kernel-ark/kernel/smp.c
Shaohua Li 9a46ad6d6d 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>
2013-02-21 17:22:20 -08:00

689 lines
18 KiB
C

/*
* Generic helpers for smp ipi calls
*
* (C) Jens Axboe <jens.axboe@oracle.com> 2008
*/
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/gfp.h>
#include <linux/smp.h>
#include <linux/cpu.h>
#include "smpboot.h"
#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
enum {
CSD_FLAG_LOCK = 0x01,
};
struct call_function_data {
struct call_single_data __percpu *csd;
cpumask_var_t cpumask;
cpumask_var_t cpumask_ipi;
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
struct call_single_queue {
struct list_head list;
raw_spinlock_t lock;
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_queue, call_single_queue);
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:
if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
cpu_to_node(cpu)))
return notifier_from_errno(-ENOMEM);
if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
cpu_to_node(cpu)))
return notifier_from_errno(-ENOMEM);
cfd->csd = alloc_percpu(struct call_single_data);
if (!cfd->csd) {
free_cpumask_var(cfd->cpumask);
return notifier_from_errno(-ENOMEM);
}
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
free_cpumask_var(cfd->cpumask);
free_cpumask_var(cfd->cpumask_ipi);
free_percpu(cfd->csd);
break;
#endif
};
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
.notifier_call = hotplug_cfd,
};
void __init call_function_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int i;
for_each_possible_cpu(i) {
struct call_single_queue *q = &per_cpu(call_single_queue, i);
raw_spin_lock_init(&q->lock);
INIT_LIST_HEAD(&q->list);
}
hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
register_cpu_notifier(&hotplug_cfd_notifier);
}
/*
* csd_lock/csd_unlock used to serialize access to per-cpu csd resources
*
* 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.
*/
static void csd_lock_wait(struct call_single_data *data)
{
while (data->flags & CSD_FLAG_LOCK)
cpu_relax();
}
static void csd_lock(struct call_single_data *data)
{
csd_lock_wait(data);
data->flags = CSD_FLAG_LOCK;
/*
* prevent CPU from reordering the above assignment
* to ->flags with any subsequent assignments to other
* fields of the specified call_single_data structure:
*/
smp_mb();
}
static void csd_unlock(struct call_single_data *data)
{
WARN_ON(!(data->flags & CSD_FLAG_LOCK));
/*
* ensure we're all done before releasing data:
*/
smp_mb();
data->flags &= ~CSD_FLAG_LOCK;
}
/*
* Insert a previously allocated call_single_data element
* for execution on the given CPU. data must already have
* ->func, ->info, and ->flags set.
*/
static
void generic_exec_single(int cpu, struct call_single_data *data, int wait)
{
struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
unsigned long flags;
int ipi;
raw_spin_lock_irqsave(&dst->lock, flags);
ipi = list_empty(&dst->list);
list_add_tail(&data->list, &dst->list);
raw_spin_unlock_irqrestore(&dst->lock, flags);
/*
* 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
* locking and barrier primitives. Generic code isn't really
* equipped to do the right thing...
*/
if (ipi)
arch_send_call_function_single_ipi(cpu);
if (wait)
csd_lock_wait(data);
}
/*
* Invoked by arch to handle an IPI for call function single. Must be
* called from the arch with interrupts disabled.
*/
void generic_smp_call_function_single_interrupt(void)
{
struct call_single_queue *q = &__get_cpu_var(call_single_queue);
unsigned int data_flags;
LIST_HEAD(list);
/*
* Shouldn't receive this interrupt on a cpu that is not yet online.
*/
WARN_ON_ONCE(!cpu_online(smp_processor_id()));
raw_spin_lock(&q->lock);
list_replace_init(&q->list, &list);
raw_spin_unlock(&q->lock);
while (!list_empty(&list)) {
struct call_single_data *data;
data = list_entry(list.next, struct call_single_data, list);
list_del(&data->list);
/*
* 'data' can be invalid after this call if flags == 0
* (when called through generic_exec_single()),
* so save them away before making the call:
*/
data_flags = data->flags;
data->func(data->info);
/*
* Unlocked CSDs are valid through generic_exec_single():
*/
if (data_flags & CSD_FLAG_LOCK)
csd_unlock(data);
}
}
static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
/*
* 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.
*
* Returns 0 on success, else a negative status code.
*/
int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
int wait)
{
struct call_single_data d = {
.flags = 0,
};
unsigned long flags;
int this_cpu;
int err = 0;
/*
* prevent preemption and reschedule on another processor,
* as well as CPU removal
*/
this_cpu = get_cpu();
/*
* 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);
if (cpu == this_cpu) {
local_irq_save(flags);
func(info);
local_irq_restore(flags);
} else {
if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
struct call_single_data *data = &d;
if (!wait)
data = &__get_cpu_var(csd_data);
csd_lock(data);
data->func = func;
data->info = info;
generic_exec_single(cpu, data, wait);
} else {
err = -ENXIO; /* CPU not online */
}
}
put_cpu();
return err;
}
EXPORT_SYMBOL(smp_call_function_single);
/*
* 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).
