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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for chained PMU counters in guests
   - improved SError handling
   - handle Neoverse N1 erratum #1349291
   - allow side-channel mitigation status to be migrated
   - standardise most AArch64 system register accesses to msr_s/mrs_s
   - fix host MPIDR corruption on 32bit
   - selftests ckleanups

  x86:
   - PMU event {white,black}listing
   - ability for the guest to disable host-side interrupt polling
   - fixes for enlightened VMCS (Hyper-V pv nested virtualization),
   - new hypercall to yield to IPI target
   - support for passing cstate MSRs through to the guest
   - lots of cleanups and optimizations

  Generic:
   - Some txt->rST conversions for the documentation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (128 commits)
  Documentation: virtual: Add toctree hooks
  Documentation: kvm: Convert cpuid.txt to .rst
  Documentation: virtual: Convert paravirt_ops.txt to .rst
  KVM: x86: Unconditionally enable irqs in guest context
  KVM: x86: PMU Event Filter
  kvm: x86: Fix -Wmissing-prototypes warnings
  KVM: Properly check if "page" is valid in kvm_vcpu_unmap
  KVM: arm/arm64: Initialise host's MPIDRs by reading the actual register
  KVM: LAPIC: Retry tune per-vCPU timer_advance_ns if adaptive tuning goes insane
  kvm: LAPIC: write down valid APIC registers
  KVM: arm64: Migrate _elx sysreg accessors to msr_s/mrs_s
  KVM: doc: Add API documentation on the KVM_REG_ARM_WORKAROUNDS register
  KVM: arm/arm64: Add save/restore support for firmware workaround state
  arm64: KVM: Propagate full Spectre v2 workaround state to KVM guests
  KVM: arm/arm64: Support chained PMU counters
  KVM: arm/arm64: Remove pmc->bitmask
  KVM: arm/arm64: Re-create event when setting counter value
  KVM: arm/arm64: Extract duplicated code to own function
  KVM: arm/arm64: Rename kvm_pmu_{enable/disable}_counter functions
  KVM: LAPIC: ARBPRI is a reserved register for x2APIC
  ...

6 files changed, 455 insertions, 120 deletions

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 1be486d5d7cb..e2bb5bd60227 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -237,10 +237,10 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 
 		switch (index) {
 		case TIMER_VTIMER:
-			cnt_ctl = read_sysreg_el0(cntv_ctl);
+			cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL);
 			break;
 		case TIMER_PTIMER:
-			cnt_ctl = read_sysreg_el0(cntp_ctl);
+			cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL);
 			break;
 		case NR_KVM_TIMERS:
 			/* GCC is braindead */
@@ -350,20 +350,20 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(cntv_ctl);
-		ctx->cnt_cval = read_sysreg_el0(cntv_cval);
+		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL);
+		ctx->cnt_cval = read_sysreg_el0(SYS_CNTV_CVAL);
 
 		/* Disable the timer */
-		write_sysreg_el0(0, cntv_ctl);
+		write_sysreg_el0(0, SYS_CNTV_CTL);
 		isb();
 
 		break;
 	case TIMER_PTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(cntp_ctl);
-		ctx->cnt_cval = read_sysreg_el0(cntp_cval);
+		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL);
+		ctx->cnt_cval = read_sysreg_el0(SYS_CNTP_CVAL);
 
 		/* Disable the timer */
-		write_sysreg_el0(0, cntp_ctl);
+		write_sysreg_el0(0, SYS_CNTP_CTL);
 		isb();
 
 		break;
@@ -429,14 +429,14 @@ static void timer_restore_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		write_sysreg_el0(ctx->cnt_cval, cntv_cval);
+		write_sysreg_el0(ctx->cnt_cval, SYS_CNTV_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, cntv_ctl);
+		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTV_CTL);
 		break;
 	case TIMER_PTIMER:
-		write_sysreg_el0(ctx->cnt_cval, cntp_cval);
+		write_sysreg_el0(ctx->cnt_cval, SYS_CNTP_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, cntp_ctl);
+		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTP_CTL);
 		break;
 	case NR_KVM_TIMERS:
 		BUG();
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index bd5c55916d0d..f645c0fbf7ec 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -93,9 +93,9 @@ int kvm_arch_hardware_setup(void)
 	return 0;
 }
 
-void kvm_arch_check_processor_compat(void *rtn)
+int kvm_arch_check_processor_compat(void)
 {
-	*(int *)rtn = 0;
+	return 0;
 }
 
