OpenCloudOS-Kernel/arch/powerpc/kernel/idle_book3s.S

1003 lines
26 KiB
ArmAsm

/*
* This file contains idle entry/exit functions for POWER7,
* POWER8 and POWER9 CPUs.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/threads.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ppc-opcode.h>
#include <asm/hw_irq.h>
#include <asm/kvm_book3s_asm.h>
#include <asm/opal.h>
#include <asm/cpuidle.h>
#include <asm/exception-64s.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/mmu.h>
#undef DEBUG
/*
* Use unused space in the interrupt stack to save and restore
* registers for winkle support.
*/
#define _MMCR0 GPR0
#define _SDR1 GPR3
#define _PTCR GPR3
#define _RPR GPR4
#define _SPURR GPR5
#define _PURR GPR6
#define _TSCR GPR7
#define _DSCR GPR8
#define _AMOR GPR9
#define _WORT GPR10
#define _WORC GPR11
#define _LPCR GPR12
#define PSSCR_EC_ESL_MASK_SHIFTED (PSSCR_EC | PSSCR_ESL) >> 16
.text
/*
* Used by threads before entering deep idle states. Saves SPRs
* in interrupt stack frame
*/
save_sprs_to_stack:
/*
* Note all register i.e per-core, per-subcore or per-thread is saved
* here since any thread in the core might wake up first
*/
BEGIN_FTR_SECTION
/*
* Note - SDR1 is dropped in Power ISA v3. Hence not restoring
* SDR1 here
*/
mfspr r3,SPRN_PTCR
std r3,_PTCR(r1)
mfspr r3,SPRN_LPCR
std r3,_LPCR(r1)
FTR_SECTION_ELSE
mfspr r3,SPRN_SDR1
std r3,_SDR1(r1)
ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
mfspr r3,SPRN_RPR
std r3,_RPR(r1)
mfspr r3,SPRN_SPURR
std r3,_SPURR(r1)
mfspr r3,SPRN_PURR
std r3,_PURR(r1)
mfspr r3,SPRN_TSCR
std r3,_TSCR(r1)
mfspr r3,SPRN_DSCR
std r3,_DSCR(r1)
mfspr r3,SPRN_AMOR
std r3,_AMOR(r1)
mfspr r3,SPRN_WORT
std r3,_WORT(r1)
mfspr r3,SPRN_WORC
std r3,_WORC(r1)
/*
* On POWER9, there are idle states such as stop4, invoked via cpuidle,
* that lose hypervisor resources. In such cases, we need to save
* additional SPRs before entering those idle states so that they can
* be restored to their older values on wakeup from the idle state.
*
* On POWER8, the only such deep idle state is winkle which is used
* only in the context of CPU-Hotplug, where these additional SPRs are
* reinitiazed to a sane value. Hence there is no need to save/restore
* these SPRs.
*/
BEGIN_FTR_SECTION
blr
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
power9_save_additional_sprs:
mfspr r3, SPRN_PID
mfspr r4, SPRN_LDBAR
std r3, STOP_PID(r13)
std r4, STOP_LDBAR(r13)
mfspr r3, SPRN_FSCR
mfspr r4, SPRN_HFSCR
std r3, STOP_FSCR(r13)
std r4, STOP_HFSCR(r13)
mfspr r3, SPRN_MMCRA
mfspr r4, SPRN_MMCR0
std r3, STOP_MMCRA(r13)
std r4, _MMCR0(r1)
mfspr r3, SPRN_MMCR1
mfspr r4, SPRN_MMCR2
std r3, STOP_MMCR1(r13)
std r4, STOP_MMCR2(r13)
blr
power9_restore_additional_sprs:
ld r3,_LPCR(r1)
ld r4, STOP_PID(r13)
mtspr SPRN_LPCR,r3
mtspr SPRN_PID, r4
ld r3, STOP_LDBAR(r13)
ld r4, STOP_FSCR(r13)
mtspr SPRN_LDBAR, r3
mtspr SPRN_FSCR, r4
ld r3, STOP_HFSCR(r13)
ld r4, STOP_MMCRA(r13)
mtspr SPRN_HFSCR, r3
mtspr SPRN_MMCRA, r4
ld r3, _MMCR0(r1)
ld r4, STOP_MMCR1(r13)
mtspr SPRN_MMCR0, r3
mtspr SPRN_MMCR1, r4
ld r3, STOP_MMCR2(r13)
mtspr SPRN_MMCR2, r3
blr
/*
* Used by threads when the lock bit of core_idle_state is set.
