Merge tag 'kvm-s390-20140422' of...

Merge tag 'kvm-s390-20140422' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into queue

Lazy storage key handling
-------------------------
Linux does not use the ACC and F bits of the storage key. Newer Linux
versions also do not use the storage keys for dirty and reference
tracking. We can optimize the guest handling for those guests for faults
as well as page-in and page-out by simply not caring about the guest
visible storage key. We trap guest storage key instruction to enable
those keys only on demand.

Migration bitmap

Until now s390 never provided a proper dirty bitmap.  Let's provide a
proper migration bitmap for s390. We also change the user dirty tracking
to a fault based mechanism. This makes the host completely independent
from the storage keys. Long term this will allow us to back guest memory
with large pages.

per-VM device attributes
------------------------
To avoid the introduction of new ioctls, let's provide the
attribute semanantic also on the VM-"device".

Userspace controlled CMMA
-------------------------
The CMMA assist is changed from "always on" to "on if requested" via
per-VM device attributes. In addition a callback to reset all usage
states is provided.

Proper guest DAT handling for intercepts
----------------------------------------
While instructions handled by SIE take care of all addressing aspects,
KVM/s390 currently does not care about guest address translation of
intercepts. This worked out fine, because
- the s390 Linux kernel has a 1:1 mapping between kernel virtual<->real
 for all pages up to memory size
- intercepts happen only for a small amount of cases
- all of these intercepts happen to be in the kernel text for current
  distros

Of course we need to be better for other intercepts, kernel modules etc.
We provide the infrastructure and rework all in-kernel intercepts to work
on logical addresses (paging etc) instead of real ones. The code has
been running internally for several months now, so it is time for going
public.

GDB support
-----------
We provide breakpoints, single stepping and watchpoints.

Fixes/Cleanups
--------------
- Improve program check delivery
- Factor out the handling of transactional memory  on program checks
- Use the existing define __LC_PGM_TDB
- Several cleanups in the lowcore structure
- Documentation

NOTES
-----
- All patches touching base s390 are either ACKed or written by the s390
  maintainers
- One base KVM patch "KVM: add kvm_is_error_gpa() helper"
- One patch introduces the notion of VM device attributes
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Conflicts:
	include/uapi/linux/kvm.h

Documentation/virtual/kvm/api.txt

@@ -2314,8 +2314,8 @@ struct kvm_create_device {
 
 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL
-Type: device ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
+Type: device ioctl, vm ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
@@ -2340,8 +2340,8 @@ struct kvm_device_attr {
 
 4.81 KVM_HAS_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL
-Type: device ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
+Type: device ioctl, vm ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:

Documentation/virtual/kvm/devices/vm.txt

+Generic vm interface
+====================================
+
+The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same
+struct kvm_device_attr as other devices, but targets VM-wide settings
+and controls.
+
+The groups and attributes per virtual machine, if any, are architecture
+specific.
+
+1. GROUP: KVM_S390_VM_MEM_CTRL
+Architectures: s390
+
+1.1. ATTRIBUTE: KVM_S390_VM_MEM_CTRL
+Parameters: none
+Returns: -EBUSY if already a vcpus is defined, otherwise 0
+
+Enables CMMA for the virtual machine
+
+1.2. ATTRIBUTE: KVM_S390_VM_CLR_CMMA
+Parameteres: none
+Returns: 0
+
+Clear the CMMA status for all guest pages, so any pages the guest marked
+as unused are again used any may not be reclaimed by the host.

Documentation/virtual/kvm/s390-diag.txt

@@ -78,3 +78,5 @@ DIAGNOSE function code 'X'501 - KVM breakpoint
 
 If the function code specifies 0x501, breakpoint functions may be performed.
 This function code is handled by userspace.
+
+This diagnose function code has no subfunctions and uses no parameters.

arch/s390/include/asm/ctl_reg.h

@@ -57,6 +57,20 @@ static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
 void smp_ctl_set_bit(int cr, int bit);
 void smp_ctl_clear_bit(int cr, int bit);
 
+union ctlreg0 {
+	unsigned long val;
+	struct {
+#ifdef CONFIG_64BIT
+		unsigned long	   : 32;
+#endif
+		unsigned long	   : 3;
+		unsigned long lap  : 1; /* Low-address-protection control */
+		unsigned long	   : 4;
+		unsigned long edat : 1; /* Enhanced-DAT-enablement control */
+		unsigned long	   : 23;
+	};
+};
+
 #ifdef CONFIG_SMP
 # define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
 # define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)

arch/s390/include/asm/kvm_host.h

@@ -39,9 +39,17 @@ struct sca_entry {
 	__u64	reserved2[2];
 } __attribute__((packed));
 
+union ipte_control {
+	unsigned long val;
+	struct {
+		unsigned long k  : 1;
+		unsigned long kh : 31;
+		unsigned long kg : 32;
+	};
+};
 
