Merge branch 'cpus4096-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'cpus4096-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (66 commits)
  x86: export vector_used_by_percpu_irq
  x86: use logical apicid in x2apic_cluster's x2apic_cpu_mask_to_apicid_and()
  sched: nominate preferred wakeup cpu, fix
  x86: fix lguest used_vectors breakage, -v2
  x86: fix warning in arch/x86/kernel/io_apic.c
  sched: fix warning in kernel/sched.c
  sched: move test_sd_parent() to an SMP section of sched.h
  sched: add SD_BALANCE_NEWIDLE at MC and CPU level for sched_mc>0
  sched: activate active load balancing in new idle cpus
  sched: bias task wakeups to preferred semi-idle packages
  sched: nominate preferred wakeup cpu
  sched: favour lower logical cpu number for sched_mc balance
  sched: framework for sched_mc/smt_power_savings=N
  sched: convert BALANCE_FOR_xx_POWER to inline functions
  x86: use possible_cpus=NUM to extend the possible cpus allowed
  x86: fix cpu_mask_to_apicid_and to include cpu_online_mask
  x86: update io_apic.c to the new cpumask code
  x86: Introduce topology_core_cpumask()/topology_thread_cpumask()
  x86: xen: use smp_call_function_many()
  x86: use work_on_cpu in x86/kernel/cpu/mcheck/mce_amd_64.c
  ...

Fixed up trivial conflict in kernel/time/tick-sched.c manually

8 files changed, 159 insertions, 64 deletions

diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 54bbf6e04ee8..0e9e2bc0ee96 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -40,6 +40,9 @@
 #ifndef node_to_cpumask
 #define node_to_cpumask(node)	((void)node, cpu_online_map)
 #endif
+#ifndef cpumask_of_node
+#define cpumask_of_node(node)	((void)node, cpu_online_mask)
+#endif
 #ifndef node_to_first_cpu
 #define node_to_first_cpu(node)	((void)(node),0)
 #endif
@@ -54,9 +57,18 @@
 				)
 #endif
 
+#ifndef cpumask_of_pcibus
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+#endif
+
 #endif	/* CONFIG_NUMA */
 
-/* returns pointer to cpumask for specified node */
+/*
+ * returns pointer to cpumask for specified node
+ * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
+ */
 #ifndef node_to_cpumask_ptr
 
 #define	node_to_cpumask_ptr(v, node) 					\
diff --git a/include/asm-m32r/smp.h b/include/asm-m32r/smp.h
index c5dd66916692..b96a6d2ffbc3 100644
--- a/include/asm-m32r/smp.h
+++ b/include/asm-m32r/smp.h
@@ -63,8 +63,6 @@ extern volatile int cpu_2_physid[NR_CPUS];
 #define raw_smp_processor_id()	(current_thread_info()->cpu)
 
 extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_possible_map;
-extern cpumask_t cpu_present_map;
 
 static __inline__ int hard_smp_processor_id(void)
 {
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index ed3a5d473e52..cea153697ec7 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -82,13 +82,13 @@ struct clock_event_device {
 	int			shift;
 	int			rating;
 	int			irq;
-	cpumask_t		cpumask;
+	const struct cpumask	*cpumask;
 	int			(*set_next_event)(unsigned long evt,
 						  struct clock_event_device *);
 	void			(*set_mode)(enum clock_event_mode mode,
 					    struct clock_event_device *);
 	void			(*event_handler)(struct clock_event_device *);
-	void			(*broadcast)(cpumask_t mask);
+	void			(*broadcast)(const struct cpumask *mask);
 	struct list_head	list;
 	enum clock_event_mode	mode;
 	ktime_t			next_event;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 21e1dd43e52a..d4bf52603e6b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -339,36 +339,6 @@ extern cpumask_t cpu_mask_all;
 #endif
 #define	CPUMASK_PTR(v, m) 	cpumask_t *v = &(m->v)
 
