Merge tag 'kvm-s390-next-5.17-1' of...

Merge tag 'kvm-s390-next-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fix and cleanup

- fix sigp sense/start/stop/inconsistency
- cleanups

Documentation/virt/kvm/api.rst

@@ -3701,7 +3701,7 @@ KVM with the currently defined set of flags.
 :Architectures: s390
 :Type: vm ioctl
 :Parameters: struct kvm_s390_skeys
-:Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
+:Returns: 0 on success, KVM_S390_GET_SKEYS_NONE if guest is not using storage
           keys, negative value on error
 
 This ioctl is used to get guest storage key values on the s390
@@ -3720,7 +3720,7 @@ you want to get.
 
 The count field is the number of consecutive frames (starting from start_gfn)
 whose storage keys to get. The count field must be at least 1 and the maximum
-allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
+allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range
 will cause the ioctl to return -EINVAL.
 
 The skeydata_addr field is the address to a buffer large enough to hold count
@@ -3744,7 +3744,7 @@ you want to set.
 
 The count field is the number of consecutive frames (starting from start_gfn)
 whose storage keys to get. The count field must be at least 1 and the maximum
-allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
+allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range
 will cause the ioctl to return -EINVAL.
 
 The skeydata_addr field is the address to a buffer containing count bytes of

arch/s390/include/asm/uv.h

@@ -91,23 +91,23 @@ struct uv_cb_header {
 
 /* Query Ultravisor Information */
 struct uv_cb_qui {
-	struct uv_cb_header header;
-	u64 reserved08;
-	u64 inst_calls_list[4];
-	u64 reserved30[2];
-	u64 uv_base_stor_len;
-	u64 reserved48;
-	u64 conf_base_phys_stor_len;
-	u64 conf_base_virt_stor_len;
-	u64 conf_virt_var_stor_len;
-	u64 cpu_stor_len;
-	u32 reserved70[3];
-	u32 max_num_sec_conf;
-	u64 max_guest_stor_addr;
-	u8  reserved88[158 - 136];
-	u16 max_guest_cpu_id;
-	u64 uv_feature_indications;
-	u8  reserveda0[200 - 168];
+	struct uv_cb_header header;		/* 0x0000 */
+	u64 reserved08;				/* 0x0008 */
+	u64 inst_calls_list[4];			/* 0x0010 */
+	u64 reserved30[2];			/* 0x0030 */
+	u64 uv_base_stor_len;			/* 0x0040 */
+	u64 reserved48;				/* 0x0048 */
+	u64 conf_base_phys_stor_len;		/* 0x0050 */
+	u64 conf_base_virt_stor_len;		/* 0x0058 */
+	u64 conf_virt_var_stor_len;		/* 0x0060 */
+	u64 cpu_stor_len;			/* 0x0068 */
+	u32 reserved70[3];			/* 0x0070 */
+	u32 max_num_sec_conf;			/* 0x007c */
+	u64 max_guest_stor_addr;		/* 0x0080 */
+	u8  reserved88[158 - 136];		/* 0x0088 */
+	u16 max_guest_cpu_id;			/* 0x009e */
+	u64 uv_feature_indications;		/* 0x00a0 */
+	u8  reserveda8[200 - 168];		/* 0x00a8 */
 } __packed __aligned(8);
 
 /* Initialize Ultravisor */

arch/s390/kvm/gaccess.c

@@ -794,46 +794,100 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
-			    unsigned long *pages, unsigned long nr_pages,
-			    const union asce asce, enum gacc_mode mode)
+/**
+ * guest_range_to_gpas() - Calculate guest physical addresses of page fragments
+ * covering a logical range
+ * @vcpu: virtual cpu
+ * @ga: guest address, start of range
+ * @ar: access register
+ * @gpas: output argument, may be NULL
+ * @len: length of range in bytes
+ * @asce: address-space-control element to use for translation
+ * @mode: access mode
+ *
+ * Translate a logical range to a series of guest absolute addresses,
+ * such that the concatenation of page fragments starting at each gpa make up
+ * the whole range.
+ * The translation is performed as if done by the cpu for the given @asce, @ar,
+ * @mode and state of the @vcpu.
+ * If the translation causes an exception, its program interruption code is
+ * returned and the &struct kvm_s390_pgm_info pgm member of @vcpu is modified
+ * such that a subsequent call to kvm_s390_inject_prog_vcpu() will inject
+ * a correct exception into the guest.
+ * The resulting gpas are stored into @gpas, unless it is NULL.
+ *
+ * Note: All fragments except the first one start at the beginning of a page.
+ *	 When deriving the boundaries of a fragment from a gpa, all but the last
+ *	 fragment end at the end of the page.
+ *
+ * Return:
+ * * 0		- success
+ * * <0		- translation could not be performed, for example if  guest
+ *		  memory could not be accessed
+ * * >0		- an access exception occurred. In this case the returned value
+ *		  is the program interruption code and the contents of pgm may
+ *		  be used to inject an exception into the guest.
+ */
+static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
+			       unsigned long *gpas, unsigned long len,
+			       const union asce asce, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	unsigned int offset = offset_in_page(ga);
+	unsigned int fragment_len;
 	int lap_enabled, rc = 0;
 	enum prot_type prot;
+	unsigned long gpa;
 