 struct sca_block {
-	__u64	ipte_control;
+	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
 	__u64	reserved2;
@@ -85,12 +93,26 @@ struct kvm_s390_sie_block {
 	__u8	reserved40[4];		/* 0x0040 */
 #define LCTL_CR0	0x8000
 #define LCTL_CR6	0x0200
+#define LCTL_CR9	0x0040
+#define LCTL_CR10	0x0020
+#define LCTL_CR11	0x0010
 #define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
+#define ICTL_PINT	0x20000000
 #define ICTL_LPSW	0x00400000
+#define ICTL_STCTL	0x00040000
+#define ICTL_ISKE	0x00004000
+#define ICTL_SSKE	0x00002000
+#define ICTL_RRBE	0x00001000
 	__u32	ictl;			/* 0x0048 */
 	__u32	eca;			/* 0x004c */
+#define ICPT_INST	0x04
+#define ICPT_PROGI	0x08
+#define ICPT_INSTPROGI	0x0C
+#define ICPT_OPEREXC	0x2C
+#define ICPT_PARTEXEC	0x38
+#define ICPT_IOINST	0x40
 	__u8	icptcode;		/* 0x0050 */
 	__u8	reserved51;		/* 0x0051 */
 	__u16	ihcpu;			/* 0x0052 */
@@ -109,9 +131,21 @@ struct kvm_s390_sie_block {
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
-	__u8	reservedb0[30];		/* 0x00b0 */
+	__u8	reservedb0[28];		/* 0x00b0 */
+	__u16	pgmilc;			/* 0x00cc */
 	__u16	iprcc;			/* 0x00ce */
-	__u8	reservedd0[48];		/* 0x00d0 */
+	__u32	dxc;			/* 0x00d0 */
+	__u16	mcn;			/* 0x00d4 */
+	__u8	perc;			/* 0x00d6 */
+	__u8	peratmid;		/* 0x00d7 */
+	__u64	peraddr;		/* 0x00d8 */
+	__u8	eai;			/* 0x00e0 */
+	__u8	peraid;			/* 0x00e1 */
+	__u8	oai;			/* 0x00e2 */
+	__u8	armid;			/* 0x00e3 */
+	__u8	reservede4[4];		/* 0x00e4 */
+	__u64	tecmc;			/* 0x00e8 */
+	__u8	reservedf0[16];		/* 0x00f0 */
 	__u64	gcr[16];		/* 0x0100 */
 	__u64	gbea;			/* 0x0180 */
 	__u8	reserved188[24];	/* 0x0188 */
@@ -146,6 +180,8 @@ struct kvm_vcpu_stat {
 	u32 exit_instruction;
 	u32 instruction_lctl;
 	u32 instruction_lctlg;
+	u32 instruction_stctl;
+	u32 instruction_stctg;
 	u32 exit_program_interruption;
 	u32 exit_instr_and_program;
 	u32 deliver_external_call;
@@ -164,6 +200,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_stpx;
 	u32 instruction_stap;
 	u32 instruction_storage_key;
+	u32 instruction_ipte_interlock;
 	u32 instruction_stsch;
 	u32 instruction_chsc;
 	u32 instruction_stsi;
@@ -190,6 +227,51 @@ struct kvm_vcpu_stat {
 #define PGM_ADDRESSING			0x05
 #define PGM_SPECIFICATION		0x06
 #define PGM_DATA			0x07
+#define PGM_FIXED_POINT_OVERFLOW	0x08
+#define PGM_FIXED_POINT_DIVIDE		0x09
+#define PGM_DECIMAL_OVERFLOW		0x0a
+#define PGM_DECIMAL_DIVIDE		0x0b
+#define PGM_HFP_EXPONENT_OVERFLOW	0x0c
+#define PGM_HFP_EXPONENT_UNDERFLOW	0x0d
+#define PGM_HFP_SIGNIFICANCE		0x0e
+#define PGM_HFP_DIVIDE			0x0f
+#define PGM_SEGMENT_TRANSLATION		0x10
+#define PGM_PAGE_TRANSLATION		0x11
+#define PGM_TRANSLATION_SPEC		0x12
+#define PGM_SPECIAL_OPERATION		0x13
+#define PGM_OPERAND			0x15
+#define PGM_TRACE_TABEL			0x16
+#define PGM_SPACE_SWITCH		0x1c
+#define PGM_HFP_SQUARE_ROOT		0x1d
+#define PGM_PC_TRANSLATION_SPEC		0x1f
+#define PGM_AFX_TRANSLATION		0x20
+#define PGM_ASX_TRANSLATION		0x21
+#define PGM_LX_TRANSLATION		0x22
+#define PGM_EX_TRANSLATION		0x23
+#define PGM_PRIMARY_AUTHORITY		0x24
+#define PGM_SECONDARY_AUTHORITY		0x25
+#define PGM_LFX_TRANSLATION		0x26
+#define PGM_LSX_TRANSLATION		0x27
+#define PGM_ALET_SPECIFICATION		0x28
+#define PGM_ALEN_TRANSLATION		0x29
+#define PGM_ALE_SEQUENCE		0x2a
+#define PGM_ASTE_VALIDITY		0x2b
+#define PGM_ASTE_SEQUENCE		0x2c
+#define PGM_EXTENDED_AUTHORITY		0x2d
+#define PGM_LSTE_SEQUENCE		0x2e
+#define PGM_ASTE_INSTANCE		0x2f
+#define PGM_STACK_FULL			0x30
+#define PGM_STACK_EMPTY			0x31
+#define PGM_STACK_SPECIFICATION		0x32
+#define PGM_STACK_TYPE			0x33
+#define PGM_STACK_OPERATION		0x34
+#define PGM_ASCE_TYPE			0x38
+#define PGM_REGION_FIRST_TRANS		0x39
+#define PGM_REGION_SECOND_TRANS		0x3a
+#define PGM_REGION_THIRD_TRANS		0x3b
+#define PGM_MONITOR			0x40
+#define PGM_PER				0x80
+#define PGM_CRYPTO_OPERATION		0x119
 
 struct kvm_s390_interrupt_info {
 	struct list_head list;
@@ -229,6 +311,45 @@ struct kvm_s390_float_interrupt {
 	unsigned int irq_count;
 };
 
+struct kvm_hw_wp_info_arch {
+	unsigned long addr;
+	unsigned long phys_addr;
+	int len;
+	char *old_data;
+};
+
+struct kvm_hw_bp_info_arch {
+	unsigned long addr;
+	int len;
+};
+
+/*
+ * Only the upper 16 bits of kvm_guest_debug->control are arch specific.
+ * Further KVM_GUESTDBG flags which an be used from userspace can be found in
+ * arch/s390/include/uapi/asm/kvm.h
+ */
+#define KVM_GUESTDBG_EXIT_PENDING 0x10000000
+
+#define guestdbg_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)
+#define guestdbg_sstep_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+#define guestdbg_hw_bp_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+#define guestdbg_exit_pending(vcpu) (guestdbg_enabled(vcpu) && \
+		(vcpu->guest_debug & KVM_GUESTDBG_EXIT_PENDING))
+
+struct kvm_guestdbg_info_arch {
+	unsigned long cr0;
+	unsigned long cr9;
+	unsigned long cr10;
+	unsigned long cr11;
+	struct kvm_hw_bp_info_arch *hw_bp_info;
+	struct kvm_hw_wp_info_arch *hw_wp_info;
+	int nr_hw_bp;
+	int nr_hw_wp;
+	unsigned long last_bp;
+};
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
@@ -238,11 +359,13 @@ struct kvm_vcpu_arch {
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct tasklet_struct tasklet;
+	struct kvm_s390_pgm_info pgm;
 	union  {
 		struct cpuid	cpu_id;
 		u64		stidp_data;
 	};
 	struct gmap *gmap;
+	struct kvm_guestdbg_info_arch guestdbg;
 #define KVM_S390_PFAULT_TOKEN_INVALID	(-1UL)
 	unsigned long pfault_token;
 	unsigned long pfault_select;
@@ -285,7 +408,9 @@ struct kvm_arch{
 	struct gmap *gmap;
 	int css_support;
 	int use_irqchip;
+	int use_cmma;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
+	wait_queue_head_t ipte_wq;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)

arch/s390/include/asm/lowcore.h

@@ -56,13 +56,14 @@ struct _lowcore {
 	__u16	pgm_code;			/* 0x008e */
 	__u32	trans_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u32	per_address;			/* 0x0098 */
 	__u32	monitor_code;			/* 0x009c */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00b8-0x00a4];	/* 0x00a4 */
 	__u16	subchannel_id;			/* 0x00b8 */
 	__u16	subchannel_nr;			/* 0x00ba */
@@ -196,12 +197,13 @@ struct _lowcore {
 	__u16	pgm_code;			/* 0x008e */
 	__u32	data_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u64	per_address;			/* 0x0098 */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00a8-0x00a4];	/* 0x00a4 */
 	__u64	trans_exc_code;			/* 0x00a8 */
 	__u64	monitor_code;			/* 0x00b0 */