 
@@ -1332,6 +1332,8 @@ static void cpu_hyp_reset(void)
 
 static void cpu_hyp_reinit(void)
 {
+	kvm_init_host_cpu_context(&this_cpu_ptr(&kvm_host_data)->host_ctxt);
+
 	cpu_hyp_reset();
 
 	if (is_kernel_in_hyp_mode())
@@ -1569,7 +1571,6 @@ static int init_hyp_mode(void)
 		kvm_host_data_t *cpu_data;
 
 		cpu_data = per_cpu_ptr(&kvm_host_data, cpu);
-		kvm_init_host_cpu_context(&cpu_data->host_ctxt, cpu);
 		err = create_hyp_mappings(cpu_data, cpu_data + 1, PAGE_HYP);
 
 		if (err) {
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index da740764a7ee..3dd8238ed246 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -13,29 +13,144 @@
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
 
+static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
+
+#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1
+
 /**
- * kvm_pmu_get_counter_value - get PMU counter value
+ * kvm_pmu_idx_is_64bit - determine if select_idx is a 64bit counter
  * @vcpu: The vcpu pointer
  * @select_idx: The counter index
  */
-u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+static bool kvm_pmu_idx_is_64bit(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];
+	return (select_idx == ARMV8_PMU_CYCLE_IDX &&
+		__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC);
+}
 
-	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
-	counter = __vcpu_sys_reg(vcpu, reg);
+static 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);
+}
+
+/**
+ * kvm_pmu_pmc_is_chained - determine if the pmc is chained
+ * @pmc: The PMU counter pointer
+ */
+static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc)
+{
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 
-	/* The real counter value is equal to the value of counter register plus
+	return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+}
+
+/**
+ * kvm_pmu_idx_is_high_counter - determine if select_idx is a high/low counter
+ * @select_idx: The counter index
+ */
+static bool kvm_pmu_idx_is_high_counter(u64 select_idx)
+{
+	return select_idx & 0x1;
+}
+
+/**
+ * kvm_pmu_get_canonical_pmc - obtain the canonical pmc
+ * @pmc: The PMU counter pointer
+ *
+ * When a pair of PMCs are chained together we use the low counter (canonical)
+ * to hold the underlying perf event.
+ */
+static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc)
+{
+	if (kvm_pmu_pmc_is_chained(pmc) &&
+	    kvm_pmu_idx_is_high_counter(pmc->idx))
+		return pmc - 1;
+
+	return pmc;
+}
+
+/**
+ * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ */
+static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	u64 eventsel, reg;
+
+	select_idx |= 0x1;
+
+	if (select_idx == ARMV8_PMU_CYCLE_IDX)
+		return false;
+
+	reg = PMEVTYPER0_EL0 + select_idx;
+	eventsel = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_EVENT;
+
+	return eventsel == ARMV8_PMUV3_PERFCTR_CHAIN;
+}
+
+/**
+ * kvm_pmu_get_pair_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @pmc: The PMU counter pointer
+ */
+static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
+					  struct kvm_pmc *pmc)
+{
+	u64 counter, counter_high, reg, enabled, running;
+
+	if (kvm_pmu_pmc_is_chained(pmc)) {
+		pmc = kvm_pmu_get_canonical_pmc(pmc);
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+
+		counter = __vcpu_sys_reg(vcpu, reg);
+		counter_high = __vcpu_sys_reg(vcpu, reg + 1);
+
+		counter = lower_32_bits(counter) | (counter_high << 32);
+	} else {
+		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->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;
+	return counter;
+}
+
+/**
+ * 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;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_pmc_is_chained(pmc) &&
+	    kvm_pmu_idx_is_high_counter(select_idx))
+		counter = upper_32_bits(counter);
+
+	else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
+		counter = lower_32_bits(counter);
+
+	return counter;
 }
 
 /**
@@ -51,6 +166,23 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 	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);
+
+	/* Recreate the perf event to reflect the updated sample_period */
+	kvm_pmu_create_perf_event(vcpu, select_idx);
+}
+
+/**
+ * kvm_pmu_release_perf_event - remove the perf event
+ * @pmc: The PMU counter pointer
+ */
+static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
+{
+	pmc = kvm_pmu_get_canonical_pmc(pmc);
+	if (pmc->perf_event) {
+		perf_event_disable(pmc->perf_event);
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+	}
 }
 
