Re: [PATCH 2/6] KVM: Add KVM_PRE_FAULT_MEMORY vcpu ioctl to pre-populate guest memory

[Binbin Wu <binbin.wu@linux.intel.com>]

On 4/19/2024 4:59 PM, Paolo Bonzini wrote:
> From: Isaku Yamahata <isaku.yamahata@intel.com>
>
> Add a new ioctl KVM_PRE_FAULT_MEMORY in the KVM common code. It iterates on the
> memory range and calls the arch-specific function.  Add stub arch function
> as a weak symbol.
>
> Suggested-by: Sean Christopherson <seanjc@google.com>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> Reviewed-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
> Message-ID: <819322b8f25971f2b9933bfa4506e618508ad782.1712785629.git.isaku.yamahata@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   include/linux/kvm_host.h |  5 ++++
>   include/uapi/linux/kvm.h | 10 +++++++
>   virt/kvm/Kconfig         |  3 ++
>   virt/kvm/kvm_main.c      | 63 ++++++++++++++++++++++++++++++++++++++++
>   4 files changed, 81 insertions(+)
>
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 8dea11701ab2..9e9943e5e37c 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -2478,4 +2478,9 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages
>   void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
>   #endif
>   
> +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
> +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
> +				    struct kvm_pre_fault_memory *range);
> +#endif
> +
>   #endif
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 2190adbe3002..917d2964947d 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -917,6 +917,7 @@ struct kvm_enable_cap {
>   #define KVM_CAP_MEMORY_ATTRIBUTES 233
>   #define KVM_CAP_GUEST_MEMFD 234
>   #define KVM_CAP_VM_TYPES 235
> +#define KVM_CAP_PRE_FAULT_MEMORY 236
>   
>   struct kvm_irq_routing_irqchip {
>   	__u32 irqchip;
> @@ -1548,4 +1549,13 @@ struct kvm_create_guest_memfd {
>   	__u64 reserved[6];
>   };
>   
> +#define KVM_PRE_FAULT_MEMORY	_IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory)
> +
> +struct kvm_pre_fault_memory {
> +	__u64 gpa;
> +	__u64 size;
> +	__u64 flags;
> +	__u64 padding[5];
> +};
> +
>   #endif /* __LINUX_KVM_H */
> diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
> index 754c6c923427..b14e14cdbfb9 100644
> --- a/virt/kvm/Kconfig
> +++ b/virt/kvm/Kconfig
> @@ -67,6 +67,9 @@ config HAVE_KVM_INVALID_WAKEUPS
>   config KVM_GENERIC_DIRTYLOG_READ_PROTECT
>          bool
>   
> +config KVM_GENERIC_PRE_FAULT_MEMORY
> +       bool
> +
>   config KVM_COMPAT
>          def_bool y
>          depends on KVM && COMPAT && !(S390 || ARM64 || RISCV)
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 38b498669ef9..51d8dbe7e93b 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -4379,6 +4379,55 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
>   	return fd;
>   }
>   
> +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
> +static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
> +				     struct kvm_pre_fault_memory *range)
> +{
> +	int idx;
> +	long r;
> +	u64 full_size;
> +
> +	if (range->flags)
> +		return -EINVAL;
> +
> +	if (!PAGE_ALIGNED(range->gpa) ||
> +	    !PAGE_ALIGNED(range->size) ||
> +	    range->gpa + range->size <= range->gpa)
> +		return -EINVAL;
> +
> +	if (!range->size)
> +		return 0;

range->size equals 0 can be covered by "range->gpa + range->size <= 
range->gpa"

If we want to return success when size is 0 (, though I am not sure it's 
needed),
we need to use "range->gpa + range->size < range->gpa" instead.


> +
> +	vcpu_load(vcpu);
> +	idx = srcu_read_lock(&vcpu->kvm->srcu);
> +
> +	full_size = range->size;
> +	do {
> +		if (signal_pending(current)) {
> +			r = -EINTR;
> +			break;
> +		}
> +
> +		r = kvm_arch_vcpu_pre_fault_memory(vcpu, range);
> +		if (r < 0)
> +			break;
> +
> +		if (WARN_ON_ONCE(r == 0))
> +			break;
> +
> +		range->size -= r;
> +		range->gpa += r;
> +		cond_resched();
> +	} while (range->size);
> +
> +	srcu_read_unlock(&vcpu->kvm->srcu, idx);
> +	vcpu_put(vcpu);
> +
> +	/* Return success if at least one page was mapped successfully.  */
> +	return full_size == range->size ? r : 0;
> +}
> +#endif
> +
>   static long kvm_vcpu_ioctl(struct file *filp,
>   			   unsigned int ioctl, unsigned long arg)
>   {
> @@ -4580,6 +4629,20 @@ static long kvm_vcpu_ioctl(struct file *filp,
>   		r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
>   		break;
>   	}
> +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
> +	case KVM_PRE_FAULT_MEMORY: {
> +		struct kvm_pre_fault_memory range;
> +
> +		r = -EFAULT;
> +		if (copy_from_user(&range, argp, sizeof(range)))
> +			break;
> +		r = kvm_vcpu_pre_fault_memory(vcpu, &range);
> +		/* Pass back leftover range. */
> +		if (copy_to_user(argp, &range, sizeof(range)))
> +			r = -EFAULT;
> +		break;
> +	}
> +#endif
>   	default:
>   		r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
>   	}