2009-11-18 05:27:27 +07:00
|
|
|
for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids;
|
|
|
|
cpu = cpumask_next_and(cpu, nodemask, mask)) {
|
|
|
|
if (cpu_online(cpu))
|
|
|
|
goto call;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Any online will do: smp_call_function_single handles nr_cpu_ids. */
|
|
|
|
cpu = cpumask_any_and(mask, cpu_online_mask);
|
|
|
|
call:
|
|
|
|
ret = smp_call_function_single(cpu, func, info, wait);
|
|
|
|
put_cpu();
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(smp_call_function_any);
|
|
|
|
|
2008-06-26 16:21:34 +07:00
|
|
|
/**
|
2008-12-30 05:35:16 +07:00
|
|
|
* smp_call_function_many(): Run a function on a set of other CPUs.
|
|
|
|
* @mask: The set of cpus to run on (only runs on online subset).
|
2008-06-26 16:21:34 +07:00
|
|
|
* @func: The function to run. This must be fast and non-blocking.
|
|
|
|
* @info: An arbitrary pointer to pass to the function.
|
2009-02-25 22:52:11 +07:00
|
|
|
* @wait: If true, wait (atomically) until function has completed
|
|
|
|
* on other CPUs.
|
2008-06-26 16:21:34 +07:00
|
|
|
*
|
2009-10-22 18:19:34 +07:00
|
|
|
* If @wait is true, then returns once @func has returned.
|
2008-06-26 16:21:34 +07:00
|
|
|
*
|
|
|
|
* You must not call this function with disabled interrupts or from a
|
|
|
|
* hardware interrupt handler or from a bottom half handler. Preemption
|
|
|
|
* must be disabled when calling this function.
|
|
|
|
*/
|
2008-12-30 05:35:16 +07:00
|
|
|
void smp_call_function_many(const struct cpumask *mask,
|
2010-10-27 23:28:36 +07:00
|
|
|
smp_call_func_t func, void *info, bool wait)
|
2008-06-26 16:21:34 +07:00
|
|
|
{
|
2013-05-01 05:27:28 +07:00
|
|
|
struct call_function_data *cfd;
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
int cpu, next_cpu, this_cpu = smp_processor_id();
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2009-08-20 08:05:35 +07:00
|
|
|
/*
|
|
|
|
* Can deadlock when called with interrupts disabled.
|
|
|
|
* We allow cpu's that are not yet online though, as no one else can
|
|
|
|
* send smp call function interrupt to this cpu and as such deadlocks
|
|
|
|
* can't happen.
|
|
|
|
*/
|
|
|
|
WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
|
2011-01-20 18:07:13 +07:00
|
|
|
&& !oops_in_progress && !early_boot_irqs_disabled);
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2011-03-16 02:27:17 +07:00
|
|
|
/* Try to fastpath. So, what's a CPU they want? Ignoring this one. */
|
2008-12-30 05:35:16 +07:00
|
|
|
cpu = cpumask_first_and(mask, cpu_online_mask);
|
2009-02-25 22:52:11 +07:00
|
|
|
if (cpu == this_cpu)
|
2008-12-30 05:35:16 +07:00
|
|
|
cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
|
2009-02-25 22:52:11 +07:00
|
|
|
|
2008-12-30 05:35:16 +07:00
|
|
|
/* No online cpus? We're done. */
|
|
|
|
if (cpu >= nr_cpu_ids)
|
|
|
|
return;
|
|
|
|
|
|
|
|
/* Do we have another CPU which isn't us? */
