[PATCH V5 4/10] KVM/VMX: Add hv tlb range flush support

[PATCH V5 4/10] KVM/VMX: Add hv tlb range flush support

[ltykernel]

From: Lan Tianyu <Tianyu.Lan@microsoft.com>

This patch is to register tlb_remote_flush_with_range callback with
hv tlb range flush interface.

Signed-off-by: Lan Tianyu <Tianyu.Lan@microsoft.com>
---
Change since v4:
	- Use new function kvm_fill_hv_flush_list_func() to fill flush
       request.
Change since v3:
	- Merge Vitaly's don't pass EPT configuration info to
vmx_hv_remote_flush_tlb() fix.
Change since v1:
	- Pass flush range with new hyper-v tlb flush struct rather
       than KVM tlb flush struct.
---
 arch/x86/kvm/vmx.c | 69 ++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 49 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index edbc96cb990a..405dfbde70b2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1567,7 +1567,38 @@ static void check_ept_pointer_match(struct kvm *kvm)
 	to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH;
 }
 
-static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
+int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
+		void *data)
+{
+	struct kvm_tlb_range *range = data;
+
+	return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn,
+			range->pages);
+}
+
+static inline int __hv_remote_flush_tlb_with_range(struct kvm *kvm,
+		struct kvm_vcpu *vcpu, struct kvm_tlb_range *range)
+{
+	u64 ept_pointer = to_vmx(vcpu)->ept_pointer;
+
+	/* If ept_pointer is invalid pointer, bypass flush request. */
+	if (!VALID_PAGE(ept_pointer))
+		return 0;
+
+	/*
+	 * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs address
+	 * of the base of EPT PML4 table, strip off EPT configuration
+	 * information.
+	 */
+	if (range)
+		return hyperv_flush_guest_mapping_range(ept_pointer & PAGE_MASK,
+				kvm_fill_hv_flush_list_func, (void *)range);
+	else
+		return hyperv_flush_guest_mapping(ept_pointer & PAGE_MASK);
+}
+
+static int hv_remote_flush_tlb_with_range(struct kvm *kvm,
+		struct kvm_tlb_range *range)
 {
 	struct kvm_vcpu *vcpu;
 	int ret = -ENOTSUPP, i;
@@ -1577,30 +1608,23 @@ static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
 	if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK)
 		check_ept_pointer_match(kvm);
 
-	/*
-	 * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs the address of the
-	 * base of EPT PML4 table, strip off EPT configuration information.
-	 * If ept_pointer is invalid pointer, bypass the flush request.
-	 */
 	if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) {
-		kvm_for_each_vcpu(i, vcpu, kvm) {
-			if (!VALID_PAGE(to_vmx(vcpu)->ept_pointer))
-				return 0;
-
-			ret |= hyperv_flush_guest_mapping(
-				to_vmx(vcpu)->ept_pointer & PAGE_MASK);
-		}
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			ret |= __hv_remote_flush_tlb_with_range(
+					kvm, vcpu, range);
 	} else {
-		if (!VALID_PAGE(to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer))
-			return 0;
-
-		ret = hyperv_flush_guest_mapping(
-			to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer & PAGE_MASK);
+		ret = __hv_remote_flush_tlb_with_range(kvm,
+				kvm_get_vcpu(kvm, 0), range);
 	}
 
 	spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
 	return ret;
 }
+
+static int hv_remote_flush_tlb(struct kvm *kvm)
+{
+	return hv_remote_flush_tlb_with_range(kvm, NULL);
+}
 #else /* !IS_ENABLED(CONFIG_HYPERV) */
 static inline void evmcs_write64(unsigned long field, u64 value) {}
 static inline void evmcs_write32(unsigned long field, u32 value) {}
@@ -7957,8 +7981,11 @@ static __init int hardware_setup(void)
 
