Merge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-s…

…ched

* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched: (140 commits)
  sched: sync wakeups preempt too
  sched: affine sync wakeups
  sched: guest CPU accounting: maintain guest state in KVM
  sched: guest CPU accounting: maintain stats in account_system_time()
  sched: guest CPU accounting: add guest-CPU /proc/<pid>/stat fields
  sched: guest CPU accounting: add guest-CPU /proc/stat field
  sched: domain sysctl fixes: add terminator comment
  sched: domain sysctl fixes: do not crash on allocation failure
  sched: domain sysctl fixes: unregister the sysctl table before domains
  sched: domain sysctl fixes: use for_each_online_cpu()
  sched: domain sysctl fixes: use kcalloc()
  Make scheduler debug file operations const
  sched: enable wake-idle on CONFIG_SCHED_MC=y
  sched: reintroduce topology.h tunings
  sched: allow the immediate migration of cache-cold tasks
  sched: debug, improve migration statistics
  sched: debug: increase width of debug line
  sched: activate task_hot() only on fair-scheduled tasks
  sched: reintroduce cache-hot affinity
  sched: speed up context-switches a bit
  ...

Documentation/sched-design-CFS.txt

@@ -117,3 +117,70 @@ Some implementation details:
    iterators of the scheduling modules are used. The balancing code got
    quite a bit simpler as a result.
 
+
+Group scheduler extension to CFS
+================================
+
+Normally the scheduler operates on individual tasks and strives to provide
+fair CPU time to each task. Sometimes, it may be desirable to group tasks
+and provide fair CPU time to each such task group. For example, it may
+be desirable to first provide fair CPU time to each user on the system
+and then to each task belonging to a user.
+
+CONFIG_FAIR_GROUP_SCHED strives to achieve exactly that. It lets
+SCHED_NORMAL/BATCH tasks be be grouped and divides CPU time fairly among such
+groups. At present, there are two (mutually exclusive) mechanisms to group
+tasks for CPU bandwidth control purpose:
+
+	- Based on user id (CONFIG_FAIR_USER_SCHED)
+		In this option, tasks are grouped according to their user id.
+	- Based on "cgroup" pseudo filesystem (CONFIG_FAIR_CGROUP_SCHED)
+		This options lets the administrator create arbitrary groups
+		of tasks, using the "cgroup" pseudo filesystem. See
+		Documentation/cgroups.txt for more information about this
+		filesystem.
+
+Only one of these options to group tasks can be chosen and not both.
+
+Group scheduler tunables:
+
+When CONFIG_FAIR_USER_SCHED is defined, a directory is created in sysfs for
+each new user and a "cpu_share" file is added in that directory.
+
+	# cd /sys/kernel/uids
+	# cat 512/cpu_share		# Display user 512's CPU share
+	1024
+	# echo 2048 > 512/cpu_share	# Modify user 512's CPU share
+	# cat 512/cpu_share		# Display user 512's CPU share
+	2048
+	#
+
+CPU bandwidth between two users are divided in the ratio of their CPU shares.
+For ex: if you would like user "root" to get twice the bandwidth of user
+"guest", then set the cpu_share for both the users such that "root"'s
+cpu_share is twice "guest"'s cpu_share
+
+
+When CONFIG_FAIR_CGROUP_SCHED is defined, a "cpu.shares" file is created
+for each group created using the pseudo filesystem. See example steps
+below to create task groups and modify their CPU share using the "cgroups"
+pseudo filesystem
+
+	# mkdir /dev/cpuctl
+	# mount -t cgroup -ocpu none /dev/cpuctl
+	# cd /dev/cpuctl
+
+	# mkdir multimedia	# create "multimedia" group of tasks
+	# mkdir browser		# create "browser" group of tasks
+
+	# #Configure the multimedia group to receive twice the CPU bandwidth
+	# #that of browser group
+
+	# echo 2048 > multimedia/cpu.shares
+	# echo 1024 > browser/cpu.shares
+
+	# firefox &	# Launch firefox and move it to "browser" group
+	# echo <firefox_pid> > browser/tasks
+
+	# #Launch gmplayer (or your favourite movie player)
+	# echo <movie_player_pid> > multimedia/tasks

