Merge branch 'for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:

 - make kworkers report the workqueue it is executing or has executed
   most recently in /proc/PID/comm (so they show up in ps/top)

 - CONFIG_SMP shuffle to move stuff which isn't necessary for UP builds
   inside CONFIG_SMP.

* 'for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: move function definitions within CONFIG_SMP block
  workqueue: Make sure struct worker is accessible for wq_worker_comm()
  workqueue: Show the latest workqueue name in /proc/PID/{comm,stat,status}
  proc: Consolidate task->comm formatting into proc_task_name()
  workqueue: Set worker->desc to workqueue name by default
  workqueue: Make worker_attach/detach_pool() update worker->pool
  workqueue: Replace pool->attach_mutex with global wq_pool_attach_mutex

fs/proc/array.c

@@ -96,22 +96,29 @@
 #include <asm/processor.h>
 #include "internal.h"
 
-static inline void task_name(struct seq_file *m, struct task_struct *p)
+void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape)
 {
 	char *buf;
 	size_t size;
-	char tcomm[sizeof(p->comm)];
+	char tcomm[64];
 	int ret;
 
-	get_task_comm(tcomm, p);
+	if (p->flags & PF_WQ_WORKER)
-
+		wq_worker_comm(tcomm, sizeof(tcomm), p);
-	seq_puts(m, "Name:\t");
+	else
+		__get_task_comm(tcomm, sizeof(tcomm), p);
 
 	size = seq_get_buf(m, &buf);
-	ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+	if (escape) {
-	seq_commit(m, ret < size ? ret : -1);
+		ret = string_escape_str(tcomm, buf, size,
+					ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+		if (ret >= size)
+			ret = -1;
+	} else {
+		ret = strscpy(buf, tcomm, size);
+	}
 
-	seq_putc(m, '\n');
+	seq_commit(m, ret);
 }
 
 /*
@@ -390,7 +397,10 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 {
 	struct mm_struct *mm = get_task_mm(task);
 
-	task_name(m, task);
+	seq_puts(m, "Name:\t");
+	proc_task_name(m, task, true);
+	seq_putc(m, '\n');
+
 	task_state(m, ns, pid, task);
 
 	if (mm) {
@@ -425,7 +435,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	u64 cutime, cstime, utime, stime;
 	u64 cgtime, gtime;
 	unsigned long rsslim = 0;
-	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
 
 	state = *get_task_state(task);
@@ -452,8 +461,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		}
 	}
 
-	get_task_comm(tcomm, task);
-
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
 	cutime = cstime = utime = stime = 0;
@@ -520,7 +527,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns));
 	seq_puts(m, " (");
-	seq_puts(m, tcomm);
+	proc_task_name(m, task, false);
 	seq_puts(m, ") ");
 	seq_putc(m, state);
 	seq_put_decimal_ll(m, " ", ppid);

fs/proc/base.c

@@ -1563,9 +1563,8 @@ static int comm_show(struct seq_file *m, void *v)
 	if (!p)
 		return -ESRCH;
 
-	task_lock(p);
+	proc_task_name(m, p, false);
-	seq_printf(m, "%s\n", p->comm);
+	seq_putc(m, '\n');
-	task_unlock(p);
 
 	put_task_struct(p);
 

fs/proc/internal.h

@@ -136,6 +136,8 @@ unsigned name_to_int(const struct qstr *qstr);
  */
 extern const struct file_operations proc_tid_children_operations;
 
+extern void proc_task_name(struct seq_file *m, struct task_struct *p,
+			   bool escape);
 extern int proc_tid_stat(struct seq_file *, struct pid_namespace *,
 			 struct pid *, struct task_struct *);
 extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *,

include/linux/workqueue.h

@@ -494,6 +494,7 @@ extern unsigned int work_busy(struct work_struct *work);
 extern __printf(1, 2) void set_worker_desc(const char *fmt, ...);
 extern void print_worker_info(const char *log_lvl, struct task_struct *task);
 extern void show_workqueue_state(void);
+extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);
 
 /**
  * queue_work - queue work on a workqueue

kernel/workqueue.c

@@ -66,7 +66,7 @@ enum {
 	 * be executing on any CPU.  The pool behaves as an unbound one.
 	 *
 	 * Note that DISASSOCIATED should be flipped only while holding
-	 * attach_mutex to avoid changing binding state while
+	 * wq_pool_attach_mutex to avoid changing binding state while
 	 * worker_attach_to_pool() is in progress.
 	 */
 	POOL_MANAGER_ACTIVE	= 1 << 0,	/* being managed */
@@ -123,7 +123,7 @@ enum {
  *    cpu or grabbing pool->lock is enough for read access.  If
  *    POOL_DISASSOCIATED is set, it's identical to L.
  *
- * A: pool->attach_mutex protected.
+ * A: wq_pool_attach_mutex protected.
  *
  * PL: wq_pool_mutex protected.
  *
@@ -166,7 +166,6 @@ struct worker_pool {
 						/* L: hash of busy workers */
 
 	struct worker		*manager;	/* L: purely informational */
-	struct mutex		attach_mutex;	/* attach/detach exclusion */
 	struct list_head	workers;	/* A: attached workers */
 	struct completion	*detach_completion; /* all workers detached */
 
