um: Switch clocksource to hrtimers

UML is using an obsolete itimer call for
all timers and "polls" for kernel space timer firing
in its userspace portion resulting in a long list
of bugs and incorrect behaviour(s). It also uses
ITIMER_VIRTUAL for its timer which results in the
timer being dependent on it running and the cpu
load.

This patch fixes this by moving to posix high resolution
timers firing off CLOCK_MONOTONIC and relaying the timer
correctly to the UML userspace.

Fixes:
- crashes when hosts suspends/resumes
- broken userspace timers - effecive ~40Hz instead
of what they should be. Note - this modifies skas behavior
by no longer setting an itimer per clone(). Timer events
are relayed instead.
- kernel network packet scheduling disciplines
- tcp behaviour especially under load
- various timer related corner cases

Finally, overall responsiveness of userspace is better.

Signed-off-by: Thomas Meyer <[e-mail]>
Signed-off-by: Anton Ivanov <[e-mail]>
[rw: massaged commit message]
Signed-off-by: Richard Weinberger <[e-mail]>

arch/um/Makefile

···
 # The wrappers will select whether using "malloc" or the kernel allocator.
 LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc
 
-LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt))
+LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt
 
 # Used by link-vmlinux.sh which has special support for um link
 export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)

arch/um/include/shared/os.h

···
 /*
+ * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk})
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
 /* process.c */
 extern unsigned long os_process_pc(int pid);
 extern int os_process_parent(int pid);
+extern void os_alarm_process(int pid);
 extern void os_stop_process(int pid);
 extern void os_kill_process(int pid, int reap_child);
 extern void os_kill_ptraced_process(int pid, int reap_child);
···
 extern char *get_umid(void);
 
 /* signal.c */
-extern void timer_init(void);
+extern void timer_set_signal_handler(void);
 extern void set_sigstack(void *sig_stack, int size);
 extern void remove_sigstack(void);
 extern void set_handler(int sig);
···
 extern int get_signals(void);
 extern int set_signals(int enable);
 extern int os_is_signal_stack(void);
+extern void deliver_alarm(void);
 
 /* util.c */
 extern void stack_protections(unsigned long address);
···
 extern void os_fix_helper_signals(void);
 
 /* time.c */
-extern void idle_sleep(unsigned long long nsecs);
-extern int set_interval(void);
-extern int timer_one_shot(int ticks);
-extern long long disable_timer(void);
+extern void os_idle_sleep(unsigned long long nsecs);
+extern int os_timer_create(void* timer);
+extern int os_timer_set_interval(void* timer, void* its);
+extern int os_timer_one_shot(int ticks);
+extern long long os_timer_disable(void);
+extern long os_timer_remain(void* timer);
 extern void uml_idle_timer(void);
+extern long long os_persistent_clock_emulation(void);
 extern long long os_nsecs(void);
+extern long long os_vnsecs(void);
 
 /* skas/mem.c */
 extern long run_syscall_stub(struct mm_id * mm_idp,

arch/um/include/shared/skas/stub-data.h

···
 /*
+
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2005 Jeff Dike ([e-mail])
  * Licensed under the GPL
  */
···
 #ifndef __STUB_DATA_H
 #define __STUB_DATA_H
 
-#include <sys/time.h>
+#include <time.h>
 
 struct stub_data {
-	long offset;
+	unsigned long offset;
 	int fd;
-	struct itimerval timer;
 	long err;
 };
 

arch/um/include/shared/timer-internal.h

···
+/*
+ * Copyright (C) 2012 - 2014 Cisco Systems
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __TIMER_INTERNAL_H__
+#define __TIMER_INTERNAL_H__
+
+#define TIMER_MULTIPLIER 256
+#define TIMER_MIN_DELTA  500
+
+#endif

arch/um/kernel/process.c

···
 /*
+ * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk})
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Copyright 2003 PathScale, Inc.
  * Licensed under the GPL
···
 #include <kern_util.h>
 #include <os.h>
 #include <skas.h>
+#include <timer-internal.h>
 
