android_kernel_samsung_msm8976/arch/x86_64/kernel/vmlinux.lds.S
Fenghua Yu 5fb7dc37dc define new percpu interface for shared data
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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 10:04:44 -07:00

226 lines
5.8 KiB
ArmAsm

/* ld script to make x86-64 Linux kernel
* Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
*/
#define LOAD_OFFSET __START_KERNEL_map
#include <asm-generic/vmlinux.lds.h>
#include <asm/page.h>
#undef i386 /* in case the preprocessor is a 32bit one */
OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
OUTPUT_ARCH(i386:x86-64)
ENTRY(phys_startup_64)
jiffies_64 = jiffies;
_proxy_pda = 1;
PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
data PT_LOAD FLAGS(7); /* RWE */
user PT_LOAD FLAGS(7); /* RWE */
data.init PT_LOAD FLAGS(7); /* RWE */
note PT_NOTE FLAGS(4); /* R__ */
}
SECTIONS
{
. = __START_KERNEL;
phys_startup_64 = startup_64 - LOAD_OFFSET;
_text = .; /* Text and read-only data */
.text : AT(ADDR(.text) - LOAD_OFFSET) {
/* First the code that has to be first for bootstrapping */
*(.bootstrap.text)
_stext = .;
/* Then the rest */
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
KPROBES_TEXT
*(.fixup)
*(.gnu.warning)
} :text = 0x9090
/* out-of-line lock text */
.text.lock : AT(ADDR(.text.lock) - LOAD_OFFSET) { *(.text.lock) }
_etext = .; /* End of text section */
. = ALIGN(16); /* Exception table */
__start___ex_table = .;
__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { *(__ex_table) }
__stop___ex_table = .;
BUG_TABLE
RODATA
. = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */
/* Data */
.data : AT(ADDR(.data) - LOAD_OFFSET) {
DATA_DATA
CONSTRUCTORS
} :data
_edata = .; /* End of data section */
. = ALIGN(PAGE_SIZE);
. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
.data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
*(.data.cacheline_aligned)
}
. = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
.data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
*(.data.read_mostly)
}
#define VSYSCALL_ADDR (-10*1024*1024)
#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
. = VSYSCALL_ADDR;
.vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { *(.vsyscall_0) } :user
__vsyscall_0 = VSYSCALL_VIRT_ADDR;
. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
.vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) }
. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
.vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))
{ *(.vsyscall_gtod_data) }
vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
.vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
{ *(.vsyscall_1) }
.vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
{ *(.vsyscall_2) }
.vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
vgetcpu_mode = VVIRT(.vgetcpu_mode);
. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
.jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
jiffies = VVIRT(.jiffies);
.vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3))
{ *(.vsyscall_3) }
. = VSYSCALL_VIRT_ADDR + 4096;
#undef VSYSCALL_ADDR
#undef VSYSCALL_PHYS_ADDR
#undef VSYSCALL_VIRT_ADDR
#undef VLOAD_OFFSET
#undef VLOAD
#undef VVIRT_OFFSET
#undef VVIRT
. = ALIGN(8192); /* init_task */
.data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
*(.data.init_task)
}:data.init
. = ALIGN(4096);
.data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
*(.data.page_aligned)
}
/* might get freed after init */
. = ALIGN(4096);
__smp_alt_begin = .;
__smp_alt_instructions = .;
.smp_altinstructions : AT(ADDR(.smp_altinstructions) - LOAD_OFFSET) {
*(.smp_altinstructions)
}
__smp_alt_instructions_end = .;
. = ALIGN(8);
__smp_locks = .;
.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
*(.smp_locks)
}
__smp_locks_end = .;
.smp_altinstr_replacement : AT(ADDR(.smp_altinstr_replacement) - LOAD_OFFSET) {
*(.smp_altinstr_replacement)
}
. = ALIGN(4096);
__smp_alt_end = .;
. = ALIGN(4096); /* Init code and data */
__init_begin = .;
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
_sinittext = .;
*(.init.text)
_einittext = .;
}
__initdata_begin = .;
.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) { *(.init.data) }
__initdata_end = .;
. = ALIGN(16);
__setup_start = .;
.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) { *(.init.setup) }
__setup_end = .;
__initcall_start = .;
.initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
INITCALLS
}
__initcall_end = .;
__con_initcall_start = .;
.con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
*(.con_initcall.init)
}
__con_initcall_end = .;
SECURITY_INIT
. = ALIGN(8);
__alt_instructions = .;
.altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
*(.altinstructions)
}
__alt_instructions_end = .;
.altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
*(.altinstr_replacement)
}
/* .exit.text is discard at runtime, not link time, to deal with references
from .altinstructions and .eh_frame */
.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { *(.exit.text) }
.exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) { *(.exit.data) }
#ifdef CONFIG_BLK_DEV_INITRD
. = ALIGN(4096);
__initramfs_start = .;
.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { *(.init.ramfs) }
__initramfs_end = .;
#endif
PERCPU(4096)
. = ALIGN(4096);
__init_end = .;
. = ALIGN(4096);
__nosave_begin = .;
.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { *(.data.nosave) }
. = ALIGN(4096);
__nosave_end = .;
__bss_start = .; /* BSS */
.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
*(.bss.page_aligned)
*(.bss)
}
__bss_stop = .;
_end = . ;
/* Sections to be discarded */
/DISCARD/ : {
*(.exitcall.exit)
*(.eh_frame)
}
STABS_DEBUG
DWARF_DEBUG
}