[patch 055/209] define new percpu interface for shared data

[patch 055/209] define new percpu interface for shared data

[akpm]

From: Fenghua Yu <fenghua.yu@intel.com>

per cpu data section contains two types of data.  One set which is
exclusively accessed by the local cpu and the other set which is per cpu,
but also shared by remote cpus.  In the current kernel, these two sets are
not clearely separated out.  This can potentially cause the same data
cacheline shared between the two sets of data, which will result in
unnecessary bouncing of the cacheline between cpus.

One way to fix the problem is to cacheline align the remotely accessed per
cpu data, both at the beginning and at the end.  Because of the padding at
both ends, this will likely cause some memory wastage and also the
interface to achieve this is not clean.

This patch:

Moves the remotely accessed per cpu data (which is currently marked
as ____cacheline_aligned_in_smp) into a different section, where all the data
elements are cacheline aligned. And as such, this differentiates the local
only data and remotely accessed data cleanly.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: <linux-arch@vger.kernel.org>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/alpha/kernel/vmlinux.lds.S   |    5 +----
 arch/arm/kernel/vmlinux.lds.S     |    1 +
 arch/cris/arch-v32/vmlinux.lds.S  |    5 +----
 arch/frv/kernel/vmlinux.lds.S     |    5 +----
 arch/i386/kernel/vmlinux.lds.S    |    1 +
 arch/ia64/kernel/vmlinux.lds.S    |    1 +
 arch/m32r/kernel/vmlinux.lds.S    |    5 +----
 arch/mips/kernel/vmlinux.lds.S    |    5 +----
 arch/parisc/kernel/vmlinux.lds.S  |    7 +++----
 arch/powerpc/kernel/vmlinux.lds.S |    1 +
 arch/ppc/kernel/vmlinux.lds.S     |    5 +----
 arch/s390/kernel/vmlinux.lds.S    |    5 +----
 arch/sh/kernel/vmlinux.lds.S      |    5 +----
 arch/sh64/kernel/vmlinux.lds.S    |    5 ++++-
 arch/sparc/kernel/vmlinux.lds.S   |    5 +----
 arch/sparc64/kernel/vmlinux.lds.S |    6 ++----
 arch/x86_64/kernel/vmlinux.lds.S  |    6 ++----
 arch/xtensa/kernel/vmlinux.lds.S  |    5 +----
 include/asm-generic/percpu.h      |    8 ++++++++
 include/asm-generic/vmlinux.lds.h |    8 ++++++++
 include/asm-i386/percpu.h         |    5 +++++
 include/asm-ia64/percpu.h         |   10 ++++++++++
 include/asm-powerpc/percpu.h      |    7 +++++++
 include/asm-s390/percpu.h         |    7 +++++++
 include/asm-sparc64/percpu.h      |    7 +++++++
 include/asm-x86_64/percpu.h       |    7 +++++++
 26 files changed, 84 insertions(+), 53 deletions(-)

diff -puN arch/alpha/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/alpha/kernel/vmlinux.lds.S
--- a/arch/alpha/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/alpha/kernel/vmlinux.lds.S
@@ -69,10 +69,7 @@ SECTIONS
   . = ALIGN(8);
   SECURITY_INIT
 
-  . = ALIGN(8192);
-  __per_cpu_start = .;
-  .data.percpu : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(8192)
 
   . = ALIGN(2*8192);
   __init_end = .;
diff -puN arch/arm/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/arm/kernel/vmlinux.lds.S
--- a/arch/arm/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/arm/kernel/vmlinux.lds.S
@@ -66,6 +66,7 @@ SECTIONS
 		. = ALIGN(4096);
 		__per_cpu_start = .;
 			*(.data.percpu)
+			*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;
 #ifndef CONFIG_XIP_KERNEL
 		__init_begin = _stext;
diff -puN arch/cris/arch-v32/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/cris/arch-v32/vmlinux.lds.S
--- a/arch/cris/arch-v32/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/cris/arch-v32/vmlinux.lds.S
@@ -91,10 +91,7 @@ SECTIONS
 	}
 	SECURITY_INIT
 
