Re: [PATCH v6 4/8] KVM: Extend the memslot to support fd-based private memory
From: Sean Christopherson
Date: Fri Jun 17 2022 - 16:52:33 EST
On Thu, May 19, 2022, Chao Peng wrote:
> @@ -653,12 +662,12 @@ struct kvm_irq_routing_table {
> };
> #endif
>
> -#ifndef KVM_PRIVATE_MEM_SLOTS
> -#define KVM_PRIVATE_MEM_SLOTS 0
> +#ifndef KVM_INTERNAL_MEM_SLOTS
> +#define KVM_INTERNAL_MEM_SLOTS 0
> #endif
This rename belongs in a separate patch.
> #define KVM_MEM_SLOTS_NUM SHRT_MAX
> -#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)
> +#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
>
> #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
> static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
> @@ -1087,9 +1096,9 @@ enum kvm_mr_change {
> };
>
> int kvm_set_memory_region(struct kvm *kvm,
> - const struct kvm_userspace_memory_region *mem);
> + const struct kvm_user_mem_region *mem);
> int __kvm_set_memory_region(struct kvm *kvm,
> - const struct kvm_userspace_memory_region *mem);
> + const struct kvm_user_mem_region *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,
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index e10d131edd80..28cacd3656d4 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -103,6 +103,29 @@ struct kvm_userspace_memory_region {
> __u64 userspace_addr; /* start of the userspace allocated memory */
> };
>
> +struct kvm_userspace_memory_region_ext {
> + struct kvm_userspace_memory_region region;
> + __u64 private_offset;
> + __u32 private_fd;
> + __u32 pad1;
> + __u64 pad2[14];
> +};
> +
> +#ifdef __KERNEL__
> +/* Internal helper, the layout must match above user visible structures */
It's worth explicity calling out which structureso this aliases. And rather than
add a comment about the layout needing to match that, enforce it in code. I
personally wouldn't bother with an expolicit comment about the layout, IMO that's
a fairly obvious implication of aliasing.
/*
* kvm_user_mem_region is a kernel-only alias of kvm_userspace_memory_region_ext
* that "unpacks" kvm_userspace_memory_region so that KVM can directly access
* all fields from the top-level "extended" region.
*/
And I think it's in this patch that you missed a conversion to the alias, in the
prototype for check_memory_region_flags() (looks like it gets fixed up later in
the series).
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0f81bf0407be..8765b334477d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1466,7 +1466,7 @@ static void kvm_replace_memslot(struct kvm *kvm,
}
}
-static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+static int check_memory_region_flags(const struct kvm_user_mem_region *mem)
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
@@ -4514,6 +4514,33 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
return fd;
}
+#define SANITY_CHECK_MEM_REGION_FIELD(field) \
+do { \
+ BUILD_BUG_ON(offsetof(struct kvm_user_mem_region, field) != \
+ offsetof(struct kvm_userspace_memory_region, field)); \
+ BUILD_BUG_ON(sizeof_field(struct kvm_user_mem_region, field) != \
+ sizeof_field(struct kvm_userspace_memory_region, field)); \
+} while (0)
+
+#define SANITY_CHECK_MEM_REGION_EXT_FIELD(field) \
+do { \
+ BUILD_BUG_ON(offsetof(struct kvm_user_mem_region, field) != \
+ offsetof(struct kvm_userspace_memory_region_ext, field)); \
+ BUILD_BUG_ON(sizeof_field(struct kvm_user_mem_region, field) != \
+ sizeof_field(struct kvm_userspace_memory_region_ext, field)); \
+} while (0)
+
+static void kvm_sanity_check_user_mem_region_alias(void)
+{
+ SANITY_CHECK_MEM_REGION_FIELD(slot);
+ SANITY_CHECK_MEM_REGION_FIELD(flags);
+ SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
+ SANITY_CHECK_MEM_REGION_FIELD(memory_size);
+ SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
+ SANITY_CHECK_MEM_REGION_EXT_FIELD(private_offset);
+ SANITY_CHECK_MEM_REGION_EXT_FIELD(private_fd);
+}
+
static long kvm_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -4541,6 +4568,8 @@ static long kvm_vm_ioctl(struct file *filp,
unsigned long size;
u32 flags;
+ kvm_sanity_check_user_mem_region_alias();
+
memset(&mem, 0, sizeof(mem));
r = -EFAULT;
> +struct kvm_user_mem_region {
> + __u32 slot;
> + __u32 flags;
> + __u64 guest_phys_addr;
> + __u64 memory_size;
> + __u64 userspace_addr;
> + __u64 private_offset;
> + __u32 private_fd;
> + __u32 pad1;
> + __u64 pad2[14];
> +};
> +#endif
> +
> /*
> * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
> * other bits are reserved for kvm internal use which are defined in
> @@ -110,6 +133,7 @@ struct kvm_userspace_memory_region {
> */
> #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
> #define KVM_MEM_READONLY (1UL << 1)
> +#define KVM_MEM_PRIVATE (1UL << 2)
Hmm, KVM_MEM_PRIVATE is technically wrong now that a "private" memslot maps private
and/or shared memory. Strictly speaking, we don't actually need a new flag. Valid
file descriptors must be >=0, so the logic for specifying a memslot that can be
converted between private and shared could be that "(int)private_fd < 0" means
"not convertible", i.e. derive the flag from private_fd.
And looking at the two KVM consumers of the flag, via kvm_slot_is_private(), they're
both wrong. Both kvm_faultin_pfn() and kvm_mmu_max_mapping_level() should operate
on the _fault_, not the slot. So it would actually be a positive to not have an easy
way to query if a slot supports conversion.
> /* for KVM_IRQ_LINE */
> struct kvm_irq_level {
...
> + if (flags & KVM_MEM_PRIVATE) {
An added bonus of dropping KVM_MEM_PRIVATE is that these checks go away.
> + r = -EINVAL;
> + goto out;
> + }
> +
> + size = sizeof(struct kvm_userspace_memory_region);
> +
> + if (copy_from_user(&mem, argp, size))
> + goto out;
> +
> + r = -EINVAL;
> + if ((flags ^ mem.flags) & KVM_MEM_PRIVATE)
> goto out;
>
> - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
> + r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
> break;
> }
> case KVM_GET_DIRTY_LOG: {
> --
> 2.25.1
>