diff options
Diffstat (limited to 'arch/powerpc/kernel')
39 files changed, 688 insertions, 455 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index be257b0aae36..36c30f31ec93 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -55,7 +55,9 @@ obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_IBMEBUS) += ibmebus.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +ifeq ($(CONFIG_PPC32),y) obj-$(CONFIG_E500) += idle_e500.o +endif obj-$(CONFIG_6xx) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o @@ -67,7 +69,7 @@ endif obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o obj-$(CONFIG_MODULES) += module.o module_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_44x) += cpu_setup_44x.o -obj-$(CONFIG_FSL_BOOKE) += cpu_setup_fsl_booke.o dbell.o +obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o dbell.o obj-$(CONFIG_PPC_BOOK3E_64) += dbell.o extra-y := head_$(CONFIG_WORD_SIZE).o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index b876e989220b..8184ee97e484 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -889,7 +889,7 @@ int fix_alignment(struct pt_regs *regs) #ifdef CONFIG_PPC_FPU preempt_disable(); enable_kernel_fp(); - cvt_df(&data.dd, (float *)&data.v[4], ¤t->thread); + cvt_df(&data.dd, (float *)&data.v[4]); preempt_enable(); #else return 0; @@ -933,7 +933,7 @@ int fix_alignment(struct pt_regs *regs) #ifdef CONFIG_PPC_FPU preempt_disable(); enable_kernel_fp(); - cvt_fd((float *)&data.v[4], &data.dd, ¤t->thread); + cvt_fd((float *)&data.v[4], &data.dd); preempt_enable(); #else return 0; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 7f0d6fcc28a3..bd0df2e6aa8f 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -61,7 +61,7 @@ #endif #endif -#if defined(CONFIG_FSL_BOOKE) +#if defined(CONFIG_PPC_FSL_BOOK3E) #include "../mm/mmu_decl.h" #endif @@ -181,17 +181,19 @@ int main(void) offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid)); DEFINE(SLBSHADOW_STACKESID, offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid)); + DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area)); DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0)); DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1)); DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int)); DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int)); - DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area)); + DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx)); + DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx)); #endif /* CONFIG_PPC_STD_MMU_64 */ DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); - DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr)); - DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr)); + DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime)); + DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user)); DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); @@ -485,7 +487,7 @@ int main(void) DEFINE(PGD_T_LOG2, PGD_T_LOG2); DEFINE(PTE_T_LOG2, PTE_T_LOG2); #endif -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_FSL_BOOK3E DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam)); DEFINE(TLBCAM_MAS0, offsetof(struct tlbcam, MAS0)); DEFINE(TLBCAM_MAS1, offsetof(struct tlbcam, MAS1)); diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S index 7d606f89a839..e32b4a9a2c22 100644 --- a/arch/powerpc/kernel/cpu_setup_44x.S +++ b/arch/powerpc/kernel/cpu_setup_44x.S @@ -35,6 +35,7 @@ _GLOBAL(__setup_cpu_440grx) _GLOBAL(__setup_cpu_460ex) _GLOBAL(__setup_cpu_460gt) _GLOBAL(__setup_cpu_460sx) +_GLOBAL(__setup_cpu_apm821xx) mflr r4 bl __init_fpu_44x bl __fixup_440A_mcheck diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 0adb50ad8031..894e64fa481e 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -51,6 +51,7 @@ _GLOBAL(__e500_dcache_setup) isync blr +#ifdef CONFIG_PPC32 _GLOBAL(__setup_cpu_e200) /* enable dedicated debug exception handling resources (Debug APU) */ mfspr r3,SPRN_HID0 @@ -72,3 +73,17 @@ _GLOBAL(__setup_cpu_e500mc) bl __setup_e500mc_ivors mtlr r4 blr +#endif +/* Right now, restore and setup are the same thing */ +_GLOBAL(__restore_cpu_e5500) +_GLOBAL(__setup_cpu_e5500) + mflr r4 + bl __e500_icache_setup + bl __e500_dcache_setup +#ifdef CONFIG_PPC_BOOK3E_64 + bl .