17 files changed, 642 insertions, 300 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1c91a176b9ae..6a642098e5c3 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -236,12 +236,16 @@ static inline void *bio_data(struct bio *bio)
 #define __BVEC_END(bio)         bio_iovec_idx((bio), (bio)->bi_vcnt - 1)
 #define __BVEC_START(bio)       bio_iovec_idx((bio), (bio)->bi_idx)
 
+/* Default implementation of BIOVEC_PHYS_MERGEABLE */
+#define __BIOVEC_PHYS_MERGEABLE(vec1, vec2)     \
+        ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
+
 /*
  * allow arch override, for eg virtualized architectures (put in asm/io.h)
  */
 #ifndef BIOVEC_PHYS_MERGEABLE
 #define BIOVEC_PHYS_MERGEABLE(vec1, vec2)       \
-        ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
+        __BIOVEC_PHYS_MERGEABLE(vec1, vec2)
 #endif
 
 #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h
index 8c0f9505b48c..7605fdd1eb65 100644
--- a/include/linux/cnt32_to_63.h
+++ b/include/linux/cnt32_to_63.h
@@ -16,6 +16,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/byteorder.h>
+#include <asm/system.h>
 
 /* this is used only to give gcc a clue about good code generation */
 union cnt32_to_63 {
@@ -53,11 +54,19 @@ union cnt32_to_63 {
  * needed increment.  And any race in updating the value in memory is harmless
  * as the same value would simply be stored more than once.
  *
- * The only restriction for the algorithm to work properly is that this
- * code must be executed at least once per each half period of the 32-bit
- * counter to properly update the state bit in memory. This is usually not a
- * problem in practice, but if it is then a kernel timer could be scheduled
- * to manage for this code to be executed often enough.
+ * The restrictions for the algorithm to work properly are:
+ *
+ * 1) this code must be called at least once per each half period of the
+ *    32-bit counter;
+ *
+ * 2) this code must not be preempted for a duration longer than the
+ *    32-bit counter half period minus the longest period between two
+ *    calls to this code.
+ *
+ * Those requirements ensure proper update to the state bit in memory.
+ * This is usually not a problem in practice, but if it is then a kernel
+ * timer should be scheduled to manage for this code to be executed often
+ * enough.
  *
  * Note that the top bit (bit 63) in the returned value should be considered
  * as garbage.  It is not cleared here because callers are likely to use a
@@ -68,9 +77,10 @@ union cnt32_to_63 {
  */
 #define cnt32_to_63(cnt_lo) \
 ({ \
-        static volatile u32 __m_cnt_hi; \
+        static u32 __m_cnt_hi; \
         union cnt32_to_63 __x; \
         __x.hi = __m_cnt_hi; \
+        smp_rmb(); \
         __x.lo = (cnt_lo); \
         if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \
                 __m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index d3219d73f8e6..21e1dd43e52a 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -5,6 +5,9 @@
  * Cpumasks provide a bitmap suitable for representing the
  * set of CPU's in a system, one bit position per CPU number.
  *
+ * The new cpumask_ ops take a "struct cpumask *"; the old ones
+ * use cpumask_t.
+ *
  * See detailed comments in the file linux/bitmap.h describing the
  * data type on which these cpumasks are based.
  *
@@ -31,7 +34,7 @@
  *       will span the entire range of NR_CPUS.
  * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
  *
- * The available cpumask operations are:
+ * The obsolescent cpumask operations are:
  *
  * void cpu_set(cpu, mask)              turn on bit 'cpu' in mask
  * void cpu_clear(cpu, mask)            turn off bit 'cpu' in mask
@@ -138,7 +141,7 @@
 #include <linux/threads.h>
 #include <linux/bitmap.h>
 
-typedef struct { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
+typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
 extern cpumask_t _unused_cpumask_arg_;
 
