Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) client-ip=23.128.96.37;
Message-ID: <17947d72-22fb-b600-aada-c5a4008e3995@intel.com>
Date:   Fri, 15 Sep 2023 14:59:23 +0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:102.0) Gecko/20100101
 Firefox/102.0 Thunderbird/102.15.1
Subject: Re: [RFC PATCH v12 06/33] KVM: Introduce KVM_SET_USER_MEMORY_REGION2
Content-Language: en-US
To:     Sean Christopherson <seanjc@google.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Marc Zyngier <maz@kernel.org>,
        Oliver Upton <oliver.upton@linux.dev>,
        Huacai Chen <chenhuacai@kernel.org>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Anup Patel <anup@brainfault.org>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        "Matthew Wilcox (Oracle)" <willy@infradead.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Paul Moore <paul@paul-moore.com>,
        James Morris <jmorris@namei.org>,
        "Serge E. Hallyn" <serge@hallyn.com>
Cc:     kvm@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
        kvmarm@lists.linux.dev, linux-mips@vger.kernel.org,
        linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org,
        linux-riscv@lists.infradead.org, linux-fsdevel@vger.kernel.org,
        linux-mm@kvack.org, linux-security-module@vger.kernel.org,
        linux-kernel@vger.kernel.org,
        Chao Peng <chao.p.peng@linux.intel.com>,
        Fuad Tabba <tabba@google.com>,
        Jarkko Sakkinen <jarkko@kernel.org>,
        Anish Moorthy <amoorthy@google.com>,
        Yu Zhang <yu.c.zhang@linux.intel.com>,
        Isaku Yamahata <isaku.yamahata@intel.com>,
        Xu Yilun <yilun.xu@intel.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Vishal Annapurve <vannapurve@google.com>,
        Ackerley Tng <ackerleytng@google.com>,
        Maciej Szmigiero <mail@maciej.szmigiero.name>,
        David Hildenbrand <david@redhat.com>,
        Quentin Perret <qperret@google.com>,
        Michael Roth <michael.roth@amd.com>,
        Wang <wei.w.wang@intel.com>,
        Liam Merwick <liam.merwick@oracle.com>,
        Isaku Yamahata <isaku.yamahata@gmail.com>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
References: <20230914015531.1419405-1-seanjc@google.com>
 <20230914015531.1419405-7-seanjc@google.com>
From:   Xiaoyao Li <xiaoyao.li@intel.com>
In-Reply-To: <20230914015531.1419405-7-seanjc@google.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 9/14/2023 9:55 AM, Sean Christopherson wrote:
> Introduce a "version 2" of KVM_SET_USER_MEMORY_REGION so that additional
> information can be supplied without setting userspace up to fail.  The
> padding in the new kvm_userspace_memory_region2 structure will be used to
> pass a file descriptor in addition to the userspace_addr, i.e. allow
> userspace to point at a file descriptor and map memory into a guest that
> is NOT mapped into host userspace.
> 
> Alternatively, KVM could simply add "struct kvm_userspace_memory_region2"
> without a new ioctl(), but as Paolo pointed out, adding a new ioctl()
> makes detection of bad flags a bit more robust, e.g. if the new fd field
> is guarded only by a flag and not a new ioctl(), then a userspace bug
> (setting a "bad" flag) would generate out-of-bounds access instead of an
> -EINVAL error.
