Merge branch 'for-4.5/block-dax' into for-4.5/libnvdimm

28 files changed, 174 insertions, 75 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/badblocks.h b/include/linux/badblocks.h
new file mode 100644
index 000000000000..c3bdf8c59480
--- /dev/null
+++ b/include/linux/badblocks.h
@@ -0,0 +1,65 @@
+#ifndef _LINUX_BADBLOCKS_H
+#define _LINUX_BADBLOCKS_H
+
+#include <linux/seqlock.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+#define BB_LEN_MASK	(0x00000000000001FFULL)
+#define BB_OFFSET_MASK	(0x7FFFFFFFFFFFFE00ULL)
+#define BB_ACK_MASK	(0x8000000000000000ULL)
+#define BB_MAX_LEN	512
+#define BB_OFFSET(x)	(((x) & BB_OFFSET_MASK) >> 9)
+#define BB_LEN(x)	(((x) & BB_LEN_MASK) + 1)
+#define BB_ACK(x)	(!!((x) & BB_ACK_MASK))
+#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63))
+
+/* Bad block numbers are stored sorted in a single page.
+ * 64bits is used for each block or extent.
+ * 54 bits are sector number, 9 bits are extent size,
+ * 1 bit is an 'acknowledged' flag.
+ */
+#define MAX_BADBLOCKS	(PAGE_SIZE/8)
+
+struct badblocks {
+	struct device *dev;	/* set by devm_init_badblocks */
+	int count;		/* count of bad blocks */
+	int unacked_exist;	/* there probably are unacknowledged
+				 * bad blocks.  This is only cleared
+				 * when a read discovers none
+				 */
+	int shift;		/* shift from sectors to block size
+				 * a -ve shift means badblocks are
+				 * disabled.*/
+	u64 *page;		/* badblock list */
+	int changed;
+	seqlock_t lock;
+	sector_t sector;
+	sector_t size;		/* in sectors */
+};
+
+int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
+		   sector_t *first_bad, int *bad_sectors);
+int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
+			int acknowledged);
+int badblocks_clear(struct badblocks *bb, sector_t s, int sectors);
+void ack_all_badblocks(struct badblocks *bb);
+ssize_t badblocks_show(struct badblocks *bb, char *page, int unack);
+ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
+			int unack);
+int badblocks_init(struct badblocks *bb, int enable);
+void badblocks_exit(struct badblocks *bb);
+struct device;
+int devm_init_badblocks(struct device *dev, struct badblocks *bb);
+static inline void devm_exit_badblocks(struct device *dev, struct badblocks *bb)
+{
+	if (bb->dev != dev) {
+		dev_WARN_ONCE(dev, 1, "%s: badblocks instance not associated\n",
+				__func__);
+		return;
+	}
+	badblocks_exit(bb);
+}
+#endif
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/fs.h b/include/linux/fs.h
index 3aa514254161..96fabc93b583 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -482,6 +482,9 @@ struct block_device {
 	int			bd_fsfreeze_count;
 	/* Mutex for freeze */
 	struct mutex		bd_fsfreeze_mutex;
+#ifdef CONFIG_FS_DAX
+	int			bd_map_count;
+#endif
 };
 
 /*
@@ -2264,6 +2267,14 @@ extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
+#ifdef CONFIG_FS_DAX
+extern bool blkdev_dax_capable(struct block_device *bdev);
+#else
+static inline bool blkdev_dax_capable(struct block_device *bdev)
+{
+	return false;
+}
+#endif
 
 extern struct super_block *blockdev_superblock;
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 847cc1d91634..5c706765404a 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -162,6 +162,7 @@ struct disk_part_tbl {
 };
 
 struct disk_events;
+struct badblocks;
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
@@ -213,6 +214,7 @@ struct gendisk {
 	struct kobject integrity_kobj;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
 	int node_id;
+	struct badblocks *bb;
 };
 
 static inline struct gendisk *part_to_disk(struct hd_struct *part)
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/libnvdimm.h b/include/linux/libnvdimm.h
index 3f021dc5da8c..bed40dff0e86 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -116,6 +116,7 @@ static inline struct nd_blk_region_desc *to_blk_region_desc(
 
 }
 
+int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length);
 struct nvdimm_bus *__nvdimm_bus_register(struct device *parent,
 		struct nvdimm_bus_descriptor *nfit_desc, struct module *module);
 #define nvdimm_bus_register(parent, desc) \
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/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/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/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/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/fs.h b/include/uapi/linux/fs.h
index f15d980249b5..401c409e9239 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -152,6 +152,8 @@ struct inodes_stat_t {
 #define BLKSECDISCARD _IO(0x12,125)
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
+#define BLKDAXSET _IO(0x12,128)
+#define BLKDAXGET _IO(0x12,129)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
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