X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fpercpu.c;h=442010cc91c6c82eb8489e64d21500baa52b5911;hb=3b4798cbc13dd8d1150aa6377f97f0e11450a67d;hp=b3d0bcff8c7cddb6506f66f81335e24c4952187b;hpb=a530b7958612bafe2027e21359083dba84f0b3b4;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/percpu.c b/mm/percpu.c
index b3d0bcf..442010c 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -46,8 +46,6 @@
  *
  * To use this allocator, arch code should do the followings.
  *
- * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA
- *
  * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
  *   regular address to percpu pointer and back if they need to be
  *   different from the default
@@ -58,6 +56,7 @@
 
 #include <linux/bitmap.h>
 #include <linux/bootmem.h>
+#include <linux/err.h>
 #include <linux/list.h>
 #include <linux/log2.h>
 #include <linux/mm.h>
@@ -73,6 +72,7 @@
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
@@ -93,10 +93,11 @@ struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
-	struct vm_struct	*vm;		/* mapped vmalloc region */
+	void			*base_addr;	/* base address of this chunk */
 	int			map_used;	/* # of map entries used */
 	int			map_alloc;	/* # of map entries allocated */
 	int			*map;		/* allocation map */
+	struct vm_struct	**vms;		/* mapped vmalloc regions */
 	bool			immutable;	/* no [de]population allowed */
 	unsigned long		populated[];	/* populated bitmap */
 };
@@ -104,7 +105,7 @@ struct pcpu_chunk {
 static int pcpu_unit_pages __read_mostly;
 static int pcpu_unit_size __read_mostly;
 static int pcpu_nr_units __read_mostly;
-static int pcpu_chunk_size __read_mostly;
+static int pcpu_atom_size __read_mostly;
 static int pcpu_nr_slots __read_mostly;
 static size_t pcpu_chunk_struct_size __read_mostly;
 
@@ -116,8 +117,13 @@ static unsigned int pcpu_last_unit_cpu __read_mostly;
 void *pcpu_base_addr __read_mostly;
 EXPORT_SYMBOL_GPL(pcpu_base_addr);
 
-/* cpu -> unit map */
-const int *pcpu_unit_map __read_mostly;
+static const int *pcpu_unit_map __read_mostly;		/* cpu -> unit */
+const unsigned long *pcpu_unit_offsets __read_mostly;	/* cpu -> unit offset */
+
+/* group information, used for vm allocation */
+static int pcpu_nr_groups __read_mostly;
+static const unsigned long *pcpu_group_offsets __read_mostly;
+static const size_t *pcpu_group_sizes __read_mostly;
 
 /*
  * The first chunk which always exists.  Note that unlike other
@@ -146,7 +152,10 @@ static int pcpu_reserved_chunk_limit;
  *
  * During allocation, pcpu_alloc_mutex is kept locked all the time and
  * pcpu_lock is grabbed and released as necessary.  All actual memory
- * allocations are done using GFP_KERNEL with pcpu_lock released.
+ * allocations are done using GFP_KERNEL with pcpu_lock released.  In
+ * general, percpu memory can't be allocated with irq off but
+ * irqsave/restore are still used in alloc path so that it can be used
+ * from early init path - sched_init() specifically.
  *
  * Free path accesses and alters only the index data structures, so it
  * can be safely called from atomic context.  When memory needs to be
@@ -195,8 +204,8 @@ static int pcpu_page_idx(unsigned int cpu, int page_idx)
 static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
 				     unsigned int cpu, int page_idx)
 {
-	return (unsigned long)chunk->vm->addr +
-		(pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT);
+	return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] +
+		(page_idx << PAGE_SHIFT);
 }
 
 static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
@@ -323,7 +332,7 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
  */
 static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 {
-	void *first_start = pcpu_first_chunk->vm->addr;
+	void *first_start = pcpu_first_chunk->base_addr;
 
 	/* is it in the first chunk? */
 	if (addr >= first_start && addr < first_start + pcpu_unit_size) {
@@ -340,67 +349,91 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 	 * space.  Note that any possible cpu id can be used here, so
 	 * there's no need to worry about preemption or cpu hotplug.
 	 */
-	addr += pcpu_unit_map[smp_processor_id()] * pcpu_unit_size;
+	addr += pcpu_unit_offsets[raw_smp_processor_id()];
 	return pcpu_get_page_chunk(vmalloc_to_page(addr));
 }
 
 /**
- * pcpu_extend_area_map - extend area map for allocation
- * @chunk: target chunk
+ * pcpu_need_to_extend - determine whether chunk area map needs to be extended
+ * @chunk: chunk of interest
  *
- * Extend area map of @chunk so that it can accomodate an allocation.
- * A single allocation can split an area into three areas, so this
- * function makes sure that @chunk->map has at least two extra slots.
+ * Determine whether area map of @chunk needs to be extended to
+ * accomodate a new allocation.
  *
  * CONTEXT:
- * pcpu_alloc_mutex, pcpu_lock.  pcpu_lock is released and reacquired
- * if area map is extended.
+ * pcpu_lock.
  *
  * RETURNS:
- * 0 if noop, 1 if successfully extended, -errno on failure.
+ * New target map allocation length if extension is necessary, 0
+ * otherwise.
  */
-static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
+static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
 {
 	int new_alloc;
-	int *new;
-	size_t size;
 
-	/* has enough? */
 	if (chunk->map_alloc >= chunk->map_used + 2)
 		return 0;
 
-	spin_unlock_irq(&pcpu_lock);
-
 	new_alloc = PCPU_DFL_MAP_ALLOC;
 	while (new_alloc < chunk->map_used + 2)
 		new_alloc *= 2;
 
-	new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
-	if (!new) {
-		spin_lock_irq(&pcpu_lock);
+	return new_alloc;
+}
+
+/**
+ * pcpu_extend_area_map - extend area map of a chunk
+ * @chunk: chunk of interest
+ * @new_alloc: new target allocation length of the area map
+ *
+ * Extend area map of @chunk to have @new_alloc entries.
+ *
+ * CONTEXT:
+ * Does GFP_KERNEL allocation.  Grabs and releases pcpu_lock.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
+{
+	int *old = NULL, *new = NULL;
+	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
+	unsigned long flags;
+
+	new = pcpu_mem_alloc(new_size);
+	if (!new)
 		return -ENOMEM;
-	}
 
-	/*
-	 * Acquire pcpu_lock and switch to new area map.  Only free
-	 * could have happened inbetween, so map_used couldn't have
-	 * grown.
-	 */
-	spin_lock_irq(&pcpu_lock);
-	BUG_ON(new_alloc < chunk->map_used + 2);
+	/* acquire pcpu_lock and switch to new area map */
+	spin_lock_irqsave(&pcpu_lock, flags);
+
+	if (new_alloc <= chunk->map_alloc)
+		goto out_unlock;
 
-	size = chunk->map_alloc * sizeof(chunk->map[0]);
-	memcpy(new, chunk->map, size);
+	old_size = chunk->map_alloc * sizeof(chunk->map[0]);
+	memcpy(new, chunk->map, old_size);
 
