Merge tag 'v3.13-rc5' into next

Linux 3.13-rc5

* tag 'v3.13-rc5': (231 commits)
  Linux 3.13-rc5
  aio: clean up and fix aio_setup_ring page mapping
  aio/migratepages: make aio migrate pages sane
  aio: fix kioctx leak introduced by "aio: Fix a trinity splat"
  Don't set the INITRD_COMPRESS environment variable automatically
  mm: fix build of split ptlock code
  pstore: Don't allow high traffic options on fragile devices
  mm: do not allocate page->ptl dynamically, if spinlock_t fits to long
  mm: page_alloc: revert NUMA aspect of fair allocation policy
  Revert "mm: page_alloc: exclude unreclaimable allocations from zone fairness policy"
  mm: Fix NULL pointer dereference in madvise(MADV_WILLNEED) support
  qla2xxx: Fix scsi_host leak on qlt_lport_register callback failure
  target: Remove extra percpu_ref_init
  arm64: ptrace: avoid using HW_BREAKPOINT_EMPTY for disabled events
  ARC: Allow conditional multiple inclusion of uapi/asm/unistd.h
  target/file: Update hw_max_sectors based on current block_size
  iser-target: Move INIT_WORK setup into isert_create_device_ib_res
  iscsi-target: Fix incorrect np->np_thread NULL assignment
  mm/hugetlb: check for pte NULL pointer in __page_check_address()
  fix build with make 3.80
  ...

Conflicts:
	drivers/usb/phy/Kconfig

14 files changed, 124 insertions, 46 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f330d28e4d0e..db0923458940 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -217,7 +217,7 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #endif
 
 #ifndef pte_accessible
-# define pte_accessible(pte)		((void)(pte),1)
+# define pte_accessible(mm, pte)	((void)(pte), 1)
 #endif
 
 #ifndef flush_tlb_fix_spurious_fault
@@ -599,11 +599,10 @@ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	barrier();
 #endif
-	if (pmd_none(pmdval))
+	if (pmd_none(pmdval) || pmd_trans_huge(pmdval))
 		return 1;
 	if (unlikely(pmd_bad(pmdval))) {
-		if (!pmd_trans_huge(pmdval))
-			pmd_clear_bad(pmd);
+		pmd_clear_bad(pmd);
 		return 1;
 	}
 	return 0;
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index ddf2b420ac8f..1cd3f5d767a8 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -3,13 +3,11 @@
 
 #include <linux/thread_info.h>
 
-/*
- * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
- * that think a non-zero value indicates we cannot preempt.
- */
+#define PREEMPT_ENABLED	(0)
+
 static __always_inline int preempt_count(void)
 {
-	return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
+	return current_thread_info()->preempt_count;
 }
 
 static __always_inline int *preempt_count_ptr(void)
@@ -17,11 +15,6 @@ static __always_inline int *preempt_count_ptr(void)
 	return &current_thread_info()->preempt_count;
 }
 
-/*
- * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
- * alternative is loosing a reschedule. Better schedule too often -- also this
- * should be a very rare operation.
- */
 static __always_inline void preempt_count_set(int pc)
 {
 	*preempt_count_ptr() = pc;
@@ -41,28 +34,17 @@ static __always_inline void preempt_count_set(int pc)
 	task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
 } while (0)
 
-/*
- * We fold the NEED_RESCHED bit into the preempt count such that
- * preempt_enable() can decrement and test for needing to reschedule with a
- * single instruction.
- *
- * We invert the actual bit, so that when the decrement hits 0 we know we both
- * need to resched (the bit is cleared) and can resched (no preempt count).
- */
-
 static __always_inline void set_preempt_need_resched(void)
 {
-	*preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-	*preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-	return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
+	return false;
 }
 
 /*
@@ -81,7 +63,12 @@ static __always_inline void __preempt_count_sub(int val)
 
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return !--*preempt_count_ptr();
+	/*
+	 * Because of load-store architectures cannot do per-cpu atomic
+	 * operations; we cannot use PREEMPT_NEED_RESCHED because it might get
+	 * lost.
+	 */
+	return !--*preempt_count_ptr() && tif_need_resched();
 }
 
 /*
@@ -89,7 +76,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(void)
 {
-	return unlikely(!*preempt_count_ptr());
+	return unlikely(!preempt_count() && tif_need_resched());
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index c8929c3832db..4bfde0e99ed5 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -19,7 +19,7 @@
 