|
|
|
|
next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
|
2009-02-25 22:52:11 +07:00
|
|
|
if (next_cpu == this_cpu)
|
2008-12-30 05:35:16 +07:00
|
|
|
next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
|
|
|
|
|
|
|
|
/* Fastpath: do that cpu by itself. */
|
|
|
|
if (next_cpu >= nr_cpu_ids) {
|
|
|
|
smp_call_function_single(cpu, func, info, wait);
|
|
|
|
return;
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
|
|
|
|
2013-05-01 05:27:28 +07:00
|
|
|
cfd = &__get_cpu_var(cfd_data);
|
2011-03-16 02:27:16 +07:00
|
|
|
|
2013-05-01 05:27:28 +07:00
|
|
|
cpumask_and(cfd->cpumask, mask, cpu_online_mask);
|
|
|
|
cpumask_clear_cpu(this_cpu, cfd->cpumask);
|
2011-03-16 02:27:17 +07:00
|
|
|
|
|
|
|
/* Some callers race with other cpus changing the passed mask */
|
2013-05-01 05:27:28 +07:00
|
|
|
if (unlikely(!cpumask_weight(cfd->cpumask)))
|
2011-03-16 02:27:17 +07:00
|
|
|
return;
|
2008-06-26 16:21:34 +07:00
|
|
|
|
2013-05-01 05:27:28 +07:00
|
|
|
for_each_cpu(cpu, cfd->cpumask) {
|
|
|
|
struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
|
|
|
|
csd_lock(csd);
|
|
|
|
csd->func = func;
|
|
|
|
csd->info = info;
|
2014-01-31 06:45:47 +07:00
|
|
|
llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
}
|
2008-10-31 00:28:41 +07:00
|
|
|
|
2008-06-26 16:21:34 +07:00
|
|
|
/* Send a message to all CPUs in the map */
|
2014-01-31 06:45:48 +07:00
|
|
|
arch_send_call_function_ipi_mask(cfd->cpumask);
|
2008-06-26 16:21:34 +07:00
|
|
|
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
if (wait) {
|
2013-05-01 05:27:28 +07:00
|
|
|
for_each_cpu(cpu, cfd->cpumask) {
|
|
|
|
struct call_single_data *csd;
|
|
|
|
|
|
|
|
csd = per_cpu_ptr(cfd->csd, cpu);
|
smp: make smp_call_function_many() use logic similar to smp_call_function_single()
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 07:43:03 +07:00
|
|
|
csd_lock_wait(csd);
|
|
|
|
}
|
|
|
|
}
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
2008-12-30 05:35:16 +07:00
|
|
|
EXPORT_SYMBOL(smp_call_function_many);
|
2008-06-26 16:21:34 +07:00
|
|
|
|
|
|
|
/**
|
|
|
|
* smp_call_function(): Run a function on all other CPUs.
|
|
|
|
* @func: The function to run. This must be fast and non-blocking.
|
|
|
|
* @info: An arbitrary pointer to pass to the function.
|
2009-02-25 22:52:11 +07:00
|
|
|
* @wait: If true, wait (atomically) until function has completed
|
|
|
|
* on other CPUs.
|
2008-06-26 16:21:34 +07:00
|
|
|
*
|
2008-12-30 05:35:16 +07:00
|
|
|
* Returns 0.
|
2008-06-26 16:21:34 +07:00
|
|
|
*
|
|
|
|
* If @wait is true, then returns once @func has returned; otherwise
|
2009-10-22 18:19:34 +07:00
|
|
|
* it returns just before the target cpu calls @func.
|
2008-06-26 16:21:34 +07:00
|
|
|
*
|
|
|
|
* You must not call this function with disabled interrupts or from a
|
|
|
|
* hardware interrupt handler or from a bottom half handler.