 	/*
 	 * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is
 	 * one of the first chunks and still using static map.
 	 */
 	if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC)
-		pcpu_mem_free(chunk->map, size);
+		old = chunk->map;
 
 	chunk->map_alloc = new_alloc;
 	chunk->map = new;
+	new = NULL;
+
+out_unlock:
+	spin_unlock_irqrestore(&pcpu_lock, flags);
+
+	/*
+	 * pcpu_mem_free() might end up calling vfree() which uses
+	 * IRQ-unsafe lock and thus can't be called under pcpu_lock.
+	 */
+	pcpu_mem_free(old, old_size);
+	pcpu_mem_free(new, new_size);
+
 	return 0;
 }
 
@@ -986,8 +1019,8 @@ static void free_pcpu_chunk(struct pcpu_chunk *chunk)
 {
 	if (!chunk)
 		return;
-	if (chunk->vm)
-		free_vm_area(chunk->vm);
+	if (chunk->vms)
+		pcpu_free_vm_areas(chunk->vms, pcpu_nr_groups);
 	pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
 	kfree(chunk);
 }
@@ -1004,8 +1037,10 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
 	chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
 	chunk->map[chunk->map_used++] = pcpu_unit_size;
 
-	chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL);
-	if (!chunk->vm) {
+	chunk->vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
+				       pcpu_nr_groups, pcpu_atom_size,
+				       GFP_KERNEL);
+	if (!chunk->vms) {
 		free_pcpu_chunk(chunk);
 		return NULL;
 	}
@@ -1013,6 +1048,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
 	INIT_LIST_HEAD(&chunk->list);
 	chunk->free_size = pcpu_unit_size;
 	chunk->contig_hint = pcpu_unit_size;
+	chunk->base_addr = chunk->vms[0]->addr - pcpu_group_offsets[0];
 
 	return chunk;
 }
@@ -1033,8 +1069,11 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
  */
 static void *pcpu_alloc(size_t size, size_t align, bool reserved)
 {
+	static int warn_limit = 10;
 	struct pcpu_chunk *chunk;
-	int slot, off;
+	const char *err;
+	int slot, off, new_alloc;
+	unsigned long flags;
 
 	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
 		WARN(true, "illegal size (%zu) or align (%zu) for "
@@ -1043,17 +1082,31 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
 	}
 
 	mutex_lock(&pcpu_alloc_mutex);
-	spin_lock_irq(&pcpu_lock);
+	spin_lock_irqsave(&pcpu_lock, flags);
 
 	/* serve reserved allocations from the reserved chunk if available */
 	if (reserved && pcpu_reserved_chunk) {
 		chunk = pcpu_reserved_chunk;
-		if (size > chunk->contig_hint ||
-		    pcpu_extend_area_map(chunk) < 0)
+
+		if (size > chunk->contig_hint) {
+			err = "alloc from reserved chunk failed";
 			goto fail_unlock;
+		}
+
+		while ((new_alloc = pcpu_need_to_extend(chunk))) {
+			spin_unlock_irqrestore(&pcpu_lock, flags);
+			if (pcpu_extend_area_map(chunk, new_alloc) < 0) {
+				err = "failed to extend area map of reserved chunk";
+				goto fail_unlock_mutex;
+			}
+			spin_lock_irqsave(&pcpu_lock, flags);
+		}
+
 		off = pcpu_alloc_area(chunk, size, align);
 		if (off >= 0)
 			goto area_found;
+
+		err = "alloc from reserved chunk failed";
 		goto fail_unlock;
 	}
 
@@ -1064,13 +1117,20 @@ restart:
 			if (size > chunk->contig_hint)
 				continue;
 
-			switch (pcpu_extend_area_map(chunk)) {
-			case 0:
-				break;
-			case 1:
-				goto restart;	/* pcpu_lock dropped, restart */
-			default:
-				goto fail_unlock;
+			new_alloc = pcpu_need_to_extend(chunk);
+			if (new_alloc) {
+				spin_unlock_irqrestore(&pcpu_lock, flags);
+				if (pcpu_extend_area_map(chunk,
+							 new_alloc) < 0) {
+					err = "failed to extend area map";
+					goto fail_unlock_mutex;
+				}
+				spin_lock_irqsave(&pcpu_lock, flags);
+				/*
+				 * pcpu_lock has been dropped, need to
+				 * restart cpu_slot list walking.
+				 */
+				goto restart;
 			}
 
 			off = pcpu_alloc_area(chunk, size, align);
@@ -1080,35 +1140,45 @@ restart:
 	}
 
 	/* hmmm... no space left, create a new chunk */
-	spin_unlock_irq(&pcpu_lock);
+	spin_unlock_irqrestore(&pcpu_lock, flags);
 
 	chunk = alloc_pcpu_chunk();
-	if (!chunk)
+	if (!chunk) {
+		err = "failed to allocate new chunk";
 		goto fail_unlock_mutex;
+	}
 
-	spin_lock_irq(&pcpu_lock);
+	spin_lock_irqsave(&pcpu_lock, flags);
 	pcpu_chunk_relocate(chunk, -1);
 	goto restart;
 
 area_found:
-	spin_unlock_irq(&pcpu_lock);
+	spin_unlock_irqrestore(&pcpu_lock, flags);
 
 	/* populate, map and clear the area */
 	if (pcpu_populate_chunk(chunk, off, size)) {
-		spin_lock_irq(&pcpu_lock);
+		spin_lock_irqsave(&pcpu_lock, flags);
 		pcpu_free_area(chunk, off);
+		err = "failed to populate";
 		goto fail_unlock;
 	}
 
 	mutex_unlock(&pcpu_alloc_mutex);
 
-	/* return address relative to unit0 */
-	return __addr_to_pcpu_ptr(chunk->vm->addr + off);
+	/* return address relative to base address */
+	return __addr_to_pcpu_ptr(chunk->base_addr + off);
 
 fail_unlock:
-	spin_unlock_irq(&pcpu_lock);
+	spin_unlock_irqrestore(&pcpu_lock, flags);
 fail_unlock_mutex:
 	mutex_unlock(&pcpu_alloc_mutex);
+	if (warn_limit) {
+		pr_warning("PERCPU: allocation failed, size=%zu align=%zu, "
+			   "%s\n", size, align, err);
+		dump_stack();
+		if (!--warn_limit)
+			pr_info("PERCPU: limit reached, disable warning\n");
+	}
 	return NULL;
 }
 
@@ -1181,12 +1251,13 @@ static void pcpu_reclaim(struct work_struct *work)
 	}
 
 	spin_unlock_irq(&pcpu_lock);
-	mutex_unlock(&pcpu_alloc_mutex);
 
 	list_for_each_entry_safe(chunk, next, &todo, list) {
 		pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
 		free_pcpu_chunk(chunk);
 	}
+
+	mutex_unlock(&pcpu_alloc_mutex);
 }
 
 /**
@@ -1211,7 +1282,7 @@ void free_percpu(void *ptr)
 	spin_lock_irqsave(&pcpu_lock, flags);
 
 	chunk = pcpu_chunk_addr_search(addr);
-	off = addr - chunk->vm->addr;
+	off = addr - chunk->base_addr;
 
 	pcpu_free_area(chunk, off);
 
