From 1e8341ae0c0e117f0626cd6cf6732a0a9c8723f2 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Sun, 12 May 2013 07:26:22 +0800 Subject: powerpc: Move the patch_exception to a common place So that it can be used by other codes. No function change. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/code-patching.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index a6f8c7a5cbb7..97e02f985df8 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -34,6 +34,13 @@ int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); unsigned long branch_target(const unsigned int *instr); unsigned int translate_branch(const unsigned int *dest, const unsigned int *src); +#ifdef CONFIG_PPC_BOOK3E_64 +void __patch_exception(int exc, unsigned long addr); +#define patch_exception(exc, name) do { \ + extern unsigned int name; \ + __patch_exception((exc), (unsigned long)&name); \ +} while (0) +#endif static inline unsigned long ppc_function_entry(void *func) { -- cgit v1.2.3 From 0ce636700c5bad54eda0e62903a1803f6d67b31d Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Thu, 22 Aug 2013 09:30:35 +0800 Subject: powerpc: purge all the prefetched instructions for the coherent icache flush As Benjamin Herrenschmidt has indicated, we still need a dummy icbi to purge all the prefetched instructions from the ifetch buffers for the snooping icache. We also need a sync before the icbi to order the actual stores to memory that might have modified instructions with the icbi. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cache.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 9e495c9a6a88..ed0afc1e44a4 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -41,8 +41,20 @@ struct ppc64_caches { extern struct ppc64_caches ppc64_caches; #endif /* __powerpc64__ && ! __ASSEMBLY__ */ -#if !defined(__ASSEMBLY__) +#if defined(__ASSEMBLY__) +/* + * For a snooping icache, we still need a dummy icbi to purge all the + * prefetched instructions from the ifetch buffers. We also need a sync + * before the icbi to order the the actual stores to memory that might + * have modified instructions with the icbi. + */ +#define PURGE_PREFETCHED_INS \ + sync; \ + icbi 0,r3; \ + sync; \ + isync +#else #define __read_mostly __attribute__((__section__(".data..read_mostly"))) #ifdef CONFIG_6xx -- cgit v1.2.3 From c041cfa2af1ccb8d0346dc576144a1085e9b4d4b Mon Sep 17 00:00:00 2001 From: "fan.du" Date: Wed, 23 Jan 2013 16:06:11 +0800 Subject: powerpc: Make irq_stat.timers_irqs counting more specific Current irq_stat.timers_irqs counting doesn't discriminate timer event handler and other timer interrupt(like arch_irq_work_raise). Sometimes we need to know exactly how much interrupts timer event handler fired, so let's be more specific on this. Signed-off-by: Fan Du Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hardirq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 3bdcfce2c42a..418fb654370d 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -6,7 +6,8 @@ typedef struct { unsigned int __softirq_pending; - unsigned int timer_irqs; + unsigned int timer_irqs_event; + unsigned int timer_irqs_others; unsigned int pmu_irqs; unsigned int mce_exceptions; unsigned int spurious_irqs; -- cgit v1.2.3 From b14a7253cf999412e5a0dd39d58b0a42d19fd73a Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:03:51 +0530 Subject: powerpc/book3s: Split the common exception prolog logic into two section. This patch splits the common exception prolog logic into three parts to facilitate reuse of existing code in the next patch. This patch also re-arranges few instructions in such a way that the second part now deals with saving register values from paca save area to stack frame, and the third part deals with saving current register values to stack frame. The second and third part will be reused in the machine check exception routine in the subsequent patch. Please note that this patch does not introduce or change existing code logic. Instead it is just a code movement and instruction re-ordering. Patch Acked-by Paul. But made some minor modification (explained above) to address Paul's comment in the later patch(3). Signed-off-by: Mahesh Salgaonkar Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/exception-64s.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 894662a5d4d5..ff4e2e80856d 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -301,9 +301,12 @@ do_kvm_##n: \ beq 4f; /* if from kernel mode */ \ ACCOUNT_CPU_USER_ENTRY(r9, r10); \ SAVE_PPR(area, r9, r10); \ -4: std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ +4: EXCEPTION_PROLOG_COMMON_2(area) \ + EXCEPTION_PROLOG_COMMON_3(n) \ + ACCOUNT_STOLEN_TIME + +/* Save original regs values from save area to stack frame. */ +#define EXCEPTION_PROLOG_COMMON_2(area) \ ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \ ld r10,area+EX_R10(r13); \ std r9,GPR9(r1); \ @@ -318,11 +321,16 @@ do_kvm_##n: \ ld r10,area+EX_CFAR(r13); \ std r10,ORIG_GPR3(r1); \ END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ + GET_CTR(r10, area); \ + std r10,_CTR(r1); + +#define EXCEPTION_PROLOG_COMMON_3(n) \ + std r2,GPR2(r1); /* save r2 in stackframe */ \ + SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ + SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ mflr r9; /* Get LR, later save to stack */ \ ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ std r9,_LINK(r1); \ - GET_CTR(r10, area); \ - std r10,_CTR(r1); \ lbz r10,PACASOFTIRQEN(r13); \ mfspr r11,SPRN_XER; /* save XER in stackframe */ \ std r10,SOFTE(r1); \ @@ -332,8 +340,7 @@ do_kvm_##n: \ li r10,0; \ ld r11,exception_marker@toc(r2); \ std r10,RESULT(r1); /* clear regs->result */ \ - std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ \ - ACCOUNT_STOLEN_TIME + std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ /* * Exception vectors. -- cgit v1.2.3 From 729b0f715371ce1e7636b4958fc45d6882442456 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:04:00 +0530 Subject: powerpc/book3s: Introduce exclusive emergency stack for machine check exception. This patch introduces exclusive emergency stack for machine check exception. We use emergency stack to handle machine check exception so that we can save MCE information (srr1, srr0, dar and dsisr) before turning on ME bit and be ready for re-entrancy. This helps us to prevent clobbering of MCE information in case of nested machine checks. The reason for using emergency stack over normal kernel stack is that the machine check might occur in the middle of setting up a stack frame which may result into improper use of kernel stack. Signed-off-by: Mahesh Salgaonkar Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/paca.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index b6ea9e068c13..c3523d1dda58 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -152,6 +152,15 @@ struct paca_struct { */ struct opal_machine_check_event *opal_mc_evt; #endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* Exclusive emergency stack pointer for machine check exception. */ + void *mc_emergency_sp; + /* + * Flag to check whether we are in machine check early handler + * and already using emergency stack. + */ + u16 in_mce; +#endif /* Stuff for accurate time accounting */ u64 user_time; /* accumulated usermode TB ticks */ -- cgit v1.2.3 From 4c703416efc0a23f83a282b9240bb92fbd9e0be9 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:04:40 +0530 Subject: powerpc/book3s: Introduce a early machine check hook in cpu_spec. This patch adds the early machine check function pointer in cputable for CPU specific early machine check handling. The early machine handle routine will be called in real mode to handle SLB and TLB errors. We can not reuse the existing machine_check hook because it is always invoked in kernel virtual mode and we would already be in trouble if we get SLB or TLB errors. This patch just sets up a mechanism to invoke CPU specific handler. The subsequent patches will populate the function pointer. Signed-off-by: Mahesh Salgaonkar Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cputable.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 0d4939ba48e7..c5b107afca4d 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -90,6 +90,13 @@ struct cpu_spec { * if the error is fatal, 1 if it was fully recovered and 0 to * pass up (not CPU originated) */ int (*machine_check)(struct pt_regs *regs); + + /* + * Processor specific early machine check handler which is + * called in real mode to handle SLB and TLB errors. + */ + long (*machine_check_early)(struct pt_regs *regs); + }; extern struct cpu_spec *cur_cpu_spec; -- cgit v1.2.3 From 0440705049b041d84268ea57f6e90e2f16618897 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:04:56 +0530 Subject: powerpc/book3s: Add flush_tlb operation in cpu_spec. This patch introduces flush_tlb operation in cpu_spec structure. This will help us to invoke appropriate CPU-side flush tlb routine. This patch adds the foundation to invoke CPU specific flush routine for respective architectures. Currently this patch introduce flush_tlb for p7 and p8. Signed-off-by: Mahesh Salgaonkar Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cputable.