[GIT PULL v1 07/17] KVM: s390: Add capability to support 2G hugepages

[Claudio Imbrenda <imbrenda@linux.ibm.com>]

Add KVM_CAP_S390_HPAGE_2G to signal to userspace that 2G hugepages may
be used to back the guest; restrictions apply similar to 1M hugepages.

Enable the (for now still ignored) GMAP_FLAG_ALLOW_HPAGE_2G flag for
the guest gmap, and propagate / disable it as necessary.

Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Message-ID: <20260609150930.665370-3-imbrenda@linux.ibm.com>
---
 arch/s390/kvm/gmap.c     |  5 +++++
 arch/s390/kvm/kvm-s390.c | 26 ++++++++++++++++++++++++++
 arch/s390/kvm/pv.c       |  5 ++++-
 include/uapi/linux/kvm.h |  1 +
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index fe138d17caaf..f8bd6c135e3c 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -105,6 +105,11 @@ static void gmap_add_child(struct gmap *parent, struct gmap *child)
 	else
 		clear_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &child->flags);
 
+	if (test_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &parent->flags))
+		set_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &child->flags);
+	else
+		clear_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &child->flags);
+
 	if (kvm_is_ucontrol(parent->kvm))
 		clear_bit(GMAP_FLAG_OWNS_PAGETABLES, &child->flags);
 	list_add(&child->list, &parent->children);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index abc7941d7bb4..6de36421548c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -646,6 +646,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		if (hpage && !(kvm && kvm_is_ucontrol(kvm)))
 			r = 1;
 		break;
+	case KVM_CAP_S390_HPAGE_2G:
+		r = 0;
+		if (hpage_2g && !(kvm && kvm_is_ucontrol(kvm)))
+			r = 1;
+		break;
 	case KVM_CAP_S390_MEM_OP:
 		r = MEM_OP_MAX_SIZE;
 		break;
@@ -902,6 +907,27 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_HPAGE_2G:
+		mutex_lock(&kvm->lock);
+		if (kvm->created_vcpus) {
+			r = -EBUSY;
+		} else if (!hpage_2g || kvm->arch.use_cmma || kvm_is_ucontrol(kvm)) {
+			r = -EINVAL;
+		} else {
+			r = 0;
+			set_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &kvm->arch.gmap->flags);
+			/*
+			 * We might have to create fake 4k page
+			 * tables. To avoid that the hardware works on
+			 * stale PGSTEs, we emulate these instructions.
+			 */
+			kvm->arch.use_skf = 0;
+			kvm->arch.use_pfmfi = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE_2G %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	case KVM_CAP_S390_USER_STSI:
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index c2dafd812a3b..b9a23df96f7d 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -721,7 +721,10 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	uvcb.flags.ap_allow_instr = kvm->arch.model.uv_feat_guest.ap;
 	uvcb.flags.ap_instr_intr = kvm->arch.model.uv_feat_guest.ap_intr;
 
-	clear_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &kvm->arch.gmap->flags);
+	scoped_guard(write_lock, &kvm->mmu_lock) {
+		clear_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &kvm->arch.gmap->flags);
+		clear_bit(GMAP_FLAG_ALLOW_HPAGE_2G, &kvm->arch.gmap->flags);
+	}
 	gmap_split_huge_pages(kvm->arch.gmap);
 
 	cc = uv_call_sched(0, (u64)&uvcb);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6c8afa2047bf..419011097fa8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -996,6 +996,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_S390_USER_OPEREXEC 246
 #define KVM_CAP_S390_KEYOP 247
 #define KVM_CAP_S390_VSIE_ESAMODE 248
+#define KVM_CAP_S390_HPAGE_2G 249
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
-- 
2.54.0