Merge tag 'kvm-arm-for-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-next

KVM/ARM changes for Linux v4.5

- Complete rewrite of the arm64 world switch in C, hopefully
  paving the way for more sharing with the 32bit code, better
  maintainability and easier integration of new features.
  Also smaller and slightly faster in some cases...
- Support for 16bit VM identifiers
- Various cleanups

33 files changed, 166 insertions, 248 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 054833939995..1991aea2ec4c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -870,8 +870,8 @@ static inline int acpi_dev_get_property(struct acpi_device *adev,
 }
 
 static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
-				const char *name, const char *cells_name,
-				size_t index, struct acpi_reference_args *args)
+				const char *name, size_t index,
+				struct acpi_reference_args *args)
 {
 	return -ENXIO;
 }
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/blkdev.h b/include/linux/blkdev.h
index c0d2b7927c1f..0169ba2e2e64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -254,6 +254,7 @@ struct queue_limits {
 	unsigned long		virt_boundary_mask;
 
 	unsigned int		max_hw_sectors;
+	unsigned int		max_dev_sectors;
 	unsigned int		chunk_sectors;
 	unsigned int		max_sectors;
 	unsigned int		max_segment_size;
@@ -773,7 +774,6 @@ extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
 		unsigned int len);
-extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 			     struct bio_set *bs, gfp_t gfp_mask,
@@ -960,7 +960,6 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
-extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de464e6683b6..83d1926c61e4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_map {
 	struct user_struct *user;
 	const struct bpf_map_ops *ops;
 	struct work_struct work;
+	atomic_t usercnt;
 };
 
 struct bpf_map_type_list {
@@ -167,8 +168,10 @@ struct bpf_prog *bpf_prog_get(u32 ufd);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
-struct bpf_map *bpf_map_get(u32 ufd);
+struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
+void bpf_map_inc(struct bpf_map *map, bool uref);
+void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
 extern int sysctl_unprivileged_bpf_disabled;
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/cpufreq.h b/include/linux/cpufreq.h
index ef4c5b1a860f..177c7680c1a8 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -77,6 +77,7 @@ struct cpufreq_policy {
 	unsigned int		suspend_freq; /* freq to set during suspend */
 
 	unsigned int		policy; /* see above */
+	unsigned int		last_policy; /* policy before unplug */
 	struct cpufreq_governor	*governor; /* see below */
 	void			*governor_data;
 	bool			governor_enabled; /* governor start/stop flag */
diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h
index cc92268af89a..6ac3cad9aef1 100644
--- a/include/linux/dns_resolver.h
+++ b/include/linux/dns_resolver.h
@@ -27,7 +27,7 @@
 #ifdef __KERNEL__
 
 extern int dns_query(const char *type, const char *name, size_t namelen,
-		     const char *options, char **_result, time_t *_expiry);
+		     const char *options, char **_result, time64_t *_expiry);
 
 #endif /* KERNEL */
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 0ef2a97ccdb5..402753bccafa 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -227,7 +227,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
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/kref.h b/include/linux/kref.h
index 484604d184be..e15828fd71f1 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -19,7 +19,6 @@
 #include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
-#include <linux/spinlock.h>
 
 struct kref {
 	atomic_t refcount;
@@ -99,38 +98,6 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)
 	return kref_sub(kref, 1, release);
 }
 
-/**
- * kref_put_spinlock_irqsave - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
- *	     last reference to the object is released.
- *	     This pointer is required, and it is not acceptable to pass kfree
- *	     in as this function.
- * @lock: lock to take in release case
- *
- * Behaves identical to kref_put with one exception.  If the reference count
- * drops to zero, the lock will be taken atomically wrt dropping the reference
- * count.  The release function has to call spin_unlock() without _irqrestore.
- */
-static inline int kref_put_spinlock_irqsave(struct kref *kref,
-		void (*release)(struct kref *kref),
-		spinlock_t *lock)
-{
-	unsigned long flags;
-
-	WARN_ON(release == NULL);
-	if (atomic_add_unless(&kref->refcount, -1, 1))
-		return 0;
-	spin_lock_irqsave(lock, flags);
-	if (atomic_dec_and_test(&kref->refcount)) {
-		release(kref);
-		local_irq_restore(flags);
-		return 1;
-	}
-	spin_unlock_irqrestore(lock, flags);
-	return 0;
-}
-
 static inline int kref_put_mutex(struct kref *kref,
 				 void (*release)(struct kref *kref),
 				 struct mutex *lock)
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 69c9057e1ab8..034117b3be5f 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -50,15 +50,21 @@ 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 {
 	u8	mtype;
 	u8	fmtype;
-	u16	res16;
 	u8	num_ch;
 	u8	num_lun;
 	u8	num_pln;
@@ -74,9 +80,9 @@ struct nvm_id_group {
 	u32	tbet;
 	u32	tbem;
 	u32	mpos;
+	u32	mccap;
 	u16	cpar;
-	u8	res[913];
-} __packed;
+};
 
 struct nvm_addr_format {
 	u8	ch_offset;
@@ -91,19 +97,15 @@ struct nvm_addr_format {
 	u8	pg_len;
 	u8	sect_offset;
 	u8	sect_len;
-	u8	res[4];
 };
 
 struct nvm_id {
 	u8	ver_id;
 	u8	vmnt;
 	u8	cgrps;
-	u8	res[5];
 	u32	cap;
 	u32	dom;
 	struct nvm_addr_format ppaf;
-	u8	ppat;
-	u8	resv[224];
 	struct nvm_id_group groups[4];
 } __packed;
 
@@ -123,39 +125,28 @@ struct nvm_tgt_instance {
 #define NVM_VERSION_MINOR 0
 #define NVM_VERSION_PATCH 0
 
-#define NVM_SEC_BITS (8)
-#define NVM_PL_BITS  (6)
-#define NVM_PG_BITS  (16)
 #define NVM_BLK_BITS (16)
-#define NVM_LUN_BITS (10)
+#define NVM_PG_BITS  (16)
+#define NVM_SEC_BITS (8)
+#define NVM_PL_BITS  (8)
+#define NVM_LUN_BITS (8)
 #define NVM_CH_BITS  (8)
 
 struct ppa_addr {
+	/* Generic structure for all addresses */
 	union {
-		/* Channel-based PPA format in nand 4x2x2x2x8x10 */
-		struct {
-			u64 ch		: 4;
-			u64 sec		: 2; /* 4 sectors per page */
-			u64 pl		: 2; /* 4 planes per LUN */
-			u64 lun		: 2; /* 4 LUNs per channel */
-			u64 pg		: 8; /* 256 pages per block */
-			u64 blk		: 10;/* 1024 blocks per plane */
-			u64 resved		: 36;
-		} chnl;
-
-		/* Generic structure for all addresses */
 		struct {
+			u64 blk		: NVM_BLK_BITS;
+			u64 pg		: NVM_PG_BITS;
 			u64 sec		: NVM_SEC_BITS;
 			u64 pl		: NVM_PL_BITS;
-			u64 pg		: NVM_PG_BITS;
-			u64 blk		: NVM_BLK_BITS;
 			u64 lun		: NVM_LUN_BITS;
 			u64 ch		: NVM_CH_BITS;
 		} g;
 
 		u64 ppa;
 	};
-} __packed;
+};
 
 struct nvm_rq {
 	struct nvm_tgt_instance *ins;
@@ -191,18 +182,18 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata)
 struct nvm_block;
 
 typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
-typedef int (nvm_bb_update_fn)(u32, void *, unsigned int, 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_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
+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 request_queue *, int, unsigned int,
+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);
 
@@ -210,7 +201,7 @@ struct nvm_dev_ops {
 	nvm_id_fn		*identity;
 	nvm_get_l2p_tbl_fn	*get_l2p_tbl;
 	nvm_op_bb_tbl_fn	*get_bb_tbl;
-	nvm_op_set_bb_fn	*set_bb;
+	nvm_op_set_bb_fn	*set_bb_tbl;
 
 	nvm_submit_io_fn	*submit_io;
 	nvm_erase_blk_fn	*erase_block;
@@ -220,7 +211,7 @@ struct nvm_dev_ops {
 	nvm_dev_dma_alloc_fn	*dev_dma_alloc;
 	nvm_dev_dma_free_fn	*dev_dma_free;
 
-	uint8_t			max_phys_sect;
+	unsigned int		max_phys_sect;
 };
 
 struct nvm_lun {
@@ -229,7 +220,9 @@ struct nvm_lun {
 	int lun_id;
 	int chnl_id;
 
+	unsigned int nr_inuse_blocks;	/* Number of used blocks */
 	unsigned int nr_free_blocks;	/* Number of unused blocks */
+	unsigned int nr_bad_blocks;	/* Number of bad blocks */
 	struct nvm_block *blocks;
 
 	spinlock_t lock;
@@ -263,8 +256,7 @@ struct nvm_dev {
 	int blks_per_lun;
 	int sec_size;
 	int oob_size;
-	int addr_mode;
-	struct nvm_addr_format addr_format;
+	struct nvm_addr_format ppaf;
 
 	/* Calculated/Cached values. These do not reflect the actual usable
 	 * blocks at run-time.
@@ -290,118 +282,45 @@ struct nvm_dev {
 	char name[DISK_NAME_LEN];
 };
 
-/* fallback conversion */
-static struct ppa_addr __generic_to_linear_addr(struct nvm_dev *dev,
-							struct ppa_addr r)
+static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
+						struct ppa_addr r)
 {
 	struct ppa_addr l;
 
-	l.ppa = r.g.sec +
-		r.g.pg  * dev->sec_per_pg +
-		r.g.blk * (dev->pgs_per_blk *
-				dev->sec_per_pg) +
-		r.g.lun * (dev->blks_per_lun *
-				dev->pgs_per_blk *
-				dev->sec_per_pg) +
-		r.g.ch * (dev->blks_per_lun *
-				dev->pgs_per_blk *
-				dev->luns_per_chnl *
-				dev->sec_per_pg);
+	l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset;
+	l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset;
+	l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset;
+	l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset;
+	l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset;
+	l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset;
 
 	return l;
 }
 
-/* fallback conversion */
-static struct ppa_addr __linear_to_generic_addr(struct nvm_dev *dev,
-							struct ppa_addr r)
+static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
+						struct ppa_addr r)
 {
 	struct ppa_addr l;
-	int secs, pgs, blks, luns;
-	sector_t ppa = r.ppa;
-
-	l.ppa = 0;
-
-	div_u64_rem(ppa, dev->sec_per_pg, &secs);
-	l.g.sec = secs;
 
-	sector_div(ppa, dev->sec_per_pg);
-	div_u64_rem(ppa, dev->sec_per_blk, &pgs);
-	l.g.pg = pgs;
-
-	sector_div(ppa, dev->pgs_per_blk);
-	div_u64_rem(ppa, dev->blks_per_lun, &blks);
-	l.g.blk = blks;
-
-	sector_div(ppa, dev->blks_per_lun);
-	div_u64_rem(ppa, dev->luns_per_chnl, &luns);
-	l.g.lun = luns;
-
-	sector_div(ppa, dev->luns_per_chnl);
-	l.g.ch = ppa;
-
-	return l;
-}
-
-static struct ppa_addr __generic_to_chnl_addr(struct ppa_addr r)
-{
-	struct ppa_addr l;
-
-	l.ppa = 0;
-
-	l.chnl.sec = r.g.sec;
-	l.chnl.pl = r.g.pl;
-	l.chnl.pg = r.g.pg;
-	l.chnl.blk = r.g.blk;
-	l.chnl.lun = r.g.lun;
-	l.chnl.ch = r.g.ch;
-
-	return l;
-}
-
-static struct ppa_addr __chnl_to_generic_addr(struct ppa_addr r)
-{
-	struct ppa_addr l;
-
-	l.ppa = 0;
-
-	l.g.sec = r.chnl.sec;
-	l.g.pl = r.chnl.pl;
-	l.g.pg = r.chnl.pg;
-	l.g.blk = r.chnl.blk;
-	l.g.lun = r.chnl.lun;
-	l.g.ch = r.chnl.ch;
+	/*
+	 * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc.
+	 */
+	l.g.blk = (r.ppa >> dev->ppaf.blk_offset) &
+					(((1 << dev->ppaf.blk_len) - 1));
+	l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) &
+					(((1 << dev->ppaf.pg_len) - 1));
+	l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) &
+					(((1 << dev->ppaf.sect_len) - 1));
+	l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) &
+					(((1 << dev->ppaf.pln_len) - 1));
+	l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) &
+					(((1 << dev->ppaf.lun_len) - 1));
+	l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) &
+					(((1 << dev->ppaf.ch_len) - 1));
 
 	return l;
 }
 
-static inline struct ppa_addr addr_to_generic_mode(struct nvm_dev *dev,
-						struct ppa_addr gppa)
-{
-	switch (dev->addr_mode) {
-	case NVM_ADDRMODE_LINEAR:
-		return __linear_to_generic_addr(dev, gppa);
-	case NVM_ADDRMODE_CHANNEL:
-		return __chnl_to_generic_addr(gppa);
-	default:
-		BUG();
-	}
-	return gppa;
-}
-
-static inline struct ppa_addr generic_to_addr_mode(struct nvm_dev *dev,
-						struct ppa_addr gppa)
-{
-	switch (dev->addr_mode) {
-	case NVM_ADDRMODE_LINEAR:
-		return __generic_to_linear_addr(dev, gppa);
-	case NVM_ADDRMODE_CHANNEL:
-		return __generic_to_chnl_addr(gppa);
-	default:
-		BUG();
-	}
-	return gppa;
-}
-
 static inline int ppa_empty(struct ppa_addr ppa_addr)
 {
 	return (ppa_addr.ppa == ADDR_EMPTY);
@@ -468,7 +387,7 @@ typedef int (nvmm_end_io_fn)(struct nvm_rq *, int);
 typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *,
 								unsigned long);
 typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int);
-typedef void (nvmm_free_blocks_print_fn)(struct nvm_dev *);
+typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *);
 
 struct nvmm_type {
 	const char *name;
@@ -492,7 +411,7 @@ struct nvmm_type {
 	nvmm_get_lun_fn *get_lun;
 
 	/* Statistics */
-	nvmm_free_blocks_print_fn *free_blocks_print;
+	nvmm_lun_info_print_fn *lun_info_print;
 	struct list_head list;
 };
 
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/net.h b/include/linux/net.h
index 70ac5e28e6b7..0b4ac7da583a 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -34,8 +34,12 @@ struct inode;
 struct file;
 struct net;
 
-#define SOCK_ASYNC_NOSPACE	0
-#define SOCK_ASYNC_WAITDATA	1
+/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located
+ * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
+ * Eventually all flags will be in sk->sk_wq_flags.
+ */
+#define SOCKWQ_ASYNC_NOSPACE	0
+#define SOCKWQ_ASYNC_WAITDATA	1
 #define SOCK_NOSPACE		2
 #define SOCK_PASSCRED		3
 #define SOCK_PASSSEC		4
@@ -89,6 +93,7 @@ struct socket_wq {
 	/* Note: wait MUST be first field of socket_wq */
 	wait_queue_head_t	wait;
 	struct fasync_struct	*fasync_list;
+	unsigned long		flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */
 	struct rcu_head		rcu;
 } ____cacheline_aligned_in_smp;
 
@@ -96,7 +101,7 @@ struct socket_wq {
  *  struct socket - general BSD socket
  *  @state: socket state (%SS_CONNECTED, etc)
  *  @type: socket type (%SOCK_STREAM, etc)
- *  @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
+ *  @flags: socket flags (%SOCK_NOSPACE, etc)
  *  @ops: protocol specific socket operations
  *  @file: File back pointer for gc
  *  @sk: internal networking protocol agnostic socket representation
@@ -202,7 +207,7 @@ enum {
 	SOCK_WAKE_URG,
 };
 
-int sock_wake_async(struct socket *sk, int how, int band);
+int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
 int sock_register(const struct net_proto_family *fam);
 void sock_unregister(int family);
 int __sock_create(struct net *net, int family, int type, int proto,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 67bfac1abfc1..3b5d134e945a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1398,7 +1398,8 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length
+ *	@hard_header_len: Hardware header length, which means that this is the
+ *			  minimum size of a packet.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 570d630f98ae..11bbae44f4cb 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -251,6 +251,7 @@ struct nfs4_layoutget {
 	struct nfs4_layoutget_res res;
 	struct rpc_cred *cred;
 	gfp_t gfp_flags;
+	long timeout;
 };
 
 struct nfs4_getdeviceinfo_args {
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/pci.h b/include/linux/pci.h
index e828e7b4afec..6ae25aae88fd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -412,9 +412,18 @@ struct pci_host_bridge {
 	void (*release_fn)(struct pci_host_bridge *);
 	void *release_data;
 	unsigned int ignore_reset_delay:1;	/* for entire hierarchy */
+	/* Resource alignment requirements */
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+			const struct resource *res,
+			resource_size_t start,
+			resource_size_t size,
+			resource_size_t align);
 };
 
 #define	to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev)
+
+struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);
+
 void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
 		     void (*release_fn)(struct pci_host_bridge *),
 		     void *release_data);
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/scpi_protocol.h b/include/linux/scpi_protocol.h
index 80af3cd35ae4..72ce932c69b2 100644
--- a/include/linux/scpi_protocol.h
+++ b/include/linux/scpi_protocol.h
@@ -71,7 +71,7 @@ struct scpi_ops {
 	int (*sensor_get_value)(u16, u32 *);
 };
 
-#if IS_ENABLED(CONFIG_ARM_SCPI_PROTOCOL)
+#if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL)
 struct scpi_ops *get_scpi_ops(void);
 #else
 static inline struct scpi_ops *get_scpi_ops(void) { return NULL; }
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/syscalls.h b/include/linux/syscalls.h
index a156b82dd14c..c2b66a277e98 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -524,7 +524,7 @@ asmlinkage long sys_chown(const char __user *filename,
 asmlinkage long sys_lchown(const char __user *filename,
 				uid_t user, gid_t group);
 asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group);
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 asmlinkage long sys_chown16(const char __user *filename,
 				old_uid_t user, old_gid_t group);
 asmlinkage long sys_lchown16(const char __user *filename,
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 4014a59828fc..613c29bd6baf 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -438,7 +438,8 @@ static inline void thermal_zone_device_unregister(
 static inline int thermal_zone_bind_cooling_device(
 	struct thermal_zone_device *tz, int trip,
 	struct thermal_cooling_device *cdev,
-	unsigned long upper, unsigned long lower)
+	unsigned long upper, unsigned long lower,
+	unsigned int weight)
 { return -ENODEV; }
 static inline int thermal_zone_unbind_cooling_device(
 	struct thermal_zone_device *tz, int trip,
diff --git a/include/linux/types.h b/include/linux/types.h
index 70d8500bddf1..70dd3dfde631 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -35,7 +35,7 @@ typedef __kernel_gid16_t        gid16_t;
 
 typedef unsigned long		uintptr_t;
 
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 /* This is defined by include/asm-{arch}/posix_types.h */
 typedef __kernel_old_uid_t	old_uid_t;
 typedef __kernel_old_gid_t	old_gid_t;
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