-#define cpumask_scnprintf(buf, len, src) \
-			__cpumask_scnprintf((buf), (len), &(src), NR_CPUS)
-static inline int __cpumask_scnprintf(char *buf, int len,
-					const cpumask_t *srcp, int nbits)
-{
-	return bitmap_scnprintf(buf, len, srcp->bits, nbits);
-}
-
-#define cpumask_parse_user(ubuf, ulen, dst) \
-			__cpumask_parse_user((ubuf), (ulen), &(dst), NR_CPUS)
-static inline int __cpumask_parse_user(const char __user *buf, int len,
-					cpumask_t *dstp, int nbits)
-{
-	return bitmap_parse_user(buf, len, dstp->bits, nbits);
-}
-
-#define cpulist_scnprintf(buf, len, src) \
-			__cpulist_scnprintf((buf), (len), &(src), NR_CPUS)
-static inline int __cpulist_scnprintf(char *buf, int len,
-					const cpumask_t *srcp, int nbits)
-{
-	return bitmap_scnlistprintf(buf, len, srcp->bits, nbits);
-}
-
-#define cpulist_parse(buf, dst) __cpulist_parse((buf), &(dst), NR_CPUS)
-static inline int __cpulist_parse(const char *buf, cpumask_t *dstp, int nbits)
-{
-	return bitmap_parselist(buf, dstp->bits, nbits);
-}
-
 #define cpu_remap(oldbit, old, new) \
 		__cpu_remap((oldbit), &(old), &(new), NR_CPUS)
 static inline int __cpu_remap(int oldbit,
@@ -540,9 +510,6 @@ extern cpumask_t cpu_active_map;
 	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD	\
 }
 
-/* This produces more efficient code. */
-#define nr_cpumask_bits	NR_CPUS
-
 #else /* NR_CPUS > BITS_PER_LONG */
 
 #define CPU_BITS_ALL						\
@@ -550,9 +517,15 @@ extern cpumask_t cpu_active_map;
 	[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,		\
 	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD		\
 }
+#endif /* NR_CPUS > BITS_PER_LONG */
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* Assuming NR_CPUS is huge, a runtime limit is more efficient.  Also,
+ * not all bits may be allocated. */
 #define nr_cpumask_bits	nr_cpu_ids
-#endif /* NR_CPUS > BITS_PER_LONG */
+#else
+#define nr_cpumask_bits	NR_CPUS
+#endif
 
 /* verify cpu argument to cpumask_* operators */
 static inline unsigned int cpumask_check(unsigned int cpu)
@@ -946,6 +919,63 @@ static inline void cpumask_copy(struct cpumask *dstp,
 #define cpumask_of(cpu) (get_cpu_mask(cpu))
 
 /**
+ * cpumask_scnprintf - print a cpumask into a string as comma-separated hex
+ * @buf: the buffer to sprintf into
+ * @len: the length of the buffer
+ * @srcp: the cpumask to print
+ *
+ * If len is zero, returns zero.  Otherwise returns the length of the
+ * (nul-terminated) @buf string.
+ */
+static inline int cpumask_scnprintf(char *buf, int len,
+				    const struct cpumask *srcp)
+{
+	return bitmap_scnprintf(buf, len, srcp->bits, nr_cpumask_bits);
+}
+
+/**
+ * cpumask_parse_user - extract a cpumask from a user string
+ * @buf: the buffer to extract from
+ * @len: the length of the buffer
+ * @dstp: the cpumask to set.
+ *
+ * Returns -errno, or 0 for success.
+ */
+static inline int cpumask_parse_user(const char __user *buf, int len,
+				     struct cpumask *dstp)
+{
+	return bitmap_parse_user(buf, len, dstp->bits, nr_cpumask_bits);
+}
+
+/**
+ * cpulist_scnprintf - print a cpumask into a string as comma-separated list
+ * @buf: the buffer to sprintf into
+ * @len: the length of the buffer
+ * @srcp: the cpumask to print
+ *
+ * If len is zero, returns zero.  Otherwise returns the length of the
+ * (nul-terminated) @buf string.
+ */
+static inline int cpulist_scnprintf(char *buf, int len,
+				    const struct cpumask *srcp)
+{
+	return bitmap_scnlistprintf(buf, len, srcp->bits, nr_cpumask_bits);
+}
+
+/**
+ * cpulist_parse_user - extract a cpumask from a user string of ranges
+ * @buf: the buffer to extract from
+ * @len: the length of the buffer
+ * @dstp: the cpumask to set.
+ *
+ * Returns -errno, or 0 for success.
+ */
+static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
+{
+	return bitmap_parselist(buf, dstp->bits, nr_cpumask_bits);
+}
+
+/**
  * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
  * @bitmap: the bitmap
  *
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 8cc8ef47f5b6..990355fbc54e 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -111,13 +111,13 @@ extern void enable_irq(unsigned int irq);
 
