[PATCH 19/20] KVM: arm64: Raise PKVM_HYP_REQ_SPLIT on guest to host sharing

[Vincent Donnefort]

Pages shared by the guest with the host are annotated into the guest
stage-2. If the shared page is backed by a huge mapping, we need to
split it first.

Raise a PKVM_HYP_REQ_SPLIT for the host on the guest HVC MEM_SHARE, if a
block exists (-E2BIG) and replay the HVC (by rewinding the ELR).

At the moment, the guest HVC MEM_SHARE is single-page only. This means
unsharing is ensured to find a PTE-level mapping. However as this is
most likely be extended later, raise the same PKVM_HYP_REQ_SPLIT on the
guest HVC MEM_UNSHARE.

Signed-off-by: Vincent Donnefort <vdonnefort at google.com>

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 3b8e95b83bf4..57f4303aede1 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -1082,16 +1082,34 @@ static u64 __pkvm_memshare_page_req(struct kvm_vcpu *vcpu, u64 ipa)
 	return ARM_EXCEPTION_TRAP;
 }
 
+static u64 pkvm_request_split(struct pkvm_hyp_vcpu *hyp_vcpu, u64 gfn, u64 nr_pages)
+{
+	struct pkvm_hyp_req *req = &hyp_vcpu->host_vcpu->arch.pkvm_hyp_req;
+	u64 elr;
+
+	req->type = PKVM_HYP_REQ_SPLIT;
+	req->split.gfn = gfn;
+	req->split.nr_pages = nr_pages;
+
+	/* Rewind the ELR so we return to the HVC once the block is split */
+	elr = read_sysreg(elr_el2);
+	elr -= 4;
+	write_sysreg(elr, elr_el2);
+
+	return ARM_EXCEPTION_PKVM_HYP_REQ;
+}
+
 static bool pkvm_memshare_call(u64 *ret, struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct pkvm_hyp_vcpu *hyp_vcpu;
 	u64 ipa = smccc_get_arg1(vcpu);
+	u64 gfn = hyp_phys_to_pfn(ipa);
 
 	if (!PAGE_ALIGNED(ipa))
 		goto out_guest;
 
 	hyp_vcpu = container_of(vcpu, struct pkvm_hyp_vcpu, vcpu);
-	switch (__pkvm_guest_share_host(hyp_vcpu, hyp_phys_to_pfn(ipa), 1)) {
+	switch (__pkvm_guest_share_host(hyp_vcpu, gfn, 1)) {
 	case 0:
 		ret[0] = SMCCC_RET_SUCCESS;
 		goto out_guest;
@@ -1102,6 +1120,9 @@ static bool pkvm_memshare_call(u64 *ret, struct kvm_vcpu *vcpu, u64 *exit_code)
 		 */
 		*exit_code = __pkvm_memshare_page_req(vcpu, ipa);
 		goto out_host;
+	case -E2BIG:
+		*exit_code = pkvm_request_split(hyp_vcpu, gfn, 1);
+		goto out_host;
 	}
 
 out_guest:
@@ -1110,17 +1131,29 @@ static bool pkvm_memshare_call(u64 *ret, struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
-static void pkvm_memunshare_call(u64 *ret, struct kvm_vcpu *vcpu)
+static bool pkvm_memunshare_call(u64 *ret, struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct pkvm_hyp_vcpu *hyp_vcpu;
 	u64 ipa = smccc_get_arg1(vcpu);
+	u64 gfn = hyp_phys_to_pfn(ipa);
 
 	if (!PAGE_ALIGNED(ipa))
-		return;
+		goto out_guest;
 
 	hyp_vcpu = container_of(vcpu, struct pkvm_hyp_vcpu, vcpu);
-	if (!__pkvm_guest_unshare_host(hyp_vcpu, hyp_phys_to_pfn(ipa), 1))
+	switch (__pkvm_guest_unshare_host(hyp_vcpu, gfn, 1)) {
+	case 0:
 		ret[0] = SMCCC_RET_SUCCESS;
+		goto out_guest;
+	case -E2BIG:
+		*exit_code = pkvm_request_split(hyp_vcpu, gfn, 1);
+		goto out_host;
+	}
+
+out_guest:
+	return true;
+out_host:
+	return false;
 }
 
 /*
@@ -1165,7 +1198,7 @@ bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code)
 			break;
 		}
 
-		pkvm_memunshare_call(val, vcpu);
+		handled = pkvm_memunshare_call(val, vcpu, exit_code);
 		break;
 	default:
 		/* Punt everything else back to the host, for now. */
-- 
2.55.0.508.g3f0d502094-goog