Merge tag 'for-linus-4.5-rc0-tag' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/xen/tip

Pull xen updates from David Vrabel:
 "Xen features and fixes for 4.5-rc0:

   - Stolen ticks and PV wallclock support for arm/arm64

   - Add grant copy ioctl to gntdev device"

* tag 'for-linus-4.5-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/gntdev: add ioctl for grant copy
  x86/xen: don't reset vcpu_info on a cancelled suspend
  xen/gntdev: constify mmu_notifier_ops structures
  xen/grant-table: constify gnttab_ops structure
  xen/time: use READ_ONCE
  xen/x86: convert remaining timespec to timespec64 in xen_pvclock_gtod_notify
  xen/x86: support XENPF_settime64
  xen/arm: set the system time in Xen via the XENPF_settime64 hypercall
  xen/arm: introduce xen_read_wallclock
  arm: extend pvclock_wall_clock with sec_hi
  xen: introduce XENPF_settime64
  xen/arm: introduce HYPERVISOR_platform_op on arm and arm64
  xen: rename dom0_op to platform_op
  xen/arm: account for stolen ticks
  arm64: introduce CONFIG_PARAVIRT, PARAVIRT_TIME_ACCOUNTING and pv_time_ops
  arm: introduce CONFIG_PARAVIRT, PARAVIRT_TIME_ACCOUNTING and pv_time_ops
  missing include asm/paravirt.h in cputime.c
  xen: move xen_setup_runstate_info and get_runstate_snapshot to drivers/xen/time.c

arch/arm/Kconfig

@@ -1824,6 +1824,25 @@ config SWIOTLB
 config IOMMU_HELPER
 	def_bool SWIOTLB
 
+config PARAVIRT
+	bool "Enable paravirtualization code"
+	help
+	  This changes the kernel so it can modify itself when it is run
+	  under a hypervisor, potentially improving performance significantly
+	  over full virtualization.
+
+config PARAVIRT_TIME_ACCOUNTING
+	bool "Paravirtual steal time accounting"
+	select PARAVIRT
+	default n
+	help
+	  Select this option to enable fine granularity task steal time
+	  accounting. Time spent executing other tasks in parallel with
+	  the current vCPU is discounted from the vCPU power. To account for
+	  that, there can be a small performance impact.
+
+	  If in doubt, say N here.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
@@ -1837,6 +1856,7 @@ config XEN
 	select ARCH_DMA_ADDR_T_64BIT
 	select ARM_PSCI
 	select SWIOTLB_XEN
+	select PARAVIRT
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
 

arch/arm/include/asm/paravirt.h

@@ -0,0 +1,20 @@
+#ifndef _ASM_ARM_PARAVIRT_H
+#define _ASM_ARM_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops {
+	unsigned long long (*steal_clock)(int cpu);
+};
+extern struct pv_time_ops pv_time_ops;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return pv_time_ops.steal_clock(cpu);
+}
+#endif
+
+#endif

arch/arm/include/asm/xen/hypercall.h

@@ -35,6 +35,7 @@
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
+#include <xen/interface/platform.h>
 
 long privcmd_call(unsigned call, unsigned long a1,
 		unsigned long a2, unsigned long a3,
@@ -49,6 +50,12 @@ int HYPERVISOR_memory_op(unsigned int cmd, void *arg);
 int HYPERVISOR_physdev_op(int cmd, void *arg);
 int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
 int HYPERVISOR_tmem_op(void *arg);
+int HYPERVISOR_platform_op_raw(void *arg);
+static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
+{
+	op->interface_version = XENPF_INTERFACE_VERSION;
+	return HYPERVISOR_platform_op_raw(op);
+}
 int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr);
 
 static inline int

arch/arm/include/asm/xen/interface.h

@@ -27,6 +27,8 @@
 		(hnd).p = val;				\
 	} while (0)
 
