Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "On the x86 side, there are some optimizations and documentation
  updates.  The big ARM/KVM change for 3.11, support for AArch64, will
  come through Catalin Marinas's tree.  s390 and PPC have misc cleanups
  and bugfixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (87 commits)
  KVM: PPC: Ignore PIR writes
  KVM: PPC: Book3S PR: Invalidate SLB entries properly
  KVM: PPC: Book3S PR: Allow guest to use 1TB segments
  KVM: PPC: Book3S PR: Don't keep scanning HPTEG after we find a match
  KVM: PPC: Book3S PR: Fix invalidation of SLB entry 0 on guest entry
  KVM: PPC: Book3S PR: Fix proto-VSID calculations
  KVM: PPC: Guard doorbell exception with CONFIG_PPC_DOORBELL
  KVM: Fix RTC interrupt coalescing tracking
  kvm: Add a tracepoint write_tsc_offset
  KVM: MMU: Inform users of mmio generation wraparound
  KVM: MMU: document fast invalidate all mmio sptes
  KVM: MMU: document fast invalidate all pages
  KVM: MMU: document fast page fault
  KVM: MMU: document mmio page fault
  KVM: MMU: document write_flooding_count
  KVM: MMU: document clear_spte_count
  KVM: MMU: drop kvm_mmu_zap_mmio_sptes
  KVM: MMU: init kvm generation close to mmio wrap-around value
  KVM: MMU: add tracepoint for check_mmio_spte
  KVM: MMU: fast invalidate all mmio sptes
  ...

16 files changed, 527 insertions, 283 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 16bd5d169cdb..3238d4004e84 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -62,13 +62,20 @@ struct sca_block {
 #define CPUSTAT_MCDS       0x00000100
 #define CPUSTAT_SM         0x00000080
 #define CPUSTAT_G          0x00000008
+#define CPUSTAT_GED        0x00000004
 #define CPUSTAT_J          0x00000002
 #define CPUSTAT_P          0x00000001
 
 struct kvm_s390_sie_block {
 	atomic_t cpuflags;		/* 0x0000 */
 	__u32	prefix;			/* 0x0004 */
-	__u8	reserved8[32];		/* 0x0008 */
+	__u8	reserved08[4];		/* 0x0008 */
+#define PROG_IN_SIE (1<<0)
+	__u32	prog0c;			/* 0x000c */
+	__u8	reserved10[16];		/* 0x0010 */
+#define PROG_BLOCK_SIE 0x00000001
+	atomic_t prog20;		/* 0x0020 */
+	__u8	reserved24[4];		/* 0x0024 */
 	__u64	cputm;			/* 0x0028 */
 	__u64	ckc;			/* 0x0030 */
 	__u64	epoch;			/* 0x0038 */
@@ -90,7 +97,8 @@ struct kvm_s390_sie_block {
 	__u32	scaoh;			/* 0x005c */
 	__u8	reserved60;		/* 0x0060 */
 	__u8	ecb;			/* 0x0061 */
-	__u8	reserved62[2];		/* 0x0062 */
+	__u8    ecb2;                   /* 0x0062 */
+	__u8    reserved63[1];          /* 0x0063 */
 	__u32	scaol;			/* 0x0064 */
 	__u8	reserved68[4];		/* 0x0068 */
 	__u32	todpr;			/* 0x006c */
@@ -130,6 +138,7 @@ struct kvm_vcpu_stat {
 	u32 deliver_program_int;
 	u32 deliver_io_int;
 	u32 exit_wait_state;
+	u32 instruction_pfmf;
 	u32 instruction_stidp;
 	u32 instruction_spx;
 	u32 instruction_stpx;
@@ -166,7 +175,7 @@ struct kvm_s390_ext_info {
 };
 
