[PATCH v6 04/10] KVM: arm64: Add a range to __pkvm_host_unshare_guest()

From: Vincent Donnefort <hidden>
Date: 2025-05-21 12:51:12
Also in: kvmarm, lkml
Subsystem: arm64 port (aarch64 architecture), kernel virtual machine for arm64 (kvm/arm64), the rest · Maintainers: Catalin Marinas, Will Deacon, Marc Zyngier, Oliver Upton, Linus Torvalds

In preparation for supporting stage-2 huge mappings for np-guest. Add a
nr_pages argument to the __pkvm_host_unshare_guest hypercall. This range
supports only two values: 1 or PMD_SIZE / PAGE_SIZE (that is 512 on a
4K-pages system).

Signed-off-by: Vincent Donnefort <redacted>

diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 47aa7b01114f..19671edbe18f 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h

@@ -41,7 +41,7 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
 			    enum kvm_pgtable_prot prot);
-int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
+int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm);
 int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
 int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
 int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm);

diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 4d3d215955c3..5c03bd1db873 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -270,6 +270,7 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
 	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	DECLARE_REG(u64, nr_pages, host_ctxt, 3);
 	struct pkvm_hyp_vm *hyp_vm;
 	int ret = -EINVAL;

@@ -280,7 +281,7 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
 	if (!hyp_vm)
 		goto out;
 
-	ret = __pkvm_host_unshare_guest(gfn, hyp_vm);
+	ret = __pkvm_host_unshare_guest(gfn, nr_pages, hyp_vm);
 	put_pkvm_hyp_vm(hyp_vm);
 out:
 	cpu_reg(host_ctxt, 1) =  ret;

diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 8051235ea194..2703bce3b773 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -980,10 +980,9 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu
 	return ret;
 }
 
-static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)
+static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa, u64 size)
 {
 	enum pkvm_page_state state;
-	struct hyp_page *page;
 	kvm_pte_t pte;
 	u64 phys;
 	s8 level;

@@ -994,7 +993,7 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
 		return ret;
 	if (!kvm_pte_valid(pte))
 		return -ENOENT;
-	if (level != KVM_PGTABLE_LAST_LEVEL)
+	if (kvm_granule_size(level) != size)
 		return -E2BIG;
 
 	state = guest_get_page_state(pte, ipa);

@@ -1002,43 +1001,49 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
 		return -EPERM;
 
 	phys = kvm_pte_to_phys(pte);
-	ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
+	ret = check_range_allowed_memory(phys, phys + size);
 	if (WARN_ON(ret))
 		return ret;
 
-	page = hyp_phys_to_page(phys);
-	if (get_host_state(page) != PKVM_PAGE_SHARED_OWNED)
-		return -EPERM;
-	if (WARN_ON(!page->host_share_guest_count))
-		return -EINVAL;
+	for_each_hyp_page(page, phys, size) {
+		if (get_host_state(page) != PKVM_PAGE_SHARED_OWNED)
+			return -EPERM;
+		if (WARN_ON(!page->host_share_guest_count))
+			return -EINVAL;
+	}
 
 	*__phys = phys;
 
 	return 0;
 }
 
-int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm)
+int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm)
 {
 	u64 ipa = hyp_pfn_to_phys(gfn);
-	struct hyp_page *page;
-	u64 phys;
+	u64 size, phys;
 	int ret;
 
+	ret = __guest_check_transition_size(0, ipa, nr_pages, &size);
+	if (ret)
+		return ret;
+
 	host_lock_component();
 	guest_lock_component(vm);
 
-	ret = __check_host_shared_guest(vm, &phys, ipa);
+	ret = __check_host_shared_guest(vm, &phys, ipa, size);
 	if (ret)
 		goto unlock;
 
-	ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE);
+	ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, size);
 	if (ret)
 		goto unlock;
 
-	page = hyp_phys_to_page(phys);
-	page->host_share_guest_count--;
-	if (!page->host_share_guest_count)
-		WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED));
+	for_each_hyp_page(page, phys, size) {
+		/* __check_host_shared_guest() protects against underflow */
+		page->host_share_guest_count--;
+		if (!page->host_share_guest_count)
+			set_host_state(page, PKVM_PAGE_OWNED);
+	}
 
 unlock:
 	guest_unlock_component(vm);

@@ -1058,7 +1063,7 @@ static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa)
 	host_lock_component();
 	guest_lock_component(vm);
 
-	ret = __check_host_shared_guest(vm, &phys, ipa);
+	ret = __check_host_shared_guest(vm, &phys, ipa, PAGE_SIZE);
 
 	guest_unlock_component(vm);
 	host_unlock_component();

@@ -1245,7 +1250,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);
 	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
-	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
 
 	selftest_state.host = PKVM_PAGE_OWNED;
 	selftest_state.hyp = PKVM_NOPAGE;

@@ -1253,7 +1258,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
 	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);
-	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
 	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
 
 	selftest_state.host = PKVM_PAGE_SHARED_OWNED;

@@ -1264,7 +1269,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
-	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
 
 	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);
 	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);

@@ -1276,7 +1281,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
-	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
 
 	hyp_unpin_shared_mem(virt, virt + size);
 	assert_page_state();

@@ -1295,7 +1300,7 @@ void pkvm_ownership_selftest(void *base)
 	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
 	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
 	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
-	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
 	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
 
 	selftest_state.host = PKVM_PAGE_OWNED;

@@ -1319,11 +1324,11 @@ void pkvm_ownership_selftest(void *base)
 	WARN_ON(hyp_virt_to_page(virt)->host_share_guest_count != 2);
 
 	selftest_state.guest[0] = PKVM_NOPAGE;
-	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn, 1, vm);
 
 	selftest_state.guest[1] = PKVM_NOPAGE;
 	selftest_state.host = PKVM_PAGE_OWNED;
-	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn + 1, vm);
+	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn + 1, 1, vm);
 
 	selftest_state.host = PKVM_NOPAGE;
 	selftest_state.hyp = PKVM_PAGE_OWNED;

diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 0285e2cd2e7f..f77c5157a8d7 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c

@@ -371,7 +371,7 @@ int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
-		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
+		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn, 1);
 		if (WARN_ON(ret))
 			break;
 		rb_erase(&mapping->node, &pgt->pkvm_mappings);

-- 
2.49.0.1112.g889b7c5bd8-goog

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help