[PATCH] documentation: Make sample code and documentation consistent

2016-03-07 Thread Yao Dongdong 
In the chapter 'analogy with reader-writer locking', the sample
code uses spinlock_t in reader-writer case. Just correct it so
that we can read the document easily.

Signed-off-by: Yao Dongdong <yaodongd...@huawei.com>
---
 Documentation/RCU/whatisRCU.txt |   22 +++---
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index dc49c67..e33304e 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -681,22 +681,30 @@ Although RCU can be used in many different ways, a very 
common use of
 RCU is analogous to reader-writer locking.  The following unified
 diff shows how closely related RCU and reader-writer locking can be.

+   @@ -5,5 +5,5 @@ struct el {
+   int data;
+   /* Other data fields */
+   };
+   -rwlock_t listmutex;
+   +spinlock_t listmutex;
+   struct el head;
+
@@ -13,15 +14,15 @@
struct list_head *lp;
struct el *p;

-   -   read_lock();
+   -   read_lock();
-   list_for_each_entry(p, head, lp) {
+   rcu_read_lock();
+   list_for_each_entry_rcu(p, head, lp) {
if (p->key == key) {
*result = p->data;
-   -   read_unlock();
+   -   read_unlock();
+   rcu_read_unlock();
return 1;
}
}
-   -   read_unlock();
+   -   read_unlock();
+   rcu_read_unlock();
return 0;
 }
@@ -732,7 +740,7 @@ Or, for those who prefer a side-by-side listing:
  5   int data;  5   int data;
  6   /* Other data fields */6   /* Other data fields */
  7 };   7 };
- 8 spinlock_t listmutex;8 spinlock_t listmutex;
+ 8 rwlock_t listmutex;  8 spinlock_t listmutex;
  9 struct el head;  9 struct el head;

  1 int search(long key, int *result)1 int search(long key, int *result)
@@ -740,15 +748,15 @@ Or, for those who prefer a side-by-side listing:
  3   struct list_head *lp;  3   struct list_head *lp;
  4   struct el *p;  4   struct el *p;
  5  5
- 6   read_lock();   6   rcu_read_lock();
+ 6   read_lock(); 6   rcu_read_lock();
  7   list_for_each_entry(p, head, lp) { 7   list_for_each_entry_rcu(p, head, 
lp) {
  8 if (p->key == key) { 8 if (p->key == key) {
  9   *result = p->data; 9   *result = p->data;
-10   read_unlock();10   rcu_read_unlock();
+10   read_unlock();  10   rcu_read_unlock();
 11   return 1; 11   return 1;
 12 }   12 }
 13   } 13   }
-14   read_unlock();14   rcu_read_unlock();
+14   read_unlock();  14   rcu_read_unlock();
 15   return 0; 15   return 0;
 16 }   16 }

--
1.7.9.5

[PATCH] documentation: Make sample code and documentation consistent

2016-03-07 Thread Yao Dongdong 
In the chapter 'analogy with reader-writer locking', the sample
code uses spinlock_t in reader-writer case. Just correct it so
that we can read the document easily.

Signed-off-by: Yao Dongdong 
---
 Documentation/RCU/whatisRCU.txt |   22 +++---
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index dc49c67..e33304e 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -681,22 +681,30 @@ Although RCU can be used in many different ways, a very 
common use of
 RCU is analogous to reader-writer locking.  The following unified
 diff shows how closely related RCU and reader-writer locking can be.

+   @@ -5,5 +5,5 @@ struct el {
+   int data;
+   /* Other data fields */
+   };
+   -rwlock_t listmutex;
+   +spinlock_t listmutex;
+   struct el head;
+
@@ -13,15 +14,15 @@
struct list_head *lp;
struct el *p;

-   -   read_lock();
+   -   read_lock();
-   list_for_each_entry(p, head, lp) {
+   rcu_read_lock();
+   list_for_each_entry_rcu(p, head, lp) {
if (p->key == key) {
*result = p->data;
-   -   read_unlock();
+   -   read_unlock();
+   rcu_read_unlock();
return 1;
}
}
-   -   read_unlock();
+   -   read_unlock();
+   rcu_read_unlock();
return 0;
 }
@@ -732,7 +740,7 @@ Or, for those who prefer a side-by-side listing:
  5   int data;  5   int data;
  6   /* Other data fields */6   /* Other data fields */
  7 };   7 };
- 8 spinlock_t listmutex;8 spinlock_t listmutex;
+ 8 rwlock_t listmutex;  8 spinlock_t listmutex;
  9 struct el head;  9 struct el head;

  1 int search(long key, int *result)1 int search(long key, int *result)
@@ -740,15 +748,15 @@ Or, for those who prefer a side-by-side listing:
  3   struct list_head *lp;  3   struct list_head *lp;
  4   struct el *p;  4   struct el *p;
  5  5
- 6   read_lock();   6   rcu_read_lock();
+ 6   read_lock(); 6   rcu_read_lock();
  7   list_for_each_entry(p, head, lp) { 7   list_for_each_entry_rcu(p, head, 
lp) {
  8 if (p->key == key) { 8 if (p->key == key) {
  9   *result = p->data; 9   *result = p->data;
-10   read_unlock();10   rcu_read_unlock();
+10   read_unlock();  10   rcu_read_unlock();
 11   return 1; 11   return 1;
 12 }   12 }
 13   } 13   }
-14   read_unlock();14   rcu_read_unlock();
+14   read_unlock();  14   rcu_read_unlock();
 15   return 0; 15   return 0;
 16 }   16 }

--
1.7.9.5

[PATCH] rcu: Remove reduplicate check of cpu_online

2015-02-25 Thread Yao Dongdong 
The calling function invoke_rcu_core will check it.

Signed-off-by: Yao Dongdong 
---
 kernel/rcu/tree.c |2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 48d640c..e5f9b7e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2741,7 +2741,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct 
rcu_data *rdp,
 * If called from an extended quiescent state, invoke the RCU
 * core in order to force a re-evaluation of RCU's idleness.
 */
-   if (!rcu_is_watching() && cpu_online(smp_processor_id()))
+   if (!rcu_is_watching())
invoke_rcu_core();
 
/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
-- 
1.7.9.5

--
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/

[PATCH] rcu: Remove reduplicate check of cpu_online

2015-02-25 Thread Yao Dongdong 
The calling function invoke_rcu_core will check it.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
---
 kernel/rcu/tree.c |2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 48d640c..e5f9b7e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2741,7 +2741,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct 
rcu_data *rdp,
 * If called from an extended quiescent state, invoke the RCU
 * core in order to force a re-evaluation of RCU's idleness.
 */
-   if (!rcu_is_watching()  cpu_online(smp_processor_id()))
+   if (!rcu_is_watching())
invoke_rcu_core();
 
/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
-- 
1.7.9.5

--
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/

[tip:sched/core] sched/core: Remove check of p->sched_class

2015-01-14 Thread tip-bot for Yao Dongdong 
Commit-ID:  1b537c7d1e58c761212a193085f9049b58f672e6
Gitweb: http://git.kernel.org/tip/1b537c7d1e58c761212a193085f9049b58f672e6
Author: Yao Dongdong 
AuthorDate: Mon, 29 Dec 2014 14:41:43 +0800
Committer:  Ingo Molnar 
CommitDate: Wed, 14 Jan 2015 13:34:17 +0100

sched/core: Remove check of p->sched_class

Search all usage of p->sched_class in sched/core.c, no one check it
before use, so it seems that every task must belong to one sched_class.