 /**
@@ -63,15 +195,23 @@ 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);
+	pmc = kvm_pmu_get_canonical_pmc(pmc);
+	if (!pmc->perf_event)
+		return;
+
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_pmc_is_chained(pmc)) {
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
+		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+	} else {
 		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;
+		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
 	}
+
+	kvm_pmu_release_perf_event(pmc);
 }
 
 /**
@@ -87,8 +227,9 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 	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;
 	}
+
+	bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 }
 
 /**
@@ -101,15 +242,8 @@ 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;
-		}
-	}
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+		kvm_pmu_release_perf_event(&pmu->pmc[i]);
 }
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
@@ -124,13 +258,13 @@ u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 }
 
 /**
- * kvm_pmu_enable_counter - enable selected PMU counter
+ * kvm_pmu_enable_counter_mask - enable selected PMU counters
  * @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)
+void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
@@ -144,6 +278,18 @@ void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 
 		pmc = &pmu->pmc[i];
+
+		/*
+		 * For high counters of chained events we must recreate the
+		 * perf event with the long (64bit) attribute set.
+		 */
+		if (kvm_pmu_pmc_is_chained(pmc) &&
+		    kvm_pmu_idx_is_high_counter(i)) {
+			kvm_pmu_create_perf_event(vcpu, i);
+			continue;
+		}
+
+		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event) {
 			perf_event_enable(pmc->perf_event);
 			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
@@ -153,13 +299,13 @@ void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
 }
 
 /**
- * kvm_pmu_disable_counter - disable selected PMU counter
+ * kvm_pmu_disable_counter_mask - disable selected PMU counters
  * @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)
+void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
@@ -173,6 +319,18 @@ void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 
 		pmc = &pmu->pmc[i];
+
+		/*
+		 * For high counters of chained events we must recreate the
+		 * perf event with the long (64bit) attribute unset.
+		 */
+		if (kvm_pmu_pmc_is_chained(pmc) &&
+		    kvm_pmu_idx_is_high_counter(i)) {
+			kvm_pmu_create_perf_event(vcpu, i);
+			continue;
+		}
+
+		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event)
 			perf_event_disable(pmc->perf_event);
 	}
@@ -262,17 +420,6 @@ 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 the perf event overflows, set the overflow status and inform the vcpu.
  */
@@ -329,17 +476,15 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
  */
 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,
+		kvm_pmu_enable_counter_mask(vcpu,
 		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
 	} else {
-		kvm_pmu_disable_counter(vcpu, mask);
+		kvm_pmu_disable_counter_mask(vcpu, mask);
 	}
 
 	if (val & ARMV8_PMU_PMCR_C)
@@ -349,11 +494,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 		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)
@@ -363,50 +503,75 @@ static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
 }
 
 /**
- * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
+ * kvm_pmu_create_perf_event - create a perf event for a counter
  * @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)
+static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	struct kvm_pmc *pmc;
 	struct perf_event *event;
 	struct perf_event_attr attr;
-	u64 eventsel, counter;
+	u64 eventsel, counter, reg, data;
+
+	/*
+	 * For chained counters the event type and filtering attributes are
+	 * obtained from the low/even counter. We also use this counter to
+	 * determine if the event is enabled/disabled.
+	 */
+	pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]);
+
+	reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx;
+	data = __vcpu_sys_reg(vcpu, reg);
 
 	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_PMUV3_PERFCTR_SW_INCR &&
-	    select_idx != ARMV8_PMU_CYCLE_IDX)
+	    pmc->idx != ARMV8_PMU_CYCLE_IDX)
 		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.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->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 = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
+	attr.config = (pmc->idx == ARMV8_PMU_CYCLE_IDX) ?
 		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : 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;
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
-	event = perf_event_create_kernel_counter(&attr, -1, current,
+	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+		/**
+		 * The initial sample period (overflow count) of an event. For
+		 * chained counters we only support overflow interrupts on the
+		 * high counter.
+		 */
+		attr.sample_period = (-counter) & GENMASK(63, 0);
+		event = perf_event_create_kernel_counter(&attr, -1, current,
+							 kvm_pmu_perf_overflow,
+							 pmc + 1);
+
+		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
+			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+	} else {
+		/* The initial sample period (overflow count) of an event. */
+		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+			attr.sample_period = (-counter) & GENMASK(63, 0);
+		else
+			attr.sample_period = (-counter) & GENMASK(31, 0);
+
+		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));
@@ -416,6 +581,57 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	pmc->perf_event = event;
 }
 
