1 files changed, 225 insertions, 156 deletions

diff --git a/mm/percpu.c b/mm/percpu.c
index 3f930018aa6..2ddf9a990db 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -67,6 +67,7 @@
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
+#include <linux/kmemleak.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -101,10 +102,11 @@ struct pcpu_chunk {
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
 	void			*base_addr;	/* base address of this chunk */
-	int			map_used;	/* # of map entries used */
+	int			map_used;	/* # of map entries used before the sentry */
 	int			map_alloc;	/* # of map entries allocated */
 	int			*map;		/* allocation map */
 	void			*data;		/* chunk data */
+	int			first_free;	/* no free below this */
 	bool			immutable;	/* no [de]population allowed */
 	unsigned long		populated[];	/* populated bitmap */
 };
@@ -116,9 +118,9 @@ static int pcpu_atom_size __read_mostly;
 static int pcpu_nr_slots __read_mostly;
 static size_t pcpu_chunk_struct_size __read_mostly;
 
-/* cpus with the lowest and highest unit numbers */
-static unsigned int pcpu_first_unit_cpu __read_mostly;
-static unsigned int pcpu_last_unit_cpu __read_mostly;
+/* cpus with the lowest and highest unit addresses */
+static unsigned int pcpu_low_unit_cpu __read_mostly;
+static unsigned int pcpu_high_unit_cpu __read_mostly;
 
 /* the address of the first chunk which starts with the kernel static area */
 void *pcpu_base_addr __read_mostly;
@@ -273,11 +275,11 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
 	     (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))
 
 /**
- * pcpu_mem_alloc - allocate memory
+ * pcpu_mem_zalloc - allocate memory
  * @size: bytes to allocate
  *
  * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vmalloc() is used.  The returned
+ * kzalloc() is used; otherwise, vzalloc() is used.  The returned
  * memory is always zeroed.
  *
  * CONTEXT:
@@ -286,7 +288,7 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void *pcpu_mem_alloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size)
 {
 	if (WARN_ON_ONCE(!slab_is_available()))
 		return NULL;
@@ -302,7 +304,7 @@ static void *pcpu_mem_alloc(size_t size)
  * @ptr: memory to free
  * @size: size of the area
  *
- * Free @ptr.  @ptr should have been allocated using pcpu_mem_alloc().
+ * Free @ptr.  @ptr should have been allocated using pcpu_mem_zalloc().
  */
 static void pcpu_mem_free(void *ptr, size_t size)
 {
@@ -342,7 +344,7 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
  * @chunk: chunk of interest
  *
  * Determine whether area map of @chunk needs to be extended to
- * accomodate a new allocation.
+ * accommodate a new allocation.
  *
  * CONTEXT:
  * pcpu_lock.
@@ -355,11 +357,11 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
 {
 	int new_alloc;
 
-	if (chunk->map_alloc >= chunk->map_used + 2)
+	if (chunk->map_alloc >= chunk->map_used + 3)
 		return 0;
 
 	new_alloc = PCPU_DFL_MAP_ALLOC;
-	while (new_alloc < chunk->map_used + 2)
+	while (new_alloc < chunk->map_used + 3)
 		new_alloc *= 2;
 
 	return new_alloc;
@@ -384,7 +386,7 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
 	unsigned long flags;
 
-	new = pcpu_mem_alloc(new_size);
+	new = pcpu_mem_zalloc(new_size);
 	if (!new)
 		return -ENOMEM;
 
@@ -417,48 +419,6 @@ out_unlock:
 }
 
 /**
- * pcpu_split_block - split a map block
- * @chunk: chunk of interest
- * @i: index of map block to split
- * @head: head size in bytes (can be 0)
- * @tail: tail size in bytes (can be 0)
- *
- * Split the @i'th map block into two or three blocks.  If @head is
- * non-zero, @head bytes block is inserted before block @i moving it
- * to @i+1 and reducing its size by @head bytes.
- *
- * If @tail is non-zero, the target block, which can be @i or @i+1
- * depending on @head, is reduced by @tail bytes and @tail byte block
- * is inserted after the target block.
- *
- * @chunk->map must have enough free slots to accomodate the split.
- *
- * CONTEXT:
- * pcpu_lock.
- */
-static void pcpu_split_block(struct pcpu_chunk *chunk, int i,
-			     int head, int tail)
-{
-	int nr_extra = !!head + !!tail;
-
-	BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra);
-
-	/* insert new subblocks */
-	memmove(&chunk->map[i + nr_extra], &chunk->map[i],
-		sizeof(chunk->map[0]) * (chunk->map_used - i));
-	chunk->map_used += nr_extra;
-
-	if (head) {
-		chunk->map[i + 1] = chunk->map[i] - head;
-		chunk->map[i++] = head;
-	}
-	if (tail) {
-		chunk->map[i++] -= tail;
-		chunk->map[i] = tail;
-	}
-}
-
-/**
  * pcpu_alloc_area - allocate area from a pcpu_chunk
  * @chunk: chunk of interest
  * @size: wanted size in bytes
@@ -482,19 +442,27 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
 	int oslot = pcpu_chunk_slot(chunk);
 	int max_contig = 0;
 	int i, off;
+	bool seen_free = false;
+	int *p;
 
-	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) {
-		bool is_last = i + 1 == chunk->map_used;
+	for (i = chunk->first_free, p = chunk->map + i; i < chunk->map_used; i++, p++) {
 		int head, tail;
+		int this_size;
+
+		off = *p;
+		if (off & 1)
+			continue;
 
 		/* extra for alignment requirement */
 		head = ALIGN(off, align) - off;
-		BUG_ON(i == 0 && head != 0);
 
-		if (chunk->map[i] < 0)
-			continue;
-		if (chunk->map[i] < head + size) {
-			max_contig = max(chunk->map[i], max_contig);
+		this_size = (p[1] & ~1) - off;
+		if (this_size < head + size) {
+			if (!seen_free) {
+				chunk->first_free = i;
+				seen_free = true;
+			}
+			max_contig = max(this_size, max_contig);
 			continue;
 		}
 
@@ -504,44 +472,59 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
 		 * than sizeof(int), which is very small but isn't too
 		 * uncommon for percpu allocations.
 		 */
-		if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) {
-			if (chunk->map[i - 1] > 0)
-				chunk->map[i - 1] += head;
-			else {
-				chunk->map[i - 1] -= head;
+		if (head && (head < sizeof(int) || !(p[-1] & 1))) {
+			*p = off += head;
+			if (p[-1] & 1)
 				chunk->free_size -= head;
-			}
-			chunk->map[i] -= head;
-			off += head;
+			else
+				max_contig = max(*p - p[-1], max_contig);
+			this_size -= head;
 			head = 0;
 		}
 
 		/* if tail is small, just keep it around */
-		tail = chunk->map[i] - head - size;
-		if (tail < sizeof(int))
+		tail = this_size - head - size;
+		if (tail < sizeof(int)) {
 			tail = 0;
+			size = this_size - head;
+		}
 
 		/* split if warranted */
 		if (head || tail) {
-			pcpu_split_block(chunk, i, head, tail);
+			int nr_extra = !!head + !!tail;
+
+			/* insert new subblocks */
+			memmove(p + nr_extra + 1, p + 1,
+				sizeof(chunk->map[0]) * (chunk->map_used - i));
+			chunk->map_used += nr_extra;
+
 			if (head) {
-				i++;
-				off += head;
-				max_contig = max(chunk->map[i - 1], max_contig);
+				if (!seen_free) {
+					chunk->first_free = i;
+					seen_free = true;
+				}
+				*++p = off += head;
+				++i;
+				max_contig = max(head, max_contig);
+			}
+			if (tail) {
+				p[1] = off + size;
+				max_contig = max(tail, max_contig);
 			}
-			if (tail)
-				max_contig = max(chunk->map[i + 1], max_contig);
 		}
 
+		if (!seen_free)
+			chunk->first_free = i + 1;
+
 		/* update hint and mark allocated */
-		if (is_last)
+		if (i + 1 == chunk->map_used)
 			chunk->contig_hint = max_contig; /* fully scanned */
 		else
 			chunk->contig_hint = max(chunk->contig_hint,
 						 max_contig);
 
