Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
  percpu: update comments to reflect that percpu allocations are always zero-filled
  percpu: Optimize __get_cpu_var()
  x86, percpu: Optimize this_cpu_ptr
  percpu: clear memory allocated with the km allocator
  percpu: fix build breakage on s390 and cleanup build configuration tests
  percpu: use percpu allocator on UP too
  percpu: reduce PCPU_MIN_UNIT_SIZE to 32k
  vmalloc: pcpu_get/free_vm_areas() aren't needed on UP

Fixed up trivial conflicts in include/linux/percpu.h

10 files changed, 281 insertions, 236 deletions

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index cd28f9a..f899e01 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -47,6 +47,20 @@
 #ifdef CONFIG_SMP
 #define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
 #define __my_cpu_offset		percpu_read(this_cpu_off)
+
+/*
+ * Compared to the generic __my_cpu_offset version, the following
+ * saves one instruction and avoids clobbering a temp register.
+ */
+#define __this_cpu_ptr(ptr)				\
+({							\
+	unsigned long tcp_ptr__;			\
+	__verify_pcpu_ptr(ptr);				\
+	asm volatile("add " __percpu_arg(1) ", %0"	\
+		     : "=r" (tcp_ptr__)			\
+		     : "m" (this_cpu_off), "0" (ptr));	\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
+})
 #else
 #define __percpu_arg(x)		"%P" #x
 #endif
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 08923b6..d17784e 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -55,14 +55,18 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
  */
 #define per_cpu(var, cpu) \
 	(*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
-#define __get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(&(var), my_cpu_offset))
-#define __raw_get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(&(var), __my_cpu_offset))
 
-#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#ifndef __this_cpu_ptr
 #define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+#endif
+#ifdef CONFIG_DEBUG_PREEMPT
+#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#else
+#define this_cpu_ptr(ptr) __this_cpu_ptr(ptr)
+#endif
 
+#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
+#define __raw_get_cpu_var(var) (*__this_cpu_ptr(&(var)))
 
 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void setup_per_cpu_areas(void);
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 0eb5083..5095b83 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -48,10 +48,8 @@
 	preempt_enable();				\
 } while (0)
 
-#ifdef CONFIG_SMP
-
 /* minimum unit size, also is the maximum supported allocation size */
-#define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
+#define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
 /*
  * Percpu allocator can serve percpu allocations before slab is
@@ -146,37 +144,20 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
  * dynamically allocated. Non-atomic access to the current CPU's
  * version should probably be combined with get_cpu()/put_cpu().
  */
+#ifdef CONFIG_SMP
 #define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
+#else
+#define per_cpu_ptr(ptr, cpu)	({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
+#endif
 
 extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+#if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
 extern void __init setup_per_cpu_areas(void);
 #endif
 extern void __init percpu_init_late(void);
 
-#else /* CONFIG_SMP */
-
-#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
-
-/* can't distinguish from other static vars, always false */
-static inline bool is_kernel_percpu_address(unsigned long addr)
-{
-	return false;
-}
-
-static inline void __init setup_per_cpu_areas(void) { }
-
-static inline void __init percpu_init_late(void) { }
-
-static inline void *pcpu_lpage_remapped(void *kaddr)
-{
-	return NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 extern void __percpu *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void __percpu *__pdata);
 extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 01c2145..63a4fe6 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -117,10 +117,12 @@ extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
 extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 
+#ifdef CONFIG_SMP
 struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 				     const size_t *sizes, int nr_vms,
 				     size_t align, gfp_t gfp_mask);
 
 void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
+#endif
 
 #endif /* _LINUX_VMALLOC_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index f0fb912..c2c8a4a 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -301,3 +301,11 @@ config NOMMU_INITIAL_TRIM_EXCESS
 	  of 1 says that all excess pages should be trimmed.
 
 	  See Documentation/nommu-mmap.txt for more information.
+
+#
+# UP and nommu archs use km based percpu allocator
+#
+config NEED_PER_CPU_KM
+	depends on !SMP
+	bool
+	default y
diff --git a/mm/Makefile b/mm/Makefile
index 34b2546..f73f75a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -11,7 +11,7 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
-			   page_isolation.o mm_init.o mmu_context.o \
+			   page_isolation.o mm_init.o mmu_context.o percpu.o \
 			   $(mmu-y)
 obj-y += init-mm.o
 
