Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/tip/tip

Pull core locking changes from Ingo Molnar:
 "The biggest changes:

   - add lockdep support for seqcount/seqlocks structures, this
     unearthed both bugs and required extra annotation.

   - move the various kernel locking primitives to the new
     kernel/locking/ directory"

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  block: Use u64_stats_init() to initialize seqcounts
  locking/lockdep: Mark __lockdep_count_forward_deps() as static
  lockdep/proc: Fix lock-time avg computation
  locking/doc: Update references to kernel/mutex.c
  ipv6: Fix possible ipv6 seqlock deadlock
  cpuset: Fix potential deadlock w/ set_mems_allowed
  seqcount: Add lockdep functionality to seqcount/seqlock structures
  net: Explicitly initialize u64_stats_sync structures for lockdep
  locking: Move the percpu-rwsem code to kernel/locking/
  locking: Move the lglocks code to kernel/locking/
  locking: Move the rwsem code to kernel/locking/
  locking: Move the rtmutex code to kernel/locking/
  locking: Move the semaphore core to kernel/locking/
  locking: Move the spinlock code to kernel/locking/
  locking: Move the lockdep code to kernel/locking/
  locking: Move the mutex code to kernel/locking/
  hung_task debugging: Add tracepoint to report the hang
  x86/locking/kconfig: Update paravirt spinlock Kconfig description
  lockstat: Report avg wait and hold times
  lockdep, x86/alternatives: Drop ancient lockdep fixup message
  ...

Documentation/DocBook/kernel-locking.tmpl

@@ -1958,7 +1958,7 @@ machines due to caching.
   <chapter id="apiref-mutex">
    <title>Mutex API reference</title>
 !Iinclude/linux/mutex.h
-!Ekernel/mutex.c
+!Ekernel/locking/mutex.c
   </chapter>
 
   <chapter id="apiref-futex">

Documentation/mutex-design.txt

@@ -116,11 +116,11 @@ using mutexes at the moment, please let me know if you find any. ]
 Implementation of mutexes
 -------------------------
 
-'struct mutex' is the new mutex type, defined in include/linux/mutex.h
-and implemented in kernel/mutex.c. It is a counter-based mutex with a
-spinlock and a wait-list. The counter has 3 states: 1 for "unlocked",
-0 for "locked" and negative numbers (usually -1) for "locked, potential
-waiters queued".
+'struct mutex' is the new mutex type, defined in include/linux/mutex.h and
+implemented in kernel/locking/mutex.c. It is a counter-based mutex with a
+spinlock and a wait-list. The counter has 3 states: 1 for "unlocked", 0 for
+"locked" and negative numbers (usually -1) for "locked, potential waiters
+queued".
 
 the APIs of 'struct mutex' have been streamlined:
 

arch/x86/Kconfig

@@ -635,10 +635,10 @@ config PARAVIRT_SPINLOCKS
 	  spinlock implementation with something virtualization-friendly
 	  (for example, block the virtual CPU rather than spinning).
 
-	  Unfortunately the downside is an up to 5% performance hit on
-	  native kernels, with various workloads.
+	  It has a minimal impact on native kernels and gives a nice performance
+	  benefit on paravirtualized KVM / Xen kernels.
 
-	  If you are unsure how to answer this question, answer N.
+	  If you are unsure how to answer this question, answer Y.
 
 source "arch/x86/xen/Kconfig"
 

arch/x86/kernel/alternative.c

@@ -402,17 +402,6 @@ void alternatives_enable_smp(void)
 {
 	struct smp_alt_module *mod;
 
