24 files changed, 291 insertions, 150 deletions

diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 6bb29633e1f1..b65c414b6c0e 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -58,6 +58,9 @@ int main(void)
 	OFFSET(__SF_BACKCHAIN, stack_frame, back_chain);
 	OFFSET(__SF_GPRS, stack_frame, gprs);
 	OFFSET(__SF_EMPTY, stack_frame, empty1);
+	OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]);
+	OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]);
+	OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]);
 	BLANK();
 	/* timeval/timezone offsets for use by vdso */
 	OFFSET(__VDSO_UPD_COUNT, vdso_data, tb_update_count);
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 530226b6cb19..86b3e74f569e 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -277,7 +277,7 @@ debug_info_alloc(const char *name, int pages_per_area, int nr_areas,
 	memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *));
 	memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS *
 		sizeof(struct dentry*));
-	atomic_set(&(rc->ref_count), 0);
+	refcount_set(&(rc->ref_count), 0);
 
 	return rc;
 
@@ -361,7 +361,7 @@ debug_info_create(const char *name, int pages_per_area, int nr_areas,
         debug_area_last = rc;
         rc->next = NULL;
 
-	debug_info_get(rc);
+	refcount_set(&rc->ref_count, 1);
 out:
 	return rc;
 }
@@ -416,7 +416,7 @@ static void
 debug_info_get(debug_info_t * db_info)
 {
 	if (db_info)
-		atomic_inc(&db_info->ref_count);
+		refcount_inc(&db_info->ref_count);
 }
 
 /*
@@ -431,7 +431,7 @@ debug_info_put(debug_info_t *db_info)
 
 	if (!db_info)
 		return;
-	if (atomic_dec_and_test(&db_info->ref_count)) {
+	if (refcount_dec_and_test(&db_info->ref_count)) {
 		for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
 			if (!db_info->views[i])
 				continue;
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index ac6abcd3fe6a..349914571772 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -38,6 +38,7 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = {
 	[DIAG_STAT_X224] = { .code = 0x224, .name = "EBCDIC-Name Table" },
 	[DIAG_STAT_X250] = { .code = 0x250, .name = "Block I/O" },
 	[DIAG_STAT_X258] = { .code = 0x258, .name = "Page-Reference Services" },
+	[DIAG_STAT_X26C] = { .code = 0x26c, .name = "Certain System Information" },
 	[DIAG_STAT_X288] = { .code = 0x288, .name = "Time Bomb" },
 	[DIAG_STAT_X2C4] = { .code = 0x2c4, .name = "FTP Services" },
 	[DIAG_STAT_X2FC] = { .code = 0x2fc, .name = "Guest Performance Data" },
@@ -236,3 +237,31 @@ int diag224(void *ptr)
 	return rc;
 }
 EXPORT_SYMBOL(diag224);
+
+/*
+ * Diagnose 26C: Access Certain System Information
+ */
+static inline int __diag26c(void *req, void *resp, enum diag26c_sc subcode)
+{
+	register unsigned long _req asm("2") = (addr_t) req;
+	register unsigned long _resp asm("3") = (addr_t) resp;
+	register unsigned long _subcode asm("4") = subcode;
+	register unsigned long _rc asm("5") = -EOPNOTSUPP;
+
+	asm volatile(
+		"	sam31\n"
+		"	diag	%[rx],%[ry],0x26c\n"
+		"0:	sam64\n"
+		EX_TABLE(0b,0b)
+		: "+d" (_rc)
+		: [rx] "d" (_req), "d" (_resp), [ry] "d" (_subcode)
+		: "cc", "memory");
+	return _rc;
+}
+
+int diag26c(void *req, void *resp, enum diag26c_sc subcode)
+{
+	diag_stat_inc(DIAG_STAT_X26C);
+	return __diag26c(req, resp, subcode);
+}
+EXPORT_SYMBOL(diag26c);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 829e1c53005c..dab78babfab6 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -98,8 +98,10 @@ static int show_address(void *data, unsigned long address, int reliable)
 	return 0;
 }
 
