Merge tag 'v4.5-rc5' into devel

Linux 4.5-rc5

40 files changed, 215 insertions, 102 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 29189aeace19..4571ef1a12a9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -682,9 +682,12 @@ static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
 /*
  * q->prep_rq_fn return values
  */
-#define BLKPREP_OK              0       /* serve it */
-#define BLKPREP_KILL            1       /* fatal error, kill */
-#define BLKPREP_DEFER           2       /* leave on queue */
+enum {
+        BLKPREP_OK,             /* serve it */
+        BLKPREP_KILL,           /* fatal error, kill, return -EIO */
+        BLKPREP_DEFER,          /* leave on queue */
+        BLKPREP_INVALID,        /* invalid command, kill, return -EREMOTEIO */
+};
 
 extern unsigned long blk_max_low_pfn, blk_max_pfn;
 
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index f89b31d45cc8..c1ef6f14e7be 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -63,6 +63,18 @@
 #define CEPH_FEATURE_OSD_MIN_SIZE_RECOVERY (1ULL<<49)
 // duplicated since it was introduced at the same time as MIN_SIZE_RECOVERY
 #define CEPH_FEATURE_OSD_PROXY_FEATURES (1ULL<<49)  /* overlap w/ above */
+#define CEPH_FEATURE_MON_METADATA (1ULL<<50)
+#define CEPH_FEATURE_OSD_BITWISE_HOBJ_SORT (1ULL<<51) /* can sort objs bitwise */
+#define CEPH_FEATURE_OSD_PROXY_WRITE_FEATURES (1ULL<<52)
+#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V3 (1ULL<<53)
+#define CEPH_FEATURE_OSD_HITSET_GMT (1ULL<<54)
+#define CEPH_FEATURE_HAMMER_0_94_4 (1ULL<<55)
+#define CEPH_FEATURE_NEW_OSDOP_ENCODING   (1ULL<<56) /* New, v7 encoding */
+#define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */
+#define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */
+#define CEPH_FEATURE_CRUSH_TUNABLES5    (1ULL<<58) /* chooseleaf stable mode */
+// duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5
+#define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING   (1ULL<<58) /* New, v7 encoding */
 
 /*
  * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature
@@ -108,7 +120,9 @@ static inline u64 ceph_sanitize_features(u64 features)
          CEPH_FEATURE_CRUSH_TUNABLES3 |         \
          CEPH_FEATURE_OSD_PRIMARY_AFFINITY |    \
          CEPH_FEATURE_MSGR_KEEPALIVE2 |         \
-         CEPH_FEATURE_CRUSH_V4)
+         CEPH_FEATURE_CRUSH_V4 |                \
+         CEPH_FEATURE_CRUSH_TUNABLES5 |         \
+         CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
         (CEPH_FEATURE_NOSRCADDR |        \
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 7f540f7f588d..789471dba6fb 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -127,6 +127,12 @@ struct cgroup_subsys_state {
          */
         u64 serial_nr;
 
+        /*
+         * Incremented by online self and children.  Used to guarantee that
+         * parents are not offlined before their children.
+         */
+        atomic_t online_cnt;
+
         /* percpu_ref killing and RCU release */
         struct rcu_head rcu_head;
         struct work_struct destroy_work;
diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h
index bda5ec0b4b4d..fccf7f44139d 100644
--- a/include/linux/cleancache.h
+++ b/include/linux/cleancache.h
@@ -37,7 +37,7 @@ struct cleancache_ops {
         void (*invalidate_fs)(int);
 };
 
-extern int cleancache_register_ops(struct cleancache_ops *ops);
+extern int cleancache_register_ops(const struct cleancache_ops *ops);
 extern void __cleancache_init_fs(struct super_block *);
 extern void __cleancache_init_shared_fs(struct super_block *);
 extern int  __cleancache_get_page(struct page *);
@@ -48,14 +48,14 @@ extern void __cleancache_invalidate_fs(struct super_block *);
 
