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/
  ...

16 files changed, 196 insertions, 175 deletions

diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 3795590e152a..0574add2a1e3 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -127,7 +127,7 @@ struct acpi_processor_performance {
         unsigned int state_count;
         struct acpi_processor_px *states;
         struct acpi_psd_package domain_info;
-        cpumask_t shared_cpu_map;
+        cpumask_var_t shared_cpu_map;
         unsigned int shared_type;
 };
 
@@ -172,7 +172,7 @@ struct acpi_processor_throttling {
         unsigned int state_count;
         struct acpi_processor_tx_tss *states_tss;
         struct acpi_tsd_package domain_info;
-        cpumask_t shared_cpu_map;
+        cpumask_var_t shared_cpu_map;
         int (*acpi_processor_get_throttling) (struct acpi_processor * pr);
         int (*acpi_processor_set_throttling) (struct acpi_processor * pr,
                                               int state);
diff --git a/include/asm-frv/bitops.h b/include/asm-frv/bitops.h
index 39456ba0ec17..287f6f697ce2 100644
--- a/include/asm-frv/bitops.h
+++ b/include/asm-frv/bitops.h
@@ -339,6 +339,19 @@ int __ffs(unsigned long x)
         return 31 - bit;
 }
 
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __fls(unsigned long word)
+{
+        unsigned long bit;
+        asm("scan %1,gr0,%0" : "=r"(bit) : "r"(word));
+        return bit;
+}
+
 /*
  * special slimline version of fls() for calculating ilog2_u32()
  * - note: no protection against n == 0
diff --git a/include/asm-m32r/bitops.h b/include/asm-m32r/bitops.h
index 6dc9b81bf9f3..aaddf0d57603 100644
--- a/include/asm-m32r/bitops.h
+++ b/include/asm-m32r/bitops.h
@@ -251,6 +251,7 @@ static __inline__ int test_and_change_bit(int nr, volatile void * addr)
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #ifdef __KERNEL__
diff --git a/include/asm-m68k/bitops.h b/include/asm-m68k/bitops.h
index 3e8106442d5a..9bde784e7bad 100644
--- a/include/asm-m68k/bitops.h
+++ b/include/asm-m68k/bitops.h
@@ -315,6 +315,11 @@ static inline int fls(int x)
         return 32 - cnt;
 }
 
+static inline int __fls(int x)
+{
+        return fls(x) - 1;
+}
+
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
diff --git a/include/asm-mn10300/bitops.h b/include/asm-mn10300/bitops.h
index cc6d40c05cf3..0b610f482abb 100644
--- a/include/asm-mn10300/bitops.h
+++ b/include/asm-mn10300/bitops.h
@@ -196,6 +196,17 @@ int fls(int x)
 }
 
 /**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __fls(unsigned long word)
+{
+        return __ilog2_u32(word);
+}
+
+/**
  * ffs - find first bit set
  * @x: the word to search
  *
diff --git a/include/asm-xtensa/bitops.h b/include/asm-xtensa/bitops.h
index 23261e8f2e5a..6c3930397bd3 100644
--- a/include/asm-xtensa/bitops.h
+++ b/include/asm-xtensa/bitops.h
@@ -82,6 +82,16 @@ static inline int fls (unsigned int x)
         return 32 - __cntlz(x);
 }
 
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __fls(unsigned long word)
+{
+        return 31 - __cntlz(word);
+}
 #else
 
 /* Use the generic implementation if we don't have the nsa/nsau instructions. */
@@ -90,6 +100,7 @@ static inline int fls (unsigned int x)
 # include <asm-generic/bitops/__ffs.h>
 # include <asm-generic/bitops/ffz.h>
 # include <asm-generic/bitops/fls.h>
+# include <asm-generic/bitops/__fls.h>
 
 #endif
 
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index a08c33a26ca9..2878811c6134 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -137,9 +137,12 @@ extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
                 (1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL               \
 )
 
