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:   isaku.yamahata@intel.com
To:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
        Paolo Bonzini <pbonzini@redhat.com>, erdemaktas@google.com,
        Sean Christopherson <seanjc@google.com>,
        Sagi Shahar <sagis@google.com>,
        David Matlack <dmatlack@google.com>,
        Kai Huang <kai.huang@intel.com>,
        Zhi Wang <zhi.wang.linux@gmail.com>, chen.bo@intel.com,
        hang.yuan@intel.com, tina.zhang@intel.com,
        Xiaoyao Li <xiaoyao.li@intel.com>
Subject: [RFC PATCH v4 08/16] KVM: TDX: Pin pages via get_page() right before ADD/AUG'ed to TDs
Date:   Tue, 25 Jul 2023 15:23:54 -0700
Message-Id: <1519e0b3af4df9de3fe07f750896b44896cdc591.1690323516.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1690323516.git.isaku.yamahata@intel.com>
References: <cover.1690323516.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Xiaoyao Li <xiaoyao.li@intel.com>

When kvm_faultin_pfn(), it doesn't have the info regarding which page level
will the gfn be mapped at. Hence it doesn't know to pin a 4K page or a
2M page.

Move the guest private pages pinning logic right before
TDH_MEM_PAGE_ADD/AUG() since at that time it knows the page level info.

Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/kvm/vmx/tdx.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index c122160142fd..bd1582e6b693 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1361,7 +1361,8 @@ static void tdx_measure_page(struct kvm_tdx *kvm_tdx, hpa_t gpa, int size)
 	}
 }
 
-static void tdx_unpin(struct kvm *kvm, kvm_pfn_t pfn, int level)
+static void tdx_unpin(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
+		      enum pg_level level)
 {
 	int i;
 
@@ -1397,12 +1398,12 @@ static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
 	if (likely(is_td_finalized(kvm_tdx))) {
 		err = tdh_mem_page_aug(kvm_tdx->tdr_pa, gpa, tdx_level, hpa, &out);
 		if (unlikely(err == TDX_ERROR_SEPT_BUSY)) {
-			tdx_unpin(kvm, pfn, level);
+			tdx_unpin(kvm, gfn, pfn, level);
 			return -EAGAIN;
 		}
 		if (KVM_BUG_ON(err, kvm)) {
 			pr_tdx_error(TDH_MEM_PAGE_AUG, err, &out);
-			tdx_unpin(kvm, pfn, level);
+			tdx_unpin(kvm, gfn, pfn, level);
 			return -EIO;
 		}
 		return 0;
@@ -1425,7 +1426,7 @@ static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
 	 * always uses vcpu 0's page table and protected by vcpu->mutex).
 	 */
 	if (KVM_BUG_ON(kvm_tdx->source_pa == INVALID_PAGE, kvm)) {
-		tdx_unpin(kvm, pfn, level);
+		tdx_unpin(kvm, gfn, pfn, level);
 		return -EINVAL;
 	}
 
@@ -1443,7 +1444,7 @@ static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
 	} while (unlikely(err == TDX_ERROR_SEPT_BUSY));
 	if (KVM_BUG_ON(err, kvm)) {
 		pr_tdx_error(TDH_MEM_PAGE_ADD, err, &out);
-		tdx_unpin(kvm, pfn, level);
+		tdx_unpin(kvm, gfn, pfn, level);
 		return -EIO;
 	} else if (measure)
 		tdx_measure_page(kvm_tdx, gpa, KVM_HPAGE_SIZE(level));
@@ -1472,7 +1473,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
 		err = tdx_reclaim_page(hpa, level, false, 0);
 		if (KVM_BUG_ON(err, kvm))
 			return -EIO;
-		tdx_unpin(kvm, pfn, level);
+		tdx_unpin(kvm, gfn, pfn, level);
 		return 0;
 	}
 
@@ -1505,7 +1506,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
 			r = -EIO;
 		} else {
 			tdx_clear_page(hpa, PAGE_SIZE);
-			tdx_unpin(kvm, pfn + i, PG_LEVEL_4K);
+			tdx_unpin(kvm, gfn + i, pfn + i, PG_LEVEL_4K);
 		}
 		hpa += PAGE_SIZE;
 	}
-- 
2.25.1