 #define PGM_OPERATION            0x01
-#define PGM_PRIVILEGED_OPERATION 0x02
+#define PGM_PRIVILEGED_OP	 0x02
 #define PGM_EXECUTE              0x03
 #define PGM_PROTECTION           0x04
 #define PGM_ADDRESSING           0x05
@@ -219,7 +228,7 @@ struct kvm_s390_local_interrupt {
 	atomic_t active;
 	struct kvm_s390_float_interrupt *float_int;
 	int timer_due; /* event indicator for waitqueue below */
-	wait_queue_head_t wq;
+	wait_queue_head_t *wq;
 	atomic_t *cpuflags;
 	unsigned int action_bits;
 };
@@ -266,4 +275,5 @@ struct kvm_arch{
 };
 
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
+extern char sie_exit;
 #endif
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 5f0173a31693..1141fb3e7b21 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -14,3 +14,13 @@
 /* Per-CPU flags for PMU states */
 #define PMU_F_RESERVED			0x1000
 #define PMU_F_ENABLED			0x2000
+
+#ifdef CONFIG_64BIT
+
+/* Perf callbacks */
+struct pt_regs;
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs) perf_misc_flags(regs)
+
+#endif /* CONFIG_64BIT */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 9aefa3c64eb2..0ea4e591fa78 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -296,18 +296,16 @@ extern unsigned long MODULES_END;
 #define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INV)
 
 /* Page status table bits for virtualization */
-#define RCP_ACC_BITS	0xf0000000UL
-#define RCP_FP_BIT	0x08000000UL
-#define RCP_PCL_BIT	0x00800000UL
-#define RCP_HR_BIT	0x00400000UL
-#define RCP_HC_BIT	0x00200000UL
-#define RCP_GR_BIT	0x00040000UL
-#define RCP_GC_BIT	0x00020000UL
-#define RCP_IN_BIT	0x00002000UL	/* IPTE notify bit */
-
-/* User dirty / referenced bit for KVM's migration feature */
-#define KVM_UR_BIT	0x00008000UL
-#define KVM_UC_BIT	0x00004000UL
+#define PGSTE_ACC_BITS	0xf0000000UL
+#define PGSTE_FP_BIT	0x08000000UL
+#define PGSTE_PCL_BIT	0x00800000UL
+#define PGSTE_HR_BIT	0x00400000UL
+#define PGSTE_HC_BIT	0x00200000UL
+#define PGSTE_GR_BIT	0x00040000UL
+#define PGSTE_GC_BIT	0x00020000UL
+#define PGSTE_UR_BIT	0x00008000UL
+#define PGSTE_UC_BIT	0x00004000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x00002000UL	/* IPTE notify bit */
 
 #else /* CONFIG_64BIT */
 
@@ -364,18 +362,16 @@ extern unsigned long MODULES_END;
 				 | _SEGMENT_ENTRY_SPLIT | _SEGMENT_ENTRY_CO)
 
 /* Page status table bits for virtualization */
-#define RCP_ACC_BITS	0xf000000000000000UL
-#define RCP_FP_BIT	0x0800000000000000UL
-#define RCP_PCL_BIT	0x0080000000000000UL
-#define RCP_HR_BIT	0x0040000000000000UL
-#define RCP_HC_BIT	0x0020000000000000UL
-#define RCP_GR_BIT	0x0004000000000000UL
-#define RCP_GC_BIT	0x0002000000000000UL
-#define RCP_IN_BIT	0x0000200000000000UL	/* IPTE notify bit */
-
-/* User dirty / referenced bit for KVM's migration feature */
-#define KVM_UR_BIT	0x0000800000000000UL
-#define KVM_UC_BIT	0x0000400000000000UL
+#define PGSTE_ACC_BITS	0xf000000000000000UL
+#define PGSTE_FP_BIT	0x0800000000000000UL
+#define PGSTE_PCL_BIT	0x0080000000000000UL
+#define PGSTE_HR_BIT	0x0040000000000000UL
+#define PGSTE_HC_BIT	0x0020000000000000UL
+#define PGSTE_GR_BIT	0x0004000000000000UL
+#define PGSTE_GC_BIT	0x0002000000000000UL
+#define PGSTE_UR_BIT	0x0000800000000000UL
+#define PGSTE_UC_BIT	0x0000400000000000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x0000200000000000UL	/* IPTE notify bit */
 