 /*
  * This is a per-cpu array.  A processor only modifies its entry and it only
···
 
 void arch_cpu_idle(void)
 {
-	unsigned long long nsecs;
-
 	cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
-	nsecs = disable_timer();
-	idle_sleep(nsecs);
+	os_idle_sleep(UM_NSEC_PER_SEC);
 	local_irq_enable();
 }
 

arch/um/kernel/skas/clone.c

···
 /*
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
 		goto out;
 
 	err = stub_syscall4(__NR_ptrace, PTRACE_TRACEME, 0, 0, 0);
-	if (err)
-		goto out;
-
-	err = stub_syscall3(__NR_setitimer, ITIMER_VIRTUAL,
-			    (long) &data->timer, 0);
 	if (err)
 		goto out;
 

arch/um/kernel/skas/mmu.c

···
 /*
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
 	if (current->mm != NULL && current->mm != &init_mm)
 		from_mm = &current->mm->context;
 
+	block_signals();
 	if (from_mm)
 		to_mm->id.u.pid = copy_context_skas0(stack,
 						     from_mm->id.u.pid);
 	else to_mm->id.u.pid = start_userspace(stack);
+	unblock_signals();
 
 	if (to_mm->id.u.pid < 0) {
 		ret = to_mm->id.u.pid;

arch/um/kernel/time.c

···
 /*
+ * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk})
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
+ * Copyright (C) 2012-2014 Cisco Systems
  * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
 #include <linux/threads.h>
 #include <asm/irq.h>
 #include <asm/param.h>
 #include <kern_util.h>
 #include <os.h>
+#include <timer-internal.h>
 
 void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 {
···
 
 static int itimer_shutdown(struct clock_event_device *evt)
 {
-	disable_timer();
+	os_timer_disable();
 	return 0;
 }
 
 static int itimer_set_periodic(struct clock_event_device *evt)
 {
-	set_interval();
+	os_timer_set_interval(NULL, NULL);
 	return 0;
 }
 
 static int itimer_next_event(unsigned long delta,
 			     struct clock_event_device *evt)
 {
-	return timer_one_shot(delta + 1);
+	return os_timer_one_shot(delta);
 }
 
-static struct clock_event_device itimer_clockevent = {
-	.name			= "itimer",
+static int itimer_one_shot(struct clock_event_device *evt)
+{
+	os_timer_one_shot(1);
+	return 0;
+}
+
+static struct clock_event_device timer_clockevent = {
+	.name			= "posix-timer",
 	.rating			= 250,
 	.cpumask		= cpu_all_mask,
 	.features		= CLOCK_EVT_FEAT_PERIODIC |
 				  CLOCK_EVT_FEAT_ONESHOT,
 	.set_state_shutdown	= itimer_shutdown,
 	.set_state_periodic	= itimer_set_periodic,
-	.set_state_oneshot	= itimer_shutdown,
+	.set_state_oneshot	= itimer_one_shot,
 	.set_next_event		= itimer_next_event,
-	.shift			= 32,
+	.shift			= 0,
+	.max_delta_ns		= 0xffffffff,
+	.min_delta_ns		= TIMER_MIN_DELTA, //microsecond resolution should be enough for anyone, same as 640K RAM
 	.irq			= 0,
+	.mult			= 1,
 };
 
 static irqreturn_t um_timer(int irq, void *dev)
 {
-	(*itimer_clockevent.event_handler)(&itimer_clockevent);
+	if (get_current()->mm != NULL)
+	{
+        /* userspace - relay signal, results in correct userspace timers */
+		os_alarm_process(get_current()->mm->context.id.u.pid);
+	}
+
+	(*timer_clockevent.event_handler)(&timer_clockevent);
 
 	return IRQ_HANDLED;
 }
 
-static cycle_t itimer_read(struct clocksource *cs)
+static cycle_t timer_read(struct clocksource *cs)
 {
-	return os_nsecs() / 1000;
+	return os_nsecs() / TIMER_MULTIPLIER;
 }
 
-static struct clocksource itimer_clocksource = {
-	.name		= "itimer",
+static struct clocksource timer_clocksource = {
+	.name		= "timer",
 	.rating		= 300,
-	.read		= itimer_read,
+	.read		= timer_read,
 	.mask		= CLOCKSOURCE_MASK(64),
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static void __init setup_itimer(void)
+static void __init timer_setup(void)
 {
 	int err;
 
