linux/arch/arm/mach-tegra/sleep-tegra20.S
Nick Desaulniers a2faac3986 ARM: 9263/1: use .arch directives instead of assembler command line flags
Similar to commit a6c30873ee ("ARM: 8989/1: use .fpu assembler
directives instead of assembler arguments").

GCC and GNU binutils support setting the "sub arch" via -march=,
-Wa,-march, target function attribute, and .arch assembler directive.

Clang was missing support for -Wa,-march=, but this was implemented in
clang-13.

The behavior of both GCC and Clang is to
prefer -Wa,-march= over -march= for assembler and assembler-with-cpp
sources, but Clang will warn about the -march= being unused.

clang: warning: argument unused during compilation: '-march=armv6k'
[-Wunused-command-line-argument]

Since most assembler is non-conditionally assembled with one sub arch
(modulo arch/arm/delay-loop.S which conditionally is assembled as armv4
based on CONFIG_ARCH_RPC, and arch/arm/mach-at91/pm-suspend.S which is
conditionally assembled as armv7-a based on CONFIG_CPU_V7), prefer the
.arch assembler directive.

Add a few more instances found in compile testing as found by Arnd and
Nathan.

Link: 1d51c699b9
Link: https://bugs.llvm.org/show_bug.cgi?id=48894
Link: https://github.com/ClangBuiltLinux/linux/issues/1195
Link: https://github.com/ClangBuiltLinux/linux/issues/1315

