mirror of
https://github.com/brain-hackers/u-boot-brain
synced 2024-07-09 20:56:16 +09:00
114c86d826
For ARM architecture, enable the CONFIG_USE_ARCH_MEMSET/MEMCPY, will highly increase the memset/memcpy performance. This is able thanks to the ARM multiple register instructions. Unfortunatelly the relocation is done without the cache enabled, so it takes some time, but zeroing the BSS memory takes much more longer, especially for the configs with big static buffers. A quick test confirms, that the boot time improvement after using the arch memcpy for relocation has no significant meaning. The same test confirms that enable the memset for zeroing BSS, reduces the boot time. So this patch enables the arch memset for zeroing the BSS after the relocation process. For ARM boards, this can be enabled in board configs by defining: 'CONFIG_USE_ARCH_MEMSET'. This was tested on Trats2. A quick test with trace. Boot time from start to main_loop() entry: - ~1384ms - before this change - ~888ms - after this change Signed-off-by: Przemyslaw Marczak <p.marczak@samsung.com> Reviewed-by: Simon Glass <sjg@chromium.org> Cc: Albert Aribaud <albert.u.boot@aribaud.net> Cc: Tom Rini <trini@konsulko.com>
156 lines
4.6 KiB
ArmAsm
156 lines
4.6 KiB
ArmAsm
/*
|
|
* crt0 - C-runtime startup Code for ARM U-Boot
|
|
*
|
|
* Copyright (c) 2012 Albert ARIBAUD <albert.u.boot@aribaud.net>
|
|
*
|
|
* SPDX-License-Identifier: GPL-2.0+
|
|
*/
|
|
|
|
#include <config.h>
|
|
#include <asm-offsets.h>
|
|
#include <linux/linkage.h>
|
|
|
|
/*
|
|
* This file handles the target-independent stages of the U-Boot
|
|
* start-up where a C runtime environment is needed. Its entry point
|
|
* is _main and is branched into from the target's start.S file.
|
|
*
|
|
* _main execution sequence is:
|
|
*
|
|
* 1. Set up initial environment for calling board_init_f().
|
|
* This environment only provides a stack and a place to store
|
|
* the GD ('global data') structure, both located in some readily
|
|
* available RAM (SRAM, locked cache...). In this context, VARIABLE
|
|
* global data, initialized or not (BSS), are UNAVAILABLE; only
|
|
* CONSTANT initialized data are available.
|
|
*
|
|
* 2. Call board_init_f(). This function prepares the hardware for
|
|
* execution from system RAM (DRAM, DDR...) As system RAM may not
|
|
* be available yet, , board_init_f() must use the current GD to
|
|
* store any data which must be passed on to later stages. These
|
|
* data include the relocation destination, the future stack, and
|
|
* the future GD location.
|
|
*
|
|
* (the following applies only to non-SPL builds)
|
|
*
|
|
* 3. Set up intermediate environment where the stack and GD are the
|
|
* ones allocated by board_init_f() in system RAM, but BSS and
|
|
* initialized non-const data are still not available.
|
|
*
|
|
* 4. Call relocate_code(). This function relocates U-Boot from its
|
|
* current location into the relocation destination computed by
|
|
* board_init_f().
|
|
*
|
|
* 5. Set up final environment for calling board_init_r(). This
|
|
* environment has BSS (initialized to 0), initialized non-const
|
|
* data (initialized to their intended value), and stack in system
|
|
* RAM. GD has retained values set by board_init_f(). Some CPUs
|
|
* have some work left to do at this point regarding memory, so
|
|
* call c_runtime_cpu_setup.
|
|
*
|
|
* 6. Branch to board_init_r().
|
|
*/
|
|
|
|
/*
|
|
* entry point of crt0 sequence
|
|
*/
|
|
|
|
ENTRY(_main)
|
|
|
|
/*
|
|
* Set up initial C runtime environment and call board_init_f(0).
|
|
*/
|
|
|
|
#if defined(CONFIG_SPL_BUILD) && defined(CONFIG_SPL_STACK)
|
|
ldr sp, =(CONFIG_SPL_STACK)
|
|
#else
|
|
ldr sp, =(CONFIG_SYS_INIT_SP_ADDR)
|
|
#endif
|
|
bic sp, sp, #7 /* 8-byte alignment for ABI compliance */
|
|
mov r2, sp
|
|
sub sp, sp, #GD_SIZE /* allocate one GD above SP */
|
|
bic sp, sp, #7 /* 8-byte alignment for ABI compliance */
|
|
mov r9, sp /* GD is above SP */
|
|
mov r1, sp
|
|
mov r0, #0
|
|
clr_gd:
|
|
cmp r1, r2 /* while not at end of GD */
|
|
strlo r0, [r1] /* clear 32-bit GD word */
|
|
addlo r1, r1, #4 /* move to next */
|
|
blo clr_gd
|
|
#if defined(CONFIG_SYS_MALLOC_F_LEN)
|
|
sub sp, sp, #CONFIG_SYS_MALLOC_F_LEN
|
|
str sp, [r9, #GD_MALLOC_BASE]
|
|
#endif
|
|
/* mov r0, #0 not needed due to above code */
|
|
bl board_init_f
|
|
|
|
#if ! defined(CONFIG_SPL_BUILD)
|
|
|
|
/*
|
|
* Set up intermediate environment (new sp and gd) and call
|
|
* relocate_code(addr_moni). Trick here is that we'll return
|
|
* 'here' but relocated.
|
|
*/
|
|
|
|
ldr sp, [r9, #GD_START_ADDR_SP] /* sp = gd->start_addr_sp */
|
|
bic sp, sp, #7 /* 8-byte alignment for ABI compliance */
|
|
ldr r9, [r9, #GD_BD] /* r9 = gd->bd */
|
|
sub r9, r9, #GD_SIZE /* new GD is below bd */
|
|
|
|
adr lr, here
|
|
ldr r0, [r9, #GD_RELOC_OFF] /* r0 = gd->reloc_off */
|
|
add lr, lr, r0
|
|
ldr r0, [r9, #GD_RELOCADDR] /* r0 = gd->relocaddr */
|
|
b relocate_code
|
|
here:
|
|
/*
|
|
* now relocate vectors
|
|
*/
|
|
|
|
bl relocate_vectors
|
|
|
|
/* Set up final (full) environment */
|
|
|
|
bl c_runtime_cpu_setup /* we still call old routine here */
|
|
#endif
|
|
#if !defined(CONFIG_SPL_BUILD) || defined(CONFIG_SPL_FRAMEWORK)
|
|
# ifdef CONFIG_SPL_BUILD
|
|
/* Use a DRAM stack for the rest of SPL, if requested */
|
|
bl spl_relocate_stack_gd
|
|
cmp r0, #0
|
|
movne sp, r0
|
|
# endif
|
|
ldr r0, =__bss_start /* this is auto-relocated! */
|
|
|
|
#ifdef CONFIG_USE_ARCH_MEMSET
|
|
ldr r3, =__bss_end /* this is auto-relocated! */
|
|
mov r1, #0x00000000 /* prepare zero to clear BSS */
|
|
|
|
subs r2, r3, r0 /* r2 = memset len */
|
|
bl memset
|
|
#else
|
|
ldr r1, =__bss_end /* this is auto-relocated! */
|
|
mov r2, #0x00000000 /* prepare zero to clear BSS */
|
|
|
|
clbss_l:cmp r0, r1 /* while not at end of BSS */
|
|
strlo r2, [r0] /* clear 32-bit BSS word */
|
|
addlo r0, r0, #4 /* move to next */
|
|
blo clbss_l
|
|
#endif
|
|
|
|
#if ! defined(CONFIG_SPL_BUILD)
|
|
bl coloured_LED_init
|
|
bl red_led_on
|
|
#endif
|
|
/* call board_init_r(gd_t *id, ulong dest_addr) */
|
|
mov r0, r9 /* gd_t */
|
|
ldr r1, [r9, #GD_RELOCADDR] /* dest_addr */
|
|
/* call board_init_r */
|
|
ldr pc, =board_init_r /* this is auto-relocated! */
|
|
|
|
/* we should not return here. */
|
|
#endif
|
|
|
|
ENDPROC(_main)
|