arch/s390/include/asm/mmu.h

@@ -16,6 +16,8 @@ typedef struct {
 	unsigned long vdso_base;
 	/* The mmu context has extended page tables. */
 	unsigned int has_pgste:1;
+	/* The mmu context uses storage keys. */
+	unsigned int use_skey:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						      \

arch/s390/include/asm/mmu_context.h

@@ -23,6 +23,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
 	mm->context.has_pgste = 0;
+	mm->context.use_skey = 0;
 	mm->context.asce_limit = STACK_TOP_MAX;
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;

arch/s390/include/asm/pgalloc.h

@@ -22,7 +22,8 @@ unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
 
-void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long);
+void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,
+			    bool init_skey);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq);
 

arch/s390/include/asm/pgtable.h

@@ -309,7 +309,8 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT	0x00200000UL
 #define PGSTE_GR_BIT	0x00040000UL
 #define PGSTE_GC_BIT	0x00020000UL
-#define PGSTE_IN_BIT	0x00008000UL	/* IPTE notify bit */
+#define PGSTE_UC_BIT	0x00008000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x00004000UL	/* IPTE notify bit */
 
 #else /* CONFIG_64BIT */
 
@@ -391,7 +392,8 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT	0x0020000000000000UL
 #define PGSTE_GR_BIT	0x0004000000000000UL
 #define PGSTE_GC_BIT	0x0002000000000000UL
-#define PGSTE_IN_BIT	0x0000800000000000UL	/* IPTE notify bit */
+#define PGSTE_UC_BIT	0x0000800000000000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x0000400000000000UL	/* IPTE notify bit */
 
 #endif /* CONFIG_64BIT */
 
@@ -466,6 +468,16 @@ static inline int mm_has_pgste(struct mm_struct *mm)
 #endif
 	return 0;
 }
+
+static inline int mm_use_skey(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+	if (mm->context.use_skey)
+		return 1;
+#endif
+	return 0;
+}
+
 /*
  * pgd/pmd/pte query functions
  */
@@ -699,26 +711,17 @@ static inline void pgste_set(pte_t *ptep, pgste_t pgste)
 #endif
 }
 
-static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
+static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste,
+				       struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address, bits, skey;
 
-	if (pte_val(*ptep) & _PAGE_INVALID)
+	if (!mm_use_skey(mm) || pte_val(*ptep) & _PAGE_INVALID)
 		return pgste;
 	address = pte_val(*ptep) & PAGE_MASK;
 	skey = (unsigned long) page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
-	if (!(pgste_val(pgste) & PGSTE_HC_BIT) && (bits & _PAGE_CHANGED)) {
-		/* Transfer dirty + referenced bit to host bits in pgste */
-		pgste_val(pgste) |= bits << 52;
-		page_set_storage_key(address, skey ^ bits, 0);
-	} else if (!(pgste_val(pgste) & PGSTE_HR_BIT) &&
-		   (bits & _PAGE_REFERENCED)) {
-		/* Transfer referenced bit to host bit in pgste */
-		pgste_val(pgste) |= PGSTE_HR_BIT;
-		page_reset_referenced(address);
-	}
 	/* Transfer page changed & referenced bit to guest bits in pgste */
 	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
 	/* Copy page access key and fetch protection bit to pgste */
@@ -729,25 +732,14 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 
 }
 
-static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
-{
-#ifdef CONFIG_PGSTE
-	if (pte_val(*ptep) & _PAGE_INVALID)
-		return pgste;
-	/* Get referenced bit from storage key */
-	if (page_reset_referenced(pte_val(*ptep) & PAGE_MASK))
-		pgste_val(pgste) |= PGSTE_HR_BIT | PGSTE_GR_BIT;
-#endif
-	return pgste;
-}
-
-static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
+static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry,
+				 struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address;
 	unsigned long nkey;
 
-	if (pte_val(entry) & _PAGE_INVALID)
+	if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID)
 		return;
 	VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID));
 	address = pte_val(entry) & PAGE_MASK;
@@ -757,15 +749,17 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
 	 * key C/R to 0.
 	 */
 	nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
 	page_set_storage_key(address, nkey, 0);
 #endif
 }
 
-static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
+static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 {
-	if (!MACHINE_HAS_ESOP &&
-	    (pte_val(entry) & _PAGE_PRESENT) &&
-	    (pte_val(entry) & _PAGE_WRITE)) {
+	if ((pte_val(entry) & _PAGE_PRESENT) &&
+	    (pte_val(entry) & _PAGE_WRITE) &&
+	    !(pte_val(entry) & _PAGE_INVALID)) {
+		if (!MACHINE_HAS_ESOP) {
 			/*
 			 * Without enhanced suppression-on-protection force
 			 * the dirty bit on for all writable ptes.
@@ -773,7 +767,12 @@ static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
 			pte_val(entry) |= _PAGE_DIRTY;
 			pte_val(entry) &= ~_PAGE_PROTECT;
 		}
+		if (!(pte_val(entry) & _PAGE_PROTECT))
+			/* This pte allows write access, set user-dirty */
+			pgste_val(pgste) |= PGSTE_UC_BIT;
+	}
 	*ptep = entry;
+	return pgste;
 }
 
 /**
@@ -839,6 +838,8 @@ unsigned long __gmap_fault(unsigned long address, struct gmap *);
 unsigned long gmap_fault(unsigned long address, struct gmap *);
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
 void __gmap_zap(unsigned long address, struct gmap *);
+bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *);
+
 
 void gmap_register_ipte_notifier(struct gmap_notifier *);
 void gmap_unregister_ipte_notifier(struct gmap_notifier *);
@@ -870,8 +871,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
-		pgste_set_key(ptep, pgste, entry);
-		pgste_set_pte(ptep, entry);
+		pgste_set_key(ptep, pgste, entry, mm);
+		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else {
 		if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1)
@@ -1017,45 +1018,6 @@ static inline pte_t pte_mkhuge(pte_t pte)
 }
 #endif
 
-/*
- * Get (and clear) the user dirty bit for a pte.
- */
-static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
-						 pte_t *ptep)
-{
-	pgste_t pgste;
-	int dirty = 0;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_update_all(ptep, pgste);
-		dirty = !!(pgste_val(pgste) & PGSTE_HC_BIT);
-		pgste_val(pgste) &= ~PGSTE_HC_BIT;
-		pgste_set_unlock(ptep, pgste);
-		return dirty;
-	}
-	return dirty;
-}
-
-/*
- * Get (and clear) the user referenced bit for a pte.
- */
-static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
-						 pte_t *ptep)
-{
-	pgste_t pgste;
-	int young = 0;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_update_young(ptep, pgste);
-		young = !!(pgste_val(pgste) & PGSTE_HR_BIT);
-		pgste_val(pgste) &= ~PGSTE_HR_BIT;
-		pgste_set_unlock(ptep, pgste);
-	}
-	return young;
-}
-
 static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 {
 	unsigned long pto = (unsigned long) ptep;
@@ -1118,6 +1080,36 @@ static inline void ptep_flush_lazy(struct mm_struct *mm,
 	atomic_sub(0x10000, &mm->context.attach_count);
 }
 
+/*
+ * Get (and clear) the user dirty bit for a pte.
+ */
+static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
+						 unsigned long addr,
+						 pte_t *ptep)
+{
+	pgste_t pgste;
+	pte_t pte;
+	int dirty;
+
+	if (!mm_has_pgste(mm))
+		return 0;
+	pgste = pgste_get_lock(ptep);
+	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
+	pgste_val(pgste) &= ~PGSTE_UC_BIT;
+	pte = *ptep;
+	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
+		pgste = pgste_ipte_notify(mm, ptep, pgste);
+		__ptep_ipte(addr, ptep);
+		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
+			pte_val(pte) |= _PAGE_PROTECT;
+		else
+			pte_val(pte) |= _PAGE_INVALID;
+		*ptep = pte;
+	}
+	pgste_set_unlock(ptep, pgste);
+	return dirty;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
@@ -1137,7 +1129,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 	pte = pte_mkold(pte);
 
 	if (mm_has_pgste(vma->vm_mm)) {
-		pgste_set_pte(ptep, pte);
+		pgste = pgste_set_pte(ptep, pgste, pte);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = pte;
@@ -1182,7 +1174,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
@@ -1205,7 +1197,7 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
 	ptep_flush_lazy(mm, address, ptep);
 
 	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set(ptep, pgste);
 	}
 	return pte;
@@ -1219,8 +1211,8 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get(ptep);
-		pgste_set_key(ptep, pgste, pte);
-		pgste_set_pte(ptep, pte);
+		pgste_set_key(ptep, pgste, pte, mm);
+		pgste = pgste_set_pte(ptep, pgste, pte);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = pte;
@@ -1246,7 +1238,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 		if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
 		    _PGSTE_GPS_USAGE_UNUSED)
 			pte_val(pte) |= _PAGE_UNUSED;
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, vma->vm_mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
@@ -1278,7 +1270,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (!full && mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
@@ -1301,7 +1293,7 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
 		pte = pte_wrprotect(pte);
 
 		if (mm_has_pgste(mm)) {
-			pgste_set_pte(ptep, pte);
+			pgste = pgste_set_pte(ptep, pgste, pte);
 			pgste_set_unlock(ptep, pgste);
 		} else
 			*ptep = pte;
@@ -1326,7 +1318,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 	ptep_flush_direct(vma->vm_mm, address, ptep);
 
 	if (mm_has_pgste(vma->vm_mm)) {
-		pgste_set_pte(ptep, entry);
+		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = entry;
@@ -1734,6 +1726,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 extern int vmem_add_mapping(unsigned long start, unsigned long size);
 extern int vmem_remove_mapping(unsigned long start, unsigned long size);
 extern int s390_enable_sie(void);
+extern void s390_enable_skey(void);
 
 /*
  * No page table caches to initialise

arch/s390/include/asm/ptrace.h

@@ -16,6 +16,50 @@
 			 PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | \
 			 PSW_MASK_PSTATE | PSW_ASC_PRIMARY)
 
+struct psw_bits {
+	unsigned long long	: 1;
+	unsigned long long r	: 1; /* PER-Mask */
+	unsigned long long	: 3;
+	unsigned long long t	: 1; /* DAT Mode */
+	unsigned long long i	: 1; /* Input/Output Mask */
+	unsigned long long e	: 1; /* External Mask */
+	unsigned long long key	: 4; /* PSW Key */
+	unsigned long long	: 1;
+	unsigned long long m	: 1; /* Machine-Check Mask */
+	unsigned long long w	: 1; /* Wait State */
+	unsigned long long p	: 1; /* Problem State */
+	unsigned long long as	: 2; /* Address Space Control */
+	unsigned long long cc	: 2; /* Condition Code */
+	unsigned long long pm	: 4; /* Program Mask */
+	unsigned long long ri	: 1; /* Runtime Instrumentation */
+	unsigned long long	: 6;
+	unsigned long long eaba : 2; /* Addressing Mode */
+#ifdef CONFIG_64BIT
+	unsigned long long	: 31;
+	unsigned long long ia	: 64;/* Instruction Address */
+#else
+	unsigned long long ia	: 31;/* Instruction Address */
+#endif
+};
+
+enum {
+	PSW_AMODE_24BIT = 0,
+	PSW_AMODE_31BIT = 1,
+	PSW_AMODE_64BIT = 3
+};
+
+enum {
+	PSW_AS_PRIMARY	 = 0,
+	PSW_AS_ACCREG	 = 1,
+	PSW_AS_SECONDARY = 2,
+	PSW_AS_HOME	 = 3
+};
+
+#define psw_bits(__psw) (*({			\
+	typecheck(psw_t, __psw);		\
+	&(*(struct psw_bits *)(&(__psw)));	\
+}))
+
 /*
  * The pt_regs struct defines the way the registers are stored on
  * the stack during a system call.

arch/s390/include/asm/sclp.h

@@ -28,7 +28,11 @@ struct sclp_ipl_info {
 
 struct sclp_cpu_entry {
 	u8 address;
-	u8 reserved0[13];
+	u8 reserved0[2];
+	u8 : 3;
+	u8 siif : 1;
+	u8 : 4;
+	u8 reserved2[10];
 	u8 type;
 	u8 reserved1;
 } __attribute__((packed));
@@ -61,5 +65,6 @@ int sclp_pci_deconfigure(u32 fid);
 int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
 unsigned long sclp_get_hsa_size(void);
 void sclp_early_detect(void);
+int sclp_has_siif(void);
 
 #endif /* _ASM_S390_SCLP_H */

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

@@ -15,6 +15,7 @@
 #include <linux/types.h>
 
 #define __KVM_S390
+#define __KVM_HAVE_GUEST_DEBUG
 
 /* Device control API: s390-specific devices */
 #define KVM_DEV_FLIC_GET_ALL_IRQS	1
@@ -54,6 +55,13 @@ struct kvm_s390_io_adapter_req {
 	__u64 addr;
 };
 
