Merge branch kvm-arm64/sgi-injection into kvmarm/next

* kvm-arm64/sgi-injection:
  : vSGI injection improvements + fixes, courtesy Marc Zyngier
  :
  : Avoid linearly searching for vSGI targets using a compressed MPIDR to
  : index a cache. While at it, fix some egregious bugs in KVM's mishandling
  : of vcpuid (user-controlled value) and vcpu_idx.
  KVM: arm64: Clarify the ordering requirements for vcpu/RD creation
  KVM: arm64: vgic-v3: Optimize affinity-based SGI injection
  KVM: arm64: Fast-track kvm_mpidr_to_vcpu() when mpidr_data is available
  KVM: arm64: Build MPIDR to vcpu index cache at runtime
  KVM: arm64: Simplify kvm_vcpu_get_mpidr_aff()
  KVM: arm64: Use vcpu_idx for invalidation tracking
  KVM: arm64: vgic: Use vcpu_idx for the debug information
  KVM: arm64: vgic-v2: Use cpuid from userspace as vcpu_id
  KVM: arm64: vgic-v3: Refactor GICv3 SGI generation
  KVM: arm64: vgic-its: Treat the collection target address as a vcpu_id
  KVM: arm64: vgic: Make kvm_vgic_inject_irq() take a vcpu pointer

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

Author: oupton

Documentation/virt/kvm/devices/arm-vgic-v3.rst

@@ -59,6 +59,13 @@ Groups:
   It is invalid to mix calls with KVM_VGIC_V3_ADDR_TYPE_REDIST and
   KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes.
 
+  Note that to obtain reproducible results (the same VCPU being associated
+  with the same redistributor across a save/restore operation), VCPU creation
+  order, redistributor region creation order as well as the respective
+  interleaves of VCPU and region creation MUST be preserved.  Any change in
+  either ordering may result in a different vcpu_id/redistributor association,
+  resulting in a VM that will fail to run at restore time.
+
   Errors:
 
     =======  =============================================================

arch/arm64/include/asm/kvm_emulate.h

@@ -470,7 +470,7 @@ static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
+	return __vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)

arch/arm64/include/asm/kvm_host.h

@@ -212,6 +212,31 @@ struct kvm_protected_vm {
 	struct kvm_hyp_memcache teardown_mc;
 };
 
+struct kvm_mpidr_data {
+	u64			mpidr_mask;
+	DECLARE_FLEX_ARRAY(u16, cmpidr_to_idx);
+};
+
+static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr)
+{
+	unsigned long mask = data->mpidr_mask;
+	u64 aff = mpidr & MPIDR_HWID_BITMASK;
+	int nbits, bit, bit_idx = 0;
+	u16 index = 0;
+
+	/*
+	 * If this looks like RISC-V's BEXT or x86's PEXT
+	 * instructions, it isn't by accident.
+	 */
+	nbits = fls(mask);
+	for_each_set_bit(bit, &mask, nbits) {
+		index |= (aff & BIT(bit)) >> (bit - bit_idx);
+		bit_idx++;
+	}
+
+	return index;
+}
+
 struct kvm_arch {
 	struct kvm_s2_mmu mmu;
 
@@ -253,6 +278,9 @@ struct kvm_arch {
 	/* VM-wide vCPU feature set */
 	DECLARE_BITMAP(vcpu_features, KVM_VCPU_MAX_FEATURES);
 
+	/* MPIDR to vcpu index mapping, optional */
+	struct kvm_mpidr_data *mpidr_data;
+
 	/*
 	 * VM-wide PMU filter, implemented as a bitmap and big enough for
 	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).

arch/arm64/kvm/arch_timer.c

@@ -458,7 +458,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				   timer_ctx->irq.level);
 
 	if (!userspace_irqchip(vcpu->kvm)) {
-		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
 					  timer_irq(timer_ctx),
 					  timer_ctx->irq.level,
 					  timer_ctx);

arch/arm64/kvm/arm.c

@@ -205,6 +205,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	if (is_protected_kvm_enabled())
 		pkvm_destroy_hyp_vm(kvm);
 
+	kfree(kvm->arch.mpidr_data);
 	kvm_destroy_vcpus(kvm);
 
 	kvm_unshare_hyp(kvm, kvm + 1);
@@ -437,9 +438,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
-	if (*last_ran != vcpu->vcpu_id) {
+	if (*last_ran != vcpu->vcpu_idx) {
 		kvm_call_hyp(__kvm_flush_cpu_context, mmu);
-		*last_ran = vcpu->vcpu_id;
+		*last_ran = vcpu->vcpu_idx;
 	}
 
 	vcpu->cpu = cpu;
@@ -577,6 +578,57 @@ static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
 	return vcpu_get_flag(vcpu, VCPU_INITIALIZED);
 }
 
