Merge branch 'guest-memfd-mmap' into HEAD

Add support for host userspace mapping of guest_memfd-backed memory for VM
types that do NOT use support KVM_MEMORY_ATTRIBUTE_PRIVATE (which isn't
precisely the same thing as CoCo VMs, since x86's SEV-MEM and SEV-ES have
no way to detect private vs. shared).

mmap() support paves the way for several evolving KVM use cases:

* Allows VMMs like Firecracker to run guests entirely backed by
  guest_memfd [1]. This provides a unified memory management model for
  both confidential and non-confidential guests, simplifying VMM design.

* Enhanced Security via direct map removal: When combined with Patrick's
  series for direct map removal [2], this provides additional hardening
  against Spectre-like transient execution attacks by eliminating the
  need for host kernel direct maps of guest memory.

* Lays the groundwork for *restricted* mmap() support for guest_memfd-backed
  memory on CoCo platforms [3] that permit in-place sharing of guest memory
   with the host.

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

2 files changed, 25 insertions, 15 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 15656b7fba6c..8b47891adca1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -52,9 +52,10 @@
 /*
  * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally
  * used in kvm, other bits are visible for userspace which are defined in
- * include/linux/kvm_h.
+ * include/uapi/linux/kvm.h.
  */
-#define KVM_MEMSLOT_INVALID	(1UL << 16)
+#define KVM_MEMSLOT_INVALID			(1UL << 16)
+#define KVM_MEMSLOT_GMEM_ONLY			(1UL << 17)
 
 /*
  * Bit 63 of the memslot generation number is an "update in-progress flag",
@@ -602,7 +603,7 @@ struct kvm_memory_slot {
 	short id;
 	u16 as_id;
 
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#ifdef CONFIG_KVM_GUEST_MEMFD
 	struct {
 		/*
 		 * Writes protected by kvm->slots_lock.  Acquiring a
@@ -615,7 +616,7 @@ struct kvm_memory_slot {
 #endif
 };
 
-static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+static inline bool kvm_slot_has_gmem(const struct kvm_memory_slot *slot)
 {
 	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
 }
@@ -719,17 +720,17 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 }
 #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)
+#ifndef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
 {
 	return false;
 }
 #endif
 
+#ifdef CONFIG_KVM_GUEST_MEMFD
+bool kvm_arch_supports_gmem_mmap(struct kvm *kvm);
+#endif
+
 #ifndef kvm_arch_has_readonly_mem
 static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
 {
@@ -860,7 +861,7 @@ struct kvm {
 	struct notifier_block pm_notifier;
 #endif
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
-	/* Protected by slots_locks (for writes) and RCU (for reads) */
+	/* Protected by slots_lock (for writes) and RCU (for reads) */
 	struct xarray mem_attr_array;
 #endif
 	char stats_id[KVM_STATS_NAME_SIZE];
@@ -2490,6 +2491,14 @@ static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
 		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
 }
 
+static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
+{
+	if (!IS_ENABLED(CONFIG_KVM_GUEST_MEMFD))
+		return false;
+
+	return slot->flags & KVM_MEMSLOT_GMEM_ONLY;
+}
+
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
 {
@@ -2505,8 +2514,7 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 
 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;
+	return kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
 }
 #else
 static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
@@ -2515,7 +2523,7 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 }
 #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 
-#ifdef CONFIG_KVM_PRIVATE_MEM
+#ifdef CONFIG_KVM_GUEST_MEMFD
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
 		     int *max_order);
@@ -2528,13 +2536,13 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 	KVM_BUG_ON(1, kvm);
 	return -EIO;
 }
-#endif /* CONFIG_KVM_PRIVATE_MEM */
+#endif /* CONFIG_KVM_GUEST_MEMFD */
 
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
 #endif
 
-#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE
 /**
  * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
  *
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f0f0d49d2544..6efa98a57ec1 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -962,6 +962,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_ARM_EL2_E2H0 241
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
+#define KVM_CAP_GUEST_MEMFD_MMAP 244
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1598,6 +1599,7 @@ struct kvm_memory_attributes {
 #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
 
 #define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+#define GUEST_MEMFD_FLAG_MMAP	(1ULL << 0)
 
 struct kvm_create_guest_memfd {
 	__u64 size;