Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Janis Schoetterl-Glausch <scgl@linux.ibm.com>
To:     Christian Borntraeger <borntraeger@linux.ibm.com>,
        Janosch Frank <frankja@linux.ibm.com>,
        Heiko Carstens <hca@linux.ibm.com>,
        Vasily Gorbik <gor@linux.ibm.com>
Cc:     Janis Schoetterl-Glausch <scgl@linux.ibm.com>,
        David Hildenbrand <david@redhat.com>,
        Claudio Imbrenda <imbrenda@linux.ibm.com>,
        Alexander Gordeev <agordeev@linux.ibm.com>,
        kvm@vger.kernel.org, linux-s390@vger.kernel.org,
        linux-kernel@vger.kernel.org
Subject: [RFC PATCH v1 06/10] KVM: s390: Add vm IOCTL for key checked guest absolute memory access
Date:   Tue, 18 Jan 2022 10:52:06 +0100
Message-Id: <20220118095210.1651483-7-scgl@linux.ibm.com>
In-Reply-To: <20220118095210.1651483-1-scgl@linux.ibm.com>
References: <20220118095210.1651483-1-scgl@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Channel I/O honors storage keys and is performed on absolute memory.
For I/O emulation user space therefore needs to be able to do key
checked accesses.
The vm IOCTL supports read/write accesses, as well as checking
if an access would succeed.

Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Acked-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c  | 72 +++++++++++++++++++++++++++++++++++
 arch/s390/kvm/gaccess.h  |  6 +++
 arch/s390/kvm/kvm-s390.c | 81 ++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/kvm.h |  2 +
 4 files changed, 161 insertions(+)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index efe33cda38b6..db1d9a494f77 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -795,6 +795,35 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
+static int vm_check_access_key(struct kvm *kvm, char access_key,
+			       enum gacc_mode mode, gpa_t gpa)
+{
+	unsigned long hva;
+	unsigned char storage_key, access_control;
+	bool fetch_protected;
+	int r;
+
+	if (access_key == 0)
+		return 0;
+
+	hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+	if (kvm_is_error_hva(hva))
+		return PGM_ADDRESSING;
+
+	mmap_read_lock(current->mm);
+	r = get_guest_storage_key(current->mm, hva, &storage_key);
+	mmap_read_unlock(current->mm);
+	if (r)
+		return r;
+	access_control = FIELD_GET(_PAGE_ACC_BITS, storage_key);
+	if (access_control == access_key)
+		return 0;
+	fetch_protected = storage_key & _PAGE_FP_BIT;
+	if ((mode == GACC_FETCH || mode == GACC_IFETCH) && !fetch_protected)
+		return 0;
+	return PGM_PROTECTION;
+}
+
 static bool fetch_prot_override_applicable(struct kvm_vcpu *vcpu, enum gacc_mode mode,
 					   union asce asce)
 {
@@ -990,6 +1019,26 @@ access_guest_page_with_key(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa,
 	return 0;
 }
 
+int access_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, void *data,
+			      unsigned long len, enum gacc_mode mode, char key)
+{
+	int offset = offset_in_page(gpa);
+	int fragment_len;
+	int rc;
+
+	while (min(PAGE_SIZE - offset, len) > 0) {
+		fragment_len = min(PAGE_SIZE - offset, len);
+		rc = access_guest_page_with_key(kvm, mode, gpa, data, fragment_len, key);
+		if (rc)
+			return rc;
+		offset = 0;
+		len -= fragment_len;
+		data += fragment_len;
+		gpa += fragment_len;
+	}
+	return 0;
+}
+
 int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 			  void *data, unsigned long len, enum gacc_mode mode,
 			  char access_key)
@@ -1131,6 +1180,29 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 	return rc;
 }
 