-#ifdef CONFIG_LOCKDEP
-	/*
-	 * Older binutils section handling bug prevented
-	 * alternatives-replacement from working reliably.
-	 *
-	 * If this still occurs then you should see a hang
-	 * or crash shortly after this line:
-	 */
-	pr_info("lockdep: fixing up alternatives\n");
-#endif
-
 	/* Why bother if there are no other CPUs? */
 	BUG_ON(num_possible_cpus() == 1);
 

arch/x86/vdso/vclock_gettime.c

@@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->wall_time_snsec;
@@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->monotonic_time_sec;
 		ns = gtod->monotonic_time_snsec;
@@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
@@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));

block/blk-cgroup.h

@@ -402,6 +402,11 @@ struct request_list *__blk_queue_next_rl(struct request_list *rl,
 #define blk_queue_for_each_rl(rl, q)	\
 	for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q)))
 
+static inline void blkg_stat_init(struct blkg_stat *stat)
+{
+	u64_stats_init(&stat->syncp);
+}
+
 /**
  * blkg_stat_add - add a value to a blkg_stat
  * @stat: target blkg_stat
@@ -458,6 +463,11 @@ static inline void blkg_stat_merge(struct blkg_stat *to, struct blkg_stat *from)
 	blkg_stat_add(to, blkg_stat_read(from));
 }
 
+static inline void blkg_rwstat_init(struct blkg_rwstat *rwstat)
+{
+	u64_stats_init(&rwstat->syncp);
+}
+
 /**
  * blkg_rwstat_add - add a value to a blkg_rwstat
  * @rwstat: target blkg_rwstat

block/blk-throttle.c

@@ -256,6 +256,12 @@ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
 	}								\
 } while (0)
 
+static void tg_stats_init(struct tg_stats_cpu *tg_stats)
+{
+	blkg_rwstat_init(&tg_stats->service_bytes);
+	blkg_rwstat_init(&tg_stats->serviced);
+}
+
 /*
  * Worker for allocating per cpu stat for tgs. This is scheduled on the
  * system_wq once there are some groups on the alloc_list waiting for
@@ -269,12 +275,16 @@ static void tg_stats_alloc_fn(struct work_struct *work)
 
 alloc_stats:
 	if (!stats_cpu) {
+		int cpu;
+
 		stats_cpu = alloc_percpu(struct tg_stats_cpu);
 		if (!stats_cpu) {
 			/* allocation failed, try again after some time */
 			schedule_delayed_work(dwork, msecs_to_jiffies(10));
 			return;
 		}
+		for_each_possible_cpu(cpu)
+			tg_stats_init(per_cpu_ptr(stats_cpu, cpu));
 	}
 
 	spin_lock_irq(&tg_stats_alloc_lock);

block/cfq-iosched.c

@@ -1508,13 +1508,38 @@ static void cfq_init_cfqg_base(struct cfq_group *cfqg)
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
+static void cfqg_stats_init(struct cfqg_stats *stats)
+{
+	blkg_rwstat_init(&stats->service_bytes);
+	blkg_rwstat_init(&stats->serviced);
+	blkg_rwstat_init(&stats->merged);
+	blkg_rwstat_init(&stats->service_time);
+	blkg_rwstat_init(&stats->wait_time);
+	blkg_rwstat_init(&stats->queued);
+
+	blkg_stat_init(&stats->sectors);
+	blkg_stat_init(&stats->time);
+
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	blkg_stat_init(&stats->unaccounted_time);
+	blkg_stat_init(&stats->avg_queue_size_sum);
+	blkg_stat_init(&stats->avg_queue_size_samples);
+	blkg_stat_init(&stats->dequeue);
+	blkg_stat_init(&stats->group_wait_time);
+	blkg_stat_init(&stats->idle_time);
+	blkg_stat_init(&stats->empty_time);
+#endif
+}
+
 static void cfq_pd_init(struct blkcg_gq *blkg)
 {
 	struct cfq_group *cfqg = blkg_to_cfqg(blkg);
 
 	cfq_init_cfqg_base(cfqg);
 	cfqg->weight = blkg->blkcg->cfq_weight;
 	cfqg->leaf_weight = blkg->blkcg->cfq_leaf_weight;
+	cfqg_stats_init(&cfqg->stats);
+	cfqg_stats_init(&cfqg->dead_stats);
 }
 
