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/asm') 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 +++++++++++++- arch/powerpc/kernel/misc_32.S | 4 +++- arch/powerpc/kernel/misc_64.S | 6 ++++++ 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') 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 diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index e47d268727a4..879f09620f83 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -344,7 +344,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) */ _KPROBE(flush_icache_range) BEGIN_FTR_SECTION - isync + PURGE_PREFETCHED_INS blr /* for 601, do nothing */ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) li r5,L1_CACHE_BYTES-1 @@ -448,6 +448,7 @@ _GLOBAL(invalidate_dcache_range) */ _GLOBAL(__flush_dcache_icache) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ @@ -489,6 +490,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x) */ _GLOBAL(__flush_dcache_icache_phys) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr /* for 601, do nothing */ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) mfmsr r10 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index e59caf874d05..a9f7a79a3a40 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -67,6 +67,7 @@ PPC64_CACHES: _KPROBE(flush_icache_range) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) /* @@ -211,6 +212,11 @@ _GLOBAL(__flush_dcache_icache) * Different systems have different cache line sizes */ +BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS + blr +END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) + /* Flush the dcache */ ld r7,PPC64_CACHES@toc(r2) clrrdi r3,r3,PAGE_SHIFT /* Page align */ -- 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 ++- arch/powerpc/kernel/irq.c | 12 +++++++++--- arch/powerpc/kernel/time.c | 3 ++- 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include/asm') 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; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ba0165615215..9729b23bfb0a 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -354,8 +354,13 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) - seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs); - seq_printf(p, " Local timer interrupts\n"); + seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event); + seq_printf(p, " Local timer interrupts for timer event device\n"); + + seq_printf(p, "%*s: ", prec, "LOC"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others); + seq_printf(p, " Local timer interrupts for others\n"); seq_printf(p, "%*s: ", prec, "SPU"); for_each_online_cpu(j) @@ -389,11 +394,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) */ u64 arch_irq_stat_cpu(unsigned int cpu) { - u64 sum = per_cpu(irq_stat, cpu).timer_irqs; + u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event; sum += per_cpu(irq_stat, cpu).pmu_irqs; sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; + sum += per_cpu(irq_stat, cpu).timer_irqs_others; #ifdef CONFIG_PPC_DOORBELL sum += per_cpu(irq_stat, cpu).doorbell_irqs; #endif diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index b3b144121cc9..afb1b56ef4fa 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -510,7 +510,6 @@ void timer_interrupt(struct pt_regs * regs) */ may_hard_irq_enable(); - __get_cpu_var(irq_stat).timer_irqs++; #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) @@ -532,10 +531,12 @@ void timer_interrupt(struct pt_regs * regs) *next_tb = ~(u64)0; if (evt->event_handler) evt->event_handler(evt); + __get_cpu_var(irq_stat).timer_irqs_event++; } else { now = *next_tb - now; if (now <= DECREMENTER_MAX) set_dec((int)now); + __get_cpu_var(irq_stat).timer_irqs_others++; } #ifdef CONFIG_PPC64 -- 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/asm') 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 +++++++++ arch/powerpc/kernel/setup_64.c | 10 +++++++++- arch/powerpc/xmon/xmon.c | 4 ++++ 3 files changed, 22 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') 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 */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5760b9bea936..2232aff66059 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -540,7 +540,8 @@ static void __init exc_lvl_early_init(void) /* * Stack space used when we detect a bad kernel stack pointer, and - * early in SMP boots before relocation is enabled. + * early in SMP boots before relocation is enabled. Exclusive emergency + * stack for machine checks. */ static void __init emergency_stack_init(void) { @@ -563,6 +564,13 @@ static void __init emergency_stack_init(void) sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); sp += THREAD_SIZE; paca[i].emergency_sp = __va(sp); + +#ifdef CONFIG_PPC_BOOK3S_64 + /* emergency stack for machine check exception handling. */ + sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); + sp += THREAD_SIZE; + paca[i].mc_emergency_sp = __va(sp); +#endif } } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index af9d3469fb99..a90731b3d44a 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2051,6 +2051,10 @@ static void dump_one_paca(int cpu) DUMP(p, stab_addr, "lx"); #endif DUMP(p, emergency_sp, "p"); +#ifdef CONFIG_PPC_BOOK3S_64 + DUMP(p, mc_emergency_sp, "p"); + DUMP(p, in_mce, "x"); +#endif DUMP(p, data_offset, "lx"); DUMP(p, hw_cpu_id, "x"); DUMP(p, cpu_start, "x"); -- 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 +++++++ arch/powerpc/kernel/traps.c | 7 +++++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') 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; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 97a1ce72e130..330841766b09 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -293,8 +293,11 @@ void system_reset_exception(struct pt_regs *regs) */ long machine_check_early(struct pt_regs *regs) { - /* TODO: handle/decode machine check reason */ - return 0; + long handled = 0; + + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) + handled = cur_cpu_spec->machine_check_early(regs); + return handled; } #endif -- 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 +++++ arch/powerpc/kernel/cpu_setup_power.S | 38 +++++++++++++++++++++++++---------- arch/powerpc/kernel/cputable.c | 8 ++++++++ arch/powerpc/kvm/book3s_hv_ras.c | 18 ++++------------- 4 files changed, 44 insertions(+), 25 deletions(-) (limited to 'arch/powerpc/include/asm') 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; diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 18b5b9cf8e37..37d1bb002aa9 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -29,7 +29,7 @@ _GLOBAL(__setup_cpu_power7) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR bl __init_LPCR - bl __init_TLB + bl __init_tlb_power7 mtlr r11 blr @@ -42,7 +42,7 @@ _GLOBAL(__restore_cpu_power7) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR bl __init_LPCR - bl __init_TLB + bl __init_tlb_power7 mtlr r11 blr @@ -59,7 +59,7 @@ _GLOBAL(__setup_cpu_power8) oris r3, r3, LPCR_AIL_3@h bl __init_LPCR bl __init_HFSCR - bl __init_TLB + bl __init_tlb_power8 bl __init_PMU_HV mtlr r11 blr @@ -78,7 +78,7 @@ _GLOBAL(__restore_cpu_power8) oris r3, r3, LPCR_AIL_3@h bl __init_LPCR bl __init_HFSCR - bl __init_TLB + bl __init_tlb_power8 bl __init_PMU_HV mtlr r11 blr @@ -134,15 +134,31 @@ __init_HFSCR: mtspr SPRN_HFSCR,r3 blr -__init_TLB: - /* - * Clear the TLB using the "IS 3" form of tlbiel instruction - * (invalidate by congruence class). P7 has 128 CCs, P8 has 512 - * so we just always do 512 - */ +/* + * Clear the TLB using the specified IS form of tlbiel instruction + * (invalidate by congruence class). P7 has 128 CCs., P8 has 512. + * + * r3 = IS field + */ +__init_tlb_power7: + li r3,0xc00 /* IS field = 0b11 */ +_GLOBAL(__flush_tlb_power7) + li r6,128 + mtctr r6 + mr r7,r3 /* IS field */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: blr + +__init_tlb_power8: + li r3,0xc00 /* IS field = 0b11 */ +_GLOBAL(__flush_tlb_power8) li r6,512 mtctr r6 - li r7,0xc00 /* IS field = 0b11 */ + mr r7,r3 /* IS field */ ptesync 2: tlbiel r7 addi r7,r7,0x1000 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 597d954e5860..55d0f9c282b8 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -71,6 +71,8 @@ extern void __restore_cpu_power7(void); extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power8(void); extern void __restore_cpu_a2(void); +extern void __flush_tlb_power7(unsigned long inval_selector); +extern void __flush_tlb_power8(unsigned long inval_selector); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -440,6 +442,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, .platform = "power7", }, { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ @@ -456,6 +459,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, .platform = "power8", }, { /* Power7 */ @@ -474,6 +478,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, .platform = "power7", }, { /* Power7+ */ @@ -492,6 +497,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, .platform = "power7+", }, { /* Power8E */ @@ -510,6 +516,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, .platform = "power8", }, { /* Power8 */ @@ -528,6 +535,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, .platform = "power8", }, { /* Cell Broadband Engine */ diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index a353c485808c..5c427b41a2f5 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -58,18 +58,6 @@ static void reload_slb(struct kvm_vcpu *vcpu) } } -/* POWER7 TLB flush */ -static void flush_tlb_power7(struct kvm_vcpu *vcpu) -{ - unsigned long i, rb; - - rb = TLBIEL_INVAL_SET_LPID; - for (i = 0; i < POWER7_TLB_SETS; ++i) { - asm volatile("tlbiel %0" : : "r" (rb)); - rb += 1 << TLBIEL_INVAL_SET_SHIFT; - } -} - /* * On POWER7, see if we can handle a machine check that occurred inside * the guest in real mode, without switching to the host partition. @@ -96,7 +84,8 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) DSISR_MC_SLB_PARITY | DSISR_MC_DERAT_MULTI); } if (dsisr & DSISR_MC_TLB_MULTI) { - flush_tlb_power7(vcpu); + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID); dsisr &= ~DSISR_MC_TLB_MULTI; } /* Any other errors we don't understand? */ @@ -113,7 +102,8 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) reload_slb(vcpu); break; case SRR1_MC_IFETCH_TLBMULTI: - flush_tlb_power7(vcpu); + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID); break; default: handled = 0; -- 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 +++++++++++++++++ arch/powerpc/kernel/Makefile | 1 + arch/powerpc/kernel/cputable.c | 4 + arch/powerpc/kernel/mce_power.c | 150 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 227 insertions(+) create mode 100644 arch/powerpc/include/asm/mce.h create mode 100644 arch/powerpc/kernel/mce_power.c (limited to 'arch/powerpc/include/asm') 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__ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 445cb6e39d5b..07c63d0aa759 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o +obj-$(CONFIG_PPC_BOOK3S_64) += mce_power.o obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 55d0f9c282b8..c54188bcdd9e 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -73,6 +73,7 @@ extern void __restore_cpu_power8(void); extern void __restore_cpu_a2(void); extern void __flush_tlb_power7(unsigned long inval_selector); extern void __flush_tlb_power8(unsigned long inval_selector); +extern long __machine_check_early_realmode_p7(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -443,6 +444,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ @@ -479,6 +481,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, { /* Power7+ */ @@ -498,6 +501,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7+", }, { /* Power8E */ diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c new file mode 100644 index 000000000000..690547319b03 --- /dev/null +++ b/arch/powerpc/kernel/mce_power.c @@ -0,0 +1,150 @@ +/* + * Machine check exception handling CPU-side for power7 and power8 + * + * 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 + */ + +#undef DEBUG +#define pr_fmt(fmt) "mce_power: " fmt + +#include +#include +#include +#include + +/* flush SLBs and reload */ +static void flush_and_reload_slb(void) +{ + struct slb_shadow *slb; + unsigned long i, n; + + /* Invalidate all SLBs */ + asm volatile("slbmte %0,%0; slbia" : : "r" (0)); + +#ifdef CONFIG_KVM_BOOK3S_HANDLER + /* + * If machine check is hit when in guest or in transition, we will + * only flush the SLBs and continue. + */ + if (get_paca()->kvm_hstate.in_guest) + return; +#endif + + /* For host kernel, reload the SLBs from shadow SLB buffer. */ + slb = get_slb_shadow(); + if (!slb) + return; + + n = min_t(u32, slb->persistent, SLB_MIN_SIZE); + + /* Load up the SLB entries from shadow SLB */ + for (i = 0; i < n; i++) { + unsigned long rb = slb->save_area[i].esid; + unsigned long rs = slb->save_area[i].vsid; + + rb = (rb & ~0xFFFul) | i; + asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb)); + } +} + +static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) +{ + long handled = 1; + + /* + * flush and reload SLBs for SLB errors and flush TLBs for TLB errors. + * reset the error bits whenever we handle them so that at the end + * we can check whether we handled all of them or not. + * */ + if (dsisr & slb_error_bits) { + flush_and_reload_slb(); + /* reset error bits */ + dsisr &= ~(slb_error_bits); + } + if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + /* reset error bits */ + dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; + } + /* Any other errors we don't understand? */ + if (dsisr & 0xffffffffUL) + handled = 0; + + return handled; +} + +static long mce_handle_derror_p7(uint64_t dsisr) +{ + return mce_handle_derror(dsisr, P7_DSISR_MC_SLB_ERRORS); +} + +static long mce_handle_common_ierror(uint64_t srr1) +{ + long handled = 0; + + switch (P7_SRR1_MC_IFETCH(srr1)) { + case 0: + break; + case P7_SRR1_MC_IFETCH_SLB_PARITY: + case P7_SRR1_MC_IFETCH_SLB_MULTIHIT: + /* flush and reload SLBs for SLB errors. */ + flush_and_reload_slb(); + handled = 1; + break; + case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + handled = 1; + } + break; + default: + break; + } + + return handled; +} + +static long mce_handle_ierror_p7(uint64_t srr1) +{ + long handled = 0; + + handled = mce_handle_common_ierror(srr1); + + if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) { + flush_and_reload_slb(); + handled = 1; + } + return handled; +} + +long __machine_check_early_realmode_p7(struct pt_regs *regs) +{ + uint64_t srr1; + long handled = 1; + + srr1 = regs->msr; + + if (P7_SRR1_MC_LOADSTORE(srr1)) + handled = mce_handle_derror_p7(regs->dsisr); + else + handled = mce_handle_ierror_p7(srr1); + + /* TODO: Decode machine check reason. */ + return handled; +} -- 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 +++ arch/powerpc/kernel/cputable.c | 4 ++++ arch/powerpc/kernel/mce_power.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 41 insertions(+) (limited to 'arch/powerpc/include/asm') 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__ */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index c54188bcdd9e..6c8dd5da4de5 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -74,6 +74,7 @@ extern void __restore_cpu_a2(void); extern void __flush_tlb_power7(unsigned long inval_selector); extern void __flush_tlb_power8(unsigned long inval_selector); extern long __machine_check_early_realmode_p7(struct pt_regs *regs); +extern long __machine_check_early_realmode_p8(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -462,6 +463,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Power7 */ @@ -521,6 +523,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Power8 */ @@ -540,6 +543,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Cell Broadband Engine */ diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 690547319b03..60a217f11275 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -148,3 +148,37 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs) /* TODO: Decode machine check reason. */ return handled; } + +static long mce_handle_ierror_p8(uint64_t srr1) +{ + long handled = 0; + + handled = mce_handle_common_ierror(srr1); + + if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) { + flush_and_reload_slb(); + handled = 1; + } + return handled; +} + +static long mce_handle_derror_p8(uint64_t dsisr) +{ + return mce_handle_derror(dsisr, P8_DSISR_MC_SLB_ERRORS); +} + +long __machine_check_early_realmode_p8(struct pt_regs *regs) +{ + uint64_t srr1; + long handled = 1; + + srr1 = regs->msr; + + if (P7_SRR1_MC_LOADSTORE(srr1)) + handled = mce_handle_derror_p8(regs->dsisr); + else + handled = mce_handle_ierror_p8(srr1); + + /* TODO: Decode machine check reason. */ + return handled; +} -- 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 +++++++++++++++++++++++++ arch/powerpc/kernel/Makefile | 2 +- arch/powerpc/kernel/mce.c | 164 ++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/mce_power.c | 116 ++++++++++++++++++++++-- arch/powerpc/kvm/book3s_hv_ras.c | 32 ++++--- arch/powerpc/platforms/powernv/opal.c | 35 ++++---- 6 files changed, 434 insertions(+), 39 deletions(-) create mode 100644 arch/powerpc/kernel/mce.c (limited to 'arch/powerpc/include/asm') 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__ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 07c63d0aa759..904d713366ff 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o -obj-$(CONFIG_PPC_BOOK3S_64) += mce_power.o +obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c new file mode 100644 index 000000000000..aeecdf1ba897 --- /dev/null +++ b/arch/powerpc/kernel/mce.c @@ -0,0 +1,164 @@ +/* + * Machine check exception handling. + * + * 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 + */ + +#undef DEBUG +#define pr_fmt(fmt) "mce: " fmt + +#include +#include +#include +#include +#include + +static DEFINE_PER_CPU(int, mce_nest_count); +static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); + +static void mce_set_error_info(struct machine_check_event *mce, + struct mce_error_info *mce_err) +{ + mce->error_type = mce_err->error_type; + switch (mce_err->error_type) { + case MCE_ERROR_TYPE_UE: + mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type; + break; + case MCE_ERROR_TYPE_SLB: + mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type; + break; + case MCE_ERROR_TYPE_ERAT: + mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type; + break; + case MCE_ERROR_TYPE_TLB: + mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type; + break; + case MCE_ERROR_TYPE_UNKNOWN: + default: + break; + } +} + +/* + * Decode and save high level MCE information into per cpu buffer which + * is an array of machine_check_event structure. + */ +void save_mce_event(struct pt_regs *regs, long handled, + struct mce_error_info *mce_err, + uint64_t addr) +{ + uint64_t srr1; + int index = __get_cpu_var(mce_nest_count)++; + struct machine_check_event *mce = &__get_cpu_var(mce_event[index]); + + /* + * Return if we don't have enough space to log mce event. + * mce_nest_count may go beyond MAX_MC_EVT but that's ok, + * the check below will stop buffer overrun. + */ + if (index >= MAX_MC_EVT) + return; + + /* Populate generic machine check info */ + mce->version = MCE_V1; + mce->srr0 = regs->nip; + mce->srr1 = regs->msr; + mce->gpr3 = regs->gpr[3]; + mce->in_use = 1; + + mce->initiator = MCE_INITIATOR_CPU; + if (handled) + mce->disposition = MCE_DISPOSITION_RECOVERED; + else + mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; + mce->severity = MCE_SEV_ERROR_SYNC; + + srr1 = regs->msr; + + /* + * Populate the mce error_type and type-specific error_type. + */ + mce_set_error_info(mce, mce_err); + + if (!addr) + return; + + if (mce->error_type == MCE_ERROR_TYPE_TLB) { + mce->u.tlb_error.effective_address_provided = true; + mce->u.tlb_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_SLB) { + mce->u.slb_error.effective_address_provided = true; + mce->u.slb_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_ERAT) { + mce->u.erat_error.effective_address_provided = true; + mce->u.erat_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_UE) { + mce->u.ue_error.effective_address_provided = true; + mce->u.ue_error.effective_address = addr; + } + return; +} + +/* + * get_mce_event: + * mce Pointer to machine_check_event structure to be filled. + * release Flag to indicate whether to free the event slot or not. + * 0 <= do not release the mce event. Caller will invoke + * release_mce_event() once event has been consumed. + * 1 <= release the slot. + * + * return 1 = success + * 0 = failure + * + * get_mce_event() will be called by platform specific machine check + * handle routine and