Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "One of the largest releases for KVM...  Hardly any generic
  changes, but lots of architecture-specific updates.

  ARM:
   - VHE support so that we can run the kernel at EL2 on ARMv8.1 systems
   - PMU support for guests
   - 32bit world switch rewritten in C
   - various optimizations to the vgic save/restore code.

  PPC:
   - enabled KVM-VFIO integration ("VFIO device")
   - optimizations to speed up IPIs between vcpus
   - in-kernel handling of IOMMU hypercalls
   - support for dynamic DMA windows (DDW).

  s390:
   - provide the floating point registers via sync regs;
   - separated instruction vs.  data accesses
   - dirty log improvements for huge guests
   - bugfixes and documentation improvements.

  x86:
   - Hyper-V VMBus hypercall userspace exit
   - alternative implementation of lowest-priority interrupts using
     vector hashing (for better VT-d posted interrupt support)
   - fixed guest debugging with nested virtualizations
   - improved interrupt tracking in the in-kernel IOAPIC
   - generic infrastructure for tracking writes to guest
     memory - currently its only use is to speedup the legacy shadow
     paging (pre-EPT) case, but in the future it will be used for
     virtual GPUs as well
   - much cleanup (LAPIC, kvmclock, MMU, PIT), including ubsan fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (217 commits)
  KVM: x86: remove eager_fpu field of struct kvm_vcpu_arch
  KVM: x86: disable MPX if host did not enable MPX XSAVE features
  arm64: KVM: vgic-v3: Only wipe LRs on vcpu exit
  arm64: KVM: vgic-v3: Reset LRs at boot time
  arm64: KVM: vgic-v3: Do not save an LR known to be empty
  arm64: KVM: vgic-v3: Save maintenance interrupt state only if required
  arm64: KVM: vgic-v3: Avoid accessing ICH registers
  KVM: arm/arm64: vgic-v2: Make GICD_SGIR quicker to hit
  KVM: arm/arm64: vgic-v2: Only wipe LRs on vcpu exit
  KVM: arm/arm64: vgic-v2: Reset LRs at boot time
  KVM: arm/arm64: vgic-v2: Do not save an LR known to be empty
  KVM: arm/arm64: vgic-v2: Move GICH_ELRSR saving to its own function
  KVM: arm/arm64: vgic-v2: Save maintenance interrupt state only if required
  KVM: arm/arm64: vgic-v2: Avoid accessing GICH registers
  KVM: s390: allocate only one DMA page per VM
  KVM: s390: enable STFLE interpretation only if enabled for the guest
  KVM: s390: wake up when the VCPU cpu timer expires
  KVM: s390: step the VCPU timer while in enabled wait
  KVM: s390: protect VCPU cpu timer with a seqcount
  KVM: s390: step VCPU cpu timer during kvm_run ioctl
  ...

9 files changed, 850 insertions, 27 deletions

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index ea60646..a9ad4fe 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -34,6 +34,11 @@ static struct timecounter *timecounter;
 static struct workqueue_struct *wqueue;
 static unsigned int host_vtimer_irq;
 
+void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.timer_cpu.active_cleared_last = false;
+}
+
 static cycle_t kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
@@ -130,6 +135,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
 
 	BUG_ON(!vgic_initialized(vcpu->kvm));
 
+	timer->active_cleared_last = false;
 	timer->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq,
 				   timer->irq.level);
@@ -245,10 +251,35 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	else
 		phys_active = false;
 
+	/*
+	 * We want to avoid hitting the (re)distributor as much as
+	 * possible, as this is a potentially expensive MMIO access
+	 * (not to mention locks in the irq layer), and a solution for
+	 * this is to cache the "active" state in memory.
+	 *
+	 * Things to consider: we cannot cache an "active set" state,
+	 * because the HW can change this behind our back (it becomes
+	 * "clear" in the HW). We must then restrict the caching to
+	 * the "clear" state.
+	 *
+	 * The cache is invalidated on:
+	 * - vcpu put, indicating that the HW cannot be trusted to be
+	 *   in a sane state on the next vcpu load,
+	 * - any change in the interrupt state
+	 *
+	 * Usage conditions:
+	 * - cached value is "active clear"
+	 * - value to be programmed is "active clear"
+	 */
+	if (timer->active_cleared_last && !phys_active)
+		return;
+
 	ret = irq_set_irqchip_state(timer->map->irq,
 				    IRQCHIP_STATE_ACTIVE,
 				    phys_active);
 	WARN_ON(ret);
+
+	timer->active_cleared_last = !phys_active;
 }
 
 /**
diff --git a/virt/kvm/arm/hyp/timer-sr.c b/virt/kvm/arm/hyp/timer-sr.c
new file mode 100644
index 0000000..ea00d69
--- /dev/null
+++ b/virt/kvm/arm/hyp/timer-sr.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <clocksource/arm_arch_timer.h>
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	u64 val;
+
+	if (kvm->arch.timer.enabled) {
+		timer->cntv_ctl = read_sysreg_el0(cntv_ctl);
+		timer->cntv_cval = read_sysreg_el0(cntv_cval);
+	}
+
+	/* Disable the virtual timer */
+	write_sysreg_el0(0, cntv_ctl);
+
+	/* Allow physical timer/counter access for the host */
+	val = read_sysreg(cnthctl_el2);
+	val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
+	write_sysreg(val, cnthctl_el2);
+
+	/* Clear cntvoff for the host */
+	write_sysreg(0, cntvoff_el2);
+}
+
+void __hyp_text __timer_restore_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	u64 val;
+
+	/*
+	 * Disallow physical timer access for the guest
+	 * Physical counter access is allowed
+	 */
+	val = read_sysreg(cnthctl_el2);
+	val &= ~CNTHCTL_EL1PCEN;
+	val |= CNTHCTL_EL1PCTEN;
+	write_sysreg(val, cnthctl_el2);
+
+	if (kvm->arch.timer.enabled) {
+		write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2);
+		write_sysreg_el0(timer->cntv_cval, cntv_cval);
+		isb();
+		write_sysreg_el0(timer->cntv_ctl, cntv_ctl);
+	}
+}
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
new file mode 100644
index 0000000..674bdf8
--- /dev/null
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -0,0 +1,170 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
+					    void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	u32 eisr0, eisr1;
+	int i;
+	bool expect_mi;
+
+	expect_mi = !!(cpu_if->vgic_hcr & GICH_HCR_UIE);
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+		expect_mi |= (!(cpu_if->vgic_lr[i] & GICH_LR_HW) &&
+			      (cpu_if->vgic_lr[i] & GICH_LR_EOI));
+	}
+
+	if (expect_mi) {
+		cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
+
+		if (cpu_if->vgic_misr & GICH_MISR_EOI) {
+			eisr0  = readl_relaxed(base + GICH_EISR0);
+			if (unlikely(nr_lr > 32))
+				eisr1  = readl_relaxed(base + GICH_EISR1);
+			else
+				eisr1 = 0;
+		} else {
+			eisr0 = eisr1 = 0;
+		}
+	} else {
+		cpu_if->vgic_misr = 0;
+		eisr0 = eisr1 = 0;
+	}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	cpu_if->vgic_eisr = ((u64)eisr0 << 32) | eisr1;
+#else
+	cpu_if->vgic_eisr = ((u64)eisr1 << 32) | eisr0;
+#endif
+}
+
+static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	u32 elrsr0, elrsr1;
+
+	elrsr0 = readl_relaxed(base + GICH_ELRSR0);
+	if (unlikely(nr_lr > 32))
+		elrsr1 = readl_relaxed(base + GICH_ELRSR1);
+	else
+		elrsr1 = 0;
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1;
+#else
+	cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0;
+#endif
+}
+
+static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	int i;
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+			continue;
+
+		if (cpu_if->vgic_elrsr & (1UL << i)) {
+			cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
+			continue;
+		}
+
+		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
+		writel_relaxed(0, base + GICH_LR0 + (i * 4));
+	}
+}
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+
+	if (!base)
+		return;
+
+	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
+
+	if (vcpu->arch.vgic_cpu.live_lrs) {
+		cpu_if->vgic_apr = readl_relaxed(base + GICH_APR);
+
+		save_maint_int_state(vcpu, base);
+		save_elrsr(vcpu, base);