__setup_base_ivors +#else + bl __setup_e500mc_ivors +#endif + mtlr r4 + blr diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 1f9123f412ec..96a908f1cd87 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -48,6 +48,7 @@ extern void __setup_cpu_440x5(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_460ex(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_460gt(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec); +extern void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec); extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec); @@ -66,6 +67,10 @@ extern void __restore_cpu_ppc970(void); extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power7(void); #endif /* CONFIG_PPC64 */ +#if defined(CONFIG_E500) +extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); +extern void __restore_cpu_e5500(void); +#endif /* CONFIG_E500 */ /* This table only contains "desktop" CPUs, it need to be filled with embedded * ones as well... @@ -1805,6 +1810,20 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_440A, .platform = "ppc440", }, + { /* 464 in APM821xx */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x12C41C80, + .cpu_name = "APM821XX", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_apm821xx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, { /* 476 core */ .pvr_mask = 0xffff0000, .pvr_value = 0x11a50000, @@ -1891,7 +1910,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .platform = "ppc5554", } #endif /* CONFIG_E200 */ +#endif /* CONFIG_PPC32 */ #ifdef CONFIG_E500 +#ifdef CONFIG_PPC32 { /* e500 */ .pvr_mask = 0xffff0000, .pvr_value = 0x80200000, @@ -1946,6 +1967,26 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_e500mc, .platform = "ppce500mc", }, +#endif /* CONFIG_PPC32 */ + { /* e5500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80240000, + .cpu_name = "e5500", + .cpu_features = CPU_FTRS_E500MC, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | + MMU_FTR_USE_TLBILX, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 4, + .oprofile_cpu_type = "ppc/e500mc", + .oprofile_type = PPC_OPROFILE_FSL_EMB, + .cpu_setup = __setup_cpu_e5500, + .cpu_restore = __restore_cpu_e5500, + .machine_check = machine_check_e500mc, + .platform = "ppce5500", + }, +#ifdef CONFIG_PPC32 { /* default match */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, @@ -1960,8 +2001,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_e500, .platform = "powerpc", } -#endif /* CONFIG_E500 */ #endif /* CONFIG_PPC32 */ +#endif /* CONFIG_E500 */ #ifdef CONFIG_PPC_BOOK3E_64 { /* This is a default entry to get going, to be replaced by diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 4457382f8667..832c8c4db254 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -414,18 +414,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) crash_kexec_wait_realmode(crashing_cpu); #endif - for_each_irq(i) { - struct irq_desc *desc = irq_to_desc(i); - - if (!desc || !desc->chip || !desc->chip->eoi) - continue; - - if (desc->status & IRQ_INPROGRESS) - desc->chip->eoi(i); - - if (!(desc->status & IRQ_DISABLED)) - desc->chip->shutdown(i); - } + machine_kexec_mask_interrupts(); /* * Call registered shutdown routines savely. Swap out diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 37771a518119..6e54a0fd31aa 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -74,16 +74,17 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) { struct iommu_table *tbl = get_iommu_table_base(dev); - if (!tbl || tbl->it_offset > mask) { - printk(KERN_INFO - "Warning: IOMMU offset too big for device mask\n"); - if (tbl) - printk(KERN_INFO - "mask: 0x%08llx, table offset: 0x%08lx\n", - mask, tbl->it_offset); - else - printk(KERN_INFO "mask: 0x%08llx, table unavailable\n", - mask); + if (!tbl) { + dev_info(dev, "Warning: IOMMU dma not supported: mask 0x%08llx" + ", table unavailable\n", mask); + return 0; + } + + if ((tbl->it_offset + tbl->it_size) > (mask >> IOMMU_PAGE_SHIFT)) { + dev_info(dev, "Warning: IOMMU window too big for device mask\n"); + dev_info(dev, "mask: 0x%08llx, table end: 0x%08lx\n", + mask, (tbl->it_offset + tbl->it_size) << + IOMMU_PAGE_SHIFT); return 0; } else return 1; diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 84d6367ec003..cf02cad62d9a 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -12,6 +12,7 @@ #include <linux/memblock.h> #include <asm/bug.h> #include <asm/abs_addr.h> +#include <asm/machdep.h> /* * Generic direct DMA implementation @@ -89,7 +90,7 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask) /* Could be improved so platforms can set the limit in case * they have limited DMA windows */ - return mask >= (memblock_end_of_DRAM() - 1); + return mask >= get_dma_offset(dev) + (memblock_end_of_DRAM() - 1); #else return 1; #endif @@ -154,6 +155,23 @@ EXPORT_SYMBOL(dma_direct_ops); #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) +int dma_set_mask(struct device *dev, u64 dma_mask) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + if (ppc_md.dma_set_mask) + return ppc_md.dma_set_mask(dev, dma_mask); + if (unlikely(dma_ops == NULL)) + return -EIO; + if (dma_ops->set_dma_mask != NULL) + return dma_ops->set_dma_mask(dev, dma_mask); + if (!dev->dma_mask || !dma_supported(dev, dma_mask)) + return -EIO; + *dev->dma_mask = dma_mask; + return 0; +} +EXPORT_SYMBOL(dma_set_mask); + static int __init dma_init(void) { dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 42e9d908914a..d82878c4daa6 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -97,6 +97,24 @@ system_call_common: addi r9,r1,STACK_FRAME_OVERHEAD ld r11,exception_marker@toc(r2) std r11,-16(r9) /* "regshere" marker */ +#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR) +BEGIN_FW_FTR_SECTION + beq 33f + /* if from user, see if there are any DTL entries to process */ + ld r10,PACALPPACAPTR(r13) /* get ptr to VPA */ + ld r11,PACA_DTL_RIDX(r13) /* get log read index */ + ld r10,LPPACA_DTLIDX(r10) /* get log write index */ + cmpd cr1,r11,r10 + beq+ cr1,33f + bl .accumulate_stolen_time + REST_GPR(0,r1) + REST_4GPRS(3,r1) + REST_2GPRS(7,r1) + addi r9,r1,STACK_FRAME_OVERHEAD +33: +END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) +#endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */ + #ifdef CONFIG_TRACE_IRQFLAGS bl .trace_hardirqs_on REST_GPR(0,r1) @@ -202,7 +220,9 @@ syscall_exit: bge- syscall_error syscall_error_cont: ld r7,_NIP(r1) +BEGIN_FTR_SECTION stdcx. r0,0,r1 /* to clear the reservation */ +END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) andi. r6,r8,MSR_PR ld r4,_LINK(r1) /* @@ -419,6 +439,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) sync #endif /* CONFIG_SMP */ + /* + * If we optimise away the clear of the reservation in system + * calls because we know the CPU tracks the address of the + * reservation, then we need to clear it here to cover the + * case that the kernel context switch path has no larx + * instructions. + */ +BEGIN_FTR_SECTION + ldarx r6,0,r1 +END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS) + addi r6,r4,-THREAD /* Convert THREAD to 'current' */ std r6,PACACURRENT(r13) /* Set new 'current' */ @@ -576,7 +607,16 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) andi. r0,r3,MSR_RI beq- unrecov_restore + /* + * Clear the reservation. If we know the CPU tracks the address of + * the reservation then we can potentially save some cycles and use + * a larx. On POWER6 and POWER7 this is significantly faster. + */ +BEGIN_FTR_SECTION stdcx. r0,0,r1 /* to clear the reservation */ +FTR_SECTION_ELSE + ldarx r4,0,r1 +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) /* * Clear RI before restoring r13. If we are returning to diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 1667a078b3e6..9f8b01d6466f 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -824,12 +824,12 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES) /* * hash_page couldn't handle it, set soft interrupt enable back - * to what it was before the trap. Note that .raw_local_irq_restore + * to what it was before the trap. Note that .arch_local_irq_restore * handles any interrupts pending at this point. */ ld r3,SOFTE(r1) TRACE_AND_RESTORE_IRQ_PARTIAL(r3, 11f) - bl .raw_local_irq_restore + bl .arch_local_irq_restore b 11f /* We have a data breakpoint exception - handle it */ diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index fc8f5b14019c..e86c040ae585 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -163,24 +163,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) /* * These are used in the alignment trap handler when emulating * single-precision loads and stores. - * We restore and save the fpscr so the task gets the same result - * and exceptions as if the cpu had performed the load or store. */ _GLOBAL(cvt_fd) - lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ - MTFSF_L(0) lfs 0,0(r3) stfd 0,0(r4) - mffs 0 - stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */ blr _GLOBAL(cvt_df) - lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ - MTFSF_L(0) lfd 0,0(r3) stfs 0,0(r4) - mffs 0 - stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */ blr diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index a90625f9b485..8278e8bad5a0 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -923,11 +923,7 @@ initial_mmu: mtspr SPRN_PID,r0 sync - /* Configure and load two entries into TLB slots 62 and 63. - * In case we are pinning TLBs, these are reserved in by the - * other TLB functions. If not reserving, then it doesn't - * matter where they are loaded. - */ + /* Configure and load one entry into TLB slots 63 */ clrrwi r4,r4,10 /* Mask off the real page number */ ori r4,r4,(TLB_WR | TLB_EX) /* Set the write and execute bits */ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 4faeba247854..529b817f473b 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -152,8 +152,11 @@ _ENTRY(__early_start) /* Check to see if we're the second processor, and jump * to the secondary_start code if so */ - mfspr r24,SPRN_PIR - cmpwi r24,0 + lis r24, boot_cpuid@h + ori r24, r24, boot_cpuid@l + lwz r24, 0(r24) + cmpwi r24, -1 + mfspr r24,SPRN_PIR bne __secondary_start #endif @@ -175,6 +178,9 @@ _ENTRY(__early_start) li r0,0 stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) + rlwinm r22,r1,0,0,31-THREAD_SHIFT /* current thread_info */ + stw r24, TI_CPU(r22) + bl early_init #ifdef CONFIG_RELOCATABLE diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 4a65386995d7..ce557f6f00fc 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -116,7 +116,7 @@ static inline notrace void set_soft_enabled(unsigned long enable) : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled))); } -notrace void raw_local_irq_restore(unsigned long en) +notrace void arch_local_irq_restore(unsigned long en) { /* * get_paca()->soft_enabled = en; @@ -192,7 +192,7 @@ notrace void raw_local_irq_restore(unsigned long en) __hard_irq_enable(); } -EXPORT_SYMBOL(raw_local_irq_restore); +EXPORT_SYMBOL(arch_local_irq_restore); #endif /* CONFIG_PPC64 */ static int show_other_interrupts(struct seq_file *p, int prec) @@ -587,8 +587,10 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, * this will be fixed once slab is made available early * instead of the current cruft */ - if (mem_init_done) + if (mem_init_done) { + of_node_put(host->of_node); kfree(host); + } return NULL; } irq_map[0].host = host; @@ -1143,7 +1145,7 @@ static int virq_debug_show(struct seq_file *m, void *private) unsigned long flags; struct irq_desc *desc; const char *p; - char none[] = "none"; + static const char none[] = "none"; int i; seq_printf(m, "%-5s %-7s %-15s %s\n", "virq", "hwirq", diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 50362b6ef6e9..16468362ad57 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -56,7 +56,7 @@ static unsigned long get_purr(void) for_each_possible_cpu(cpu) { if (firmware_has_feature(FW_FEATURE_ISERIES)) - sum_purr += lppaca[cpu].emulated_time_base; + sum_purr += lppaca_of(cpu).emulated_time_base; else { struct cpu_usage *cu; @@ -263,7 +263,7 @@ static void parse_ppp_data(struct seq_file *m) ppp_data.active_system_procs); /* pool related entries are apropriate for shared configs */ - if (lppaca[0].shared_proc) { + if (lppaca_of(0).shared_proc) { unsigned long pool_idle_time, pool_procs; seq_printf(m, "pool=%d\n", ppp_data.pool_num); @@ -460,8 +460,8 @@ static void pseries_cmo_data(struct seq_file *m) return; for_each_possible_cpu(cpu) { - cmo_faults += lppaca[cpu].cmo_faults; - cmo_fault_time += lppaca[cpu].cmo_fault_time; + cmo_faults += lppaca_of(cpu).cmo_faults; + cmo_fault_time += lppaca_of(cpu).cmo_fault_time; } seq_printf(m, "cmo_faults=%lu\n", cmo_faults); @@ -479,8 +479,8 @@ static void splpar_dispatch_data(struct seq_file *m) unsigned long dispatch_dispersions = 0; for_each_possible_cpu(cpu) { - dispatches += lppaca[cpu].yield_count; - dispatch_dispersions += lppaca[cpu].dispersion_count; + dispatches += lppaca_of(cpu).yield_count; + dispatch_dispersions += lppaca_of(cpu).dispersion_count; } seq_printf(m, "dispatches=%lu\n", dispatches); @@ -545,7 +545,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) seq_printf(m, "partition_potential_processors=%d\n", partition_potential_processors); - seq_printf(m, "shared_processor_mode=%d\n", lppaca[0].shared_proc); + seq_printf(m, "shared_processor_mode=%d\n", lppaca_of(0).shared_proc); seq_printf(m, "slb_size=%d\n", mmu_slb_size); @@ -780,6 +780,7 @@ static const struct file_operations lparcfg_fops = { .write = lparcfg_write, .open = lparcfg_open, .release = single_release, + .llseek = seq_lseek, }; static int __init lparcfg_init(void) diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index dd6c141f1662..df7e20c191cd 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -14,10 +14,34 @@ #include <linux/threads.h> #include <linux/memblock.h> #include <linux/of.h> +#include <linux/irq.h> + #include <asm/machdep.h> #include <asm/prom.h> #include <asm/sections.h> +void machine_kexec_mask_interrupts(void) { + unsigned int i; + + for_each_irq(i) { + struct irq_desc *desc = irq_to_desc(i); + + if (!desc || !desc->chip) + continue; + + if (desc->chip->eoi && + desc->status & IRQ_INPROGRESS) + desc->chip->eoi(i); + + if (desc->chip->mask) + desc->chip->mask(i); + + if (desc->chip->disable && + !(desc->status & IRQ_DISABLED)) + desc->chip->disable(i); + } +} + void machine_crash_shutdown(struct pt_regs *regs) { if (ppc_md.machine_crash_shutdown) diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kernel/machine_kexec_32.c index ae63a964b858..e63f2e7d2efb 100644 --- a/arch/powerpc/kernel/machine_kexec_32.c +++ b/arch/powerpc/kernel/machine_kexec_32.c @@ -39,6 +39,10 @@ void default_machine_kexec(struct kimage *image) /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + /* mask each interrupt so we are in a more sane state for the + * kexec kernel */ + machine_kexec_mask_interrupts(); + page_list = image->head; /* we need both effective and real address here */ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index d0a26f1770fe..ebf9846f3c3b 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -27,6 +27,20 @@ extern unsigned long __toc_start; #ifdef CONFIG_PPC_BOOK3S /* + * We only have to have statically allocated lppaca structs on + * legacy iSeries, which supports at most 64 cpus. + */ +#ifdef CONFIG_PPC_ISERIES +#if NR_CPUS < 64 +#define NR_LPPACAS NR_CPUS +#else +#define NR_LPPACAS 64 +#endif +#else /* not iSeries */ +#define NR_LPPACAS 1 +#endif + +/* * The structure which the hypervisor knows about - this structure * should not cross a page boundary. The vpa_init/register_vpa call * is now known to fail if the lppaca structure crosses a page @@ -36,7 +50,7 @@ extern unsigned long __toc_start; * will suffice to ensure that it doesn't cross a page boundary. */ struct lppaca lppaca[] = { - [0 ... (NR_CPUS-1)] = { + [0 ... (NR_LPPACAS-1)] = { .desc = 0xd397d781, /* "LpPa" */ .size = sizeof(struct lppaca), .dyn_proc_status = 2, @@ -49,6 +63,54 @@ struct lppaca lppaca[] = { }, }; +static struct lppaca *extra_lppacas; +static long __initdata lppaca_size; + +static void allocate_lppacas(int nr_cpus, unsigned long limit) +{ + if (nr_cpus <= NR_LPPACAS) + return; + + lppaca_size = PAGE_ALIGN(sizeof(struct lppaca) * + (nr_cpus - NR_LPPACAS)); + extra_lppacas = __va(memblock_alloc_base(lppaca_size, + PAGE_SIZE, limit)); +} + +static struct lppaca *new_lppaca(int cpu) +{ + struct lppaca *lp; + + if (cpu < NR_LPPACAS) + return &lppaca[cpu]; + + lp = extra_lppacas + (cpu - NR_LPPACAS); + *lp = lppaca[0]; + + return lp; +} + +static void free_lppacas(void) +{ + long new_size = 0, nr; + + if (!lppaca_size) + return; + nr = num_possible_cpus() - NR_LPPACAS; + if (nr > 0) + new_size = PAGE_ALIGN(nr * sizeof(struct lppaca)); + if (new_size >= lppaca_size) + return; + + memblock_free(__pa(extra_lppacas) + new_size, lppaca_size - new_size); + lppaca_size = new_size; +} + +#else + +static inline void allocate_lppacas(int nr_cpus, unsigned long limit) { } +static inline void free_lppacas(void) { } + #endif /* CONFIG_PPC_BOOK3S */ #ifdef CONFIG_PPC_STD_MMU_64 @@ -88,7 +150,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL; #ifdef CONFIG_PPC_BOOK3S - new_paca->lppaca_ptr = &lppaca[cpu]; + new_paca->lppaca_ptr = new_lppaca(cpu); #else new_paca->kernel_pgd = swapper_pg_dir; #endif @@ -127,7 +189,7 @@ void __init allocate_pacas(void) * the first segment. On iSeries they must be within the area mapped * by the HV, which is HvPagesToMap * HVPAGESIZE bytes. */ - limit = min(0x10000000ULL, memblock.rmo_size); + limit = min(0x10000000ULL, ppc64_rma_size); if (firmware_has_feature(FW_FEATURE_ISERIES)) limit = min(limit, HvPagesToMap * HVPAGESIZE); @@ -144,6 +206,8 @@ void __init allocate_pacas(void) printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n", paca_size, nr_cpus, paca); + allocate_lppacas(nr_cpus, limit); + /* Can't use for_each_*_cpu, as they aren't functional yet */ for (cpu = 0; cpu < nr_cpus; cpu++) initialise_paca(&paca[cpu], cpu); @@ -164,4 +228,6 @@ void __init free_unused_pacas(void) paca_size - new_size); paca_size = new_size; + + free_lppacas(); } diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 9021c4ad4bbd..10a44e68ef11 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1090,8 +1090,6 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) bus->number, bus->self ? pci_name(bus->self) : "PHB"); list_for_each_entry(dev, &bus->devices, bus_list) { - struct dev_archdata *sd = &dev->dev.archdata; - /* Cardbus can call us to add new devices to a bus, so ignore * those who are already fully discovered */ @@ -1107,7 +1105,7 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); /* Hook up default DMA ops */ - sd->dma_ops = pci_dma_ops; + set_dma_ops(&dev->dev, pci_dma_ops); set_dma_offset(&dev->dev, PCI_DRAM_OFFSET); /* Additional platform DMA/iommu setup */ diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c index 95ad9dad298e..d05ae4204bbf 100644 --- a/arch/powerpc/kernel/perf_callchain.c +++ b/arch/powerpc/kernel/perf_callchain.c @@ -23,18 +23,6 @@ #include "ppc32.h" #endif -/* - * Store another value in a callchain_entry. - */ -static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip) -{ - unsigned int nr = entry->nr; - - if (nr < PERF_MAX_STACK_DEPTH) { - entry->ip[nr] = ip; - entry->nr = nr + 1; - } -} /* * Is sp valid as the address of the next kernel stack frame after prev_sp? @@ -58,8 +46,8 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp) return 0; } -static void perf_callchain_kernel(struct pt_regs *regs, - struct perf_callchain_entry *entry) +void +perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) { unsigned long sp, next_sp; unsigned long next_ip; @@ -69,8 +57,7 @@ static void perf_callchain_kernel(struct pt_regs *regs, lr = regs->link; sp = regs->gpr[1]; - callchain_store(entry, PERF_CONTEXT_KERNEL); - callchain_store(entry, regs->nip); + perf_callchain_store(entry, regs->nip); if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD)) return; @@ -89,7 +76,7 @@ static void perf_callchain_kernel(struct pt_regs *regs, next_ip = regs->nip; lr = regs->link; level = 0; - callchain_store(entry, PERF_CONTEXT_KERNEL); + perf_callchain_store(entry, PERF_CONTEXT_KERNEL); } else { if (level == 0) @@ -111,7 +98,7 @@ static void perf_callchain_kernel(struct pt_regs *regs, ++level; } - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); if (!valid_next_sp(next_sp, sp)) return; sp = next_sp; @@ -233,8 +220,8 @@ static int sane_signal_64_frame(unsigned long sp) puc == (unsigned long) &sf->uc; } -static void perf_callchain_user_64(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static void perf_callchain_user_64(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned long sp, next_sp; unsigned long next_ip; @@ -246,8 +233,7 @@ static void perf_callchain_user_64(struct pt_regs *regs, next_ip = regs->nip; lr = regs->link; sp = regs->gpr[1]; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); for (;;) { fp = (unsigned long __user *) sp; @@ -276,14 +262,14 @@ static void perf_callchain_user_64(struct pt_regs *regs, read_user_stack_64(&uregs[PT_R1], &sp)) return; level = 0; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_store(entry, next_ip); continue; } if (level == 0) next_ip = lr; - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); ++level; sp = next_sp; } @@ -315,8 +301,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) return __get_user_inatomic(*ret, ptr); } -static inline void