@@ -1231,19 +1302,319 @@ void free_percpu(void *ptr)
 EXPORT_SYMBOL_GPL(free_percpu);
 
 /**
- * pcpu_setup_first_chunk - initialize the first percpu chunk
- * @static_size: the size of static percpu area in bytes
- * @reserved_size: the size of reserved percpu area in bytes, 0 for none
+ * per_cpu_ptr_to_phys - convert translated percpu address to physical address
+ * @addr: the address to be converted to physical address
+ *
+ * Given @addr which is dereferenceable address obtained via one of
+ * percpu access macros, this function translates it into its physical
+ * address.  The caller is responsible for ensuring @addr stays valid
+ * until this function finishes.
+ *
+ * RETURNS:
+ * The physical address for @addr.
+ */
+phys_addr_t per_cpu_ptr_to_phys(void *addr)
+{
+	if ((unsigned long)addr < VMALLOC_START ||
+			(unsigned long)addr >= VMALLOC_END)
+		return __pa(addr);
+	else
+		return page_to_phys(vmalloc_to_page(addr));
+}
+
+static inline size_t pcpu_calc_fc_sizes(size_t static_size,
+					size_t reserved_size,
+					ssize_t *dyn_sizep)
+{
+	size_t size_sum;
+
+	size_sum = PFN_ALIGN(static_size + reserved_size +
+			     (*dyn_sizep >= 0 ? *dyn_sizep : 0));
+	if (*dyn_sizep != 0)
+		*dyn_sizep = size_sum - static_size - reserved_size;
+
+	return size_sum;
+}
+
+/**
+ * pcpu_alloc_alloc_info - allocate percpu allocation info
+ * @nr_groups: the number of groups
+ * @nr_units: the number of units
+ *
+ * Allocate ai which is large enough for @nr_groups groups containing
+ * @nr_units units.  The returned ai's groups[0].cpu_map points to the
+ * cpu_map array which is long enough for @nr_units and filled with
+ * NR_CPUS.  It's the caller's responsibility to initialize cpu_map
+ * pointer of other groups.
+ *
+ * RETURNS:
+ * Pointer to the allocated pcpu_alloc_info on success, NULL on
+ * failure.
+ */
+struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
+						      int nr_units)
+{
+	struct pcpu_alloc_info *ai;
+	size_t base_size, ai_size;
+	void *ptr;
+	int unit;
+
+	base_size = ALIGN(sizeof(*ai) + nr_groups * sizeof(ai->groups[0]),
+			  __alignof__(ai->groups[0].cpu_map[0]));
+	ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]);
+
+	ptr = alloc_bootmem_nopanic(PFN_ALIGN(ai_size));
+	if (!ptr)
+		return NULL;
+	ai = ptr;
+	ptr += base_size;
+
+	ai->groups[0].cpu_map = ptr;
+
+	for (unit = 0; unit < nr_units; unit++)
+		ai->groups[0].cpu_map[unit] = NR_CPUS;
+
+	ai->nr_groups = nr_groups;
+	ai->__ai_size = PFN_ALIGN(ai_size);
+
+	return ai;
+}
+
+/**
+ * pcpu_free_alloc_info - free percpu allocation info
+ * @ai: pcpu_alloc_info to free
+ *
+ * Free @ai which was allocated by pcpu_alloc_alloc_info().
+ */
+void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
+{
+	free_bootmem(__pa(ai), ai->__ai_size);
+}
+
+/**
+ * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
+ * @reserved_size: the size of reserved percpu area in bytes
  * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
- * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE
+ * @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.
+ */
+struct pcpu_alloc_info * __init pcpu_build_alloc_info(
+				size_t reserved_size, ssize_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 group_cnt_max = 0, 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_map));
+
+	/*
+	 * 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.
+	 */
+	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_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]++;
+		group_cnt_max = max(group_cnt_max, 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 25%.  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
+ *
+ * Print out information about @ai using loglevel @lvl.
+ */
+static void pcpu_dump_alloc_info(const char *lvl,
+				 const struct pcpu_alloc_info *ai)
+{
+	int group_width = 1, cpu_width = 1, width;
+	char empty_str[] = "--------";
+	int alloc = 0, alloc_end = 0;
+	int group, v;
+	int upa, apl;	/* units per alloc, allocs per line */
+
+	v = ai->nr_groups;
+	while (v /= 10)
+		group_width++;
+
+	v = num_possible_cpus();
+	while (v /= 10)
+		cpu_width++;
+	empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0';
+
+	upa = ai->alloc_size / ai->unit_size;
+	width = upa * (cpu_width + 1) + group_width + 3;
+	apl = rounddown_pow_of_two(max(60 / width, 1));
+
+	printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu",
+	       lvl, ai->static_size, ai->reserved_size, ai->dyn_size,
+	       ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size);
+
+	for (group = 0; group < ai->nr_groups; group++) {
+		const struct pcpu_group_info *gi = &ai->groups[group];
+		int unit = 0, unit_end = 0;
+
+		BUG_ON(gi->nr_units % upa);
+		for (alloc_end += gi->nr_units / upa;
+		     alloc < alloc_end; alloc++) {
+			if (!(alloc % apl)) {
+				printk("\n");
+				printk("%spcpu-alloc: ", lvl);
+			}
+			printk("[%0*d] ", group_width, group);
+
+			for (unit_end += upa; unit < unit_end; unit++)
+				if (gi->cpu_map[unit] != NR_CPUS)
+					printk("%0*d ", cpu_width,
+					       gi->cpu_map[unit]);
+				else
+					printk("%s ", empty_str);
+		}
+	}
+	printk("\n");
+}
+
+/**
+ * pcpu_setup_first_chunk - initialize the first percpu chunk
+ * @ai: pcpu_alloc_info describing how to percpu area is shaped
  * @base_addr: mapped address
- * @unit_map: cpu -> unit map, NULL for sequential mapping
  *
  * Initialize the first percpu chunk which contains the kernel static
  * perpcu area.  This function is to be called from arch percpu area
  * setup path.
  *
- * @reserved_size, if non-zero, specifies the amount of bytes to
+ * @ai contains all information necessary to initialize the first
+ * chunk and prime the dynamic percpu allocator.
+ *
+ * @ai->static_size is the size of static percpu area.
+ *
+ * @ai->reserved_size, if non-zero, specifies the amount of bytes to
  * reserve after the static area in the first chunk.  This reserves
  * the first chunk such that it's available only through reserved
  * percpu allocation.  This is primarily used to serve module percpu
@@ -1251,14 +1622,26 @@ EXPORT_SYMBOL_GPL(free_percpu);
  * limited offset range for symbol relocations to guarantee module
  * percpu symbols fall inside the relocatable range.
  *
- * @dyn_size, if non-negative, determines the number of bytes
- * available for dynamic allocation in the first chunk.  Specifying
- * non-negative value makes percpu leave alone the area beyond
- * @static_size + @reserved_size + @dyn_size.
+ * @ai->dyn_size determines the number of bytes available for dynamic
+ * allocation in the first chunk.  The area between @ai->static_size +
+ * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused.
+ *
+ * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE
+ * and equal to or larger than @ai->static_size + @ai->reserved_size +
+ * @ai->dyn_size.
+ *
+ * @ai->atom_size is the allocation atom size and used as alignment
+ * for vm areas.
+ *
+ * @ai->alloc_size is the allocation size and always multiple of
+ * @ai->atom_size.  This is larger than @ai->atom_size if
+ * @ai->unit_size is larger than @ai->atom_size.
  *
- * @unit_size specifies unit size and must be aligned to PAGE_SIZE and
- * equal to or larger than @static_size + @reserved_size + if
- * non-negative, @dyn_size.
+ * @ai->nr_groups and @ai->groups describe virtual memory layout of
+ * percpu areas.  Units which should be colocated are put into the
+ * same group.  Dynamic VM areas will be allocated according to these
+ * groupings.  If @ai->nr_groups is zero, a single group containing
+ * all units is assumed.
  *
  * The caller should have mapped the first chunk at @base_addr and
  * copied static data to each unit.
@@ -1271,86 +1654,99 @@ EXPORT_SYMBOL_GPL(free_percpu);
  * and available for dynamic allocation like any other chunks.
  *
  * RETURNS:
- * The determined pcpu_unit_size which can be used to initialize
- * percpu access.
+ * 0 on success, -errno on failure.
  */
-size_t __init pcpu_setup_first_chunk(size_t static_size, size_t reserved_size,
-				     ssize_t dyn_size, size_t unit_size,
-				     void *base_addr, const int *unit_map)
+int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
+				  void *base_addr)
 {
-	static struct vm_struct first_vm;
+	static char cpus_buf[4096] __initdata;
 	static int smap[2], dmap[2];
-	size_t size_sum = static_size + reserved_size +
-			  (dyn_size >= 0 ? dyn_size : 0);
+	size_t dyn_size = ai->dyn_size;
+	size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
 	struct pcpu_chunk *schunk, *dchunk = NULL;
-	unsigned int cpu, tcpu;
-	int i;
+	unsigned long *group_offsets;
+	size_t *group_sizes;
+	unsigned long *unit_off;
+	unsigned int cpu;
+	int *unit_map;
+	int group, unit, i;
+
+	cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask);
+
+#define PCPU_SETUP_BUG_ON(cond)	do {					\
+	if (unlikely(cond)) {						\
+		pr_emerg("PERCPU: failed to initialize, %s", #cond);	\
+		pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf);	\
+		pcpu_dump_alloc_info(KERN_EMERG, ai);			\
+		BUG();							\
+	}								\
+} while (0)
 
