Merge tag 's390-5.1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 fixes from Martin Schwidefsky:
 "Improvements and bug fixes for 5.1-rc2:

   - Fix early free of the channel program in vfio

   - On AP device removal make sure that all messages are flushed with
     the driver still attached that queued the message

   - Limit brk randomization to 32MB to reduce the chance that the heap
     of ld.so is placed after the main stack

   - Add a rolling average for the steal time of a CPU, this will be
     needed for KVM to decide when to do busy waiting

   - Fix a warning in the CPU-MF code

   - Add a notification handler for AP configuration change to react
     faster to new AP devices"

* tag 's390-5.1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/cpumf: Fix warning from check_processor_id
  zcrypt: handle AP Info notification from CHSC SEI command
  vfio: ccw: only free cp on final interrupt
  s390/vtime: steal time exponential moving average
  s390/zcrypt: revisit ap device remove procedure
  s390: limit brk randomization to 32MB

6 files changed, 76 insertions, 48 deletions

diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index 1a6a7092d942..e94a0a28b5eb 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -360,4 +360,15 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
 	return reg1;
 }
 
+/*
+ * Interface to tell the AP bus code that a configuration
+ * change has happened. The bus code should at least do
+ * an ap bus resource rescan.
+ */
+#if IS_ENABLED(CONFIG_ZCRYPT)
+void ap_bus_cfg_chg(void);
+#else
+static inline void ap_bus_cfg_chg(void){};
+#endif
+
 #endif /* _ASM_S390_AP_H_ */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 7d22a474a040..f74639a05f0f 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -252,11 +252,14 @@ do {								\
 
 /*
  * Cache aliasing on the latest machines calls for a mapping granularity
- * of 512KB. For 64-bit processes use a 512KB alignment and a randomization
- * of up to 1GB. For 31-bit processes the virtual address space is limited,
- * use no alignment and limit the randomization to 8MB.
+ * of 512KB for the anonymous mapping base. For 64-bit processes use a
+ * 512KB alignment and a randomization of up to 1GB. For 31-bit processes
+ * the virtual address space is limited, use no alignment and limit the
+ * randomization to 8MB.
+ * For the additional randomization of the program break use 32MB for
+ * 64-bit and 8MB for 31-bit.
  */
-#define BRK_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ffffUL)
+#define BRK_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x1fffUL)
 #define MMAP_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ff80UL)
 #define MMAP_ALIGN_MASK	(is_compat_task() ? 0 : 0x7fUL)
 #define STACK_RND_MASK	MMAP_RND_MASK
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index cc0947e08b6f..5b9f10b1e55d 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -91,52 +91,53 @@ struct lowcore {
 	__u64	hardirq_timer;			/* 0x02e8 */
 	__u64	softirq_timer;			/* 0x02f0 */
 	__u64	steal_timer;			/* 0x02f8 */
-	__u64	last_update_timer;		/* 0x0300 */
-	__u64	last_update_clock;		/* 0x0308 */
-	__u64	int_clock;			/* 0x0310 */
-	__u64	mcck_clock;			/* 0x0318 */
-	__u64	clock_comparator;		/* 0x0320 */
-	__u64	boot_clock[2];			/* 0x0328 */
+	__u64	avg_steal_timer;		/* 0x0300 */
+	__u64	last_update_timer;		/* 0x0308 */
+	__u64	last_update_clock;		/* 0x0310 */
+	__u64	int_clock;			/* 0x0318*/
+	__u64	mcck_clock;			/* 0x0320 */
+	__u64	clock_comparator;		/* 0x0328 */
+	__u64	boot_clock[2];			/* 0x0330 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x0338 */
-	__u64	kernel_stack;			/* 0x0340 */
+	__u64	current_task;			/* 0x0340 */
+	__u64	kernel_stack;			/* 0x0348 */
 
 	/* Interrupt, DAT-off and restartstack. */
-	__u64	async_stack;			/* 0x0348 */
-	__u64	nodat_stack;			/* 0x0350 */
-	__u64	restart_stack;			/* 0x0358 */
+	__u64	async_stack;			/* 0x0350 */
+	__u64	nodat_stack;			/* 0x0358 */
+	__u64	restart_stack;			/* 0x0360 */
 
 	/* Restart function and parameter. */
-	__u64	restart_fn;			/* 0x0360 */
-	__u64	restart_data;			/* 0x0368 */
-	__u64	restart_source;			/* 0x0370 */
+	__u64	restart_fn;			/* 0x0368 */
+	__u64	restart_data;			/* 0x0370 */
+	__u64	restart_source;			/* 0x0378 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0378 */
-	__u64	user_asce;			/* 0x0380 */
-	__u64	vdso_asce;			/* 0x0388 */
+	__u64	kernel_asce;			/* 0x0380 */
+	__u64	user_asce;			/* 0x0388 */
+	__u64	vdso_asce;			/* 0x0390 */
 