 static void cfq_pd_offline(struct blkcg_gq *blkg)

drivers/net/dummy.c

@@ -88,10 +88,16 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int dummy_dev_init(struct net_device *dev)
 {
+	int i;
 	dev->dstats = alloc_percpu(struct pcpu_dstats);
 	if (!dev->dstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_dstats *dstats;
+		dstats = per_cpu_ptr(dev->dstats, i);
+		u64_stats_init(&dstats->syncp);
+	}
 	return 0;
 }
 

drivers/net/ethernet/emulex/benet/be_main.c

@@ -2148,6 +2148,9 @@ static int be_tx_qs_create(struct be_adapter *adapter)
 		if (status)
 			return status;
 
+		u64_stats_init(&txo->stats.sync);
+		u64_stats_init(&txo->stats.sync_compl);
+
 		/* If num_evt_qs is less than num_tx_qs, then more than
 		 * one txq share an eq
 		 */
@@ -2209,6 +2212,7 @@ static int be_rx_cqs_create(struct be_adapter *adapter)
 		if (rc)
 			return rc;
 
+		u64_stats_init(&rxo->stats.sync);
 		eq = &adapter->eq_obj[i % adapter->num_evt_qs].q;
 		rc = be_cmd_cq_create(adapter, cq, eq, false, 3);
 		if (rc)

drivers/net/ethernet/intel/igb/igb_main.c

@@ -1224,6 +1224,9 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		ring->count = adapter->tx_ring_count;
 		ring->queue_index = txr_idx;
 
+		u64_stats_init(&ring->tx_syncp);
+		u64_stats_init(&ring->tx_syncp2);
+
 		/* assign ring to adapter */
 		adapter->tx_ring[txr_idx] = ring;
 
@@ -1257,6 +1260,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		ring->count = adapter->rx_ring_count;
 		ring->queue_index = rxr_idx;
 
+		u64_stats_init(&ring->rx_syncp);
+
 		/* assign ring to adapter */
 		adapter->rx_ring[rxr_idx] = ring;
 	}

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -5085,6 +5085,8 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 	if (!tx_ring->tx_buffer_info)
 		goto err;
 
+	u64_stats_init(&tx_ring->syncp);
+
 	/* round up to nearest 4K */
 	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
@@ -5167,6 +5169,8 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
 	if (!rx_ring->rx_buffer_info)
 		goto err;
 
+	u64_stats_init(&rx_ring->syncp);
+
 	/* Round up to nearest 4K */
 	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);

drivers/net/ethernet/marvell/mvneta.c

@@ -2792,6 +2792,9 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp = netdev_priv(dev);
 
+	u64_stats_init(&pp->tx_stats.syncp);
+	u64_stats_init(&pp->rx_stats.syncp);
+
 	pp->weight = MVNETA_RX_POLL_WEIGHT;
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;

drivers/net/ethernet/marvell/sky2.c

@@ -4763,6 +4763,9 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port,
 	sky2->hw = hw;
 	sky2->msg_enable = netif_msg_init(debug, default_msg);
 
+	u64_stats_init(&sky2->tx_stats.syncp);
+	u64_stats_init(&sky2->rx_stats.syncp);
+
 	/* Auto speed and flow control */
 	sky2->flags = SKY2_FLAG_AUTO_SPEED | SKY2_FLAG_AUTO_PAUSE;
 	if (hw->chip_id != CHIP_ID_YUKON_XL)

drivers/net/ethernet/neterion/vxge/vxge-main.c

@@ -2072,6 +2072,10 @@ static int vxge_open_vpaths(struct vxgedev *vdev)
 				vdev->config.tx_steering_type;
 			vpath->fifo.ndev = vdev->ndev;
 			vpath->fifo.pdev = vdev->pdev;
+
+			u64_stats_init(&vpath->fifo.stats.syncp);
+			u64_stats_init(&vpath->ring.stats.syncp);
+
 			if (vdev->config.tx_steering_type)
 				vpath->fifo.txq =
 					netdev_get_tx_queue(vdev->ndev, i);