|
|
|
|
*/
|
2010-10-27 23:28:36 +07:00
|
|
|
int smp_call_function(smp_call_func_t func, void *info, int wait)
|
2008-06-26 16:21:34 +07:00
|
|
|
{
|
|
|
|
preempt_disable();
|
2008-12-30 05:35:16 +07:00
|
|
|
smp_call_function_many(cpu_online_mask, func, info, wait);
|
2008-06-26 16:21:34 +07:00
|
|
|
preempt_enable();
|
2009-02-25 22:52:11 +07:00
|
|
|
|
2008-12-30 05:35:16 +07:00
|
|
|
return 0;
|
2008-06-26 16:21:34 +07:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(smp_call_function);
|
2011-01-13 07:59:39 +07:00
|
|
|
|
2011-03-23 06:34:06 +07:00
|
|
|
/* Setup configured maximum number of CPUs to activate */
|
|
|
|
unsigned int setup_max_cpus = NR_CPUS;
|
|
|
|
EXPORT_SYMBOL(setup_max_cpus);
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Setup routine for controlling SMP activation
|
|
|
|
*
|
|
|
|
* Command-line option of "nosmp" or "maxcpus=0" will disable SMP
|
|
|
|
* activation entirely (the MPS table probe still happens, though).
|
|
|
|
*
|
|
|
|
* Command-line option of "maxcpus=<NUM>", where <NUM> is an integer
|
|
|
|
* greater than 0, limits the maximum number of CPUs activated in
|
|
|
|
* SMP mode to <NUM>.
|
|
|
|
*/
|
|
|
|
|
|
|
|
void __weak arch_disable_smp_support(void) { }
|
|
|
|
|
|
|
|
static int __init nosmp(char *str)
|
|
|
|
{
|
|
|
|
setup_max_cpus = 0;
|
|
|
|
arch_disable_smp_support();
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
early_param("nosmp", nosmp);
|
|
|
|
|
|
|
|
/* this is hard limit */
|
|
|
|
static int __init nrcpus(char *str)
|
|
|
|
{
|
|
|
|
int nr_cpus;
|
|
|
|
|
|
|
|
get_option(&str, &nr_cpus);
|
|
|
|
if (nr_cpus > 0 && nr_cpus < nr_cpu_ids)
|
|
|
|
nr_cpu_ids = nr_cpus;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
early_param("nr_cpus", nrcpus);
|
|
|
|
|
|
|
|
static int __init maxcpus(char *str)
|
|
|
|
{
|
|
|
|
get_option(&str, &setup_max_cpus);
|
|
|
|
if (setup_max_cpus == 0)
|
|
|
|
arch_disable_smp_support();
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
early_param("maxcpus", maxcpus);
|
|
|
|
|
|
|
|
/* Setup number of possible processor ids */
|
|
|
|
int nr_cpu_ids __read_mostly = NR_CPUS;
|
|
|
|
EXPORT_SYMBOL(nr_cpu_ids);
|
|
|
|
|
|
|
|
/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
|
|
|
|
void __init setup_nr_cpu_ids(void)
|
|
|
|
{
|
|
|
|
nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
|
|
|
|
}
|
|
|
|
|
x86/boot: Further compress CPUs bootup message
Turn it into (for example):
[ 0.073380] x86: Booting SMP configuration:
[ 0.074005] .... node #0, CPUs: #1 #2 #3 #4 #5 #6 #7
[ 0.603005] .... node #1, CPUs: #8 #9 #10 #11 #12 #13 #14 #15
[ 1.200005] .... node #2, CPUs: #16 #17 #18 #19 #20 #21 #22 #23
[ 1.796005] .... node #3, CPUs: #24 #25 #26 #27 #28 #29 #30 #31
[ 2.393005] .... node #4, CPUs: #32 #33 #34 #35 #36 #37 #38 #39
[ 2.996005] .... node #5, CPUs: #40 #41 #42 #43 #44 #45 #46 #47
[ 3.600005] .... node #6, CPUs: #48 #49 #50 #51 #52 #53 #54 #55
[ 4.202005] .... node #7, CPUs: #56 #57 #58 #59 #60 #61 #62 #63
[ 4.811005] .... node #8, CPUs: #64 #65 #66 #67 #68 #69 #70 #71
[ 5.421006] .... node #9, CPUs: #72 #73 #74 #75 #76 #77 #78 #79
[ 6.032005] .... node #10, CPUs: #80 #81 #82 #83 #84 #85 #86 #87
[ 6.648006] .... node #11, CPUs: #88 #89 #90 #91 #92 #93 #94 #95
[ 7.262005] .... node #12, CPUs: #96 #97 #98 #99 #100 #101 #102 #103
[ 7.865005] .... node #13, CPUs: #104 #105 #106 #107 #108 #109 #110 #111
[ 8.466005] .... node #14, CPUs: #112 #113 #114 #115 #116 #117 #118 #119
[ 9.073006] .... node #15, CPUs: #120 #121 #122 #123 #124 #125 #126 #127
[ 9.679901] x86: Booted up 16 nodes, 128 CPUs
and drop useless elements.
