Merge tag 'kvmarm-fixes-6.12-3' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 6.12, take #3

- Stop wasting space in the HYP idmap, as we are dangerously close
  to the 4kB limit, and this has already exploded in -next

- Fix another race in vgic_init()

- Fix a UBSAN error when faking the cache topology with MTE
  enabled

Author: bonzini

arch/arm64/include/asm/kvm_asm.h

@@ -178,6 +178,7 @@ struct kvm_nvhe_init_params {
 	unsigned long hcr_el2;
 	unsigned long vttbr;
 	unsigned long vtcr;
+	unsigned long tmp;
 };
 
 /*

arch/arm64/kernel/asm-offsets.c

@@ -146,6 +146,7 @@ int main(void)
   DEFINE(NVHE_INIT_HCR_EL2,	offsetof(struct kvm_nvhe_init_params, hcr_el2));
   DEFINE(NVHE_INIT_VTTBR,	offsetof(struct kvm_nvhe_init_params, vttbr));
   DEFINE(NVHE_INIT_VTCR,	offsetof(struct kvm_nvhe_init_params, vtcr));
+  DEFINE(NVHE_INIT_TMP,		offsetof(struct kvm_nvhe_init_params, tmp));
 #endif
 #ifdef CONFIG_CPU_PM
   DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));

arch/arm64/kvm/hyp/nvhe/hyp-init.S

@@ -24,28 +24,25 @@
 	.align	11
 
 SYM_CODE_START(__kvm_hyp_init)
-	ventry	__invalid		// Synchronous EL2t
-	ventry	__invalid		// IRQ EL2t
-	ventry	__invalid		// FIQ EL2t
-	ventry	__invalid		// Error EL2t
+	ventry	.			// Synchronous EL2t
+	ventry	.			// IRQ EL2t
+	ventry	.			// FIQ EL2t
+	ventry	.			// Error EL2t
 
-	ventry	__invalid		// Synchronous EL2h
-	ventry	__invalid		// IRQ EL2h
-	ventry	__invalid		// FIQ EL2h
-	ventry	__invalid		// Error EL2h
+	ventry	.			// Synchronous EL2h
+	ventry	.			// IRQ EL2h
+	ventry	.			// FIQ EL2h
+	ventry	.			// Error EL2h
 
 	ventry	__do_hyp_init		// Synchronous 64-bit EL1
-	ventry	__invalid		// IRQ 64-bit EL1
-	ventry	__invalid		// FIQ 64-bit EL1
-	ventry	__invalid		// Error 64-bit EL1
+	ventry	.			// IRQ 64-bit EL1
+	ventry	.			// FIQ 64-bit EL1
+	ventry	.			// Error 64-bit EL1
 
-	ventry	__invalid		// Synchronous 32-bit EL1
-	ventry	__invalid		// IRQ 32-bit EL1
-	ventry	__invalid		// FIQ 32-bit EL1
-	ventry	__invalid		// Error 32-bit EL1
-
-__invalid:
-	b	.
+	ventry	.			// Synchronous 32-bit EL1
+	ventry	.			// IRQ 32-bit EL1
+	ventry	.			// FIQ 32-bit EL1
+	ventry	.			// Error 32-bit EL1
 
 	/*
 	 * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers.
@@ -76,6 +73,13 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)
 
+SYM_CODE_START_LOCAL(__kvm_init_el2_state)
+	/* Initialize EL2 CPU state to sane values. */
+	init_el2_state				// Clobbers x0..x2
+	finalise_el2_state
+	ret
+SYM_CODE_END(__kvm_init_el2_state)
+
 /*
  * Initialize the hypervisor in EL2.
  *
@@ -102,9 +106,12 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
 	// TPIDR_EL2 is used to preserve x0 across the macro maze...
 	isb
 	msr	tpidr_el2, x0
-	init_el2_state
-	finalise_el2_state
+	str	lr, [x0, #NVHE_INIT_TMP]
+
+	bl	__kvm_init_el2_state
+
 	mrs	x0, tpidr_el2
+	ldr	lr, [x0, #NVHE_INIT_TMP]
 
 1:
 	ldr	x1, [x0, #NVHE_INIT_TPIDR_EL2]
@@ -199,9 +206,8 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
-	/* Initialize EL2 CPU state to sane values. */
-	init_el2_state				// Clobbers x0..x2
-	finalise_el2_state
+	bl	__kvm_init_el2_state
+
 	__init_el2_nvhe_prepare_eret
 
 	/* Enable MMU, set vectors and stack. */

arch/arm64/kvm/sys_regs.c

@@ -1994,7 +1994,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 * one cache line.
 	 */
 	if (kvm_has_mte(vcpu->kvm))
-		clidr |= 2 << CLIDR_TTYPE_SHIFT(loc);
+		clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
 
 	__vcpu_sys_reg(vcpu, r->reg) = clidr;
 

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

@@ -544,14 +544,23 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 	if (ret)
 		goto out;
 
-	dist->ready = true;
 	dist_base = dist->vgic_dist_base;
 	mutex_unlock(&kvm->arch.config_lock);
 
 	ret = vgic_register_dist_iodev(kvm, dist_base, type);
-	if (ret)
+	if (ret) {
 		kvm_err("Unable to register VGIC dist MMIO regions\n");
+		goto out_slots;
+	}
 
+	/*
+	 * kvm_io_bus_register_dev() guarantees all readers see the new MMIO
+	 * registration before returning through synchronize_srcu(), which also
+	 * implies a full memory barrier. As such, marking the distributor as
+	 * 'ready' here is guaranteed to be ordered after all vCPUs having seen
+	 * a completely configured distributor.
+	 */
+	dist->ready = true;
 	goto out_slots;
 out:
 	mutex_unlock(&kvm->arch.config_lock);

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

@@ -236,7 +236,12 @@ static int vgic_set_common_attr(struct kvm_device *dev,
 
 		mutex_lock(&dev->kvm->arch.config_lock);
 
-		if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis)
+		/*
+		 * Either userspace has already configured NR_IRQS or
+		 * the vgic has already been initialized and vgic_init()
+		 * supplied a default amount of SPIs.
+		 */
+		if (dev->kvm->arch.vgic.nr_spis)
 			ret = -EBUSY;
 		else
 			dev->kvm->arch.vgic.nr_spis =