* Threads will spin in HMT_LOW until the lock bit is cleared.
* r14 - pointer to core_idle_state
* r15 - used to load contents of core_idle_state
* r9 - used as a temporary variable
*/
core_idle_lock_held:
HMT_LOW
3: lwz r15,0(r14)
andis. r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
bne 3b
HMT_MEDIUM
lwarx r15,0,r14
andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
bne- core_idle_lock_held
blr
/*
* Pass requested state in r3:
* r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8
* - Requested PSSCR value in POWER9
*
* Address of idle handler to branch to in realmode in r4
*/
pnv_powersave_common:
/* Use r3 to pass state nap/sleep/winkle */
/* NAP is a state loss, we create a regs frame on the
* stack, fill it up with the state we care about and
* stick a pointer to it in PACAR1. We really only
* need to save PC, some CR bits and the NV GPRs,
* but for now an interrupt frame will do.
*/
mtctr r4
mflr r0
std r0,16(r1)
stdu r1,-INT_FRAME_SIZE(r1)
std r0,_LINK(r1)
std r0,_NIP(r1)
/* We haven't lost state ... yet */
li r0,0
stb r0,PACA_NAPSTATELOST(r13)
/* Continue saving state */
SAVE_GPR(2, r1)
SAVE_NVGPRS(r1)
mfcr r5
std r5,_CCR(r1)
std r1,PACAR1(r13)
BEGIN_FTR_SECTION
/*
* POWER9 does not require real mode to stop, and presently does not
* set hwthread_state for KVM (threads don't share MMU context), so
* we can remain in virtual mode for this.
*/
bctr
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
/*
* POWER8
* Go to real mode to do the nap, as required by the architecture.
* Also, we need to be in real mode before setting hwthread_state,
* because as soon as we do that, another thread can switch
* the MMU context to the guest.
*/
LOAD_REG_IMMEDIATE(r7, MSR_IDLE)
mtmsrd r7,0
bctr
/*
* This is the sequence required to execute idle instructions, as
* specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
*/
#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
/* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
std r0,0(r1); \
ptesync; \
ld r0,0(r1); \
236: cmpd cr0,r0,r0; \
bne 236b; \
IDLE_INST;
.globl pnv_enter_arch207_idle_mode
pnv_enter_arch207_idle_mode:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/* Tell KVM we're entering idle */
li r4,KVM_HWTHREAD_IN_IDLE
/******************************************************/
/* N O T E W E L L ! ! ! N O T E W E L L */
/* The following store to HSTATE_HWTHREAD_STATE(r13) */
/* MUST occur in real mode, i.e. with the MMU off, */
/* and the MMU must stay off until we clear this flag */
/* and test HSTATE_HWTHREAD_REQ(r13) in */
/* pnv_powersave_wakeup in this file. */
/* The reason is that another thread can switch the */
/* MMU to a guest context whenever this flag is set */
/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on, */
/* that would potentially cause this thread to start */
/* executing instructions from guest memory in */
/* hypervisor mode, leading to a host crash or data */
/* corruption, or worse. */
/******************************************************/
stb r4,HSTATE_HWTHREAD_STATE(r13)
#endif
stb r3,PACA_THREAD_IDLE_STATE(r13)
cmpwi cr3,r3,PNV_THREAD_SLEEP
bge cr3,2f
IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
/* No return */
2:
/* Sleep or winkle */
lbz r7,PACA_THREAD_MASK(r13)
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
li r5,0
beq cr3,3f
lis r5,PNV_CORE_IDLE_WINKLE_COUNT@h
3:
lwarx_loop1:
lwarx r15,0,r14
andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
bnel- core_idle_lock_held
add r15,r15,r5 /* Add if winkle */
andc r15,r15,r7 /* Clear thread bit */
andi. r9,r15,PNV_CORE_IDLE_THREAD_BITS
/*
* If cr0 = 0, then current thread is the last thread of the core entering
* sleep. Last thread needs to execute the hardware bug workaround code if
* required by the platform.
* Make the workaround call unconditionally here. The below branch call is
* patched out when the idle states are discovered if the platform does not
* require it.