Change num_digits() to hpa's division-avoiding, cell-phone-typed
version which he went at great lengths and pains to submit on a
Saturday evening.
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: huawei.libin@huawei.com
Cc: wangyijing@huawei.com
Cc: fenghua.yu@intel.com
Cc: guohanjun@huawei.com
Cc: paul.gortmaker@windriver.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20130930095624.GB16383@pd.tnic
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-09-30 16:56:24 +07:00
|
|
|
void __weak smp_announce(void)
|
|
|
|
{
|
|
|
|
printk(KERN_INFO "Brought up %d CPUs\n", num_online_cpus());
|
|
|
|
}
|
|
|
|
|
2011-03-23 06:34:06 +07:00
|
|
|
/* Called by boot processor to activate the rest. */
|
|
|
|
void __init smp_init(void)
|
|
|
|
{
|
|
|
|
unsigned int cpu;
|
|
|
|
|
2012-04-21 07:08:50 +07:00
|
|
|
idle_threads_init();
|
|
|
|
|
2011-03-23 06:34:06 +07:00
|
|
|
/* FIXME: This should be done in userspace --RR */
|
|
|
|
for_each_present_cpu(cpu) {
|
|
|
|
if (num_online_cpus() >= setup_max_cpus)
|
|
|
|
break;
|
|
|
|
if (!cpu_online(cpu))
|
|
|
|
cpu_up(cpu);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Any cleanup work */
|
x86/boot: Further compress CPUs bootup message
Turn it into (for example):
[ 0.073380] x86: Booting SMP configuration:
[ 0.074005] .... node #0, CPUs: #1 #2 #3 #4 #5 #6 #7
[ 0.603005] .... node #1, CPUs: #8 #9 #10 #11 #12 #13 #14 #15
[ 1.200005] .... node #2, CPUs: #16 #17 #18 #19 #20 #21 #22 #23
[ 1.796005] .... node #3, CPUs: #24 #25 #26 #27 #28 #29 #30 #31
[ 2.393005] .... node #4, CPUs: #32 #33 #34 #35 #36 #37 #38 #39
[ 2.996005] .... node #5, CPUs: #40 #41 #42 #43 #44 #45 #46 #47
[ 3.600005] .... node #6, CPUs: #48 #49 #50 #51 #52 #53 #54 #55
[ 4.202005] .... node #7, CPUs: #56 #57 #58 #59 #60 #61 #62 #63
[ 4.811005] .... node #8, CPUs: #64 #65 #66 #67 #68 #69 #70 #71
[ 5.421006] .... node #9, CPUs: #72 #73 #74 #75 #76 #77 #78 #79
[ 6.032005] .... node #10, CPUs: #80 #81 #82 #83 #84 #85 #86 #87
[ 6.648006] .... node #11, CPUs: #88 #89 #90 #91 #92 #93 #94 #95
[ 7.262005] .... node #12, CPUs: #96 #97 #98 #99 #100 #101 #102 #103
[ 7.865005] .... node #13, CPUs: #104 #105 #106 #107 #108 #109 #110 #111
[ 8.466005] .... node #14, CPUs: #112 #113 #114 #115 #116 #117 #118 #119
[ 9.073006] .... node #15, CPUs: #120 #121 #122 #123 #124 #125 #126 #127
[ 9.679901] x86: Booted up 16 nodes, 128 CPUs
and drop useless elements.