 #if IS_ENABLED(CONFIG_HYPERV)
 	if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH
-	    && enable_ept)
-		kvm_x86_ops->tlb_remote_flush = vmx_hv_remote_flush_tlb;
+	    && enable_ept) {
+		kvm_x86_ops->tlb_remote_flush = hv_remote_flush_tlb;
+		kvm_x86_ops->tlb_remote_flush_with_range =
+				hv_remote_flush_tlb_with_range;
+	}
 #endif
 
 	if (!cpu_has_vmx_ple()) {
@@ -11567,6 +11594,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
 
+	vmx->ept_pointer = INVALID_PAGE;
+
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
 	/*
-- 
2.14.4

[PATCH V5 8/10] KVM/MMU: Move tlb flush in kvm_set_pte_rmapp() to kvm_mmu_notifier_change_pte()

[ltykernel]

From: Lan Tianyu <Tianyu.Lan@microsoft.com>

This patch is to move tlb flush in kvm_set_pte_rmapp() to
kvm_mmu_notifier_change_pte() in order to avoid redundant tlb flush.

Signed-off-by: Lan Tianyu <Tianyu.Lan@microsoft.com>
---
 arch/x86/kvm/mmu.c  | 8 ++------
 virt/kvm/kvm_main.c | 5 ++++-
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 06bfcd327ef6..b13b419166c4 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1776,10 +1776,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 		}
 	}
 
-	if (need_flush)
-		kvm_flush_remote_tlbs(kvm);
-
-	return 0;
+	return need_flush;
 }
 
 struct slot_rmap_walk_iterator {
@@ -1915,8 +1912,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
-	kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
-	return 0;
+	return kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
 }
 
 static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2679e476b6c3..dac4b0446aed 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -354,7 +354,10 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
 	kvm->mmu_notifier_seq++;
-	kvm_set_spte_hva(kvm, address, pte);
+
+	if (kvm_set_spte_hva(kvm, address, pte))
+		kvm_flush_remote_tlbs(kvm);
+
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
-- 
2.14.4

[PATCH V5 9/10] KVM/MMU: Flush tlb directly in the kvm_set_pte_rmapp()

[ltykernel]

From: Lan Tianyu <Tianyu.Lan@microsoft.com>

This patch is to flush tlb directly in the kvm_set_pte_rmapp()
and return 0.

Signed-off-by: Lan Tianyu <Tianyu.Lan@microsoft.com>
---
 arch/x86/kvm/mmu.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b13b419166c4..39e0e2572710 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1776,6 +1776,11 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 		}
 	}
 
+	if (need_flush && kvm_available_flush_tlb_with_range()) {
+		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+		return 0;
+	}
+
 	return need_flush;
 }
 
-- 
2.14.4

[PATCH V5 10/10] KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range()

[ltykernel]

From: Lan Tianyu <Tianyu.Lan@microsoft.com>

Originally, flush tlb is done by slot_handle_level_range(). This patch
is to flush tlb directly in the kvm_zap_gfn_range() when range
flush is available.

Signed-off-by: Lan Tianyu <Tianyu.Lan@microsoft.com>
---
Change since v4:
	Move operation of setting flush_tlb out of for loop.
---
 arch/x86/kvm/mmu.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 39e0e2572710..898560b0807c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -5633,8 +5633,13 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
+	bool flush_tlb = true;
+	bool flush = false;
 	int i;
 
+	if (kvm_available_flush_tlb_with_range())
+		flush_tlb = false;
+
 	spin_lock(&kvm->mmu_lock);
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		slots = __kvm_memslots(kvm, i);
@@ -5646,12 +5651,17 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 			if (start >= end)
 				continue;
 
-			slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
-						PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL,
-						start, end - 1, true);
+			flush |= slot_handle_level_range(kvm, memslot,
+					kvm_zap_rmapp, PT_PAGE_TABLE_LEVEL,
+					PT_MAX_HUGEPAGE_LEVEL, start,
+					end - 1, flush_tlb);
 		}
 	}
 
+	if (flush)
+		kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
+				gfn_end - gfn_start + 1);
+
 	spin_unlock(&kvm->mmu_lock);
 }
 
-- 
2.14.4