Signed-off-by: Yao Dongdong 
[ Moved the early class assignment to make it boot. ]
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Linus Torvalds 
Link: 
http://lkml.kernel.org/r/1419835303-28958-1-git-send-email-yaodongd...@huawei.com
Signed-off-by: Ingo Molnar 
---
 kernel/sched/core.c | 12 ++--
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 95ac795..46a2345 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4744,7 +4744,7 @@ static struct rq *move_queued_task(struct task_struct *p, 
int new_cpu)
 
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
-   if (p->sched_class && p->sched_class->set_cpus_allowed)
+   if (p->sched_class->set_cpus_allowed)
p->sched_class->set_cpus_allowed(p, new_mask);
 
cpumask_copy(>cpus_allowed, new_mask);
@@ -7254,6 +7254,11 @@ void __init sched_init(void)
enter_lazy_tlb(_mm, current);
 
/*
+* During early bootup we pretend to be a normal task:
+*/
+   current->sched_class = _sched_class;
+
+   /*
 * Make us the idle thread. Technically, schedule() should not be
 * called from this thread, however somewhere below it might be,
 * but because we are the idle thread, we just pick up running again
@@ -7263,11 +7268,6 @@ void __init sched_init(void)
 
calc_load_update = jiffies + LOAD_FREQ;
 
-   /*
-* During early bootup we pretend to be a normal task:
-*/
-   current->sched_class = _sched_class;
-
 #ifdef CONFIG_SMP
zalloc_cpumask_var(_domains_tmpmask, GFP_NOWAIT);
/* May be allocated at isolcpus cmdline parse time */
--
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/

[tip:sched/core] sched/core: Remove check of p-sched_class

2015-01-14 Thread tip-bot for Yao Dongdong 
Commit-ID:  1b537c7d1e58c761212a193085f9049b58f672e6
Gitweb: http://git.kernel.org/tip/1b537c7d1e58c761212a193085f9049b58f672e6
Author: Yao Dongdong yaodongd...@huawei.com
AuthorDate: Mon, 29 Dec 2014 14:41:43 +0800
Committer:  Ingo Molnar mi...@kernel.org
CommitDate: Wed, 14 Jan 2015 13:34:17 +0100

sched/core: Remove check of p-sched_class

Search all usage of p-sched_class in sched/core.c, no one check it
before use, so it seems that every task must belong to one sched_class.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
[ Moved the early class assignment to make it boot. ]
Signed-off-by: Peter Zijlstra (Intel) pet...@infradead.org
Cc: Linus Torvalds torva...@linux-foundation.org
Link: 
http://lkml.kernel.org/r/1419835303-28958-1-git-send-email-yaodongd...@huawei.com
Signed-off-by: Ingo Molnar mi...@kernel.org
---
 kernel/sched/core.c | 12 ++--
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 95ac795..46a2345 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4744,7 +4744,7 @@ static struct rq *move_queued_task(struct task_struct *p, 
int new_cpu)
 
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
-   if (p-sched_class  p-sched_class-set_cpus_allowed)
+   if (p-sched_class-set_cpus_allowed)
p-sched_class-set_cpus_allowed(p, new_mask);
 
cpumask_copy(p-cpus_allowed, new_mask);
@@ -7254,6 +7254,11 @@ void __init sched_init(void)
enter_lazy_tlb(init_mm, current);
 
/*
+* During early bootup we pretend to be a normal task:
+*/
+   current-sched_class = fair_sched_class;
+
+   /*
 * Make us the idle thread. Technically, schedule() should not be
 * called from this thread, however somewhere below it might be,
 * but because we are the idle thread, we just pick up running again
@@ -7263,11 +7268,6 @@ void __init sched_init(void)
 
calc_load_update = jiffies + LOAD_FREQ;
 
-   /*
-* During early bootup we pretend to be a normal task:
-*/
-   current-sched_class = fair_sched_class;
-
 #ifdef CONFIG_SMP
zalloc_cpumask_var(sched_domains_tmpmask, GFP_NOWAIT);
/* May be allocated at isolcpus cmdline parse time */
--
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/

[PATCH] sched/core: remove check of p->sched_class

2014-12-28 Thread Yao Dongdong 
Search all usage of p->sched_class in sched/core.c, no one check it
before use, so it seems that every task must belong to one sched_class.

Signed-off-by: Yao Dongdong 
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b7..bdab49b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4740,7 +4740,7 @@ static struct rq *move_queued_task(struct task_struct *p, 
int new_cpu)
 
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
-   if (p->sched_class && p->sched_class->set_cpus_allowed)
+   if (p->sched_class->set_cpus_allowed)
p->sched_class->set_cpus_allowed(p, new_mask);
 
cpumask_copy(>cpus_allowed, new_mask);
-- 
2.1.0

--
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/

[PATCH] sched/core: remove check of p-sched_class

2014-12-28 Thread Yao Dongdong 
Search all usage of p-sched_class in sched/core.c, no one check it
before use, so it seems that every task must belong to one sched_class.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b7..bdab49b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4740,7 +4740,7 @@ static struct rq *move_queued_task(struct task_struct *p, 
int new_cpu)
 
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
-   if (p-sched_class  p-sched_class-set_cpus_allowed)
+   if (p-sched_class-set_cpus_allowed)
p-sched_class-set_cpus_allowed(p, new_mask);
 
cpumask_copy(p-cpus_allowed, new_mask);
-- 
2.1.0

--
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/

[PATCH] selinux: Remove security_ops extern

2014-11-27 Thread Yao Dongdong 
security_ops is not used in this file.

Signed-off-by: Yao Dongdong 
---
 security/selinux/hooks.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c603b20..6da7532 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -95,8 +95,6 @@
 #include "audit.h"
 #include "avc_ss.h"
 
-extern struct security_operations *security_ops;
-
 /* SECMARK reference count */
 static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0);
 
-- 
1.8.3.4

--
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/

[PATCH] selinux: Remove security_ops extern

2014-11-27 Thread Yao Dongdong 
security_ops is not used in this file.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
---
 security/selinux/hooks.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c603b20..6da7532 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -95,8 +95,6 @@
 #include audit.h
 #include avc_ss.h
 
-extern struct security_operations *security_ops;
-
 /* SECMARK reference count */
 static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0);
 
-- 
1.8.3.4

--
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/

[PATCH] sched, cleanup, dm bufio: Replace dm_bufio_cond_resched with might_resched

2014-11-19 Thread Yao Dongdong 
The judge of need_resched() before _cond_resched() in dm_bufio_cond_resched()
is no need. Because _cond_resched() itself judges should_resched() which means
need and can resched. In addition, might_resched() can do all these.