 #endif /* CONFIG_64BIT */
 
@@ -615,8 +611,8 @@ static inline pgste_t pgste_get_lock(pte_t *ptep)
 	asm(
 		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	nihh	%0,0xff7f\n"	/* clear RCP_PCL_BIT in old */
-		"	oihh	%1,0x0080\n"	/* set RCP_PCL_BIT in new */
+		"	nihh	%0,0xff7f\n"	/* clear PCL bit in old */
+		"	oihh	%1,0x0080\n"	/* set PCL bit in new */
 		"	csg	%0,%1,%2\n"
 		"	jl	0b\n"
 		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
@@ -629,7 +625,7 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
 	asm(
-		"	nihh	%1,0xff7f\n"	/* clear RCP_PCL_BIT */
+		"	nihh	%1,0xff7f\n"	/* clear PCL bit */
 		"	stg	%1,%0\n"
 		: "=Q" (ptep[PTRS_PER_PTE])
 		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
@@ -662,14 +658,14 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 	else if (bits)
 		page_reset_referenced(address);
 	/* Transfer page changed & referenced bit to guest bits in pgste */
-	pgste_val(pgste) |= bits << 48;		/* RCP_GR_BIT & RCP_GC_BIT */
+	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
 	/* Get host changed & referenced bits from pgste */
-	bits |= (pgste_val(pgste) & (RCP_HR_BIT | RCP_HC_BIT)) >> 52;
+	bits |= (pgste_val(pgste) & (PGSTE_HR_BIT | PGSTE_HC_BIT)) >> 52;
 	/* Transfer page changed & referenced bit to kvm user bits */
-	pgste_val(pgste) |= bits << 45;		/* KVM_UR_BIT & KVM_UC_BIT */
+	pgste_val(pgste) |= bits << 45;		/* PGSTE_UR_BIT & PGSTE_UC_BIT */
 	/* Clear relevant host bits in pgste. */
-	pgste_val(pgste) &= ~(RCP_HR_BIT | RCP_HC_BIT);
-	pgste_val(pgste) &= ~(RCP_ACC_BITS | RCP_FP_BIT);
+	pgste_val(pgste) &= ~(PGSTE_HR_BIT | PGSTE_HC_BIT);
+	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
 	/* Copy page access key and fetch protection bit to pgste */
 	pgste_val(pgste) |=
 		(unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
@@ -690,15 +686,15 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 	/* Get referenced bit from storage key */
 	young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
 	if (young)
-		pgste_val(pgste) |= RCP_GR_BIT;
+		pgste_val(pgste) |= PGSTE_GR_BIT;
 	/* Get host referenced bit from pgste */
-	if (pgste_val(pgste) & RCP_HR_BIT) {
-		pgste_val(pgste) &= ~RCP_HR_BIT;
+	if (pgste_val(pgste) & PGSTE_HR_BIT) {
+		pgste_val(pgste) &= ~PGSTE_HR_BIT;
 		young = 1;
 	}
 	/* Transfer referenced bit to kvm user bits and pte */
 	if (young) {
-		pgste_val(pgste) |= KVM_UR_BIT;
+		pgste_val(pgste) |= PGSTE_UR_BIT;
 		pte_val(*ptep) |= _PAGE_SWR;
 	}
 #endif
@@ -720,7 +716,7 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
 	 * The guest C/R information is still in the PGSTE, set real
 	 * key C/R to 0.
 	 */
-	nkey = (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56;
+	nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
 	page_set_storage_key(address, nkey, 0);
 #endif
 }
@@ -750,6 +746,7 @@ struct gmap {
 	struct mm_struct *mm;
 	unsigned long *table;
 	unsigned long asce;
+	void *private;
 	struct list_head crst_list;
 };
 
