Merge branch 'sched/urgent' into sched/core, to merge fixes before applying new changes

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

17 files changed, 95 insertions, 87 deletions

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index ec4112d257bc..8f8ae95c6e27 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -482,8 +482,8 @@ extern struct cpufreq_governor cpufreq_gov_conservative;
  *********************************************************************/
 
 /* Special Values of .frequency field */
-#define CPUFREQ_ENTRY_INVALID	~0
-#define CPUFREQ_TABLE_END	~1
+#define CPUFREQ_ENTRY_INVALID	~0u
+#define CPUFREQ_TABLE_END	~1u
 /* Special Values of .flags field */
 #define CPUFREQ_BOOST_FREQ	(1 << 0)
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 5ab4e3a76721..92abb497ab14 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -593,6 +593,7 @@ struct ata_host {
 	struct device 		*dev;
 	void __iomem * const	*iomap;
 	unsigned int		n_ports;
+	unsigned int		n_tags;			/* nr of NCQ tags */
 	void			*private_data;
 	struct ata_port_operations *ops;
 	unsigned long		flags;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b12f4bbd064c..35b51e7af886 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -578,8 +578,6 @@ struct mlx4_cq {
 	u32			cons_index;
 
 	u16                     irq;
-	bool                    irq_affinity_change;
-
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
 	int			arm_sn;
@@ -1167,6 +1165,8 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 		   int *vector);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
+int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec);
+
 int mlx4_get_phys_port_id(struct mlx4_dev *dev);
 int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
 int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 11692dea18aa..42aa9b9ecd5f 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -17,6 +17,7 @@
 #include <linux/lockdep.h>
 #include <linux/atomic.h>
 #include <asm/processor.h>
+#include <linux/osq_lock.h>
 
 /*
  * Simple, straightforward mutexes with strict semantics:
@@ -46,7 +47,6 @@
  * - detects multi-task circular deadlocks and prints out all affected
  *   locks and tasks (and only those tasks)
  */
-struct optimistic_spin_queue;
 struct mutex {
 	/* 1: unlocked, 0: locked, negative: locked, possible waiters */
 	atomic_t		count;
@@ -56,7 +56,7 @@ struct mutex {
 	struct task_struct	*owner;
 #endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	struct optimistic_spin_queue	*osq;	/* Spinner MCS lock */
+	struct optimistic_spin_queue osq; /* Spinner MCS lock */
 #endif
 #ifdef CONFIG_DEBUG_MUTEXES
 	const char 		*name;
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index a70c9493d55a..d449018d0726 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -25,9 +25,6 @@ struct phy_device *of_phy_attach(struct net_device *dev,
 
 extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np);
 
-extern void of_mdiobus_link_phydev(struct mii_bus *mdio,
-				   struct phy_device *phydev);
-
 #else /* CONFIG_OF */
 static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 {
@@ -63,11 +60,6 @@ static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np)
 {
 	return NULL;
 }
-
-static inline void of_mdiobus_link_phydev(struct mii_bus *mdio,
-					  struct phy_device *phydev)
-{
-}
 #endif /* CONFIG_OF */
 
 #if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY)
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
new file mode 100644
index 000000000000..90230d5811c5
--- /dev/null
+++ b/include/linux/osq_lock.h
@@ -0,0 +1,27 @@
+#ifndef __LINUX_OSQ_LOCK_H
+#define __LINUX_OSQ_LOCK_H
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ */
+
+#define OSQ_UNLOCKED_VAL (0)
+
+struct optimistic_spin_queue {
+	/*
+	 * Stores an encoded value of the CPU # of the tail node in the queue.
+	 * If the queue is empty, then it's set to OSQ_UNLOCKED_VAL.
+	 */
+	atomic_t tail;
+};
+
+/* Init macro and function. */
+#define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) }
+
+static inline void osq_lock_init(struct optimistic_spin_queue *lock)
+{
+	atomic_set(&lock->tail, OSQ_UNLOCKED_VAL);
+}
+
+#endif
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0a97b583ee8d..e1474ae18c88 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -399,6 +399,18 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
 }
 
 /*
+ * Get the offset in PAGE_SIZE.
+ * (TODO: hugepage should have ->index in PAGE_SIZE)
+ */
+static inline pgoff_t page_to_pgoff(struct page *page)
+{
+	if (unlikely(PageHeadHuge(page)))
+		return page->index << compound_order(page);
+	else
+		return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+}
+
+/*
  * Return byte-offset into filesystem object for page.
  */
 static inline loff_t page_offset(struct page *page)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5a75d19aa661..6a94cc8b1ca0 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -44,7 +44,6 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
-#include <linux/percpu.h>
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
@@ -300,41 +299,6 @@ bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
 
