Re: [PATCH v2 05/11] KVM: s390: Add optional storage key checking to MEMOP IOCTL

[Christian Borntraeger <borntraeger@linux.ibm.com>]

Am 07.02.22 um 17:59 schrieb Janis Schoetterl-Glausch:
> User space needs a mechanism to perform key checked accesses when
> emulating instructions.
> 
> The key can be passed as an additional argument.
> Having an additional argument is flexible, as user space can
> pass the guest PSW's key, in order to make an access the same way the
> CPU would, or pass another key if necessary.
> 
> Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
> Acked-by: Janosch Frank <frankja@linux.ibm.com>
> Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
> ---
>   arch/s390/kvm/kvm-s390.c | 49 +++++++++++++++++++++++++++++++---------
>   include/uapi/linux/kvm.h |  8 +++++--
>   2 files changed, 44 insertions(+), 13 deletions(-)
> 
> diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
> index cf347e1a4f17..71e61fb3f0d9 100644
> --- a/arch/s390/kvm/kvm-s390.c
> +++ b/arch/s390/kvm/kvm-s390.c
> @@ -32,6 +32,7 @@
>   #include <linux/sched/signal.h>
>   #include <linux/string.h>
>   #include <linux/pgtable.h>
> +#include <linux/bitfield.h>
>   
>   #include <asm/asm-offsets.h>
>   #include <asm/lowcore.h>
> @@ -2359,6 +2360,11 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
>   	return r;
>   }
>   
> +static bool access_key_invalid(u8 access_key)
> +{
> +	return access_key > 0xf;
> +}
> +
>   long kvm_arch_vm_ioctl(struct file *filp,
>   		       unsigned int ioctl, unsigned long arg)
>   {
> @@ -4687,34 +4693,54 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
>   				  struct kvm_s390_mem_op *mop)
>   {
>   	void __user *uaddr = (void __user *)mop->buf;
> +	u8 access_key = 0, ar = 0;
>   	void *tmpbuf = NULL;
> +	bool check_reserved;
>   	int r = 0;
>   	const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
> -				    | KVM_S390_MEMOP_F_CHECK_ONLY;
> +				    | KVM_S390_MEMOP_F_CHECK_ONLY
> +				    | KVM_S390_MEMOP_F_SKEY_PROTECTION;
>   
> -	if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size)
> +	if (mop->flags & ~supported_flags || !mop->size)
>   		return -EINVAL;
> -
>   	if (mop->size > MEM_OP_MAX_SIZE)
>   		return -E2BIG;
> -
>   	if (kvm_s390_pv_cpu_is_protected(vcpu))
>   		return -EINVAL;
> -
>   	if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
>   		tmpbuf = vmalloc(mop->size);
>   		if (!tmpbuf)
>   			return -ENOMEM;
>   	}
> +	ar = mop->ar;
> +	mop->ar = 0;

Why this assignment to 0?

> +	if (ar >= NUM_ACRS)
> +		return -EINVAL;
> +	if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) {
> +		access_key = mop->key;
> +		mop->key = 0;

and this? I think we can leave mop unchanged.

In fact, why do we add the ar and access_key variable?
This breaks the check from above (if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size))  into two checks
and it will create a memleak for tmpbuf.

Simply use mop->key and mop->ar below and get rid of the local variables.
The structure has no concurrency and gcc will handle that just as the local variable.

Other than that this looks good.
> +		if (access_key_invalid(access_key))
> +			return -EINVAL;
> +	}
> +	/*
> +	 * Check that reserved/unused == 0, but only for extensions,
> +	 * so we stay backward compatible.
> +	 * This gives us more design flexibility for future extensions, i.e.
> +	 * we can add functionality without adding a flag.
> +	 */
> +	check_reserved = mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION;
> +	if (check_reserved && memchr_inv(&mop->reserved, 0, sizeof(mop->reserved)))
> +		return -EINVAL;
>   
>   	switch (mop->op) {
>   	case KVM_S390_MEMOP_LOGICAL_READ:
>   		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
> -			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
> -					    mop->size, GACC_FETCH, 0);
> +			r = check_gva_range(vcpu, mop->gaddr, ar, mop->size,
> +					    GACC_FETCH, access_key);
>   			break;
>   		}
> -		r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
> +		r = read_guest_with_key(vcpu, mop->gaddr, ar, tmpbuf,
> +					mop->size, access_key);
>   		if (r == 0) {
>   			if (copy_to_user(uaddr, tmpbuf, mop->size))
>   				r = -EFAULT;
> @@ -4722,15 +4748,16 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
>   		break;
>   	case KVM_S390_MEMOP_LOGICAL_WRITE:
>   		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
> -			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
> -					    mop->size, GACC_STORE, 0);
> +			r = check_gva_range(vcpu, mop->gaddr, ar, mop->size,
> +					    GACC_STORE, access_key);
>   			break;
>   		}
>   		if (copy_from_user(tmpbuf, uaddr, mop->size)) {
>   			r = -EFAULT;
>   			break;
>   		}
> -		r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
> +		r = write_guest_with_key(vcpu, mop->gaddr, ar, tmpbuf,
> +					 mop->size, access_key);
>   		break;
>   	}
>   
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index b46bcdb0cab1..5771b026fbc0 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -562,9 +562,12 @@ struct kvm_s390_mem_op {
>   	__u32 op;		/* type of operation */
>   	__u64 buf;		/* buffer in userspace */
>   	union {
> -		__u8 ar;	/* the access register number */
> +		struct {
> +			__u8 ar;	/* the access register number */
> +			__u8 key;	/* access key to use for storage key protection */
> +		};
>   		__u32 sida_offset; /* offset into the sida */
> -		__u8 reserved[32]; /* should be set to 0 */
> +		__u8 reserved[32]; /* must be set to 0 */
>   	};
>   };