+		save_lrs(vcpu, base);
+
+		writel_relaxed(0, base + GICH_HCR);
+
+		vcpu->arch.vgic_cpu.live_lrs = 0;
+	} else {
+		cpu_if->vgic_eisr = 0;
+		cpu_if->vgic_elrsr = ~0UL;
+		cpu_if->vgic_misr = 0;
+		cpu_if->vgic_apr = 0;
+	}
+}
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+	int i, nr_lr;
+	u64 live_lrs = 0;
+
+	if (!base)
+		return;
+
+	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+
+	for (i = 0; i < nr_lr; i++)
+		if (cpu_if->vgic_lr[i] & GICH_LR_STATE)
+			live_lrs |= 1UL << i;
+
+	if (live_lrs) {
+		writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
+		writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
+		for (i = 0; i < nr_lr; i++) {
+			if (!(live_lrs & (1UL << i)))
+				continue;
+
+			writel_relaxed(cpu_if->vgic_lr[i],
+				       base + GICH_LR0 + (i * 4));
+		}
+	}
+
+	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
+	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
+}
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
new file mode 100644
index 0000000..b5754c6
--- /dev/null
+++ b/virt/kvm/arm/pmu.c
@@ -0,0 +1,529 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd.
+ * Author: Shannon Zhao <shannon.zhao@linaro.org>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+#include <asm/kvm_emulate.h>
+#include <kvm/arm_pmu.h>
+#include <kvm/arm_vgic.h>
+
+/**
+ * kvm_pmu_get_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ */
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	u64 counter, reg, enabled, running;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
+	counter = vcpu_sys_reg(vcpu, reg);
+
+	/* The real counter value is equal to the value of counter register plus
+	 * the value perf event counts.
+	 */
+	if (pmc->perf_event)
+		counter += perf_event_read_value(pmc->perf_event, &enabled,
+						 &running);
+
+	return counter & pmc->bitmask;
+}
+
+/**
+ * kvm_pmu_set_counter_value - set PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ * @val: The counter value
+ */
+void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
+{
+	u64 reg;
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
+	vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
+}
+
+/**
+ * kvm_pmu_stop_counter - stop PMU counter
+ * @pmc: The PMU counter pointer
+ *
+ * If this counter has been configured to monitor some event, release it here.
+ */
+static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
+{
+	u64 counter, reg;
+
+	if (pmc->perf_event) {
+		counter = kvm_pmu_get_counter_value(vcpu, pmc->idx);
+		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
+		vcpu_sys_reg(vcpu, reg) = counter;
+		perf_event_disable(pmc->perf_event);
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+	}
+}
+
+/**
+ * kvm_pmu_vcpu_reset - reset pmu state for cpu
+ * @vcpu: The vcpu pointer
+ *
+ */
+void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
+		pmu->pmc[i].idx = i;
+		pmu->pmc[i].bitmask = 0xffffffffUL;
+	}
+}
+
+/**
+ * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu
+ * @vcpu: The vcpu pointer
+ *
+ */
+void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		struct kvm_pmc *pmc = &pmu->pmc[i];
+
+		if (pmc->perf_event) {
+			perf_event_disable(pmc->perf_event);
+			perf_event_release_kernel(pmc->perf_event);
+			pmc->perf_event = NULL;
+		}
+	}
+}
+
+u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
+{
+	u64 val = vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT;
+
+	val &= ARMV8_PMU_PMCR_N_MASK;
+	if (val == 0)
+		return BIT(ARMV8_PMU_CYCLE_IDX);
+	else
+		return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX);
+}
+
+/**
+ * kvm_pmu_enable_counter - enable selected PMU counter
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCNTENSET register
+ *
+ * Call perf_event_enable to start counting the perf event
+ */
+void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+
+	if (!(vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val)
+		return;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		if (!(val & BIT(i)))
+			continue;
+
+		pmc = &pmu->pmc[i];
+		if (pmc->perf_event) {
+			perf_event_enable(pmc->perf_event);
+			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
+				kvm_debug("fail to enable perf event\n");
+		}
+	}
+}
+
+/**
+ * kvm_pmu_disable_counter - disable selected PMU counter
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCNTENCLR register
+ *
+ * Call perf_event_disable to stop counting the perf event
+ */
