4 files changed, 165 insertions, 20 deletions

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 032560295fcb..d08e4d2a9b92 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -591,6 +591,21 @@ static inline int cpulist_scnprintf(char *buf, int len,
 }
 
 /**
+ * cpumask_parse - extract a cpumask from from a string
+ * @buf: the buffer to extract from
+ * @dstp: the cpumask to set.
+ *
+ * Returns -errno, or 0 for success.
+ */
+static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
+{
+        char *nl = strchr(buf, '\n');
+        int len = nl ? nl - buf : strlen(buf);
+
+        return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
+}
+
+/**
  * cpulist_parse - extract a cpumask from a user string of ranges
  * @buf: the buffer to extract from
  * @dstp: the cpumask to set.
diff --git a/include/linux/device.h b/include/linux/device.h
index 88615ccaf23a..711793b145ff 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -297,6 +297,8 @@ void subsys_interface_unregister(struct subsys_interface *sif);
 
 int subsys_system_register(struct bus_type *subsys,
                            const struct attribute_group **groups);
+int subsys_virtual_register(struct bus_type *subsys,
+                            const struct attribute_group **groups);
 
 /**
  * struct class - device classes
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2d02c76a01be..bcbc30397f23 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1793,7 +1793,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_SWAPWRITE    0x00800000      /* Allowed to write to swap */
 #define PF_SPREAD_PAGE  0x01000000      /* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB  0x02000000      /* Spread some slab caches over cpuset */
-#define PF_THREAD_BOUND 0x04000000      /* Thread bound to specific cpu */
+#define PF_NO_SETAFFINITY 0x04000000    /* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MEMPOLICY    0x10000000      /* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER 0x20000000      /* Thread belongs to the rt mutex tester */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 8afab27cdbc2..717975639378 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -11,6 +11,7 @@
 #include <linux/lockdep.h>
 #include <linux/threads.h>
 #include <linux/atomic.h>
+#include <linux/cpumask.h>
 
 struct workqueue_struct;
 
@@ -68,7 +69,7 @@ enum {
                                   WORK_STRUCT_COLOR_BITS,
 
         /* data contains off-queue information when !WORK_STRUCT_PWQ */
-        WORK_OFFQ_FLAG_BASE     = WORK_STRUCT_FLAG_BITS,
+        WORK_OFFQ_FLAG_BASE     = WORK_STRUCT_COLOR_SHIFT,
 
         WORK_OFFQ_CANCELING     = (1 << WORK_OFFQ_FLAG_BASE),
 
@@ -115,6 +116,20 @@ struct delayed_work {
         int cpu;
 };
 
+/*
+ * A struct for workqueue attributes.  This can be used to change
+ * attributes of an unbound workqueue.
+ *
+ * Unlike other fields, ->no_numa isn't a property of a worker_pool.  It
+ * only modifies how apply_workqueue_attrs() select pools and thus doesn't
+ * participate in pool hash calculations or equality comparisons.
+ */
+struct workqueue_attrs {
+        int                     nice;           /* nice level */
+        cpumask_var_t           cpumask;        /* allowed CPUs */
+        bool                    no_numa;        /* disable NUMA affinity */
+};
+
 static inline struct delayed_work *to_delayed_work(struct work_struct *work)
 {
         return container_of(work, struct delayed_work, work);
@@ -283,9 +298,10 @@ enum {
         WQ_MEM_RECLAIM          = 1 << 3, /* may be used for memory reclaim */
         WQ_HIGHPRI              = 1 << 4, /* high priority */
         WQ_CPU_INTENSIVE        = 1 << 5, /* cpu instensive workqueue */
+        WQ_SYSFS                = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */
 
-        WQ_DRAINING             = 1 << 6, /* internal: workqueue is draining */
-        WQ_RESCUER              = 1 << 7, /* internal: workqueue has rescuer */
+        __WQ_DRAINING           = 1 << 16, /* internal: workqueue is draining */
+        __WQ_ORDERED            = 1 << 17, /* internal: workqueue is ordered */
 
         WQ_MAX_ACTIVE           = 512,    /* I like 512, better ideas? */
         WQ_MAX_UNBOUND_PER_CPU  = 4,      /* 4 * #cpus for unbound wq */
@@ -388,7 +404,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)                    \
-        alloc_workqueue(fmt, WQ_UNBOUND | (flags), 1, ##args)
+        alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)                                          \
         alloc_workqueue((name), WQ_MEM_RECLAIM, 1)
@@ -399,30 +415,23 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
+struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask);
+void free_workqueue_attrs(struct workqueue_attrs *attrs);
+int apply_workqueue_attrs(struct workqueue_struct *wq,
+                          const struct workqueue_attrs *attrs);
+
 extern bool queue_work_on(int cpu, struct workqueue_struct *wq,
                         struct work_struct *work);
-extern bool queue_work(struct workqueue_struct *wq, struct work_struct *work);
 extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
                         struct delayed_work *work, unsigned long delay);
-extern bool queue_delayed_work(struct workqueue_struct *wq,
-                        struct delayed_work *work, unsigned long delay);
 extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
                         struct delayed_work *dwork, unsigned long delay);
-extern bool mod_delayed_work(struct workqueue_struct *wq,
-                        struct delayed_work *dwork, unsigned long delay);
 
 extern void flush_workqueue(struct workqueue_struct *wq);
 extern void drain_workqueue(struct workqueue_struct *wq);
 extern void flush_scheduled_work(void);
 