 /*
- * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
- */
-
-#define RCU_COND_RESCHED_LIM 256	/* ms vs. 100s of ms. */
-DECLARE_PER_CPU(int, rcu_cond_resched_count);
-void rcu_resched(void);
-
-/*
- * Is it time to report RCU quiescent states?
- *
- * Note unsynchronized access to rcu_cond_resched_count.  Yes, we might
- * increment some random CPU's count, and possibly also load the result from
- * yet another CPU's count.  We might even clobber some other CPU's attempt
- * to zero its counter.  This is all OK because the goal is not precision,
- * but rather reasonable amortization of rcu_note_context_switch() overhead
- * and extremely high probability of avoiding RCU CPU stall warnings.
- * Note that this function has to be preempted in just the wrong place,
- * many thousands of times in a row, for anything bad to happen.
- */
-static inline bool rcu_should_resched(void)
-{
-	return raw_cpu_inc_return(rcu_cond_resched_count) >=
-	       RCU_COND_RESCHED_LIM;
-}
-
-/*
- * Report quiscent states to RCU if it is time to do so.
- */
-static inline void rcu_cond_resched(void)
-{
-	if (unlikely(rcu_should_resched()))
-		rcu_resched();
-}
-
-/*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
  */
@@ -358,9 +322,19 @@ void wait_rcu_gp(call_rcu_func_t crf);
  * initialization.
  */
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+void init_rcu_head(struct rcu_head *head);
+void destroy_rcu_head(struct rcu_head *head);
 void init_rcu_head_on_stack(struct rcu_head *head);
 void destroy_rcu_head_on_stack(struct rcu_head *head);
 #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void init_rcu_head(struct rcu_head *head)
+{
+}
+
+static inline void destroy_rcu_head(struct rcu_head *head)
+{
+}
+
 static inline void init_rcu_head_on_stack(struct rcu_head *head)
 {
 }
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index d5b13bc07a0b..561e8615528d 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -15,13 +15,13 @@
 #ifdef __KERNEL__
 /*
  * the rw-semaphore definition
- * - if activity is 0 then there are no active readers or writers
- * - if activity is +ve then that is the number of active readers
- * - if activity is -1 then there is one active writer
+ * - if count is 0 then there are no active readers or writers
+ * - if count is +ve then that is the number of active readers
+ * - if count is -1 then there is one active writer
  * - if wait_list is not empty, then there are processes waiting for the semaphore
  */
 struct rw_semaphore {
-	__s32			activity;
+	__s32			count;
 	raw_spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 8d79708146aa..035d3c57fc8a 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -13,10 +13,11 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
-
 #include <linux/atomic.h>
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#include <linux/osq_lock.h>
+#endif
 
-struct optimistic_spin_queue;
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
@@ -25,15 +26,15 @@ struct rw_semaphore;
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
 	long count;
-	raw_spinlock_t wait_lock;
 	struct list_head wait_list;
-#ifdef CONFIG_SMP
+	raw_spinlock_t wait_lock;
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+	struct optimistic_spin_queue osq; /* spinner MCS lock */
 	/*
 	 * Write owner. Used as a speculative check to see
 	 * if the owner is running on the cpu.
 	 */
 	struct task_struct *owner;
-	struct optimistic_spin_queue *osq; /* spinner MCS lock */
 #endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
@@ -64,22 +65,19 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
-#if defined(CONFIG_SMP) && !defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
-#define __RWSEM_INITIALIZER(name)			\
-	{ RWSEM_UNLOCKED_VALUE,				\
-	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
-	  LIST_HEAD_INIT((name).wait_list),		\
-	  NULL, /* owner */				\
-	  NULL /* mcs lock */                           \
-	  __RWSEM_DEP_MAP_INIT(name) }
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL
 #else
-#define __RWSEM_INITIALIZER(name)			\
-	{ RWSEM_UNLOCKED_VALUE,				\
-	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
-	  LIST_HEAD_INIT((name).wait_list)		\
-	  __RWSEM_DEP_MAP_INIT(name) }
+#define __RWSEM_OPT_INIT(lockname)
 #endif
 