Signed-off-by: Yao Dongdong 
---
 drivers/md/dm-bufio.c | 35 +++
 1 file changed, 11 insertions(+), 24 deletions(-)

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index afe7971..3660a24 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -186,19 +186,6 @@ static void dm_bufio_unlock(struct dm_bufio_client *c)
mutex_unlock(>lock);
 }
 
-/*
- * FIXME Move to sched.h?
- */
-#ifdef CONFIG_PREEMPT_VOLUNTARY
-#  define dm_bufio_cond_resched()  \
-do {   \
-   if (unlikely(need_resched()))   \
-   _cond_resched();\
-} while (0)
-#else
-#  define dm_bufio_cond_resched()do { } while (0)
-#endif
-
 /**/
 
 /*
@@ -648,7 +635,7 @@ static void __flush_write_list(struct list_head *write_list)
list_entry(write_list->next, struct dm_buffer, 
write_list);
list_del(>write_list);
submit_io(b, WRITE, b->block, write_endio);
-   dm_bufio_cond_resched();
+   might_resched();
}
blk_finish_plug();
 }
@@ -687,7 +674,7 @@ static struct dm_buffer *__get_unclaimed_buffer(struct 
dm_bufio_client *c)
__unlink_buffer(b);
return b;
}
-   dm_bufio_cond_resched();
+   might_resched();
}
 
list_for_each_entry_reverse(b, >lru[LIST_DIRTY], lru_list) {
@@ -698,7 +685,7 @@ static struct dm_buffer *__get_unclaimed_buffer(struct 
dm_bufio_client *c)
__unlink_buffer(b);
return b;
}
-   dm_bufio_cond_resched();
+   might_resched();
}
 
return NULL;
@@ -830,7 +817,7 @@ static void __write_dirty_buffers_async(struct 
dm_bufio_client *c, int no_wait,
return;
 
__write_dirty_buffer(b, write_list);
-   dm_bufio_cond_resched();
+   might_resched();
}
 }
 
@@ -880,7 +867,7 @@ static void __check_watermark(struct dm_bufio_client *c,
return;
 
__free_buffer_wake(b);
-   dm_bufio_cond_resched();
+   might_resched();
}
 
if (c->n_buffers[LIST_DIRTY] > threshold_buffers)
@@ -896,7 +883,7 @@ static struct dm_buffer *__find(struct dm_bufio_client *c, 
sector_t block)
 
hlist_for_each_entry(b, >cache_hash[DM_BUFIO_HASH(block)],
 hash_list) {
-   dm_bufio_cond_resched();
+   might_resched();
if (b->block == block)
return b;
}
@@ -1090,7 +1077,7 @@ void dm_bufio_prefetch(struct dm_bufio_client *c,
submit_io(b, READ, b->block, read_endio);
dm_bufio_release(b);
 
-   dm_bufio_cond_resched();
+   might_resched();
 
if (!n_blocks)
goto flush_plug;
@@ -1211,7 +1198,7 @@ again:
!test_bit(B_WRITING, >state))
__relink_lru(b, LIST_CLEAN);
 
-   dm_bufio_cond_resched();
+   might_resched();
 
/*
 * If we dropped the lock, the list is no longer consistent,
@@ -1473,7 +1460,7 @@ static long __scan(struct dm_bufio_client *c, unsigned 
long nr_to_scan,
freed += __cleanup_old_buffer(b, gfp_mask, 0);
if (!--nr_to_scan)
return freed;
-   dm_bufio_cond_resched();
+   might_resched();
}
}
return freed;
@@ -1704,11 +1691,11 @@ static void cleanup_old_buffers(void)
   struct dm_buffer, lru_list);
if (!__cleanup_old_buffer(b, 0, max_age * HZ))
break;
-   dm_bufio_cond_resched();
+   might_resched();
}
 
dm_bufio_unlock(c);
-   dm_bufio_cond_resched();
+   might_resched();
}
mutex_unlock(_bufio_clients_lock);
 }
-- 
1.8.3.4

--
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/

[PATCH] sched, cleanup, dm bufio: Replace dm_bufio_cond_resched with might_resched

2014-11-19 Thread Yao Dongdong 
The judge of need_resched() before _cond_resched() in dm_bufio_cond_resched()
is no need. Because _cond_resched() itself judges should_resched() which means
need and can resched. In addition, might_resched() can do all these.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
---
 drivers/md/dm-bufio.c | 35 +++
 1 file changed, 11 insertions(+), 24 deletions(-)

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index afe7971..3660a24 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -186,19 +186,6 @@ static void dm_bufio_unlock(struct dm_bufio_client *c)
mutex_unlock(c-lock);
 }
 
-/*
- * FIXME Move to sched.h?
- */
-#ifdef CONFIG_PREEMPT_VOLUNTARY
-#  define dm_bufio_cond_resched()  \
-do {   \
-   if (unlikely(need_resched()))   \
-   _cond_resched();\
-} while (0)
-#else
-#  define dm_bufio_cond_resched()do { } while (0)
-#endif
-
 /**/
 
 /*
@@ -648,7 +635,7 @@ static void __flush_write_list(struct list_head *write_list)
list_entry(write_list-next, struct dm_buffer, 
write_list);
list_del(b-write_list);
submit_io(b, WRITE, b-block, write_endio);
-   dm_bufio_cond_resched();
+   might_resched();
}
blk_finish_plug(plug);
 }
@@ -687,7 +674,7 @@ static struct dm_buffer *__get_unclaimed_buffer(struct 
dm_bufio_client *c)
__unlink_buffer(b);
return b;
}
-   dm_bufio_cond_resched();
+   might_resched();
}
 
list_for_each_entry_reverse(b, c-lru[LIST_DIRTY], lru_list) {
@@ -698,7 +685,7 @@ static struct dm_buffer *__get_unclaimed_buffer(struct 
dm_bufio_client *c)
__unlink_buffer(b);
return b;
}
-   dm_bufio_cond_resched();
+   might_resched();
}
 
return NULL;
@@ -830,7 +817,7 @@ static void __write_dirty_buffers_async(struct 
dm_bufio_client *c, int no_wait,
return;
 
__write_dirty_buffer(b, write_list);
-   dm_bufio_cond_resched();
+   might_resched();
}
 }
 
@@ -880,7 +867,7 @@ static void __check_watermark(struct dm_bufio_client *c,
return;
 
__free_buffer_wake(b);
-   dm_bufio_cond_resched();
+   might_resched();
}
 
if (c-n_buffers[LIST_DIRTY]  threshold_buffers)
@@ -896,7 +883,7 @@ static struct dm_buffer *__find(struct dm_bufio_client *c, 
sector_t block)
 
hlist_for_each_entry(b, c-cache_hash[DM_BUFIO_HASH(block)],
 hash_list) {
-   dm_bufio_cond_resched();
+   might_resched();
if (b-block == block)
return b;
}
@@ -1090,7 +1077,7 @@ void dm_bufio_prefetch(struct dm_bufio_client *c,
submit_io(b, READ, b-block, read_endio);
dm_bufio_release(b);
 
-   dm_bufio_cond_resched();
+   might_resched();
 
if (!n_blocks)
goto flush_plug;
@@ -1211,7 +1198,7 @@ again:
!test_bit(B_WRITING, b-state))
__relink_lru(b, LIST_CLEAN);
 
-   dm_bufio_cond_resched();
+   might_resched();
 
/*
 * If we dropped the lock, the list is no longer consistent,
@@ -1473,7 +1460,7 @@ static long __scan(struct dm_bufio_client *c, unsigned 
long nr_to_scan,
freed += __cleanup_old_buffer(b, gfp_mask, 0);
if (!--nr_to_scan)
return freed;
-   dm_bufio_cond_resched();
+   might_resched();
}
}
return freed;
@@ -1704,11 +1691,11 @@ static void cleanup_old_buffers(void)
   struct dm_buffer, lru_list);
if (!__cleanup_old_buffer(b, 0, max_age * HZ))
break;
-   dm_bufio_cond_resched();
+   might_resched();
}
 
dm_bufio_unlock(c);
-   dm_bufio_cond_resched();
+   might_resched();
}
mutex_unlock(dm_bufio_clients_lock);
 }
-- 
1.8.3.4

--
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/

[tip:sched/core] sched: Check if we got a shallowest_idle_cpu before searching for least_loaded_cpu

2014-11-04 Thread tip-bot for Yao Dongdong 
Commit-ID:  9f96742a13135e6c609cc99a3a458402af3c8f31
Gitweb: http://git.kernel.org/tip/9f96742a13135e6c609cc99a3a458402af3c8f31
Author: Yao Dongdong 
AuthorDate: Tue, 28 Oct 2014 04:08:06 +
Committer:  Ingo Molnar 
CommitDate: Tue, 4 Nov 2014 07:17:51 +0100

sched: Check if we got a shallowest_idle_cpu before searching for 
least_loaded_cpu

Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.