Change num_digits() to hpa's division-avoiding, cell-phone-typed
version which he went at great lengths and pains to submit on a
Saturday evening.
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: huawei.libin@huawei.com
Cc: wangyijing@huawei.com
Cc: fenghua.yu@intel.com
Cc: guohanjun@huawei.com
Cc: paul.gortmaker@windriver.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20130930095624.GB16383@pd.tnic
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-09-30 16:56:24 +07:00
|
|
|
smp_announce();
|
2011-03-23 06:34:06 +07:00
|
|
|
smp_cpus_done(setup_max_cpus);
|
|
|
|
}
|
|
|
|
|
2011-01-13 07:59:39 +07:00
|
|
|
/*
|
2011-01-20 18:07:13 +07:00
|
|
|
* Call a function on all processors. May be used during early boot while
|
|
|
|
* early_boot_irqs_disabled is set. Use local_irq_save/restore() instead
|
|
|
|
* of local_irq_disable/enable().
|
2011-01-13 07:59:39 +07:00
|
|
|
*/
|
|
|
|
int on_each_cpu(void (*func) (void *info), void *info, int wait)
|
|
|
|
{
|
2011-01-20 18:07:13 +07:00
|
|
|
unsigned long flags;
|
2011-01-13 07:59:39 +07:00
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
preempt_disable();
|
|
|
|
ret = smp_call_function(func, info, wait);
|
2011-01-20 18:07:13 +07:00
|
|
|
local_irq_save(flags);
|
2011-01-13 07:59:39 +07:00
|
|
|
func(info);
|
2011-01-20 18:07:13 +07:00
|
|
|
local_irq_restore(flags);
|
2011-01-13 07:59:39 +07:00
|
|
|
preempt_enable();
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(on_each_cpu);
|
smp: introduce a generic on_each_cpu_mask() function
We have lots of infrastructure in place to partition multi-core systems
such that we have a group of CPUs that are dedicated to specific task:
cgroups, scheduler and interrupt affinity, and cpuisol= boot parameter.
Still, kernel code will at times interrupt all CPUs in the system via IPIs
for various needs. These IPIs are useful and cannot be avoided
altogether, but in certain cases it is possible to interrupt only specific
CPUs that have useful work to do and not the entire system.
This patch set, inspired by discussions with Peter Zijlstra and Frederic
Weisbecker when testing the nohz task patch set, is a first stab at trying
to explore doing this by locating the places where such global IPI calls
are being made and turning the global IPI into an IPI for a specific group
of CPUs. The purpose of the patch set is to get feedback if this is the
right way to go for dealing with this issue and indeed, if the issue is
even worth dealing with at all. Based on the feedback from this patch set
I plan to offer further patches that address similar issue in other code
paths.
This patch creates an on_each_cpu_mask() and on_each_cpu_cond()
infrastructure API (the former derived from existing arch specific
versions in Tile and Arm) and uses them to turn several global IPI
invocation to per CPU group invocations.
Core kernel:
on_each_cpu_mask() calls a function on processors specified by cpumask,
which may or may not include the local processor.
You must not call this function with disabled interrupts or from a
hardware interrupt handler or from a bottom half handler.
arch/arm:
Note that the generic version is a little different then the Arm one:
1. It has the mask as first parameter
2. It calls the function on the calling CPU with interrupts disabled,
but this should be OK since the function is called on the other CPUs
with interrupts disabled anyway.
arch/tile:
The API is the same as the tile private one, but the generic version
also calls the function on the with interrupts disabled in UP case
This is OK since the function is called on the other CPUs
with interrupts disabled.
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Michal Nazarewicz <mina86@mina86.org>
Cc: Kosaki Motohiro <kosaki.motohiro@gmail.com>
Cc: Milton Miller <miltonm@bga.com>
Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-29 04:42:43 +07:00
|
|
|
|
|
|
|
/**
|
|
|
|
* on_each_cpu_mask(): Run a function on processors specified by
|
|
|
|
* cpumask, which may include the local processor.
|
|
|
|
* @mask: The set of cpus to run on (only runs on online subset).
|
|
|
|
* @func: The function to run. This must be fast and non-blocking.
|
|
|
|
* @info: An arbitrary pointer to pass to the function.
|
|
|
|
* @wait: If true, wait (atomically) until function has completed
|
|
|
|
* on other CPUs.
|
|
|
|
*
|
|
|
|
* If @wait is true, then returns once @func has returned.
|
|
|
|
*
|
2013-09-12 04:23:29 +07:00
|
|
|
* You must not call this function with disabled interrupts or from a
|
|
|
|
* hardware interrupt handler or from a bottom half handler. The
|
|
|
|
* exception is that it may be used during early boot while
|
|
|
|
* early_boot_irqs_disabled is set.
|
smp: introduce a generic on_each_cpu_mask() function
We have lots of infrastructure in place to partition multi-core systems
such that we have a group of CPUs that are dedicated to specific task:
cgroups, scheduler and interrupt affinity, and cpuisol= boot parameter.
Still, kernel code will at times interrupt all CPUs in the system via IPIs
for various needs. These IPIs are useful and cannot be avoided
altogether, but in certain cases it is possible to interrupt only specific
CPUs that have useful work to do and not the entire system.
This patch set, inspired by discussions with Peter Zijlstra and Frederic
Weisbecker when testing the nohz task patch set, is a first stab at trying
to explore doing this by locating the places where such global IPI calls
are being made and turning the global IPI into an IPI for a specific group
of CPUs. The purpose of the patch set is to get feedback if this is the
right way to go for dealing with this issue and indeed, if the issue is
even worth dealing with at all. Based on the feedback from this patch set
I plan to offer further patches that address similar issue in other code
paths.
This patch creates an on_each_cpu_mask() and on_each_cpu_cond()
infrastructure API (the former derived from existing arch specific
versions in Tile and Arm) and uses them to turn several global IPI
invocation to per CPU group invocations.
Core kernel:
on_each_cpu_mask() calls a function on processors specified by cpumask,
which may or may not include the local processor.
You must not call this function with disabled interrupts or from a
hardware interrupt handler or from a bottom half handler.
arch/arm:
Note that the generic version is a little different then the Arm one:
1. It has the mask as first parameter
2. It calls the function on the calling CPU with interrupts disabled,
but this should be OK since the function is called on the other CPUs
with interrupts disabled anyway.
arch/tile:
The API is the same as the tile private one, but the generic version
also calls the function on the with interrupts disabled in UP case
This is OK since the function is called on the other CPUs
with interrupts disabled.
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Michal Nazarewicz <mina86@mina86.org>
Cc: Kosaki Motohiro <kosaki.motohiro@gmail.com>
Cc: Milton Miller <miltonm@bga.com>
Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-29 04:42:43 +07:00
|
|
|
*/
|
|
|
|
void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
|
|
|
|
void *info, bool wait)
|
|
|
|
{
|
|
|
|
int cpu = get_cpu();
|
|
|
|
|
|
|
|
smp_call_function_many(mask, func, info, wait);
|
|
|
|
if (cpumask_test_cpu(cpu, mask)) {
|
2013-09-12 04:23:29 +07:00
|
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
smp: introduce a generic on_each_cpu_mask() function
We have lots of infrastructure in place to partition multi-core systems
such that we have a group of CPUs that are dedicated to specific task:
cgroups, scheduler and interrupt affinity, and cpuisol= boot parameter.
Still, kernel code will at times interrupt all CPUs in the system via IPIs
for various needs. These IPIs are useful and cannot be avoided
altogether, but in certain cases it is possible to interrupt only specific
CPUs that have useful work to do and not the entire system.
