alistair23-linux/arch/powerpc/kernel/idle_power7.S

245 lines
5.3 KiB
ArmAsm
Raw Normal View History

/*
powerpc: Rework lazy-interrupt handling The current implementation of lazy interrupts handling has some issues that this tries to address. We don't do the various workarounds we need to do when re-enabling interrupts in some cases such as when returning from an interrupt and thus we may still lose or get delayed decrementer or doorbell interrupts. The current scheme also makes it much harder to handle the external "edge" interrupts provided by some BookE processors when using the EPR facility (External Proxy) and the Freescale Hypervisor. Additionally, we tend to keep interrupts hard disabled in a number of cases, such as decrementer interrupts, external interrupts, or when a masked decrementer interrupt is pending. This is sub-optimal. This is an attempt at fixing it all in one go by reworking the way we do the lazy interrupt disabling from the ground up. The base idea is to replace the "hard_enabled" field with a "irq_happened" field in which we store a bit mask of what interrupt occurred while soft-disabled. When re-enabling, either via arch_local_irq_restore() or when returning from an interrupt, we can now decide what to do by testing bits in that field. We then implement replaying of the missed interrupts either by re-using the existing exception frame (in exception exit case) or via the creation of a new one from an assembly trampoline (in the arch_local_irq_enable case). This removes the need to play with the decrementer to try to create fake interrupts, among others. In addition, this adds a few refinements: - We no longer hard disable decrementer interrupts that occur while soft-disabled. We now simply bump the decrementer back to max (on BookS) or leave it stopped (on BookE) and continue with hard interrupts enabled, which means that we'll potentially get better sample quality from performance monitor interrupts. - Timer, decrementer and doorbell interrupts now hard-enable shortly after removing the source of the interrupt, which means they no longer run entirely hard disabled. Again, this will improve perf sample quality. - On Book3E 64-bit, we now make the performance monitor interrupt act as an NMI like Book3S (the necessary C code for that to work appear to already be present in the FSL perf code, notably calling nmi_enter instead of irq_enter). (This also fixes a bug where BookE perfmon interrupts could clobber r14 ... oops) - We could make "masked" decrementer interrupts act as NMIs when doing timer-based perf sampling to improve the sample quality. Signed-off-by-yet: Benjamin Herrenschmidt <benh@kernel.crashing.org> --- v2: - Add hard-enable to decrementer, timer and doorbells - Fix CR clobber in masked irq handling on BookE - Make embedded perf interrupt act as an NMI - Add a PACA_HAPPENED_EE_EDGE for use by FSL if they want to retrigger an interrupt without preventing hard-enable v3: - Fix or vs. ori bug on Book3E - Fix enabling of interrupts for some exceptions on Book3E v4: - Fix resend of doorbells on return from interrupt on Book3E v5: - Rebased on top of my latest series, which involves some significant rework of some aspects of the patch. v6: - 32-bit compile fix - more compile fixes with various .config combos - factor out the asm code to soft-disable interrupts - remove the C wrapper around preempt_schedule_irq v7: - Fix a bug with hard irq state tracking on native power7
2012-03-06 00:27:59 -07:00
* 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>
powerpc: Rework lazy-interrupt handling The current implementation of lazy interrupts handling has some issues that this tries to address. We don't do the various workarounds we need to do when re-enabling interrupts in some cases such as when returning from an interrupt and thus we may still lose or get delayed decrementer or doorbell interrupts. The current scheme also makes it much harder to handle the external "edge" interrupts provided by some BookE processors when using the EPR facility (External Proxy) and the Freescale Hypervisor. Additionally, we tend to keep interrupts hard disabled in a number of cases, such as decrementer interrupts, external interrupts, or when a masked decrementer interrupt is