Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Three cases of simple overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/cgroup/cpuset.c

@@ -1892,6 +1892,7 @@ static struct cftype files[] = {
 	{
 		.name = "memory_pressure",
 		.read_u64 = cpuset_read_u64,
+		.private = FILE_MEMORY_PRESSURE,
 	},
 
 	{

kernel/events/core.c

@@ -10034,28 +10034,27 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 
 		/*
-		 * Do not allow to attach to a group in a different
-		 * task or CPU context:
+		 * Make sure we're both events for the same CPU;
+		 * grouping events for different CPUs is broken; since
+		 * you can never concurrently schedule them anyhow.
 		 */
-		if (move_group) {
-			/*
-			 * Make sure we're both on the same task, or both
-			 * per-cpu events.
-			 */
-			if (group_leader->ctx->task != ctx->task)
-				goto err_context;
+		if (group_leader->cpu != event->cpu)
+			goto err_context;
 
-			/*
-			 * Make sure we're both events for the same CPU;
-			 * grouping events for different CPUs is broken; since
-			 * you can never concurrently schedule them anyhow.
-			 */
-			if (group_leader->cpu != event->cpu)
-				goto err_context;
-		} else {
-			if (group_leader->ctx != ctx)
-				goto err_context;
-		}
+		/*
+		 * Make sure we're both on the same task, or both
+		 * per-CPU events.
+		 */
+		if (group_leader->ctx->task != ctx->task)
+			goto err_context;
+
+		/*
+		 * Do not allow to attach to a group in a different task
+		 * or CPU context. If we're moving SW events, we'll fix
+		 * this up later, so allow that.
+		 */
+		if (!move_group && group_leader->ctx != ctx)
+			goto err_context;
 
 		/*
 		 * Only a group leader can be exclusive or pinned

kernel/events/uprobes.c

@@ -1262,8 +1262,6 @@ void uprobe_end_dup_mmap(void)
 
 void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
 {
-	newmm->uprobes_state.xol_area = NULL;
-
 	if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) {
 		set_bit(MMF_HAS_UPROBES, &newmm->flags);
 		/* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */

kernel/fork.c

@@ -785,6 +785,13 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 #endif
 }
 
+static void mm_init_uprobes_state(struct mm_struct *mm)
+{
+#ifdef CONFIG_UPROBES
+	mm->uprobes_state.xol_area = NULL;
+#endif
+}
+
 static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	struct user_namespace *user_ns)
 {
@@ -806,11 +813,13 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_init_cpumask(mm);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_mm_init(mm);
 	init_tlb_flush_pending(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	mm->pmd_huge_pte = NULL;
 #endif
+	mm_init_uprobes_state(mm);
 
 	if (current->mm) {
 		mm->flags = current->mm->flags & MMF_INIT_MASK;

kernel/kthread.c

@@ -637,6 +637,7 @@ repeat:
 		schedule();
 
 	try_to_freeze();
+	cond_resched();
 	goto repeat;
 }
 EXPORT_SYMBOL_GPL(kthread_worker_fn);

kernel/sched/wait.c

@@ -70,9 +70,10 @@ static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
 
 	list_for_each_entry_safe(curr, next, &wq_head->head, entry) {
 		unsigned flags = curr->flags;
-
-		if (curr->func(curr, mode, wake_flags, key) &&
-				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+		int ret = curr->func(curr, mode, wake_flags, key);
+		if (ret < 0)
+			break;
+		if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
 			break;
 	}
 }

kernel/time/timer.c

@@ -203,6 +203,7 @@ struct timer_base {
 	bool			migration_enabled;
 	bool			nohz_active;
 	bool			is_idle;
+	bool			must_forward_clk;
 	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
 	struct hlist_head	vectors[WHEEL_SIZE];
 } ____cacheline_aligned;
@@ -856,13 +857,19 @@ get_target_base(struct timer_base *base, unsigned tflags)
 
 static inline void forward_timer_base(struct timer_base *base)
 {
-	unsigned long jnow = READ_ONCE(jiffies);
+	unsigned long jnow;
 
 	/*
-	 * We only forward the base when it's idle and we have a delta between
-	 * base clock and jiffies.
+	 * We only forward the base when we are idle or have just come out of
+	 * idle (must_forward_clk logic), and have a delta between base clock
+	 * and jiffies. In the common case, run_timers will take care of it.
 	 */
-	if (!base->is_idle || (long) (jnow - base->clk) < 2)
+	if (likely(!base->must_forward_clk))
+		return;
+
+	jnow = READ_ONCE(jiffies);
+	base->must_forward_clk = base->is_idle;
+	if ((long)(jnow - base->clk) < 2)
 		return;
 
 	/*
@@ -938,6 +945,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	 * same array bucket then just return:
 	 */
 	if (timer_pending(timer)) {
+		/*
+		 * The downside of this optimization is that it can result in
+		 * larger granularity than you would get from adding a new
+		 * timer with this expiry.
+		 */
 		if (timer->expires == expires)
 			return 1;
 
@@ -948,6 +960,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 * dequeue/enqueue dance.
 		 */
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 
 		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);
@@ -964,6 +977,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		}
 	} else {
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 	}
 
 	ret = detach_if_pending(timer, base, false);
@@ -991,12 +1005,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 			raw_spin_lock(&base->lock);
 			WRITE_ONCE(timer->flags,
 				   (timer->flags & ~TIMER_BASEMASK) | base->cpu);
+			forward_timer_base(base);
 		}
 	}
 