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
2022-11-08 18:36:17 +00:00

438 lines
10 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (c) 2010-2012, NVIDIA Corporation. All rights reserved.
* Copyright (c) 2011, Google, Inc.
*
* Author: Colin Cross <ccross@android.com>
* Gary King <gking@nvidia.com>
*/
#include <linux/linkage.h>
#include <soc/tegra/flowctrl.h>
#include <asm/assembler.h>
#include <asm/proc-fns.h>
#include <asm/cp15.h>
#include <asm/cache.h>
#include "irammap.h"
#include "reset.h"
#include "sleep.h"
#define EMC_CFG 0xc
#define EMC_ADR_CFG 0x10
#define EMC_NOP 0xdc
#define EMC_SELF_REF 0xe0
#define EMC_REQ_CTRL 0x2b0
#define EMC_EMC_STATUS 0x2b4
#define CLK_RESET_CCLK_BURST 0x20
#define CLK_RESET_CCLK_DIVIDER 0x24
#define CLK_RESET_SCLK_BURST 0x28
#define CLK_RESET_SCLK_DIVIDER 0x2c
#define CLK_RESET_PLLC_BASE 0x80
#define CLK_RESET_PLLM_BASE 0x90
#define CLK_RESET_PLLP_BASE 0xa0
#define APB_MISC_XM2CFGCPADCTRL 0x8c8
#define APB_MISC_XM2CFGDPADCTRL 0x8cc
#define APB_MISC_XM2CLKCFGPADCTRL 0x8d0
#define APB_MISC_XM2COMPPADCTRL 0x8d4
#define APB_MISC_XM2VTTGENPADCTRL 0x8d8
#define APB_MISC_XM2CFGCPADCTRL2 0x8e4
#define APB_MISC_XM2CFGDPADCTRL2 0x8e8
#define PLLC_STORE_MASK (1 << 0)
#define PLLM_STORE_MASK (1 << 1)
#define PLLP_STORE_MASK (1 << 2)
.arch armv7-a
.macro test_pll_state, rd, test_mask
ldr \rd, tegra_pll_state
tst \rd, #\test_mask
.endm
.macro store_pll_state, rd, tmp, r_car_base, pll_base, pll_mask
ldr \rd, [\r_car_base, #\pll_base]
tst \rd, #(1 << 30)
ldr \rd, tegra_pll_state
biceq \rd, \rd, #\pll_mask
orrne \rd, \rd, #\pll_mask
adr \tmp, tegra_pll_state
str \rd, [\tmp]
.endm
.macro pll_enable, rd, r_car_base, pll_base, test_mask
test_pll_state \rd, \test_mask
beq 1f
ldr \rd, [\r_car_base, #\pll_base]
tst \rd, #(1 << 30)
orreq \rd, \rd, #(1 << 30)
streq \rd, [\r_car_base, #\pll_base]
1:
.endm
.macro emc_device_mask, rd, base
ldr \rd, [\base, #EMC_ADR_CFG]
tst \rd, #(0x3 << 24)
moveq \rd, #(0x1 << 8) @ just 1 device
movne \rd, #(0x3 << 8) @ 2 devices
.endm
#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PM_SLEEP)
/*
* tegra20_hotplug_shutdown(void)
*
* puts the current cpu in reset
* should never return
*/
ENTRY(tegra20_hotplug_shutdown)
/* Put this CPU down */
cpu_id r0
bl tegra20_cpu_shutdown
ret lr @ should never get here
ENDPROC(tegra20_hotplug_shutdown)
/*
* tegra20_cpu_shutdown(int cpu)
*
* r0 is cpu to reset
*
* puts the specified CPU in wait-for-event mode on the flow controller
* and puts the CPU in reset
* can be called on the current cpu or another cpu
* if called on the current cpu, does not return
* MUST NOT BE CALLED FOR CPU 0.
*
* corrupts r0-r3, r12
*/
ENTRY(tegra20_cpu_shutdown)
cmp r0, #0
reteq lr @ must not be called for CPU 0
cpu_to_halt_reg r1, r0
ldr r3, =TEGRA_FLOW_CTRL_VIRT
mov r2, #FLOW_CTRL_WAITEVENT | FLOW_CTRL_JTAG_RESUME
str r2, [r3, r1] @ put flow controller in wait event mode
ldr r2, [r3, r1]
isb
dsb
movw r1, 0x1011
mov r1, r1, lsl r0
ldr r3, =TEGRA_CLK_RESET_VIRT
str r1, [r3, #0x340] @ put slave CPU in reset
isb
dsb
cpu_id r3
cmp r3, r0
beq .
ret lr
ENDPROC(tegra20_cpu_shutdown)
#endif
#ifdef CONFIG_PM_SLEEP
/*
* tegra20_sleep_core_finish(unsigned long v2p)
*
* Enters suspend in LP0 or LP1 by turning off the mmu and jumping to
* tegra20_tear_down_core in IRAM
*/
ENTRY(tegra20_sleep_core_finish)
mov r4, r0
