Merge tag 'kvm-s390-next-4.14-2' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/kvms390/linux

KVM: s390: Fixes and features for 4.14

- merge of topic branch tlb-flushing from the s390 tree to get the
  no-dat base features
- merge of kvm/master to avoid conflicts with additional sthyi fixes
- wire up the no-dat enhancements in KVM
- multiple epoch facility (z14 feature)
- Configuration z/Architecture Mode
- more sthyi fixes
- gdb server range checking fix
- small code cleanups

Documentation/virtual/kvm/devices/vm.txt

@@ -176,7 +176,8 @@ Architectures: s390
 
 3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
 
-Allows user space to set/get the TOD clock extension (u8).
+Allows user space to set/get the TOD clock extension (u8) (superseded by
+KVM_S390_VM_TOD_EXT).
 
 Parameters: address of a buffer in user space to store the data (u8) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
@@ -190,6 +191,17 @@ the POP (u64).
 Parameters: address of a buffer in user space to store the data (u64) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
 
+3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it
+also allows user space to get/set it. If the guest CPU model does not support
+it, it is stored as 0 and not allowed to be set to a value != 0.
+
+Parameters: address of a buffer in user space to store the data
+            (kvm_s390_vm_tod_clock) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+
 4. GROUP: KVM_S390_VM_CRYPTO
 Architectures: s390
 

arch/s390/include/asm/kvm_host.h

@@ -226,7 +226,9 @@ struct kvm_s390_sie_block {
 #define ECB3_RI  0x01
 	__u8    ecb3;			/* 0x0063 */
 	__u32	scaol;			/* 0x0064 */
-	__u8	reserved68[4];		/* 0x0068 */
+	__u8	reserved68;		/* 0x0068 */
+	__u8    epdx;			/* 0x0069 */
+	__u8    reserved6a[2];		/* 0x006a */
 	__u32	todpr;			/* 0x006c */
 	__u8	reserved70[16];		/* 0x0070 */
 	__u64	mso;			/* 0x0080 */
@@ -265,6 +267,7 @@ struct kvm_s390_sie_block {
 	__u64	cbrlo;			/* 0x01b8 */
 	__u8	reserved1c0[8];		/* 0x01c0 */
 #define ECD_HOSTREGMGMT	0x20000000
+#define ECD_MEF		0x08000000
 	__u32	ecd;			/* 0x01c8 */
 	__u8	reserved1cc[18];	/* 0x01cc */
 	__u64	pp;			/* 0x01de */
@@ -739,6 +742,7 @@ struct kvm_arch{
 	struct kvm_s390_cpu_model model;
 	struct kvm_s390_crypto crypto;
 	struct kvm_s390_vsie vsie;
+	u8 epdx;
 	u64 epoch;
 	struct kvm_s390_migration_state *migration_state;
 	/* subset of available cpu features enabled by user space */

arch/s390/include/asm/page-states.h

@@ -13,7 +13,8 @@
 #define ESSA_SET_POT_VOLATILE		4
 #define ESSA_SET_STABLE_RESIDENT	5
 #define ESSA_SET_STABLE_IF_RESIDENT	6
+#define ESSA_SET_STABLE_NODAT		7
 
-#define ESSA_MAX	ESSA_SET_STABLE_IF_RESIDENT
+#define ESSA_MAX	ESSA_SET_STABLE_NODAT
 
 #endif

arch/s390/include/asm/page.h

@@ -133,6 +133,9 @@ static inline int page_reset_referenced(unsigned long addr)
 struct page;
 void arch_free_page(struct page *page, int order);
 void arch_alloc_page(struct page *page, int order);
+void arch_set_page_dat(struct page *page, int order);
+void arch_set_page_nodat(struct page *page, int order);
+int arch_test_page_nodat(struct page *page);
 void arch_set_page_states(int make_stable);
 
 static inline int devmem_is_allowed(unsigned long pfn)

arch/s390/include/asm/pgtable.h

@@ -376,6 +376,7 @@ static inline int is_module_addr(void *addr)
 
