arm-trusted-firmware/bl32/sp_min/sp_min.ld.S

212 lines
5.9 KiB
ArmAsm
Raw Normal View History

/*
Introduce unified API to zero memory Introduce zeromem_dczva function on AArch64 that can handle unaligned addresses and make use of DC ZVA instruction to zero a whole block at a time. This zeroing takes place directly in the cache to speed it up without doing external memory access. Remove the zeromem16 function on AArch64 and replace it with an alias to zeromem. This zeromem16 function is now deprecated. Remove the 16-bytes alignment constraint on __BSS_START__ in firmware-design.md as it is now not mandatory anymore (it used to comply with zeromem16 requirements). Change the 16-bytes alignment constraints in SP min's linker script to a 8-bytes alignment constraint as the AArch32 zeromem implementation is now more efficient on 8-bytes aligned addresses. Introduce zero_normalmem and zeromem helpers in platform agnostic header that are implemented this way: * AArch32: * zero_normalmem: zero using usual data access * zeromem: alias for zero_normalmem * AArch64: * zero_normalmem: zero normal memory using DC ZVA instruction (needs MMU enabled) * zeromem: zero using usual data access Usage guidelines: in most cases, zero_normalmem should be preferred. There are 2 scenarios where zeromem (or memset) must be used instead: * Code that must run with MMU disabled (which means all memory is considered device memory for data accesses). * Code that fills device memory with null bytes. Optionally, the following rule can be applied if performance is important: * Code zeroing small areas (few bytes) that are not secrets should use memset to take advantage of compiler optimizations. Note: Code zeroing security-related critical information should use zero_normalmem/zeromem instead of memset to avoid removal by compilers' optimizations in some cases or misbehaving versions of GCC. Fixes ARM-software/tf-issues#408 Change-Id: Iafd9663fc1070413c3e1904e54091cf60effaa82 Signed-off-by: Douglas Raillard <douglas.raillard@arm.com>
2016-12-02 13:51:54 +00:00
* Copyright (c) 2016-2017, ARM Limited and Contributors. All rights reserved.
*
* SPDX-License-Identifier: BSD-3-Clause
*/
#include <platform_def.h>
OUTPUT_FORMAT(elf32-littlearm)
OUTPUT_ARCH(arm)
ENTRY(sp_min_vector_table)
MEMORY {
RAM (rwx): ORIGIN = BL32_BASE, LENGTH = BL32_LIMIT - BL32_BASE
}
SECTIONS
{
. = BL32_BASE;
ASSERT(. == ALIGN(4096),
"BL32_BASE address is not aligned on a page boundary.")
#if SEPARATE_CODE_AND_RODATA
.text . : {
__TEXT_START__ = .;
*entrypoint.o(.text*)
*(.text*)
*(.vectors)
. = NEXT(4096);
__TEXT_END__ = .;
} >RAM
.rodata . : {
__RODATA_START__ = .;
*(.rodata*)
/* Ensure 4-byte alignment for descriptors and ensure inclusion */
. = ALIGN(4);
__RT_SVC_DESCS_START__ = .;
KEEP(*(rt_svc_descs))
__RT_SVC_DESCS_END__ = .;
/*
* Ensure 4-byte alignment for cpu_ops so that its fields are also
* aligned. Also ensure cpu_ops inclusion.
*/
. = ALIGN(4);
__CPU_OPS_START__ = .;
KEEP(*(cpu_ops))
__CPU_OPS_END__ = .;
. = NEXT(4096);
__RODATA_END__ = .;
} >RAM
#else
ro . : {
__RO_START__ = .;
*entrypoint.o(.text*)
*(.text*)
*(.rodata*)
/* Ensure 4-byte alignment for descriptors and ensure inclusion */
. = ALIGN(4);
__RT_SVC_DESCS_START__ = .;
KEEP(*(rt_svc_descs))
__RT_SVC_DESCS_END__ = .;
/*
* Ensure 4-byte alignment for cpu_ops so that its fields are also
* aligned. Also ensure cpu_ops inclusion.
