[PATCH 12/20] KVM: arm64: Handle huge mappings in __pkvm_host_force_reclaim_page_guest()

In preparation for supporting stage-2 huge mappings for protected VMs, allow
__pkvm_host_force_reclaim_page_guest() to work with PMD_SIZE mappings.
As this HVC is called from a non-preemptible context, it is not possible
to rely on the host pkvm_mappings tree to get the mapping size. Instead,
use the actual host stage-2 mapping size and compare it with the guest
stage-2.

Signed-off-by: Vincent Donnefort <[email protected]>

diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index d5ee079a5d70..47c5c6b4869e 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -1292,11 +1292,9 @@ static int __guest_check_transition_size(u64 phys, u64 ipa, u64 nr_pages, u64 *s
 	return 0;
 }
 
-static void hyp_poison_page(phys_addr_t phys)
+static void __hyp_poison_page(void *addr, size_t size)
 {
-	void *addr = hyp_fixmap_map(phys);
-
-	memset(addr, 0, PAGE_SIZE);
+	memset(addr, 0, size);
 	/*
 	 * Prefer kvm_flush_dcache_to_poc() over __clean_dcache_guest_page()
 	 * here as the latter may elide the CMO under the assumption that FWB
@@ -1304,19 +1302,15 @@ static void hyp_poison_page(phys_addr_t phys)
 	 * host stage-2 and would otherwise lead to a malicious host potentially
 	 * being able to read the contents of newly reclaimed guest pages.
 	 */
-	kvm_flush_dcache_to_poc(addr, PAGE_SIZE);
-	hyp_fixmap_unmap();
+	kvm_flush_dcache_to_poc(addr, size);
 }
 
 static void hyp_poison_range(phys_addr_t phys, u64 size)
 {
-	u64 offset;
-
-	for (offset = 0; offset < size; offset += PAGE_SIZE)
-		hyp_poison_page(phys + offset);
+	__apply_guest_page(__hyp_va(phys), size, __hyp_poison_page);
 }
 
-static int host_stage2_get_guest_info(phys_addr_t phys, struct pkvm_hyp_vm **vm,
+static int host_stage2_get_guest_info(phys_addr_t phys, u64 *size, struct pkvm_hyp_vm **vm,
 				      u64 *gfn)
 {
 	enum pkvm_page_state state;
@@ -1344,34 +1338,43 @@ static int host_stage2_get_guest_info(phys_addr_t phys, struct pkvm_hyp_vm **vm,
 	if (ret)
 		return ret;
 
-	if (WARN_ON(level != KVM_PGTABLE_LAST_LEVEL))
-		return -EINVAL;
+	/* We only support either PAGE_SIZE or PMD_SIZE */
+	if (level < KVM_PGTABLE_LAST_LEVEL - 1)
+		return -E2BIG;
 
-	return host_stage2_decode_gfn_meta(pte, vm, gfn);
+	ret = host_stage2_decode_gfn_meta(pte, vm, gfn);
+	if (ret)
+		return ret;
+
+	*size = kvm_granule_size(level);
+
+	return 0;
 }
 
 int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys)
 {
+	u64 gfn, ipa, pa, size;
 	struct pkvm_hyp_vm *vm;
-	u64 gfn, ipa, pa;
 	kvm_pte_t pte;
 	int ret;
 
-	phys &= PAGE_MASK;
-
 	hyp_spin_lock(&vm_table_lock);
 	host_lock_component();
 
-	ret = host_stage2_get_guest_info(phys, &vm, &gfn);
+	ret = host_stage2_get_guest_info(phys, &size, &vm, &gfn);
 	if (ret)
 		goto unlock_host;
 
 	ipa = hyp_pfn_to_phys(gfn);
+
 	guest_lock_component(vm);
-	ret = get_valid_guest_pte(vm, ipa, PAGE_SIZE, &pte, &pa);
+	ret = get_valid_guest_pte(vm, ipa, size, &pte, &pa);
 	if (ret)
 		goto unlock_guest;
 
+	phys = ALIGN_DOWN(phys, size);
+	pa = ALIGN_DOWN(pa, size);
+
 	WARN_ON(pa != phys);
 	if (guest_get_page_state(pte, ipa) != PKVM_PAGE_OWNED) {
 		ret = -EPERM;
@@ -1379,14 +1382,14 @@ int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys)
 	}
 
 	/* We really shouldn't be allocating, so don't pass a memcache */
-	ret = kvm_pgtable_stage2_annotate(&vm->pgt, ipa, PAGE_SIZE, NULL,
+	ret = kvm_pgtable_stage2_annotate(&vm->pgt, ipa, size, NULL,
 					  KVM_GUEST_INVALID_PTE_TYPE_POISONED,
 					  0);
 	if (ret)
 		goto unlock_guest;
 
-	hyp_poison_page(phys);
-	WARN_ON(host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HOST));
+	hyp_poison_range(phys, size);
+	WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HOST));
 unlock_guest:
 	guest_unlock_component(vm);
 unlock_host:
-- 
2.55.0.508.g3f0d502094-goog