 /* Guest Page State used for virtualization */
 #define _PGSTE_GPS_ZERO			0x0000000080000000UL
+#define _PGSTE_GPS_NODAT		0x0000000040000000UL
 #define _PGSTE_GPS_USAGE_MASK		0x0000000003000000UL
 #define _PGSTE_GPS_USAGE_STABLE		0x0000000000000000UL
 #define _PGSTE_GPS_USAGE_UNUSED		0x0000000001000000UL
@@ -952,15 +953,30 @@ static inline pte_t pte_mkhuge(pte_t pte)
 #define IPTE_GLOBAL	0
 #define	IPTE_LOCAL	1
 
-static inline void __ptep_ipte(unsigned long address, pte_t *ptep, int local)
+#define IPTE_NODAT	0x400
+#define IPTE_GUEST_ASCE	0x800
+
+static inline void __ptep_ipte(unsigned long address, pte_t *ptep,
+			       unsigned long opt, unsigned long asce,
+			       int local)
 {
 	unsigned long pto = (unsigned long) ptep;
 
-	/* Invalidation + TLB flush for the pte */
+	if (__builtin_constant_p(opt) && opt == 0) {
+		/* Invalidation + TLB flush for the pte */
+		asm volatile(
+			"	.insn	rrf,0xb2210000,%[r1],%[r2],0,%[m4]"
+			: "+m" (*ptep) : [r1] "a" (pto), [r2] "a" (address),
+			  [m4] "i" (local));
+		return;
+	}
+
+	/* Invalidate ptes with options + TLB flush of the ptes */
+	opt = opt | (asce & _ASCE_ORIGIN);
 	asm volatile(
-		"       .insn rrf,0xb2210000,%[r1],%[r2],0,%[m4]"
-		: "+m" (*ptep) : [r1] "a" (pto), [r2] "a" (address),
-		  [m4] "i" (local));
+		"	.insn	rrf,0xb2210000,%[r1],%[r2],%[r3],%[m4]"
+		: [r2] "+a" (address), [r3] "+a" (opt)
+		: [r1] "a" (pto), [m4] "i" (local) : "memory");
 }
 
 static inline void __ptep_ipte_range(unsigned long address, int nr,
@@ -1341,31 +1357,61 @@ static inline void __pmdp_csp(pmd_t *pmdp)
 #define IDTE_GLOBAL	0
 #define IDTE_LOCAL	1
 
-static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp, int local)
+#define IDTE_PTOA	0x0800
+#define IDTE_NODAT	0x1000
+#define IDTE_GUEST_ASCE	0x2000
+
+static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
+			       unsigned long opt, unsigned long asce,
+			       int local)
 {
 	unsigned long sto;
 
-	sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t);
-	asm volatile(
-		"	.insn	rrf,0xb98e0000,%[r1],%[r2],0,%[m4]"
-		: "+m" (*pmdp)
-		: [r1] "a" (sto), [r2] "a" ((address & HPAGE_MASK)),
-		  [m4] "i" (local)
-		: "cc" );
+	sto = (unsigned long) pmdp - pmd_index(addr) * sizeof(pmd_t);
+	if (__builtin_constant_p(opt) && opt == 0) {
+		/* flush without guest asce */
+		asm volatile(
+			"	.insn	rrf,0xb98e0000,%[r1],%[r2],0,%[m4]"
+			: "+m" (*pmdp)
+			: [r1] "a" (sto), [r2] "a" ((addr & HPAGE_MASK)),
+			  [m4] "i" (local)
+			: "cc" );
+	} else {
+		/* flush with guest asce */
+		asm volatile(
+			"	.insn	rrf,0xb98e0000,%[r1],%[r2],%[r3],%[m4]"
+			: "+m" (*pmdp)
+			: [r1] "a" (sto), [r2] "a" ((addr & HPAGE_MASK) | opt),
+			  [r3] "a" (asce), [m4] "i" (local)
+			: "cc" );
+	}
 }
 