 	/* sanity checks */
 	BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
 		     ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
-	BUG_ON(!static_size);
-	BUG_ON(!base_addr);
-	BUG_ON(unit_size < size_sum);
-	BUG_ON(unit_size & ~PAGE_MASK);
-	BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE);
-
-	/* determine number of units and verify and initialize pcpu_unit_map */
-	if (unit_map) {
-		int first_unit = INT_MAX, last_unit = INT_MIN;
-
-		for_each_possible_cpu(cpu) {
-			int unit = unit_map[cpu];
-
-			BUG_ON(unit < 0);
-			for_each_possible_cpu(tcpu) {
-				if (tcpu == cpu)
-					break;
-				/* the mapping should be one-to-one */
-				BUG_ON(unit_map[tcpu] == unit);
-			}
+	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
+	PCPU_SETUP_BUG_ON(!ai->static_size);
+	PCPU_SETUP_BUG_ON(!base_addr);
+	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
+	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
+	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
+
+	/* process group information and build config tables accordingly */
+	group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
+	group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0]));
+	unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0]));
+	unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		unit_map[cpu] = UINT_MAX;
+	pcpu_first_unit_cpu = NR_CPUS;
+
+	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
+		const struct pcpu_group_info *gi = &ai->groups[group];
+
+		group_offsets[group] = gi->base_offset;
+		group_sizes[group] = gi->nr_units * ai->unit_size;
+
+		for (i = 0; i < gi->nr_units; i++) {
+			cpu = gi->cpu_map[i];
+			if (cpu == NR_CPUS)
+				continue;
 
-			if (unit < first_unit) {
+			PCPU_SETUP_BUG_ON(cpu > nr_cpu_ids);
+			PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
+			PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX);
+
+			unit_map[cpu] = unit + i;
+			unit_off[cpu] = gi->base_offset + i * ai->unit_size;
+
+			if (pcpu_first_unit_cpu == NR_CPUS)
 				pcpu_first_unit_cpu = cpu;
-				first_unit = unit;
-			}
-			if (unit > last_unit) {
-				pcpu_last_unit_cpu = cpu;
-				last_unit = unit;
-			}
 		}
-		pcpu_nr_units = last_unit + 1;
-		pcpu_unit_map = unit_map;
-	} else {
-		int *identity_map;
+	}
+	pcpu_last_unit_cpu = cpu;
+	pcpu_nr_units = unit;
 
-		/* #units == #cpus, identity mapped */
-		identity_map = alloc_bootmem(num_possible_cpus() *
-					     sizeof(identity_map[0]));
+	for_each_possible_cpu(cpu)
+		PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);
 
-		for_each_possible_cpu(cpu)
-			identity_map[cpu] = cpu;
+	/* we're done parsing the input, undefine BUG macro and dump config */
+#undef PCPU_SETUP_BUG_ON
+	pcpu_dump_alloc_info(KERN_INFO, ai);
 
-		pcpu_first_unit_cpu = 0;
-		pcpu_last_unit_cpu = pcpu_nr_units - 1;
-		pcpu_nr_units = num_possible_cpus();
-		pcpu_unit_map = identity_map;
-	}
+	pcpu_nr_groups = ai->nr_groups;
+	pcpu_group_offsets = group_offsets;
+	pcpu_group_sizes = group_sizes;
+	pcpu_unit_map = unit_map;
+	pcpu_unit_offsets = unit_off;
 
 	/* determine basic parameters */
-	pcpu_unit_pages = unit_size >> PAGE_SHIFT;
+	pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
 	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
-	pcpu_chunk_size = pcpu_nr_units * pcpu_unit_size;
+	pcpu_atom_size = ai->atom_size;
 	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
 		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
 
-	if (dyn_size < 0)
-		dyn_size = pcpu_unit_size - static_size - reserved_size;
-
-	first_vm.flags = VM_ALLOC;
-	first_vm.size = pcpu_chunk_size;
-	first_vm.addr = base_addr;
-
 	/*
 	 * Allocate chunk slots.  The additional last slot is for
 	 * empty chunks.
@@ -1369,23 +1765,23 @@ size_t __init pcpu_setup_first_chunk(size_t static_size, size_t reserved_size,
 	 */
 	schunk = alloc_bootmem(pcpu_chunk_struct_size);
 	INIT_LIST_HEAD(&schunk->list);
-	schunk->vm = &first_vm;
+	schunk->base_addr = base_addr;
 	schunk->map = smap;
 	schunk->map_alloc = ARRAY_SIZE(smap);
 	schunk->immutable = true;
 	bitmap_fill(schunk->populated, pcpu_unit_pages);
 
