Merge branch 'kvm-arm64/misc-7.3' into next

* kvm-arm64/misc-7.3:
  : Miscellaneous fixes for KVM/arm64, 7.3
  :
  :  - Fixes for saving invalid table entries as part of saving the ITS
  :    tables (Fuad Tabba)
  :
  :  - Don't reallocate the SPI array for re-attempted vgic_init(), avoiding
  :    a memory leak (Fuad Tabba)
  :
  :  - Hold a reference on an LPI when saving the pending state (Qihang)
  :
  :  - Don't WARN for out-of-range, guest-supplied INTID (Karl)
  :
  :  - Avoid corrupting GPRs for 32-bit CP64 reads (Karl)
  :
  :  - Reset 'in kernel' VGIC state when private IRQ allocation fails (Fuad)
  :
  :  - Avoid kallsyms lookup in nVHE panic unless the host stage-2 is also
  :    disabled (Vincent)
  :
  :  - Disregard Pending+Active state when computing maintenance IRQ for
  :    ICH_MISR_EL2.NP (Kajetan)
  :
  :  - Various Sashiko-identified issues dealing with GICv5 (Sascha)
  :
  :  - Fix CPU onlining in pKVM due to mismatched accesses when the MMU is
  :    disabled (Will)
  KVM: arm64: Validate GICv5 timer PPIs before claiming ownership
  KVM: arm64: vgic: Reject out-of-range GICv5 PPI IDs
  KVM: arm64: vgic: Prevent speculative SPI array underflow
  KVM: arm64: vgic: Free gic_kvm_info on initialization failure
  KVM: arm64: Avoid mismatched accesses to 'struct kvm_nvhe_init_params'
  KVM: arm64: vgic: Fix detection of MI on no pending LR
  KVM: arm64: Drop %pB on nVHE panic when stage-2 is active
  KVM: arm64: vgic: Reset in_kernel on private IRQ allocation failure
  KVM: arm64: GICv2: Don't WARN on out-of-range GICV_DIR INTID
  KVM: arm64: Preserve GPRs for AArch32 CP64 reads generating an UNDEF
  KVM: arm64: vgic-v3: take an LPI reference in vgic_v3_save_pending_tables
  KVM: arm64: vgic-its: Point saved ITEs at the next valid entry
  KVM: arm64: vgic-its: Don't save collections the table cannot hold
  KVM: arm64: vgic: Don't leak the SPI array when init is retried
  KVM: arm64: vgic-its: Don't dereference a NULL collection on ITT save

Signed-off-by: Oliver Upton <oupton@kernel.org>

13 files changed, 70 insertions, 31 deletions

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index c686fee9767a..e5b92ac09e69 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -215,7 +215,6 @@ struct kvm_nvhe_init_params {
 	unsigned long hcr_el2;
 	unsigned long vttbr;
 	unsigned long vtcr;
-	unsigned long tmp;
 };
 
 /*
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index b6367ff3a49c..9c853ed3ceab 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -124,7 +124,6 @@ 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));
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index db60facad9f3..6ac3321f4c57 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1535,13 +1535,14 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
 
 		ctx = vcpu_get_timer(vcpu, i);
 		irq = timer_irq(ctx);
-		if (kvm_vgic_set_owner(vcpu, irq, ctx))
-			break;
 
 		/* With GICv5, the default PPI is what you get -- nothing else */
 		if (vgic_is_v5(vcpu->kvm) && irq != get_vgic_ppi(vcpu->kvm, default_ppi[i]))
 			break;
 
+		if (kvm_vgic_set_owner(vcpu, irq, ctx))
+			break;
+
 		/*
 		 * We know by construction that we only have PPIs, so all values
 		 * are less than 32 for non-GICv5 VGICs. On GICv5, they are
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 29108e5c0206..db37678dcb05 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -530,10 +530,20 @@ void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
 		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
 }
 
+static bool nvhe_hyp_panic_host_s2_disabled(void)
+{
+	return !is_protected_kvm_enabled() ||
+	       IS_ENABLED(CONFIG_PKVM_DISABLE_STAGE2_ON_PANIC);
+}
+
 static void print_nvhe_hyp_panic(const char *name, u64 panic_addr)
 {
-	kvm_err("nVHE hyp %s at: [<%016llx>] %pB!\n", name, panic_addr,
-		(void *)(panic_addr + kaslr_offset()));
+	/* Kallsyms might not be mapped in the host stage-2 */
+	if (nvhe_hyp_panic_host_s2_disabled())
+		kvm_err("nVHE hyp %s at: [<%016llx>] %pB!\n", name, panic_addr,
+			(void *)(panic_addr + kaslr_offset()));
+	else
+		kvm_err("nVHE hyp %s at: %016llx!\n", name, panic_addr);
 }
 
 static void kvm_nvhe_report_cfi_failure(u64 panic_addr)
@@ -561,8 +571,7 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 		unsigned int line = 0;
 