-	/* Try to forward a stale timer base clock */
-	forward_timer_base(base);
-
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
@@ -1112,6 +1124,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
 		WRITE_ONCE(timer->flags,
 			   (timer->flags & ~TIMER_BASEMASK) | cpu);
 	}
+	forward_timer_base(base);
 
 	debug_activate(timer, timer->expires);
 	internal_add_timer(base, timer);
@@ -1497,10 +1510,16 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		if (!is_max_delta)
 			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
-		 * If we expect to sleep more than a tick, mark the base idle:
+		 * If we expect to sleep more than a tick, mark the base idle.
+		 * Also the tick is stopped so any added timer must forward
+		 * the base clk itself to keep granularity small. This idle
+		 * logic is only maintained for the BASE_STD base, deferrable
+		 * timers may still see large granularity skew (by design).
 		 */
-		if ((expires - basem) > TICK_NSEC)
+		if ((expires - basem) > TICK_NSEC) {
+			base->must_forward_clk = true;
 			base->is_idle = true;
+		}
 	}
 	raw_spin_unlock(&base->lock);
 
@@ -1611,6 +1630,19 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
+	/*
+	 * must_forward_clk must be cleared before running timers so that any
+	 * timer functions that call mod_timer will not try to forward the
+	 * base. idle trcking / clock forwarding logic is only used with
+	 * BASE_STD timers.
+	 *
+	 * The deferrable base does not do idle tracking at all, so we do
+	 * not forward it. This can result in very large variations in
+	 * granularity for deferrable timers, but they can be deferred for
+	 * long periods due to idle.
+	 */
+	base->must_forward_clk = false;
+
 	__run_timers(base);
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));

kernel/trace/ftrace.c

@@ -889,6 +889,10 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace)
 
 	function_profile_call(trace->func, 0, NULL, NULL);
 
+	/* If function graph is shutting down, ret_stack can be NULL */
+	if (!current->ret_stack)
+		return 0;
+
 	if (index >= 0 && index < FTRACE_RETFUNC_DEPTH)
 		current->ret_stack[index].subtime = 0;
 

kernel/trace/ring_buffer.c

@@ -4386,15 +4386,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * the page that was allocated, with the read page of the buffer.
  *
  * Returns:
- *  The page allocated, or NULL on error.
+ *  The page allocated, or ERR_PTR
  */
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 {
-	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_data_page *bpage = NULL;
 	unsigned long flags;
 	struct page *page;
 
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return ERR_PTR(-ENODEV);
+
+	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
@@ -4412,7 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 	page = alloc_pages_node(cpu_to_node(cpu),
 				GFP_KERNEL | __GFP_NORETRY, 0);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	bpage = page_address(page);
 
@@ -4467,8 +4471,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *
  * for example:
  *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
- *	if (!rpage)
- *		return error;
+ *	if (IS_ERR(rpage))
+ *		return PTR_ERR(rpage);
  *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
  *	if (ret >= 0)
  *		process_page(rpage, ret);

kernel/trace/ring_buffer_benchmark.c

@@ -113,7 +113,7 @@ static enum event_status read_page(int cpu)
 	int i;
 
 	bpage = ring_buffer_alloc_read_page(buffer, cpu);
-	if (!bpage)
+	if (IS_ERR(bpage))
 		return EVENT_DROPPED;
 
 	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);

kernel/trace/trace.c

@@ -6598,7 +6598,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 {
 	struct ftrace_buffer_info *info = filp->private_data;
 	struct trace_iterator *iter = &info->iter;
-	ssize_t ret;
+	ssize_t ret = 0;
 	ssize_t size;
 
 	if (!count)
@@ -6612,10 +6612,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
 							  iter->cpu_file);
-		info->spare_cpu = iter->cpu_file;
+		if (IS_ERR(info->spare)) {
+			ret = PTR_ERR(info->spare);
+			info->spare = NULL;
+		} else {
+			info->spare_cpu = iter->cpu_file;
+		}
 	}
 	if (!info->spare)
-		return -ENOMEM;
+		return ret;
 
 	/* Do we have previous read data to read? */
 	if (info->read < PAGE_SIZE)
@@ -6790,8 +6795,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		ref->ref = 1;
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
-		if (!ref->page) {
-			ret = -ENOMEM;
+		if (IS_ERR(ref->page)) {
+			ret = PTR_ERR(ref->page);
+			ref->page = NULL;
 			kfree(ref);
 			break;
 		}
@@ -8293,6 +8299,7 @@ __init static int tracer_alloc_buffers(void)
 	if (ret < 0)
 		goto out_free_cpumask;
 	/* Used for event triggers */
+	ret = -ENOMEM;
 	temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
 	if (!temp_buffer)
 		goto out_rm_hp_state;
@@ -8407,4 +8414,4 @@ __init static int clear_boot_tracer(void)
 }
 
 fs_initcall(tracer_init_tracefs);
-late_initcall(clear_boot_tracer);
+late_initcall_sync(clear_boot_tracer);

kernel/trace/trace_events_filter.c

@@ -1959,6 +1959,10 @@ static int create_filter(struct trace_event_call *call,
 		if (err && set_str)
 			append_filter_err(ps, filter);
 	}
+	if (err && !set_str) {
+		free_event_filter(filter);
+		filter = NULL;
+	}
 	create_filter_finish(ps);
 
 	*filterp = filter;

kernel/trace/tracing_map.c

@@ -221,16 +221,19 @@ void tracing_map_array_free(struct tracing_map_array *a)
 	if (!a)
 		return;
 
-	if (!a->pages) {
-		kfree(a);
-		return;
-	}
+	if (!a->pages)
+		goto free;
 
 	for (i = 0; i < a->n_pages; i++) {
 		if (!a->pages[i])
 			break;
 		free_page((unsigned long)a->pages[i]);
 	}
+
+	kfree(a->pages);
+
+ free:
+	kfree(a);
 }
 
 struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,