-	if (reserved_size) {
-		schunk->free_size = reserved_size;
+	if (ai->reserved_size) {
+		schunk->free_size = ai->reserved_size;
 		pcpu_reserved_chunk = schunk;
-		pcpu_reserved_chunk_limit = static_size + reserved_size;
+		pcpu_reserved_chunk_limit = ai->static_size + ai->reserved_size;
 	} else {
 		schunk->free_size = dyn_size;
 		dyn_size = 0;			/* dynamic area covered */
 	}
 	schunk->contig_hint = schunk->free_size;
 
-	schunk->map[schunk->map_used++] = -static_size;
+	schunk->map[schunk->map_used++] = -ai->static_size;
 	if (schunk->free_size)
 		schunk->map[schunk->map_used++] = schunk->free_size;
 
@@ -1393,7 +1789,7 @@ size_t __init pcpu_setup_first_chunk(size_t static_size, size_t reserved_size,
 	if (dyn_size) {
 		dchunk = alloc_bootmem(pcpu_chunk_struct_size);
 		INIT_LIST_HEAD(&dchunk->list);
-		dchunk->vm = &first_vm;
+		dchunk->base_addr = base_addr;
 		dchunk->map = dmap;
 		dchunk->map_alloc = ARRAY_SIZE(dmap);
 		dchunk->immutable = true;
@@ -1409,37 +1805,62 @@ size_t __init pcpu_setup_first_chunk(size_t static_size, size_t reserved_size,
 	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	/* we're done */
-	pcpu_base_addr = schunk->vm->addr;
-	return pcpu_unit_size;
+	pcpu_base_addr = base_addr;
+	return 0;
 }
 
-static size_t pcpu_calc_fc_sizes(size_t static_size, size_t reserved_size,
-				 ssize_t *dyn_sizep)
-{
-	size_t size_sum;
+const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
+	[PCPU_FC_AUTO]	= "auto",
+	[PCPU_FC_EMBED]	= "embed",
+	[PCPU_FC_PAGE]	= "page",
+};
 
-	size_sum = PFN_ALIGN(static_size + reserved_size +
-			     (*dyn_sizep >= 0 ? *dyn_sizep : 0));
-	if (*dyn_sizep != 0)
-		*dyn_sizep = size_sum - static_size - reserved_size;
+enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;
 
-	return size_sum;
+static int __init percpu_alloc_setup(char *str)
+{
+	if (0)
+		/* nada */;
+#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
+	else if (!strcmp(str, "embed"))
+		pcpu_chosen_fc = PCPU_FC_EMBED;
+#endif
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+	else if (!strcmp(str, "page"))
+		pcpu_chosen_fc = PCPU_FC_PAGE;
+#endif
+	else
+		pr_warning("PERCPU: unknown allocator %s specified\n", str);
+
+	return 0;
 }
+early_param("percpu_alloc", percpu_alloc_setup);
 
+#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
+	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
 /**
  * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
- * @static_size: the size of static percpu area in bytes
  * @reserved_size: the size of reserved percpu area in bytes
  * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @atom_size: allocation atom size
+ * @cpu_distance_fn: callback to determine distance between cpus, optional
+ * @alloc_fn: function to allocate percpu page
+ * @free_fn: funtion to free percpu page
  *
  * This is a helper to ease setting up embedded first percpu chunk and
  * can be called where pcpu_setup_first_chunk() is expected.
  *
  * If this function is used to setup the first chunk, it is allocated
- * as a contiguous area using bootmem allocator and used as-is without
- * being mapped into vmalloc area.  This enables the first chunk to
- * piggy back on the linear physical mapping which often uses larger
- * page size.
+ * by calling @alloc_fn and used as-is without being mapped into
+ * vmalloc area.  Allocations are always whole multiples of @atom_size
+ * aligned to @atom_size.
+ *
+ * This enables the first chunk to piggy back on the linear physical
+ * mapping which often uses larger page size.  Please note that this
+ * can result in very sparse cpu->unit mapping on NUMA machines thus
+ * requiring large vmalloc address space.  Don't use this allocator if
+ * vmalloc space is not orders of magnitude larger than distances
+ * between node memory addresses (ie. 32bit NUMA machines).
  *
  * When @dyn_size is positive, dynamic area might be larger than
  * specified to fill page alignment.  When @dyn_size is auto,
@@ -1447,82 +1868,149 @@ static size_t pcpu_calc_fc_sizes(size_t static_size, size_t reserved_size,
  * and reserved areas.
  *
  * If the needed size is smaller than the minimum or specified unit
- * size, the leftover is returned to the bootmem allocator.
+ * size, the leftover is returned using @free_fn.
  *
  * RETURNS:
- * The determined pcpu_unit_size which can be used to initialize
- * percpu access on success, -errno on failure.
+ * 0 on success, -errno on failure.
  */
-ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
-				      ssize_t dyn_size)
+int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
+				  size_t atom_size,
+				  pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
+				  pcpu_fc_alloc_fn_t alloc_fn,
+				  pcpu_fc_free_fn_t free_fn)
 {
-	size_t size_sum, unit_size, chunk_size;
-	void *base;
-	unsigned int cpu;
+	void *base = (void *)ULONG_MAX;
+	void **areas = NULL;
+	struct pcpu_alloc_info *ai;
+	size_t size_sum, areas_size, max_distance;
+	int group, i, rc;
+
+	ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
+				   cpu_distance_fn);
+	if (IS_ERR(ai))
+		return PTR_ERR(ai);
+
+	size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
+	areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));
+
+	areas = alloc_bootmem_nopanic(areas_size);
+	if (!areas) {
+		rc = -ENOMEM;
+		goto out_free;
+	}
 
-	/* determine parameters and allocate */
-	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size);
+	/* allocate, copy and determine base address */
+	for (group = 0; group < ai->nr_groups; group++) {
+		struct pcpu_group_info *gi = &ai->groups[group];
+		unsigned int cpu = NR_CPUS;
+		void *ptr;
 
-	unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
-	chunk_size = unit_size * num_possible_cpus();
+		for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++)
+			cpu = gi->cpu_map[i];
+		BUG_ON(cpu == NR_CPUS);
 
-	base = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE,
-				       __pa(MAX_DMA_ADDRESS));
-	if (!base) {
-		pr_warning("PERCPU: failed to allocate %zu bytes for "
-			   "embedding\n", chunk_size);
-		return -ENOMEM;
-	}
+		/* allocate space for the whole group */
+		ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size);
+		if (!ptr) {
+			rc = -ENOMEM;
+			goto out_free_areas;
+		}
+		areas[group] = ptr;
 
-	/* return the leftover and copy */
-	for_each_possible_cpu(cpu) {
-		void *ptr = base + cpu * unit_size;
+		base = min(ptr, base);
 
-		free_bootmem(__pa(ptr + size_sum), unit_size - size_sum);
-		memcpy(ptr, __per_cpu_load, static_size);
+		for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
+			if (gi->cpu_map[i] == NR_CPUS) {
+				/* unused unit, free whole */
+				free_fn(ptr, ai->unit_size);
+				continue;
+			}
+			/* copy and return the unused part */
+			memcpy(ptr, __per_cpu_load, ai->static_size);
+			free_fn(ptr + size_sum, ai->unit_size - size_sum);
+		}
 	}
 