@@ -808,8 +805,8 @@ static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
 					pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	if (pgste_val(pgste) & RCP_IN_BIT) {
-		pgste_val(pgste) &= ~RCP_IN_BIT;
+	if (pgste_val(pgste) & PGSTE_IN_BIT) {
+		pgste_val(pgste) &= ~PGSTE_IN_BIT;
 		gmap_do_ipte_notify(mm, addr, ptep);
 	}
 #endif
@@ -977,8 +974,8 @@ static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste = pgste_update_all(ptep, pgste);
-		dirty = !!(pgste_val(pgste) & KVM_UC_BIT);
-		pgste_val(pgste) &= ~KVM_UC_BIT;
+		dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
+		pgste_val(pgste) &= ~PGSTE_UC_BIT;
 		pgste_set_unlock(ptep, pgste);
 		return dirty;
 	}
@@ -997,8 +994,8 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste = pgste_update_young(ptep, pgste);
-		young = !!(pgste_val(pgste) & KVM_UR_BIT);
-		pgste_val(pgste) &= ~KVM_UR_BIT;
+		young = !!(pgste_val(pgste) & PGSTE_UR_BIT);
+		pgste_val(pgste) &= ~PGSTE_UR_BIT;
 		pgste_set_unlock(ptep, pgste);
 	}
 	return young;
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index d6de844bc30a..2416138ebd3e 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -7,6 +7,7 @@
 #define ASM_OFFSETS_C
 
 #include <linux/kbuild.h>
+#include <linux/kvm_host.h>
 #include <linux/sched.h>
 #include <asm/cputime.h>
 #include <asm/vdso.h>
@@ -162,6 +163,8 @@ int main(void)
 	DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb));
 	DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb));
 	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
+	DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c));
+	DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20));
 #endif /* CONFIG_32BIT */
 	return 0;
 }
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index bc5864c5148b..1c039d0c24c7 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -47,7 +47,6 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		 _TIF_MCCK_PENDING)
 _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		 _TIF_SYSCALL_TRACEPOINT)
-_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 
 #define BASED(name) name-system_call(%r13)
 
@@ -81,23 +80,27 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 #endif
 	.endm
 
-	.macro	HANDLE_SIE_INTERCEPT scratch,pgmcheck
+	.macro	HANDLE_SIE_INTERCEPT scratch,reason
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
 	tmhh	%r8,0x0001		# interrupting from user ?
-	jnz	.+42
+	jnz	.+62
 	lgr	\scratch,%r9
-	slg	\scratch,BASED(.Lsie_loop)
-	clg	\scratch,BASED(.Lsie_length)
-	.if	\pgmcheck
+	slg	\scratch,BASED(.Lsie_critical)
+	clg	\scratch,BASED(.Lsie_critical_length)
+	.if	\reason==1
 	# Some program interrupts are suppressing (e.g. protection).
 	# We must also check the instruction after SIE in that case.
 	# do_protection_exception will rewind to rewind_pad
-	jh	.+22
+	jh	.+42
 	.else
-	jhe	.+22
+	jhe	.+42
 	.endif
-	lg	%r9,BASED(.Lsie_loop)
-	LPP	BASED(.Lhost_id)	# set host id
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	LPP	__SF_EMPTY+16(%r15)		# set host id
+	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+	larl	%r9,sie_exit			# skip forward to sie_exit
+	mvi	__SF_EMPTY+31(%r15),\reason	# set exit reason
 #endif
 	.endm
 