+void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+
+	if (!val)
+		return;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		if (!(val & BIT(i)))
+			continue;
+
+		pmc = &pmu->pmc[i];
+		if (pmc->perf_event)
+			perf_event_disable(pmc->perf_event);
+	}
+}
+
+static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
+{
+	u64 reg = 0;
+
+	if ((vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+		reg = vcpu_sys_reg(vcpu, PMOVSSET_EL0);
+		reg &= vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+		reg &= vcpu_sys_reg(vcpu, PMINTENSET_EL1);
+		reg &= kvm_pmu_valid_counter_mask(vcpu);
+
+	return reg;
+}
+
+/**
+ * kvm_pmu_overflow_set - set PMU overflow interrupt
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMOVSSET register
+ */
+void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val)
+{
+	u64 reg;
+
+	if (val == 0)
+		return;
+
+	vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= val;
+	reg = kvm_pmu_overflow_status(vcpu);
+	if (reg != 0)
+		kvm_vcpu_kick(vcpu);
+}
+
+static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	bool overflow;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return;
+
+	overflow = !!kvm_pmu_overflow_status(vcpu);
+	if (pmu->irq_level != overflow) {
+		pmu->irq_level = overflow;
+		kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+				    pmu->irq_num, overflow);
+	}
+}
+
+/**
+ * kvm_pmu_flush_hwstate - flush pmu state to cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the PMU has overflowed while we were running in the host, and inject
+ * an interrupt if that was the case.
+ */
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	kvm_pmu_update_state(vcpu);
+}
+
+/**
+ * kvm_pmu_sync_hwstate - sync pmu state from cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the PMU has overflowed while we were running in the guest, and
+ * inject an interrupt if that was the case.
+ */
+void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+	kvm_pmu_update_state(vcpu);
+}
+
+static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu;
+	struct kvm_vcpu_arch *vcpu_arch;
+
+	pmc -= pmc->idx;
+	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
+	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
+	return container_of(vcpu_arch, struct kvm_vcpu, arch);
+}
+
+/**
+ * When perf event overflows, call kvm_pmu_overflow_set to set overflow status.
+ */
+static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
+				  struct perf_sample_data *data,
+				  struct pt_regs *regs)
+{
+	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	int idx = pmc->idx;
+
+	kvm_pmu_overflow_set(vcpu, BIT(idx));
+}
+
+/**
+ * kvm_pmu_software_increment - do software increment
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMSWINC register
+ */
+void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	u64 type, enable, reg;
+
+	if (val == 0)
+		return;
+
+	enable = vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+	for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) {
+		if (!(val & BIT(i)))
+			continue;
+		type = vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
+		       & ARMV8_PMU_EVTYPE_EVENT;
+		if ((type == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		    && (enable & BIT(i))) {
+			reg = vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+			reg = lower_32_bits(reg);
+			vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
+			if (!reg)
+				kvm_pmu_overflow_set(vcpu, BIT(i));
+		}
+	}
+}
+
+/**
+ * kvm_pmu_handle_pmcr - handle PMCR register
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCR register
+ */
+void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+	u64 mask;
+	int i;
+
+	mask = kvm_pmu_valid_counter_mask(vcpu);
+	if (val & ARMV8_PMU_PMCR_E) {
+		kvm_pmu_enable_counter(vcpu,
+				vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
+	} else {
+		kvm_pmu_disable_counter(vcpu, mask);
+	}
+
+	if (val & ARMV8_PMU_PMCR_C)
+		kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
+
+	if (val & ARMV8_PMU_PMCR_P) {
+		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
+			kvm_pmu_set_counter_value(vcpu, i, 0);
+	}
+
+	if (val & ARMV8_PMU_PMCR_LC) {
+		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
+		pmc->bitmask = 0xffffffffffffffffUL;
+	}
+}
+
+static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	return (vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) &&
+	       (vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(select_idx));
+}
+
+/**
+ * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
+ * @vcpu: The vcpu pointer
+ * @data: The data guest writes to PMXEVTYPER_EL0
+ * @select_idx: The number of selected counter
+ *
+ * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an
+ * event with given hardware event number. Here we call perf_event API to
+ * emulate this action and create a kernel perf event for it.
+ */
+void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
+				    u64 select_idx)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	struct perf_event *event;
+	struct perf_event_attr attr;
+	u64 eventsel, counter;
+
+	kvm_pmu_stop_counter(vcpu, pmc);
+	eventsel = data & ARMV8_PMU_EVTYPE_EVENT;
+
+	/* Software increment event does't need to be backed by a perf event */
+	if (eventsel == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		return;
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.type = PERF_TYPE_RAW;
+	attr.size = sizeof(attr);
+	attr.pinned = 1;
+	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, select_idx);
+	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
+	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
+	attr.exclude_hv = 1; /* Don't count EL2 events */
+	attr.exclude_host = 1; /* Don't count host events */
+	attr.config = eventsel;
+
+	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
+	/* The initial sample period (overflow count) of an event. */
+	attr.sample_period = (-counter) & pmc->bitmask;
+
+	event = perf_event_create_kernel_counter(&attr, -1, current,
+						 kvm_pmu_perf_overflow, pmc);
+	if (IS_ERR(event)) {
+		pr_err_once("kvm: pmu event creation failed %ld\n",
+			    PTR_ERR(event));
+		return;
+	}
+
+	pmc->perf_event = event;
+}
+
+bool kvm_arm_support_pmu_v3(void)
+{
+	/*
+	 * Check if HW_PERF_EVENTS are supported by checking the number of
+	 * hardware performance counters. This could ensure the presence of
+	 * a physical PMU and CONFIG_PERF_EVENT is selected.
+	 */
+	return (perf_num_counters() > 0);
+}
+
+static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_arm_support_pmu_v3())
+		return -ENODEV;
+
+	if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features) ||
+	    !kvm_arm_pmu_irq_initialized(vcpu))
+		return -ENXIO;
+
+	if (kvm_arm_pmu_v3_ready(vcpu))
+		return -EBUSY;
+
+	kvm_pmu_vcpu_reset(vcpu);
+	vcpu->arch.pmu.ready = true;
+
+	return 0;
+}
+
+static bool irq_is_valid(struct kvm *kvm, int irq, bool is_ppi)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			continue;
+
+		if (is_ppi) {
+			if (vcpu->arch.pmu.irq_num != irq)
+				return false;
+		} else {
+			if (vcpu->arch.pmu.irq_num == irq)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+
+int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ: {
+		int __user *uaddr = (int __user *)(long)attr->addr;
+		int irq;
+
+		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return -ENODEV;
+
+		if (get_user(irq, uaddr))
+			return -EFAULT;
+
+		/*
+		 * The PMU overflow interrupt could be a PPI or SPI, but for one
+		 * VM the interrupt type must be same for each vcpu. As a PPI,
+		 * the interrupt number is the same for all vcpus, while as an
+		 * SPI it must be a separate number per vcpu.
+		 */
+		if (irq < VGIC_NR_SGIS || irq >= vcpu->kvm->arch.vgic.nr_irqs ||
+		    !irq_is_valid(vcpu->kvm, irq, irq < VGIC_NR_PRIVATE_IRQS))
+			return -EINVAL;
+
+		if (kvm_arm_pmu_irq_initialized(vcpu))
+			return -EBUSY;
+
+		kvm_debug("Set kvm ARM PMU irq: %d\n", irq);
+		vcpu->arch.pmu.irq_num = irq;
+		return 0;
+	}
+	case KVM_ARM_VCPU_PMU_V3_INIT:
+		return kvm_arm_pmu_v3_init(vcpu);
+	}
+
+	return -ENXIO;
+}
+
+int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ: {
+		int __user *uaddr = (int __user *)(long)attr->addr;
+		int irq;
+
+		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return -ENODEV;
+
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			return -ENXIO;
+
+		irq = vcpu->arch.pmu.irq_num;
+		return put_user(irq, uaddr);
+	}
+	}
+
+	return -ENXIO;
+}
+
+int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ:
+	case KVM_ARM_VCPU_PMU_V3_INIT:
+		if (kvm_arm_support_pmu_v3() &&
+		    test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return 0;
+	}
+
+	return -ENXIO;
+}
diff --git a/virt/kvm/arm/vgic-v2-emul.c b/virt/kvm/arm/vgic-v2-emul.c
index 1390797..1b0bee0 100644
--- a/virt/kvm/arm/vgic-v2-emul.c
+++ b/virt/kvm/arm/vgic-v2-emul.c
@@ -321,6 +321,11 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
 