+static void kvm_init_mpidr_data(struct kvm *kvm)
+{
+	struct kvm_mpidr_data *data = NULL;
+	unsigned long c, mask, nr_entries;
+	u64 aff_set = 0, aff_clr = ~0UL;
+	struct kvm_vcpu *vcpu;
+
+	mutex_lock(&kvm->arch.config_lock);
+
+	if (kvm->arch.mpidr_data || atomic_read(&kvm->online_vcpus) == 1)
+		goto out;
+
+	kvm_for_each_vcpu(c, vcpu, kvm) {
+		u64 aff = kvm_vcpu_get_mpidr_aff(vcpu);
+		aff_set |= aff;
+		aff_clr &= aff;
+	}
+
+	/*
+	 * A significant bit can be either 0 or 1, and will only appear in
+	 * aff_set. Use aff_clr to weed out the useless stuff.
+	 */
+	mask = aff_set ^ aff_clr;
+	nr_entries = BIT_ULL(hweight_long(mask));
+
+	/*
+	 * Don't let userspace fool us. If we need more than a single page
+	 * to describe the compressed MPIDR array, just fall back to the
+	 * iterative method. Single vcpu VMs do not need this either.
+	 */
+	if (struct_size(data, cmpidr_to_idx, nr_entries) <= PAGE_SIZE)
+		data = kzalloc(struct_size(data, cmpidr_to_idx, nr_entries),
+			       GFP_KERNEL_ACCOUNT);
+
+	if (!data)
+		goto out;
+
+	data->mpidr_mask = mask;
+
+	kvm_for_each_vcpu(c, vcpu, kvm) {
+		u64 aff = kvm_vcpu_get_mpidr_aff(vcpu);
+		u16 index = kvm_mpidr_index(data, aff);
+
+		data->cmpidr_to_idx[index] = c;
+	}
+
+	kvm->arch.mpidr_data = data;
+out:
+	mutex_unlock(&kvm->arch.config_lock);
+}
+
 /*
  * Handle both the initialisation that is being done when the vcpu is
  * run for the first time, as well as the updates that must be
@@ -600,6 +652,8 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (likely(vcpu_has_run_once(vcpu)))
 		return 0;
 
+	kvm_init_mpidr_data(kvm);
+
 	kvm_arm_vcpu_init_debug(vcpu);
 
 	if (likely(irqchip_in_kernel(kvm))) {
@@ -1136,27 +1190,23 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 			  bool line_status)
 {
 	u32 irq = irq_level->irq;
-	unsigned int irq_type, vcpu_idx, irq_num;
-	int nrcpus = atomic_read(&kvm->online_vcpus);
+	unsigned int irq_type, vcpu_id, irq_num;
 	struct kvm_vcpu *vcpu = NULL;
 	bool level = irq_level->level;
 
 	irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK;
-	vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
-	vcpu_idx += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1);
+	vcpu_id = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
+	vcpu_id += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1);
 	irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK;
 
-	trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level);
+	trace_kvm_irq_line(irq_type, vcpu_id, irq_num, irq_level->level);
 
 	switch (irq_type) {
 	case KVM_ARM_IRQ_TYPE_CPU:
 		if (irqchip_in_kernel(kvm))
 			return -ENXIO;
 
-		if (vcpu_idx >= nrcpus)
-			return -EINVAL;
-
-		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+		vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
 		if (!vcpu)
 			return -EINVAL;
 
@@ -1168,25 +1218,22 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
 
-		if (vcpu_idx >= nrcpus)
-			return -EINVAL;
-
-		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+		vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
 		if (!vcpu)
 			return -EINVAL;
 
 		if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level, NULL);
+		return kvm_vgic_inject_irq(kvm, vcpu, irq_num, level, NULL);
 	case KVM_ARM_IRQ_TYPE_SPI:
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
 
 		if (irq_num < VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, 0, irq_num, level, NULL);
+		return kvm_vgic_inject_irq(kvm, NULL, irq_num, level, NULL);
 	}
 
 	return -EINVAL;
@@ -2378,6 +2425,18 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
 	unsigned long i;
 
 	mpidr &= MPIDR_HWID_BITMASK;
+
+	if (kvm->arch.mpidr_data) {
+		u16 idx = kvm_mpidr_index(kvm->arch.mpidr_data, mpidr);
+
+		vcpu = kvm_get_vcpu(kvm,
+				    kvm->arch.mpidr_data->cmpidr_to_idx[idx]);
+		if (mpidr != kvm_vcpu_get_mpidr_aff(vcpu))
+			vcpu = NULL;
+
+		return vcpu;
+	}
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu))
 			return vcpu;

arch/arm64/kvm/pmu-emul.c

@@ -365,7 +365,7 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 	pmu->irq_level = overflow;
 
 	if (likely(irqchip_in_kernel(vcpu->kvm))) {
-		int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+		int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
 					      pmu->irq_num, overflow, pmu);
 		WARN_ON(ret);
 	}

arch/arm64/kvm/vgic/vgic-debug.c

@@ -166,7 +166,7 @@ static void print_header(struct seq_file *s, struct vgic_irq *irq,
 
 	if (vcpu) {
 		hdr = "VCPU";
-		id = vcpu->vcpu_id;
+		id = vcpu->vcpu_idx;
 	}
 
 	seq_printf(s, "\n");
@@ -212,7 +212,7 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
 		      "     %2d "
 		      "\n",
 			type, irq->intid,
-			(irq->target_vcpu) ? irq->target_vcpu->vcpu_id : -1,
+			(irq->target_vcpu) ? irq->target_vcpu->vcpu_idx : -1,
 			pending,
 			irq->line_level,
 			irq->active,
@@ -224,7 +224,7 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
 			irq->mpidr,
 			irq->source,
 			irq->priority,
-			(irq->vcpu) ? irq->vcpu->vcpu_id : -1);
+			(irq->vcpu) ? irq->vcpu->vcpu_idx : -1);
 }
 
 static int vgic_debug_show(struct seq_file *s, void *v)

arch/arm64/kvm/vgic/vgic-irqfd.c

@@ -23,7 +23,7 @@ static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e,
 
 	if (!vgic_valid_spi(kvm, spi_id))
 		return -EINVAL;
-	return kvm_vgic_inject_irq(kvm, 0, spi_id, level, NULL);
+	return kvm_vgic_inject_irq(kvm, NULL, spi_id, level, NULL);
 }
 
 /**