Merge branch 'x86/cleanups' into perf/uprobes

Merge reason: We want to merge a dependent patch.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

18 files changed, 171 insertions, 46 deletions

diff --git a/kernel/compat.c b/kernel/compat.c
index f346ced..74ff849 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -31,11 +31,10 @@
 #include <asm/uaccess.h>
 
 /*
- * Note that the native side is already converted to a timespec, because
- * that's what we want anyway.
+ * Get/set struct timeval with struct timespec on the native side
  */
-static int compat_get_timeval(struct timespec *o,
-		struct compat_timeval __user *i)
+static int compat_get_timeval_convert(struct timespec *o,
+				      struct compat_timeval __user *i)
 {
 	long usec;
 
@@ -46,8 +45,8 @@ static int compat_get_timeval(struct timespec *o,
 	return 0;
 }
 
-static int compat_put_timeval(struct compat_timeval __user *o,
-		struct timeval *i)
+static int compat_put_timeval_convert(struct compat_timeval __user *o,
+				      struct timeval *i)
 {
 	return (put_user(i->tv_sec, &o->tv_sec) ||
 		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
@@ -117,7 +116,7 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
 	if (tv) {
 		struct timeval ktv;
 		do_gettimeofday(&ktv);
-		if (compat_put_timeval(tv, &ktv))
+		if (compat_put_timeval_convert(tv, &ktv))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -135,7 +134,7 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
 	struct timezone ktz;
 
 	if (tv) {
-		if (compat_get_timeval(&kts, tv))
+		if (compat_get_timeval_convert(&kts, tv))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -146,12 +145,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
 	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
 }
 
+int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
+{
+	return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) ||
+			__get_user(tv->tv_sec, &ctv->tv_sec) ||
+			__get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_timeval);
+
+int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
+{
+	return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) ||
+			__put_user(tv->tv_sec, &ctv->tv_sec) ||
+			__put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_timeval);
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
 			__get_user(ts->tv_sec, &cts->tv_sec) ||
 			__get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
+EXPORT_SYMBOL_GPL(get_compat_timespec);
 
 int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
 {
@@ -161,6 +177,42 @@ int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user
 }
 EXPORT_SYMBOL_GPL(put_compat_timespec);
 
+int compat_get_timeval(struct timeval *tv, const void __user *utv)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0;
+	else
+		return get_compat_timeval(tv, utv);
+}
+EXPORT_SYMBOL_GPL(compat_get_timeval);
+
+int compat_put_timeval(const struct timeval *tv, void __user *utv)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0;
+	else
+		return put_compat_timeval(tv, utv);
+}
+EXPORT_SYMBOL_GPL(compat_put_timeval);
+
+int compat_get_timespec(struct timespec *ts, const void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0;
+	else
+		return get_compat_timespec(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_get_timespec);
+
+int compat_put_timespec(const struct timespec *ts, void __user *uts)
+{
+	if (COMPAT_USE_64BIT_TIME)
+		return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0;
+	else
+		return put_compat_timespec(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_put_timespec);
+
 static long compat_nanosleep_restart(struct restart_block *restart)
 {
 	struct compat_timespec __user *rmtp;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7c3b9de..94afe5b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2303,7 +2303,7 @@ do {					\
 static DEFINE_PER_CPU(int, perf_throttled_count);
 static DEFINE_PER_CPU(u64, perf_throttled_seq);
 
-static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
+static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bool disable)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	s64 period, sample_period;
@@ -2322,9 +2322,13 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 	hwc->sample_period = sample_period;
 
 	if (local64_read(&hwc->period_left) > 8*sample_period) {
-		event->pmu->stop(event, PERF_EF_UPDATE);
+		if (disable)
+			event->pmu->stop(event, PERF_EF_UPDATE);
+
 		local64_set(&hwc->period_left, 0);
-		event->pmu->start(event, PERF_EF_RELOAD);
+
+		if (disable)
+			event->pmu->start(event, PERF_EF_RELOAD);
 	}
 }
 
@@ -2350,6 +2354,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		return;
 
 	raw_spin_lock(&ctx->lock);
+	perf_pmu_disable(ctx->pmu);
 