 	/*
 	 * The lpp and current_pid fields form a
 	 * 64-bit value that is set as program
 	 * parameter with the LPP instruction.
 	 */
-	__u32	lpp;				/* 0x0390 */
-	__u32	current_pid;			/* 0x0394 */
+	__u32	lpp;				/* 0x0398 */
+	__u32	current_pid;			/* 0x039c */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0398 */
-	__u32	softirq_pending;		/* 0x039c */
-	__u32	preempt_count;			/* 0x03a0 */
-	__u32	spinlock_lockval;		/* 0x03a4 */
-	__u32	spinlock_index;			/* 0x03a8 */
-	__u32	fpu_flags;			/* 0x03ac */
-	__u64	percpu_offset;			/* 0x03b0 */
-	__u64	vdso_per_cpu_data;		/* 0x03b8 */
-	__u64	machine_flags;			/* 0x03c0 */
-	__u64	gmap;				/* 0x03c8 */
-	__u8	pad_0x03d0[0x0400-0x03d0];	/* 0x03d0 */
+	__u32	cpu_nr;				/* 0x03a0 */
+	__u32	softirq_pending;		/* 0x03a4 */
+	__u32	preempt_count;			/* 0x03a8 */
+	__u32	spinlock_lockval;		/* 0x03ac */
+	__u32	spinlock_index;			/* 0x03b0 */
+	__u32	fpu_flags;			/* 0x03b4 */
+	__u64	percpu_offset;			/* 0x03b8 */
+	__u64	vdso_per_cpu_data;		/* 0x03c0 */
+	__u64	machine_flags;			/* 0x03c8 */
+	__u64	gmap;				/* 0x03d0 */
+	__u8	pad_0x03d8[0x0400-0x03d8];	/* 0x03d8 */
 
 	/* br %r1 trampoline */
 	__u16	br_r1_trampoline;		/* 0x0400 */
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index c6fad208c2fa..b6854812d2ed 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -196,23 +196,30 @@ static void cf_diag_perf_event_destroy(struct perf_event *event)
  */
 static int __hw_perf_event_init(struct perf_event *event)
 {
-	struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
 	struct perf_event_attr *attr = &event->attr;
+	struct cpu_cf_events *cpuhw;
 	enum cpumf_ctr_set i;
 	int err = 0;
 
-	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d authorized %#x\n", __func__,
-			    event, event->cpu, cpuhw->info.auth_ctl);
+	debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d\n", __func__,
+			    event, event->cpu);
 
 	event->hw.config = attr->config;
 	event->hw.config_base = 0;
-	local64_set(&event->count, 0);
 
-	/* Add all authorized counter sets to config_base */
+	/* Add all authorized counter sets to config_base. The
+	 * the hardware init function is either called per-cpu or just once
+	 * for all CPUS (event->cpu == -1).  This depends on the whether
+	 * counting is started for all CPUs or on a per workload base where
+	 * the perf event moves from one CPU to another CPU.
+	 * Checking the authorization on any CPU is fine as the hardware
+	 * applies the same authorization settings to all CPUs.
+	 */
+	cpuhw = &get_cpu_var(cpu_cf_events);
 	for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i)
 		if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i])
 			event->hw.config_base |= cpumf_ctr_ctl[i];
+	put_cpu_var(cpu_cf_events);
 
 	/* No authorized counter sets, nothing to count/sample */
 	if (!event->hw.config_base) {
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 3fe1c77c361b..bd197baf1dc3 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -266,7 +266,8 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	lc->percpu_offset = __per_cpu_offset[cpu];
 	lc->kernel_asce = S390_lowcore.kernel_asce;
 	lc->machine_flags = S390_lowcore.machine_flags;
-	lc->user_timer = lc->system_timer = lc->steal_timer = 0;
+	lc->user_timer = lc->system_timer =
+		lc->steal_timer = lc->avg_steal_timer = 0;
 	__ctl_store(lc->cregs_save_area, 0, 15);
 	save_access_regs((unsigned int *) lc->access_regs_save_area);
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 98f850e00008..a69a0911ed0e 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -124,7 +124,7 @@ static void account_system_index_scaled(struct task_struct *p, u64 cputime,
  */
 static int do_account_vtime(struct task_struct *tsk)
 {
-	u64 timer, clock, user, guest, system, hardirq, softirq, steal;
+	u64 timer, clock, user, guest, system, hardirq, softirq;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -182,12 +182,6 @@ static int do_account_vtime(struct task_struct *tsk)
 	if (softirq)
 		account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);
 
-	steal = S390_lowcore.steal_timer;
-	if ((s64) steal > 0) {
-		S390_lowcore.steal_timer = 0;
-		account_steal_time(cputime_to_nsecs(steal));
-	}
-
 	return virt_timer_forward(user + guest + system + hardirq + softirq);
 }
 
@@ -213,8 +207,19 @@ void vtime_task_switch(struct task_struct *prev)
  */
 void vtime_flush(struct task_struct *tsk)
 {
+	u64 steal, avg_steal;
+
 	if (do_account_vtime(tsk))
 		virt_timer_expire();
+
+	steal = S390_lowcore.steal_timer;
+	avg_steal = S390_lowcore.avg_steal_timer / 2;
+	if ((s64) steal > 0) {
+		S390_lowcore.steal_timer = 0;
+		account_steal_time(steal);
+		avg_steal += steal;
+	}
+	S390_lowcore.avg_steal_timer = avg_steal;
 }
 
 /*