Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core timer updates from Thomas Gleixner:
 "Timers and timekeeping updates:

   - A large overhaul of the posix CPU timer code which is a preparation
     for moving the CPU timer expiry out into task work so it can be
     properly accounted on the task/process.

     An update to the bogus permission checks will come later during the
     merge window as feedback was not complete before heading of for
     travel.

   - Switch the timerqueue code to use cached rbtrees and get rid of the
     homebrewn caching of the leftmost node.

   - Consolidate hrtimer_init() + hrtimer_init_sleeper() calls into a
     single function

   - Implement the separation of hrtimers to be forced to expire in hard
     interrupt context even when PREEMPT_RT is enabled and mark the
     affected timers accordingly.

   - Implement a mechanism for hrtimers and the timer wheel to protect
     RT against priority inversion and live lock issues when a (hr)timer
     which should be canceled is currently executing the callback.
     Instead of infinitely spinning, the task which tries to cancel the
     timer blocks on a per cpu base expiry lock which is held and
     released by the (hr)timer expiry code.

   - Enable the Hyper-V TSC page based sched_clock for Hyper-V guests
     resulting in faster access to timekeeping functions.

   - Updates to various clocksource/clockevent drivers and their device
     tree bindings.

   - The usual small improvements all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (101 commits)
  posix-cpu-timers: Fix permission check regression
  posix-cpu-timers: Always clear head pointer on dequeue
  hrtimer: Add a missing bracket and hide `migration_base' on !SMP
  posix-cpu-timers: Make expiry_active check actually work correctly
  posix-timers: Unbreak CONFIG_POSIX_TIMERS=n build
  tick: Mark sched_timer to expire in hard interrupt context
  hrtimer: Add kernel doc annotation for HRTIMER_MODE_HARD
  x86/hyperv: Hide pv_ops access for CONFIG_PARAVIRT=n
  posix-cpu-timers: Utilize timerqueue for storage
  posix-cpu-timers: Move state tracking to struct posix_cputimers
  posix-cpu-timers: Deduplicate rlimit handling
  posix-cpu-timers: Remove pointless comparisons
  posix-cpu-timers: Get rid of 64bit divisions
  posix-cpu-timers: Consolidate timer expiry further
  posix-cpu-timers: Get rid of zero checks
  rlimit: Rewrite non-sensical RLIMIT_CPU comment
  posix-cpu-timers: Respect INFINITY for hard RTTIME limit
  posix-cpu-timers: Switch thread group sampling to array
  posix-cpu-timers: Restructure expiry array
  posix-cpu-timers: Remove cputime_expires
  ...

5 files changed, 17 insertions, 9 deletions

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 349a61d8bf34..f5937742b290 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -122,7 +122,7 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 
 		if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
 			return vmf_insert_pfn(vma, vmf->address,
-					vmalloc_to_pfn(tsc_pg));
+					virt_to_phys(tsc_pg) >> PAGE_SHIFT);
 	}
 
 	return VM_FAULT_SIGBUS;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index d314cf1e15fd..2db3972c0e0f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -315,8 +315,6 @@ void __init hyperv_init(void)
 
 	x86_init.pci.arch_init = hv_pci_init;
 
-	/* Register Hyper-V specific clocksource */
-	hv_init_clocksource();
 	return;
 
 remove_cpuhp_state:
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index ba71a63cdac4..e9ee139cf29e 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -51,7 +51,7 @@ extern struct pvclock_vsyscall_time_info pvclock_page
 	__attribute__((visibility("hidden")));
 #endif
 
-#ifdef CONFIG_HYPERV_TSCPAGE
+#ifdef CONFIG_HYPERV_TIMER
 extern struct ms_hyperv_tsc_page hvclock_page
 	__attribute__((visibility("hidden")));
 #endif
@@ -228,7 +228,7 @@ static u64 vread_pvclock(void)
 }
 #endif
 
-#ifdef CONFIG_HYPERV_TSCPAGE
+#ifdef CONFIG_HYPERV_TIMER
 static u64 vread_hvclock(void)
 {
 	return hv_read_tsc_page(&hvclock_page);
@@ -251,7 +251,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode)
 		return vread_pvclock();
 	}
 #endif
-#ifdef CONFIG_HYPERV_TSCPAGE
+#ifdef CONFIG_HYPERV_TIMER
 	if (clock_mode == VCLOCK_HVCLOCK) {
 		barrier();
 		return vread_hvclock();
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 062f77279ce3..267daad8c036 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -29,6 +29,7 @@
 #include <asm/timer.h>
 #include <asm/reboot.h>
 #include <asm/nmi.h>
+#include <clocksource/hyperv_timer.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -338,6 +339,15 @@ static void __init ms_hyperv_init_platform(void)
 		x2apic_phys = 1;
 # endif
 
+	/* Register Hyper-V specific clocksource */
+	hv_init_clocksource();
+#endif
+}
+
+void hv_setup_sched_clock(void *sched_clock)
+{
+#ifdef CONFIG_PARAVIRT
+	pv_ops.time.sched_clock = sched_clock;
 #endif
 }
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e904ff06a83d..2a4f278f3b56 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1598,7 +1598,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 	    likely(ns > apic->lapic_timer.timer_advance_ns)) {
 		expire = ktime_add_ns(now, ns);
 		expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
-		hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS);
+		hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD);
 	} else
 		apic_timer_expired(apic);
 
@@ -2299,7 +2299,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS);
+		     HRTIMER_MODE_ABS_HARD);
 	apic->lapic_timer.timer.function = apic_timer_fn;
 	if (timer_advance_ns == -1) {
 		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
@@ -2484,7 +2484,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 
 	timer = &vcpu->arch.apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
-		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_HARD);
 }
 
 /*