percpu: introduce DEFINE_PER_CPU_PAGE_ALIGNED() macro

While examining holes in percpu section I found this :

c05f5000 D per_cpu__current_task
c05f5000 D __per_cpu_start
c05f5004 D per_cpu__cpu_number
c05f5008 D per_cpu__irq_regs
c05f500c d per_cpu__cpu_devices
c05f5040 D per_cpu__cyc2ns

<Big Hole of about 4000 bytes>

c05f6000 d per_cpu__cpuid4_info
c05f6004 d per_cpu__cache_kobject
c05f6008 d per_cpu__index_kobject

<Big Hole of about 4000 bytes>

c05f7000 D per_cpu__gdt_page

This is because gdt_page is a percpu variable, defined with
a page alignement, and linker is doing its job, two times because of .o
nesting in the build process.

I introduced a new macro DEFINE_PER_CPU_PAGE_ALIGNED() to avoid
wasting this space. All page aligned variables (only one at this time)
are put in a separate
subsection .data.percpu.page_aligned, at the very begining of percpu zone.

Before patch , on a x86_32 machine :

.data.percpu                30232   3227471872
.data.percpu                22168   3227471872

Thats 8064 bytes saved for each CPU.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

4 files changed, 10 insertions, 1 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d0463a946247..b2f54fafb8bc 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -21,7 +21,7 @@
 
 #include "cpu.h"
 
-DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
         [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
         [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
         [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index ce5ed083a1e9..0f7c29a8c4ea 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -189,6 +189,7 @@ SECTIONS
   . = 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 = .;
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f054778e916c..69e5c1182fde 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -348,6 +348,7 @@
         . = ALIGN(align);                                               \
         __per_cpu_start = .;                                            \
         .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {          \
+                *(.data.percpu.page_aligned)                            \
                 *(.data.percpu)                                         \
                 *(.data.percpu.shared_aligned)                          \
         }                                                               \
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 4cdd393e71e1..2edacc8e6b8b 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -23,12 +23,19 @@
         __attribute__((__section__(SHARED_ALIGNED_SECTION)))            \
         PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name             \
         ____cacheline_aligned_in_smp
+
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)                 \
+        __attribute__((__section__(".data.percpu.page_aligned")))       \
+        PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
 #else
 #define DEFINE_PER_CPU(type, name)                                      \
         PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
 
 #define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)                     \
         DEFINE_PER_CPU(type, name)
+
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)               \
+        DEFINE_PER_CPU(type, name)
 #endif
 
 #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)