Merge branch 'for-linus' into for-next

Conflicts:
	drivers/gpu/drm/i915/intel_pm.c

41 files changed, 213 insertions, 104 deletions

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index db284bff29dc..9dbb739cafa0 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -5,7 +5,7 @@
  * Copyright 2001 Red Hat, Inc.
  * Based on code from mm/memory.c Copyright Linus Torvalds and others.
  *
- * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 2b8ed123ad36..defeaac0745f 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -107,7 +107,7 @@ static inline __u64 ror64(__u64 word, unsigned int shift)
  */
 static inline __u32 rol32(__u32 word, unsigned int shift)
 {
-	return (word << shift) | (word >> (32 - shift));
+	return (word << shift) | (word >> ((-shift) & 31));
 }
 
 /**
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 60d44b26276d..06b77f9dd3f2 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -90,7 +90,6 @@ enum {
  */
 struct cgroup_file {
 	/* do not access any fields from outside cgroup core */
-	struct list_head node;			/* anchored at css->files */
 	struct kernfs_node *kn;
 };
 
@@ -134,9 +133,6 @@ struct cgroup_subsys_state {
 	 */
 	u64 serial_nr;
 
-	/* all cgroup_files associated with this css */
-	struct list_head files;
-
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
@@ -426,12 +422,9 @@ struct cgroup_subsys {
 	void (*css_reset)(struct cgroup_subsys_state *css);
 	void (*css_e_css_changed)(struct cgroup_subsys_state *css);
 
-	int (*can_attach)(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset);
-	void (*cancel_attach)(struct cgroup_subsys_state *css,
-			      struct cgroup_taskset *tset);
-	void (*attach)(struct cgroup_subsys_state *css,
-		       struct cgroup_taskset *tset);
+	int (*can_attach)(struct cgroup_taskset *tset);
+	void (*cancel_attach)(struct cgroup_taskset *tset);
+	void (*attach)(struct cgroup_taskset *tset);
 	int (*can_fork)(struct task_struct *task, void **priv_p);
 	void (*cancel_fork)(struct task_struct *task, void *priv);
 	void (*fork)(struct task_struct *task, void *priv);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 22e3754f89c5..cb91b44f5f78 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -88,6 +88,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
+void cgroup_file_notify(struct cgroup_file *cfile);
 
 char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
@@ -119,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state
 struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
 						     struct cgroup_subsys_state *css);
 
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+					 struct cgroup_subsys_state **dst_cssp);
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+					struct cgroup_subsys_state **dst_cssp);
 
 void css_task_iter_start(struct cgroup_subsys_state *css,
 			 struct css_task_iter *it);
@@ -235,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it);
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
+ * @dst_css: the destination css
  * @tset: taskset to iterate
  *
  * @tset may contain multiple tasks and they may belong to multiple
- * processes.  When there are multiple tasks in @tset, if a task of a
- * process is in @tset, all tasks of the process are in @tset.  Also, all
- * are guaranteed to share the same source and destination csses.
+ * processes.
+ *
+ * On the v2 hierarchy, there may be tasks from multiple processes and they
+ * may not share the source or destination csses.
+ *
+ * On traditional hierarchies, when there are multiple tasks in @tset, if a
+ * task of a process is in @tset, all tasks of the process are in @tset.
+ * Also, all are guaranteed to share the same source and destination csses.
  *
  * Iteration is not in any specific order.
  */
-#define cgroup_taskset_for_each(task, tset)				\
-	for ((task) = cgroup_taskset_first((tset)); (task);		\
-	     (task) = cgroup_taskset_next((tset)))
+#define cgroup_taskset_for_each(task, dst_css, tset)			\
+	for ((task) = cgroup_taskset_first((tset), &(dst_css));		\
+	     (task);							\
+	     (task) = cgroup_taskset_next((tset), &(dst_css)))
 
