Merge branch 'kvm-no-struct-page' into HEAD

TL;DR: Eliminate KVM's long-standing (and heinous) behavior of essentially
guessing which pfns are refcounted pages (see kvm_pfn_to_refcounted_page()).

Getting there requires "fixing" arch code that isn't obviously broken.
Specifically, to get rid of kvm_pfn_to_refcounted_page(), KVM needs to
stop marking pages/folios dirty/accessed based solely on the pfn that's
stored in KVM's stage-2 page tables.

Instead of tracking which SPTEs correspond to refcounted pages, simply
remove all of the code that operates on "struct page" based ona the pfn
in stage-2 PTEs.  This is the back ~40-50% of the series.

For x86 in particular, which sets accessed/dirty status when that info
would be "lost", e.g. when SPTEs are zapped or KVM clears the dirty flag
in a SPTE, foregoing the updates provides very measurable performance
improvements for related operations.  E.g. when clearing dirty bits as
part of dirty logging, and zapping SPTEs to reconstitue huge pages when
disabling dirty logging.

The front ~40% of the series is cleanups and prep work, and most of it is
x86 focused (purely because x86 added the most special cases, *sigh*).
E.g. several of the inputs to hva_to_pfn() (and it's myriad wrappers),
can be removed by cleaning up and deduplicating x86 code.

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

1 files changed, 82 insertions, 39 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 45be36e5285f..02f0206fd2dc 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -97,6 +97,7 @@
 #define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
 #define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 2)
 #define KVM_PFN_ERR_SIGPENDING	(KVM_PFN_ERR_MASK + 3)
+#define KVM_PFN_ERR_NEEDS_IO	(KVM_PFN_ERR_MASK + 4)
 
 /*
  * error pfns indicate that the gfn is in slot but faild to
@@ -153,13 +154,6 @@ static inline bool kvm_is_error_gpa(gpa_t gpa)
 	return gpa == INVALID_GPA;
 }
 
-#define KVM_ERR_PTR_BAD_PAGE	(ERR_PTR(-ENOENT))
-
-static inline bool is_error_page(struct page *page)
-{
-	return IS_ERR(page);
-}
-
 #define KVM_REQUEST_MASK           GENMASK(7,0)
 #define KVM_REQUEST_NO_WAKEUP      BIT(8)
 #define KVM_REQUEST_WAIT           BIT(9)
@@ -279,21 +273,19 @@ enum {
 	READING_SHADOW_PAGE_TABLES,
 };
 
-#define KVM_UNMAPPED_PAGE	((void *) 0x500 + POISON_POINTER_DELTA)
-
 struct kvm_host_map {
 	/*
 	 * Only valid if the 'pfn' is managed by the host kernel (i.e. There is
 	 * a 'struct page' for it. When using mem= kernel parameter some memory
 	 * can be used as guest memory but they are not managed by host
 	 * kernel).
-	 * If 'pfn' is not managed by the host kernel, this field is
-	 * initialized to KVM_UNMAPPED_PAGE.
 	 */
+	struct page *pinned_page;
 	struct page *page;
 	void *hva;
 	kvm_pfn_t pfn;
 	kvm_pfn_t gfn;
+	bool writable;
 };
 
 /*
@@ -1176,6 +1168,10 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_
 	     kvm_memslot_iter_is_valid(iter, end);			\
 	     kvm_memslot_iter_next(iter))
 
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
+struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
+struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
+
 /*
  * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
  * - create a new memory slot
@@ -1214,33 +1210,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm);
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot);
 
-int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
-			    struct page **pages, int nr_pages);
+int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn,
+		       struct page **pages, int nr_pages);
+
+struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write);
+static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+	return __gfn_to_page(kvm, gfn, true);
+}
 
-struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
 unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
 				      bool *writable);
+
+static inline void kvm_release_page_unused(struct page *page)
+{
+	if (!page)
+		return;
+
+	put_page(page);
+}
+
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 
-kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
-kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
-		      bool *writable);
-kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn);
-kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn);
-kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
-			       bool atomic, bool interruptible, bool *async,
-			       bool write_fault, bool *writable, hva_t *hva);
-
-void kvm_release_pfn_clean(kvm_pfn_t pfn);
-void kvm_release_pfn_dirty(kvm_pfn_t pfn);
-void kvm_set_pfn_dirty(kvm_pfn_t pfn);
-void kvm_set_pfn_accessed(kvm_pfn_t pfn);
-
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
+static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page,
+					    bool unused, bool dirty)
+{
+	lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused);
+
+	if (!page)
+		return;
+
+	/*
+	 * If the page that KVM got from the *primary MMU* is writable, and KVM
+	 * installed or reused a SPTE, mark the page/folio dirty.  Note, this
+	 * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if
+	 * the GFN is write-protected.  Folios can't be safely marked dirty
+	 * outside of mmu_lock as doing so could race with writeback on the
+	 * folio.  As a result, KVM can't mark folios dirty in the fast page
+	 * fault handler, and so KVM must (somewhat) speculatively mark the
+	 * folio dirty if KVM could locklessly make the SPTE writable.
+	 */
+	if (unused)
+		kvm_release_page_unused(page);
+	else if (dirty)
+		kvm_release_page_dirty(page);
+	else
+		kvm_release_page_clean(page);
+}
+
+kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn,
+			    unsigned int foll, bool *writable,
+			    struct page **refcounted_page);
+
+static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
+					bool write, bool *writable,
+					struct page **refcounted_page)
+{
+	return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn,
+				 write ? FOLL_WRITE : 0, writable, refcounted_page);
+}
+
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
 int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
@@ -1304,17 +1337,28 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 })
 
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
-struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
 void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
-struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
-struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
-int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
+int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map,
+		   bool writable);
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map);
+
+static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa,
+			       struct kvm_host_map *map)
+{
+	return __kvm_vcpu_map(vcpu, gpa, map, true);
+}
+
+static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa,
+					struct kvm_host_map *map)
+{
+	return __kvm_vcpu_map(vcpu, gpa, map, false);
+}
+
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
 int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
@@ -1686,9 +1730,6 @@ void kvm_arch_sync_events(struct kvm *kvm);
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 
-struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn);
-bool kvm_is_zone_device_page(struct page *page);
-
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
 	unsigned gsi;
@@ -2461,11 +2502,13 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 
 #ifdef CONFIG_KVM_PRIVATE_MEM
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
+		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
+		     int *max_order);
 #else
 static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
-				   kvm_pfn_t *pfn, int *max_order)
+				   kvm_pfn_t *pfn, struct page **page,
+				   int *max_order)
 {
 	KVM_BUG_ON(1, kvm);
 	return -EIO;