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: (46 commits)
  powerpc64: convert to dynamic percpu allocator
  sparc64: use embedding percpu first chunk allocator
  percpu: kill lpage first chunk allocator
  x86,percpu: use embedding for 64bit NUMA and page for 32bit NUMA
  percpu: update embedding first chunk allocator to handle sparse units
  percpu: use group information to allocate vmap areas sparsely
  vmalloc: implement pcpu_get_vm_areas()
  vmalloc: separate out insert_vmalloc_vm()
  percpu: add chunk->base_addr
  percpu: add pcpu_unit_offsets[]
  percpu: introduce pcpu_alloc_info and pcpu_group_info
  percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward
  percpu: add @align to pcpu_fc_alloc_fn_t
  percpu: make @dyn_size mandatory for pcpu_setup_first_chunk()
  percpu: drop @static_size from first chunk allocators
  percpu: generalize first chunk allocator selection
  percpu: build first chunk allocators selectively
  percpu: rename 4k first chunk allocator to page
  percpu: improve boot messages
  percpu: fix pcpu_reclaim() locking
  ...

Fix trivial conflict as by Tejun Heo in kernel/sched.c

5 files changed, 53 insertions, 24 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d00131ca0835..2c42e1526d03 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -49,6 +49,9 @@ config GENERIC_HARDIRQS_NO__DO_IRQ
 config HAVE_SETUP_PER_CPU_AREA
         def_bool PPC64
 
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+        def_bool PPC64
+
 config IRQ_PER_CPU
         bool
         default y
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1f6816003ebe..aa6e4500635f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -57,6 +57,7 @@
 #include <asm/cache.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
+#include <asm/mmu-hash64.h>
 #include <asm/firmware.h>
 #include <asm/xmon.h>
 #include <asm/udbg.h>
@@ -569,25 +570,53 @@ void cpu_die(void)
 }
 
 #ifdef CONFIG_SMP
-void __init setup_per_cpu_areas(void)
+#define PCPU_DYN_SIZE           ()
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-        int i;
-        unsigned long size;
-        char *ptr;
-
-        /* Copy section for each CPU (we discard the original) */
-        size = ALIGN(__per_cpu_end - __per_cpu_start, PAGE_SIZE);
-#ifdef CONFIG_MODULES
-        if (size < PERCPU_ENOUGH_ROOM)
-                size = PERCPU_ENOUGH_ROOM;
-#endif
+        return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+                                    __pa(MAX_DMA_ADDRESS));
+}
 
-        for_each_possible_cpu(i) {
-                ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+        free_bootmem(__pa(ptr), size);
+}
 
-                paca[i].data_offset = ptr - __per_cpu_start;
-                memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-        }
+static int pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+        if (cpu_to_node(from) == cpu_to_node(to))
+                return LOCAL_DISTANCE;
+        else
+                return REMOTE_DISTANCE;
+}
+
+void __init setup_per_cpu_areas(void)
+{
+        const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
+        size_t atom_size;
+        unsigned long delta;
+        unsigned int cpu;
+        int rc;
+
+        /*
+         * Linear mapping is one of 4K, 1M and 16M.  For 4K, no need
+         * to group units.  For larger mappings, use 1M atom which
+         * should be large enough to contain a number of units.
+         */
+        if (mmu_linear_psize == MMU_PAGE_4K)
+                atom_size = PAGE_SIZE;
+        else
+                atom_size = 1 << 20;
+
+        rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
+                                    pcpu_fc_alloc, pcpu_fc_free);
+        if (rc < 0)
+                panic("cannot initialize percpu area (err=%d)", rc);
+
+        delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+        for_each_possible_cpu(cpu)
+                paca[cpu].data_offset = delta + pcpu_unit_offsets[cpu];
 }
 #endif
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8ef8a14abc95..244e3658983c 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -37,12 +37,6 @@ jiffies = jiffies_64 + 4;
 #endif
 SECTIONS
 {
-        /* Sections to be discarded. */
-        /DISCARD/ : {
-        *(.exitcall.exit)
-        EXIT_DATA
-        }
-
         . = KERNELBASE;
 
 /*
@@ -298,4 +292,7 @@ SECTIONS
         . = ALIGN(PAGE_SIZE);
         _end = . ;
         PROVIDE32 (end = .);
+
+        /* Sections to be discarded. */
+        DISCARDS
 }
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index ab5fb48b3e90..687fddaa24c5 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -31,7 +31,7 @@ struct stab_entry {
 
 #define NR_STAB_CACHE_ENTRIES 8
 static DEFINE_PER_CPU(long, stab_cache_ptr);
-static DEFINE_PER_CPU(long, stab_cache[NR_STAB_CACHE_ENTRIES]);
+static DEFINE_PER_CPU(long [NR_STAB_CACHE_ENTRIES], stab_cache);
 
 /*
  * Create a segment table entry for the given esid/vsid pair.
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index f6e04bcc70ef..51ffde40af2b 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -37,7 +37,7 @@
   */
 
 #define MSG_COUNT 4
-static DEFINE_PER_CPU(unsigned int, ps3_ipi_virqs[MSG_COUNT]);
+static DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs);
 
 static void do_message_pass(int target, int msg)
 {