cpuset: use static key better and convert to new API

An important function for cpusets is cpuset_node_allowed(), which
optimizes on the fact if there's a single root CPU set, it must be
trivially allowed.  But the check "nr_cpusets() <= 1" doesn't use the
cpusets_enabled_key static key the right way where static keys eliminate
branching overhead with jump labels.

This patch converts it so that static key is used properly.  It's also
switched to the new static key API and the checking functions are
converted to return bool instead of int.  We also provide a new variant
__cpuset_zone_allowed() which expects that the static key check was
already done and they key was enabled.  This is needed for
get_page_from_freelist() where we want to also avoid the relatively
slower check when ALLOC_CPUSET is not set in alloc_flags.

The impact on the page allocator microbenchmark is less than expected
but the cleanup in itself is worthwhile.

                                             4.6.0-rc2                  4.6.0-rc2
                                       multcheck-v1r20               cpuset-v1r20
  Min      alloc-odr0-1               348.00 (  0.00%)           348.00 (  0.00%)
  Min      alloc-odr0-2               254.00 (  0.00%)           254.00 (  0.00%)
  Min      alloc-odr0-4               213.00 (  0.00%)           213.00 (  0.00%)
  Min      alloc-odr0-8               186.00 (  0.00%)           183.00 (  1.61%)
  Min      alloc-odr0-16              173.00 (  0.00%)           171.00 (  1.16%)
  Min      alloc-odr0-32              166.00 (  0.00%)           163.00 (  1.81%)
  Min      alloc-odr0-64              162.00 (  0.00%)           159.00 (  1.85%)
  Min      alloc-odr0-128             160.00 (  0.00%)           157.00 (  1.88%)
  Min      alloc-odr0-256             169.00 (  0.00%)           166.00 (  1.78%)
  Min      alloc-odr0-512             180.00 (  0.00%)           180.00 (  0.00%)
  Min      alloc-odr0-1024            188.00 (  0.00%)           187.00 (  0.53%)
  Min      alloc-odr0-2048            194.00 (  0.00%)           193.00 (  0.52%)
  Min      alloc-odr0-4096            199.00 (  0.00%)           198.00 (  0.50%)
  Min      alloc-odr0-8192            202.00 (  0.00%)           201.00 (  0.50%)
  Min      alloc-odr0-16384           203.00 (  0.00%)           202.00 (  0.49%)

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Zefan Li <lizefan@huawei.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Vlastimil Babka 2016-05-19 17:14:30 -07:00 committed by Linus Torvalds
parent 0b423ca22f
commit 002f290627
3 changed files with 36 additions and 22 deletions

View File

@ -16,26 +16,26 @@
#ifdef CONFIG_CPUSETS
extern struct static_key cpusets_enabled_key;
extern struct static_key_false cpusets_enabled_key;
static inline bool cpusets_enabled(void)
{
return static_key_false(&cpusets_enabled_key);
return static_branch_unlikely(&cpusets_enabled_key);
}
static inline int nr_cpusets(void)
{
/* jump label reference count + the top-level cpuset */
return static_key_count(&cpusets_enabled_key) + 1;
return static_key_count(&cpusets_enabled_key.key) + 1;
}
static inline void cpuset_inc(void)
{
static_key_slow_inc(&cpusets_enabled_key);
static_branch_inc(&cpusets_enabled_key);
}
static inline void cpuset_dec(void)
{
static_key_slow_dec(&cpusets_enabled_key);
static_branch_dec(&cpusets_enabled_key);
}
extern int cpuset_init(void);
@ -48,16 +48,25 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
void cpuset_init_current_mems_allowed(void);
int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
extern int __cpuset_node_allowed(int node, gfp_t gfp_mask);
extern bool __cpuset_node_allowed(int node, gfp_t gfp_mask);
static inline int cpuset_node_allowed(int node, gfp_t gfp_mask)
static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask)
{
return nr_cpusets() <= 1 || __cpuset_node_allowed(node, gfp_mask);
if (cpusets_enabled())
return __cpuset_node_allowed(node, gfp_mask);
return true;
}
static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
{
return cpuset_node_allowed(zone_to_nid(z), gfp_mask);
return __cpuset_node_allowed(zone_to_nid(z), gfp_mask);
}
static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
{
if (cpusets_enabled())
return __cpuset_zone_allowed(z, gfp_mask);
return true;
}
extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
@ -172,14 +181,19 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
return 1;
}
static inline int cpuset_node_allowed(int node, gfp_t gfp_mask)
static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask)
{
return 1;
return true;
}
static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
{
return 1;
return true;
}
static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
{
return true;
}
static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,

View File

@ -61,7 +61,7 @@
#include <linux/cgroup.h>
#include <linux/wait.h>
struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
/* See "Frequency meter" comments, below. */
@ -2528,27 +2528,27 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
* GFP_KERNEL - any node in enclosing hardwalled cpuset ok
* GFP_USER - only nodes in current tasks mems allowed ok.
*/
int __cpuset_node_allowed(int node, gfp_t gfp_mask)
bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
{
struct cpuset *cs; /* current cpuset ancestors */
int allowed; /* is allocation in zone z allowed? */
unsigned long flags;
if (in_interrupt())
return 1;
return true;
if (node_isset(node, current->mems_allowed))
return 1;
return true;
/*
* Allow tasks that have access to memory reserves because they have
* been OOM killed to get memory anywhere.
*/
if (unlikely(test_thread_flag(TIF_MEMDIE)))
return 1;
return true;
if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */
return 0;
return false;
if (current->flags & PF_EXITING) /* Let dying task have memory */
return 1;
return true;
/* Not hardwall and node outside mems_allowed: scan up cpusets */
spin_lock_irqsave(&callback_lock, flags);

View File

@ -2859,7 +2859,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
if (cpusets_enabled() &&
(alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed(zone, gfp_mask))
!__cpuset_zone_allowed(zone, gfp_mask))
continue;
/*
* Distribute pages in proportion to the individual