scheduler changes for v3.10

index 1616562..1fe4970 100644
@@ -1,31 +1,10 @@
 #ifndef _ASM_X86_CONTEXT_TRACKING_H
 #define _ASM_X86_CONTEXT_TRACKING_H
 
-#ifndef __ASSEMBLY__
-#include <linux/context_tracking.h>
-#include <asm/ptrace.h>
-
-static inline void exception_enter(struct pt_regs *regs)
-{
-	user_exit();
-}
-
-static inline void exception_exit(struct pt_regs *regs)
-{
-#ifdef CONFIG_CONTEXT_TRACKING
-	if (user_mode(regs))
-		user_enter();
-#endif
-}
-
-#else /* __ASSEMBLY__ */
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER call schedule_user
 #else
 # define SCHEDULE_USER call schedule
 #endif
 
-#endif /* !__ASSEMBLY__ */
-
 #endif

index b686a90..cd6d9a5 100644
@@ -20,6 +20,7 @@
  *   Authors: Anthony Liguori <[email protected]>
  */
 
+#include <linux/context_tracking.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/kvm_para.h>

@@ -43,7 +44,6 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/kvm_guest.h>
-#include <asm/context_tracking.h>
 
 static int kvmapf = 1;
 

@@ -254,16 +254,18 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
 dotraplinkage void __kprobes
 do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	enum ctx_state prev_state;
+
 	switch (kvm_read_and_reset_pf_reason()) {
 	default:
 		do_page_fault(regs, error_code);
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
-		exception_enter(regs);
+		prev_state = exception_enter();
 		exit_idle();
 		kvm_async_pf_task_wait((u32)read_cr2());
-		exception_exit(regs);
+		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
 		rcu_irq_enter();

216 lines not on this page · raw message

index 2b97525..fa8c02d 100644
@@ -13,12 +13,12 @@
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 #include <linux/prefetch.h>		/* prefetchw			*/
+#include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
-#include <asm/context_tracking.h>	/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:

@@ -1222,7 +1222,9 @@ good_area:
 dotraplinkage void __kprobes
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
-	exception_enter(regs);
+	enum ctx_state prev_state;
+
+	prev_state = exception_enter();
 	__do_page_fault(regs, error_code);
-	exception_exit(regs);
+	exception_exit(prev_state);
 }

index 900af59..95c02c0 100644
@@ -458,7 +458,6 @@ struct cgroup_subsys {
 	void (*bind)(struct cgroup *root);
 
 	int subsys_id;
-	int active;
 	int disabled;
 	int early_init;
 	/*

index b28d161..365f4a6 100644
@@ -1,9 +1,9 @@
 #ifndef _LINUX_CONTEXT_TRACKING_H
 #define _LINUX_CONTEXT_TRACKING_H
 
-#ifdef CONFIG_CONTEXT_TRACKING
 #include <linux/sched.h>
 #include <linux/percpu.h>
+#include <asm/ptrace.h>
 
 struct context_tracking {
 	/*

@@ -13,12 +13,13 @@ struct context_tracking {
 	 * may be further optimized using static keys.
 	 */
 	bool active;
-	enum {
+	enum ctx_state {
 		IN_KERNEL = 0,
 		IN_USER,
 	} state;
 };
 
+#ifdef CONFIG_CONTEXT_TRACKING
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
 static inline bool context_tracking_in_user(void)

@@ -33,12 +34,31 @@ static inline bool context_tracking_active(void)
 
 extern void user_enter(void);
 extern void user_exit(void);
+
+static inline enum ctx_state exception_enter(void)
+{
+	enum ctx_state prev_ctx;
+
+	prev_ctx = this_cpu_read(context_tracking.state);
+	user_exit();
+
+	return prev_ctx;
+}
+
+static inline void exception_exit(enum ctx_state prev_ctx)
+{
+	if (prev_ctx == IN_USER)
+		user_enter();
+}
+
 extern void context_tracking_task_switch(struct task_struct *prev,
 					 struct task_struct *next);
 #else
 static inline bool context_tracking_in_user(void) { return false; }
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
+static inline enum ctx_state exception_enter(void) { return 0; }
+static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
 						struct task_struct *next) { }
 #endif /* !CONFIG_CONTEXT_TRACKING */

index b8ba855..931a619 100644
@@ -30,6 +30,15 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
 }
 
 /**
+ * div64_u64_rem - unsigned 64bit divide with 64bit divisor
+ */
+static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
+{
+	*remainder = dividend % divisor;
+	return dividend / divisor;
+}
+
+/**
  * div64_u64 - unsigned 64bit divide with 64bit divisor
  */
 static inline u64 div64_u64(u64 dividend, u64 divisor)

