Merge branch 'mm-delete-change-gpte' into HEAD

The .change_pte() MMU notifier callback was intended as an optimization
and for this reason it was initially called without a surrounding
mmu_notifier_invalidate_range_{start,end}() pair.  It was only ever
implemented by KVM (which was also the original user of MMU notifiers)
and the rules on when to call set_pte_at_notify() rather than set_pte_at()
have always been pretty obscure.

It may seem a miracle that it has never caused any hard to trigger
bugs, but there's a good reason for that: KVM's implementation has
been nonfunctional for a good part of its existence.  Already in
2012, commit 6bdb913 ("mm: wrap calls to set_pte_at_notify with
invalidate_range_start and invalidate_range_end", 2012-10-09) changed the
.change_pte() callback to occur within an invalidate_range_start/end()
pair; and because KVM unmaps the sPTEs during .invalidate_range_start(),
.change_pte() has no hope of finding a sPTE to change.

Therefore, all the code for .change_pte() can be removed from both KVM
and mm/, and set_pte_at_notify() can be replaced with just set_pte_at().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: bonzini

arch/arm64/kvm/mmu.c

@@ -1768,40 +1768,6 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 	return false;
 }
 
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	kvm_pfn_t pfn = pte_pfn(range->arg.pte);
-
-	if (!kvm->arch.mmu.pgt)
-		return false;
-
-	WARN_ON(range->end - range->start != 1);
-
-	/*
-	 * If the page isn't tagged, defer to user_mem_abort() for sanitising
-	 * the MTE tags. The S2 pte should have been unmapped by
-	 * mmu_notifier_invalidate_range_end().
-	 */
-	if (kvm_has_mte(kvm) && !page_mte_tagged(pfn_to_page(pfn)))
-		return false;
-
-	/*
-	 * We've moved a page around, probably through CoW, so let's treat
-	 * it just like a translation fault and the map handler will clean
-	 * the cache to the PoC.
-	 *
-	 * The MMU notifiers will have unmapped a huge PMD before calling
-	 * ->change_pte() (which in turn calls kvm_set_spte_gfn()) and
-	 * therefore we never need to clear out a huge PMD through this
-	 * calling path and a memcache is not required.
-	 */
-	kvm_pgtable_stage2_map(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT,
-			       PAGE_SIZE, __pfn_to_phys(pfn),
-			       KVM_PGTABLE_PROT_R, NULL, 0);
-
-	return false;
-}
-
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	u64 size = (range->end - range->start) << PAGE_SHIFT;

arch/loongarch/include/asm/kvm_host.h

@@ -203,7 +203,6 @@ void kvm_flush_tlb_all(void);
 void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa);
 int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write);
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);

arch/loongarch/kvm/mmu.c

@@ -494,38 +494,6 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 			range->end << PAGE_SHIFT, &ctx);
 }
 
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	unsigned long prot_bits;
-	kvm_pte_t *ptep;
-	kvm_pfn_t pfn = pte_pfn(range->arg.pte);
-	gpa_t gpa = range->start << PAGE_SHIFT;
-
-	ptep = kvm_populate_gpa(kvm, NULL, gpa, 0);
-	if (!ptep)
-		return false;
-
-	/* Replacing an absent or old page doesn't need flushes */
-	if (!kvm_pte_present(NULL, ptep) || !kvm_pte_young(*ptep)) {
-		kvm_set_pte(ptep, 0);
-		return false;
-	}
-
-	/* Fill new pte if write protected or page migrated */
-	prot_bits = _PAGE_PRESENT | __READABLE;
-	prot_bits |= _CACHE_MASK & pte_val(range->arg.pte);
-
-	/*
-	 * Set _PAGE_WRITE or _PAGE_DIRTY iff old and new pte both support
-	 * _PAGE_WRITE for map_page_fast if next page write fault
-	 * _PAGE_DIRTY since gpa has already recorded as dirty page
-	 */
-	prot_bits |= __WRITEABLE & *ptep & pte_val(range->arg.pte);
-	kvm_set_pte(ptep, kvm_pfn_pte(pfn, __pgprot(prot_bits)));
-
-	return true;
-}
-
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	kvm_ptw_ctx ctx;

arch/mips/kvm/mmu.c

@@ -444,36 +444,6 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 	return true;
 }
 