+#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op
+
 #ifndef __ASSEMBLY__
 /* Explicitly size integers that represent pfns in the interface with
  * Xen so that we can have one ABI that works for 32 and 64 bit guests.
@@ -76,6 +78,7 @@ struct pvclock_wall_clock {
 	u32   version;
 	u32   sec;
 	u32   nsec;
+	u32   sec_hi;
 } __attribute__((__packed__));
 #endif
 

arch/arm/kernel/Makefile

@@ -81,6 +81,7 @@ obj-$(CONFIG_EFI)		+= efi.o
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o
 endif
+obj-$(CONFIG_PARAVIRT)	+= paravirt.o
 
 head-y			:= head$(MMUEXT).o
 obj-$(CONFIG_DEBUG_LL)	+= debug.o

arch/arm/kernel/paravirt.c

@@ -0,0 +1,25 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2013 Citrix Systems
+ *
+ * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+ */
+
+#include <linux/export.h>
+#include <linux/jump_label.h>
+#include <linux/types.h>
+#include <asm/paravirt.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops pv_time_ops;
+EXPORT_SYMBOL_GPL(pv_time_ops);

arch/arm/xen/enlighten.c

@@ -12,6 +12,7 @@
 #include <xen/page.h>
 #include <xen/interface/sched.h>
 #include <xen/xen-ops.h>
+#include <asm/paravirt.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include <asm/system_misc.h>
@@ -25,6 +26,10 @@
 #include <linux/cpufreq.h>
 #include <linux/cpu.h>
 #include <linux/console.h>
+#include <linux/pvclock_gtod.h>
+#include <linux/time64.h>
+#include <linux/timekeeping.h>
+#include <linux/timekeeper_internal.h>
 
 #include <linux/mm.h>
 
@@ -79,6 +84,83 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
 
+static unsigned long long xen_stolen_accounting(int cpu)
+{
+	struct vcpu_runstate_info state;
+
+	BUG_ON(cpu != smp_processor_id());
+
+	xen_get_runstate_snapshot(&state);
+
+	WARN_ON(state.state != RUNSTATE_running);
+
+	return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline];
+}
+
+static void xen_read_wallclock(struct timespec64 *ts)
+{
+	u32 version;
+	struct timespec64 now, ts_monotonic;
+	struct shared_info *s = HYPERVISOR_shared_info;
+	struct pvclock_wall_clock *wall_clock = &(s->wc);
+
+	/* get wallclock at system boot */
+	do {
+		version = wall_clock->version;
+		rmb();		/* fetch version before time */
+		now.tv_sec  = ((uint64_t)wall_clock->sec_hi << 32) | wall_clock->sec;
+		now.tv_nsec = wall_clock->nsec;
+		rmb();		/* fetch time before checking version */
+	} while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+	/* time since system boot */
+	ktime_get_ts64(&ts_monotonic);
+	*ts = timespec64_add(now, ts_monotonic);
+}
+
+static int xen_pvclock_gtod_notify(struct notifier_block *nb,
+				   unsigned long was_set, void *priv)
+{
+	/* Protected by the calling core code serialization */
+	static struct timespec64 next_sync;
+
+	struct xen_platform_op op;
+	struct timespec64 now, system_time;
+	struct timekeeper *tk = priv;
+
+	now.tv_sec = tk->xtime_sec;
+	now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
+	system_time = timespec64_add(now, tk->wall_to_monotonic);
+
+	/*
+	 * We only take the expensive HV call when the clock was set
+	 * or when the 11 minutes RTC synchronization time elapsed.
+	 */
+	if (!was_set && timespec64_compare(&now, &next_sync) < 0)
+		return NOTIFY_OK;
+
+	op.cmd = XENPF_settime64;
+	op.u.settime64.mbz = 0;
+	op.u.settime64.secs = now.tv_sec;
+	op.u.settime64.nsecs = now.tv_nsec;
+	op.u.settime64.system_time = timespec64_to_ns(&system_time);
+	(void)HYPERVISOR_platform_op(&op);
+
+	/*
+	 * Move the next drift compensation time 11 minutes
+	 * ahead. That's emulating the sync_cmos_clock() update for
+	 * the hardware RTC.
+	 */
+	next_sync = now;
+	next_sync.tv_sec += 11 * 60;
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xen_pvclock_gtod_notifier = {
+	.notifier_call = xen_pvclock_gtod_notify,
+};
+
 static void xen_percpu_init(void)
 {
 	struct vcpu_register_vcpu_info info;
@@ -104,6 +186,8 @@ static void xen_percpu_init(void)
 	BUG_ON(err);
 	per_cpu(xen_vcpu, cpu) = vcpup;
 
+	xen_setup_runstate_info(cpu);
+
 after_register_vcpu_info:
 	enable_percpu_irq(xen_events_irq, 0);
 	put_cpu();
@@ -271,6 +355,11 @@ static int __init xen_guest_init(void)
 
 	register_cpu_notifier(&xen_cpu_notifier);
 
