Linux 3.4.60

commit 3bc38cbceb upstream.

If there are UNUSABLE regions in the machine memory map, dom0 will
attempt to map them 1:1 which is not permitted by Xen and the kernel
will crash.

There isn't anything interesting in the UNUSABLE region that the dom0
kernel needs access to so we can avoid making the 1:1 mapping and
treat it as RAM.

We only do this for dom0, as that is where tboot case shows up.
A PV domU could have an UNUSABLE region in its pseudo-physical map
and would need to be handled in another patch.

This fixes a boot failure on hosts with tboot.

tboot marks a region in the e820 map as unusable and the dom0 kernel
would attempt to map this region and Xen does not permit unusable
regions to be mapped by guests.

  (XEN)  0000000000000000 - 0000000000060000 (usable)
  (XEN)  0000000000060000 - 0000000000068000 (reserved)
  (XEN)  0000000000068000 - 000000000009e000 (usable)
  (XEN)  0000000000100000 - 0000000000800000 (usable)
  (XEN)  0000000000800000 - 0000000000972000 (unusable)

tboot marked this region as unusable.

  (XEN)  0000000000972000 - 00000000cf200000 (usable)
  (XEN)  00000000cf200000 - 00000000cf38f000 (reserved)
  (XEN)  00000000cf38f000 - 00000000cf3ce000 (ACPI data)
  (XEN)  00000000cf3ce000 - 00000000d0000000 (reserved)
  (XEN)  00000000e0000000 - 00000000f0000000 (reserved)
  (XEN)  00000000fe000000 - 0000000100000000 (reserved)
  (XEN)  0000000100000000 - 0000000630000000 (usable)

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
[v1: Altered the patch and description with domU's with UNUSABLE regions]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 59
+SUBLEVEL = 60
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

arch/x86/xen/setup.c

@@ -213,6 +213,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
 	e820_add_region(start, end - start, type);
 }
 
+void xen_ignore_unusable(struct e820entry *list, size_t map_size)
+{
+	struct e820entry *entry;
+	unsigned int i;
+
+	for (i = 0, entry = list; i < map_size; i++, entry++) {
+		if (entry->type == E820_UNUSABLE)
+			entry->type = E820_RAM;
+	}
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
@@ -251,6 +262,17 @@ char * __init xen_memory_setup(void)
 	}
 	BUG_ON(rc);
 
+	/*
+	 * Xen won't allow a 1:1 mapping to be created to UNUSABLE
+	 * regions, so if we're using the machine memory map leave the
+	 * region as RAM as it is in the pseudo-physical map.
+	 *
+	 * UNUSABLE regions in domUs are not handled and will need
+	 * a patch in the future.
+	 */
+	if (xen_initial_domain())
+		xen_ignore_unusable(map, memmap.nr_entries);
+
 	/* Make sure the Xen-supplied memory map is well-ordered. */
 	sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
 

drivers/ata/libata-pmp.c

@@ -289,24 +289,24 @@ static int sata_pmp_configure(struct ata_device *dev, int print_info)
 
 	/* Disable sending Early R_OK.
 	 * With "cached read" HDD testing and multiple ports busy on a SATA
-	 * host controller, 3726 PMP will very rarely drop a deferred
+	 * host controller, 3x26 PMP will very rarely drop a deferred
 	 * R_OK that was intended for the host. Symptom will be all
 	 * 5 drives under test will timeout, get reset, and recover.
 	 */
-	if (vendor == 0x1095 && devid == 0x3726) {
+	if (vendor == 0x1095 && (devid == 0x3726 || devid == 0x3826)) {
 		u32 reg;
 
 		err_mask = sata_pmp_read(&ap->link, PMP_GSCR_SII_POL, &reg);
 		if (err_mask) {
 			rc = -EIO;
-			reason = "failed to read Sil3726 Private Register";
+			reason = "failed to read Sil3x26 Private Register";
 			goto fail;
 		}
 		reg &= ~0x1;
 		err_mask = sata_pmp_write(&ap->link, PMP_GSCR_SII_POL, reg);
 		if (err_mask) {
 			rc = -EIO;
-			reason = "failed to write Sil3726 Private Register";
+			reason = "failed to write Sil3x26 Private Register";
 			goto fail;
 		}
 	}
@@ -383,8 +383,8 @@ static void sata_pmp_quirks(struct ata_port *ap)
 	u16 devid = sata_pmp_gscr_devid(gscr);
 	struct ata_link *link;
 