@@ -36,11 +36,6 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifdef CONFIG_SMP
-obj-y += percpu.o
-else
-obj-y += percpu_up.o
-endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index df68085..89633fe 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -27,7 +27,7 @@
  *   chunk size is not aligned.  percpu-km code will whine about it.
  */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#if defined(CONFIG_SMP) && defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
 #error "contiguous percpu allocation is incompatible with paged first chunk"
 #endif
 
@@ -35,7 +35,11 @@
 
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 {
-	/* noop */
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
+
 	return 0;
 }
 
diff --git a/mm/percpu.c b/mm/percpu.c
index c76ef38..6fc9015 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -76,6 +76,7 @@
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
 
+#ifdef CONFIG_SMP
 /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
 #ifndef __addr_to_pcpu_ptr
 #define __addr_to_pcpu_ptr(addr)					\
@@ -89,6 +90,11 @@
 			 (unsigned long)pcpu_base_addr -		\
 			 (unsigned long)__per_cpu_start)
 #endif
+#else	/* CONFIG_SMP */
+/* on UP, it's always identity mapped */
+#define __addr_to_pcpu_ptr(addr)	(void __percpu *)(addr)
+#define __pcpu_ptr_to_addr(ptr)		(void __force *)(ptr)
+#endif	/* CONFIG_SMP */
 
 struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
@@ -820,8 +826,8 @@ fail_unlock_mutex:
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align.  Might
- * sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align.
+ * Might sleep.  Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -840,9 +846,10 @@ EXPORT_SYMBOL_GPL(__alloc_percpu);
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align from reserved
- * percpu area if arch has set it up; otherwise, allocation is served
- * from the same dynamic area.  Might sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align
+ * from reserved percpu area if arch has set it up; otherwise,
+ * allocation is served from the same dynamic area.  Might sleep.
+ * Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -949,6 +956,7 @@ EXPORT_SYMBOL_GPL(free_percpu);
  */
 bool is_kernel_percpu_address(unsigned long addr)
 {
+#ifdef CONFIG_SMP
 	const size_t static_size = __per_cpu_end - __per_cpu_start;
 	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
 	unsigned int cpu;
@@ -959,6 +967,8 @@ bool is_kernel_percpu_address(unsigned long addr)
 		if ((void *)addr >= start && (void *)addr < start + static_size)
 			return true;
         }
+#endif
+	/* on UP, can't distinguish from other static vars, always false */
 	return false;
 }
 