 static const struct vgic_io_range vgic_dist_ranges[] = {
 	{
+		.base		= GIC_DIST_SOFTINT,
+		.len		= 4,
+		.handle_mmio	= handle_mmio_sgi_reg,
+	},
+	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,
 		.bits_per_irq	= 0,
@@ -387,11 +392,6 @@ static const struct vgic_io_range vgic_dist_ranges[] = {
 		.handle_mmio	= handle_mmio_cfg_reg,
 	},
 	{
-		.base		= GIC_DIST_SOFTINT,
-		.len		= 4,
-		.handle_mmio	= handle_mmio_sgi_reg,
-	},
-	{
 		.base		= GIC_DIST_SGI_PENDING_CLEAR,
 		.len		= VGIC_NR_SGIS,
 		.handle_mmio	= handle_mmio_sgi_clear,
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index ff02f08..67ec334 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -176,6 +176,15 @@ static const struct vgic_ops vgic_v2_ops = {
 
 static struct vgic_params vgic_v2_params;
 
+static void vgic_cpu_init_lrs(void *params)
+{
+	struct vgic_params *vgic = params;
+	int i;
+
+	for (i = 0; i < vgic->nr_lr; i++)
+		writel_relaxed(0, vgic->vctrl_base + GICH_LR0 + (i * 4));
+}
+
 /**
  * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
  * @node:	pointer to the DT node
@@ -257,6 +266,9 @@ int vgic_v2_probe(struct device_node *vgic_node,
 
 	vgic->type = VGIC_V2;
 	vgic->max_gic_vcpus = VGIC_V2_MAX_CPUS;
+
+	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
+
 	*ops = &vgic_v2_ops;
 	*params = vgic;
 	goto out;
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 453eafd..999bdc6 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -42,7 +42,7 @@ static u32 ich_vtr_el2;
 static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
 {
 	struct vgic_lr lr_desc;
-	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)];
+	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr];
 
 	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
 		lr_desc.irq = val & ICH_LR_VIRTUALID_MASK;
@@ -106,7 +106,7 @@ static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
 		lr_val |= ((u64)lr_desc.hwirq) << ICH_LR_PHYS_ID_SHIFT;
 	}
 
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)] = lr_val;
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = lr_val;
 
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
@@ -216,6 +216,11 @@ static const struct vgic_ops vgic_v3_ops = {
 
 static struct vgic_params vgic_v3_params;
 
+static void vgic_cpu_init_lrs(void *params)
+{
+	kvm_call_hyp(__vgic_v3_init_lrs);
+}
+
 /**
  * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
  * @node:	pointer to the DT node
@@ -284,6 +289,8 @@ int vgic_v3_probe(struct device_node *vgic_node,
 	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
 		 vcpu_res.start, vgic->maint_irq);
 