+/**
+ * kvm_pmu_update_pmc_chained - update chained bitmap
+ * @vcpu: The vcpu pointer
+ * @select_idx: The number of selected counter
+ *
+ * Update the chained bitmap based on the event type written in the
+ * typer register.
+ */
+static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+		/*
+		 * During promotion from !chained to chained we must ensure
+		 * the adjacent counter is stopped and its event destroyed
+		 */
+		if (!kvm_pmu_pmc_is_chained(pmc))
+			kvm_pmu_stop_counter(vcpu, pmc);
+
+		set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+	} else {
+		clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+	}
+}
+
+/**
+ * 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)
+{
+	u64 reg, event_type = data & ARMV8_PMU_EVTYPE_MASK;
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
+
+	__vcpu_sys_reg(vcpu, reg) = event_type;
+
+	kvm_pmu_update_pmc_chained(vcpu, select_idx);
+	kvm_pmu_create_perf_event(vcpu, select_idx);
+}
+
 bool kvm_arm_support_pmu_v3(void)
 {
 	/*
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index be3c9cdca9f3..87927f7e1ee7 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -401,8 +401,16 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 		feature = smccc_get_arg1(vcpu);
 		switch(feature) {
 		case ARM_SMCCC_ARCH_WORKAROUND_1:
-			if (kvm_arm_harden_branch_predictor())
+			switch (kvm_arm_harden_branch_predictor()) {
+			case KVM_BP_HARDEN_UNKNOWN:
+				break;
+			case KVM_BP_HARDEN_WA_NEEDED:
 				val = SMCCC_RET_SUCCESS;
+				break;
+			case KVM_BP_HARDEN_NOT_REQUIRED:
+				val = SMCCC_RET_NOT_REQUIRED;
+				break;
+			}
 			break;
 		case ARM_SMCCC_ARCH_WORKAROUND_2:
 			switch (kvm_arm_have_ssbd()) {
@@ -430,42 +438,103 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
 {
-	return 1;		/* PSCI version */
+	return 3;		/* PSCI version and two workaround registers */
 }
 
 int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
-	if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices))
+	if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices++))
+		return -EFAULT;
+
+	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, uindices++))
+		return -EFAULT;
+
+	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++))
 		return -EFAULT;
 
 	return 0;
 }
 
+#define KVM_REG_FEATURE_LEVEL_WIDTH	4
+#define KVM_REG_FEATURE_LEVEL_MASK	(BIT(KVM_REG_FEATURE_LEVEL_WIDTH) - 1)
+
+/*
+ * Convert the workaround level into an easy-to-compare number, where higher
+ * values mean better protection.
+ */
+static int get_kernel_wa_level(u64 regid)
+{
+	switch (regid) {
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+		switch (kvm_arm_harden_branch_predictor()) {
+		case KVM_BP_HARDEN_UNKNOWN:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
+		case KVM_BP_HARDEN_WA_NEEDED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL;
+		case KVM_BP_HARDEN_NOT_REQUIRED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED;
+		}
+		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+		switch (kvm_arm_have_ssbd()) {
+		case KVM_SSBD_FORCE_DISABLE:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
+		case KVM_SSBD_KERNEL:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL;
+		case KVM_SSBD_FORCE_ENABLE:
+		case KVM_SSBD_MITIGATED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
+		case KVM_SSBD_UNKNOWN:
+		default:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN;
+		}
+	}
+
+	return -EINVAL;
+}
+
 int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
-	if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
-		void __user *uaddr = (void __user *)(long)reg->addr;
-		u64 val;
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
 
+	switch (reg->id) {
+	case KVM_REG_ARM_PSCI_VERSION:
 		val = kvm_psci_version(vcpu, vcpu->kvm);
-		if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
-			return -EFAULT;
+		break;
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
+		break;
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
 
-		return 0;
+		if (val == KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL &&
+		    kvm_arm_get_vcpu_workaround_2_flag(vcpu))
+			val |= KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED;
+		break;
+	default:
+		return -ENOENT;
 	}
 
-	return -EINVAL;
+	if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
 }
 
 int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
-	if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
-		void __user *uaddr = (void __user *)(long)reg->addr;
-		bool wants_02;
-		u64 val;
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+	int wa_level;
 
