Merge tag 's390-7.0-3' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 fixes from Vasily Gorbik:

 - Fix guest pfault init to pass a physical address to DIAG 0x258,
   restoring pfault interrupts and avoiding vCPU stalls during host
   page-in

 - Fix kexec/kdump hangs with stack protector by marking
   s390_reset_system() __no_stack_protector; set_prefix(0) switches
   lowcore and the canary no longer matches

 - Fix idle/vtime cputime accounting (idle-exit ordering, vtimer
   double-forwarding) and small cleanups

* tag 's390-7.0-3' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/pfault: Fix virtual vs physical address confusion
  s390/kexec: Disable stack protector in s390_reset_system()
  s390/idle: Remove psw_idle() prototype
  s390/vtime: Use lockdep_assert_irqs_disabled() instead of BUG_ON()
  s390/vtime: Use __this_cpu_read() / get rid of READ_ONCE()
  s390/irq/idle: Remove psw bits early
  s390/idle: Inline update_timer_idle()
  s390/idle: Slightly optimize idle time accounting
  s390/idle: Add comment for non obvious code
  s390/vtime: Fix virtual timer forwarding
  s390/idle: Fix cpu idle exit cpu time accounting

arch/s390/include/asm/idle.h

@@ -19,9 +19,9 @@ struct s390_idle_data {
 	unsigned long mt_cycles_enter[8];
 };
 
+DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
+
 extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
-void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
-
 #endif /* _S390_IDLE_H */

arch/s390/include/asm/vtime.h

@@ -2,6 +2,12 @@
 #ifndef _S390_VTIME_H
 #define _S390_VTIME_H
 
+#include <asm/lowcore.h>
+#include <asm/cpu_mf.h>
+#include <asm/idle.h>
+
+DECLARE_PER_CPU(u64, mt_cycles[8]);
+
 static inline void update_timer_sys(void)
 {
 	struct lowcore *lc = get_lowcore();
@@ -20,4 +26,32 @@ static inline void update_timer_mcck(void)
 	lc->last_update_timer = lc->mcck_enter_timer;
 }
 
+static inline void update_timer_idle(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	struct lowcore *lc = get_lowcore();
+	u64 cycles_new[8];
+	int i, mtid;
+
+	mtid = smp_cpu_mtid;
+	if (mtid) {
+		stcctm(MT_DIAG, mtid, cycles_new);
+		for (i = 0; i < mtid; i++)
+			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
+	}
+	/*
+	 * This is a bit subtle: Forward last_update_clock so it excludes idle
+	 * time. For correct steal time calculation in do_account_vtime() add
+	 * passed wall time before idle_enter to steal_timer:
+	 * During the passed wall time before idle_enter CPU time may have
+	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
+	 * The accounted CPU times will be subtracted again from steal_timer
+	 * when accumulated steal time is calculated in do_account_vtime().
+	 */
+	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
+	lc->last_update_clock = lc->int_clock;
+	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
+	lc->last_update_timer = lc->sys_enter_timer;
+}
+
 #endif /* _S390_VTIME_H */

arch/s390/kernel/entry.h

@@ -56,8 +56,6 @@ long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t);
 long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user *return_code, unsigned long flags);
 
-DECLARE_PER_CPU(u64, mt_cycles[8]);
-
 unsigned long stack_alloc(void);
 void stack_free(unsigned long stack);
 

arch/s390/kernel/idle.c

@@ -15,37 +15,22 @@
 #include <trace/events/power.h>
 #include <asm/cpu_mf.h>
 #include <asm/cputime.h>
+#include <asm/idle.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
-#include "entry.h"
 
-static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
+DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
 
 void account_idle_time_irq(void)
 {
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
-	struct lowcore *lc = get_lowcore();
 	unsigned long idle_time;
-	u64 cycles_new[8];
-	int i;
 
-	if (smp_cpu_mtid) {
-		stcctm(MT_DIAG, smp_cpu_mtid, cycles_new);
-		for (i = 0; i < smp_cpu_mtid; i++)
-			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
-	}
-
-	idle_time = lc->int_clock - idle->clock_idle_enter;
-
-	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
-	lc->last_update_clock = lc->int_clock;
-
-	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
-	lc->last_update_timer = lc->sys_enter_timer;
+	idle_time = get_lowcore()->int_clock - idle->clock_idle_enter;
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
-	WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time);
-	WRITE_ONCE(idle->idle_count, READ_ONCE(idle->idle_count) + 1);
+	__atomic64_add(idle_time, &idle->idle_time);
+	__atomic64_add_const(1, &idle->idle_count);
 	account_idle_time(cputime_to_nsecs(idle_time));
 }
 

arch/s390/kernel/ipl.c

@@ -2377,7 +2377,7 @@ void __init setup_ipl(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
 }
 
-void s390_reset_system(void)
+void __no_stack_protector s390_reset_system(void)
 {
 	/* Disable prefixing */
 	set_prefix(0);

arch/s390/kernel/irq.c

@@ -146,6 +146,12 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle) {
+		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -154,7 +160,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 			current->thread.last_break = regs->last_break;
 	}
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 
@@ -171,9 +176,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 void noinstr do_ext_irq(struct pt_regs *regs)
@@ -182,6 +184,12 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle) {
+		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -194,7 +202,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	regs->int_parm = get_lowcore()->ext_params;
 	regs->int_parm_long = get_lowcore()->ext_params2;
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 
@@ -203,9 +210,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	irq_exit_rcu();
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 static void show_msi_interrupt(struct seq_file *p, int irq)

arch/s390/kernel/vtime.c

@@ -48,8 +48,7 @@ static inline void set_vtimer(u64 expires)
 
 static inline int virt_timer_forward(u64 elapsed)
 {
-	BUG_ON(!irqs_disabled());
-
+	lockdep_assert_irqs_disabled();
 	if (list_empty(&virt_timer_list))
 		return 0;
 	elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed);
@@ -137,23 +136,16 @@ static int do_account_vtime(struct task_struct *tsk)
 		lc->system_timer += timer;
 
 	/* Update MT utilization calculation */
-	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+	if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
 	/* Calculate cputime delta */
-	user = update_tsk_timer(&tsk->thread.user_timer,
-				READ_ONCE(lc->user_timer));
-	guest = update_tsk_timer(&tsk->thread.guest_timer,
-				 READ_ONCE(lc->guest_timer));
-	system = update_tsk_timer(&tsk->thread.system_timer,
-				  READ_ONCE(lc->system_timer));
-	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
-				   READ_ONCE(lc->hardirq_timer));
-	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
-				   READ_ONCE(lc->softirq_timer));
-	lc->steal_timer +=
-		clock - user - guest - system - hardirq - softirq;
+	user = update_tsk_timer(&tsk->thread.user_timer, lc->user_timer);
+	guest = update_tsk_timer(&tsk->thread.guest_timer, lc->guest_timer);
+	system = update_tsk_timer(&tsk->thread.system_timer, lc->system_timer);
+	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, lc->hardirq_timer);
+	softirq = update_tsk_timer(&tsk->thread.softirq_timer, lc->softirq_timer);
+	lc->steal_timer += clock - user - guest - system - hardirq - softirq;
 
 	/* Push account value */
 	if (user) {
@@ -225,10 +217,6 @@ static u64 vtime_delta(void)
 	return timer - lc->last_update_timer;
 }
 
-/*
- * Update process times based on virtual cpu times stored by entry.S
- * to the lowcore fields user_timer, system_timer & steal_clock.
- */
 void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct lowcore *lc = get_lowcore();
@@ -238,27 +226,17 @@ void vtime_account_kernel(struct task_struct *tsk)
 		lc->guest_timer += delta;
 	else
 		lc->system_timer += delta;
-
-	virt_timer_forward(delta);
 }
 EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_softirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->softirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->softirq_timer += vtime_delta();
 }
 
 void vtime_account_hardirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->hardirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->hardirq_timer += vtime_delta();
 }
 
 /*

arch/s390/mm/pfault.c

@@ -62,7 +62,7 @@ int __pfault_init(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		: [rc] "+d" (rc)
-		: [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_init_refbk)), "m" (pfault_init_refbk)
 		: "cc");
 	return rc;
 }
@@ -84,7 +84,7 @@ void __pfault_fini(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		:
-		: [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_fini_refbk)), "m" (pfault_fini_refbk)
 		: "cc");
 }