@@ -61,8 +70,16 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder);
 #endif
 
+#ifndef div64_u64_rem
+extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder);
+#endif
+
 #ifndef div64_u64
-extern u64 div64_u64(u64 dividend, u64 divisor);
+static inline u64 div64_u64(u64 dividend, u64 divisor)
+{
+	u64 remainder;
+	return div64_u64_rem(dividend, divisor, &remainder);
+}
 #endif
 
 #ifndef div64_s64

272 lines not on this page · raw message

index a32f943..5c46281 100644
@@ -4468,7 +4468,6 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	 * need to invoke fork callbacks here. */
 	BUG_ON(!list_empty(&init_task.tasks));
 
-	ss->active = 1;
 	BUG_ON(online_css(ss, dummytop));
 
 	mutex_unlock(&cgroup_mutex);

@@ -4573,7 +4572,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	}
 	write_unlock(&css_set_lock);
 
-	ss->active = 1;
 	ret = online_css(ss, dummytop);
 	if (ret)
 		goto err_unload;

@@ -4614,7 +4612,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	mutex_lock(&cgroup_mutex);
 
 	offline_css(ss, dummytop);
-	ss->active = 0;
 
 	if (ss->use_id)
 		idr_destroy(&ss->idr);

index 8d932b1..f3146ed 100644
@@ -1230,7 +1230,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	p->prev_cputime.utime = p->prev_cputime.stime = 0;
 #endif
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN

341 lines not on this page · raw message

296 lines not on this page · raw message

new file mode 100644
index 0000000..ed60562
@@ -0,0 +1,17 @@
+#ifdef CONFIG_CGROUP_CPUACCT
+
+extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
+
+#else
+
+static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+}
+
+static inline void
+cpuacct_account_field(struct task_struct *p, int index, u64 val)
+{
+}
+
+#endif

268 lines not on this page · raw message

327 lines not on this page · raw message

index b6baf37..b8ce773 100644
@@ -13,6 +13,16 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
+
+static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
+{
+	idle_exit_fair(rq);
+}
+
+static void post_schedule_idle(struct rq *rq)
+{
+	idle_enter_fair(rq);
+}
 #endif /* CONFIG_SMP */
 /*
  * Idle tasks are unconditionally rescheduled:

@@ -25,6 +35,10 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
+#ifdef CONFIG_SMP
+	/* Trigger the post schedule to do an idle_enter for CFS */
+	rq->post_schedule = 1;
+#endif
 	return rq->idle;
 }
 

@@ -86,6 +100,8 @@ const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
+	.pre_schedule		= pre_schedule_idle,
+	.post_schedule		= post_schedule_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,

290 lines not on this page · raw message

index a163b6c..3af5728 100644
@@ -79,9 +79,10 @@ EXPORT_SYMBOL(div_s64_rem);
 #endif
 
 /**
- * div64_u64 - unsigned 64bit divide with 64bit divisor
+ * div64_u64_rem - unsigned 64bit divide with 64bit divisor and 64bit remainder
  * @dividend:	64bit dividend
  * @divisor:	64bit divisor
+ * @remainder:  64bit remainder
  *
  * This implementation is a modified version of the algorithm proposed
  * by the book 'Hacker's Delight'.  The original source and full proof

@@ -89,27 +90,33 @@ EXPORT_SYMBOL(div_s64_rem);
  *
  * 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c.txt'
  */
-#ifndef div64_u64
-u64 div64_u64(u64 dividend, u64 divisor)
+#ifndef div64_u64_rem
+u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
 {
 	u32 high = divisor >> 32;
 	u64 quot;
 
 	if (high == 0) {
-		quot = div_u64(dividend, divisor);
+		u32 rem32;
+		quot = div_u64_rem(dividend, divisor, &rem32);
+		*remainder = rem32;
 	} else {
 		int n = 1 + fls(high);
 		quot = div_u64(dividend >> n, divisor >> n);
 
 		if (quot != 0)
 			quot--;
-		if ((dividend - quot * divisor) >= divisor)
+
+		*remainder = dividend - quot * divisor;
+		if (*remainder >= divisor) {
 			quot++;
+			*remainder -= divisor;
+		}
 	}
 
 	return quot;
 }
-EXPORT_SYMBOL(div64_u64);
+EXPORT_SYMBOL(div64_u64_rem);
 #endif
 
 /**