-		chunk->free_size -= chunk->map[i];
-		chunk->map[i] = -chunk->map[i];
+		chunk->free_size -= size;
+		*p |= 1;
 
 		pcpu_chunk_relocate(chunk, oslot);
 		return off;
@@ -569,34 +552,50 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
 static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
 {
 	int oslot = pcpu_chunk_slot(chunk);
-	int i, off;
-
-	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++]))
-		if (off == freeme)
-			break;
+	int off = 0;
+	unsigned i, j;
+	int to_free = 0;
+	int *p;
+
+	freeme |= 1;	/* we are searching for <given offset, in use> pair */
+
+	i = 0;
+	j = chunk->map_used;
+	while (i != j) {
+		unsigned k = (i + j) / 2;
+		off = chunk->map[k];
+		if (off < freeme)
+			i = k + 1;
+		else if (off > freeme)
+			j = k;
+		else
+			i = j = k;
+	}
 	BUG_ON(off != freeme);
-	BUG_ON(chunk->map[i] > 0);
 
-	chunk->map[i] = -chunk->map[i];
-	chunk->free_size += chunk->map[i];
+	if (i < chunk->first_free)
+		chunk->first_free = i;
+
+	p = chunk->map + i;
+	*p = off &= ~1;
+	chunk->free_size += (p[1] & ~1) - off;
 
+	/* merge with next? */
+	if (!(p[1] & 1))
+		to_free++;
 	/* merge with previous? */
-	if (i > 0 && chunk->map[i - 1] >= 0) {
-		chunk->map[i - 1] += chunk->map[i];
-		chunk->map_used--;
-		memmove(&chunk->map[i], &chunk->map[i + 1],
-			(chunk->map_used - i) * sizeof(chunk->map[0]));
+	if (i > 0 && !(p[-1] & 1)) {
+		to_free++;
 		i--;
+		p--;
 	}
-	/* merge with next? */
-	if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) {
-		chunk->map[i] += chunk->map[i + 1];
-		chunk->map_used--;
-		memmove(&chunk->map[i + 1], &chunk->map[i + 2],
-			(chunk->map_used - (i + 1)) * sizeof(chunk->map[0]));
+	if (to_free) {
+		chunk->map_used -= to_free;
+		memmove(p + 1, p + 1 + to_free,
+			(chunk->map_used - i) * sizeof(chunk->map[0]));
 	}
 
-	chunk->contig_hint = max(chunk->map[i], chunk->contig_hint);
+	chunk->contig_hint = max(chunk->map[i + 1] - chunk->map[i] - 1, chunk->contig_hint);
 	pcpu_chunk_relocate(chunk, oslot);
 }
 
@@ -604,18 +603,21 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 {
 	struct pcpu_chunk *chunk;
 
-	chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
+	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
 	if (!chunk)
 		return NULL;
 
-	chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
+						sizeof(chunk->map[0]));
 	if (!chunk->map) {
-		kfree(chunk);
+		pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 		return NULL;
 	}
 
 	chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
-	chunk->map[chunk->map_used++] = pcpu_unit_size;
+	chunk->map[0] = 0;
+	chunk->map[1] = pcpu_unit_size | 1;
+	chunk->map_used = 1;
 
 	INIT_LIST_HEAD(&chunk->list);
 	chunk->free_size = pcpu_unit_size;
@@ -629,7 +631,7 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
 	if (!chunk)
 		return;
 	pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
-	kfree(chunk);
+	pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 }
 
 /*
@@ -709,6 +711,17 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
 	const char *err;
 	int slot, off, new_alloc;
 	unsigned long flags;
+	void __percpu *ptr;
+
+	/*
+	 * We want the lowest bit of offset available for in-use/free
+	 * indicator, so force >= 16bit alignment and make size even.
+	 */
+	if (unlikely(align < 2))
+		align = 2;
+
+	if (unlikely(size & 1))
+		size++;
 
 	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
 		WARN(true, "illegal size (%zu) or align (%zu) for "
@@ -801,7 +814,9 @@ area_found:
 	mutex_unlock(&pcpu_alloc_mutex);
 