 	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
@@ -2381,13 +2386,17 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		/*
 		 * restart the event
 		 * reload only if value has changed
+		 * we have stopped the event so tell that
+		 * to perf_adjust_period() to avoid stopping it
+		 * twice.
 		 */
 		if (delta > 0)
-			perf_adjust_period(event, period, delta);
+			perf_adjust_period(event, period, delta, false);
 
 		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
 	}
 
+	perf_pmu_enable(ctx->pmu);
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -4567,7 +4576,7 @@ static int __perf_event_overflow(struct perf_event *event,
 		hwc->freq_time_stamp = now;
 
 		if (delta > 0 && delta < 2*TICK_NSEC)
-			perf_adjust_period(event, delta, hwc->last_period);
+			perf_adjust_period(event, delta, hwc->last_period, true);
 	}
 
 	/*
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index b0309f7..3330022 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -658,10 +658,10 @@ int __init init_hw_breakpoint(void)
 
  err_alloc:
 	for_each_possible_cpu(err_cpu) {
-		if (err_cpu == cpu)
-			break;
 		for (i = 0; i < TYPE_MAX; i++)
 			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+		if (err_cpu == cpu)
+			break;
 	}
 
 	return -ENOMEM;
diff --git a/kernel/exit.c b/kernel/exit.c
index 4b4042f..4db0200 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -473,7 +473,7 @@ static void close_files(struct files_struct * files)
 		i = j * __NFDBITS;
 		if (i >= fdt->max_fds)
 			break;
-		set = fdt->open_fds->fds_bits[j++];
+		set = fdt->open_fds[j++];
 		while (set) {
 			if (set & 1) {
 				struct file * file = xchg(&fdt->fd[i], NULL);
diff --git a/kernel/fork.c b/kernel/fork.c
index 1b2ef3c..e2cd3e2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -66,6 +66,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/oom.h>
 #include <linux/khugepaged.h>
+#include <linux/signalfd.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -910,7 +911,7 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
 			return -ENOMEM;
 
 		new_ioc->ioprio = ioc->ioprio;
-		put_io_context(new_ioc, NULL);
+		put_io_context(new_ioc);
 	}
 #endif
 	return 0;
@@ -935,8 +936,10 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_sighand(struct sighand_struct *sighand)
 {
-	if (atomic_dec_and_test(&sighand->count))
+	if (atomic_dec_and_test(&sighand->count)) {
+		signalfd_cleanup(sighand);
 		kmem_cache_free(sighand_cachep, sighand);
+	}
 }
 
 
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 342d8f4..0119b9d 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -53,7 +53,7 @@ unsigned long probe_irq_on(void)
 			if (desc->irq_data.chip->irq_set_type)
 				desc->irq_data.chip->irq_set_type(&desc->irq_data,
 							 IRQ_TYPE_PROBE);
-			irq_startup(desc);
+			irq_startup(desc, false);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -70,7 +70,7 @@ unsigned long probe_irq_on(void)
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && irq_settings_can_probe(desc)) {
 			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
-			if (irq_startup(desc))
+			if (irq_startup(desc, false))
 				desc->istate |= IRQS_PENDING;
 		}
 		raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f7c543a..fb7db75 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -157,19 +157,22 @@ static void irq_state_set_masked(struct irq_desc *desc)
 	irqd_set(&desc->irq_data, IRQD_IRQ_MASKED);
 }
 
-int irq_startup(struct irq_desc *desc)
+int irq_startup(struct irq_desc *desc, bool resend)
 {
+	int ret = 0;
+
 	irq_state_clr_disabled(desc);
 	desc->depth = 0;
 
 	if (desc->irq_data.chip->irq_startup) {
-		int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
+		ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
 		irq_state_clr_masked(desc);
-		return ret;
+	} else {
+		irq_enable(desc);
 	}
-
-	irq_enable(desc);
-	return 0;
+	if (resend)
+		check_irq_resend(desc, desc->irq_data.irq);
+	return ret;
 }
 
 void irq_shutdown(struct irq_desc *desc)
@@ -330,6 +333,24 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_simple_irq);
 