-	err = request_irq(TIMER_IRQ, um_timer, 0, "timer", NULL);
+	err = request_irq(TIMER_IRQ, um_timer, IRQF_TIMER, "hr timer", NULL);
 	if (err != 0)
 		printk(KERN_ERR "register_timer : request_irq failed - "
 		       "errno = %d\n", -err);
 
-	itimer_clockevent.mult = div_sc(HZ, NSEC_PER_SEC, 32);
-	itimer_clockevent.max_delta_ns =
-		clockevent_delta2ns(60 * HZ, &itimer_clockevent);
-	itimer_clockevent.min_delta_ns =
-		clockevent_delta2ns(1, &itimer_clockevent);
-	err = clocksource_register_hz(&itimer_clocksource, USEC_PER_SEC);
+	err = os_timer_create(NULL);
+	if (err != 0) {
+		printk(KERN_ERR "creation of timer failed - errno = %d\n", -err);
+		return;
+	}
+
+	err = clocksource_register_hz(&timer_clocksource, NSEC_PER_SEC/TIMER_MULTIPLIER);
 	if (err) {
 		printk(KERN_ERR "clocksource_register_hz returned %d\n", err);
 		return;
 	}
-	clockevents_register_device(&itimer_clockevent);
+	clockevents_register_device(&timer_clockevent);
 }
 
 void read_persistent_clock(struct timespec *ts)
 {
-	long long nsecs = os_nsecs();
+	long long nsecs = os_persistent_clock_emulation();
 
 	set_normalized_timespec(ts, nsecs / NSEC_PER_SEC,
 				nsecs % NSEC_PER_SEC);
···
 
 void __init time_init(void)
 {
-	timer_init();
-	late_time_init = setup_itimer;
+	timer_set_signal_handler();
+	late_time_init = timer_setup;
 }

arch/um/os-Linux/internal.h

···
-void alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc);

arch/um/os-Linux/main.c

···
 /*
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
 
 	/*
 	 * This signal stuff used to be in the reboot case.  However,
-	 * sometimes a SIGVTALRM can come in when we're halting (reproducably
+	 * sometimes a timer signal can come in when we're halting (reproducably
 	 * when writing out gcov information, presumably because that takes
 	 * some time) and cause a segfault.
 	 */
 
-	/* stop timers and set SIGVTALRM to be ignored */
-	disable_timer();
+	/* stop timers and set timer signal to be ignored */
+	os_timer_disable();
 
 	/* disable SIGIO for the fds and set SIGIO to be ignored */
 	err = deactivate_all_fds();

arch/um/os-Linux/process.c

···
 /*
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
 		printk(UM_KERN_ERR "Failed to scan '%s'\n", data);
 
 	return parent;
+}
+
+void os_alarm_process(int pid)
+{
+	kill(pid, SIGALRM);
 }
 
 void os_stop_process(int pid)

arch/um/os-Linux/signal.c

···
 /*
+ * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk})
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2004 PathScale, Inc
  * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
···
 #include <kern_util.h>
 #include <os.h>
 #include <sysdep/mcontext.h>
-#include "internal.h"
 
 void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
 	[SIGTRAP]	= relay_signal,
···
 	[SIGBUS]	= bus_handler,
 	[SIGSEGV]	= segv_handler,
 	[SIGIO]		= sigio_handler,
-	[SIGVTALRM]	= timer_handler };
+	[SIGALRM]	= timer_handler
+};
 
 static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 {
···
 	}
 
 	/* enable signals if sig isn't IRQ signal */
-	if ((sig != SIGIO) && (sig != SIGWINCH) && (sig != SIGVTALRM))
+	if ((sig != SIGIO) && (sig != SIGWINCH) && (sig != SIGALRM))
 		unblock_signals();
 
 	(*sig_info[sig])(sig, si, &r);
···
 #define SIGIO_BIT 0
 #define SIGIO_MASK (1 << SIGIO_BIT)
 
-#define SIGVTALRM_BIT 1
-#define SIGVTALRM_MASK (1 << SIGVTALRM_BIT)
+#define SIGALRM_BIT 1
+#define SIGALRM_MASK (1 << SIGALRM_BIT)
 
 static int signals_enabled;
 static unsigned int signals_pending;
···
 	set_signals(enabled);
 }
 
