Re: [RFC PATCH v1 07/37] KVM: Introduce KVM_SET_MEMORY_ATTRIBUTES2
From: Ackerley Tng <hidden>
Date: 2025-10-22 16:51:52
Also in:
cgroups, kvm, linux-fsdevel, linux-kselftest, linux-mm, linux-trace-kernel, lkml
Subsystem:
documentation, kernel virtual machine (kvm), the rest · Maintainers:
Jonathan Corbet, Paolo Bonzini, Linus Torvalds
Steven Price [off-list ref] writes:
On 17/10/2025 21:11, Ackerley Tng wrote:quoted
[...snip...]@@ -5366,15 +5375,35 @@ static long kvm_vm_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES + case KVM_SET_MEMORY_ATTRIBUTES2: case KVM_SET_MEMORY_ATTRIBUTES: { - struct kvm_memory_attributes attrs; + struct kvm_memory_attributes2 attrs; + unsigned long size; + + if (ioctl == KVM_SET_MEMORY_ATTRIBUTES) { + /* + * Fields beyond struct kvm_userspace_memory_region shouldn't be + * accessed, but avoid leaking kernel memory in case of a bug. + */ + memset(&mem, 0, sizeof(mem));s/mem/attrs/gquoted
+ size = sizeof(struct kvm_set_memory_attributes); + } else { + size = sizeof(struct kvm_set_memory_attributes2);s/kvm_set_memory_attributes/kvm_memory_attributes/ (on both sizeof lines above and in the SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD macro).quoted
+ } + + /* Ensure the common parts of the two structs are identical. */ + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(slot); + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(flags); + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(guest_phys_addr); + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(memory_size); + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(userspace_addr);The fields are: * address * size * attributes * flags The list you've got appears to match struct kvm_userspace_memory_region - copy/paste error?
Yes I did copy/paste this from KVM_SET_USER_MEMORY_REGION2. Thanks for catching this! I missed out build-testing this with CONFIG_KVM_VM_MEMORY_ATTRIBUTES. I've done that and here's a replacement patch.
Thanks, Stevequoted
[...snip...]
From 31283972574bde2ffa1960d30c80286f8467c594 Mon Sep 17 00:00:00 2001 From: Ackerley Tng <redacted> Date: Thu, 16 Oct 2025 11:48:01 -0700 Subject: [PATCH] KVM: Introduce KVM_SET_MEMORY_ATTRIBUTES2 Introduce a "version 2" of KVM_SET_MEMORY_ATTRIBUTES to support returning information back to userspace. This new ioctl and structure will, in a later patch, be shared as a guest_memfd ioctl, where the padding in the new kvm_memory_attributes2 structure will be for writing the response from the guest_memfd ioctl to userspace. A new ioctl is necessary for these reasons: 1. KVM_SET_MEMORY_ATTRIBUTES is currently a write-only ioctl and does not allow userspace to read fields. There's nothing in code (yet?) that validates this, but using _IOWR for consistency would be prudent. 2. KVM_SET_MEMORY_ATTRIBUTES, when used as a guest_memfd ioctl, will need an additional field to provide userspace with more error details. Alternatively, a completely new ioctl could be defined, unrelated to KVM_SET_MEMORY_ATTRIBUTES, but using the same ioctl number and struct for the vm and guest_memfd ioctls streamlines the interface for userspace. In addition, any memory attributes, implemented on the vm or guest_memfd ioctl, can be easily shared with the other. Suggested-by: Sean Christopherson <seanjc@google.com> Change-Id: I50cd506d9a28bf68a90e659015603de579569bc1 Signed-off-by: Ackerley Tng <redacted> --- Documentation/virt/kvm/api.rst | 32 ++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 12 ++++++++++++ virt/kvm/kvm_main.c | 34 +++++++++++++++++++++++++++++++--- 3 files changed, 75 insertions(+), 3 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 754b662a453c3..a812769d79bf6 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst@@ -6355,6 +6355,8 @@ S390: Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set. Returns -EINVAL if called on a protected VM. +.. _KVM_SET_MEMORY_ATTRIBUTES: + 4.141 KVM_SET_MEMORY_ATTRIBUTES -------------------------------