 #ifdef CONFIG_CLEANCACHE
 #define cleancache_enabled (1)
-static inline bool cleancache_fs_enabled(struct page *page)
-{
-        return page->mapping->host->i_sb->cleancache_poolid >= 0;
-}
 static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping)
 {
         return mapping->host->i_sb->cleancache_poolid >= 0;
 }
+static inline bool cleancache_fs_enabled(struct page *page)
+{
+        return cleancache_fs_enabled_mapping(page->mapping);
+}
 #else
 #define cleancache_enabled (0)
 #define cleancache_fs_enabled(_page) (0)
@@ -89,11 +89,9 @@ static inline void cleancache_init_shared_fs(struct super_block *sb)
 
 static inline int cleancache_get_page(struct page *page)
 {
-        int ret = -1;
-
         if (cleancache_enabled && cleancache_fs_enabled(page))
-                ret = __cleancache_get_page(page);
-        return ret;
+                return __cleancache_get_page(page);
+        return -1;
 }
 
 static inline void cleancache_put_page(struct page *page)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 00b042c49ccd..48f5aab117ae 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -144,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  */
 #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
 #define __trace_if(cond) \
-        if (__builtin_constant_p((cond)) ? !!(cond) :                   \
+        if (__builtin_constant_p(!!(cond)) ? !!(cond) :                 \
         ({                                                              \
                 int ______r;                                            \
                 static struct ftrace_branch_data                        \
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 85a868ccb493..fea160ee5803 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -137,6 +137,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
         task_unlock(current);
 }
 
+extern void cpuset_post_attach_flush(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -243,6 +245,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
         return false;
 }
 
+static inline void cpuset_post_attach_flush(void)
+{
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 48b49305716b..be8f12b8f195 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -59,7 +59,8 @@ enum {
         CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */
         CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10,
         CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11,
-        CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12
+        CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12,
+        CRUSH_RULE_SET_CHOOSELEAF_STABLE = 13
 };
 
 /*
@@ -205,6 +206,11 @@ struct crush_map {
          * mappings line up a bit better with previous mappings. */
         __u8 chooseleaf_vary_r;
 
+        /* if true, it makes chooseleaf firstn to return stable results (if
+         * no local retry) so that data migrations would be optimal when some
+         * device fails. */
+        __u8 chooseleaf_stable;
+
 #ifndef __KERNEL__
         /*
          * version 0 (original) of straw_calc has various flaws.  version 1
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8204c3dc3800..818e45078929 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -14,6 +14,17 @@ int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
                 dax_iodone_t);
 int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
                 dax_iodone_t);
+
+#ifdef CONFIG_FS_DAX
+struct page *read_dax_sector(struct block_device *bdev, sector_t n);
+#else
+static inline struct page *read_dax_sector(struct block_device *bdev,
+                sector_t n)
+{
+        return ERR_PTR(-ENXIO);
+}
+#endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
                                 unsigned int flags, get_block_t, dax_iodone_t);
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 251a2090a554..e0ee0b3000b2 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -19,6 +19,8 @@
 
 int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
+void devpts_add_ref(struct inode *ptmx_inode);
+void devpts_del_ref(struct inode *ptmx_inode);
 /* mknod in devpts */
 struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
                 void *priv);
@@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode);
 /* Dummy stubs in the no-pty case */
 static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
 static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
+static inline void devpts_add_ref(struct inode *ptmx_inode) { }
+static inline void devpts_del_ref(struct inode *ptmx_inode) { }
 static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
                 dev_t device, int index, void *priv)
 {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 569b5a866bb1..47be3ad7d3e5 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1199,7 +1199,10 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *),
 struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
                                        struct list_head *head, bool remove);
 
-bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len);
+bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+                     unsigned long data_size);
+bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
+                                  size_t len);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1a2046275cdf..ae681002100a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -484,9 +484,6 @@ struct block_device {
         int                     bd_fsfreeze_count;
         /* Mutex for freeze */
         struct mutex            bd_fsfreeze_mutex;
-#ifdef CONFIG_FS_DAX
-        int                     bd_map_count;
-#endif
 };
 
 /*
@@ -2907,7 +2904,7 @@ extern void replace_mount_options(struct super_block *sb, char *options);
 
 static inline bool io_is_direct(struct file *filp)
 {
-        return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
+        return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
 }
 