 #define cpu_set(cpu, dst) __cpu_set((cpu), &(dst))
@@ -527,4 +530,556 @@ extern cpumask_t cpu_active_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)
+
+#if NR_CPUS <= BITS_PER_LONG
+#define CPU_BITS_ALL                                            \
+{                                                               \
+        [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                                            \
+{                                                               \
+        [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,                \
+        [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD         \
+}
+
+#define nr_cpumask_bits nr_cpu_ids
+#endif /* NR_CPUS > BITS_PER_LONG */
+
+/* verify cpu argument to cpumask_* operators */
+static inline unsigned int cpumask_check(unsigned int cpu)
+{
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+        WARN_ON_ONCE(cpu >= nr_cpumask_bits);
+#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
+        return cpu;
+}
+
+#if NR_CPUS == 1
+/* Uniprocessor.  Assume all masks are "1". */
+static inline unsigned int cpumask_first(const struct cpumask *srcp)
+{
+        return 0;
+}
+
+/* Valid inputs for n are -1 and 0. */
+static inline unsigned int cpumask_next(int n, const struct cpumask *srcp)
+{
+        return n+1;
+}
+
+static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
+{
+        return n+1;
+}
+
+static inline unsigned int cpumask_next_and(int n,
+                                            const struct cpumask *srcp,
+                                            const struct cpumask *andp)
+{
+        return n+1;
+}
+
+/* cpu must be a valid cpu, ie 0, so there's no other choice. */
+static inline unsigned int cpumask_any_but(const struct cpumask *mask,
+                                           unsigned int cpu)
+{
+        return 1;
+}
+
+#define for_each_cpu(cpu, mask)                 \
+        for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
+#define for_each_cpu_and(cpu, mask, and)        \
+        for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)and)
+#else
+/**
+ * cpumask_first - get the first cpu in a cpumask
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static inline unsigned int cpumask_first(const struct cpumask *srcp)
+{
+        return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_next - get the next cpu in a cpumask
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set.
+ */
+static inline unsigned int cpumask_next(int n, const struct cpumask *srcp)
+{
+        /* -1 is a legal arg here. */
+        if (n != -1)
+                cpumask_check(n);
+        return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
+}
+
+/**
+ * cpumask_next_zero - get the next unset cpu in a cpumask
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus unset.
+ */
+static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
+{
+        /* -1 is a legal arg here. */
+        if (n != -1)
+                cpumask_check(n);
+        return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
+}
+
+int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
+int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
+
+/**
+ * for_each_cpu - iterate over every cpu in a mask
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask pointer
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu(cpu, mask)                         \
+        for ((cpu) = -1;                                \
+                (cpu) = cpumask_next((cpu), (mask)),    \
+                (cpu) < nr_cpu_ids;)
+
+/**
+ * for_each_cpu_and - iterate over every cpu in both masks
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the first cpumask pointer
+ * @and: the second cpumask pointer
+ *
+ * This saves a temporary CPU mask in many places.  It is equivalent to:
+ *      struct cpumask tmp;
+ *      cpumask_and(&tmp, &mask, &and);
+ *      for_each_cpu(cpu, &tmp)
+ *              ...
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_and(cpu, mask, and)                                \
+        for ((cpu) = -1;                                                \
+                (cpu) = cpumask_next_and((cpu), (mask), (and)),         \
+                (cpu) < nr_cpu_ids;)
+#endif /* SMP */
+
+#define CPU_BITS_NONE                                           \
+{                                                               \
+        [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL                  \
+}
+
+#define CPU_BITS_CPU0                                           \
+{                                                               \
+        [0] =  1UL                                              \
+}
+
+/**
+ * cpumask_set_cpu - set a cpu in a cpumask
+ * @cpu: cpu number (< nr_cpu_ids)
+ * @dstp: the cpumask pointer
+ */
+static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+{
+        set_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
+/**
+ * cpumask_clear_cpu - clear a cpu in a cpumask
+ * @cpu: cpu number (< nr_cpu_ids)
+ * @dstp: the cpumask pointer
+ */
+static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+        clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
+/**
+ * cpumask_test_cpu - test for a cpu in a cpumask
+ * @cpu: cpu number (< nr_cpu_ids)
+ * @cpumask: the cpumask pointer
+ *
+ * No static inline type checking - see Subtlety (1) above.
+ */
+#define cpumask_test_cpu(cpu, cpumask) \
+        test_bit(cpumask_check(cpu), (cpumask)->bits)
+
+/**
+ * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask
+ * @cpu: cpu number (< nr_cpu_ids)
+ * @cpumask: the cpumask pointer
+ *
+ * test_and_set_bit wrapper for cpumasks.
+ */
+static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+{
+        return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
+}
+
+/**
+ * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask
+ * @dstp: the cpumask pointer
+ */
+static inline void cpumask_setall(struct cpumask *dstp)
+{
+        bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask
+ * @dstp: the cpumask pointer
+ */
+static inline void cpumask_clear(struct cpumask *dstp)
+{
+        bitmap_zero(cpumask_bits(dstp), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_and - *dstp = *src1p & *src2p
+ * @dstp: the cpumask result
+ * @src1p: the first input
+ * @src2p: the second input
+ */
+static inline void cpumask_and(struct cpumask *dstp,
+                               const struct cpumask *src1p,
+                               const struct cpumask *src2p)
+{
+        bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
+                                       cpumask_bits(src2p), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_or - *dstp = *src1p | *src2p
+ * @dstp: the cpumask result
+ * @src1p: the first input
+ * @src2p: the second input
+ */
+static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
+                              const struct cpumask *src2p)
+{
+        bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p),
+                                      cpumask_bits(src2p), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_xor - *dstp = *src1p ^ *src2p
