KVM: s390: Extend MEM_OP ioctl by storage key checked cmpxchg

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
op. For now, support this op for absolute accesses only.

This op can be used, 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>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20230206164602.138068-13-scgl@linux.ibm.com
Message-Id: <20230206164602.138068-13-scgl@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>

1 files changed, 109 insertions, 0 deletions

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 0243b6e38d36..3eb85f254881 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1162,6 +1162,115 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 }
 
 /**
+ * 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_addr 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.
+ * @success: output value indicating if an exchange occurred.
+ *
+ * Atomically exchange the value at @gpa by @new, if it contains *@old.
+ * Honors storage keys.
+ *
+ * Return: * 0: successful exchange
+ *         * >0: a program interruption code indicating the reason cmpxchg could
+ *               not be attempted
+ *         * -EINVAL: address misaligned or len not power of two
+ *         * -EAGAIN: transient failure (len 1 or 2)
+ *         * -EOPNOTSUPP: read-only memslot (should never occur)
+ */
+int cmpxchg_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, int len,
+			       __uint128_t *old_addr, __uint128_t new,
+			       u8 access_key, bool *success)
+{
+	gfn_t gfn = gpa_to_gfn(gpa);
+	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;
+
+	hva += offset_in_page(gpa);
+	/*
+	 * The cmpxchg_user_key macro depends on the type of "old", so we need
+	 * a case for each valid length and get some code duplication as long
+	 * as we don't introduce a new macro.
+	 */
+	switch (len) {
+	case 1: {
+		u8 old;
+
+		ret = cmpxchg_user_key((u8 __user *)hva, &old, *old_addr, new, access_key);
+		*success = !ret && old == *old_addr;
+		*old_addr = old;
+		break;
+	}
+	case 2: {
+		u16 old;
+
+		ret = cmpxchg_user_key((u16 __user *)hva, &old, *old_addr, new, access_key);
+		*success = !ret && old == *old_addr;
+		*old_addr = old;
+		break;
+	}
+	case 4: {
+		u32 old;
+
+		ret = cmpxchg_user_key((u32 __user *)hva, &old, *old_addr, new, access_key);
+		*success = !ret && old == *old_addr;
+		*old_addr = old;
+		break;
+	}
+	case 8: {
+		u64 old;
+
+		ret = cmpxchg_user_key((u64 __user *)hva, &old, *old_addr, new, access_key);
+		*success = !ret && old == *old_addr;
+		*old_addr = old;
+		break;
+	}
+	case 16: {
+		__uint128_t old;
+
+		ret = cmpxchg_user_key((__uint128_t __user *)hva, &old, *old_addr, new, access_key);
+		*success = !ret && old == *old_addr;
+		*old_addr = old;
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+	if (*success)
+		mark_page_dirty_in_slot(kvm, slot, gfn);
+	/*
+	 * Assume that the fault is caused by protection, either key protection
+	 * or user page write protection.
+	 */
+	if (ret == -EFAULT)
+		ret = PGM_PROTECTION;
+	return ret;
+}
+
+/**
  * guest_translate_address_with_key - translate guest logical into guest absolute address
  * @vcpu: virtual cpu
  * @gva: Guest virtual address