@@ -297,6 +296,7 @@ static bool wq_numa_enabled;		/* unbound NUMA affinity enabled */
 static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
 
 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
+static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */
 static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
 static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
 
@@ -399,14 +399,14 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
  * @worker: iteration cursor
  * @pool: worker_pool to iterate workers of
  *
- * This must be called with @pool->attach_mutex.
+ * This must be called with wq_pool_attach_mutex.
  *
  * The if/else clause exists only for the lockdep assertion and can be
  * ignored.
  */
 #define for_each_pool_worker(worker, pool)				\
 	list_for_each_entry((worker), &(pool)->workers, node)		\
-		if (({ lockdep_assert_held(&pool->attach_mutex); false; })) { } \
+		if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \
 		else
 
 /**
@@ -1724,7 +1724,7 @@ static struct worker *alloc_worker(int node)
 static void worker_attach_to_pool(struct worker *worker,
 				   struct worker_pool *pool)
 {
-	mutex_lock(&pool->attach_mutex);
+	mutex_lock(&wq_pool_attach_mutex);
 
 	/*
 	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
@@ -1733,37 +1733,40 @@ static void worker_attach_to_pool(struct worker *worker,
 	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
 
 	/*
-	 * The pool->attach_mutex ensures %POOL_DISASSOCIATED remains
+	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
-	 * stable across this function.  See the comments above the
+	 * stable across this function.  See the comments above the flag
-	 * flag definition for details.
+	 * definition for details.
 	 */
 	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
 
 	list_add_tail(&worker->node, &pool->workers);
+	worker->pool = pool;
 
-	mutex_unlock(&pool->attach_mutex);
+	mutex_unlock(&wq_pool_attach_mutex);
 }
 
 /**
  * worker_detach_from_pool() - detach a worker from its pool
  * @worker: worker which is attached to its pool
- * @pool: the pool @worker is attached to
  *
  * Undo the attaching which had been done in worker_attach_to_pool().  The
  * caller worker shouldn't access to the pool after detached except it has
  * other reference to the pool.
  */
-static void worker_detach_from_pool(struct worker *worker,
+static void worker_detach_from_pool(struct worker *worker)
-				    struct worker_pool *pool)
 {
+	struct worker_pool *pool = worker->pool;
 	struct completion *detach_completion = NULL;
 
-	mutex_lock(&pool->attach_mutex);
+	mutex_lock(&wq_pool_attach_mutex);
+
 	list_del(&worker->node);
+	worker->pool = NULL;
+
 	if (list_empty(&pool->workers))
 		detach_completion = pool->detach_completion;
-	mutex_unlock(&pool->attach_mutex);
+	mutex_unlock(&wq_pool_attach_mutex);
 
 	/* clear leftover flags without pool->lock after it is detached */
 	worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND);
@@ -1799,7 +1802,6 @@ static struct worker *create_worker(struct worker_pool *pool)
 	if (!worker)
 		goto fail;
 
-	worker->pool = pool;
 	worker->id = id;
 
 	if (pool->cpu >= 0)
@@ -2086,6 +2088,12 @@ __acquires(&pool->lock)
 	worker->current_pwq = pwq;
 	work_color = get_work_color(work);
 
+	/*
+	 * Record wq name for cmdline and debug reporting, may get
+	 * overridden through set_worker_desc().
+	 */
+	strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN);
+
 	list_del_init(&work->entry);
 
 	/*
@@ -2181,7 +2189,6 @@ __acquires(&pool->lock)
 	worker->current_work = NULL;
 	worker->current_func = NULL;
 	worker->current_pwq = NULL;
-	worker->desc_valid = false;
 	pwq_dec_nr_in_flight(pwq, work_color);
 }
 
@@ -2206,6 +2213,16 @@ static void process_scheduled_works(struct worker *worker)
 	}
 }
 
+static void set_pf_worker(bool val)
+{
+	mutex_lock(&wq_pool_attach_mutex);
+	if (val)
+		current->flags |= PF_WQ_WORKER;
+	else
+		current->flags &= ~PF_WQ_WORKER;
+	mutex_unlock(&wq_pool_attach_mutex);
+}
+
 /**
  * worker_thread - the worker thread function
  * @__worker: self
@@ -2224,7 +2241,7 @@ static int worker_thread(void *__worker)
 	struct worker_pool *pool = worker->pool;
 