Signed-off-by: Yao Dongdong 
Reviewed-by: Srikar Dronamraju 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Linus Torvalds 
Link: 
http://lkml.kernel.org/r/1414469286-6023-1-git-send-email-yaodongd...@huawei.com
Signed-off-by: Ingo Molnar 
---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ec32c26d..d03d76d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4641,7 +4641,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == 
this_cpu)) {
min_load = load;
--
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/

[tip:sched/core] sched: Check if we got a shallowest_idle_cpu before searching for least_loaded_cpu

2014-11-04 Thread tip-bot for Yao Dongdong 
Commit-ID:  9f96742a13135e6c609cc99a3a458402af3c8f31
Gitweb: http://git.kernel.org/tip/9f96742a13135e6c609cc99a3a458402af3c8f31
Author: Yao Dongdong yaodongd...@huawei.com
AuthorDate: Tue, 28 Oct 2014 04:08:06 +
Committer:  Ingo Molnar mi...@kernel.org
CommitDate: Tue, 4 Nov 2014 07:17:51 +0100

sched: Check if we got a shallowest_idle_cpu before searching for 
least_loaded_cpu

Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
Reviewed-by: Srikar Dronamraju sri...@linux.vnet.ibm.com
Signed-off-by: Peter Zijlstra (Intel) pet...@infradead.org
Cc: Linus Torvalds torva...@linux-foundation.org
Link: 
http://lkml.kernel.org/r/1414469286-6023-1-git-send-email-yaodongd...@huawei.com
Signed-off-by: Ingo Molnar mi...@kernel.org
---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ec32c26d..d03d76d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4641,7 +4641,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq-idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load  min_load || (load == min_load  i == 
this_cpu)) {
min_load = load;
--
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/

Re: [PATCH 1/2] Thermal:Fix memory leak if occur goto unregister

2014-11-03 Thread Yao Dongdong 
On 2014/11/4 2:35, Eduardo Valentin wrote:
> Hello,
>
> On Mon, Nov 03, 2014 at 06:17:37PM +, R, Durgadoss wrote:
>>> -Original Message-
>>> From: linux-pm-ow...@vger.kernel.org [mailto:linux-pm-
>>> ow...@vger.kernel.org] On Behalf Of Eduardo Valentin
>>> Sent: Monday, October 20, 2014 6:04 PM
>>> To: Yao Dongdong
>>> Cc: Zhang, Rui; linux...@vger.kernel.org; LKML
>>> Subject: Re: [PATCH 1/2] Thermal:Fix memory leak if occur goto unregister
>>>
>>> Hello,
>>>
>>> On Mon, Oct 20, 2014 at 04:27:36PM +0800, Yao Dongdong wrote:
>>>> Signed-off-by:yaodongd...@huawei.com
>>> Acked-by: Eduardo Valentin 
>>>
>>> Rui, would you take care of this?
>>>
>> If I remember it right, this 'tz' is freed in the thermal_release()
>> function, during device_unregister().
>>
>> It is similar in all other functions in thermal_core.c
>>
>> So, Yao, Did you really test this patch ?
>> And did not see any crashes ?
>>
> Yao, reading the patch change carefully, now I see that Durga is correct
> here. 
>
>> Thanks,
>> Durga
>>
>>>> ---
>>>>  drivers/thermal/thermal_core.c | 1 +
>>>>  1 file changed, 1 insertion(+)
>>>>
>>>> diff --git a/drivers/thermal/thermal_core.c 
>>>> b/drivers/thermal/thermal_core.c
>>>> index 71b0ec0..5b7d466 100644
>>>> --- a/drivers/thermal/thermal_core.c
>>>> +++ b/drivers/thermal/thermal_core.c
>>>> @@ -1574,6 +1574,7 @@ struct thermal_zone_device
>>> *thermal_zone_device_register(const char *type,
>>>>  unregister:
>>>> release_idr(_tz_idr, _idr_lock, tz->id);
>>>> device_unregister(>device);
>>>> +   kfree(tz);
> The device unregister is called above your kfree call, which will cause
> the thermal_release to be called. Did you test the code for double kfree
> calls? Your patch probably inserts a memory corruption.
>
> I will revert your patch from my tree until you provide an answer about
> your testing.

Yes, i have checked it and you are right, the patch will double kfree tz.

Thansks Durga for correcting me.

> Thanks,
>
>
> Eduardo Valentin
>
>>>> return ERR_PTR(result);
>>>>  }
>>>>  EXPORT_SYMBOL_GPL(thermal_zone_device_register);
>>>> --
>>>> 1.8.0.1
>>>>
>>>>


--
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/

Re: [PATCH 1/2] Thermal:Fix memory leak if occur goto unregister

2014-11-03 Thread Yao Dongdong 
On 2014/11/4 2:35, Eduardo Valentin wrote:
 Hello,

 On Mon, Nov 03, 2014 at 06:17:37PM +, R, Durgadoss wrote:
 -Original Message-
 From: linux-pm-ow...@vger.kernel.org [mailto:linux-pm-
 ow...@vger.kernel.org] On Behalf Of Eduardo Valentin
 Sent: Monday, October 20, 2014 6:04 PM
 To: Yao Dongdong
 Cc: Zhang, Rui; linux...@vger.kernel.org; LKML
 Subject: Re: [PATCH 1/2] Thermal:Fix memory leak if occur goto unregister

 Hello,

 On Mon, Oct 20, 2014 at 04:27:36PM +0800, Yao Dongdong wrote:
 Signed-off-by:yaodongd...@huawei.com
 Acked-by: Eduardo Valentin edubez...@gmail.com

 Rui, would you take care of this?

 If I remember it right, this 'tz' is freed in the thermal_release()
 function, during device_unregister().

 It is similar in all other functions in thermal_core.c

 So, Yao, Did you really test this patch ?
 And did not see any crashes ?

 Yao, reading the patch change carefully, now I see that Durga is correct
 here. 

 Thanks,
 Durga

 ---
  drivers/thermal/thermal_core.c | 1 +
  1 file changed, 1 insertion(+)

 diff --git a/drivers/thermal/thermal_core.c 
 b/drivers/thermal/thermal_core.c
 index 71b0ec0..5b7d466 100644
 --- a/drivers/thermal/thermal_core.c
 +++ b/drivers/thermal/thermal_core.c
 @@ -1574,6 +1574,7 @@ struct thermal_zone_device
 *thermal_zone_device_register(const char *type,
  unregister:
 release_idr(thermal_tz_idr, thermal_idr_lock, tz-id);
 device_unregister(tz-device);
 +   kfree(tz);
 The device unregister is called above your kfree call, which will cause
 the thermal_release to be called. Did you test the code for double kfree
 calls? Your patch probably inserts a memory corruption.

 I will revert your patch from my tree until you provide an answer about
 your testing.