 #define USE_CMPXCHG_LOCKREF \
 	(IS_ENABLED(CONFIG_ARCH_USE_CMPXCHG_LOCKREF) && \
-	 IS_ENABLED(CONFIG_SMP) && !BLOATED_SPINLOCKS)
+	 IS_ENABLED(CONFIG_SMP) && SPINLOCK_SIZE <= 4)
 
 struct lockref {
 	union {
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 69ed5f5e9f6e..c45c089bfdac 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -133,4 +133,34 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return ret;
 }
 
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+
+#ifndef mul_u64_u32_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+	return (u64)(((unsigned __int128)a * mul) >> shift);
+}
+#endif /* mul_u64_u32_shr */
+
+#else
+
+#ifndef mul_u64_u32_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+	u32 ah, al;
+	u64 ret;
+
+	al = a;
+	ah = a >> 32;
+
+	ret = ((u64)al * mul) >> shift;
+	if (ah)
+		ret += ((u64)ah * mul) << (32 - shift);
+
+	return ret;
+}
+#endif /* mul_u64_u32_shr */
+
+#endif
+
 #endif /* _LINUX_MATH64_H */
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f5096b58b20d..f015c059e159 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -55,7 +55,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
 extern int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page,
-		struct buffer_head *head, enum migrate_mode mode);
+		struct buffer_head *head, enum migrate_mode mode,
+		int extra_count);
 #else
 
 static inline void putback_lru_pages(struct list_head *l) {}
@@ -90,10 +91,19 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
+extern bool pmd_trans_migrating(pmd_t pmd);
+extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
 extern int migrate_misplaced_page(struct page *page,
 				  struct vm_area_struct *vma, int node);
 extern bool migrate_ratelimited(int node);
 #else
+static inline bool pmd_trans_migrating(pmd_t pmd)
+{
+	return false;
+}
+static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+}
 static inline int migrate_misplaced_page(struct page *page,
 					 struct vm_area_struct *vma, int node)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1cedd000cf29..35527173cf50 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1317,7 +1317,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
 #if USE_SPLIT_PTE_PTLOCKS
-#if BLOATED_SPINLOCKS
+#if ALLOC_SPLIT_PTLOCKS
 extern bool ptlock_alloc(struct page *page);
 extern void ptlock_free(struct page *page);
 
@@ -1325,7 +1325,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page)
 {
 	return page->ptl;
 }
-#else /* BLOATED_SPINLOCKS */
+#else /* ALLOC_SPLIT_PTLOCKS */
 static inline bool ptlock_alloc(struct page *page)
 {
 	return true;
@@ -1339,7 +1339,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page)
 {
 	return &page->ptl;
 }
-#endif /* BLOATED_SPINLOCKS */
+#endif /* ALLOC_SPLIT_PTLOCKS */
 
 static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bd299418a934..290901a8c1de 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -26,6 +26,7 @@ struct address_space;
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 #define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
 		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
+#define ALLOC_SPLIT_PTLOCKS	(SPINLOCK_SIZE > BITS_PER_LONG/8)
 
 /*
  * Each physical page in the system has a struct page associated with
@@ -155,7 +156,7 @@ struct page {
 						 * system if PG_buddy is set.
 						 */
 #if USE_SPLIT_PTE_PTLOCKS
-#if BLOATED_SPINLOCKS
+#if ALLOC_SPLIT_PTLOCKS
 		spinlock_t *ptl;
 #else
 		spinlock_t ptl;
@@ -443,6 +444,14 @@ struct mm_struct {
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
 #endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+	/*
+	 * An operation with batched TLB flushing is going on. Anything that
+	 * can move process memory needs to flush the TLB when moving a
+	 * PROT_NONE or PROT_NUMA mapped page.
+	 */
+	bool tlb_flush_pending;
+#endif
 	struct uprobes_state uprobes_state;
 };
 
@@ -459,4 +468,45 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 	return mm->cpu_vm_mask_var;
 }
 
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+	mm->tlb_flush_pending = true;
+
+	/*
+	 * Guarantee that the tlb_flush_pending store does not leak into the
+	 * critical section updating the page tables
+	 */
+	smp_mb__before_spinlock();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index abd437d0a8a7..ece0c6bbfcc5 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -51,6 +51,7 @@ struct pstore_info {
 	char		*buf;
 	size_t		bufsize;
 	struct mutex	read_mutex;	/* serialize open/read/close */
+	int		flags;
 	int		(*open)(struct pstore_info *psi);
 	int		(*close)(struct pstore_info *psi);
 	ssize_t		(*read)(u64 *id, enum pstore_type_id *type,
@@ -70,6 +71,8 @@ struct pstore_info {
 	void		*data;
 };
 