+	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
+
 	*ops = &vgic_v3_ops;
 	*params = vgic;
 
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 65da997..f0d061f 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -109,8 +109,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 	/* cancel outstanding work queue item */
 	while (!list_empty(&vcpu->async_pf.queue)) {
 		struct kvm_async_pf *work =
-			list_entry(vcpu->async_pf.queue.next,
-				   typeof(*work), queue);
+			list_first_entry(&vcpu->async_pf.queue,
+					 typeof(*work), queue);
 		list_del(&work->queue);
 
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
@@ -127,8 +127,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 	spin_lock(&vcpu->async_pf.lock);
 	while (!list_empty(&vcpu->async_pf.done)) {
 		struct kvm_async_pf *work =
-			list_entry(vcpu->async_pf.done.next,
-				   typeof(*work), link);
+			list_first_entry(&vcpu->async_pf.done,
+					 typeof(*work), link);
 		list_del(&work->link);
 		kmem_cache_free(async_pf_cache, work);
 	}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5af50c3..7ba1d10 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -72,11 +72,11 @@ module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
 
 /* Default doubles per-vcpu halt_poll_ns. */
 static unsigned int halt_poll_ns_grow = 2;
-module_param(halt_poll_ns_grow, int, S_IRUGO);
+module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
 
 /* Default resets per-vcpu halt_poll_ns . */
 static unsigned int halt_poll_ns_shrink;
-module_param(halt_poll_ns_shrink, int, S_IRUGO);
+module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
 
 /*
  * Ordering of locks:
@@ -619,13 +619,10 @@ void *kvm_kvzalloc(unsigned long size)
 
 static void kvm_destroy_devices(struct kvm *kvm)
 {
-	struct list_head *node, *tmp;
+	struct kvm_device *dev, *tmp;
 
-	list_for_each_safe(node, tmp, &kvm->devices) {
-		struct kvm_device *dev =
-			list_entry(node, struct kvm_device, vm_node);
-
-		list_del(node);
+	list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
+		list_del(&dev->vm_node);
 		dev->ops->destroy(dev);
 	}
 }
@@ -1436,11 +1433,17 @@ kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
 {
 	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
 
-	if (addr == KVM_HVA_ERR_RO_BAD)
+	if (addr == KVM_HVA_ERR_RO_BAD) {
+		if (writable)
+			*writable = false;
 		return KVM_PFN_ERR_RO_FAULT;
+	}
 
-	if (kvm_is_error_hva(addr))
+	if (kvm_is_error_hva(addr)) {
+		if (writable)
+			*writable = false;
 		return KVM_PFN_NOSLOT;
+	}
 
 	/* Do not map writable pfn in the readonly memslot. */
 	if (writable && memslot_is_readonly(slot)) {
@@ -1942,14 +1945,15 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
 
 static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
 {
-	int old, val;
+	unsigned int old, val, grow;
 
 	old = val = vcpu->halt_poll_ns;
+	grow = READ_ONCE(halt_poll_ns_grow);
 	/* 10us base */
-	if (val == 0 && halt_poll_ns_grow)
+	if (val == 0 && grow)
 		val = 10000;
 	else
-		val *= halt_poll_ns_grow;
+		val *= grow;
 
 	if (val > halt_poll_ns)
 		val = halt_poll_ns;
@@ -1960,13 +1964,14 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
 
 static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
 {
-	int old, val;
+	unsigned int old, val, shrink;
 
 	old = val = vcpu->halt_poll_ns;
-	if (halt_poll_ns_shrink == 0)
+	shrink = READ_ONCE(halt_poll_ns_shrink);
+	if (shrink == 0)
 		val = 0;
 	else
-		val /= halt_poll_ns_shrink;
+		val /= shrink;
 
 	vcpu->halt_poll_ns = val;
 	trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);