Merge tag 'kvm-s390-next-20150318' of...

Merge tag 'kvm-s390-next-20150318' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into queue

KVM: s390: Features and fixes for 4.1 (kvm/next)

1. Fixes
2. Implement access register mode in KVM
3. Provide a userspace post handler for the STSI instruction
4. Provide an interface for compliant memory accesses
5. Provide an interface for getting/setting the guest storage key
6. Fixup for the vector facility patches: do not announce the
   vector facility in the guest for old QEMUs.

1-5 were initially shown as RFC in

http://www.spinics.net/lists/kvm/msg114720.html

some small review changes
- added some ACKs
- have the AR mode patches first
- get rid of unnecessary AR_INVAL define
- typos and language

6. two new patches
The two new patches fixup the vector support patches that were
introduced in the last pull request for QEMU versions that dont
know about vector support and guests that do. (We announce the
facility bit, but dont enable the facility so vector aware guests
will crash on vector instructions).

Documentation/virtual/kvm/api.txt

@@ -2716,6 +2716,110 @@ The fields in each entry are defined as follows:
    eax, ebx, ecx, edx: the values returned by the cpuid instruction for
          this function/index combination
 
+4.89 KVM_S390_MEM_OP
+
+Capability: KVM_CAP_S390_MEM_OP
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_mem_op (in)
+Returns: = 0 on success,
+         < 0 on generic error (e.g. -EFAULT or -ENOMEM),
+         > 0 if an exception occurred while walking the page tables
+
+Read or write data from/to the logical (virtual) memory of a VPCU.
+
+Parameters are specified via the following structure:
+
+struct kvm_s390_mem_op {
+	__u64 gaddr;		/* the guest address */
+	__u64 flags;		/* flags */
+	__u32 size;		/* amount of bytes */
+	__u32 op;		/* type of operation */
+	__u64 buf;		/* buffer in userspace */
+	__u8 ar;		/* the access register number */
+	__u8 reserved[31];	/* should be set to 0 */
+};
+
+The type of operation is specified in the "op" field. It is either
+KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or
+KVM_S390_MEMOP_LOGICAL_WRITE for writing to logical memory space. The
+KVM_S390_MEMOP_F_CHECK_ONLY flag can be set in the "flags" field to check
+whether the corresponding memory access would create an access exception
+(without touching the data in the memory at the destination). In case an
+access exception occurred while walking the MMU tables of the guest, the
+ioctl returns a positive error number to indicate the type of exception.
+This exception is also raised directly at the corresponding VCPU if the
+flag KVM_S390_MEMOP_F_INJECT_EXCEPTION is set in the "flags" field.
+
+The start address of the memory region has to be specified in the "gaddr"
+field, and the length of the region in the "size" field. "buf" is the buffer
+supplied by the userspace application where the read data should be written
+to for KVM_S390_MEMOP_LOGICAL_READ, or where the data that should be written
+is stored for a KVM_S390_MEMOP_LOGICAL_WRITE. "buf" is unused and can be NULL
+when KVM_S390_MEMOP_F_CHECK_ONLY is specified. "ar" designates the access
+register number to be used.
+
+The "reserved" field is meant for future extensions. It is not used by
+KVM with the currently defined set of flags.
+
+4.90 KVM_S390_GET_SKEYS
+
+Capability: KVM_CAP_S390_SKEYS
+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
+         keys, negative value on error
+
+This ioctl is used to get guest storage key values on the s390
+architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
+
+struct kvm_s390_skeys {
+	__u64 start_gfn;
+	__u64 count;
+	__u64 skeydata_addr;
+	__u32 flags;
+	__u32 reserved[9];
+};
+
+The start_gfn field is the number of the first guest frame whose storage keys
+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
+will cause the ioctl to return -EINVAL.
+
+The skeydata_addr field is the address to a buffer large enough to hold count
+bytes. This buffer will be filled with storage key data by the ioctl.
+
+4.91 KVM_S390_SET_SKEYS
+
+Capability: KVM_CAP_S390_SKEYS
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_skeys
+Returns: 0 on success, negative value on error
+
+This ioctl is used to set guest storage key values on the s390
+architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
+See section on KVM_S390_GET_SKEYS for struct definition.
+
+The start_gfn field is the number of the first guest frame whose storage keys
+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
+will cause the ioctl to return -EINVAL.
+
+The skeydata_addr field is the address to a buffer containing count bytes of
+storage keys. Each byte in the buffer will be set as the storage key for a
+single frame starting at start_gfn for count frames.
+
+Note: If any architecturally invalid key value is found in the given data then
+the ioctl will return -EINVAL.
+
 5. The kvm_run structure
 ------------------------
 