/* Flush, disable the L1 data cache and exit SMP */
mov r0, #TEGRA_FLUSH_CACHE_ALL
bl tegra_disable_clean_inv_dcache
mov r0, r4
mov32 r3, tegra_shut_off_mmu
add r3, r3, r0
mov32 r0, tegra20_tear_down_core
mov32 r1, tegra20_iram_start
sub r0, r0, r1
mov32 r1, TEGRA_IRAM_LPx_RESUME_AREA
add r0, r0, r1
ret r3
ENDPROC(tegra20_sleep_core_finish)
/*
* tegra20_tear_down_cpu
*
* Switches the CPU cluster to PLL-P and enters sleep.
*/
ENTRY(tegra20_tear_down_cpu)
bl tegra_switch_cpu_to_pllp
b tegra20_enter_sleep
ENDPROC(tegra20_tear_down_cpu)
/* START OF ROUTINES COPIED TO IRAM */
.align L1_CACHE_SHIFT
.globl tegra20_iram_start
tegra20_iram_start:
/*
* tegra20_lp1_reset
*
* reset vector for LP1 restore; copied into IRAM during suspend.
* Brings the system back up to a safe staring point (SDRAM out of
* self-refresh, PLLC, PLLM and PLLP reenabled, CPU running on PLLP,
* system clock running on the same PLL that it suspended at), and
* jumps to tegra_resume to restore virtual addressing and PLLX.
* The physical address of tegra_resume expected to be stored in
* PMC_SCRATCH41.
*
* NOTE: THIS *MUST* BE RELOCATED TO TEGRA_IRAM_LPx_RESUME_AREA.
*/
ENTRY(tegra20_lp1_reset)
/*
* The CPU and system bus are running at 32KHz and executing from
* IRAM when this code is executed; immediately switch to CLKM and
* enable PLLM, PLLP, PLLC.
*/
mov32 r0, TEGRA_CLK_RESET_BASE
mov r1, #(1 << 28)
str r1, [r0, #CLK_RESET_SCLK_BURST]
str r1, [r0, #CLK_RESET_CCLK_BURST]
mov r1, #0
str r1, [r0, #CLK_RESET_CCLK_DIVIDER]
str r1, [r0, #CLK_RESET_SCLK_DIVIDER]
pll_enable r1, r0, CLK_RESET_PLLM_BASE, PLLM_STORE_MASK
pll_enable r1, r0, CLK_RESET_PLLP_BASE, PLLP_STORE_MASK
pll_enable r1, r0, CLK_RESET_PLLC_BASE, PLLC_STORE_MASK
adr r2, tegra20_sdram_pad_address
adr r4, tegra20_sdram_pad_save
mov r5, #0
ldr r6, tegra20_sdram_pad_size
padload:
ldr r7, [r2, r5] @ r7 is the addr in the pad_address
ldr r1, [r4, r5]
str r1, [r7] @ restore the value in pad_save
add r5, r5, #4
cmp r6, r5
bne padload
padload_done:
/* 255uS delay for PLL stabilization */
mov32 r7, TEGRA_TMRUS_BASE
ldr r1, [r7]
add r1, r1, #0xff
wait_until r1, r7, r9
adr r4, tegra20_sclk_save
ldr r4, [r4]
str r4, [r0, #CLK_RESET_SCLK_BURST]
mov32 r4, ((1 << 28) | (4)) @ burst policy is PLLP
str r4, [r0, #CLK_RESET_CCLK_BURST]
mov32 r0, TEGRA_EMC_BASE
ldr r1, [r0, #EMC_CFG]
bic r1, r1, #(1 << 31) @ disable DRAM_CLK_STOP
str r1, [r0, #EMC_CFG]
mov r1, #0
str r1, [r0, #EMC_SELF_REF] @ take DRAM out of self refresh
mov r1, #1
str r1, [r0, #EMC_NOP]
str r1, [r0, #EMC_NOP]
emc_device_mask r1, r0
exit_selfrefresh_loop:
ldr r2, [r0, #EMC_EMC_STATUS]
ands r2, r2, r1
bne exit_selfrefresh_loop
mov r1, #0 @ unstall all transactions
str r1, [r0, #EMC_REQ_CTRL]
mov32 r0, TEGRA_PMC_BASE
ldr r0, [r0, #PMC_SCRATCH41]
ret r0 @ jump to tegra_resume
ENDPROC(tegra20_lp1_reset)
/*
* tegra20_tear_down_core
*
* copied into and executed from IRAM
* puts memory in self-refresh for LP0 and LP1
*/
tegra20_tear_down_core:
bl tegra20_sdram_self_refresh
bl tegra20_switch_cpu_to_clk32k
b tegra20_enter_sleep
/*
* tegra20_switch_cpu_to_clk32k
*
* In LP0 and LP1 all PLLs will be turned off. Switch the CPU and system clock
* to the 32KHz clock.
*/
tegra20_switch_cpu_to_clk32k:
/*
* start by switching to CLKM to safely disable PLLs, then switch to
* CLKS.
*/
mov r0, #(1 << 28)
str r0, [r5, #CLK_RESET_SCLK_BURST]
str r0, [r5, #CLK_RESET_CCLK_BURST]
mov r0, #0
str r0, [r5, #CLK_RESET_CCLK_DIVIDER]
str r0, [r5, #CLK_RESET_SCLK_DIVIDER]
/* 2uS delay delay between changing SCLK and disabling PLLs */
mov32 r7, TEGRA_TMRUS_BASE
ldr r1, [r7]
add r1, r1, #2
wait_until r1, r7, r9
store_pll_state r0, r1, r5, CLK_RESET_PLLC_BASE, PLLC_STORE_MASK
store_pll_state r0, r1, r5, CLK_RESET_PLLM_BASE, PLLM_STORE_MASK
store_pll_state r0, r1, r5, CLK_RESET_PLLP_BASE, PLLP_STORE_MASK
/* disable PLLM, PLLP and PLLC */
ldr r0, [r5, #CLK_RESET_PLLM_BASE]
bic r0, r0, #(1 << 30)
str r0, [r5, #CLK_RESET_PLLM_BASE]
ldr r0, [r5, #CLK_RESET_PLLP_BASE]
bic r0, r0, #(1 << 30)
str r0, [r5, #CLK_RESET_PLLP_BASE]
ldr r0, [r5, #CLK_RESET_PLLC_BASE]
bic r0, r0, #(1 << 30)
str r0, [r5, #CLK_RESET_PLLC_BASE]
/* switch to CLKS */
mov r0, #0 /* brust policy = 32KHz */
str r0, [r5, #CLK_RESET_SCLK_BURST]
ret lr
/*
* tegra20_enter_sleep
*
* uses flow controller to enter sleep state
* executes from IRAM with SDRAM in selfrefresh when target state is LP0 or LP1
* executes from SDRAM with target state is LP2
*/
tegra20_enter_sleep:
mov32 r6, TEGRA_FLOW_CTRL_BASE
mov r0, #FLOW_CTRL_WAIT_FOR_INTERRUPT
orr r0, r0, #FLOW_CTRL_HALT_CPU_IRQ | FLOW_CTRL_HALT_CPU_FIQ
cpu_id r1
cpu_to_halt_reg r1, r1
str r0, [r6, r1]
dsb
ldr r0, [r6, r1] /* memory barrier */
halted:
dsb
wfe /* CPU should be power gated here */
isb
b halted
/*
* tegra20_sdram_self_refresh
*
* called with MMU off and caches disabled
* puts sdram in self refresh
* must be executed from IRAM
*/
tegra20_sdram_self_refresh:
mov32 r1, TEGRA_EMC_BASE @ r1 reserved for emc base addr
mov r2, #3
str r2, [r1, #EMC_REQ_CTRL] @ stall incoming DRAM requests
emcidle:
ldr r2, [r1, #EMC_EMC_STATUS]
tst r2, #4
beq emcidle
mov r2, #1
str r2, [r1, #EMC_SELF_REF]
emc_device_mask r2, r1
emcself:
ldr r3, [r1, #EMC_EMC_STATUS]
and r3, r3, r2
cmp r3, r2
bne emcself @ loop until DDR in self-refresh
adr r2, tegra20_sdram_pad_address
adr r3, tegra20_sdram_pad_safe
adr r4, tegra20_sdram_pad_save
mov r5, #0
ldr r6, tegra20_sdram_pad_size
padsave:
ldr r0, [r2, r5] @ r0 is the addr in the pad_address
ldr r1, [r0]
str r1, [r4, r5] @ save the content of the addr
ldr r1, [r3, r5]
str r1, [r0] @ set the save val to the addr
add r5, r5, #4
cmp r6, r5
bne padsave
padsave_done:
mov32 r5, TEGRA_CLK_RESET_BASE
ldr r0, [r5, #CLK_RESET_SCLK_BURST]
adr r2, tegra20_sclk_save
str r0, [r2]
dsb
ret lr
tegra20_sdram_pad_address:
.word TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGCPADCTRL
.word TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGDPADCTRL
.word TEGRA_APB_MISC_BASE + APB_MISC_XM2CLKCFGPADCTRL
.word TEGRA_APB_MISC_BASE + APB_MISC_XM2COMPPADCTRL
.word TEGRA_APB_MISC_BASE + APB_MISC_XM2VTTGENPADCTRL
.word TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGCPADCTRL2
.word TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGDPADCTRL2
tegra20_sdram_pad_size:
.word tegra20_sdram_pad_size - tegra20_sdram_pad_address
tegra20_sdram_pad_safe:
.word 0x8
.word 0x8
.word 0x0
.word 0x8
.word 0x5500
.word 0x08080040
.word 0x0
tegra20_sclk_save:
.word 0x0
tegra20_sdram_pad_save:
.rept (tegra20_sdram_pad_size - tegra20_sdram_pad_address) / 4
.long 0
.endr
tegra_pll_state:
.word 0x0
.ltorg
/* dummy symbol for end of IRAM */
.align L1_CACHE_SHIFT
.globl tegra20_iram_end
tegra20_iram_end:
b .
#endif