[PATCH] scheduler fixes

 - introduce new type of context-switch locking, this is a must-have for
   ia64 and sparc64.

 - load_balance() bug noticed by Scott Rhine and myself: scan the
   whole list to find imbalance number of tasks, not just the tail
   of the list.

 - sched_yield() fix: use current->array not rq->active.

8 files changed, 17 insertions, 35 deletions

diff --git a/include/asm-i386/system.h b/include/asm-i386/system.h
index b5bfa022bde7..d6b04c0fed09 100644
--- a/include/asm-i386/system.h
+++ b/include/asm-i386/system.h
@@ -11,11 +11,6 @@
 struct task_struct;	/* one of the stranger aspects of C forward declarations.. */
 extern void FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));
 
-#define prepare_arch_schedule(prev)		do { } while(0)
-#define finish_arch_schedule(prev)		do { } while(0)
-#define prepare_arch_switch(rq)			do { } while(0)
-#define finish_arch_switch(rq)			spin_unlock_irq(&(rq)->lock)
-
 #define switch_to(prev,next,last) do {					\
 	asm volatile("pushl %%esi\n\t"					\
 		     "pushl %%edi\n\t"					\
diff --git a/include/asm-ppc/system.h b/include/asm-ppc/system.h
index a9a6b1ac6aab..00fafc7226c1 100644
--- a/include/asm-ppc/system.h
+++ b/include/asm-ppc/system.h
@@ -83,11 +83,6 @@ extern void cacheable_memzero(void *p, unsigned int nb);
 struct device_node;
 extern void note_scsi_host(struct device_node *, void *);
 
-#define prepare_arch_schedule(prev)		do { } while(0)
-#define finish_arch_schedule(prev)		do { } while(0)
-#define prepare_arch_switch(rq)			do { } while(0)
-#define finish_arch_switch(rq)			spin_unlock_irq(&(rq)->lock)
-
 struct task_struct;
 extern void __switch_to(struct task_struct *, struct task_struct *);
 #define switch_to(prev, next, last)	__switch_to((prev), (next))
diff --git a/include/asm-s390/system.h b/include/asm-s390/system.h
index ab7e6a28196f..15e1af97a358 100644
--- a/include/asm-s390/system.h
+++ b/include/asm-s390/system.h
@@ -18,11 +18,6 @@
 #endif
 #include <linux/kernel.h>
 
-#define prepare_arch_schedule(prev)		do { } while (0)
-#define finish_arch_schedule(prev)		do { } while (0)
-#define prepare_arch_switch(rq)			do { } while (0)
-#define finish_arch_switch(rq)			spin_unlock_irq(&(rq)->lock)
-
 #define switch_to(prev,next,last) do {					     \
 	if (prev == next)						     \
 		break;							     \
diff --git a/include/asm-s390x/system.h b/include/asm-s390x/system.h
index 2454658db855..81810a4819b9 100644
--- a/include/asm-s390x/system.h
+++ b/include/asm-s390x/system.h
@@ -18,11 +18,6 @@
 #endif
 #include <linux/kernel.h>
 
-#define prepare_arch_schedule(prev)		do { } while (0)
-#define finish_arch_schedule(prev)		do { } while (0)
-#define prepare_arch_switch(rq)			do { } while (0)
-#define finish_arch_switch(rq)			spin_unlock_irq(&(rq)->lock)
-
 #define switch_to(prev,next),last do {					     \
 	if (prev == next)						     \
 		break;							     \
diff --git a/include/asm-sparc64/system.h b/include/asm-sparc64/system.h
index f98e5915e612..4f8af64d6572 100644
--- a/include/asm-sparc64/system.h
+++ b/include/asm-sparc64/system.h
@@ -140,13 +140,17 @@ extern void __flushw_user(void);
 #define flush_user_windows flushw_user
 #define flush_register_windows flushw_all
 
-#define prepare_arch_schedule(prev)	task_lock(prev)
-#define finish_arch_schedule(prev)	task_unlock(prev)
-#define prepare_arch_switch(rq)		\
-do {	spin_unlock(&(rq)->lock);	\
-	flushw_all();			\
+#define prepare_arch_switch(rq, next)		\
+do {	spin_lock(&(next)->switch_lock);	\
+	spin_unlock(&(rq)->lock);		\
+	flushw_all();				\
 } while (0)
-#define finish_arch_switch(rq)		local_irq_enable()
+
+#define finish_arch_switch(rq, prev)		\
+do {	spin_unlock_irq(&(prev)->switch_lock);	\
+} while (0)
+
+
 
 #ifndef CONFIG_DEBUG_SPINLOCK
 #define CHECK_LOCKS(PREV)	do { } while(0)
diff --git a/include/asm-x86_64/system.h b/include/asm-x86_64/system.h
index c9604630f910..c0c88ba72c97 100644
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -13,11 +13,6 @@
 #define LOCK_PREFIX ""
 #endif
 
-#define prepare_arch_schedule(prev)            do { } while(0)
-#define finish_arch_schedule(prev)             do { } while(0)
-#define prepare_arch_switch(rq)                        do { } while(0)
-#define finish_arch_switch(rq)                 spin_unlock_irq(&(rq)->lock)
-
 #define __STR(x) #x
 #define STR(x) __STR(x)
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 4fcbad0862b8..56c6b7181796 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -47,7 +47,7 @@
     lock_depth:		-1,						\
     prio:		MAX_PRIO-20,					\
     static_prio:	MAX_PRIO-20,					\
-    policy:		SCHED_OTHER,					\
+    policy:		SCHED_NORMAL,					\
     cpus_allowed:	-1,						\
     mm:			NULL,						\
     active_mm:		&init_mm,					\
@@ -78,6 +78,7 @@
     pending:		{ NULL, &tsk.pending.head, {{0}}},		\
     blocked:		{{0}},						\
     alloc_lock:		SPIN_LOCK_UNLOCKED,				\
+    switch_lock:	SPIN_LOCK_UNLOCKED,				\
     journal_info:	NULL,						\
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 004d2a129ca4..6dd4746e58cd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -116,7 +116,7 @@ extern unsigned long nr_uninterruptible(void);
 /*
  * Scheduling policies
  */
-#define SCHED_OTHER		0
+#define SCHED_NORMAL		0
 #define SCHED_FIFO		1
 #define SCHED_RR		2
 
@@ -207,7 +207,7 @@ struct signal_struct {
 
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * priority is 0..MAX_RT_PRIO-1, and SCHED_OTHER tasks are
+ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL tasks are
  * in the range MAX_RT_PRIO..MAX_PRIO-1. Priority values
  * are inverted: lower p->prio value means higher priority.
  *
@@ -264,7 +264,7 @@ struct task_struct {
 
 	unsigned long policy;
 	unsigned long cpus_allowed;
-	unsigned int time_slice;
+	unsigned int time_slice, first_time_slice;
 
 	struct list_head tasks;
 
@@ -361,6 +361,8 @@ struct task_struct {
    	u32 self_exec_id;
 /* Protection of (de-)allocation: mm, files, fs, tty */
 	spinlock_t alloc_lock;
+/* context-switch lock */
+	spinlock_t switch_lock;
 
 /* journalling filesystem info */
 	void *journal_info;