3 files changed, 64 insertions, 42 deletions

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index d3a38d687104..b8b9084527b1 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -45,6 +45,16 @@
 #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
@@ -104,16 +114,11 @@ extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
                                                              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,
@@ -140,6 +145,7 @@ extern bool is_kernel_percpu_address(unsigned long addr);
 #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 */
 
@@ -153,6 +159,8 @@ static inline bool is_kernel_percpu_address(unsigned long addr)
 
 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;
diff --git a/init/main.c b/init/main.c
index a42fdf4aeba9..4ddb53f04f2a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -532,6 +532,7 @@ static void __init mm_init(void)
         page_cgroup_init_flatmem();
         mem_init();
         kmem_cache_init();
+        percpu_init_late();
         pgtable_cache_init();
         vmalloc_init();
 }
diff --git a/mm/percpu.c b/mm/percpu.c
index 6470e7710231..e61dc2cc5873 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -282,6 +282,9 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
  */
 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 {
@@ -392,13 +395,6 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
         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;
         new = NULL;
@@ -604,7 +600,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 {
         struct pcpu_chunk *chunk;
 
-        chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL);
+        chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
         if (!chunk)
                 return NULL;
 
@@ -1013,20 +1009,6 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
                 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
@@ -1085,7 +1067,7 @@ 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: 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
  *
@@ -1103,8 +1085,8 @@ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
  * 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)
 {
@@ -1123,13 +1105,17 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info(
         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);
@@ -1350,7 +1336,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
                                   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;