Yes, i have checked it and you are right, the patch will double kfree tz.

Thansks Durga for correcting me.

 Thanks,


 Eduardo Valentin

 return ERR_PTR(result);
  }
  EXPORT_SYMBOL_GPL(thermal_zone_device_register);
 --
 1.8.0.1




--
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/

Re: [PATCH 1/2 resend] Thermal:Fix memory leak if occur goto unregister

2014-10-28 Thread Yao Dongdong 
Hello Eduardo,

I'm sorry for that my patches listed below have format problems, so i resend 
them.

https://lkml.org/lkml/2014/10/20/85
https://lkml.org/lkml/2014/10/20/84

Thanks,
Yao Dongdong

--
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/

[PATCH 1/2 resend] Thermal:Fix memory leak if occur goto unregister

2014-10-28 Thread Yao Dongdong 
Signed-off-by: Yao Dongdong 
Acked-by: Eduardo Valentin 
---
 drivers/thermal/thermal_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 9bf10aa..d358605 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1581,6 +1581,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,
 unregister:
release_idr(_tz_idr, _idr_lock, tz->id);
device_unregister(>device);
+   kfree(tz);
return ERR_PTR(result);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_register);
-- 
1.8.3.4

--
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/

[PATCH 2/2 resend] Thermal:Remove usless if(!result) before return tz

2014-10-28 Thread Yao Dongdong 
result is always zero when comes here.

Signed-off-by: Yao Dongdong 
Acked-by: Eduardo Valentin 
---
 drivers/thermal/thermal_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index d358605..a438c95 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1575,8 +1575,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,
 
thermal_zone_device_update(tz);
 
-   if (!result)
-   return tz;
+   return tz;
 
 unregister:
release_idr(_tz_idr, _idr_lock, tz->id);
-- 
1.8.3.4

--
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/

[PATCH 2/2 resend] Thermal:Remove usless if(!result) before return tz

2014-10-28 Thread Yao Dongdong 
result is always zero when comes here.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
Acked-by: Eduardo Valentin edubez...@gmail.com
---
 drivers/thermal/thermal_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index d358605..a438c95 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1575,8 +1575,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,
 
thermal_zone_device_update(tz);
 
-   if (!result)
-   return tz;
+   return tz;
 
 unregister:
release_idr(thermal_tz_idr, thermal_idr_lock, tz-id);
-- 
1.8.3.4

--
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/

[PATCH 1/2 resend] Thermal:Fix memory leak if occur goto unregister

2014-10-28 Thread Yao Dongdong 
Signed-off-by: Yao Dongdong yaodongd...@huawei.com
Acked-by: Eduardo Valentin edubez...@gmail.com
---
 drivers/thermal/thermal_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 9bf10aa..d358605 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1581,6 +1581,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,
 unregister:
release_idr(thermal_tz_idr, thermal_idr_lock, tz-id);
device_unregister(tz-device);
+   kfree(tz);
return ERR_PTR(result);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_register);
-- 
1.8.3.4

--
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/

Re: [PATCH 1/2 resend] Thermal:Fix memory leak if occur goto unregister

2014-10-28 Thread Yao Dongdong 
Hello Eduardo,

I'm sorry for that my patches listed below have format problems, so i resend 
them.

https://lkml.org/lkml/2014/10/20/85
https://lkml.org/lkml/2014/10/20/84

Thanks,
Yao Dongdong

--
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/

[PATCH resend] sched:check if got a shallowest_idle_cpu before search for least_loaded_cpu

2014-10-27 Thread Yao Dongdong 
Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.

Signed-off-by: Yao Dongdong 
Reviewed-by: Srikar Dronamraju 
---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf..2445a23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4446,7 +4446,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == 
this_cpu)) {
min_load = load;
-- 
1.8.3.4

--
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/

Re: [PATCH v2]sched:add check of shallowest_idle_cpu before search for least_loaded_cpu

2014-10-27 Thread Yao Dongdong 
On 2014/10/27 20:30, Peter Zijlstra wrote:
> Please as to try again:
>
> Applying patch 
> patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
> patching file kernel/sched/fair.c
> Hunk #1 FAILED at 4446.
> 1 out of 1 hunk FAILED -- rejects in file kernel/sched/fair.c
> Patch 
> patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
>  does not apply (enforce with -f)
> quilt returned 1, with 0 fuzz and 1 rejects
> use quilt -f? y/n [y]: y
> Applying patch 
> patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
> patching file kernel/sched/fair.c
> Hunk #1 FAILED at 4446.
> 1 out of 1 hunk FAILED -- saving rejects to file kernel/sched/fair.c.rej
> Applied patch 
> patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
>  (forced; needs refresh)
> reject patch 
> patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
>  file kernel/sched/fair.c hunk 1 line 4
> [a]uto[m]erge,edit [f]ile [p]atch [r]ej,[n]ext,[d]elete: [amfdprn]: m
> rej started:
> [a]uto[m]erge,edit [f]ile [p]atch [r]ej,[n]ext,[d]elete: [amfdprn]: 
> kernel/sched/fair.c: 1 matched, 0 conflicts remain
> n
> patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
>  done [s]top, [n]ext, [r]efresh [snr]: r
> WARNING: Use a single space after Signed-off-by:
> #13: 
> Signed-off-by:yaodongd...@huawei.com
>
> ERROR: code indent should use tabs where possible
> #25: FILE: kernel/sched/fair.c:4644:
> +   } else if (shallowest_idle_cpu == -1) {$
>
> WARNING: please, no spaces at the start of a line
> #25: FILE: kernel/sched/fair.c:4644:
> +   } else if (shallowest_idle_cpu == -1) {$
>
> total: 1 errors, 2 warnings, 8 lines checked
>
> NOTE: whitespace errors detected, you may wish to use scripts/cleanpatch or
>   scripts/cleanfile
>
> .
>
I 'm sorry, and i will fix and resend another one.

Thanks,
Yao Dongdong

--
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/

[PATCH v2]sched:add check of shallowest_idle_cpu before search for least_loaded_cpu

2014-10-27 Thread Yao Dongdong 
Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.

Signed-off-by:yaodongd...@huawei.com
Reviewed-by: Srikar Dronamraju 
 ---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf..2445a23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4446,7 +4446,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == 
this_cpu)) {
min_load = load;
--
1.8.0.1


--
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/

Re: [PATCH] sched:skip loop non-idle cpus after find an idle cpu while find_idlest_cpu

2014-10-27 Thread Yao Dongdong 
On 2014/10/27 16:04, Srikar Dronamraju wrote:
> * Yao Dongdong  [2014-10-27 11:13:17]:
>
>> Idle cpu is idler than non-idle cpu, so we needn't loop non-idle cpus after 
>> find an idle cpu.
>>
> While this check looks good,
> I dont see how we are avoiding a loop?
>
> Are you suggesting that we break of the for loop once we set
> shallowest_idle_cpu?
>
Thanks for your review.

I agree that the submit message is a bit misleading, what this patch do is just 
avoiding search for least_loaded_cpu
in non-idle cpus.

sched:add check of shallowest_idle_cpu before search for least_loaded_cpu

Idle cpu is idler than non-idle cpu, so we needn't search for 
least_loaded_cpu
after we have found an idle cpu.

what about this?