pending. This is sub-optimal. This is an attempt at fixing it all in one go by reworking the way we do the lazy interrupt disabling from the ground up. The base idea is to replace the "hard_enabled" field with a "irq_happened" field in which we store a bit mask of what interrupt occurred while soft-disabled. When re-enabling, either via arch_local_irq_restore() or when returning from an interrupt, we can now decide what to do by testing bits in that field. We then implement replaying of the missed interrupts either by re-using the existing exception frame (in exception exit case) or via the creation of a new one from an assembly trampoline (in the arch_local_irq_enable case). This removes the need to play with the decrementer to try to create fake interrupts, among others. In addition, this adds a few refinements: - We no longer hard disable decrementer interrupts that occur while soft-disabled. We now simply bump the decrementer back to max (on BookS) or leave it stopped (on BookE) and continue with hard interrupts enabled, which means that we'll potentially get better sample quality from performance monitor interrupts. - Timer, decrementer and doorbell interrupts now hard-enable shortly after removing the source of the interrupt, which means they no longer run entirely hard disabled. Again, this will improve perf sample quality. - On Book3E 64-bit, we now make the performance monitor interrupt act as an NMI like Book3S (the necessary C code for that to work appear to already be present in the FSL perf code, notably calling nmi_enter instead of irq_enter). (This also fixes a bug where BookE perfmon interrupts could clobber r14 ... oops) - We could make "masked" decrementer interrupts act as NMIs when doing timer-based perf sampling to improve the sample quality. Signed-off-by-yet: Benjamin Herrenschmidt <benh@kernel.crashing.org> --- v2: - Add hard-enable to decrementer, timer and doorbells - Fix CR clobber in masked irq handling on BookE - Make embedded perf interrupt act as an NMI - Add a PACA_HAPPENED_EE_EDGE for use by FSL if they want to retrigger an interrupt without preventing hard-enable v3: - Fix or vs. ori bug on Book3E - Fix enabling of interrupts for some exceptions on Book3E v4: - Fix resend of doorbells on return from interrupt on Book3E v5: - Rebased on top of my latest series, which involves some significant rework of some aspects of the patch. v6: - 32-bit compile fix - more compile fixes with various .config combos - factor out the asm code to soft-disable interrupts - remove the C wrapper around preempt_schedule_irq v7: - Fix a bug with hard irq state tracking on native power7
2012-03-06 00:27:59 -07:00
#include <asm/hw_irq.h>
#include <asm/kvm_book3s_asm.h>
#include <asm/opal.h>
#undef DEBUG
/* 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
/*
* Pass requested state in r3:
* 0 - nap
* 1 - sleep
*
* 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 */
powerpc: Rework lazy-interrupt handling The current implementation of lazy interrupts handling has some issues that this tries to address. We don't do the various workarounds we need to do when re-enabling interrupts in some cases such as when returning from an interrupt and thus we may still lose or get delayed decrementer or doorbell interrupts. The current scheme also makes it much harder to handle the external "edge" interrupts provided by some BookE processors when using the EPR facility (External Proxy) and the Freescale Hypervisor. Additionally, we tend to keep interrupts hard disabled in a number of cases, such as decrementer interrupts, external interrupts, or when a masked decrementer interrupt is pending. This is sub-optimal. This is an attempt at fixing it all in one go by reworking the way we do the lazy interrupt disabling from the ground up. The base idea is to replace the "hard_enabled" field with a "irq_happened" field in which we store a bit mask of what interrupt occurred while soft-disabled. When re-enabling, either via arch_local_irq_restore() or when returning from an interrupt, we can now decide what to do by testing bits in that field. We then implement replaying of the missed interrupts either by re-using the existing exception frame (in exception exit case) or via the creation of a new one