-static void show_trace(struct task_struct *task, unsigned long sp)
+void show_stack(struct task_struct *task, unsigned long *stack)
 {
+	unsigned long sp = (unsigned long) stack;
+
 	if (!sp)
 		sp = task ? task->thread.ksp : current_stack_pointer();
 	printk("Call Trace:\n");
@@ -109,29 +111,6 @@ static void show_trace(struct task_struct *task, unsigned long sp)
 	debug_show_held_locks(task);
 }
 
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-	unsigned long *stack;
-	int i;
-
-	stack = sp;
-	if (!stack) {
-		if (!task)
-			stack = (unsigned long *)current_stack_pointer();
-		else
-			stack = (unsigned long *)task->thread.ksp;
-	}
-	printk(KERN_DEFAULT "Stack:\n");
-	for (i = 0; i < 20; i++) {
-		if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
-			break;
-		if (i % 4 == 0)
-			printk(KERN_DEFAULT "       ");
-		pr_cont("%016lx%c", *stack++, i % 4 == 3 ? '\n' : ' ');
-	}
-	show_trace(task, (unsigned long)sp);
-}
-
 static void show_last_breaking_event(struct pt_regs *regs)
 {
 	printk("Last Breaking-Event-Address:\n");
@@ -149,8 +128,8 @@ void show_registers(struct pt_regs *regs)
 		pr_cont(" (%pSR)", (void *)regs->psw.addr);
 	pr_cont("\n");
 	printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
-	       "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e,
-	       psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm);
+	       "P:%x AS:%x CC:%x PM:%x", psw->per, psw->dat, psw->io, psw->ext,
+	       psw->key, psw->mcheck, psw->wait, psw->pstate, psw->as, psw->cc, psw->pm);
 	pr_cont(" RI:%x EA:%x\n", psw->ri, psw->eaba);
 	printk("%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
 	       regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
@@ -169,7 +148,7 @@ void show_regs(struct pt_regs *regs)
 	show_registers(regs);
 	/* Show stack backtrace if pt_regs is from kernel mode */
 	if (!user_mode(regs))
-		show_trace(NULL, regs->gprs[15]);
+		show_stack(NULL, (unsigned long *) regs->gprs[15]);
 	show_last_breaking_event(regs);
 }
 
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index a5f5d3bb3dbc..21900e1cee9c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -52,7 +52,7 @@ _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
 _CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \
 		   _CIF_ASCE_SECONDARY | _CIF_FPU)
-_PIF_WORK	= (_PIF_PER_TRAP)
+_PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
 
 #define BASED(name) name-cleanup_critical(%r13)
 
@@ -225,18 +225,24 @@ ENTRY(sie64a)
 	jnz	.Lsie_skip
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	jo	.Lsie_skip			# exit if fp/vx regs changed
+.Lsie_entry:
 	sie	0(%r14)
 .Lsie_skip:
 	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 .Lsie_done:
 # 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 between sie64a and .Lsie_done should not cause program
-# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
+# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
+# Other instructions between sie64a and .Lsie_done should not cause program
+# interrupts. So lets use 3 nops as a landing pad for all possible rewinds.
 # See also .Lcleanup_sie
-.Lrewind_pad:
-	nop	0
+.Lrewind_pad6:
+	nopr	7
+.Lrewind_pad4:
+	nopr	7
+.Lrewind_pad2:
+	nopr	7
 	.globl sie_exit
 sie_exit:
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
@@ -249,7 +255,9 @@ sie_exit:
 	stg	%r14,__SF_EMPTY+16(%r15)	# set exit reason code
 	j	sie_exit
 
-	EX_TABLE(.Lrewind_pad,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad6,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad4,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad2,.Lsie_fault)
 	EX_TABLE(sie_exit,.Lsie_fault)
 EXPORT_SYMBOL(sie64a)
 EXPORT_SYMBOL(sie_exit)
@@ -312,6 +320,7 @@ ENTRY(system_call)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lsysc_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -326,6 +335,8 @@ ENTRY(system_call)
 	jo	.Lsysc_mcck_pending
 	TSTMSK	__TI_flags(%r12),_TIF_NEED_RESCHED
 	jo	.Lsysc_reschedule
+	TSTMSK	__PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
+	jo	.Lsysc_syscall_restart
 #ifdef CONFIG_UPROBES
 	TSTMSK	__TI_flags(%r12),_TIF_UPROBE
 	jo	.Lsysc_uprobe_notify
@@ -339,6 +350,8 @@ ENTRY(system_call)
 	jo	.Lsysc_patch_pending	# handle live patching just before
 					# signals and possible syscall restart
 #endif
+	TSTMSK	__PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
+	jo	.Lsysc_syscall_restart
 	TSTMSK	__TI_flags(%r12),_TIF_SIGPENDING
 	jo	.Lsysc_sigpending
 	TSTMSK	__TI_flags(%r12),_TIF_NOTIFY_RESUME
@@ -440,6 +453,15 @@ ENTRY(system_call)
 	jg	do_per_trap
 
 #
+# _PIF_SYSCALL_RESTART is set, repeat the current system call
+#
+.Lsysc_syscall_restart:
+	ni	__PT_FLAGS+7(%r11),255-_PIF_SYSCALL_RESTART
+	lmg	%r1,%r7,__PT_R1(%r11)	# load svc arguments
+	lg	%r2,__PT_ORIG_GPR2(%r11)
+	j	.Lsysc_do_svc
+
+#
 # call tracehook_report_syscall_entry/tracehook_report_syscall_exit before
 # and after the system call
 #
@@ -623,6 +645,7 @@ ENTRY(io_int_handler)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lio_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -872,9 +895,7 @@ ENTRY(save_fpu_regs)
 	oi	__LC_CPU_FLAGS+7,_CIF_FPU
 	br	%r14
 .Lsave_fpu_regs_end:
-#if IS_ENABLED(CONFIG_KVM)
 EXPORT_SYMBOL(save_fpu_regs)
-#endif
 
 /*
  * Load floating-point controls and floating-point or vector registers.
@@ -1102,7 +1123,13 @@ cleanup_critical:
 	.quad	.Lsie_done
 
 .Lcleanup_sie:
-	lg	%r9,__SF_EMPTY(%r15)		# get control block pointer
+	cghi    %r11,__LC_SAVE_AREA_ASYNC 	#Is this in normal interrupt?
+	je      1f
+	slg     %r9,BASED(.Lsie_crit_mcck_start)
+	clg     %r9,BASED(.Lsie_crit_mcck_length)
+	jh      1f
+	oi      __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST
+1:	lg	%r9,__SF_EMPTY(%r15)		# get control block pointer
 	ni	__SIE_PROG0C+3(%r9),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	larl	%r9,sie_exit			# skip forward to sie_exit
@@ -1174,15 +1201,23 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_sysc_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_sysc_restore_insn)
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
 	je	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_sysc_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_sysc_restore_insn:
+	.quad	.Lsysc_exit_timer
 	.quad	.Lsysc_done - 4
 
 .Lcleanup_io_tif:
@@ -1190,15 +1225,20 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_io_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_io_restore_insn)
-	je	0f
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_io_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_io_restore_insn:
+	.quad	.Lio_exit_timer
 	.quad	.Lio_done - 4
 
 .Lcleanup_idle:
@@ -1274,6 +1314,10 @@ cleanup_critical:
 	.quad	.Lsie_gmap
 .Lsie_critical_length:
 	.quad	.Lsie_done - .Lsie_gmap
+.Lsie_crit_mcck_start:
+	.quad   .Lsie_entry
+.Lsie_crit_mcck_length:
+	.quad   .Lsie_skip - .Lsie_entry
 #endif
 
 	.section .rodata, "a"
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 27477f34cc0a..d03a6d12c4bd 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -173,6 +173,8 @@ int __init ftrace_dyn_arch_init(void)
 	return 0;
 }
 
