[PATCH v9 10/17] KVM: x86: Compute max_mapping_level with input from guest_memfd

[Fuad Tabba <tabba@google.com>]

From: Ackerley Tng <ackerleytng@google.com>

This patch adds kvm_gmem_max_mapping_level(), which always returns
PG_LEVEL_4K since guest_memfd only supports 4K pages for now.

When guest_memfd supports shared memory, max_mapping_level (especially
when recovering huge pages - see call to __kvm_mmu_max_mapping_level()
from recover_huge_pages_range()) should take input from
guest_memfd.

Input from guest_memfd should be taken in these cases:

+ if the memslot supports shared memory (guest_memfd is used for
  shared memory, or in future both shared and private memory) or
+ if the memslot is only used for private memory and that gfn is
  private.

If the memslot doesn't use guest_memfd, figure out the
max_mapping_level using the host page tables like before.

This patch also refactors and inlines the other call to
__kvm_mmu_max_mapping_level().

In kvm_mmu_hugepage_adjust(), guest_memfd's input is already
provided (if applicable) in fault->max_level. Hence, there is no need
to query guest_memfd.

lpage_info is queried like before, and then if the fault is not from
guest_memfd, adjust fault->req_level based on input from host page
tables.

Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/x86/kvm/mmu/mmu.c   | 92 ++++++++++++++++++++++++++--------------
 include/linux/kvm_host.h |  7 +++
 virt/kvm/guest_memfd.c   | 12 ++++++
 3 files changed, 79 insertions(+), 32 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cfbb471f7c70..9e0bc8114859 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3256,12 +3256,11 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
 	return level;
 }
 
-static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       gfn_t gfn, int max_level, bool is_private)
+static int kvm_lpage_info_max_mapping_level(struct kvm *kvm,
+					    const struct kvm_memory_slot *slot,
+					    gfn_t gfn, int max_level)
 {
 	struct kvm_lpage_info *linfo;
-	int host_level;
 
 	max_level = min(max_level, max_huge_page_level);
 	for ( ; max_level > PG_LEVEL_4K; max_level--) {
@@ -3270,23 +3269,61 @@ static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
 			break;
 	}
 
-	if (is_private)
-		return max_level;
+	return max_level;
+}
+
+static inline u8 kvm_max_level_for_order(int order)
+{
+	BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
+
+	KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K));
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
+		return PG_LEVEL_1G;
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+		return PG_LEVEL_2M;
+
+	return PG_LEVEL_4K;
+}
+
+static inline int kvm_gmem_max_mapping_level(const struct kvm_memory_slot *slot,
+					     gfn_t gfn, int max_level)
+{
+	int max_order;
 
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
-	host_level = host_pfn_mapping_level(kvm, gfn, slot);
-	return min(host_level, max_level);
+	max_order = kvm_gmem_mapping_order(slot, gfn);
+	return min(max_level, kvm_max_level_for_order(max_order));
 }
 
 int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			      const struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	bool is_private = kvm_slot_has_gmem(slot) &&
-			  kvm_mem_is_private(kvm, gfn);
+	int max_level;
+
+	max_level = kvm_lpage_info_max_mapping_level(kvm, slot, gfn, PG_LEVEL_NUM);
+	if (max_level == PG_LEVEL_4K)
+		return PG_LEVEL_4K;
 
-	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, PG_LEVEL_NUM, is_private);
+	if (kvm_slot_has_gmem(slot) &&
+	    (kvm_gmem_memslot_supports_shared(slot) ||
+	     kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE)) {
+		return kvm_gmem_max_mapping_level(slot, gfn, max_level);
+	}
+
+	return min(max_level, host_pfn_mapping_level(kvm, gfn, slot));
+}
+
+static inline bool fault_from_gmem(struct kvm_page_fault *fault)
+{
+	return fault->is_private ||
+	       (kvm_slot_has_gmem(fault->slot) &&
+		kvm_gmem_memslot_supports_shared(fault->slot));
 }
 
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -3309,12 +3346,20 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * Enforce the iTLB multihit workaround after capturing the requested
 	 * level, which will be used to do precise, accurate accounting.
 	 */
-	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
-						       fault->gfn, fault->max_level,
-						       fault->is_private);
+	fault->req_level = kvm_lpage_info_max_mapping_level(vcpu->kvm, slot,
+							    fault->gfn, fault->max_level);
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
+	if (!fault_from_gmem(fault)) {
+		int host_level;
+
+		host_level = host_pfn_mapping_level(vcpu->kvm, fault->gfn, slot);
+		fault->req_level = min(fault->req_level, host_level);
+		if (fault->req_level == PG_LEVEL_4K)
+			return;
+	}
+
 	/*
 	 * mmu_invalidate_retry() was successful and mmu_lock is held, so
 	 * the pmd can't be split from under us.
@@ -4448,23 +4493,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 		vcpu->stat.pf_fixed++;
 }
 
-static inline u8 kvm_max_level_for_order(int order)
-{
-	BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
-
-	KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) &&
-			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) &&
-			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K));
-
-	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
-		return PG_LEVEL_1G;
-
-	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
-		return PG_LEVEL_2M;
-
-	return PG_LEVEL_4K;
-}
-
 static u8 kvm_max_level_for_fault_and_order(struct kvm *kvm,
 					    struct kvm_page_fault *fault,
 					    int order)
@@ -4523,7 +4551,7 @@ static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu,
 {
 	unsigned int foll = fault->write ? FOLL_WRITE : 0;
 
-	if (fault->is_private || kvm_gmem_memslot_supports_shared(fault->slot))
+	if (fault_from_gmem(fault))
 		return kvm_mmu_faultin_pfn_gmem(vcpu, fault);
 
 	foll |= FOLL_NOWAIT;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index de7b46ee1762..f9bb025327c3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2560,6 +2560,7 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
 		     int *max_order);
+int kvm_gmem_mapping_order(const struct kvm_memory_slot *slot, gfn_t gfn);
 #else
 static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
@@ -2569,6 +2570,12 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 	KVM_BUG_ON(1, kvm);
 	return -EIO;
 }
+static inline int kvm_gmem_mapping_order(const struct kvm_memory_slot *slot,
+					 gfn_t gfn)
+{
+	BUG();
+	return 0;
+}
 #endif /* CONFIG_KVM_GMEM */
 
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index fe0245335c96..b8e247063b20 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -774,6 +774,18 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 }
 EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
 
+/**
+ * Returns the mapping order for this @gfn in @slot.
+ *
+ * This is equal to max_order that would be returned if kvm_gmem_get_pfn() were
+ * called now.
+ */
+int kvm_gmem_mapping_order(const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_mapping_order);
+
 #ifdef CONFIG_KVM_GENERIC_GMEM_POPULATE
 long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque)
-- 
2.49.0.1045.g170613ef41-goog