 /**
  * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
  * @leader: the loop cursor
+ * @dst_css: the destination css
  * @tset: takset to iterate
  *
  * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
  * may not contain any.
  */
-#define cgroup_taskset_for_each_leader(leader, tset)			\
-	for ((leader) = cgroup_taskset_first((tset)); (leader);		\
-	     (leader) = cgroup_taskset_next((tset)))			\
+#define cgroup_taskset_for_each_leader(leader, dst_css, tset)		\
+	for ((leader) = cgroup_taskset_first((tset), &(dst_css));	\
+	     (leader);							\
+	     (leader) = cgroup_taskset_next((tset), &(dst_css)))	\
 		if ((leader) != (leader)->group_leader)			\
 			;						\
 		else
@@ -516,19 +528,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
-/**
- * cgroup_file_notify - generate a file modified event for a cgroup_file
- * @cfile: target cgroup_file
- *
- * @cfile must have been obtained by setting cftype->file_offset.
- */
-static inline void cgroup_file_notify(struct cgroup_file *cfile)
-{
-	/* might not have been created due to one of the CFTYPE selector flags */
-	if (cfile->kn)
-		kernfs_notify(cfile->kn);
-}
-
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
index 7be22da321f3..a4cf57cd0f75 100644
--- a/include/linux/enclosure.h
+++ b/include/linux/enclosure.h
@@ -29,7 +29,11 @@
 /* A few generic types ... taken from ses-2 */
 enum enclosure_component_type {
 	ENCLOSURE_COMPONENT_DEVICE = 0x01,
+	ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS = 0x07,
+	ENCLOSURE_COMPONENT_SCSI_TARGET_PORT = 0x14,
+	ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT = 0x15,
 	ENCLOSURE_COMPONENT_ARRAY_DEVICE = 0x17,
+	ENCLOSURE_COMPONENT_SAS_EXPANDER = 0x18,
 };
 
 /* ses-2 common element status */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index c9ae0c6ec050..d5d798b35c1f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -330,6 +330,7 @@ struct rdists {
 };
 
 struct irq_domain;
+struct device_node;
 int its_cpu_init(void);
 int its_init(struct device_node *node, struct rdists *rdists,
 	     struct irq_domain *domain);
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 8dde55974f18..0536524bb9eb 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -5,7 +5,7 @@
  * Jump label support
  *
  * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  *
  * DEPRECATED API:
  *
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index d0a1f99e24e3..4894c6888bc6 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_DEBUG_KMEMLEAK
 
-extern void kmemleak_init(void) __ref;
+extern void kmemleak_init(void) __init;
 extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			   gfp_t gfp) __ref;
 extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 83577f8fd15b..600c1e0626a5 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -210,6 +210,7 @@ enum {
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
 					    /* (doesn't imply presence) */
 	ATA_FLAG_SATA		= (1 << 1),
+	ATA_FLAG_NO_LOG_PAGE	= (1 << 5), /* do not issue log page read */
 	ATA_FLAG_NO_ATAPI	= (1 << 6), /* No ATAPI support */
 	ATA_FLAG_PIO_DMA	= (1 << 7), /* PIO cmds via DMA */
 	ATA_FLAG_PIO_LBA48	= (1 << 8), /* Host DMA engine is LBA28 only */
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index c6916aec43b6..034117b3be5f 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -50,9 +50,16 @@ enum {
 	NVM_IO_DUAL_ACCESS	= 0x1,
 	NVM_IO_QUAD_ACCESS	= 0x2,
 
+	/* NAND Access Modes */
 	NVM_IO_SUSPEND		= 0x80,
 	NVM_IO_SLC_MODE		= 0x100,
 	NVM_IO_SCRAMBLE_DISABLE	= 0x200,
+
+	/* Block Types */
+	NVM_BLK_T_FREE		= 0x0,
+	NVM_BLK_T_BAD		= 0x1,
+	NVM_BLK_T_DEV		= 0x2,
+	NVM_BLK_T_HOST		= 0x4,
 };
 
 struct nvm_id_group {
@@ -176,17 +183,17 @@ struct nvm_block;
 
 typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
 typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
-typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *);
-typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32,
+typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
+typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
 				nvm_l2p_update_fn *, void *);
 typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
 				nvm_bb_update_fn *, void *);
-typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int);
-typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *);
-typedef int (nvm_erase_blk_fn)(struct request_queue *, struct nvm_rq *);
-typedef void *(nvm_create_dma_pool_fn)(struct request_queue *, char *);
+typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int);
+typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
 typedef void (nvm_destroy_dma_pool_fn)(void *);
-typedef void *(nvm_dev_dma_alloc_fn)(struct request_queue *, void *, gfp_t,
+typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
 								dma_addr_t *);
 typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
 
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 70400dc7660f..c57e424d914b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -2,7 +2,7 @@
  * Runtime locking correctness validator
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * see Documentation/locking/lockdep-design.txt for more details.
  */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7501626ab529..d3133be12d92 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -427,6 +427,17 @@ enum {
 };
 
 enum {
+	/*
+	 * Max wqe size for rdma read is 512 bytes, so this
+	 * limits our max_sge_rd as the wqe needs to fit:
+	 * - ctrl segment (16 bytes)
+	 * - rdma segment (16 bytes)
+	 * - scatter elements (16 bytes each)
+	 */
+	MLX4_MAX_SGE_RD	= (512 - 16 - 16) / 16
+};
+
+enum {
 	MLX4_DEV_PMC_SUBTYPE_GUID_INFO	 = 0x14,
 	MLX4_DEV_PMC_SUBTYPE_PORT_INFO	 = 0x15,
 	MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE	 = 0x16,
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 877ef226f90f..772362adf471 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -1,6 +1,7 @@
 #ifndef LINUX_MM_DEBUG_H
 #define LINUX_MM_DEBUG_H 1
 
+#include <linux/bug.h>
 #include <linux/stringify.h>
 
 struct page;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3b5d134e945a..3143c847bddb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2084,7 +2084,7 @@ struct pcpu_sw_netstats {
 })
 
 #define netdev_alloc_pcpu_stats(type)					\
-	__netdev_alloc_pcpu_stats(type, GFP_KERNEL);
+	__netdev_alloc_pcpu_stats(type, GFP_KERNEL)
 
 #include <linux/notifier.h>
 
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 249d1bb01e03..5646b24bfc64 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -14,7 +14,7 @@ struct nfnl_callback {
 	int (*call_rcu)(struct sock *nl, struct sk_buff *skb, 
 		    const struct nlmsghdr *nlh,
 		    const struct nlattr * const cda[]);
-	int (*call_batch)(struct sock *nl, struct sk_buff *skb,
+	int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb,
 			  const struct nlmsghdr *nlh,
 			  const struct nlattr * const cda[]);
 	const struct nla_policy *policy;	/* netlink attribute policy */
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 039f2eec49ce..1e0deb8e8494 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -46,12 +46,14 @@ extern int of_irq_get(struct device_node *dev, int index);
 extern int of_irq_get_byname(struct device_node *dev, const char *name);
 extern int of_irq_to_resource_table(struct device_node *dev,
 		struct resource *res, int nr_irqs);
+extern struct device_node *of_irq_find_parent(struct device_node *child);
 extern struct irq_domain *of_msi_get_domain(struct device *dev,
 					    struct device_node *np,
 					    enum irq_domain_bus_token token);
 extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
 						       u32 rid);
 extern void of_msi_configure(struct device *dev, struct device_node *np);
+u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
@@ -70,6 +72,11 @@ static inline int of_irq_to_resource_table(struct device_node *dev,
 {
 	return 0;
 }
+static inline void *of_irq_find_parent(struct device_node *child)
+{
+	return NULL;
+}
+
 static inline struct irq_domain *of_msi_get_domain(struct device *dev,
 						   struct device_node *np,
 						   enum irq_domain_bus_token token)
@@ -84,6 +91,11 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
+static inline u32 of_msi_map_rid(struct device *dev,
+				 struct device_node *msi_np, u32 rid_in)
+{
+	return rid_in;
+}
 #endif
 
 #if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC)
@@ -93,7 +105,6 @@ static inline void of_msi_configure(struct device *dev, struct device_node *np)
  * so declare it here regardless of the CONFIG_OF_IRQ setting.
  */
 extern unsigned int irq_of_parse_and_map(struct device_node *node, int index);
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
 
 #else /* !CONFIG_OF && !CONFIG_SPARC */
 static inline unsigned int irq_of_parse_and_map(struct device_node *dev,
@@ -101,12 +112,6 @@ static inline unsigned int irq_of_parse_and_map(struct device_node *dev,
 {
 	return 0;
 }
-
-static inline u32 of_msi_map_rid(struct device *dev,
-				 struct device_node *msi_np, u32 rid_in)
-{
-	return rid_in;
-}
 #endif /* !CONFIG_OF */
 
 #endif /* __OF_IRQ_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d841d33bcdc9..f9828a48f16a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -697,9 +697,11 @@ struct perf_cgroup {
  * if there is no cgroup event for the current CPU context.
  */
 static inline struct perf_cgroup *
-perf_cgroup_from_task(struct task_struct *task)
+perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
 {
-	return container_of(task_css(task, perf_event_cgrp_id),
+	return container_of(task_css_check(task, perf_event_cgrp_id,
+					   ctx ? lockdep_is_held(&ctx->lock)
+					       : true),
 			    struct perf_cgroup, css);
 }
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h
index e2878baeb90e..4299f4ba03bd 100644
--- a/include/linux/platform_data/edma.h
+++ b/include/linux/platform_data/edma.h
@@ -72,7 +72,7 @@ struct edma_soc_info {
 	struct edma_rsv_info	*rsv;
 
 	/* List of channels allocated for memcpy, terminated with -1 */
-	s16			*memcpy_channels;
+	s32			*memcpy_channels;
 
 	s8	(*queue_priority_mapping)[2];
 	const s16	(*xbar_chans)[2];
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index 5440f64d2942..21221338ad18 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -1,7 +1,7 @@
 /*
  * FLoating proportions
  *
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * This file contains the public data structure and API definitions.
  */
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 6a4347639c03..1d1ba2c5ee7a 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -9,6 +9,8 @@
 #ifndef __COMMON_HSI__
 #define __COMMON_HSI__
 
+#define CORE_SPQE_PAGE_SIZE_BYTES                       4096
+
 #define FW_MAJOR_VERSION	8
 #define FW_MINOR_VERSION	4
 #define FW_REVISION_VERSION	2
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index b920c3605c46..41b9049b57e2 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -111,7 +111,8 @@ static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain)
 	used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) -
 		(u32)p_chain->cons_idx;
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= (used / p_chain->elem_per_page);
+		used -= p_chain->prod_idx / p_chain->elem_per_page -
+			p_chain->cons_idx / p_chain->elem_per_page;
 
 	return p_chain->capacity - used;
 }
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 843ceca9a21e..e50b31d18462 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -19,6 +19,7 @@
 
 #include <linux/atomic.h>
 #include <linux/compiler.h>
+#include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/jhash.h>
 #include <linux/list_nulls.h>
@@ -339,10 +340,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl,
 int rhashtable_init(struct rhashtable *ht,
 		    const struct rhashtable_params *params);
 
-int rhashtable_insert_slow(struct rhashtable *ht, const void *key,
-			   struct rhash_head *obj,
-			   struct bucket_table *old_tbl);
-int rhashtable_insert_rehash(struct rhashtable *ht);
+struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
+					    const void *key,
+					    struct rhash_head *obj,
+					    struct bucket_table *old_tbl);
+int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl);
 
 int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter);
 void rhashtable_walk_exit(struct rhashtable_iter *iter);
@@ -598,9 +600,11 @@ restart:
 
 	new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 	if (unlikely(new_tbl)) {
-		err = rhashtable_insert_slow(ht, key, obj, new_tbl);
-		if (err == -EAGAIN)
+		tbl = rhashtable_insert_slow(ht, key, obj, new_tbl);
+		if (!IS_ERR_OR_NULL(tbl))
 			goto slow_path;
+
+		err = PTR_ERR(tbl);
 		goto out;
 	}
 
@@ -611,7 +615,7 @@ restart:
 	if (unlikely(rht_grow_above_100(ht, tbl))) {
 slow_path:
 		spin_unlock_bh(lock);
-		err = rhashtable_insert_rehash(ht);
+		err = rhashtable_insert_rehash(ht, tbl);
 		rcu_read_unlock();
 		if (err)
 			return err;
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 0adedca24c5b..0e1b1540597a 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -99,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  * grabbing every spinlock (and more).  So the "read" side to such a
  * lock is anything which disables preemption.
  */
-#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP)
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 /**
  * stop_machine: freeze the machine on all CPUs and run this function
@@ -118,7 +118,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
 int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
-#else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#else	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 
 static inline int stop_machine(cpu_stop_fn_t fn, void *data,
 				 const struct cpumask *cpus)
@@ -137,5 +137,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 	return stop_machine(fn, data, cpus);
 }
 
-#endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#endif	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 #endif	/* _LINUX_STOP_MACHINE */
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 0bdc72f36905..4a29c75b146e 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -21,7 +21,7 @@
  * Authors:
  *	Srikar Dronamraju
  *	Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/errno.h>
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 9948c874e3f1..1d0043dc34e4 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -47,4 +47,7 @@
 /* device generates spurious wakeup, ignore remote wakeup capability */
 #define USB_QUIRK_IGNORE_REMOTE_WAKEUP		BIT(9)
 
+/* device can't handle Link Power Management */
+#define USB_QUIRK_NO_LPM			BIT(10)
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 610a86a892b8..ddb440975382 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -44,9 +44,6 @@ struct vfio_device_ops {
 	void	(*request)(void *device_data, unsigned int count);
 };
 
-extern struct iommu_group *vfio_iommu_group_get(struct device *dev);
-extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev);
-
 extern int vfio_add_group_dev(struct device *dev,
 			      const struct vfio_device_ops *ops,
 			      void *device_data);
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 1e1bf9f963a9..513b36f04dfd 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -145,7 +145,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 	list_del(&old->task_list);
 }
 
-typedef int wait_bit_action_f(struct wait_bit_key *);
+typedef int wait_bit_action_f(struct wait_bit_key *, int mode);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
@@ -960,10 +960,10 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 	} while (0)
 
 
-extern int bit_wait(struct wait_bit_key *);
-extern int bit_wait_io(struct wait_bit_key *);
-extern int bit_wait_timeout(struct wait_bit_key *);
-extern int bit_wait_io_timeout(struct wait_bit_key *);
+extern int bit_wait(struct wait_bit_key *, int);
+extern int bit_wait_io(struct wait_bit_key *, int);
+extern int bit_wait_timeout(struct wait_bit_key *, int);
+extern int bit_wait_io_timeout(struct wait_bit_key *, int);
 
 /**
  * wait_on_bit - wait for a bit to be cleared
diff --git a/include/net/dst.h b/include/net/dst.h
index 1279f9b09791..c7329dcd90cc 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -322,6 +322,39 @@ static inline void skb_dst_force(struct sk_buff *skb)
 	}
 }
 
+/**
+ * dst_hold_safe - Take a reference on a dst if possible
+ * @dst: pointer to dst entry
+ *
+ * This helper returns false if it could not safely
+ * take a reference on a dst.
+ */
+static inline bool dst_hold_safe(struct dst_entry *dst)
+{
+	if (dst->flags & DST_NOCACHE)
+		return atomic_inc_not_zero(&dst->__refcnt);
+	dst_hold(dst);
+	return true;
+}
+
+/**
+ * skb_dst_force_safe - makes sure skb dst is refcounted
+ * @skb: buffer
+ *
+ * If dst is not yet refcounted and not destroyed, grab a ref on it.
+ */
+static inline void skb_dst_force_safe(struct sk_buff *skb)
+{
+	if (skb_dst_is_noref(skb)) {
+		struct dst_entry *dst = skb_dst(skb);
+
+		if (!dst_hold_safe(dst))
+			dst = NULL;
+
+		skb->_skb_refdst = (unsigned long)dst;
+	}
+}
+
 
 /**
  *	__skb_tunnel_rx - prepare skb for rx reinsert
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 2134e6d815bc..625bdf95d673 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -210,18 +210,37 @@ struct inet_sock {
 #define IP_CMSG_ORIGDSTADDR	BIT(6)
 #define IP_CMSG_CHECKSUM	BIT(7)
 
-/* SYNACK messages might be attached to request sockets.
+/**
+ * sk_to_full_sk - Access to a full socket
+ * @sk: pointer to a socket
+ *
+ * SYNACK messages might be attached to request sockets.
  * Some places want to reach the listener in this case.
  */
-static inline struct sock *skb_to_full_sk(const struct sk_buff *skb)
+static inline struct sock *sk_to_full_sk(struct sock *sk)
 {
-	struct sock *sk = skb->sk;
-
+#ifdef CONFIG_INET
 	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
 		sk = inet_reqsk(sk)->rsk_listener;
+#endif
+	return sk;
+}
+
+/* sk_to_full_sk() variant with a const argument */
+static inline const struct sock *sk_const_to_full_sk(const struct sock *sk)
+{
+#ifdef CONFIG_INET
+	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
+		sk = ((const struct request_sock *)sk)->rsk_listener;
+#endif
 	return sk;
 }
 
+static inline struct sock *skb_to_full_sk(const struct sk_buff *skb)
+{
+	return sk_to_full_sk(skb->sk);
+}
+
 static inline struct inet_sock *inet_sk(const struct sock *sk)
 {
 	return (struct inet_sock *)sk;
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 4a6009d4486b..235c7811a86a 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -78,6 +78,7 @@ void inet_initpeers(void) __init;
 static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
 {
 	iaddr->a4.addr = ip;
+	iaddr->a4.vif = 0;
 	iaddr->family = AF_INET;
 }
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 7bbb71081aeb..eea9bdeecba2 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1493,7 +1493,8 @@ struct sctp_association {
 		 *             : SACK's are not delayed (see Section 6).
 		 */
 		__u8    sack_needed:1,     /* Do we need to sack the peer? */
-			sack_generation:1;
+			sack_generation:1,
+			zero_window_announced:1;
 		__u32	sack_cnt;
 
 		__u32   adaptation_ind;	 /* Adaptation Code point. */
diff --git a/include/net/sock.h b/include/net/sock.h
index 52d27ee924f4..14d3c0734007 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -388,7 +388,7 @@ struct sock {
 		struct socket_wq	*sk_wq_raw;
 	};
 #ifdef CONFIG_XFRM
-	struct xfrm_policy	*sk_policy[2];
+	struct xfrm_policy __rcu *sk_policy[2];
 #endif
 	struct dst_entry	*sk_rx_dst;
 	struct dst_entry __rcu	*sk_dst_cache;
@@ -404,6 +404,7 @@ struct sock {
 				sk_userlocks : 4,
 				sk_protocol  : 8,
 				sk_type      : 16;
+#define SK_PROTOCOL_MAX U8_MAX
 	kmemcheck_bitfield_end(flags);
 	int			sk_wmem_queued;
 	gfp_t			sk_allocation;
@@ -740,6 +741,8 @@ enum sock_flags {
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
 };
 
+#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+
 static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
 {
 	nsk->sk_flags = osk->sk_flags;
@@ -814,7 +817,7 @@ void sk_stream_write_space(struct sock *sk);
 static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	/* dont let skb dst not refcounted, we are going to leave rcu lock */
-	skb_dst_force(skb);
+	skb_dst_force_safe(skb);
 
 	if (!sk->sk_backlog.tail)
 		sk->sk_backlog.head = skb;
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index c1c899c3a51b..e289ada6adf6 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -79,7 +79,7 @@ struct vxlanhdr {
 };
 
 /* VXLAN header flags. */
-#define VXLAN_HF_RCO BIT(24)
+#define VXLAN_HF_RCO BIT(21)
 #define VXLAN_HF_VNI BIT(27)
 #define VXLAN_HF_GBP BIT(31)
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 4a9c21f9b4ea..d6f6e5006ee9 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -548,6 +548,7 @@ struct xfrm_policy {
 	u16			family;
 	struct xfrm_sec_ctx	*security;
 	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
+	struct rcu_head		rcu;
 };
 
 static inline struct net *xp_net(const struct xfrm_policy *xp)
@@ -1141,12 +1142,14 @@ static inline int xfrm6_route_forward(struct sk_buff *skb)
 	return xfrm_route_forward(skb, AF_INET6);
 }
 
-int __xfrm_sk_clone_policy(struct sock *sk);
+int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk);
 
-static inline int xfrm_sk_clone_policy(struct sock *sk)
+static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
 {
-	if (unlikely(sk->sk_policy[0] || sk->sk_policy[1]))
-		return __xfrm_sk_clone_policy(sk);
+	sk->sk_policy[0] = NULL;
+	sk->sk_policy[1] = NULL;
+	if (unlikely(osk->sk_policy[0] || osk->sk_policy[1]))
+		return __xfrm_sk_clone_policy(sk, osk);
 	return 0;
 }
 
@@ -1154,12 +1157,16 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir);
 
 static inline void xfrm_sk_free_policy(struct sock *sk)
 {
-	if (unlikely(sk->sk_policy[0] != NULL)) {
-		xfrm_policy_delete(sk->sk_policy[0], XFRM_POLICY_MAX);
+	struct xfrm_policy *pol;
+
+	pol = rcu_dereference_protected(sk->sk_policy[0], 1);
+	if (unlikely(pol != NULL)) {
+		xfrm_policy_delete(pol, XFRM_POLICY_MAX);
 		sk->sk_policy[0] = NULL;
 	}
-	if (unlikely(sk->sk_policy[1] != NULL)) {
-		xfrm_policy_delete(sk->sk_policy[1], XFRM_POLICY_MAX+1);
+	pol = rcu_dereference_protected(sk->sk_policy[1], 1);
+	if (unlikely(pol != NULL)) {
+		xfrm_policy_delete(pol, XFRM_POLICY_MAX+1);
 		sk->sk_policy[1] = NULL;
 	}
 }
@@ -1169,7 +1176,7 @@ void xfrm_garbage_collect(struct net *net);
 #else
 
 static inline void xfrm_sk_free_policy(struct sock *sk) {}
-static inline int xfrm_sk_clone_policy(struct sock *sk) { return 0; }
+static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; }
 static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; }  
 static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } 
 static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 188df91d5851..ec9b44dd3d80 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -237,6 +237,8 @@ struct ib_vendor_mad {
 	u8			data[IB_MGMT_VENDOR_DATA];
 };
 
+#define IB_MGMT_CLASSPORTINFO_ATTR_ID	cpu_to_be16(0x0001)
+
 struct ib_class_port_info {
 	u8			base_version;
 	u8			class_version;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 9a68a19532ba..120da1d7f57e 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1271,6 +1271,7 @@ struct ib_uobject {
 	int			id;		/* index into kernel idr */
 	struct kref		ref;
 	struct rw_semaphore	mutex;		/* protects .live */
+	struct rcu_head		rcu;		/* kfree_rcu() overhead */
 	int			live;
 };
 
diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h
index 2ae8812d7b1a..94dc6a9772e0 100644
--- a/include/sound/hda_register.h
+++ b/include/sound/hda_register.h
@@ -93,6 +93,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define AZX_REG_HSW_EM4			0x100c
 #define AZX_REG_HSW_EM5			0x1010
 
+/* Skylake/Broxton display HD-A controller Extended Mode registers */
+#define AZX_REG_SKL_EM4L		0x1040
+
 /* PCI space */
 #define AZX_PCIREG_TCSEL		0x44
 
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 628e6e64c2fb..c2e5d6cb34e3 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -186,6 +186,7 @@ header-y += if_tunnel.h
 header-y += if_vlan.h
 header-y += if_x25.h
 header-y += igmp.h
+header-y += ila.h
 header-y += in6.h
 header-y += inet_diag.h
 header-y += in.h
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 28ccedd000f5..a27222d5b413 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -628,7 +628,7 @@ struct ovs_action_hash {
  * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the
  * mask, the corresponding bit in the value is copied to the connection
  * tracking mark field in the connection.
- * @OVS_CT_ATTR_LABEL: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN
+ * @OVS_CT_ATTR_LABELS: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN
  * mask. For each bit set in the mask, the corresponding bit in the value is
  * copied to the connection tracking label field in the connection.
  * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG.
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 751b69f858c8..9fd7b5d8df2f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -39,13 +39,6 @@
 #define VFIO_SPAPR_TCE_v2_IOMMU		7
 
 /*
- * The No-IOMMU IOMMU offers no translation or isolation for devices and
- * supports no ioctls outside of VFIO_CHECK_EXTENSION.  Use of VFIO's No-IOMMU
- * code will taint the host kernel and should be used with extreme caution.
- */
-#define VFIO_NOIOMMU_IOMMU		8
-
-/*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between
  * kernel and userspace.  We therefore use the _IO() macro for these
diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h
index 7d28aff605c7..7dc685b4057d 100644
--- a/include/xen/interface/io/ring.h
+++ b/include/xen/interface/io/ring.h
@@ -181,6 +181,20 @@ struct __name##_back_ring {						\
 #define RING_GET_REQUEST(_r, _idx)					\
     (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
 
+/*
+ * Get a local copy of a request.
+ *
+ * Use this in preference to RING_GET_REQUEST() so all processing is
+ * done on a local copy that cannot be modified by the other end.
+ *
+ * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
+ * to be ineffective where _req is a struct which consists of only bitfields.
+ */
+#define RING_COPY_REQUEST(_r, _idx, _req) do {				\
+	/* Use volatile to force the copy into _req. */			\
+	*(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx);	\
+} while (0)
+
 #define RING_GET_RESPONSE(_r, _idx)					\
     (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))