-static void real_alarm_handler(mcontext_t *mc)
+static void timer_real_alarm_handler(mcontext_t *mc)
 {
 	struct uml_pt_regs regs;
 
 	if (mc != NULL)
 		get_regs_from_mc(&regs, mc);
-	regs.is_user = 0;
-	unblock_signals();
-	timer_handler(SIGVTALRM, NULL, &regs);
+	timer_handler(SIGALRM, NULL, &regs);
 }
 
-void alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc)
+void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc)
 {
 	int enabled;
 
 	enabled = signals_enabled;
 	if (!signals_enabled) {
-		signals_pending |= SIGVTALRM_MASK;
+		signals_pending |= SIGALRM_MASK;
 		return;
 	}
 
 	block_signals();
 
-	real_alarm_handler(mc);
+	timer_real_alarm_handler(mc);
 	set_signals(enabled);
 }
 
-void timer_init(void)
+void deliver_alarm(void) {
+    timer_alarm_handler(SIGALRM, NULL, NULL);
+}
+
+void timer_set_signal_handler(void)
 {
-	set_handler(SIGVTALRM);
+	set_handler(SIGALRM);
 }
 
 void set_sigstack(void *sig_stack, int size)
···
 
 	[SIGIO] = sig_handler,
 	[SIGWINCH] = sig_handler,
-	[SIGVTALRM] = alarm_handler
+	[SIGALRM] = timer_alarm_handler
 };
-
 
 static void hard_handler(int sig, siginfo_t *si, void *p)
 {
···
 
 	/* block irq ones */
 	sigemptyset(&action.sa_mask);
-	sigaddset(&action.sa_mask, SIGVTALRM);
 	sigaddset(&action.sa_mask, SIGIO);
 	sigaddset(&action.sa_mask, SIGWINCH);
+	sigaddset(&action.sa_mask, SIGALRM);
 
 	if (sig == SIGSEGV)
 		flags |= SA_NODEFER;
···
 		if (save_pending & SIGIO_MASK)
 			sig_handler_common(SIGIO, NULL, NULL);
 
-		if (save_pending & SIGVTALRM_MASK)
-			real_alarm_handler(NULL);
+		if (save_pending & SIGALRM_MASK)
+			timer_real_alarm_handler(NULL);
 	}
 }
 

arch/um/os-Linux/skas/process.c

···
 /*
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
  * Copyright (C) 2002- 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
  * Signals that are OK to receive in the stub - we'll just continue it.
  * SIGWINCH will happen when UML is inside a detached screen.
  */
-#define STUB_SIG_MASK ((1 << SIGVTALRM) | (1 << SIGWINCH))
+#define STUB_SIG_MASK ((1 << SIGALRM) | (1 << SIGWINCH))
 
 /* Signals that the stub will finish with - anything else is an error */
 #define STUB_DONE_MASK (1 << SIGTRAP)
···
 static int userspace_tramp(void *stack)
 {
 	void *addr;
-	int err, fd;
+	int fd;
 	unsigned long long offset;
 
 	ptrace(PTRACE_TRACEME, 0, 0, 0);
 
 	signal(SIGTERM, SIG_DFL);
 	signal(SIGWINCH, SIG_IGN);
-	err = set_interval();
-	if (err) {
-		printk(UM_KERN_ERR "userspace_tramp - setting timer failed, "
-		       "errno = %d\n", err);
-		exit(1);
-	}
 
 	/*
 	 * This has a pte, but it can't be mapped in with the usual
···
 			       "errno = %d\n", errno);
 			goto out_kill;
 		}
-	} while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGVTALRM));
+	} while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM));
 
 	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) {
 		err = -EINVAL;
···
 
 void userspace(struct uml_pt_regs *regs)
 {
-	struct itimerval timer;
-	unsigned long long nsecs, now;
 	int err, status, op, pid = userspace_pid[0];
 	/* To prevent races if using_sysemu changes under us.*/
 	int local_using_sysemu;
···
 	/* Handle any immediate reschedules or signals */
 	interrupt_end();
 
