linux-kernel - [PATCH 7/9] KVM: arm64: Add range to pkvm

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250228102530.1229089-13-vdonnefort@google.com>
Date: Fri, 28 Feb 2025 10:25:28 +0000
From: Vincent Donnefort <vdonnefort@...gle.com>
To: maz@...nel.org, oliver.upton@...ux.dev, joey.gouly@....com, 
	suzuki.poulose@....com, yuzenghui@...wei.com, catalin.marinas@....com, 
	will@...nel.org
Cc: qperret@...gle.com, linux-arm-kernel@...ts.infradead.org, 
	kvmarm@...ts.linux.dev, linux-kernel@...r.kernel.org, kernel-team@...roid.com, 
	Vincent Donnefort <vdonnefort@...gle.com>
Subject: [PATCH 7/9] KVM: arm64: Add range to pkvm_mappings

From: Quentin Perret <qperret@...gle.com>

In preparation for supporting stage-2 huge mappings for np-guest, add a
nr_pages member for pkvm_mappings to allow EL1 to track the size of the
stage-2 mapping.

Signed-off-by: Quentin Perret <qperret@...gle.com>
Signed-off-by: Vincent Donnefort <vdonnefort@...gle.com>

diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index f0d52efb858e..0e944a754b96 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -166,6 +166,7 @@ struct pkvm_mapping {
 	struct rb_node node;
 	u64 gfn;
 	u64 pfn;
+	u64 nr_pages;
 	u64 __subtree_last;	/* Internal member for interval tree */
 };
 
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index da637c565ac9..9c9833f27fe3 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -278,7 +278,7 @@ static u64 __pkvm_mapping_start(struct pkvm_mapping *m)
 
 static u64 __pkvm_mapping_end(struct pkvm_mapping *m)
 {
-	return (m->gfn + 1) * PAGE_SIZE - 1;
+	return (m->gfn + m->nr_pages) * PAGE_SIZE - 1;
 }
 
 INTERVAL_TREE_DEFINE(struct pkvm_mapping, node, u64, __subtree_last,
@@ -315,7 +315,8 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e
 		return 0;
 
 	for_each_mapping_in_range_safe(pgt, start, end, mapping) {
-		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn, 1);
+		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn,
+					mapping->nr_pages);
 		if (WARN_ON(ret))
 			return ret;
 		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
@@ -345,16 +346,32 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		return -EINVAL;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
-	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, 1, prot);
-	if (ret) {
-		/* Is the gfn already mapped due to a racing vCPU? */
-		if (ret == -EPERM)
+
+	/*
+	 * Calling stage2_map() on top of existing mappings is either happening because of a race
+	 * with another vCPU, or because we're changing between page and block mappings. As per
+	 * user_mem_abort(), same-size permission faults are handled in the relax_perms() path.
+	 */
+	mapping = pkvm_mapping_iter_first(&pgt->pkvm_mappings, addr, addr + size - 1);
+	if (mapping) {
+		if (size == (mapping->nr_pages * PAGE_SIZE))
 			return -EAGAIN;
+
+		/* Remove _any_ pkvm_mapping overlapping with the range, bigger or smaller. */
+		ret = __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+		if (ret)
+			return ret;
+		mapping = NULL;
 	}
 
+	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, size / PAGE_SIZE, prot);
+	if (WARN_ON(ret))
+		return ret;
+
 	swap(mapping, cache->mapping);
 	mapping->gfn = gfn;
 	mapping->pfn = pfn;
+	mapping->nr_pages = size / PAGE_SIZE;
 	pkvm_mapping_insert(mapping, &pgt->pkvm_mappings);
 
 	return ret;
@@ -376,7 +393,8 @@ 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, 1);
+		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn,
+					mapping->nr_pages);
 		if (WARN_ON(ret))
 			break;
 	}
@@ -391,7 +409,8 @@ int pkvm_pgtable_stage2_flush(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)
-		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE);
+		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn),
+					  PAGE_SIZE * mapping->nr_pages);
 
 	return 0;
 }
@@ -406,7 +425,7 @@ 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,
-					   1, mkold);
+					   mapping->nr_pages, mkold);
 
 	return young;
 }
-- 
2.48.1.711.g2feabab25a-goog