arch/i386/Kconfig

@@ -214,6 +214,17 @@ config X86_ES7000
 
 endchoice
 
+config SCHED_NO_NO_OMIT_FRAME_POINTER
+	bool "Single-depth WCHAN output"
+	default y
+	help
+	  Calculate simpler /proc/<PID>/wchan values. If this option
+	  is disabled then wchan values will recurse back to the
+	  caller function. This provides more accurate wchan values,
+	  at the expense of slightly more scheduling overhead.
+
+	  If in doubt, say "Y".
+
 config PARAVIRT
 	bool "Paravirtualization support (EXPERIMENTAL)"
 	depends on EXPERIMENTAL

drivers/kvm/kvm.h

@@ -624,6 +624,16 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 
 int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
+static inline void kvm_guest_enter(void)
+{
+	current->flags |= PF_VCPU;
+}
+
+static inline void kvm_guest_exit(void)
+{
+	current->flags &= ~PF_VCPU;
+}
+
 static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 				     u32 error_code)
 {

drivers/kvm/kvm_main.c

@@ -2046,13 +2046,15 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run);
 
 	vcpu->guest_mode = 1;
+	kvm_guest_enter();
 
 	if (vcpu->requests)
 		if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
 			kvm_x86_ops->tlb_flush(vcpu);
 
 	kvm_x86_ops->run(vcpu, kvm_run);
 
+	kvm_guest_exit();
 	vcpu->guest_mode = 0;
 	local_irq_enable();
 

fs/pipe.c

@@ -45,8 +45,7 @@ void pipe_wait(struct pipe_inode_info *pipe)
 	 * Pipes are system-local resources, so sleeping on them
 	 * is considered a noninteractive wait:
 	 */
-	prepare_to_wait(&pipe->wait, &wait,
-			TASK_INTERRUPTIBLE | TASK_NONINTERACTIVE);
+	prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE);
 	if (pipe->inode)
 		mutex_unlock(&pipe->inode->i_mutex);
 	schedule();
@@ -383,7 +382,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 
 	/* Signal writers asynchronously that there is more room. */
 	if (do_wakeup) {
-		wake_up_interruptible(&pipe->wait);
+		wake_up_interruptible_sync(&pipe->wait);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
 	if (ret > 0)
@@ -556,7 +555,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
 out:
 	mutex_unlock(&inode->i_mutex);
 	if (do_wakeup) {
-		wake_up_interruptible(&pipe->wait);
+		wake_up_interruptible_sync(&pipe->wait);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 	}
 	if (ret > 0)
@@ -650,7 +649,7 @@ pipe_release(struct inode *inode, int decr, int decw)
 	if (!pipe->readers && !pipe->writers) {
 		free_pipe_info(inode);
 	} else {
-		wake_up_interruptible(&pipe->wait);
+		wake_up_interruptible_sync(&pipe->wait);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}

fs/proc/array.c

@@ -370,6 +370,11 @@ static cputime_t task_stime(struct task_struct *p)
 }
 #endif
 
+static cputime_t task_gtime(struct task_struct *p)
+{
+	return p->gtime;
+}
+
 static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 {
 	unsigned long vsize, eip, esp, wchan = ~0UL;
@@ -385,6 +390,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 	unsigned long cmin_flt = 0, cmaj_flt = 0;
 	unsigned long  min_flt = 0,  maj_flt = 0;
 	cputime_t cutime, cstime, utime, stime;
+	cputime_t cgtime, gtime;
 	unsigned long rsslim = 0;
 	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
@@ -403,6 +409,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
 	cutime = cstime = utime = stime = cputime_zero;
+	cgtime = gtime = cputime_zero;
 
 	rcu_read_lock();
 	if (lock_task_sighand(task, &flags)) {
@@ -420,6 +427,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 		cmaj_flt = sig->cmaj_flt;
 		cutime = sig->cutime;
 		cstime = sig->cstime;
+		cgtime = sig->cgtime;
 		rsslim = sig->rlim[RLIMIT_RSS].rlim_cur;
 
 		/* add up live thread stats at the group level */
@@ -430,13 +438,15 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 				maj_flt += t->maj_flt;
 				utime = cputime_add(utime, task_utime(t));
 				stime = cputime_add(stime, task_stime(t));
+				gtime = cputime_add(gtime, task_gtime(t));
 				t = next_thread(t);
 			} while (t != task);
 
 			min_flt += sig->min_flt;
 			maj_flt += sig->maj_flt;
 			utime = cputime_add(utime, sig->utime);
 			stime = cputime_add(stime, sig->stime);
+			gtime += cputime_add(gtime, sig->gtime);
 		}
 
 		sid = signal_session(sig);
@@ -454,6 +464,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 		maj_flt = task->maj_flt;
 		utime = task_utime(task);
 		stime = task_stime(task);
+		gtime = task_gtime(task);
 	}
 