+/* kvm attr_group  on vm fd */
+#define KVM_S390_VM_MEM_CTRL		0
+
+/* kvm attributes for mem_ctrl */
+#define KVM_S390_VM_MEM_ENABLE_CMMA	0
+#define KVM_S390_VM_MEM_CLR_CMMA	1
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* general purpose regs for s390 */
@@ -72,11 +80,31 @@ struct kvm_fpu {
 	__u64 fprs[16];
 };
 
+#define KVM_GUESTDBG_USE_HW_BP		0x00010000
+
+#define KVM_HW_BP			1
+#define KVM_HW_WP_WRITE			2
+#define KVM_SINGLESTEP			4
+
 struct kvm_debug_exit_arch {
+	__u64 addr;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
+};
+
+struct kvm_hw_breakpoint {
+	__u64 addr;
+	__u64 phys_addr;
+	__u64 len;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
 };
 
 /* for KVM_SET_GUEST_DEBUG */
 struct kvm_guest_debug_arch {
+	__u32 nr_hw_bp;
+	__u32 pad; /* Should be set to 0 */
+	struct kvm_hw_breakpoint __user *hw_bp;
 };
 
 #define KVM_SYNC_PREFIX (1UL << 0)

arch/s390/kernel/asm-offsets.c

@@ -89,16 +89,22 @@ int main(void)
 	DEFINE(__LC_PGM_ILC, offsetof(struct _lowcore, pgm_ilc));
 	DEFINE(__LC_PGM_INT_CODE, offsetof(struct _lowcore, pgm_code));
 	DEFINE(__LC_TRANS_EXC_CODE, offsetof(struct _lowcore, trans_exc_code));
-	DEFINE(__LC_PER_CAUSE, offsetof(struct _lowcore, per_perc_atmid));
+	DEFINE(__LC_MON_CLASS_NR, offsetof(struct _lowcore, mon_class_num));
+	DEFINE(__LC_PER_CODE, offsetof(struct _lowcore, per_code));
+	DEFINE(__LC_PER_ATMID, offsetof(struct _lowcore, per_atmid));
 	DEFINE(__LC_PER_ADDRESS, offsetof(struct _lowcore, per_address));
-	DEFINE(__LC_PER_PAID, offsetof(struct _lowcore, per_access_id));
-	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_access_id));
+	DEFINE(__LC_EXC_ACCESS_ID, offsetof(struct _lowcore, exc_access_id));
+	DEFINE(__LC_PER_ACCESS_ID, offsetof(struct _lowcore, per_access_id));
+	DEFINE(__LC_OP_ACCESS_ID, offsetof(struct _lowcore, op_access_id));
+	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_mode_id));
+	DEFINE(__LC_MON_CODE, offsetof(struct _lowcore, monitor_code));
 	DEFINE(__LC_SUBCHANNEL_ID, offsetof(struct _lowcore, subchannel_id));
 	DEFINE(__LC_SUBCHANNEL_NR, offsetof(struct _lowcore, subchannel_nr));
 	DEFINE(__LC_IO_INT_PARM, offsetof(struct _lowcore, io_int_parm));
 	DEFINE(__LC_IO_INT_WORD, offsetof(struct _lowcore, io_int_word));
 	DEFINE(__LC_STFL_FAC_LIST, offsetof(struct _lowcore, stfl_fac_list));
 	DEFINE(__LC_MCCK_CODE, offsetof(struct _lowcore, mcck_interruption_code));
+	DEFINE(__LC_MCCK_EXT_DAM_CODE, offsetof(struct _lowcore, external_damage_code));
 	DEFINE(__LC_RST_OLD_PSW, offsetof(struct _lowcore, restart_old_psw));
 	DEFINE(__LC_EXT_OLD_PSW, offsetof(struct _lowcore, external_old_psw));
 	DEFINE(__LC_SVC_OLD_PSW, offsetof(struct _lowcore, svc_old_psw));
@@ -156,6 +162,8 @@ int main(void)
 #ifdef CONFIG_32BIT
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr));
 #else /* CONFIG_32BIT */
+	DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code));
+	DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address));
 	DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2));
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area));
 	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));

arch/s390/kernel/entry.S

@@ -391,8 +391,8 @@ ENTRY(pgm_check_handler)
 	jz	pgm_kprobe
 	oi	__TI_flags+3(%r12),_TIF_PER_TRAP
 	mvc	__THREAD_per_address(4,%r1),__LC_PER_ADDRESS
-	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CAUSE
-	mvc	__THREAD_per_paid(1,%r1),__LC_PER_PAID
+	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CODE
+	mvc	__THREAD_per_paid(1,%r1),__LC_PER_ACCESS_ID
 0:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
 	l	%r1,BASED(.Ljump_table)

arch/s390/kernel/entry64.S

@@ -423,8 +423,8 @@ ENTRY(pgm_check_handler)
 	jz	pgm_kprobe
 	oi	__TI_flags+7(%r12),_TIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
-	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CAUSE
-	mvc	__THREAD_per_paid(1,%r14),__LC_PER_PAID
+	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
+	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
 0:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table

arch/s390/kvm/Makefile

@@ -11,5 +11,7 @@ common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqch
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
-kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o
+kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o
+kvm-objs += diag.o gaccess.o guestdbg.o
+
 obj-$(CONFIG_KVM) += kvm.o

arch/s390/kvm/diag.c

@@ -64,12 +64,12 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 	int rc;
 	u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4;
 	u16 ry = (vcpu->arch.sie_block->ipa & 0x0f);
-	unsigned long hva_token = KVM_HVA_ERR_BAD;
 
 	if (vcpu->run->s.regs.gprs[rx] & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	if (copy_from_guest(vcpu, &parm, vcpu->run->s.regs.gprs[rx], sizeof(parm)))
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = read_guest(vcpu, vcpu->run->s.regs.gprs[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)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
@@ -89,8 +89,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 		    parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL)
 			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-		hva_token = gfn_to_hva(vcpu->kvm, gpa_to_gfn(parm.token_addr));
-		if (kvm_is_error_hva(hva_token))
+		if (kvm_is_error_gpa(vcpu->kvm, parm.token_addr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		vcpu->arch.pfault_token = parm.token_addr;
@@ -167,17 +166,11 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 
 	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
 	switch (subcode) {
-	case 0:
-	case 1:
-		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
-		return -EOPNOTSUPP;
 	case 3:
 		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
-		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
 		break;
 	case 4:
 		vcpu->run->s390_reset_flags = 0;
-		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
 		break;
 	default:
 		return -EOPNOTSUPP;

arch/s390/kvm/intercept.c

@@ -16,6 +16,7 @@
 #include <linux/pagemap.h>
 
 #include <asm/kvm_host.h>
+#include <asm/asm-offsets.h>
 
 #include "kvm-s390.h"
 #include "gaccess.h"
@@ -29,6 +30,7 @@ static const intercept_handler_t instruction_handlers[256] = {
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
+	[0xb6] = kvm_s390_handle_stctl,
 	[0xb7] = kvm_s390_handle_lctl,
 	[0xb9] = kvm_s390_handle_b9,
 	[0xe5] = kvm_s390_handle_e5,
@@ -109,22 +111,112 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
+static void __extract_prog_irq(struct kvm_vcpu *vcpu,
+			       struct kvm_s390_pgm_info *pgm_info)
+{
+	memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info));
+	pgm_info->code = vcpu->arch.sie_block->iprcc;
+
+	switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) {
+	case PGM_AFX_TRANSLATION:
+	case PGM_ASX_TRANSLATION:
+	case PGM_EX_TRANSLATION:
+	case PGM_LFX_TRANSLATION:
+	case PGM_LSTE_SEQUENCE:
+	case PGM_LSX_TRANSLATION:
+	case PGM_LX_TRANSLATION:
+	case PGM_PRIMARY_AUTHORITY:
+	case PGM_SECONDARY_AUTHORITY:
+	case PGM_SPACE_SWITCH:
+		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		break;
+	case PGM_ALEN_TRANSLATION:
+	case PGM_ALE_SEQUENCE:
+	case PGM_ASTE_INSTANCE:
+	case PGM_ASTE_SEQUENCE:
+	case PGM_ASTE_VALIDITY:
+	case PGM_EXTENDED_AUTHORITY:
+		pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+		break;
+	case PGM_ASCE_TYPE:
+	case PGM_PAGE_TRANSLATION:
+	case PGM_REGION_FIRST_TRANS:
+	case PGM_REGION_SECOND_TRANS:
+	case PGM_REGION_THIRD_TRANS:
+	case PGM_SEGMENT_TRANSLATION:
+		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
+		pgm_info->op_access_id  = vcpu->arch.sie_block->oai;
+		break;
+	case PGM_MONITOR:
+		pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn;
+		pgm_info->mon_code = vcpu->arch.sie_block->tecmc;
+		break;
+	case PGM_DATA:
+		pgm_info->data_exc_code = vcpu->arch.sie_block->dxc;
+		break;
+	case PGM_PROTECTION:
+		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
+		break;
+	default:
+		break;
+	}
+
+	if (vcpu->arch.sie_block->iprcc & PGM_PER) {
+		pgm_info->per_code = vcpu->arch.sie_block->perc;
+		pgm_info->per_atmid = vcpu->arch.sie_block->peratmid;
+		pgm_info->per_address = vcpu->arch.sie_block->peraddr;
+		pgm_info->per_access_id = vcpu->arch.sie_block->peraid;
+	}
+}
+
+/*
+ * restore ITDB to program-interruption TDB in guest lowcore
+ * and set TX abort indication if required
+*/
+static int handle_itdb(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_itdb *itdb;
+	int rc;
+
+	if (!IS_TE_ENABLED(vcpu) || !IS_ITDB_VALID(vcpu))
+		return 0;
+	if (current->thread.per_flags & PER_FLAG_NO_TE)
+		return 0;
+	itdb = (struct kvm_s390_itdb *)vcpu->arch.sie_block->itdba;
+	rc = write_guest_lc(vcpu, __LC_PGM_TDB, itdb, sizeof(*itdb));
+	if (rc)
+		return rc;
+	memset(itdb, 0, sizeof(*itdb));
+
+	return 0;
+}
+
+#define per_event(vcpu) (vcpu->arch.sie_block->iprcc & PGM_PER)
+
 static int handle_prog(struct kvm_vcpu *vcpu)
 {
+	struct kvm_s390_pgm_info pgm_info;
+	int rc;
+
 	vcpu->stat.exit_program_interruption++;
 
-	/* Restore ITDB to Program-Interruption TDB in guest memory */
-	if (IS_TE_ENABLED(vcpu) &&
-	    !(current->thread.per_flags & PER_FLAG_NO_TE) &&
-	    IS_ITDB_VALID(vcpu)) {
-		copy_to_guest(vcpu, TDB_ADDR, vcpu->arch.sie_block->itdba,
-			      sizeof(struct kvm_s390_itdb));
-		memset((void *) vcpu->arch.sie_block->itdba, 0,
-		       sizeof(struct kvm_s390_itdb));
+	if (guestdbg_enabled(vcpu) && per_event(vcpu)) {
+		kvm_s390_handle_per_event(vcpu);
+		/* the interrupt might have been filtered out completely */
+		if (vcpu->arch.sie_block->iprcc == 0)
+			return 0;
 	}
 
 	trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc);
-	return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc);
+
+	rc = handle_itdb(vcpu);
+	if (rc)
+		return rc;
+
+	__extract_prog_irq(vcpu, &pgm_info);
+	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
 static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)

arch/s390/kvm/kvm-s390.h

@@ -28,7 +28,6 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
 
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & 0x10))
-#define TDB_ADDR		0x1800UL
 #define TDB_FORMAT1		1
 #define IS_ITDB_VALID(vcpu)	((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1))
 
@@ -130,6 +129,7 @@ void kvm_s390_tasklet(unsigned long parm);
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
 void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
 void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu);
+void kvm_s390_clear_float_irqs(struct kvm *kvm);
 int __must_check kvm_s390_inject_vm(struct kvm *kvm,
 				    struct kvm_s390_interrupt *s390int);
 int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
@@ -137,6 +137,8 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 						    u64 cr6, u64 schid);
+void kvm_s390_reinject_io_int(struct kvm *kvm,
+			      struct kvm_s390_interrupt_info *inti);
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
 
 /* implemented in priv.c */
@@ -145,6 +147,7 @@ int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_b9(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_eb(struct kvm_vcpu *vcpu);
 
@@ -158,14 +161,64 @@ void s390_vcpu_block(struct kvm_vcpu *vcpu);
 void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
 void exit_sie_sync(struct kvm_vcpu *vcpu);
-/* are we going to support cmma? */
-bool kvm_enabled_cmma(void);
+int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
+/* is cmma enabled */
+bool kvm_s390_cmma_enabled(struct kvm *kvm);
+int test_vfacility(unsigned long nr);
+
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
+/* implemented in interrupt.c */
+int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
+			     struct kvm_s390_pgm_info *pgm_info);
+
+/**
+ * kvm_s390_inject_prog_cond - conditionally inject a program check
+ * @vcpu: virtual cpu
+ * @rc: original return/error code
+ *
+ * This function is supposed to be used after regular guest access functions
+ * failed, to conditionally inject a program check to a vcpu. The typical
+ * pattern would look like
+ *
+ * rc = write_guest(vcpu, addr, data, len);
+ * if (rc)
+ *	return kvm_s390_inject_prog_cond(vcpu, rc);
+ *
+ * A negative return code from guest access functions implies an internal error
+ * like e.g. out of memory. In these cases no program check should be injected
+ * to the guest.
+ * A positive value implies that an exception happened while accessing a guest's
+ * memory. In this case all data belonging to the corresponding program check
+ * has been stored in vcpu->arch.pgm and can be injected with
+ * kvm_s390_inject_prog_irq().
+ *
+ * Returns: - the original @rc value if @rc was negative (internal error)
+ *	    - zero if @rc was already zero
+ *	    - zero or error code from injecting if @rc was positive
+ *	      (program check injected to @vcpu)
+ */
+static inline int kvm_s390_inject_prog_cond(struct kvm_vcpu *vcpu, int rc)
+{
+	if (rc <= 0)
+		return rc;
+	return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+}
 
 /* implemented in interrupt.c */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int psw_extint_disabled(struct kvm_vcpu *vcpu);
 void kvm_s390_destroy_adapters(struct kvm *kvm);
 
+/* implemented in guestdbg.c */
+void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
+void kvm_s390_restore_guest_per_regs(struct kvm_vcpu *vcpu);
+void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu);
+int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
+			    struct kvm_guest_debug *dbg);
+void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
+void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
+void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
+
 #endif

arch/s390/kvm/sigp.c

@@ -235,7 +235,6 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 	struct kvm_vcpu *dst_vcpu = NULL;
 	struct kvm_s390_interrupt_info *inti;
 	int rc;
-	u8 tmp;
 
 	if (cpu_addr < KVM_MAX_VCPUS)
 		dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
@@ -243,10 +242,13 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 		return SIGP_CC_NOT_OPERATIONAL;
 	li = &dst_vcpu->arch.local_int;
 
-	/* make sure that the new value is valid memory */
-	address = address & 0x7fffe000u;
-	if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
-	   copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) {
+	/*
+	 * Make sure the new value is valid memory. We only need to check the
+	 * first page, since address is 8k aligned and memory pieces are always
+	 * at least 1MB aligned and have at least a size of 1MB.
+	 */
+	address &= 0x7fffe000u;
+	if (kvm_is_error_gpa(vcpu->kvm, address)) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INVALID_PARAMETER;
 		return SIGP_CC_STATUS_STORED;

arch/s390/kvm/trace.h

@@ -30,6 +30,20 @@
 	TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id,		\
 		  __entry->pswmask, __entry->pswaddr, p_args)
 
+TRACE_EVENT(kvm_s390_skey_related_inst,
+	    TP_PROTO(VCPU_PROTO_COMMON),
+	    TP_ARGS(VCPU_ARGS_COMMON),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    ),
+	    VCPU_TP_PRINTK("%s", "first instruction related to skeys on vcpu")
+	);
+
 TRACE_EVENT(kvm_s390_major_guest_pfault,
 	    TP_PROTO(VCPU_PROTO_COMMON),
 	    TP_ARGS(VCPU_ARGS_COMMON),
@@ -301,6 +315,31 @@ TRACE_EVENT(kvm_s390_handle_lctl,
 			   __entry->reg1, __entry->reg3, __entry->addr)
 	);
 
+TRACE_EVENT(kvm_s390_handle_stctl,
+	    TP_PROTO(VCPU_PROTO_COMMON, int g, int reg1, int reg3, u64 addr),
+	    TP_ARGS(VCPU_ARGS_COMMON, g, reg1, reg3, addr),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, g)
+		    __field(int, reg1)
+		    __field(int, reg3)
+		    __field(u64, addr)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->g = g;
+		    __entry->reg1 = reg1;
+		    __entry->reg3 = reg3;
+		    __entry->addr = addr;
+		    ),
+
+	    VCPU_TP_PRINTK("%s: storing cr %x-%x to %016llx",
+			   __entry->g ? "stctg" : "stctl",
+			   __entry->reg1, __entry->reg3, __entry->addr)
+	);
+
 TRACE_EVENT(kvm_s390_handle_prefix,
 	    TP_PROTO(VCPU_PROTO_COMMON, int set, u32 address),
 	    TP_ARGS(VCPU_ARGS_COMMON, set, address),

arch/s390/mm/pgtable.c

@@ -832,6 +832,7 @@ void gmap_do_ipte_notify(struct mm_struct *mm, pte_t *pte)
 	}
 	spin_unlock(&gmap_notifier_lock);
 }
+EXPORT_SYMBOL_GPL(gmap_do_ipte_notify);
 
 static inline int page_table_with_pgste(struct page *page)
 {
@@ -864,8 +865,7 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
 	atomic_set(&page->_mapcount, 0);
 	table = (unsigned long *) page_to_phys(page);
 	clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
-	clear_table(table + PTRS_PER_PTE, PGSTE_HR_BIT | PGSTE_HC_BIT,
-		    PAGE_SIZE/2);
+	clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
 	return table;
 }
 
@@ -883,8 +883,8 @@ static inline void page_table_free_pgste(unsigned long *table)
 	__free_page(page);
 }
 
-static inline unsigned long page_table_reset_pte(struct mm_struct *mm,
-			pmd_t *pmd, unsigned long addr, unsigned long end)
+static inline unsigned long page_table_reset_pte(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, unsigned long end, bool init_skey)
 {
 	pte_t *start_pte, *pte;
 	spinlock_t *ptl;
@@ -895,6 +895,22 @@ static inline unsigned long page_table_reset_pte(struct mm_struct *mm,
 	do {
 		pgste = pgste_get_lock(pte);
 		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+		if (init_skey) {
+			unsigned long address;
+
+			pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
+					      PGSTE_GR_BIT | PGSTE_GC_BIT);
+
+			/* skip invalid and not writable pages */
+			if (pte_val(*pte) & _PAGE_INVALID ||
+			    !(pte_val(*pte) & _PAGE_WRITE)) {
+				pgste_set_unlock(pte, pgste);
+				continue;
+			}
+
+			address = pte_val(*pte) & PAGE_MASK;
+			page_set_storage_key(address, PAGE_DEFAULT_KEY, 1);
+		}
 		pgste_set_unlock(pte, pgste);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap_unlock(start_pte, ptl);
@@ -902,8 +918,8 @@ static inline unsigned long page_table_reset_pte(struct mm_struct *mm,
 	return addr;
 }
 
-static inline unsigned long page_table_reset_pmd(struct mm_struct *mm,
-			pud_t *pud, unsigned long addr, unsigned long end)
+static inline unsigned long page_table_reset_pmd(struct mm_struct *mm, pud_t *pud,
+			unsigned long addr, unsigned long end, bool init_skey)
 {
 	unsigned long next;
 	pmd_t *pmd;
@@ -913,14 +929,14 @@ static inline unsigned long page_table_reset_pmd(struct mm_struct *mm,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		next = page_table_reset_pte(mm, pmd, addr, next);
+		next = page_table_reset_pte(mm, pmd, addr, next, init_skey);
 	} while (pmd++, addr = next, addr != end);
 
 	return addr;
 }
 
-static inline unsigned long page_table_reset_pud(struct mm_struct *mm,
-			pgd_t *pgd, unsigned long addr, unsigned long end)
+static inline unsigned long page_table_reset_pud(struct mm_struct *mm, pgd_t *pgd,
+			unsigned long addr, unsigned long end, bool init_skey)
 {
 	unsigned long next;
 	pud_t *pud;
@@ -930,14 +946,14 @@ static inline unsigned long page_table_reset_pud(struct mm_struct *mm,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		next = page_table_reset_pmd(mm, pud, addr, next);
+		next = page_table_reset_pmd(mm, pud, addr, next, init_skey);
 	} while (pud++, addr = next, addr != end);
 
 	return addr;
 }
 
-void page_table_reset_pgste(struct mm_struct *mm,
-			unsigned long start, unsigned long end)
+void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
+			    unsigned long end, bool init_skey)
 {
 	unsigned long addr, next;
 	pgd_t *pgd;
@@ -949,7 +965,7 @@ void page_table_reset_pgste(struct mm_struct *mm,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		next = page_table_reset_pud(mm, pgd, addr, next);
+		next = page_table_reset_pud(mm, pgd, addr, next, init_skey);
 	} while (pgd++, addr = next, addr != end);
 	up_read(&mm->mmap_sem);
 }
@@ -989,7 +1005,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	/* changing the guest storage key is considered a change of the page */
 	if ((pgste_val(new) ^ pgste_val(old)) &
 	    (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT))
-		pgste_val(new) |= PGSTE_HC_BIT;
+		pgste_val(new) |= PGSTE_UC_BIT;
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(*ptep, ptl);
@@ -1011,6 +1027,11 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
 	return NULL;
 }
 
+void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
+			    unsigned long end, bool init_skey)
+{
+}
+
 static inline void page_table_free_pgste(unsigned long *table)
 {
 }
@@ -1357,6 +1378,50 @@ int s390_enable_sie(void)
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
 
+/*
+ * Enable storage key handling from now on and initialize the storage
+ * keys with the default key.
+ */
+void s390_enable_skey(void)
+{
+	/*
+	 * To avoid races between multiple vcpus, ending in calling
+	 * page_table_reset twice or more,
+	 * the page_table_lock is taken for serialization.
+	 */
+	spin_lock(&current->mm->page_table_lock);
+	if (mm_use_skey(current->mm)) {
+		spin_unlock(&current->mm->page_table_lock);
+		return;
+	}
+
+	current->mm->context.use_skey = 1;
+	spin_unlock(&current->mm->page_table_lock);
+	page_table_reset_pgste(current->mm, 0, TASK_SIZE, true);
+}
+EXPORT_SYMBOL_GPL(s390_enable_skey);
+
+/*
+ * Test and reset if a guest page is dirty
+ */
+bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap)
+{
+	pte_t *pte;
+	spinlock_t *ptl;
+	bool dirty = false;
+
+	pte = get_locked_pte(gmap->mm, address, &ptl);
+	if (unlikely(!pte))
+		return false;
+
+	if (ptep_test_and_clear_user_dirty(gmap->mm, address, pte))
+		dirty = true;
+
+	spin_unlock(ptl);
+	return dirty;
+}
+EXPORT_SYMBOL_GPL(gmap_test_and_clear_dirty);
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmdp)

drivers/s390/char/sclp_early.c

@@ -22,7 +22,8 @@ struct read_info_sccb {
 	u8	rnsize;			/* 10 */
 	u8	_reserved0[16 - 11];	/* 11-15 */
 	u16	ncpurl;			/* 16-17 */
-	u8	_reserved7[24 - 18];	/* 18-23 */
+	u16	cpuoff;			/* 18-19 */
+	u8	_reserved7[24 - 20];	/* 20-23 */
 	u8	loadparm[8];		/* 24-31 */
 	u8	_reserved1[48 - 32];	/* 32-47 */
 	u64	facilities;		/* 48-55 */
@@ -45,6 +46,7 @@ static unsigned int sclp_con_has_linemode __initdata;
 static unsigned long sclp_hsa_size;
 static unsigned int sclp_max_cpu;
 static struct sclp_ipl_info sclp_ipl_info;
+static unsigned char sclp_siif;
 
 u64 sclp_facilities;
 u8 sclp_fac84;
@@ -96,6 +98,9 @@ static int __init sclp_read_info_early(struct read_info_sccb *sccb)
 
 static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 {
+	struct sclp_cpu_entry *cpue;
+	u16 boot_cpu_address, cpu;
+
 	if (sclp_read_info_early(sccb))
 		return;
 
@@ -116,6 +121,15 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 		sclp_max_cpu = sccb->hcpua + 1;
 	}
 
+	boot_cpu_address = stap();
+	cpue = (void *)sccb + sccb->cpuoff;
+	for (cpu = 0; cpu < sccb->ncpurl; cpue++, cpu++) {
+		if (boot_cpu_address != cpue->address)
+			continue;
+		sclp_siif = cpue->siif;
+		break;
+	}
+
 	/* Save IPL information */
 	sclp_ipl_info.is_valid = 1;
 	if (sccb->flags & 0x2)
@@ -148,6 +162,12 @@ unsigned int sclp_get_max_cpu(void)
 	return sclp_max_cpu;
 }
 
+int sclp_has_siif(void)
+{
+	return sclp_siif;
+}
+EXPORT_SYMBOL(sclp_has_siif);
+
 /*
  * This function will be called after sclp_facilities_detect(), which gets
  * called from early.c code. The sclp_facilities_detect() function retrieves

include/linux/kvm_host.h

@@ -880,6 +880,13 @@ static inline hpa_t pfn_to_hpa(pfn_t pfn)
 	return (hpa_t)pfn << PAGE_SHIFT;
 }
 
+static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
+{
+	unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+
+	return kvm_is_error_hva(hva);
+}
+
 static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
 {
 	set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);

include/uapi/linux/kvm.h

@@ -745,6 +745,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_ENABLE_CAP_VM 98
 #define KVM_CAP_S390_IRQCHIP 99
 #define KVM_CAP_IOEVENTFD_NO_LENGTH 100
+#define KVM_CAP_VM_ATTRIBUTES 101
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

virt/kvm/kvm_main.c

@@ -637,14 +637,12 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
  */
 static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
-#ifndef CONFIG_S390
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
 	memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes);
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
-#endif /* !CONFIG_S390 */
 	return 0;
 }