mirror of
https://github.com/ARM-software/arm-trusted-firmware.git
synced 2025-04-08 05:43:53 +00:00
89dba82dfa
Errata application is painful for performance. For a start, it's done when the core has just come out of reset, which means branch predictors and caches will be empty so a branch to a workaround function must be fetched from memory and that round trip is very slow. Then it also runs with the I-cache off, which means that the loop to iterate over the workarounds must also be fetched from memory on each iteration. We can remove both branches. First, we can simply apply every erratum directly instead of defining a workaround function and jumping to it. Currently, no errata that need to be applied at both reset and runtime, with the same workaround function, exist. If the need arose in future, this should be achievable with a reset + runtime wrapper combo. Then, we can construct a function that applies each erratum linearly instead of looping over the list. If this function is part of the reset function, then the only "far" branches at reset will be for the checker functions. Importantly, this mitigates the slowdown even when an erratum is disabled. The result is ~50% speedup on N1SDP and ~20% on AArch64 Juno on wakeup from PSCI calls that end in powerdown. This is roughly back to the baseline of v2.9, before the errata framework regressed on performance (or a little better). It is important to note that there are other slowdowns since then that remain unknown. Change-Id: Ie4d5288a331b11fd648e5c4a0b652b74160b07b9 Signed-off-by: Boyan Karatotev <boyan.karatotev@arm.com>
92 lines
2 KiB
ArmAsm
92 lines
2 KiB
ArmAsm
/*
|
|
* Copyright (c) 2020-2025, Arm Limited. All rights reserved.
|
|
*
|
|
* SPDX-License-Identifier: BSD-3-Clause
|
|
*/
|
|
|
|
#include <arch.h>
|
|
#include <asm_macros.S>
|
|
#include <common/bl_common.h>
|
|
#include <generic.h>
|
|
#include <cpu_macros.S>
|
|
#include <plat_macros.S>
|
|
|
|
cpu_reset_prologue generic
|
|
|
|
/* ---------------------------------------------
|
|
* Disable L1 data cache and unified L2 cache
|
|
* ---------------------------------------------
|
|
*/
|
|
func generic_disable_dcache
|
|
mrs x1, sctlr_el3
|
|
bic x1, x1, #SCTLR_C_BIT
|
|
msr sctlr_el3, x1
|
|
isb
|
|
ret
|
|
endfunc generic_disable_dcache
|
|
|
|
func generic_core_pwr_dwn
|
|
mov x18, x30
|
|
|
|
/* ---------------------------------------------
|
|
* Turn off caches.
|
|
* ---------------------------------------------
|
|
*/
|
|
bl generic_disable_dcache
|
|
|
|
/* ---------------------------------------------
|
|
* Flush L1 caches.
|
|
* ---------------------------------------------
|
|
*/
|
|
mov x0, #DCCISW
|
|
bl dcsw_op_level1
|
|
|
|
ret x18
|
|
endfunc generic_core_pwr_dwn
|
|
|
|
func generic_cluster_pwr_dwn
|
|
mov x18, x30
|
|
|
|
/* ---------------------------------------------
|
|
* Turn off caches.
|
|
* ---------------------------------------------
|
|
*/
|
|
bl generic_disable_dcache
|
|
|
|
/* ---------------------------------------------
|
|
* Flush L1 caches.
|
|
* ---------------------------------------------
|
|
*/
|
|
mov x0, #DCCISW
|
|
bl dcsw_op_level1
|
|
|
|
/* ---------------------------------------------
|
|
* Disable the optional ACP.
|
|
* ---------------------------------------------
|
|
*/
|
|
bl plat_disable_acp
|
|
|
|
/* ---------------------------------------------
|
|
* Flush L2 caches.
|
|
* ---------------------------------------------
|
|
*/
|
|
mov x0, #DCCISW
|
|
bl dcsw_op_level2
|
|
|
|
ret x18
|
|
|
|
endfunc generic_cluster_pwr_dwn
|
|
|
|
/* ---------------------------------------------
|
|
* Unimplemented functions.
|
|
* ---------------------------------------------
|
|
*/
|
|
.equ generic_cpu_reg_dump, 0
|
|
|
|
cpu_reset_func_start generic
|
|
cpu_reset_func_end generic
|
|
|
|
declare_cpu_ops generic, AARCH64_GENERIC_MIDR, \
|
|
generic_reset_func, \
|
|
generic_core_pwr_dwn, \
|
|
generic_cluster_pwr_dwn
|