> 
> Cc: Jarkko Sakkinen <jarkko@kernel.org> > Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>

Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>

> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
>   arch/x86/kvm/x86.c       |  2 +-
>   include/linux/kvm_host.h |  4 ++--
>   include/uapi/linux/kvm.h | 13 +++++++++++++
>   virt/kvm/kvm_main.c      | 38 ++++++++++++++++++++++++++++++--------
>   4 files changed, 46 insertions(+), 11 deletions(-)
> 
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 6c9c81e82e65..8356907079e1 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -12447,7 +12447,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
>   	}
>   
>   	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
> -		struct kvm_userspace_memory_region m;
> +		struct kvm_userspace_memory_region2 m;
>   
>   		m.slot = id | (i << 16);
>   		m.flags = 0;
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 5faba69403ac..4e741ff27af3 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -1146,9 +1146,9 @@ enum kvm_mr_change {
>   };
>   
>   int kvm_set_memory_region(struct kvm *kvm,
> -			  const struct kvm_userspace_memory_region *mem);
> +			  const struct kvm_userspace_memory_region2 *mem);
>   int __kvm_set_memory_region(struct kvm *kvm,
> -			    const struct kvm_userspace_memory_region *mem);
> +			    const struct kvm_userspace_memory_region2 *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 13065dd96132..bd1abe067f28 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -95,6 +95,16 @@ struct kvm_userspace_memory_region {
>   	__u64 userspace_addr; /* start of the userspace allocated memory */
>   };
>   
> +/* for KVM_SET_USER_MEMORY_REGION2 */
> +struct kvm_userspace_memory_region2 {
> +	__u32 slot;
> +	__u32 flags;
> +	__u64 guest_phys_addr;
> +	__u64 memory_size;
> +	__u64 userspace_addr;
> +	__u64 pad[16];
> +};
> +
>   /*
>    * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
>    * userspace, other bits are reserved for kvm internal use which are defined
> @@ -1192,6 +1202,7 @@ struct kvm_ppc_resize_hpt {
>   #define KVM_CAP_COUNTER_OFFSET 227
>   #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
>   #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
> +#define KVM_CAP_USER_MEMORY2 230
>   
>   #ifdef KVM_CAP_IRQ_ROUTING
>   
> @@ -1473,6 +1484,8 @@ struct kvm_vfio_spapr_tce {
>   					struct kvm_userspace_memory_region)
>   #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
>   #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
> +#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
> +					 struct kvm_userspace_memory_region2)
>   
>   /* enable ucontrol for s390 */
>   struct kvm_s390_ucas_mapping {
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 8d21757cd5e9..7c0e38752526 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -1571,7 +1571,7 @@ 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_userspace_memory_region2 *mem)
>   {
>   	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
>   
> @@ -1973,7 +1973,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
>    * Must be called holding kvm->slots_lock for write.
>    */
>   int __kvm_set_memory_region(struct kvm *kvm,
> -			    const struct kvm_userspace_memory_region *mem)
> +			    const struct kvm_userspace_memory_region2 *mem)
>   {
>   	struct kvm_memory_slot *old, *new;
>   	struct kvm_memslots *slots;
> @@ -2077,7 +2077,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
>   EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
>   
>   int kvm_set_memory_region(struct kvm *kvm,
> -			  const struct kvm_userspace_memory_region *mem)
> +			  const struct kvm_userspace_memory_region2 *mem)
>   {
>   	int r;
>   
> @@ -2089,7 +2089,7 @@ int kvm_set_memory_region(struct kvm *kvm,
>   EXPORT_SYMBOL_GPL(kvm_set_memory_region);
>   
>   static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
> -					  struct kvm_userspace_memory_region *mem)
> +					  struct kvm_userspace_memory_region2 *mem)
>   {
>   	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
>   		return -EINVAL;
> @@ -4559,6 +4559,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
>   {
>   	switch (arg) {
>   	case KVM_CAP_USER_MEMORY:
> +	case KVM_CAP_USER_MEMORY2:
>   	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
>   	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
>   	case KVM_CAP_INTERNAL_ERROR_DATA:
> @@ -4814,6 +4815,14 @@ 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_userspace_memory_region, field) !=		\
> +		     offsetof(struct kvm_userspace_memory_region2, field));	\
> +	BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) !=		\
> +		     sizeof_field(struct kvm_userspace_memory_region2, field));	\
> +} while (0)
> +
>   static long kvm_vm_ioctl(struct file *filp,
>   			   unsigned int ioctl, unsigned long arg)
>   {
> @@ -4836,15 +4845,28 @@ static long kvm_vm_ioctl(struct file *filp,
>   		r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
>   		break;
>   	}
> +	case KVM_SET_USER_MEMORY_REGION2:
>   	case KVM_SET_USER_MEMORY_REGION: {
> -		struct kvm_userspace_memory_region kvm_userspace_mem;
> +		struct kvm_userspace_memory_region2 mem;
> +		unsigned long size;
> +
> +		if (ioctl == KVM_SET_USER_MEMORY_REGION)
> +			size = sizeof(struct kvm_userspace_memory_region);
> +		else
> +			size = sizeof(struct kvm_userspace_memory_region2);
> +
> +		/* Ensure the common parts of the two structs are identical. */
> +		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);
>   
>   		r = -EFAULT;
> -		if (copy_from_user(&kvm_userspace_mem, argp,
> -						sizeof(kvm_userspace_mem)))
> +		if (copy_from_user(&mem, argp, size))
>   			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: {