Merge branch 'quilt/rr'

Conflicts:
	kernel/sched.c

13 files changed, 167 insertions, 169 deletions

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/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..34bce34e8a93 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -268,6 +268,25 @@ static inline void __cpus_shift_left(cpumask_t *dstp,
 	bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
 }
 
+/**
+ * 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.
  *
@@ -278,11 +297,11 @@ 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);
 }
 
 /*
@@ -416,74 +435,63 @@ int __next_cpu_nr(int n, const cpumask_t *srcp);
 
 /*
  * 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.
+ *
+ *     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
  *
- *  #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
+ *  If !CONFIG_HOTPLUG_CPU, present == possible, and active == online.
  *
- *  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.
+ *  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_map is forced to have
+ *  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 +504,6 @@ 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 +691,7 @@ 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 +934,7 @@ 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 +948,7 @@ 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 +963,8 @@ 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 +977,7 @@ 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);
 }
 
 /**
@@ -1051,12 +1037,6 @@ 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 +1045,16 @@ 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);
-}
+#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_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);
-}
+/* 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/lguest_launcher.h b/include/linux/lguest_launcher.h
index e7217dc58f39..a53407a4165c 100644
--- a/include/linux/lguest_launcher.h
+++ b/include/linux/lguest_launcher.h
@@ -54,9 +54,13 @@ struct lguest_vqconfig {
 /* Write command first word is a request. */
 enum lguest_req
 {
-	LHREQ_INITIALIZE, /* + base, pfnlimit, pgdir, start */
+	LHREQ_INITIALIZE, /* + base, pfnlimit, start */
 	LHREQ_GETDMA, /* No longer used */
 	LHREQ_IRQ, /* + irq */
 	LHREQ_BREAK, /* + on/off flag (on blocks until someone does off) */
 };
+
+/* The alignment to use between consumer and producer parts of vring.
+ * x86 pagesize for historical reasons. */
+#define LGUEST_VRING_ALIGN	4096
 #endif /* _LINUX_LGUEST_LAUNCHER */
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index b3dfa72f13b9..389fc4a99419 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -53,7 +53,7 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
 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)
 {
-	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..e467fc940e81 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -64,15 +64,16 @@ 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/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/topology.h b/include/linux/topology.h
index 0c5b5ac36d8e..a73d81864bc5 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -191,5 +191,11 @@ int arch_update_cpu_topology(void);
 #ifndef topology_core_siblings
 #define topology_core_siblings(cpu)		cpumask_of_cpu(cpu)
 #endif
+#ifndef topology_thread_cpumask
+#define topology_thread_cpumask(cpu)		cpumask_of(cpu)
+#endif
+#ifndef topology_core_cpumask
+#define topology_core_cpumask(cpu)		cpumask_of(cpu)
+#endif
 
 #endif /* _LINUX_TOPOLOGY_H */
diff --git a/include/linux/virtio_balloon.h b/include/linux/virtio_balloon.h
index c30c7bfbf39b..8726ff77763e 100644
--- a/include/linux/virtio_balloon.h
+++ b/include/linux/virtio_balloon.h
@@ -10,6 +10,9 @@
 /* The feature bitmap for virtio balloon */
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
 
+/* Size of a PFN in the balloon interface. */
+#define VIRTIO_BALLOON_PFN_SHIFT 12
+
 struct virtio_balloon_config
 {
 	/* Number of pages host wants Guest to give up. */
diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h
index 19a0da0dba41..7615ffcdd555 100644
--- a/include/linux/virtio_console.h
+++ b/include/linux/virtio_console.h
@@ -7,6 +7,17 @@
 /* The ID for virtio console */
 #define VIRTIO_ID_CONSOLE	3
 
+/* Feature bits */
+#define VIRTIO_CONSOLE_F_SIZE	0	/* Does host provide console size? */
+
+struct virtio_console_config {
+	/* colums of the screens */
+	__u16 cols;
+	/* rows of the screens */
+	__u16 rows;
+} __attribute__((packed));
+
+
 #ifdef __KERNEL__
 int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int));
 #endif /* __KERNEL__ */
diff --git a/include/linux/virtio_pci.h b/include/linux/virtio_pci.h
index cdef35742932..cd0fd5d181a6 100644
--- a/include/linux/virtio_pci.h
+++ b/include/linux/virtio_pci.h
@@ -53,4 +53,12 @@
 
 /* Virtio ABI version, this must match exactly */
 #define VIRTIO_PCI_ABI_VERSION		0
+
+/* How many bits to shift physical queue address written to QUEUE_PFN.
+ * 12 is historical, and due to x86 page size. */
+#define VIRTIO_PCI_QUEUE_ADDR_SHIFT	12
+
+/* The alignment to use between consumer and producer parts of vring.
+ * x86 pagesize again. */
+#define VIRTIO_PCI_VRING_ALIGN		4096
 #endif
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index c4a598fb3826..71e03722fb59 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -83,7 +83,7 @@ struct vring {
  *	__u16 avail_idx;
  *	__u16 available[num];
  *
- *	// Padding to the next page boundary.
+ *	// Padding to the next align boundary.
  *	char pad[];
  *
  *	// A ring of used descriptor heads with free-running index.
@@ -93,19 +93,19 @@ struct vring {
  * };
  */
 static inline void vring_init(struct vring *vr, unsigned int num, void *p,
-			      unsigned long pagesize)
+			      unsigned long align)
 {
 	vr->num = num;
 	vr->desc = p;
 	vr->avail = p + num*sizeof(struct vring_desc);
-	vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + pagesize-1)
-			    & ~(pagesize - 1));
+	vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + align-1)
+			    & ~(align - 1));
 }
 
-static inline unsigned vring_size(unsigned int num, unsigned long pagesize)
+static inline unsigned vring_size(unsigned int num, unsigned long align)
 {
 	return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num)
-		 + pagesize - 1) & ~(pagesize - 1))
+		 + align - 1) & ~(align - 1))
 		+ sizeof(__u16) * 2 + sizeof(struct vring_used_elem) * num;
 }
 
@@ -115,6 +115,7 @@ struct virtio_device;
 struct virtqueue;
 
 struct virtqueue *vring_new_virtqueue(unsigned int num,
+				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      void *pages,
 				      void (*notify)(struct virtqueue *vq),