@@ -450,7 +453,7 @@ ENTRY(io_int_handler)
 	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
 	lmg	%r8,%r9,__LC_IO_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14,0
+	HANDLE_SIE_INTERCEPT %r14,2
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
 	tmhh	%r8,0x0001		# interrupting from user?
 	jz	io_skip
@@ -603,7 +606,7 @@ ENTRY(ext_int_handler)
 	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
 	lmg	%r8,%r9,__LC_EXT_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14,0
+	HANDLE_SIE_INTERCEPT %r14,3
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
 	tmhh	%r8,0x0001		# interrupting from user ?
 	jz	ext_skip
@@ -651,7 +654,7 @@ ENTRY(mcck_int_handler)
 	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
 	lmg	%r8,%r9,__LC_MCK_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14,0
+	HANDLE_SIE_INTERCEPT %r14,4
 	tm	__LC_MCCK_CODE,0x80	# system damage?
 	jo	mcck_panic		# yes -> rest of mcck code invalid
 	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
@@ -945,56 +948,50 @@ ENTRY(sie64a)
 	stmg	%r6,%r14,__SF_GPRS(%r15)	# save kernel registers
 	stg	%r2,__SF_EMPTY(%r15)		# save control block pointer
 	stg	%r3,__SF_EMPTY+8(%r15)		# save guest register save area
-	xc	__SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0
+	xc	__SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason
 	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
-# some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions in the sie_loop should not cause program interrupts. So
-# lets use a nop (47 00 00 00) as a landing pad.
-# See also HANDLE_SIE_INTERCEPT
-rewind_pad:
-	nop	0
-sie_loop:
-	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
-	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
-	jnz	sie_exit
 	lg	%r14,__LC_GMAP			# get gmap pointer
 	ltgr	%r14,%r14
 	jz	sie_gmap
 	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
 sie_gmap:
 	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
+	tm	__SIE_PROG20+3(%r14),1		# last exit...
+	jnz	sie_done
 	LPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
 sie_done:
 	LPP	__SF_EMPTY+16(%r15)		# set host id
-	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
-sie_exit:
+	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+# some program checks are suppressing. C code (e.g. do_protection_exception)
+# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
+# instructions beween sie64a and sie_done should not cause program
+# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# See also HANDLE_SIE_INTERCEPT
+rewind_pad:
+	nop	0
+	.globl sie_exit
+sie_exit:
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
 	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
 	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
-	lghi	%r2,0
+	lg	%r2,__SF_EMPTY+24(%r15)		# return exit reason code
 	br	%r14
 sie_fault:
-	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
-	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
-	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
-	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
-	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
-	lghi	%r2,-EFAULT
-	br	%r14
+	lghi	%r14,-EFAULT
+	stg	%r14,__SF_EMPTY+24(%r15)	# set exit reason code
+	j	sie_exit
 
 	.align	8
-.Lsie_loop:
-	.quad	sie_loop
-.Lsie_length:
-	.quad	sie_done - sie_loop
-.Lhost_id:
-	.quad	0
+.Lsie_critical:
+	.quad	sie_gmap
+.Lsie_critical_length:
+	.quad	sie_done - sie_gmap
 
 	EX_TABLE(rewind_pad,sie_fault)
-	EX_TABLE(sie_loop,sie_fault)
+	EX_TABLE(sie_exit,sie_fault)
 #endif
 
 		.section .rodata, "a"
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index f58f37f66824..a6fc037671b1 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -13,6 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
+#include <linux/kvm_host.h>
 #include <linux/percpu.h>
 #include <linux/export.h>
 #include <asm/irq.h>
@@ -39,6 +40,57 @@ int perf_num_counters(void)
 }
 EXPORT_SYMBOL(perf_num_counters);
 