+ * @dstp: the cpumask result
+ * @src1p: the first input
+ * @src2p: the second input
+ */
+static inline void cpumask_xor(struct cpumask *dstp,
+                               const struct cpumask *src1p,
+                               const struct cpumask *src2p)
+{
+        bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p),
+                                       cpumask_bits(src2p), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_andnot - *dstp = *src1p & ~*src2p
+ * @dstp: the cpumask result
+ * @src1p: the first input
+ * @src2p: the second input
+ */
+static inline void cpumask_andnot(struct cpumask *dstp,
+                                  const struct cpumask *src1p,
+                                  const struct cpumask *src2p)
+{
+        bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
+                                          cpumask_bits(src2p), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_complement - *dstp = ~*srcp
+ * @dstp: the cpumask result
+ * @srcp: the input to invert
+ */
+static inline void cpumask_complement(struct cpumask *dstp,
+                                      const struct cpumask *srcp)
+{
+        bitmap_complement(cpumask_bits(dstp), cpumask_bits(srcp),
+                                              nr_cpumask_bits);
+}
+
+/**
+ * cpumask_equal - *src1p == *src2p
+ * @src1p: the first input
+ * @src2p: the second input
+ */
+static inline bool cpumask_equal(const struct cpumask *src1p,
+                                const struct cpumask *src2p)
+{
+        return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p),
+                                                 nr_cpumask_bits);
+}
+
+/**
+ * cpumask_intersects - (*src1p & *src2p) != 0
+ * @src1p: the first input
+ * @src2p: the second input
+ */
+static inline bool cpumask_intersects(const struct cpumask *src1p,
+                                     const struct cpumask *src2p)
+{
+        return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p),
+                                                      nr_cpumask_bits);
+}
+
+/**
+ * cpumask_subset - (*src1p & ~*src2p) == 0
+ * @src1p: the first input
+ * @src2p: the second input
+ */
+static inline int cpumask_subset(const struct cpumask *src1p,
+                                 const struct cpumask *src2p)
+{
+        return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
+                                                  nr_cpumask_bits);
+}
+
+/**
+ * cpumask_empty - *srcp == 0
+ * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear.
+ */
+static inline bool cpumask_empty(const struct cpumask *srcp)
+{
+        return bitmap_empty(cpumask_bits(srcp), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_full - *srcp == 0xFFFFFFFF...
+ * @srcp: the cpumask to that all cpus < nr_cpu_ids are set.
+ */
+static inline bool cpumask_full(const struct cpumask *srcp)
+{
+        return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_weight - Count of bits in *srcp
+ * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ */
+static inline unsigned int cpumask_weight(const struct cpumask *srcp)
+{
+        return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_shift_right - *dstp = *srcp >> n
+ * @dstp: the cpumask result
+ * @srcp: the input to shift
+ * @n: the number of bits to shift by
+ */
+static inline void cpumask_shift_right(struct cpumask *dstp,
+                                       const struct cpumask *srcp, int n)
+{
+        bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n,
+                                               nr_cpumask_bits);
+}
+
+/**
+ * cpumask_shift_left - *dstp = *srcp << n
+ * @dstp: the cpumask result
+ * @srcp: the input to shift
+ * @n: the number of bits to shift by
+ */
+static inline void cpumask_shift_left(struct cpumask *dstp,
+                                      const struct cpumask *srcp, int n)
+{
+        bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n,
+                                              nr_cpumask_bits);
+}
+
+/**
+ * cpumask_copy - *dstp = *srcp
+ * @dstp: the result
+ * @srcp: the input cpumask
+ */
+static inline void cpumask_copy(struct cpumask *dstp,
+                                const struct cpumask *srcp)
+{
+        bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), nr_cpumask_bits);
+}
+
+/**
+ * cpumask_any - pick a "random" cpu from *srcp
+ * @srcp: the input cpumask
+ *
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+#define cpumask_any(srcp) cpumask_first(srcp)
+
+/**
+ * cpumask_first_and - return the first cpu from *srcp1 & *srcp2
+ * @src1p: the first input
+ * @src2p: the second input
+ *
+ * Returns >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
+ */
+#define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p))
+
+/**
+ * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ *
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+#define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2))
+
+/**
+ * cpumask_of - the cpumask containing just a given cpu
+ * @cpu: the cpu (<= nr_cpu_ids)
+ */
+#define cpumask_of(cpu) (get_cpu_mask(cpu))
+
+/**
+ * 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;
+}
+
+/**
+ * cpumask_size - size to allocate for a 'struct cpumask' in bytes
+ *
+ * This will eventually be a runtime variable, depending on nr_cpu_ids.
+ */
+static inline size_t cpumask_size(void)
+{
+        /* FIXME: Once all cpumask assignments are eliminated, this
+         * can be nr_cpumask_bits */
+        return BITS_TO_LONGS(NR_CPUS) * sizeof(long);
+}
+
+/*
+ * cpumask_var_t: struct cpumask for stack usage.
+ *
+ * Oh, the wicked games we play!  In order to make kernel coding a
+ * little more difficult, we typedef cpumask_var_t to an array or a
+ * pointer: doing &mask on an array is a noop, so it still works.
+ *
+ * ie.
+ *      cpumask_var_t tmpmask;
+ *      if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ *              return -ENOMEM;
+ *
+ *        ... use 'tmpmask' like a normal struct cpumask * ...
+ *
+ *      free_cpumask_var(tmpmask);
+ */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+typedef struct cpumask *cpumask_var_t;
+
+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);
+void free_bootmem_cpumask_var(cpumask_var_t mask);
+
+#else
+typedef struct cpumask cpumask_var_t[1];
+
+static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+        return true;
+}
+
+static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
+{
+}
+
+static inline void free_cpumask_var(cpumask_var_t mask)
+{
+}
+
+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);
+#define cpu_all_mask to_cpumask(cpu_all_bits)
+
+/* 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);
+}
+
+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);
+}
 #endif /* __LINUX_CPUMASK_H */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 2b3645b1acf4..07e510a3b00a 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -239,7 +239,7 @@ static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
         timer->_softexpires = ktime_add_safe(timer->_softexpires, time);
 }
 
