Merge branch 'cpus4096-for-linus-3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'cpus4096-for-linus-3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (77 commits)
  x86: setup_per_cpu_areas() cleanup
  cpumask: fix compile error when CONFIG_NR_CPUS is not defined
  cpumask: use alloc_cpumask_var_node where appropriate
  cpumask: convert shared_cpu_map in acpi_processor* structs to cpumask_var_t
  x86: use cpumask_var_t in acpi/boot.c
  x86: cleanup some remaining usages of NR_CPUS where s/b nr_cpu_ids
  sched: put back some stack hog changes that were undone in kernel/sched.c
  x86: enable cpus display of kernel_max and offlined cpus
  ia64: cpumask fix for is_affinity_mask_valid()
  cpumask: convert RCU implementations, fix
  xtensa: define __fls
  mn10300: define __fls
  m32r: define __fls
  h8300: define __fls
  frv: define __fls
  cris: define __fls
  cpumask: CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
  cpumask: zero extra bits in alloc_cpumask_var_node
  cpumask: replace for_each_cpu_mask_nr with for_each_cpu in kernel/time/
  cpumask: convert mm/
  ...

112 files changed, 1285 insertions, 878 deletions

diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index bd699da24666..45932ec21cee 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -31,3 +31,51 @@ not defined by include/asm-XXX/topology.h:
 2) core_id: 0
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
+
+Additionally, cpu topology information is provided under
+/sys/devices/system/cpu and includes these files.  The internal
+source for the output is in brackets ("[]").
+
+    kernel_max: the maximum cpu index allowed by the kernel configuration.
+		[NR_CPUS-1]
+
+    offline:	cpus that are not online because they have been
+		HOTPLUGGED off (see cpu-hotplug.txt) or exceed the limit
+		of cpus allowed by the kernel configuration (kernel_max
+		above). [~cpu_online_mask + cpus >= NR_CPUS]
+
+    online:	cpus that are online and being scheduled [cpu_online_mask]
+
+    possible:	cpus that have been allocated resources and can be
+		brought online if they are present. [cpu_possible_mask]
+
+    present:	cpus that have been identified as being present in the
+		system. [cpu_present_mask]
+
+The format for the above output is compatible with cpulist_parse()
+[see <linux/cpumask.h>].  Some examples follow.
+
+In this example, there are 64 cpus in the system but cpus 32-63 exceed
+the kernel max which is limited to 0..31 by the NR_CPUS config option
+being 32.  Note also that cpus 2 and 4-31 are not online but could be
+brought online as they are both present and possible.
+
+     kernel_max: 31
+        offline: 2,4-31,32-63
+         online: 0-1,3
+       possible: 0-31
+        present: 0-31
+
+In this example, the NR_CPUS config option is 128, but the kernel was
+started with possible_cpus=144.  There are 4 cpus in the system and cpu2
+was manually taken offline (and is the only cpu that can be brought
+online.)
+
+     kernel_max: 127
+        offline: 2,4-127,128-143
+         online: 0-1,3
+       possible: 0-127
+        present: 0-3
+
+See cpu-hotplug.txt for the possible_cpus=NUM kernel start parameter
+as well as more information on the various cpumask's.
diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h
index 149532e162c4..b4f284c72ff3 100644
--- a/arch/alpha/include/asm/topology.h
+++ b/arch/alpha/include/asm/topology.h
@@ -39,7 +39,24 @@ static inline cpumask_t node_to_cpumask(int node)
 	return node_cpu_mask;
 }
 
+extern struct cpumask node_to_cpumask_map[];
+/* FIXME: This is dumb, recalculating every time.  But simple. */
+static const struct cpumask *cpumask_of_node(int node)
+{
+	int cpu;
+
+	cpumask_clear(&node_to_cpumask_map[node]);
+
+	for_each_online_cpu(cpu) {
+		if (cpu_to_node(cpu) == node)
+			cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+	}
+
+	return &node_to_cpumask_map[node];
+}
+
 #define pcibus_to_cpumask(bus)	(cpu_online_map)
+#define cpumask_of_pcibus(bus)	(cpu_online_mask)
 