@@ -1067,161 +1077,6 @@ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
 }
 
 /**
- * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
- * @reserved_size: the size of reserved percpu area in bytes
- * @dyn_size: minimum free size for dynamic allocation in bytes
- * @atom_size: allocation atom size
- * @cpu_distance_fn: callback to determine distance between cpus, optional
- *
- * This function determines grouping of units, their mappings to cpus
- * and other parameters considering needed percpu size, allocation
- * atom size and distances between CPUs.
- *
- * Groups are always mutliples of atom size and CPUs which are of
- * LOCAL_DISTANCE both ways are grouped together and share space for
- * units in the same group.  The returned configuration is guaranteed
- * to have CPUs on different nodes on different groups and >=75% usage
- * of allocated virtual address space.
- *
- * RETURNS:
- * On success, pointer to the new allocation_info is returned.  On
- * failure, ERR_PTR value is returned.
- */
-static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
-				size_t reserved_size, size_t dyn_size,
-				size_t atom_size,
-				pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
-{
-	static int group_map[NR_CPUS] __initdata;
-	static int group_cnt[NR_CPUS] __initdata;
-	const size_t static_size = __per_cpu_end - __per_cpu_start;
-	int nr_groups = 1, nr_units = 0;
-	size_t size_sum, min_unit_size, alloc_size;
-	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
-	int last_allocs, group, unit;
-	unsigned int cpu, tcpu;
-	struct pcpu_alloc_info *ai;
-	unsigned int *cpu_map;
-
-	/* this function may be called multiple times */
-	memset(group_map, 0, sizeof(group_map));
-	memset(group_cnt, 0, sizeof(group_cnt));
-
-	/* calculate size_sum and ensure dyn_size is enough for early alloc */
-	size_sum = PFN_ALIGN(static_size + reserved_size +
-			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
-	dyn_size = size_sum - static_size - reserved_size;
-
-	/*
-	 * Determine min_unit_size, alloc_size and max_upa such that
-	 * alloc_size is multiple of atom_size and is the smallest
-	 * which can accomodate 4k aligned segments which are equal to
-	 * or larger than min_unit_size.
-	 */
-	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
-
-	alloc_size = roundup(min_unit_size, atom_size);
-	upa = alloc_size / min_unit_size;
-	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
-		upa--;
-	max_upa = upa;
-
-	/* group cpus according to their proximity */
-	for_each_possible_cpu(cpu) {
-		group = 0;
-	next_group:
-		for_each_possible_cpu(tcpu) {
-			if (cpu == tcpu)
-				break;
-			if (group_map[tcpu] == group && cpu_distance_fn &&
-			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
-			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
-				group++;
-				nr_groups = max(nr_groups, group + 1);
-				goto next_group;
-			}
-		}
-		group_map[cpu] = group;
-		group_cnt[group]++;
-	}
-
-	/*
-	 * Expand unit size until address space usage goes over 75%
-	 * and then as much as possible without using more address
-	 * space.
-	 */
-	last_allocs = INT_MAX;
-	for (upa = max_upa; upa; upa--) {
-		int allocs = 0, wasted = 0;
-
-		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
-			continue;
-
-		for (group = 0; group < nr_groups; group++) {
-			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
-			allocs += this_allocs;
-			wasted += this_allocs * upa - group_cnt[group];
-		}
-
-		/*
-		 * Don't accept if wastage is over 1/3.  The
-		 * greater-than comparison ensures upa==1 always
-		 * passes the following check.
-		 */
-		if (wasted > num_possible_cpus() / 3)
-			continue;
-
-		/* and then don't consume more memory */
-		if (allocs > last_allocs)
-			break;
-		last_allocs = allocs;
-		best_upa = upa;
-	}
-	upa = best_upa;
-
-	/* allocate and fill alloc_info */
-	for (group = 0; group < nr_groups; group++)
-		nr_units += roundup(group_cnt[group], upa);
-
-	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
-	if (!ai)
-		return ERR_PTR(-ENOMEM);
-	cpu_map = ai->groups[0].cpu_map;
-
-	for (group = 0; group < nr_groups; group++) {
-		ai->groups[group].cpu_map = cpu_map;
-		cpu_map += roundup(group_cnt[group], upa);
-	}
-
-	ai->static_size = static_size;
-	ai->reserved_size = reserved_size;
-	ai->dyn_size = dyn_size;
-	ai->unit_size = alloc_size / upa;
-	ai->atom_size = atom_size;
-	ai->alloc_size = alloc_size;
-
-	for (group = 0, unit = 0; group_cnt[group]; group++) {
-		struct pcpu_group_info *gi = &ai->groups[group];
-
-		/*
-		 * Initialize base_offset as if all groups are located
-		 * back-to-back.  The caller should update this to
-		 * reflect actual allocation.
-		 */
-		gi->base_offset = unit * ai->unit_size;
-
-		for_each_possible_cpu(cpu)
-			if (group_map[cpu] == group)
-				gi->cpu_map[gi->nr_units++] = cpu;
-		gi->nr_units = roundup(gi->nr_units, upa);
-		unit += gi->nr_units;
-	}
-	BUG_ON(unit != nr_units);
-
-	return ai;
-}
-
-/**
  * pcpu_dump_alloc_info - print out information about pcpu_alloc_info
  * @lvl: loglevel
  * @ai: allocation info to dump
@@ -1363,7 +1218,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	/* sanity checks */
 	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
+#ifdef CONFIG_SMP
 	PCPU_SETUP_BUG_ON(!ai->static_size);
+#endif
 	PCPU_SETUP_BUG_ON(!base_addr);
 	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
 	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
@@ -1488,6 +1345,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	return 0;
 }
 
+#ifdef CONFIG_SMP
+
 const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
 	[PCPU_FC_AUTO]	= "auto",
 	[PCPU_FC_EMBED]	= "embed",
@@ -1515,8 +1374,180 @@ static int __init percpu_alloc_setup(char *str)
 }
 early_param("percpu_alloc", percpu_alloc_setup);
 
