Merge tag 'v3.13-rc8' into core/locking

Refresh the tree with the latest fixes, before applying new changes.

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

14 files changed, 149 insertions, 14 deletions

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/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/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)