from an assembly trampoline (in the arch_local_irq_enable case). This removes the need to play with the decrementer to try to create fake interrupts, among others. In addition, this adds a few refinements: - We no longer hard disable decrementer interrupts that occur while soft-disabled. We now simply bump the decrementer back to max (on BookS) or leave it stopped (on BookE) and continue with hard interrupts enabled, which means that we'll potentially get better sample quality from performance monitor interrupts. - Timer, decrementer and doorbell interrupts now hard-enable shortly after removing the source of the interrupt, which means they no longer run entirely hard disabled. Again, this will improve perf sample quality. - On Book3E 64-bit, we now make the performance monitor interrupt act as an NMI like Book3S (the necessary C code for that to work appear to already be present in the FSL perf code, notably calling nmi_enter instead of irq_enter). (This also fixes a bug where BookE perfmon interrupts could clobber r14 ... oops) - We could make "masked" decrementer interrupts act as NMIs when doing timer-based perf sampling to improve the sample quality. Signed-off-by-yet: Benjamin Herrenschmidt <benh@kernel.crashing.org> --- v2: - Add hard-enable to decrementer, timer and doorbells - Fix CR clobber in masked irq handling on BookE - Make embedded perf interrupt act as an NMI - Add a PACA_HAPPENED_EE_EDGE for use by FSL if they want to retrigger an interrupt without preventing hard-enable v3: - Fix or vs. ori bug on Book3E - Fix enabling of interrupts for some exceptions on Book3E v4: - Fix resend of doorbells on return from interrupt on Book3E v5: - Rebased on top of my latest series, which involves some significant rework of some aspects of the patch. v6: - 32-bit compile fix - more compile fixes with various .config combos - factor out the asm code to soft-disable interrupts - remove the C wrapper around preempt_schedule_irq v7: - Fix a bug with hard irq state tracking on native power7
2012-03-06 00:27:59 -07:00
/* Check if something happened while soft-disabled */
lbz r0,PACAIRQHAPPENED(r13)
powerpc/powernv: Don't call generic code on offline cpus On PowerNV platforms, when a CPU is offline, we put it into nap mode. It's possible that the CPU wakes up from nap mode while it is still offline due to a stray IPI. A misdirected device interrupt could also potentially cause it to wake up. In that circumstance, we need to clear the interrupt so that the CPU can go back to nap mode. In the past the clearing of the interrupt was accomplished by briefly enabling interrupts and allowing the normal interrupt handling code (do_IRQ() etc.) to handle the interrupt. This has the problem that this code calls irq_enter() and irq_exit(), which call functions such as account_system_vtime() which use RCU internally. Use of RCU is not permitted on offline CPUs and will trigger errors if RCU checking is enabled. To avoid calling into any generic code which might use RCU, we adopt a different method of clearing interrupts on offline CPUs. Since we are on the PowerNV platform, we know that the system interrupt controller is a XICS being driven directly (i.e. not via hcalls) by the kernel. Hence this adds a new icp_native_flush_interrupt() function to the native-mode XICS driver and arranges to call that when an offline CPU is woken from nap. This new function reads the interrupt from the XICS. If it is an IPI, it clears the IPI; if it is a device interrupt, it prints a warning and disables the source. Then it does the end-of-interrupt processing for the interrupt. The other thing that briefly enabling interrupts did was to check and clear the irq_happened flag in this CPU's PACA. Therefore, after flushing the interrupt from the XICS, we also clear all bits except the PACA_IRQ_HARD_DIS (interrupts are hard disabled) bit from the irq_happened flag. The PACA_IRQ_HARD_DIS flag is set by power7_nap() and is left set to indicate that interrupts are hard disabled. This means we then have to ignore that flag in power7_nap(), which is reasonable since it doesn't indicate that any interrupt event needs servicing. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-09-01 22:23:16 -06:00
andi. r0,r0,~PACA_IRQ_HARD_DIS@l