in KVM. + * When we call get_mce_event(), we are still in interrupt context and + * preemption will not be scheduled until ret_from_expect() routine + * is called. + */ +int get_mce_event(struct machine_check_event *mce, bool release) +{ + int index = __get_cpu_var(mce_nest_count) - 1; + struct machine_check_event *mc_evt; + int ret = 0; + + /* Sanity check */ + if (index < 0) + return ret; + + /* Check if we have MCE info to process. */ + if (index < MAX_MC_EVT) { + mc_evt = &__get_cpu_var(mce_event[index]); + /* Copy the event structure and release the original */ + if (mce) + *mce = *mc_evt; + if (release) + mc_evt->in_use = 0; + ret = 1; + } + /* Decrement the count to free the slot. */ + if (release) + __get_cpu_var(mce_nest_count)--; + + return ret; +} + +void release_mce_event(void) +{ + get_mce_event(NULL, true); +} diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 60a217f11275..b36e777a734f 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -133,22 +133,116 @@ static long mce_handle_ierror_p7(uint64_t srr1) return handled; } +static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1) +{ + switch (P7_SRR1_MC_IFETCH(srr1)) { + case P7_SRR1_MC_IFETCH_SLB_PARITY: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + break; + case P7_SRR1_MC_IFETCH_SLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + break; + case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + break; + case P7_SRR1_MC_IFETCH_UE: + case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH; + break; + case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = + MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH; + break; + } +} + +static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1) +{ + mce_get_common_ierror(mce_err, srr1); + if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; + } +} + +static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr) +{ + if (dsisr & P7_DSISR_MC_UE) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE; + } else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = + MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE; + } else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + } else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; + } +} + long __machine_check_early_realmode_p7(struct pt_regs *regs) { - uint64_t srr1; + uint64_t srr1, addr; long handled = 1; + struct mce_error_info mce_error_info = { 0 }; srr1 = regs->msr; - if (P7_SRR1_MC_LOADSTORE(srr1)) + /* + * Handle memory errors depending whether this was a load/store or + * ifetch exception. Also, populate the mce error_type and + * type-specific error_type from either SRR1 or DSISR, depending + * whether this was a load/store or ifetch exception + */ + if (P7_SRR1_MC_LOADSTORE(srr1)) { handled = mce_handle_derror_p7(regs->dsisr); - else + mce_get_derror_p7(&mce_error_info, regs->dsisr); + addr = regs->dar; + } else { handled = mce_handle_ierror_p7(srr1); + mce_get_ierror_p7(&mce_error_info, srr1); + addr = regs->nip; + } - /* TODO: Decode machine check reason. */ + save_mce_event(regs, handled, &mce_error_info, addr); return handled; } +static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1) +{ + mce_get_common_ierror(mce_err, srr1); + if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } +} + +static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr) +{ + mce_get_derror_p7(mce_err, dsisr); + if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } +} + static long mce_handle_ierror_p8(uint64_t srr1) { long handled = 0; @@ -169,16 +263,22 @@ static long mce_handle_derror_p8(uint64_t dsisr) long __machine_check_early_realmode_p8(struct pt_regs *regs) { - uint64_t srr1; + uint64_t srr1, addr; long handled = 1; + struct mce_error_info mce_error_info = { 0 }; srr1 = regs->msr; - if (P7_SRR1_MC_LOADSTORE(srr1)) + if (P7_SRR1_MC_LOADSTORE(srr1)) { handled = mce_handle_derror_p8(regs->dsisr); - else + mce_get_derror_p8(&mce_error_info, regs->dsisr); + addr = regs->dar; + } else { handled = mce_handle_ierror_p8(srr1); + mce_get_ierror_p8(&mce_error_info, srr1); + addr = regs->nip; + } - /* TODO: Decode machine check reason. */ + save_mce_event(regs, handled, &mce_error_info, addr); return handled; } diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index 5c427b41a2f5..768a9f977c00 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -12,6 +12,7 @@ #include #include #include +#include /* SRR1 bits for machine check on POWER7 */ #define SRR1_MC_LDSTERR (1ul << (63-42)) @@ -67,9 +68,7 @@ static void reload_slb(struct kvm_vcpu *vcpu) static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) { unsigned long srr1 = vcpu->arch.shregs.msr; -#ifdef CONFIG_PPC_POWERNV - struct opal_machine_check_event *opal_evt; -#endif + struct machine_check_event mce_evt; long handled = 1; if (srr1 & SRR1_MC_LDSTERR) { @@ -109,22 +108,31 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) handled = 0; } -#ifdef CONFIG_PPC_POWERNV /* - * See if OPAL has already handled the condition. - * We assume that if the condition is recovered then OPAL + * See if we have already handled the condition in the linux host. + * We assume that if the condition is recovered then linux host * will have generated an error log event that we will pick * up and log later. + * Don't release mce event now. In case if condition is not + * recovered we do guest exit and go back to linux host machine + * check handler. Hence we need make sure that current mce event + * is available for linux host to consume. */ - opal_evt = local_paca->opal_mc_evt; - if (opal_evt->version == OpalMCE_V1 && - (opal_evt->severity == OpalMCE_SEV_NO_ERROR || - opal_evt->disposition == OpalMCE_DISPOSITION_RECOVERED)) + if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE)) + goto out; + + if (mce_evt.version == MCE_V1 && + (mce_evt.severity == MCE_SEV_NO_ERROR || + mce_evt.disposition == MCE_DISPOSITION_RECOVERED)) handled = 1; +out: + /* + * If we have handled the error, then release the mce event because + * we will be delivering machine check to guest. + */ if (handled) - opal_evt->in_use = 0; -#endif + release_mce_event(); return handled; } diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 1c798cd55372..c5e71d773f47 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "powernv.h" @@ -256,8 +257,7 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) int opal_machine_check(struct pt_regs *regs) { - struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt; - struct opal_machine_check_event evt; + struct machine_check_event evt; const char *level, *sevstr, *subtype; static const char *opal_mc_ue_types[] = { "Indeterminate", @@ -282,30 +282,29 @@ int opal_machine_check(struct pt_regs *regs) "Multihit", }; - /* Copy the event structure and release the original */ - evt = *opal_evt; - opal_evt->in_use = 0; + if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) + return 0; /* Print things out */ - if (evt.version != OpalMCE_V1) { + if (evt.version != MCE_V1) { pr_err("Machine Check Exception, Unknown event version %d !\n", evt.version); return 0; } switch(evt.severity) { - case OpalMCE_SEV_NO_ERROR: + case MCE_SEV_NO_ERROR: level = KERN_INFO; sevstr = "Harmless"; break; - case OpalMCE_SEV_WARNING: + case MCE_SEV_WARNING: level = KERN_WARNING; sevstr = ""; break; - case OpalMCE_SEV_ERROR_SYNC: + case MCE_SEV_ERROR_SYNC: level = KERN_ERR; sevstr = "Severe"; break; - case OpalMCE_SEV_FATAL: + case MCE_SEV_FATAL: default: level = KERN_ERR; sevstr = "Fatal"; @@ -313,12 +312,12 @@ int opal_machine_check(struct pt_regs *regs) } printk("%s%s Machine check interrupt [%s]\n", level, sevstr, - evt.disposition == OpalMCE_DISPOSITION_RECOVERED ? + evt.disposition == MCE_DISPOSITION_RECOVERED ? "Recovered" : "[Not recovered"); printk("%s Initiator: %s\n", level, - evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown"); + evt.initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown"); switch(evt.error_type) { - case OpalMCE_ERROR_TYPE_UE: + case MCE_ERROR_TYPE_UE: subtype = evt.u.ue_error.ue_error_type < ARRAY_SIZE(opal_mc_ue_types) ? opal_mc_ue_types[evt.u.ue_error.ue_error_type] @@ -331,7 +330,7 @@ int opal_machine_check(struct pt_regs *regs) printk("%s Physial address: %016llx\n", level, evt.u.ue_error.physical_address); break; - case OpalMCE_ERROR_TYPE_SLB: + case MCE_ERROR_TYPE_SLB: subtype = evt.u.slb_error.slb_error_type < ARRAY_SIZE(opal_mc_slb_types) ? opal_mc_slb_types[evt.u.slb_error.slb_error_type] @@ -341,7 +340,7 @@ int opal_machine_check(struct pt_regs *regs) printk("%s Effective address: %016llx\n", level, evt.u.slb_error.effective_address); break; - case OpalMCE_ERROR_TYPE_ERAT: + case MCE_ERROR_TYPE_ERAT: subtype = evt.u.erat_error.erat_error_type < ARRAY_SIZE(opal_mc_erat_types) ? opal_mc_erat_types[evt.u.erat_error.erat_error_type] @@ -351,7 +350,7 @@ int opal_machine_check(struct pt_regs *regs) printk("%s Effective address: %016llx\n", level, evt.u.erat_error.effective_address); break; - case OpalMCE_ERROR_TYPE_TLB: + case MCE_ERROR_TYPE_TLB: subtype = evt.u.tlb_error.tlb_error_type < ARRAY_SIZE(opal_mc_tlb_types) ? opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type] @@ -362,11 +361,11 @@ int opal_machine_check(struct pt_regs *regs) level, evt.u.tlb_error.effective_address); break; default: - case OpalMCE_ERROR_TYPE_UNKNOWN: + case MCE_ERROR_TYPE_UNKNOWN: printk("%s Error type: Unknown\n", level); break; } - return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1; + return evt.severity == MCE_SEV_FATAL ? 0 : 1; } static irqreturn_t opal_interrupt(int irq, void *data) -- 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 + arch/powerpc/kernel/entry_64.S | 5 ++ arch/powerpc/kernel/exceptions-64s.S | 7 +- arch/powerpc/kernel/mce.c | 154 ++++++++++++++++++++++++++++++++++ arch/powerpc/platforms/powernv/opal.c | 97 +-------------------- 5 files changed, 168 insertions(+), 98 deletions(-) (limited to 'arch/powerpc/include/asm') 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__ */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index bbfb0294b354..770d6d65c47b 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -183,6 +183,11 @@ syscall_exit: #ifdef SHOW_SYSCALLS bl .do_show_syscall_exit ld r3,RESULT(r1) +#endif +#ifdef CONFIG_PPC_BOOK3S_64 +BEGIN_FTR_SECTION + bl .machine_check_process_queued_event +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) #endif CURRENT_THREAD_INFO(r12, r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 1aec3025eeee..862b9dd4a9db 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -855,7 +855,8 @@ BEGIN_FTR_SECTION /* Supervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) -3: MACHINE_CHECK_HANDLER_WINDUP +3: bl .machine_check_queue_event + MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) b .power7_enter_nap_mode @@ -895,8 +896,10 @@ BEGIN_FTR_SECTION 2: /* * Return from MC interrupt. - * TODO: Queue up the MCE event so that we can log it later. + * Queue up the MCE event so that we can log it later, while + * returning from kernel or opal call. */ + bl .machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP rfid 9: diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index aeecdf1ba897..1c6d15701c56 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -31,6 +31,10 @@ static DEFINE_PER_CPU(int, mce_nest_count); static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); +/* Queue for delayed MCE events. */ +static DEFINE_PER_CPU(int, mce_queue_count); +static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue); + static void mce_set_error_info(struct machine_check_event *mce, struct mce_error_info *mce_err) { @@ -162,3 +166,153 @@ void release_mce_event(void) { get_mce_event(NULL, true); } + +/* + * Queue up the MCE event which then can be handled later. + */ +void machine_check_queue_event(void) +{ + int index; + struct machine_check_event evt; + + if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) + return; + + index = __get_cpu_var(mce_queue_count)++; + /* If queue is full, just return for now. */ + if (index >= MAX_MC_EVT) { + __get_cpu_var(mce_queue_count)--; + return; + } + __get_cpu_var(mce_event_queue[index]) = evt; +} + +/* + * process pending MCE event from the mce event queue. This function will be + * called during syscall exit. + */ +void machine_check_process_queued_event(void) +{ + int index; + + preempt_disable(); + /* + * For now just print it to console. + * TODO: log this error event to FSP or nvram. + */ + while (__get_cpu_var(mce_queue_count) > 0) { + index = __get_cpu_var(mce_queue_count) - 1; + machine_check_print_event_info( + &__get_cpu_var(mce_event_queue[index])); + __get_cpu_var(mce_queue_count)--; + } + preempt_enable(); +} + +void machine_check_print_event_info(struct machine_check_event *evt) +{ + const char *level, *sevstr, *subtype; + static const char *mc_ue_types[] = { + "Indeterminate", + "Instruction fetch", + "Page table walk ifetch", + "Load/Store", + "Page table walk Load/Store", + }; + static const char *mc_slb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *mc_erat_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *mc_tlb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + + /* Print things out */ + if (evt->version != MCE_V1) { + pr_err("Machine Check Exception, Unknown event version %d !\n", + evt->version); + return; + } + switch (evt->severity) { + case MCE_SEV_NO_ERROR: + level = KERN_INFO; + sevstr = "Harmless"; + break; + case MCE_SEV_WARNING: + level = KERN_WARNING; + sevstr = ""; + break; + case MCE_SEV_ERROR_SYNC: + level = KERN_ERR; + sevstr = "Severe"; + break; + case MCE_SEV_FATAL: + default: + level = KERN_ERR; + sevstr = "Fatal"; + break; + } + + printk("%s%s Machine check interrupt [%s]\n", level, sevstr, + evt->disposition == MCE_DISPOSITION_RECOVERED ? + "Recovered" : "[Not recovered"); + printk("%s Initiator: %s\n", level, + evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown"); + switch (evt->error_type) { + case MCE_ERROR_TYPE_UE: + subtype = evt->u.ue_error.ue_error_type < + ARRAY_SIZE(mc_ue_types) ? + mc_ue_types[evt->u.ue_error.ue_error_type] + : "Unknown"; + printk("%s Error type: UE [%s]\n", level, subtype); + if (evt->u.ue_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.ue_error.effective_address); + if (evt->u.ue_error.physical_address_provided) + printk("%s Physial address: %016llx\n", + level, evt->u.ue_error.physical_address); + break; + case MCE_ERROR_TYPE_SLB: + subtype = evt->u.slb_error.slb_error_type < + ARRAY_SIZE(mc_slb_types) ? + mc_slb_types[evt->u.slb_error.slb_error_type] + : "Unknown"; + printk("%s Error type: SLB [%s]\n", level, subtype); + if (evt->u.slb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.slb_error.effective_address); + break; + case MCE_ERROR_TYPE_ERAT: + subtype = evt->u.erat_error.erat_error_type < + ARRAY_SIZE(mc_erat_types) ? + mc_erat_types[evt->u.erat_error.erat_error_type] + : "Unknown"; + printk("%s Error type: ERAT [%s]\n", level, subtype); + if (evt->u.erat_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.erat_error.effective_address); + break; + case MCE_ERROR_TYPE_TLB: + subtype = evt->u.tlb_error.tlb_error_type < + ARRAY_SIZE(mc_tlb_types) ? + mc_tlb_types[evt->u.tlb_error.tlb_error_type] + : "Unknown"; + printk("%s Error type: TLB [%s]\n", level, subtype); + if (evt->u.tlb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.tlb_error.effective_address); + break; + default: + case MCE_ERROR_TYPE_UNKNOWN: + printk("%s Error type: Unknown\n", level); + break; + } +} diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index c5e71d773f47..245096f90437 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -258,29 +258,6 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) int opal_machine_check(struct pt_regs *regs) { struct machine_check_event evt; - const char *level, *sevstr, *subtype; - static const char *opal_mc_ue_types[] = { - "Indeterminate", - "Instruction fetch", - "Page table walk ifetch", - "Load/Store", - "Page table walk Load/Store", - }; - static const char *opal_mc_slb_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - static const char *opal_mc_erat_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - static const char *opal_mc_tlb_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return 0; @@ -291,80 +268,8 @@ int opal_machine_check(struct pt_regs *regs) evt.version); return 0; } - switch(evt.severity) { - case MCE_SEV_NO_ERROR: - level = KERN_INFO; - sevstr = "Harmless"; - break; - case MCE_SEV_WARNING: - level = KERN_WARNING; - sevstr = ""; - break; - case MCE_SEV_ERROR_SYNC: - level = KERN_ERR; - sevstr = "Severe"; - break; - case MCE_SEV_FATAL: - default: - level = KERN_ERR; - sevstr = "Fatal"; - break; - } + machine_check_print_event_info(&evt); - printk("%s%s Machine check interrupt [%s]\n", level, sevstr, - evt.disposition == MCE_DISPOSITION_RECOVERED ? - "Recovered" : "[Not recovered"); - printk("%s Initiator: %s\n", level, - evt.initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown"); - switch(evt.error_type) { - case MCE_ERROR_TYPE_UE: - subtype = evt.u.ue_error.ue_error_type < - ARRAY_SIZE(opal_mc_ue_types) ? - opal_mc_ue_types[evt.u.ue_error.ue_error_type] - : "Unknown"; - printk("%s Error type: UE [%s]\n", level, subtype); - if (evt.u.ue_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.ue_error.effective_address); - if (evt.u.ue_error.physical_address_provided) - printk("%s Physial address: %016llx\n", - level, evt.u.ue_error.physical_address); - break; - case MCE_ERROR_TYPE_SLB: - subtype = evt.u.slb_error.slb_error_type < - ARRAY_SIZE(opal_mc_slb_types) ? - opal_mc_slb_types[evt.u.slb_error.slb_error_type] - : "Unknown"; - printk("%s Error type: SLB [%s]\n", level, subtype); - if (evt.u.slb_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.slb_error.effective_address); - break; - case MCE_ERROR_TYPE_ERAT: - subtype = evt.u.erat_error.erat_error_type < - ARRAY_SIZE(opal_mc_erat_types) ? - opal_mc_erat_types[evt.u.erat_error.erat_error_type] - : "Unknown"; - printk("%s Error type: ERAT [%s]\n", level, subtype); - if (evt.u.erat_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.erat_error.effective_address); - break; - case MCE_ERROR_TYPE_TLB: - subtype = evt.u.tlb_error.tlb_error_type < - ARRAY_SIZE(opal_mc_tlb_types) ? - opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type] - : "Unknown"; - printk("%s Error type: TLB [%s]\n", level, subtype); - if (evt.u.tlb_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.tlb_error.effective_address); - break; - default: - case MCE_ERROR_TYPE_UNKNOWN: - printk("%s Error type: Unknown\n", level); - break; - } return evt.severity == MCE_SEV_FATAL ? 0 : 1; } -- 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 + arch/powerpc/kernel/mce.c | 27 ++++++++++++++++++++++ arch/powerpc/platforms/powernv/opal.c | 43 ++++++++++++++++++++++++++++++++++- 3 files changed, 70 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') 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__ */ diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 1c6d15701c56..c0c52ec1fca7 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -316,3 +316,30 @@ void machine_check_print_event_info(struct machine_check_event *evt) break; } } + +uint64_t get_mce_fault_addr(struct machine_check_event *evt) +{ + switch (evt->error_type) { + case MCE_ERROR_TYPE_UE: + if (evt->u.ue_error.effective_address_provided) + return evt->u.ue_error.effective_address; + break; + case MCE_ERROR_TYPE_SLB: + if (evt->u.slb_error.effective_address_provided) + return evt->u.slb_error.effective_address; + break; + case MCE_ERROR_TYPE_ERAT: + if (evt->u.erat_error.effective_address_provided) + return evt->u.erat_error.effective_address; + break; + case MCE_ERROR_TYPE_TLB: + if (evt->u.tlb_error.effective_address_provided) + return evt->u.tlb_error.effective_address; + break; + default: + case MCE_ERROR_TYPE_UNKNOWN: + break; + } + return 0; +} +EXPORT_SYMBOL(get_mce_fault_addr); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index f348bd49487c..01e74cbc67e9 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -251,6 +252,44 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) return written; } +static int opal_recover_mce(struct pt_regs *regs, + struct machine_check_event *evt) +{ + int recovered = 0; + uint64_t ea = get_mce_fault_addr(evt); + + if (!