Merge branch 'perf/urgent' into perf/core, to pick up fixes

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

kernel/cgroup/cgroup-v1.c

@@ -471,6 +471,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 	 */
 	p++;
 	if (p >= end) {
+		(*pos)++;
 		return NULL;
 	} else {
 		*pos = *p;
@@ -782,7 +783,7 @@ void cgroup1_release_agent(struct work_struct *work)
 
 	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
 	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-	if (!pathbuf || !agentbuf)
+	if (!pathbuf || !agentbuf || !strlen(agentbuf))
 		goto out;
 
 	spin_lock_irq(&css_set_lock);

kernel/cgroup/cgroup.c

@@ -3542,21 +3542,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_IO);
 }
 static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_MEM);
 }
 static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi;
+	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 
 	return psi_show(seq, psi, PSI_CPU);
 }
@@ -4400,12 +4400,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 		}
 	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
-	if (!list_empty(&cset->tasks))
+	if (!list_empty(&cset->tasks)) {
 		it->task_pos = cset->tasks.next;
-	else if (!list_empty(&cset->mg_tasks))
+		it->cur_tasks_head = &cset->tasks;
+	} else if (!list_empty(&cset->mg_tasks)) {
 		it->task_pos = cset->mg_tasks.next;
-	else
+		it->cur_tasks_head = &cset->mg_tasks;
+	} else {
 		it->task_pos = cset->dying_tasks.next;
+		it->cur_tasks_head = &cset->dying_tasks;
+	}
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
@@ -4463,10 +4467,14 @@ repeat:
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->tasks_head)
+		if (it->task_pos == it->tasks_head) {
 			it->task_pos = it->mg_tasks_head->next;
-		if (it->task_pos == it->mg_tasks_head)
+			it->cur_tasks_head = it->mg_tasks_head;
+		}
+		if (it->task_pos == it->mg_tasks_head) {
 			it->task_pos = it->dying_tasks_head->next;
+			it->cur_tasks_head = it->dying_tasks_head;
+		}
 		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
 	} else {
@@ -4485,11 +4493,12 @@ repeat:
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (!atomic_read(&task->signal->live))
+		if (it->cur_tasks_head == it->dying_tasks_head &&
+		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (task->flags & PF_EXITING)
+		if (it->cur_tasks_head == it->dying_tasks_head)
 			goto repeat;
 	}
 }
@@ -4595,6 +4604,9 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
 	struct kernfs_open_file *of = s->private;
 	struct css_task_iter *it = of->priv;
 
+	if (pos)
+		(*pos)++;
+
 	return css_task_iter_next(it);
 }
 
@@ -4610,7 +4622,7 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 	 * from position 0, so we can simply keep iterating on !0 *pos.
 	 */
 	if (!it) {
-		if (WARN_ON_ONCE((*pos)++))
+		if (WARN_ON_ONCE((*pos)))
 			return ERR_PTR(-EINVAL);
 
 		it = kzalloc(sizeof(*it), GFP_KERNEL);
@@ -4618,10 +4630,11 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 			return ERR_PTR(-ENOMEM);
 		of->priv = it;
 		css_task_iter_start(&cgrp->self, iter_flags, it);
-	} else if (!(*pos)++) {
+	} else if (!(*pos)) {
 		css_task_iter_end(it);
 		css_task_iter_start(&cgrp->self, iter_flags, it);
-	}
+	} else
+		return it->cur_task;
 
 	return cgroup_procs_next(s, NULL, NULL);
 }
@@ -6258,6 +6271,10 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 		return;
 	}
 
+	/* Don't associate the sock with unrelated interrupted task's cgroup. */
+	if (in_interrupt())
+		return;
+
 	rcu_read_lock();
 
 	while (true) {

kernel/exit.c

@@ -619,8 +619,8 @@ static void forget_original_parent(struct task_struct *father,
 	reaper = find_new_reaper(father, reaper);
 	list_for_each_entry(p, &father->children, sibling) {
 		for_each_thread(p, t) {
-			t->real_parent = reaper;
-			BUG_ON((!t->ptrace) != (t->parent == father));
+			RCU_INIT_POINTER(t->real_parent, reaper);
+			BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father));
 			if (likely(!t->ptrace))
 				t->parent = t->real_parent;
 			if (t->pdeath_signal)

kernel/fork.c

@@ -1508,7 +1508,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 		return 0;
 	}
 	sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
-	rcu_assign_pointer(tsk->sighand, sig);
+	RCU_INIT_POINTER(tsk->sighand, sig);
 	if (!sig)
 		return -ENOMEM;
 

kernel/futex.c

@@ -385,9 +385,9 @@ static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
  */
 static struct futex_hash_bucket *hash_futex(union futex_key *key)
 {
-	u32 hash = jhash2((u32*)&key->both.word,
-			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
+	u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4,
 			  key->both.offset);
+
 	return &futex_queues[hash & (futex_hashsize - 1)];
 }
 
@@ -429,7 +429,7 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode); /* implies smp_mb(); (B) */
+		smp_mb();		/* explicit smp_mb(); (B) */
 		break;
 	case FUT_OFF_MMSHARED:
 		futex_get_mm(key); /* implies smp_mb(); (B) */
@@ -463,7 +463,6 @@ static void drop_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		iput(key->shared.inode);
 		break;
 	case FUT_OFF_MMSHARED:
 		mmdrop(key->private.mm);
@@ -505,6 +504,46 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
 	return timeout;
 }
 