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index c5b107afca4d..617cc767c076 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -97,6 +97,11 @@ struct cpu_spec { */ long (*machine_check_early)(struct pt_regs *regs); + /* + * Processor specific routine to flush tlbs. + */ + void (*flush_tlb)(unsigned long inval_selector); + }; extern struct cpu_spec *cur_cpu_spec; -- cgit v1.2.3 From e22a22740c1ac23aaa10835f026b3549ee3e4e75 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:05:11 +0530 Subject: powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power7. If we get a machine check exception due to SLB or TLB errors, then flush SLBs/TLBs and reload SLBs to recover. We do this in real mode before turning on MMU. Otherwise we would run into nested machine checks. If we get a machine check when we are in guest, then just flush the SLBs and continue. This patch handles errors for power7. The next patch will handle errors for power8 Signed-off-by: Mahesh Salgaonkar Signed-off-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/bitops.h | 5 +++ arch/powerpc/include/asm/mce.h | 67 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) create mode 100644 arch/powerpc/include/asm/mce.h (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 910194e9a1e2..a5e9a7d494d8 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -46,6 +46,11 @@ #include #include +/* PPC bit number conversion */ +#define PPC_BITLSHIFT(be) (BITS_PER_LONG - 1 - (be)) +#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit)) +#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs)) + /* * clear_bit doesn't imply a memory barrier */ diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h new file mode 100644 index 000000000000..8157d4eaead6 --- /dev/null +++ b/arch/powerpc/include/asm/mce.h @@ -0,0 +1,67 @@ +/* + * Machine check exception header file. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar + */ + +#ifndef __ASM_PPC64_MCE_H__ +#define __ASM_PPC64_MCE_H__ + +#include + +/* + * Machine Check bits on power7 and power8 + */ +#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */ + +/* SRR1 bits for machine check (On Power7 and Power8) */ +#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */ + +#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45)) +#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45)) + +/* SRR1 bits for machine check (On Power8) */ +#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45)) + +/* DSISR bits for machine check (On Power7 and Power8) */ +#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */ +#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */ +#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */ +#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */ +#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */ +#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */ +#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */ + +/* + * DSISR bits for machine check (Power8) in addition to above. + * Secondary DERAT Multihit + */ +#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54)) + +/* SLB error bits */ +#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \ + P7_DSISR_MC_SLB_PARITY_MFSLB | \ + P7_DSISR_MC_SLB_MULTIHIT | \ + P7_DSISR_MC_SLB_MULTIHIT_PARITY) + +#endif /* __ASM_PPC64_MCE_H__ */ -- cgit v1.2.3 From ae744f3432d3872c51298d922728e13c24ccc068 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:05:26 +0530 Subject: powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power8. This patch handles the memory errors on power8. If we get a machine check exception due to SLB or TLB errors, then flush SLBs/TLBs and reload SLBs to recover. Signed-off-by: Mahesh Salgaonkar Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mce.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index 8157d4eaead6..e3ffa825b970 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -64,4 +64,7 @@ P7_DSISR_MC_SLB_MULTIHIT | \ P7_DSISR_MC_SLB_MULTIHIT_PARITY) +#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \ + P8_DSISR_MC_ERAT_MULTIHIT_SEC) + #endif /* __ASM_PPC64_MCE_H__ */ -- cgit v1.2.3 From 36df96f8acaf51992177645eb2d781f766ce97dc Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:05:40 +0530 Subject: powerpc/book3s: Decode and save machine check event. Now that we handle machine check in linux, the MCE decoding should also take place in linux host. This info is crucial to log before we go down in case we can not handle the machine check errors. This patch decodes and populates a machine check event which contain high level meaning full MCE information. We do this in real mode C code with ME bit on. The MCE information is still available on emergency stack (in pt_regs structure format). Even if we take another exception at this point the MCE early handler will allocate a new stack frame on top of current one. So when we return back here we still have our MCE information safe on current stack. We use per cpu buffer to save high level MCE information. Each per cpu buffer is an array of machine check event structure indexed by per cpu counter mce_nest_count. The mce_nest_count is incremented every time we enter machine check early handler in real mode to get the current free slot (index = mce_nest_count - 1). The mce_nest_count is decremented once the MCE info is consumed by virtual mode machine exception handler. This patch provides save_mce_event(), get_mce_event() and release_mce_event() generic routines that can be used by machine check handlers to populate and retrieve the event. The routine release_mce_event() will free the event slot so that it can be reused. Caller can invoke get_mce_event() with a release flag either to release the event slot immediately OR keep it so that it can be fetched again. The event slot can be also released anytime by invoking release_mce_event(). This patch also updates kvm code to invoke get_mce_event to retrieve generic mce event rather than paca->opal_mce_evt. The KVM code always calls get_mce_event() with release flags set to false so that event is available for linus host machine If machine check occurs while we are in guest, KVM tries to handle the error. If KVM is able to handle MC error successfully, it enters the guest and delivers the machine check to guest. If KVM is not able to handle MC error, it exists the guest and passes the control to linux host machine check handler which then logs MC event and decides how to handle it in linux host. In failure case, KVM needs to make sure that the MC event is available for linux host to consume. Hence KVM always calls get_mce_event() with release flags set to false and later it invokes release_mce_event() only if it succeeds to handle error. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mce.h | 124 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 124 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index e3ffa825b970..87cad2a808c2 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -66,5 +66,129 @@ #define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \ P8_DSISR_MC_ERAT_MULTIHIT_SEC) +enum MCE_Version { + MCE_V1 = 1, +}; + +enum MCE_Severity { + MCE_SEV_NO_ERROR = 0, + MCE_SEV_WARNING = 1, + MCE_SEV_ERROR_SYNC = 2, + MCE_SEV_FATAL = 3, +}; + +enum MCE_Disposition { + MCE_DISPOSITION_RECOVERED = 0, + MCE_DISPOSITION_NOT_RECOVERED = 1, +}; + +enum MCE_Initiator { + MCE_INITIATOR_UNKNOWN = 0, + MCE_INITIATOR_CPU = 1, +}; + +enum MCE_ErrorType { + MCE_ERROR_TYPE_UNKNOWN = 0, + MCE_ERROR_TYPE_UE = 1, + MCE_ERROR_TYPE_SLB = 2, + MCE_ERROR_TYPE_ERAT = 3, + MCE_ERROR_TYPE_TLB = 4, +}; + +enum MCE_UeErrorType { + MCE_UE_ERROR_INDETERMINATE = 0, + MCE_UE_ERROR_IFETCH = 1, + MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2, + MCE_UE_ERROR_LOAD_STORE = 3, + MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4, +}; + +enum MCE_SlbErrorType { + MCE_SLB_ERROR_INDETERMINATE = 0, + MCE_SLB_ERROR_PARITY = 1, + MCE_SLB_ERROR_MULTIHIT = 2, +}; + +enum MCE_EratErrorType { + MCE_ERAT_ERROR_INDETERMINATE = 0, + MCE_ERAT_ERROR_PARITY = 1, + MCE_ERAT_ERROR_MULTIHIT = 2, +}; + +enum MCE_TlbErrorType { + MCE_TLB_ERROR_INDETERMINATE = 0, + MCE_TLB_ERROR_PARITY = 1, + MCE_TLB_ERROR_MULTIHIT = 2, +}; + +struct machine_check_event { + enum MCE_Version version:8; /* 0x00 */ + uint8_t in_use; /* 0x01 */ + enum MCE_Severity severity:8; /* 0x02 */ + enum MCE_Initiator initiator:8; /* 0x03 */ + enum MCE_ErrorType error_type:8; /* 0x04 */ + enum MCE_Disposition disposition:8; /* 0x05 */ + uint8_t reserved_1[2]; /* 0x06 */ + uint64_t gpr3; /* 0x08 */ + uint64_t srr0; /* 0x10 */ + uint64_t srr1; /* 0x18 */ + union { /* 0x20 */ + struct { + enum MCE_UeErrorType ue_error_type:8; + uint8_t effective_address_provided; + uint8_t physical_address_provided; + uint8_t reserved_1[5]; + uint64_t effective_address; + uint64_t physical_address; + uint8_t reserved_2[8]; + } ue_error; + + struct { + enum MCE_SlbErrorType slb_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } slb_error; + + struct { + enum MCE_EratErrorType erat_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } erat_error; + + struct { + enum MCE_TlbErrorType tlb_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } tlb_error; + } u; +}; + +struct mce_error_info { + enum MCE_ErrorType error_type:8; + union { + enum MCE_UeErrorType ue_error_type:8; + enum MCE_SlbErrorType slb_error_type:8; + enum MCE_EratErrorType erat_error_type:8; + enum MCE_TlbErrorType tlb_error_type:8; + } u; + uint8_t reserved[2]; +}; + +#define MAX_MC_EVT 100 + +/* Release flags for get_mce_event() */ +#define MCE_EVENT_RELEASE true +#define MCE_EVENT_DONTRELEASE false + +extern void save_mce_event(struct pt_regs *regs, long handled, + struct mce_error_info *mce_err, uint64_t addr); +extern int get_mce_event(struct machine_check_event *mce, bool release); +extern void release_mce_event(void); #endif /* __ASM_PPC64_MCE_H__ */ -- cgit v1.2.3 From b5ff4211a8294be2ddbaf963fa3666fa042292a8 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:05:49 +0530 Subject: powerpc/book3s: Queue up and process delayed MCE events. When machine check real mode handler can not continue into host kernel in V mode, it returns from the interrupt and we loose MCE event which never gets logged. In such a situation queue up the MCE event so that we can log it later when we get back into host kernel with r1 pointing to kernel stack e.g. during syscall exit. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mce.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index 87cad2a808c2..3276b409299c 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -190,5 +190,8 @@ extern void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t addr); extern int get_mce_event(struct machine_check_event *mce, bool release); extern void release_mce_event(void); +extern void machine_check_queue_event(void); +extern void machine_check_process_queued_event(void); +extern void machine_check_print_event_info(struct machine_check_event *evt); #endif /* __ASM_PPC64_MCE_H__ */ -- cgit v1.2.3 From b63a0ffe35de7e5f9b907bbc2c783e702f7e15af Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 30 Oct 2013 20:06:13 +0530 Subject: powerpc/powernv: Machine check exception handling. Add basic error handling in machine check exception handler. - If MSR_RI isn't set, we can not recover. - Check if disposition set to OpalMCE_DISPOSITION_RECOVERED. - Check if address at fault is inside kernel address space, if not then send SIGBUS to process if we hit exception when in userspace. - If address at fault is not provided then and if we get a synchronous machine check while in userspace then kill the task. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mce.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index 3276b409299c..a2b8c7b35fba 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -193,5 +193,6 @@ extern void release_mce_event(void); extern void machine_check_queue_event(void); extern void machine_check_process_queued_event(void); extern void machine_check_print_event_info(struct machine_check_event *evt); +extern uint64_t get_mce_fault_addr(struct machine_check_event *evt); #endif /* __ASM_PPC64_MCE_H__ */ -- cgit v1.2.3 From 24366360035a9e0a9870ed7208aa2ba1948f844d Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Mon, 18 Nov 2013 15:35:58 +0530 Subject: powerpc/powernv: Infrastructure to read opal messages in generic format. Opal now has a new messaging infrastructure to push the messages to linux in a generic format for different type of messages using only one event bit. The format of the opal message is as below: struct opal_msg { uint32_t msg_type; uint32_t reserved; uint64_t params[8]; }; This patch allows clients to subscribe for notification for specific message type. It is upto the subscriber to decipher the messages who showed interested in receiving specific message type. The interface to subscribe for notification is: int opal_message_notifier_register(enum OpalMessageType msg_type, struct notifier_block *nb) The notifier will fetch the opal message when available and notify the subscriber with message type and the opal message. It is subscribers responsibility to copy the message data before returning from notifier callback. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 033c06be1d84..ffb2036fcfb2 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -132,6 +132,8 @@ extern int opal_enter_rtas(struct rtas_args *args, #define OPAL_FLASH_VALIDATE 76 #define OPAL_FLASH_MANAGE 77 #define OPAL_FLASH_UPDATE 78 +#define OPAL_GET_MSG 85 +#define OPAL_CHECK_ASYNC_COMPLETION 86 #ifndef __ASSEMBLY__ @@ -211,7 +213,16 @@ enum OpalPendingState { OPAL_EVENT_ERROR_LOG = 0x40, OPAL_EVENT_EPOW = 0x80, OPAL_EVENT_LED_STATUS = 0x100, - OPAL_EVENT_PCI_ERROR = 0x200 + OPAL_EVENT_PCI_ERROR = 0x200, + OPAL_EVENT_MSG_PENDING = 0x800, +}; + +enum OpalMessageType { + OPAL_MSG_ASYNC_COMP = 0, + OPAL_MSG_MEM_ERR, + OPAL_MSG_EPOW, + OPAL_MSG_SHUTDOWN, + OPAL_MSG_TYPE_MAX, }; /* Machine check related definitions */ @@ -356,6 +367,12 @@ enum OpalLPCAddressType { OPAL_LPC_FW = 2, }; +struct opal_msg { + uint32_t msg_type; + uint32_t reserved; + uint64_t params[8]; +}; + struct opal_machine_check_event { enum OpalMCE_Version version:8; /* 0x00 */ uint8_t in_use; /* 0x01 */ @@ -731,6 +748,9 @@ int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result); int64_t opal_manage_flash(uint8_t op); int64_t opal_update_flash(uint64_t blk_list); +int64_t opal_get_msg(uint64_t buffer, size_t size); +int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token); + /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); @@ -744,6 +764,8 @@ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); extern int opal_notifier_register(struct notifier_block *nb); +extern int opal_message_notifier_register(enum OpalMessageType msg_type, + struct notifier_block *nb); extern void opal_notifier_enable(void); extern void opal_notifier_disable(void); extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val); -- cgit v1.2.3 From 7e1ce5a492e18449fd47ef6305b26e0c572d26e9 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Mon, 18 Nov 2013 16:39:22 +0530 Subject: powerpc/powernv: Move SG list structure to header file Move SG list and entry structure to header file so that it can be used in other places as well. Signed-off-by: Vasant Hegde Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index ffb2036fcfb2..0a2ac85998d7 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -33,6 +33,28 @@ struct opal_takeover_args { u64 rd_loc; /* r11 */ }; +/* + * SG entry + * + * WARNING: The current implementation requires each entry + * to represent a block that is 4k aligned *and* each block + * size except the last one in the list to be as well. + */ +struct opal_sg_entry { + void *data; + long length; +}; + +/* sg list */ +struct opal_sg_list { + unsigned long num_entries; + struct opal_sg_list *next; + struct opal_sg_entry entry[]; +}; + +/* We calculate number of sg entries based on PAGE_SIZE */ +#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry)) + extern long opal_query_takeover(u64 *hal_size, u64 *hal_align); extern long opal_do_takeover(struct opal_takeover_args *args); -- cgit v1.2.3 From d905c5df9aef38d63df268f6f5e7b13894f626d3 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Thu, 21 Nov 2013 17:43:14 +1100 Subject: PPC: POWERNV: move iommu_add_device earlier The current implementation of IOMMU on sPAPR does not use iommu_ops and therefore does not call IOMMU API's bus_set_iommu() which 1) sets iommu_ops for a bus 2) registers a bus notifier Instead, PCI devices are added to IOMMU groups from subsys_initcall_sync(tce_iommu_init) which does basically the same thing without using iommu_ops callbacks. However Freescale PAMU driver (https://lkml.org/lkml/2013/7/1/158) implements iommu_ops and when tce_iommu_init is called, every PCI device is already added to some group so there is a conflict. This patch does 2 things: 1. removes the loop in which PCI devices were added to groups and adds explicit iommu_add_device() calls to add devices as soon as they get the iommu_table pointer assigned to them. 2. moves a bus notifier to powernv code in order to avoid conflict with the notifier from Freescale driver. iommu_add_device() and iommu_del_device() are public now. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/iommu.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index c34656a8925e..774fa2776907 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -101,8 +101,34 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name); */ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, int nid); +#ifdef CONFIG_IOMMU_API extern void iommu_register_group(struct iommu_table *tbl, int pci_domain_number, unsigned long pe_num); +extern int iommu_add_device(struct device *dev); +extern void iommu_del_device(struct device *dev); +#else +static inline void iommu_register_group(struct iommu_table *tbl, + int pci_domain_number, + unsigned long pe_num) +{ +} + +static inline int iommu_add_device(struct device *dev) +{ + return 0; +} + +static inline void iommu_del_device(struct device *dev) +{ +} +#endif /* !CONFIG_IOMMU_API */ + +static inline void set_iommu_table_base_and_group(struct device *dev, + void *base) +{ + set_iommu_table_base(dev, base); + iommu_add_device(dev); +} extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl, struct scatterlist *sglist, int nelems, -- cgit v1.2.3 From 0150a3dd92fc45b599bf2442b47d40921b4aa2d2 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 29 Nov 2013 13:27:18 +1100 Subject: powerpc: Add real mode cache inhibited IO accessors These accessors allow us to do cache inhibited accesses when in real mode. They should only be used in real mode. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/io.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 575fbf81fad0..97d3869991ca 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -191,8 +191,24 @@ DEF_MMIO_OUT_D(out_le32, 32, stw); #endif /* __BIG_ENDIAN */ +/* + * Cache inhibitied accessors for use in real mode, you don't want to use these + * unless you know what you're doing. + * + * NB. These use the cpu byte ordering. + */ +DEF_MMIO_OUT_X(out_rm8, 8, stbcix); +DEF_MMIO_OUT_X(out_rm16, 16, sthcix); +DEF_MMIO_OUT_X(out_rm32, 32, stwcix); +DEF_MMIO_IN_X(in_rm8, 8, lbzcix); +DEF_MMIO_IN_X(in_rm16, 16, lhzcix); +DEF_MMIO_IN_X(in_rm32, 32, lwzcix); + #ifdef __powerpc64__ +DEF_MMIO_OUT_X(out_rm64, 64, stdcix); +DEF_MMIO_IN_X(in_rm64, 64, ldcix); + #ifdef __BIG_ENDIAN__ DEF_MMIO_OUT_D(out_be64, 64, std); DEF_MMIO_IN_D(in_be64, 64, ld); -- cgit v1.2.3 From 1a8f6f97ea4dbaaa21b05cae2dacea47e4aea37b Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 5 Dec 2013 11:31:08 +0800 Subject: powerpc: Make slb_shadow a local The only external user of slb_shadow is the pseries lpar code, and it can access through the paca array instead. Signed-off-by: Jeremy Kerr Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/lppaca.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 844c28de7ec0..d0a2a2f99564 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -132,8 +132,6 @@ struct slb_shadow { } save_area[SLB_NUM_BOLTED]; } ____cacheline_aligned; -extern struct slb_shadow slb_shadow[]; - /* * Layout of entries in the hypervisor's dispatch trace log buffer. */ -- cgit v1.2.3 From c8c06f5a0dde0fed260c54d550962187f266ed0d Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 18 Nov 2013 14:58:10 +0530 Subject: powerpc/mm: Free up _PAGE_COHERENCE for numa fault use later Set memory coherence always on hash64 config. If a platform cannot have memory coherence always set they can infer that from _PAGE_NO_CACHE and _PAGE_WRITETHRU like in lpar. So we dont' really need a separate bit for tracking _PAGE_COHERENCE. Signed-off-by: Aneesh Kumar K.V Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pte-hash64.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h index 0419eeb53274..55aea0caf95e 100644 --- a/arch/powerpc/include/asm/pte-hash64.h +++ b/arch/powerpc/include/asm/pte-hash64.h @@ -19,7 +19,7 @@ #define _PAGE_FILE 0x0002 /* (!present only) software: pte holds file offset */ #define _PAGE_EXEC 0x0004 /* No execute on POWER4 and newer (we invert) */ #define _PAGE_GUARDED 0x0008 -#define _PAGE_COHERENT 0x0010 /* M: enforce memory coherence (SMP systems) */ +/* We can derive Memory coherence from _PAGE_NO_CACHE */ #define _PAGE_NO_CACHE 0x0020 /* I: cache inhibit */ #define _PAGE_WRITETHRU 0x0040 /* W: cache write-through */ #define _PAGE_DIRTY 0x0080 /* C: page changed */ -- cgit v1.2.3 From c34a51ce49b40b9667cd7f5cc2e40475af8b4c3d Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 18 Nov 2013 14:58:13 +0530 Subject: powerpc/mm: Enable _PAGE_NUMA for book3s We steal the _PAGE_COHERENCE bit and use that for indicating NUMA ptes. Signed-off-by: Aneesh Kumar K.V Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgtable.h | 66 ++++++++++++++++++++++++++++++++++- arch/powerpc/include/asm/pte-hash64.h | 6 ++++ 2 files changed, 71 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 7d6eacf249cf..b999ca318985 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -3,6 +3,7 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ +#include #include /* For TASK_SIZE */ #include #include @@ -33,10 +34,73 @@ static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } -static inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_PRESENT; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } +#ifdef CONFIG_NUMA_BALANCING + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & (_PAGE_PRESENT | _PAGE_NUMA); +} + +#define pte_numa pte_numa +static inline int pte_numa(pte_t pte) +{ + return (pte_val(pte) & + (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA; +} + +#define pte_mknonnuma pte_mknonnuma +static inline pte_t pte_mknonnuma(pte_t pte) +{ + pte_val(pte) &= ~_PAGE_NUMA; + pte_val(pte) |= _PAGE_PRESENT | _PAGE_ACCESSED; + return pte; +} + +#define pte_mknuma pte_mknuma +static inline pte_t pte_mknuma(pte_t pte) +{ + /* + * We should not set _PAGE_NUMA on non present ptes. Also clear the + * present bit so that hash_page will return 1 and we collect this + * as numa fault. + */ + if (pte_present(pte)) { + pte_val(pte) |= _PAGE_NUMA; + pte_val(pte) &= ~_PAGE_PRESENT; + } else + VM_BUG_ON(1); + return pte; +} + +#define pmd_numa pmd_numa +static inline int pmd_numa(pmd_t pmd) +{ + return pte_numa(pmd_pte(pmd)); +} + +#define pmd_mknonnuma pmd_mknonnuma +static inline pmd_t pmd_mknonnuma(pmd_t pmd) +{ + return pte_pmd(pte_mknonnuma(pmd_pte(pmd))); +} + +#define pmd_mknuma pmd_mknuma +static inline pmd_t pmd_mknuma(pmd_t pmd) +{ + return pte_pmd(pte_mknuma(pmd_pte(pmd))); +} + +# else + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} +#endif /* CONFIG_NUMA_BALANCING */ + /* Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h index 55aea0caf95e..2505d8eab15c 100644 --- a/arch/powerpc/include/asm/pte-hash64.h +++ b/arch/powerpc/include/asm/pte-hash64.h @@ -27,6 +27,12 @@ #define _PAGE_RW 0x0200 /* software: user write access allowed */ #define _PAGE_BUSY 0x0800 /* software: PTE & hash are busy */ +/* + * Used for tracking numa faults + */ +#define _PAGE_NUMA 0x00000010 /* Gather numa placement stats */ + + /* No separate kernel read-only */ #define _PAGE_KERNEL_RW (_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */ #define _PAGE_KERNEL_RO _PAGE_KERNEL_RW -- cgit v1.2.3 From 75eb3d9b60c280a275099fbed06a890cee2d784b Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Fri, 15 Nov 2013 09:50:57 +0530 Subject: powerpc/powernv: Get FSP memory errors and plumb into memory poison infrastructure. Get the memory errors reported by opal and plumb it into memory poison infrastructure. This patch uses new messaging channel infrastructure to pull the fsp memory errors to linux. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 52 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 0a2ac85998d7..aded1b81bfd6 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -443,6 +443,58 @@ struct opal_machine_check_event { } u; }; +/* FSP memory errors handling */ +enum OpalMemErr_Version { + OpalMemErr_V1 = 1, +}; + +enum OpalMemErrType { + OPAL_MEM_ERR_TYPE_RESILIENCE = 0, + OPAL_MEM_ERR_TYPE_DYN_DALLOC, + OPAL_MEM_ERR_TYPE_SCRUB, +}; + +/* Memory Reilience error type */ +enum OpalMemErr_ResilErrType { + OPAL_MEM_RESILIENCE_CE = 0, + OPAL_MEM_RESILIENCE_UE, + OPAL_MEM_RESILIENCE_UE_SCRUB, +}; + +/* Dynamic Memory Deallocation type */ +enum OpalMemErr_DynErrType { + OPAL_MEM_DYNAMIC_DEALLOC = 0, +}; + +/* OpalMemoryErrorData->flags */ +#define OPAL_MEM_CORRECTED_ERROR 0x0001 +#define OPAL_MEM_THRESHOLD_EXCEEDED 0x0002 +#define OPAL_MEM_ACK_REQUIRED 0x8000 + +struct OpalMemoryErrorData { + enum OpalMemErr_Version version:8; /* 0x00 */ + enum OpalMemErrType type:8; /* 0x01 */ + uint16_t flags; /* 0x02 */ + uint8_t reserved_1[4]; /* 0x04 */ + + union { + /* Memory Resilience corrected/uncorrected error info */ + struct { + enum OpalMemErr_ResilErrType resil_err_type:8; + uint8_t reserved_1[7]; + uint64_t physical_address_start; + uint64_t physical_address_end; + } resilience; + /* Dynamic memory deallocation error info */ + struct { + enum OpalMemErr_DynErrType dyn_err_type:8; + uint8_t reserved_1[7]; + uint64_t physical_address_start; + uint64_t physical_address_end; + } dyn_dealloc; + } u; +}; + enum { OPAL_P7IOC_DIAG_TYPE_NONE = 0, OPAL_P7IOC_DIAG_TYPE_RGC = 1, -- cgit v1.2.3 From e589a4404fa06730355de204d3d136ed9bbc7dea Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Mon, 9 Dec 2013 18:17:01 +1100 Subject: powerpc/iommu: Update constant names to reflect their hardcoded page size The powerpc iommu uses a hardcoded page size of 4K. This patch changes the name of the IOMMU_PAGE_* macros to reflect the hardcoded values. A future patch will use the existing names to support dynamic page sizes. Signed-off-by: Alistair Popple Signed-off-by: Alexey Kardashevskiy Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/iommu.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 774fa2776907..0869c7e74421 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -30,10 +30,10 @@ #include #include -#define IOMMU_PAGE_SHIFT 12 -#define IOMMU_PAGE_SIZE (ASM_CONST(1) << IOMMU_PAGE_SHIFT) -#define IOMMU_PAGE_MASK (~((1 << IOMMU_PAGE_SHIFT) - 1)) -#define IOMMU_PAGE_ALIGN(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE) +#define IOMMU_PAGE_SHIFT_4K 12 +#define IOMMU_PAGE_SIZE_4K (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K) +#define IOMMU_PAGE_MASK_4K (~((1 << IOMMU_PAGE_SHIFT_4K) - 1)) +#define IOMMU_PAGE_ALIGN_4K(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE_4K) /* Boot time flags */ extern int iommu_is_off; @@ -42,7 +42,7 @@ extern int iommu_force_on; /* Pure 2^n version of get_order */ static __inline__ __attribute_const__ int get_iommu_order(unsigned long size) { - return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT) + 1; + return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT_4K) + 1; } -- cgit v1.2.3 From 3a553170d35d69bea3877bffa508489dfa6f133d Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Mon, 9 Dec 2013 18:17:02 +1100 Subject: powerpc/iommu: Add it_page_shift field to determine iommu page size This patch adds a it_page_shift field to struct iommu_table and initiliases it to 4K for all platforms. Signed-off-by: Alistair Popple Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 0869c7e74421..7c928342f3f5 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -76,6 +76,7 @@ struct iommu_table { struct iommu_pool large_pool; struct iommu_pool pools[IOMMU_NR_POOLS]; unsigned long *it_map; /* A simple allocation bitmap for now */ + unsigned long it_page_shift;/* table iommu page size */ #ifdef CONFIG_IOMMU_API struct iommu_group *it_group; #endif -- cgit v1.2.3 From d084775738b746648d4102337163a04534a02982 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Mon, 9 Dec 2013 18:17:03 +1100 Subject: powerpc/iommu: Update the generic code to use dynamic iommu page sizes This patch updates the generic iommu backend code to use the it_page_shift field to determine the iommu page size instead of using hardcoded values. Signed-off-by: Alistair Popple Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/iommu.