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>
60 lines
1.5 KiB
ArmAsm
60 lines
1.5 KiB
ArmAsm
/*
|
|
* Copyright (c) 2019-2025, Arm Limited. All rights reserved.
|
|
*
|
|
* SPDX-License-Identifier: BSD-3-Clause
|
|
*/
|
|
#include <arch.h>
|
|
|
|
#include <asm_macros.S>
|
|
#include <common/bl_common.h>
|
|
#include <common/debug.h>
|
|
#include <cortex_a65.h>
|
|
#include <cpu_macros.S>
|
|
#include <dsu_macros.S>
|
|
#include <plat_macros.S>
|
|
|
|
/* Hardware handled coherency */
|
|
#if !HW_ASSISTED_COHERENCY
|
|
#error "Cortex-A65 must be compiled with HW_ASSISTED_COHERENCY enabled"
|
|
#endif
|
|
|
|
/* 64-bit only core */
|
|
#if CTX_INCLUDE_AARCH32_REGS
|
|
#error "Cortex-A65 supports only AArch64. Compile with CTX_INCLUDE_AARCH32_REGS=0"
|
|
#endif
|
|
|
|
cpu_reset_prologue cortex_a65
|
|
|
|
workaround_reset_start cortex_a65, ERRATUM(936184), ERRATA_DSU_936184
|
|
errata_dsu_936184_wa_impl
|
|
workaround_reset_end cortex_a65, ERRATUM(936184)
|
|
|
|
check_erratum_custom_start cortex_a65, ERRATUM(936184)
|
|
check_errata_dsu_936184_impl
|
|
ret
|
|
check_erratum_custom_end cortex_a65, ERRATUM(936184)
|
|
|
|
cpu_reset_func_start cortex_a65
|
|
cpu_reset_func_end cortex_a65
|
|
|
|
func cortex_a65_cpu_pwr_dwn
|
|
mrs x0, CORTEX_A65_CPUPWRCTLR_EL1
|
|
orr x0, x0, #CORTEX_A65_CPUPWRCTLR_EL1_CORE_PWRDN_BIT
|
|
msr CORTEX_A65_CPUPWRCTLR_EL1, x0
|
|
isb
|
|
ret
|
|
endfunc cortex_a65_cpu_pwr_dwn
|
|
|
|
.section .rodata.cortex_a65_regs, "aS"
|
|
cortex_a65_regs: /* The ascii list of register names to be reported */
|
|
.asciz "cpuectlr_el1", ""
|
|
|
|
func cortex_a65_cpu_reg_dump
|
|
adr x6, cortex_a65_regs
|
|
mrs x8, CORTEX_A65_ECTLR_EL1
|
|
ret
|
|
endfunc cortex_a65_cpu_reg_dump
|
|
|
|
declare_cpu_ops cortex_a65, CORTEX_A65_MIDR, \
|
|
cortex_a65_reset_func, \
|
|
cortex_a65_cpu_pwr_dwn
|