+	pv_time_ops.steal_clock = xen_stolen_accounting;
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (xen_initial_domain())
+		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
+
 	return 0;
 }
 early_initcall(xen_guest_init);
@@ -282,6 +371,11 @@ static int __init xen_pm_init(void)
 
 	pm_power_off = xen_power_off;
 	arm_pm_restart = xen_restart;
+	if (!xen_initial_domain()) {
+		struct timespec64 ts;
+		xen_read_wallclock(&ts);
+		do_settimeofday64(&ts);
+	}
 
 	return 0;
 }
@@ -307,5 +401,6 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
 EXPORT_SYMBOL_GPL(privcmd_call);

arch/arm/xen/hypercall.S

@@ -89,6 +89,7 @@ HYPERCALL2(memory_op);
 HYPERCALL2(physdev_op);
 HYPERCALL3(vcpu_op);
 HYPERCALL1(tmem_op);
+HYPERCALL1(platform_op_raw);
 HYPERCALL2(multicall);
 
 ENTRY(privcmd_call)

arch/arm64/Kconfig

@@ -555,6 +555,25 @@ config SECCOMP
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.
 
+config PARAVIRT
+	bool "Enable paravirtualization code"
+	help
+	  This changes the kernel so it can modify itself when it is run
+	  under a hypervisor, potentially improving performance significantly
+	  over full virtualization.
+
+config PARAVIRT_TIME_ACCOUNTING
+	bool "Paravirtual steal time accounting"
+	select PARAVIRT
+	default n
+	help
+	  Select this option to enable fine granularity task steal time
+	  accounting. Time spent executing other tasks in parallel with
+	  the current vCPU is discounted from the vCPU power. To account for
+	  that, there can be a small performance impact.
+
+	  If in doubt, say N here.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
@@ -563,6 +582,7 @@ config XEN
 	bool "Xen guest support on ARM64"
 	depends on ARM64 && OF
 	select SWIOTLB_XEN
+	select PARAVIRT
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
 

arch/arm64/include/asm/paravirt.h

@@ -0,0 +1,20 @@
+#ifndef _ASM_ARM64_PARAVIRT_H
+#define _ASM_ARM64_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops {
+	unsigned long long (*steal_clock)(int cpu);
+};
+extern struct pv_time_ops pv_time_ops;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return pv_time_ops.steal_clock(cpu);
+}
+#endif
+
+#endif

arch/arm64/kernel/Makefile

@@ -41,6 +41,7 @@ arm64-obj-$(CONFIG_EFI)			+= efi.o efi-entry.stub.o
 arm64-obj-$(CONFIG_PCI)			+= pci.o
 arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
 arm64-obj-$(CONFIG_ACPI)		+= acpi.o
+arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)

arch/arm64/kernel/paravirt.c

@@ -0,0 +1,25 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2013 Citrix Systems
+ *
+ * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+ */
+
+#include <linux/export.h>
+#include <linux/jump_label.h>
+#include <linux/types.h>
+#include <asm/paravirt.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops pv_time_ops;
+EXPORT_SYMBOL_GPL(pv_time_ops);

arch/arm64/xen/hypercall.S

@@ -80,6 +80,7 @@ HYPERCALL2(memory_op);
 HYPERCALL2(physdev_op);
 HYPERCALL3(vcpu_op);
 HYPERCALL1(tmem_op);
+HYPERCALL1(platform_op_raw);
 HYPERCALL2(multicall);
 
 ENTRY(privcmd_call)

arch/x86/include/asm/xen/hypercall.h

@@ -310,10 +310,10 @@ HYPERVISOR_mca(struct xen_mc *mc_op)
 }
 
 static inline int
-HYPERVISOR_dom0_op(struct xen_platform_op *platform_op)
+HYPERVISOR_platform_op(struct xen_platform_op *op)
 {
-	platform_op->interface_version = XENPF_INTERFACE_VERSION;
-	return _hypercall1(int, dom0_op, platform_op);
+	op->interface_version = XENPF_INTERFACE_VERSION;
+	return _hypercall1(int, platform_op, op);
 }
 
 static inline int

arch/x86/xen/apic.c

@@ -64,7 +64,7 @@ static u32 xen_apic_read(u32 reg)
 	if (reg != APIC_ID)
 		return 0;
 
-	ret = HYPERVISOR_dom0_op(&op);
+	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
 		return 0;