-static inline void hrtimer_add_expires_ns(struct hrtimer *timer, unsigned long ns)
+static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns)
 {
         timer->_expires = ktime_add_ns(timer->_expires, ns);
         timer->_softexpires = ktime_add_ns(timer->_softexpires, ns);
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 9e7b49b8062d..a5cb0c3f6dcf 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -114,6 +114,8 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev);
 
 extern int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
                              u16 vlan_tci, int polling);
+extern int vlan_hwaccel_do_receive(struct sk_buff *skb);
+
 #else
 static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
@@ -133,6 +135,11 @@ static inline int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
         BUG();
         return NET_XMIT_SUCCESS;
 }
+
+static inline int vlan_hwaccel_do_receive(struct sk_buff *skb)
+{
+        return 0;
+}
 #endif
 
 /**
diff --git a/include/linux/libata.h b/include/linux/libata.h
index f5441edee55f..59b0f1c807b5 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -373,6 +373,8 @@ enum {
         ATA_HORKAGE_IVB         = (1 << 8),     /* cbl det validity bit bugs */
         ATA_HORKAGE_STUCK_ERR   = (1 << 9),     /* stuck ERR on next PACKET */
         ATA_HORKAGE_BRIDGE_OK   = (1 << 10),    /* no bridge limits */
+        ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands
+                                                    not multiple of 16 bytes */
 
          /* DMA mask for user DMA control: User visible values; DO NOT
             renumber */
@@ -696,6 +698,7 @@ struct ata_port {
         unsigned int            cbl;    /* cable type; ATA_CBL_xxx */
 
         struct ata_queued_cmd   qcmd[ATA_MAX_QUEUE];
+        unsigned long           qc_allocated;
         unsigned int            qc_active;
         int                     nr_active_links; /* #links with active qcs */
 
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index ee6e822d5994..403aa505f27e 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -130,7 +130,7 @@ struct mmc_card {
 #define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR)
 
 #define mmc_card_name(c)        ((c)->cid.prod_name)
-#define mmc_card_id(c)          ((c)->dev.bus_id)
+#define mmc_card_id(c)          (dev_name(&(c)->dev))
 
 #define mmc_list_to_card(l)     container_of(l, struct mmc_card, node)
 #define mmc_get_drvdata(c)      dev_get_drvdata(&(c)->dev)
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index bde891f64591..f842f234e44f 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -176,7 +176,7 @@ static inline void *mmc_priv(struct mmc_host *host)
 
 #define mmc_dev(x)      ((x)->parent)
 #define mmc_classdev(x) (&(x)->class_dev)
-#define mmc_hostname(x) ((x)->class_dev.bus_id)
+#define mmc_hostname(x) (dev_name(&(x)->class_dev))
 
 extern int mmc_suspend_host(struct mmc_host *, pm_message_t);
 extern int mmc_resume_host(struct mmc_host *);
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index 07bee4a0d457..451bdfc85830 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -63,7 +63,7 @@ struct sdio_func {
 
 #define sdio_func_set_present(f) ((f)->state |= SDIO_STATE_PRESENT)
 
-#define sdio_func_id(f)         ((f)->dev.bus_id)
+#define sdio_func_id(f)         (dev_name(&(f)->dev))
 
 #define sdio_get_drvdata(f)     dev_get_drvdata(&(f)->dev)
 #define sdio_set_drvdata(f,d)   dev_set_drvdata(&(f)->dev, d)
diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h
index ba63858056c7..e0a9b207920d 100644
--- a/include/linux/msdos_fs.h
+++ b/include/linux/msdos_fs.h
@@ -46,11 +46,6 @@
 #define DELETED_FLAG    0xe5    /* marks file as deleted when in name[0] */
 #define IS_FREE(n)      (!*(n) || *(n) == DELETED_FLAG)
 
-/* valid file mode bits */
-#define MSDOS_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXU | S_IRWXG | S_IRWXO)
-/* Convert attribute bits and a mask to the UNIX mode. */
-#define MSDOS_MKMODE(a, m) (m & (a & ATTR_RO ? S_IRUGO|S_IXUGO : S_IRWXUGO))
-
 #define MSDOS_NAME      11      /* maximum name length */
 #define MSDOS_LONGNAME  256     /* maximum name length */
 #define MSDOS_SLOTS     21      /* max # of slots for short and long names */
@@ -167,282 +162,10 @@ struct msdos_dir_slot {
 };
 
 #ifdef __KERNEL__
-
-#include <linux/buffer_head.h>
-#include <linux/string.h>
-#include <linux/nls.h>
-#include <linux/fs.h>
-#include <linux/mutex.h>
-
-/*
- * vfat shortname flags
- */
-#define VFAT_SFN_DISPLAY_LOWER  0x0001 /* convert to lowercase for display */
-#define VFAT_SFN_DISPLAY_WIN95  0x0002 /* emulate win95 rule for display */
-#define VFAT_SFN_DISPLAY_WINNT  0x0004 /* emulate winnt rule for display */
-#define VFAT_SFN_CREATE_WIN95   0x0100 /* emulate win95 rule for create */
-#define VFAT_SFN_CREATE_WINNT   0x0200 /* emulate winnt rule for create */
-
-struct fat_mount_options {
-        uid_t fs_uid;
-        gid_t fs_gid;
-        unsigned short fs_fmask;
-        unsigned short fs_dmask;
-        unsigned short codepage;  /* Codepage for shortname conversions */
-        char *iocharset;          /* Charset used for filename input/display */
-        unsigned short shortname; /* flags for shortname display/create rule */
-        unsigned char name_check; /* r = relaxed, n = normal, s = strict */
-        unsigned short allow_utime;/* permission for setting the [am]time */
-        unsigned quiet:1,         /* set = fake successful chmods and chowns */
-                 showexec:1,      /* set = only set x bit for com/exe/bat */
-                 sys_immutable:1, /* set = system files are immutable */
-                 dotsOK:1,        /* set = hidden and system files are named '.filename' */
-                 isvfat:1,        /* 0=no vfat long filename support, 1=vfat support */
-                 utf8:1,          /* Use of UTF-8 character set (Default) */
-                 unicode_xlate:1, /* create escape sequences for unhandled Unicode */
-                 numtail:1,       /* Does first alias have a numeric '~1' type tail? */
-                 flush:1,         /* write things quickly */
-                 nocase:1,        /* Does this need case conversion? 0=need case conversion*/
-                 usefree:1,       /* Use free_clusters for FAT32 */
-                 tz_utc:1;        /* Filesystem timestamps are in UTC */
-};
-
-#define FAT_HASH_BITS   8
-#define FAT_HASH_SIZE   (1UL << FAT_HASH_BITS)
-#define FAT_HASH_MASK   (FAT_HASH_SIZE-1)
-
-/*
- * MS-DOS file system in-core superblock data
- */
-struct msdos_sb_info {
-        unsigned short sec_per_clus; /* sectors/cluster */
-        unsigned short cluster_bits; /* log2(cluster_size) */
-        unsigned int cluster_size;   /* cluster size */
-        unsigned char fats,fat_bits; /* number of FATs, FAT bits (12 or 16) */
-        unsigned short fat_start;
-        unsigned long fat_length;    /* FAT start & length (sec.) */
-        unsigned long dir_start;
-        unsigned short dir_entries;  /* root dir start & entries */
-        unsigned long data_start;    /* first data sector */
-        unsigned long max_cluster;   /* maximum cluster number */
-        unsigned long root_cluster;  /* first cluster of the root directory */
-        unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */
-        struct mutex fat_lock;
-        unsigned int prev_free;      /* previously allocated cluster number */
-        unsigned int free_clusters;  /* -1 if undefined */
-        unsigned int free_clus_valid; /* is free_clusters valid? */
-        struct fat_mount_options options;
-        struct nls_table *nls_disk;  /* Codepage used on disk */
-        struct nls_table *nls_io;    /* Charset used for input and display */
-        const void *dir_ops;                 /* Opaque; default directory operations */
-        int dir_per_block;           /* dir entries per block */
-        int dir_per_block_bits;      /* log2(dir_per_block) */
-
-        int fatent_shift;
-        struct fatent_operations *fatent_ops;
-
-        spinlock_t inode_hash_lock;
-        struct hlist_head inode_hashtable[FAT_HASH_SIZE];
-};
-
-#define FAT_CACHE_VALID 0       /* special case for valid cache */
-
-/*
- * MS-DOS file system inode data in memory
- */
-struct msdos_inode_info {
-        spinlock_t cache_lru_lock;
-        struct list_head cache_lru;
-        int nr_caches;
-        /* for avoiding the race between fat_free() and fat_get_cluster() */
-        unsigned int cache_valid_id;
-
-        loff_t mmu_private;
-        int i_start;            /* first cluster or 0 */
-        int i_logstart;         /* logical first cluster */
-        int i_attrs;            /* unused attribute bits */
-        loff_t i_pos;           /* on-disk position of directory entry or 0 */
-        struct hlist_node i_fat_hash;   /* hash by i_location */
-        struct inode vfs_inode;
-};
-
-struct fat_slot_info {
-        loff_t i_pos;           /* on-disk position of directory entry */
-        loff_t slot_off;        /* offset for slot or de start */
-        int nr_slots;           /* number of slots + 1(de) in filename */
-        struct msdos_dir_entry *de;
-        struct buffer_head *bh;
-};
-
-static inline struct msdos_sb_info *MSDOS_SB(struct super_block *sb)
-{
-        return sb->s_fs_info;
-}
-
-static inline struct msdos_inode_info *MSDOS_I(struct inode *inode)
-{
-        return container_of(inode, struct msdos_inode_info, vfs_inode);
-}
-
-/* Return the FAT attribute byte for this inode */
-static inline u8 fat_attr(struct inode *inode)
-{
-        return ((inode->i_mode & S_IWUGO) ? ATTR_NONE : ATTR_RO) |
-                (S_ISDIR(inode->i_mode) ? ATTR_DIR : ATTR_NONE) |
-                MSDOS_I(inode)->i_attrs;
-}
-
-static inline unsigned char fat_checksum(const __u8 *name)
-{
-        unsigned char s = name[0];
-        s = (s<<7) + (s>>1) + name[1];  s = (s<<7) + (s>>1) + name[2];
-        s = (s<<7) + (s>>1) + name[3];  s = (s<<7) + (s>>1) + name[4];
-        s = (s<<7) + (s>>1) + name[5];  s = (s<<7) + (s>>1) + name[6];
-        s = (s<<7) + (s>>1) + name[7];  s = (s<<7) + (s>>1) + name[8];
-        s = (s<<7) + (s>>1) + name[9];  s = (s<<7) + (s>>1) + name[10];
-        return s;
-}
-
-static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus)
-{
-        return ((sector_t)clus - FAT_START_ENT) * sbi->sec_per_clus
-                + sbi->data_start;
-}
-
-static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len)