-	if (getitimer(ITIMER_VIRTUAL, &timer))
-		printk(UM_KERN_ERR "Failed to get itimer, errno = %d\n", errno);
-	nsecs = timer.it_value.tv_sec * UM_NSEC_PER_SEC +
-		timer.it_value.tv_usec * UM_NSEC_PER_USEC;
-	nsecs += os_nsecs();
-
 	while (1) {
+
 		/*
 		 * This can legitimately fail if the process loads a
 		 * bogus value into a segment register.  It will
···
 			case SIGTRAP:
 				relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
 				break;
-			case SIGVTALRM:
-				now = os_nsecs();
-				if (now < nsecs)
-					break;
-				block_signals();
-				(*sig_info[sig])(sig, (struct siginfo *)&si, regs);
-				unblock_signals();
-				nsecs = timer.it_value.tv_sec *
-					UM_NSEC_PER_SEC +
-					timer.it_value.tv_usec *
-					UM_NSEC_PER_USEC;
-				nsecs += os_nsecs();
+			case SIGALRM:
 				break;
 			case SIGIO:
 			case SIGILL:
···
 
 int copy_context_skas0(unsigned long new_stack, int pid)
 {
-	struct timeval tv = { .tv_sec = 0, .tv_usec = UM_USEC_PER_SEC / UM_HZ };
 	int err;
 	unsigned long current_stack = current_stub_stack();
 	struct stub_data *data = (struct stub_data *) current_stack;
···
 	 * prepare offset and fd of child's stack as argument for parent's
 	 * and child's mmap2 calls
 	 */
-	*data = ((struct stub_data) { .offset	= MMAP_OFFSET(new_offset),
-				      .fd	= new_fd,
-				      .timer    = ((struct itimerval)
-					           { .it_value = tv,
-						     .it_interval = tv }) });
+	*data = ((struct stub_data) {
+			.offset	= MMAP_OFFSET(new_offset),
+			.fd     = new_fd
+	});
 
 	err = ptrace_setregs(pid, thread_regs);
 	if (err < 0) {

arch/um/os-Linux/time.c

···
 /*
+ * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk})
+ * Copyright (C) 2015 Thomas Meyer ([e-mail])
+ * Copyright (C) 2012-2014 Cisco Systems
  * Copyright (C) 2000 - 2007 Jeff Dike (jdike{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
···
 #include <sys/time.h>
 #include <kern_util.h>
 #include <os.h>
-#include "internal.h"
+#include <string.h>
+#include <timer-internal.h>
 
-int set_interval(void)
-{
-	int usec = UM_USEC_PER_SEC / UM_HZ;
-	struct itimerval interval = ((struct itimerval) { { 0, usec },
-							  { 0, usec } });
+static timer_t event_high_res_timer = 0;
 
-	if (setitimer(ITIMER_VIRTUAL, &interval, NULL) == -1)
-		return -errno;
-
-	return 0;
-}
-
-int timer_one_shot(int ticks)
-{
-	unsigned long usec = ticks * UM_USEC_PER_SEC / UM_HZ;
-	unsigned long sec = usec / UM_USEC_PER_SEC;
-	struct itimerval interval;
-
-	usec %= UM_USEC_PER_SEC;
-	interval = ((struct itimerval) { { 0, 0 }, { sec, usec } });
-
-	if (setitimer(ITIMER_VIRTUAL, &interval, NULL) == -1)
-		return -errno;
-
-	return 0;
-}
-
-/**
- * timeval_to_ns - Convert timeval to nanoseconds
- * @ts:		pointer to the timeval variable to be converted
- *
- * Returns the scalar nanosecond representation of the timeval
- * parameter.
- *
- * Ripped from linux/time.h because it's a kernel header, and thus
- * unusable from here.
- */
 static inline long long timeval_to_ns(const struct timeval *tv)
 {
 	return ((long long) tv->tv_sec * UM_NSEC_PER_SEC) +
 		tv->tv_usec * UM_NSEC_PER_USEC;
 }
 
-long long disable_timer(void)
+static inline long long timespec_to_ns(const struct timespec *ts)
 {
-	struct itimerval time = ((struct itimerval) { { 0, 0 }, { 0, 0 } });
-	long long remain, max = UM_NSEC_PER_SEC / UM_HZ;
+	return ((long long) ts->tv_sec * UM_NSEC_PER_SEC) +
+		ts->tv_nsec;
+}
 
-	if (setitimer(ITIMER_VIRTUAL, &time, &time) < 0)
-		printk(UM_KERN_ERR "disable_timer - setitimer failed, "
-		       "errno = %d\n", errno);
+long long os_persistent_clock_emulation (void) {
+	struct timespec realtime_tp;
 
-	remain = timeval_to_ns(&time.it_value);
-	if (remain > max)
-		remain = max;
+	clock_gettime(CLOCK_REALTIME, &realtime_tp);
+	return timespec_to_ns(&realtime_tp);
+}
 
-	return remain;
+/**
+ * os_timer_create() - create an new posix (interval) timer
+ */
+int os_timer_create(void* timer) {
+
+	timer_t* t = timer;
+
+	if(t == NULL) {
+		t = &event_high_res_timer;
+	}
+
+	if (timer_create(
+		CLOCK_MONOTONIC,
+		NULL,
+		t) == -1) {
+		return -1;
+	}
+	return 0;
+}
+
+int os_timer_set_interval(void* timer, void* i)
+{
+	struct itimerspec its;
+	unsigned long long nsec;
+	timer_t* t = timer;
+	struct itimerspec* its_in = i;
+
+	if(t == NULL) {
+		t = &event_high_res_timer;
+	}
+
+	nsec = UM_NSEC_PER_SEC / UM_HZ;
+
+	if(its_in != NULL) {
+		its.it_value.tv_sec = its_in->it_value.tv_sec;
+		its.it_value.tv_nsec = its_in->it_value.tv_nsec;
+	} else {
+		its.it_value.tv_sec = 0;
+		its.it_value.tv_nsec = nsec;
+	}
+
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = nsec;
+
+	if(timer_settime(*t, 0, &its, NULL) == -1) {
+		return -errno;
+	}
+
+	return 0;
+}
+
+/**
+ * os_timer_remain() - returns the remaining nano seconds of the given interval
+ *                     timer
+ * Because this is the remaining time of an interval timer, which correspondends
+ * to HZ, this value can never be bigger than one second. Just
+ * the nanosecond part of the timer is returned.
+ * The returned time is relative to the start time of the interval timer.
+ * Return an negative value in an error case.
+ */
+long os_timer_remain(void* timer)
+{
+	struct itimerspec its;
+	timer_t* t = timer;
+
+	if(t == NULL) {
+		t = &event_high_res_timer;
+	}
+
+	if(timer_gettime(t, &its) == -1) {
+		return -errno;
+	}
+
+	return its.it_value.tv_nsec;
+}
+
+int os_timer_one_shot(int ticks)
+{
+	struct itimerspec its;
+	unsigned long long nsec;
+	unsigned long sec;
+
+    nsec = (ticks + 1);
+    sec = nsec / UM_NSEC_PER_SEC;
+	nsec = nsec % UM_NSEC_PER_SEC;
+
+	its.it_value.tv_sec = nsec / UM_NSEC_PER_SEC;
+	its.it_value.tv_nsec = nsec;
+
+	its.it_interval.tv_sec = 0;
+	its.it_interval.tv_nsec = 0; // we cheat here
+
+	timer_settime(event_high_res_timer, 0, &its, NULL);
+	return 0;
+}
+
+/**
+ * os_timer_disable() - disable the posix (interval) timer
+ * Returns the remaining interval timer time in nanoseconds
+ */
+long long os_timer_disable(void)
+{
+	struct itimerspec its;
+
+	memset(&its, 0, sizeof(struct itimerspec));
+	timer_settime(event_high_res_timer, 0, &its, &its);
+
+	return its.it_value.tv_sec * UM_NSEC_PER_SEC + its.it_value.tv_nsec;
+}
+
+long long os_vnsecs(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_PROCESS_CPUTIME_ID,&ts);
+	return timespec_to_ns(&ts);
 }
 
 long long os_nsecs(void)
 {
-	struct timeval tv;
+	struct timespec ts;
 
