7 files changed, 77 insertions, 10 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 5e0bd6426693..c77c6487552f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -33,7 +33,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 obj-$(CONFIG_SMP) += percpu.o
 else
 obj-$(CONFIG_SMP) += allocpercpu.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
index dfdee6a47359..df34ceae0c67 100644
--- a/mm/allocpercpu.c
+++ b/mm/allocpercpu.c
@@ -5,6 +5,8 @@
  */
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/bootmem.h>
+#include <asm/sections.h>
 
 #ifndef cache_line_size
 #define cache_line_size()       L1_CACHE_BYTES
@@ -147,3 +149,29 @@ void free_percpu(void *__pdata)
         kfree(__percpu_disguise(__pdata));
 }
 EXPORT_SYMBOL_GPL(free_percpu);
+
+/*
+ * Generic percpu area setup.
+ */
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+
+EXPORT_SYMBOL(__per_cpu_offset);
+
+void __init setup_per_cpu_areas(void)
+{
+        unsigned long size, i;
+        char *ptr;
+        unsigned long nr_possible_cpus = num_possible_cpus();
+
+        /* Copy section for each CPU (we discard the original) */
+        size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
+        ptr = alloc_bootmem_pages(size * nr_possible_cpus);
+
+        for_each_possible_cpu(i) {
+                __per_cpu_offset[i] = ptr - __per_cpu_start;
+                memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+                ptr += size;
+        }
+}
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c
index d5292fc6f523..177a5169bbde 100644
--- a/mm/kmemleak-test.c
+++ b/mm/kmemleak-test.c
@@ -36,7 +36,7 @@ struct test_node {
 };
 
 static LIST_HEAD(test_list);
-static DEFINE_PER_CPU(void *, test_pointer);
+static DEFINE_PER_CPU(void *, kmemleak_test_pointer);
 
 /*
  * Some very simple testing. This function needs to be extended for
@@ -86,9 +86,9 @@ static int __init kmemleak_test_init(void)
         }
 
         for_each_possible_cpu(i) {
-                per_cpu(test_pointer, i) = kmalloc(129, GFP_KERNEL);
+                per_cpu(kmemleak_test_pointer, i) = kmalloc(129, GFP_KERNEL);
                 pr_info("kmemleak: kmalloc(129) = %p\n",
-                        per_cpu(test_pointer, i));
+                        per_cpu(kmemleak_test_pointer, i));
         }
 
         return 0;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7687879253b9..3c7f5e1afe5f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -610,6 +610,8 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite)
         }
 }
 
+static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
+
 /**
  * balance_dirty_pages_ratelimited_nr - balance dirty memory state
  * @mapping: address_space which was dirtied
@@ -627,7 +629,6 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite)
 void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
                                         unsigned long nr_pages_dirtied)
 {
-        static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
         unsigned long ratelimit;
         unsigned long *p;
 
@@ -640,7 +641,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
          * tasks in balance_dirty_pages(). Period.
          */
         preempt_disable();
-        p =  &__get_cpu_var(ratelimits);
+        p =  &__get_cpu_var(bdp_ratelimits);
         *p += nr_pages_dirtied;
         if (unlikely(*p >= ratelimit)) {
                 *p = 0;
diff --git a/mm/percpu.c b/mm/percpu.c
index b70f2acd8853..b14984566f5a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -43,7 +43,7 @@
  *
  * To use this allocator, arch code should do the followings.
  *
- * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ * - 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
@@ -1275,3 +1275,41 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
                                       reserved_size, dyn_size,
                                       pcpue_unit_size, pcpue_ptr, NULL);
 }
+
+/*
+ * Generic percpu area setup.
+ *
+ * The embedding helper is used because its behavior closely resembles
+ * the original non-dynamic generic percpu area setup.  This is
+ * important because many archs have addressing restrictions and might
+ * fail if the percpu area is located far away from the previous
+ * location.  As an added bonus, in non-NUMA cases, embedding is
+ * generally a good idea TLB-wise because percpu area can piggy back
+ * on the physical linear memory mapping which uses large page
+ * mappings on applicable archs.
+ */
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+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;
+
+        /*
+         * 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, -1);
+        if (unit_size < 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;
+}
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
diff --git a/mm/quicklist.c b/mm/quicklist.c
index e66d07d1b4ff..6eedf7e473d1 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -19,7 +19,7 @@
 #include <linux/module.h>
 #include <linux/quicklist.h>
 
-DEFINE_PER_CPU(struct quicklist, quicklist)[CONFIG_NR_QUICK];
+DEFINE_PER_CPU(struct quicklist [CONFIG_NR_QUICK], quicklist);
 
 #define FRACTION_OF_NODE_MEM    16
 
diff --git a/mm/slub.c b/mm/slub.c
index 819f056b39c6..ffc895cc3a68 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2092,8 +2092,8 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
  */
 #define NR_KMEM_CACHE_CPU 100
 
-static DEFINE_PER_CPU(struct kmem_cache_cpu,
-                                kmem_cache_cpu)[NR_KMEM_CACHE_CPU];
+static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU],
+                      kmem_cache_cpu);
 
 static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
 static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);