+#define small_const_nbits(nbits) \
+        (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
+
 static inline void bitmap_zero(unsigned long *dst, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = 0UL;
         else {
                 int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
@@ -150,7 +153,7 @@ static inline void bitmap_zero(unsigned long *dst, int nbits)
 static inline void bitmap_fill(unsigned long *dst, int nbits)
 {
         size_t nlongs = BITS_TO_LONGS(nbits);
-        if (nlongs > 1) {
+        if (!small_const_nbits(nbits)) {
                 int len = (nlongs - 1) * sizeof(unsigned long);
                 memset(dst, 0xff,  len);
         }
@@ -160,7 +163,7 @@ static inline void bitmap_fill(unsigned long *dst, int nbits)
 static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
                         int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = *src;
         else {
                 int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
@@ -171,7 +174,7 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 static inline void bitmap_and(unsigned long *dst, const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = *src1 & *src2;
         else
                 __bitmap_and(dst, src1, src2, nbits);
@@ -180,7 +183,7 @@ static inline void bitmap_and(unsigned long *dst, const unsigned long *src1,
 static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = *src1 | *src2;
         else
                 __bitmap_or(dst, src1, src2, nbits);
@@ -189,7 +192,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = *src1 ^ *src2;
         else
                 __bitmap_xor(dst, src1, src2, nbits);
@@ -198,7 +201,7 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 static inline void bitmap_andnot(unsigned long *dst, const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = *src1 & ~(*src2);
         else
                 __bitmap_andnot(dst, src1, src2, nbits);
@@ -207,7 +210,7 @@ static inline void bitmap_andnot(unsigned long *dst, const unsigned long *src1,
 static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
                         int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits);
         else
                 __bitmap_complement(dst, src, nbits);
@@ -216,7 +219,7 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr
 static inline int bitmap_equal(const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
         else
                 return __bitmap_equal(src1, src2, nbits);
@@ -225,7 +228,7 @@ static inline int bitmap_equal(const unsigned long *src1,
 static inline int bitmap_intersects(const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
         else
                 return __bitmap_intersects(src1, src2, nbits);
@@ -234,7 +237,7 @@ static inline int bitmap_intersects(const unsigned long *src1,
 static inline int bitmap_subset(const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
         else
                 return __bitmap_subset(src1, src2, nbits);
@@ -242,7 +245,7 @@ static inline int bitmap_subset(const unsigned long *src1,
 
 static inline int bitmap_empty(const unsigned long *src, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
         else
                 return __bitmap_empty(src, nbits);
@@ -250,7 +253,7 @@ static inline int bitmap_empty(const unsigned long *src, int nbits)
 
 static inline int bitmap_full(const unsigned long *src, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
         else
                 return __bitmap_full(src, nbits);
@@ -258,7 +261,7 @@ static inline int bitmap_full(const unsigned long *src, int nbits)
 
 static inline int bitmap_weight(const unsigned long *src, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
         return __bitmap_weight(src, nbits);
 }
@@ -266,7 +269,7 @@ static inline int bitmap_weight(const unsigned long *src, int nbits)
 static inline void bitmap_shift_right(unsigned long *dst,
                         const unsigned long *src, int n, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = *src >> n;
         else
                 __bitmap_shift_right(dst, src, n, nbits);
@@ -275,7 +278,7 @@ static inline void bitmap_shift_right(unsigned long *dst,
 static inline void bitmap_shift_left(unsigned long *dst,
                         const unsigned long *src, int n, int nbits)
 {
-        if (nbits <= BITS_PER_LONG)
+        if (small_const_nbits(nbits))
                 *dst = (*src << n) & BITMAP_LAST_WORD_MASK(nbits);
         else
                 __bitmap_shift_left(dst, src, n, nbits);
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 024f2b027244..61829139795a 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -134,9 +134,20 @@ extern unsigned long find_first_bit(const unsigned long *addr,
  */
 extern unsigned long find_first_zero_bit(const unsigned long *addr,
                                          unsigned long size);
-
 #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
+#ifdef CONFIG_GENERIC_FIND_LAST_BIT
+/**
+ * find_last_bit - find the last set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit, or size.
+ */
+extern unsigned long find_last_bit(const unsigned long *addr,
+                                   unsigned long size);
+#endif /* CONFIG_GENERIC_FIND_LAST_BIT */
+
 #ifdef CONFIG_GENERIC_FIND_NEXT_BIT
 
 /**
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index d4bf52603e6b..9f315382610b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -144,6 +144,7 @@
 typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
 extern cpumask_t _unused_cpumask_arg_;
 
+#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
 #define cpu_set(cpu, dst) __cpu_set((cpu), &(dst))
 static inline void __cpu_set(int cpu, volatile cpumask_t *dstp)
 {
@@ -267,6 +268,26 @@ static inline void __cpus_shift_left(cpumask_t *dstp,
 {
         bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
 }
+#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
+
+/**
+ * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
+ * @bitmap: the bitmap
+ *
+ * There are a few places where cpumask_var_t isn't appropriate and
+ * static cpumasks must be used (eg. very early boot), yet we don't
+ * expose the definition of 'struct cpumask'.
+ *
+ * This does the conversion, and can be used as a constant initializer.
+ */
+#define to_cpumask(bitmap)                                              \
+        ((struct cpumask *)(1 ? (bitmap)                                \
+                            : (void *)sizeof(__check_is_bitmap(bitmap))))
+
+static inline int __check_is_bitmap(const unsigned long *bitmap)
+{
+        return 1;
+}
 
 /*
  * Special-case data structure for "single bit set only" constant CPU masks.
@@ -278,13 +299,14 @@ static inline void __cpus_shift_left(cpumask_t *dstp,
 extern const unsigned long
         cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)];
 
-static inline const cpumask_t *get_cpu_mask(unsigned int cpu)
+static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 {
         const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];
         p -= cpu / BITS_PER_LONG;
-        return (const cpumask_t *)p;
+        return to_cpumask(p);
 }
 
+#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
 /*
  * In cases where we take the address of the cpumask immediately,
  * gcc optimizes it out (it's a constant) and there's no huge stack
@@ -370,19 +392,22 @@ static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp,
 {
         bitmap_fold(dstp->bits, origp->bits, sz, nbits);
 }
+#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
 
 #if NR_CPUS == 1
 
 #define nr_cpu_ids              1
+#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
 #define first_cpu(src)          ({ (void)(src); 0; })
 #define next_cpu(n, src)        ({ (void)(src); 1; })
 #define any_online_cpu(mask)    0
 #define for_each_cpu_mask(cpu, mask)    \
         for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
-
+#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
 #else /* NR_CPUS > 1 */
 
 extern int nr_cpu_ids;
+#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
 int __first_cpu(const cpumask_t *srcp);
 int __next_cpu(int n, const cpumask_t *srcp);
 int __any_online_cpu(const cpumask_t *mask);
@@ -394,8 +419,10 @@ int __any_online_cpu(const cpumask_t *mask);
         for ((cpu) = -1;                                \
                 (cpu) = next_cpu((cpu), (mask)),        \
                 (cpu) < NR_CPUS; )
+#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
 #endif
 
+#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
 #if NR_CPUS <= 64
 
 #define next_cpu_nr(n, src)             next_cpu(n, src)
@@ -413,77 +440,67 @@ int __next_cpu_nr(int n, const cpumask_t *srcp);
                 (cpu) < nr_cpu_ids; )
 
 #endif /* NR_CPUS > 64 */
+#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
 