-	. =  ALIGN (8192);
-	__per_cpu_start = .;
-	.data.percpu  : { *(.data.percpu) }
-	__per_cpu_end = .;
+	PERCPU(8192)
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	.init.ramfs : {
diff -puN arch/frv/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/frv/kernel/vmlinux.lds.S
--- a/arch/frv/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/frv/kernel/vmlinux.lds.S
@@ -57,10 +57,7 @@ SECTIONS
   __alt_instructions_end = .;
  .altinstr_replacement : { *(.altinstr_replacement) }
 
-  . = ALIGN(4096);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(4096)
 
 #ifdef CONFIG_BLK_DEV_INITRD
   . = ALIGN(4096);
diff -puN arch/i386/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/i386/kernel/vmlinux.lds.S
--- a/arch/i386/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/i386/kernel/vmlinux.lds.S
@@ -181,6 +181,7 @@ SECTIONS
   .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
 	__per_cpu_start = .;
 	*(.data.percpu)
+	*(.data.percpu.shared_aligned)
 	__per_cpu_end = .;
   }
   . = ALIGN(4096);
diff -puN arch/ia64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/ia64/kernel/vmlinux.lds.S
--- a/arch/ia64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/ia64/kernel/vmlinux.lds.S
@@ -206,6 +206,7 @@ SECTIONS
 	{
 		__per_cpu_start = .;
 		*(.data.percpu)
+		*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;
 	}
   . = __phys_per_cpu_start + PERCPU_PAGE_SIZE;	/* ensure percpu data fits
diff -puN arch/m32r/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/m32r/kernel/vmlinux.lds.S
--- a/arch/m32r/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/m32r/kernel/vmlinux.lds.S
@@ -110,10 +110,7 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(4096);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(4096)
   . = ALIGN(4096);
   __init_end = .;
   /* freed after init ends here */
diff -puN arch/mips/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/mips/kernel/vmlinux.lds.S
--- a/arch/mips/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/mips/kernel/vmlinux.lds.S
@@ -119,10 +119,7 @@ SECTIONS
   .init.ramfs : { *(.init.ramfs) }
   __initramfs_end = .;
 #endif
-  . = ALIGN(_PAGE_SIZE);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(_PAGE_SIZE)
   . = ALIGN(_PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff -puN arch/parisc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/parisc/kernel/vmlinux.lds.S
--- a/arch/parisc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/parisc/kernel/vmlinux.lds.S
@@ -181,10 +181,9 @@ SECTIONS
   .init.ramfs : { *(.init.ramfs) }
   __initramfs_end = .;
 #endif
-  . = ALIGN(ASM_PAGE_SIZE);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+
+  PERCPU(ASM_PAGE_SIZE)
+
   . = ALIGN(ASM_PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff -puN arch/powerpc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/powerpc/kernel/vmlinux.lds.S
--- a/arch/powerpc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/powerpc/kernel/vmlinux.lds.S
@@ -144,6 +144,7 @@ SECTIONS
 	.data.percpu : {
 		__per_cpu_start = .;
 		*(.data.percpu)
+		*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;
 	}
 
diff -puN arch/ppc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/ppc/kernel/vmlinux.lds.S
--- a/arch/ppc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/ppc/kernel/vmlinux.lds.S
@@ -130,10 +130,7 @@ SECTIONS
   __ftr_fixup : { *(__ftr_fixup) }
   __stop___ftr_fixup = .;
 
-  . = ALIGN(4096);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(4096)
 
 #ifdef CONFIG_BLK_DEV_INITRD
   . = ALIGN(4096);
diff -puN arch/s390/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/s390/kernel/vmlinux.lds.S
--- a/arch/s390/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/s390/kernel/vmlinux.lds.S
@@ -107,10 +107,7 @@ SECTIONS
   . = ALIGN(2);
   __initramfs_end = .;
 #endif
-  . = ALIGN(4096);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(4096)
   . = ALIGN(4096);
   __init_end = .;
   /* freed after init ends here */
diff -puN arch/sh/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/sh/kernel/vmlinux.lds.S
--- a/arch/sh/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/sh/kernel/vmlinux.lds.S
@@ -60,10 +60,7 @@ SECTIONS
   . = ALIGN(PAGE_SIZE);
   __nosave_end = .;
 
