Merge branch 'perf/urgent' into perf/core

Pick up the latest fixes, refresh the development tree.

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

30 files changed, 203 insertions, 68 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index c602c7718421..ddabed1f51c2 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -169,7 +169,8 @@ struct acpi_device_flags {
 	u32 ejectable:1;
 	u32 power_manageable:1;
 	u32 match_driver:1;
-	u32 reserved:27;
+	u32 no_hotplug:1;
+	u32 reserved:26;
 };
 
 /* File System */
@@ -344,6 +345,7 @@ extern struct kobject *acpi_kobj;
 extern int acpi_bus_generate_netlink_event(const char*, const char*, u8, int);
 void acpi_bus_private_data_handler(acpi_handle, void *);
 int acpi_bus_get_private_data(acpi_handle, void **);
+void acpi_bus_no_hotplug(acpi_handle handle);
 extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32);
 extern int register_acpi_notifier(struct notifier_block *);
 extern int unregister_acpi_notifier(struct notifier_block *);
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/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 87578c109e48..49376aec2fbb 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -600,7 +600,7 @@
 	{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
-	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 669fef5c745a..3e0fbe441763 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -3,6 +3,6 @@
 
 #include <uapi/linux/auxvec.h>
 
-#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 20 /* NEW_AUX_ENT entries in auxiliary table */
   /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
 #endif /* _LINUX_AUXVEC_H */
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index fe68a5a98583..7032518f8542 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -6,6 +6,8 @@
 #include <linux/proc_fs.h>
 #include <linux/elf.h>
 
+#include <asm/pgtable.h> /* for pgprot_t */
+
 #define ELFCORE_ADDR_MAX	(-1ULL)
 #define ELFCORE_ADDR_ERR	(-2ULL)
 
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index eff50e062be8..d9c8dbd3373f 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -445,7 +445,7 @@ static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data)
 static inline struct i2c_adapter *
 i2c_parent_is_i2c_adapter(const struct i2c_adapter *adapter)
 {
-#if IS_ENABLED(I2C_MUX)
+#if IS_ENABLED(CONFIG_I2C_MUX)
 	struct device *parent = adapter->dev.parent;
 
 	if (parent != NULL && parent->type == &i2c_adapter_type)
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 0e23c26485f4..9b503376738f 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -418,6 +418,7 @@ enum {
 	ATA_HORKAGE_DUMP_ID	= (1 << 16),	/* dump IDENTIFY data */
 	ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17),	/* Set max sects to 65535 */
 	ATA_HORKAGE_ATAPI_DMADIR = (1 << 18),	/* device requires dmadir */
+	ATA_HORKAGE_NO_NCQ_TRIM	= (1 << 19),	/* don't use queued TRIM */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
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/netdevice.h b/include/linux/netdevice.h
index d9a550bf3e8e..ce2a1f5f9a1e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -769,7 +769,8 @@ struct netdev_phys_port_id {
  *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
  *	Required can not be NULL.
  *
- * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
+ * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
+ *                         void *accel_priv);
  *	Called to decide which queue to when device supports multiple
  *	transmit queues.
  *
@@ -990,7 +991,8 @@ struct net_device_ops {
 	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
 						   struct net_device *dev);
 	u16			(*ndo_select_queue)(struct net_device *dev,
-						    struct sk_buff *skb);
+						    struct sk_buff *skb,
+						    void *accel_priv);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
@@ -1529,7 +1531,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 }
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb);
+				    struct sk_buff *skb,
+				    void *accel_priv);
 u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
 
 /*
@@ -1819,6 +1822,7 @@ int dev_close(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct sk_buff *newskb);
 int dev_queue_xmit(struct sk_buff *skb);
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
 void unregister_netdevice_many(struct list_head *head);
@@ -1912,6 +1916,15 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+static inline int dev_rebuild_header(struct sk_buff *skb)
+{
+	const struct net_device *dev = skb->dev;
+
+	if (!dev->header_ops || !dev->header_ops->rebuild)
+		return 0;
+	return dev->header_ops->rebuild(skb);
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
@@ -2417,7 +2430,7 @@ int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq, void *accel_priv);
+			struct netdev_queue *txq);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 
 extern int		netdev_budget;
@@ -3008,6 +3021,19 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
 	dev->gso_max_size = size;
 }
 
+static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
+					int pulled_hlen, u16 mac_offset,
+					int mac_len)
+{
+	skb->protocol = protocol;
+	skb->encapsulation = 1;
+	skb_push(skb, pulled_hlen);
+	skb_reset_transport_header(skb);
+	skb->mac_header = mac_offset;
+	skb->network_header = skb->mac_header + mac_len;
+	skb->mac_len = mac_len;
+}
+
 static inline bool netif_is_macvlan(struct net_device *dev)
 {
 	return dev->priv_flags & IFF_MACVLAN;
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 57e890abe1f0..a5fc7d01aad6 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -69,6 +69,7 @@
 	__PCPU_DUMMY_ATTRS char __pcpu_scope_##name;			\
 	extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name;		\
 	__PCPU_DUMMY_ATTRS char __pcpu_unique_##name;			\
+	extern __PCPU_ATTRS(sec) __typeof__(type) name;			\
 	__PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak			\
 	__typeof__(type) name
 #else
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/rtnetlink.h b/include/linux/rtnetlink.h
index 939428ad25ac..8e3e66ac0a52 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -24,6 +24,11 @@ extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
 #ifdef CONFIG_PROVE_LOCKING
 extern int lockdep_rtnl_is_held(void);
+#else
+static inline int lockdep_rtnl_is_held(void)
+{
+	return 1;
+}
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 
 /**
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/linux/seqlock.h b/include/linux/seqlock.h
index cf87a24c0f92..535f158977b9 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -117,15 +117,15 @@ repeat:
 }
 
