Re: [PATCH v5 01/10] KVM: s390: Extend MEM_OP ioctl by storage key checked cmpxchg

On 1/10/23 21:26, 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

include/uapi/linux/kvm.h | 7 +++ arch/s390/kvm/gaccess.h | 3 ++ arch/s390/kvm/gaccess.c | 102 +++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/kvm-s390.c | 41 +++++++++++++++- 4 files changed, 151 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 55155e262646..452f43c1cc34 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -583,6 +583,8 @@ struct kvm_s390_mem_op { struct { __u8 ar; /* the access register number */ __u8 key; /* access key, ignored if flag unset */

• 	__u8 pad1[6];	/* ignored */
  

• 	__u64 old_addr;	/* ignored if flag unset */
  

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

@@ -599,6 +601,11 @@ 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) +/* flags specifying extension support */

Would that fit behind the bit shifts without getting into the "line too long" territory?

+#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG 0x2

\n please

+/* Non program exception return codes (pgm codes are 16 bit) */ +#define KVM_S390_MEMOP_R_NO_XCHG (1 << 16) /* for KVM_INTERRUPT */ struct kvm_interrupt { diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 9408d6cc8e2c..92a3b9fb31ec 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -206,6 +206,9 @@ 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,

• 	       __uint128_t *old, __uint128_t 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..6165e761a637 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1161,6 +1161,108 @@ 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_addr: 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
    

1 Access related program interruption code indicating the reason

cmpxchg could not be attempted

< 1 Kernel / input data error codes

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

• •     * -EAGAIN: transient failure (len 1 or 2)
    

• •     * -EOPNOTSUPP: read-only memslot (should never occur)
    

Would PGM_PROTECTED also make sense here instead of EOPNOTSUPP?

• */

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

• 	       __uint128_t *old_addr, __uint128_t 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 read-only memslot, even though that cannot occur
  

• * since those are unsupported.
  

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

• */
  

• if (!writable)

• return -EOPNOTSUPP;
  

[...]

/**

• 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 e4890e04b210..56f4f6ddd5bb 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -584,7 +584,6 @@ 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:

@@ -598,6 +597,14 @@ 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:

• /*
  

•  * Flag bits indicating which extensions are supported.
  

•  * The first extension doesn't use a flag, but pretend it does,
  

•  * this way that can be changed in the future.
  

•  */
  

• r = KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG | 1;
  

• break;
  

  case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID:

@@ -2772,12 +2779,19 @@ static bool access_key_invalid(u8 access_key) static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) { void __user *uaddr = (void __user *)mop->buf;

• void __user *old_addr = (void __user *)mop->old_addr;
• union {

• __uint128_t quad;
  

• char raw[sizeof(__uint128_t)];
  

• } old = { .quad = 0}, new = { .quad = 0 };
• unsigned int off_in_quad = sizeof(new) - mop->size; u64 supported_flags; void *tmpbuf = NULL; int r, srcu_idx;

supported_flags = KVM_S390_MEMOP_F_SKEY_PROTECTION

• 	  | KVM_S390_MEMOP_F_CHECK_ONLY;
  

• 	  | KVM_S390_MEMOP_F_CHECK_ONLY
  

• 	  | KVM_S390_MEMOP_F_CMPXCHG;
  

  if (mop->flags & ~supported_flags || !mop->size) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE)

@@ -2799,6 +2813,21 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) } else { mop->key = 0; }

• if (mop->flags & KVM_S390_MEMOP_F_CMPXCHG) {

• /*
  

•  * This validates off_in_quad. Checking that size is a power
  

•  * of two is not necessary, as cmpxchg_guest_abs_with_key
  

•  * takes care of that
  

•  */
  

• if (mop->size > sizeof(new))
  

• 	return -EINVAL;
  

!mop->size || mop->size > sizeof(new)

• if (mop->op != KVM_S390_MEMOP_ABSOLUTE_WRITE)
  

• 	return -EINVAL;
  

• if (copy_from_user(&new.raw[off_in_quad], uaddr, mop->size))
  

• 	return -EFAULT;
  

• if (copy_from_user(&old.raw[off_in_quad], old_addr, mop->size))
  

• 	return -EFAULT;
  

• } if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { tmpbuf = vmalloc(mop->size); if (!tmpbuf)

@@ -2829,6 +2858,14 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) case KVM_S390_MEMOP_ABSOLUTE_WRITE: { if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_STORE, mop->key);

• } else if (mop->flags & KVM_S390_MEMOP_F_CMPXCHG) {
  

• 	r = cmpxchg_guest_abs_with_key(kvm, mop->gaddr, mop->size,
  

• 				       &old.quad, new.quad, mop->key);
  

• 	if (r == 1) {
  

• 		r = KVM_S390_MEMOP_R_NO_XCHG;
  

Why don't we return KVM_S390_MEMOP_R_NO_XCHG from cmpxchg_guest_abs_with_key instead of aliasing 1 here?

• 		if (copy_to_user(old_addr, &old.raw[off_in_quad], mop->size))
  

• 			r = -EFAULT;
  

• 	}
  

  } else { if (copy_from_user(tmpbuf, uaddr, mop->size)) { r = -EFAULT;