-  . = ALIGN(PAGE_SIZE);
-  __per_cpu_start = .;
-  .data.percpu : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(PAGE_SIZE)
   .data.cacheline_aligned : { *(.data.cacheline_aligned) }
 
   _edata = .;			/* End of data section */
diff -puN arch/sh64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/sh64/kernel/vmlinux.lds.S
--- a/arch/sh64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/sh64/kernel/vmlinux.lds.S
@@ -87,7 +87,10 @@ SECTIONS
 
   . = ALIGN(PAGE_SIZE);
   __per_cpu_start = .;
-  .data.percpu : C_PHYS(.data.percpu) { *(.data.percpu) }
+  .data.percpu : C_PHYS(.data.percpu) {
+	*(.data.percpu)
+	*(.data.percpu.shared_aligned)
+  }
   __per_cpu_end = . ;
   .data.cacheline_aligned : C_PHYS(.data.cacheline_aligned) { *(.data.cacheline_aligned) }
 
diff -puN arch/sparc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/sparc/kernel/vmlinux.lds.S
--- a/arch/sparc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/sparc/kernel/vmlinux.lds.S
@@ -65,10 +65,7 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(4096);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(4096)
   . = ALIGN(4096);
   __init_end = .;
   . = ALIGN(32);
diff -puN arch/sparc64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/sparc64/kernel/vmlinux.lds.S
--- a/arch/sparc64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/sparc64/kernel/vmlinux.lds.S
@@ -90,10 +90,8 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(PAGE_SIZE);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(PAGE_SIZE)
+
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
   __bss_start = .;
diff -puN arch/x86_64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/x86_64/kernel/vmlinux.lds.S
--- a/arch/x86_64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/x86_64/kernel/vmlinux.lds.S
@@ -194,10 +194,8 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(4096);
-  __per_cpu_start = .;
-  .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(4096)
+
   . = ALIGN(4096);
   __init_end = .;
 
diff -puN arch/xtensa/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/xtensa/kernel/vmlinux.lds.S
--- a/arch/xtensa/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
+++ a/arch/xtensa/kernel/vmlinux.lds.S
@@ -190,10 +190,7 @@ SECTIONS
   __initramfs_end = .;
 #endif
 
-  . = ALIGN(4096);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  PERCPU(4096)
 
 
   /* We need this dummy segment here */
diff -puN include/asm-generic/percpu.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-generic/percpu.h
--- a/include/asm-generic/percpu.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-generic/percpu.h
@@ -14,6 +14,11 @@ extern unsigned long __per_cpu_offset[NR
 #define DEFINE_PER_CPU(type, name) \
     __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
 
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name				\
+    ____cacheline_aligned_in_smp
+
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu) (*({				\
 	extern int simple_identifier_##var(void);	\
@@ -34,6 +39,9 @@ do {								\
 #define DEFINE_PER_CPU(type, name) \
     __typeof__(type) per_cpu__##name
 
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
+    DEFINE_PER_CPU(type, name)
+
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
 #define __raw_get_cpu_var(var)			per_cpu__##var
diff -puN include/asm-generic/vmlinux.lds.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-generic/vmlinux.lds.h
--- a/include/asm-generic/vmlinux.lds.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-generic/vmlinux.lds.h
@@ -245,3 +245,11 @@
   	*(.initcall7.init)						\
   	*(.initcall7s.init)
 
+#define PERCPU(align)							\
+	. = ALIGN(align);						\
+	__per_cpu_start = .;						\
+	.data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {		\
+		*(.data.percpu)						\
+		*(.data.percpu.shared_aligned)				\
+	}								\
+	__per_cpu_end = .;
diff -puN include/asm-i386/percpu.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-i386/percpu.h
--- a/include/asm-i386/percpu.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-i386/percpu.h
@@ -54,6 +54,11 @@ extern unsigned long __per_cpu_offset[];
 #define DEFINE_PER_CPU(type, name) \
     __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
 
