17 files changed, 113 insertions, 55 deletions

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/cpufreq.h b/include/linux/cpufreq.h
index a5ea52f793f3..718e8725de8a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -499,16 +499,6 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev,
 }
 #endif
 
-static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos)
-{
-	while ((*pos)->frequency != CPUFREQ_TABLE_END)
-		if ((*pos)->frequency != CPUFREQ_ENTRY_INVALID)
-			return true;
-		else
-			(*pos)++;
-	return false;
-}
-
 /*
  * cpufreq_for_each_entry -	iterate over a cpufreq_frequency_table
  * @pos:	the cpufreq_frequency_table * to use as a loop cursor.
@@ -525,8 +515,11 @@ static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos)
  * @table:      the cpufreq_frequency_table * to iterate over.
  */
 
-#define cpufreq_for_each_valid_entry(pos, table)	\
-	for (pos = table; cpufreq_next_valid(&pos); pos++)
+#define cpufreq_for_each_valid_entry(pos, table)			\
+	for (pos = table; pos->frequency != CPUFREQ_TABLE_END; pos++)	\
+		if (pos->frequency == CPUFREQ_ENTRY_INVALID)		\
+			continue;					\
+		else
 
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table);
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/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/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/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/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/pfn_t.h b/include/linux/pfn_t.h
index 0703b5360d31..37448ab5fb5c 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -29,7 +29,7 @@ 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, unsigned long flags);
 
 static inline bool pfn_t_has_page(pfn_t pfn)
 {
@@ -48,7 +48,7 @@ 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));
 }
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 95403d2ccaf5..cccaf4a29e9f 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -34,6 +34,8 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp);
 
 int dev_pm_opp_get_opp_count(struct device *dev);
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev);
+unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev);
+unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev);
 struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
@@ -60,6 +62,9 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 void dev_pm_opp_put_supported_hw(struct device *dev);
 int dev_pm_opp_set_prop_name(struct device *dev, const char *name);
 void dev_pm_opp_put_prop_name(struct device *dev);
+int dev_pm_opp_set_regulator(struct device *dev, const char *name);
+void dev_pm_opp_put_regulator(struct device *dev);
+int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 #else
 static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
@@ -86,6 +91,16 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 	return 0;
 }
 
+static inline unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
+{
+	return 0;
+}
+
+static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
+{
+	return 0;
+}
+
 static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
 {
 	return NULL;
@@ -151,6 +166,18 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 
 static inline void dev_pm_opp_put_prop_name(struct device *dev) {}
 
+static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name)
+{
+	return -EINVAL;
+}
+
+static inline void dev_pm_opp_put_regulator(struct device *dev) {}
+
+static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
+{
+	return -EINVAL;
+}
+
 #endif		/* CONFIG_PM_OPP */
 
 #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
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);