 	/* scale priority and nice values from timeslices to -20..20 */
@@ -471,7 +482,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 
 	res = sprintf(buffer, "%d (%s) %c %d %d %d %d %d %u %lu \
 %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
-%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu\n",
+%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
 		task->pid,
 		tcomm,
 		state,
@@ -516,7 +527,9 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 		task_cpu(task),
 		task->rt_priority,
 		task->policy,
-		(unsigned long long)delayacct_blkio_ticks(task));
+		(unsigned long long)delayacct_blkio_ticks(task),
+		cputime_to_clock_t(gtime),
+		cputime_to_clock_t(cgtime));
 	if (mm)
 		mmput(mm);
 	return res;

fs/proc/base.c

@@ -304,7 +304,7 @@ static int proc_pid_schedstat(struct task_struct *task, char *buffer)
 	return sprintf(buffer, "%llu %llu %lu\n",
 			task->sched_info.cpu_time,
 			task->sched_info.run_delay,
-			task->sched_info.pcnt);
+			task->sched_info.pcount);
 }
 #endif
 

fs/proc/proc_misc.c

@@ -443,6 +443,7 @@ static int show_stat(struct seq_file *p, void *v)
 	int i;
 	unsigned long jif;
 	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
+	cputime64_t guest;
 	u64 sum = 0;
 	struct timespec boottime;
 	unsigned int *per_irq_sum;
@@ -453,6 +454,7 @@ static int show_stat(struct seq_file *p, void *v)
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = cputime64_zero;
+	guest = cputime64_zero;
 	getboottime(&boottime);
 	jif = boottime.tv_sec;
 
@@ -467,22 +469,24 @@ static int show_stat(struct seq_file *p, void *v)
 		irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq);
 		softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
+		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
 		for (j = 0; j < NR_IRQS; j++) {
 			unsigned int temp = kstat_cpu(i).irqs[j];
 			sum += temp;
 			per_irq_sum[j] += temp;
 		}
 	}
 
-	seq_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu\n",
+	seq_printf(p, "cpu  %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
 		(unsigned long long)cputime64_to_clock_t(user),
 		(unsigned long long)cputime64_to_clock_t(nice),
 		(unsigned long long)cputime64_to_clock_t(system),
 		(unsigned long long)cputime64_to_clock_t(idle),
 		(unsigned long long)cputime64_to_clock_t(iowait),
 		(unsigned long long)cputime64_to_clock_t(irq),
 		(unsigned long long)cputime64_to_clock_t(softirq),
-		(unsigned long long)cputime64_to_clock_t(steal));
+		(unsigned long long)cputime64_to_clock_t(steal),
+		(unsigned long long)cputime64_to_clock_t(guest));
 	for_each_online_cpu(i) {
 
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
@@ -494,7 +498,9 @@ static int show_stat(struct seq_file *p, void *v)
 		irq = kstat_cpu(i).cpustat.irq;
 		softirq = kstat_cpu(i).cpustat.softirq;
 		steal = kstat_cpu(i).cpustat.steal;
-		seq_printf(p, "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu\n",
+		guest = kstat_cpu(i).cpustat.guest;
+		seq_printf(p,
+			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
 			i,
 			(unsigned long long)cputime64_to_clock_t(user),
 			(unsigned long long)cputime64_to_clock_t(nice),
@@ -503,7 +509,8 @@ static int show_stat(struct seq_file *p, void *v)
 			(unsigned long long)cputime64_to_clock_t(iowait),
 			(unsigned long long)cputime64_to_clock_t(irq),
 			(unsigned long long)cputime64_to_clock_t(softirq),
-			(unsigned long long)cputime64_to_clock_t(steal));
+			(unsigned long long)cputime64_to_clock_t(steal),
+			(unsigned long long)cputime64_to_clock_t(guest));
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 

include/linux/kernel_stat.h

@@ -23,6 +23,7 @@ struct cpu_usage_stat {
 	cputime64_t idle;
 	cputime64_t iowait;
 	cputime64_t steal;
+	cputime64_t guest;
 };
 
 struct kernel_stat {