(regs->msr & MSR_RI)) { + /* If MSR_RI isn't set, we cannot recover */ + recovered = 0; + } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { + /* Platform corrected itself */ + recovered = 1; + } else if (ea && !is_kernel_addr(ea)) { + /* + * Faulting address is not in kernel text. We should be fine. + * We need to find which process uses this address. + * For now, kill the task if we have received exception when + * in userspace. + * + * TODO: Queue up this address for hwpoisioning later. + */ + if (user_mode(regs) && !is_global_init(current)) { + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } else + recovered = 0; + } else if (user_mode(regs) && !is_global_init(current) && + evt->severity == MCE_SEV_ERROR_SYNC) { + /* + * If we have received a synchronous error when in userspace + * kill the task. + */ + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } + return recovered; +} + int opal_machine_check(struct pt_regs *regs) { struct machine_check_event evt; @@ -266,7 +305,9 @@ int opal_machine_check(struct pt_regs *regs) } machine_check_print_event_info(&evt); - return evt.severity == MCE_SEV_FATAL ? 0 : 1; + if (opal_recover_mce(regs, &evt)) + return 1; + return 0; } static irqreturn_t opal_interrupt(int irq, void *data) -- 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 ++++++- arch/powerpc/platforms/powernv/opal-wrappers.S | 2 + arch/powerpc/platforms/powernv/opal.c | 90 ++++++++++++++++++++++++++ 3 files changed, 115 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') 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); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index e7806504e976..719aa5c325c6 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -126,3 +126,5 @@ OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU); OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE); OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE); OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE); +OPAL_CALL(opal_get_msg, OPAL_GET_MSG); +OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 01e74cbc67e9..7a184a0ff183 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -40,6 +40,7 @@ extern u64 opal_mc_secondary_handler[]; static unsigned int *opal_irqs; static unsigned int opal_irq_count; static ATOMIC_NOTIFIER_HEAD(opal_notifier_head); +static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; static DEFINE_SPINLOCK(opal_notifier_lock); static uint64_t last_notified_mask = 0x0ul; static atomic_t opal_notifier_hold = ATOMIC_INIT(0); @@ -167,6 +168,95 @@ void opal_notifier_disable(void) atomic_set(&opal_notifier_hold, 1); } +/* + * Opal message notifier based on message type. Allow subscribers to get + * notified for specific messgae type. + */ +int opal_message_notifier_register(enum OpalMessageType msg_type, + struct notifier_block *nb) +{ + if (!nb) { + pr_warning("%s: Invalid argument (%p)\n", + __func__, nb); + return -EINVAL; + } + if (msg_type > OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Invalid message type argument (%d)\n", + __func__, msg_type); + return -EINVAL; + } + return atomic_notifier_chain_register( + &opal_msg_notifier_head[msg_type], nb); +} + +static void opal_message_do_notify(uint32_t msg_type, void *msg) +{ + /* notify subscribers */ + atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type], + msg_type, msg); +} + +static void opal_handle_message(void) +{ + s64 ret; + /* + * TODO: pre-allocate a message buffer depending on opal-msg-size + * value in /proc/device-tree. + */ + static struct opal_msg msg; + + ret = opal_get_msg(__pa(&msg), sizeof(msg)); + /* No opal message pending. */ + if (ret == OPAL_RESOURCE) + return; + + /* check for errors. */ + if (ret) { + pr_warning("%s: Failed to retrive opal message, err=%lld\n", + __func__, ret); + return; + } + + /* Sanity check */ + if (msg.msg_type > OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Unknown message type: %u\n", + __func__, msg.msg_type); + return; + } + opal_message_do_notify(msg.msg_type, (void *)&msg); +} + +static int opal_message_notify(struct notifier_block *nb, + unsigned long events, void *change) +{ + if (events & OPAL_EVENT_MSG_PENDING) + opal_handle_message(); + return 0; +} + +static struct notifier_block opal_message_nb = { + .notifier_call = opal_message_notify, + .next = NULL, + .priority = 0, +}; + +static int __init opal_message_init(void) +{ + int ret, i; + + for (i = 0; i < OPAL_MSG_TYPE_MAX; i++) + ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]); + + ret = opal_notifier_register(&opal_message_nb); + if (ret) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + return 0; +} +early_initcall(opal_message_init); + int opal_get_chars(uint32_t vtermno, char *buf, int count) { s64 rc; -- 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 ++++++++++++++++++++ arch/powerpc/platforms/powernv/opal-flash.c | 31 ++++++----------------------- 2 files changed, 28 insertions(+), 25 deletions(-) (limited to 'arch/powerpc/include/asm') 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); diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 6ffa6b1ec5b7..4aeae4f36e1d 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -103,27 +103,6 @@ struct image_header_t { uint32_t size; }; -/* Scatter/gather entry */ -struct opal_sg_entry { - void *data; - long length; -}; - -/* We calculate number of entries based on PAGE_SIZE */ -#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry)) - -/* - * This struct is very similar but not identical to that - * needed by the opal flash update. All we need to do for - * opal is rewrite num_entries into a version/length and - * translate the pointers to absolute. - */ -struct opal_sg_list { - unsigned long num_entries; - struct opal_sg_list *next; - struct opal_sg_entry entry[SG_ENTRIES_PER_NODE]; -}; - struct validate_flash_t { int status; /* Return status */ void *buf; /* Candiate image buffer */ @@ -333,7 +312,7 @@ static struct opal_sg_list *image_data_to_sglist(void) addr = image_data.data; size = image_data.size; - sg1 = kzalloc((sizeof(struct opal_sg_list)), GFP_KERNEL); + sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!sg1) return NULL; @@ -351,8 +330,7 @@ static struct opal_sg_list *image_data_to_sglist(void) sg1->num_entries++; if (sg1->num_entries >= SG_ENTRIES_PER_NODE) { - sg1->next = kzalloc((sizeof(struct opal_sg_list)), - GFP_KERNEL); + sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!sg1->next) { pr_err("%s : Failed to allocate memory\n", __func__); @@ -402,7 +380,10 @@ static int opal_flash_update(int op) else sg->next = NULL; - /* Make num_entries into the version/length field */ + /* + * Convert num_entries to version/length format + * to satisfy OPAL. + */ sg->num_entries = (SG_LIST_VERSION << 56) | (sg->num_entries * sizeof(struct opal_sg_entry) + 16); } -- 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 ++++++++++++++++ arch/powerpc/kernel/iommu.c | 48 +++-------------------------- arch/powerpc/platforms/powernv/pci-ioda.c | 8 ++--- arch/powerpc/platforms/powernv/pci-p5ioc2.c | 2 +- arch/powerpc/platforms/powernv/pci.c | 33 +++++++++++++++++++- arch/powerpc/platforms/pseries/iommu.c | 8 +++-- 6 files changed, 72 insertions(+), 53 deletions(-) (limited to 'arch/powerpc/include/asm') 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, diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 572bb5b95f35..d22abe0b08e3 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1105,7 +1105,7 @@ void iommu_release_ownership(struct iommu_table *tbl) } EXPORT_SYMBOL_GPL(iommu_release_ownership); -static int iommu_add_device(struct device *dev) +int iommu_add_device(struct device *dev) { struct iommu_table *tbl; int ret = 0; @@ -1134,52 +1134,12 @@ static int iommu_add_device(struct device *dev) return ret; } +EXPORT_SYMBOL_GPL(iommu_add_device); -static void iommu_del_device(struct device *dev) +void iommu_del_device(struct device *dev) { iommu_group_remove_device(dev); } - -static int iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - return iommu_add_device(dev); - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = iommu_bus_notifier, -}; - -static int __init tce_iommu_init(void) -{ - struct pci_dev *pdev = NULL; - - BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE); - - for_each_pci_dev(pdev) - iommu_add_device(&pdev->dev); - - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} - -subsys_initcall_sync(tce_iommu_init); - -#else - -void iommu_register_group(struct iommu_table *tbl, - int pci_domain_number, unsigned long pe_num) -{ -} +EXPORT_SYMBOL_GPL(iommu_del_device); #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 084cdfa40682..614356cac466 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -460,7 +460,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev return; pe = &phb->ioda.pe_array[pdn->pe_number]; - set_iommu_table_base(&pdev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); } static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) @@ -468,7 +468,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { - set_iommu_table_base(&dev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&dev->dev, &pe->tce32_table); if (dev->subordinate) pnv_ioda_setup_bus_dma(pe, dev->subordinate); } @@ -644,7 +644,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number); if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); + set_iommu_table_base_and_group(&pe->pdev->dev, tbl); else pnv_ioda_setup_bus_dma(pe, pe->pbus); @@ -722,7 +722,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, iommu_init_table(tbl, phb->hose->node); if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); + set_iommu_table_base_and_group(&pe->pdev->dev, tbl); else pnv_ioda_setup_bus_dma(pe, pe->pbus); diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index f8b4bd8afb2e..e3807d69393e 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -92,7 +92,7 @@ static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb, pci_domain_nr(phb->hose->bus), phb->opal_id); } - set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table); + set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table); } static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 4eb33a9ed532..6f3d49c18d64 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -536,7 +536,7 @@ static void pnv_pci_dma_fallback_setup(struct pci_controller *hose, pdn->iommu_table = pnv_pci_setup_bml_iommu(hose); if (!pdn->iommu_table) return; - set_iommu_table_base(&pdev->dev, pdn->iommu_table); + set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table); } static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) @@ -657,3 +657,34 @@ void __init pnv_pci_init(void) ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs; #endif } + +static int tce_iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + return iommu_add_device(dev); + case BUS_NOTIFY_DEL_DEVICE: + if (dev->iommu_group) + iommu_del_device(dev); + return 0; + default: + return 0; + } +} + +static struct notifier_block tce_iommu_bus_nb = { + .notifier_call = tce_iommu_bus_notifier, +}; + +static int __init tce_iommu_bus_notifier_init(void) +{ + BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE); + + bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); + return 0; +} + +subsys_initcall_sync(tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index f253361552ae..a80af6c20cba 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -687,7 +687,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) iommu_table_setparms(phb, dn, tbl); PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node); iommu_register_group(tbl, pci_domain_nr(phb->bus), 0); - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); return; } @@ -699,7 +700,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) dn = dn->parent; if (dn && PCI_DN(dn)) - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); else printk(KERN_WARNING "iommu: Device %s has no iommu table\n", pci_name(dev)); @@ -1193,7 +1195,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) pr_debug(" found DMA window, table: %p\n", pci->iommu_table); } - set_iommu_table_base(&dev->dev, pci->iommu_table); + set_iommu_table_base_and_group(&dev->dev, pci->iommu_table); } static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) -- 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/asm') 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 -- arch/powerpc/kernel/paca.c | 2 +- arch/powerpc/platforms/pseries/lpar.c | 2 +- 3 files changed, 2 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/include/asm') 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. */ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0620eaaaad45..9095a6f7ac2c 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -99,7 +99,7 @@ static inline void free_lppacas(void) { } * 3 persistent SLBs are registered here. The buffer will be zero * initially, hence will all be invaild until we actually write them. */ -struct slb_shadow slb_shadow[] __cacheline_aligned = { +static struct slb_shadow slb_shadow[] __cacheline_aligned = { [0 ... (NR_CPUS-1)] = { .persistent = cpu_to_be32(SLB_NUM_BOLTED), .buffer_length = cpu_to_be32(sizeof(struct slb_shadow)), diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4fca3def9db9..28cf0f33c5be 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -92,7 +92,7 @@ void vpa_init(int cpu) * PAPR says this feature is SLB-Buffer but firmware never * reports that. All SPLPAR support SLB shadow buffer. */ - addr = __pa(&slb_shadow[cpu]); + addr = __pa(paca[cpu].slb_shadow_ptr); if (firmware_has_feature(FW_FEATURE_SPLPAR)) { ret = register_slb_shadow(hwcpu, addr); if (ret) -- 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 +- arch/powerpc/mm/hash_low_64.S | 15 ++++++++++++--- arch/powerpc/mm/hash_utils_64.c | 7 ++++--- arch/powerpc/mm/hugepage-hash64.c | 6 +++++- arch/powerpc/mm/hugetlbpage-hash64.c | 4 ++++ 5 files changed, 26 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/include/asm') 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 */ diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index d3cbda62857b..1136d26a95ae 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -148,7 +148,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r30,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) @@ -457,7 +460,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r3,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) @@ -795,7 +801,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r30,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 6176b3cdf579..de6881259aef 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -169,9 +169,10 @@ static unsigned long htab_convert_pte_flags(unsigned long pteflags) if ((pteflags & _PAGE_USER) && !((pteflags & _PAGE_RW) && (pteflags & _PAGE_DIRTY))) rflags |= 1; - - /* Always add C */ - return rflags | HPTE_R_C; + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + return rflags | HPTE_R_C | HPTE_R_M; } int htab_bolt_mapping(unsigned long vstart, unsigned long vend, diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 34de9e0cdc34..826893fcb3a7 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -127,7 +127,11 @@ repeat: /* Add in WIMG bits */ rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | - _PAGE_COHERENT | _PAGE_GUARDED)); + _PAGE_GUARDED)); + /* + * enable the memory coherence always + */ + rflags |= HPTE_R_M; /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index 0b7fb6761015..a5bcf9301196 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -99,6 +99,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, /* Add in WIMG bits */ rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED)); + /* + * enable the memory coherence always + */ + rflags |= HPTE_R_M; slot = hpte_insert_repeating(hash, vpn, pa, rflags, 0, mmu_psize, ssize); -- 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 ++++ arch/powerpc/platforms/Kconfig.cputype | 1 + 3 files changed, 72 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') 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 diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index bca2465a9c34..434fda39bf8b 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -72,6 +72,7 @@ config PPC_BOOK3S_64 select PPC_HAVE_PMU_SUPPORT select SYS_SUPPORTS_HUGETLBFS select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES + select ARCH_SUPPORTS_NUMA_BALANCING config PPC_BOOK3E_64 bool "Embedded processors" -- 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 ++++++++ arch/powerpc/platforms/powernv/Makefile | 1 + .../powerpc/platforms/powernv/opal-memory-errors.c | 146 +++++++++++++++++++++ 3 files changed, 199 insertions(+) create mode 100644 arch/powerpc/platforms/powernv/opal-memory-errors.c (limited to 'arch/powerpc/include/asm') 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, diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 873fa1370dc4..8d767fde5a6a 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o obj-$(CONFIG_EEH) += eeh-ioda.o eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o +obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c new file mode 100644 index 000000000000..ec4132239cdf --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c @@ -0,0 +1,146 @@ +/* + * OPAL asynchronus Memory error handling support in PowreNV. + * + * 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 + */ + +#undef DEBUG + +#include +#include +#include +#include +#include + +#include +#include + +static int opal_mem_err_nb_init; +static LIST_HEAD(opal_memory_err_list); +static DEFINE_SPINLOCK(opal_mem_err_lock); + +struct OpalMsgNode { + struct list_head list; + struct opal_msg msg; +}; + +static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt) +{ + uint64_t paddr_start, paddr_end; + + pr_debug("%s: Retrived memory error event, type: 0x%x\n", + __func__, merr_evt->type); + switch (merr_evt->type) { + case OPAL_MEM_ERR_TYPE_RESILIENCE: + paddr_start = merr_evt->u.resilience.physical_address_start; + paddr_end = merr_evt->u.resilience.physical_address_end; + break; + case OPAL_MEM_ERR_TYPE_DYN_DALLOC: + paddr_start = merr_evt->u.dyn_dealloc.physical_address_start; + paddr_end = merr_evt->u.dyn_dealloc.physical_address_end; + break; + default: + return; + } + + for (; paddr_start < paddr_end; paddr_start += PAGE_SIZE) { + memory_failure(paddr_start >> PAGE_SHIFT, 0, 0); + } +} + +static void handle_memory_error(void) +{ + unsigned long flags; + struct OpalMemoryErrorData *merr_evt; + struct OpalMsgNode *msg_node; + + spin_lock_irqsave(&opal_mem_err_lock, flags); + while (!list_empty(&opal_memory_err_list)) { + msg_node = list_entry(opal_memory_err_list.next, + struct OpalMsgNode, list); + list_del(&msg_node->list); + spin_unlock_irqrestore(&opal_mem_err_lock, flags); + + merr_evt = (struct OpalMemoryErrorData *) + &msg_node->msg.params[0]; + handle_memory_error_event(merr_evt); + kfree(msg_node); + spin_lock_irqsave(&opal_mem_err_lock, flags); + } + spin_unlock_irqrestore(&opal_mem_err_lock, flags); +} + +static void mem_error_handler(struct work_struct *work) +{ + handle_memory_error(); +} + +static DECLARE_WORK(mem_error_work, mem_error_handler); + +/* + * opal_memory_err_event - notifier handler that queues up the opal message + * to be preocessed later. + */ +static int opal_memory_err_event(struct notifier_block *nb, + unsigned long msg_type, void *msg) +{ + unsigned long flags; + struct OpalMsgNode *msg_node; + + if (msg_type != OPAL_MSG_MEM_ERR) + return 0; + + msg_node = kzalloc(sizeof(*msg_node), GFP_ATOMIC); + if (!msg_node) { + pr_err("MEMORY_ERROR: out of memory, Opal message event not" + "handled\n"); + return -ENOMEM; + } + memcpy(&msg_node->msg, msg, sizeof(struct opal_msg)); + + spin_lock_irqsave(&opal_mem_err_lock, flags); + list_add(&msg_node->list, &opal_memory_err_list); + spin_unlock_irqrestore(&opal_mem_err_lock, flags); + + schedule_work(&mem_error_work); + return 0; +} + +static struct notifier_block opal_mem_err_nb = { + .notifier_call = opal_memory_err_event, + .next = NULL, + .priority = 0, +}; + +static int __init opal_mem_err_init(void) +{ + int ret; + + if (!opal_mem_err_nb_init) { + ret = opal_message_notifier_register( + OPAL_MSG_MEM_ERR, &opal_mem_err_nb); + if (ret) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + opal_mem_err_nb_init = 1; + } + return 0; +} +subsys_initcall(opal_mem_err_init); -- 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 ++--- arch/powerpc/kernel/dma-iommu.c | 4 +- arch/powerpc/kernel/iommu.c | 78 +++++++++++++++++----------------- arch/powerpc/kernel/vio.c | 19 +++++---- arch/powerpc/platforms/cell/iommu.c | 12 +++--- arch/powerpc/platforms/powernv/pci.c | 4 +- arch/powerpc/platforms/pseries/iommu.c | 8 ++-- arch/powerpc/platforms/pseries/setup.c | 4 +- arch/powerpc/platforms/wsp/wsp_pci.c | 10 ++--- drivers/net/ethernet/ibm/ibmveth.c | 9 ++-- drivers/vfio/vfio_iommu_spapr_tce.c | 28 ++++++------ 11 files changed, 94 insertions(+), 92 deletions(-) (limited to 'arch/powerpc/include/asm') 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; } diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index e4897523de41..5cfe3dbfc4a0 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -83,10 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) return 0; } - if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT)) { + if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT_4K)) { dev_info(dev, "Warning: IOMMU offset too big for device mask\n"); dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n", - mask, tbl->it_offset << IOMMU_PAGE_SHIFT); + mask, tbl->it_offset << IOMMU_PAGE_SHIFT_4K); return 0; } else return 1; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index d22abe0b08e3..df4a7f1b7444 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -251,14 +251,14 @@ again: if (dev) boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - 1 << IOMMU_PAGE_SHIFT); + 1 << IOMMU_PAGE_SHIFT_4K); else - boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT); + boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT_4K); /* 4GB boundary for iseries_hv_alloc and iseries_hv_map */ n = iommu_area_alloc(tbl->it_map, limit, start, npages, - tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT, - align_mask); + tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT_4K, + align_mask); if (n == -1) { if (likely(pass == 0)) { /* First try the pool from the start */ @@ -320,12 +320,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, return DMA_ERROR_CODE; entry += tbl->it_offset; /* Offset into real TCE table */ - ret = entry << IOMMU_PAGE_SHIFT; /* Set the return dma address */ + ret = entry << IOMMU_PAGE_SHIFT_4K; /* Set the return dma address */ /* Put the TCEs in the HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - (unsigned long)page & IOMMU_PAGE_MASK, - direction, attrs); + (unsigned long)page & IOMMU_PAGE_MASK_4K, + direction, attrs); /* ppc_md.tce_build() only returns non-zero for transient errors. * Clean up the table bitmap in this case and return @@ -352,7 +352,7 @@ static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr, { unsigned long entry, free_entry; - entry = dma_addr >> IOMMU_PAGE_SHIFT; + entry = dma_addr >> IOMMU_PAGE_SHIFT_4K; free_entry = entry - tbl->it_offset; if (((free_entry + npages) > tbl->it_size) || @@ -401,7 +401,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned long flags; struct iommu_pool *pool; - entry = dma_addr >> IOMMU_PAGE_SHIFT; + entry = dma_addr >> IOMMU_PAGE_SHIFT_4K; free_entry = entry - tbl->it_offset; pool = get_pool(tbl, free_entry); @@ -468,13 +468,13 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Allocate iommu entries for that segment */ vaddr = (unsigned long) sg_virt(s); - npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE_4K); align = 0; - if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE && + if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; + align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K; entry = iommu_range_alloc(dev, tbl, npages, &handle, - mask >> IOMMU_PAGE_SHIFT, align); + mask >> IOMMU_PAGE_SHIFT_4K, align); DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); @@ -489,16 +489,16 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; - dma_addr = entry << IOMMU_PAGE_SHIFT; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK); + dma_addr = entry << IOMMU_PAGE_SHIFT_4K; + dma_addr |= (s->offset & ~IOMMU_PAGE_MASK_4K); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); /* Insert into HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - vaddr & IOMMU_PAGE_MASK, - direction, attrs); + vaddr & IOMMU_PAGE_MASK_4K, + direction, attrs); if(unlikely(build_fail)) goto failure; @@ -559,9 +559,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, if (s->dma_length != 0) { unsigned long vaddr, npages; - vaddr = s->dma_address & IOMMU_PAGE_MASK; + vaddr = s->dma_address & IOMMU_PAGE_MASK_4K; npages = iommu_num_pages(s->dma_address, s->dma_length, - IOMMU_PAGE_SIZE); + IOMMU_PAGE_SIZE_4K); __iommu_free(tbl, vaddr, npages); s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; @@ -592,7 +592,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (sg->dma_length == 0) break; npages = iommu_num_pages(dma_handle, sg->dma_length, - IOMMU_PAGE_SIZE); + IOMMU_PAGE_SIZE_4K); __iommu_free(tbl, dma_handle, npages); sg = sg_next(sg); } @@ -676,7 +676,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) set_bit(0, tbl->it_map); /* We only split the IOMMU table if we have 1GB or more of space */ - if ((tbl->it_size << IOMMU_PAGE_SHIFT) >= (1UL * 1024 * 1024 * 1024)) + if ((tbl->it_size << IOMMU_PAGE_SHIFT_4K) >= (1UL * 1024 * 1024 * 1024)) tbl->nr_pools = IOMMU_NR_POOLS; else tbl->nr_pools = 1; @@ -768,16 +768,16 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, vaddr = page_address(page) + offset; uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE_4K); if (tbl) { align = 0; - if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && size >= PAGE_SIZE && + if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && size >= PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; + align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K; dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction, - mask >> IOMMU_PAGE_SHIFT, align, + mask >> IOMMU_PAGE_SHIFT_4K, align, attrs); if (dma_handle == DMA_ERROR_CODE) { if (printk_ratelimit()) { @@ -786,7 +786,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, npages); } } else - dma_handle |= (uaddr & ~IOMMU_PAGE_MASK); + dma_handle |= (uaddr & ~IOMMU_PAGE_MASK_4K); } return dma_handle; @@ -801,7 +801,7 @@ void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, BUG_ON(direction == DMA_NONE); if (tbl) { - npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE_4K); iommu_free(tbl, dma_handle, npages); } } @@ -845,10 +845,10 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> IOMMU_PAGE_SHIFT; + nio_pages = size >> IOMMU_PAGE_SHIFT_4K; io_order = get_iommu_order(size); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, - mask >> IOMMU_PAGE_SHIFT, io_order, NULL); + mask >> IOMMU_PAGE_SHIFT_4K, io_order, NULL); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); return NULL; @@ -864,7 +864,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> IOMMU_PAGE_SHIFT; + nio_pages = size >> IOMMU_PAGE_SHIFT_4K; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); @@ -935,10 +935,10 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl, if (tce_value) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK) + if (ioba & ~IOMMU_PAGE_MASK_4K) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT; + ioba >>= IOMMU_PAGE_SHIFT_4K; if (ioba < tbl->it_offset) return -EINVAL; @@ -955,13 +955,13 @@ int iommu_tce_put_param_check(struct iommu_table *tbl, if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ))) return -EINVAL; - if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ)) + if (tce & ~(IOMMU_PAGE_MASK_4K | TCE_PCI_WRITE | TCE_PCI_READ)) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK) + if (ioba & ~IOMMU_PAGE_MASK_4K) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT; + ioba >>= IOMMU_PAGE_SHIFT_4K; if (ioba < tbl->it_offset) return -EINVAL; @@ -1037,7 +1037,7 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, /* if (unlikely(ret)) pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n", - __func__, hwaddr, entry << IOMMU_PAGE_SHIFT, + __func__, hwaddr, entry << IOMMU_PAGE_SHIFT_4K, hwaddr, ret); */ return ret; @@ -1049,14 +1049,14 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, { int ret; struct page *page = NULL; - unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK & ~PAGE_MASK; + unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK_4K & ~PAGE_MASK; enum dma_data_direction direction = iommu_tce_direction(tce); ret = get_user_pages_fast(tce & PAGE_MASK, 1, direction != DMA_TO_DEVICE, &page); if (unlikely(ret != 1)) { /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n", - tce, entry << IOMMU_PAGE_SHIFT, ret); */ + tce, entry << IOMMU_PAGE_SHIFT_4K, ret); */ return -EFAULT; } hwaddr = (unsigned long) page_address(page) + offset; @@ -1067,7 +1067,7 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, if (ret < 0) pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n", - __func__, entry << IOMMU_PAGE_SHIFT, tce, ret); + __func__, entry << IOMMU_PAGE_SHIFT_4K, tce, ret); return ret; } diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 76a64821f4a2..2e89fa350763 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -520,14 +520,14 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, struct vio_dev *viodev = to_vio_dev(dev); dma_addr_t ret = DMA_ERROR_CODE; - if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE))) { + if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K))) { atomic_inc(&viodev->cmo.allocs_failed); return ret; } ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs); if (unlikely(dma_mapping_error(dev, ret))) { - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K)); atomic_inc(&viodev->cmo.allocs_failed); } @@ -543,7 +543,7 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs); - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K)); } static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, @@ -556,7 +556,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, size_t alloc_size = 0; for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE); + alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE_4K); if (vio_cmo_alloc(viodev, alloc_size)) { atomic_inc(&viodev->cmo.allocs_failed); @@ -572,7 +572,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, } for (sgl = sglist, count = 0; count < ret; count++, sgl++) - alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE); + alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K); if (alloc_size) vio_cmo_dealloc(viodev, alloc_size); @@ -590,7 +590,7 @@ static void vio_dma_iommu_unmap_sg(struct device *dev, int count = 0; for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE); + alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K); dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs); @@ -736,7 +736,8 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) return -EINVAL; } - viodev->cmo.desired = IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev)); + viodev->cmo.desired = + IOMMU_PAGE_ALIGN_4K(viodrv->get_desired_dma(viodev)); if (viodev->cmo.desired < VIO_CMO_MIN_ENT) viodev->cmo.desired = VIO_CMO_MIN_ENT; size = VIO_CMO_MIN_ENT; @@ -1176,9 +1177,9 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) &tbl->it_index, &offset, &size); /* TCE table size - measured in tce entries */ - tbl->it_size = size >> IOMMU_PAGE_SHIFT; + tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K; /* offset for VIO should always be 0 */ - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; + tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K; tbl->it_busno = 0; tbl->it_type = TCE_VB; tbl->it_blocksize = 16; diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index b53560660b72..fc61b908eaf0 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE) + for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE_4K) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); @@ -430,7 +430,7 @@ static void cell_iommu_setup_hardware(struct cbe_iommu *iommu, { cell_iommu_setup_stab(iommu, base, size, 0, 0); iommu->ptab = cell_iommu_alloc_ptab(iommu, base, size, 0, 0, - IOMMU_PAGE_SHIFT); + IOMMU_PAGE_SHIFT_4K); cell_iommu_enable_hardware(iommu); } @@ -487,8 +487,8 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, window->table.it_blocksize = 16; window->table.it_base = (unsigned long)iommu->ptab; window->table.it_index = iommu->nid; - window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT) + pte_offset; - window->table.it_size = size >> IOMMU_PAGE_SHIFT; + window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT_4K) + pte_offset; + window->table.it_size = size >> IOMMU_PAGE_SHIFT_4K; iommu_init_table(&window->table, iommu->nid); @@ -773,7 +773,7 @@ static void __init cell_iommu_init_one(struct device_node *np, /* Setup the iommu_table */ cell_iommu_setup_window(iommu, np, base, size, - offset >> IOMMU_PAGE_SHIFT); + offset >> IOMMU_PAGE_SHIFT_4K); } static void __init cell_disable_iommus(void) @@ -1122,7 +1122,7 @@ static int __init cell_iommu_fixed_mapping_init(void) cell_iommu_setup_stab(iommu, dbase, dsize, fbase, fsize); iommu->ptab = cell_iommu_alloc_ptab(iommu, dbase, dsize, 0, 0, - IOMMU_PAGE_SHIFT); + IOMMU_PAGE_SHIFT_4K); cell_iommu_setup_fixed_ptab(iommu, np, dbase, dsize, fbase, fsize); cell_iommu_enable_hardware(iommu); diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index bac289aac7cc..7f4d857668a9 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -564,7 +564,7 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, { tbl->it_blocksize = 16; tbl->it_base = (unsigned long)tce_mem; - tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT; + tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT_4K; tbl->it_index = 0; tbl->it_size = tce_size >> 3; tbl->it_busno = 0; @@ -761,7 +761,7 @@ static struct notifier_block tce_iommu_bus_nb = { static int __init tce_iommu_bus_notifier_init(void) { - BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE); + BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE_4K); bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); return 0; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index a80af6c20cba..1b7531ce0c0c 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -488,7 +488,7 @@ static void iommu_table_setparms(struct pci_controller *phb, tbl->it_busno = phb->bus->number; /* Units of tce entries */ - tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT; + tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT_4K; /* Test if we are going over 2GB of DMA space */ if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) { @@ -499,7 +499,7 @@ static void iommu_table_setparms(struct pci_controller *phb, phb->dma_window_base_cur += phb->dma_window_size; /* Set the tce table size - measured in entries */ - tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT; + tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT_4K; tbl->it_index = 0; tbl->it_blocksize = 16; @@ -540,8 +540,8 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb, tbl->it_base = 0; tbl->it_blocksize = 16; tbl->it_type = TCE_PCI; - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; - tbl->it_size = size >> IOMMU_PAGE_SHIFT; + tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K; + tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K; } static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index c1f190858701..49cd16e6b450 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -72,7 +72,7 @@ int CMO_PrPSP = -1; int CMO_SecPSP = -1; -unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT); +unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); EXPORT_SYMBOL(CMO_PageSize); int fwnmi_active; /* TRUE if an FWNMI handler is present */ @@ -569,7 +569,7 @@ void pSeries_cmo_feature_init(void) { char *ptr, *key, *value, *end; int call_status; - int page_order = IOMMU_PAGE_SHIFT; + int page_order = IOMMU_PAGE_SHIFT_4K; pr_debug(" -> fw_cmo_feature_init()\n"); spin_lock(&rtas_data_buf_lock); diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c index 62cb527493e7..8a589618551e 100644 --- a/arch/powerpc/platforms/wsp/wsp_pci.c +++ b/arch/powerpc/platforms/wsp/wsp_pci.c @@ -260,7 +260,7 @@ static int tce_build_wsp(struct iommu_table *tbl, long index, long npages, *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n", - tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT); + tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT_4K); uaddr += TCE_PAGE_SIZE; index++; @@ -381,8 +381,8 @@ static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb, /* Init bits and pieces */ tbl->table.it_blocksize = 16; - tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT; - tbl->table.it_size = size >> IOMMU_PAGE_SHIFT; + tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT_4K; + tbl->table.it_size = size >> IOMMU_PAGE_SHIFT_4K; /* * It's already blank but we clear it anyway. @@ -449,8 +449,8 @@ static void wsp_pci_dma_dev_setup(struct pci_dev *pdev) if (table) { pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n", pci_name(pdev), - table->table.it_offset << IOMMU_PAGE_SHIFT, - (table->table.it_offset << IOMMU_PAGE_SHIFT) + table->table.it_offset << IOMMU_PAGE_SHIFT_4K, + (table->table.it_offset << IOMMU_PAGE_SHIFT_4K) + phb->dma32_region_size - 1); archdata->dma_data.iommu_table_base = &table->table; return; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 952d795230a4..f7d7538b6bd9 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1282,24 +1282,25 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev) /* netdev inits at probe time along with the structures we need below*/ if (netdev == NULL) - return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT); + return IOMMU_PAGE_ALIGN_4K(IBMVETH_IO_ENTITLEMENT_DEFAULT); adapter = netdev_priv(netdev); ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE; - ret += IOMMU_PAGE_ALIGN(netdev->mtu); + ret += IOMMU_PAGE_ALIGN_4K(netdev->mtu); for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { /* add the size of the active receive buffers */ if (adapter->rx_buff_pool[i].active) ret += adapter->rx_buff_pool[i].size * - IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i]. + IOMMU_PAGE_ALIGN_4K(adapter->rx_buff_pool[i]. buff_size); rxqentries += adapter->rx_buff_pool[i].size; } /* add the size of the receive queue entries */ - ret += IOMMU_PAGE_ALIGN(rxqentries * sizeof(struct ibmveth_rx_q_entry)); + ret += IOMMU_PAGE_ALIGN_4K( + rxqentries * sizeof(struct ibmveth_rx_q_entry)); return ret; } diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index bdae7a04af75..a84788ba662c 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -81,7 +81,7 @@ static int tce_iommu_enable(struct tce_container *container) * enforcing the limit based on the max that the guest can map. */ down_write(¤t->mm->mmap_sem); - npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT; + npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT; locked = current->mm->locked_vm + npages; lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { @@ -110,7 +110,7 @@ static void tce_iommu_disable(struct tce_container *container) down_write(¤t->mm->mmap_sem); current->mm->locked_vm -= (container->tbl->it_size << - IOMMU_PAGE_SHIFT) >> PAGE_SHIFT; + IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT; up_write(¤t->mm->mmap_sem); } @@ -174,8 +174,8 @@ static long tce_iommu_ioctl(void *iommu_data, if (info.argsz < minsz) return -EINVAL; - info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT; - info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT; + info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT_4K; + info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT_4K; info.flags = 0; if (copy_to_user((void __user *)arg, &info, minsz)) @@ -205,8 +205,8 @@ static long tce_iommu_ioctl(void *iommu_data, VFIO_DMA_MAP_FLAG_WRITE)) return -EINVAL; - if ((param.size & ~IOMMU_PAGE_MASK) || - (param.vaddr & ~IOMMU_PAGE_MASK)) + if ((param.size & ~IOMMU_PAGE_MASK_4K) || + (param.vaddr & ~IOMMU_PAGE_MASK_4K)) return -EINVAL; /* iova is checked by the IOMMU API */ @@ -220,17 +220,17 @@ static long tce_iommu_ioctl(void *iommu_data, if (ret) return ret; - for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) { + for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) { ret = iommu_put_tce_user_mode(tbl, - (param.iova >> IOMMU_PAGE_SHIFT) + i, + (param.iova >> IOMMU_PAGE_SHIFT_4K) + i, tce); if (ret) break; - tce += IOMMU_PAGE_SIZE; + tce += IOMMU_PAGE_SIZE_4K; } if (ret) iommu_clear_tces_and_put_pages(tbl, - param.iova >> IOMMU_PAGE_SHIFT, i); + param.iova >> IOMMU_PAGE_SHIFT_4K, i); iommu_flush_tce(tbl); @@ -256,17 +256,17 @@ static long tce_iommu_ioctl(void *iommu_data, if (param.flags) return -EINVAL; - if (param.size & ~IOMMU_PAGE_MASK) + if (param.size & ~IOMMU_PAGE_MASK_4K) return -EINVAL; ret = iommu_tce_clear_param_check(tbl, param.iova, 0, - param.size >> IOMMU_PAGE_SHIFT); + param.size >> IOMMU_PAGE_SHIFT_4K); if (ret) return ret; ret = iommu_clear_tces_and_put_pages(tbl, - param.iova >> IOMMU_PAGE_SHIFT, - param.size >> IOMMU_PAGE_SHIFT); + param.iova >> IOMMU_PAGE_SHIFT_4K, + param.size >> IOMMU_PAGE_SHIFT_4K); iommu_flush_tce(tbl); return ret; -- 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 + arch/powerpc/kernel/vio.c | 5 +++-- arch/powerpc/platforms/cell/iommu.c | 8 +++++--- arch/powerpc/platforms/pasemi/iommu.c | 5 ++++- arch/powerpc/platforms/powernv/pci.c | 3 ++- arch/powerpc/platforms/pseries/iommu.c | 10 ++++++---- arch/powerpc/platforms/wsp/wsp_pci.c | 5 +++-- 7 files changed, 24 