 	lap_enabled = low_address_protection_enabled(vcpu, asce);
-	while (nr_pages) {
+	while (min(PAGE_SIZE - offset, len) > 0) {
+		fragment_len = min(PAGE_SIZE - offset, len);
 		ga = kvm_s390_logical_to_effective(vcpu, ga);
 		if (mode == GACC_STORE && lap_enabled && is_low_address(ga))
 			return trans_exc(vcpu, PGM_PROTECTION, ga, ar, mode,
 					 PROT_TYPE_LA);
-		ga &= PAGE_MASK;
 		if (psw_bits(*psw).dat) {
-			rc = guest_translate(vcpu, ga, pages, asce, mode, &prot);
+			rc = guest_translate(vcpu, ga, &gpa, asce, mode, &prot);
 			if (rc < 0)
 				return rc;
 		} else {
-			*pages = kvm_s390_real_to_abs(vcpu, ga);
-			if (kvm_is_error_gpa(vcpu->kvm, *pages))
+			gpa = kvm_s390_real_to_abs(vcpu, ga);
+			if (kvm_is_error_gpa(vcpu->kvm, gpa))
 				rc = PGM_ADDRESSING;
 		}
 		if (rc)
 			return trans_exc(vcpu, rc, ga, ar, mode, prot);
-		ga += PAGE_SIZE;
-		pages++;
-		nr_pages--;
+		if (gpas)
+			*gpas++ = gpa;
+		offset = 0;
+		ga += fragment_len;
+		len -= fragment_len;
 	}
 	return 0;
 }
 
+static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa,
+			     void *data, unsigned int len)
+{
+	const unsigned int offset = offset_in_page(gpa);
+	const gfn_t gfn = gpa_to_gfn(gpa);
+	int rc;
+
+	if (mode == GACC_STORE)
+		rc = kvm_write_guest_page(kvm, gfn, data, offset, len);
+	else
+		rc = kvm_read_guest_page(kvm, gfn, data, offset, len);
+	return rc;
+}
+
 int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		 unsigned long len, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	unsigned long _len, nr_pages, gpa, idx;
-	unsigned long pages_array[2];
-	unsigned long *pages;
+	unsigned long nr_pages, idx;
+	unsigned long gpa_array[2];
+	unsigned int fragment_len;
+	unsigned long *gpas;
 	int need_ipte_lock;
 	union asce asce;
 	int rc;
@@ -845,49 +899,42 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 	if (rc)
 		return rc;
 	nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
-	pages = pages_array;
-	if (nr_pages > ARRAY_SIZE(pages_array))
-		pages = vmalloc(array_size(nr_pages, sizeof(unsigned long)));
-	if (!pages)
+	gpas = gpa_array;
+	if (nr_pages > ARRAY_SIZE(gpa_array))
+		gpas = vmalloc(array_size(nr_pages, sizeof(unsigned long)));
+	if (!gpas)
 		return -ENOMEM;
 	need_ipte_lock = psw_bits(*psw).dat && !asce.r;
 	if (need_ipte_lock)
 		ipte_lock(vcpu);
-	rc = guest_page_range(vcpu, ga, ar, pages, nr_pages, asce, mode);
+	rc = guest_range_to_gpas(vcpu, ga, ar, gpas, len, asce, mode);
 	for (idx = 0; idx < nr_pages && !rc; idx++) {
-		gpa = *(pages + idx) + (ga & ~PAGE_MASK);
-		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (mode == GACC_STORE)
-			rc = kvm_write_guest(vcpu->kvm, gpa, data, _len);
-		else
-			rc = kvm_read_guest(vcpu->kvm, gpa, data, _len);
-		len -= _len;
-		ga += _len;
-		data += _len;
+		fragment_len = min(PAGE_SIZE - offset_in_page(gpas[idx]), len);
+		rc = access_guest_page(vcpu->kvm, mode, gpas[idx], data, fragment_len);
+		len -= fragment_len;
+		data += fragment_len;
 	}
 	if (need_ipte_lock)
 		ipte_unlock(vcpu);
-	if (nr_pages > ARRAY_SIZE(pages_array))
-		vfree(pages);
+	if (nr_pages > ARRAY_SIZE(gpa_array))
+		vfree(gpas);
 	return rc;
 }
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 		      void *data, unsigned long len, enum gacc_mode mode)
 {
-	unsigned long _len, gpa;
+	unsigned int fragment_len;
+	unsigned long gpa;
 	int rc = 0;
 
 	while (len && !rc) {
 		gpa = kvm_s390_real_to_abs(vcpu, gra);
-		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (mode)
-			rc = write_guest_abs(vcpu, gpa, data, _len);
-		else
-			rc = read_guest_abs(vcpu, gpa, data, _len);
-		len -= _len;
-		gra += _len;
-		data += _len;
+		fragment_len = min(PAGE_SIZE - offset_in_page(gpa), len);
+		rc = access_guest_page(vcpu->kvm, mode, gpa, data, fragment_len);
+		len -= fragment_len;
+		gra += fragment_len;
+		data += fragment_len;
 	}
 	return rc;
 }
@@ -909,8 +956,6 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 			    unsigned long *gpa, enum gacc_mode mode)
 {
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	enum prot_type prot;
 	union asce asce;
 	int rc;
 
@@ -918,23 +963,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 	rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode);
 	if (rc)
 		return rc;
-	if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
-		if (mode == GACC_STORE)
-			return trans_exc(vcpu, PGM_PROTECTION, gva, 0,
-					 mode, PROT_TYPE_LA);
-	}
-
-	if (psw_bits(*psw).dat && !asce.r) {	/* Use DAT? */
-		rc = guest_translate(vcpu, gva, gpa, asce, mode, &prot);
-		if (rc > 0)
-			return trans_exc(vcpu, rc, gva, 0, mode, prot);
-	} else {
-		*gpa = kvm_s390_real_to_abs(vcpu, gva);
-		if (kvm_is_error_gpa(vcpu->kvm, *gpa))
-			return trans_exc(vcpu, rc, gva, PGM_ADDRESSING, mode, 0);
-	}
-
-	return rc;
+	return guest_range_to_gpas(vcpu, gva, ar, gpa, 1, asce, mode);
 }
 
 /**
@@ -948,17 +977,14 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode)
 {
-	unsigned long gpa;
-	unsigned long currlen;
+	union asce asce;
 	int rc = 0;
 
+	rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode);
+	if (rc)
+		return rc;
 	ipte_lock(vcpu);
-	while (length > 0 && !rc) {
-		currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE));
-		rc = guest_translate_address(vcpu, gva, ar, &gpa, mode);
-		gva += currlen;
-		length -= currlen;
-	}
+	rc = guest_range_to_gpas(vcpu, gva, ar, NULL, length, asce, mode);
 	ipte_unlock(vcpu);
 
 	return rc;

arch/s390/kvm/interrupt.c

@@ -2116,6 +2116,13 @@ int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu)
 	return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
 }
 
+int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+	return test_bit(IRQ_PEND_RESTART, &li->pending_irqs);
+}
+
 void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

arch/s390/kvm/kvm-s390.c

@@ -4599,10 +4599,15 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+	/*
+	 * Set the VCPU to STOPPED and THEN clear the interrupt flag,
+	 * now that the SIGP STOP and SIGP STOP AND STORE STATUS orders
+	 * have been fully processed. This will ensure that the VCPU
+	 * is kept BUSY if another VCPU is inquiring with SIGP SENSE.
+	 */
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	kvm_s390_clear_stop_irq(vcpu);
 
-	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {

arch/s390/kvm/kvm-s390.h

@@ -441,6 +441,7 @@ void kvm_s390_destroy_adapters(struct kvm *kvm);
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu);
 extern struct kvm_device_ops kvm_flic_ops;
 int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu);
+int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu);
 void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu);
 int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
 			   void __user *buf, int len);

arch/s390/kvm/sigp.c

@@ -276,6 +276,34 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
+	/*
+	 * SIGP RESTART, SIGP STOP, and SIGP STOP AND STORE STATUS orders
+	 * are processed asynchronously. Until the affected VCPU finishes
+	 * its work and calls back into KVM to clear the (RESTART or STOP)
+	 * interrupt, we need to return any new non-reset orders "busy".
+	 *
+	 * This is important because a single VCPU could issue:
+	 *  1) SIGP STOP $DESTINATION
+	 *  2) SIGP SENSE $DESTINATION
+	 *
+	 * If the SIGP SENSE would not be rejected as "busy", it could
+	 * return an incorrect answer as to whether the VCPU is STOPPED
+	 * or OPERATING.
+	 */
+	if (order_code != SIGP_INITIAL_CPU_RESET &&
+	    order_code != SIGP_CPU_RESET) {
+		/*
+		 * Lockless check. Both SIGP STOP and SIGP (RE)START
+		 * properly synchronize everything while processing
+		 * their orders, while the guest cannot observe a
+		 * difference when issuing other orders from two
+		 * different VCPUs.
+		 */
+		if (kvm_s390_is_stop_irq_pending(dst_vcpu) ||
+		    kvm_s390_is_restart_irq_pending(dst_vcpu))
+			return SIGP_CC_BUSY;
+	}
+
 	switch (order_code) {
 	case SIGP_SENSE:
 		vcpu->stat.instruction_sigp_sense++;