KVM: Let/force architectures to deal with arch specific memslot data

Pass the "old" slot to kvm_arch_prepare_memory_region() and force arch
code to handle propagating arch specific data from "new" to "old" when
necessary.  This is a baby step towards dynamically allocating "new" from
the get go, and is a (very) minor performance boost on x86 due to not
unnecessarily copying arch data.

For PPC HV, copy the rmap in the !CREATE and !DELETE paths, i.e. for MOVE
and FLAGS_ONLY.  This is functionally a nop as the previous behavior
would overwrite the pointer for CREATE, and eventually discard/ignore it
for DELETE.

For x86, copy the arch data only for FLAGS_ONLY changes.  Unlike PPC HV,
x86 needs to reallocate arch data in the MOVE case as the size of x86's
allocations depend on the alignment of the memslot's gfn.

Opportunistically tweak kvm_arch_prepare_memory_region()'s param order to
match the "commit" prototype.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
[mss: add missing RISCV kvm_arch_prepare_memory_region() change]
Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Message-Id: <67dea5f11bbcfd71e3da5986f11e87f5dd4013f9.1638817639.git.maciej.szmigiero@oracle.com>

arch/arm64/kvm/mmu.c

@@ -1486,8 +1486,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
 				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
 	hva_t hva = mem->userspace_addr;
@@ -1502,7 +1503,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 * Prevent userspace from creating a memory region outside of the IPA
 	 * space addressable by the KVM guest IPA space.
 	 */
-	if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
+	if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
 		return -EFAULT;
 
 	mmap_read_lock(current->mm);
@@ -1536,7 +1537,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 
 		if (vma->vm_flags & VM_PFNMAP) {
 			/* IO region dirty page logging not allowed */
-			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
 				ret = -EINVAL;
 				break;
 			}

arch/mips/kvm/mips.c

@@ -214,8 +214,9 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
 				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
 	return 0;

arch/powerpc/include/asm/kvm_ppc.h

@@ -200,12 +200,13 @@ extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern void kvmppc_core_free_memslot(struct kvm *kvm,
 				     struct kvm_memory_slot *slot);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				struct kvm_memory_slot *memslot,
 				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *new,
 				enum kvm_mr_change change);
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change);
 extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
@@ -274,12 +275,13 @@ struct kvmppc_ops {
 	int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log);
 	void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot);
 	int (*prepare_memory_region)(struct kvm *kvm,
-				     struct kvm_memory_slot *memslot,
 				     const struct kvm_userspace_memory_region *mem,
+				     const struct kvm_memory_slot *old,
+				     struct kvm_memory_slot *new,
 				     enum kvm_mr_change change);
 	void (*commit_memory_region)(struct kvm *kvm,
 				     const struct kvm_userspace_memory_region *mem,
-				     const struct kvm_memory_slot *old,
+				     struct kvm_memory_slot *old,
 				     const struct kvm_memory_slot *new,
 				     enum kvm_mr_change change);
 	bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range);

arch/powerpc/kvm/book3s.c

@@ -847,17 +847,17 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 }
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				struct kvm_memory_slot *memslot,
-				const struct kvm_userspace_memory_region *mem,
-				enum kvm_mr_change change)
+				      const struct kvm_userspace_memory_region *mem,
+				      const struct kvm_memory_slot *old,
+				      struct kvm_memory_slot *new,
+				      enum kvm_mr_change change)
 {
-	return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem,
-							change);
+	return kvm->arch.kvm_ops->prepare_memory_region(kvm, mem, old, new, change);
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {

arch/powerpc/kvm/book3s_hv.c

@@ -4854,17 +4854,20 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot)
 }
 
 static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
-					struct kvm_memory_slot *slot,
-					const struct kvm_userspace_memory_region *mem,
-					enum kvm_mr_change change)
+				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
 
 	if (change == KVM_MR_CREATE) {
-		slot->arch.rmap = vzalloc(array_size(npages,
-					  sizeof(*slot->arch.rmap)));
-		if (!slot->arch.rmap)
+		new->arch.rmap = vzalloc(array_size(npages,
+					  sizeof(*new->arch.rmap)));
+		if (!new->arch.rmap)
 			return -ENOMEM;
+	} else if (change != KVM_MR_DELETE) {
+		new->arch.rmap = old->arch.rmap;
 	}
 
 	return 0;
@@ -4872,7 +4875,7 @@ static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
 
 static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {

arch/powerpc/kvm/book3s_pr.c

@@ -1899,16 +1899,17 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm,
 }
 
 static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
-					struct kvm_memory_slot *memslot,
-					const struct kvm_userspace_memory_region *mem,
-					enum kvm_mr_change change)
+				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	return 0;
 }
 
 static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {

arch/powerpc/kvm/booke.c

@@ -1821,8 +1821,9 @@ void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 }
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot,
 				      const struct kvm_userspace_memory_region *mem,
+				      const struct kvm_memory_slot *old,
+				      struct kvm_memory_slot *new,
 				      enum kvm_mr_change change)
 {
 	return 0;
@@ -1830,7 +1831,7 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {

arch/powerpc/kvm/powerpc.c

@@ -698,11 +698,12 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
 				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
-	return kvmppc_core_prepare_memory_region(kvm, memslot, mem, change);
+	return kvmppc_core_prepare_memory_region(kvm, mem, old, new, change);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,

arch/riscv/kvm/mmu.c

@@ -477,8 +477,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				struct kvm_memory_slot *memslot,
 				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
 	hva_t hva = mem->userspace_addr;
@@ -494,7 +495,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 * Prevent userspace from creating a memory region outside of the GPA
 	 * space addressable by the KVM guest GPA space.
 	 */
-	if ((memslot->base_gfn + memslot->npages) >=
+	if ((new->base_gfn + new->npages) >=
 	    (stage2_gpa_size >> PAGE_SHIFT))
 		return -EFAULT;
 
@@ -541,7 +542,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 			pa += vm_start - vma->vm_start;
 
 			/* IO region dirty page logging not allowed */
-			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
 				ret = -EINVAL;
 				goto out;
 			}

arch/s390/kvm/kvm-s390.c

@@ -5007,8 +5007,9 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
 				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
 	/* A few sanity checks. We can have memory slots which have to be

arch/x86/kvm/x86.c

@@ -11674,13 +11674,20 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				struct kvm_memory_slot *memslot,
-				const struct kvm_userspace_memory_region *mem,
-				enum kvm_mr_change change)
+				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
+				   enum kvm_mr_change change)
 {
 	if (change == KVM_MR_CREATE || change == KVM_MR_MOVE)
-		return kvm_alloc_memslot_metadata(kvm, memslot,
+		return kvm_alloc_memslot_metadata(kvm, new,
 						  mem->memory_size >> PAGE_SHIFT);
+
+	if (change == KVM_MR_FLAGS_ONLY)
+		memcpy(&new->arch, &old->arch, sizeof(old->arch));
+	else if (WARN_ON_ONCE(change != KVM_MR_DELETE))
+		return -EIO;
+
 	return 0;
 }
 

include/linux/kvm_host.h

@@ -833,8 +833,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				struct kvm_memory_slot *memslot,
 				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *new,
 				enum kvm_mr_change change);
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,

virt/kvm/kvm_main.c

@@ -1636,10 +1636,7 @@ static int kvm_set_memslot(struct kvm *kvm,
 		old.as_id = new->as_id;
 	}
 
-	/* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */
-	memcpy(&new->arch, &old.arch, sizeof(old.arch));
-
-	r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
+	r = kvm_arch_prepare_memory_region(kvm, mem, &old, new, change);
 	if (r)
 		goto out_slots;