-		if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
-			return -EFAULT;
+	if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg->id) {
+	case KVM_REG_ARM_PSCI_VERSION:
+	{
+		bool wants_02;
 
 		wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
 
@@ -482,6 +551,54 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 			vcpu->kvm->arch.psci_version = val;
 			return 0;
 		}
+		break;
+	}
+
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
+			return -EINVAL;
+
+		if (get_kernel_wa_level(reg->id) < val)
+			return -EINVAL;
+
+		return 0;
+
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+		if (val & ~(KVM_REG_FEATURE_LEVEL_MASK |
+			    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED))
+			return -EINVAL;
+
+		wa_level = val & KVM_REG_FEATURE_LEVEL_MASK;
+
+		if (get_kernel_wa_level(reg->id) < wa_level)
+			return -EINVAL;
+
+		/* The enabled bit must not be set unless the level is AVAIL. */
+		if (wa_level != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL &&
+		    wa_level != val)
+			return -EINVAL;
+
+		/* Are we finished or do we need to check the enable bit ? */
+		if (kvm_arm_have_ssbd() != KVM_SSBD_KERNEL)
+			return 0;
+
+		/*
+		 * If this kernel supports the workaround to be switched on
+		 * or off, make sure it matches the requested setting.
+		 */
+		switch (wa_level) {
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
+			kvm_arm_set_vcpu_workaround_2_flag(vcpu,
+			    val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED);
+			break;
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED:
+			kvm_arm_set_vcpu_workaround_2_flag(vcpu, true);
+			break;
+		}
+
+		return 0;
+	default:
+		return -ENOENT;
 	}
 
 	return -EINVAL;
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 2e6fc7c66a11..58e4f88b2b9f 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -184,9 +184,7 @@ int kvm_set_irq_routing(struct kvm *kvm,
 
 	nr_rt_entries += 1;
 
-	new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)),
-		      GFP_KERNEL_ACCOUNT);
-
+	new = kzalloc(struct_size(new, map, nr_rt_entries), GFP_KERNEL_ACCOUNT);
 	if (!new)
 		return -ENOMEM;
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2f2d24a4dd5c..b4ab59dd6846 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -95,7 +95,7 @@ EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
  *	kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
-DEFINE_SPINLOCK(kvm_lock);
+DEFINE_MUTEX(kvm_lock);
 static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
@@ -680,9 +680,9 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (r)
 		goto out_err;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	preempt_notifier_inc();
 
@@ -728,9 +728,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
 	kvm_destroy_vm_debugfs(kvm);
 	kvm_arch_sync_events(kvm);
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
@@ -1790,7 +1790,7 @@ void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
 	if (!map->hva)
 		return;
 
-	if (map->page)
+	if (map->page != KVM_UNMAPPED_PAGE)
 		kunmap(map->page);
 #ifdef CONFIG_HAS_IOMEM
 	else
@@ -4031,13 +4031,13 @@ static int vm_stat_get(void *_offset, u64 *val)
 	u64 tmp_val;
 
 	*val = 0;
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vm_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
 		*val += tmp_val;
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -4050,12 +4050,12 @@ static int vm_stat_clear(void *_offset, u64 val)
 	if (val)
 		return -EINVAL;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vm_stat_clear_per_vm((void *)&stat_tmp, 0);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	return 0;
 }
@@ -4070,13 +4070,13 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	u64 tmp_val;
 
 	*val = 0;
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vcpu_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
 		*val += tmp_val;
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -4089,12 +4089,12 @@ static int vcpu_stat_clear(void *_offset, u64 val)
 	if (val)
 		return -EINVAL;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vcpu_stat_clear_per_vm((void *)&stat_tmp, 0);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	return 0;
 }
@@ -4115,7 +4115,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	if (!kvm_dev.this_device || !kvm)
 		return;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	if (type == KVM_EVENT_CREATE_VM) {
 		kvm_createvm_count++;
 		kvm_active_vms++;
@@ -4124,7 +4124,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	}
 	created = kvm_createvm_count;
 	active = kvm_active_vms;
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT);
 	if (!env)
@@ -4221,6 +4221,11 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 	kvm_arch_vcpu_put(vcpu);
 }
 
+static void check_processor_compat(void *rtn)
+{
+	*(int *)rtn = kvm_arch_check_processor_compat();
+}
+
 int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		  struct module *module)
 {
@@ -4252,9 +4257,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		goto out_free_0a;
 
 	for_each_online_cpu(cpu) {
-		smp_call_function_single(cpu,
-				kvm_arch_check_processor_compat,
-				&r, 1);
+		smp_call_function_single(cpu, check_processor_compat, &r, 1);
 		if (r < 0)
 			goto out_free_1;
 	}