+static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs)
+{
+	struct stack_frame *stack = (struct stack_frame *) regs->gprs[15];
+
+	if (!stack)
+		return NULL;
+
+	return (struct kvm_s390_sie_block *) stack->empty1[0];
+}
+
+static bool is_in_guest(struct pt_regs *regs)
+{
+	unsigned long ip = instruction_pointer(regs);
+
+	if (user_mode(regs))
+		return false;
+
+	return ip == (unsigned long) &sie_exit;
+}
+
+static unsigned long guest_is_user_mode(struct pt_regs *regs)
+{
+	return sie_block(regs)->gpsw.mask & PSW_MASK_PSTATE;
+}
+
+static unsigned long instruction_pointer_guest(struct pt_regs *regs)
+{
+	return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN;
+}
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	return is_in_guest(regs) ? instruction_pointer_guest(regs)
+				 : instruction_pointer(regs);
+}
+
+static unsigned long perf_misc_guest_flags(struct pt_regs *regs)
+{
+	return guest_is_user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER
+					: PERF_RECORD_MISC_GUEST_KERNEL;
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	if (is_in_guest(regs))
+		return perf_misc_guest_flags(regs);
+
+	return user_mode(regs) ? PERF_RECORD_MISC_USER
+			       : PERF_RECORD_MISC_KERNEL;
+}
+
 void perf_event_print_debug(void)
 {
 	struct cpumf_ctr_info cf_info;
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
index 9bdbcef1da9e..3bac589844a7 100644
--- a/arch/s390/kernel/s390_ksyms.c
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -7,6 +7,7 @@ EXPORT_SYMBOL(_mcount);
 #endif
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
 EXPORT_SYMBOL(sie64a);
+EXPORT_SYMBOL(sie_exit);
 #endif
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 8fe9d65a4585..40b4c6470f88 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -6,7 +6,8 @@
 # it under the terms of the GNU General Public License (version 2 only)
 # as published by the Free Software Foundation.
 
-common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o eventfd.o)
+KVM := ../../../virt/kvm
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 1c01a9912989..3074475c8ae0 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -132,6 +132,9 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 {
 	int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
 
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
 	trace_kvm_s390_handle_diag(vcpu, code);
 	switch (code) {
 	case 0x10:
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index b7d1b2edeeb3..5ee56e5acc23 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -22,87 +22,6 @@
 #include "trace.h"
 #include "trace-s390.h"
 
-static int handle_lctlg(struct kvm_vcpu *vcpu)
-{
-	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
-	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	u64 useraddr;
-	int reg, rc;
-
-	vcpu->stat.instruction_lctlg++;
-
-	useraddr = kvm_s390_get_base_disp_rsy(vcpu);
-
-	if (useraddr & 7)
-		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-
-	reg = reg1;
-
-	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3,
-		   useraddr);
-	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr);
-
-	do {
-		rc = get_guest(vcpu, vcpu->arch.sie_block->gcr[reg],
-			       (u64 __user *) useraddr);
-		if (rc)
-			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		useraddr += 8;
-		if (reg == reg3)
-			break;
-		reg = (reg + 1) % 16;
-	} while (1);
-	return 0;
-}
-
-static int handle_lctl(struct kvm_vcpu *vcpu)
-{
-	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
-	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	u64 useraddr;
-	u32 val = 0;
-	int reg, rc;
-
-	vcpu->stat.instruction_lctl++;
-
-	useraddr = kvm_s390_get_base_disp_rs(vcpu);
-
-	if (useraddr & 3)
-		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-
-	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3,
-		   useraddr);
-	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr);
-
-	reg = reg1;
-	do {
-		rc = get_guest(vcpu, val, (u32 __user *) useraddr);
-		if (rc)
-			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul;
-		vcpu->arch.sie_block->gcr[reg] |= val;
-		useraddr += 4;
-		if (reg == reg3)
-			break;
-		reg = (reg + 1) % 16;
-	} while (1);
-	return 0;
-}
-
-static const intercept_handler_t eb_handlers[256] = {
-	[0x2f] = handle_lctlg,
-	[0x8a] = kvm_s390_handle_priv_eb,
-};
-
-static int handle_eb(struct kvm_vcpu *vcpu)
-{
-	intercept_handler_t handler;
-
-	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
-	if (handler)
-		return handler(vcpu);
-	return -EOPNOTSUPP;
-}
 
 static const intercept_handler_t instruction_handlers[256] = {
 	[0x01] = kvm_s390_handle_01,
@@ -110,10 +29,10 @@ static const intercept_handler_t instruction_handlers[256] = {
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
-	[0xb7] = handle_lctl,
+	[0xb7] = kvm_s390_handle_lctl,
 	[0xb9] = kvm_s390_handle_b9,
 	[0xe5] = kvm_s390_handle_e5,
-	[0xeb] = handle_eb,
+	[0xeb] = kvm_s390_handle_eb,
 };
 