+/**
+ * check_gpa_range - test a range of guest physical addresses for accessibility
+ * @kvm: virtual machine instance
+ * @gpa: guest physical address
+ * @length: length of test range
+ * @mode: access mode to test, relevant for storage keys
+ * @access_key: access key to mach the storage keys with
+ */
+int check_gpa_range(struct kvm *kvm, unsigned long gpa, unsigned long length,
+		    enum gacc_mode mode, char access_key)
+{
+	unsigned int fragment_len;
+	int rc = 0;
+
+	while (length && !rc) {
+		fragment_len = min(PAGE_SIZE - offset_in_page(gpa), length);
+		rc = vm_check_access_key(kvm, access_key, mode, gpa);
+		length -= fragment_len;
+		gpa += fragment_len;
+	}
+	return rc;
+}
+
 /**
  * kvm_s390_check_low_addr_prot_real - check for low-address protection
  * @vcpu: virtual cpu
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 0d4416178bb6..d89178b92d51 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -194,6 +194,12 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode,
 		    char access_key);
 
+int check_gpa_range(struct kvm *kvm, unsigned long gpa, unsigned long length,
+		    enum gacc_mode mode, char access_key);
+
+int access_guest_abs_with_key(struct kvm *kvm, gpa_t gpa, void *data,
+			      unsigned long len, enum gacc_mode mode, char key);
+
 int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 			  void *data, unsigned long len, enum gacc_mode mode,
 			  char access_key);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c4acdb025ff1..8dab956f84a6 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2390,6 +2390,78 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
 	return r;
 }
 
+static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+	static const __u8 zeros[sizeof(mop->reserved)] = {0};
+	void __user *uaddr = (void __user *)mop->buf;
+	u64 supported_flags;
+	void *tmpbuf = NULL;
+	char access_key;
+	int r, srcu_idx;
+
+	access_key = FIELD_GET(KVM_S390_MEMOP_F_SKEYS_ACC, mop->flags);
+	supported_flags = KVM_S390_MEMOP_F_SKEYS_ACC
+			  | KVM_S390_MEMOP_F_CHECK_ONLY;
+	if (mop->flags & ~supported_flags)
+		return -EINVAL;
+	if (mop->size > MEM_OP_MAX_SIZE)
+		return -E2BIG;
+	if (kvm_s390_pv_is_protected(kvm))
+		return -EINVAL;
+	if (memcmp(mop->reserved, zeros, sizeof(zeros)) != 0)
+		return -EINVAL;
+
+	if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
+		tmpbuf = vmalloc(mop->size);
+		if (!tmpbuf)
+			return -ENOMEM;
+	}
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	if (kvm_is_error_gpa(kvm, mop->gaddr)) {
+		r = PGM_ADDRESSING;
+		goto out_unlock;
+	}
+
+	switch (mop->op) {
+	case KVM_S390_MEMOP_ABSOLUTE_READ: {
+		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
+			r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_FETCH, access_key);
+		} else {
+			r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
+						      mop->size, GACC_FETCH, access_key);
+			if (r == 0) {
+				if (copy_to_user(uaddr, tmpbuf, mop->size))
+					r = -EFAULT;
+			}
+		}
+		break;
+	}
+	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, access_key);
+		} else {
+			if (copy_from_user(tmpbuf, uaddr, mop->size)) {
+				r = -EFAULT;
+				break;
+			}
+			r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
+						      mop->size, GACC_STORE, access_key);
+		}
+		break;
+	}
+	default:
+		r = -EINVAL;
+	}
+
+out_unlock:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	vfree(tmpbuf);
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -2514,6 +2586,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		}
 		break;
 	}
+	case KVM_S390_MEM_OP: {
+		struct kvm_s390_mem_op mem_op;
+
+		if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0)
+			r = kvm_s390_vm_mem_op(kvm, &mem_op);
+		else
+			r = -EFAULT;
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e3f450b2f346..dd04170287fd 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -572,6 +572,8 @@ struct kvm_s390_mem_op {
 #define KVM_S390_MEMOP_LOGICAL_WRITE	1
 #define KVM_S390_MEMOP_SIDA_READ	2
 #define KVM_S390_MEMOP_SIDA_WRITE	3
+#define KVM_S390_MEMOP_ABSOLUTE_READ	4
+#define KVM_S390_MEMOP_ABSOLUTE_WRITE	5
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
-- 
2.32.0