 extern cpumask_t irq_default_affinity;
 
-extern int irq_set_affinity(unsigned int irq, cpumask_t cpumask);
+extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
 #else /* CONFIG_SMP */
 
-static inline int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
+static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/irq.h b/include/linux/irq.h
index d64a6d49bdef..f899b502f186 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -113,7 +113,8 @@ struct irq_chip {
 	void		(*eoi)(unsigned int irq);
 
 	void		(*end)(unsigned int irq);
-	void		(*set_affinity)(unsigned int irq, cpumask_t dest);
+	void		(*set_affinity)(unsigned int irq,
+					const struct cpumask *dest);
 	int		(*retrigger)(unsigned int irq);
 	int		(*set_type)(unsigned int irq, unsigned int flow_type);
 	int		(*set_wake)(unsigned int irq, unsigned int on);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8395e715809d..158d53d07765 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -250,7 +250,7 @@ extern void init_idle_bootup_task(struct task_struct *idle);
 extern int runqueue_is_locked(void);
 extern void task_rq_unlock_wait(struct task_struct *p);
 
-extern cpumask_t nohz_cpu_mask;
+extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
 extern int select_nohz_load_balancer(int cpu);
 #else
@@ -758,20 +758,51 @@ enum cpu_idle_type {
 #define SD_SERIALIZE		1024	/* Only a single load balancing instance */
 #define SD_WAKE_IDLE_FAR	2048	/* Gain latency sacrificing cache hit */
 
-#define BALANCE_FOR_MC_POWER	\
-	(sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)
+enum powersavings_balance_level {
+	POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
+	POWERSAVINGS_BALANCE_BASIC,	/* Fill one thread/core/package
+					 * first for long running threads
+					 */
+	POWERSAVINGS_BALANCE_WAKEUP,	/* Also bias task wakeups to semi-idle
+					 * cpu package for power savings
+					 */
+	MAX_POWERSAVINGS_BALANCE_LEVELS
+};
 
-#define BALANCE_FOR_PKG_POWER	\
-	((sched_mc_power_savings || sched_smt_power_savings) ?	\
-	 SD_POWERSAVINGS_BALANCE : 0)
+extern int sched_mc_power_savings, sched_smt_power_savings;
 
-#define test_sd_parent(sd, flag)	((sd->parent &&		\
-					 (sd->parent->flags & flag)) ? 1 : 0)
+static inline int sd_balance_for_mc_power(void)
+{
+	if (sched_smt_power_savings)
+		return SD_POWERSAVINGS_BALANCE;
 
+	return 0;
+}
+
+static inline int sd_balance_for_package_power(void)
+{
+	if (sched_mc_power_savings | sched_smt_power_savings)
+		return SD_POWERSAVINGS_BALANCE;
+
+	return 0;
+}
+
+/*
+ * Optimise SD flags for power savings:
+ * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
+ * Keep default SD flags if sched_{smt,mc}_power_saving=0
+ */
+
+static inline int sd_power_saving_flags(void)
+{
+	if (sched_mc_power_savings | sched_smt_power_savings)
+		return SD_BALANCE_NEWIDLE;
+
+	return 0;
+}
 
 struct sched_group {
 	struct sched_group *next;	/* Must be a circular list */
-	cpumask_t cpumask;
 