+#define	PSTORE_FLAGS_FRAGILE	1
+
 #ifdef CONFIG_PSTORE
 extern int pstore_register(struct pstore_info *);
 extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason);
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 8e00f9f6f963..9e7db9e73cc1 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -43,6 +43,7 @@ extern int unregister_reboot_notifier(struct notifier_block *);
  * Architecture-specific implementations of sys_reboot commands.
  */
 
+extern void migrate_to_reboot_cpu(void);
 extern void machine_restart(char *cmd);
 extern void machine_halt(void);
 extern void machine_power_off(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 768b037dfacb..53f97eb8dbc7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -440,8 +440,6 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
-#define PREEMPT_ENABLED		(PREEMPT_NEED_RESCHED)
-
 #ifdef CONFIG_PREEMPT_COUNT
 #define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
 #else
@@ -932,7 +930,8 @@ struct pipe_inode_info;
 struct uts_namespace;
 
 struct load_weight {
-	unsigned long weight, inv_weight;
+	unsigned long weight;
+	u32 inv_weight;
 };
 
 struct sched_avg {
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 45412a6afa69..321301c0a643 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -517,10 +517,6 @@ struct se_node_acl {
 	u32			acl_index;
 #define MAX_ACL_TAG_SIZE 64
 	char			acl_tag[MAX_ACL_TAG_SIZE];
-	u64			num_cmds;
-	u64			read_bytes;
-	u64			write_bytes;
-	spinlock_t		stats_lock;
 	/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
 	atomic_t		acl_pr_ref_count;
 	struct se_dev_entry	**device_list;
@@ -624,6 +620,7 @@ struct se_dev_attrib {
 	u32		unmap_granularity;
 	u32		unmap_granularity_alignment;
 	u32		max_write_same_len;
+	u32		max_bytes_per_io;
 	struct se_device *da_dev;
 	struct config_group da_group;
 };
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index bcb0912afe7a..f854ca4a1372 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -75,6 +75,7 @@
 #define DRM_VMW_PARAM_FIFO_CAPS        4
 #define DRM_VMW_PARAM_MAX_FB_SIZE      5
 #define DRM_VMW_PARAM_FIFO_HW_VERSION  6
+#define DRM_VMW_PARAM_MAX_SURF_MEMORY  7
 
 /**
  * struct drm_vmw_getparam_arg
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e1802d6153ae..959d454f76a1 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -679,6 +679,7 @@ enum perf_event_type {
 	 *
 	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index 65e12099ef89..ae665ac59c36 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -146,7 +146,7 @@ struct blkif_request_segment_aligned {
 struct blkif_request_rw {
 	uint8_t        nr_segments;  /* number of segments                   */
 	blkif_vdev_t   handle;       /* only for read/write requests         */
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
 	uint32_t       _pad1;	     /* offsetof(blkif_request,u.rw.id) == 8 */
 #endif
 	uint64_t       id;           /* private guest value, echoed in resp  */
@@ -163,7 +163,7 @@ struct blkif_request_discard {
 	uint8_t        flag;         /* BLKIF_DISCARD_SECURE or zero.        */
 #define BLKIF_DISCARD_SECURE (1<<0)  /* ignored if discard-secure=0          */
 	blkif_vdev_t   _pad1;        /* only for read/write requests         */
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
 	uint32_t       _pad2;        /* offsetof(blkif_req..,u.discard.id)==8*/
 #endif
 	uint64_t       id;           /* private guest value, echoed in resp  */
@@ -175,7 +175,7 @@ struct blkif_request_discard {
 struct blkif_request_other {
 	uint8_t      _pad1;
 	blkif_vdev_t _pad2;        /* only for read/write requests         */
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
 	uint32_t     _pad3;        /* offsetof(blkif_req..,u.other.id)==8*/
 #endif
 	uint64_t     id;           /* private guest value, echoed in resp  */
@@ -184,7 +184,7 @@ struct blkif_request_other {
 struct blkif_request_indirect {
 	uint8_t        indirect_op;
 	uint16_t       nr_segments;
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
 	uint32_t       _pad1;        /* offsetof(blkif_...,u.indirect.id) == 8 */
 #endif
 	uint64_t       id;
@@ -192,7 +192,7 @@ struct blkif_request_indirect {
 	blkif_vdev_t   handle;
 	uint16_t       _pad2;
 	grant_ref_t    indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST];
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
 	uint32_t      _pad3;         /* make it 64 byte aligned */
 #else
 	uint64_t      _pad3;         /* make it 64 byte aligned */