-	gettimeofday(&tv, NULL);
-	return timeval_to_ns(&tv);
+	clock_gettime(CLOCK_MONOTONIC,&ts);
+	return timespec_to_ns(&ts);
 }
 
-#ifdef UML_CONFIG_NO_HZ_COMMON
-static int after_sleep_interval(struct timespec *ts)
-{
-	return 0;
-}
-
-static void deliver_alarm(void)
-{
-	alarm_handler(SIGVTALRM, NULL, NULL);
-}
-
-static unsigned long long sleep_time(unsigned long long nsecs)
-{
-	return nsecs;
-}
-
-#else
-unsigned long long last_tick;
-unsigned long long skew;
-
-static void deliver_alarm(void)
-{
-	unsigned long long this_tick = os_nsecs();
-	int one_tick = UM_NSEC_PER_SEC / UM_HZ;
-
-	/* Protection against the host's time going backwards */
-	if ((last_tick != 0) && (this_tick < last_tick))
-		this_tick = last_tick;
-
-	if (last_tick == 0)
-		last_tick = this_tick - one_tick;
-
-	skew += this_tick - last_tick;
-
-	while (skew >= one_tick) {
-		alarm_handler(SIGVTALRM, NULL, NULL);
-		skew -= one_tick;
-	}
-
-	last_tick = this_tick;
-}
-
-static unsigned long long sleep_time(unsigned long long nsecs)
-{
-	return nsecs > skew ? nsecs - skew : 0;
-}
-
-static inline long long timespec_to_us(const struct timespec *ts)
-{
-	return ((long long) ts->tv_sec * UM_USEC_PER_SEC) +
-		ts->tv_nsec / UM_NSEC_PER_USEC;
-}
-
-static int after_sleep_interval(struct timespec *ts)
-{
-	int usec = UM_USEC_PER_SEC / UM_HZ;
-	long long start_usecs = timespec_to_us(ts);
-	struct timeval tv;
-	struct itimerval interval;
-
-	/*
-	 * It seems that rounding can increase the value returned from
-	 * setitimer to larger than the one passed in.  Over time,
-	 * this will cause the remaining time to be greater than the
-	 * tick interval.  If this happens, then just reduce the first
-	 * tick to the interval value.
-	 */
-	if (start_usecs > usec)
-		start_usecs = usec;
-
-	start_usecs -= skew / UM_NSEC_PER_USEC;
-	if (start_usecs < 0)
-		start_usecs = 0;
-
-	tv = ((struct timeval) { .tv_sec  = start_usecs / UM_USEC_PER_SEC,
-				 .tv_usec = start_usecs % UM_USEC_PER_SEC });
-	interval = ((struct itimerval) { { 0, usec }, tv });
-
-	if (setitimer(ITIMER_VIRTUAL, &interval, NULL) == -1)
-		return -errno;
-
-	return 0;
-}
-#endif
-
-void idle_sleep(unsigned long long nsecs)
+/**
+ * os_idle_sleep() - sleep for a given time of nsecs
+ * @nsecs: nanoseconds to sleep
+ */
+void os_idle_sleep(unsigned long long nsecs)
 {
 	struct timespec ts;
 
+	if (nsecs <= 0) {
+		return;
+	}
+
+	ts = ((struct timespec) {
+			.tv_sec  = nsecs / UM_NSEC_PER_SEC,
+			.tv_nsec = nsecs % UM_NSEC_PER_SEC
+	});
+
 	/*
-	 * nsecs can come in as zero, in which case, this starts a
-	 * busy loop.  To prevent this, reset nsecs to the tick
-	 * interval if it is zero.
+	 * Relay the signal if clock_nanosleep is interrupted.
 	 */
-	if (nsecs == 0)
-		nsecs = UM_NSEC_PER_SEC / UM_HZ;
-
-	nsecs = sleep_time(nsecs);
-	ts = ((struct timespec) { .tv_sec	= nsecs / UM_NSEC_PER_SEC,
-				  .tv_nsec	= nsecs % UM_NSEC_PER_SEC });
-
-	if (nanosleep(&ts, &ts) == 0)
+	if (clock_nanosleep(CLOCK_MONOTONIC, 0, &ts, NULL)) {
 		deliver_alarm();
-	after_sleep_interval(&ts);
+	}
 }