Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   David Stevens <stevensd@chromium.org>
To:     Marc Zyngier <maz@kernel.org>,
        Sean Christopherson <seanjc@google.com>
Cc:     Oliver Upton <oliver.upton@linux.dev>,
        Paolo Bonzini <pbonzini@redhat.com>,
        linux-arm-kernel@lists.infradead.org, kvmarm@lists.cs.columbia.edu,
        linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
        David Stevens <stevensd@chromium.org>
Subject: [PATCH v6 3/4] KVM: arm64/mmu: use gfn_to_pfn_noref
Date:   Thu, 30 Mar 2023 17:58:01 +0900
Message-Id: <20230330085802.2414466-4-stevensd@google.com>
In-Reply-To: <20230330085802.2414466-1-stevensd@google.com>
References: <20230330085802.2414466-1-stevensd@google.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: David Stevens <stevensd@chromium.org>

Switch the arm64 mmu to the new gfn_to_pfn_noref functions. This allows
IO and PFNMAP mappings backed with valid struct pages but without
refcounting (e.g. tail pages of non-compound higher order allocations)
to be mapped into the guest.

Signed-off-by: David Stevens <stevensd@chromium.org>
---
 arch/arm64/kvm/mmu.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 7113587222ff..0fd726e82a19 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1082,7 +1082,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
 static unsigned long
 transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			    unsigned long hva, kvm_pfn_t *pfnp,
-			    phys_addr_t *ipap)
+			    struct page **page, phys_addr_t *ipap)
 {
 	kvm_pfn_t pfn = *pfnp;
 
@@ -1091,7 +1091,8 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	 * sure that the HVA and IPA are sufficiently aligned and that the
 	 * block map is contained within the memslot.
 	 */
-	if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
+	if (*page &&
+	    fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
 	    get_user_mapping_size(kvm, hva) >= PMD_SIZE) {
 		/*
 		 * The address we faulted on is backed by a transparent huge
@@ -1112,10 +1113,11 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		 * page accordingly.
 		 */
 		*ipap &= PMD_MASK;
-		kvm_release_pfn_clean(pfn);
+		kvm_release_page_clean(*page);
 		pfn &= ~(PTRS_PER_PMD - 1);
-		get_page(pfn_to_page(pfn));
 		*pfnp = pfn;
+		*page = pfn_to_page(pfn);
+		get_page(*page);
 
 		return PMD_SIZE;
 	}
@@ -1201,6 +1203,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	short vma_shift;
 	gfn_t gfn;
 	kvm_pfn_t pfn;
+	struct page *page;
 	bool logging_active = memslot_is_logging(memslot);
 	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	unsigned long vma_pagesize, fault_granule;
@@ -1301,8 +1304,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 */
 	smp_rmb();
 
-	pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
-				   write_fault, &writable, NULL);
+	pfn = __gfn_to_pfn_noref_memslot(memslot, gfn, false, false, NULL,
+					 write_fault, &writable, NULL, &page);
 	if (pfn == KVM_PFN_ERR_HWPOISON) {
 		kvm_send_hwpoison_signal(hva, vma_shift);
 		return 0;
@@ -1348,7 +1351,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			vma_pagesize = fault_granule;
 		else
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
-								   hva, &pfn,
+								   hva,
+								   &pfn, &page,
 								   &fault_ipa);
 	}
 
@@ -1395,8 +1399,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 out_unlock:
 	read_unlock(&kvm->mmu_lock);
-	kvm_set_pfn_accessed(pfn);
-	kvm_release_pfn_clean(pfn);
+	kvm_release_pfn_noref_clean(pfn, page);
 	return ret != -EAGAIN ? ret : 0;
 }
 
-- 
2.40.0.348.gf938b09366-goog