+#ifdef CONFIG_MODULES
+
 static int __init ftrace_plt_init(void)
 {
 	unsigned int *ip;
@@ -191,6 +193,8 @@ static int __init ftrace_plt_init(void)
 }
 device_initcall(ftrace_plt_init);
 
+#endif /* CONFIG_MODULES */
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * Hook the return address and push it in the stack of return addresses
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index e545ffe5155a..8e622bb52f7a 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -564,8 +564,6 @@ static struct kset *ipl_kset;
 
 static void __ipl_run(void *unused)
 {
-	if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW)
-		diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
 	diag308(DIAG308_LOAD_CLEAR, NULL);
 	if (MACHINE_IS_VM)
 		__cpcmd("IPL", NULL, 0, NULL);
@@ -1088,10 +1086,7 @@ static void __reipl_run(void *unused)
 		break;
 	case REIPL_METHOD_CCW_DIAG:
 		diag308(DIAG308_SET, reipl_block_ccw);
-		if (MACHINE_IS_LPAR)
-			diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
-		else
-			diag308(DIAG308_LOAD_CLEAR, NULL);
+		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case REIPL_METHOD_FCP_RW_DIAG:
 		diag308(DIAG308_SET, reipl_block_fcp);
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index 6aa630a8d24f..262506cee4c3 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -93,7 +93,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	args.entry = entry;
 	args.type = type;
 
-	stop_machine(__sm_arch_jump_label_transform, &args, NULL);
+	stop_machine_cpuslocked(__sm_arch_jump_label_transform, &args, NULL);
 }
 
 void arch_jump_label_transform_static(struct jump_entry *entry,
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3d6a99746454..6842e4501e2e 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -196,7 +196,7 @@ void arch_arm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_arm_kprobe);
 
@@ -204,7 +204,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_disarm_kprobe);
 
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 49a6bd45957b..3d0b14afa232 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 985589523970..31d03a84126c 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -25,6 +25,8 @@
 #include <asm/crw.h>
 #include <asm/switch_to.h>
 #include <asm/ctl_reg.h>
+#include <asm/asm-offsets.h>
+#include <linux/kvm_host.h>
 
 struct mcck_struct {
 	unsigned int kill_task : 1;
@@ -274,12 +276,39 @@ static int notrace s390_validate_registers(union mci mci, int umode)
 	return kill_task;
 }
 
+/*
+ * Backup the guest's machine check info to its description block
+ */
+static void notrace s390_backup_mcck_info(struct pt_regs *regs)
+{
+	struct mcck_volatile_info *mcck_backup;
+	struct sie_page *sie_page;
+
+	/* r14 contains the sie block, which was set in sie64a */
+	struct kvm_s390_sie_block *sie_block =
+			(struct kvm_s390_sie_block *) regs->gprs[14];
+
+	if (sie_block == NULL)
+		/* Something's seriously wrong, stop system. */
+		s390_handle_damage();
+
+	sie_page = container_of(sie_block, struct sie_page, sie_block);
+	mcck_backup = &sie_page->mcck_info;
+	mcck_backup->mcic = S390_lowcore.mcck_interruption_code &
+				~(MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE);
+	mcck_backup->ext_damage_code = S390_lowcore.external_damage_code;
+	mcck_backup->failing_storage_address
+			= S390_lowcore.failing_storage_address;
+}
+
 #define MAX_IPD_COUNT	29
 #define MAX_IPD_TIME	(5 * 60 * USEC_PER_SEC) /* 5 minutes */
 
 #define ED_STP_ISLAND	6	/* External damage STP island check */
 #define ED_STP_SYNC	7	/* External damage STP sync check */
 