-static inline void __pudp_idte(unsigned long address, pud_t *pudp, int local)
+static inline void __pudp_idte(unsigned long addr, pud_t *pudp,
+			       unsigned long opt, unsigned long asce,
+			       int local)
 {
 	unsigned long r3o;
 
-	r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t);
+	r3o = (unsigned long) pudp - pud_index(addr) * sizeof(pud_t);
 	r3o |= _ASCE_TYPE_REGION3;
-	asm volatile(
-		"	.insn	rrf,0xb98e0000,%[r1],%[r2],0,%[m4]"
-		: "+m" (*pudp)
-		: [r1] "a" (r3o), [r2] "a" ((address & PUD_MASK)),
-		  [m4] "i" (local)
-		: "cc");
+	if (__builtin_constant_p(opt) && opt == 0) {
+		/* flush without guest asce */
+		asm volatile(
+			"	.insn	rrf,0xb98e0000,%[r1],%[r2],0,%[m4]"
+			: "+m" (*pudp)
+			: [r1] "a" (r3o), [r2] "a" ((addr & PUD_MASK)),
+			  [m4] "i" (local)
+			: "cc");
+	} else {
+		/* flush with guest asce */
+		asm volatile(
+			"	.insn	rrf,0xb98e0000,%[r1],%[r2],%[r3],%[m4]"
+			: "+m" (*pudp)
+			: [r1] "a" (r3o), [r2] "a" ((addr & PUD_MASK) | opt),
+			  [r3] "a" (asce), [m4] "i" (local)
+			: "cc" );
+	}
 }
 
 pmd_t pmdp_xchg_direct(struct mm_struct *, unsigned long, pmd_t *, pmd_t);

arch/s390/include/asm/setup.h

@@ -29,8 +29,9 @@
 #define MACHINE_FLAG_TE		_BITUL(11)
 #define MACHINE_FLAG_TLB_LC	_BITUL(12)
 #define MACHINE_FLAG_VX		_BITUL(13)
-#define MACHINE_FLAG_NX		_BITUL(14)
-#define MACHINE_FLAG_GS		_BITUL(15)
+#define MACHINE_FLAG_TLB_GUEST	_BITUL(14)
+#define MACHINE_FLAG_NX		_BITUL(15)
+#define MACHINE_FLAG_GS		_BITUL(16)
 
 #define LPP_MAGIC		_BITUL(31)
 #define LPP_PFAULT_PID_MASK	_AC(0xffffffff, UL)
@@ -68,6 +69,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
 #define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
+#define MACHINE_HAS_TLB_GUEST	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_GUEST)
 #define MACHINE_HAS_NX		(S390_lowcore.machine_flags & MACHINE_FLAG_NX)
 #define MACHINE_HAS_GS		(S390_lowcore.machine_flags & MACHINE_FLAG_GS)
 
@@ -106,7 +108,8 @@ extern void pfault_fini(void);
 
 void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault);
 
-extern void cmma_init(void);
+void cmma_init(void);
+void cmma_init_nodat(void);
 
 extern void (*_machine_restart)(char *command);
 extern void (*_machine_halt)(void);

arch/s390/include/asm/tlbflush.h

@@ -20,10 +20,15 @@ static inline void __tlb_flush_local(void)
  */
 static inline void __tlb_flush_idte(unsigned long asce)
 {
+	unsigned long opt;
+
+	opt = IDTE_PTOA;
+	if (MACHINE_HAS_TLB_GUEST)
+		opt |= IDTE_GUEST_ASCE;
 	/* Global TLB flush for the mm */
 	asm volatile(
 		"	.insn	rrf,0xb98e0000,0,%0,%1,0"
-		: : "a" (2048), "a" (asce) : "cc");
+		: : "a" (opt), "a" (asce) : "cc");
 }
 
