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: allow limited allocation before slab is online
percpu: make @dyn_size always mean min dyn_size in first chunk init functions

include/linux/percpu.h

···
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
 
 /*
+ * Percpu allocator can serve percpu allocations before slab is
+ * initialized which allows slab to depend on the percpu allocator.
+ * The following two parameters decide how much resource to
+ * preallocate for this.  Keep PERCPU_DYNAMIC_RESERVE equal to or
+ * larger than PERCPU_DYNAMIC_EARLY_SIZE.
+ */
+#define PERCPU_DYNAMIC_EARLY_SLOTS	128
+#define PERCPU_DYNAMIC_EARLY_SIZE	(12 << 10)
+
+/*
  * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
  * back on the first chunk for dynamic percpu allocation if arch is
  * manually allocating and mapping it for faster access (as a part of
···
 							     int nr_units);
 extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai);
 
-extern 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);
-
 extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 					 void *base_addr);
 
 #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
-extern int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
+extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 				size_t atom_size,
 				pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
 				pcpu_fc_alloc_fn_t alloc_fn,
···
 #ifndef 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 */
 
···
 }
 
 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)
 {

init/main.c

···
 	page_cgroup_init_flatmem();
 	mem_init();
 	kmem_cache_init();
+	percpu_init_late();
 	pgtable_cache_init();
 	vmalloc_init();
 }

mm/percpu.c

···
  */
 static void *pcpu_mem_alloc(size_t size)
 {
+	if (WARN_ON_ONCE(!slab_is_available()))
+		return NULL;
+
 	if (size <= PAGE_SIZE)
 		return kzalloc(size, GFP_KERNEL);
 	else {
···
 
 	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)
-		old = chunk->map;
 
 	chunk->map_alloc = new_alloc;
 	chunk->map = new;
···
 {
 	struct pcpu_chunk *chunk;
 
-	chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL);
+	chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
 	if (!chunk)
 		return NULL;
 
···
 		return page_to_phys(pcpu_addr_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
···
 /**
  * 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
+ * @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
  *
···
  * 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,
+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)
 {
···
 	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.
 	 */
-	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);
···
 				  void *base_addr)
 {
 	static char cpus_buf[4096] __initdata;
-	static int smap[2], dmap[2];
+	static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
+	static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
 	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;
···
 } while (0)
 
 	/* sanity checks */
-	BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
-		     ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
 	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);
+	PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
 	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
 
 	/* process group information and build config tables accordingly */
···
 /**
  * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
  * @reserved_size: the size of reserved percpu area in bytes
- * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @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
  * @alloc_fn: function to allocate percpu page
···
  * 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,
- * @dyn_size is just big enough to fill page alignment after static
- * and reserved areas.
+ * @dyn_size specifies the minimum dynamic area size.
  *
  * If the needed size is smaller than the minimum or specified unit
  * size, the leftover is returned using @free_fn.
···
  * RETURNS:
  * 0 on success, -errno on failure.
  */
-int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
+int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 				  size_t atom_size,
 				  pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
 				  pcpu_fc_alloc_fn_t alloc_fn,
···
 
 	snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10);
 
-	ai = pcpu_build_alloc_info(reserved_size, -1, PAGE_SIZE, NULL);
+	ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL);
 	if (IS_ERR(ai))
 		return PTR_ERR(ai);
 	BUG_ON(ai->nr_groups != 1);
···
 		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
 }
 #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+
+/*
+ * First and reserved chunks are initialized with temporary allocation
+ * map in initdata so that they can be used before slab is online.
+ * This function is called after slab is brought up and replaces those
+ * with properly allocated maps.
+ */
+void __init percpu_init_late(void)
+{
+	struct pcpu_chunk *target_chunks[] =
+		{ pcpu_first_chunk, pcpu_reserved_chunk, NULL };
+	struct pcpu_chunk *chunk;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; (chunk = target_chunks[i]); i++) {
+		int *map;
+		const size_t size = PERCPU_DYNAMIC_EARLY_SLOTS * sizeof(map[0]);
+
+		BUILD_BUG_ON(size > PAGE_SIZE);
+
+		map = pcpu_mem_alloc(size);
+		BUG_ON(!map);
+
+		spin_lock_irqsave(&pcpu_lock, flags);
+		memcpy(map, chunk->map, size);
+		chunk->map = map;
+		spin_unlock_irqrestore(&pcpu_lock, flags);
+	}
+}