OpenCloudOS-Kernel/arch/arm/mach-tegra/sleep-tegra20.S

576 lines
14 KiB
ArmAsm
Raw Normal View History

/* 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 __tegra20_cpu1_resettable_status_offset \
(__tegra_cpu_reset_handler_data_offset + RESET_DATA(RESETTABLE_STATUS))
.macro pll_enable, rd, r_car_base, pll_base
ldr \rd, [\r_car_base, #\pll_base]
tst \rd, #(1 << 30)
orreq \rd, \rd, #(1 << 30)
streq \rd, [\r_car_base, #\pll_base]
.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
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
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
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
reteq lr @ must not be called for CPU 0
mov32 r1, TEGRA_IRAM_RESET_BASE_VIRT
ldr r2, =__tegra20_cpu1_resettable_status_offset
mov r12, #CPU_RESETTABLE
strb r12, [r1, r2]
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 .
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
ret lr
ENDPROC(tegra20_cpu_shutdown)
#endif
#ifdef CONFIG_PM_SLEEP
/*
* tegra_pen_lock
*
* spinlock implementation with no atomic test-and-set and no coherence
* using Peterson's algorithm on strongly-ordered registers
* used to synchronize a cpu waking up from wfi with entering lp2 on idle
*
* The reference link of Peterson's algorithm:
* http://en.wikipedia.org/wiki/Peterson's_algorithm
*
* SCRATCH37 = r1 = !turn (inverted from Peterson's algorithm)
* on cpu 0:
* r2 = flag[0] (in SCRATCH38)
* r3 = flag[1] (in SCRATCH39)
* on cpu1:
* r2 = flag[1] (in SCRATCH39)
* r3 = flag[0] (in SCRATCH38)
*
* must be called with MMU on
* corrupts r0-r3, r12
*/
ENTRY(tegra_pen_lock)
mov32 r3, TEGRA_PMC_VIRT
cpu_id r0
add r1, r3, #PMC_SCRATCH37
cmp r0, #0
addeq r2, r3, #PMC_SCRATCH38
addeq r3, r3, #PMC_SCRATCH39
addne r2, r3, #PMC_SCRATCH39
addne r3, r3, #PMC_SCRATCH38
mov r12, #1
str r12, [r2] @ flag[cpu] = 1
dsb
str r12, [r1] @ !turn = cpu
1: dsb
ldr r12, [r3]
cmp r12, #1 @ flag[!cpu] == 1?
ldreq r12, [r1]
cmpeq r12, r0 @ !turn == cpu?
beq 1b @ while !turn == cpu && flag[!cpu] == 1
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
ret lr @ locked
ENDPROC(tegra_pen_lock)
ENTRY(tegra_pen_unlock)
dsb
mov32 r3, TEGRA_PMC_VIRT
cpu_id r0
cmp r0, #0
addeq r2, r3, #PMC_SCRATCH38
addne r2, r3, #PMC_SCRATCH39
mov r12, #0
str r12, [r2]
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
ret lr
ENDPROC(tegra_pen_unlock)
/*
* tegra20_cpu_clear_resettable(void)
*
* Called to clear the "resettable soon" flag in IRAM variable when
* it is expected that the secondary CPU will be idle soon.
*/
ENTRY(tegra20_cpu_clear_resettable)
mov32 r1, TEGRA_IRAM_RESET_BASE_VIRT
ldr r2, =__tegra20_cpu1_resettable_status_offset
mov r12, #CPU_NOT_RESETTABLE
strb r12, [r1, r2]
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
ret lr
ENDPROC(tegra20_cpu_clear_resettable)
/*
* tegra20_cpu_set_resettable_soon(void)
*
* Called to set the "resettable soon" flag in IRAM variable when
* it is expected that the secondary CPU will be idle soon.
*/
ENTRY(tegra20_cpu_set_resettable_soon)
mov32 r1, TEGRA_IRAM_RESET_BASE_VIRT
ldr r2, =__tegra20_cpu1_resettable_status_offset
mov r12, #CPU_RESETTABLE_SOON
strb r12, [r1, r2]
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
ret lr
ENDPROC(tegra20_cpu_set_resettable_soon)
/*
* tegra20_cpu_is_resettable_soon(void)
*
* Returns true if the "resettable soon" flag in IRAM variable has been
* set because it is expected that the secondary CPU will be idle soon.
*/
ENTRY(tegra20_cpu_is_resettable_soon)
mov32 r1, TEGRA_IRAM_RESET_BASE_VIRT
ldr r2, =__tegra20_cpu1_resettable_status_offset
ldrb r12, [r1, r2]
cmp r12, #CPU_RESETTABLE_SOON
moveq r0, #1
movne r0, #0
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
ret lr
ENDPROC(tegra20_cpu_is_resettable_soon)
/*
* 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)
ARM: tegra: Ensure entire dcache is flushed on entering LP0/1 Tegra support several low-power (LPx) states, which are: - LP0: CPU + Core voltage off and DRAM in self-refresh - LP1: CPU voltage off and DRAM in self-refresh - LP2: CPU voltage off When entering any of the above states the tegra_disable_clean_inv_dcache() function is called to flush the dcache. The function tegra_disable_clean_inv_dcache() will either flush the entire data cache or up to the Level of Unification Inner Shareable (LoUIS) depending on the value in r0. When tegra_disable_clean_inv_dcache() is called by tegra20_sleep_core_finish() or tegra30_sleep_core_finish(), to enter LP0 and LP1 power state, the r0 register contains a physical memory address which will not be equal to TEGRA_FLUSH_CACHE_ALL (1) and so the data cache will be only flushed to the LoUIS. However, when tegra_disable_clean_inv_dcache() called by tegra_sleep_cpu_finish() to enter to LP2 power state, r0 is set to TEGRA_FLUSH_CACHE_ALL to flush the entire dcache. Please note that tegra20_sleep_core_finish(), tegra30_sleep_core_finish() and tegra_sleep_cpu_finish() are called by the boot CPU once all other CPUs have been disabled and so it seems appropriate to flush the entire cache at this stage. Therefore, ensure that r0 is set to TEGRA_FLUSH_CACHE_ALL when calling tegra_disable_clean_inv_dcache() from tegra20_sleep_core_finish() and tegra30_sleep_core_finish(). Signed-off-by: Jon Hunter <jonathanh@nvidia.com> Reviewed-by: Joseph Lo <josephl@nvidia.com> Signed-off-by: Thierry Reding <treding@nvidia.com>
2015-11-19 22:19:47 +08:00
mov r4, r0
/* Flush, disable the L1 data cache and exit SMP */
ARM: tegra: Ensure entire dcache is flushed on entering LP0/1 Tegra support several low-power (LPx) states, which are: - LP0: CPU + Core voltage off and DRAM in self-refresh - LP1: CPU voltage off and DRAM in self-refresh - LP2: CPU voltage off When entering any of the above states the tegra_disable_clean_inv_dcache() function is called to flush the dcache. The function tegra_disable_clean_inv_dcache() will either flush the entire data cache or up to the Level of Unification Inner Shareable (LoUIS) depending on the value in r0. When tegra_disable_clean_inv_dcache() is called by tegra20_sleep_core_finish() or tegra30_sleep_core_finish(), to enter LP0 and LP1 power state, the r0 register contains a physical memory address which will not be equal to TEGRA_FLUSH_CACHE_ALL (1) and so the data cache will be only flushed to the LoUIS. However, when tegra_disable_clean_inv_dcache() called by tegra_sleep_cpu_finish() to enter to LP2 power state, r0 is set to TEGRA_FLUSH_CACHE_ALL to flush the entire dcache. Please note that tegra20_sleep_core_finish(), tegra30_sleep_core_finish() and tegra_sleep_cpu_finish() are called by the boot CPU once all other CPUs have been disabled and so it seems appropriate to flush the entire cache at this stage. Therefore, ensure that r0 is set to TEGRA_FLUSH_CACHE_ALL when calling tegra_disable_clean_inv_dcache() from tegra20_sleep_core_finish() and tegra30_sleep_core_finish(). Signed-off-by: Jon Hunter <jonathanh@nvidia.com> Reviewed-by: Joseph Lo <josephl@nvidia.com> Signed-off-by: Thierry Reding <treding@nvidia.com>
2015-11-19 22:19:47 +08:00
mov r0, #TEGRA_FLUSH_CACHE_ALL
bl tegra_disable_clean_inv_dcache
ARM: tegra: Ensure entire dcache is flushed on entering LP0/1 Tegra support several low-power (LPx) states, which are: - LP0: CPU + Core voltage off and DRAM in self-refresh - LP1: CPU voltage off and DRAM in self-refresh - LP2: CPU voltage off When entering any of the above states the tegra_disable_clean_inv_dcache() function is called to flush the dcache. The function tegra_disable_clean_inv_dcache() will either flush the entire data cache or up to the Level of Unification Inner Shareable (LoUIS) depending on the value in r0. When tegra_disable_clean_inv_dcache() is called by tegra20_sleep_core_finish() or tegra30_sleep_core_finish(), to enter