 /*
  * The following particular system cpumasks and operations manage
- * possible, present, active and online cpus.  Each of them is a fixed size
- * bitmap of size NR_CPUS.
+ * possible, present, active and online cpus.
  *
- *  #ifdef CONFIG_HOTPLUG_CPU
- *     cpu_possible_map - has bit 'cpu' set iff cpu is populatable
- *     cpu_present_map  - has bit 'cpu' set iff cpu is populated
- *     cpu_online_map   - has bit 'cpu' set iff cpu available to scheduler
- *     cpu_active_map   - has bit 'cpu' set iff cpu available to migration
- *  #else
- *     cpu_possible_map - has bit 'cpu' set iff cpu is populated
- *     cpu_present_map  - copy of cpu_possible_map
- *     cpu_online_map   - has bit 'cpu' set iff cpu available to scheduler
- *  #endif
+ *     cpu_possible_mask- has bit 'cpu' set iff cpu is populatable
+ *     cpu_present_mask - has bit 'cpu' set iff cpu is populated
+ *     cpu_online_mask  - has bit 'cpu' set iff cpu available to scheduler
+ *     cpu_active_mask  - has bit 'cpu' set iff cpu available to migration
  *
- *  In either case, NR_CPUS is fixed at compile time, as the static
- *  size of these bitmaps.  The cpu_possible_map is fixed at boot
- *  time, as the set of CPU id's that it is possible might ever
- *  be plugged in at anytime during the life of that system boot.
- *  The cpu_present_map is dynamic(*), representing which CPUs
- *  are currently plugged in.  And cpu_online_map is the dynamic
- *  subset of cpu_present_map, indicating those CPUs available
- *  for scheduling.
+ *  If !CONFIG_HOTPLUG_CPU, present == possible, and active == online.
  *
- *  If HOTPLUG is enabled, then cpu_possible_map is forced to have
+ *  The cpu_possible_mask is fixed at boot time, as the set of CPU id's
+ *  that it is possible might ever be plugged in at anytime during the
+ *  life of that system boot.  The cpu_present_mask is dynamic(*),
+ *  representing which CPUs are currently plugged in.  And
+ *  cpu_online_mask is the dynamic subset of cpu_present_mask,
+ *  indicating those CPUs available for scheduling.
+ *
+ *  If HOTPLUG is enabled, then cpu_possible_mask is forced to have
  *  all NR_CPUS bits set, otherwise it is just the set of CPUs that
  *  ACPI reports present at boot.
  *
- *  If HOTPLUG is enabled, then cpu_present_map varies dynamically,
+ *  If HOTPLUG is enabled, then cpu_present_mask varies dynamically,
  *  depending on what ACPI reports as currently plugged in, otherwise
- *  cpu_present_map is just a copy of cpu_possible_map.
+ *  cpu_present_mask is just a copy of cpu_possible_mask.
  *
- *  (*) Well, cpu_present_map is dynamic in the hotplug case.  If not
- *      hotplug, it's a copy of cpu_possible_map, hence fixed at boot.
+ *  (*) Well, cpu_present_mask is dynamic in the hotplug case.  If not
+ *      hotplug, it's a copy of cpu_possible_mask, hence fixed at boot.
  *
  * Subtleties:
  * 1) UP arch's (NR_CPUS == 1, CONFIG_SMP not defined) hardcode
  *    assumption that their single CPU is online.  The UP
- *    cpu_{online,possible,present}_maps are placebos.  Changing them
+ *    cpu_{online,possible,present}_masks are placebos.  Changing them
  *    will have no useful affect on the following num_*_cpus()
  *    and cpu_*() macros in the UP case.  This ugliness is a UP
  *    optimization - don't waste any instructions or memory references
  *    asking if you're online or how many CPUs there are if there is
  *    only one CPU.
- * 2) Most SMP arch's #define some of these maps to be some
- *    other map specific to that arch.  Therefore, the following
- *    must be #define macros, not inlines.  To see why, examine
- *    the assembly code produced by the following.  Note that
- *    set1() writes phys_x_map, but set2() writes x_map:
- *        int x_map, phys_x_map;
- *        #define set1(a) x_map = a
- *        inline void set2(int a) { x_map = a; }
- *        #define x_map phys_x_map
- *        main(){ set1(3); set2(5); }
  */
 
-extern cpumask_t cpu_possible_map;
-extern cpumask_t cpu_online_map;
-extern cpumask_t cpu_present_map;
-extern cpumask_t cpu_active_map;
+extern const struct cpumask *const cpu_possible_mask;
+extern const struct cpumask *const cpu_online_mask;
+extern const struct cpumask *const cpu_present_mask;
+extern const struct cpumask *const cpu_active_mask;
+
+/* These strip const, as traditionally they weren't const. */
+#define cpu_possible_map        (*(cpumask_t *)cpu_possible_mask)
+#define cpu_online_map          (*(cpumask_t *)cpu_online_mask)
+#define cpu_present_map         (*(cpumask_t *)cpu_present_mask)
+#define cpu_active_map          (*(cpumask_t *)cpu_active_mask)
 