*/
.global pnv_fastsleep_workaround_at_entry
pnv_fastsleep_workaround_at_entry:
beq fastsleep_workaround_at_entry
stwcx. r15,0,r14
bne- lwarx_loop1
isync
common_enter: /* common code for all the threads entering sleep or winkle */
bgt cr3,enter_winkle
IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
fastsleep_workaround_at_entry:
oris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
stwcx. r15,0,r14
bne- lwarx_loop1
isync
/* Fast sleep workaround */
li r3,1
li r4,1
bl opal_config_cpu_idle_state
/* Unlock */
xoris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
lwsync
stw r15,0(r14)
b common_enter
enter_winkle:
bl save_sprs_to_stack
IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
/*
* r3 - PSSCR value corresponding to the requested stop state.
*/
power_enter_stop:
/*
* Check if we are executing the lite variant with ESL=EC=0
*/
andis. r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
clrldi r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
bne .Lhandle_esl_ec_set
PPC_STOP
li r3,0 /* Since we didn't lose state, return 0 */
std r3, PACA_REQ_PSSCR(r13)
/*
* pnv_wakeup_noloss() expects r12 to contain the SRR1 value so
* it can determine if the wakeup reason is an HMI in
* CHECK_HMI_INTERRUPT.
*
* However, when we wakeup with ESL=0, SRR1 will not contain the wakeup
* reason, so there is no point setting r12 to SRR1.
*
* Further, we clear r12 here, so that we don't accidentally enter the
* HMI in pnv_wakeup_noloss() if the value of r12[42:45] == WAKE_HMI.
*/
li r12, 0
b pnv_wakeup_noloss
.Lhandle_esl_ec_set:
BEGIN_FTR_SECTION
/*
* POWER9 DD2.0 or earlier can incorrectly set PMAO when waking up after
* a state-loss idle. Saving and restoring MMCR0 over idle is a
* workaround.
*/
mfspr r4,SPRN_MMCR0
std r4,_MMCR0(r1)
END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
/*
* Check if the requested state is a deep idle state.
*/
LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
ld r4,ADDROFF(pnv_first_deep_stop_state)(r5)
cmpd r3,r4
bge .Lhandle_deep_stop
PPC_STOP /* Does not return (system reset interrupt) */
.Lhandle_deep_stop:
/*
* Entering deep idle state.
* Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
* stack and enter stop
*/
lbz r7,PACA_THREAD_MASK(r13)
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
lwarx_loop_stop:
lwarx r15,0,r14
andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
bnel- core_idle_lock_held
andc r15,r15,r7 /* Clear thread bit */
stwcx. r15,0,r14
bne- lwarx_loop_stop
isync
bl save_sprs_to_stack
PPC_STOP /* Does not return (system reset interrupt) */
/*
* Entered with MSR[EE]=0 and no soft-masked interrupts pending.
* r3 contains desired idle state (PNV_THREAD_NAP/SLEEP/WINKLE).
*/
_GLOBAL(power7_idle_insn)
/* Now check if user or arch enabled NAP mode */
LOAD_REG_ADDR(r4, pnv_enter_arch207_idle_mode)
b pnv_powersave_common
#define CHECK_HMI_INTERRUPT \
BEGIN_FTR_SECTION_NESTED(66); \
rlwinm r0,r12,45-31,0xf; /* extract wake reason field (P8) */ \
FTR_SECTION_ELSE_NESTED(66); \
rlwinm r0,r12,45-31,0xe; /* P7 wake reason field is 3 bits */ \
ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \
cmpwi r0,0xa; /* Hypervisor maintenance ? */ \
bne+ 20f; \
/* Invoke opal call to handle hmi */ \
ld r2,PACATOC(r13); \
ld r1,PACAR1(r13); \
std r3,ORIG_GPR3(r1); /* Save original r3 */ \
li r3,0; /* NULL argument */ \
bl hmi_exception_realmode; \
nop; \
ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \
20: nop;
/*
* Entered with MSR[EE]=0 and no soft-masked interrupts pending.
* r3 contains desired PSSCR register value.
*
* Offline (CPU unplug) case also must notify KVM that the CPU is
* idle.
*/
_GLOBAL(power9_offline_stop)
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/*
* Tell KVM we're entering idle.
* This does not have to be done in real mode because the P9 MMU
* is independent per-thread. Some steppings share radix/hash mode
* between threads, but in that case KVM has a barrier sync in real
* mode before and after switching between radix and hash.