 	/* return address relative to base address */
-	return __addr_to_pcpu_ptr(chunk->base_addr + off);
+	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
+	kmemleak_alloc_percpu(ptr, size);
+	return ptr;
 
 fail_unlock:
 	spin_unlock_irqrestore(&pcpu_lock, flags);
@@ -915,6 +930,8 @@ void free_percpu(void __percpu *ptr)
 	if (!ptr)
 		return;
 
+	kmemleak_free_percpu(ptr);
+
 	addr = __pcpu_ptr_to_addr(ptr);
 
 	spin_lock_irqsave(&pcpu_lock, flags);
@@ -977,6 +994,17 @@ bool is_kernel_percpu_address(unsigned long addr)
  * address.  The caller is responsible for ensuring @addr stays valid
  * until this function finishes.
  *
+ * percpu allocator has special setup for the first chunk, which currently
+ * supports either embedding in linear address space or vmalloc mapping,
+ * and, from the second one, the backing allocator (currently either vm or
+ * km) provides translation.
+ *
+ * The addr can be tranlated simply without checking if it falls into the
+ * first chunk. But the current code reflects better how percpu allocator
+ * actually works, and the verification can discover both bugs in percpu
+ * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
+ * code.
+ *
  * RETURNS:
  * The physical address for @addr.
  */
@@ -984,19 +1012,19 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
 {
 	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
 	bool in_first_chunk = false;
-	unsigned long first_start, first_end;
+	unsigned long first_low, first_high;
 	unsigned int cpu;
 
 	/*
-	 * The following test on first_start/end isn't strictly
+	 * The following test on unit_low/high isn't strictly
 	 * necessary but will speed up lookups of addresses which
 	 * aren't in the first chunk.
 	 */
-	first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0);
-	first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu,
-				    pcpu_unit_pages);
-	if ((unsigned long)addr >= first_start &&
-	    (unsigned long)addr < first_end) {
+	first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
+	first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
+				     pcpu_unit_pages);
+	if ((unsigned long)addr >= first_low &&
+	    (unsigned long)addr < first_high) {
 		for_each_possible_cpu(cpu) {
 			void *start = per_cpu_ptr(base, cpu);
 
@@ -1008,13 +1036,14 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
 	}
 
 	if (in_first_chunk) {
-		if ((unsigned long)addr < VMALLOC_START ||
-		    (unsigned long)addr >= VMALLOC_END)
+		if (!is_vmalloc_addr(addr))
 			return __pa(addr);
 		else
-			return page_to_phys(vmalloc_to_page(addr));
+			return page_to_phys(vmalloc_to_page(addr)) +
+			       offset_in_page(addr);
 	} else
-		return page_to_phys(pcpu_addr_to_page(addr));
+		return page_to_phys(pcpu_addr_to_page(addr)) +
+		       offset_in_page(addr);
 }
 
 /**
@@ -1044,7 +1073,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
 			  __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));
+	ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0);
 	if (!ptr)
 		return NULL;
 	ai = ptr;
@@ -1069,7 +1098,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
  */
 void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
 {
-	free_bootmem(__pa(ai), ai->__ai_size);
+	memblock_free_early(__pa(ai), ai->__ai_size);
 }
 
 /**
@@ -1113,20 +1142,20 @@ static void pcpu_dump_alloc_info(const char *lvl,
 		for (alloc_end += gi->nr_units / upa;
 		     alloc < alloc_end; alloc++) {
 			if (!(alloc % apl)) {
-				printk("\n");
+				printk(KERN_CONT "\n");
 				printk("%spcpu-alloc: ", lvl);
 			}
-			printk("[%0*d] ", group_width, group);
+			printk(KERN_CONT "[%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,
+					printk(KERN_CONT "%0*d ", cpu_width,
 					       gi->cpu_map[unit]);
 				else
-					printk("%s ", empty_str);
+					printk(KERN_CONT "%s ", empty_str);
 		}
 	}
-	printk("\n");
+	printk(KERN_CONT "\n");
 }
 