 #if NR_CPUS > 1
-#define num_online_cpus()       cpus_weight_nr(cpu_online_map)
-#define num_possible_cpus()     cpus_weight_nr(cpu_possible_map)
-#define num_present_cpus()      cpus_weight_nr(cpu_present_map)
-#define cpu_online(cpu)         cpu_isset((cpu), cpu_online_map)
-#define cpu_possible(cpu)       cpu_isset((cpu), cpu_possible_map)
-#define cpu_present(cpu)        cpu_isset((cpu), cpu_present_map)
-#define cpu_active(cpu)         cpu_isset((cpu), cpu_active_map)
+#define num_online_cpus()       cpumask_weight(cpu_online_mask)
+#define num_possible_cpus()     cpumask_weight(cpu_possible_mask)
+#define num_present_cpus()      cpumask_weight(cpu_present_mask)
+#define cpu_online(cpu)         cpumask_test_cpu((cpu), cpu_online_mask)
+#define cpu_possible(cpu)       cpumask_test_cpu((cpu), cpu_possible_mask)
+#define cpu_present(cpu)        cpumask_test_cpu((cpu), cpu_present_mask)
+#define cpu_active(cpu)         cpumask_test_cpu((cpu), cpu_active_mask)
 #else
 #define num_online_cpus()       1
 #define num_possible_cpus()     1
@@ -496,10 +513,6 @@ extern cpumask_t cpu_active_map;
 
 #define cpu_is_offline(cpu)     unlikely(!cpu_online(cpu))
 
-#define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_possible_map)
-#define for_each_online_cpu(cpu)   for_each_cpu_mask_nr((cpu), cpu_online_map)
-#define for_each_present_cpu(cpu)  for_each_cpu_mask_nr((cpu), cpu_present_map)
-
 /* These are the new versions of the cpumask operators: passed by pointer.
  * The older versions will be implemented in terms of these, then deleted. */
 #define cpumask_bits(maskp) ((maskp)->bits)
@@ -687,7 +700,7 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  * No static inline type checking - see Subtlety (1) above.
  */
 #define cpumask_test_cpu(cpu, cpumask) \
-        test_bit(cpumask_check(cpu), (cpumask)->bits)
+        test_bit(cpumask_check(cpu), cpumask_bits((cpumask)))
 
 /**
  * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask
@@ -930,7 +943,7 @@ static inline void cpumask_copy(struct cpumask *dstp,
 static inline int cpumask_scnprintf(char *buf, int len,
                                     const struct cpumask *srcp)
 {
-        return bitmap_scnprintf(buf, len, srcp->bits, nr_cpumask_bits);
+        return bitmap_scnprintf(buf, len, cpumask_bits(srcp), nr_cpumask_bits);
 }
 
 /**
@@ -944,7 +957,7 @@ static inline int cpumask_scnprintf(char *buf, int len,
 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);
+        return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -959,7 +972,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len,
 static inline int cpulist_scnprintf(char *buf, int len,
                                     const struct cpumask *srcp)
 {
-        return bitmap_scnlistprintf(buf, len, srcp->bits, nr_cpumask_bits);
+        return bitmap_scnlistprintf(buf, len, cpumask_bits(srcp),
+                                    nr_cpumask_bits);
 }
 
 /**
@@ -972,26 +986,7 @@ static inline int cpulist_scnprintf(char *buf, int len,
  */
 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
- *
- * There are a few places where cpumask_var_t isn't appropriate and
- * static cpumasks must be used (eg. very early boot), yet we don't
- * expose the definition of 'struct cpumask'.
- *
- * This does the conversion, and can be used as a constant initializer.
- */
-#define to_cpumask(bitmap)                                              \
-        ((struct cpumask *)(1 ? (bitmap)                                \
-                            : (void *)sizeof(__check_is_bitmap(bitmap))))
-
-static inline int __check_is_bitmap(const unsigned long *bitmap)
-{
-        return 1;
+        return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -1025,6 +1020,7 @@ static inline size_t cpumask_size(void)
 #ifdef CONFIG_CPUMASK_OFFSTACK
 typedef struct cpumask *cpumask_var_t;
 
+bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
 void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
@@ -1038,6 +1034,12 @@ static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
         return true;
 }
 