* Note that @wait will be implicitly turned on in case of allocation failures,
* since we fall back to on-stack allocation.
*
* 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,
smp_call_func_t func, void *info, int wait)
{
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. */
nodemask = cpumask_of_node(cpu_to_node(cpu));
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);
/**
* __smp_call_function_single(): Run a function on a specific CPU
* @cpu: The CPU to run on.
* @data: Pre-allocated and setup data structure
* @wait: If true, wait until function has completed on specified CPU.
*
* Like smp_call_function_single(), but allow caller to pass in a
* pre-allocated data structure. Useful for embedding @data inside
* other structures, for instance.
*/
void __smp_call_function_single(int cpu, struct call_single_data *data,
int wait)
{
unsigned int this_cpu;
unsigned long flags;
this_cpu = get_cpu();
/*
* 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(smp_processor_id()) && wait && irqs_disabled()
&& !oops_in_progress);
if (cpu == this_cpu) {
local_irq_save(flags);
data->func(data->info);
local_irq_restore(flags);
} else {
csd_lock(data);
generic_exec_single(cpu, data, wait);
}
put_cpu();
}
/**
* 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).
* @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.
*
* 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.
*/
void smp_call_function_many(const struct cpumask *mask,
smp_call_func_t func, void *info, bool wait)
{
struct call_function_data *data;
int cpu, next_cpu, this_cpu = smp_processor_id();
/*
* 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 && !early_boot_irqs_disabled);
/* Try to fastpath. So, what's a CPU they want? Ignoring this one. */
cpu = cpumask_first_and(mask, cpu_online_mask);
if (cpu == this_cpu)
cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
/* 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);
if (next_cpu == this_cpu)
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;
}
data = &__get_cpu_var(cfd_data);
cpumask_and(data->cpumask, mask, cpu_online_mask);
cpumask_clear_cpu(this_cpu, data->cpumask);
/* Some callers race with other cpus changing the passed mask */
if (unlikely(!cpumask_weight(data->cpumask)))
return;
/*
* After we put an entry into the list, data->cpumask
* may be cleared again when another CPU sends another IPI for
* a SMP function call, so data->cpumask will be zero.
*/
cpumask_copy(data->cpumask_ipi, data->cpumask);
for_each_cpu(cpu, data->cpumask) {
struct call_single_data *csd = per_cpu_ptr(data->csd, cpu);
struct call_single_queue *dst =
&per_cpu(call_single_queue, cpu);
unsigned long flags;
csd_lock(csd);
csd->func = func;
csd->info = info;
raw_spin_lock_irqsave(&dst->lock, flags);
list_add_tail(&csd->list, &dst->list);
raw_spin_unlock_irqrestore(&dst->lock, flags);
}
/* Send a message to all CPUs in the map */
arch_send_call_function_ipi_mask(data->cpumask_ipi);
if (wait) {
for_each_cpu(cpu, data->cpumask) {
struct call_single_data *csd =
per_cpu_ptr(data->csd, cpu);
csd_lock_wait(csd);
}
}
}
EXPORT_SYMBOL(smp_call_function_many);
/**
* 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.
* @wait: If true, wait (atomically) until function has completed
* on other CPUs.
*
* Returns 0.
*
* If @wait is true, then returns once @func has returned; otherwise
* it returns just before the target cpu calls @func.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
int smp_call_function(smp_call_func_t func, void *info, int wait)
{
preempt_disable();
smp_call_function_many(cpu_online_mask, func, info, wait);
preempt_enable();
return 0;
}
EXPORT_SYMBOL(smp_call_function);
#endif /* USE_GENERIC_SMP_HELPERS */
/* 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;
}
/* Called by boot processor to activate the rest. */
void __init smp_init(void)
{
unsigned int cpu;
idle_threads_init();
/* 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 */
printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
smp_cpus_done(setup_max_cpus);
}
/*
* 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().
*/
int on_each_cpu(void (*func) (void *info), void *info, int wait)
{
unsigned long flags;
int ret = 0;
preempt_disable();
ret = smp_call_function(func, info, wait);
local_irq_save(flags);
func(info);
local_irq_restore(flags);
preempt_enable();
return ret;
}
EXPORT_SYMBOL(on_each_cpu);
/**
* 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.
*
* 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_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)) {
local_irq_disable();
func(info);
local_irq_enable();
}
put_cpu();
}
EXPORT_SYMBOL(on_each_cpu_mask);
/*
* 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);
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);