-	/* we're ready, commit */
-	pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
-		size_sum >> PAGE_SHIFT, base, static_size);
+	/* base address is now known, determine group base offsets */
+	max_distance = 0;
+	for (group = 0; group < ai->nr_groups; group++) {
+		ai->groups[group].base_offset = areas[group] - base;
+		max_distance = max_t(size_t, max_distance,
+				     ai->groups[group].base_offset);
+	}
+	max_distance += ai->unit_size;
+
+	/* warn if maximum distance is further than 75% of vmalloc space */
+	if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
+		pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
+			   "space 0x%lx\n",
+			   max_distance, VMALLOC_END - VMALLOC_START);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+		/* and fail if we have fallback */
+		rc = -EINVAL;
+		goto out_free;
+#endif
+	}
 
-	return pcpu_setup_first_chunk(static_size, reserved_size, dyn_size,
-				      unit_size, base, NULL);
+	pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
+		PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
+		ai->dyn_size, ai->unit_size);
+
+	rc = pcpu_setup_first_chunk(ai, base);
+	goto out_free;
+
+out_free_areas:
+	for (group = 0; group < ai->nr_groups; group++)
+		free_fn(areas[group],
+			ai->groups[group].nr_units * ai->unit_size);
+out_free:
+	pcpu_free_alloc_info(ai);
+	if (areas)
+		free_bootmem(__pa(areas), areas_size);
+	return rc;
 }
+#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
+	  !CONFIG_HAVE_SETUP_PER_CPU_AREA */
 
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
 /**
- * pcpu_4k_first_chunk - map the first chunk using PAGE_SIZE pages
- * @static_size: the size of static percpu area in bytes
+ * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
  * @reserved_size: the size of reserved percpu area in bytes
  * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE
  * @free_fn: funtion to free percpu page, always called with PAGE_SIZE
  * @populate_pte_fn: function to populate pte
  *
- * This is a helper to ease setting up embedded first percpu chunk and
- * can be called where pcpu_setup_first_chunk() is expected.
+ * This is a helper to ease setting up page-remapped first percpu
+ * chunk and can be called where pcpu_setup_first_chunk() is expected.
  *
  * This is the basic allocator.  Static percpu area is allocated
  * page-by-page into vmalloc area.
  *
  * RETURNS:
- * The determined pcpu_unit_size which can be used to initialize
- * percpu access on success, -errno on failure.
+ * 0 on success, -errno on failure.
  */
-ssize_t __init pcpu_4k_first_chunk(size_t static_size, size_t reserved_size,
-				   pcpu_fc_alloc_fn_t alloc_fn,
-				   pcpu_fc_free_fn_t free_fn,
-				   pcpu_fc_populate_pte_fn_t populate_pte_fn)
+int __init pcpu_page_first_chunk(size_t reserved_size,
+				 pcpu_fc_alloc_fn_t alloc_fn,
+				 pcpu_fc_free_fn_t free_fn,
+				 pcpu_fc_populate_pte_fn_t populate_pte_fn)
 {
 	static struct vm_struct vm;
+	struct pcpu_alloc_info *ai;
+	char psize_str[16];
 	int unit_pages;
 	size_t pages_size;
 	struct page **pages;
-	unsigned int cpu;
-	int i, j;
-	ssize_t ret;
+	int unit, i, j, rc;
 
-	unit_pages = PFN_UP(max_t(size_t, static_size + reserved_size,
-				  PCPU_MIN_UNIT_SIZE));
+	snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10);
+
+	ai = pcpu_build_alloc_info(reserved_size, -1, PAGE_SIZE, NULL);
+	if (IS_ERR(ai))
+		return PTR_ERR(ai);
+	BUG_ON(ai->nr_groups != 1);
+	BUG_ON(ai->groups[0].nr_units != num_possible_cpus());
+
+	unit_pages = ai->unit_size >> PAGE_SHIFT;
 
 	/* unaligned allocations can't be freed, round up to page size */
 	pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
@@ -1531,14 +2019,15 @@ ssize_t __init pcpu_4k_first_chunk(size_t static_size, size_t reserved_size,
 
 	/* allocate pages */
 	j = 0;
-	for_each_possible_cpu(cpu)
+	for (unit = 0; unit < num_possible_cpus(); unit++)
 		for (i = 0; i < unit_pages; i++) {
+			unsigned int cpu = ai->groups[0].cpu_map[unit];
 			void *ptr;
 
-			ptr = alloc_fn(cpu, PAGE_SIZE);
+			ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE);
 			if (!ptr) {
-				pr_warning("PERCPU: failed to allocate "
-					   "4k page for cpu%u\n", cpu);
+				pr_warning("PERCPU: failed to allocate %s page "
+					   "for cpu%u\n", psize_str, cpu);
 				goto enomem;
 			}
 			pages[j++] = virt_to_page(ptr);
@@ -1546,21 +2035,21 @@ ssize_t __init pcpu_4k_first_chunk(size_t static_size, size_t reserved_size,
 
 	/* allocate vm area, map the pages and copy static data */
 	vm.flags = VM_ALLOC;
-	vm.size = num_possible_cpus() * unit_pages << PAGE_SHIFT;
+	vm.size = num_possible_cpus() * ai->unit_size;
 	vm_area_register_early(&vm, PAGE_SIZE);
 
-	for_each_possible_cpu(cpu) {
-		unsigned long unit_addr = (unsigned long)vm.addr +
-			(cpu * unit_pages << PAGE_SHIFT);
+	for (unit = 0; unit < num_possible_cpus(); unit++) {
+		unsigned long unit_addr =
+			(unsigned long)vm.addr + unit * ai->unit_size;
 
 		for (i = 0; i < unit_pages; i++)
 			populate_pte_fn(unit_addr + (i << PAGE_SHIFT));
 
 		/* pte already populated, the following shouldn't fail */
-		ret = __pcpu_map_pages(unit_addr, &pages[cpu * unit_pages],
-				       unit_pages);
-		if (ret < 0)
-			panic("failed to map percpu area, err=%zd\n", ret);
+		rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages],
+				      unit_pages);
+		if (rc < 0)
+			panic("failed to map percpu area, err=%d\n", rc);
 
 		/*
 		 * FIXME: Archs with virtual cache should flush local
@@ -1571,410 +2060,27 @@ ssize_t __init pcpu_4k_first_chunk(size_t static_size, size_t reserved_size,
 		 */
 
 		/* copy static data */
-		memcpy((void *)unit_addr, __per_cpu_load, static_size);
+		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
 	}
 
 	/* we're ready, commit */
-	pr_info("PERCPU: %d 4k pages per cpu, static data %zu bytes\n",
-		unit_pages, static_size);
+	pr_info("PERCPU: %d %s pages/cpu @%p s%zu r%zu d%zu\n",
+		unit_pages, psize_str, vm.addr, ai->static_size,
+		ai->reserved_size, ai->dyn_size);
 