 /**
@@ -1216,8 +1245,10 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
 #ifdef CONFIG_SMP
 	PCPU_SETUP_BUG_ON(!ai->static_size);
+	PCPU_SETUP_BUG_ON((unsigned long)__per_cpu_start & ~PAGE_MASK);
 #endif
 	PCPU_SETUP_BUG_ON(!base_addr);
+	PCPU_SETUP_BUG_ON((unsigned long)base_addr & ~PAGE_MASK);
 	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);
@@ -1225,14 +1256,18 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
 
 	/* 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]));
+	group_offsets = memblock_virt_alloc(ai->nr_groups *
+					     sizeof(group_offsets[0]), 0);
+	group_sizes = memblock_virt_alloc(ai->nr_groups *
+					   sizeof(group_sizes[0]), 0);
+	unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0);
+	unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0);
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		unit_map[cpu] = UINT_MAX;
-	pcpu_first_unit_cpu = NR_CPUS;
+
+	pcpu_low_unit_cpu = NR_CPUS;
+	pcpu_high_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];
@@ -1252,9 +1287,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 			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;
-			pcpu_last_unit_cpu = cpu;
+			/* determine low/high unit_cpu */
+			if (pcpu_low_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
+				pcpu_low_unit_cpu = cpu;
+			if (pcpu_high_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
+				pcpu_high_unit_cpu = cpu;
 		}
 	}
 	pcpu_nr_units = unit;
@@ -1284,7 +1323,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 * empty chunks.
 	 */
 	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
-	pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
+	pcpu_slot = memblock_virt_alloc(
+			pcpu_nr_slots * sizeof(pcpu_slot[0]), 0);
 	for (i = 0; i < pcpu_nr_slots; i++)
 		INIT_LIST_HEAD(&pcpu_slot[i]);
 
@@ -1295,7 +1335,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 * covers static area + reserved area (mostly used for module
 	 * static percpu allocation).
 	 */
-	schunk = alloc_bootmem(pcpu_chunk_struct_size);
+	schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 	INIT_LIST_HEAD(&schunk->list);
 	schunk->base_addr = base_addr;
 	schunk->map = smap;
@@ -1313,13 +1353,17 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	}
 	schunk->contig_hint = schunk->free_size;
 
-	schunk->map[schunk->map_used++] = -ai->static_size;
+	schunk->map[0] = 1;
+	schunk->map[1] = ai->static_size;
+	schunk->map_used = 1;
 	if (schunk->free_size)
-		schunk->map[schunk->map_used++] = schunk->free_size;
+		schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size);
+	else
+		schunk->map[1] |= 1;
 
 	/* init dynamic chunk if necessary */
 	if (dyn_size) {
-		dchunk = alloc_bootmem(pcpu_chunk_struct_size);
+		dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 		INIT_LIST_HEAD(&dchunk->list);
 		dchunk->base_addr = base_addr;
 		dchunk->map = dmap;
@@ -1328,8 +1372,10 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 		bitmap_fill(dchunk->populated, pcpu_unit_pages);
 
 		dchunk->contig_hint = dchunk->free_size = dyn_size;
-		dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
-		dchunk->map[dchunk->map_used++] = dchunk->free_size;
+		dchunk->map[0] = 1;
+		dchunk->map[1] = pcpu_reserved_chunk_limit;
+		dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1;
+		dchunk->map_used = 2;
 	}
 
 	/* link the first chunk in */
@@ -1343,7 +1389,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 #ifdef CONFIG_SMP
 
-const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
+const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = {
 	[PCPU_FC_AUTO]	= "auto",
 	[PCPU_FC_EMBED]	= "embed",
 	[PCPU_FC_PAGE]	= "page",
@@ -1353,6 +1399,9 @@ enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;
 
 static int __init percpu_alloc_setup(char *str)
 {
+	if (!str)
+		return -EINVAL;
+
 	if (0)
 		/* nada */;
 #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
@@ -1436,7 +1485,7 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
 	/*
 	 * 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
+	 * which can accommodate 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);
@@ -1551,7 +1600,7 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
  * @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
+ * @free_fn: function 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.
@@ -1596,7 +1645,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 	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);
+	areas = memblock_virt_alloc_nopanic(areas_size, 0);
 	if (!areas) {
 		rc = -ENOMEM;
 		goto out_free;
@@ -1618,9 +1667,21 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 			rc = -ENOMEM;
 			goto out_free_areas;
 		}
+		/* kmemleak tracks the percpu allocations separately */
+		kmemleak_free(ptr);
 		areas[group] = ptr;
 
