On Tue, May 13, 2014 at 12:58:51PM +0200, Peter Zijlstra wrote:
> On Tue, May 13, 2014 at 10:45:35AM +0100, Mel Gorman wrote:
> > +#ifdef HAVE_JUMP_LABEL
> > +extern struct static_key cpusets_enabled_key;
> > +static inline bool cpusets_enabled(void)
> > +{
> > + return static_key_false(&cpusets_enabled_key);
> > +}
> > +
> > +/* jump label reference count + the top-level cpuset */
> > +#define number_of_cpusets (static_key_count(&cpusets_enabled_key) + 1)
> > +
> > +static inline void cpuset_inc(void)
> > +{
> > + static_key_slow_inc(&cpusets_enabled_key);
> > +}
> > +
> > +static inline void cpuset_dec(void)
> > +{
> > + static_key_slow_dec(&cpusets_enabled_key);
> > +}
> > +
> > +static inline void cpuset_init_count(void) { }
> > +
> > +#else
> > extern int number_of_cpusets; /* How many cpusets are defined in
> > system? */
> >
> > +static inline bool cpusets_enabled(void)
> > +{
> > + return number_of_cpusets > 1;
> > +}
> > +
> > +static inline void cpuset_inc(void)
> > +{
> > + number_of_cpusets++;
> > +}
> > +
> > +static inline void cpuset_dec(void)
> > +{
> > + number_of_cpusets--;
> > +}
> > +
> > +static inline void cpuset_init_count(void)
> > +{
> > + number_of_cpusets = 1;
> > +}
> > +#endif /* HAVE_JUMP_LABEL */
>
> I'm still puzzled by the whole #else branch here, why not
> unconditionally use the jump-label one? Without HAVE_JUMP_LABEL we'll
> revert to a simple atomic_t counter, which should be perfectly fine, no?
No good reason -- the intent was to preserve the old behaviour if jump
labels were not available but there is no good reason for that. I'll delete
the alternative implementation, make number_of_cpusets an inline function
and move cpusets_enabled_key into the __read_mostly section. It's untested
but the patch now looks like
---8<---
mm: page_alloc: Use jump labels to avoid checking number_of_cpusets
If cpusets are not in use then we still check a global variable on every
page allocation. Use jump labels to avoid the overhead.
Signed-off-by: Mel Gorman <mgor...@suse.de>
Reviewed-by: Rik van Riel <r...@redhat.com>
---
include/linux/cpuset.h | 28 +++++++++++++++++++++++++---
kernel/cpuset.c | 14 ++++----------
mm/page_alloc.c | 3 ++-
3 files changed, 31 insertions(+), 14 deletions(-)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index b19d3dc..a94af76 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -15,7 +15,27 @@
#ifdef CONFIG_CPUSETS
-extern int number_of_cpusets; /* How many cpusets are defined in system? */
+extern struct static_key cpusets_enabled_key;
+static inline bool cpusets_enabled(void)
+{
+ return static_key_false(&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;
+}
+
+static inline void cpuset_inc(void)
+{
+ static_key_slow_inc(&cpusets_enabled_key);
+}
+
+static inline void cpuset_dec(void)
+{
+ static_key_slow_dec(&cpusets_enabled_key);
+}
extern int cpuset_init(void);
extern void cpuset_init_smp(void);
@@ -32,13 +52,13 @@ extern int __cpuset_node_allowed_hardwall(int node, gfp_t
gfp_mask);
static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
{
- return number_of_cpusets <= 1 ||
+ return nr_cpusets() <= 1 ||
__cpuset_node_allowed_softwall(node, gfp_mask);
}
static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
{
- return number_of_cpusets <= 1 ||
+ return nr_cpusets() <= 1 ||
__cpuset_node_allowed_hardwall(node, gfp_mask);
}
@@ -124,6 +144,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
#else /* !CONFIG_CPUSETS */
+static inline bool cpusets_enabled(void) { return false; }
+
static inline int cpuset_init(void) { return 0; }
static inline void cpuset_init_smp(void) {}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3d54c41..1300178 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -61,12 +61,7 @@
#include <linux/cgroup.h>
#include <linux/wait.h>
-/*
- * Tracks how many cpusets are currently defined in system.
- * When there is only one cpuset (the root cpuset) we can
- * short circuit some hooks.
- */
-int number_of_cpusets __read_mostly;
+struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
/* See "Frequency meter" comments, below. */
@@ -611,7 +606,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
goto done;
}
- csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL);
+ csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL);
if (!csa)
goto done;
csn = 0;
@@ -1888,7 +1883,7 @@ static int cpuset_css_online(struct cgroup_subsys_state
*css)
if (is_spread_slab(parent))
set_bit(CS_SPREAD_SLAB, &cs->flags);
- number_of_cpusets++;
+ cpuset_inc();
if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
goto out_unlock;
@@ -1939,7 +1934,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state
*css)
if (is_sched_load_balance(cs))
update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
- number_of_cpusets--;
+ cpuset_dec();
clear_bit(CS_ONLINE, &cs->flags);
mutex_unlock(&cpuset_mutex);
@@ -1992,7 +1987,6 @@ int __init cpuset_init(void)
if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL))
BUG();
- number_of_cpusets = 1;
return 0;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5c559e3..cb12b9a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1930,7 +1930,8 @@ zonelist_scan:
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
- if ((alloc_flags & ALLOC_CPUSET) &&
+ if (cpusets_enabled() &&
+ (alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
continue;
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
