8 files changed, 135 insertions, 96 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:
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 54a968b4b924..ee5615d65211 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -107,10 +107,14 @@ typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr);
 
 extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
                                 size_t static_size, size_t reserved_size,
-                                ssize_t unit_size, ssize_t dyn_size,
+                                ssize_t dyn_size, ssize_t unit_size,
                                 void *base_addr,
                                 pcpu_populate_pte_fn_t populate_pte_fn);
 
+extern ssize_t __init pcpu_embed_first_chunk(
+                                size_t static_size, size_t reserved_size,
+                                ssize_t dyn_size, ssize_t unit_size);
+
 /*
  * Use this to get to a cpu's version of the per-cpu object
  * dynamically allocated. Non-atomic access to the current CPU's
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
index 3653c570232b..1882923bc706 100644
--- a/mm/allocpercpu.c
+++ b/mm/allocpercpu.c
@@ -120,7 +120,7 @@ void *__alloc_percpu(size_t size, size_t align)
          * 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 > __alignof__(unsigned long long));
+        WARN_ON_ONCE(align > SMP_CACHE_BYTES);
 
         if (unlikely(!pdata))
                 return NULL;
diff --git a/mm/percpu.c b/mm/percpu.c
index bfe6a3afaf45..1aa5d8fbca12 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -46,7 +46,8 @@
  * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
  *
  * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
- *   regular address to percpu pointer and back
+ *   regular address to percpu pointer and back if they need to be
+ *   different from the default
  *
  * - use pcpu_setup_first_chunk() during percpu area initialization to
  *   setup the first chunk containing the kernel static percpu area
@@ -67,11 +68,24 @@
 #include <linux/workqueue.h>
 
 #include <asm/cacheflush.h>
+#include <asm/sections.h>
 #include <asm/tlbflush.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 */
 
+/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
+#ifndef __addr_to_pcpu_ptr
+#define __addr_to_pcpu_ptr(addr)                                        \
+        (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr  \
+                 + (unsigned long)__per_cpu_start)
+#endif
+#ifndef __pcpu_ptr_to_addr
+#define __pcpu_ptr_to_addr(ptr)                                         \
+        (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr   \
+                 - (unsigned long)__per_cpu_start)
+#endif
+
 struct pcpu_chunk {
         struct list_head        list;           /* linked to pcpu_slot lists */
         struct rb_node          rb_node;        /* key is chunk->vm->addr */
@@ -1013,8 +1027,8 @@ EXPORT_SYMBOL_GPL(free_percpu);
  * @get_page_fn: callback to fetch page pointer
  * @static_size: the size of static percpu area in bytes
  * @reserved_size: the size of reserved percpu area in bytes
- * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
  * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
  * @base_addr: mapped address, NULL for auto
  * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary
  *
@@ -1039,14 +1053,14 @@ EXPORT_SYMBOL_GPL(free_percpu);
  * limited offset range for symbol relocations to guarantee module
  * percpu symbols fall inside the relocatable range.
  *
+ * @dyn_size, if non-negative, determines the number of bytes
+ * available for dynamic allocation in the first chunk.  Specifying
+ * non-negative value makes percpu leave alone the area beyond
+ * @static_size + @reserved_size + @dyn_size.
+ *
  * @unit_size, if non-negative, specifies unit size and must be
  * aligned to PAGE_SIZE and equal to or larger than @static_size +
- * @reserved_size + @dyn_size.
- *
- * @dyn_size, if non-negative, limits the number of bytes available
- * for dynamic allocation in the first chunk.  Specifying non-negative
- * value make percpu leave alone the area beyond @static_size +
- * @reserved_size + @dyn_size.
+ * @reserved_size + if non-negative, @dyn_size.
  *
  * Non-null @base_addr means that the caller already allocated virtual
  * region for the first chunk and mapped it.  percpu must not mess
@@ -1069,12 +1083,14 @@ EXPORT_SYMBOL_GPL(free_percpu);
  */
 size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
                                      size_t static_size, size_t reserved_size,
-                                     ssize_t unit_size, ssize_t dyn_size,
+                                     ssize_t dyn_size, ssize_t unit_size,
                                      void *base_addr,
                                      pcpu_populate_pte_fn_t populate_pte_fn)
 {
         static struct vm_struct first_vm;
         static int smap[2], dmap[2];
+        size_t size_sum = static_size + reserved_size +
+                          (dyn_size >= 0 ? dyn_size : 0);
         struct pcpu_chunk *schunk, *dchunk = NULL;
         unsigned int cpu;
         int nr_pages;
@@ -1085,20 +1101,18 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
                      ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
         BUG_ON(!static_size);
         if (unit_size >= 0) {
-                BUG_ON(unit_size < static_size + reserved_size +
-                                   (dyn_size >= 0 ? dyn_size : 0));
+                BUG_ON(unit_size < size_sum);
                 BUG_ON(unit_size & ~PAGE_MASK);
-        } else {
-                BUG_ON(dyn_size >= 0);
+                BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE);
+        } else
                 BUG_ON(base_addr);
-        }
         BUG_ON(base_addr && populate_pte_fn);
 
         if (unit_size >= 0)
                 pcpu_unit_pages = unit_size >> PAGE_SHIFT;
         else
                 pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT,
-                                        PFN_UP(static_size + reserved_size));
+                                        PFN_UP(size_sum));
 
         pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
         pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
@@ -1224,3 +1238,89 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
         pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
         return pcpu_unit_size;
 }
+
+/*
+ * Embedding first chunk setup helper.
+ */
+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);
+}
+
+/**
+ * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
+ * @static_size: the size of static percpu area in bytes
+ * @reserved_size: the size of reserved percpu area in bytes
+ * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
+ *
+ * This is a helper to ease setting up embedded first percpu chunk and
+ * can be called where pcpu_setup_first_chunk() is expected.
+ *
+ * If this function is used to setup the first chunk, it is 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 mapping which often uses larger
+ * page size.
+ *
+ * When @dyn_size is positive, dynamic area might be larger than
+ * specified to fill page alignment.  Also, when @dyn_size is auto,
+ * @dyn_size does not fill the whole first chunk but only what's
+ * necessary for page alignment after static and reserved areas.
+ *
+ * If the needed size is smaller than the minimum or specified unit
+ * size, the leftover is returned to the bootmem allocator.
+ *
+ * RETURNS:
+ * The determined pcpu_unit_size which can be used to initialize
+ * percpu access on success, -errno on failure.
+ */
+ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
+                                      ssize_t dyn_size, ssize_t unit_size)
+{
+        unsigned int cpu;
+
+        /* determine parameters and allocate */
+        pcpue_size = PFN_ALIGN(static_size + reserved_size +
+                               (dyn_size >= 0 ? dyn_size : 0));
+        if (dyn_size != 0)
+                dyn_size = pcpue_size - static_size - reserved_size;
+
+        if (unit_size >= 0) {
+                BUG_ON(unit_size < pcpue_size);
+                pcpue_unit_size = unit_size;
+        } else
+                pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
+
+        pcpue_ptr = __alloc_bootmem_nopanic(
+                                        num_possible_cpus() * pcpue_unit_size,
+                                        PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+        if (!pcpue_ptr)
+                return -ENOMEM;
+
+        /* return the leftover and copy */
+        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,
+                                      reserved_size, dyn_size,
+                                      pcpue_unit_size, pcpue_ptr, NULL);
+}