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 7c928342f3f5..f7a8036579b5 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -35,17 +35,14 @@ #define IOMMU_PAGE_MASK_4K (~((1 << IOMMU_PAGE_SHIFT_4K) - 1)) #define IOMMU_PAGE_ALIGN_4K(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE_4K) +#define IOMMU_PAGE_SIZE(tblptr) (ASM_CONST(1) << (tblptr)->it_page_shift) +#define IOMMU_PAGE_MASK(tblptr) (~((1 << (tblptr)->it_page_shift) - 1)) +#define IOMMU_PAGE_ALIGN(addr, tblptr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE(tblptr)) + /* Boot time flags */ extern int iommu_is_off; extern int iommu_force_on; -/* Pure 2^n version of get_order */ -static __inline__ __attribute_const__ int get_iommu_order(unsigned long size) -{ - return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT_4K) + 1; -} - - /* * IOMAP_MAX_ORDER defines the largest contiguous block * of dma space we can get. IOMAP_MAX_ORDER = 13 @@ -82,6 +79,14 @@ struct iommu_table { #endif }; +/* Pure 2^n version of get_order */ +static inline __attribute_const__ +int get_iommu_order(unsigned long size, struct iommu_table *tbl) +{ + return __ilog2((size - 1) >> tbl->it_page_shift) + 1; +} + + struct scatterlist; static inline void set_iommu_table_base(struct device *dev, void *base) -- cgit v1.2.3 From 228b1a473037c89d524e03a569c688a22241b4ea Mon Sep 17 00:00:00 2001 From: Mihai Caraman Date: Thu, 8 Aug 2013 15:56:09 +0300 Subject: powerpc/booke64: Add LRAT error exception handler LRAT (Logical to Real Address Translation) present in MMU v2 provides hardware translation from a logical page number (LPN) to a real page number (RPN) when tlbwe is executed by a guest or when a page table translation occurs from a guest virtual address. Add LRAT error exception handler to Booke3E 64-bit kernel and the basic KVM handler to avoid build breakage. This is a prerequisite for KVM LRAT support that will follow. Signed-off-by: Mihai Caraman Signed-off-by: Scott Wood --- arch/powerpc/include/asm/kvm_asm.h | 1 + arch/powerpc/include/asm/reg_booke.h | 1 + 2 files changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 1bd92fd43cfb..1503d8c7c41b 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -74,6 +74,7 @@ #define BOOKE_INTERRUPT_GUEST_DBELL_CRIT 39 #define BOOKE_INTERRUPT_HV_SYSCALL 40 #define BOOKE_INTERRUPT_HV_PRIV 41 +#define BOOKE_INTERRUPT_LRAT_ERROR 42 /* book3s */ diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 2e31aacd8acc..1f7134dd0946 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -101,6 +101,7 @@ #define SPRN_IVOR39 0x1B1 /* Interrupt Vector Offset Register 39 */ #define SPRN_IVOR40 0x1B2 /* Interrupt Vector Offset Register 40 */ #define SPRN_IVOR41 0x1B3 /* Interrupt Vector Offset Register 41 */ +#define SPRN_IVOR42 0x1B4 /* Interrupt Vector Offset Register 42 */ #define SPRN_GIVOR2 0x1B8 /* Guest IVOR2 */ #define SPRN_GIVOR3 0x1B9 /* Guest IVOR3 */ #define SPRN_GIVOR4 0x1BA /* Guest IVOR4 */ -- cgit v1.2.3 From 640e922501103aaf2e0abb4cf4de5d49fa8342f7 Mon Sep 17 00:00:00 2001 From: Joseph Myers Date: Tue, 10 Dec 2013 23:07:45 +0000 Subject: powerpc: fix exception clearing in e500 SPE float emulation The e500 SPE floating-point emulation code clears existing exceptions (__FPU_FPSCR &= ~FP_EX_MASK;) before ORing in the exceptions from the emulated operation. However, these exception bits are the "sticky", cumulative exception bits, and should only be cleared by the user program setting SPEFSCR, not implicitly by any floating-point instruction (whether executed purely by the hardware or emulated). The spurious clearing of these bits shows up as missing exceptions in glibc testing. Fixing this, however, is not as simple as just not clearing the bits, because while the bits may be from previous floating-point operations (in which case they should not be cleared), the processor can also set the sticky bits itself before the interrupt for an exception occurs, and this can happen in cases when IEEE 754 semantics are that the sticky bit should not be set. Specifically, the "invalid" sticky bit is set in various cases with non-finite operands, where IEEE 754 semantics do not involve raising such an exception, and the "underflow" sticky bit is set in cases of exact underflow, whereas IEEE 754 semantics are that this flag is set only for inexact underflow. Thus, for correct emulation the kernel needs to know the setting of these two sticky bits before the instruction being emulated. When a floating-point operation raises an exception, the kernel can note the state of the sticky bits immediately afterwards. Some functions that affect the state of these bits, such as fesetenv and feholdexcept, need to use prctl with PR_GET_FPEXC and PR_SET_FPEXC anyway, and so it is natural to record the state of those bits during that call into the kernel and so avoid any need for a separate call into the kernel to inform it of a change to those bits. Thus, the interface I chose to use (in this patch and the glibc port) is that one of those prctl calls must be made after any userspace change to those sticky bits, other than through a floating-point operation that traps into the kernel anyway. feclearexcept and fesetexceptflag duly make those calls, which would not be required were it not for this issue. The previous EGLIBC port, and the uClibc code copied from it, is fundamentally broken as regards any use of prctl for floating-point exceptions because it didn't use the PR_FP_EXC_SW_ENABLE bit in its prctl calls (and did various worse things, such as passing a pointer when prctl expected an integer). If you avoid anything where prctl is used, the clearing of sticky bits still means it will never give anything approximating correct exception semantics with existing kernels. I don't believe the patch makes things any worse for existing code that doesn't try to inform the kernel of changes to sticky bits - such code may get incorrect exceptions in some cases, but it would have done so anyway in other cases. Signed-off-by: Joseph Myers Signed-off-by: Scott Wood --- arch/powerpc/include/asm/processor.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index fc14a38c7ccf..91441d9cbaae 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -256,6 +256,8 @@ struct thread_struct { unsigned long evr[32]; /* upper 32-bits of SPE regs */ u64 acc; /* Accumulator */ unsigned long spefscr; /* SPE & eFP status */ + unsigned long spefscr_last; /* SPEFSCR value on last prctl + call or trap return */ int used_spe; /* set if process has used spe */ #endif /* CONFIG_SPE */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -317,7 +319,9 @@ struct thread_struct { (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack) #ifdef CONFIG_SPE -#define SPEFSCR_INIT .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, +#define SPEFSCR_INIT \ + .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, \ + .spefscr_last = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, #else #define SPEFSCR_INIT #endif -- cgit v1.2.3 From 71a6fa17e1526d3f26f4711cc55d339f96c49a95 Mon Sep 17 00:00:00 2001 From: Wang Dongsheng Date: Tue, 17 Dec 2013 16:16:59 +0800 Subject: powerpc/fsl: add E6500 PVR and SPRN_PWRMGTCR0 define E6500 PVR and SPRN_PWRMGTCR0 will be used in subsequent pw20/altivec idle patches. Signed-off-by: Wang Dongsheng Signed-off-by: Scott Wood --- arch/powerpc/include/asm/reg.h | 2 ++ arch/powerpc/include/asm/reg_booke.h | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index fa8388ed94c5..62b114e079cf 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1075,6 +1075,8 @@ #define PVR_8560 0x80200000 #define PVR_VER_E500V1 0x8020 #define PVR_VER_E500V2 0x8021 +#define PVR_VER_E6500 0x8040 + /* * For the 8xx processors, all of them report the same PVR family for * the PowerPC core. The various versions of these processors must be diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 1f7134dd0946..163c3b05a76e 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -171,6 +171,7 @@ #define SPRN_L2CSR1 0x3FA /* L2 Data Cache Control and Status Register 1 */ #define SPRN_DCCR 0x3FA /* Data Cache Cacheability Register */ #define SPRN_ICCR 0x3FB /* Instruction Cache Cacheability Register */ +#define SPRN_PWRMGTCR0 0x3FB /* Power management control register 0 */ #define SPRN_SVR 0x3FF /* System Version Register */ /* @@ -217,6 +218,14 @@ #define CCR1_DPC 0x00000100 /* Disable L1 I-Cache/D-Cache parity checking */ #define CCR1_TCS 0x00000080 /* Timer Clock Select */ +/* Bit definitions for PWRMGTCR0. */ +#define PWRMGTCR0_PW20_WAIT (1 << 14) /* PW20 state enable bit */ +#define PWRMGTCR0_PW20_ENT_SHIFT 8 +#define PWRMGTCR0_PW20_ENT 0x3F00 +#define PWRMGTCR0_AV_IDLE_PD_EN (1 << 22) /* Altivec idle enable */ +#define PWRMGTCR0_AV_IDLE_CNT_SHIFT 16 +#define PWRMGTCR0_AV_IDLE_CNT 0x3F0000 + /* Bit definitions for the MCSR. */ #define MCSR_MCS 0x80000000 /* Machine Check Summary */ #define MCSR_IB 0x40000000 /* Instruction PLB Error */ -- cgit v1.2.3 From 1c49abec677c7ff495837dbaafad8e12f09c29fc Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 24 Dec 2013 15:12:05 +0800 Subject: powerpc: introduce macro LOAD_REG_ADDR_PIC This is used to get the address of a variable when the kernel is not running at the linked or relocated address. Signed-off-by: Kevin Hao Signed-off-by: Scott Wood --- arch/powerpc/include/asm/ppc_asm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index f595b98079ee..1279c59624ed 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -295,6 +295,11 @@ n: * you want to access various offsets within it). On ppc32 this is * identical to LOAD_REG_IMMEDIATE. * + * LOAD_REG_ADDR_PIC(rn, name) + * Loads the address of label 'name' into register 'run'. Use this when + * the kernel doesn't run at the linked or relocated address. Please + * note that this macro will clobber the lr register. + * * LOAD_REG_ADDRBASE(rn, name) * ADDROFF(name) * LOAD_REG_ADDRBASE loads part of the address of label 'name' into @@ -305,6 +310,14 @@ n: * LOAD_REG_ADDRBASE(rX, name) * ld rY,ADDROFF(name)(rX) */ + +/* Be careful, this will clobber the lr register. */ +#define LOAD_REG_ADDR_PIC(reg, name) \ + bl 0f; \ +0: mflr reg; \ + addis reg,reg,(name - 0b)@ha; \ + addi reg,reg,(name - 0b)@l; + #ifdef __powerpc64__ #define LOAD_REG_IMMEDIATE(reg,expr) \ lis reg,(expr)@highest; \ -- cgit v1.2.3 From 28efc35fe68dacbddc4b12c2fa8f2df1593a4ad3 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 11 Oct 2013 19:22:38 -0500 Subject: powerpc/e6500: TLB miss handler with hardware tablewalk support There are a few things that make the existing hw tablewalk handlers unsuitable for e6500: - Indirect entries go in TLB1 (though the resulting direct entries go in TLB0). - It has threads, but no "tlbsrx." -- so we need a spinlock and a normal "tlbsx". Because we need this lock, hardware tablewalk is mandatory on e6500 unless we want to add spinlock+tlbsx to the normal bolted TLB miss handler. - TLB1 has no HES (nor next-victim hint) so we need software round robin (TODO: integrate this round robin data with hugetlb/KVM) - The existing tablewalk handlers map half of a page table at a time, because IBM hardware has a fixed 1MiB indirect page size. e6500 has variable size indirect entries, with a minimum of 2MiB. So we can't do the half-page indirect mapping, and even if we could it would be less efficient than mapping the full page. - Like on e5500, the linear mapping is bolted, so we don't need the overhead of supporting nested tlb misses. Note that hardware tablewalk does not work in rev1 of e6500. We do not expect to support e6500 rev1 in mainline Linux. Signed-off-by: Scott Wood Cc: Mihai Caraman --- arch/powerpc/include/asm/mmu-book3e.h | 13 +++++++++++++ arch/powerpc/include/asm/mmu.h | 21 +++++++++++---------- arch/powerpc/include/asm/paca.h | 6 ++++++ 3 files changed, 30 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index 936db360790a..89b785d16846 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -286,8 +286,21 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) extern int mmu_linear_psize; extern int mmu_vmemmap_psize; +struct tlb_core_data { + /* For software way selection, as on Freescale TLB1 */ + u8 esel_next, esel_max, esel_first; + + /* Per-core spinlock for e6500 TLB handlers (no tlbsrx.) */ + u8 lock; +}; + #ifdef CONFIG_PPC64 extern unsigned long linear_map_top; +extern int book3e_htw_mode; + +#define PPC_HTW_NONE 0 +#define PPC_HTW_IBM 1 +#define PPC_HTW_E6500 2 /* * 64-bit booke platforms don't load the tlb in the tlb miss handler code. diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 691fd8aca939..f8d1d6dcf7db 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -180,16 +180,17 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr) #define MMU_PAGE_64K_AP 3 /* "Admixed pages" (hash64 only) */ #define MMU_PAGE_256K 4 #define MMU_PAGE_1M 5 -#define MMU_PAGE_4M 6 -#define MMU_PAGE_8M 7 -#define MMU_PAGE_16M 8 -#define MMU_PAGE_64M 9 -#define MMU_PAGE_256M 10 -#define MMU_PAGE_1G 11 -#define MMU_PAGE_16G 12 -#define MMU_PAGE_64G 13 - -#define MMU_PAGE_COUNT 14 +#define MMU_PAGE_2M 6 +#define MMU_PAGE_4M 7 +#define MMU_PAGE_8M 8 +#define MMU_PAGE_16M 9 +#define MMU_PAGE_64M 10 +#define MMU_PAGE_256M 11 +#define MMU_PAGE_1G 12 +#define MMU_PAGE_16G 13 +#define MMU_PAGE_64G 14 + +#define MMU_PAGE_COUNT 15 #if defined(CONFIG_PPC_STD_MMU_64) /* 64-bit classic hash table MMU */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index c3523d1dda58..e81731c62a7f 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -113,6 +113,10 @@ struct paca_struct { /* Keep pgd in the same cacheline as the start of extlb */ pgd_t *pgd __attribute__((aligned(0x80))); /* Current PGD */ pgd_t *kernel_pgd; /* Kernel PGD */ + + /* Shared by all threads of a core -- points to tcd of first thread */ + struct tlb_core_data *tcd_ptr; + /* We can have up to 3 levels of reentrancy in the TLB miss handler */ u64 extlb[3][EX_TLB_SIZE / sizeof(u64)]; u64 exmc[8]; /* used for machine checks */ @@ -123,6 +127,8 @@ struct paca_struct { void *mc_kstack; void *crit_kstack; void *dbg_kstack; + + struct tlb_core_data tcd; #endif /* CONFIG_PPC_BOOK3E */ mm_context_t context; -- cgit v1.2.3 From a655f724df2c0e1634477c7e89da81477a691c0f Mon Sep 17 00:00:00 2001 From: Shaohui Xie Date: Tue, 7 Jan 2014 14:27:41 +0800 Subject: powerpc/85xx: handle the eLBC error interrupt if it exists in dts On P1020, P1021, P1022, and P1023, eLBC event interrupts are routed to internal interrupt 3 while ELBC error interrupts are routed to internal interrupt 0. We need to call request_irq for each. Signed-off-by: Shaohui Xie Signed-off-by: Wang Dongsheng Signed-off-by: Kumar Gala [scottwood@freescale.com: reworded commit message and fixed author] Signed-off-by: Scott Wood --- arch/powerpc/include/asm/fsl_lbc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/fsl_lbc.h b/arch/powerpc/include/asm/fsl_lbc.h index 420b45368fcf..067fb0dca549 100644 --- a/arch/powerpc/include/asm/fsl_lbc.h +++ b/arch/powerpc/include/asm/fsl_lbc.h @@ -285,7 +285,7 @@ struct fsl_lbc_ctrl { /* device info */ struct device *dev; struct fsl_lbc_regs __iomem *regs; - int irq; + int irq[2]; wait_queue_head_t irq_wait; spinlock_t lock; void *nand; -- cgit v1.2.3 From c141611fb1ee2cfc374cf9be5327e97f361c4bed Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 9 Jan 2014 00:44:29 -0500 Subject: powerpc: Delete non-required instances of include None of these files are actually using any __init type directives and hence don't need to include . Most are just a left over from __devinit and __cpuinit removal, or simply due to code getting copied from one driver to the next. The one instance where we add an include for init.h covers off a case where that file was implicitly getting it from another header which itself didn't need it. Signed-off-by: Paul Gortmaker Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/paca.h | 1 - arch/powerpc/include/asm/ppc_asm.h | 1 - arch/powerpc/include/asm/ps3.h | 1 - arch/powerpc/include/asm/vio.h | 1 - 4 files changed, 4 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index c3523d1dda58..68bee4636045 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -16,7 +16,6 @@ #ifdef CONFIG_PPC64 -#include #include #include #include diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index f595b98079ee..7689e0e98d33 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -4,7 +4,6 @@ #ifndef _ASM_POWERPC_PPC_ASM_H #define _ASM_POWERPC_PPC_ASM_H -#include #include #include #include diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h index 678a7c1d9cb8..a1bc7e758422 100644 --- a/arch/powerpc/include/asm/ps3.h +++ b/arch/powerpc/include/asm/ps3.h @@ -21,7 +21,6 @@ #if !defined(_ASM_POWERPC_PS3_H) #define _ASM_POWERPC_PS3_H -#include #include #include #include diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h index 68d0cc998b1b..4f9b7ca0710f 100644 --- a/arch/powerpc/include/asm/vio.h +++ b/arch/powerpc/include/asm/vio.h @@ -15,7 +15,6 @@ #define _ASM_POWERPC_VIO_H #ifdef __KERNEL__ -#include #include #include #include -- cgit v1.2.3 From 1d350544d5bf17d835d2850004c64ca51235c771 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 3 Jan 2014 17:47:12 +0800 Subject: powerpc/eeh: Add restore_config operation After reset on the specific PE or PHB, we never configure AER correctly on PowerNV platform. We needn't care it on pSeries platform. The patch introduces additional EEH operation eeh_ops:: restore_config() so that we have chance to configure AER correctly for PowerNV platform. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d3e5e9bc8f94..7f8adc848cd6 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -157,6 +157,7 @@ struct eeh_ops { int (*read_config)(struct device_node *dn, int where, int size, u32 *val); int (*write_config)(struct device_node *dn, int where, int size, u32 val); int (*next_error)(struct eeh_pe **pe); + int (*restore_config)(struct device_node *dn); }; extern struct eeh_ops *eeh_ops; -- cgit v1.2.3 From 9be3becc2f99f4f2b1b697a616b1aa9e7889d68f Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 3 Jan 2014 17:47:13 +0800 Subject: powerpc/eeh: Call opal_pci_reinit() on powernv for restoring config space The patch implements the EEH operation backend restore_config() for PowerNV platform. That relies on OPAL API opal_pci_reinit() where we reinitialize the error reporting properly after PE or PHB reset. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index a4041e9ed550..9a87b4401a41 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -344,12 +344,16 @@ enum OpalMveEnableAction { OPAL_ENABLE_MVE = 1 }; -enum OpalPciResetAndReinitScope { +enum OpalPciResetScope { OPAL_PHB_COMPLETE = 1, OPAL_PCI_LINK = 2, OPAL_PHB_ERROR = 3, OPAL_PCI_HOT_RESET = 4, OPAL_PCI_FUNDAMENTAL_RESET = 5, OPAL_PCI_IODA_TABLE_RESET = 6, }; +enum OpalPciReinitScope { + OPAL_REINIT_PCI_DEV = 1000 +}; + enum OpalPciResetState { OPAL_DEASSERT_RESET = 0, OPAL_ASSERT_RESET = 1 @@ -801,7 +805,7 @@ int64_t opal_pci_get_phb_diag_data(uint64_t phb_id, void *diag_buffer, int64_t opal_pci_get_phb_diag_data2(uint64_t phb_id, void *diag_buffer, uint64_t diag_buffer_len); int64_t opal_pci_fence_phb(uint64_t phb_id); -int64_t opal_pci_reinit(uint64_t phb_id, uint8_t reinit_scope); +int64_t opal_pci_reinit(uint64_t phb_id, uint64_t reinit_scope, uint64_t data); int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t error_type, uint8_t mask_action); int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action); int64_t opal_get_epow_status(__be64 *status); -- cgit v1.2.3 From f26c7a035b7f2f1a7505ce42e4ba946b12f7df91 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Sun, 12 Jan 2014 14:13:45 +0800 Subject: powerpc/eeh: Hotplug improvement When EEH error comes to one specific PCI device before its driver is loaded, we will apply hotplug to recover the error. During the plug time, the PCI device will be probed and its driver is loaded. Then we wrongly calls to the error handlers if the driver supports EEH explicitly. The patch intends to fix by introducing flag EEH_DEV_NO_HANDLER and set it before we remove the PCI device. In turn, we can avoid wrongly calls the error handlers of the PCI device after its driver loaded. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 7f8adc848cd6..8b4b8e4a5c32 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -90,7 +90,8 @@ struct eeh_pe { #define EEH_DEV_IRQ_DISABLED (1 << 3) /* Interrupt disabled */ #define EEH_DEV_DISCONNECTED (1 << 4) /* Removing from PE */ -#define EEH_DEV_SYSFS (1 << 8) /* Sysfs created */ +#define EEH_DEV_NO_HANDLER (1 << 8) /* No error handler */ +#define EEH_DEV_SYSFS (1 << 9) /* Sysfs created */ struct eeh_dev { int mode; /* EEH mode */ -- cgit v1.2.3 From d4edc5b6c480a0917e61d93d55531d7efa6230be Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Mon, 30 Dec 2013 17:05:34 +0530 Subject: powerpc: Fix the setup of CPU-to-Node mappings during CPU online On POWER platforms, the hypervisor can notify the guest kernel about dynamic changes in the cpu-numa associativity (VPHN topology update). Hence the cpu-to-node mappings that we got from the firmware during boot, may no longer be valid after such updates. This is handled using the arch_update_cpu_topology() hook in the scheduler, and the sched-domains are rebuilt according to the new mappings. But unfortunately, at the moment, CPU hotplug ignores these updated mappings and instead queries the firmware for the cpu-to-numa relationships and uses them during CPU online. So the kernel can end up assigning wrong NUMA nodes to CPUs during subsequent CPU hotplug online operations (after booting). Further, a particularly problematic scenario can result from this bug: On POWER platforms, the SMT mode can be switched between 1, 2, 4 (and even 8) threads per core. The switch to Single-Threaded (ST) mode is performed by offlining all except the first CPU thread in each core. Switching back to SMT mode involves onlining those other threads back, in each core. Now consider this scenario: 1. During boot, the kernel gets the cpu-to-node mappings from the firmware and assigns the CPUs to NUMA nodes appropriately, during CPU online. 2. Later on, the hypervisor updates the cpu-to-node mappings dynamically and communicates this update to the kernel. The kernel in turn updates its cpu-to-node associations and rebuilds its sched domains. Everything is fine so far. 3. Now, the user switches the machine from SMT to ST mode (say, by running ppc64_cpu --smt=1). This involves offlining all except 1 thread in each core. 4. The user then tries to switch back from ST to SMT mode (say, by running ppc64_cpu --smt=4), and this involves onlining those threads back. Since CPU hotplug ignores the new mappings, it queries the firmware and tries to associate the newly onlined sibling threads to the old NUMA nodes. This results in sibling threads within the same core getting associated with different NUMA nodes, which is incorrect. The scheduler's build-sched-domains code gets thoroughly confused with this and enters an infinite loop and causes soft-lockups, as explained in detail in commit 3be7db6ab (powerpc: VPHN topology change updates all siblings). So to fix this, use the numa_cpu_lookup_table to remember the updated cpu-to-node mappings, and use them during CPU hotplug online operations. Further, we also need to ensure that all threads in a core are assigned to a common NUMA node, irrespective of whether all those threads were online during the topology update. To achieve this, we take care not to use cpu_sibling_mask() since it is not hotplug invariant. Instead, we use cpu_first_sibling_thread() and set up the mappings manually using the 'threads_per_core' value for that particular platform. This helps us ensure that we don't hit this bug with any combination of CPU hotplug and SMT mode switching. Cc: stable@vger.kernel.org Signed-off-by: Srivatsa S. Bhat Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/topology.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 89e3ef2496ac..d0b5fca6b077 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -22,7 +22,15 @@ struct device_node; static inline int cpu_to_node(int cpu) { - return numa_cpu_lookup_table[cpu]; + int nid; + + nid = numa_cpu_lookup_table[cpu]; + + /* + * During early boot, the numa-cpu lookup table might not have been + * setup for all CPUs yet. In such cases, default to node 0. + */ + return (nid < 0) ? 0 : nid; } #define parent_node(node) (node) -- cgit v1.2.3 From 30c826358d10c1d6f8147de3310b97488daec830 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Tue, 14 Jan 2014 15:45:09 +0530 Subject: Move precessing of MCE queued event out from syscall exit path. Huge Dickins reported an issue that b5ff4211a829 "powerpc/book3s: Queue up and process delayed MCE events" breaks the PowerMac G5 boot. This patch fixes it by moving the mce even processing away from syscall exit, which was wrong to do that in first place, and using irq work framework to delay processing of mce event. Reported-by: Hugh Dickins Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mce.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index a2b8c7b35fba..8e99edf6d966 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -191,7 +191,6 @@ extern void save_mce_event(struct pt_regs *regs, long handled, extern int get_mce_event(struct machine_check_event *mce, bool release); extern void release_mce_event(void); extern void machine_check_queue_event(void); -extern void machine_check_process_queued_event(void); extern void machine_check_print_event_info(struct machine_check_event *evt); extern uint64_t get_mce_fault_addr(struct machine_check_event *evt); -- cgit v1.2.3 From ae39c58c2e56209ae3503286ffe2338d5e9a4bed Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 13 Jan 2014 15:56:28 +1100 Subject: powerpc: Reclaim two unused thread_info flag bits TIF_PERFMON_WORK and TIF_PERFMON_CTXSW are completely unused. They appear to be related to the old perfmon2 code, which has been superseded by the perf_event infrastructure. This removes their definitions so that the bits can be used for other purposes. Signed-off-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/thread_info.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 9854c564ac52..fc2bf414c584 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -91,8 +91,6 @@ static inline struct thread_info *current_thread_info(void) #define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_32BIT 4 /* 32 bit binary */ -#define TIF_PERFMON_WORK 5 /* work for pfm_handle_work() */ -#define TIF_PERFMON_CTXSW 6 /* perfmon needs ctxsw calls */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ #define TIF_NOHZ 9 /* in adaptive nohz mode */ @@ -115,8 +113,6 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NEED_RESCHED (1< Date: Mon, 13 Jan 2014 15:56:29 +1100 Subject: powerpc: Don't corrupt transactional state when using FP/VMX in kernel Currently, when we have a process using the transactional memory facilities on POWER8 (that is, the processor is in transactional or suspended state), and the process enters the kernel and the kernel then uses the floating-point or vector (VMX/Altivec) facility, we end up corrupting the user-visible FP/VMX/VSX state. This happens, for example, if a page fault causes a copy-on-write operation, because the copy_page function will use VMX to do the copy on POWER8. The test program below demonstrates the bug. The bug happens because when FP/VMX state for a transactional process is stored in the thread_struct, we store the checkpointed state in .fp_state/.vr_state and the transactional (current) state in .transact_fp/.transact_vr. However, when the kernel wants to use FP/VMX, it calls enable_kernel_fp() or enable_kernel_altivec(), which saves the current state in .fp_state/.vr_state. Furthermore, when we return to the user process we return with FP/VMX/VSX disabled. The next time the process uses FP/VMX/VSX, we don't know which set of state (the current register values, .fp_state/.vr_state, or .transact_fp/.transact_vr) we