LP0 and LP1 power state, the r0 register contains a physical memory address which will not be equal to TEGRA_FLUSH_CACHE_ALL (1) and so the data cache will be only flushed to the LoUIS. However, when tegra_disable_clean_inv_dcache() called by tegra_sleep_cpu_finish() to enter to LP2 power state, r0 is set to TEGRA_FLUSH_CACHE_ALL to flush the entire dcache. Please note that tegra20_sleep_core_finish(), tegra30_sleep_core_finish() and tegra_sleep_cpu_finish() are called by the boot CPU once all other CPUs have been disabled and so it seems appropriate to flush the entire cache at this stage. Therefore, ensure that r0 is set to TEGRA_FLUSH_CACHE_ALL when calling tegra_disable_clean_inv_dcache() from tegra20_sleep_core_finish() and tegra30_sleep_core_finish(). Signed-off-by: Jon Hunter <jonathanh@nvidia.com> Reviewed-by: Joseph Lo <josephl@nvidia.com> Signed-off-by: Thierry Reding <treding@nvidia.com>
2015-11-19 22:19:47 +08:00
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
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
ret r3
ENDPROC(tegra20_sleep_core_finish)
/*
* tegra20_sleep_cpu_secondary_finish(unsigned long v2p)
*
* Enters WFI on secondary CPU by exiting coherency.
*/
ENTRY(tegra20_sleep_cpu_secondary_finish)
stmfd sp!, {r4-r11, lr}
mrc p15, 0, r11, c1, c0, 1 @ save actlr before exiting coherency
/* Flush and disable the L1 data cache */
mov r0, #TEGRA_FLUSH_CACHE_LOUIS
bl tegra_disable_clean_inv_dcache
mov32 r0, TEGRA_IRAM_RESET_BASE_VIRT
ldr r4, =__tegra20_cpu1_resettable_status_offset
mov r3, #CPU_RESETTABLE
strb r3, [r0, r4]
bl tegra_cpu_do_idle
/*
* cpu may be reset while in wfi, which will return through
* tegra_resume to cpu_resume
* or interrupt may wake wfi, which will return here
* cpu state is unchanged - MMU is on, cache is on, coherency
* is off, and the data cache is off
*
* r11 contains the original actlr
*/
bl tegra_pen_lock
mov32 r0, TEGRA_IRAM_RESET_BASE_VIRT
ldr r4, =__tegra20_cpu1_resettable_status_offset
mov r3, #CPU_NOT_RESETTABLE
strb r3, [r0, r4]
bl tegra_pen_unlock
/* Re-enable the data cache */
mrc p15, 0, r10, c1, c0, 0
orr r10, r10, #CR_C
mcr p15, 0, r10, c1, c0, 0
isb
mcr p15, 0, r11, c1, c0, 1 @ reenable coherency
/* Invalidate the TLBs & BTAC */
mov r1, #0
mcr p15, 0, r1, c8, c3, 0 @ invalidate shared TLBs
mcr p15, 0, r1, c7, c1, 6 @ invalidate shared BTAC
dsb
isb
/* the cpu was running with coherency disabled,
* caches may be out of date */
bl v7_flush_kern_cache_louis
ldmfd sp!, {r4 - r11, pc}
ENDPROC(tegra20_sleep_cpu_secondary_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
pll_enable r1, r0, CLK_RESET_PLLP_BASE
pll_enable r1, r0, CLK_RESET_PLLC_BASE
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]
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
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
/* 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]
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
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
ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ ARMv6 and greater introduced a new instruction ("bx") which can be used to return from function calls. Recent CPUs perform better when the "bx lr" instruction is used rather than the "mov pc, lr" instruction, and this sequence is strongly recommended to be used by the ARM architecture manual (section A.4.1.1). We provide a new macro "ret" with all its variants for the condition code which will resolve to the appropriate instruction. Rather than doing this piecemeal, and miss some instances, change all the "mov pc" instances to use the new macro, with the exception of the "movs" instruction and the kprobes code. This allows us to detect the "mov pc, lr" case and fix it up - and also gives us the possibility of deploying this for other registers depending on the CPU selection. Reported-by: Will Deacon <will.deacon@arm.com> Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1 Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood Tested-by: Shawn Guo <shawn.guo@freescale.com> Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385 Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-06-30 23:29:12 +08:00
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
.ltorg
/* dummy symbol for end of IRAM */
.align L1_CACHE_SHIFT
.globl tegra20_iram_end
tegra20_iram_end:
b .
#endif