@@ -6512,6 +6514,36 @@ the capability to be present. `flags` must currently be zero. +4.144 KVM_SET_MEMORY_ATTRIBUTES2 +--------------------------------- + +:Capability: KVM_CAP_MEMORY_ATTRIBUTES2 +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_memory_attributes2 (in/out) +:Returns: 0 on success, <0 on error + +KVM_SET_MEMORY_ATTRIBUTES2 is an extension to +KVM_SET_MEMORY_ATTRIBUTES that supports returning (writing) values to +userspace. The original (pre-extension) fields are shared with +KVM_SET_MEMORY_ATTRIBUTES identically. + +Attribute values are shared with KVM_SET_MEMORY_ATTRIBUTES. + +:: + + struct kvm_memory_attributes2 { + __u64 address; + __u64 size; + __u64 attributes; + __u64 flags; + __u64 reserved[4]; + }; + + #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) + +See also: :ref: `KVM_SET_MEMORY_ATTRIBUTES`. + .. _kvm_run:
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 52f6000ab0208..c300e38c7c9cd 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h@@ -963,6 +963,7 @@ struct kvm_enable_cap { #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 #define KVM_CAP_GUEST_MEMFD_FLAGS 244 +#define KVM_CAP_MEMORY_ATTRIBUTES2 245 struct kvm_irq_routing_irqchip { __u32 irqchip;
@@ -1617,4 +1618,15 @@ struct kvm_pre_fault_memory { __u64 padding[5]; }; +/* Available with KVM_CAP_MEMORY_ATTRIBUTES2 */ +#define KVM_SET_MEMORY_ATTRIBUTES2 _IOWR(KVMIO, 0xd6, struct kvm_memory_attributes2) + +struct kvm_memory_attributes2 { + __u64 address; + __u64 size; + __u64 attributes; + __u64 flags; + __u64 reserved[4]; +}; + #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 35166754a22b4..95aa51b334a70 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c@@ -2621,7 +2621,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, return r; } static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, - struct kvm_memory_attributes *attrs) + struct kvm_memory_attributes2 *attrs) { gfn_t start, end;
@@ -4959,6 +4959,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_DEVICE_CTRL: return 1; #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES + case KVM_CAP_MEMORY_ATTRIBUTES2: case KVM_CAP_MEMORY_ATTRIBUTES: if (!vm_memory_attributes) return 0;
@@ -5184,6 +5185,14 @@ do { \ sizeof_field(struct kvm_userspace_memory_region2, field)); \ } while (0) +#define SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(field) \ +do { \ + BUILD_BUG_ON(offsetof(struct kvm_memory_attributes, field) != \ + offsetof(struct kvm_memory_attributes2, field)); \ + BUILD_BUG_ON(sizeof_field(struct kvm_memory_attributes, field) != \ + sizeof_field(struct kvm_memory_attributes2, field)); \ +} while (0) + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) {
@@ -5366,15 +5375,34 @@ static long kvm_vm_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES + case KVM_SET_MEMORY_ATTRIBUTES2: case KVM_SET_MEMORY_ATTRIBUTES: { - struct kvm_memory_attributes attrs; + struct kvm_memory_attributes2 attrs; + unsigned long size; + + if (ioctl == KVM_SET_MEMORY_ATTRIBUTES) { + /* + * Fields beyond struct kvm_userspace_memory_region shouldn't be + * accessed, but avoid leaking kernel memory in case of a bug. + */ + memset(&attrs, 0, sizeof(attrs)); + size = sizeof(struct kvm_memory_attributes); + } else { + size = sizeof(struct kvm_memory_attributes2); + } + + /* Ensure the common parts of the two structs are identical. */ + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(address); + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(size); + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(attributes); + SANITY_CHECK_MEMORY_ATTRIBUTES_FIELD(flags); r = -ENOTTY; if (!vm_memory_attributes) goto out; r = -EFAULT; - if (copy_from_user(&attrs, argp, sizeof(attrs))) + if (copy_from_user(&attrs, argp, size)) goto out; r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs);
--
2.51.0.915.g61a8936c21-goog