-	ret = pcpu_setup_first_chunk(static_size, reserved_size, -1,
-				     unit_pages << PAGE_SHIFT, vm.addr, NULL);
+	rc = pcpu_setup_first_chunk(ai, vm.addr);
 	goto out_free_ar;
 
 enomem:
 	while (--j >= 0)
 		free_fn(page_address(pages[j]), PAGE_SIZE);
-	ret = -ENOMEM;
+	rc = -ENOMEM;
 out_free_ar:
 	free_bootmem(__pa(pages), pages_size);
-	return ret;
-}
-
-/*
- * Large page remapping first chunk setup helper
- */
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-
-/**
- * pcpu_lpage_build_unit_map - build unit_map for large page remapping
- * @static_size: the size of static percpu area in bytes
- * @reserved_size: the size of reserved percpu area in bytes
- * @dyn_sizep: in/out parameter for dynamic size, -1 for auto
- * @unit_sizep: out parameter for unit size
- * @unit_map: unit_map to be filled
- * @cpu_distance_fn: callback to determine distance between cpus
- *
- * This function builds cpu -> unit map and determine other parameters
- * considering needed percpu size, large page size and distances
- * between CPUs in NUMA.
- *
- * CPUs which are of LOCAL_DISTANCE both ways are grouped together and
- * may share units in the same large page.  The returned configuration
- * is guaranteed to have CPUs on different nodes on different large
- * pages and >=75% usage of allocated virtual address space.
- *
- * RETURNS:
- * On success, fills in @unit_map, sets *@dyn_sizep, *@unit_sizep and
- * returns the number of units to be allocated.  -errno on failure.
- */
-int __init pcpu_lpage_build_unit_map(size_t static_size, size_t reserved_size,
-				     ssize_t *dyn_sizep, size_t *unit_sizep,
-				     size_t lpage_size, int *unit_map,
-				     pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
-{
-	static int group_map[NR_CPUS] __initdata;
-	static int group_cnt[NR_CPUS] __initdata;
-	int group_cnt_max = 0;
-	size_t size_sum, min_unit_size, alloc_size;
-	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
-	int last_allocs;
-	unsigned int cpu, tcpu;
-	int group, unit;
-
-	/*
-	 * Determine min_unit_size, alloc_size and max_upa such that
-	 * alloc_size is multiple of lpage_size and is the smallest
-	 * which can accomodate 4k aligned segments which are equal to
-	 * or larger than min_unit_size.
-	 */
-	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, dyn_sizep);
-	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
-
-	alloc_size = roundup(min_unit_size, lpage_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, tcpu) > LOCAL_DISTANCE ||
-			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
-				group++;
-				goto next_group;
-			}
-		}
-		group_map[cpu] = group;
-		group_cnt[group]++;
-		group_cnt_max = max(group_cnt_max, 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_cnt[group]; 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 25%.  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;
-	}
-	*unit_sizep = alloc_size / best_upa;
-
-	/* assign units to cpus accordingly */
-	unit = 0;
-	for (group = 0; group_cnt[group]; group++) {
-		for_each_possible_cpu(cpu)
-			if (group_map[cpu] == group)
-				unit_map[cpu] = unit++;
-		unit = roundup(unit, best_upa);
-	}
-
-	return unit;	/* unit contains aligned number of units */
-}
-
-struct pcpul_ent {
-	void		*ptr;
-	void		*map_addr;
-};
-
-static size_t pcpul_size;
-static size_t pcpul_lpage_size;
-static int pcpul_nr_lpages;
-static struct pcpul_ent *pcpul_map;
-
-static bool __init pcpul_unit_to_cpu(int unit, const int *unit_map,
-				     unsigned int *cpup)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu)
-		if (unit_map[cpu] == unit) {
-			if (cpup)
-				*cpup = cpu;
-			return true;
-		}
-
-	return false;
-}
-
-static void __init pcpul_lpage_dump_cfg(const char *lvl, size_t static_size,
-					size_t reserved_size, size_t dyn_size,
-					size_t unit_size, size_t lpage_size,
-					const int *unit_map, int nr_units)
-{
-	int width = 1, v = nr_units;
-	char empty_str[] = "--------";
-	int upl, lpl;	/* units per lpage, lpage per line */
-	unsigned int cpu;
-	int lpage, unit;
-
-	while (v /= 10)
-		width++;
-	empty_str[min_t(int, width, sizeof(empty_str) - 1)] = '\0';
-
-	upl = max_t(int, lpage_size / unit_size, 1);
-	lpl = rounddown_pow_of_two(max_t(int, 60 / (upl * (width + 1) + 2), 1));
-
-	printk("%spcpu-lpage: sta/res/dyn=%zu/%zu/%zu unit=%zu lpage=%zu", lvl,
-	       static_size, reserved_size, dyn_size, unit_size, lpage_size);
-
-	for (lpage = 0, unit = 0; unit < nr_units; unit++) {
-		if (!(unit % upl)) {
-			if (!(lpage++ % lpl)) {
-				printk("\n");
-				printk("%spcpu-lpage: ", lvl);
-			} else
-				printk("| ");
-		}
-		if (pcpul_unit_to_cpu(unit, unit_map, &cpu))
-			printk("%0*d ", width, cpu);
-		else
-			printk("%s ", empty_str);
-	}
-	printk("\n");
-}
-
-/**
- * pcpu_lpage_first_chunk - remap the first percpu chunk using large page
- * @static_size: the size of static percpu area in bytes
- * @reserved_size: the size of reserved percpu area in bytes
- * @dyn_size: free size for dynamic allocation in bytes
- * @unit_size: unit size in bytes
- * @lpage_size: the size of a large page
- * @unit_map: cpu -> unit mapping
- * @nr_units: the number of units
- * @alloc_fn: function to allocate percpu lpage, always called with lpage_size
- * @free_fn: function to free percpu memory, @size <= lpage_size
- * @map_fn: function to map percpu lpage, always called with lpage_size
- *
- * This allocator uses large page to build and map the first chunk.
- * Unlike other helpers, the caller should always specify @dyn_size
- * and @unit_size.  These parameters along with @unit_map and
- * @nr_units can be determined using pcpu_lpage_build_unit_map().
- * This two stage initialization is to allow arch code to evaluate the
- * parameters before committing to it.
- *
- * Large pages are allocated as directed by @unit_map and other
- * parameters and mapped to vmalloc space.  Unused holes are returned
- * to the page allocator.  Note that these holes end up being actively
- * mapped twice - once to the physical mapping and to the vmalloc area
- * for the first percpu chunk.  Depending on architecture, this might
- * cause problem when changing page attributes of the returned area.
- * These double mapped areas can be detected using