+/*
+ * Generate a machine wide unique identifier for this inode.
+ *
+ * This relies on u64 not wrapping in the life-time of the machine; which with
+ * 1ns resolution means almost 585 years.
+ *
+ * This further relies on the fact that a well formed program will not unmap
+ * the file while it has a (shared) futex waiting on it. This mapping will have
+ * a file reference which pins the mount and inode.
+ *
+ * If for some reason an inode gets evicted and read back in again, it will get
+ * a new sequence number and will _NOT_ match, even though it is the exact same
+ * file.
+ *
+ * It is important that match_futex() will never have a false-positive, esp.
+ * for PI futexes that can mess up the state. The above argues that false-negatives
+ * are only possible for malformed programs.
+ */
+static u64 get_inode_sequence_number(struct inode *inode)
+{
+	static atomic64_t i_seq;
+	u64 old;
+
+	/* Does the inode already have a sequence number? */
+	old = atomic64_read(&inode->i_sequence);
+	if (likely(old))
+		return old;
+
+	for (;;) {
+		u64 new = atomic64_add_return(1, &i_seq);
+		if (WARN_ON_ONCE(!new))
+			continue;
+
+		old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new);
+		if (old)
+			return old;
+		return new;
+	}
+}
+
 /**
  * get_futex_key() - Get parameters which are the keys for a futex
  * @uaddr:	virtual address of the futex
@@ -517,9 +556,15 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
  *
  * The key words are stored in @key on success.
  *
- * For shared mappings, it's (page->index, file_inode(vma->vm_file),
- * offset_within_page).  For private mappings, it's (uaddr, current->mm).
- * We can usually work out the index without swapping in the page.
+ * For shared mappings (when @fshared), the key is:
+ *   ( inode->i_sequence, page->index, offset_within_page )
+ * [ also see get_inode_sequence_number() ]
+ *
+ * For private mappings (or when !@fshared), the key is:
+ *   ( current->mm, address, 0 )
+ *
+ * This allows (cross process, where applicable) identification of the futex
+ * without keeping the page pinned for the duration of the FUTEX_WAIT.
  *
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
@@ -659,8 +704,6 @@ again:
 		key->private.mm = mm;
 		key->private.address = address;
 
-		get_futex_key_refs(key); /* implies smp_mb(); (B) */
-
 	} else {
 		struct inode *inode;
 
@@ -692,40 +735,14 @@ again:
 			goto again;
 		}
 
-		/*
-		 * Take a reference unless it is about to be freed. Previously
-		 * this reference was taken by ihold under the page lock
-		 * pinning the inode in place so i_lock was unnecessary. The
-		 * only way for this check to fail is if the inode was
-		 * truncated in parallel which is almost certainly an
-		 * application bug. In such a case, just retry.
-		 *
-		 * We are not calling into get_futex_key_refs() in file-backed
-		 * cases, therefore a successful atomic_inc return below will
-		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
-		 */
-		if (!atomic_inc_not_zero(&inode->i_count)) {
-			rcu_read_unlock();
-			put_page(page);
-
-			goto again;
-		}
-
-		/* Should be impossible but lets be paranoid for now */
-		if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
-			err = -EFAULT;
-			rcu_read_unlock();
-			iput(inode);
-
-			goto out;
-		}
-
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
-		key->shared.inode = inode;
+		key->shared.i_seq = get_inode_sequence_number(inode);
 		key->shared.pgoff = basepage_index(tail);
 		rcu_read_unlock();
 	}
 
+	get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
 out:
 	put_page(page);
 	return err;

kernel/pid.c

@@ -247,6 +247,16 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 		tmp = tmp->parent;
 	}
 
+	/*
+	 * ENOMEM is not the most obvious choice especially for the case
+	 * where the child subreaper has already exited and the pid
+	 * namespace denies the creation of any new processes. But ENOMEM
+	 * is what we have exposed to userspace for a long time and it is
+	 * documented behavior for pid namespaces. So we can't easily
+	 * change it even if there were an error code better suited.
+	 */
+	retval = -ENOMEM;
+
 	if (unlikely(is_child_reaper(pid))) {
 		if (pid_ns_prepare_proc(ns))
 			goto out_free;

kernel/sys.c

@@ -47,6 +47,7 @@
 #include <linux/syscalls.h>
 #include <linux/kprobes.h>
 #include <linux/user_namespace.h>
+#include <linux/time_namespace.h>
 #include <linux/binfmts.h>
 
 #include <linux/sched.h>
@@ -2546,6 +2547,7 @@ static int do_sysinfo(struct sysinfo *info)
 	memset(info, 0, sizeof(struct sysinfo));
 
 	ktime_get_boottime_ts64(&tp);
+	timens_add_boottime(&tp);
 	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
 	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);

kernel/trace/blktrace.c

@@ -1896,8 +1896,11 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 	ret = 0;
-	if (bt == NULL)
+	if (bt == NULL) {
 		ret = blk_trace_setup_queue(q, bdev);
+		bt = rcu_dereference_protected(q->blk_trace,
+				lockdep_is_held(&q->blk_trace_mutex));
+	}
 
 	if (ret == 0) {
 		if (attr == &dev_attr_act_mask)

kernel/trace/ftrace.c

@@ -1547,6 +1547,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end)
 		rec = bsearch(&key, pg->records, pg->index,
 			      sizeof(struct dyn_ftrace),
 			      ftrace_cmp_recs);
+		if (rec)
+			break;
 	}
 	return rec;
 }

kernel/workqueue.c

@@ -1411,14 +1411,16 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 		return;
 	rcu_read_lock();
 retry:
-	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
-
 	/* pwq which will be used unless @work is executing elsewhere */
-	if (!(wq->flags & WQ_UNBOUND))
-		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
-	else
+	if (wq->flags & WQ_UNBOUND) {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 		pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
+	} else {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = raw_smp_processor_id();
+		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
+	}
 
 	/*
 	 * If @work was previously on a different pool, it might still be