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:   Oliver Upton <oliver.upton@linux.dev>
To:     Marc Zyngier <maz@kernel.org>, James Morse <james.morse@arm.com>,
        Alexandru Elisei <alexandru.elisei@arm.com>,
        Suzuki K Poulose <suzuki.poulose@arm.com>,
        Oliver Upton <oliver.upton@linux.dev>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will@kernel.org>
Cc:     linux-arm-kernel@lists.infradead.org, kvmarm@lists.cs.columbia.edu,
        kvm@vger.kernel.org, Quentin Perret <qperret@google.com>,
        Ricardo Koller <ricarkol@google.com>,
        Reiji Watanabe <reijiw@google.com>,
        David Matlack <dmatlack@google.com>,
        Ben Gardon <bgardon@google.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Gavin Shan <gshan@redhat.com>, Peter Xu <peterx@redhat.com>,
        Sean Christopherson <seanjc@google.com>,
        linux-kernel@vger.kernel.org
Subject: [PATCH 10/14] KVM: arm64: Atomically update stage 2 leaf attributes in parallel walks
Date:   Tue, 30 Aug 2022 19:50:36 +0000
Message-Id: <20220830195036.964607-1-oliver.upton@linux.dev>
In-Reply-To: <20220830194132.962932-1-oliver.upton@linux.dev>
References: <20220830194132.962932-1-oliver.upton@linux.dev>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The stage2 attr walker is already used for parallel walks. Since commit
f783ef1c0e82 ("KVM: arm64: Add fast path to handle permission relaxation
during dirty logging"), KVM acquires the read lock when
write-unprotecting a PTE. However, the walker only uses a simple store
to update the PTE. This is safe as the only possible race is with
hardware updates to the access flag, which is benign.

However, a subsequent change to KVM will allow more changes to the stage
2 page tables to be done in parallel. Prepare the stage 2 attribute
walker by performing atomic updates to the PTE when walking in parallel.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/pgtable.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 215a14c434ed..61a4437c8c16 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -691,6 +691,16 @@ static bool stage2_pte_is_counted(kvm_pte_t pte)
 	return kvm_pte_valid(pte) || kvm_invalid_pte_owner(pte);
 }
 
+static bool stage2_try_set_pte(kvm_pte_t *ptep, kvm_pte_t old, kvm_pte_t new, bool shared)
+{
+	if (!shared) {
+		WRITE_ONCE(*ptep, new);
+		return true;
+	}
+
+	return cmpxchg(ptep, old, new) == old;
+}
+
 static void stage2_put_pte(kvm_pte_t *ptep, struct kvm_s2_mmu *mmu, u64 addr,
 			   u32 level, struct kvm_pgtable_mm_ops *mm_ops)
 {
@@ -985,6 +995,7 @@ struct stage2_attr_data {
 	kvm_pte_t			pte;
 	u32				level;
 	struct kvm_pgtable_mm_ops	*mm_ops;
+	bool				shared;
 };
 
 static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
@@ -1017,7 +1028,9 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 		    stage2_pte_executable(pte) && !stage2_pte_executable(data->pte))
 			mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops),
 						  kvm_granule_size(level));
-		WRITE_ONCE(*ptep, pte);
+
+		if (!stage2_try_set_pte(ptep, data->pte, pte, data->shared))
+			return -EAGAIN;
 	}
 
 	return 0;
@@ -1026,7 +1039,7 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 				    u64 size, kvm_pte_t attr_set,
 				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
-				    u32 *level)
+				    u32 *level, bool shared)
 {
 	int ret;
 	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
@@ -1034,6 +1047,7 @@ static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 		.attr_set	= attr_set & attr_mask,
 		.attr_clr	= attr_clr & attr_mask,
 		.mm_ops		= pgt->mm_ops,
+		.shared		= shared,
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_attr_walker,
@@ -1057,14 +1071,14 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
 	return stage2_update_leaf_attrs(pgt, addr, size, 0,
 					KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
-					NULL, NULL);
+					NULL, NULL, false);
 }
 
 kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
 	stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
-				 &pte, NULL);
+				 &pte, NULL, false);
 	dsb(ishst);
 	return pte;
 }
@@ -1073,7 +1087,7 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
 	stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF,
-				 &pte, NULL);
+				 &pte, NULL, false);
 	/*
 	 * "But where's the TLBI?!", you scream.
 	 * "Over in the core code", I sigh.
@@ -1086,7 +1100,7 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
 bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL);
+	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, false);
 	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
 }
 
@@ -1109,7 +1123,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	if (prot & KVM_PGTABLE_PROT_X)
 		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
 
-	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level);
+	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, true);
 	if (!ret)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level);
 	return ret;
-- 
2.37.2.672.g94769d06f0-goog