[PATCH v4 37/66] KVM: arm64: nv: Unmap/flush shadow stage 2 page tables

[Marc Zyngier <maz@kernel.org>]

From: Christoffer Dall <christoffer.dall@linaro.org>

Unmap/flush shadow stage 2 page tables for the nested VMs as well as the
stage 2 page table for the guest hypervisor.

Note: A bunch of the code in mmu.c relating to MMU notifiers is
currently dealt with in an extremely abrupt way, for example by clearing
out an entire shadow stage-2 table. This will be handled in a more
efficient way using the reverse mapping feature in a later version of
the patch series.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_mmu.h    |  3 +++
 arch/arm64/include/asm/kvm_nested.h |  3 +++
 arch/arm64/kvm/mmu.c                | 29 ++++++++++++++++++---
 arch/arm64/kvm/nested.c             | 39 +++++++++++++++++++++++++++++
 4 files changed, 70 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 579980a8b05f..eaec0366526d 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -158,6 +158,8 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **haddr);
 int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 			     void **haddr);
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+			    phys_addr_t addr, phys_addr_t end);
 void free_hyp_pgds(void);
 
 void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
@@ -166,6 +168,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
 void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 3f3d8e10bd99..2987806850f0 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -114,6 +114,9 @@ extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
 				    struct kvm_s2_trans *trans);
 extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
+extern void kvm_nested_s2_wp(struct kvm *kvm);
+extern void kvm_nested_s2_clear(struct kvm *kvm);
+extern void kvm_nested_s2_flush(struct kvm *kvm);
 int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
 extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6db8fa8bc5a3..fddcbe200573 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -179,13 +179,20 @@ void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 	__unmap_stage2_range(mmu, start, size, true);
 }
 
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+			    phys_addr_t addr, phys_addr_t end)
+{
+	stage2_apply_range_resched(kvm_s2_mmu_to_kvm(mmu), addr, end, kvm_pgtable_stage2_flush);
+}
+
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
 
-	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_flush);
+	kvm_stage2_flush_range(mmu, addr, end);
 }
 
 /**
@@ -208,6 +215,8 @@ static void stage2_flush_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, slots)
 		stage2_flush_memslot(kvm, memslot);
 
+	kvm_nested_s2_flush(kvm);
+
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
@@ -562,6 +571,8 @@ void stage2_unmap_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
+	kvm_nested_s2_clear(kvm);
+
 	spin_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -636,7 +647,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
  * @addr:	Start address of range
  * @end:	End address of range
  */
-static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
 	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_wrprotect);
@@ -668,7 +679,8 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_nested_s2_wp(kvm);
 	spin_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 }
@@ -692,7 +704,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
 	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
 
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
 /*
@@ -707,6 +719,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		gfn_t gfn_offset, unsigned long mask)
 {
 	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+	kvm_nested_s2_wp(kvm);
 }
 
 static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
@@ -1247,6 +1260,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 			     (range->end - range->start) << PAGE_SHIFT,
 			     range->may_block);
 
+	kvm_nested_s2_clear(kvm);
 	return 0;
 }
 
@@ -1275,6 +1289,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 			       PAGE_SIZE, __pfn_to_phys(pfn),
 			       KVM_PGTABLE_PROT_R, NULL);
 
+	kvm_nested_s2_clear(kvm);
 	return 0;
 }
 
@@ -1293,6 +1308,11 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 					range->start << PAGE_SHIFT);
 	pte = __pte(kpte);
 	return pte_valid(pte) && pte_young(pte);
+
+	/*
+	 * TODO: Handle nested_mmu structures here using the reverse mapping in
+	 * a later version of patch series.
+	 */
 }
 
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -1525,6 +1545,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+	kvm_nested_s2_clear(kvm);
 	spin_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 2e6a97e43396..9aa4cefc954d 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -505,6 +505,45 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
 	return kvm_inject_nested_sync(vcpu, esr_el2);
 }
 
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_wp(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_wp_range(mmu, 0, kvm_phys_size(kvm));
+	}
+}
+
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_clear(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_unmap_stage2_range(mmu, 0, kvm_phys_size(kvm));
+	}
+}
+
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_flush(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_flush_range(mmu, 0, kvm_phys_size(kvm));
+	}
+}
+
 /*
  * Inject wfx to the virtual EL2 if this is not from the virtual EL2 and
  * the virtual HCR_EL2.TWX is set. Otherwise, let the host hypervisor
-- 
2.29.2