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name				\
+    ____cacheline_aligned_in_smp
+
 /* We can use this directly for local CPU (faster). */
 DECLARE_PER_CPU(unsigned long, this_cpu_off);
 
diff -puN include/asm-ia64/percpu.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-ia64/percpu.h
--- a/include/asm-ia64/percpu.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-ia64/percpu.h
@@ -29,6 +29,16 @@
 	__attribute__((__section__(".data.percpu")))		\
 	__SMALL_ADDR_AREA __typeof__(type) per_cpu__##name
 
+#ifdef CONFIG_SMP
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)			\
+	__attribute__((__section__(".data.percpu.shared_aligned")))	\
+	__SMALL_ADDR_AREA __typeof__(type) per_cpu__##name		\
+	____cacheline_aligned_in_smp
+#else
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
+	DEFINE_PER_CPU(type, name)
+#endif
+
 /*
  * Pretty much a literal copy of asm-generic/percpu.h, except that percpu_modcopy() is an
  * external routine, to avoid include-hell.
diff -puN include/asm-powerpc/percpu.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-powerpc/percpu.h
--- a/include/asm-powerpc/percpu.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-powerpc/percpu.h
@@ -20,6 +20,11 @@
 #define DEFINE_PER_CPU(type, name) \
     __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
 
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name				\
+    ____cacheline_aligned_in_smp
+
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
 #define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
@@ -40,6 +45,8 @@ extern void setup_per_cpu_areas(void);
 
 #define DEFINE_PER_CPU(type, name) \
     __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
+    DEFINE_PER_CPU(type, name)
 
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
diff -puN include/asm-s390/percpu.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-s390/percpu.h
--- a/include/asm-s390/percpu.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-s390/percpu.h
@@ -41,6 +41,11 @@ extern unsigned long __per_cpu_offset[NR
     __attribute__((__section__(".data.percpu"))) \
     __typeof__(type) per_cpu__##name
 
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name				\
+    ____cacheline_aligned_in_smp
+
 #define __get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
 #define __raw_get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
 #define per_cpu(var,cpu) __reloc_hide(var,__per_cpu_offset[cpu])
@@ -59,6 +64,8 @@ do {								\
 
 #define DEFINE_PER_CPU(type, name) \
     __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
+    DEFINE_PER_CPU(type, name)
 
 #define __get_cpu_var(var) __reloc_hide(var,0)
 #define __raw_get_cpu_var(var) __reloc_hide(var,0)
diff -puN include/asm-sparc64/percpu.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-sparc64/percpu.h
--- a/include/asm-sparc64/percpu.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-sparc64/percpu.h
@@ -18,6 +18,11 @@ extern unsigned long __per_cpu_shift;
 #define DEFINE_PER_CPU(type, name) \
     __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
 
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name				\
+    ____cacheline_aligned_in_smp
+
 register unsigned long __local_per_cpu_offset asm("g5");
 
 /* var is in discarded region: offset to particular copy we want */
@@ -38,6 +43,8 @@ do {								\
 #define real_setup_per_cpu_areas()		do { } while (0)
 #define DEFINE_PER_CPU(type, name) \
     __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
+    DEFINE_PER_CPU(type, name)
 
 #define per_cpu(var, cpu)			(*((void)cpu, &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
diff -puN include/asm-x86_64/percpu.h~define-new-percpu-interface-for-shared-data-version-4 include/asm-x86_64/percpu.h
--- a/include/asm-x86_64/percpu.h~define-new-percpu-interface-for-shared-data-version-4
+++ a/include/asm-x86_64/percpu.h
@@ -20,6 +20,11 @@
 #define DEFINE_PER_CPU(type, name) \
     __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
 
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
+    __attribute__((__section__(".data.percpu.shared_aligned"))) \
+    __typeof__(type) per_cpu__##name				\
+    ____cacheline_internodealigned_in_smp
+
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu) (*({				\
 	extern int simple_identifier_##var(void);	\
@@ -46,6 +51,8 @@ extern void setup_per_cpu_areas(void);
 
 #define DEFINE_PER_CPU(type, name) \
     __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
+    DEFINE_PER_CPU(type, name)
 
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
_

Re: [patch 055/209] define new percpu interface for shared data

[Sam Ravnborg]

