Merge branch 'linus' into perf/core, to pick up fixes

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

include/linux/backing-dev-defs.h

@@ -22,7 +22,6 @@ struct dentry;
  */
 enum wb_state {
 	WB_registered,		/* bdi_register() was done */
-	WB_shutting_down,	/* wb_shutdown() in progress */
 	WB_writeback_running,	/* Writeback is in progress */
 	WB_has_dirty_io,	/* Dirty inodes on ->b_{dirty|io|more_io} */
 	WB_start_all,		/* nr_pages == 0 (all) work pending */
@@ -189,6 +188,7 @@ struct backing_dev_info {
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
 	struct rb_root cgwb_congested_tree; /* their congested states */
+	struct mutex cgwb_release_mutex;  /* protect shutdown of wb structs */
 #else
 	struct bdi_writeback_congested *wb_congested;
 #endif

include/linux/filter.h

@@ -472,7 +472,9 @@ struct sock_fprog_kern {
 struct bpf_binary_header {
 	u16 pages;
 	u16 locked:1;
-	u8 image[];
+
+	/* Some arches need word alignment for their instructions */
+	u8 image[] __aligned(4);
 };
 
 struct bpf_prog {

include/linux/irq.h

@@ -503,6 +503,7 @@ struct irq_chip {
  * IRQCHIP_SKIP_SET_WAKE:	Skip chip.irq_set_wake(), for this irq chip
  * IRQCHIP_ONESHOT_SAFE:	One shot does not require mask/unmask
  * IRQCHIP_EOI_THREADED:	Chip requires eoi() on unmask in threaded mode
+ * IRQCHIP_SUPPORTS_LEVEL_MSI	Chip can provide two doorbells for Level MSIs
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),

include/linux/irqdesc.h

@@ -145,11 +145,6 @@ static inline void *irq_desc_get_handler_data(struct irq_desc *desc)
 	return desc->irq_common_data.handler_data;
 }
 
-static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
-{
-	return desc->irq_common_data.msi_desc;
-}
-
 /*
  * Architectures call this to let the generic IRQ layer
  * handle an interrupt.

include/linux/kernel.h

@@ -666,7 +666,7 @@ do {									\
  * your code. (Extra memory is used for special buffers that are
  * allocated when trace_printk() is used.)
  *
- * A little optization trick is done here. If there's only one
+ * A little optimization trick is done here. If there's only one
  * argument, there's no need to scan the string for printf formats.
  * The trace_puts() will suffice. But how can we take advantage of
  * using trace_puts() when trace_printk() has only one argument?

include/linux/memory.h

@@ -38,6 +38,7 @@ struct memory_block {
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
 unsigned long memory_block_size_bytes(void);
+int set_memory_block_size_order(unsigned int order);
 
 /* These states are exposed to userspace as text strings in sysfs */
 #define	MEM_ONLINE		(1<<0) /* exposed to userspace */

include/linux/nfs_xdr.h

@@ -1438,6 +1438,8 @@ enum {
 	NFS_IOHDR_EOF,
 	NFS_IOHDR_REDO,
 	NFS_IOHDR_STAT,
+	NFS_IOHDR_RESEND_PNFS,
+	NFS_IOHDR_RESEND_MDS,
 };
 
 struct nfs_io_completion;

include/linux/refcount.h

@@ -98,5 +98,7 @@ extern __must_check bool refcount_dec_if_one(refcount_t *r);
 extern __must_check bool refcount_dec_not_one(refcount_t *r);
 extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock);
 extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock);
-
+extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r,
+						       spinlock_t *lock,
+						       unsigned long *flags);
 #endif /* _LINUX_REFCOUNT_H */

include/linux/sched.h

@@ -1799,20 +1799,22 @@ static inline void rseq_set_notify_resume(struct task_struct *t)
 		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
 }
 
-void __rseq_handle_notify_resume(struct pt_regs *regs);
+void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
 
-static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+					     struct pt_regs *regs)
 {
 	if (current->rseq)
-		__rseq_handle_notify_resume(regs);
+		__rseq_handle_notify_resume(ksig, regs);
 }
 
-static inline void rseq_signal_deliver(struct pt_regs *regs)
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+				       struct pt_regs *regs)
 {
 	preempt_disable();
 	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
 	preempt_enable();
-	rseq_handle_notify_resume(regs);
+	rseq_handle_notify_resume(ksig, regs);
 }
 
 /* rseq_preempt() requires preemption to be disabled. */
@@ -1831,9 +1833,7 @@ static inline void rseq_migrate(struct task_struct *t)
 
 /*
  * If parent process has a registered restartable sequences area, the
- * child inherits. Only applies when forking a process, not a thread. In
- * case a parent fork() in the middle of a restartable sequence, set the
- * resume notifier to force the child to retry.
+ * child inherits. Only applies when forking a process, not a thread.
  */
 static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
 {
@@ -1847,7 +1847,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
 		t->rseq_len = current->rseq_len;
 		t->rseq_sig = current->rseq_sig;
 		t->rseq_event_mask = current->rseq_event_mask;
-		rseq_preempt(t);
 	}
 }
 
@@ -1864,10 +1863,12 @@ static inline void rseq_execve(struct task_struct *t)
 static inline void rseq_set_notify_resume(struct task_struct *t)
 {
 }
-static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+					     struct pt_regs *regs)
 {
 }
-static inline void rseq_signal_deliver(struct pt_regs *regs)
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+				       struct pt_regs *regs)
 {
 }
 static inline void rseq_preempt(struct task_struct *t)

include/linux/spinlock.h

@@ -427,6 +427,11 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
 #define atomic_dec_and_lock(atomic, lock) \
 		__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
 
+extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+					unsigned long *flags);
+#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \
+		__cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)))
+
 int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask,
 			   size_t max_size, unsigned int cpu_mult,
 			   gfp_t gfp);