Thanks,
Yao Dongdong

--
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/

Re: [PATCH] sched:skip loop non-idle cpus after find an idle cpu while find_idlest_cpu

2014-10-27 Thread Yao Dongdong 
On 2014/10/27 16:04, Srikar Dronamraju wrote:
 * Yao Dongdong yaodongd...@huawei.com [2014-10-27 11:13:17]:

 Idle cpu is idler than non-idle cpu, so we needn't loop non-idle cpus after 
 find an idle cpu.

 While this check looks good,
 I dont see how we are avoiding a loop?

 Are you suggesting that we break of the for loop once we set
 shallowest_idle_cpu?

Thanks for your review.

I agree that the submit message is a bit misleading, what this patch do is just 
avoiding search for least_loaded_cpu
in non-idle cpus.

sched:add check of shallowest_idle_cpu before search for least_loaded_cpu

Idle cpu is idler than non-idle cpu, so we needn't search for 
least_loaded_cpu
after we have found an idle cpu.

what about this?

Thanks,
Yao Dongdong

--
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/

[PATCH v2]sched:add check of shallowest_idle_cpu before search for least_loaded_cpu

2014-10-27 Thread Yao Dongdong 
Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.

Signed-off-by:yaodongd...@huawei.com
Reviewed-by: Srikar Dronamraju sri...@linux.vnet.ibm.com
 ---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf..2445a23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4446,7 +4446,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq-idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load  min_load || (load == min_load  i == 
this_cpu)) {
min_load = load;
--
1.8.0.1


--
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/

Re: [PATCH v2]sched:add check of shallowest_idle_cpu before search for least_loaded_cpu

2014-10-27 Thread Yao Dongdong 
On 2014/10/27 20:30, Peter Zijlstra wrote:
 Please as to try again:

 Applying patch 
 patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
 patching file kernel/sched/fair.c
 Hunk #1 FAILED at 4446.
 1 out of 1 hunk FAILED -- rejects in file kernel/sched/fair.c
 Patch 
 patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
  does not apply (enforce with -f)
 quilt returned 1, with 0 fuzz and 1 rejects
 use quilt -f? y/n [y]: y
 Applying patch 
 patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
 patching file kernel/sched/fair.c
 Hunk #1 FAILED at 4446.
 1 out of 1 hunk FAILED -- saving rejects to file kernel/sched/fair.c.rej
 Applied patch 
 patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
  (forced; needs refresh)
 reject patch 
 patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
  file kernel/sched/fair.c hunk 1 line 4
 [a]uto[m]erge,edit [f]ile [p]atch [r]ej,[n]ext,[d]elete: [amfdprn]: m
 rej started:
 [a]uto[m]erge,edit [f]ile [p]atch [r]ej,[n]ext,[d]elete: [amfdprn]: 
 kernel/sched/fair.c: 1 matched, 0 conflicts remain
 n
 patches/yao_dongdong-sched_add_check_of_shallowest_idle_cpu_before_search_for_least_loaded_cpu.patch
  done [s]top, [n]ext, [r]efresh [snr]: r
 WARNING: Use a single space after Signed-off-by:
 #13: 
 Signed-off-by:yaodongd...@huawei.com

 ERROR: code indent should use tabs where possible
 #25: FILE: kernel/sched/fair.c:4644:
 +   } else if (shallowest_idle_cpu == -1) {$

 WARNING: please, no spaces at the start of a line
 #25: FILE: kernel/sched/fair.c:4644:
 +   } else if (shallowest_idle_cpu == -1) {$

 total: 1 errors, 2 warnings, 8 lines checked

 NOTE: whitespace errors detected, you may wish to use scripts/cleanpatch or
   scripts/cleanfile

 .

I 'm sorry, and i will fix and resend another one.

Thanks,
Yao Dongdong

--
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/

[PATCH resend] sched:check if got a shallowest_idle_cpu before search for least_loaded_cpu

2014-10-27 Thread Yao Dongdong 
Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
Reviewed-by: Srikar Dronamraju sri...@linux.vnet.ibm.com
---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf..2445a23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4446,7 +4446,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq-idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load  min_load || (load == min_load  i == 
this_cpu)) {
min_load = load;
-- 
1.8.3.4

--
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/

[PATCH] sched:skip loop non-idle cpus after find an idle cpu while find_idlest_cpu

2014-10-26 Thread Yao Dongdong 
Idle cpu is idler than non-idle cpu, so we needn't loop non-idle cpus after 
find an idle cpu.

Signed-off-by:yaodongd...@huawei.com

---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf..2445a23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4446,7 +4446,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == 
this_cpu)) {
min_load = load;
--
1.8.0.1

--
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/

[PATCH] sched:skip loop non-idle cpus after find an idle cpu while find_idlest_cpu

2014-10-26 Thread Yao Dongdong 
Idle cpu is idler than non-idle cpu, so we needn't loop non-idle cpus after 
find an idle cpu.

Signed-off-by:yaodongd...@huawei.com

---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf..2445a23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4446,7 +4446,7 @@ find_idlest_cpu(struct sched_group *group, struct 
task_struct *p, int this_cpu)
latest_idle_timestamp = rq-idle_stamp;
shallowest_idle_cpu = i;
}
-   } else {
+   } else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
if (load  min_load || (load == min_load  i == 
this_cpu)) {
min_load = load;
--
1.8.0.1

--
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/

Re: [PATCH 2/2] Thermal:Remove usless if(!result) before return tz

2014-10-20 Thread Yao Dongdong 

On 2014/10/20 20:10, Eduardo Valentin wrote:
> Hello Yao
>
> On Mon, Oct 20, 2014 at 04:27:59PM +0800, Yao Dongdong wrote:
>> result is always zero when comes here.
>>
>> Signed-off-by:yaodongd...@huawei.com
>>
>> ---
>>  drivers/thermal/thermal_core.c | 3 +--
>>  1 file changed, 1 insertion(+), 2 deletions(-)
>>
>> diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
>> index 5b7d466..19cac8e 100644
>> --- a/drivers/thermal/thermal_core.c
>> +++ b/drivers/thermal/thermal_core.c
>> @@ -1568,8 +1568,7 @@ struct thermal_zone_device 
>> *thermal_zone_device_register(const char *type,
>>
>> thermal_zone_device_update(tz);
>>
>> -   if (!result)
>> -   return tz;
>> +   return tz;
>>
> Adding a return here will make the resource release below not reachable
> in the fail path.

But all fails above followed a "goto unregister", so i think it must be 
successful when come here.

Thanks.

>>  unregister:
>> release_idr(_tz_idr, _idr_lock, tz->id);
>> --
>> 1.8.0.1
>>
>>


--
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/

[PATCH 1/2] Thermal:Fix memory leak if occur goto unregister

2014-10-20 Thread Yao Dongdong 
Signed-off-by:yaodongd...@huawei.com

---
 drivers/thermal/thermal_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 71b0ec0..5b7d466 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1574,6 +1574,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,
 unregister:
release_idr(_tz_idr, _idr_lock, tz->id);
device_unregister(>device);
+   kfree(tz);
return ERR_PTR(result);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_register);
--
1.8.0.1


--
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/

[PATCH 2/2] Thermal:Remove usless if(!result) before return tz

2014-10-20 Thread Yao Dongdong 
result is always zero when comes here.