+#define MCCK_CODE_NO_GUEST	(MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE)
+
 /*
  * machine check handler.
  */
@@ -291,6 +320,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	struct mcck_struct *mcck;
 	unsigned long long tmp;
 	union mci mci;
+	unsigned long mcck_dam_code;
 
 	nmi_enter();
 	inc_irq_stat(NMI_NMI);
@@ -301,7 +331,13 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 		/* System damage -> stopping machine */
 		s390_handle_damage();
 	}
-	if (mci.pd) {
+
+	/*
+	 * Reinject the instruction processing damages' machine checks
+	 * including Delayed Access Exception into the guest
+	 * instead of damaging the host if they happen in the guest.
+	 */
+	if (mci.pd && !test_cpu_flag(CIF_MCCK_GUEST)) {
 		if (mci.b) {
 			/* Processing backup -> verify if we can survive this */
 			u64 z_mcic, o_mcic, t_mcic;
@@ -345,6 +381,14 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 		mcck->mcck_code = mci.val;
 		set_cpu_flag(CIF_MCCK_PENDING);
 	}
+
+	/*
+	 * Backup the machine check's info if it happens when the guest
+	 * is running.
+	 */
+	if (test_cpu_flag(CIF_MCCK_GUEST))
+		s390_backup_mcck_info(regs);
+
 	if (mci.cd) {
 		/* Timing facility damage */
 		s390_handle_damage();
@@ -358,15 +402,22 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 		if (mcck->stp_queue)
 			set_cpu_flag(CIF_MCCK_PENDING);
 	}
-	if (mci.se)
-		/* Storage error uncorrected */
-		s390_handle_damage();
-	if (mci.ke)
-		/* Storage key-error uncorrected */
-		s390_handle_damage();
-	if (mci.ds && mci.fa)
-		/* Storage degradation */
-		s390_handle_damage();
+
+	/*
+	 * Reinject storage related machine checks into the guest if they
+	 * happen when the guest is running.
+	 */
+	if (!test_cpu_flag(CIF_MCCK_GUEST)) {
+		if (mci.se)
+			/* Storage error uncorrected */
+			s390_handle_damage();
+		if (mci.ke)
+			/* Storage key-error uncorrected */
+			s390_handle_damage();
+		if (mci.ds && mci.fa)
+			/* Storage degradation */
+			s390_handle_damage();
+	}
 	if (mci.cp) {
 		/* Channel report word pending */
 		mcck->channel_report = 1;
@@ -377,6 +428,19 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 		mcck->warning = 1;
 		set_cpu_flag(CIF_MCCK_PENDING);
 	}
+
+	/*
+	 * If there are only Channel Report Pending and External Damage
+	 * machine checks, they will not be reinjected into the guest
+	 * because they refer to host conditions only.
+	 */
+	mcck_dam_code = (mci.val & MCIC_SUBCLASS_MASK);
+	if (test_cpu_flag(CIF_MCCK_GUEST) &&
+	(mcck_dam_code & MCCK_CODE_NO_GUEST) != mcck_dam_code) {
+		/* Set exit reason code for host's later handling */
+		*((long *)(regs->gprs[15] + __SF_SIE_REASON)) = -EINTR;
+	}
+	clear_cpu_flag(CIF_MCCK_GUEST);
 	nmi_exit();
 }
 
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ca960d0370d5..0c82f7903fc7 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -995,11 +995,11 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 	regs.int_parm = CPU_MF_INT_SF_PRA;
 	sde_regs = (struct perf_sf_sde_regs *) &regs.int_parm_long;
 
-	psw_bits(regs.psw).ia = sfr->basic.ia;
-	psw_bits(regs.psw).t  = sfr->basic.T;
-	psw_bits(regs.psw).w  = sfr->basic.W;
-	psw_bits(regs.psw).p  = sfr->basic.P;
-	psw_bits(regs.psw).as = sfr->basic.AS;
+	psw_bits(regs.psw).ia	= sfr->basic.ia;
+	psw_bits(regs.psw).dat	= sfr->basic.T;
+	psw_bits(regs.psw).wait = sfr->basic.W;
+	psw_bits(regs.psw).per	= sfr->basic.P;
+	psw_bits(regs.psw).as	= sfr->basic.AS;
 