@@ -3258,3 +3362,31 @@ Returns: 0 on success, negative value on error
 Allows use of the vector registers introduced with z13 processor, and
 provides for the synchronization between host and user space.  Will
 return -EINVAL if the machine does not support vectors.
+
+7.4 KVM_CAP_S390_USER_STSI
+
+Architectures: s390
+Parameters: none
+
+This capability allows post-handlers for the STSI instruction. After
+initial handling in the kernel, KVM exits to user space with
+KVM_EXIT_S390_STSI to allow user space to insert further data.
+
+Before exiting to userspace, kvm handlers should fill in s390_stsi field of
+vcpu->run:
+struct {
+	__u64 addr;
+	__u8 ar;
+	__u8 reserved;
+	__u8 fc;
+	__u8 sel1;
+	__u16 sel2;
+} s390_stsi;
+
+@addr - guest address of STSI SYSIB
+@fc   - function code
+@sel1 - selector 1
+@sel2 - selector 2
+@ar   - access register number
+
+KVM handlers should exit to userspace with rc = -EREMOTE.

arch/s390/include/asm/kvm_host.h

@@ -562,9 +562,9 @@ struct kvm_arch{
 	int css_support;
 	int use_irqchip;
 	int use_cmma;
-	int use_vectors;
 	int user_cpu_state_ctrl;
 	int user_sigp;
+	int user_stsi;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	int ipte_lock_count;

arch/s390/kvm/diag.c

@@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 
 	if (vcpu->run->s.regs.gprs[rx] & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm));
+	rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 	if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258)
@@ -230,7 +230,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
 
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 {
-	int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff;
+	int code = kvm_s390_get_base_disp_rs(vcpu, NULL) & 0xffff;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);

arch/s390/kvm/gaccess.h

@@ -156,9 +156,11 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
 }
 
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
-			    unsigned long *gpa, int write);
+			    ar_t ar, unsigned long *gpa, int write);
+int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
+		    unsigned long length, int is_write);
 
-int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 		 unsigned long len, int write);
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
@@ -168,6 +170,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  * write_guest - copy data from kernel space to guest space
  * @vcpu: virtual cpu
  * @ga: guest address
+ * @ar: access register
  * @data: source address in kernel space
  * @len: number of bytes to copy
  *
@@ -176,8 +179,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  * If DAT is off data will be copied to guest real or absolute memory.
  * If DAT is on data will be copied to the address space as specified by
  * the address space bits of the PSW:
- * Primary, secondory or home space (access register mode is currently not
- * implemented).
+ * Primary, secondary, home space or access register mode.
  * The addressing mode of the PSW is also inspected, so that address wrap
  * around is taken into account for 24-, 31- and 64-bit addressing mode,
  * if the to be copied data crosses page boundaries in guest address space.
@@ -210,16 +212,17 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  *	 if data has been changed in guest space in case of an exception.
  */
 static inline __must_check
-int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 		unsigned long len)
 {
-	return access_guest(vcpu, ga, data, len, 1);
+	return access_guest(vcpu, ga, ar, data, len, 1);
 }
 
 /**
  * read_guest - copy data from guest space to kernel space
  * @vcpu: virtual cpu
  * @ga: guest address
+ * @ar: access register
  * @data: destination address in kernel space
  * @len: number of bytes to copy
  *
@@ -229,10 +232,10 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
  * data will be copied from guest space to kernel space.
  */
 static inline __must_check
-int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 	       unsigned long len)
 {
-	return access_guest(vcpu, ga, data, len, 0);
+	return access_guest(vcpu, ga, ar, data, len, 0);
 }
 
 /**
@@ -330,6 +333,6 @@ int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
 void ipte_lock(struct kvm_vcpu *vcpu);
 void ipte_unlock(struct kvm_vcpu *vcpu);
 int ipte_lock_held(struct kvm_vcpu *vcpu);
-int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga);
+int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra);
 
 #endif /* __KVM_S390_GACCESS_H */

arch/s390/kvm/intercept.c

@@ -320,7 +320,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 	/* Make sure that the source is paged-in */
 	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
-				     &srcaddr, 0);
+				     reg2, &srcaddr, 0);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
@@ -329,7 +329,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 	/* Make sure that the destination is paged-in */
 	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
-				     &dstaddr, 1);
+				     reg1, &dstaddr, 1);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);

arch/s390/kvm/kvm-s390.h

@@ -70,16 +70,22 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 	kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
 }
 
-static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu)
+typedef u8 __bitwise ar_t;
+
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 
+	if (ar)
+		*ar = base2;
+
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
 }
 
 static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
-					      u64 *address1, u64 *address2)
+					      u64 *address1, u64 *address2,
+					      ar_t *ar_b1, ar_t *ar_b2)
 {
 	u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
 	u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
@@ -88,6 +94,11 @@ static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
 
 	*address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
 	*address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+
+	if (ar_b1)
+		*ar_b1 = base1;
+	if (ar_b2)
+		*ar_b2 = base2;
 }
 
 static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2)
@@ -98,7 +109,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2
 		*r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
 }
 
-static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
@@ -107,14 +118,20 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
 	if (disp2 & 0x80000)
 		disp2+=0xfff00000;
 