 /**
- * read_seqcount_begin_no_lockdep - start seq-read critical section w/o lockdep
+ * raw_read_seqcount_begin - start seq-read critical section w/o lockdep
  * @s: pointer to seqcount_t
  * Returns: count to be passed to read_seqcount_retry
  *
- * read_seqcount_begin_no_lockdep opens a read critical section of the given
+ * raw_read_seqcount_begin opens a read critical section of the given
  * seqcount, but without any lockdep checking. Validity of the critical
  * section is tested by checking read_seqcount_retry function.
  */
-static inline unsigned read_seqcount_begin_no_lockdep(const seqcount_t *s)
+static inline unsigned raw_read_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = __read_seqcount_begin(s);
 	smp_rmb();
@@ -144,7 +144,7 @@ static inline unsigned read_seqcount_begin_no_lockdep(const seqcount_t *s)
 static inline unsigned read_seqcount_begin(const seqcount_t *s)
 {
 	seqcount_lockdep_reader_access(s);
-	return read_seqcount_begin_no_lockdep(s);
+	return raw_read_seqcount_begin(s);
 }
 
 /**
@@ -206,14 +206,26 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 }
 
 
+
+static inline void raw_write_seqcount_begin(seqcount_t *s)
+{
+	s->sequence++;
+	smp_wmb();
+}
+
+static inline void raw_write_seqcount_end(seqcount_t *s)
+{
+	smp_wmb();
+	s->sequence++;
+}
+
 /*
  * Sequence counter only version assumes that callers are using their
  * own mutexing.
  */
 static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
-	s->sequence++;
-	smp_wmb();
+	raw_write_seqcount_begin(s);
 	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
 }
 
@@ -225,8 +237,7 @@ static inline void write_seqcount_begin(seqcount_t *s)
 static inline void write_seqcount_end(seqcount_t *s)
 {
 	seqcount_release(&s->dep_map, 1, _RET_IP_);
-	smp_wmb();
-	s->sequence++;
+	raw_write_seqcount_end(s);
 }
 
 /**
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 215b5ea1cb30..6f69b3f914fb 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1638,6 +1638,11 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
 	skb->mac_header += offset;
 }
 
+static inline void skb_pop_mac_header(struct sk_buff *skb)
+{
+	skb->mac_header = skb->network_header;
+}
+
 static inline void skb_probe_transport_header(struct sk_buff *skb,
 					      const int offset_hint)
 {
@@ -2526,6 +2531,10 @@ static inline void sw_tx_timestamp(struct sk_buff *skb)
  * Ethernet MAC Drivers should call this function in their hard_xmit()
  * function immediately before giving the sk_buff to the MAC hardware.
  *
+ * Specifically, one should make absolutely sure that this function is
+ * called before TX completion of this packet can trigger.  Otherwise
+ * the packet could potentially already be freed.
+ *
  * @skb: A socket buffer.
  */
 static inline void skb_tx_timestamp(struct sk_buff *skb)
diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index 31e2de7d57c5..c0f0a13ed818 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -142,7 +142,7 @@
 #define LLC_S_PF_IS_1(pdu)     ((pdu->ctrl_2 & LLC_S_PF_BIT_MASK) ? 1 : 0)
 
 #define PDU_SUPV_GET_Nr(pdu)   ((pdu->ctrl_2 & 0xFE) >> 1)
-#define PDU_GET_NEXT_Vr(sn)    (++sn & ~LLC_2_SEQ_NBR_MODULO)
+#define PDU_GET_NEXT_Vr(sn)    (((sn) + 1) & ~LLC_2_SEQ_NBR_MODULO)
 
 /* FRMR information field macros */
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 67b5d0068273..0a248b323d87 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1046,9 +1046,6 @@ struct sctp_outq {
 
 	/* Corked? */
 	char cork;
-
-	/* Is this structure empty?  */
-	char empty;
 };
 
 void sctp_outq_init(struct sctp_association *, struct sctp_outq *);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 979874c627ee..61e1935c91b1 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -978,7 +978,7 @@ struct ib_uobject {
 };
 
 struct ib_udata {
-	void __user *inbuf;
+	const void __user *inbuf;
 	void __user *outbuf;
 	size_t       inlen;
 	size_t       outlen;
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/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 2f3f7ea8c77b..fe421e8a431b 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -983,6 +983,8 @@ struct drm_radeon_cs {
 #define RADEON_INFO_SI_CP_DMA_COMPUTE	0x17
 /* CIK macrotile mode array */
 #define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY	0x18
+/* query the number of render backends */
+#define RADEON_INFO_SI_BACKEND_ENABLED_MASK	0x19
 
 
 struct drm_radeon_info {
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/input.h b/include/uapi/linux/input.h
index ecc88592ecbe..bd24470d24a2 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -464,7 +464,8 @@ struct input_keymap_entry {
 #define KEY_BRIGHTNESS_ZERO	244	/* brightness off, use ambient */
 #define KEY_DISPLAY_OFF		245	/* display device to off state */
 
-#define KEY_WIMAX		246
+#define KEY_WWAN		246	/* Wireless WAN (LTE, UMTS, GSM, etc.) */
+#define KEY_WIMAX		KEY_WWAN
 #define KEY_RFKILL		247	/* Key that controls all radios */
 
 #define KEY_MICMUTE		248	/* Mute / unmute the microphone */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ca018b4085c6..e244ed412745 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 */