 	/*
 	 * Use the hardware provided configuration level to decide if the
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 955a7b6fa0a4..93a386f4a3b5 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -245,6 +245,5 @@ ssize_t cpumf_events_sysfs_show(struct device *dev,
 	struct perf_pmu_events_attr *pmu_attr;
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
-	return sprintf(page, "event=0x%04llx,name=%s\n",
-		       pmu_attr->id, attr->attr.name);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
 }
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 999d7154bbdc..bb32b8618bf6 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -41,31 +41,6 @@
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
 
-/*
- * Return saved PC of a blocked thread. used in kernel/sched.
- * resume in entry.S does not create a new stack frame, it
- * just stores the registers %r6-%r15 to the frame given by
- * schedule. We want to return the address of the caller of
- * schedule, so we have to walk the backchain one time to
- * find the frame schedule() store its return address.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	struct stack_frame *sf, *low, *high;
-
-	if (!tsk || !task_stack_page(tsk))
-		return 0;
-	low = task_stack_page(tsk);
-	high = (struct stack_frame *) task_pt_regs(tsk);
-	sf = (struct stack_frame *) tsk->thread.ksp;
-	if (sf <= low || sf > high)
-		return 0;
-	sf = (struct stack_frame *) sf->back_chain;
-	if (sf <= low || sf > high)
-		return 0;
-	return sf->gprs[8];
-}
-
 extern void kernel_thread_starter(void);
 
 /*
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 488c5bb8dc77..252ed61a128b 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -1160,6 +1160,8 @@ static int s390_gs_cb_get(struct task_struct *target,
 		return -ENODEV;
 	if (!data)
 		return -ENODATA;
+	if (target == current)
+		save_gs_cb(data);
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   data, 0, sizeof(struct gs_cb));
 }
@@ -1170,6 +1172,7 @@ static int s390_gs_cb_set(struct task_struct *target,
 			  const void *kbuf, const void __user *ubuf)
 {
 	struct gs_cb *data = target->thread.gs_cb;
+	int rc;
 
 	if (!MACHINE_HAS_GS)
 		return -ENODEV;
@@ -1177,10 +1180,18 @@ static int s390_gs_cb_set(struct task_struct *target,
 		data = kzalloc(sizeof(*data), GFP_KERNEL);
 		if (!data)
 			return -ENOMEM;
+		data->gsd = 25;
 		target->thread.gs_cb = data;
+		if (target == current)
+			__ctl_set_bit(2, 4);
+	} else if (target == current) {
+		save_gs_cb(data);
 	}
-	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				  data, 0, sizeof(struct gs_cb));
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				data, 0, sizeof(struct gs_cb));
+	if (target == current)
+		restore_gs_cb(data);
+	return rc;
 }
 
 static int s390_gs_bc_get(struct task_struct *target,
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 3ae756c0db3d..3d1d808ea8a9 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
 	pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
 }
 
-static void __init setup_vmcoreinfo(void)
-{
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
 #ifdef CONFIG_CRASH_DUMP
 
 /*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 363000a77ffc..1020a11a24e5 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -26,6 +26,7 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/kernel_stat.h>
+#include <linux/kmemleak.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/irqflags.h>
@@ -207,6 +208,8 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 				kmem_cache_alloc(pcpu_mcesa_cache, GFP_KERNEL);
 			if (!mcesa_origin)
 				goto out;
+			/* The pointer is stored with mcesa_bits ORed in */
+			kmemleak_not_leak((void *) mcesa_origin);
 			mcesa_bits = MACHINE_HAS_GS ? 11 : 0;
 		}
 	} else {
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index eefcb54872a5..fb869b103825 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -242,7 +242,7 @@ static void print_ext_name(struct seq_file *m, int lvl,
 
 static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info)
 {
-	if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be)))
+	if (uuid_is_null(&info->vm[i].uuid))
 		return;
 	seq_printf(m, "VM%02d UUID:            %pUb\n", i, &info->vm[i].uuid);
 }
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index c3a52f9a69a0..192efdfac918 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -636,10 +636,10 @@ static void stp_work_fn(struct work_struct *work)
 		goto out_unlock;
 
 	memset(&stp_sync, 0, sizeof(stp_sync));
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
-	stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask);
-	put_online_cpus();
+	stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask);
+	cpus_read_unlock();
 
 	if (!check_sync_clock())
 		/*
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index f787b9d8f54c..442e5423ce3d 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -21,6 +21,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/cpu.h>
 #include <asm/fpu/api.h>
 #include "entry.h"
 
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index 314e0ee3016a..d94baa8db507 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -27,12 +27,12 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
 
 int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
-	if (psw_bits(regs->psw).eaba == PSW_AMODE_24BIT)
+	if (psw_bits(regs->psw).eaba == PSW_BITS_AMODE_24BIT)
 		return -EINVAL;
-	if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_AMODE_31BIT)
+	if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_BITS_AMODE_31BIT)
 		return -EINVAL;
 	clear_pt_regs_flag(regs, PIF_PER_TRAP);
-	auprobe->saved_per = psw_bits(regs->psw).r;
+	auprobe->saved_per = psw_bits(regs->psw).per;
 	auprobe->saved_int_code = regs->int_code;
 	regs->int_code = UPROBE_TRAP_NR;
 	regs->psw.addr = current->utask->xol_vaddr;
@@ -81,7 +81,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	clear_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
 	update_cr_regs(current);
-	psw_bits(regs->psw).r = auprobe->saved_per;
+	psw_bits(regs->psw).per = auprobe->saved_per;
 	regs->int_code = auprobe->saved_int_code;
 
 	if (fixup & FIXUP_PSW_NORMAL)
@@ -372,8 +372,8 @@ static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
-	if ((psw_bits(regs->psw).eaba == PSW_AMODE_24BIT) ||
-	    ((psw_bits(regs->psw).eaba == PSW_AMODE_31BIT) &&
+	if ((psw_bits(regs->psw).eaba == PSW_BITS_AMODE_24BIT) ||
+	    ((psw_bits(regs->psw).eaba == PSW_BITS_AMODE_31BIT) &&
 	     !is_compat_task())) {
 		regs->psw.addr = __rewind_psw(regs->psw, UPROBE_SWBP_INSN_SIZE);
 		do_report_trap(regs, SIGILL, ILL_ILLADR, NULL);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 10516ae3b55e..b89d19f6f2ab 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -50,6 +50,56 @@ static struct page **vdso64_pagelist;
  */
 unsigned int __read_mostly vdso_enabled = 1;
 
+static int vdso_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page **vdso_pagelist;
+	unsigned long vdso_pages;
+
+	vdso_pagelist = vdso64_pagelist;
+	vdso_pages = vdso64_pages;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		vdso_pagelist = vdso32_pagelist;
+		vdso_pages = vdso32_pages;
+	}
+#endif
+
+	if (vmf->pgoff >= vdso_pages)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = vdso_pagelist[vmf->pgoff];
+	get_page(vmf->page);
+	return 0;
+}
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+		       struct vm_area_struct *vma)
+{
+	unsigned long vdso_pages;
+
+	vdso_pages = vdso64_pages;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task())
+		vdso_pages = vdso32_pages;
+#endif
+
+	if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start)
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(current->mm != vma->vm_mm))
+		return -EFAULT;
+
+	current->mm->context.vdso_base = vma->vm_start;
+	return 0;
+}
+
+static const struct vm_special_mapping vdso_mapping = {
+	.name = "[vdso]",
+	.fault = vdso_fault,
+	.mremap = vdso_mremap,
+};
+
 static int __init vdso_setup(char *s)
 {
 	unsigned long val;
@@ -181,7 +231,7 @@ static void vdso_init_cr5(void)
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
-	struct page **vdso_pagelist;
+	struct vm_area_struct *vma;
 	unsigned long vdso_pages;
 	unsigned long vdso_base;
 	int rc;
@@ -194,13 +244,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (!uses_interp)
 		return 0;
 