 	/* tell the scheduler that this is a workqueue worker */
-	worker->task->flags |= PF_WQ_WORKER;
+	set_pf_worker(true);
 woke_up:
 	spin_lock_irq(&pool->lock);
 
@@ -2232,11 +2249,11 @@ woke_up:
 	if (unlikely(worker->flags & WORKER_DIE)) {
 		spin_unlock_irq(&pool->lock);
 		WARN_ON_ONCE(!list_empty(&worker->entry));
-		worker->task->flags &= ~PF_WQ_WORKER;
+		set_pf_worker(false);
 
 		set_task_comm(worker->task, "kworker/dying");
 		ida_simple_remove(&pool->worker_ida, worker->id);
-		worker_detach_from_pool(worker, pool);
+		worker_detach_from_pool(worker);
 		kfree(worker);
 		return 0;
 	}
@@ -2335,7 +2352,7 @@ static int rescuer_thread(void *__rescuer)
 	 * Mark rescuer as worker too.  As WORKER_PREP is never cleared, it
 	 * doesn't participate in concurrency management.
 	 */
-	rescuer->task->flags |= PF_WQ_WORKER;
+	set_pf_worker(true);
 repeat:
 	set_current_state(TASK_IDLE);
 
@@ -2367,7 +2384,6 @@ repeat:
 		worker_attach_to_pool(rescuer, pool);
 
 		spin_lock_irq(&pool->lock);
-		rescuer->pool = pool;
 
 		/*
 		 * Slurp in all works issued via this workqueue and
@@ -2417,10 +2433,9 @@ repeat:
 		if (need_more_worker(pool))
 			wake_up_worker(pool);
 
-		rescuer->pool = NULL;
 		spin_unlock_irq(&pool->lock);
 
-		worker_detach_from_pool(rescuer, pool);
+		worker_detach_from_pool(rescuer);
 
 		spin_lock_irq(&wq_mayday_lock);
 	}
@@ -2429,7 +2444,7 @@ repeat:
 
 	if (should_stop) {
 		__set_current_state(TASK_RUNNING);
-		rescuer->task->flags &= ~PF_WQ_WORKER;
+		set_pf_worker(false);
 		return 0;
 	}
 
@@ -3271,7 +3286,6 @@ static int init_worker_pool(struct worker_pool *pool)
 
 	timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0);
 
-	mutex_init(&pool->attach_mutex);
 	INIT_LIST_HEAD(&pool->workers);
 
 	ida_init(&pool->worker_ida);
@@ -3354,10 +3368,10 @@ static void put_unbound_pool(struct worker_pool *pool)
 	WARN_ON(pool->nr_workers || pool->nr_idle);
 	spin_unlock_irq(&pool->lock);
 
-	mutex_lock(&pool->attach_mutex);
+	mutex_lock(&wq_pool_attach_mutex);
 	if (!list_empty(&pool->workers))
 		pool->detach_completion = &detach_completion;
-	mutex_unlock(&pool->attach_mutex);
+	mutex_unlock(&wq_pool_attach_mutex);
 
 	if (pool->detach_completion)
 		wait_for_completion(pool->detach_completion);
@@ -4347,7 +4361,6 @@ void set_worker_desc(const char *fmt, ...)
 		va_start(args, fmt);
 		vsnprintf(worker->desc, sizeof(worker->desc), fmt, args);
 		va_end(args);
-		worker->desc_valid = true;
 	}
 }
 
@@ -4371,7 +4384,6 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
 	char desc[WORKER_DESC_LEN] = { };
 	struct pool_workqueue *pwq = NULL;
 	struct workqueue_struct *wq = NULL;
-	bool desc_valid = false;
 	struct worker *worker;
 
 	if (!(task->flags & PF_WQ_WORKER))
@@ -4384,22 +4396,18 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
 	worker = kthread_probe_data(task);
 
 	/*
-	 * Carefully copy the associated workqueue's workfn and name.  Keep
+	 * Carefully copy the associated workqueue's workfn, name and desc.
-	 * the original last '\0' in case the original contains garbage.
+	 * Keep the original last '\0' in case the original is garbage.
 	 */
 	probe_kernel_read(&fn, &worker->current_func, sizeof(fn));
 	probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq));
 	probe_kernel_read(&wq, &pwq->wq, sizeof(wq));
 	probe_kernel_read(name, wq->name, sizeof(name) - 1);
-
+	probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
-	/* copy worker description */
-	probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid));
-	if (desc_valid)
-		probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
 
 	if (fn || name[0] || desc[0]) {
 		printk("%sWorkqueue: %s %pf", log_lvl, name, fn);
-		if (desc[0])
+		if (strcmp(name, desc))
 			pr_cont(" (%s)", desc);
 		pr_cont("\n");
 	}
@@ -4579,6 +4587,47 @@ void show_workqueue_state(void)
 	rcu_read_unlock_sched();
 }
 