should be using, since we have no way to tell if we are still in the same transaction, and if not, whether the previous transaction succeeded or failed. Thus it is necessary to strictly adhere to the rule that if FP has been enabled at any point in a transaction, we must keep FP enabled for the user process with the current transactional state in the FP registers, until we detect that it is no longer in a transaction. Similarly for VMX; once enabled it must stay enabled until the process is no longer transactional. In order to keep this rule, we add a new thread_info flag which we test when returning from the kernel to userspace, called TIF_RESTORE_TM. This flag indicates that there is FP/VMX/VSX state to be restored before entering userspace, and when it is set the .tm_orig_msr field in the thread_struct indicates what state needs to be restored. The restoration is done by restore_tm_state(). The TIF_RESTORE_TM bit is set by new giveup_fpu/altivec_maybe_transactional helpers, which are called from enable_kernel_fp/altivec, giveup_vsx, and flush_fp/altivec_to_thread instead of giveup_fpu/altivec. The other thing to be done is to get the transactional FP/VMX/VSX state from .fp_state/.vr_state when doing reclaim, if that state has been saved there by giveup_fpu/altivec_maybe_transactional. Having done this, we set the FP/VMX bit in the thread's MSR after reclaim to indicate that that part of the state is now valid (having been reclaimed from the processor's checkpointed state). Finally, in the signal handling code, we move the clearing of the transactional state bits in the thread's MSR a bit earlier, before calling flush_fp_to_thread(), so that we don't unnecessarily set the TIF_RESTORE_TM bit. This is the test program: /* Michael Neuling 4/12/2013 * * See if the altivec state is leaked out of an aborted transaction due to * kernel vmx copy loops. * * gcc -m64 htm_vmxcopy.c -o htm_vmxcopy * */ /* We don't use all of these, but for reference: */ int main(int argc, char *argv[]) { long double vecin = 1.3; long double vecout; unsigned long pgsize = getpagesize(); int i; int fd; int size = pgsize*16; char tmpfile[] = "/tmp/page_faultXXXXXX"; char buf[pgsize]; char *a; uint64_t aborted = 0; fd = mkstemp(tmpfile); assert(fd >= 0); memset(buf, 0, pgsize); for (i = 0; i < size; i += pgsize) assert(write(fd, buf, pgsize) == pgsize); unlink(tmpfile); a = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0); assert(a != MAP_FAILED); asm __volatile__( "lxvd2x 40,0,%[vecinptr] ; " // set 40 to initial value TBEGIN "beq 3f ;" TSUSPEND "xxlxor 40,40,40 ; " // set 40 to 0 "std 5, 0(%[map]) ;" // cause kernel vmx copy page TABORT TRESUME TEND "li %[res], 0 ;" "b 5f ;" "3: ;" // Abort handler "li %[res], 1 ;" "5: ;" "stxvd2x 40,0,%[vecoutptr] ; " : [res]"=r"(aborted) : [vecinptr]"r"(&vecin), [vecoutptr]"r"(&vecout), [map]"r"(a) : "memory", "r0", "r3", "r4", "r5", "r6", "r7"); if (aborted && (vecin != vecout)){ printf("FAILED: vector state leaked on abort %f != %f\n", (double)vecin, (double)vecout); exit(1); } munmap(a, size); close(fd); printf("PASSED!\n"); return 0; } Signed-off-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/processor.h | 2 ++ arch/powerpc/include/asm/thread_info.h | 5 ++++- arch/powerpc/include/asm/tm.h | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index fc14a38c7ccf..232a2fa5b483 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -373,6 +373,8 @@ extern int set_endian(struct task_struct *tsk, unsigned int val); extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr); extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); +extern void fp_enable(void); +extern void vec_enable(void); extern void load_fp_state(struct thread_fp_state *fp); extern void store_fp_state(struct thread_fp_state *fp); extern void load_vr_state(struct thread_vr_state *vr); diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index fc2bf414c584..b034ecdb7c74 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -91,6 +91,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_32BIT 4 /* 32 bit binary */ +#define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ #define TIF_NOHZ 9 /* in adaptive nohz mode */ @@ -113,6 +114,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NEED_RESCHED (1< Date: Wed, 15 Jan 2014 13:16:11 +0800 Subject: powerpc/eeh: Handle multiple EEH errors For one PCI error relevant OPAL event, we possibly have multiple EEH errors for that. For example, multiple frozen PEs detected on different PHBs. Unfortunately, we didn't cover the case. The patch enumarates the return value from eeh_ops::next_error() and change eeh_handle_special_event() and eeh_ops::next_error() to handle all existing EEH errors. As Ben pointed out, we needn't list_for_each_entry_safe() since we are not deleting any PHB from the hose_list and the EEH serialized lock should be held while purging EEH events. The patch covers those suggestions as well. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 8b4b8e4a5c32..9e39ceb1d19f 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -118,6 +118,16 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev) return edev ? edev->pdev : NULL; } +/* Return values from eeh_ops::next_error */ +enum { + EEH_NEXT_ERR_NONE = 0, + EEH_NEXT_ERR_INF, + EEH_NEXT_ERR_FROZEN_PE, + EEH_NEXT_ERR_FENCED_PHB, + EEH_NEXT_ERR_DEAD_PHB, + EEH_NEXT_ERR_DEAD_IOC +}; + /* * The struct is used to trace the registered EEH operation * callback functions. Actually, those operation callback -- cgit v1.2.3 From f7d98d18a01ece2863984d4fb5ae949b18b02715 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Wed, 15 Jan 2014 17:02:04 +1100 Subject: powerpc/powernv: Call OPAL sync before kexec'ing Its possible that OPAL may be writing to host memory during kexec (like dump retrieve scenario). In this situation we might end up corrupting host memory. This patch makes OPAL sync call to make sure OPAL stops writing to host memory before kexec'ing. Signed-off-by: Vasant Hegde Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 9a87b4401a41..40157e2ca691 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -156,6 +156,7 @@ extern int opal_enter_rtas(struct rtas_args *args, #define OPAL_FLASH_UPDATE 78 #define OPAL_GET_MSG 85 #define OPAL_CHECK_ASYNC_COMPLETION 86 +#define OPAL_SYNC_HOST_REBOOT 87 #ifndef __ASSEMBLY__ @@ -828,6 +829,7 @@ int64_t opal_update_flash(uint64_t blk_list); int64_t opal_get_msg(uint64_t buffer, size_t size); int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token); +int64_t opal_sync_host_reboot(void); /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); -- cgit v1.2.3 From 3405d230b374b6923878b21b8d708d7db1f734ef Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 15 Jan 2014 18:14:28 +1100 Subject: powerpc: Add support for the optimised lockref implementation This commit adds the architecture support required to enable the optimised implementation of lockrefs. That's as simple as defining arch_spin_value_unlocked() and selecting the Kconfig option. We also define cmpxchg64_relaxed(), because the lockref code does not need the cmpxchg to have barrier semantics. Using Linus' test case[1] on one system I see a 4x improvement for the basic enablement, and a further 1.3x for cmpxchg64_relaxed(), for a total of 5.3x vs the baseline. On another system I see more like 2x improvement. [1]: http://marc.info/?l=linux-fsdevel&m=137782380714721&w=4 Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cmpxchg.h | 1 + arch/powerpc/include/asm/spinlock.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index e245aab7f191..d463c68fe7f0 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -300,6 +300,7 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new, BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg_local((ptr), (o), (n)); \ }) +#define cmpxchg64_relaxed cmpxchg64_local #else #include #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 5f54a744dcc5..5162f8cd18c0 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -54,6 +54,11 @@ #define SYNC_IO #endif +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.slock == 0; +} + /* * This returns the old value in the lock, so we succeeded * in getting the lock if the return value is 0. -- cgit v1.2.3 From 7179ba52889bef7e5e23f72908270e1ab2b7fc6f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 15 Jan 2014 18:14:29 +1100 Subject: powerpc: Implement arch_spin_is_locked() using arch_spin_value_unlocked() At a glance these are just the inverse of each other. The one subtlety is that arch_spin_value_unlocked() takes the lock by value, rather than as a pointer, which is important for the lockref code. On the other hand arch_spin_is_locked() doesn't really care, so implement it in terms of arch_spin_value_unlocked(). Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/spinlock.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 5162f8cd18c0..a30ef6999d66 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -28,8 +28,6 @@ #include #include -#define arch_spin_is_locked(x) ((x)->slock != 0) - #ifdef CONFIG_PPC64 /* use 0x800000yy when locked, where yy == CPU number */ #ifdef __BIG_ENDIAN__ @@ -59,6 +57,11 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) return lock.slock == 0; } +static inline int arch_spin_is_locked(arch_spinlock_t *lock) +{ + return !arch_spin_value_unlocked(*lock); +} + /* * This returns the old value in the lock, so we succeeded * in getting the lock if the return value is 0. -- cgit v1.2.3