+/*
+ * Called unconditionally from handle_level_irq() and only for oneshot
+ * interrupts from handle_fasteoi_irq()
+ */
+static void cond_unmask_irq(struct irq_desc *desc)
+{
+	/*
+	 * We need to unmask in the following cases:
+	 * - Standard level irq (IRQF_ONESHOT is not set)
+	 * - Oneshot irq which did not wake the thread (caused by a
+	 *   spurious interrupt or a primary handler handling it
+	 *   completely).
+	 */
+	if (!irqd_irq_disabled(&desc->irq_data) &&
+	    irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot)
+		unmask_irq(desc);
+}
+
 /**
  *	handle_level_irq - Level type irq handler
  *	@irq:	the interrupt number
@@ -362,8 +383,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	handle_irq_event(desc);
 
-	if (!irqd_irq_disabled(&desc->irq_data) && !(desc->istate & IRQS_ONESHOT))
-		unmask_irq(desc);
+	cond_unmask_irq(desc);
+
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -417,6 +438,9 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	preflow_handler(desc);
 	handle_irq_event(desc);
 
+	if (desc->istate & IRQS_ONESHOT)
+		cond_unmask_irq(desc);
+
 out_eoi:
 	desc->irq_data.chip->irq_eoi(&desc->irq_data);
 out_unlock:
@@ -625,7 +649,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
 		irq_settings_set_nothread(desc);
-		irq_startup(desc);
+		irq_startup(desc, true);
 	}
 out:
 	irq_put_desc_busunlock(desc, flags);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b795231..40378ff 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -67,7 +67,7 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
-extern int irq_startup(struct irq_desc *desc);
+extern int irq_startup(struct irq_desc *desc, bool resend);
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a9a9dbe..32313c0 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1027,7 +1027,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->istate |= IRQS_ONESHOT;
 
 		if (irq_settings_can_autoenable(desc))
-			irq_startup(desc);
+			irq_startup(desc, true);
 		else
 			/* Undo nested disables: */
 			desc->depth = 1;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 29f5b65..9788c0e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1673,8 +1673,12 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 		ri->rp = rp;
 		ri->task = current;
 
-		if (rp->entry_handler && rp->entry_handler(ri, regs))
+		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
+			raw_spin_lock_irqsave(&rp->lock, flags);
+			hlist_add_head(&ri->hlist, &rp->free_instances);
+			raw_spin_unlock_irqrestore(&rp->lock, flags);
 			return 0;
+		}
 
 		arch_prepare_kretprobe(ri, regs);
 
diff --git a/kernel/params.c b/kernel/params.c
index 32ee043..4bc965d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -97,7 +97,8 @@ static int parse_one(char *param,
 	for (i = 0; i < num_params; i++) {
 		if (parameq(param, params[i].name)) {
 			/* No one handled NULL, so do it here. */
-			if (!val && params[i].ops->set != param_set_bool)
+			if (!val && params[i].ops->set != param_set_bool
+			    && params[i].ops->set != param_set_bint)
 				return -EINVAL;
 			pr_debug("They are equal!  Calling %p\n",
 			       params[i].ops->set);
diff --git a/kernel/pid.c b/kernel/pid.c
index ce8e00d..9f08dfa 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -543,12 +543,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
  */
 void __init pidhash_init(void)
 {
-	int i, pidhash_size;
+	unsigned int i, pidhash_size;
 
 	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
 					   HASH_EARLY | HASH_SMALL,
 					   &pidhash_shift, NULL, 4096);
-	pidhash_size = 1 << pidhash_shift;
+	pidhash_size = 1U << pidhash_shift;
 
 	for (i = 0; i < pidhash_size; i++)
 		INIT_HLIST_HEAD(&pid_hash[i]);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 0c4defe..21724ee 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -231,8 +231,28 @@ extern int pm_test_level;
 #ifdef CONFIG_SUSPEND_FREEZER
 static inline int suspend_freeze_processes(void)
 {
-	int error = freeze_processes();
-	return error ? : freeze_kernel_threads();
+	int error;
+
+	error = freeze_processes();
+
+	/*
+	 * freeze_processes() automatically thaws every task if freezing
+	 * fails. So we need not do anything extra upon error.
+	 */
+	if (error)
+		goto Finish;
+
+	error = freeze_kernel_threads();
+
+	/*
+	 * freeze_kernel_threads() thaws only kernel threads upon freezing
+	 * failure. So we have to thaw the userspace tasks ourselves.
+	 */
+	if (error)
+		thaw_processes();
+
+ Finish:
+	return error;
 }
 
