Thread (85 messages) flat view 85 messages, 8 authors, 10d ago
COOLING10d

[PATCH v12 09/45] KVM: guest_memfd: Stub in ability to enable in-place shared<=>private conversion

From: Ackerley Tng via B4 Relay <devnull+ackerleytng.google.com@kernel.org>
Date: 2026-08-31 00:25:38
Also in: b4-sent, kvm, linux-coco, linux-doc, linux-kselftest, linux-mm, lkml
Subsystem: documentation, kernel virtual machine (kvm), kvm guest_memfd, the rest · Maintainers: Jonathan Corbet, Paolo Bonzini, Sean Christopherson, Linus Torvalds

From: Sean Christopherson <seanjc@google.com>

Stub in global variable to enable in-place guest_memfd private<=>shared
memory conversion, which will eventually be exposed to userspace via a
module param, and wire up the __kvm_is_private_gfn() static call to the
guest_memfd version when in-place conversion is enabled, i.e. when gmem is
the sole authority on private vs. shared memory.

Cc: Fuad Tabba <redacted>
Cc: Xiaoyao Li <redacted>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Ackerley Tng <redacted>
Signed-off-by: Ackerley Tng <redacted>
---
 Documentation/virt/kvm/api.rst |  7 +++++++
 include/linux/kvm_host.h       |  6 ++++++
 virt/kvm/guest_memfd.c         | 26 ++++++++++++++++++++++++++
 virt/kvm/kvm_main.c            | 12 +++++++++++-
 4 files changed, 50 insertions(+), 1 deletion(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index e0430cc750c9e..90a29424c54c8 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6382,6 +6382,11 @@ KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated
 on-demand.
 
 When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes
+userspace_addr vs. guest_memfd, based on the state in guest_memfd, which is the
+sole authority on private vs. shared memory.  See :ref:`KVM_CREATE_GUEST_MEMFD`
+to find out more about the creation-time shared/private status.
+
+If in-place conversion is disabled, KVM selects shared vs. private, i.e consumes
 userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE
 state.  At VM creation time, all memory is shared, i.e. the PRIVATE attribute
 is '0' for all gfns.  Userspace can control whether memory is shared/private by
@@ -6429,6 +6434,8 @@ the state of a gfn/page as needed.
 
 The "flags" field is reserved for future extensions and must be '0'.
 
+.. _KVM_CREATE_GUEST_MEMFD:
+
 4.142 KVM_CREATE_GUEST_MEMFD
 ----------------------------
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3579feb631775..b0110143d2ff8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2580,6 +2580,8 @@ static inline bool kvm_vm_is_private_gfn(struct kvm *kvm, gfn_t gfn)
 #endif  /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
 
 #ifdef kvm_arch_has_private_mem
+extern bool gmem_in_place_conversion;
+
 typedef bool (kvm_is_private_gfn_t)(struct kvm *kvm, gfn_t gfn);
 DECLARE_STATIC_CALL(__kvm_is_private_gfn, kvm_is_private_gfn_t);
 
@@ -2588,6 +2590,8 @@ static inline bool kvm_is_private_gfn(struct kvm *kvm, gfn_t gfn)
 	return static_call(__kvm_is_private_gfn)(kvm, gfn);
 }
 #else
+#define gmem_in_place_conversion false
+
 static inline bool kvm_is_private_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	return false;
@@ -2595,6 +2599,8 @@ static inline bool kvm_is_private_gfn(struct kvm *kvm, gfn_t gfn)
 #endif /* kvm_arch_has_private_mem */
 
 #ifdef CONFIG_KVM_GUEST_MEMFD
+bool kvm_gmem_is_private_gfn(struct kvm *kvm, gfn_t gfn);
+
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
 #else
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index ce5efcacda36e..cd966eef45b69 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -478,6 +478,32 @@ static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+bool kvm_gmem_is_private_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+	struct inode *inode;
+
+	if (!slot)
+		return 0;
+
+	CLASS(gmem_get_file, file)(slot);
+	if (!file)
+		return 0;
+
+	inode = file_inode(file);
+
+	/*
+	 * Rely on the maple tree's internal RCU lock to ensure a stable result.
+	 * This result can become stale as soon as the lock is dropped, so the
+	 * caller _must_ protect consumption of private vs. shared either by
+	 * holding guest_memfd's invalidate lock for the entire duration, or by
+	 * checking mmu_invalidate_retry_gfn() under mmu_lock to serialize
+	 * against concurrent attribute updates.
+	 */
+	return kvm_gmem_is_private_mem(inode, kvm_gmem_get_index(slot, gfn));
+}
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_is_private_gfn);
+
 static struct file_operations kvm_gmem_fops = {
 	.mmap		= kvm_gmem_mmap,
 	.open		= generic_file_open,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 78278730b2ae4..46d2e123448c2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -102,6 +102,10 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns_shrink);
 static bool __ro_after_init allow_unsafe_mappings;
 module_param(allow_unsafe_mappings, bool, 0444);
 
+#ifdef kvm_arch_has_private_mem
+bool __ro_after_init gmem_in_place_conversion = false;
+#endif
+
 /*
  * Ordering of locks:
  *
@@ -2423,6 +2427,9 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
 static u64 kvm_supported_vm_mem_attributes(struct kvm *kvm)
 {
 #ifdef kvm_arch_has_private_mem
+	if (gmem_in_place_conversion)
+		return 0;
+
 	if (!kvm || kvm_arch_has_private_mem(kvm))
 		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
 #endif
@@ -2634,8 +2641,11 @@ EXPORT_STATIC_CALL_GPL(__kvm_is_private_gfn);
 
 static void kvm_init_memory_attributes(void)
 {
+	if (gmem_in_place_conversion)
+		static_call_update(__kvm_is_private_gfn, kvm_gmem_is_private_gfn);
 #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
-	static_call_update(__kvm_is_private_gfn, kvm_vm_is_private_gfn);
+	else
+		static_call_update(__kvm_is_private_gfn, kvm_vm_is_private_gfn);
 #endif
 }
 #else
-- 
2.55.0.897.gb25b4bd76c-goog

Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help