 static inline int iocb_flags(struct file *file)
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 6b7e89f45aa4..533c4408529a 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -220,10 +220,7 @@ struct fsnotify_mark {
         /* List of marks by group->i_fsnotify_marks. Also reused for queueing
          * mark into destroy_list when it's waiting for the end of SRCU period
          * before it can be freed. [group->mark_mutex] */
-        union {
-                struct list_head g_list;
-                struct rcu_head g_rcu;
-        };
+        struct list_head g_list;
         /* Protects inode / mnt pointers, flags, masks */
         spinlock_t lock;
         /* List of marks for inode / vfsmount [obj_lock] */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 0639dcc98195..c2b340e23f62 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -165,7 +165,6 @@ struct ftrace_ops {
         ftrace_func_t                   saved_func;
         int __percpu                    *disabled;
 #ifdef CONFIG_DYNAMIC_FTRACE
-        int                             nr_trampolines;
         struct ftrace_ops_hash          local_hash;
         struct ftrace_ops_hash          *func_hash;
         struct ftrace_ops_hash          old_hash;
@@ -604,6 +603,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
+extern void ftrace_module_enable(struct module *mod);
 extern void ftrace_release_mod(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
@@ -613,8 +613,9 @@ static inline int skip_trace(unsigned long ip) { return 0; }
 static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
-static inline void ftrace_release_mod(struct module *mod) {}
-static inline void ftrace_module_init(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) { }
+static inline void ftrace_module_enable(struct module *mod) { }
+static inline void ftrace_release_mod(struct module *mod) { }
 static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
         return -EINVAL;
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 28ad5f6494b0..af1f2b24bbe4 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -547,16 +547,16 @@ static inline bool pm_suspended_storage(void)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-#ifdef CONFIG_CMA
-
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 /* The below functions must be run on a range from a single zone. */
 extern int alloc_contig_range(unsigned long start, unsigned long end,
                               unsigned migratetype);
 extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
+#endif
 
+#ifdef CONFIG_CMA
 /* CMA stuff */
 extern void init_cma_reserved_pageblock(struct page *page);
-
 #endif
 
 #endif /* __LINUX_GFP_H */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 76dd4f0da5ca..2ead22dd74a0 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -87,7 +87,8 @@ enum hrtimer_restart {
  * @function:   timer expiry callback function
  * @base:       pointer to the timer base (per cpu and per clock)
  * @state:      state information (See bit values above)
- * @start_pid: timer statistics field to store the pid of the task which
+ * @is_rel:     Set if the timer was armed relative
+ * @start_pid:  timer statistics field to store the pid of the task which
  *              started the timer
  * @start_site: timer statistics field to store the site where the timer
  *              was started
@@ -101,7 +102,8 @@ struct hrtimer {
         ktime_t                         _softexpires;
         enum hrtimer_restart            (*function)(struct hrtimer *);
         struct hrtimer_clock_base       *base;
-        unsigned long                   state;
+        u8                              state;
+        u8                              is_rel;
 #ifdef CONFIG_TIMER_STATS
         int                             start_pid;
         void                            *start_site;
@@ -321,6 +323,27 @@ static inline void clock_was_set_delayed(void) { }
 
 #endif
 
+static inline ktime_t
+__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now)
+{
+        ktime_t rem = ktime_sub(timer->node.expires, now);
+
+        /*
+         * Adjust relative timers for the extra we added in
+         * hrtimer_start_range_ns() to prevent short timeouts.
+         */
+        if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel)
+                rem.tv64 -= hrtimer_resolution;
+        return rem;
+}
+
+static inline ktime_t
+hrtimer_expires_remaining_adjusted(const struct hrtimer *timer)
+{
+        return __hrtimer_expires_remaining_adjusted(timer,
+                                                    timer->base->get_time());
+}
+
 extern void clock_was_set(void);
 #ifdef CONFIG_TIMERFD
 extern void timerfd_clock_was_set(void);
@@ -390,7 +413,12 @@ static inline void hrtimer_restart(struct hrtimer *timer)
 }
 
 /* Query timers: */
-extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
+extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
+
+static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
+{
+        return __hrtimer_get_remaining(timer, false);
+}
 
 extern u64 hrtimer_get_next_event(void);
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 821273ca4873..2d9b650047a5 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -235,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 /* low 64 bit */
 #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT))
 
+/* PRS_REG */
+#define DMA_PRS_PPR     ((u32)1)
+
 #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)                     \
 do {                                                                    \
         cycles_t start_time = get_cycles();                             \
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f28dff313b07..a5c539fa5d2b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -133,8 +133,9 @@ struct iommu_dm_region {
 
 /**
  * struct iommu_ops - iommu ops and capabilities
- * @domain_init: init iommu domain
- * @domain_destroy: destroy iommu domain
+ * @capable: check capability
+ * @domain_alloc: allocate iommu domain
+ * @domain_free: free iommu domain
  * @attach_dev: attach device to an iommu domain
  * @detach_dev: detach device from an iommu domain
  * @map: map a physically contiguous memory region to an iommu domain
@@ -144,8 +145,15 @@ struct iommu_dm_region {
  * @iova_to_phys: translate iova to physical address
  * @add_device: add device to iommu grouping
  * @remove_device: remove device from iommu grouping
+ * @device_group: find iommu group for a particular device
  * @domain_get_attr: Query domain attributes
  * @domain_set_attr: Change domain attributes
+ * @get_dm_regions: Request list of direct mapping requirements for a device
+ * @put_dm_regions: Free list of direct mapping requirements for a device
+ * @domain_window_enable: Configure and enable a particular window for a domain
+ * @domain_window_disable: Disable a particular window for a domain
+ * @domain_set_windows: Set the number of windows for a domain
+ * @domain_get_windows: Return the number of windows for a domain
  * @of_xlate: add OF master IDs to iommu grouping
  * @pgsize_bitmap: bitmap of supported page sizes
  * @priv: per-instance data private to the iommu driver
@@ -182,9 +190,9 @@ struct iommu_ops {
         int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
                                     phys_addr_t paddr, u64 size, int prot);
         void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr);
-        /* Set the numer of window per domain */
+        /* Set the number of windows per domain */
         int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count);
-        /* Get the numer of window per domain */
+        /* Get the number of windows per domain */
         u32 (*domain_get_windows)(struct iommu_domain *domain);
 
 #ifdef CONFIG_OF_IOMMU
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index f64622ad02c1..04579d9fbce4 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -70,6 +70,7 @@ struct irq_fwspec {
  */
 enum irq_domain_bus_token {
         DOMAIN_BUS_ANY          = 0,
+        DOMAIN_BUS_WIRED,
         DOMAIN_BUS_PCI_MSI,
         DOMAIN_BUS_PLATFORM_MSI,
         DOMAIN_BUS_NEXUS,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 851821bfd553..bec2abbd7ab2 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -526,6 +526,7 @@ enum ata_lpm_policy {
 enum ata_lpm_hints {
         ATA_LPM_EMPTY           = (1 << 0), /* port empty/probing */
         ATA_LPM_HIPM            = (1 << 1), /* may use HIPM */
+        ATA_LPM_WAKE_ONLY       = (1 << 2), /* only wake up link */
 };
 
 /* forward declarations */
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index d6750111e48e..2190419bdf0a 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -135,6 +135,10 @@ enum {
         /* Memory types */
         NVM_ID_FMTYPE_SLC       = 0,
         NVM_ID_FMTYPE_MLC       = 1,
+
+        /* Device capabilities */
+        NVM_ID_DCAP_BBLKMGMT    = 0x1,
+        NVM_UD_DCAP_ECC         = 0x2,
 };
 
 struct nvm_id_lp_mlc {
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index c57e424d914b..4dca42fd32f5 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -66,7 +66,7 @@ struct lock_class {
         /*
          * class-hash:
          */
-        struct list_head                hash_entry;
+        struct hlist_node               hash_entry;
 
         /*
          * global list of all lock-classes:
@@ -199,7 +199,7 @@ struct lock_chain {
         u8                              irq_context;
         u8                              depth;
         u16                             base;
-        struct list_head                entry;
+        struct hlist_node               entry;
         u64                             chain_key;
 };
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9ae48d4aeb5e..792c8981e633 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -51,7 +51,7 @@ enum mem_cgroup_stat_index {
         MEM_CGROUP_STAT_SWAP,           /* # of pages, swapped out */
         MEM_CGROUP_STAT_NSTATS,
         /* default hierarchy stats */
-        MEMCG_SOCK,
+        MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS,
         MEMCG_NR_STAT,
 };
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f1cd22f2df1a..516e14944339 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -201,11 +201,13 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 
 #ifdef CONFIG_STACK_GROWSUP
-#define VM_STACK_FLAGS  (VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+#define VM_STACK        VM_GROWSUP
 #else
-#define VM_STACK_FLAGS  (VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+#define VM_STACK        VM_GROWSDOWN
 #endif
 
+#define VM_STACK_FLAGS  (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+
 /*
  * Special vmas that are non-mergable, non-mlock()able.
  * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
@@ -1341,8 +1343,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
                 !vma_growsup(vma->vm_next, addr);
 }
 
-extern struct task_struct *task_of_stack(struct task_struct *task,
-                                struct vm_area_struct *vma, bool in_group);
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
                 unsigned long old_addr, struct vm_area_struct *new_vma,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d3ebb9d21a53..624b78b848b8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -424,9 +424,9 @@ struct mm_struct {
         unsigned long total_vm;         /* Total pages mapped */
         unsigned long locked_vm;        /* Pages that have PG_mlocked set */
         unsigned long pinned_vm;        /* Refcount permanently increased */
-        unsigned long data_vm;          /* VM_WRITE & ~VM_SHARED/GROWSDOWN */
-        unsigned long exec_vm;          /* VM_EXEC & ~VM_WRITE */
-        unsigned long stack_vm;         /* VM_GROWSUP/DOWN */
+        unsigned long data_vm;          /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
+        unsigned long exec_vm;          /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
+        unsigned long stack_vm;         /* VM_STACK */
         unsigned long def_flags;
         unsigned long start_code, end_code, start_data, end_data;
         unsigned long start_brk, brk, start_stack;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 33bb1b19273e..7b6c2cfee390 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -682,6 +682,12 @@ typedef struct pglist_data {
          */
         unsigned long first_deferred_pfn;
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+        spinlock_t split_queue_lock;
+        struct list_head split_queue;
+        unsigned long split_queue_len;
+#endif
 } pg_data_t;
 
 #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages)
diff --git a/include/linux/module.h b/include/linux/module.h
index 4560d8f1545d..2bb0c3085706 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -324,6 +324,12 @@ struct module_layout {
 #define __module_layout_align
 #endif
 
+struct mod_kallsyms {
+        Elf_Sym *symtab;
+        unsigned int num_symtab;
+        char *strtab;
+};
+
 struct module {
         enum module_state state;
 
@@ -405,15 +411,10 @@ struct module {
 #endif
 
 #ifdef CONFIG_KALLSYMS
-        /*
-         * We keep the symbol and string tables for kallsyms.
-         * The core_* fields below are temporary, loader-only (they
-         * could really be discarded after module init).
-         */
-        Elf_Sym *symtab, *core_symtab;
-        unsigned int num_symtab, core_num_syms;
-        char *strtab, *core_strtab;
-
+        /* Protected by RCU and/or module_mutex: use rcu_dereference() */
+        struct mod_kallsyms *kallsyms;
+        struct mod_kallsyms core_kallsyms;
+        
         /* Section attributes */
         struct module_sect_attrs *sect_attrs;
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5ac140dcb789..289c2314d766 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -512,7 +512,6 @@ static inline void napi_enable(struct napi_struct *n)
         clear_bit(NAPI_STATE_NPSVC, &n->state);
 }
 
-#ifdef CONFIG_SMP
 /**
  *      napi_synchronize - wait until NAPI is not running
  *      @n: napi context
@@ -523,12 +522,12 @@ static inline void napi_enable(struct napi_struct *n)
  */
 static inline void napi_synchronize(const struct napi_struct *n)
 {
-        while (test_bit(NAPI_STATE_SCHED, &n->state))
-                msleep(1);
+        if (IS_ENABLED(CONFIG_SMP))
+                while (test_bit(NAPI_STATE_SCHED, &n->state))
+                        msleep(1);
+        else
+                barrier();
 }
-#else
-# define napi_synchronize(n)    barrier()
-#endif
 
 enum netdev_queue_state_t {
         __QUEUE_STATE_DRV_XOFF,
diff --git a/include/linux/of.h b/include/linux/of.h
index dd10626a615f..dc6e39696b64 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -929,7 +929,7 @@ static inline int of_get_available_child_count(const struct device_node *np)
         return num;
 }
 
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && !defined(MODULE)
 #define _OF_DECLARE(table, name, compat, fn, fn_type)                   \
         static const struct of_device_id __of_table_##name              \
                 __used __section(__##table##_of_table)                  \
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f9828a48f16a..b35a61a481fa 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -634,9 +634,6 @@ struct perf_event_context {
         int                             nr_cgroups;      /* cgroup evts */
         void                            *task_ctx_data; /* pmu specific data */
         struct rcu_head                 rcu_head;
-
-        struct delayed_work             orphans_remove;
-        bool                            orphans_remove_sched;
 };
 
 /*
@@ -729,7 +726,7 @@ extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
 extern void perf_event_delayed_put(struct task_struct *task);
-extern struct perf_event *perf_event_get(unsigned int fd);
+extern struct file *perf_event_get(unsigned int fd);
 extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
 extern void perf_event_print_debug(void);
 extern void perf_pmu_disable(struct pmu *pmu);
@@ -1044,7 +1041,7 @@ extern void perf_swevent_put_recursion_context(int rctx);
 extern u64 perf_swevent_set_period(struct perf_event *event);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
-extern int __perf_event_disable(void *info);
+extern void perf_event_disable_local(struct perf_event *event);
 extern void perf_event_task_tick(void);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
@@ -1070,7 +1067,7 @@ static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)      { }
 static inline void perf_event_free_task(struct task_struct *task)       { }
 static inline void perf_event_delayed_put(struct task_struct *task)     { }
-static inline struct perf_event *perf_event_get(unsigned int fd)        { return ERR_PTR(-EINVAL); }
+static inline struct file *perf_event_get(unsigned int fd)      { return ERR_PTR(-EINVAL); }
 static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 {
         return ERR_PTR(-EINVAL);
diff --git a/include/linux/pfn.h b/include/linux/pfn.h
index 2d8e49711b63..1132953235c0 100644
--- a/include/linux/pfn.h
+++ b/include/linux/pfn.h
@@ -10,7 +10,7 @@
  * backing is indicated by flags in the high bits of the value.
  */
 typedef struct {
-        unsigned long val;
+        u64 val;
 } pfn_t;
 #endif
 
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 0703b5360d31..94994810c7c0 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -9,14 +9,13 @@
  * PFN_DEV - pfn is not covered by system memmap by default
  * PFN_MAP - pfn has a dynamic page mapping established by a device driver
  */
-#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \
-                << (BITS_PER_LONG - PAGE_SHIFT))
-#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1))
-#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2))
-#define PFN_DEV (1UL << (BITS_PER_LONG - 3))
-#define PFN_MAP (1UL << (BITS_PER_LONG - 4))
-
-static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags)
+#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
+#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
+#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
+#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
+#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
+
+static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
         pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
 
@@ -29,7 +28,7 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn)
         return __pfn_to_pfn_t(pfn, 0);
 }
 
-extern pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags);
+extern pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags);
 
 static inline bool pfn_t_has_page(pfn_t pfn)
 {
@@ -48,7 +47,7 @@ static inline struct page *pfn_t_to_page(pfn_t pfn)
         return NULL;
 }
 
-static inline dma_addr_t pfn_t_to_phys(pfn_t pfn)
+static inline phys_addr_t pfn_t_to_phys(pfn_t pfn)
 {
         return PFN_PHYS(pfn_t_to_pfn(pfn));
 }
@@ -87,7 +86,7 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
 #ifdef __HAVE_ARCH_PTE_DEVMAP
 static inline bool pfn_t_devmap(pfn_t pfn)
 {
-        const unsigned long flags = PFN_DEV|PFN_MAP;
+        const u64 flags = PFN_DEV|PFN_MAP;
 
         return (pfn.val & flags) == flags;
 }
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 7c88ad156a29..f54be7082207 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -379,12 +379,28 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
                              struct radix_tree_iter *iter, unsigned flags);
 
 /**
+ * radix_tree_iter_retry - retry this chunk of the iteration
+ * @iter:       iterator state
+ *
+ * If we iterate over a tree protected only by the RCU lock, a race
+ * against deletion or creation may result in seeing a slot for which
+ * radix_tree_deref_retry() returns true.  If so, call this function
+ * and continue the iteration.
+ */
+static inline __must_check
+void **radix_tree_iter_retry(struct radix_tree_iter *iter)
+{
+        iter->next_index = iter->index;
+        return NULL;
+}
+
+/**
  * radix_tree_chunk_size - get current chunk size
  *
  * @iter:       pointer to radix tree iterator
  * Returns:     current chunk size
  */
-static __always_inline unsigned
+static __always_inline long
 radix_tree_chunk_size(struct radix_tree_iter *iter)
 {
         return iter->next_index - iter->index;
@@ -418,9 +434,9 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags)
                         return slot + offset + 1;
                 }
         } else {
-                unsigned size = radix_tree_chunk_size(iter) - 1;
+                long size = radix_tree_chunk_size(iter);
 