-	if (vendor == 0x1095 && devid == 0x3726) {
-		/* sil3726 quirks */
+	if (vendor == 0x1095 && (devid == 0x3726 || devid == 0x3826)) {
+		/* sil3x26 quirks */
 		ata_for_each_link(link, ap, EDGE) {
 			/* link reports offline after LPM */
 			link->flags |= ATA_LFLAG_NO_LPM;

drivers/gpu/drm/i915/i915_reg.h

@@ -502,6 +502,8 @@
 					will not assert AGPBUSY# and will only
 					be delivered when out of C3. */
 #define   INSTPM_FORCE_ORDERING				(1<<7) /* GEN6+ */
+#define   INSTPM_TLB_INVALIDATE	(1<<9)
+#define   INSTPM_SYNC_FLUSH	(1<<5)
 #define ACTHD	        0x020c8
 #define FW_BLC		0x020d8
 #define FW_BLC2		0x020dc

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -767,6 +767,18 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 
 	I915_WRITE(mmio, (u32)ring->status_page.gfx_addr);
 	POSTING_READ(mmio);
+
+	/* Flush the TLB for this page */
+	if (INTEL_INFO(dev)->gen >= 6) {
+		u32 reg = RING_INSTPM(ring->mmio_base);
+		I915_WRITE(reg,
+			   _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
+					      INSTPM_SYNC_FLUSH));
+		if (wait_for((I915_READ(reg) & INSTPM_SYNC_FLUSH) == 0,
+			     1000))
+			DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
+				  ring->name);
+	}
 }
 
 static int

drivers/net/wireless/hostap/hostap_ioctl.c

@@ -522,9 +522,9 @@ static int prism2_ioctl_giwaplist(struct net_device *dev,
 
 	data->length = prism2_ap_get_sta_qual(local, addr, qual, IW_MAX_AP, 1);
 
-	memcpy(extra, &addr, sizeof(struct sockaddr) * data->length);
+	memcpy(extra, addr, sizeof(struct sockaddr) * data->length);
 	data->flags = 1; /* has quality information */
-	memcpy(extra + sizeof(struct sockaddr) * data->length, &qual,
+	memcpy(extra + sizeof(struct sockaddr) * data->length, qual,
 	       sizeof(struct iw_quality) * data->length);
 
 	kfree(addr);

drivers/net/wireless/zd1201.c

@@ -98,10 +98,12 @@ static int zd1201_fw_upload(struct usb_device *dev, int apfw)
 		goto exit;
 
 	err = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), 0x4,
-	    USB_DIR_IN | 0x40, 0,0, &ret, sizeof(ret), ZD1201_FW_TIMEOUT);
+	    USB_DIR_IN | 0x40, 0, 0, buf, sizeof(ret), ZD1201_FW_TIMEOUT);
 	if (err < 0)
 		goto exit;
 
+	memcpy(&ret, buf, sizeof(ret));
+
 	if (ret & 0x80) {
 		err = -EIO;
 		goto exit;

drivers/of/fdt.c

@@ -390,6 +390,8 @@ static void __unflatten_device_tree(struct boot_param_header *blob,
 	mem = (unsigned long)
 		dt_alloc(size + 4, __alignof__(struct device_node));
 
+	memset((void *)mem, 0, size);
+
 	((__be32 *)mem)[size / 4] = cpu_to_be32(0xdeadbeef);
 
 	pr_debug("  unflattening %lx...\n", mem);

drivers/s390/scsi/zfcp_erp.c

@@ -102,10 +102,13 @@ static void zfcp_erp_action_dismiss_port(struct zfcp_port *port)
 
 	if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_INUSE)
 		zfcp_erp_action_dismiss(&port->erp_action);
-	else
-		shost_for_each_device(sdev, port->adapter->scsi_host)
+	else {
+		spin_lock(port->adapter->scsi_host->host_lock);
+		__shost_for_each_device(sdev, port->adapter->scsi_host)
 			if (sdev_to_zfcp(sdev)->port == port)
 				zfcp_erp_action_dismiss_lun(sdev);
+		spin_unlock(port->adapter->scsi_host->host_lock);
+	}
 }
 
 static void zfcp_erp_action_dismiss_adapter(struct zfcp_adapter *adapter)
@@ -592,9 +595,11 @@ static void _zfcp_erp_lun_reopen_all(struct zfcp_port *port, int clear,
 {
 	struct scsi_device *sdev;
 