-extern bool schedule_work_on(int cpu, struct work_struct *work);
-extern bool schedule_work(struct work_struct *work);
-extern bool schedule_delayed_work_on(int cpu, struct delayed_work *work,
-                                     unsigned long delay);
-extern bool schedule_delayed_work(struct delayed_work *work,
-                                  unsigned long delay);
 extern int schedule_on_each_cpu(work_func_t func);
-extern int keventd_up(void);
 
 int execute_in_process_context(work_func_t fn, struct execute_work *);
 
@@ -435,9 +444,121 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork);
 
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
                                      int max_active);
-extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq);
+extern bool current_is_workqueue_rescuer(void);
+extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
 extern unsigned int work_busy(struct work_struct *work);
 
+/**
+ * queue_work - queue work on a workqueue
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * Returns %false if @work was already on a queue, %true otherwise.
+ *
+ * We queue the work to the CPU on which it was submitted, but if the CPU dies
+ * it can be processed by another CPU.
+ */
+static inline bool queue_work(struct workqueue_struct *wq,
+                              struct work_struct *work)
+{
+        return queue_work_on(WORK_CPU_UNBOUND, wq, work);
+}
+
+/**
+ * queue_delayed_work - queue work on a workqueue after delay
+ * @wq: workqueue to use
+ * @dwork: delayable work to queue
+ * @delay: number of jiffies to wait before queueing
+ *
+ * Equivalent to queue_delayed_work_on() but tries to use the local CPU.
+ */
+static inline bool queue_delayed_work(struct workqueue_struct *wq,
+                                      struct delayed_work *dwork,
+                                      unsigned long delay)
+{
+        return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
+}
+
+/**
+ * mod_delayed_work - modify delay of or queue a delayed work
+ * @wq: workqueue to use
+ * @dwork: work to queue
+ * @delay: number of jiffies to wait before queueing
+ *
+ * mod_delayed_work_on() on local CPU.
+ */
+static inline bool mod_delayed_work(struct workqueue_struct *wq,
+                                    struct delayed_work *dwork,
+                                    unsigned long delay)
+{
+        return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
+}
+
+/**
+ * schedule_work_on - put work task on a specific cpu
+ * @cpu: cpu to put the work task on
+ * @work: job to be done
+ *
+ * This puts a job on a specific cpu
+ */
+static inline bool schedule_work_on(int cpu, struct work_struct *work)
+{
+        return queue_work_on(cpu, system_wq, work);
+}
+
+/**
+ * schedule_work - put work task in global workqueue
+ * @work: job to be done
+ *
+ * Returns %false if @work was already on the kernel-global workqueue and
+ * %true otherwise.
+ *
+ * This puts a job in the kernel-global workqueue if it was not already
+ * queued and leaves it in the same position on the kernel-global
+ * workqueue otherwise.
+ */
+static inline bool schedule_work(struct work_struct *work)
+{
+        return queue_work(system_wq, work);
+}
+
+/**
+ * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
+ * @cpu: cpu to use
+ * @dwork: job to be done
+ * @delay: number of jiffies to wait
+ *
+ * After waiting for a given time this puts a job in the kernel-global
+ * workqueue on the specified CPU.
+ */
+static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
+                                            unsigned long delay)
+{
+        return queue_delayed_work_on(cpu, system_wq, dwork, delay);
+}
+
+/**
+ * schedule_delayed_work - put work task in global workqueue after delay
+ * @dwork: job to be done
+ * @delay: number of jiffies to wait or 0 for immediate execution
+ *
+ * After waiting for a given time this puts a job in the kernel-global
+ * workqueue.
+ */
+static inline bool schedule_delayed_work(struct delayed_work *dwork,
+                                         unsigned long delay)
+{
+        return queue_delayed_work(system_wq, dwork, delay);
+}
+
+/**
+ * keventd_up - is workqueue initialized yet?
+ */
+static inline bool keventd_up(void)
+{
+        return system_wq != NULL;
+}
+
 /*
  * Like above, but uses del_timer() instead of del_timer_sync(). This means,
  * if it returns 0 the timer function may be running and the queueing is in
@@ -466,12 +587,12 @@ static inline bool __deprecated flush_delayed_work_sync(struct delayed_work *dwo
 }
 
 #ifndef CONFIG_SMP
-static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 {
         return fn(arg);
 }
 #else
-long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
+long work_on_cpu(int cpu, long (*fn)(void *), void *arg);
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FREEZER
@@ -480,4 +601,11 @@ extern bool freeze_workqueues_busy(void);
 extern void thaw_workqueues(void);
 #endif /* CONFIG_FREEZER */
 
+#ifdef CONFIG_SYSFS
+int workqueue_sysfs_register(struct workqueue_struct *wq);
+#else   /* CONFIG_SYSFS */
+static inline int workqueue_sysfs_register(struct workqueue_struct *wq)
+{ return 0; }
+#endif  /* CONFIG_SYSFS */
+
 #endif