- * pcpu_lpage_remapped().
- *
- * RETURNS:
- * The determined pcpu_unit_size which can be used to initialize
- * percpu access on success, -errno on failure.
- */
-ssize_t __init pcpu_lpage_first_chunk(size_t static_size, size_t reserved_size,
-				      size_t dyn_size, size_t unit_size,
-				      size_t lpage_size, const int *unit_map,
-				      int nr_units,
-				      pcpu_fc_alloc_fn_t alloc_fn,
-				      pcpu_fc_free_fn_t free_fn,
-				      pcpu_fc_map_fn_t map_fn)
-{
-	static struct vm_struct vm;
-	size_t chunk_size = unit_size * nr_units;
-	size_t map_size;
-	unsigned int cpu;
-	ssize_t ret;
-	int i, j, unit;
-
-	pcpul_lpage_dump_cfg(KERN_DEBUG, static_size, reserved_size, dyn_size,
-			     unit_size, lpage_size, unit_map, nr_units);
-
-	BUG_ON(chunk_size % lpage_size);
-
-	pcpul_size = static_size + reserved_size + dyn_size;
-	pcpul_lpage_size = lpage_size;
-	pcpul_nr_lpages = chunk_size / lpage_size;
-
-	/* allocate pointer array and alloc large pages */
-	map_size = pcpul_nr_lpages * sizeof(pcpul_map[0]);
-	pcpul_map = alloc_bootmem(map_size);
-
-	/* allocate all pages */
-	for (i = 0; i < pcpul_nr_lpages; i++) {
-		size_t offset = i * lpage_size;
-		int first_unit = offset / unit_size;
-		int last_unit = (offset + lpage_size - 1) / unit_size;
-		void *ptr;
-
-		/* find out which cpu is mapped to this unit */
-		for (unit = first_unit; unit <= last_unit; unit++)
-			if (pcpul_unit_to_cpu(unit, unit_map, &cpu))
-				goto found;
-		continue;
-	found:
-		ptr = alloc_fn(cpu, lpage_size);
-		if (!ptr) {
-			pr_warning("PERCPU: failed to allocate large page "
-				   "for cpu%u\n", cpu);
-			goto enomem;
-		}
-
-		pcpul_map[i].ptr = ptr;
-	}
-
-	/* return unused holes */
-	for (unit = 0; unit < nr_units; unit++) {
-		size_t start = unit * unit_size;
-		size_t end = start + unit_size;
-		size_t off, next;
-
-		/* don't free used part of occupied unit */
-		if (pcpul_unit_to_cpu(unit, unit_map, NULL))
-			start += pcpul_size;
-
-		/* unit can span more than one page, punch the holes */
-		for (off = start; off < end; off = next) {
-			void *ptr = pcpul_map[off / lpage_size].ptr;
-			next = min(roundup(off + 1, lpage_size), end);
-			if (ptr)
-				free_fn(ptr + off % lpage_size, next - off);
-		}
-	}
-
-	/* allocate address, map and copy */
-	vm.flags = VM_ALLOC;
-	vm.size = chunk_size;
-	vm_area_register_early(&vm, unit_size);
-
-	for (i = 0; i < pcpul_nr_lpages; i++) {
-		if (!pcpul_map[i].ptr)
-			continue;
-		pcpul_map[i].map_addr = vm.addr + i * lpage_size;
-		map_fn(pcpul_map[i].ptr, lpage_size, pcpul_map[i].map_addr);
-	}
-
-	for_each_possible_cpu(cpu)
-		memcpy(vm.addr + unit_map[cpu] * unit_size, __per_cpu_load,
-		       static_size);
-
-	/* we're ready, commit */
-	pr_info("PERCPU: Remapped at %p with large pages, static data "
-		"%zu bytes\n", vm.addr, static_size);
-
-	ret = pcpu_setup_first_chunk(static_size, reserved_size, dyn_size,
-				     unit_size, vm.addr, unit_map);
-
-	/*
-	 * Sort pcpul_map array for pcpu_lpage_remapped().  Unmapped
-	 * lpages are pushed to the end and trimmed.
-	 */
-	for (i = 0; i < pcpul_nr_lpages - 1; i++)
-		for (j = i + 1; j < pcpul_nr_lpages; j++) {
-			struct pcpul_ent tmp;
-
-			if (!pcpul_map[j].ptr)
-				continue;
-			if (pcpul_map[i].ptr &&
-			    pcpul_map[i].ptr < pcpul_map[j].ptr)
-				continue;
-
-			tmp = pcpul_map[i];
-			pcpul_map[i] = pcpul_map[j];
-			pcpul_map[j] = tmp;
-		}
-
-	while (pcpul_nr_lpages && !pcpul_map[pcpul_nr_lpages - 1].ptr)
-		pcpul_nr_lpages--;
-
-	return ret;
-
-enomem:
-	for (i = 0; i < pcpul_nr_lpages; i++)
-		if (pcpul_map[i].ptr)
-			free_fn(pcpul_map[i].ptr, lpage_size);
-	free_bootmem(__pa(pcpul_map), map_size);
-	return -ENOMEM;
-}
-
-/**
- * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area
- * @kaddr: the kernel address in question
- *
- * Determine whether @kaddr falls in the pcpul recycled area.  This is
- * used by pageattr to detect VM aliases and break up the pcpu large
- * page mapping such that the same physical page is not mapped under
- * different attributes.
- *
- * The recycled area is always at the tail of a partially used large
- * page.
- *
- * RETURNS:
- * Address of corresponding remapped pcpu address if match is found;
- * otherwise, NULL.
- */
-void *pcpu_lpage_remapped(void *kaddr)
-{
-	unsigned long lpage_mask = pcpul_lpage_size - 1;
-	void *lpage_addr = (void *)((unsigned long)kaddr & ~lpage_mask);
-	unsigned long offset = (unsigned long)kaddr & lpage_mask;
-	int left = 0, right = pcpul_nr_lpages - 1;
-	int pos;
-
-	/* pcpul in use at all? */
-	if (!pcpul_map)
-		return NULL;
-
-	/* okay, perform binary search */
-	while (left <= right) {
-		pos = (left + right) / 2;
-
-		if (pcpul_map[pos].ptr < lpage_addr)
-			left = pos + 1;
-		else if (pcpul_map[pos].ptr > lpage_addr)
-			right = pos - 1;
-		else
-			return pcpul_map[pos].map_addr + offset;
-	}
-
-	return NULL;
+	pcpu_free_alloc_info(ai);
+	return rc;
 }
-#endif
+#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */
 
 /*
  * Generic percpu area setup.
@@ -1992,24 +2098,35 @@ void *pcpu_lpage_remapped(void *kaddr)
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
+static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
+				       size_t align)
+{
+	return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
+}
+
+static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
+{
+	free_bootmem(__pa(ptr), size);
+}
+
 void __init setup_per_cpu_areas(void)
 {
-	size_t static_size = __per_cpu_end - __per_cpu_start;
-	ssize_t unit_size;
 	unsigned long delta;
 	unsigned int cpu;
+	int rc;
 
 	/*
 	 * Always reserve area for module percpu variables.  That's
 	 * what the legacy allocator did.
 	 */
-	unit_size = pcpu_embed_first_chunk(static_size, PERCPU_MODULE_RESERVE,
-					   PERCPU_DYNAMIC_RESERVE);
-	if (unit_size < 0)
+	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
+				    pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
+	if (rc < 0)
 		panic("Failed to initialized percpu areas.");
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu)
-		__per_cpu_offset[cpu] = delta + cpu * unit_size;
+		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
 }
 #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */