linux-stable/arch/powerpc/kernel/idle_book3s.S
Nicholas Piggin 6d98ce0be5 powerpc/64s: Fix idle wakeup potential to clobber registers
We concluded there may be a window where the idle wakeup code could get
to pnv_wakeup_tb_loss() (which clobbers non-volatile GPRs), but the
hardware may set SRR1[46:47] to 01b (no state loss) which would result
in the wakeup code failing to restore non-volatile GPRs.

I was not able to trigger this condition with trivial tests on real
hardware or simulator, but the ISA (at least 2.07) seems to allow for
it, and Gautham says that it can happen if there is an exception pending
when the sleep/winkle instruction is executed.

Fixes: 1706567117 ("powerpc/kvm: make hypervisor state restore a function")
Cc: stable@vger.kernel.org # v4.8+
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-03-20 20:35:12 +11:00

702 lines
17 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/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 _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
#define _PTCR 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
mfspr r3,SPRN_PTCR
std r3,_PTCR(r1)
/*
* Note - SDR1 is dropped in Power ISA v3. Hence not restoring
* SDR1 here
*/
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)
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)
andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT
bne 3b
HMT_MEDIUM
lwarx r15,0,r14
andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
bne core_idle_lock_held
blr
/*
* Pass requested state in r3:
* r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8
* - Requested STOP state in POWER9
*
* To check IRQ_HAPPENED in r4
* 0 - don't check
* 1 - check
*
* Address to 'rfid' to in r5
*/
_GLOBAL(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.
*/
mflr r0
std r0,16(r1)
stdu r1,-INT_FRAME_SIZE(r1)
std r0,_LINK(r1)
std r0,_NIP(r1)
/* 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(r7, MSR_IDLE)
li r6, MSR_RI
andc r6, r9, r6
mtmsrd r6, 1 /* clear RI before setting SRR0/1 */
mtspr SPRN_SRR0, r5
mtspr SPRN_SRR1, r7
rfid
.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 the system */
/* reset interrupt vector in exceptions-64s.S. */
/* 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)
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_NORET(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
bl opal_config_cpu_idle_state
/* Clear Lock bit */
li r0,0
lwsync
stw r0,0(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:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/* Tell KVM we're entering idle */
li r4,KVM_HWTHREAD_IN_IDLE
/* DO THIS IN REAL MODE! See comment above. */
stb r4,HSTATE_HWTHREAD_STATE(r13)
#endif
/*
* 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
IDLE_STATE_ENTER_SEQ(PPC_STOP)
li r3,0 /* Since we didn't lose state, return 0 */
b pnv_wakeup_noloss
.Lhandle_esl_ec_set:
/*
* 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
IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
.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
andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
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
IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
_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
LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
b pnv_powersave_common
/* No return */
_GLOBAL(power7_sleep)
li r3,PNV_THREAD_SLEEP
li r4,1
LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
b pnv_powersave_common
/* No return */
_GLOBAL(power7_winkle)
li r3,PNV_THREAD_WINKLE
li r4,1
LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
b pnv_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 r3,0; /* NULL argument */ \
bl hmi_exception_realmode; \
nop; \
ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \
20: nop;
/*
* r3 - The PSSCR value corresponding to the stop state.
* r4 - The PSSCR mask corrresonding to the stop state.
*/
_GLOBAL(power9_idle_stop)
mfspr r5,SPRN_PSSCR
andc r5,r5,r4
or r3,r3,r5
mtspr SPRN_PSSCR,r3
LOAD_REG_ADDR(r5,power_enter_stop)
li r4,1
b pnv_powersave_common
/* No return */
/*
* Called from reset vector. Check whether we have woken up with
* hypervisor state loss. If yes, restore hypervisor state and return
* back to reset vector.
*
* r13 - Contents of HSPRG0
* cr3 - set to gt if waking up with partial/complete hypervisor state loss
*/
_GLOBAL(pnv_restore_hyp_resource)
BEGIN_FTR_SECTION
ld r2,PACATOC(r13);
/*
* 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)
mfspr r5,SPRN_PSSCR
/*
* 0-3 bits correspond to Power-Saving Level Status
* which indicates the idle state we are waking up from
*/
rldicl r5,r5,4,60
cmpd cr4,r5,r4
bge cr4,pnv_wakeup_tb_loss
/*
* Waking up without hypervisor state loss. Return to
* reset vector
*/
blr
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
/*
* POWER ISA 2.07 or less.
* Check if last bit of HSPGR0 is set. This indicates whether we are
* waking up from winkle.
*/
clrldi r5,r13,63
clrrdi r13,r13,1
/* Now that we are sure r13 is corrected, load TOC */
ld r2,PACATOC(r13);
cmpwi cr4,r5,1
mtspr SPRN_HSPRG0,r13
lbz r0,PACA_THREAD_IDLE_STATE(r13)
cmpwi cr2,r0,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 /* Return back to System Reset vector from where
pnv_restore_hyp_resource was invoked */
/*
* 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
* cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
_GLOBAL(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.
*/
mflr r17
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
/*
* At this stage
* cr2 - eq if first thread to wakeup in core
* cr3- gt if waking up with partial/complete hypervisor state loss
* cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
stwcx. r15,0,r14
bne- lwarx_loop2
isync
BEGIN_FTR_SECTION
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,clear_lock
/* Time base re-sync */
bl opal_resync_timebase;
/*
* If waking up from sleep, per core state is not lost, skip to
* clear_lock.
*/
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
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:
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.
*/
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
hypervisor_state_restored:
mtspr SPRN_SRR1,r16
mtlr r17
blr /* Return back to System Reset vector from where
pnv_restore_hyp_resource was invoked */
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.
*/
_GLOBAL(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 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(pnv_wakeup_noloss)
lbz r0,PACA_NAPSTATELOST(r13)
cmpwi r0,0
bne pnv_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