On Thu, Jul 19, 2007 at 01:48:12AM -0700, akpm@linux-foundation.org wrote:
> 
> Moves the remotely accessed per cpu data (which is currently marked
> as ____cacheline_aligned_in_smp) into a different section, where all the data
> elements are cacheline aligned. And as such, this differentiates the local
> only data and remotely accessed data cleanly.
> 
> --- a/arch/arm/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
> +++ a/arch/arm/kernel/vmlinux.lds.S
> @@ -66,6 +66,7 @@ SECTIONS
>  		. = ALIGN(4096);
>  		__per_cpu_start = .;
>  			*(.data.percpu)
> +			*(.data.percpu.shared_aligned)
>  		__per_cpu_end = .;
>  #ifndef CONFIG_XIP_KERNEL
>  		__init_begin = _stext;

Why is PERCPU not suitable for arm?


> diff -puN arch/i386/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/i386/kernel/vmlinux.lds.S
> --- a/arch/i386/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
> +++ a/arch/i386/kernel/vmlinux.lds.S
> @@ -181,6 +181,7 @@ SECTIONS
>    .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
>  	__per_cpu_start = .;
>  	*(.data.percpu)
> +	*(.data.percpu.shared_aligned)
>  	__per_cpu_end = .;
>    }
>    . = ALIGN(4096);
Ditto for i386

> --- a/arch/ia64/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
> +++ a/arch/ia64/kernel/vmlinux.lds.S
> @@ -206,6 +206,7 @@ SECTIONS
>  	{
>  		__per_cpu_start = .;
>  		*(.data.percpu)
> +		*(.data.percpu.shared_aligned)
>  		__per_cpu_end = .;
>  	}
>    . = __phys_per_cpu_start + PERCPU_PAGE_SIZE;	/* ensure percpu data fits
Ditto

> diff -puN arch/powerpc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4 arch/powerpc/kernel/vmlinux.lds.S
> --- a/arch/powerpc/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
> +++ a/arch/powerpc/kernel/vmlinux.lds.S
> @@ -144,6 +144,7 @@ SECTIONS
>  	.data.percpu : {
>  		__per_cpu_start = .;
>  		*(.data.percpu)
> +		*(.data.percpu.shared_aligned)
>  		__per_cpu_end = .;
>  	}
Ditto

	Sam

Re: [patch 055/209] define new percpu interface for shared data

[Russell King]

On Thu, Jul 19, 2007 at 10:02:53PM +0200, Sam Ravnborg wrote:
> On Thu, Jul 19, 2007 at 01:48:12AM -0700, akpm@linux-foundation.org wrote:
> > 
> > Moves the remotely accessed per cpu data (which is currently marked
> > as ____cacheline_aligned_in_smp) into a different section, where all the data
> > elements are cacheline aligned. And as such, this differentiates the local
> > only data and remotely accessed data cleanly.
> > 
> > --- a/arch/arm/kernel/vmlinux.lds.S~define-new-percpu-interface-for-shared-data-version-4
> > +++ a/arch/arm/kernel/vmlinux.lds.S
> > @@ -66,6 +66,7 @@ SECTIONS
> >  		. = ALIGN(4096);
> >  		__per_cpu_start = .;
> >  			*(.data.percpu)
> > +			*(.data.percpu.shared_aligned)
> >  		__per_cpu_end = .;
> >  #ifndef CONFIG_XIP_KERNEL
> >  		__init_begin = _stext;
> 
> Why is PERCPU not suitable for arm?

You can't put an output section inside an output section.

-- 
Russell King
 Linux kernel    2.6 ARM Linux   - http://www.arm.linux.org.uk/
 maintainer of:

RE: [patch 055/209] define new percpu interface for shared data

[Yu, Fenghua]

> Why is PERCPU not suitable for arm?
Can't put an output section inside an output section.

>Ditto for i386
__per_cpu_start and __per_cpu_end are defined as relative symbols. But
__per_cpu_start and __per_cpu_end are defined as relative symbols in
PERCPU(). Using PERCPU for i386 won't work for relocated kernel.

>Ditto
Same. __per_cpu_start and __per_cpu_end are relative symbols.

>Ditto
Same. __per_cpu_start and __per_cpu_end are relative symbols. They are
different from PERCPU definition.

Overall, PERCPU() macro make code cleaner. But above definitions can not
fit into the macro.

Thanks.

-Fenghua