+#define __RWSEM_INITIALIZER(name)				\
+	{ .count = RWSEM_UNLOCKED_VALUE,			\
+	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
+	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
+	  __RWSEM_OPT_INIT(name)				\
+	  __RWSEM_DEP_MAP_INIT(name) }
+
 #define DECLARE_RWSEM(name) \
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 41a195385081..02757d105cdb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -872,21 +872,21 @@ enum cpu_idle_type {
 #define SD_NUMA			0x4000	/* cross-node balancing */
 
 #ifdef CONFIG_SCHED_SMT
-static inline const int cpu_smt_flags(void)
+static inline int cpu_smt_flags(void)
 {
 	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
 #ifdef CONFIG_SCHED_MC
-static inline const int cpu_core_flags(void)
+static inline int cpu_core_flags(void)
 {
 	return SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
 #ifdef CONFIG_NUMA
-static inline const int cpu_numa_flags(void)
+static inline int cpu_numa_flags(void)
 {
 	return SD_NUMA;
 }
@@ -999,7 +999,7 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 bool cpus_share_cache(int this_cpu, int that_cpu);
 
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
-typedef const int (*sched_domain_flags_f)(void);
+typedef int (*sched_domain_flags_f)(void);
 
 #define SDTL_OVERLAP	0x01
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 7277caf3743d..47f425464f84 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -203,7 +203,6 @@ struct neigh_table {
 	void			(*proxy_redo)(struct sk_buff *skb);
 	char			*id;
 	struct neigh_parms	parms;
-	/* HACK. gc_* should follow parms without a gap! */
 	int			gc_interval;
 	int			gc_thresh1;
 	int			gc_thresh2;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 713b0b88bd5a..c4d86198d3d6 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -6,6 +6,7 @@
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/u64_stats_sync.h>
 #include <net/netlink.h>
 
 #define NFT_JUMP_STACK_SIZE	16
@@ -528,8 +529,9 @@ enum nft_chain_type {
 };
 
 struct nft_stats {
-	u64 bytes;
-	u64 pkts;
+	u64			bytes;
+	u64			pkts;
+	struct u64_stats_sync	syncp;
 };
 
 #define NFT_HOOK_OPS_MAX		2
diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h
index 079030c853d8..e2070960bac0 100644
--- a/include/net/netns/ieee802154_6lowpan.h
+++ b/include/net/netns/ieee802154_6lowpan.h
@@ -16,7 +16,7 @@ struct netns_sysctl_lowpan {
 struct netns_ieee802154_lowpan {
 	struct netns_sysctl_lowpan sysctl;
 	struct netns_frags	frags;
-	u16			max_dsize;
+	int			max_dsize;
 };
 
 #endif
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 26a394cb91a8..eee608b12cc9 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -13,8 +13,8 @@ struct netns_nftables {
 	struct nft_af_info	*inet;
 	struct nft_af_info	*arp;
 	struct nft_af_info	*bridge;
+	unsigned int		base_seq;
 	u8			gencursor;
-	u8			genctr;
 };
 
 #endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 173cae485de1..156350745700 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1768,9 +1768,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 static inline void
 sk_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_set(sk, dst);
-	spin_unlock(&sk->sk_dst_lock);
+	struct dst_entry *old_dst;
+
+	sk_tx_queue_clear(sk);
+	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+	dst_release(old_dst);
 }
 
 static inline void
@@ -1782,9 +1784,7 @@ __sk_dst_reset(struct sock *sk)
 static inline void
 sk_dst_reset(struct sock *sk)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_reset(sk);
-	spin_unlock(&sk->sk_dst_lock);
+	sk_dst_set(sk, NULL);
 }
 
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 40b5ca8a1b1f..25084a052a1e 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -101,6 +101,7 @@
  *  - add FATTR_CTIME
  *  - add ctime and ctimensec to fuse_setattr_in
  *  - add FUSE_RENAME2 request
+ *  - add FUSE_NO_OPEN_SUPPORT flag
  */
 
 #ifndef _LINUX_FUSE_H
@@ -229,6 +230,7 @@ struct fuse_file_lock {
  * FUSE_READDIRPLUS_AUTO: adaptive readdirplus
  * FUSE_ASYNC_DIO: asynchronous direct I/O submission
  * FUSE_WRITEBACK_CACHE: use writeback cache for buffered writes
+ * FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -247,6 +249,7 @@ struct fuse_file_lock {
 #define FUSE_READDIRPLUS_AUTO	(1 << 14)
 #define FUSE_ASYNC_DIO		(1 << 15)
 #define FUSE_WRITEBACK_CACHE	(1 << 16)
+#define FUSE_NO_OPEN_SUPPORT	(1 << 17)
 
 /**
  * CUSE INIT request/reply flags