-	shost_for_each_device(sdev, port->adapter->scsi_host)
+	spin_lock(port->adapter->scsi_host->host_lock);
+	__shost_for_each_device(sdev, port->adapter->scsi_host)
 		if (sdev_to_zfcp(sdev)->port == port)
 			_zfcp_erp_lun_reopen(sdev, clear, id, 0);
+	spin_unlock(port->adapter->scsi_host->host_lock);
 }
 
 static void zfcp_erp_strategy_followup_failed(struct zfcp_erp_action *act)
@@ -1435,8 +1440,10 @@ void zfcp_erp_set_adapter_status(struct zfcp_adapter *adapter, u32 mask)
 		atomic_set_mask(common_mask, &port->status);
 	read_unlock_irqrestore(&adapter->port_list_lock, flags);
 
-	shost_for_each_device(sdev, adapter->scsi_host)
+	spin_lock_irqsave(adapter->scsi_host->host_lock, flags);
+	__shost_for_each_device(sdev, adapter->scsi_host)
 		atomic_set_mask(common_mask, &sdev_to_zfcp(sdev)->status);
+	spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags);
 }
 
 /**
@@ -1470,11 +1477,13 @@ void zfcp_erp_clear_adapter_status(struct zfcp_adapter *adapter, u32 mask)
 	}
 	read_unlock_irqrestore(&adapter->port_list_lock, flags);
 
-	shost_for_each_device(sdev, adapter->scsi_host) {
+	spin_lock_irqsave(adapter->scsi_host->host_lock, flags);
+	__shost_for_each_device(sdev, adapter->scsi_host) {
 		atomic_clear_mask(common_mask, &sdev_to_zfcp(sdev)->status);
 		if (clear_counter)
 			atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0);
 	}
+	spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags);
 }
 
 /**
@@ -1488,16 +1497,19 @@ void zfcp_erp_set_port_status(struct zfcp_port *port, u32 mask)
 {
 	struct scsi_device *sdev;
 	u32 common_mask = mask & ZFCP_COMMON_FLAGS;
+	unsigned long flags;
 
 	atomic_set_mask(mask, &port->status);
 
 	if (!common_mask)
 		return;
 
-	shost_for_each_device(sdev, port->adapter->scsi_host)
+	spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags);
+	__shost_for_each_device(sdev, port->adapter->scsi_host)
 		if (sdev_to_zfcp(sdev)->port == port)
 			atomic_set_mask(common_mask,
 					&sdev_to_zfcp(sdev)->status);
+	spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags);
 }
 
 /**
@@ -1512,6 +1524,7 @@ void zfcp_erp_clear_port_status(struct zfcp_port *port, u32 mask)
 	struct scsi_device *sdev;
 	u32 common_mask = mask & ZFCP_COMMON_FLAGS;
 	u32 clear_counter = mask & ZFCP_STATUS_COMMON_ERP_FAILED;
+	unsigned long flags;
 
 	atomic_clear_mask(mask, &port->status);
 
@@ -1521,13 +1534,15 @@ void zfcp_erp_clear_port_status(struct zfcp_port *port, u32 mask)
 	if (clear_counter)
 		atomic_set(&port->erp_counter, 0);
 
-	shost_for_each_device(sdev, port->adapter->scsi_host)
+	spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags);
+	__shost_for_each_device(sdev, port->adapter->scsi_host)
 		if (sdev_to_zfcp(sdev)->port == port) {
 			atomic_clear_mask(common_mask,
 					  &sdev_to_zfcp(sdev)->status);
 			if (clear_counter)
 				atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0);
 		}
+	spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags);
 }
 
 /**

drivers/s390/scsi/zfcp_qdio.c

@@ -224,11 +224,9 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req,
 
 static int zfcp_qdio_sbal_check(struct zfcp_qdio *qdio)
 {
-	spin_lock_irq(&qdio->req_q_lock);
 	if (atomic_read(&qdio->req_q_free) ||
 	    !(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP))
 		return 1;
-	spin_unlock_irq(&qdio->req_q_lock);
 	return 0;
 }
 
@@ -246,9 +244,8 @@ int zfcp_qdio_sbal_get(struct zfcp_qdio *qdio)
 {
 	long ret;
 
-	spin_unlock_irq(&qdio->req_q_lock);
-	ret = wait_event_interruptible_timeout(qdio->req_q_wq,
-			       zfcp_qdio_sbal_check(qdio), 5 * HZ);
+	ret = wait_event_interruptible_lock_irq_timeout(qdio->req_q_wq,
+		       zfcp_qdio_sbal_check(qdio), qdio->req_q_lock, 5 * HZ);
 
 	if (!(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP))
 		return -EIO;
@@ -262,7 +259,6 @@ int zfcp_qdio_sbal_get(struct zfcp_qdio *qdio)
 		zfcp_erp_adapter_reopen(qdio->adapter, 0, "qdsbg_1");
 	}
 