*/
li r4,KVM_HWTHREAD_IN_IDLE
stb r4,HSTATE_HWTHREAD_STATE(r13)
#endif
/* fall through */
_GLOBAL(power9_idle_stop)
std r3, PACA_REQ_PSSCR(r13)
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
BEGIN_FTR_SECTION
sync
lwz r5, PACA_DONT_STOP(r13)
cmpwi r5, 0
bne 1f
END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
#endif
mtspr SPRN_PSSCR,r3
LOAD_REG_ADDR(r4,power_enter_stop)
b pnv_powersave_common
/* No return */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
1:
/*
* We get here when TM / thread reconfiguration bug workaround
* code wants to get the CPU into SMT4 mode, and therefore
* we are being asked not to stop.
*/
li r3, 0
std r3, PACA_REQ_PSSCR(r13)
blr /* return 0 for wakeup cause / SRR1 value */
#endif
/*
* On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1,
* HSPRG0 will be set to the HSPRG0 value of one of the
* threads in this core. Thus the value we have in r13
* may not be this thread's paca pointer.
*
* Fortunately, the TIR remains invariant. Since this thread's
* paca pointer is recorded in all its sibling's paca, we can
* correctly recover this thread's paca pointer if we
* know the index of this thread in the core.
*
* This index can be obtained from the TIR.
*
* i.e, thread's position in the core = TIR.
* If this value is i, then this thread's paca is
* paca->thread_sibling_pacas[i].
*/
power9_dd1_recover_paca:
mfspr r4, SPRN_TIR
/*
* Since each entry in thread_sibling_pacas is 8 bytes
* we need to left-shift by 3 bits. Thus r4 = i * 8
*/
sldi r4, r4, 3
/* Get &paca->thread_sibling_pacas[0] in r5 */
ld r5, PACA_SIBLING_PACA_PTRS(r13)
/* Load paca->thread_sibling_pacas[i] into r13 */
ldx r13, r4, r5
SET_PACA(r13)
/*
* Indicate that we have lost NVGPR state
* which needs to be restored from the stack.
*/
li r3, 1
stb r3,PACA_NAPSTATELOST(r13)
blr
/*
* Called from machine check handler for powersave wakeups.
* Low level machine check processing has already been done. Now just
* go through the wake up path to get everything in order.
*
* r3 - The original SRR1 value.
* Original SRR[01] have been clobbered.
* MSR_RI is clear.
*/
.global pnv_powersave_wakeup_mce
pnv_powersave_wakeup_mce:
/* Set cr3 for pnv_powersave_wakeup */
rlwinm r11,r3,47-31,30,31
cmpwi cr3,r11,2
/*
* Now put the original SRR1 with SRR1_WAKEMCE_RESVD as the wake
* reason into r12, which allows reuse of the system reset wakeup
* code without being mistaken for another type of wakeup.
*/
oris r12,r3,SRR1_WAKEMCE_RESVD@h
b pnv_powersave_wakeup
/*
* Called from reset vector for powersave wakeups.
* cr3 - set to gt if waking up with partial/complete hypervisor state loss
* r12 - SRR1
*/
.global pnv_powersave_wakeup
pnv_powersave_wakeup:
ld r2, PACATOC(r13)
BEGIN_FTR_SECTION
BEGIN_FTR_SECTION_NESTED(70)
bl power9_dd1_recover_paca
END_FTR_SECTION_NESTED_IFSET(CPU_FTR_POWER9_DD1, 70)
bl pnv_restore_hyp_resource_arch300
FTR_SECTION_ELSE
bl pnv_restore_hyp_resource_arch207
ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
li r0,PNV_THREAD_RUNNING
stb r0,PACA_THREAD_IDLE_STATE(r13) /* Clear thread state */
mr r3,r12
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
lbz r0,HSTATE_HWTHREAD_STATE(r13)
cmpwi r0,KVM_HWTHREAD_IN_KERNEL
beq 0f
li r0,KVM_HWTHREAD_IN_KERNEL
stb r0,HSTATE_HWTHREAD_STATE(r13)
/* Order setting hwthread_state vs. testing hwthread_req */
sync
0: lbz r0,HSTATE_HWTHREAD_REQ(r13)
cmpwi r0,0
beq 1f
b kvm_start_guest
1:
#endif
/* Return SRR1 from power7_nap() */
blt cr3,pnv_wakeup_noloss
b pnv_wakeup_loss
/*
* Check whether we have woken up with hypervisor state loss.
* If yes, restore hypervisor state and return back to link.
*
* cr3 - set to gt if waking up with partial/complete hypervisor state loss
*/
pnv_restore_hyp_resource_arch300:
/*
* Workaround for POWER9, if we lost resources, the ERAT
* might have been mixed up and needs flushing. We also need
* to reload MMCR0 (see comment above). We also need to set
* then clear bit 60 in MMCRA to ensure the PMU starts running.
*/
blt cr3,1f
BEGIN_FTR_SECTION
PPC_INVALIDATE_ERAT
ld r1,PACAR1(r13)
ld r4,_MMCR0(r1)
mtspr SPRN_MMCR0,r4
END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
mfspr r4,SPRN_MMCRA
ori r4,r4,(1 << (63-60))
mtspr SPRN_MMCRA,r4
xori r4,r4,(1 << (63-60))
mtspr SPRN_MMCRA,r4
1:
/*
* POWER ISA 3. Use PSSCR to determine if we
* are waking up from deep idle state
*/
LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
ld r4,ADDROFF(pnv_first_deep_stop_state)(r5)
BEGIN_FTR_SECTION_NESTED(71)
/*
* Assume that we are waking up from the state
* same as the Requested Level (RL) in the PSSCR
* which are Bits 60-63
*/
ld r5,PACA_REQ_PSSCR(r13)
rldicl r5,r5,0,60
FTR_SECTION_ELSE_NESTED(71)
/*
* 0-3 bits correspond to Power-Saving Level Status
* which indicates the idle state we are waking up from
*/
mfspr r5, SPRN_PSSCR
rldicl r5,r5,4,60
ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71)
li r0, 0 /* clear requested_psscr to say we're awake */
std r0, PACA_REQ_PSSCR(r13)
cmpd cr4,r5,r4
bge cr4,pnv_wakeup_tb_loss /* returns to caller */
blr /* Waking up without hypervisor state loss. */
/* Same calling convention as arch300 */
pnv_restore_hyp_resource_arch207:
/*
* POWER ISA 2.07 or less.
* Check if we slept with sleep or winkle.
*/
lbz r4,PACA_THREAD_IDLE_STATE(r13)
cmpwi cr2,r4,PNV_THREAD_NAP
bgt cr2,pnv_wakeup_tb_loss /* Either sleep or Winkle */
/*
* We fall through here if PACA_THREAD_IDLE_STATE shows we are waking
* up from nap. At this stage CR3 shouldn't contains 'gt' since that
* indicates we are waking with hypervisor state loss from nap.
*/
bgt cr3,.
blr /* Waking up without hypervisor state loss */
/*
* Called if waking up from idle state which can cause either partial or
* complete hyp state loss.
* In POWER8, called if waking up from fastsleep or winkle
* In POWER9, called if waking up from stop state >= pnv_first_deep_stop_state
*
* r13 - PACA
* cr3 - gt if waking up with partial/complete hypervisor state loss
*
* If ISA300:
* cr4 - gt or eq if waking up from complete hypervisor state loss.
*
* If ISA207:
* r4 - PACA_THREAD_IDLE_STATE
*/
pnv_wakeup_tb_loss:
ld r1,PACAR1(r13)
/*
* Before entering any idle state, the NVGPRs are saved in the stack.
* If there was a state loss, or PACA_NAPSTATELOST was set, then the
* NVGPRs are restored. If we are here, it is likely that state is lost,
* but not guaranteed -- neither ISA207 nor ISA300 tests to reach
* here are the same as the test to restore NVGPRS:
* PACA_THREAD_IDLE_STATE test for ISA207, PSSCR test for ISA300,
* and SRR1 test for restoring NVGPRs.
*
* We are about to clobber NVGPRs now, so set NAPSTATELOST to
* guarantee they will always be restored. This might be tightened
* with careful reading of specs (particularly for ISA300) but this
* is already a slow wakeup path and it's simpler to be safe.
*/
li r0,1
stb r0,PACA_NAPSTATELOST(r13)
/*
*
* Save SRR1 and LR in NVGPRs as they might be clobbered in
* opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
* to determine the wakeup reason if we branch to kvm_start_guest. LR
* is required to return back to reset vector after hypervisor state
* restore is complete.
*/
mr r19,r12
mr r18,r4
mflr r17
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
lbz r7,PACA_THREAD_MASK(r13)
/*
* Take the core lock to synchronize against other threads.
*
* Lock bit is set in one of the 2 cases-
* a. In the sleep/winkle enter path, the last thread is executing
* fastsleep workaround code.
* b. In the wake up path, another thread is executing fastsleep
* workaround undo code or resyncing timebase or restoring context
* In either case loop until the lock bit is cleared.
*/
1:
lwarx r15,0,r14
andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
bnel- core_idle_lock_held
oris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
stwcx. r15,0,r14
bne- 1b
isync
andi. r9,r15,PNV_CORE_IDLE_THREAD_BITS
cmpwi cr2,r9,0
/*
* At this stage
* cr2 - eq if first thread to wakeup in core
* cr3- gt if waking up with partial/complete hypervisor state loss
* ISA300:
* cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
BEGIN_FTR_SECTION
/*
* Were we in winkle?
* If yes, check if all threads were in winkle, decrement our
* winkle count, set all thread winkle bits if all were in winkle.
* Check if our thread has a winkle bit set, and set cr4 accordingly
* (to match ISA300, above). Pseudo-code for core idle state
* transitions for ISA207 is as follows (everything happens atomically
* due to store conditional and/or lock bit):
*
* nap_idle() { }
* nap_wake() { }
*
* sleep_idle()
* {
* core_idle_state &= ~thread_in_core
* }
*
* sleep_wake()
* {
* bool first_in_core, first_in_subcore;
*
* first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
* first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
*
* core_idle_state |= thread_in_core;
* }
*
* winkle_idle()
* {
* core_idle_state &= ~thread_in_core;
* core_idle_state += 1 << WINKLE_COUNT_SHIFT;
* }
*
* winkle_wake()
* {
* bool first_in_core, first_in_subcore, winkle_state_lost;
*
* first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
* first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
*
* core_idle_state |= thread_in_core;
*
* if ((core_idle_state & WINKLE_MASK) == (8 << WINKLE_COUNT_SIHFT))
* core_idle_state |= THREAD_WINKLE_BITS;
* core_idle_state -= 1 << WINKLE_COUNT_SHIFT;
*
* winkle_state_lost = core_idle_state &
* (thread_in_core << WINKLE_THREAD_SHIFT);
* core_idle_state &= ~(thread_in_core << WINKLE_THREAD_SHIFT);
* }
*
*/
cmpwi r18,PNV_THREAD_WINKLE
bne 2f
andis. r9,r15,PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT@h
subis r15,r15,PNV_CORE_IDLE_WINKLE_COUNT@h
beq 2f
ori r15,r15,PNV_CORE_IDLE_THREAD_WINKLE_BITS /* all were winkle */
2:
/* Shift thread bit to winkle mask, then test if this thread is set,
* and remove it from the winkle bits */
slwi r8,r7,8
and r8,r8,r15
andc r15,r15,r8
cmpwi cr4,r8,1 /* cr4 will be gt if our bit is set, lt if not */
lbz r4,PACA_SUBCORE_SIBLING_MASK(r13)
and r4,r4,r15
cmpwi r4,0 /* Check if first in subcore */
or r15,r15,r7 /* Set thread bit */
beq first_thread_in_subcore
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
or r15,r15,r7 /* Set thread bit */
beq cr2,first_thread_in_core
/* Not first thread in core or subcore to wake up */
b clear_lock
first_thread_in_subcore:
/*
* If waking up from sleep, subcore state is not lost. Hence
* skip subcore state restore
*/
blt cr4,subcore_state_restored
/* Restore per-subcore state */
ld r4,_SDR1(r1)
mtspr SPRN_SDR1,r4
ld r4,_RPR(r1)
mtspr SPRN_RPR,r4
ld r4,_AMOR(r1)
mtspr SPRN_AMOR,r4
subcore_state_restored:
/*
* Check if the thread is also the first thread in the core. If not,
* skip to clear_lock.
*/
bne cr2,clear_lock
first_thread_in_core:
/*
* First thread in the core waking up from any state which can cause
* partial or complete hypervisor state loss. It needs to
* call the fastsleep workaround code if the platform requires it.
* Call it unconditionally here. The below branch instruction will
* be patched out if the platform does not have fastsleep or does not
* require the workaround. Patching will be performed during the
* discovery of idle-states.