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	gpa_t gpa = range->start << PAGE_SHIFT;
-	pte_t hva_pte = range->arg.pte;
-	pte_t *gpa_pte = kvm_mips_pte_for_gpa(kvm, NULL, gpa);
-	pte_t old_pte;
-
-	if (!gpa_pte)
-		return false;
-
-	/* Mapping may need adjusting depending on memslot flags */
-	old_pte = *gpa_pte;
-	if (range->slot->flags & KVM_MEM_LOG_DIRTY_PAGES && !pte_dirty(old_pte))
-		hva_pte = pte_mkclean(hva_pte);
-	else if (range->slot->flags & KVM_MEM_READONLY)
-		hva_pte = pte_wrprotect(hva_pte);
-
-	set_pte(gpa_pte, hva_pte);
-
-	/* Replacing an absent or old page doesn't need flushes */
-	if (!pte_present(old_pte) || !pte_young(old_pte))
-		return false;
-
-	/* Pages swapped, aged, moved, or cleaned require flushes */
-	return !pte_present(hva_pte) ||
-	       !pte_young(hva_pte) ||
-	       pte_pfn(old_pte) != pte_pfn(hva_pte) ||
-	       (pte_dirty(old_pte) && !pte_dirty(hva_pte));
-}
-
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	return kvm_mips_mkold_gpa_pt(kvm, range->start, range->end);

arch/powerpc/include/asm/kvm_ppc.h

@@ -287,7 +287,6 @@ struct kvmppc_ops {
 	bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range);
 	bool (*age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
 	bool (*test_age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
-	bool (*set_spte_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
 	void (*free_memslot)(struct kvm_memory_slot *slot);
 	int (*init_vm)(struct kvm *kvm);
 	void (*destroy_vm)(struct kvm *kvm);

arch/powerpc/kvm/book3s.c

@@ -899,11 +899,6 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return kvm->arch.kvm_ops->test_age_gfn(kvm, range);
 }
 
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	return kvm->arch.kvm_ops->set_spte_gfn(kvm, range);
-}
-
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
 

arch/powerpc/kvm/book3s.h

@@ -12,7 +12,6 @@ extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
 extern bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range);
 extern bool kvm_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
 extern bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
-extern bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
 
 extern int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu);

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -1010,18 +1010,6 @@ bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
 		return kvm_test_age_rmapp(kvm, range->slot, range->start);
 }
 
-bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	WARN_ON(range->start + 1 != range->end);
-
-	if (kvm_is_radix(kvm))
-		kvm_unmap_radix(kvm, range->slot, range->start);
-	else
-		kvm_unmap_rmapp(kvm, range->slot, range->start);
-
-	return false;
-}
-
 static int vcpus_running(struct kvm *kvm)
 {
 	return atomic_read(&kvm->arch.vcpus_running) != 0;

arch/powerpc/kvm/book3s_hv.c

@@ -6364,7 +6364,6 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.unmap_gfn_range = kvm_unmap_gfn_range_hv,
 	.age_gfn = kvm_age_gfn_hv,
 	.test_age_gfn = kvm_test_age_gfn_hv,
-	.set_spte_gfn = kvm_set_spte_gfn_hv,
 	.free_memslot = kvmppc_core_free_memslot_hv,
 	.init_vm =  kvmppc_core_init_vm_hv,
 	.destroy_vm = kvmppc_core_destroy_vm_hv,

arch/powerpc/kvm/book3s_pr.c

@@ -461,12 +461,6 @@ static bool kvm_test_age_gfn_pr(struct kvm *kvm, struct kvm_gfn_range *range)
 	return false;
 }
 
-static bool kvm_set_spte_gfn_pr(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	/* The page will get remapped properly on its next fault */
-	return do_kvm_unmap_gfn(kvm, range);
-}
-
 /*****************************************/
 
 static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
@@ -2071,7 +2065,6 @@ static struct kvmppc_ops kvm_ops_pr = {
 	.unmap_gfn_range = kvm_unmap_gfn_range_pr,
 	.age_gfn  = kvm_age_gfn_pr,
 	.test_age_gfn = kvm_test_age_gfn_pr,
-	.set_spte_gfn = kvm_set_spte_gfn_pr,
 	.free_memslot = kvmppc_core_free_memslot_pr,
 	.init_vm = kvmppc_core_init_vm_pr,
 	.destroy_vm = kvmppc_core_destroy_vm_pr,