Merge branch kvm-arm64/vgic-invlpir into kvmarm-master/next

* kvm-arm64/vgic-invlpir:
  : .
  : Implement MMIO-based LPI invalidation for vGICv3.
  : .
  KVM: arm64: vgic-v3: Advertise GICR_CTLR.{IR, CES} as a new GICD_IIDR revision
  KVM: arm64: vgic-v3: Implement MMIO-based LPI invalidation
  KVM: arm64: vgic-v3: Expose GICR_CTLR.RWP when disabling LPIs
  irqchip/gic-v3: Exposes bit values for GICR_CTLR.{IR, CES}

Signed-off-by: Marc Zyngier <maz@kernel.org>

Author: Marc Zyngier

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

@@ -319,7 +319,12 @@ int vgic_init(struct kvm *kvm)
 
 	vgic_debug_init(kvm);
 
-	dist->implementation_rev = 2;
+	/*
+	 * If userspace didn't set the GIC implementation revision,
+	 * default to the latest and greatest. You know want it.
+	 */
+	if (!dist->implementation_rev)
+		dist->implementation_rev = KVM_VGIC_IMP_REV_LATEST;
 	dist->initialized = true;
 
 out:

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

@@ -683,7 +683,7 @@ int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
 	if (!vcpu)
 		return E_ITS_INT_UNMAPPED_INTERRUPT;
 
-	if (!vcpu->arch.vgic_cpu.lpis_enabled)
+	if (!vgic_lpis_enabled(vcpu))
 		return -EBUSY;
 
 	vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq);
@@ -1272,6 +1272,11 @@ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its,
 	return 0;
 }
 
+int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq)
+{
+	return update_lpi_config(kvm, irq, NULL, true);
+}
+
 /*
  * The INV command syncs the configuration bits from the memory table.
  * Must be called with the its_lock mutex held.
@@ -1288,7 +1293,41 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
 	if (!ite)
 		return E_ITS_INV_UNMAPPED_INTERRUPT;
 
-	return update_lpi_config(kvm, ite->irq, NULL, true);
+	return vgic_its_inv_lpi(kvm, ite->irq);
+}
+
+/**
+ * vgic_its_invall - invalidate all LPIs targetting a given vcpu
+ * @vcpu: the vcpu for which the RD is targetted by an invalidation
+ *
+ * Contrary to the INVALL command, this targets a RD instead of a
+ * collection, and we don't need to hold the its_lock, since no ITS is
+ * involved here.
+ */
+int vgic_its_invall(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int irq_count, i = 0;
+	u32 *intids;
+
+	irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids);
+	if (irq_count < 0)
+		return irq_count;
+
+	for (i = 0; i < irq_count; i++) {
+		struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
+		update_lpi_config(kvm, irq, vcpu, false);
+		vgic_put_irq(kvm, irq);
+	}
+
+	kfree(intids);
+
+	if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm)
+		its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe);
+
+	return 0;
 }
 
 /*
@@ -1305,32 +1344,13 @@ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its,
 	u32 coll_id = its_cmd_get_collection(its_cmd);
 	struct its_collection *collection;
 	struct kvm_vcpu *vcpu;
-	struct vgic_irq *irq;
-	u32 *intids;
-	int irq_count, i;
 
 	collection = find_collection(its, coll_id);
 	if (!its_is_collection_mapped(collection))
 		return E_ITS_INVALL_UNMAPPED_COLLECTION;
 
 	vcpu = kvm_get_vcpu(kvm, collection->target_addr);
-
-	irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids);
-	if (irq_count < 0)
-		return irq_count;
-
-	for (i = 0; i < irq_count; i++) {
-		irq = vgic_get_irq(kvm, NULL, intids[i]);
-		if (!irq)
-			continue;
-		update_lpi_config(kvm, irq, vcpu, false);
-		vgic_put_irq(kvm, irq);
-	}
-
-	kfree(intids);
-
-	if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm)
-		its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe);
+	vgic_its_invall(vcpu);
 
 	return 0;
 }

arch/arm64/kvm/vgic/vgic-mmio-v2.c

@@ -73,9 +73,13 @@ static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu,
 					   gpa_t addr, unsigned int len,
 					   unsigned long val)
 {
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	u32 reg;
+
 	switch (addr & 0x0c) {
 	case GIC_DIST_IIDR:
-		if (val != vgic_mmio_read_v2_misc(vcpu, addr, len))
+		reg = vgic_mmio_read_v2_misc(vcpu, addr, len);
+		if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK)
 			return -EINVAL;
 
 		/*
@@ -87,8 +91,16 @@ static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu,
 		 * migration from old kernels to new kernels with legacy
 		 * userspace.
 		 */
-		vcpu->kvm->arch.vgic.v2_groups_user_writable = true;
-		return 0;
+		reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg);
+		switch (reg) {
+		case KVM_VGIC_IMP_REV_2:
+		case KVM_VGIC_IMP_REV_3:
+			vcpu->kvm->arch.vgic.v2_groups_user_writable = true;
+			dist->implementation_rev = reg;
+			return 0;
+		default:
+			return -EINVAL;
+		}
 	}
 
 	vgic_mmio_write_v2_misc(vcpu, addr, len, val);

arch/arm64/kvm/vgic/vgic-mmio-v3.c

@@ -155,13 +155,27 @@ static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu,
 					   unsigned long val)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	u32 reg;
 
 	switch (addr & 0x0c) {
 	case GICD_TYPER2:
-	case GICD_IIDR:
 		if (val != vgic_mmio_read_v3_misc(vcpu, addr, len))
 			return -EINVAL;
 		return 0;
+	case GICD_IIDR:
+		reg = vgic_mmio_read_v3_misc(vcpu, addr, len);
+		if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK)
+			return -EINVAL;
+
+		reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg);
+		switch (reg) {
+		case KVM_VGIC_IMP_REV_2:
+		case KVM_VGIC_IMP_REV_3:
+			dist->implementation_rev = reg;
+			return 0;
+		default:
+			return -EINVAL;
+		}
 	case GICD_CTLR:
 		/* Not a GICv4.1? No HW SGIs */
 		if (!kvm_vgic_global_state.has_gicv4_1)
@@ -221,34 +235,58 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
 	vgic_put_irq(vcpu->kvm, irq);
 }
 
+bool vgic_lpis_enabled(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	return atomic_read(&vgic_cpu->ctlr) == GICR_CTLR_ENABLE_LPIS;
+}
+
 static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu,
 					     gpa_t addr, unsigned int len)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	unsigned long val;
 
-	return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0;
-}
+	val = atomic_read(&vgic_cpu->ctlr);
+	if (vgic_get_implementation_rev(vcpu) >= KVM_VGIC_IMP_REV_3)
+		val |= GICR_CTLR_IR | GICR_CTLR_CES;
 
+	return val;
+}
 
 static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
 				     gpa_t addr, unsigned int len,
 				     unsigned long val)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	bool was_enabled = vgic_cpu->lpis_enabled;
+	u32 ctlr;
 
 	if (!vgic_has_its(vcpu->kvm))
 		return;
 
-	vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS;
+	if (!(val & GICR_CTLR_ENABLE_LPIS)) {
+		/*
+		 * Don't disable if RWP is set, as there already an
+		 * ongoing disable. Funky guest...
+		 */
+		ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr,
+					      GICR_CTLR_ENABLE_LPIS,
+					      GICR_CTLR_RWP);
+		if (ctlr != GICR_CTLR_ENABLE_LPIS)
+			return;
 
-	if (was_enabled && !vgic_cpu->lpis_enabled) {
 		vgic_flush_pending_lpis(vcpu);
 		vgic_its_invalidate_cache(vcpu->kvm);
-	}
+		atomic_set_release(&vgic_cpu->ctlr, 0);
+	} else {
+		ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr, 0,
+					      GICR_CTLR_ENABLE_LPIS);
+		if (ctlr != 0)
+			return;
 
-	if (!was_enabled && vgic_cpu->lpis_enabled)
 		vgic_enable_lpis(vcpu);
+	}
 }
 
 static bool vgic_mmio_vcpu_rdist_is_last(struct kvm_vcpu *vcpu)
@@ -478,11 +516,10 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu,
 				     unsigned long val)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	u64 old_propbaser, propbaser;
 
 	/* Storing a value with LPIs already enabled is undefined */
-	if (vgic_cpu->lpis_enabled)
+	if (vgic_lpis_enabled(vcpu))
 		return;
 
 	do {
@@ -513,7 +550,7 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
 	u64 old_pendbaser, pendbaser;
 
 	/* Storing a value with LPIs already enabled is undefined */
-	if (vgic_cpu->lpis_enabled)
+	if (vgic_lpis_enabled(vcpu))
 		return;
 
 	do {
@@ -525,6 +562,63 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
 			   pendbaser) != old_pendbaser);
 }
 
+static unsigned long vgic_mmio_read_sync(struct kvm_vcpu *vcpu,
+					 gpa_t addr, unsigned int len)
+{
+	return !!atomic_read(&vcpu->arch.vgic_cpu.syncr_busy);
+}
+
+static void vgic_set_rdist_busy(struct kvm_vcpu *vcpu, bool busy)
+{
+	if (busy) {
+		atomic_inc(&vcpu->arch.vgic_cpu.syncr_busy);
+		smp_mb__after_atomic();
+	} else {
+		smp_mb__before_atomic();
+		atomic_dec(&vcpu->arch.vgic_cpu.syncr_busy);
+	}
+}
+
+static void vgic_mmio_write_invlpi(struct kvm_vcpu *vcpu,
+				   gpa_t addr, unsigned int len,
+				   unsigned long val)
+{
+	struct vgic_irq *irq;
+
+	/*
+	 * If the guest wrote only to the upper 32bit part of the
+	 * register, drop the write on the floor, as it is only for
+	 * vPEs (which we don't support for obvious reasons).
+	 *
+	 * Also discard the access if LPIs are not enabled.
+	 */
+	if ((addr & 4) || !vgic_lpis_enabled(vcpu))
+		return;
+
+	vgic_set_rdist_busy(vcpu, true);
+
+	irq = vgic_get_irq(vcpu->kvm, NULL, lower_32_bits(val));
+	if (irq) {
+		vgic_its_inv_lpi(vcpu->kvm, irq);
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	vgic_set_rdist_busy(vcpu, false);
+}
+
+static void vgic_mmio_write_invall(struct kvm_vcpu *vcpu,
+				   gpa_t addr, unsigned int len,
+				   unsigned long val)
+{
+	/* See vgic_mmio_write_invlpi() for the early return rationale */
+	if ((addr & 4) || !vgic_lpis_enabled(vcpu))
+		return;
+
+	vgic_set_rdist_busy(vcpu, true);
+	vgic_its_invall(vcpu);
+	vgic_set_rdist_busy(vcpu, false);
+}
+
 /*
  * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the
  * redistributors, while SPIs are covered by registers in the distributor
@@ -630,6 +724,15 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
 	REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER,
 		vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_INVLPIR,
+		vgic_mmio_read_raz, vgic_mmio_write_invlpi, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_INVALLR,
+		vgic_mmio_read_raz, vgic_mmio_write_invall, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_SYNCR,
+		vgic_mmio_read_sync, vgic_mmio_write_wi, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_IDREGS,
 		vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48,
 		VGIC_ACCESS_32bit),

arch/arm64/kvm/vgic/vgic.h

@@ -98,6 +98,11 @@
 #define DEBUG_SPINLOCK_BUG_ON(p)
 #endif
 
+static inline u32 vgic_get_implementation_rev(struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm->arch.vgic.implementation_rev;
+}
+
 /* Requires the irq_lock to be held by the caller. */
 static inline bool irq_is_pending(struct vgic_irq *irq)
 {
@@ -308,6 +313,7 @@ static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size)
 		(base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE);
 }
 
+bool vgic_lpis_enabled(struct kvm_vcpu *vcpu);
 int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr);
 int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
 			 u32 devid, u32 eventid, struct vgic_irq **irq);
@@ -317,6 +323,10 @@ void vgic_lpi_translation_cache_init(struct kvm *kvm);
 void vgic_lpi_translation_cache_destroy(struct kvm *kvm);
 void vgic_its_invalidate_cache(struct kvm *kvm);
 
+/* GICv4.1 MMIO interface */
+int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq);
+int vgic_its_invall(struct kvm_vcpu *vcpu);
+
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);

include/kvm/arm_vgic.h

@@ -231,6 +231,9 @@ struct vgic_dist {
 
 	/* Implementation revision as reported in the GICD_IIDR */
 	u32			implementation_rev;
+#define KVM_VGIC_IMP_REV_2	2 /* GICv2 restorable groups */
+#define KVM_VGIC_IMP_REV_3	3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */
+#define KVM_VGIC_IMP_REV_LATEST	KVM_VGIC_IMP_REV_3
 
 	/* Userspace can write to GICv2 IGROUPR */
 	bool			v2_groups_user_writable;
@@ -344,11 +347,12 @@ struct vgic_cpu {
 	struct vgic_io_device	rd_iodev;
 	struct vgic_redist_region *rdreg;
 	u32 rdreg_index;
+	atomic_t syncr_busy;
 
 	/* Contains the attributes and gpa of the LPI pending tables. */
 	u64 pendbaser;
-
-	bool lpis_enabled;
+	/* GICR_CTLR.{ENABLE_LPIS,RWP} */
+	atomic_t ctlr;
 
 	/* Cache guest priority bits */
 	u32 num_pri_bits;