Merge branch 'linus' into locking/core, to fix up conflicts

 Conflicts:
	mm/page_alloc.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 112 insertions, 60 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 4fb4631..d11c818 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -652,12 +652,27 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 	}
 }
 
+static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
+{
+	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
+	       BITS_PER_LONG == 64;
+}
+
+static u32 htab_size_value(const struct bpf_htab *htab, bool percpu)
+{
+	u32 size = htab->map.value_size;
+
+	if (percpu || fd_htab_map_needs_adjust(htab))
+		size = round_up(size, 8);
+	return size;
+}
+
 static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 					 void *value, u32 key_size, u32 hash,
 					 bool percpu, bool onallcpus,
 					 struct htab_elem *old_elem)
 {
-	u32 size = htab->map.value_size;
+	u32 size = htab_size_value(htab, percpu);
 	bool prealloc = htab_is_prealloc(htab);
 	struct htab_elem *l_new, **pl_new;
 	void __percpu *pptr;
@@ -696,9 +711,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 	memcpy(l_new->key, key, key_size);
 	if (percpu) {
-		/* round up value_size to 8 bytes */
-		size = round_up(size, 8);
-
 		if (prealloc) {
 			pptr = htab_elem_get_ptr(l_new, key_size);
 		} else {
@@ -1209,17 +1221,9 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 
 static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr)
 {
-	struct bpf_map *map;
-
 	if (attr->value_size != sizeof(u32))
 		return ERR_PTR(-EINVAL);
-
-	/* pointer is stored internally */
-	attr->value_size = sizeof(void *);
-	map = htab_map_alloc(attr);
-	attr->value_size = sizeof(u32);
-
-	return map;
+	return htab_map_alloc(attr);
 }
 
 static void fd_htab_map_free(struct bpf_map *map)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 9ed6a05..39ca7e9 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1899,6 +1899,7 @@ static struct cftype files[] = {
 	{
 		.name = "memory_pressure",
 		.read_u64 = cpuset_read_u64,
+		.private = FILE_MEMORY_PRESSURE,
 	},
 
 	{
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ee20d4c..03ac9c8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7906,16 +7906,15 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
 		}
 	}
 	perf_tp_event(call->event.type, count, raw_data, size, regs, head,
-		      rctx, task);
+		      rctx, task, NULL);
 }
 EXPORT_SYMBOL_GPL(perf_trace_run_bpf_submit);
 
 void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 		   struct pt_regs *regs, struct hlist_head *head, int rctx,
-		   struct task_struct *task)
+		   struct task_struct *task, struct perf_event *event)
 {
 	struct perf_sample_data data;
-	struct perf_event *event;
 
 	struct perf_raw_record raw = {
 		.frag = {
@@ -7929,9 +7928,15 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 
 	perf_trace_buf_update(record, event_type);
 
-	hlist_for_each_entry_rcu(event, head, hlist_entry) {
+	/* Use the given event instead of the hlist */
+	if (event) {
 		if (perf_tp_event_match(event, &data, regs))
 			perf_swevent_event(event, count, &data, regs);
+	} else {
+		hlist_for_each_entry_rcu(event, head, hlist_entry) {
+			if (perf_tp_event_match(event, &data, regs))
+				perf_swevent_event(event, count, &data, regs);
+		}
 	}
 
 	/*
@@ -9611,6 +9616,8 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (ret)
 		return -EFAULT;
 
+	attr->size = size;
+
 	if (attr->__reserved_1)
 		return -EINVAL;
 
@@ -10032,28 +10039,27 @@ 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
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 0e137f9..267f6ef 100644
--- a/kernel/events/uprobes.c
+++ b/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 */
diff --git a/kernel/fork.c b/kernel/fork.c
index 5fc0991..dab73d1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -787,6 +787,13 @@ 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)
 {
@@ -808,11 +815,13 @@ 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;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 26db528..1c19edf 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -637,6 +637,7 @@ repeat:
 		schedule();
 
 	try_to_freeze();
+	cond_resched();
 	goto repeat;
 }
 EXPORT_SYMBOL_GPL(kthread_worker_fn);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 17f11c6..d6afed6 100644
--- a/kernel/sched/wait.c
+++ b/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;
 	}
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index cedafa0..7e7e61c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -637,9 +637,7 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
 	tk->ktime_sec = seconds;
 
 	/* Update the monotonic raw base */
-	seconds = tk->raw_sec;
-	nsec = (u32)(tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift);
-	tk->tkr_raw.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
+	tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC);
 }
 
 /* must hold timekeeper_lock */
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 8f5d1bf..f2674a0 100644
--- a/kernel/time/timer.c
+++ b/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]));
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 562fa69..13ba2d3 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -306,6 +306,7 @@ static void
 perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
 {
+	struct perf_event *event;
 	struct ftrace_entry *entry;
 	struct hlist_head *head;
 	struct pt_regs regs;
@@ -329,8 +330,9 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 
 	entry->ip = ip;
 	entry->parent_ip = parent_ip;
+	event = container_of(ops, struct perf_event, ftrace_ops);
 	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN,
-			      1, &regs, head, NULL);
+			      1, &regs, head, NULL, event);
 
 #undef ENTRY_SIZE
 }
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c9b5aa1..8a907e1 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1200,7 +1200,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	memset(&entry[1], 0, dsize);
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
 }
 NOKPROBE_SYMBOL(kprobe_perf_func);
 
@@ -1236,7 +1236,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	entry->ret_ip = (unsigned long)ri->ret_addr;
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
 }
 NOKPROBE_SYMBOL(kretprobe_perf_func);
 #endif	/* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e10395..74d9a86 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -596,7 +596,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 			       (unsigned long *)&rec->args);
 	perf_trace_buf_submit(rec, size, rctx,
 			      sys_data->enter_event->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
 }
 
 static int perf_sysenter_enable(struct trace_event_call *call)
@@ -667,7 +667,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 	perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
-			      1, regs, head, NULL);
+			      1, regs, head, NULL, NULL);
 }
 
 static int perf_sysexit_enable(struct trace_event_call *call)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index a7581fe..4525e02 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1156,7 +1156,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	}
 
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
  out:
 	preempt_enable();
 }