-{
-#ifdef __BIG_ENDIAN
-        while (len--) {
-                *dst++ = src[0] | (src[1] << 8);
-                src += 2;
-        }
-#else
-        memcpy(dst, src, len * 2);
-#endif
-}
-
-static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
-{
-#ifdef __BIG_ENDIAN
-        while (len--) {
-                dst[0] = *src & 0x00FF;
-                dst[1] = (*src & 0xFF00) >> 8;
-                dst += 2;
-                src++;
-        }
-#else
-        memcpy(dst, src, len * 2);
-#endif
-}
-
 /* media of boot sector */
 static inline int fat_valid_media(u8 media)
 {
         return 0xf8 <= media || media == 0xf0;
 }
-
-/* fat/cache.c */
-extern void fat_cache_inval_inode(struct inode *inode);
-extern int fat_get_cluster(struct inode *inode, int cluster,
-                           int *fclus, int *dclus);
-extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
-                    unsigned long *mapped_blocks);
-
-/* fat/dir.c */
-extern const struct file_operations fat_dir_operations;
-extern int fat_search_long(struct inode *inode, const unsigned char *name,
-                           int name_len, struct fat_slot_info *sinfo);
-extern int fat_dir_empty(struct inode *dir);
-extern int fat_subdirs(struct inode *dir);
-extern int fat_scan(struct inode *dir, const unsigned char *name,
-                    struct fat_slot_info *sinfo);
-extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh,
-                                struct msdos_dir_entry **de, loff_t *i_pos);
-extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts);
-extern int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
-                           struct fat_slot_info *sinfo);
-extern int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo);
-
-/* fat/fatent.c */
-struct fat_entry {
-        int entry;
-        union {
-                u8 *ent12_p[2];
-                __le16 *ent16_p;
-                __le32 *ent32_p;
-        } u;
-        int nr_bhs;
-        struct buffer_head *bhs[2];
-};
-
-static inline void fatent_init(struct fat_entry *fatent)
-{
-        fatent->nr_bhs = 0;
-        fatent->entry = 0;
-        fatent->u.ent32_p = NULL;
-        fatent->bhs[0] = fatent->bhs[1] = NULL;
-}
-
-static inline void fatent_set_entry(struct fat_entry *fatent, int entry)
-{
-        fatent->entry = entry;
-        fatent->u.ent32_p = NULL;
-}
-
-static inline void fatent_brelse(struct fat_entry *fatent)
-{
-        int i;
-        fatent->u.ent32_p = NULL;
-        for (i = 0; i < fatent->nr_bhs; i++)
-                brelse(fatent->bhs[i]);
-        fatent->nr_bhs = 0;
-        fatent->bhs[0] = fatent->bhs[1] = NULL;
-}
-
-extern void fat_ent_access_init(struct super_block *sb);
-extern int fat_ent_read(struct inode *inode, struct fat_entry *fatent,
-                        int entry);
-extern int fat_ent_write(struct inode *inode, struct fat_entry *fatent,
-                         int new, int wait);
-extern int fat_alloc_clusters(struct inode *inode, int *cluster,
-                              int nr_cluster);
-extern int fat_free_clusters(struct inode *inode, int cluster);
-extern int fat_count_free_clusters(struct super_block *sb);
-
-/* fat/file.c */
-extern int fat_generic_ioctl(struct inode *inode, struct file *filp,
-                             unsigned int cmd, unsigned long arg);
-extern const struct file_operations fat_file_operations;
-extern const struct inode_operations fat_file_inode_operations;
-extern int fat_setattr(struct dentry * dentry, struct iattr * attr);
-extern void fat_truncate(struct inode *inode);
-extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry,
-                       struct kstat *stat);
-
-/* fat/inode.c */
-extern void fat_attach(struct inode *inode, loff_t i_pos);
-extern void fat_detach(struct inode *inode);
-extern struct inode *fat_iget(struct super_block *sb, loff_t i_pos);
-extern struct inode *fat_build_inode(struct super_block *sb,
-                        struct msdos_dir_entry *de, loff_t i_pos);
-extern int fat_sync_inode(struct inode *inode);
-extern int fat_fill_super(struct super_block *sb, void *data, int silent,
-                        const struct inode_operations *fs_dir_inode_ops, int isvfat);
-
-extern int fat_flush_inodes(struct super_block *sb, struct inode *i1,
-                            struct inode *i2);
-/* fat/misc.c */
-extern void fat_fs_panic(struct super_block *s, const char *fmt, ...);
-extern void fat_clusters_flush(struct super_block *sb);
-extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster);
-extern int date_dos2unix(unsigned short time, unsigned short date, int tz_utc);
-extern void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date,
-                              int tz_utc);
-extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs);
-
-int fat_cache_init(void);
-void fat_cache_destroy(void);
-
-#endif /* __KERNEL__ */
-
-#endif
+#endif /* !__KERNEL__ */
+#endif /* !_LINUX_MSDOS_FS_H */
diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h
index ee5124ec319e..00e2b575021f 100644
--- a/include/linux/mtd/cfi.h
+++ b/include/linux/mtd/cfi.h
@@ -282,9 +282,25 @@ struct cfi_private {
 /*
  * Returns the command address according to the given geometry.
  */
-static inline uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, int interleave, int type)
+static inline uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs,
+                                struct map_info *map, struct cfi_private *cfi)
 {
-        return (cmd_ofs * type) * interleave;
+        unsigned bankwidth = map_bankwidth(map);
+        unsigned interleave = cfi_interleave(cfi);
+        unsigned type = cfi->device_type;
+        uint32_t addr;
+        
+        addr = (cmd_ofs * type) * interleave;
+
+        /* Modify the unlock address if we are in compatiblity mode.
+         * For 16bit devices on 8 bit busses
+         * and 32bit devices on 16 bit busses
+         * set the low bit of the alternating bit sequence of the address.
+         */
+        if (((type * interleave) > bankwidth) && ((uint8_t)cmd_ofs == 0xaa))
+                addr |= (type >> 1)*interleave;
+
+        return  addr;
 }
 