+static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+                                          int node)
+{
+        return true;
+}
+
 static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
 }
@@ -1051,12 +1053,6 @@ static inline void free_bootmem_cpumask_var(cpumask_var_t mask)
 }
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 
-/* The pointer versions of the maps, these will become the primary versions. */
-#define cpu_possible_mask ((const struct cpumask *)&cpu_possible_map)
-#define cpu_online_mask ((const struct cpumask *)&cpu_online_map)
-#define cpu_present_mask ((const struct cpumask *)&cpu_present_map)
-#define cpu_active_mask ((const struct cpumask *)&cpu_active_map)
-
 /* It's common to want to use cpu_all_mask in struct member initializers,
  * so it has to refer to an address rather than a pointer. */
 extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS);
@@ -1065,51 +1061,16 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS);
 /* First bits of cpu_bit_bitmap are in fact unset. */
 #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0])
 
-/* Wrappers for arch boot code to manipulate normally-constant masks */
-static inline void set_cpu_possible(unsigned int cpu, bool possible)
-{
-        if (possible)
-                cpumask_set_cpu(cpu, &cpu_possible_map);
-        else
-                cpumask_clear_cpu(cpu, &cpu_possible_map);
-}
-
-static inline void set_cpu_present(unsigned int cpu, bool present)
-{
-        if (present)
-                cpumask_set_cpu(cpu, &cpu_present_map);
-        else
-                cpumask_clear_cpu(cpu, &cpu_present_map);
-}
-
-static inline void set_cpu_online(unsigned int cpu, bool online)
-{
-        if (online)
-                cpumask_set_cpu(cpu, &cpu_online_map);
-        else
-                cpumask_clear_cpu(cpu, &cpu_online_map);
-}
+#define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask)
+#define for_each_online_cpu(cpu)   for_each_cpu((cpu), cpu_online_mask)
+#define for_each_present_cpu(cpu)  for_each_cpu((cpu), cpu_present_mask)
 
-static inline void set_cpu_active(unsigned int cpu, bool active)
-{
-        if (active)
-                cpumask_set_cpu(cpu, &cpu_active_map);
-        else
-                cpumask_clear_cpu(cpu, &cpu_active_map);
-}
-
-static inline void init_cpu_present(const struct cpumask *src)
-{
-        cpumask_copy(&cpu_present_map, src);
-}
-
-static inline void init_cpu_possible(const struct cpumask *src)
-{
-        cpumask_copy(&cpu_possible_map, src);
-}
-
-static inline void init_cpu_online(const struct cpumask *src)
-{
-        cpumask_copy(&cpu_online_map, src);
-}
+/* Wrappers for arch boot code to manipulate normally-constant masks */
+void set_cpu_possible(unsigned int cpu, bool possible);
+void set_cpu_present(unsigned int cpu, bool present);
+void set_cpu_online(unsigned int cpu, bool online);
+void set_cpu_active(unsigned int cpu, bool active);
+void init_cpu_present(const struct cpumask *src);
+void init_cpu_possible(const struct cpumask *src);
+void init_cpu_online(const struct cpumask *src);
 #endif /* __LINUX_CPUMASK_H */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 990355fbc54e..0702c4d7bdf0 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -109,7 +109,7 @@ extern void enable_irq(unsigned int irq);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 
-extern cpumask_t irq_default_affinity;
+extern cpumask_var_t irq_default_affinity;
 
 extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
 extern int irq_can_set_affinity(unsigned int irq);
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index 301dda829e37..f3f697df1d71 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -59,8 +59,8 @@ struct rcu_ctrlblk {
         int     signaled;
 
         spinlock_t      lock    ____cacheline_internodealigned_in_smp;
-        cpumask_t       cpumask; /* CPUs that need to switch in order    */
-                                 /* for current batch to proceed.        */
+        DECLARE_BITMAP(cpumask, NR_CPUS); /* CPUs that need to switch for */
+                                          /* current batch to proceed.     */
 } ____cacheline_internodealigned_in_smp;
 