-	vdso_pagelist = vdso64_pagelist;
 	vdso_pages = vdso64_pages;
 #ifdef CONFIG_COMPAT
-	if (is_compat_task()) {
-		vdso_pagelist = vdso32_pagelist;
+	if (is_compat_task())
 		vdso_pages = vdso32_pages;
-	}
 #endif
 	/*
 	 * vDSO has a problem and was disabled, just don't "enable" it for
@@ -209,8 +256,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (vdso_pages == 0)
 		return 0;
 
-	current->mm->context.vdso_base = 0;
-
 	/*
 	 * pick a base address for the vDSO in process space. We try to put
 	 * it at vdso_base which is the "natural" base for it, but we might
@@ -225,13 +270,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	}
 
 	/*
-	 * Put vDSO base into mm struct. We need to do this before calling
-	 * install_special_mapping or the perf counter mmap tracking code
-	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
-	 */
-	current->mm->context.vdso_base = vdso_base;
-
-	/*
 	 * our vma flags don't have VM_WRITE so by default, the process
 	 * isn't allowed to write those pages.
 	 * gdb can break that with ptrace interface, and thus trigger COW
@@ -241,24 +279,23 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	 * It's fine to use that for setting breakpoints in the vDSO code
 	 * pages though.
 	 */
-	rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
-				     VM_READ|VM_EXEC|
-				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				     vdso_pagelist);
-	if (rc)
-		current->mm->context.vdso_base = 0;
+	vma = _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+				       VM_READ|VM_EXEC|
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       &vdso_mapping);
+	if (IS_ERR(vma)) {
+		rc = PTR_ERR(vma);
+		goto out_up;
+	}
+
+	current->mm->context.vdso_base = vdso_base;
+	rc = 0;
+
 out_up:
 	up_write(&mm->mmap_sem);
 	return rc;
 }
 
-const char *arch_vma_name(struct vm_area_struct *vma)
-{
-	if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base)
-		return "[vdso]";
-	return NULL;
-}
-
 static int __init vdso_init(void)
 {
 	int i;
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 72307f108c40..6e2c42bd1c3b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -31,8 +31,14 @@ SECTIONS
 {
 	. = 0x00000000;
 	.text : {
-	_text = .;		/* Text and read-only data */
+		/* Text and read-only data */
 		HEAD_TEXT
+		/*
+		 * E.g. perf doesn't like symbols starting at address zero,
+		 * therefore skip the initial PSW and channel program located
+		 * at address zero and let _text start at 0x200.
+		 */
+	_text = 0x200;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 072d84ba42a3..dd7178fbb4f3 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -110,11 +110,10 @@ static inline u64 scale_vtime(u64 vtime)
 	return vtime;
 }
 
-static void account_system_index_scaled(struct task_struct *p,
-					u64 cputime, u64 scaled,
+static void account_system_index_scaled(struct task_struct *p, u64 cputime,
 					enum cpu_usage_stat index)
 {
-	p->stimescaled += cputime_to_nsecs(scaled);
+	p->stimescaled += cputime_to_nsecs(scale_vtime(cputime));
 	account_system_index_time(p, cputime_to_nsecs(cputime), index);
 }
 
@@ -176,14 +175,11 @@ static int do_account_vtime(struct task_struct *tsk)
 	}
 
 	if (system)
-		account_system_index_scaled(tsk, system, scale_vtime(system),
-					    CPUTIME_SYSTEM);
+		account_system_index_scaled(tsk, system, CPUTIME_SYSTEM);
 	if (hardirq)
-		account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq),
-					    CPUTIME_IRQ);
+		account_system_index_scaled(tsk, hardirq, CPUTIME_IRQ);
 	if (softirq)
-		account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
-					    CPUTIME_SOFTIRQ);
+		account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);
 
 	steal = S390_lowcore.steal_timer;
 	if ((s64) steal > 0) {