 #ifdef CONFIG_SMP

arch/s390/include/uapi/asm/kvm.h

@@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req {
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1
+#define KVM_S390_VM_TOD_EXT		2
+
+struct kvm_s390_vm_tod_clock {
+	__u8  epoch_idx;
+	__u64 tod;
+};
 
 /* kvm attributes for KVM_S390_VM_CPU_MODEL */
 /* processor related attributes are r/w */

arch/s390/kernel/suspend.c

@@ -98,10 +98,16 @@ int page_key_alloc(unsigned long pages)
  */
 void page_key_read(unsigned long *pfn)
 {
+	struct page *page;
 	unsigned long addr;
-
-	addr = (unsigned long) page_address(pfn_to_page(*pfn));
-	*(unsigned char *) pfn = (unsigned char) page_get_storage_key(addr);
+	unsigned char key;
+
+	page = pfn_to_page(*pfn);
+	addr = (unsigned long) page_address(page);
+	key = (unsigned char) page_get_storage_key(addr) & 0x7f;
+	if (arch_test_page_nodat(page))
+		key |= 0x80;
+	*(unsigned char *) pfn = key;
 }
 
 /*
@@ -126,8 +132,16 @@ void page_key_memorize(unsigned long *pfn)
  */
 void page_key_write(void *address)
 {
-	page_set_storage_key((unsigned long) address,
-			     page_key_rp->data[page_key_rx], 0);
+	struct page *page;
+	unsigned char key;
+
+	key = page_key_rp->data[page_key_rx];
+	page_set_storage_key((unsigned long) address, key & 0x7f, 0);
+	page = virt_to_page(address);
+	if (key & 0x80)
+		arch_set_page_nodat(page, 0);
+	else
+		arch_set_page_dat(page, 0);
 	if (++page_key_rx >= PAGE_KEY_DATA_SIZE)
 		return;
 	page_key_rp = page_key_rp->next;

arch/s390/kernel/vdso.c

@@ -157,6 +157,8 @@ int vdso_alloc_per_cpu(struct lowcore *lowcore)
 	page_frame = get_zeroed_page(GFP_KERNEL);
 	if (!segment_table || !page_table || !page_frame)
 		goto out;
+	arch_set_page_dat(virt_to_page(segment_table), SEGMENT_ORDER);
+	arch_set_page_dat(virt_to_page(page_table), 0);
 
 	/* Initialize per-cpu vdso data page */
 	vd = (struct vdso_per_cpu_data *) page_frame;

arch/s390/kvm/guestdbg.c

@@ -308,7 +308,7 @@ static inline int in_addr_range(u64 addr, u64 a, u64 b)
 		return (addr >= a) && (addr <= b);
 	else
 		/* "overflowing" interval */
-		return (addr <= a) && (addr >= b);
+		return (addr >= a) || (addr <= b);
 }
 
 #define end_of_range(bp_info) (bp_info->addr + bp_info->len - 1)

arch/s390/kvm/interrupt.c

@@ -2479,6 +2479,7 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
 	struct kvm_s390_mchk_info *mchk;
 	union mci mci;
 	__u64 cr14 = 0;         /* upper bits are not used */
+	int rc;
 
 	mci.val = mcck_info->mcic;
 	if (mci.sr)
@@ -2496,12 +2497,13 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
 	if (mci.ck) {
 		/* Inject the floating machine check */
 		inti.type = KVM_S390_MCHK;
-		WARN_ON_ONCE(__inject_vm(vcpu->kvm, &inti));
+		rc = __inject_vm(vcpu->kvm, &inti);
 	} else {
 		/* Inject the machine check to specified vcpu */
 		irq.type = KVM_S390_MCHK;
-		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
+		rc = kvm_s390_inject_vcpu(vcpu, &irq);
 	}
+	WARN_ON_ONCE(rc);
 }
 
 int kvm_set_routing_entry(struct kvm *kvm,