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/include/asm') 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 diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 2e89fa350763..170ac24a0106 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1177,9 +1177,10 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) &tbl->it_index, &offset, &size); /* TCE table size - measured in tce entries */ - tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->it_size = size >> tbl->it_page_shift; /* offset for VIO should always be 0 */ - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K; + tbl->it_offset = offset >> tbl->it_page_shift; tbl->it_busno = 0; tbl->it_type = TCE_VB; tbl->it_blocksize = 16; diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index fc61b908eaf0..2b90ff8a93be 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE_4K) + for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); @@ -487,8 +487,10 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, window->table.it_blocksize = 16; window->table.it_base = (unsigned long)iommu->ptab; window->table.it_index = iommu->nid; - window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT_4K) + pte_offset; - window->table.it_size = size >> IOMMU_PAGE_SHIFT_4K; + window->table.it_page_shift = IOMMU_PAGE_SHIFT_4K; + window->table.it_offset = + (offset >> window->table.it_page_shift) + pte_offset; + window->table.it_size = size >> window->table.it_page_shift; iommu_init_table(&window->table, iommu->nid); diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 7d2d036754b5..2e576f2ae442 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -138,8 +138,11 @@ static void iommu_table_iobmap_setup(void) pr_debug(" -> %s\n", __func__); iommu_table_iobmap.it_busno = 0; iommu_table_iobmap.it_offset = 0; + iommu_table_iobmap.it_page_shift = IOBMAP_PAGE_SHIFT; + /* it_size is in number of entries */ - iommu_table_iobmap.it_size = 0x80000000 >> IOBMAP_PAGE_SHIFT; + iommu_table_iobmap.it_size = + 0x80000000 >> iommu_table_iobmap.it_page_shift; /* Initialize the common IOMMU code */ iommu_table_iobmap.it_base = (unsigned long)iob_l2_base; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 7f4d857668a9..569b46423a93 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -564,7 +564,8 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, { tbl->it_blocksize = 16; tbl->it_base = (unsigned long)tce_mem; - tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT_4K; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->it_offset = dma_offset >> tbl->it_page_shift; tbl->it_index = 0; tbl->it_size = tce_size >> 3; tbl->it_busno = 0; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 1b7531ce0c0c..e0299183ae54 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -486,9 +486,10 @@ static void iommu_table_setparms(struct pci_controller *phb, memset((void *)tbl->it_base, 0, *sizep); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; /* Units of tce entries */ - tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT_4K; + tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift; /* Test if we are going over 2GB of DMA space */ if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) { @@ -499,7 +500,7 @@ static void iommu_table_setparms(struct pci_controller *phb, phb->dma_window_base_cur += phb->dma_window_size; /* Set the tce table size - measured in entries */ - tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT_4K; + tbl->it_size = phb->dma_window_size >> tbl->it_page_shift; tbl->it_index = 0; tbl->it_blocksize = 16; @@ -537,11 +538,12 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb, of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; tbl->it_base = 0; tbl->it_blocksize = 16; tbl->it_type = TCE_PCI; - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K; - tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K; + tbl->it_offset = offset >> tbl->it_page_shift; + tbl->it_size = size >> tbl->it_page_shift; } static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c index 8a589618551e..9a15e5b39bb8 100644 --- a/arch/powerpc/platforms/wsp/wsp_pci.c +++ b/arch/powerpc/platforms/wsp/wsp_pci.c @@ -381,8 +381,9 @@ static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb, /* Init bits and pieces */ tbl->table.it_blocksize = 16; - tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT_4K; - tbl->table.it_size = size >> IOMMU_PAGE_SHIFT_4K; + tbl->table.it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->table.it_offset = addr >> tbl->table.it_page_shift; + tbl->table.it_size = size >> tbl->table.it_page_shift; /* * It's already blank but we clear it anyway. -- 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 +++++--- arch/powerpc/kernel/dma-iommu.c | 4 +- arch/powerpc/kernel/iommu.c | 88 +++++++++++++++++++----------------- arch/powerpc/kernel/vio.c | 25 +++++++--- arch/powerpc/platforms/powernv/pci.c | 2 - drivers/net/ethernet/ibm/ibmveth.c | 15 +++--- 6 files changed, 88 insertions(+), 65 deletions(-) (limited to 'arch/powerpc/include/asm') 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) diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 5cfe3dbfc4a0..54d0116256f7 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -83,10 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) return 0; } - if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT_4K)) { + if (tbl->it_offset > (mask >> tbl->it_page_shift)) { dev_info(dev, "Warning: IOMMU offset too big for device mask\n"); dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n", - mask, tbl->it_offset << IOMMU_PAGE_SHIFT_4K); + mask, tbl->it_offset << tbl->it_page_shift); return 0; } else return 1; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index df4a7f1b7444..f58d8135aab2 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -251,14 +251,13 @@ again: if (dev) boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - 1 << IOMMU_PAGE_SHIFT_4K); + 1 << tbl->it_page_shift); else - boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT_4K); + boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift); /* 4GB boundary for iseries_hv_alloc and iseries_hv_map */ - n = iommu_area_alloc(tbl->it_map, limit, start, npages, - tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT_4K, - align_mask); + n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset, + boundary_size >> tbl->it_page_shift, align_mask); if (n == -1) { if (likely(pass == 0)) { /* First try the pool from the start */ @@ -320,12 +319,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, return DMA_ERROR_CODE; entry += tbl->it_offset; /* Offset into real TCE table */ - ret = entry << IOMMU_PAGE_SHIFT_4K; /* Set the return dma address */ + ret = entry << tbl->it_page_shift; /* Set the return dma address */ /* Put the TCEs in the HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - (unsigned long)page & IOMMU_PAGE_MASK_4K, - direction, attrs); + (unsigned long)page & + IOMMU_PAGE_MASK(tbl), direction, attrs); /* ppc_md.tce_build() only returns non-zero for transient errors. * Clean up the table bitmap in this case and return @@ -352,7 +351,7 @@ static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr, { unsigned long entry, free_entry; - entry = dma_addr >> IOMMU_PAGE_SHIFT_4K; + entry = dma_addr >> tbl->it_page_shift; free_entry = entry - tbl->it_offset; if (((free_entry + npages) > tbl->it_size) || @@ -401,7 +400,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned long flags; struct iommu_pool *pool; - entry = dma_addr >> IOMMU_PAGE_SHIFT_4K; + entry = dma_addr >> tbl->it_page_shift; free_entry = entry - tbl->it_offset; pool = get_pool(tbl, free_entry); @@ -468,13 +467,13 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Allocate iommu entries for that segment */ vaddr = (unsigned long) sg_virt(s); - npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE_4K); + npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE(tbl)); align = 0; - if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && slen >= PAGE_SIZE && + if (tbl->it_page_shift < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K; + align = PAGE_SHIFT - tbl->it_page_shift; entry = iommu_range_alloc(dev, tbl, npages, &handle, - mask >> IOMMU_PAGE_SHIFT_4K, align); + mask >> tbl->it_page_shift, align); DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); @@ -489,16 +488,16 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; - dma_addr = entry << IOMMU_PAGE_SHIFT_4K; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK_4K); + dma_addr = entry << tbl->it_page_shift; + dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); /* Insert into HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - vaddr & IOMMU_PAGE_MASK_4K, - direction, attrs); + vaddr & IOMMU_PAGE_MASK(tbl), + direction, attrs); if(unlikely(build_fail)) goto failure; @@ -559,9 +558,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, if (s->dma_length != 0) { unsigned long vaddr, npages; - vaddr = s->dma_address & IOMMU_PAGE_MASK_4K; + vaddr = s->dma_address & IOMMU_PAGE_MASK(tbl); npages = iommu_num_pages(s->dma_address, s->dma_length, - IOMMU_PAGE_SIZE_4K); + IOMMU_PAGE_SIZE(tbl)); __iommu_free(tbl, vaddr, npages); s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; @@ -592,7 +591,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (sg->dma_length == 0) break; npages = iommu_num_pages(dma_handle, sg->dma_length, - IOMMU_PAGE_SIZE_4K); + IOMMU_PAGE_SIZE(tbl)); __iommu_free(tbl, dma_handle, npages); sg = sg_next(sg); } @@ -676,7 +675,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) set_bit(0, tbl->it_map); /* We only split the IOMMU table if we have 1GB or more of space */ - if ((tbl->it_size << IOMMU_PAGE_SHIFT_4K) >= (1UL * 1024 * 1024 * 1024)) + if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024)) tbl->nr_pools = IOMMU_NR_POOLS; else tbl->nr_pools = 1; @@ -768,16 +767,16 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, vaddr = page_address(page) + offset; uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE_4K); + npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl)); if (tbl) { align = 0; - if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && size >= PAGE_SIZE && + if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K; + align = PAGE_SHIFT - tbl->it_page_shift; dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction, - mask >> IOMMU_PAGE_SHIFT_4K, align, + mask >> tbl->it_page_shift, align, attrs); if (dma_handle == DMA_ERROR_CODE) { if (printk_ratelimit()) { @@ -786,7 +785,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, npages); } } else - dma_handle |= (uaddr & ~IOMMU_PAGE_MASK_4K); + dma_handle |= (uaddr & ~IOMMU_PAGE_MASK(tbl)); } return dma_handle; @@ -801,7 +800,8 @@ void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, BUG_ON(direction == DMA_NONE); if (tbl) { - npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE_4K); + npages = iommu_num_pages(dma_handle, size, + IOMMU_PAGE_SIZE(tbl)); iommu_free(tbl, dma_handle, npages); } } @@ -845,10 +845,10 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> IOMMU_PAGE_SHIFT_4K; - io_order = get_iommu_order(size); + nio_pages = size >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, - mask >> IOMMU_PAGE_SHIFT_4K, io_order, NULL); + mask >> tbl->it_page_shift, io_order, NULL); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); return NULL; @@ -864,7 +864,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> IOMMU_PAGE_SHIFT_4K; + nio_pages = size >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); @@ -935,10 +935,10 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl, if (tce_value) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK_4K) + if (ioba & ~IOMMU_PAGE_MASK(tbl)) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT_4K; + ioba >>= tbl->it_page_shift; if (ioba < tbl->it_offset) return -EINVAL; @@ -955,13 +955,13 @@ int iommu_tce_put_param_check(struct iommu_table *tbl, if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ))) return -EINVAL; - if (tce & ~(IOMMU_PAGE_MASK_4K | TCE_PCI_WRITE | TCE_PCI_READ)) + if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ)) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK_4K) + if (ioba & ~IOMMU_PAGE_MASK(tbl)) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT_4K; + ioba >>= tbl->it_page_shift; if (ioba < tbl->it_offset) return -EINVAL; @@ -1037,7 +1037,7 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, /* if (unlikely(ret)) pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n", - __func__, hwaddr, entry << IOMMU_PAGE_SHIFT_4K, + __func__, hwaddr, entry << IOMMU_PAGE_SHIFT(tbl), hwaddr, ret); */ return ret; @@ -1049,14 +1049,14 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, { int ret; struct page *page = NULL; - unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK_4K & ~PAGE_MASK; + unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK; enum dma_data_direction direction = iommu_tce_direction(tce); ret = get_user_pages_fast(tce & PAGE_MASK, 1, direction != DMA_TO_DEVICE, &page); if (unlikely(ret != 1)) { /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n", - tce, entry << IOMMU_PAGE_SHIFT_4K, ret); */ + tce, entry << IOMMU_PAGE_SHIFT(tbl), ret); */ return -EFAULT; } hwaddr = (unsigned long) page_address(page) + offset; @@ -1067,7 +1067,7 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, if (ret < 0) pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n", - __func__, entry << IOMMU_PAGE_SHIFT_4K, tce, ret); + __func__, entry << tbl->it_page_shift, tce, ret); return ret; } @@ -1127,6 +1127,12 @@ int iommu_add_device(struct device *dev) pr_debug("iommu_tce: adding %s to iommu group %d\n", dev_name(dev), iommu_group_id(tbl->it_group)); + if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) { + pr_err("iommu_tce: unsupported iommu page size."); + pr_err("%s has not been added\n", dev_name(dev)); + return -EINVAL; + } + ret = iommu_group_add_device(tbl->it_group, dev); if (ret < 0) pr_err("iommu_tce: %s has not been added, ret=%d\n", diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 170ac24a0106..826d8bd9e522 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -518,16 +518,18 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; dma_addr_t ret = DMA_ERROR_CODE; - if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K))) { + tbl = get_iommu_table_base(dev); + if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) { atomic_inc(&viodev->cmo.allocs_failed); return ret; } ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs); if (unlikely(dma_mapping_error(dev, ret))) { - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); atomic_inc(&viodev->cmo.allocs_failed); } @@ -540,10 +542,12 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; + tbl = get_iommu_table_base(dev); dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs); - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); } static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, @@ -551,12 +555,14 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; struct scatterlist *sgl; int ret, count = 0; size_t alloc_size = 0; + tbl = get_iommu_table_base(dev); for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE_4K); + alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl)); if (vio_cmo_alloc(viodev, alloc_size)) { atomic_inc(&viodev->cmo.allocs_failed); @@ -572,7 +578,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, } for (sgl = sglist, count = 0; count < ret; count++, sgl++) - alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K); + alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); if (alloc_size) vio_cmo_dealloc(viodev, alloc_size); @@ -585,12 +591,14 @@ static void vio_dma_iommu_unmap_sg(struct device *dev, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; struct scatterlist *sgl; size_t alloc_size = 0; int count = 0; + tbl = get_iommu_table_base(dev); for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K); + alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs); @@ -706,11 +714,14 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) { struct vio_cmo_dev_entry *dev_ent; struct device *dev = &viodev->dev; + struct iommu_table *tbl; struct vio_driver *viodrv = to_vio_driver(dev->driver); unsigned long flags; size_t size; bool dma_capable = false; + tbl = get_iommu_table_base(dev); + /* A device requires entitlement if it has a DMA window property */ switch (viodev->family) { case VDEVICE: @@ -737,7 +748,7 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) } viodev->cmo.desired = - IOMMU_PAGE_ALIGN_4K(viodrv->get_desired_dma(viodev)); + IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev), tbl); if (viodev->cmo.desired < VIO_CMO_MIN_ENT) viodev->cmo.desired = VIO_CMO_MIN_ENT; size = VIO_CMO_MIN_ENT; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 569b46423a93..b555ebc57ef5 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -762,8 +762,6 @@ static struct notifier_block tce_iommu_bus_nb = { static int __init tce_iommu_bus_notifier_init(void) { - BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE_4K); - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); return 0; } diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index f7d7538b6bd9..d04dbaba83dd 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1276,31 +1276,34 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev) { struct net_device *netdev = dev_get_drvdata(&vdev->dev); struct ibmveth_adapter *adapter; + struct iommu_table *tbl; unsigned long ret; int i; int rxqentries = 1; + tbl = get_iommu_table_base(&vdev->dev); + /* netdev inits at probe time along with the structures we need below*/ if (netdev == NULL) - return IOMMU_PAGE_ALIGN_4K(IBMVETH_IO_ENTITLEMENT_DEFAULT); + return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT, tbl); adapter = netdev_priv(netdev); ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE; - ret += IOMMU_PAGE_ALIGN_4K(netdev->mtu); + ret += IOMMU_PAGE_ALIGN(netdev->mtu, tbl); for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { /* add the size of the active receive buffers */ if (adapter->rx_buff_pool[i].active) ret += adapter->rx_buff_pool[i].size * - IOMMU_PAGE_ALIGN_4K(adapter->rx_buff_pool[i]. - buff_size); + IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i]. + buff_size, tbl); rxqentries += adapter->rx_buff_pool[i].size; } /* add the size of the receive queue entries */ - ret += IOMMU_PAGE_ALIGN_4K( - rxqentries * sizeof(struct ibmveth_rx_q_entry)); + ret += IOMMU_PAGE_ALIGN( + rxqentries * sizeof(struct ibmveth_rx_q_entry), tbl); return ret; } -- 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 + arch/powerpc/kernel/cpu_setup_fsl_booke.S | 12 ++++++++++++ arch/powerpc/kernel/exceptions-64e.S | 17 +++++++++++++++++ arch/powerpc/kvm/bookehv_interrupts.S | 2 ++ 5 files changed, 33 insertions(+) (limited to 'arch/powerpc/include/asm') 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 */ diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index bfb18c7290b7..fa6862db8a02 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -57,6 +57,12 @@ _GLOBAL(__setup_cpu_e6500) mflr r6 #ifdef CONFIG_PPC64 bl .setup_altivec_ivors + /* Touch IVOR42 only if the CPU supports E.HV category */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f + bl .setup_lrat_ivor +1: #endif bl __setup_cpu_e5500 mtlr r6 @@ -119,6 +125,12 @@ _GLOBAL(__setup_cpu_e5500) _GLOBAL(__restore_cpu_e6500) mflr r5 bl .setup_altivec_ivors + /* Touch IVOR42 only if the CPU supports E.HV category */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f + bl .setup_lrat_ivor +1: bl __restore_cpu_e5500 mtlr r5 blr diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index e7751561fd1d..4d5a0b1034e8 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -308,6 +308,7 @@ interrupt_base_book3e: /* fake trap */ EXCEPTION_STUB(0x2e0, guest_doorbell_crit) EXCEPTION_STUB(0x300, hypercall) EXCEPTION_STUB(0x320, ehpriv) + EXCEPTION_STUB(0x340, lrat_error) .globl interrupt_end_book3e interrupt_end_book3e: @@ -677,6 +678,17 @@ kernel_dbg_exc: bl .unknown_exception b .ret_from_except +/* LRAT Error interrupt */ + START_EXCEPTION(lrat_error); + NORMAL_EXCEPTION_PROLOG(0x340, BOOKE_INTERRUPT_LRAT_ERROR, + PROLOG_ADDITION_NONE) + EXCEPTION_COMMON(0x340, PACA_EXGEN, INTS_KEEP) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .save_nvgprs + INTS_RESTORE_HARD + bl .unknown_exception + b .ret_from_except + /* * An interrupt came in while soft-disabled; We mark paca->irq_happened * accordingly and if the interrupt is level sensitive, we hard disable @@ -859,6 +871,7 @@ BAD_STACK_TRAMPOLINE(0x2e0) BAD_STACK_TRAMPOLINE(0x300) BAD_STACK_TRAMPOLINE(0x310) BAD_STACK_TRAMPOLINE(0x320) +BAD_STACK_TRAMPOLINE(0x340) BAD_STACK_TRAMPOLINE(0x400) BAD_STACK_TRAMPOLINE(0x500) BAD_STACK_TRAMPOLINE(0x600) @@ -1414,3 +1427,7 @@ _GLOBAL(setup_ehv_ivors) SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */ SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */ blr + +_GLOBAL(setup_lrat_ivor) + SET_IVOR(42, 0x340) /* LRAT Error */ + blr diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index e8ed7d659c55..a0d6929d8678 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -319,6 +319,8 @@ kvm_handler BOOKE_INTERRUPT_DEBUG, EX_PARAMS(DBG), \ SPRN_DSRR0, SPRN_DSRR1, 0 kvm_handler BOOKE_INTERRUPT_DEBUG, EX_PARAMS(CRIT), \ SPRN_CSRR0, SPRN_CSRR1, 0 +kvm_handler BOOKE_INTERRUPT_LRAT_ERROR, EX_PARAMS(GEN), \ + SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR) #else /* * For input register values, see arch/powerpc/include/asm/kvm_booke_hv_asm.h -- 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 +++++- arch/powerpc/kernel/process.c | 30 ++++++++++++++++++++++++++++-- arch/powerpc/math-emu/math_efp.c | 20 +++++++++++++++++++- 3 files changed, 52 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/include/asm') 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 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3386d8ab7eb0..b08c0d03530f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1175,6 +1175,19 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) if (val & PR_FP_EXC_SW_ENABLE) { #ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); tsk->thread.fpexc_mode = val & (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); return 0; @@ -1206,9 +1219,22 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) #ifdef CONFIG_SPE - if (cpu_has_feature(CPU_FTR_SPE)) + if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); val = tsk->thread.fpexc_mode; - else + } else return -EINVAL; #else return -EINVAL; diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c index a73f0884d358..59835c625dc6 100644 --- a/arch/powerpc/math-emu/math_efp.c +++ b/arch/powerpc/math-emu/math_efp.c @@ -630,9 +630,27 @@ update_ccr: regs->ccr |= (IR << ((7 - ((speinsn >> 23) & 0x7)) << 2)); update_regs: - __FPU_FPSCR &= ~FP_EX_MASK; + /* + * If the "invalid" exception sticky bit was set by the + * processor for non-finite input, but was not set before the + * instruction being emulated, clear it. Likewise for the + * "underflow" bit, which may have been set by the processor + * for exact underflow, not just inexact underflow when the + * flag should be set for IEEE 754 semantics. Other sticky + * exceptions will only be set by the processor when they are + * correct according to IEEE 754 semantics, and we must not + * clear sticky bits that were already set before the emulated + * instruction as they represent the user-visible sticky + * exception status. "inexact" traps to kernel are not + * required for IEEE semantics and are not enabled by default, + * so the "inexact" sticky bit may have been set by a previous + * instruction without the kernel being aware of it. + */ + __FPU_FPSCR + &= ~(FP_EX_INVALID | FP_EX_UNDERFLOW) | current->thread.spefscr_last; __FPU_FPSCR |= (FP_CUR_EXCEPTIONS & FP_EX_MASK); mtspr(SPRN_SPEFSCR, __FPU_FPSCR); + current->thread.spefscr_last = __FPU_FPSCR; current->thread.evr[fc] = vc.wp[0]; regs->gpr[fc] = vc.wp[1]; -- 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/asm') 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/asm') 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 ++ arch/powerpc/kernel/asm-offsets.c | 9 ++ arch/powerpc/kernel/paca.c | 5 + arch/powerpc/kernel/setup_64.c | 31 ++++++ arch/powerpc/mm/fsl_booke_mmu.c | 7 ++ arch/powerpc/mm/mem.c | 6 ++ arch/powerpc/mm/tlb_low_64e.S | 171 ++++++++++++++++++++++++++++++++++ arch/powerpc/mm/tlb_nohash.c | 93 ++++++++++++------ 10 files changed, 326 insertions(+), 36 deletions(-) (limited to 'arch/powerpc/include/asm') 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; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 41a283956a29..ed8d68ce71f3 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -203,6 +203,15 @@ int main(void) DEFINE(PACA_MC_STACK, offsetof(struct paca_struct, mc_kstack)); DEFINE(PACA_CRIT_STACK, offsetof(struct paca_struct, crit_kstack)); DEFINE(PACA_DBG_STACK, offsetof(struct paca_struct, dbg_kstack)); + DEFINE(PACA_TCD_PTR, offsetof(struct paca_struct, tcd_ptr)); + + DEFINE(TCD_ESEL_NEXT, + offsetof(struct tlb_core_data, esel_next)); + DEFINE(TCD_ESEL_MAX, + offsetof(struct tlb_core_data, esel_max)); + DEFINE(TCD_ESEL_FIRST, + offsetof(struct tlb_core_data, esel_first)); + DEFINE(TCD_LOCK, offsetof(struct tlb_core_data, lock)); #endif /* CONFIG_PPC_BOOK3E */ #ifdef CONFIG_PPC_STD_MMU_64 diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 623c356fe34f..bf0aada02fe4 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -160,6 +160,11 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) #ifdef CONFIG_PPC_STD_MMU_64 new_paca->slb_shadow_ptr = init_slb_shadow(cpu); #endif /* CONFIG_PPC_STD_MMU_64 */ + +#ifdef CONFIG_PPC_BOOK3E + /* For now -- if we have threads this will be adjusted later */ + new_paca->tcd_ptr = &new_paca->tcd; +#endif } /* Put the paca pointer into r13 and SPRG_PACA */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2232aff66059..1ce9b87d7df8 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -97,6 +97,36 @@ int dcache_bsize; int icache_bsize; int ucache_bsize; +#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +static void setup_tlb_core_data(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + int first = cpu_first_thread_sibling(cpu); + + paca[cpu].tcd_ptr = &paca[first].tcd; + + /* + * If we have threads, we need either tlbsrx. + * or e6500 tablewalk mode, or else TLB handlers + * will be racy and could produce duplicate entries. + */ + if (smt_enabled_at_boot >= 2 && + !mmu_has_feature(MMU_FTR_USE_TLBRSRV) && + book3e_htw_mode != PPC_HTW_E6500) { + /* Should we panic instead? */ + WARN_ONCE("%s: unsupported MMU configuration -- expect problems\n", + __func__); + } + } +} +#else +static void setup_tlb_core_data(void) +{ +} +#endif + #ifdef CONFIG_SMP static char *smt_enabled_cmdline; @@ -445,6 +475,7 @@ void __init setup_system(void) smp_setup_cpu_maps(); check_smt_enabled(); + setup_tlb_core_data(); #ifdef CONFIG_SMP /* Release secondary cpus out of their spinloops at 0x60 now that diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c index a68671c18ad4..94cd728166d3 100644 --- a/arch/powerpc/mm/fsl_booke_mmu.c +++ b/arch/powerpc/mm/fsl_booke_mmu.c @@ -52,6 +52,7 @@ #include #include #include +#include #include "mmu_decl.h" @@ -191,6 +192,12 @@ static unsigned long map_mem_in_cams_addr(phys_addr_t phys, unsigned long virt, } tlbcam_index = i; +#ifdef CONFIG_PPC64 + get_paca()->tcd.esel_next = i; + get_paca()->tcd.esel_max = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY; + get_paca()->tcd.esel_first = i; +#endif + return amount_mapped; } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 3fa93dc7fe75..94448cd4b444 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -307,6 +307,12 @@ static void __init register_page_bootmem_info(void) void __init mem_init(void) { + /* + * book3s is limited to 16 page sizes due to encoding this in + * a 4-bit field for slices. + */ + BUILD_BUG_ON(MMU_PAGE_COUNT > 16); + #ifdef CONFIG_SWIOTLB swiotlb_init(0); #endif diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index b4113bf86353..75f5d2777f61 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -239,6 +239,177 @@ itlb_miss_fault_bolted: beq tlb_miss_common_bolted b itlb_miss_kernel_bolted +/* + * TLB miss handling for e6500 and derivatives, using hardware tablewalk. + * + * Linear mapping is bolted: no virtual page table or nested TLB misses + * Indirect entries in TLB1, hardware loads resulting direct entries + * into TLB0 + * No HES or NV hint on TLB1, so we need to do software round-robin + * No tlbsrx. so we need a spinlock, and we have to deal + * with MAS-damage caused by tlbsx + * 4K pages only + */ + + START_EXCEPTION(instruction_tlb_miss_e6500) + tlb_prolog_bolted BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR0 + + ld r11,PACA_TCD_PTR(r13) + srdi. r15,r16,60 /* get region */ + ori r16,r16,1 + + TLB_MISS_STATS_SAVE_INFO_BOLTED + bne tlb_miss_kernel_e6500 /* user/kernel test */ + + b tlb_miss_common_e6500 + + START_EXCEPTION(data_tlb_miss_e6500) + tlb_prolog_bolted BOOKE_INTERRUPT_DTLB_MISS SPRN_DEAR + + ld r11,PACA_TCD_PTR(r13) + srdi. r15,r16,60 /* get region */ + rldicr r16,r16,0,62 + + TLB_MISS_STATS_SAVE_INFO_BOLTED + bne tlb_miss_kernel_e6500 /* user vs kernel check */ + +/* + * This is the guts of the TLB miss handler for e6500 and derivatives. + * We are entered with: + * + * r16 = page of faulting address (low bit 0 if data, 1 if instruction) + * r15 = crap (free to use) + * r14 = page table base + * r13 = PACA + * r11 = tlb_per_core ptr + * r10 = crap (free to use) + */ +tlb_miss_common_e6500: + /* + * Search if we already have an indirect entry for that virtual + * address, and if we do, bail out. + * + * MAS6:IND should be already set based on MAS4 + */ + addi r10,r11,TCD_LOCK +1: lbarx r15,0,r10 + cmpdi r15,0 + bne 2f + li r15,1 + stbcx. r15,0,r10 + bne 1b + .subsection 1 +2: lbz r15,0(r10) + cmpdi r15,0 + bne 2b + b 1b + .previous + + mfspr r15,SPRN_MAS2 + + tlbsx 0,r16 + mfspr r10,SPRN_MAS1 + andis. r10,r10,MAS1_VALID@h + bne tlb_miss_done_e6500 + + /* Undo MAS-damage from the tlbsx */ + mfspr r10,SPRN_MAS1 + oris r10,r10,MAS1_VALID@h + mtspr SPRN_MAS1,r10 + mtspr SPRN_MAS2,r15 + + /* Now, we need to walk the page tables. First check if we are in + * range. + */ + rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4 + bne- tlb_miss_fault_e6500 + + rldicl r15,r16,64-PGDIR_SHIFT+3,64-PGD_INDEX_SIZE-3 + cmpldi cr0,r14,0 + clrrdi r15,r15,3 + beq- tlb_miss_fault_e6500 /* No PGDIR, bail */ + ldx r14,r14,r15 /* grab pgd entry */ + + rldicl r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3 + clrrdi r15,r15,3 + cmpdi cr0,r14,0 + bge tlb_miss_fault_e6500 /* Bad pgd entry or hugepage; bail */ + ldx r14,r14,r15 /* grab pud entry */ + + rldicl r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3 + clrrdi r15,r15,3 + cmpdi cr0,r14,0 + bge tlb_miss_fault_e6500 + ldx r14,r14,r15 /* Grab pmd entry */ + + mfspr r10,SPRN_MAS0 + cmpdi cr0,r14,0 + bge tlb_miss_fault_e6500 + + /* Now we build the MAS for a 2M indirect page: + * + * MAS 0 : ESEL needs to be filled by software round-robin + * MAS 1 : Fully set up + * - PID already updated by caller if necessary + * - TSIZE for now is base ind page size always + * - TID already cleared if necessary + * MAS 2 : Default not 2M-aligned, need to be redone + * MAS 3+7 : Needs to be done + */ + + ori r14,r14,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT) + mtspr SPRN_MAS7_MAS3,r14 + + clrrdi r15,r16,21 /* make EA 2M-aligned */ + mtspr SPRN_MAS2,r15 + + lbz r15,TCD_ESEL_NEXT(r11) + lbz r16,TCD_ESEL_MAX(r11) + lbz r14,TCD_ESEL_FIRST(r11) + rlwimi r10,r15,16,0x00ff0000 /* insert esel_next into MAS0 */ + addi r15,r15,1 /* increment esel_next */ + mtspr SPRN_MAS0,r10 + cmpw r15,r16 + iseleq r15,r14,r15 /* if next == last use first */ + stb r15,TCD_ESEL_NEXT(r11) + + tlbwe + +tlb_miss_done_e6500: + .macro tlb_unlock_e6500 + li r15,0 + isync + stb r15,TCD_LOCK(r11) + .endm + + tlb_unlock_e6500 + TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK) + tlb_epilog_bolted + rfi + +tlb_miss_kernel_e6500: + mfspr r10,SPRN_MAS1 + ld r14,PACA_KERNELPGD(r13) + cmpldi cr0,r15,8 /* Check for vmalloc region */ + rlwinm r10,r10,0,16,1 /* Clear TID */ + mtspr SPRN_MAS1,r10 + beq+ tlb_miss_common_e6500 + +tlb_miss_fault_e6500: + tlb_unlock_e6500 + /* We need to check if it was an instruction miss */ + andi. r16,r16,1 + bne itlb_miss_fault_e6500 +dtlb_miss_fault_e6500: + TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT) + tlb_epilog_bolted + b exc_data_storage_book3e +itlb_miss_fault_e6500: + TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) + tlb_epilog_bolted + b exc_instruction_storage_book3e + + /********************************************************************** * * * TLB miss handling for Book3E with TLB reservation and HES support * diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 8805b7b87dc6..735839b74dc5 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -43,6 +43,7 @@ #include #include #include +#include #include "mmu_decl.h" @@ -58,6 +59,10 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { .shift = 12, .enc = BOOK3E_PAGESZ_4K, }, + [MMU_PAGE_2M] = { + .shift = 21, + .enc = BOOK3E_PAGESZ_2M, + }, [MMU_PAGE_4M] = { .shift = 22, .enc = BOOK3E_PAGESZ_4M, @@ -136,7 +141,7 @@ static inline int mmu_get_tsize(int psize) int mmu_linear_psize; /* Page size used for the linear mapping */ int mmu_pte_psize; /* Page size used for PTE pages */ int mmu_vmemmap_psize; /* Page size used for the virtual mem map */ -int book3e_htw_enabled; /* Is HW tablewalk enabled ? */ +int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */ unsigned long linear_map_top; /* Top of linear mapping */ #endif /* CONFIG_PPC64 */ @@ -377,7 +382,7 @@ void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address) { int tsize = mmu_psize_defs[mmu_pte_psize].enc; - if (book3e_htw_enabled) { + if (book3e_htw_mode != PPC_HTW_NONE) { unsigned long start = address & PMD_MASK; unsigned long end = address + PMD_SIZE; unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift; @@ -430,7 +435,7 @@ static void setup_page_sizes(void) def = &mmu_psize_defs[psize]; shift = def->shift; - if (shift == 0) + if (shift == 0 || shift & 1) continue; /* adjust to be in terms of 4^shift Kb */ @@ -440,21 +445,40 @@ static void setup_page_sizes(void) def->flags |= MMU_PAGE_SIZE_DIRECT; } - goto no_indirect; + goto out; } if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) { - u32 tlb1ps = mfspr(SPRN_TLB1PS); + u32 tlb1cfg, tlb1ps; + + tlb0cfg = mfspr(SPRN_TLB0CFG); + tlb1cfg = mfspr(SPRN_TLB1CFG); + tlb1ps = mfspr(SPRN_TLB1PS); + eptcfg = mfspr(SPRN_EPTCFG); + + if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT)) + book3e_htw_mode = PPC_HTW_E6500; + + /* + * We expect 4K subpage size and unrestricted indirect size. + * The lack of a restriction on indirect size is a Freescale + * extension, indicated by PSn = 0 but SPSn != 0. + */ + if (eptcfg != 2) + book3e_htw_mode = PPC_HTW_NONE; for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { struct mmu_psize_def *def = &mmu_psize_defs[psize]; if (tlb1ps & (1U << (def->shift - 10))) { def->flags |= MMU_PAGE_SIZE_DIRECT; + + if (book3e_htw_mode && psize == MMU_PAGE_2M) + def->flags |= MMU_PAGE_SIZE_INDIRECT; } } - goto no_indirect; + goto out; } #endif @@ -471,8 +495,11 @@ static void setup_page_sizes(void) } /* Indirect page sizes supported ? */ - if ((tlb0cfg & TLBnCFG_IND) == 0) - goto no_indirect; + if ((tlb0cfg & TLBnCFG_IND) == 0 || + (tlb0cfg & TLBnCFG_PT) == 0) + goto out; + + book3e_htw_mode = PPC_HTW_IBM; /* Now, we only deal with one IND page size for each * direct size. Hopefully all implementations today are @@ -497,8 +524,8 @@ static void setup_page_sizes(void) def->ind = ps + 10; } } - no_indirect: +out: /* Cleanup array and print summary */ pr_info("MMU: Supported page sizes\n"); for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { @@ -520,23 +547,23 @@ static void setup_page_sizes(void) static void setup_mmu_htw(void) { - /* Check if HW tablewalk is present, and if yes, enable it by: - * - * - patching the TLB miss handlers to branch to the - * one dedicates to it - * - * - setting the global book3e_htw_enabled - */ - unsigned int tlb0cfg = mfspr(SPRN_TLB0CFG); + /* + * If we want to use HW tablewalk, enable it by patching the TLB miss + * handlers to branch to the one dedicated to it. + */ - if ((tlb0cfg & TLBnCFG_IND) && - (tlb0cfg & TLBnCFG_PT)) { + switch (book3e_htw_mode) { + case PPC_HTW_IBM: patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e); - book3e_htw_enabled = 1; + break; + case PPC_HTW_E6500: + patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); + patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e); + break; } pr_info("MMU: Book3E HW tablewalk %s\n", - book3e_htw_enabled ? "enabled" : "not supported"); + book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported"); } /* @@ -576,8 +603,16 @@ static void __early_init_mmu(int boot_cpu) /* Set MAS4 based on page table setting */ mas4 = 0x4 << MAS4_WIMGED_SHIFT; - if (book3e_htw_enabled) { - mas4 |= mas4 | MAS4_INDD; + switch (book3e_htw_mode) { + case PPC_HTW_E6500: + mas4 |= MAS4_INDD; + mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT; + mas4 |= MAS4_TLBSELD(1); + mmu_pte_psize = MMU_PAGE_2M; + break; + + case PPC_HTW_IBM: + mas4 |= MAS4_INDD; #ifdef CONFIG_PPC_64K_PAGES mas4 |= BOOK3E_PAGESZ_256M << MAS4_TSIZED_SHIFT; mmu_pte_psize = MMU_PAGE_256M; @@ -585,13 +620,16 @@ static void __early_init_mmu(int boot_cpu) mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT; mmu_pte_psize = MMU_PAGE_1M; #endif - } else { + break; + + case PPC_HTW_NONE: #ifdef CONFIG_PPC_64K_PAGES mas4 |= BOOK3E_PAGESZ_64K << MAS4_TSIZED_SHIFT; #else mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT; #endif mmu_pte_psize = mmu_virtual_psize; + break; } mtspr(SPRN_MAS4, mas4); @@ -611,8 +649,11 @@ static void __early_init_mmu(int boot_cpu) /* limit memory so we dont have linear faults */ memblock_enforce_memory_limit(linear_map_top); - patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); - patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e); + if (book3e_htw_mode == PPC_HTW_NONE) { + patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); + patch_exception(0x1e0, + exc_instruction_tlb_miss_bolted_book3e); + } } #endif -- 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 +- arch/powerpc/sysdev/fsl_lbc.c | 31 +++++++++++++++++++++++++------ 2 files changed, 26 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include/asm') 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; diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c index 6bc5a546d49f..d631022ffb4b 100644 --- a/arch/powerpc/sysdev/fsl_lbc.c +++ b/arch/powerpc/sysdev/fsl_lbc.c @@ -214,10 +214,14 @@ static irqreturn_t fsl_lbc_ctrl_irq(int irqno, void *data) struct fsl_lbc_ctrl *ctrl = data; struct fsl_lbc_regs __iomem *lbc = ctrl->regs; u32 status; + unsigned long flags; + spin_lock_irqsave(&fsl_lbc_lock, flags); status = in_be32(&lbc->ltesr); - if (!status) + if (!status) { + spin_unlock_irqrestore(&fsl_lbc_lock, flags); return IRQ_NONE; + } out_be32(&lbc->ltesr, LTESR_CLEAR); out_be32(&lbc->lteatr, 0); @@ -260,6 +264,7 @@ static irqreturn_t fsl_lbc_ctrl_irq(int irqno, void *data) if (status & ~LTESR_MASK) dev_err(ctrl->dev, "Unknown error: " "LTESR 0x%08X\n", status); + spin_unlock_irqrestore(&fsl_lbc_lock, flags); return IRQ_HANDLED; } @@ -298,8 +303,8 @@ static int fsl_lbc_ctrl_probe(struct platform_device *dev) goto err; } - fsl_lbc_ctrl_dev->irq = irq_of_parse_and_map(dev->dev.of_node, 0); - if (fsl_lbc_ctrl_dev->irq == NO_IRQ) { + fsl_lbc_ctrl_dev->irq[0] = irq_of_parse_and_map(dev->dev.of_node, 0); + if (!fsl_lbc_ctrl_dev->irq[0]) { dev_err(&dev->dev, "failed to get irq resource\n"); ret = -ENODEV; goto err; @@ -311,20 +316,34 @@ static int fsl_lbc_ctrl_probe(struct platform_device *dev) if (ret < 0) goto err; - ret = request_irq(fsl_lbc_ctrl_dev->irq, fsl_lbc_ctrl_irq, 0, + ret = request_irq(fsl_lbc_ctrl_dev->irq[0], fsl_lbc_ctrl_irq, 0, "fsl-lbc", fsl_lbc_ctrl_dev); if (ret != 0) { dev_err(&dev->dev, "failed to install irq (%d)\n", - fsl_lbc_ctrl_dev->irq); - ret = fsl_lbc_ctrl_dev->irq; + fsl_lbc_ctrl_dev->irq[0]); + ret = fsl_lbc_ctrl_dev->irq[0]; goto err; } + fsl_lbc_ctrl_dev->irq[1] = irq_of_parse_and_map(dev->dev.of_node, 1); + if (fsl_lbc_ctrl_dev->irq[1]) { + ret = request_irq(fsl_lbc_ctrl_dev->irq[1], fsl_lbc_ctrl_irq, + IRQF_SHARED, "fsl-lbc-err", fsl_lbc_ctrl_dev); + if (ret) { + dev_err(&dev->dev, "failed to install irq (%d)\n", + fsl_lbc_ctrl_dev->irq[1]); + ret = fsl_lbc_ctrl_dev->irq[1]; + goto err1; + } + } + /* Enable interrupts for any detected events */ out_be32(&fsl_lbc_ctrl_dev->regs->lteir, LTEIR_ENABLE); return 0; +err1: + free_irq(fsl_lbc_ctrl_dev->irq[0], fsl_lbc_ctrl_dev); err: iounmap(fsl_lbc_ctrl_dev->regs); kfree(fsl_lbc_ctrl_dev); -- 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 - arch/powerpc/kernel/cacheinfo.c | 1 - arch/powerpc/kernel/crash.c | 1 - arch/powerpc/kernel/eeh_pe.c | 1 - arch/powerpc/kernel/head_64.S | 1 + arch/powerpc/kernel/hw_breakpoint.c | 1 - arch/powerpc/kernel/iomap.c | 1 - arch/powerpc/kernel/kgdb.c | 1 - arch/powerpc/kernel/process.c | 1 - arch/powerpc/kernel/smp-tbsync.c | 1 - arch/powerpc/kernel/syscalls.c | 1 - arch/powerpc/kernel/vdso32/vdso32_wrapper.S | 1 - arch/powerpc/kernel/vdso64/vdso64_wrapper.S | 1 - arch/powerpc/mm/pgtable.c | 1 - arch/powerpc/mm/pgtable_64.c | 1 - arch/powerpc/mm/tlb_hash64.c | 1 - arch/powerpc/oprofile/op_model_7450.c | 1 - arch/powerpc/oprofile/op_model_cell.c | 1 - arch/powerpc/oprofile/op_model_fsl_emb.c | 1 - arch/powerpc/oprofile/op_model_pa6t.c | 1 - arch/powerpc/oprofile/op_model_power4.c | 1 - arch/powerpc/oprofile/op_model_rs64.c | 1 - arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c | 1 - arch/powerpc/platforms/83xx/suspend.c | 1 - arch/powerpc/platforms/85xx/sgy_cts1000.c | 1 - arch/powerpc/platforms/chrp/smp.c | 1 - arch/powerpc/platforms/embedded6xx/hlwd-pic.c | 1 - arch/powerpc/platforms/pasemi/dma_lib.c | 1 - arch/powerpc/platforms/powermac/pfunc_core.c | 1 - arch/powerpc/platforms/powernv/eeh-ioda.c | 1 - arch/powerpc/platforms/pseries/cmm.c | 1 - arch/powerpc/platforms/pseries/dtl.c | 1 - arch/powerpc/sysdev/cpm2_pic.c | 1 - arch/powerpc/sysdev/fsl_ifc.c | 1 - arch/powerpc/sysdev/ge/ge_pic.h | 1 - arch/powerpc/sysdev/i8259.c | 1 - arch/powerpc/sysdev/mpc8xx_pic.c | 1 - arch/powerpc/sysdev/qe_lib/qe_io.c | 1 - arch/powerpc/sysdev/qe_lib/ucc.c | 1 - arch/powerpc/sysdev/qe_lib/ucc_fast.c | 1 - arch/powerpc/sysdev/qe_lib/ucc_slow.c | 1 - arch/powerpc/sysdev/udbg_memcons.c | 1 - arch/powerpc/sysdev/xics/icp-hv.c | 1 - 46 files changed, 1 insertion(+), 45 deletions(-) (limited to 'arch/powerpc/include/asm') 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 diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 654932727873..abfa011344d9 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -12,7 +12,6 @@ #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index fdcd8f551aff..18d7c80ddeb9 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index f9450537e335..1feccd64f955 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4f0946de2d5c..b7363bd42452 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -23,6 +23,7 @@ */ #include +#include #include #include #include diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index f0b47d1a6b0e..b0a1792279bb 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 97a3715ac8bd..b82227e7e21b 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -3,7 +3,6 @@ * * (C) Copyright 2004 Linus Torvalds */ -#include #include #include #include diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 83e89d310734..8504657379f1 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -15,7 +15,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3386d8ab7eb0..bf8e136316e2 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c index e68fd1ae727a..7a37ecd3afa3 100644 --- a/arch/powerpc/kernel/smp-tbsync.c +++ b/arch/powerpc/kernel/smp-tbsync.