powerpc: Rework lazy-interrupt handling The current implementation of lazy interrupts handling has some issues that this tries to address. We don't do the various workarounds we need to do when re-enabling interrupts in some cases such as when returning from an interrupt and thus we may still lose or get delayed decrementer or doorbell interrupts. The current scheme also makes it much harder to handle the external "edge" interrupts provided by some BookE processors when using the EPR facility (External Proxy) and the Freescale Hypervisor. Additionally, we tend to keep interrupts hard disabled in a number of cases, such as decrementer interrupts, external interrupts, or when a masked decrementer interrupt is pending. This is sub-optimal. This is an attempt at fixing it all in one go by reworking the way we do the lazy interrupt disabling from the ground up. The base idea is to replace the "hard_enabled" field with a "irq_happened" field in which we store a bit mask of what interrupt occurred while soft-disabled. When re-enabling, either via arch_local_irq_restore() or when returning from an interrupt, we can now decide what to do by testing bits in that field. We then implement replaying of the missed interrupts either by re-using the existing exception frame (in exception exit case) or via the creation of a new one from an assembly trampoline (in the arch_local_irq_enable case). This removes the need to play with the decrementer to try to create fake interrupts, among others. In addition, this adds a few refinements: - We no longer hard disable decrementer interrupts that occur while soft-disabled. We now simply bump the decrementer back to max (on BookS) or leave it stopped (on BookE) and continue with hard interrupts enabled, which means that we'll potentially get better sample quality from performance monitor interrupts. - Timer, decrementer and doorbell interrupts now hard-enable shortly after removing the source of the interrupt, which means they no longer run entirely hard disabled. Again, this will improve perf sample quality. - On Book3E 64-bit, we now make the performance monitor interrupt act as an NMI like Book3S (the necessary C code for that to work appear to already be present in the FSL perf code, notably calling nmi_enter instead of irq_enter). (This also fixes a bug where BookE perfmon interrupts could clobber r14 ... oops) - We could make "masked" decrementer interrupts act as NMIs when doing timer-based perf sampling to improve the sample quality. Signed-off-by-yet: Benjamin Herrenschmidt <benh@kernel.crashing.org> --- v2: - Add hard-enable to decrementer, timer and doorbells - Fix CR clobber in masked irq handling on BookE - Make embedded perf interrupt act as an NMI - Add a PACA_HAPPENED_EE_EDGE for use by FSL if they want to retrigger an interrupt without preventing hard-enable v3: - Fix or vs. ori bug on Book3E - Fix enabling of interrupts for some exceptions on Book3E v4: - Fix resend of doorbells on return from interrupt on Book3E v5: - Rebased on top of my latest series, which involves some significant rework of some aspects of the patch. v6: - 32-bit compile fix - more compile fixes with various .config combos - factor out the asm code to soft-disable interrupts - remove the C wrapper around preempt_schedule_irq v7: - Fix a bug with hard irq state tracking on native power7
2012-03-06 00:27:59 -07:00
beq 1f
cmpwi cr0,r4,0
beq 1f
powerpc: Rework lazy-interrupt handling The current implementation of lazy interrupts handling has some issues that this tries to address. We don't do the various workarounds we need to do when re-enabling interrupts in some cases such as when returning from an interrupt and thus we may still lose or get delayed decrementer or doorbell interrupts. The current scheme also makes it much harder to handle the external "edge" interrupts provided by some BookE processors when using the EPR facility (External Proxy) and the Freescale Hypervisor. Additionally, we tend to keep interrupts hard disabled in a number of cases, such as decrementer interrupts, external interrupts, or when a masked decrementer interrupt is pending. This is sub-optimal. This is an attempt at fixing it all in one go by reworking the way we do the lazy interrupt disabling from