 /*
@@ -430,7 +446,7 @@ static inline uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t
                                 int type, map_word *prev_val)
 {
         map_word val;
-        uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, cfi_interleave(cfi), type);
+        uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, map, cfi);
         val = cfi_build_cmd(cmd, map, cfi);
 
         if (prev_val)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c75b82bda327..feb4657bb043 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1136,7 +1136,7 @@ static inline void pci_mmcfg_late_init(void) { }
 #endif
 
 #ifdef CONFIG_HAS_IOMEM
-static inline void * pci_ioremap_bar(struct pci_dev *pdev, int bar)
+static inline void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
 {
         /*
          * Make sure the BAR is actually a memory resource, not an IO resource
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b483f39a7112..295b7c756ca6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1349,6 +1349,8 @@ struct task_struct {
          */
         unsigned long timer_slack_ns;
         unsigned long default_timer_slack_ns;
+
+        struct list_head        *scm_work_list;
 };
 
 /*
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 2e4d58b26c06..3f9a60043a97 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -64,8 +64,17 @@ 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);
+
+static inline void smp_call_function_many(const struct cpumask *mask,
+                                          void (*func)(void *info), void *info,
+                                          int wait)
+{
+        smp_call_function_mask(*mask, func, info, wait);
+}
+
 int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
                                 int wait);
 void __smp_call_function_single(int cpuid, struct call_single_data *data);
diff --git a/include/linux/timer.h b/include/linux/timer.h
index d4ba79248a27..daf9685b861c 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -186,4 +186,9 @@ unsigned long __round_jiffies_relative(unsigned long j, int cpu);
 unsigned long round_jiffies(unsigned long j);
 unsigned long round_jiffies_relative(unsigned long j);
 
+unsigned long __round_jiffies_up(unsigned long j, int cpu);
+unsigned long __round_jiffies_up_relative(unsigned long j, int cpu);
+unsigned long round_jiffies_up(unsigned long j);
+unsigned long round_jiffies_up_relative(unsigned long j);
+
 #endif
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 2158fc0d5a56..117f1b7405cf 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -99,7 +99,7 @@ void arch_update_cpu_topology(void);
                                 | SD_BALANCE_FORK       \
                                 | SD_BALANCE_EXEC       \
                                 | SD_WAKE_AFFINE        \
-                                | SD_WAKE_IDLE          \
+                                | SD_WAKE_BALANCE       \
                                 | SD_SHARE_CPUPOWER,    \
         .last_balance           = jiffies,              \
         .balance_interval       = 1,                    \
@@ -120,10 +120,10 @@ void arch_update_cpu_topology(void);
         .wake_idx               = 1,                    \
         .forkexec_idx           = 1,                    \
         .flags                  = SD_LOAD_BALANCE       \
-                                | SD_BALANCE_NEWIDLE    \
                                 | SD_BALANCE_FORK       \
                                 | SD_BALANCE_EXEC       \
                                 | SD_WAKE_AFFINE        \
+                                | SD_WAKE_BALANCE       \
                                 | SD_SHARE_PKG_RESOURCES\
                                 | BALANCE_FOR_MC_POWER, \
         .last_balance           = jiffies,              \
@@ -146,10 +146,10 @@ void arch_update_cpu_topology(void);
         .wake_idx               = 1,                    \
         .forkexec_idx           = 1,                    \
         .flags                  = SD_LOAD_BALANCE       \
-                                | SD_BALANCE_NEWIDLE    \
-                                | SD_BALANCE_FORK       \
                                 | SD_BALANCE_EXEC       \
+                                | SD_BALANCE_FORK       \
                                 | SD_WAKE_AFFINE        \
+                                | SD_WAKE_BALANCE       \
                                 | BALANCE_FOR_PKG_POWER,\
         .last_balance           = jiffies,              \
         .balance_interval       = 1,                    \
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 89a5a1231ffb..b36291130f22 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -240,4 +240,12 @@ void cancel_rearming_delayed_work(struct delayed_work *work)
         cancel_delayed_work_sync(work);
 }
 
+#ifndef CONFIG_SMP
+static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+{
+        return fn(arg);
+}
+#else
+long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
+#endif /* CONFIG_SMP */
 #endif