+/* used to show worker information through /proc/PID/{comm,stat,status} */
+void wq_worker_comm(char *buf, size_t size, struct task_struct *task)
+{
+	int off;
+
+	/* always show the actual comm */
+	off = strscpy(buf, task->comm, size);
+	if (off < 0)
+		return;
+
+	/* stabilize PF_WQ_WORKER and worker pool association */
+	mutex_lock(&wq_pool_attach_mutex);
+
+	if (task->flags & PF_WQ_WORKER) {
+		struct worker *worker = kthread_data(task);
+		struct worker_pool *pool = worker->pool;
+
+		if (pool) {
+			spin_lock_irq(&pool->lock);
+			/*
+			 * ->desc tracks information (wq name or
+			 * set_worker_desc()) for the latest execution.  If
+			 * current, prepend '+', otherwise '-'.
+			 */
+			if (worker->desc[0] != '\0') {
+				if (worker->current_work)
+					scnprintf(buf + off, size - off, "+%s",
+						  worker->desc);
+				else
+					scnprintf(buf + off, size - off, "-%s",
+						  worker->desc);
+			}
+			spin_unlock_irq(&pool->lock);
+		}
+	}
+
+	mutex_unlock(&wq_pool_attach_mutex);
+}
+
+#ifdef CONFIG_SMP
+
 /*
  * CPU hotplug.
  *
@@ -4600,7 +4649,7 @@ static void unbind_workers(int cpu)
 	struct worker *worker;
 
 	for_each_cpu_worker_pool(pool, cpu) {
-		mutex_lock(&pool->attach_mutex);
+		mutex_lock(&wq_pool_attach_mutex);
 		spin_lock_irq(&pool->lock);
 
 		/*
@@ -4616,7 +4665,7 @@ static void unbind_workers(int cpu)
 		pool->flags |= POOL_DISASSOCIATED;
 
 		spin_unlock_irq(&pool->lock);
-		mutex_unlock(&pool->attach_mutex);
+		mutex_unlock(&wq_pool_attach_mutex);
 
 		/*
 		 * Call schedule() so that we cross rq->lock and thus can
@@ -4657,7 +4706,7 @@ static void rebind_workers(struct worker_pool *pool)
 {
 	struct worker *worker;
 
-	lockdep_assert_held(&pool->attach_mutex);
+	lockdep_assert_held(&wq_pool_attach_mutex);
 
 	/*
 	 * Restore CPU affinity of all workers.  As all idle workers should
@@ -4727,7 +4776,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
 	static cpumask_t cpumask;
 	struct worker *worker;
 
-	lockdep_assert_held(&pool->attach_mutex);
+	lockdep_assert_held(&wq_pool_attach_mutex);
 
 	/* is @cpu allowed for @pool? */
 	if (!cpumask_test_cpu(cpu, pool->attrs->cpumask))
@@ -4762,14 +4811,14 @@ int workqueue_online_cpu(unsigned int cpu)
 	mutex_lock(&wq_pool_mutex);
 
 	for_each_pool(pool, pi) {
-		mutex_lock(&pool->attach_mutex);
+		mutex_lock(&wq_pool_attach_mutex);
 
 		if (pool->cpu == cpu)
 			rebind_workers(pool);
 		else if (pool->cpu < 0)
 			restore_unbound_workers_cpumask(pool, cpu);
 
-		mutex_unlock(&pool->attach_mutex);
+		mutex_unlock(&wq_pool_attach_mutex);
 	}
 
 	/* update NUMA affinity of unbound workqueues */
@@ -4799,8 +4848,6 @@ int workqueue_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-
 struct work_for_cpu {
 	struct work_struct work;
 	long (*fn)(void *);

kernel/workqueue_internal.h

@@ -31,13 +31,12 @@ struct worker {
 	struct work_struct	*current_work;	/* L: work being processed */
 	work_func_t		current_func;	/* L: current_work's fn */
 	struct pool_workqueue	*current_pwq; /* L: current_work's pwq */
-	bool			desc_valid;	/* ->desc is valid */
 	struct list_head	scheduled;	/* L: scheduled works */
 
 	/* 64 bytes boundary on 64bit, 32 on 32bit */
 
 	struct task_struct	*task;		/* I: worker task */
-	struct worker_pool	*pool;		/* I: the associated pool */
+	struct worker_pool	*pool;		/* A: the associated pool */
 						/* L: for rescuers */
 	struct list_head	node;		/* A: anchored at pool->workers */
 						/* A: runs through worker->node */