drivers/net/ethernet/nvidia/forcedeth.c

@@ -5619,6 +5619,8 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	spin_lock_init(&np->lock);
 	spin_lock_init(&np->hwstats_lock);
 	SET_NETDEV_DEV(dev, &pci_dev->dev);
+	u64_stats_init(&np->swstats_rx_syncp);
+	u64_stats_init(&np->swstats_tx_syncp);
 
 	init_timer(&np->oom_kick);
 	np->oom_kick.data = (unsigned long) dev;

drivers/net/ethernet/realtek/8139too.c

@@ -790,6 +790,9 @@ static struct net_device *rtl8139_init_board(struct pci_dev *pdev)
 
 	pci_set_master (pdev);
 
+	u64_stats_init(&tp->rx_stats.syncp);
+	u64_stats_init(&tp->tx_stats.syncp);
+
 retry:
 	/* PIO bar register comes first. */
 	bar = !use_io;

drivers/net/ethernet/tile/tilepro.c

@@ -1008,6 +1008,8 @@ static void tile_net_register(void *dev_ptr)
 	info->egress_timer.data = (long)info;
 	info->egress_timer.function = tile_net_handle_egress_timer;
 
+	u64_stats_init(&info->stats.syncp);
+
 	priv->cpu[my_cpu] = info;
 
 	/*

drivers/net/ethernet/via/via-rhine.c

@@ -987,6 +987,9 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	rp->base = ioaddr;
 
+	u64_stats_init(&rp->tx_stats.syncp);
+	u64_stats_init(&rp->rx_stats.syncp);
+
 	/* Get chip registers into a sane state */
 	rhine_power_init(dev);
 	rhine_hw_init(dev, pioaddr);

drivers/net/ifb.c

@@ -265,6 +265,7 @@ MODULE_PARM_DESC(numifbs, "Number of ifb devices");
 static int __init ifb_init_one(int index)
 {
 	struct net_device *dev_ifb;
+	struct ifb_private *dp;
 	int err;
 
 	dev_ifb = alloc_netdev(sizeof(struct ifb_private),
@@ -273,6 +274,10 @@ static int __init ifb_init_one(int index)
 	if (!dev_ifb)
 		return -ENOMEM;
 
+	dp = netdev_priv(dev_ifb);
+	u64_stats_init(&dp->rsync);
+	u64_stats_init(&dp->tsync);
+
 	dev_ifb->rtnl_link_ops = &ifb_link_ops;
 	err = register_netdevice(dev_ifb);
 	if (err < 0)

drivers/net/loopback.c

@@ -137,10 +137,16 @@ static const struct ethtool_ops loopback_ethtool_ops = {
 
 static int loopback_dev_init(struct net_device *dev)
 {
+	int i;
 	dev->lstats = alloc_percpu(struct pcpu_lstats);
 	if (!dev->lstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_lstats *lb_stats;
+		lb_stats = per_cpu_ptr(dev->lstats, i);
+		u64_stats_init(&lb_stats->syncp);
+	}
 	return 0;
 }
 

drivers/net/macvlan.c

@@ -534,6 +534,7 @@ static int macvlan_init(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct net_device *lowerdev = vlan->lowerdev;
+	int i;
 
 	dev->state		= (dev->state & ~MACVLAN_STATE_MASK) |
 				  (lowerdev->state & MACVLAN_STATE_MASK);
@@ -549,6 +550,12 @@ static int macvlan_init(struct net_device *dev)
 	if (!vlan->pcpu_stats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct macvlan_pcpu_stats *mvlstats;
+		mvlstats = per_cpu_ptr(vlan->pcpu_stats, i);
+		u64_stats_init(&mvlstats->syncp);
+	}
+
 	return 0;
 }