-	spin_lock_irq(&qdio->req_q_lock);
 	return -EIO;
 }
 

drivers/xen/events.c

@@ -324,7 +324,7 @@ static void init_evtchn_cpu_bindings(void)
 
 	for_each_possible_cpu(i)
 		memset(per_cpu(cpu_evtchn_mask, i),
-		       (i == 0) ? ~0 : 0, sizeof(*per_cpu(cpu_evtchn_mask, i)));
+		       (i == 0) ? ~0 : 0, NR_EVENT_CHANNELS/8);
 }
 
 static inline void clear_evtchn(int port)

fs/nilfs2/segbuf.c

@@ -345,8 +345,7 @@ static void nilfs_end_bio_write(struct bio *bio, int err)
 
 	if (err == -EOPNOTSUPP) {
 		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		bio_put(bio);
-		/* to be detected by submit_seg_bio() */
+		/* to be detected by nilfs_segbuf_submit_bio() */
 	}
 
 	if (!uptodate)
@@ -377,12 +376,12 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
 	bio->bi_private = segbuf;
 	bio_get(bio);
 	submit_bio(mode, bio);
+	segbuf->sb_nbio++;
 	if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
 		bio_put(bio);
 		err = -EOPNOTSUPP;
 		goto failed;
 	}
-	segbuf->sb_nbio++;
 	bio_put(bio);
 
 	wi->bio = NULL;

include/linux/wait.h

@@ -530,6 +530,63 @@ do {									\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1))
 
 
+#define __wait_event_interruptible_lock_irq_timeout(wq, condition,	\
+						    lock, ret)		\
+do {									\
+	DEFINE_WAIT(__wait);						\
+									\
+	for (;;) {							\
+		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			break;						\
+		}							\
+		spin_unlock_irq(&lock);					\
+		ret = schedule_timeout(ret);				\
+		spin_lock_irq(&lock);					\
+		if (!ret)						\
+			break;						\
+	}								\
+	finish_wait(&wq, &__wait);					\
+} while (0)
+
+/**
+ * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets true or a timeout elapses.
+ *		The condition is checked under the lock. This is expected
+ *		to be called with the lock taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before schedule()
+ *	  and reacquired afterwards.
+ * @timeout: timeout, in jiffies
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true or signal is received. The @condition is
+ * checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before going to sleep and is reacquired afterwards.
+ *
+ * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it
+ * was interrupted by a signal, and the remaining jiffies otherwise
+ * if the condition evaluated to true before the timeout elapsed.
+ */
+#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock,	\
+						  timeout)		\
+({									\
+	int __ret = timeout;						\
+									\
+	if (!(condition))						\
+		__wait_event_interruptible_lock_irq_timeout(		\
+					wq, condition, lock, __ret);	\
+	__ret;								\
+})
+
 
 #define __wait_event_killable(wq, condition, ret)			\
 do {									\

kernel/workqueue.c

@@ -128,6 +128,7 @@ struct worker {
 	};
 
 	struct work_struct	*current_work;	/* L: work being processed */
+	work_func_t		current_func;	/* L: current_work's fn */
 	struct cpu_workqueue_struct *current_cwq; /* L: current_work's cwq */
 	struct list_head	scheduled;	/* L: scheduled works */
 	struct task_struct	*task;		/* I: worker task */
@@ -838,7 +839,8 @@ static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
 	struct hlist_node *tmp;
 
