Merge branch 'kvm-guestmemfd' into HEAD

Introduce several new KVM uAPIs to ultimately create a guest-first memory
subsystem within KVM, a.k.a. guest_memfd.  Guest-first memory allows KVM
to provide features, enhancements, and optimizations that are kludgly
or outright impossible to implement in a generic memory subsystem.

The core KVM ioctl() for guest_memfd is KVM_CREATE_GUEST_MEMFD, which
similar to the generic memfd_create(), creates an anonymous file and
returns a file descriptor that refers to it.  Again like "regular"
memfd files, guest_memfd files live in RAM, have volatile storage,
and are automatically released when the last reference is dropped.
The key differences between memfd files (and every other memory subystem)
is that guest_memfd files are bound to their owning virtual machine,
cannot be mapped, read, or written by userspace, and cannot be resized.
guest_memfd files do however support PUNCH_HOLE, which can be used to
convert a guest memory area between the shared and guest-private states.

A second KVM ioctl(), KVM_SET_MEMORY_ATTRIBUTES, allows userspace to
specify attributes for a given page of guest memory.  In the long term,
it will likely be extended to allow userspace to specify per-gfn RWX
protections, including allowing memory to be writable in the guest
without it also being writable in host userspace.

The immediate and driving use case for guest_memfd are Confidential
(CoCo) VMs, specifically AMD's SEV-SNP, Intel's TDX, and KVM's own pKVM.
For such use cases, being able to map memory into KVM guests without
requiring said memory to be mapped into the host is a hard requirement.
While SEV+ and TDX prevent untrusted software from reading guest private
data by encrypting guest memory, pKVM provides confidentiality and
integrity *without* relying on memory encryption.  In addition, with
SEV-SNP and especially TDX, accessing guest private memory can be fatal
to the host, i.e. KVM must be prevent host userspace from accessing
guest memory irrespective of hardware behavior.

Long term, guest_memfd may be useful for use cases beyond CoCo VMs,
for example hardening userspace against unintentional accesses to guest
memory.  As mentioned earlier, KVM's ABI uses userspace VMA protections to
define the allow guest protection (with an exception granted to mapping
guest memory executable), and similarly KVM currently requires the guest
mapping size to be a strict subset of the host userspace mapping size.
Decoupling the mappings sizes would allow userspace to precisely map
only what is needed and with the required permissions, without impacting
guest performance.

A guest-first memory subsystem also provides clearer line of sight to
things like a dedicated memory pool (for slice-of-hardware VMs) and
elimination of "struct page" (for offload setups where userspace _never_
needs to DMA from or into guest memory).

guest_memfd is the result of 3+ years of development and exploration;
taking on memory management responsibilities in KVM was not the first,
second, or even third choice for supporting CoCo VMs.  But after many
failed attempts to avoid KVM-specific backing memory, and looking at
where things ended up, it is quite clear that of all approaches tried,
guest_memfd is the simplest, most robust, and most extensible, and the
right thing to do for KVM and the kernel at-large.

The "development cycle" for this version is going to be very short;
ideally, next week I will merge it as is in kvm/next, taking this through
the KVM tree for 6.8 immediately after the end of the merge window.
The series is still based on 6.6 (plus KVM changes for 6.7) so it
will require a small fixup for changes to get_file_rcu() introduced in
6.7 by commit 0ede61d8589c ("file: convert to SLAB_TYPESAFE_BY_RCU").
The fixup will be done as part of the merge commit, and most of the text
above will become the commit message for the merge.

Pending post-merge work includes:
- hugepage support
- looking into using the restrictedmem framework for guest memory
- introducing a testing mechanism to poison memory, possibly using
  the same memory attributes introduced here
- SNP and TDX support

There are two non-KVM patches buried in the middle of this series:

  fs: Rename anon_inode_getfile_secure() and anon_inode_getfd_secure()
  mm: Add AS_UNMOVABLE to mark mapping as completely unmovable

The first is small and mostly suggested-by Christian Brauner; the second
a bit less so but it was written by an mm person (Vlastimil Babka).