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 4e3cc47f26b9..cd9be9aa016d 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 6e8f507ed32b..79683d0393f5 100644 --- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -1,4 +1,3 @@ -#include #include #include diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S index b8553d62b792..8df9e2463007 100644 --- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -1,4 +1,3 @@ -#include #include #include diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index ad90429bbd8b..c695943a513c 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 02e8681fb865..7f0e872ab83d 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 36e44b4260eb..c99f6510a0b2 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -23,7 +23,6 @@ #include #include -#include #include #include #include diff --git a/arch/powerpc/oprofile/op_model_7450.c b/arch/powerpc/oprofile/op_model_7450.c index ff617246d128..d29b6e4e5e72 100644 --- a/arch/powerpc/oprofile/op_model_7450.c +++ b/arch/powerpc/oprofile/op_model_7450.c @@ -16,7 +16,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c index b9589c19ccda..1f0ebdeea5f7 100644 --- a/arch/powerpc/oprofile/op_model_cell.c +++ b/arch/powerpc/oprofile/op_model_cell.c @@ -16,7 +16,6 @@ #include #include -#include #include #include #include diff --git a/arch/powerpc/oprofile/op_model_fsl_emb.c b/arch/powerpc/oprofile/op_model_fsl_emb.c index 2a82d3ed464d..14cf86fdddab 100644 --- a/arch/powerpc/oprofile/op_model_fsl_emb.c +++ b/arch/powerpc/oprofile/op_model_fsl_emb.c @@ -14,7 +14,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/oprofile/op_model_pa6t.c b/arch/powerpc/oprofile/op_model_pa6t.c index 42f778dff919..a114a7c22d40 100644 --- a/arch/powerpc/oprofile/op_model_pa6t.c +++ b/arch/powerpc/oprofile/op_model_pa6t.c @@ -22,7 +22,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c index f444b94935f5..962fe7b3e3fb 100644 --- a/arch/powerpc/oprofile/op_model_power4.c +++ b/arch/powerpc/oprofile/op_model_power4.c @@ -10,7 +10,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/oprofile/op_model_rs64.c b/arch/powerpc/oprofile/op_model_rs64.c index 9b801b8c8c5a..7e5b8ed3a1b7 100644 --- a/arch/powerpc/oprofile/op_model_rs64.c +++ b/arch/powerpc/oprofile/op_model_rs64.c @@ -8,7 +8,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index fd71cfdf2380..e238b6a55b15 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -11,7 +11,6 @@ * (at your option) any later version. */ -#include #include #include #include diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 3d9716ccd327..4b4c081df94d 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -10,7 +10,6 @@ * by the Free Software Foundation. */ -#include #include #include #include diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c index b9197cea1854..bb75add67084 100644 --- a/arch/powerpc/platforms/85xx/sgy_cts1000.c +++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c index dead91b177b9..b6c9a0dcc924 100644 --- a/arch/powerpc/platforms/chrp/smp.c +++ b/arch/powerpc/platforms/chrp/smp.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 6c03034dbbd3..c269caee58f9 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -15,7 +15,6 @@ #define pr_fmt(fmt) DRV_MODULE_NAME ": " fmt #include -#include #include #include #include diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c index f3defd8a2806..aafa01ba062f 100644 --- a/arch/powerpc/platforms/pasemi/dma_lib.c +++ b/arch/powerpc/platforms/pasemi/dma_lib.c @@ -18,7 +18,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c index d588e48dff74..43075081721f 100644 --- a/arch/powerpc/platforms/powermac/pfunc_core.c +++ b/arch/powerpc/platforms/powermac/pfunc_core.c @@ -5,7 +5,6 @@ * FIXME: LOCKING !!! */ -#include #include #include #include diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 9b1db254898a..007ac4989841 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 1e561bef459b..2d8bf15879fd 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 5db66f1fbc26..7d61498e45c0 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -20,7 +20,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include #include #include #include diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c index 10386b676d87..a11bd1d433ad 100644 --- a/arch/powerpc/sysdev/cpm2_pic.c +++ b/arch/powerpc/sysdev/cpm2_pic.c @@ -27,7 +27,6 @@ */ #include -#include #include #include #include diff --git a/arch/powerpc/sysdev/fsl_ifc.c b/arch/powerpc/sysdev/fsl_ifc.c index d7fc72239144..fbc885b31946 100644 --- a/arch/powerpc/sysdev/fsl_ifc.c +++ b/arch/powerpc/sysdev/fsl_ifc.c @@ -19,7 +19,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include #include #include #include diff --git a/arch/powerpc/sysdev/ge/ge_pic.h b/arch/powerpc/sysdev/ge/ge_pic.h index 6149916da3f4..908dbd9826b6 100644 --- a/arch/powerpc/sysdev/ge/ge_pic.h +++ b/arch/powerpc/sysdev/ge/ge_pic.h @@ -1,7 +1,6 @@ #ifndef __GEF_PIC_H__ #define __GEF_PIC_H__ -#include void gef_pic_cascade(unsigned int, struct irq_desc *); unsigned int gef_pic_get_irq(void); diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c index 997df6a7ab5d..45598da0b321 100644 --- a/arch/powerpc/sysdev/i8259.c +++ b/arch/powerpc/sysdev/i8259.c @@ -8,7 +8,6 @@ */ #undef DEBUG -#include #include #include #include diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c index b724622c3a0b..c4828c0be5bd 100644 --- a/arch/powerpc/sysdev/mpc8xx_pic.c +++ b/arch/powerpc/sysdev/mpc8xx_pic.c @@ -1,6 +1,5 @@ #include #include -#include #include #include #include diff --git a/arch/powerpc/sysdev/qe_lib/qe_io.c b/arch/powerpc/sysdev/qe_lib/qe_io.c index a88807b3dd57..d09994164daf 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_io.c +++ b/arch/powerpc/sysdev/qe_lib/qe_io.c @@ -16,7 +16,6 @@ #include #include -#include #include #include #include diff --git a/arch/powerpc/sysdev/qe_lib/ucc.c b/arch/powerpc/sysdev/qe_lib/ucc.c index 134b07d29435..621575b7e84a 100644 --- a/arch/powerpc/sysdev/qe_lib/ucc.c +++ b/arch/powerpc/sysdev/qe_lib/ucc.c @@ -14,7 +14,6 @@ * option) any later version. */ #include -#include #include #include #include diff --git a/arch/powerpc/sysdev/qe_lib/ucc_fast.c b/arch/powerpc/sysdev/qe_lib/ucc_fast.c index cceb2e366738..65aaf15032ae 100644 --- a/arch/powerpc/sysdev/qe_lib/ucc_fast.c +++ b/arch/powerpc/sysdev/qe_lib/ucc_fast.c @@ -13,7 +13,6 @@ * option) any later version. */ #include -#include #include #include #include diff --git a/arch/powerpc/sysdev/qe_lib/ucc_slow.c b/arch/powerpc/sysdev/qe_lib/ucc_slow.c index 1c062f48f1ac..befaf1123f7f 100644 --- a/arch/powerpc/sysdev/qe_lib/ucc_slow.c +++ b/arch/powerpc/sysdev/qe_lib/ucc_slow.c @@ -13,7 +13,6 @@ * option) any later version. */ #include -#include #include #include #include diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c index ce5a7b489e4b..9998c0de12d0 100644 --- a/arch/powerpc/sysdev/udbg_memcons.c +++ b/arch/powerpc/sysdev/udbg_memcons.c @@ -18,7 +18,6 @@ * 2 of the License, or (at your option) any later version. */ -#include #include #include #include diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index df0fc5821469..c1917cf67c3d 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -12,7 +12,6 @@ #include #include #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 + arch/powerpc/kernel/eeh_pe.c | 3 +++ arch/powerpc/platforms/powernv/eeh-powernv.c | 3 ++- arch/powerpc/platforms/pseries/eeh_pseries.c | 4 +++- 4 files changed, 9 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') 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; diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 1feccd64f955..f0c353fa655a 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -736,6 +736,9 @@ static void *eeh_restore_one_device_bars(void *data, void *flag) else eeh_restore_device_bars(edev, dn); + if (eeh_ops->restore_config) + eeh_ops->restore_config(dn); + return NULL; } diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 73b981438cc5..ab91e6a34afa 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -359,7 +359,8 @@ static struct eeh_ops powernv_eeh_ops = { .configure_bridge = powernv_eeh_configure_bridge, .read_config = pnv_pci_cfg_read, .write_config = pnv_pci_cfg_write, - .next_error = powernv_eeh_next_error + .next_error = powernv_eeh_next_error, + .restore_config = NULL }; /** diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ccb633e077b1..9ef3cc8ebc11 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -689,7 +689,9 @@ static struct eeh_ops pseries_eeh_ops = { .get_log = pseries_eeh_get_log, .configure_bridge = pseries_eeh_configure_bridge, .read_config = pseries_eeh_read_config, - .write_config = pseries_eeh_write_config + .write_config = pseries_eeh_write_config, + .next_error = NULL, + .restore_config = NULL }; /** -- 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 ++++++-- arch/powerpc/platforms/powernv/eeh-powernv.c | 23 ++++++++++++++++++++++- 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include/asm') 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); diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index ab91e6a34afa..a79fddc5e74e 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -344,6 +344,27 @@ static int powernv_eeh_next_error(struct eeh_pe **pe) return -EEXIST; } +static int powernv_eeh_restore_config(struct device_node *dn) +{ + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct pnv_phb *phb; + s64 ret; + + if (!edev) + return -EEXIST; + + phb = edev->phb->private_data; + ret = opal_pci_reinit(phb->opal_id, + OPAL_REINIT_PCI_DEV, edev->config_addr); + if (ret) { + pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n", + __func__, edev->config_addr, ret); + return -EIO; + } + + return 0; +} + static struct eeh_ops powernv_eeh_ops = { .name = "powernv", .init = powernv_eeh_init, @@ -360,7 +381,7 @@ static struct eeh_ops powernv_eeh_ops = { .read_config = pnv_pci_cfg_read, .write_config = pnv_pci_cfg_write, .next_error = powernv_eeh_next_error, - .restore_config = NULL + .restore_config = powernv_eeh_restore_config }; /** -- 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 ++- arch/powerpc/kernel/eeh.c | 15 +++++++++++++++ arch/powerpc/kernel/eeh_driver.c | 10 +++++++--- 3 files changed, 24 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/include/asm') 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 */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f4b7a227f183..148db72a8c43 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -921,6 +921,13 @@ void eeh_add_device_late(struct pci_dev *dev) eeh_sysfs_remove_device(edev->pdev); edev->mode &= ~EEH_DEV_SYSFS; + /* + * We definitely should have the PCI device removed + * though it wasn't correctly. So we needn't call + * into error handler afterwards. + */ + edev->mode |= EEH_DEV_NO_HANDLER; + edev->pdev = NULL; dev->dev.archdata.edev = NULL; } @@ -1023,6 +1030,14 @@ void eeh_remove_device(struct pci_dev *dev) else edev->mode |= EEH_DEV_DISCONNECTED; + /* + * We're removing from the PCI subsystem, that means + * the PCI device driver can't support EEH or not + * well. So we rely on hotplug completely to do recovery + * for the specific PCI device. + */ + edev->mode |= EEH_DEV_NO_HANDLER; + eeh_addr_cache_rmv_dev(dev); eeh_sysfs_remove_device(dev); edev->mode &= ~EEH_DEV_SYSFS; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 4ef59c33777f..7db39203a073 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -217,7 +217,8 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) if (!driver) return NULL; if (!driver->err_handler || - !driver->err_handler->mmio_enabled) { + !driver->err_handler->mmio_enabled || + (edev->mode & EEH_DEV_NO_HANDLER)) { eeh_pcid_put(dev); return NULL; } @@ -258,7 +259,8 @@ static void *eeh_report_reset(void *data, void *userdata) eeh_enable_irq(dev); if (!driver->err_handler || - !driver->err_handler->slot_reset) { + !driver->err_handler->slot_reset || + (edev->mode & EEH_DEV_NO_HANDLER)) { eeh_pcid_put(dev); return NULL; } @@ -297,7 +299,9 @@ static void *eeh_report_resume(void *data, void *userdata) eeh_enable_irq(dev); if (!driver->err_handler || - !driver->err_handler->resume) { + !driver->err_handler->resume || + (edev->mode & EEH_DEV_NO_HANDLER)) { + edev->mode &= ~EEH_DEV_NO_HANDLER; eeh_pcid_put(dev); return NULL; } -- 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 +++++- arch/powerpc/mm/numa.c | 70 +++++++++++++++++++++++++++++++++++-- 2 files changed, 76 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/include/asm') 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) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 078d3e00a616..6847d509162f 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -31,6 +31,8 @@ #include #include #include +#include +#include #include #include #include @@ -152,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn, } } -static void map_cpu_to_node(int cpu, int node) +static void reset_numa_cpu_lookup_table(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + numa_cpu_lookup_table[cpu] = -1; +} + +static void update_numa_cpu_lookup_table(unsigned int cpu, int node) { numa_cpu_lookup_table[cpu] = node; +} + +static void map_cpu_to_node(int cpu, int node) +{ + update_numa_cpu_lookup_table(cpu, node); dbg("adding cpu %d to node %d\n", cpu, node); @@ -522,11 +537,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem, */ static int numa_setup_cpu(unsigned long lcpu) { - int nid = 0; - struct device_node *cpu = of_get_cpu_node(lcpu, NULL); + int nid; + struct device_node *cpu; + + /* + * If a valid cpu-to-node mapping is already available, use it + * directly instead of querying the firmware, since it represents + * the most recent mapping notified to us by the platform (eg: VPHN). + */ + if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) { + map_cpu_to_node(lcpu, nid); + return nid; + } + + cpu = of_get_cpu_node(lcpu, NULL); if (!cpu) { WARN_ON(1); + nid = 0; goto out; } @@ -1067,6 +1095,7 @@ void __init do_init_bootmem(void) */ setup_node_to_cpumask_map(); + reset_numa_cpu_lookup_table(); register_cpu_notifier(&ppc64_numa_nb); cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE, (void *)(unsigned long)boot_cpuid); @@ -1445,6 +1474,33 @@ static int update_cpu_topology(void *data) return 0; } +static int update_lookup_table(void *data) +{ + struct topology_update_data *update; + + if (!data) + return -EINVAL; + + /* + * Upon topology update, the numa-cpu lookup table needs to be updated + * for all threads in the core, including offline CPUs, to ensure that + * future hotplug operations respect the cpu-to-node associativity + * properly. + */ + for (update = data; update; update = update->next) { + int nid, base, j; + + nid = update->new_nid; + base = cpu_first_thread_sibling(update->cpu); + + for (j = 0; j < threads_per_core; j++) { + update_numa_cpu_lookup_table(base + j, nid); + } + } + + return 0; +} + /* * Update the node maps and sysfs entries for each cpu whose home node * has changed. Returns 1 when the topology has changed, and 0 otherwise. @@ -1513,6 +1569,14 @@ int arch_update_cpu_topology(void) stop_machine(update_cpu_topology, &updates[0], &updated_cpus); + /* + * Update the numa-cpu lookup table with the new mappings, even for + * offline CPUs. It is best to perform this update from the stop- + * machine context. + */ + stop_machine(update_lookup_table, &updates[0], + cpumask_of(raw_smp_processor_id())); + for (ud = &updates[0]; ud; ud = ud->next) { unregister_cpu_under_node(ud->cpu, ud->old_nid); register_cpu_under_node(ud->cpu, ud->new_nid); -- 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 - arch/powerpc/kernel/entry_64.S | 5 ----- arch/powerpc/kernel/mce.c | 13 ++++++++++--- 3 files changed, 10 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/include/asm') 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); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 770d6d65c47b..bbfb0294b354 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -183,11 +183,6 @@ syscall_exit: #ifdef SHOW_SYSCALLS bl .do_show_syscall_exit ld r3,RESULT(r1) -#endif -#ifdef CONFIG_PPC_BOOK3S_64 -BEGIN_FTR_SECTION - bl .machine_check_process_queued_event -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) #endif CURRENT_THREAD_INFO(r12, r1) diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index c0c52ec1fca7..cadef7e64e42 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -26,6 +26,7 @@ #include #include #include +#include #include static DEFINE_PER_CPU(int, mce_nest_count); @@ -35,6 +36,11 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); static DEFINE_PER_CPU(int, mce_queue_count); static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue); +static void machine_check_process_queued_event(struct irq_work *work); +struct irq_work mce_event_process_work = { + .func = machine_check_process_queued_event, +}; + static void mce_set_error_info(struct machine_check_event *mce, struct mce_error_info *mce_err) { @@ -185,17 +191,19 @@ void machine_check_queue_event(void) return; } __get_cpu_var(mce_event_queue[index]) = evt; + + /* Queue irq work to process this event later. */ + irq_work_queue(&mce_event_process_work); } /* * process pending MCE event from the mce event queue. This function will be * called during syscall exit. */ -void machine_check_process_queued_event(void) +static void machine_check_process_queued_event(struct irq_work *work) { int index; - preempt_disable(); /* * For now just print it to console. * TODO: log this error event to FSP or nvram. @@ -206,7 +214,6 @@ void machine_check_process_queued_event(void) &__get_cpu_var(mce_event_queue[index])); __get_cpu_var(mce_queue_count)--; } - preempt_enable(); } void machine_check_print_event_info(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/asm') 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 + arch/powerpc/kernel/entry_64.S | 12 ++- arch/powerpc/kernel/fpu.S | 16 ++++ arch/powerpc/kernel/process.c | 146 ++++++++++++++++++++++++++++++--- arch/powerpc/kernel/signal.c | 3 +- arch/powerpc/kernel/signal_32.c | 21 ++--- arch/powerpc/kernel/signal_64.c | 14 ++-- arch/powerpc/kernel/traps.c | 12 +-- arch/powerpc/kernel/vector.S | 10 +++ 11 files changed, 195 insertions(+), 47 deletions(-) (limited to 'arch/powerpc/include/asm') 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<thread.regs && + MSR_TM_ACTIVE(tsk->thread.regs->msr) && + !test_thread_flag(TIF_RESTORE_TM)) { + tsk->thread.tm_orig_msr = tsk->thread.regs->msr; + set_thread_flag(TIF_RESTORE_TM); + } + + giveup_fpu(tsk); +} + +void giveup_altivec_maybe_transactional(struct task_struct *tsk) +{ + /* + * If we are saving the current thread's registers, and the + * thread is in a transactional state, set the TIF_RESTORE_TM + * bit so that we know to restore the registers before + * returning to userspace. + */ + if (tsk == current && tsk->thread.regs && + MSR_TM_ACTIVE(tsk->thread.regs->msr) && + !test_thread_flag(TIF_RESTORE_TM)) { + tsk->thread.tm_orig_msr = tsk->thread.regs->msr; + set_thread_flag(TIF_RESTORE_TM); + } + + giveup_altivec(tsk); +} + +#else +#define giveup_fpu_maybe_transactional(tsk) giveup_fpu(tsk) +#define giveup_altivec_maybe_transactional(tsk) giveup_altivec(tsk) +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + #ifdef CONFIG_PPC_FPU /* * Make sure the floating-point register state in the @@ -101,13 +143,13 @@ void flush_fp_to_thread(struct task_struct *tsk) */ BUG_ON(tsk != current); #endif - giveup_fpu(tsk); + giveup_fpu_maybe_transactional(tsk); } preempt_enable(); } } EXPORT_SYMBOL_GPL(flush_fp_to_thread); -#endif +#endif /* CONFIG_PPC_FPU */ void enable_kernel_fp(void) { @@ -115,11 +157,11 @@ void enable_kernel_fp(void) #ifdef CONFIG_SMP if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) - giveup_fpu(current); + giveup_fpu_maybe_transactional(current); else giveup_fpu(NULL); /* just enables FP for kernel */ #else - giveup_fpu(last_task_used_math); + giveup_fpu_maybe_transactional(last_task_used_math); #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_fp); @@ -131,11 +173,11 @@ void enable_kernel_altivec(void) #ifdef CONFIG_SMP if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) - giveup_altivec(current); + giveup_altivec_maybe_transactional(current); else giveup_altivec_notask(); #else - giveup_altivec(last_task_used_altivec); + giveup_altivec_maybe_transactional(last_task_used_altivec); #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_altivec); @@ -152,7 +194,7 @@ void flush_altivec_to_thread(struct task_struct *tsk) #ifdef CONFIG_SMP BUG_ON(tsk != current); #endif - giveup_altivec(tsk); + giveup_altivec_maybe_transactional(tsk); } preempt_enable(); } @@ -181,8 +223,8 @@ EXPORT_SYMBOL(enable_kernel_vsx); void giveup_vsx(struct task_struct *tsk) { - giveup_fpu(tsk); - giveup_altivec(tsk); + giveup_fpu_maybe_transactional(tsk); + giveup_altivec_maybe_transactional(tsk); __giveup_vsx(tsk); } @@ -478,7 +520,48 @@ static inline bool hw_brk_match(struct arch_hw_breakpoint *a, return false; return true; } + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void tm_reclaim_thread(struct thread_struct *thr, + struct thread_info *ti, uint8_t cause) +{ + unsigned long msr_diff = 0; + + /* + * If FP/VSX registers have been already saved to the + * thread_struct, move them to the transact_fp array. + * We clear the TIF_RESTORE_TM bit since after the reclaim + * the thread will no longer be transactional. + */ + if (test_ti_thread_flag(ti, TIF_RESTORE_TM)) { + msr_diff = thr->tm_orig_msr & ~thr->regs->msr; + if (msr_diff & MSR_FP) + memcpy(&thr->transact_fp, &thr->fp_state, + sizeof(struct thread_fp_state)); + if (msr_diff & MSR_VEC) + memcpy(&thr->transact_vr, &thr->vr_state, + sizeof(struct thread_vr_state)); + clear_ti_thread_flag(ti, TIF_RESTORE_TM); + msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; + } + + tm_reclaim(thr, thr->regs->msr, cause); + + /* Having done the reclaim, we now have the checkpointed + * FP/VSX values in the registers. These might be valid + * even if we have previously called enable_kernel_fp() or + * flush_fp_to_thread(), so update thr->regs->msr to + * indicate their current validity. + */ + thr->regs->msr |= msr_diff; +} + +void tm_reclaim_current(uint8_t cause) +{ + tm_enable(); + tm_reclaim_thread(¤t->thread, current_thread_info(), cause); +} + static inline void tm_reclaim_task(struct task_struct *tsk) { /* We have to work out if we're switching from/to a task that's in the @@ -501,9 +584,11 @@ static inline void tm_reclaim_task(struct task_struct *tsk) /* Stash the original thread MSR, as giveup_fpu et al will * modify it. We hold onto it to see whether the task used - * FP & vector regs. + * FP & vector regs. If the TIF_RESTORE_TM flag is set, + * tm_orig_msr is already set. */ - thr->tm_orig_msr = thr->regs->msr; + if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM)) + thr->tm_orig_msr = thr->regs->msr; TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " "ccr=%lx, msr=%lx, trap=%lx)\n", @@ -511,7 +596,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk) thr->regs->ccr, thr->regs->msr, thr->regs->trap); - tm_reclaim(thr, thr->regs->msr, TM_CAUSE_RESCHED); + tm_reclaim_thread(thr, task_thread_info(tsk), TM_CAUSE_RESCHED); TM_DEBUG("--- tm_reclaim on pid %d complete\n", tsk->pid); @@ -587,6 +672,43 @@ static inline void __switch_to_tm(struct task_struct *prev) tm_reclaim_task(prev); } } + +/* + * This is called if we are on the way out to userspace and the + * TIF_RESTORE_TM flag is set. It checks if we need to reload + * FP and/or vector state and does so if necessary. + * If userspace is inside a transaction (whether active or + * suspended) and FP/VMX/VSX instructions have ever been enabled + * inside that transaction, then we have to keep them enabled + * and keep the FP/VMX/VSX state loaded while ever the transaction + * continues. The reason is that if we didn't, and subsequently + * got a FP/VMX/VSX unavailable interrupt inside a transaction, + * we don't know whether it's the same transaction, and thus we + * don't know which of the checkpointed state and the transactional + * state to use. + */ +void restore_tm_state(struct pt_regs *regs) +{ + unsigned long msr_diff; + + clear_thread_flag(TIF_RESTORE_TM); + if (!MSR_TM_ACTIVE(regs->msr)) + return; + + msr_diff = current->thread.tm_orig_msr & ~regs->msr; + msr_diff &= MSR_FP | MSR_VEC | MSR_VSX; + if (msr_diff & MSR_FP) { + fp_enable(); + load_fp_state(¤t->thread.fp_state); + regs->msr |= current->thread.fpexc_mode; + } + if (msr_diff & MSR_VEC) { + vec_enable(); + load_vr_state(¤t->thread.vr_state); + } + regs->msr |= msr_diff; +} + #else #define tm_recheckpoint_new_task(new) #define __switch_to_tm(prev) diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 457e97aa2945..8fc4177ed65a 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -203,8 +203,7 @@ unsigned long get_tm_stackpointer(struct pt_regs *regs) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (MSR_TM_ACTIVE(regs->msr)) { - tm_enable(); - tm_reclaim(¤t->thread, regs->msr, TM_CAUSE_SIGNAL); + tm_reclaim_current(TM_CAUSE_SIGNAL); if (MSR_TM_TRANSACTIONAL(regs->msr)) return current->thread.ckpt_regs.gpr[1]; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 68027bfa5f8e..6ce69e6f1fcb 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -519,6 +519,13 @@ static int save_tm_user_regs(struct pt_regs *regs, { unsigned long msr = regs->msr; + /* Remove TM bits from thread's MSR. The MSR in the sigcontext + * just indicates to userland that we were doing a transaction, but we + * don't want to return in transactional state. This also ensures + * that flush_fp_to_thread won't set TIF_RESTORE_TM again. + */ + regs->msr &= ~MSR_TS_MASK; + /* Make sure floating point registers are stored in regs */ flush_fp_to_thread(current); @@ -1056,13 +1063,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, /* enter the signal handler in native-endian mode */ regs->msr &= ~MSR_LE; regs->msr |= (MSR_KERNEL & MSR_LE); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state: - */ - regs->msr &= ~MSR_TS_MASK; -#endif return 1; badframe: @@ -1484,13 +1484,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state: - */ - regs->msr &= ~MSR_TS_MASK; -#endif return 1; badframe: diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 42991045349f..e35bf773df7a 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -192,6 +192,13 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, BUG_ON(!MSR_TM_ACTIVE(regs->msr)); + /* Remove TM bits from thread's MSR. The MSR in the sigcontext + * just indicates to userland that we were doing a transaction, but we + * don't want to return in transactional state. This also ensures + * that flush_fp_to_thread won't set TIF_RESTORE_TM again. + */ + regs->msr &= ~MSR_TS_MASK; + flush_fp_to_thread(current); #ifdef CONFIG_ALTIVEC @@ -749,13 +756,6 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, /* Make sure signal handler doesn't get spurious FP exceptions */ current->thread.fp_state.fpscr = 0; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state: - */ - regs->msr &= ~MSR_TS_MASK; -#endif /* Set up to return from userspace. */ if (vdso64_rt_sigtramp && current->mm->context.vdso_base) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 330841766b09..26e1358ff0bc 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1399,7 +1399,6 @@ void fp_unavailable_tm(struct pt_regs *regs) TM_DEBUG("FP Unavailable trap whilst transactional at 0x%lx, MSR=%lx\n", regs->nip, regs->msr); - tm_enable(); /* We can only have got here if the task started using FP after * beginning the transaction. So, the transactional regs are just a @@ -1408,8 +1407,7 @@ void fp_unavailable_tm(struct pt_regs *regs) * transaction, and probably retry but now with FP enabled. So the * checkpointed FP registers need to be loaded. */ - tm_reclaim(¤t->thread, current->thread.regs->msr, - TM_CAUSE_FAC_UNAV); + tm_reclaim_current(TM_CAUSE_FAC_UNAV); /* Reclaim didn't save out any FPRs to transact_fprs. */ /* Enable FP for the task: */ @@ -1432,9 +1430,7 @@ void altivec_unavailable_tm(struct pt_regs *regs) TM_DEBUG("Vector Unavailable trap whilst transactional at 0x%lx," "MSR=%lx\n", regs->nip, regs->msr); - tm_enable(); - tm_reclaim(¤t->thread, current->thread.regs->msr, - TM_CAUSE_FAC_UNAV); + tm_reclaim_current(TM_CAUSE_FAC_UNAV); regs->msr |= MSR_VEC; tm_recheckpoint(¤t->thread, regs->msr); current->thread.used_vr = 1; @@ -1455,10 +1451,8 @@ void vsx_unavailable_tm(struct pt_regs *regs) "MSR=%lx\n", regs->nip, regs->msr); - tm_enable(); /* This reclaims FP and/or VR regs if they're already enabled */ - tm_reclaim(¤t->thread, current->thread.regs->msr, - TM_CAUSE_FAC_UNAV); + tm_reclaim_current(TM_CAUSE_FAC_UNAV); regs->msr |= MSR_VEC | MSR_FP | current->thread.fpexc_mode | MSR_VSX; diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 0458a9aaba9d..74f8050518d6 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -36,6 +36,16 @@ _GLOBAL(do_load_up_transact_altivec) blr #endif +/* + * Enable use of VMX/Altivec for the caller. + */ +_GLOBAL(vec_enable) + mfmsr r3 + oris r3,r3,MSR_VEC@h + MTMSRD(r3) + isync + blr + /* * Load state from memory into VMX registers including VSCR. * Assumes the caller has enabled VMX in the MSR. -- cgit v1.2.3 From 7e4e7867b1e551b7b8f326da3604c47332972bc6 Mon Sep 17 00:00:00 2001 From: Gavin Shan 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 ++ arch/powerpc/kernel/eeh_driver.c | 150 ++++++++++++++++-------------- arch/powerpc/platforms/powernv/eeh-ioda.c | 39 +++++--- 3 files changed, 112 insertions(+), 87 deletions(-) (limited to 'arch/powerpc/include/asm') 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 diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7db39203a073..baa3b06e6dab 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -630,84 +630,90 @@ static void eeh_handle_special_event(void) { struct eeh_pe *pe, *phb_pe; struct pci_bus *bus; - struct pci_controller *hose, *tmp; + struct pci_controller *hose; unsigned long flags; - int rc = 0; + int rc; - /* - * The return value from next_error() has been classified as follows. - * It might be good to enumerate them. However, next_error() is only - * supported by PowerNV platform for now. So it would be fine to use - * integer directly: - * - * 4 - Dead IOC 3 - Dead PHB - * 2 - Fenced PHB 1 - Frozen PE - * 0 - No error found - * - */ - rc = eeh_ops->next_error(&pe); - if (rc <= 0) - return; - switch (rc) { - case 4: - /* Mark all PHBs in dead state */ - eeh_serialize_lock(&flags); - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe) continue; - - eeh_pe_state_mark(phb_pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + do { + rc = eeh_ops->next_error(&pe); + + switch (rc) { + case EEH_NEXT_ERR_DEAD_IOC: + /* Mark all PHBs in dead state */ + eeh_serialize_lock(&flags); + + /* Purge all events */ + eeh_remove_event(NULL); + + list_for_each_entry(hose, &hose_list, list_node) { + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe) continue; + + eeh_pe_state_mark(phb_pe, + EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + } + + eeh_serialize_unlock(flags); + + break; + case EEH_NEXT_ERR_FROZEN_PE: + case EEH_NEXT_ERR_FENCED_PHB: + case EEH_NEXT_ERR_DEAD_PHB: + /* Mark the PE in fenced state */ + eeh_serialize_lock(&flags); + + /* Purge all events of the PHB */ + eeh_remove_event(pe); + + if (rc == EEH_NEXT_ERR_DEAD_PHB) + eeh_pe_state_mark(pe, + EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + else + eeh_pe_state_mark(pe, + EEH_PE_ISOLATED | EEH_PE_RECOVERING); + + eeh_serialize_unlock(flags); + + break; + case EEH_NEXT_ERR_NONE: + return; + default: + pr_warn("%s: Invalid value %d from next_error()\n", + __func__, rc); + return; } - eeh_serialize_unlock(flags); - - /* Purge all events */ - eeh_remove_event(NULL); - break; - case 3: - case 2: - case 1: - /* Mark the PE in fenced state */ - eeh_serialize_lock(&flags); - if (rc == 3) - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); - else - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_RECOVERING); - eeh_serialize_unlock(flags); - - /* Purge all events of the PHB */ - eeh_remove_event(pe); - break; - default: - pr_err("%s: Invalid value %d from next_error()\n", - __func__, rc); - return; - } - /* - * For fenced PHB and frozen PE, it's handled as normal - * event. We have to remove the affected PHBs for dead - * PHB and IOC - */ - if (rc == 2 || rc == 1) - eeh_handle_normal_event(pe); - else { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe || !(phb_pe->state & EEH_PE_PHB_DEAD)) - continue; - - bus = eeh_pe_bus_get(phb_pe); - /* Notify all devices that they're about to go down. */ - eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - pcibios_remove_pci_devices(bus); + /* + * For fenced PHB and frozen PE, it's handled as normal + * event. We have to remove the affected PHBs for dead + * PHB and IOC + */ + if (rc == EEH_NEXT_ERR_FROZEN_PE || + rc == EEH_NEXT_ERR_FENCED_PHB) { + eeh_handle_normal_event(pe); + } else { + list_for_each_entry(hose, &hose_list, list_node) { + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe || + !(phb_pe->state & EEH_PE_PHB_DEAD)) + continue; + + /* Notify all devices to be down */ + bus = eeh_pe_bus_get(phb_pe); + eeh_pe_dev_traverse(pe, + eeh_report_failure, NULL); + pcibios_remove_pci_devices(bus); + } } - } + + /* + * If we have detected dead IOC, we needn't proceed + * any more since all PHBs would have been removed + */ + if (rc == EEH_NEXT_ERR_DEAD_IOC) + break; + } while (rc != EEH_NEXT_ERR_NONE); } /** diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 007ac4989841..8dd16f4675a2 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -735,12 +735,12 @@ static int ioda_eeh_get_pe(struct pci_controller *hose, */ static int ioda_eeh_next_error(struct eeh_pe **pe) { - struct pci_controller *hose, *tmp; + struct pci_controller *hose; struct pnv_phb *phb; u64 frozen_pe_no; u16 err_type, severity; long rc; - int ret = 1; + int ret = EEH_NEXT_ERR_NONE; /* * While running here, it's safe to purge the event queue. @@ -750,7 +750,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) eeh_remove_event(NULL); opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + list_for_each_entry(hose, &hose_list, list_node) { /* * If the subordinate PCI buses of the PHB has been * removed, we needn't take care of it any more. @@ -789,19 +789,19 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) switch (err_type) { case OPAL_EEH_IOC_ERROR: if (severity == OPAL_EEH_SEV_IOC_DEAD) { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { + list_for_each_entry(hose, &hose_list, + list_node) { phb = hose->private_data; phb->eeh_state |= PNV_EEH_STATE_REMOVED; } pr_err("EEH: dead IOC detected\n"); - ret = 4; - goto out; + ret = EEH_NEXT_ERR_DEAD_IOC; } else if (severity == OPAL_EEH_SEV_INF) { pr_info("EEH: IOC informative error " "detected\n"); ioda_eeh_hub_diag(hose); + ret = EEH_NEXT_ERR_NONE; } break; @@ -813,21 +813,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) pr_err("EEH: dead PHB#%x detected\n", hose->global_number); phb->eeh_state |= PNV_EEH_STATE_REMOVED; - ret = 3; - goto out; + ret = EEH_NEXT_ERR_DEAD_PHB; } else if (severity == OPAL_EEH_SEV_PHB_FENCED) { if (ioda_eeh_get_phb_pe(hose, pe)) break; pr_err("EEH: fenced PHB#%x detected\n", hose->global_number); - ret = 2; - goto out; + ret = EEH_NEXT_ERR_FENCED_PHB; } else if (severity == OPAL_EEH_SEV_INF) { pr_info("EEH: PHB#%x informative error " "detected\n", hose->global_number); ioda_eeh_phb_diag(hose); + ret = EEH_NEXT_ERR_NONE; } break; @@ -837,13 +836,23 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", (*pe)->addr, (*pe)->phb->global_number); - ret = 1; - goto out; + ret = EEH_NEXT_ERR_FROZEN_PE; + break; + default: + pr_warn("%s: Unexpected error type %d\n", + __func__, err_type); } + + /* + * If we have no errors on the specific PHB or only + * informative error there, we continue poking it. + * Otherwise, we need actions to be taken by upper + * layer. + */ + if (ret > EEH_NEXT_ERR_INF) + break; } - ret = 0; -out: return ret; } -- 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 ++ arch/powerpc/platforms/powernv/opal-wrappers.S | 1 + arch/powerpc/platforms/powernv/opal.c | 16 ++++++++++++++++ arch/powerpc/platforms/powernv/setup.c | 6 ++++-- 4 files changed, 23 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') 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); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 719aa5c325c6..3e8829c40fbb 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -128,3 +128,4 @@ OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE); OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE); OPAL_CALL(opal_get_msg, OPAL_GET_MSG); OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION); +OPAL_CALL(opal_sync_host_reboot, OPAL_SYNC_HOST_REBOOT); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 7a184a0ff183..65499adaecff 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -482,10 +483,25 @@ subsys_initcall(opal_init); void opal_shutdown(void) { unsigned int i; + long rc = OPAL_BUSY; + /* First free interrupts, which will also mask them */ for (i = 0; i < opal_irq_count; i++) { if (opal_irqs[i]) free_irq(opal_irqs[i], NULL); opal_irqs[i] = 0; } + + /* + * Then sync with OPAL which ensure anything that can + * potentially write to our memory has completed such + * as an ongoing dump retrieval + */ + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_sync_host_reboot(); + if (rc == OPAL_BUSY) + opal_poll_events(NULL); + else + mdelay(10); + } } diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 19884b2a51b4..a932feb2901c 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -145,8 +145,10 @@ static void pnv_shutdown(void) /* Let the PCI code clear up IODA tables */ pnv_pci_shutdown(); - /* And unregister all OPAL interrupts so they don't fire - * up while we kexec + /* + * Stop OPAL activity: Unregister all OPAL interrupts so they + * don't fire up while we kexec and make sure all potentially + * DMA'ing ops are complete (such as dump retrieval). */ opal_shutdown(); } -- 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/Kconfig | 1 + arch/powerpc/include/asm/cmpxchg.h | 1 + arch/powerpc/include/asm/spinlock.h | 5 +++++ 3 files changed, 7 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fa395179ddd6..6ca5d5cabeb1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -139,6 +139,7 @@ config PPC select OLD_SIGACTION if PPC32 select HAVE_DEBUG_STACKOVERFLOW select HAVE_IRQ_EXIT_ON_IRQ_STACK + select ARCH_USE_CMPXCHG_LOCKREF if PPC64 config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN 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/asm') 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