5 files changed, 14 insertions, 79 deletions

diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 85598f7da407..1602373e539c 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -64,6 +64,7 @@ SECTIONS
                 __initramfs_end = .;
 #endif
                 . = ALIGN(4096);
+                __per_cpu_load = .;
                 __per_cpu_start = .;
                         *(.data.percpu.page_aligned)
                         *(.data.percpu)
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index f45e4e508eca..3765efc5f963 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -213,17 +213,9 @@ SECTIONS
         { *(.data.cacheline_aligned) }
 
   /* Per-cpu data: */
-  percpu : { } :percpu
   . = ALIGN(PERCPU_PAGE_SIZE);
-  __phys_per_cpu_start = .;
-  .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
-        {
-                __per_cpu_start = .;
-                *(.data.percpu.page_aligned)
-                *(.data.percpu)
-                *(.data.percpu.shared_aligned)
-                __per_cpu_end = .;
-        }
+  PERCPU_VADDR(PERCPU_ADDR, :percpu)
+  __phys_per_cpu_start = __per_cpu_load;
   . = __phys_per_cpu_start + PERCPU_PAGE_SIZE;  /* ensure percpu data fits
                                                  * into percpu page size
                                                  */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 295ccc5e86b1..67f07f453385 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -181,14 +181,7 @@ SECTIONS
                 __initramfs_end = .;
         }
 #endif
-        . = ALIGN(PAGE_SIZE);
-        .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
-                __per_cpu_start = .;
-                *(.data.percpu.page_aligned)
-                *(.data.percpu)
-                *(.data.percpu.shared_aligned)
-                __per_cpu_end = .;
-        }
+        PERCPU(PAGE_SIZE)
 
         . = ALIGN(8);
         .machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 8f1d2fbec1d4..aee103b26d01 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -43,14 +43,6 @@
 #else /* ...!ASSEMBLY */
 
 #include <linux/stringify.h>
-#include <asm/sections.h>
-
-#define __addr_to_pcpu_ptr(addr)                                        \
-        (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr  \
-                 + (unsigned long)__per_cpu_start)
-#define __pcpu_ptr_to_addr(ptr)                                         \
-        (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr   \
-                 - (unsigned long)__per_cpu_start)
 
 #ifdef CONFIG_SMP
 #define __percpu_arg(x)         "%%"__stringify(__percpu_seg)":%P" #x
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index efa615f2bf43..400331b50a53 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -233,8 +233,8 @@ proceed:
                 "%zu bytes\n", vm.addr, static_size);
 
         ret = pcpu_setup_first_chunk(pcpur_get_page, static_size,
-                                     PERCPU_FIRST_CHUNK_RESERVE,
-                                     PMD_SIZE, dyn_size, vm.addr, NULL);
+                                     PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
+                                     PMD_SIZE, vm.addr, NULL);
         goto out_free_ar;
 
 enomem:
@@ -257,31 +257,13 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
  * Embedding allocator
  *
  * The first chunk is sized to just contain the static area plus
- * module and dynamic reserves, and allocated as a contiguous area
- * using bootmem allocator and used as-is without being mapped into
- * vmalloc area.  This enables the first chunk to piggy back on the
- * linear physical PMD mapping and doesn't add any additional pressure
- * to TLB.  Note that if the needed size is smaller than the minimum
- * unit size, the leftover is returned to the bootmem allocator.
+ * module and dynamic reserves and embedded into linear physical
+ * mapping so that it can use PMD mapping without additional TLB
+ * pressure.
  */
-static void *pcpue_ptr __initdata;
-static size_t pcpue_size __initdata;
-static size_t pcpue_unit_size __initdata;
-
-static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
-{
-        size_t off = (size_t)pageno << PAGE_SHIFT;
-
-        if (off >= pcpue_size)
-                return NULL;
-
-        return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off);
-}
-
 static ssize_t __init setup_pcpu_embed(size_t static_size)
 {
-        unsigned int cpu;
-        size_t dyn_size;
+        size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
 
         /*
          * If large page isn't supported, there's no benefit in doing
@@ -291,33 +273,8 @@ static ssize_t __init setup_pcpu_embed(size_t static_size)
         if (!cpu_has_pse || pcpu_need_numa())
                 return -EINVAL;
 
-        /* allocate and copy */
-        pcpue_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
-                               PERCPU_DYNAMIC_RESERVE);
-        pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
-        dyn_size = pcpue_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
-
-        pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size,
-                                       PAGE_SIZE);
-        if (!pcpue_ptr)
-                return -ENOMEM;
-
-        for_each_possible_cpu(cpu) {
-                void *ptr = pcpue_ptr + cpu * pcpue_unit_size;
-
-                free_bootmem(__pa(ptr + pcpue_size),
-                             pcpue_unit_size - pcpue_size);
-                memcpy(ptr, __per_cpu_load, static_size);
-        }
-
-        /* we're ready, commit */
-        pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
-                pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size);
-
-        return pcpu_setup_first_chunk(pcpue_get_page, static_size,
-                                      PERCPU_FIRST_CHUNK_RESERVE,
-                                      pcpue_unit_size, dyn_size,
-                                      pcpue_ptr, NULL);
+        return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
+                                      reserve - PERCPU_FIRST_CHUNK_RESERVE, -1);
 }
 
 /*
@@ -375,8 +332,8 @@ static ssize_t __init setup_pcpu_4k(size_t static_size)
                 pcpu4k_nr_static_pages, static_size);
 
         ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size,
-                                     PERCPU_FIRST_CHUNK_RESERVE, -1, -1, NULL,
-                                     pcpu4k_populate_pte);
+                                     PERCPU_FIRST_CHUNK_RESERVE, -1,
+                                     -1, NULL, pcpu4k_populate_pte);
         goto out_free_ar;
 
 enomem: