[RFC PATCH v5 08/16] KVM: TDX: Pin pages via get_page() right before ADD/AUG'ed to TDs

[isaku.yamahata@xxxxxxxxx]

From: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>

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@xxxxxxxxx>
---
 arch/x86/kvm/vmx/tdx.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index c37b66f9a52a..0558faee5b19 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1435,7 +1435,8 @@ 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;
 
@@ -1457,7 +1458,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t gfn,
 
 	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 (unlikely(err == (TDX_EPT_ENTRY_NOT_FREE | TDX_OPERAND_ID_RCX))) {
@@ -1473,7 +1474,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t gfn,
 					 &tmpout);
 		if (KVM_BUG_ON(tmp, kvm)) {
 			pr_tdx_error(TDH_MEM_SEPT_RD, tmp, &tmpout);
-			tdx_unpin(kvm, pfn, level);
+			tdx_unpin(kvm, gfn, pfn, level);
 			return -EIO;
 		}
 		pr_debug_ratelimited("gfn 0x%llx pg_level %d pfn 0x%llx entry 0x%llx level_stat 0x%llx\n",
@@ -1484,7 +1485,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t gfn,
 		if (level_state.level == tdx_level &&
 		    level_state.state == TDX_SEPT_PENDING &&
 		    entry.leaf && entry.pfn == pfn && entry.sve) {
-			tdx_unpin(kvm, pfn, level);
+			tdx_unpin(kvm, gfn, pfn, level);
 			WARN_ON_ONCE(!(to_kvm_tdx(kvm)->attributes &
 				       TDX_TD_ATTR_SEPT_VE_DISABLE));
 			return -EAGAIN;
@@ -1492,7 +1493,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t gfn,
 	}
 	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;
 	}
 
@@ -1528,7 +1529,7 @@ static int tdx_sept_page_add(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;
 	}
 
@@ -1546,7 +1547,7 @@ static int tdx_sept_page_add(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));
@@ -1599,7 +1600,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
 		err = tdx_reclaim_page(hpa, level);
 		if (KVM_BUG_ON(err, kvm))
 			return -EIO;
-		tdx_unpin(kvm, pfn, level);
+		tdx_unpin(kvm, gfn, pfn, level);
 		return 0;
 	}
 
@@ -1632,7 +1633,7 @@ 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