1 files changed, 119 insertions, 23 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4944136efaa2..ea1523a7b83a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -80,8 +80,8 @@
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
-#ifndef KVM_ADDRESS_SPACE_NUM
-#define KVM_ADDRESS_SPACE_NUM	1
+#ifndef KVM_MAX_NR_ADDRESS_SPACES
+#define KVM_MAX_NR_ADDRESS_SPACES	1
 #endif
 
 /*
@@ -253,9 +253,10 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	pte_t pte;
+	unsigned long attributes;
 };
 
 struct kvm_gfn_range {
@@ -588,8 +589,20 @@ struct kvm_memory_slot {
 	u32 flags;
 	short id;
 	u16 as_id;
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	struct {
+		struct file __rcu *file;
+		pgoff_t pgoff;
+	} gmem;
+#endif
 };
 
+static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+{
+	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
+}
+
 static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
 {
 	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
@@ -677,13 +690,29 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#if KVM_MAX_NR_ADDRESS_SPACES == 1
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
 #endif
 
+/*
+ * Arch code must define kvm_arch_has_private_mem if support for private memory
+ * is enabled.
+ */
+#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
@@ -721,9 +750,9 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	unsigned long nr_memslot_pages;
 	/* The two memslot sets - active and inactive (per address space) */
-	struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
+	struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
 	/* The current active memslot set for each address space */
-	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
 	struct xarray vcpu_array;
 	/*
 	 * Protected by slots_lock, but can be read outside if an
@@ -783,12 +812,12 @@ struct kvm {
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
-	unsigned long mmu_invalidate_range_start;
-	unsigned long mmu_invalidate_range_end;
+	gfn_t mmu_invalidate_range_start;
+	gfn_t mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -807,6 +836,10 @@ struct kvm {
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
 #endif
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	/* Protected by slots_locks (for writes) and RCU (for reads) */
+	struct xarray mem_attr_array;
+#endif
 	char stats_id[KVM_STATS_NAME_SIZE];
 };
 
@@ -989,7 +1022,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
+	as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
 			lockdep_is_held(&kvm->slots_lock) ||
 			!refcount_read(&kvm->users_count));
@@ -1146,9 +1179,9 @@ enum kvm_mr_change {
 };
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+			  const struct kvm_userspace_memory_region2 *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
+			    const struct kvm_userspace_memory_region2 *mem);
 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,
@@ -1392,10 +1425,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end);
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm);
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
+void kvm_mmu_invalidate_end(struct kvm *kvm);
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1947,7 +1980,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
@@ -1970,9 +2003,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 	return 0;
 }
 
-static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
 					   unsigned long mmu_seq,
-					   unsigned long hva)
+					   gfn_t gfn)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
@@ -1981,10 +2014,20 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
 	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_invalidate_in_progress) &&
-	    hva >= kvm->mmu_invalidate_range_start &&
-	    hva < kvm->mmu_invalidate_range_end)
-		return 1;
+	if (unlikely(kvm->mmu_invalidate_in_progress)) {
+		/*
+		 * Dropping mmu_lock after bumping mmu_invalidate_in_progress
+		 * but before updating the range is a KVM bug.
+		 */
+		if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
+				 kvm->mmu_invalidate_range_end == INVALID_GPA))
+			return 1;
+
+		if (gfn >= kvm->mmu_invalidate_range_start &&
+		    gfn < kvm->mmu_invalidate_range_end)
+			return 1;
+	}
+
 	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
@@ -2318,4 +2361,57 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 /* Max number of entries allowed for each kvm dirty ring */
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
+static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						 gpa_t gpa, gpa_t size,
+						 bool is_write, bool is_exec,
+						 bool is_private)
+{
+	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+	vcpu->run->memory_fault.gpa = gpa;
+	vcpu->run->memory_fault.size = size;
+
+	/* RWX flags are not (yet) defined or communicated to userspace. */
+	vcpu->run->memory_fault.flags = 0;
+	if (is_private)
+		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
+}
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+	return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range);
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
+	       kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+#else
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return false;
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
+#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);
+#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_BUG_ON(1, kvm);
+	return -EIO;
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif