Merge branch 'perf/urgent' into perf/core, to queue up dependent patch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

18 files changed, 84 insertions, 51 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/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/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/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/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/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/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/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/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 37448ab5fb5c..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(phys_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)
 {
@@ -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 00b17c526c1f..f54be7082207 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -400,7 +400,7 @@ void **radix_tree_iter_retry(struct radix_tree_iter *iter)
  * @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;
@@ -434,9 +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/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);