6 files changed, 36 insertions, 198 deletions

diff --git a/mm/Makefile b/mm/Makefile
index ebf849042ed3..82131d0f8d85 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -34,11 +34,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 obj-$(CONFIG_SMP) += percpu.o
-else
-obj-$(CONFIG_SMP) += allocpercpu.o
-endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
deleted file mode 100644
index df34ceae0c67..000000000000
--- a/mm/allocpercpu.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * linux/mm/allocpercpu.c
- *
- * Separated from slab.c August 11, 2006 Christoph Lameter
- */
-#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
-#endif
-
-/**
- * percpu_depopulate - depopulate per-cpu data for given cpu
- * @__pdata: per-cpu data to depopulate
- * @cpu: depopulate per-cpu data for this cpu
- *
- * Depopulating per-cpu data for a cpu going offline would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- */
-static void percpu_depopulate(void *__pdata, int cpu)
-{
-        struct percpu_data *pdata = __percpu_disguise(__pdata);
-
-        kfree(pdata->ptrs[cpu]);
-        pdata->ptrs[cpu] = NULL;
-}
-
-/**
- * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
- * @__pdata: per-cpu data to depopulate
- * @mask: depopulate per-cpu data for cpu's selected through mask bits
- */
-static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask)
-{
-        int cpu;
-        for_each_cpu_mask_nr(cpu, *mask)
-                percpu_depopulate(__pdata, cpu);
-}
-
-#define percpu_depopulate_mask(__pdata, mask) \
-        __percpu_depopulate_mask((__pdata), &(mask))
-
-/**
- * percpu_populate - populate per-cpu data for given cpu
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @cpu: populate per-data for this cpu
- *
- * Populating per-cpu data for a cpu coming online would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- * Per-cpu object is populated with zeroed buffer.
- */
-static void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
-{
-        struct percpu_data *pdata = __percpu_disguise(__pdata);
-        int node = cpu_to_node(cpu);
-
-        /*
-         * We should make sure each CPU gets private memory.
-         */
-        size = roundup(size, cache_line_size());
-
-        BUG_ON(pdata->ptrs[cpu]);
-        if (node_online(node))
-                pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node);
-        else
-                pdata->ptrs[cpu] = kzalloc(size, gfp);
-        return pdata->ptrs[cpu];
-}
-
-/**
- * percpu_populate_mask - populate per-cpu data for more cpu's
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @mask: populate per-cpu data for cpu's selected through mask bits
- *
- * Per-cpu objects are populated with zeroed buffers.
- */
-static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
-                                  cpumask_t *mask)
-{
-        cpumask_t populated;
-        int cpu;
-
-        cpus_clear(populated);
-        for_each_cpu_mask_nr(cpu, *mask)
-                if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
-                        __percpu_depopulate_mask(__pdata, &populated);
-                        return -ENOMEM;
-                } else
-                        cpu_set(cpu, populated);
-        return 0;
-}
-
-#define percpu_populate_mask(__pdata, size, gfp, mask) \
-        __percpu_populate_mask((__pdata), (size), (gfp), &(mask))
-
-/**
- * alloc_percpu - initial setup of per-cpu data
- * @size: size of per-cpu object
- * @align: alignment
- *
- * Allocate dynamic percpu area.  Percpu objects are populated with
- * zeroed buffers.
- */
-void *__alloc_percpu(size_t size, size_t align)
-{
-        /*
-         * We allocate whole cache lines to avoid false sharing
-         */
-        size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size());
-        void *pdata = kzalloc(sz, GFP_KERNEL);
-        void *__pdata = __percpu_disguise(pdata);
-
-        /*
-         * Can't easily make larger alignment work with kmalloc.  WARN
-         * on it.  Larger alignment should only be used for module
-         * percpu sections on SMP for which this path isn't used.
-         */
-        WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-
-        if (unlikely(!pdata))
-                return NULL;
-        if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL,
-                                           &cpu_possible_map)))
-                return __pdata;
-        kfree(pdata);
-        return NULL;
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-/**
- * free_percpu - final cleanup of per-cpu data
- * @__pdata: object to clean up
- *
- * We simply clean up any per-cpu object left. No need for the client to
- * track and specify through a bis mask which per-cpu objects are to free.
- */
-void free_percpu(void *__pdata)
-{
-        if (unlikely(!__pdata))
-                return;
-        __percpu_depopulate_mask(__pdata, cpu_possible_mask);
-        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/percpu.c b/mm/percpu.c
index 5adfc268b408..442010cc91c6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -46,8 +46,6 @@
  *
  * To use this allocator, arch code should do the followings.
  *
- * - 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
  *   different from the default
@@ -74,6 +72,7 @@
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 #define PCPU_SLOT_BASE_SHIFT            5       /* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC              16      /* start a map with 16 ents */
@@ -1302,6 +1301,27 @@ void free_percpu(void *ptr)
 }
 EXPORT_SYMBOL_GPL(free_percpu);
 