Signed-off-by:yaodongd...@huawei.com

---
 drivers/thermal/thermal_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5b7d466..19cac8e 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1568,8 +1568,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,

thermal_zone_device_update(tz);

-   if (!result)
-   return tz;
+   return tz;

 unregister:
release_idr(_tz_idr, _idr_lock, tz->id);
--
1.8.0.1


--
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/

[PATCH 1/2] Thermal:Fix memory leak if occur goto unregister

2014-10-20 Thread Yao Dongdong 
Signed-off-by:yaodongd...@huawei.com

---
 drivers/thermal/thermal_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 71b0ec0..5b7d466 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1574,6 +1574,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,
 unregister:
release_idr(thermal_tz_idr, thermal_idr_lock, tz-id);
device_unregister(tz-device);
+   kfree(tz);
return ERR_PTR(result);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_register);
--
1.8.0.1


--
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/

[PATCH 2/2] Thermal:Remove usless if(!result) before return tz

2014-10-20 Thread Yao Dongdong 
result is always zero when comes here.

Signed-off-by:yaodongd...@huawei.com

---
 drivers/thermal/thermal_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5b7d466..19cac8e 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1568,8 +1568,7 @@ struct thermal_zone_device 
*thermal_zone_device_register(const char *type,

thermal_zone_device_update(tz);

-   if (!result)
-   return tz;
+   return tz;

 unregister:
release_idr(thermal_tz_idr, thermal_idr_lock, tz-id);
--
1.8.0.1


--
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/

Re: [PATCH 2/2] Thermal:Remove usless if(!result) before return tz

2014-10-20 Thread Yao Dongdong 

On 2014/10/20 20:10, Eduardo Valentin wrote:
 Hello Yao

 On Mon, Oct 20, 2014 at 04:27:59PM +0800, Yao Dongdong wrote:
 result is always zero when comes here.

 Signed-off-by:yaodongd...@huawei.com

 ---
  drivers/thermal/thermal_core.c | 3 +--
  1 file changed, 1 insertion(+), 2 deletions(-)

 diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
 index 5b7d466..19cac8e 100644
 --- a/drivers/thermal/thermal_core.c
 +++ b/drivers/thermal/thermal_core.c
 @@ -1568,8 +1568,7 @@ struct thermal_zone_device 
 *thermal_zone_device_register(const char *type,

 thermal_zone_device_update(tz);

 -   if (!result)
 -   return tz;
 +   return tz;

 Adding a return here will make the resource release below not reachable
 in the fail path.

But all fails above followed a goto unregister, so i think it must be 
successful when come here.

Thanks.

  unregister:
 release_idr(thermal_tz_idr, thermal_idr_lock, tz-id);
 --
 1.8.0.1




--
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/

Re: [PATCH v2 2/2] sched/fair: leverage the idle state info when choosing the "idlest" cpu

2014-09-18 Thread Yao Dongdong 
On 2014/9/4 23:32, Nicolas Pitre wrote:
> The code in find_idlest_cpu() looks for the CPU with the smallest load.
> However, if multiple CPUs are idle, the first idle CPU is selected
> irrespective of the depth of its idle state.
>
> Among the idle CPUs we should pick the one with with the shallowest idle
> state, or the latest to have gone idle if all idle CPUs are in the same
> state.  The later applies even when cpuidle is configured out.
>
> This patch doesn't cover the following issues:
>
> - The idle exit latency of a CPU might be larger than the time needed
>   to migrate the waking task to an already running CPU with sufficient
>   capacity, and therefore performance would benefit from task packing
>   in such case (in most cases task packing is about power saving).
>
> - Some idle states have a non negligible and non abortable entry latency
>   which needs to run to completion before the exit latency can start.
>   A concurrent patch series is making this info available to the cpuidle
>   core.  Once available, the entry latency with the idle timestamp could
>   determine when the exit latency may be effective.
>
> Those issues will be handled in due course.  In the mean time, what
> is implemented here should improve things already compared to the current
> state of affairs.
>
> Based on an initial patch from Daniel Lezcano.
>
> Signed-off-by: Nicolas Pitre 
> ---
>  kernel/sched/fair.c | 43 ---
>  1 file changed, 36 insertions(+), 7 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index bfa3c86d0d..416329e1a6 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -23,6 +23,7 @@
>  #include 
>  #include 
>  #include 
> +#include 
>  #include 
>  #include 
>  #include 
> @@ -4428,20 +4429,48 @@ static int
>  find_idlest_cpu(struct sched_group *group, struct task_struct *p, int 
> this_cpu)
>  {
>   unsigned long load, min_load = ULONG_MAX;
> - int idlest = -1;
> + unsigned int min_exit_latency = UINT_MAX;
> + u64 latest_idle_timestamp = 0;
> + int least_loaded_cpu = this_cpu;
> + int shallowest_idle_cpu = -1;
>   int i;
>  
>   /* Traverse only the allowed CPUs */
>   for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
> - load = weighted_cpuload(i);
> -
> - if (load < min_load || (load == min_load && i == this_cpu)) {
> - min_load = load;
> - idlest = i;
> + if (idle_cpu(i)) {
> + struct rq *rq = cpu_rq(i);
> + struct cpuidle_state *idle = idle_get_state(rq);
> + if (idle && idle->exit_latency < min_exit_latency) {
> + /*
> +  * We give priority to a CPU whose idle state
> +  * has the smallest exit latency irrespective
> +  * of any idle timestamp.
> +  */
> + min_exit_latency = idle->exit_latency;
> + latest_idle_timestamp = rq->idle_stamp;
> + shallowest_idle_cpu = i;
> + } else if ((!idle || idle->exit_latency == 
> min_exit_latency) &&
> +rq->idle_stamp > latest_idle_timestamp) {
> + /*
> +  * If equal or no active idle state, then
> +  * the most recently idled CPU might have
> +  * a warmer cache.
> +  */
> + latest_idle_timestamp = rq->idle_stamp;
> + shallowest_idle_cpu = i;
> + }
> + cpuidle_put_state(rq);
> + } else {
I think we needn't test no idle cpus after find an idle cpu.
And what about this?
 } else if (shallowest_idle_cpu == -1) {

> + load = weighted_cpuload(i);
> + if (load < min_load ||
> + (load == min_load && i == this_cpu)) {
> + min_load = load;
> + least_loaded_cpu = i;
> + }
>   }
>   }
>  
> - return idlest;
> + return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : 
> least_loaded_cpu;
>  }
>  
>  /*

--
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/

Re: [PATCH v2 2/2] sched/fair: leverage the idle state info when choosing the idlest cpu

2014-09-18 Thread Yao Dongdong 
On 2014/9/4 23:32, Nicolas Pitre wrote:
 The code in find_idlest_cpu() looks for the CPU with the smallest load.
 However, if multiple CPUs are idle, the first idle CPU is selected
 irrespective of the depth of its idle state.

 Among the idle CPUs we should pick the one with with the shallowest idle
 state, or the latest to have gone idle if all idle CPUs are in the same
 state.  The later applies even when cpuidle is configured out.

 This patch doesn't cover the following issues:

 - The idle exit latency of a CPU might be larger than the time needed
   to migrate the waking task to an already running CPU with sufficient
   capacity, and therefore performance would benefit from task packing
   in such case (in most cases task packing is about power saving).

 - Some idle states have a non negligible and non abortable entry latency
   which needs to run to completion before the exit latency can start.
   A concurrent patch series is making this info available to the cpuidle
   core.  Once available, the entry latency with the idle timestamp could
   determine when the exit latency may be effective.

 Those issues will be handled in due course.  In the mean time, what
 is implemented here should improve things already compared to the current
 state of affairs.

 Based on an initial patch from Daniel Lezcano.