 		base = min(ptr, base);
+	}
+
+	/*
+	 * Copy data and free unused parts.  This should happen after all
+	 * allocations are complete; otherwise, we may end up with
+	 * overlapping groups.
+	 */
+	for (group = 0; group < ai->nr_groups; group++) {
+		struct pcpu_group_info *gi = &ai->groups[group];
+		void *ptr = areas[group];
 
 		for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
 			if (gi->cpu_map[i] == NR_CPUS) {
@@ -1644,10 +1705,10 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 	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) {
+	if (max_distance > VMALLOC_TOTAL * 3 / 4) {
 		pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
-			   "space 0x%lx\n",
-			   max_distance, VMALLOC_END - VMALLOC_START);
+			   "space 0x%lx\n", max_distance,
+			   VMALLOC_TOTAL);
 #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
 		/* and fail if we have fallback */
 		rc = -EINVAL;
@@ -1664,12 +1725,13 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 
 out_free_areas:
 	for (group = 0; group < ai->nr_groups; group++)
-		free_fn(areas[group],
-			ai->groups[group].nr_units * ai->unit_size);
+		if (areas[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);
+		memblock_free_early(__pa(areas), areas_size);
 	return rc;
 }
 #endif /* BUILD_EMBED_FIRST_CHUNK */
@@ -1679,7 +1741,7 @@ out_free:
  * 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
+ * @free_fn: function to free percpu page, always called with PAGE_SIZE
  * @populate_pte_fn: function to populate pte
  *
  * This is a helper to ease setting up page-remapped first percpu
@@ -1717,7 +1779,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
 	/* unaligned allocations can't be freed, round up to page size */
 	pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
 			       sizeof(pages[0]));
-	pages = alloc_bootmem(pages_size);
+	pages = memblock_virt_alloc(pages_size, 0);
 
 	/* allocate pages */
 	j = 0;
@@ -1732,6 +1794,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
 					   "for cpu%u\n", psize_str, cpu);
 				goto enomem;
 			}
+			/* kmemleak tracks the percpu allocations separately */
+			kmemleak_free(ptr);
 			pages[j++] = virt_to_page(ptr);
 		}
 
@@ -1778,7 +1842,7 @@ enomem:
 		free_fn(page_address(pages[j]), PAGE_SIZE);
 	rc = -ENOMEM;
 out_free_ar:
-	free_bootmem(__pa(pages), pages_size);
+	memblock_free_early(__pa(pages), pages_size);
 	pcpu_free_alloc_info(ai);
 	return rc;
 }
@@ -1803,12 +1867,13 @@ 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));
+	return  memblock_virt_alloc_from_nopanic(
+			size, align, __pa(MAX_DMA_ADDRESS));
 }
 
 static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
 {
-	free_bootmem(__pa(ptr), size);
+	memblock_free_early(__pa(ptr), size);
 }
 
 void __init setup_per_cpu_areas(void)
@@ -1851,9 +1916,13 @@ void __init setup_per_cpu_areas(void)
 	void *fc;
 
 	ai = pcpu_alloc_alloc_info(1, 1);
-	fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	fc = memblock_virt_alloc_from_nopanic(unit_size,
+					      PAGE_SIZE,
+					      __pa(MAX_DMA_ADDRESS));
 	if (!ai || !fc)
 		panic("Failed to allocate memory for percpu areas.");
+	/* kmemleak tracks the percpu allocations separately */
+	kmemleak_free(fc);
 
 	ai->dyn_size = unit_size;
 	ai->unit_size = unit_size;
@@ -1888,7 +1957,7 @@ void __init percpu_init_late(void)
 
 		BUILD_BUG_ON(size > PAGE_SIZE);
 
-		map = pcpu_mem_alloc(size);
+		map = pcpu_mem_zalloc(size);
 		BUG_ON(!map);
 
 		spin_lock_irqsave(&pcpu_lock, flags);