+	if (ar)
+		*ar = base2;
+
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2;
 }
 
-static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu)
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 
+	if (ar)
+		*ar = base2;
+
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
 }
 
@@ -125,13 +142,24 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
 	vcpu->arch.sie_block->gpsw.mask |= cc << 44;
 }
 
-/* test availability of facility in a kvm intance */
+/* test availability of facility in a kvm instance */
 static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr)
 {
 	return __test_facility(nr, kvm->arch.model.fac->mask) &&
 		__test_facility(nr, kvm->arch.model.fac->list);
 }
 
+static inline int set_kvm_facility(u64 *fac_list, unsigned long nr)
+{
+	unsigned char *ptr;
+
+	if (nr >= MAX_FACILITY_BIT)
+		return -EINVAL;
+	ptr = (unsigned char *) fac_list + (nr >> 3);
+	*ptr |= (0x80UL >> (nr & 7));
+	return 0;
+}
+
 /* are cpu states controlled by user space */
 static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
 {

arch/s390/kvm/sigp.c

@@ -434,7 +434,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	order_code = kvm_s390_get_base_disp_rs(vcpu);
+	order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
 	if (handle_sigp_order_in_user_space(vcpu, order_code))
 		return -EOPNOTSUPP;
 
@@ -476,7 +476,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
 	int r3 = vcpu->arch.sie_block->ipa & 0x000f;
 	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
 	struct kvm_vcpu *dest_vcpu;
-	u8 order_code = kvm_s390_get_base_disp_rs(vcpu);
+	u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
 
 	trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
 

include/uapi/linux/kvm.h

@@ -147,6 +147,16 @@ struct kvm_pit_config {
 
 #define KVM_PIT_SPEAKER_DUMMY     1
 
+struct kvm_s390_skeys {
+	__u64 start_gfn;
+	__u64 count;
+	__u64 skeydata_addr;
+	__u32 flags;
+	__u32 reserved[9];
+};
+#define KVM_S390_GET_SKEYS_NONE   1
+#define KVM_S390_SKEYS_MAX        1048576
+
 #define KVM_EXIT_UNKNOWN          0
 #define KVM_EXIT_EXCEPTION        1
 #define KVM_EXIT_IO               2
@@ -172,6 +182,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_S390_TSCH        22
 #define KVM_EXIT_EPR              23
 #define KVM_EXIT_SYSTEM_EVENT     24
+#define KVM_EXIT_S390_STSI        25
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -309,6 +320,15 @@ struct kvm_run {
 			__u32 type;
 			__u64 flags;
 		} system_event;
+		/* KVM_EXIT_S390_STSI */
+		struct {
+			__u64 addr;
+			__u8 ar;
+			__u8 reserved;
+			__u8 fc;
+			__u8 sel1;
+			__u16 sel2;
+		} s390_stsi;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -365,6 +385,24 @@ struct kvm_translation {
 	__u8  pad[5];
 };
 
+/* for KVM_S390_MEM_OP */
+struct kvm_s390_mem_op {
+	/* in */
+	__u64 gaddr;		/* the guest address */
+	__u64 flags;		/* flags */
+	__u32 size;		/* amount of bytes */
+	__u32 op;		/* type of operation */
+	__u64 buf;		/* buffer in userspace */
+	__u8 ar;		/* the access register number */
+	__u8 reserved[31];	/* should be set to 0 */
+};
+/* types for kvm_s390_mem_op->op */
+#define KVM_S390_MEMOP_LOGICAL_READ	0
+#define KVM_S390_MEMOP_LOGICAL_WRITE	1
+/* 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)
+
 /* for KVM_INTERRUPT */
 struct kvm_interrupt {
 	/* in */
@@ -761,6 +799,9 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_CHECK_EXTENSION_VM 105
 #define KVM_CAP_S390_USER_SIGP 106
 #define KVM_CAP_S390_VECTOR_REGISTERS 107
+#define KVM_CAP_S390_MEM_OP 108
+#define KVM_CAP_S390_USER_STSI 109
+#define KVM_CAP_S390_SKEYS 110
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1136,6 +1177,11 @@ struct kvm_s390_ucas_mapping {
 #define KVM_ARM_VCPU_INIT	  _IOW(KVMIO,  0xae, struct kvm_vcpu_init)
 #define KVM_ARM_PREFERRED_TARGET  _IOR(KVMIO,  0xaf, struct kvm_vcpu_init)
 #define KVM_GET_REG_LIST	  _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
+/* Available with KVM_CAP_S390_MEM_OP */
+#define KVM_S390_MEM_OP		  _IOW(KVMIO,  0xb1, struct kvm_s390_mem_op)
+/* Available with KVM_CAP_S390_SKEYS */
+#define KVM_S390_GET_SKEYS      _IOW(KVMIO, 0xb2, struct kvm_s390_skeys)
+#define KVM_S390_SET_SKEYS      _IOW(KVMIO, 0xb3, struct kvm_s390_skeys)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)