 static int handle_noop(struct kvm_vcpu *vcpu)
@@ -174,47 +93,12 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 
 static int handle_validity(struct kvm_vcpu *vcpu)
 {
-	unsigned long vmaddr;
 	int viwhy = vcpu->arch.sie_block->ipb >> 16;
-	int rc;
 
 	vcpu->stat.exit_validity++;
 	trace_kvm_s390_intercept_validity(vcpu, viwhy);
-	if (viwhy == 0x37) {
-		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix,
-				    vcpu->arch.gmap);
-		if (IS_ERR_VALUE(vmaddr)) {
-			rc = -EOPNOTSUPP;
-			goto out;
-		}
-		rc = fault_in_pages_writeable((char __user *) vmaddr,
-			 PAGE_SIZE);
-		if (rc) {
-			/* user will receive sigsegv, exit to user */
-			rc = -EOPNOTSUPP;
-			goto out;
-		}
-		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix + PAGE_SIZE,
-				    vcpu->arch.gmap);
-		if (IS_ERR_VALUE(vmaddr)) {
-			rc = -EOPNOTSUPP;
-			goto out;
-		}
-		rc = fault_in_pages_writeable((char __user *) vmaddr,
-			 PAGE_SIZE);
-		if (rc) {
-			/* user will receive sigsegv, exit to user */
-			rc = -EOPNOTSUPP;
-			goto out;
-		}
-	} else
-		rc = -EOPNOTSUPP;
-
-out:
-	if (rc)
-		VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
-			   viwhy);
-	return rc;
+	WARN_ONCE(true, "kvm: unhandled validity intercept 0x%x\n", viwhy);
+	return -EOPNOTSUPP;
 }
 
 static int handle_instruction(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5c948177529e..7f35cb33e510 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -438,7 +438,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 no_timer:
 	spin_lock(&vcpu->arch.local_int.float_int->lock);
 	spin_lock_bh(&vcpu->arch.local_int.lock);
-	add_wait_queue(&vcpu->arch.local_int.wq, &wait);
+	add_wait_queue(&vcpu->wq, &wait);
 	while (list_empty(&vcpu->arch.local_int.list) &&
 		list_empty(&vcpu->arch.local_int.float_int->list) &&
 		(!vcpu->arch.local_int.timer_due) &&
@@ -452,7 +452,7 @@ no_timer:
 	}
 	__unset_cpu_idle(vcpu);
 	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&vcpu->arch.local_int.wq, &wait);
+	remove_wait_queue(&vcpu->wq, &wait);
 	spin_unlock_bh(&vcpu->arch.local_int.lock);
 	spin_unlock(&vcpu->arch.local_int.float_int->lock);
 	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
@@ -465,8 +465,8 @@ void kvm_s390_tasklet(unsigned long parm)
 
 	spin_lock(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.timer_due = 1;
-	if (waitqueue_active(&vcpu->arch.local_int.wq))
-		wake_up_interruptible(&vcpu->arch.local_int.wq);
+	if (waitqueue_active(&vcpu->wq))
+		wake_up_interruptible(&vcpu->wq);
 	spin_unlock(&vcpu->arch.local_int.lock);
 }
 
