Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Keqian Zhu <zhukeqian1@huawei.com>
To:     <linux-kernel@vger.kernel.org>,
        <linux-arm-kernel@lists.infradead.org>,
        <kvmarm@lists.cs.columbia.edu>, <kvm@vger.kernel.org>
CC:     Catalin Marinas <catalin.marinas@arm.com>,
        Marc Zyngier <maz@kernel.org>,
        James Morse <james.morse@arm.com>,
        Will Deacon <will@kernel.org>,
        "Suzuki K Poulose" <suzuki.poulose@arm.com>,
        Sean Christopherson <sean.j.christopherson@intel.com>,
        Julien Thierry <julien.thierry.kdev@gmail.com>,
        Mark Brown <broonie@kernel.org>,
        "Thomas Gleixner" <tglx@linutronix.de>,
        Andrew Morton <akpm@linux-foundation.org>,
        Alexios Zavras <alexios.zavras@intel.com>,
        <liangpeng10@huawei.com>, <zhengxiang9@huawei.com>,
        <wanghaibin.wang@huawei.com>, Keqian Zhu <zhukeqian1@huawei.com>
Subject: [PATCH 02/12] KVM: arm64: Modify stage2 young mechanism to support hw DBM
Date:   Tue, 16 Jun 2020 17:35:43 +0800
Message-ID: <20200616093553.27512-3-zhukeqian1@huawei.com>
In-Reply-To: <20200616093553.27512-1-zhukeqian1@huawei.com>
References: <20200616093553.27512-1-zhukeqian1@huawei.com>
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Marking PTs young (set AF bit) should be atomic to avoid cover
dirty status set by hardware.

Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com>
---
 arch/arm64/include/asm/kvm_mmu.h | 32 ++++++++++++++++++++++----------
 arch/arm64/kvm/mmu.c             | 15 ++++++++-------
 2 files changed, 30 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index e0ee6e23d626..51af71505fbc 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -215,6 +215,18 @@ static inline void kvm_set_s2pte_readonly(pte_t *ptep)
 	} while (pteval != old_pteval);
 }
 
+static inline void kvm_set_s2pte_young(pte_t *ptep)
+{
+	pteval_t old_pteval, pteval;
+
+	pteval = READ_ONCE(pte_val(*ptep));
+	do {
+		old_pteval = pteval;
+		pteval |= PTE_AF;
+		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
+	} while (pteval != old_pteval);
+}
+
 static inline bool kvm_s2pte_readonly(pte_t *ptep)
 {
 	return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY;
@@ -230,6 +242,11 @@ static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp)
 	kvm_set_s2pte_readonly((pte_t *)pmdp);
 }
 
+static inline void kvm_set_s2pmd_young(pmd_t *pmdp)
+{
+	kvm_set_s2pte_young((pte_t *)pmdp);
+}
+
 static inline bool kvm_s2pmd_readonly(pmd_t *pmdp)
 {
 	return kvm_s2pte_readonly((pte_t *)pmdp);
@@ -245,6 +262,11 @@ static inline void kvm_set_s2pud_readonly(pud_t *pudp)
 	kvm_set_s2pte_readonly((pte_t *)pudp);
 }
 
+static inline void kvm_set_s2pud_young(pud_t *pudp)
+{
+	kvm_set_s2pte_young((pte_t *)pudp);
+}
+
 static inline bool kvm_s2pud_readonly(pud_t *pudp)
 {
 	return kvm_s2pte_readonly((pte_t *)pudp);
@@ -255,16 +277,6 @@ static inline bool kvm_s2pud_exec(pud_t *pudp)
 	return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
 }
 
-static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
-{
-	return pud_mkyoung(pud);
-}
-
-static inline bool kvm_s2pud_young(pud_t pud)
-{
-	return pud_young(pud);
-}
-
 #ifdef CONFIG_ARM64_HW_AFDBM
 static inline bool kvm_hw_dbm_enabled(void)
 {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c0035cab6b6..5ad87bce23c0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2008,8 +2008,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
  * Resolve the access fault by making the page young again.
  * Note that because the faulting entry is guaranteed not to be
  * cached in the TLB, we don't need to invalidate anything.
- * Only the HW Access Flag updates are supported for Stage 2 (no DBM),
- * so there is no need for atomic (pte|pmd)_mkyoung operations.
+ *
+ * Note: Both DBM and HW AF updates are supported for Stage2, so
+ * young operations should be atomic.
  */
 static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
@@ -2027,15 +2028,15 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 		goto out;
 
 	if (pud) {		/* HugeTLB */
-		*pud = kvm_s2pud_mkyoung(*pud);
+		kvm_set_s2pud_young(pud);
 		pfn = kvm_pud_pfn(*pud);
 		pfn_valid = true;
 	} else	if (pmd) {	/* THP, HugeTLB */
-		*pmd = pmd_mkyoung(*pmd);
+		kvm_set_s2pmd_young(pmd);
 		pfn = pmd_pfn(*pmd);
 		pfn_valid = true;
-	} else {
-		*pte = pte_mkyoung(*pte);	/* Just a page... */
+	} else {		/* Just a page... */
+		kvm_set_s2pte_young(pte);
 		pfn = pte_pfn(*pte);
 		pfn_valid = true;
 	}
@@ -2280,7 +2281,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 		return 0;
 
 	if (pud)
-		return kvm_s2pud_young(*pud);
+		return pud_young(*pud);
 	else if (pmd)
 		return pmd_young(*pmd);
 	else
-- 
2.19.1