 Signed-off-by: Nicolas Pitre n...@linaro.org
 ---
  kernel/sched/fair.c | 43 ---
  1 file changed, 36 insertions(+), 7 deletions(-)

 diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
 index bfa3c86d0d..416329e1a6 100644
 --- a/kernel/sched/fair.c
 +++ b/kernel/sched/fair.c
 @@ -23,6 +23,7 @@
  #include linux/latencytop.h
  #include linux/sched.h
  #include linux/cpumask.h
 +#include linux/cpuidle.h
  #include linux/slab.h
  #include linux/profile.h
  #include linux/interrupt.h
 @@ -4428,20 +4429,48 @@ static int
  find_idlest_cpu(struct sched_group *group, struct task_struct *p, int 
 this_cpu)
  {
   unsigned long load, min_load = ULONG_MAX;
 - int idlest = -1;
 + unsigned int min_exit_latency = UINT_MAX;
 + u64 latest_idle_timestamp = 0;
 + int least_loaded_cpu = this_cpu;
 + int shallowest_idle_cpu = -1;
   int i;
  
   /* Traverse only the allowed CPUs */
   for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
 - load = weighted_cpuload(i);
 -
 - if (load  min_load || (load == min_load  i == this_cpu)) {
 - min_load = load;
 - idlest = i;
 + if (idle_cpu(i)) {
 + struct rq *rq = cpu_rq(i);
 + struct cpuidle_state *idle = idle_get_state(rq);
 + if (idle  idle-exit_latency  min_exit_latency) {
 + /*
 +  * We give priority to a CPU whose idle state
 +  * has the smallest exit latency irrespective
 +  * of any idle timestamp.
 +  */
 + min_exit_latency = idle-exit_latency;
 + latest_idle_timestamp = rq-idle_stamp;
 + shallowest_idle_cpu = i;
 + } else if ((!idle || idle-exit_latency == 
 min_exit_latency) 
 +rq-idle_stamp  latest_idle_timestamp) {
 + /*
 +  * If equal or no active idle state, then
 +  * the most recently idled CPU might have
 +  * a warmer cache.
 +  */
 + latest_idle_timestamp = rq-idle_stamp;
 + shallowest_idle_cpu = i;
 + }
 + cpuidle_put_state(rq);
 + } else {
I think we needn't test no idle cpus after find an idle cpu.
And what about this?
 } else if (shallowest_idle_cpu == -1) {

 + load = weighted_cpuload(i);
 + if (load  min_load ||
 + (load == min_load  i == this_cpu)) {
 + min_load = load;
 + least_loaded_cpu = i;
 + }
   }
   }
  
 - return idlest;
 + return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : 
 least_loaded_cpu;
  }
  
  /*

--
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/

Re: [PATCH] Documentation/memory-barriers.txt: match table to its comment followed

2014-09-16 Thread Yao Dongdong 
On 2014/9/16 17:24, Jianyu Zhan wrote:
> Hi,
>
> Some one has submitted a patch addressing this issue a few days ago.
> The patch is now being cooked in the paulk's tree now, IIRC.
>
> Thanks,
> Jianyu Zhan
>
I have found the patch you mentioned.

Thanks
> On Tue, Sep 16, 2014 at 4:51 PM, Yao Dongdong  wrote:
>> The table shows CPU2's sequence of events as "x = B; y = A;", but its 
>> comment followed
>> described as "x = A; y = B;".
>>
>> Signed-off-by: Yao Dongdong 
>> ---
>>  Documentation/memory-barriers.txt | 4 ++--
>>  1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/Documentation/memory-barriers.txt 
>> b/Documentation/memory-barriers.txt
>> index a4de88f..9a46bbe 100644
>> --- a/Documentation/memory-barriers.txt
>> +++ b/Documentation/memory-barriers.txt
>> @@ -115,8 +115,8 @@ For example, consider the following sequence of events:
>> CPU 1   CPU 2
>> === ===
>> { A == 1; B == 2 }
>> -   A = 3;  x = B;
>> -   B = 4;  y = A;
>> +   A = 3;  x = A;
>> +   B = 4;  y = B;
>>
>>  The set of accesses as seen by the memory system in the middle can be 
>> arranged
>>  in 24 different combinations:
>> --
>> 1.8.0.1
>>
>> --
>> 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/

--
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/

[PATCH] Documentation/memory-barriers.txt: match table to its comment followed

2014-09-16 Thread Yao Dongdong 
The table shows CPU2's sequence of events as "x = B; y = A;", but its comment 
followed
described as "x = A; y = B;".

Signed-off-by: Yao Dongdong 
---
 Documentation/memory-barriers.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/memory-barriers.txt 
b/Documentation/memory-barriers.txt
index a4de88f..9a46bbe 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -115,8 +115,8 @@ For example, consider the following sequence of events:
CPU 1   CPU 2
=== ===
{ A == 1; B == 2 }
-   A = 3;  x = B;
-   B = 4;  y = A;
+   A = 3;  x = A;
+   B = 4;  y = B;

 The set of accesses as seen by the memory system in the middle can be arranged
 in 24 different combinations:
--
1.8.0.1

--
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/

[PATCH] Documentation/memory-barriers.txt: match table to its comment followed

2014-09-16 Thread Yao Dongdong 
The table shows CPU2's sequence of events as x = B; y = A;, but its comment 
followed
described as x = A; y = B;.

Signed-off-by: Yao Dongdong yaodongd...@huawei.com
---
 Documentation/memory-barriers.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/memory-barriers.txt 
b/Documentation/memory-barriers.txt
index a4de88f..9a46bbe 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -115,8 +115,8 @@ For example, consider the following sequence of events:
CPU 1   CPU 2
=== ===
{ A == 1; B == 2 }
-   A = 3;  x = B;
-   B = 4;  y = A;
+   A = 3;  x = A;
+   B = 4;  y = B;

 The set of accesses as seen by the memory system in the middle can be arranged
 in 24 different combinations:
--
1.8.0.1

--
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/

Re: [PATCH] Documentation/memory-barriers.txt: match table to its comment followed

2014-09-16 Thread Yao Dongdong 
On 2014/9/16 17:24, Jianyu Zhan wrote:
 Hi,

 Some one has submitted a patch addressing this issue a few days ago.
 The patch is now being cooked in the paulk's tree now, IIRC.

 Thanks,
 Jianyu Zhan

I have found the patch you mentioned.

Thanks
 On Tue, Sep 16, 2014 at 4:51 PM, Yao Dongdong yaodongd...@huawei.com wrote:
 The table shows CPU2's sequence of events as x = B; y = A;, but its 
 comment followed
 described as x = A; y = B;.

 Signed-off-by: Yao Dongdong yaodongd...@huawei.com
 ---
  Documentation/memory-barriers.txt | 4 ++--
  1 file changed, 2 insertions(+), 2 deletions(-)

 diff --git a/Documentation/memory-barriers.txt 
 b/Documentation/memory-barriers.txt
 index a4de88f..9a46bbe 100644
 --- a/Documentation/memory-barriers.txt
 +++ b/Documentation/memory-barriers.txt
 @@ -115,8 +115,8 @@ For example, consider the following sequence of events:
 CPU 1   CPU 2
 === ===
 { A == 1; B == 2 }
 -   A = 3;  x = B;
 -   B = 4;  y = A;
 +   A = 3;  x = A;
 +   B = 4;  y = B;

  The set of accesses as seen by the memory system in the middle can be 
 arranged
  in 24 different combinations:
 --
 1.8.0.1

 --
 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/

--
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/