 		/* All hyp bugs, including warnings, are treated as fatal. */
-		if (!is_protected_kvm_enabled() ||
-		    IS_ENABLED(CONFIG_PKVM_DISABLE_STAGE2_ON_PANIC)) {
+		if (nvhe_hyp_panic_host_s2_disabled()) {
 			struct bug_entry *bug = find_bug(elr_in_kimg);
 
 			if (bug)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 89cb553be1e5..0b3e0b28dfc7 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -106,16 +106,19 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
 	and	x2, x1, x2
 	cbz	x2, 1f
 
-	// hVHE: Replay the EL2 setup to account for the E2H bit
-	// TPIDR_EL2 is used to preserve x0 across the macro maze...
+	/*
+	 * hVHE: Replay the EL2 setup to account for the E2H bit
+	 * TPIDR_EL2 and FAR_EL2 are used to preserve x0 and LR across
+	 * the macro maze...
+	 */
 	isb
 	msr	tpidr_el2, x0
-	str	lr, [x0, #NVHE_INIT_TMP]
+	msr	far_el2, lr
 
 	bl	__kvm_init_el2_state
 
+	mrs	lr, far_el2
 	mrs	x0, tpidr_el2
-	ldr	lr, [x0, #NVHE_INIT_TMP]
 
 1:
 	ldr	x1, [x0, #NVHE_INIT_TPIDR_EL2]
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 75a84761e69c..44aae52c473d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -4969,10 +4969,8 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	 * Make a 64-bit value out of Rt and Rt2. As we use the same trap
 	 * backends between AArch32 and AArch64, we get away with it.
 	 */
-	if (params.is_write) {
-		params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
-		params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
-	}
+	params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
+	params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
 
 	/*
 	 * If the table contains a handler, handle the
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 907057881b26..4012df6002ea 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -176,6 +176,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 		}
 
 		kvm->arch.vgic.vgic_model = 0;
+		kvm->arch.vgic.in_kernel = false;
 		goto out_unlock;
 	}
 
@@ -210,6 +211,9 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
 	int i;
 
+	if (dist->spis)
+		return 0;
+
 	dist->active_spis = (atomic_t)ATOMIC_INIT(0);
 	dist->spis = kzalloc_objs(struct vgic_irq, nr_spis, GFP_KERNEL_ACCOUNT);
 	if (!dist->spis)
@@ -787,7 +791,8 @@ int kvm_vgic_hyp_init(void)
 
 	if (has_mask && !gic_kvm_info->maint_irq) {
 		kvm_err("No vgic maintenance irq\n");
-		return -ENXIO;
+		ret = -ENXIO;
+		goto out_free;
 	}
 
 	/*
@@ -820,6 +825,7 @@ int kvm_vgic_hyp_init(void)
 
 	kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq;
 
+out_free:
 	kfree(gic_kvm_info);
 	gic_kvm_info = NULL;
 
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 740b39875728..f6538b1976f9 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -2026,15 +2026,16 @@ static u32 compute_next_devid_offset(struct list_head *h,
 
 static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite)
 {
-	struct its_ite *next;
-	u32 next_offset;
+	struct its_ite *next = ite;
 
-	if (list_is_last(&ite->ite_list, h))
-		return 0;
-	next = list_next_entry(ite, ite_list);
-	next_offset = next->event_id - ite->event_id;
+	/* Point at the next ITE that vgic_its_save_ite() stores as valid. */
+	list_for_each_entry_continue(next, h, ite_list) {
+		if (next->collection)
+			return min_t(u32, next->event_id - ite->event_id,
+				     VITS_ITE_MAX_EVENTID_OFFSET);
+	}
 
-	return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET);
+	return 0;
 }
 
 /**
@@ -2110,6 +2111,14 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
 	u32 next_offset;
 	u64 val;
 
