Re: [PATCH v1 2/9] KVM: s390: Extend MEM_OP ioctl by storage key checked cmpxchg

On 30/09/2022 23.07, Janis Schoetterl-Glausch wrote:

User space can use the MEM_OP ioctl to make storage key checked reads and writes to the guest, however, it has no way of performing atomic, key checked, accesses to the guest. Extend the MEM_OP ioctl in order to allow for this, by adding a cmpxchg mode. For now, support this mode for absolute accesses only.

This mode can be use, for example, to set the device-state-change indicator and the adapter-local-summary indicator atomically.

Signed-off-by: Janis Schoetterl-Glausch scgl@linux.ibm.com

...

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index eed0315a77a6..b856705f3f6b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -580,7 +580,9 @@ struct kvm_translation { struct kvm_s390_mem_op { /* in */ __u64 gaddr; /* the guest address */

• /* in & out */ __u64 flags; /* flags */
• /* in */ __u32 size; /* amount of bytes */ __u32 op; /* type of operation */ __u64 buf; /* buffer in userspace */

@@ -588,6 +590,8 @@ struct kvm_s390_mem_op { struct { __u8 ar; /* the access register number */ __u8 key; /* access key, ignored if flag unset */

• 	/* in & out */
  

• 	__u64 old[2];	/* ignored if flag unset */
  

The alignment looks very unfortunate now ... could you please add a "__u8 pad[6]" or "__u8 pad[14]" in front of the new field?

};
__u32 sida_offset; /* offset into the sida */
__u8 reserved[32]; /* ignored */

@@ -604,6 +608,7 @@ struct kvm_s390_mem_op { #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) #define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) +#define KVM_S390_MEMOP_F_CMPXCHG (1ULL << 3) /* for KVM_INTERRUPT */ struct kvm_interrupt { diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 9408d6cc8e2c..a1cb66ae0995 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -206,6 +206,10 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, unsigned long len, enum gacc_mode mode); +int cmpxchg_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, int len,

• 	       unsigned __int128 *old,
  

• 	       unsigned __int128 new, u8 access_key);
  

• /**
  • write_guest_with_key - copy data from kernel space to guest space
  • @vcpu: virtual cpu

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 0243b6e38d36..c0e490ecc372 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1161,6 +1161,62 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, return rc; } +/**

• • cmpxchg_guest_abs_with_key() - Perform cmpxchg on guest absolute address.
• • @kvm: Virtual machine instance.
• • @gpa: Absolute guest address of the location to be changed.
• • @len: Operand length of the cmpxchg, required: 1 <= len <= 16. Providing a

• •   non power of two will result in failure.
    

• • @old_p: Pointer to old value. If the location at @gpa contains this value, the

• •     exchange will succeed. After calling cmpxchg_guest_abs_with_key() *@old
    

• •     contains the value at @gpa before the attempt to exchange the value.
    

• • @new: The value to place at @gpa.
• • @access_key: The access key to use for the guest access.
• • Atomically exchange the value at @gpa by @new, if it contains *@old.
• • Honors storage keys.
• • Return: * 0: successful exchange

• •     * 1: exchange unsuccessful
    

• •     * a program interruption code indicating the reason cmpxchg could
    

• •       not be attempted
    

• •     * -EINVAL: address misaligned or len not power of two
    

• */

+int cmpxchg_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, int len,

• 	       unsigned __int128 *old_p, unsigned __int128 new,
  

• 	       u8 access_key)
  

+{

• gfn_t gfn = gpa >> PAGE_SHIFT;
• struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
• bool writable;
• hva_t hva;
• int ret;
• if (!IS_ALIGNED(gpa, len))

• return -EINVAL;
  

• hva = gfn_to_hva_memslot_prot(slot, gfn, &writable);
• if (kvm_is_error_hva(hva))

• return PGM_ADDRESSING;
  

• /*

• * Check if it's a ro memslot, even tho that can't occur (they're unsupported).
  

Not everybody is used to read such abbreviated English ... I'd recommend to spell it rather properly (ro ==> read-only, tho ==> though)

• * Don't try to actually handle that case.
  

• */
  

• if (!writable)

• return -EOPNOTSUPP;
  

• hva += offset_in_page(gpa);
• ret = cmpxchg_user_key_size(len, (void __user *)hva, old_p, new, access_key);
• mark_page_dirty_in_slot(kvm, slot, gfn);
• /*

• * Assume that the fault is caused by key protection, the alternative
  

• * is that the user page is write protected.
  

• */
  

• if (ret == -EFAULT)

• ret = PGM_PROTECTION;
  

• return ret;

+}

• /**
  • guest_translate_address_with_key - translate guest logical into guest absolute address
  • @vcpu: virtual cpu

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b7ef0b71014d..d594d1318d2a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -576,7 +576,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_VCPU_RESETS: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_S390_DIAG318:

• case KVM_CAP_S390_MEM_OP_EXTENSION: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2:

@@ -590,6 +589,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_MEM_OP: r = MEM_OP_MAX_SIZE; break;

• case KVM_CAP_S390_MEM_OP_EXTENSION:

• r = 0x3;
  

Add a comment to explain that magic value 0x3 ?

• break;
  

  case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID:

Thomas