+/*
+ * pcpu_embed_first_chunk() is used by the generic percpu setup.
+ * Build it if needed by the arch config or the generic setup is going
+ * to be used.
+ */
 #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
 	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
+#define BUILD_EMBED_FIRST_CHUNK
+#endif
+
+/* build pcpu_page_first_chunk() iff needed by the arch config */
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
+#define BUILD_PAGE_FIRST_CHUNK
+#endif
+
+/* pcpu_build_alloc_info() is used by both embed and page first chunk */
+#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)
+/**
+ * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
+ * @reserved_size: the size of reserved percpu area in bytes
+ * @dyn_size: minimum free size for dynamic allocation in bytes
+ * @atom_size: allocation atom size
+ * @cpu_distance_fn: callback to determine distance between cpus, optional
+ *
+ * This function determines grouping of units, their mappings to cpus
+ * and other parameters considering needed percpu size, allocation
+ * atom size and distances between CPUs.
+ *
+ * Groups are always mutliples of atom size and CPUs which are of
+ * LOCAL_DISTANCE both ways are grouped together and share space for
+ * units in the same group.  The returned configuration is guaranteed
+ * to have CPUs on different nodes on different groups and >=75% usage
+ * of allocated virtual address space.
+ *
+ * RETURNS:
+ * On success, pointer to the new allocation_info is returned.  On
+ * failure, ERR_PTR value is returned.
+ */
+static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
+				size_t reserved_size, size_t dyn_size,
+				size_t atom_size,
+				pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
+{
+	static int group_map[NR_CPUS] __initdata;
+	static int group_cnt[NR_CPUS] __initdata;
+	const size_t static_size = __per_cpu_end - __per_cpu_start;
+	int nr_groups = 1, nr_units = 0;
+	size_t size_sum, min_unit_size, alloc_size;
+	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
+	int last_allocs, group, unit;
+	unsigned int cpu, tcpu;
+	struct pcpu_alloc_info *ai;
+	unsigned int *cpu_map;
+
+	/* this function may be called multiple times */
+	memset(group_map, 0, sizeof(group_map));
+	memset(group_cnt, 0, sizeof(group_cnt));
+
+	/* calculate size_sum and ensure dyn_size is enough for early alloc */
+	size_sum = PFN_ALIGN(static_size + reserved_size +
+			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
+	dyn_size = size_sum - static_size - reserved_size;
+
+	/*
+	 * Determine min_unit_size, alloc_size and max_upa such that
+	 * alloc_size is multiple of atom_size and is the smallest
+	 * which can accomodate 4k aligned segments which are equal to
+	 * or larger than min_unit_size.
+	 */
+	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
+
+	alloc_size = roundup(min_unit_size, atom_size);
+	upa = alloc_size / min_unit_size;
+	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+		upa--;
+	max_upa = upa;
+
+	/* group cpus according to their proximity */
+	for_each_possible_cpu(cpu) {
+		group = 0;
+	next_group:
+		for_each_possible_cpu(tcpu) {
+			if (cpu == tcpu)
+				break;
+			if (group_map[tcpu] == group && cpu_distance_fn &&
+			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
+			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
+				group++;
+				nr_groups = max(nr_groups, group + 1);
+				goto next_group;
+			}
+		}
+		group_map[cpu] = group;
+		group_cnt[group]++;
+	}
+
+	/*
+	 * Expand unit size until address space usage goes over 75%
+	 * and then as much as possible without using more address
+	 * space.
+	 */
+	last_allocs = INT_MAX;
+	for (upa = max_upa; upa; upa--) {
+		int allocs = 0, wasted = 0;
+
+		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+			continue;
+
+		for (group = 0; group < nr_groups; group++) {
+			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
+			allocs += this_allocs;
+			wasted += this_allocs * upa - group_cnt[group];
+		}
+
+		/*
+		 * Don't accept if wastage is over 1/3.  The
+		 * greater-than comparison ensures upa==1 always
+		 * passes the following check.
+		 */
+		if (wasted > num_possible_cpus() / 3)
+			continue;
+
+		/* and then don't consume more memory */
+		if (allocs > last_allocs)
+			break;
+		last_allocs = allocs;
+		best_upa = upa;
+	}
+	upa = best_upa;
+
+	/* allocate and fill alloc_info */
+	for (group = 0; group < nr_groups; group++)
+		nr_units += roundup(group_cnt[group], upa);
+
+	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
+	if (!ai)
+		return ERR_PTR(-ENOMEM);
+	cpu_map = ai->groups[0].cpu_map;
+
+	for (group = 0; group < nr_groups; group++) {
+		ai->groups[group].cpu_map = cpu_map;
+		cpu_map += roundup(group_cnt[group], upa);
+	}
+
+	ai->static_size = static_size;
+	ai->reserved_size = reserved_size;
+	ai->dyn_size = dyn_size;
+	ai->unit_size = alloc_size / upa;
+	ai->atom_size = atom_size;
+	ai->alloc_size = alloc_size;
+
+	for (group = 0, unit = 0; group_cnt[group]; group++) {
+		struct pcpu_group_info *gi = &ai->groups[group];
+
+		/*
+		 * Initialize base_offset as if all groups are located
+		 * back-to-back.  The caller should update this to
+		 * reflect actual allocation.
+		 */
+		gi->base_offset = unit * ai->unit_size;
+
+		for_each_possible_cpu(cpu)
+			if (group_map[cpu] == group)
+				gi->cpu_map[gi->nr_units++] = cpu;
+		gi->nr_units = roundup(gi->nr_units, upa);
+		unit += gi->nr_units;
+	}
+	BUG_ON(unit != nr_units);
+
+	return ai;
+}
+#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
+
+#if defined(BUILD_EMBED_FIRST_CHUNK)
 /**
  * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1645,10 +1676,9 @@ out_free:
 		free_bootmem(__pa(areas), areas_size);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
-	  !CONFIG_HAVE_SETUP_PER_CPU_AREA */
+#endif /* BUILD_EMBED_FIRST_CHUNK */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#ifdef BUILD_PAGE_FIRST_CHUNK
 /**
  * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1756,10 +1786,11 @@ out_free_ar:
 	pcpu_free_alloc_info(ai);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */
+#endif /* BUILD_PAGE_FIRST_CHUNK */
 
+#ifndef	CONFIG_HAVE_SETUP_PER_CPU_AREA
 /*
- * Generic percpu area setup.
+ * Generic SMP percpu area setup.
  *
  * The embedding helper is used because its behavior closely resembles
  * the original non-dynamic generic percpu area setup.  This is
@@ -1770,7 +1801,6 @@ out_free_ar:
  * on the physical linear memory mapping which uses large page
  * mappings on applicable archs.
  */
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
@@ -1799,13 +1829,48 @@ void __init setup_per_cpu_areas(void)
 				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
 				    pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
 	if (rc < 0)
-		panic("Failed to initialized percpu areas.");
+		panic("Failed to initialize percpu areas.");
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu)
 		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
 }
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+#endif	/* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+
+#else	/* CONFIG_SMP */
+
+/*
+ * UP percpu area setup.
+ *
+ * UP always uses km-based percpu allocator with identity mapping.
+ * Static percpu variables are indistinguishable from the usual static
+ * variables and don't require any special preparation.
+ */
+void __init setup_per_cpu_areas(void)
+{
+	const size_t unit_size =
+		roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE,
+					 PERCPU_DYNAMIC_RESERVE));
+	struct pcpu_alloc_info *ai;
+	void *fc;
+
+	ai = pcpu_alloc_alloc_info(1, 1);
+	fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	if (!ai || !fc)
+		panic("Failed to allocate memory for percpu areas.");
+
+	ai->dyn_size = unit_size;
+	ai->unit_size = unit_size;
+	ai->atom_size = unit_size;
+	ai->alloc_size = unit_size;
+	ai->groups[0].nr_units = 1;
+	ai->groups[0].cpu_map[0] = 0;
+
+	if (pcpu_setup_first_chunk(ai, fc) < 0)
+		panic("Failed to initialize percpu areas.");
+}
+
+#endif	/* CONFIG_SMP */
 
 /*
  * First and reserved chunks are initialized with temporary allocation
diff --git a/mm/percpu_up.c b/mm/percpu_up.c
deleted file mode 100644
index db884fa..0000000
--- a/mm/percpu_up.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * mm/percpu_up.c - dummy percpu memory allocator implementation for UP
- */
-
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/slab.h>
-
-void __percpu *__alloc_percpu(size_t size, size_t align)
-{
-	/*
-	 * Can't easily make larger alignment work with kmalloc.  WARN
-	 * on it.  Larger alignment should only be used for module
-	 * percpu sections on SMP for which this path isn't used.
-	 */
-	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-	return (void __percpu __force *)kzalloc(size, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-void free_percpu(void __percpu *p)
-{
-	kfree(this_cpu_ptr(p));
-}
-EXPORT_SYMBOL_GPL(free_percpu);
-
-phys_addr_t per_cpu_ptr_to_phys(void *addr)
-{
-	return __pa(addr);
-}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d8087f0..9f90962 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2065,6 +2065,7 @@ void free_vm_area(struct vm_struct *area)
 }
 EXPORT_SYMBOL_GPL(free_vm_area);
 
+#ifdef CONFIG_SMP
 static struct vmap_area *node_to_va(struct rb_node *n)
 {
 	return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
@@ -2345,6 +2346,7 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 		free_vm_area(vms[i]);
 	kfree(vms);
 }
+#endif	/* CONFIG_SMP */
 
 #ifdef CONFIG_PROC_FS
 static void *s_start(struct seq_file *m, loff_t *pos)