summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/linux/percpu.h13
-rw-r--r--init/main.c1
-rw-r--r--mm/percpu.c52
3 files changed, 54 insertions, 12 deletions
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 3ffd05e550de..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
@@ -135,6 +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 */
@@ -148,6 +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 3bdb152f412f..3ff8dd0fb512 100644
--- a/init/main.c
+++ b/init/main.c
@@ -522,6 +522,7 @@ 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 c3e7010c6d71..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;
@@ -1109,7 +1105,9 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
memset(group_map, 0, sizeof(group_map));
memset(group_cnt, 0, sizeof(group_cnt));
- size_sum = PFN_ALIGN(static_size + reserved_size + dyn_size);
+ /* 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;
/*
@@ -1338,7 +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;
size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
struct pcpu_chunk *schunk, *dchunk = NULL;
@@ -1361,14 +1360,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
} 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 */
@@ -1806,3 +1804,33 @@ void __init setup_per_cpu_areas(void)
__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);
+ }
+}