1
linux/arch/x86/kernel/vmlinux_64.lds.S
Tejun Heo 1a51e3a0ae x86: fold pda into percpu area on SMP
[ Based on original patch from Christoph Lameter and Mike Travis. ]

Currently pdas and percpu areas are allocated separately.  %gs points
to local pda and percpu area can be reached using pda->data_offset.
This patch folds pda into percpu area.

Due to strange gcc requirement, pda needs to be at the beginning of
the percpu area so that pda->stack_canary is at %gs:40.  To achieve
this, a new percpu output section macro - PERCPU_VADDR_PREALLOC() - is
added and used to reserve pda sized chunk at the start of the percpu
area.

After this change, for boot cpu, %gs first points to pda in the
data.init area and later during setup_per_cpu_areas() gets updated to
point to the actual pda.  This means that setup_per_cpu_areas() need
to reload %gs for CPU0 while clearing pda area for other cpus as cpu0
already has modified it when control reaches setup_per_cpu_areas().

This patch also removes now unnecessary get_local_pda() and its call
sites.

A lot of this patch is taken from Mike Travis' "x86_64: Fold pda into
per cpu area" patch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-16 14:19:46 +01:00

264 lines
6.6 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/asm-offsets.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 */
#ifdef CONFIG_SMP
percpu PT_LOAD FLAGS(7); /* RWE */
#endif
note PT_NOTE FLAGS(0); /* ___ */
}
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 */
*(.text.head)
_stext = .;
/* Then the rest */
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
_etext = .; /* End of text section */
} :text = 0x9090
NOTES :text :note
. = ALIGN(16); /* Exception table */
__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
__start___ex_table = .;
*(__ex_table)
__stop___ex_table = .;
} :text = 0x9090
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_clock : AT(VLOAD(.vsyscall_clock))
{ *(.vsyscall_clock) }
vsyscall_clock = VVIRT(.vsyscall_clock);
.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 + PAGE_SIZE;
#undef VSYSCALL_ADDR
#undef VSYSCALL_PHYS_ADDR
#undef VSYSCALL_VIRT_ADDR
#undef VLOAD_OFFSET
#undef VLOAD
#undef VVIRT_OFFSET
#undef VVIRT
. = ALIGN(THREAD_SIZE); /* init_task */
.data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
*(.data.init_task)
}:data.init
. = ALIGN(PAGE_SIZE);
.data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
*(.data.page_aligned)
}
/* might get freed after init */
. = ALIGN(PAGE_SIZE);
__smp_alt_begin = .;
__smp_locks = .;
.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
*(.smp_locks)
}
__smp_locks_end = .;
. = ALIGN(PAGE_SIZE);
__smp_alt_end = .;
. = ALIGN(PAGE_SIZE); /* Init code and data */
__init_begin = .;
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
_sinittext = .;
INIT_TEXT
_einittext = .;
}
.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
__initdata_begin = .;
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 = .;
__x86_cpu_dev_start = .;
.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
*(.x86_cpu_dev.init)
}
__x86_cpu_dev_end = .;
SECURITY_INIT
. = ALIGN(8);
.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
__parainstructions = .;
*(.parainstructions)
__parainstructions_end = .;
}
. = 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(PAGE_SIZE);
__initramfs_start = .;
.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { *(.init.ramfs) }
__initramfs_end = .;
#endif
#ifdef CONFIG_SMP
/*
* percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
* output PHDR, so the next output section - __data_nosave - should
* switch it back to data.init. Also, pda should be at the head of
* percpu area. Preallocate it.
*/
. = ALIGN(PAGE_SIZE);
PERCPU_VADDR_PREALLOC(0, :percpu, pda_size)
#else
PERCPU(PAGE_SIZE)
#endif
. = ALIGN(PAGE_SIZE);
__init_end = .;
. = ALIGN(PAGE_SIZE);
__nosave_begin = .;
.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
*(.data.nosave)
} :data.init /* switch back to data.init, see PERCPU_VADDR() above */
. = ALIGN(PAGE_SIZE);
__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
}
/*
* Build-time check on the image size:
*/
ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
"kernel image bigger than KERNEL_IMAGE_SIZE")