[PATCH v5 1/7] KVM: arm64: Skip cache maintenance for non-cacheable pKVM mappings

[Fuad Tabba]

From: Bradley Morgan <include at grrlz.net>

The pKVM flush path walks its own pkvm_mappings list and cleans the
data cache for every mapping, unlike the generic stage-2 walker it
shadows, which skips non-cacheable leaves. Cleaning the cacheable
alias of a non-cacheable mapping is pointless and can corrupt a
device endpoint. Record whether a mapping is non-cacheable in spare
bits of nr_pages and skip cache maintenance for it.

Fixes: e912efed485a ("KVM: arm64: Introduce the EL1 pKVM MMU")
Suggested-by: Marc Zyngier <maz at kernel.org>
Signed-off-by: Bradley Morgan <include at grrlz.net>
[tabba: use Marc's anonymous bitfield in place of the open-coded mask and helpers]
Signed-off-by: Fuad Tabba <fuad.tabba at linux.dev>
---
 arch/arm64/include/asm/kvm_pkvm.h |  5 ++++-
 arch/arm64/kvm/pkvm.c             | 15 +++++++++------
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index 74fedd9c5ff0..57afb07d6b13 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -195,7 +195,10 @@ struct pkvm_mapping {
 	struct rb_node node;
 	u64 gfn;
 	u64 pfn;
-	u64 nr_pages;
+	struct {
+		u64 nr_pages:48;
+		u64 nc:1;
+	};
 	u64 __subtree_last;	/* Internal member for interval tree */
 };
 
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 053e4f733e4b..f70c601dcf4c 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -369,7 +369,7 @@ static int __pkvm_pgtable_stage2_unshare(struct kvm_pgtable *pgt, u64 start, u64
 
 	for_each_mapping_in_range_safe(pgt, start, end, mapping) {
 		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn,
-					mapping->nr_pages);
+					(u64)mapping->nr_pages);
 		if (WARN_ON(ret))
 			return ret;
 		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
@@ -473,6 +473,7 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	mapping->gfn = gfn;
 	mapping->pfn = pfn;
 	mapping->nr_pages = size / PAGE_SIZE;
+	mapping->nc = !!(prot & (KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC));
 	pkvm_mapping_insert(mapping, &pgt->pkvm_mappings);
 
 	return ret;
@@ -503,7 +504,7 @@ int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	lockdep_assert_held(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
 		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn,
-					mapping->nr_pages);
+					(u64)mapping->nr_pages);
 		if (WARN_ON(ret))
 			break;
 	}
@@ -517,9 +518,11 @@ int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	struct pkvm_mapping *mapping;
 
 	lockdep_assert_held(&kvm->mmu_lock);
-	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
-		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn),
-					  PAGE_SIZE * mapping->nr_pages);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
+		if (!mapping->nc)
+			__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn),
+						  PAGE_SIZE * mapping->nr_pages);
+	}
 
 	return 0;
 }
@@ -537,7 +540,7 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64
 	lockdep_assert_held(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
 		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,
-					   mapping->nr_pages, mkold);
+					   (u64)mapping->nr_pages, mkold);
 
 	return young;
 }
-- 
2.39.5