This patch set, inspired by discussions with Peter Zijlstra and Frederic
Weisbecker when testing the nohz task patch set, is a first stab at trying
to explore doing this by locating the places where such global IPI calls
are being made and turning the global IPI into an IPI for a specific group
of CPUs. The purpose of the patch set is to get feedback if this is the
right way to go for dealing with this issue and indeed, if the issue is
even worth dealing with at all. Based on the feedback from this patch set
I plan to offer further patches that address similar issue in other code
paths.
This patch creates an on_each_cpu_mask() and on_each_cpu_cond()
infrastructure API (the former derived from existing arch specific
versions in Tile and Arm) and uses them to turn several global IPI
invocation to per CPU group invocations.
Core kernel:
on_each_cpu_mask() calls a function on processors specified by cpumask,
which may or may not include the local processor.
You must not call this function with disabled interrupts or from a
hardware interrupt handler or from a bottom half handler.
arch/arm:
Note that the generic version is a little different then the Arm one:
1. It has the mask as first parameter
2. It calls the function on the calling CPU with interrupts disabled,
but this should be OK since the function is called on the other CPUs
with interrupts disabled anyway.
arch/tile:
The API is the same as the tile private one, but the generic version
also calls the function on the with interrupts disabled in UP case
This is OK since the function is called on the other CPUs
with interrupts disabled.
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Michal Nazarewicz <mina86@mina86.org>
Cc: Kosaki Motohiro <kosaki.motohiro@gmail.com>
Cc: Milton Miller <miltonm@bga.com>
Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-29 04:42:43 +07:00
|
|
|
func(info);
|
2013-09-12 04:23:29 +07:00
|
|
|
local_irq_restore(flags);
|
smp: introduce a generic on_each_cpu_mask() function
We have lots of infrastructure in place to partition multi-core systems
such that we have a group of CPUs that are dedicated to specific task:
cgroups, scheduler and interrupt affinity, and cpuisol= boot parameter.
Still, kernel code will at times interrupt all CPUs in the system via IPIs
for various needs. These IPIs are useful and cannot be avoided
altogether, but in certain cases it is possible to interrupt only specific
CPUs that have useful work to do and not the entire system.
This patch set, inspired by discussions with Peter Zijlstra and Frederic
Weisbecker when testing the nohz task patch set, is a first stab at trying
to explore doing this by locating the places where such global IPI calls
are being made and turning the global IPI into an IPI for a specific group
of CPUs. The purpose of the patch set is to get feedback if this is the
right way to go for dealing with this issue and indeed, if the issue is
even worth dealing with at all. Based on the feedback from this patch set
I plan to offer further patches that address similar issue in other code
paths.
This patch creates an on_each_cpu_mask() and on_each_cpu_cond()
infrastructure API (the former derived from existing arch specific
versions in Tile and Arm) and uses them to turn several global IPI
invocation to per CPU group invocations.
Core kernel:
on_each_cpu_mask() calls a function on processors specified by cpumask,
which may or may not include the local processor.
You must not call this function with disabled interrupts or from a
hardware interrupt handler or from a bottom half handler.
arch/arm:
Note that the generic version is a little different then the Arm one:
1. It has the mask as first parameter
2. It calls the function on the calling CPU with interrupts disabled,
but this should be OK since the function is called on the other CPUs
with interrupts disabled anyway.
arch/tile:
The API is the same as the tile private one, but the generic version
also calls the function on the with interrupts disabled in UP case
This is OK since the function is called on the other CPUs
with interrupts disabled.
