linux/arch/powerpc/kernel/idle_power7.S
Shreyas B. Prabhu b32aadc1a8 powerpc/powernv: Fix race in updating core_idle_state
core_idle_state is maintained for each core. It uses 0-7 bits to track
whether a thread in the core has entered fastsleep or winkle. 8th bit is
used as a lock bit.
The lock bit is set in these 2 scenarios-
 - The thread is first in subcore to wakeup from sleep/winkle.
 - If its the last thread in the core about to enter sleep/winkle

While the lock bit is set, if any other thread in the core wakes up, it
loops until the lock bit is cleared before proceeding in the wakeup
path. This helps prevent race conditions w.r.t fastsleep workaround and
prevents threads from switching to process context before core/subcore
resources are restored.

But, in the path to sleep/winkle entry, we currently don't check for
lock-bit. This exposes us to following race when running with subcore
on-

First thread in the subcorea		Another thread in the same
waking up		   		core entering sleep/winkle

lwarx   r15,0,r14
ori     r15,r15,PNV_CORE_IDLE_LOCK_BIT
stwcx.  r15,0,r14
[Code to restore subcore state]

						lwarx   r15,0,r14
						[clear thread bit]
						stwcx.  r15,0,r14

andi.   r15,r15,PNV_CORE_IDLE_THREAD_BITS
stw     r15,0(r14)

Here, after the thread entering sleep clears its thread bit in
core_idle_state, the value is overwritten by the thread waking up.
In such cases when the core enters fastsleep, code mistakes an idle
thread as running. Because of this, the first thread waking up from
fastsleep which is supposed to resync timebase skips it. So we can
end up having a core with stale timebase value.

This patch fixes the above race by looping on the lock bit even while
entering the idle states.

Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Fixes: 7b54e9f213f76 'powernv/powerpc: Add winkle support for offline cpus'
Cc: stable@vger.kernel.org # 3.19+
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-07-07 10:16:52 +10:00

523 lines
12 KiB
ArmAsm

/*
* This file contains the power_save function for Power7 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/mmu-hash64.h>
#undef DEBUG
/*
* Use unused space in the interrupt stack to save and restore
* registers for winkle support.
*/
#define _SDR1 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
/* Idle state entry routines */
#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
/* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
std r0,0(r1); \
ptesync; \
ld r0,0(r1); \
1: cmp cr0,r0,r0; \
bne 1b; \
IDLE_INST; \
b .
.text
/*
* 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
*/
core_idle_lock_held:
HMT_LOW
3: lwz r15,0(r14)
andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT
bne 3b
HMT_MEDIUM
lwarx r15,0,r14
blr
/*
* Pass requested state in r3:
* r3 - PNV_THREAD_NAP/SLEEP/WINKLE
*
* To check IRQ_HAPPENED in r4
* 0 - don't check
* 1 - check
*/
_GLOBAL(power7_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.
*/
mflr r0
std r0,16(r1)
stdu r1,-INT_FRAME_SIZE(r1)
std r0,_LINK(r1)
std r0,_NIP(r1)
#ifndef CONFIG_SMP
/* Make sure FPU, VSX etc... are flushed as we may lose
* state when going to nap mode
*/
bl discard_lazy_cpu_state
#endif /* CONFIG_SMP */
/* Hard disable interrupts */
mfmsr r9
rldicl r9,r9,48,1
rotldi r9,r9,16
mtmsrd r9,1 /* hard-disable interrupts */
/* Check if something happened while soft-disabled */
lbz r0,PACAIRQHAPPENED(r13)
andi. r0,r0,~PACA_IRQ_HARD_DIS@l
beq 1f
cmpwi cr0,r4,0
beq 1f
addi r1,r1,INT_FRAME_SIZE
ld r0,16(r1)
li r3,0 /* Return 0 (no nap) */
mtlr r0
blr
1: /* We mark irqs hard disabled as this is the state we'll
* be in when returning and we need to tell arch_local_irq_restore()
* about it
*/
li r0,PACA_IRQ_HARD_DIS
stb r0,PACAIRQHAPPENED(r13)
/* 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 r4
std r4,_CCR(r1)
std r9,_MSR(r1)
std r1,PACAR1(r13)
/*
* 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(r5, MSR_IDLE)
li r6, MSR_RI
andc r6, r9, r6
LOAD_REG_ADDR(r7, power7_enter_nap_mode)
mtmsrd r6, 1 /* clear RI before setting SRR0/1 */
mtspr SPRN_SRR0, r7
mtspr SPRN_SRR1, r5
rfid
.globl power7_enter_nap_mode
power7_enter_nap_mode:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/* Tell KVM we're napping */
li r4,KVM_HWTHREAD_IN_NAP
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(PPC_NAP)
/* No return */
2:
/* Sleep or winkle */
lbz r7,PACA_THREAD_MASK(r13)
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
lwarx_loop1:
lwarx r15,0,r14
andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
bnel core_idle_lock_held
andc r15,r15,r7 /* Clear thread bit */
andi. r15,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(PPC_SLEEP)
fastsleep_workaround_at_entry:
ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
stwcx. r15,0,r14
bne- lwarx_loop1
isync
/* Fast sleep workaround */
li r3,1
li r4,1
li r0,OPAL_CONFIG_CPU_IDLE_STATE
bl opal_call_realmode
/* Clear Lock bit */
li r0,0
lwsync
stw r0,0(r14)
b common_enter
enter_winkle:
/*
* 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
*/
mfspr r3,SPRN_SDR1
std r3,_SDR1(r1)
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)
IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
_GLOBAL(power7_idle)
/* Now check if user or arch enabled NAP mode */
LOAD_REG_ADDRBASE(r3,powersave_nap)
lwz r4,ADDROFF(powersave_nap)(r3)
cmpwi 0,r4,0
beqlr
li r3, 1
/* fall through */
_GLOBAL(power7_nap)
mr r4,r3
li r3,PNV_THREAD_NAP
b power7_powersave_common
/* No return */
_GLOBAL(power7_sleep)
li r3,PNV_THREAD_SLEEP
li r4,1
b power7_powersave_common
/* No return */
_GLOBAL(power7_winkle)
li r3,3
li r4,1
b power7_powersave_common
/* No return */
#define CHECK_HMI_INTERRUPT \
mfspr r0,SPRN_SRR1; \
BEGIN_FTR_SECTION_NESTED(66); \
rlwinm r0,r0,45-31,0xf; /* extract wake reason field (P8) */ \
FTR_SECTION_ELSE_NESTED(66); \
rlwinm r0,r0,45-31,0xe; /* 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 r0,OPAL_HANDLE_HMI; /* Pass opal token argument*/ \
bl opal_call_realmode; \
ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \
20: nop;
_GLOBAL(power7_wakeup_tb_loss)
ld r2,PACATOC(r13);
ld r1,PACAR1(r13)
/*
* Before entering any idle state, the NVGPRs are saved in the stack
* and they are restored before switching to the process context. Hence
* until they are restored, they are free to be used.
*
* Save SRR1 in a NVGPR as it might be clobbered in opal_call_realmode
* (called in CHECK_HMI_INTERRUPT). SRR1 is required to determine the
* wakeup reason if we branch to kvm_start_guest.
*/
mfspr r16,SPRN_SRR1
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
lbz r7,PACA_THREAD_MASK(r13)
ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
lwarx_loop2:
lwarx r15,0,r14
andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
/*
* 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.
*/
bnel core_idle_lock_held
cmpwi cr2,r15,0
lbz r4,PACA_SUBCORE_SIBLING_MASK(r13)
and r4,r4,r15
cmpwi cr1,r4,0 /* Check if first in subcore */
/*
* At this stage
* cr1 - 0b0100 if first thread to wakeup in subcore
* cr2 - 0b0100 if first thread to wakeup in core
* cr3- 0b0010 if waking up from sleep or winkle
* cr4 - 0b0100 if waking up from winkle
*/
or r15,r15,r7 /* Set thread bit */
beq cr1,first_thread_in_subcore
/* Not first thread in subcore to wake up */
stwcx. r15,0,r14
bne- lwarx_loop2
isync
b common_exit
first_thread_in_subcore:
/* First thread in subcore to wakeup */
ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
stwcx. r15,0,r14
bne- lwarx_loop2
isync
/*
* If waking up from sleep, subcore state is not lost. Hence
* skip subcore state restore
*/
bne 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 fastsleep. 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 when the idle states are discovered if platform
* does not require workaround.
*/
.global pnv_fastsleep_workaround_at_exit
pnv_fastsleep_workaround_at_exit:
b fastsleep_workaround_at_exit
timebase_resync:
/* Do timebase resync if we are waking up from sleep. Use cr3 value
* set in exceptions-64s.S */
ble cr3,clear_lock
/* Time base re-sync */
li r0,OPAL_RESYNC_TIMEBASE
bl opal_call_realmode;
/* TODO: Check r3 for failure */
/*
* If waking up from sleep, per core state is not lost, skip to
* clear_lock.
*/
bne cr4,clear_lock
/* Restore per core state */
ld r4,_TSCR(r1)
mtspr SPRN_TSCR,r4
ld r4,_WORC(r1)
mtspr SPRN_WORC,r4
clear_lock:
andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS
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.
*/
bne cr4,hypervisor_state_restored
/* Waking up from winkle */
/* Restore per thread state */
bl __restore_cpu_power8
/* 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
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
hypervisor_state_restored:
li r5,PNV_THREAD_RUNNING
stb r5,PACA_THREAD_IDLE_STATE(r13)
mtspr SPRN_SRR1,r16
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
li r0,KVM_HWTHREAD_IN_KERNEL
stb r0,HSTATE_HWTHREAD_STATE(r13)
/* Order setting hwthread_state vs. testing hwthread_req */
sync
lbz r0,HSTATE_HWTHREAD_REQ(r13)
cmpwi r0,0
beq 6f
b kvm_start_guest
6:
#endif
REST_NVGPRS(r1)
REST_GPR(2, r1)
ld r3,_CCR(r1)
ld r4,_MSR(r1)
ld r5,_NIP(r1)
addi r1,r1,INT_FRAME_SIZE
mtcr r3
mfspr r3,SPRN_SRR1 /* Return SRR1 */
mtspr SPRN_SRR1,r4
mtspr SPRN_SRR0,r5
rfid
fastsleep_workaround_at_exit:
li r3,1
li r4,0
li r0,OPAL_CONFIG_CPU_IDLE_STATE
bl opal_call_realmode
b timebase_resync
/*
* R3 here contains the value that will be returned to the caller
* of power7_nap.
*/
_GLOBAL(power7_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 r6,_CCR(r1)
ld r4,_MSR(r1)
ld r5,_NIP(r1)
addi r1,r1,INT_FRAME_SIZE
mtcr r6
mtspr SPRN_SRR1,r4
mtspr SPRN_SRR0,r5
rfid
/*
* R3 here contains the value that will be returned to the caller
* of power7_nap.
*/
_GLOBAL(power7_wakeup_noloss)
lbz r0,PACA_NAPSTATELOST(r13)
cmpwi r0,0
bne power7_wakeup_loss
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
ld r1,PACAR1(r13)
ld r6,_CCR(r1)
ld r4,_MSR(r1)
ld r5,_NIP(r1)
addi r1,r1,INT_FRAME_SIZE
mtcr r6
mtspr SPRN_SRR1,r4
mtspr SPRN_SRR0,r5
rfid