+/**
+ * per_cpu_ptr_to_phys - convert translated percpu address to physical address
+ * @addr: the address to be converted to physical address
+ *
+ * Given @addr which is dereferenceable address obtained via one of
+ * percpu access macros, this function translates it into its physical
+ * address.  The caller is responsible for ensuring @addr stays valid
+ * until this function finishes.
+ *
+ * RETURNS:
+ * The physical address for @addr.
+ */
+phys_addr_t per_cpu_ptr_to_phys(void *addr)
+{
+        if ((unsigned long)addr < VMALLOC_START ||
+                        (unsigned long)addr >= VMALLOC_END)
+                return __pa(addr);
+        else
+                return page_to_phys(vmalloc_to_page(addr));
+}
+
 static inline size_t pcpu_calc_fc_sizes(size_t static_size,
                                         size_t reserved_size,
                                         ssize_t *dyn_sizep)
diff --git a/mm/slab.c b/mm/slab.c
index a6c9166996a9..29b09599af7c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -697,7 +697,7 @@ static inline void init_lock_keys(void)
 static DEFINE_MUTEX(cache_chain_mutex);
 static struct list_head cache_chain;
 
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
+static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
@@ -838,7 +838,7 @@ __setup("noaliencache", noaliencache_setup);
  * objects freed on different nodes from which they were allocated) and the
  * flushing of remote pcps by calling drain_node_pages.
  */
-static DEFINE_PER_CPU(unsigned long, reap_node);
+static DEFINE_PER_CPU(unsigned long, slab_reap_node);
 
 static void init_reap_node(int cpu)
 {
@@ -848,17 +848,17 @@ static void init_reap_node(int cpu)
         if (node == MAX_NUMNODES)
                 node = first_node(node_online_map);
 
-        per_cpu(reap_node, cpu) = node;
+        per_cpu(slab_reap_node, cpu) = node;
 }
 
 static void next_reap_node(void)
 {
-        int node = __get_cpu_var(reap_node);
+        int node = __get_cpu_var(slab_reap_node);
 
         node = next_node(node, node_online_map);
         if (unlikely(node >= MAX_NUMNODES))
                 node = first_node(node_online_map);
-        __get_cpu_var(reap_node) = node;
+        __get_cpu_var(slab_reap_node) = node;
 }
 
 #else
@@ -875,7 +875,7 @@ static void next_reap_node(void)
  */
 static void __cpuinit start_cpu_timer(int cpu)
 {
-        struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
+        struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
 
         /*
          * When this gets called from do_initcalls via cpucache_init(),
@@ -1039,7 +1039,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
  */
 static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
 {
-        int node = __get_cpu_var(reap_node);
+        int node = __get_cpu_var(slab_reap_node);
 
         if (l3->alien) {
                 struct array_cache *ac = l3->alien[node];
@@ -1300,9 +1300,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
                  * anything expensive but will only modify reap_work
                  * and reschedule the timer.
                 */
-                cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+                cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu));
                 /* Now the cache_reaper is guaranteed to be not running. */
-                per_cpu(reap_work, cpu).work.func = NULL;
+                per_cpu(slab_reap_work, cpu).work.func = NULL;
                 break;
         case CPU_DOWN_FAILED:
         case CPU_DOWN_FAILED_FROZEN:
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 0f551a4a44cd..9b08d790df6f 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -761,7 +761,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
         spin_lock(&vbq->lock);
         list_add(&vb->free_list, &vbq->free);
         spin_unlock(&vbq->lock);
-        put_cpu_var(vmap_cpu_blocks);
+        put_cpu_var(vmap_block_queue);
 
         return vb;
 }
@@ -826,7 +826,7 @@ again:
                 }
                 spin_unlock(&vb->lock);
         }
-        put_cpu_var(vmap_cpu_blocks);
+        put_cpu_var(vmap_block_queue);
         rcu_read_unlock();
 
         if (!addr) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c81321f9feec..dad2327e4580 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -883,11 +883,10 @@ static void vmstat_update(struct work_struct *w)
 
 static void __cpuinit start_cpu_timer(int cpu)
 {
-        struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
+        struct delayed_work *work = &per_cpu(vmstat_work, cpu);
 
-        INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
-        schedule_delayed_work_on(cpu, vmstat_work,
-                                 __round_jiffies_relative(HZ, cpu));
+        INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
+        schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
 }
 
 /*