 static inline void suspend_thaw_processes(void)
diff --git a/kernel/power/process.c b/kernel/power/process.c
index eeca003..7e42645 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -143,7 +143,10 @@ int freeze_processes(void)
 /**
  * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator.
  *
- * On success, returns 0.  On failure, -errno and system is fully thawed.
+ * On success, returns 0.  On failure, -errno and only the kernel threads are
+ * thawed, so as to give a chance to the caller to do additional cleanups
+ * (if any) before thawing the userspace tasks. So, it is the responsibility
+ * of the caller to thaw the userspace tasks, when the time is right.
  */
 int freeze_kernel_threads(void)
 {
@@ -159,7 +162,7 @@ int freeze_kernel_threads(void)
 	BUG_ON(in_atomic());
 
 	if (error)
-		thaw_processes();
+		thaw_kernel_threads();
 	return error;
 }
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index e5a21a8..3e10007 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -249,13 +249,15 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		}
 		pm_restore_gfp_mask();
 		error = hibernation_snapshot(data->platform_support);
-		if (!error) {
+		if (error) {
+			thaw_kernel_threads();
+		} else {
 			error = put_user(in_suspend, (int __user *)arg);
 			if (!error && !freezer_test_done)
 				data->ready = 1;
 			if (freezer_test_done) {
 				freezer_test_done = false;
-				thaw_processes();
+				thaw_kernel_threads();
 			}
 		}
 		break;
diff --git a/kernel/relay.c b/kernel/relay.c
index 4335e1d..ab56a17 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -164,10 +164,14 @@ depopulate:
  */
 static struct rchan_buf *relay_create_buf(struct rchan *chan)
 {
-	struct rchan_buf *buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
-	if (!buf)
+	struct rchan_buf *buf;
+
+	if (chan->n_subbufs > UINT_MAX / sizeof(size_t *))
 		return NULL;
 
+	buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
+	if (!buf)
+		return NULL;
 	buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL);
 	if (!buf->padding)
 		goto free_buf;
@@ -574,6 +578,8 @@ struct rchan *relay_open(const char *base_filename,
 
 	if (!(subbuf_size && n_subbufs))
 		return NULL;
+	if (subbuf_size > UINT_MAX / n_subbufs)
+		return NULL;
 
 	chan = kzalloc(sizeof(struct rchan), GFP_KERNEL);
 	if (!chan)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5255c9d..33a0676 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1932,7 +1932,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
 	finish_lock_switch(rq, prev);
-	trace_sched_stat_sleeptime(current, rq->clock);
 
 	fire_sched_in_preempt_notifiers(current);
 	if (mm)
@@ -6729,7 +6728,7 @@ int __init sched_create_sysfs_power_savings_entries(struct device *dev)
 static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 			     void *hcpu)
 {
-	switch (action & ~CPU_TASKS_FROZEN) {
+	switch (action) {
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
 		cpuset_update_active_cpus();
@@ -6742,7 +6741,7 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
 			       void *hcpu)
 {
-	switch (action & ~CPU_TASKS_FROZEN) {
+	switch (action) {
 	case CPU_DOWN_PREPARE:
 		cpuset_update_active_cpus();
 		return NOTIFY_OK;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7c6414f..aca16b8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1003,6 +1003,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		if (unlikely(delta > se->statistics.sleep_max))
 			se->statistics.sleep_max = delta;
 
+		se->statistics.sleep_start = 0;
 		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {
@@ -1019,6 +1020,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		if (unlikely(delta > se->statistics.block_max))
 			se->statistics.block_max = delta;
 
+		se->statistics.block_start = 0;
 		se->statistics.sum_sleep_runtime += delta;
 
 		if (tsk) {