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
  ...

4 files changed, 95 insertions, 42 deletions

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);