@@ -613,7 +613,7 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 	spin_lock_bh(&li->lock);
 	list_add(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
-	BUG_ON(waitqueue_active(&li->wq));
+	BUG_ON(waitqueue_active(li->wq));
 	spin_unlock_bh(&li->lock);
 	return 0;
 }
@@ -746,8 +746,8 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	li = fi->local_int[sigcpu];
 	spin_lock_bh(&li->lock);
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(&li->wq))
-		wake_up_interruptible(&li->wq);
+	if (waitqueue_active(li->wq))
+		wake_up_interruptible(li->wq);
 	spin_unlock_bh(&li->lock);
 	spin_unlock(&fi->lock);
 	mutex_unlock(&kvm->lock);
@@ -832,8 +832,8 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 	if (inti->type == KVM_S390_SIGP_STOP)
 		li->action_bits |= ACTION_STOP_ON_STOP;
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(&li->wq))
-		wake_up_interruptible(&vcpu->arch.local_int.wq);
+	if (waitqueue_active(&vcpu->wq))
+		wake_up_interruptible(&vcpu->wq);
 	spin_unlock_bh(&li->lock);
 	mutex_unlock(&vcpu->kvm->lock);
 	return 0;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c1c7c683fa26..ba694d2ba51e 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -59,6 +59,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
 	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
 	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
+	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
 	{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
 	{ "instruction_spx", VCPU_STAT(instruction_spx) },
 	{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
@@ -84,6 +85,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 };
 
 static unsigned long long *facilities;
+static struct gmap_notifier gmap_notifier;
 
 /* Section: not file related */
 int kvm_arch_hardware_enable(void *garbage)
@@ -96,13 +98,18 @@ void kvm_arch_hardware_disable(void *garbage)
 {
 }
 
+static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);
+
 int kvm_arch_hardware_setup(void)
 {
+	gmap_notifier.notifier_call = kvm_gmap_notifier;
+	gmap_register_ipte_notifier(&gmap_notifier);
 	return 0;
 }
 
 void kvm_arch_hardware_unsetup(void)
 {
+	gmap_unregister_ipte_notifier(&gmap_notifier);
 }
 
 void kvm_arch_check_processor_compat(void *rtn)
@@ -239,6 +246,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		kvm->arch.gmap = gmap_alloc(current->mm);
 		if (!kvm->arch.gmap)
 			goto out_nogmap;
+		kvm->arch.gmap->private = kvm;
 	}
 
 	kvm->arch.css_support = 0;
@@ -270,7 +278,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 	free_page((unsigned long)(vcpu->arch.sie_block));
 	kvm_vcpu_uninit(vcpu);
-	kfree(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static void kvm_free_vcpus(struct kvm *kvm)
@@ -309,6 +317,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		vcpu->arch.gmap = gmap_alloc(current->mm);
 		if (!vcpu->arch.gmap)
 			return -ENOMEM;
+		vcpu->arch.gmap->private = vcpu->kvm;
 		return 0;
 	}
 
@@ -373,8 +382,10 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
 						    CPUSTAT_SM |
-						    CPUSTAT_STOPPED);
+						    CPUSTAT_STOPPED |
+						    CPUSTAT_GED);
 	vcpu->arch.sie_block->ecb   = 6;
+	vcpu->arch.sie_block->ecb2  = 8;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	vcpu->arch.sie_block->fac   = (int) (long) facilities;
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
@@ -397,7 +408,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	rc = -ENOMEM;
 
-	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu)
 		goto out;
 
@@ -427,7 +438,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	spin_lock(&kvm->arch.float_int.lock);
 	kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
-	init_waitqueue_head(&vcpu->arch.local_int.wq);
+	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
 	spin_unlock(&kvm->arch.float_int.lock);
 
@@ -442,7 +453,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 out_free_sie_block:
 	free_page((unsigned long)(vcpu->arch.sie_block));
 out_free_cpu:
-	kfree(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
 	return ERR_PTR(rc);
 }
@@ -454,6 +465,50 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+void s390_vcpu_block(struct kvm_vcpu *vcpu)
+{
+	atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+}
+
+void s390_vcpu_unblock(struct kvm_vcpu *vcpu)
+{
+	atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+}
+
+/*
+ * Kick a guest cpu out of SIE and wait until SIE is not running.
+ * If the CPU is not running (e.g. waiting as idle) the function will
+ * return immediately. */
+void exit_sie(struct kvm_vcpu *vcpu)
+{
+	atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
+	while (vcpu-