 /* Is batch a before batch b ? */
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index b3dfa72f13b9..40ea5058c2ec 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -50,10 +50,11 @@ int seq_path(struct seq_file *, struct path *, char *);
 int seq_dentry(struct seq_file *, struct dentry *, char *);
 int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
                   char *esc);
-int seq_bitmap(struct seq_file *m, unsigned long *bits, unsigned int nr_bits);
-static inline int seq_cpumask(struct seq_file *m, cpumask_t *mask)
+int seq_bitmap(struct seq_file *m, const unsigned long *bits,
+                                   unsigned int nr_bits);
+static inline int seq_cpumask(struct seq_file *m, const struct cpumask *mask)
 {
-        return seq_bitmap(m, mask->bits, NR_CPUS);
+        return seq_bitmap(m, mask->bits, nr_cpu_ids);
 }
 
 static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask)
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 6e7ba16ff454..b82466968101 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -21,6 +21,9 @@ struct call_single_data {
         u16 priv;
 };
 
+/* total number of cpus in this system (may exceed NR_CPUS) */
+extern unsigned int total_cpus;
+
 #ifdef CONFIG_SMP
 
 #include <linux/preempt.h>
@@ -64,15 +67,16 @@ extern void smp_cpus_done(unsigned int max_cpus);
  * Call a function on all other processors
  */
 int smp_call_function(void(*func)(void *info), void *info, int wait);
-/* Deprecated: use smp_call_function_many() which uses a cpumask ptr. */
-int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
-                                int wait);
+void smp_call_function_many(const struct cpumask *mask,
+                            void (*func)(void *info), void *info, bool wait);
 
-static inline void smp_call_function_many(const struct cpumask *mask,
-                                          void (*func)(void *info), void *info,
-                                          int wait)
+/* Deprecated: Use smp_call_function_many which takes a pointer to the mask. */
+static inline int
+smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
+                       int wait)
 {
-        smp_call_function_mask(*mask, func, info, wait);
+        smp_call_function_many(&mask, func, info, wait);
+        return 0;
 }
 
 int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index faf1519b5adc..74d59a641362 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -23,7 +23,7 @@
  *
  * This can be thought of as a very heavy write lock, equivalent to
  * grabbing every spinlock in the kernel. */
-int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus);
+int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
 
 /**
  * __stop_machine: freeze the machine on all CPUs and run this function
@@ -34,11 +34,11 @@ int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus);
  * Description: This is a special version of the above, which assumes cpus
  * won't come or go while it's being called.  Used by hotplug cpu.
  */
-int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus);
+int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
 #else
 
 static inline int stop_machine(int (*fn)(void *), void *data,
-                               const cpumask_t *cpus)
+                               const struct cpumask *cpus)
 {
         int ret;
         local_irq_disable();
diff --git a/include/linux/threads.h b/include/linux/threads.h
index 38d1a5d6568e..052b12bec8bd 100644
--- a/include/linux/threads.h
+++ b/include/linux/threads.h
@@ -8,17 +8,17 @@
  */
 
 /*
- * Maximum supported processors that can run under SMP.  This value is
- * set via configure setting.  The maximum is equal to the size of the
- * bitmasks used on that platform, i.e. 32 or 64.  Setting this smaller
- * saves quite a bit of memory.
+ * Maximum supported processors.  Setting this smaller saves quite a
+ * bit of memory.  Use nr_cpu_ids instead of this except for static bitmaps.
  */
-#ifdef CONFIG_SMP
-#define NR_CPUS         CONFIG_NR_CPUS
-#else
-#define NR_CPUS         1
+#ifndef CONFIG_NR_CPUS
+/* FIXME: This should be fixed in the arch's Kconfig */
+#define CONFIG_NR_CPUS  1
 #endif
 
+/* Places which use this should consider cpumask_var_t. */
+#define NR_CPUS         CONFIG_NR_CPUS
+
 #define MIN_THREADS_LEFT_FOR_ROOT 4
 
 /*
diff --git a/include/linux/tick.h b/include/linux/tick.h
index b6ec8189ac0c..469b82d88b3b 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -84,10 +84,10 @@ static inline void tick_cancel_sched_timer(int cpu) { }
 
 # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern struct tick_device *tick_get_broadcast_device(void);
-extern cpumask_t *tick_get_broadcast_mask(void);
+extern struct cpumask *tick_get_broadcast_mask(void);
 
 #  ifdef CONFIG_TICK_ONESHOT
-extern cpumask_t *tick_get_broadcast_oneshot_mask(void);
+extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 #  endif
 
 # endif /* BROADCAST */