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Michal Nazarewicz <mina86@mina86.org>
Cc: Kosaki Motohiro <kosaki.motohiro@gmail.com>
Cc: Milton Miller <miltonm@bga.com>
Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-29 04:42:43 +07:00
|
|
|
}
|
|
|
|
put_cpu();
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(on_each_cpu_mask);
|
2012-03-29 04:42:43 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* on_each_cpu_cond(): Call a function on each processor for which
|
|
|
|
* the supplied function cond_func returns true, optionally waiting
|
|
|
|
* for all the required CPUs to finish. This may include the local
|
|
|
|
* processor.
|
|
|
|
* @cond_func: A callback function that is passed a cpu id and
|
|
|
|
* the the info parameter. The function is called
|
|
|
|
* with preemption disabled. The function should
|
|
|
|
* return a blooean value indicating whether to IPI
|
|
|
|
* the specified CPU.
|
|
|
|
* @func: The function to run on all applicable CPUs.
|
|
|
|
* This must be fast and non-blocking.
|
|
|
|
* @info: An arbitrary pointer to pass to both functions.
|
|
|
|
* @wait: If true, wait (atomically) until function has
|
|
|
|
* completed on other CPUs.
|
|
|
|
* @gfp_flags: GFP flags to use when allocating the cpumask
|
|
|
|
* used internally by the function.
|
|
|
|
*
|
|
|
|
* The function might sleep if the GFP flags indicates a non
|
|
|
|
* atomic allocation is allowed.
|
|
|
|
*
|
|
|
|
* Preemption is disabled to protect against CPUs going offline but not online.
|
|
|
|
* CPUs going online during the call will not be seen or sent an IPI.
|
|
|
|
*
|
|
|
|
* You must not call this function with disabled interrupts or
|
|
|
|
* from a hardware interrupt handler or from a bottom half handler.
|
|
|
|
*/
|
|
|
|
void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
|
|
|
|
smp_call_func_t func, void *info, bool wait,
|
|
|
|
gfp_t gfp_flags)
|
|
|
|
{
|
|
|
|
cpumask_var_t cpus;
|
|
|
|
int cpu, ret;
|
|
|
|
|
|
|
|
might_sleep_if(gfp_flags & __GFP_WAIT);
|
|
|
|
|
|
|
|
if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
|
|
|
|
preempt_disable();
|
|
|
|
for_each_online_cpu(cpu)
|
|
|
|
if (cond_func(cpu, info))
|
|
|
|
cpumask_set_cpu(cpu, cpus);
|
|
|
|
on_each_cpu_mask(cpus, func, info, wait);
|
|
|
|
preempt_enable();
|
|
|
|
free_cpumask_var(cpus);
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* No free cpumask, bother. No matter, we'll
|
|
|
|
* just have to IPI them one by one.
|
|
|
|
*/
|
|
|
|
preempt_disable();
|
|
|
|
for_each_online_cpu(cpu)
|
|
|
|
if (cond_func(cpu, info)) {
|
|
|
|
ret = smp_call_function_single(cpu, func,
|
|
|
|
info, wait);
|
|
|
|
WARN_ON_ONCE(!ret);
|
|
|
|
}
|
|
|
|
preempt_enable();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(on_each_cpu_cond);
|
2012-05-08 00:59:48 +07:00
|
|
|
|
|
|
|
static void do_nothing(void *unused)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* kick_all_cpus_sync - Force all cpus out of idle
|
|
|
|
*
|
|
|
|
* Used to synchronize the update of pm_idle function pointer. It's
|
|
|
|
* called after the pointer is updated and returns after the dummy
|
|
|
|
* callback function has been executed on all cpus. The execution of
|
|
|
|
* the function can only happen on the remote cpus after they have
|
|
|
|
* left the idle function which had been called via pm_idle function
|
|
|
|
* pointer. So it's guaranteed that nothing uses the previous pointer
|
|
|
|
* anymore.
|
|
|
|
*/
|
|
|
|
void kick_all_cpus_sync(void)
|
|
|
|
{
|
|
|
|
/* Make sure the change is visible before we kick the cpus */
|
|
|
|
smp_mb();
|
|
|
|
smp_call_function(do_nothing, NULL, 1);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
|