 	hlist_for_each_entry(worker, tmp, bwh, hentry)
-		if (worker->current_work == work)
+		if (worker->current_work == work &&
+		    worker->current_func == work->func)
 			return worker;
 	return NULL;
 }
@@ -848,9 +850,27 @@ static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
  * @gcwq: gcwq of interest
  * @work: work to find worker for
  *
- * Find a worker which is executing @work on @gcwq.  This function is
- * identical to __find_worker_executing_work() except that this
- * function calculates @bwh itself.
+ * Find a worker which is executing @work on @gcwq by searching
+ * @gcwq->busy_hash which is keyed by the address of @work.  For a worker
+ * to match, its current execution should match the address of @work and
+ * its work function.  This is to avoid unwanted dependency between
+ * unrelated work executions through a work item being recycled while still
+ * being executed.
+ *
+ * This is a bit tricky.  A work item may be freed once its execution
+ * starts and nothing prevents the freed area from being recycled for
+ * another work item.  If the same work item address ends up being reused
+ * before the original execution finishes, workqueue will identify the
+ * recycled work item as currently executing and make it wait until the
+ * current execution finishes, introducing an unwanted dependency.
+ *
+ * This function checks the work item address, work function and workqueue
+ * to avoid false positives.  Note that this isn't complete as one may
+ * construct a work function which can introduce dependency onto itself
+ * through a recycled work item.  Well, if somebody wants to shoot oneself
+ * in the foot that badly, there's only so much we can do, and if such
+ * deadlock actually occurs, it should be easy to locate the culprit work
+ * function.
  *
  * CONTEXT:
  * spin_lock_irq(gcwq->lock).
@@ -1721,10 +1741,9 @@ static void move_linked_works(struct work_struct *work, struct list_head *head,
 		*nextp = n;
 }
 
-static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
+static void cwq_activate_delayed_work(struct work_struct *work)
 {
-	struct work_struct *work = list_first_entry(&cwq->delayed_works,
-						    struct work_struct, entry);
+	struct cpu_workqueue_struct *cwq = get_work_cwq(work);
 	struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq);
 
 	trace_workqueue_activate_work(work);
@@ -1733,6 +1752,14 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
 	cwq->nr_active++;
 }
 
+static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
+{
+	struct work_struct *work = list_first_entry(&cwq->delayed_works,
+						    struct work_struct, entry);
+
+	cwq_activate_delayed_work(work);
+}
+
 /**
  * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight
  * @cwq: cwq of interest
@@ -1804,7 +1831,6 @@ __acquires(&gcwq->lock)
 	struct global_cwq *gcwq = cwq->gcwq;
 	struct hlist_head *bwh = busy_worker_head(gcwq, work);
 	bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE;
-	work_func_t f = work->func;
 	int work_color;
 	struct worker *collision;
 #ifdef CONFIG_LOCKDEP
@@ -1833,6 +1859,7 @@ __acquires(&gcwq->lock)
 	debug_work_deactivate(work);
 	hlist_add_head(&worker->hentry, bwh);
 	worker->current_work = work;
+	worker->current_func = work->func;
 	worker->current_cwq = cwq;
 	work_color = get_work_color(work);
 
@@ -1870,7 +1897,7 @@ __acquires(&gcwq->lock)
 	lock_map_acquire_read(&cwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
 	trace_workqueue_execute_start(work);
-	f(work);
+	worker->current_func(work);
 	/*
 	 * While we must be careful to not use "work" after this, the trace
 	 * point will only record its address.
@@ -1880,11 +1907,10 @@ __acquires(&gcwq->lock)
 	lock_map_release(&cwq->wq->lockdep_map);
 
 	if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
-		printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
-		       "%s/0x%08x/%d\n",
-		       current->comm, preempt_count(), task_pid_nr(current));
-		printk(KERN_ERR "    last function: ");
-		print_symbol("%s\n", (unsigned long)f);
+		pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n"
+		       "     last function: %pf\n",
+		       current->comm, preempt_count(), task_pid_nr(current),
+		       worker->current_func);
 		debug_show_held_locks(current);
 		dump_stack();
 	}
@@ -1898,6 +1924,7 @@ __acquires(&gcwq->lock)
 	/* we're done with it, release */
 	hlist_del_init(&worker->hentry);
 	worker->current_work = NULL;
+	worker->current_func = NULL;
 	worker->current_cwq = NULL;
 	cwq_dec_nr_in_flight(cwq, work_color, false);
 }
@@ -2625,6 +2652,18 @@ static int try_to_grab_pending(struct work_struct *work)
 		smp_rmb();
 		if (gcwq == get_work_gcwq(work)) {
 			debug_work_deactivate(work);
+
+			/*
+			 * A delayed work item cannot be grabbed directly
+			 * because it might have linked NO_COLOR work items
+			 * which, if left on the delayed_list, will confuse
+			 * cwq->nr_active management later on and cause
+			 * stall.  Make sure the work item is activated
+			 * before grabbing.
+			 */
+			if (*work_data_bits(work) & WORK_STRUCT_DELAYED)
+				cwq_activate_delayed_work(work);
+
 			list_del_init(&work->entry);
 			cwq_dec_nr_in_flight(get_work_cwq(work),
 				get_work_color(work),