*/
.global pnv_fastsleep_workaround_at_exit
pnv_fastsleep_workaround_at_exit:
b fastsleep_workaround_at_exit
timebase_resync:
/*
* Use cr3 which indicates that we are waking up with atleast partial
* hypervisor state loss to determine if TIMEBASE RESYNC is needed.
*/
ble cr3,.Ltb_resynced
/* Time base re-sync */
bl opal_resync_timebase;
/*
* If waking up from sleep (POWER8), per core state
* is not lost, skip to clear_lock.
*/
.Ltb_resynced:
blt cr4,clear_lock
/*
* First thread in the core to wake up and its waking up with
* complete hypervisor state loss. Restore per core hypervisor
* state.
*/
BEGIN_FTR_SECTION
ld r4,_PTCR(r1)
mtspr SPRN_PTCR,r4
ld r4,_RPR(r1)
mtspr SPRN_RPR,r4
ld r4,_AMOR(r1)
mtspr SPRN_AMOR,r4
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
ld r4,_TSCR(r1)
mtspr SPRN_TSCR,r4
ld r4,_WORC(r1)
mtspr SPRN_WORC,r4
clear_lock:
xoris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
lwsync
stw r15,0(r14)
common_exit:
/*
* Common to all threads.
*
* If waking up from sleep, hypervisor state is not lost. Hence
* skip hypervisor state restore.
*/
blt cr4,hypervisor_state_restored
/* Waking up from winkle */
BEGIN_MMU_FTR_SECTION
b no_segments
END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
/* Restore SLB from PACA */
ld r8,PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
li r3, SLBSHADOW_SAVEAREA
LDX_BE r5, r8, r3
addi r3, r3, 8
LDX_BE r6, r8, r3
andis. r7,r5,SLB_ESID_V@h
beq 1f
slbmte r6,r5
1: addi r8,r8,16
.endr
no_segments:
/* Restore per thread state */
ld r4,_SPURR(r1)
mtspr SPRN_SPURR,r4
ld r4,_PURR(r1)
mtspr SPRN_PURR,r4
ld r4,_DSCR(r1)
mtspr SPRN_DSCR,r4
ld r4,_WORT(r1)
mtspr SPRN_WORT,r4
/* Call cur_cpu_spec->cpu_restore() */
LOAD_REG_ADDR(r4, cur_cpu_spec)
ld r4,0(r4)
ld r12,CPU_SPEC_RESTORE(r4)
#ifdef PPC64_ELF_ABI_v1
ld r12,0(r12)
#endif
mtctr r12
bctrl
/*
* On POWER9, we can come here on wakeup from a cpuidle stop state.
* Hence restore the additional SPRs to the saved value.
*
* On POWER8, we come here only on winkle. Since winkle is used
* only in the case of CPU-Hotplug, we don't need to restore
* the additional SPRs.
*/
BEGIN_FTR_SECTION
bl power9_restore_additional_sprs
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
hypervisor_state_restored:
mr r12,r19
mtlr r17
blr /* return to pnv_powersave_wakeup */
fastsleep_workaround_at_exit:
li r3,1
li r4,0
bl opal_config_cpu_idle_state
b timebase_resync
/*
* R3 here contains the value that will be returned to the caller
* of power7_nap.
* R12 contains SRR1 for CHECK_HMI_INTERRUPT.
*/
.global pnv_wakeup_loss
pnv_wakeup_loss:
ld r1,PACAR1(r13)
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
REST_NVGPRS(r1)
REST_GPR(2, r1)
ld r4,PACAKMSR(r13)
ld r5,_LINK(r1)
ld r6,_CCR(r1)
addi r1,r1,INT_FRAME_SIZE
mtlr r5
mtcr r6
mtmsrd r4
blr
/*
* R3 here contains the value that will be returned to the caller
* of power7_nap.
* R12 contains SRR1 for CHECK_HMI_INTERRUPT.
*/
pnv_wakeup_noloss:
lbz r0,PACA_NAPSTATELOST(r13)
cmpwi r0,0
bne pnv_wakeup_loss
ld r1,PACAR1(r13)
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
ld r4,PACAKMSR(r13)
ld r5,_NIP(r1)
ld r6,_CCR(r1)
addi r1,r1,INT_FRAME_SIZE
mtlr r5
mtcr r6
mtmsrd r4
blr