 	/*
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
@@ -784,8 +815,15 @@ struct sched_group {
 	 * (see include/linux/reciprocal_div.h)
 	 */
 	u32 reciprocal_cpu_power;
+
+	unsigned long cpumask[];
 };
 
+static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
+{
+	return to_cpumask(sg->cpumask);
+}
+
 enum sched_domain_level {
 	SD_LV_NONE = 0,
 	SD_LV_SIBLING,
@@ -809,7 +847,6 @@ struct sched_domain {
 	struct sched_domain *parent;	/* top domain must be null terminated */
 	struct sched_domain *child;	/* bottom domain must be null terminated */
 	struct sched_group *groups;	/* the balancing groups of the domain */
-	cpumask_t span;			/* span of all CPUs in this domain */
 	unsigned long min_interval;	/* Minimum balance interval ms */
 	unsigned long max_interval;	/* Maximum balance interval ms */
 	unsigned int busy_factor;	/* less balancing by factor if busy */
@@ -864,18 +901,35 @@ struct sched_domain {
 #ifdef CONFIG_SCHED_DEBUG
 	char *name;
 #endif
+
+	/* span of all CPUs in this domain */
+	unsigned long span[];
 };
 
-extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
+{
+	return to_cpumask(sd->span);
+}
+
+extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
 				    struct sched_domain_attr *dattr_new);
 extern int arch_reinit_sched_domains(void);
 
+/* Test a flag in parent sched domain */
+static inline int test_sd_parent(struct sched_domain *sd, int flag)
+{
+	if (sd->parent && (sd->parent->flags & flag))
+		return 1;
+
+	return 0;
+}
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
 
 static inline void
-partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
 			struct sched_domain_attr *dattr_new)
 {
 }
@@ -926,7 +980,7 @@ struct sched_class {
 	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
 
 	void (*set_cpus_allowed)(struct task_struct *p,
-				 const cpumask_t *newmask);
+				 const struct cpumask *newmask);
 
 	void (*rq_online)(struct rq *rq);
 	void (*rq_offline)(struct rq *rq);
@@ -1579,12 +1633,12 @@ extern cputime_t task_gtime(struct task_struct *p);
 
 #ifdef CONFIG_SMP
 extern int set_cpus_allowed_ptr(struct task_struct *p,
-				const cpumask_t *new_mask);
+				const struct cpumask *new_mask);
 #else
 static inline int set_cpus_allowed_ptr(struct task_struct *p,
-				       const cpumask_t *new_mask)
+				       const struct cpumask *new_mask)
 {
-	if (!cpu_isset(0, *new_mask))
+	if (!cpumask_test_cpu(0, new_mask))
 		return -EINVAL;
 	return 0;
 }
@@ -2195,10 +2249,8 @@ __trace_special(void *__tr, void *__data,
 }
 #endif
 
-extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask);
-extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
-
-extern int sched_mc_power_savings, sched_smt_power_savings;
+extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
+extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
 extern void normalize_rt_tasks(void);
 
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 0c5b5ac36d8e..e632d29f0544 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -125,7 +125,8 @@ int arch_update_cpu_topology(void);
 				| SD_WAKE_AFFINE	\
 				| SD_WAKE_BALANCE	\
 				| SD_SHARE_PKG_RESOURCES\
-				| BALANCE_FOR_MC_POWER,	\
+				| sd_balance_for_mc_power()\
+				| sd_power_saving_flags(),\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
 }
@@ -150,7 +151,8 @@ int arch_update_cpu_topology(void);
 				| SD_BALANCE_FORK	\
 				| SD_WAKE_AFFINE	\
 				| SD_WAKE_BALANCE	\
-				| BALANCE_FOR_PKG_POWER,\
+				| sd_balance_for_package_power()\
+				| sd_power_saving_flags(),\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
 }