+	/*
+	 * MAPC with V=0 keeps the ITEs mapped but drops their collection,
+	 * and with it the ICID. Save a zeroed entry, which the restore path
+	 * reads back as invalid.
+	 */
+	if (!ite->collection)
+		return vgic_its_write_entry_lock(its, gpa, 0ULL, ite);
+
 	next_offset = compute_next_eventid_offset(&dev->itt_head, ite);
 	val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) |
 	       ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) |
@@ -2523,6 +2532,9 @@ static int vgic_its_save_collection_table(struct vgic_its *its)
 	max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
 
 	list_for_each_entry(collection, &its->collection_list, coll_list) {
+		if (!vgic_its_check_id(its, baser, collection->collection_id, NULL))
+			return -EINVAL;
+
 		ret = vgic_its_save_cte(its, collection, gpa);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
index cafa3cb32bda..7182f63fc938 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -170,8 +170,9 @@ void vgic_v2_deactivate(struct kvm_vcpu *vcpu, u32 val)
 	/* Make sure we're in the same context as LR handling */
 	local_irq_save(flags);
 
+	/* Guest-supplied INTID: out of range yields no irq, so ignore it */
 	irq = vgic_get_vcpu_irq(vcpu, val);
-	if (WARN_ON_ONCE(!irq))
+	if (!irq)
 		goto out;
 
 	/* See the corresponding v3 code for the rationale */
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 5c69fa615823..e3e84d7f5ad5 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -152,7 +152,7 @@ static void vgic_compute_mi_state(struct kvm_vcpu *vcpu, struct mi_state *mi_sta
 			eisr |= BIT(i);
 		if (!(lr & ICH_LR_STATE))
 			elrsr |= BIT(i);
-		pend |= (lr & ICH_LR_PENDING_BIT);
+		pend |= (lr & ICH_LR_STATE) == ICH_LR_PENDING_BIT;
 	}
 
 	mi_state->eisr	= eisr;
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 91514d6faf74..963b5044490b 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -611,9 +611,13 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		bool is_pending;
 		bool stored;
 
+		irq = vgic_get_irq(kvm, index);
+		if (!irq)
+			continue;
+
 		vcpu = irq->target_vcpu;
 		if (!vcpu)
-			continue;
+			goto put_irq;
 
 		pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
 
@@ -624,7 +628,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		if (ptr != last_ptr) {
 			ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 			if (ret)
-				goto out;
+				goto put_irq;
 			last_ptr = ptr;
 		}
 
@@ -636,7 +640,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 			vgic_v4_get_vlpi_state(irq, &is_pending);
 
 		if (stored == is_pending)
-			continue;
+			goto put_irq;
 
 		if (is_pending)
 			val |= 1 << bit_nr;
@@ -644,6 +648,8 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 			val &= ~(1 << bit_nr);
 
 		ret = vgic_write_guest_lock(kvm, ptr, &val, 1);
+put_irq:
+		vgic_put_irq(kvm, irq);
 		if (ret)
 			goto out;
 	}
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index ccb7e3a90cd0..faae11e713e3 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -93,8 +93,9 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, u32 intid)
 	/* SPIs */
 	if (intid >= VGIC_NR_PRIVATE_IRQS &&
 	    intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) {
-		intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS);
-		return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
+		intid -= VGIC_NR_PRIVATE_IRQS;
+		intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis);
+		return &kvm->arch.vgic.spis[intid];
 	}
 
 	/* LPIs */
@@ -117,6 +118,8 @@ struct vgic_irq *vgic_get_vcpu_irq(struct kvm_vcpu *vcpu, u32 intid)
 		switch (type) {
 		case KVM_DEV_TYPE_ARM_VGIC_V5:
 			intid = vgic_v5_get_hwirq_id(intid);
+			if (intid >= VGIC_V5_NR_PRIVATE_IRQS)
+				return NULL;
 			intid = array_index_nospec(intid, VGIC_V5_NR_PRIVATE_IRQS);
 			break;
 		default:
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index bd1bb03500b3..40a12bfc98c9 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -65,6 +65,8 @@
 		switch (t) {						\
 		case KVM_DEV_TYPE_ARM_VGIC_V5:				\
 			__ret = is_v5_type(GICV5_HWIRQ_TYPE_PPI, (i));	\
+			__ret &= FIELD_GET(GICV5_HWIRQ_ID, (i)) <	\
+				 VGIC_V5_NR_PRIVATE_IRQS;		\
 			break;						\
 		default:						\
 			__ret  = (i) >= VGIC_NR_SGIS;			\