*/
. = ALIGN(4);
__CPU_OPS_START__ = .;
KEEP(*(cpu_ops))
__CPU_OPS_END__ = .;
*(.vectors)
__RO_END_UNALIGNED__ = .;
/*
* Memory page(s) mapped to this section will be marked as
* read-only, executable. No RW data from the next section must
* creep in. Ensure the rest of the current memory block is unused.
*/
. = NEXT(4096);
__RO_END__ = .;
} >RAM
#endif
ASSERT(__CPU_OPS_END__ > __CPU_OPS_START__,
"cpu_ops not defined for this platform.")
/*
* Define a linker symbol to mark start of the RW memory area for this
* image.
*/
__RW_START__ = . ;
.data . : {
__DATA_START__ = .;
*(.data*)
__DATA_END__ = .;
} >RAM
stacks (NOLOAD) : {
__STACKS_START__ = .;
*(tzfw_normal_stacks)
__STACKS_END__ = .;
} >RAM
/*
* The .bss section gets initialised to 0 at runtime.
Introduce unified API to zero memory Introduce zeromem_dczva function on AArch64 that can handle unaligned addresses and make use of DC ZVA instruction to zero a whole block at a time. This zeroing takes place directly in the cache to speed it up without doing external memory access. Remove the zeromem16 function on AArch64 and replace it with an alias to zeromem. This zeromem16 function is now deprecated. Remove the 16-bytes alignment constraint on __BSS_START__ in firmware-design.md as it is now not mandatory anymore (it used to comply with zeromem16 requirements). Change the 16-bytes alignment constraints in SP min's linker script to a 8-bytes alignment constraint as the AArch32 zeromem implementation is now more efficient on 8-bytes aligned addresses. Introduce zero_normalmem and zeromem helpers in platform agnostic header that are implemented this way: * AArch32: * zero_normalmem: zero using usual data access * zeromem: alias for zero_normalmem * AArch64: * zero_normalmem: zero normal memory using DC ZVA instruction (needs MMU enabled) * zeromem: zero using usual data access Usage guidelines: in most cases, zero_normalmem should be preferred. There are 2 scenarios where zeromem (or memset) must be used instead: * Code that must run with MMU disabled (which means all memory is considered device memory for data accesses). * Code that fills device memory with null bytes. Optionally, the following rule can be applied if performance is important: * Code zeroing small areas (few bytes) that are not secrets should use memset to take advantage of compiler optimizations. Note: Code zeroing security-related critical information should use zero_normalmem/zeromem instead of memset to avoid removal by compilers' optimizations in some cases or misbehaving versions of GCC. Fixes ARM-software/tf-issues#408 Change-Id: Iafd9663fc1070413c3e1904e54091cf60effaa82 Signed-off-by: Douglas Raillard <douglas.raillard@arm.com>
2016-12-02 13:51:54 +00:00
* Its base address should be 8-byte aligned for better performance of the
* zero-initialization code.
*/
Introduce unified API to zero memory Introduce zeromem_dczva function on AArch64 that can handle unaligned addresses and make use of DC ZVA instruction to zero a whole block at a time. This zeroing takes place directly in the cache to speed it up without doing external memory access. Remove the zeromem16 function on AArch64 and replace it with an alias to zeromem. This zeromem16 function is now deprecated. Remove the 16-bytes alignment constraint on __BSS_START__ in firmware-design.md as it is now not mandatory anymore (it used to comply with zeromem16 requirements). Change the 16-bytes alignment constraints in SP min's linker script to a 8-bytes alignment constraint as the AArch32 zeromem implementation is now more efficient on 8-bytes aligned addresses. Introduce zero_normalmem and zeromem helpers in platform agnostic header that are implemented this way: * AArch32: * zero_normalmem: zero using usual data access * zeromem: alias for zero_normalmem * AArch64: * zero_normalmem: zero normal memory using DC ZVA instruction (needs MMU enabled) * zeromem: zero using usual data access Usage guidelines: in most cases, zero_normalmem should be preferred. There are 2 scenarios where zeromem (or memset) must be used instead: * Code that must run with MMU disabled (which means all memory is considered device memory for data accesses). * Code that fills device memory with null bytes. Optionally, the following rule can be applied if performance is important: * Code zeroing small areas (few bytes) that are not secrets should use memset to take advantage of compiler optimizations. Note: Code zeroing security-related critical information should use zero_normalmem/zeromem instead of memset to avoid removal by compilers' optimizations in some cases or misbehaving versions of GCC. Fixes ARM-software/tf-issues#408 Change-Id: Iafd9663fc1070413c3e1904e54091cf60effaa82 Signed-off-by: Douglas Raillard <douglas.raillard@arm.com>
2016-12-02 13:51:54 +00:00
.bss (NOLOAD) : ALIGN(8) {
__BSS_START__ = .;
*(.bss*)
*(COMMON)
#if !USE_COHERENT_MEM
/*
* Bakery locks are stored in normal .bss memory
*
* Each lock's data is spread across multiple cache lines, one per CPU,
* but multiple locks can share the same cache line.
* The compiler will allocate enough memory for one CPU's bakery locks,
* the remaining cache lines are allocated by the linker script
*/
. = ALIGN(CACHE_WRITEBACK_GRANULE);
__BAKERY_LOCK_START__ = .;
*(bakery_lock)
. = ALIGN(CACHE_WRITEBACK_GRANULE);
__PERCPU_BAKERY_LOCK_SIZE__ = ABSOLUTE(. - __BAKERY_LOCK_START__);
. = . + (__PERCPU_BAKERY_LOCK_SIZE__ * (PLATFORM_CORE_COUNT - 1));
__BAKERY_LOCK_END__ = .;
#ifdef PLAT_PERCPU_BAKERY_LOCK_SIZE
ASSERT(__PERCPU_BAKERY_LOCK_SIZE__ == PLAT_PERCPU_BAKERY_LOCK_SIZE,
"PLAT_PERCPU_BAKERY_LOCK_SIZE does not match bakery lock requirements");
#endif
#endif
#if ENABLE_PMF
/*
* Time-stamps are stored in normal .bss memory
*
* The compiler will allocate enough memory for one CPU's time-stamps,
* the remaining memory for other CPU's is allocated by the
* linker script
*/
. = ALIGN(CACHE_WRITEBACK_GRANULE);
__PMF_TIMESTAMP_START__ = .;
KEEP(*(pmf_timestamp_array))
. = ALIGN(CACHE_WRITEBACK_GRANULE);
__PMF_PERCPU_TIMESTAMP_END__ = .;
__PERCPU_TIMESTAMP_SIZE__ = ABSOLUTE(. - __PMF_TIMESTAMP_START__);
. = . + (__PERCPU_TIMESTAMP_SIZE__ * (PLATFORM_CORE_COUNT - 1));
__PMF_TIMESTAMP_END__ = .;
#endif /* ENABLE_PMF */
__BSS_END__ = .;
} >RAM
/*
* The xlat_table section is for full, aligned page tables (4K).
* Removing them from .bss avoids forcing 4K alignment on
* the .bss section and eliminates the unecessary zero init
*/
xlat_table (NOLOAD) : {
*(xlat_table)
} >RAM
__BSS_SIZE__ = SIZEOF(.bss);
#if USE_COHERENT_MEM
/*
* The base address of the coherent memory section must be page-aligned (4K)
* to guarantee that the coherent data are stored on their own pages and
* are not mixed with normal data. This is required to set up the correct
* memory attributes for the coherent data page tables.
*/
coherent_ram (NOLOAD) : ALIGN(4096) {
__COHERENT_RAM_START__ = .;
/*
* Bakery locks are stored in coherent memory
*
* Each lock's data is contiguous and fully allocated by the compiler
*/
*(bakery_lock)
*(tzfw_coherent_mem)
__COHERENT_RAM_END_UNALIGNED__ = .;
/*
* Memory page(s) mapped to this section will be marked
* as device memory. No other unexpected data must creep in.
* Ensure the rest of the current memory page is unused.
*/
. = NEXT(4096);
__COHERENT_RAM_END__ = .;
} >RAM
__COHERENT_RAM_UNALIGNED_SIZE__ =
__COHERENT_RAM_END_UNALIGNED__ - __COHERENT_RAM_START__;
#endif
/*
* Define a linker symbol to mark end of the RW memory area for this
* image.
*/
__RW_END__ = .;
__BL32_END__ = .;
}