-                while (size--) {
+                while (--size > 0) {
                         slot++;
                         iter->index++;
                         if (likely(*slot))
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index a7a06d1dcf9c..a0118d5929a9 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -152,6 +152,8 @@ void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
 
 # define jiffies        raid6_jiffies()
 # define printk         printf
+# define pr_err(format, ...) fprintf(stderr, format, ## __VA_ARGS__)
+# define pr_info(format, ...) fprintf(stdout, format, ## __VA_ARGS__)
 # define GFP_KERNEL     0
 # define __get_free_pages(x, y) ((unsigned long)mmap(NULL, PAGE_SIZE << (y), \
                                                      PROT_READ|PROT_WRITE,   \
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bdf597c4f0be..a07f42bedda3 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -109,20 +109,6 @@ static inline void put_anon_vma(struct anon_vma *anon_vma)
                 __put_anon_vma(anon_vma);
 }
 
-static inline void vma_lock_anon_vma(struct vm_area_struct *vma)
-{
-        struct anon_vma *anon_vma = vma->anon_vma;
-        if (anon_vma)
-                down_write(&anon_vma->root->rwsem);
-}
-
-static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
-{
-        struct anon_vma *anon_vma = vma->anon_vma;
-        if (anon_vma)
-                up_write(&anon_vma->root->rwsem);
-}
-
 static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
 {
         down_write(&anon_vma->root->rwsem);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 11f935c1a090..4ce9ff7086f4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -299,6 +299,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index e7a018eaf3a2..017fced60242 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -1,10 +1,13 @@
 #ifndef __LINUX_SWIOTLB_H
 #define __LINUX_SWIOTLB_H
 
+#include <linux/dma-direction.h>
+#include <linux/init.h>
 #include <linux/types.h>
 
 struct device;
 struct dma_attrs;
+struct page;
 struct scatterlist;
 
 extern int swiotlb_force;
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index acd522a91539..acfdbf353a0b 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -14,8 +14,10 @@
  * See the file COPYING for more details.
  */
 
+#include <linux/smp.h>
 #include <linux/errno.h>
 #include <linux/types.h>
+#include <linux/cpumask.h>
 #include <linux/rcupdate.h>
 #include <linux/tracepoint-defs.h>
 
@@ -132,6 +134,9 @@ extern void syscall_unregfunc(void);
                 void *it_func;                                          \
                 void *__data;                                           \
                                                                         \
+                if (!cpu_online(raw_smp_processor_id()))                \
+                        return;                                         \
+                                                                        \
                 if (!(cond))                                            \
                         return;                                         \
                 prercu;                                                 \
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 2fd8708ea888..d9fb4b043f56 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -649,6 +649,7 @@ extern long vt_compat_ioctl(struct tty_struct *tty,
 /* tty_mutex.c */
 /* functions for preparation of BKL removal */
 extern void __lockfunc tty_lock(struct tty_struct *tty);
+extern int  tty_lock_interruptible(struct tty_struct *tty);
 extern void __lockfunc tty_unlock(struct tty_struct *tty);
 extern void __lockfunc tty_lock_slave(struct tty_struct *tty);
 extern void __lockfunc tty_unlock_slave(struct tty_struct *tty);
diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h
index cbb20afdbc01..bb679b48f408 100644
--- a/include/linux/ucs2_string.h
+++ b/include/linux/ucs2_string.h
@@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s);
 unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
 int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
 
+unsigned long ucs2_utf8size(const ucs2_char_t *src);
+unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
+                           unsigned long maxlength);
+
 #endif /* _LINUX_UCS2_STRING_H_ */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0e32bc71245e..ca73c503b92a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -311,6 +311,7 @@ enum {
 
         __WQ_DRAINING           = 1 << 16, /* internal: workqueue is draining */
         __WQ_ORDERED            = 1 << 17, /* internal: workqueue is ordered */
+        __WQ_LEGACY             = 1 << 18, /* internal: create*_workqueue() */
 
         WQ_MAX_ACTIVE           = 512,    /* I like 512, better ideas? */
         WQ_MAX_UNBOUND_PER_CPU  = 4,      /* 4 * #cpus for unbound wq */
@@ -411,12 +412,12 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
         alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)                                          \
-        alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
+        alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
 #define create_freezable_workqueue(name)                                \
-        alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
-                        1, (name))
+        alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \
+                        WQ_MEM_RECLAIM, 1, (name))
 #define create_singlethread_workqueue(name)                             \
-        alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
+        alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);