the ground up. The base idea is to replace the "hard_enabled" field with a "irq_happened" field in which we store a bit mask of what interrupt occurred while soft-disabled. When re-enabling, either via arch_local_irq_restore() or when returning from an interrupt, we can now decide what to do by testing bits in that field. We then implement replaying of the missed interrupts either by re-using the existing exception frame (in exception exit case) or via the creation of a new one from an assembly trampoline (in the arch_local_irq_enable case). This removes the need to play with the decrementer to try to create fake interrupts, among others. In addition, this adds a few refinements: - We no longer hard disable decrementer interrupts that occur while soft-disabled. We now simply bump the decrementer back to max (on BookS) or leave it stopped (on BookE) and continue with hard interrupts enabled, which means that we'll potentially get better sample quality from performance monitor interrupts. - Timer, decrementer and doorbell interrupts now hard-enable shortly after removing the source of the interrupt, which means they no longer run entirely hard disabled. Again, this will improve perf sample quality. - On Book3E 64-bit, we now make the performance monitor interrupt act as an NMI like Book3S (the necessary C code for that to work appear to already be present in the FSL perf code, notably calling nmi_enter instead of irq_enter). (This also fixes a bug where BookE perfmon interrupts could clobber r14 ... oops) - We could make "masked" decrementer interrupts act as NMIs when doing timer-based perf sampling to improve the sample quality. Signed-off-by-yet: Benjamin Herrenschmidt <benh@kernel.crashing.org> --- v2: - Add hard-enable to decrementer, timer and doorbells - Fix CR clobber in masked irq handling on BookE - Make embedded perf interrupt act as an NMI - Add a PACA_HAPPENED_EE_EDGE for use by FSL if they want to retrigger an interrupt without preventing hard-enable v3: - Fix or vs. ori bug on Book3E - Fix enabling of interrupts for some exceptions on Book3E v4: - Fix resend of doorbells on return from interrupt on Book3E v5: - Rebased on top of my latest series, which involves some significant rework of some aspects of the patch. v6: - 32-bit compile fix - more compile fixes with various .config combos - factor out the asm code to soft-disable interrupts - remove the C wrapper around preempt_schedule_irq v7: - Fix a bug with hard irq state tracking on native power7
2012-03-06 00:27:59 -07:00
addi r1,r1,INT_FRAME_SIZE
ld r0,16(r1)
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)
_GLOBAL(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
cmpwi cr0,r3,1
beq 2f
IDLE_STATE_ENTER_SEQ(PPC_NAP)
/* No return */
2: IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
/* No return */
_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 r3,0
b power7_powersave_common
/* No return */
_GLOBAL(power7_sleep)
li r3,1
li r4,1
b power7_powersave_common
/* No return */
/*
* Make opal call in realmode. This is a generic function to be called
* from realmode from reset vector. It handles endianess.
*
* r13 - paca pointer
* r1 - stack pointer
* r3 - opal token
*/
opal_call_realmode:
mflr r12
std r12,_LINK(r1)
ld r2,PACATOC(r13)
/* Set opal return address */
LOAD_REG_ADDR(r0,return_from_opal_call)
mtlr r0
/* Handle endian-ness */
li r0,MSR_LE
mfmsr r12
andc r12,r12,r0
mtspr SPRN_HSRR1,r12
mr r0,r3 /* Move opal token to r0 */
LOAD_REG_ADDR(r11,opal)
ld r12,8(r11)
ld r2,0(r11)
mtspr SPRN_HSRR0,r12
hrfid
return_from_opal_call:
FIXUP_ENDIAN
ld r0,_LINK(r1)
mtlr r0
blr
#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,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)
BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
/* Time base re-sync */
li r3,OPAL_RESYNC_TIMEBASE
bl opal_call_realmode;
/* TODO: Check r3 for failure */
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
_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 r3,_CCR(r1)
ld r4,_MSR(r1)
ld r5,_NIP(r1)
addi r1,r1,INT_FRAME_SIZE
mtcr r3
mtspr SPRN_SRR1,r4
mtspr SPRN_SRR0,r5
rfid
_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 r4,_MSR(r1)
ld r5,_NIP(r1)
addi r1,r1,INT_FRAME_SIZE
mtspr SPRN_SRR1,r4
mtspr SPRN_SRR0,r5
rfid