 #endif /* !CONFIG_NUMA */
 # include <asm-generic/topology.h>
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index d0f1620007f7..703731accda6 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -50,7 +50,8 @@ int irq_select_affinity(unsigned int irq)
 	if (!irq_desc[irq].chip->set_affinity || irq_user_affinity[irq])
 		return 1;
 
-	while (!cpu_possible(cpu) || !cpu_isset(cpu, irq_default_affinity))
+	while (!cpu_possible(cpu) ||
+	       !cpumask_test_cpu(cpu, irq_default_affinity))
 		cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
 	last_cpu = cpu;
 
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index a449e999027c..02bee6983ce2 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -79,6 +79,11 @@ int alpha_l3_cacheshape;
 unsigned long alpha_verbose_mcheck = CONFIG_VERBOSE_MCHECK_ON;
 #endif
 
+#ifdef CONFIG_NUMA
+struct cpumask node_to_cpumask_map[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_to_cpumask_map);
+#endif
+
 /* Which processor we booted from.  */
 int boot_cpuid;
 
diff --git a/arch/avr32/include/asm/bitops.h b/arch/avr32/include/asm/bitops.h
index 1a50b69b1a19..f7dd5f71edf7 100644
--- a/arch/avr32/include/asm/bitops.h
+++ b/arch/avr32/include/asm/bitops.h
@@ -263,6 +263,11 @@ static inline int fls(unsigned long word)
 	return 32 - result;
 }
 
+static inline int __fls(unsigned long word)
+{
+	return fls(word) - 1;
+}
+
 unsigned long find_first_zero_bit(const unsigned long *addr,
 				  unsigned long size);
 unsigned long find_next_zero_bit(const unsigned long *addr,
diff --git a/arch/blackfin/include/asm/bitops.h b/arch/blackfin/include/asm/bitops.h
index b39a175c79c1..c428e4106f89 100644
--- a/arch/blackfin/include/asm/bitops.h
+++ b/arch/blackfin/include/asm/bitops.h
@@ -213,6 +213,7 @@ static __inline__ int __test_bit(int nr, const void *addr)
 #endif				/* __KERNEL__ */
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #endif				/* _BLACKFIN_BITOPS_H */
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index c0e62f811e09..9e69cfb7f134 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -148,6 +148,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 #define ffs kernel_ffs
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/find.h>
diff --git a/arch/h8300/include/asm/bitops.h b/arch/h8300/include/asm/bitops.h
index cb18e3b0aa94..cb9ddf5fc54f 100644
--- a/arch/h8300/include/asm/bitops.h
+++ b/arch/h8300/include/asm/bitops.h
@@ -207,6 +207,7 @@ static __inline__ unsigned long __ffs(unsigned long word)
 #endif /* __KERNEL__ */
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #endif /* _H8300_BITOPS_H */
diff --git a/arch/ia64/include/asm/irq.h b/arch/ia64/include/asm/irq.h
index 3627116fb0e2..36429a532630 100644
--- a/arch/ia64/include/asm/irq.h
+++ b/arch/ia64/include/asm/irq.h
@@ -27,7 +27,7 @@ irq_canonicalize (int irq)
 }
 
 extern void set_irq_affinity_info (unsigned int irq, int dest, int redir);
-bool is_affinity_mask_valid(cpumask_t cpumask);
+bool is_affinity_mask_valid(cpumask_var_t cpumask);
 
 #define is_affinity_mask_valid is_affinity_mask_valid
 
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index a3cc9f65f954..76a33a91ca69 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -34,6 +34,7 @@
  * Returns a bitmask of CPUs on Node 'node'.
  */
 #define node_to_cpumask(node) (node_to_cpu_mask[node])
+#define cpumask_of_node(node) (&node_to_cpu_mask[node])
 
 /*
  * Returns the number of the node containing Node 'nid'.
@@ -45,7 +46,7 @@
 /*
  * Returns the number of the first CPU on Node 'node'.
  */
-#define node_to_first_cpu(node) (first_cpu(node_to_cpumask(node)))
+#define node_to_first_cpu(node) (cpumask_f