perf_callchain_user_64(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static inline void perf_callchain_user_64(struct perf_callchain_entry *entry, + struct pt_regs *regs) { } @@ -435,8 +421,8 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp, return mctx->mc_gregs; } -static void perf_callchain_user_32(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static void perf_callchain_user_32(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned int sp, next_sp; unsigned int next_ip; @@ -447,8 +433,7 @@ static void perf_callchain_user_32(struct pt_regs *regs, next_ip = regs->nip; lr = regs->link; sp = regs->gpr[1]; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); while (entry->nr < PERF_MAX_STACK_DEPTH) { fp = (unsigned int __user *) (unsigned long) sp; @@ -470,45 +455,24 @@ static void perf_callchain_user_32(struct pt_regs *regs, read_user_stack_32(&uregs[PT_R1], &sp)) return; level = 0; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_store(entry, next_ip); continue; } if (level == 0) next_ip = lr; - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); ++level; sp = next_sp; } } -/* - * Since we can't get PMU interrupts inside a PMU interrupt handler, - * we don't need separate irq and nmi entries here. - */ -static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain); - -struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) +void +perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { - struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain); - - entry->nr = 0; - - if (!user_mode(regs)) { - perf_callchain_kernel(regs, entry); - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; - } - - if (regs) { - if (current_is_64bit()) - perf_callchain_user_64(regs, entry); - else - perf_callchain_user_32(regs, entry); - } - - return entry; + if (current_is_64bit()) + perf_callchain_user_64(entry, regs); + else + perf_callchain_user_32(entry, regs); } diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index d301a30445e0..3129c855933c 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -402,6 +402,9 @@ static void power_pmu_read(struct perf_event *event) { s64 val, delta, prev; + if (event->hw.state & PERF_HES_STOPPED) + return; + if (!event->hw.idx) return; /* @@ -517,7 +520,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0) * Disable all events to prevent PMU interrupts and to allow * events to be added or removed. */ -void hw_perf_disable(void) +static void power_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -565,7 +568,7 @@ void hw_perf_disable(void) * If we were previously disabled and events were added, then * put the new config on the PMU. */ -void hw_perf_enable(void) +static void power_pmu_enable(struct pmu *pmu) { struct perf_event *event; struct cpu_hw_events *cpuhw; @@ -672,6 +675,8 @@ void hw_perf_enable(void) } local64_set(&event->hw.prev_count, val); event->hw.idx = idx; + if (event->hw.state & PERF_HES_STOPPED) + val = 0; write_pmc(idx, val); perf_event_update_userpage(event); } @@ -727,7 +732,7 @@ static int collect_events(struct perf_event *group, int max_count, * re-enable the PMU in order to get hw_perf_enable to do the * actual work of reconfiguring the PMU. */ -static int power_pmu_enable(struct perf_event *event) +static int power_pmu_add(struct perf_event *event, int ef_flags) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -735,7 +740,7 @@ static int power_pmu_enable(struct perf_event *event) int ret = -EAGAIN; local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); /* * Add the event to the list (if there is room) @@ -749,6 +754,9 @@ static int power_pmu_enable(struct perf_event *event) cpuhw->events[n0] = event->hw.config; cpuhw->flags[n0] = event->hw.event_base; + if (!(ef_flags & PERF_EF_START)) + event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be peformed @@ -769,7 +777,7 @@ nocheck: ret = 0; out: - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } @@ -777,14 +785,14 @@ nocheck: /* * Remove a event from the PMU. */ -static void power_pmu_disable(struct perf_event *event) +static void power_pmu_del(struct perf_event *event, int ef_flags) { struct cpu_hw_events *cpuhw; long i; unsigned long flags; local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); power_pmu_read(event); @@ -821,34 +829,60 @@ static void power_pmu_disable(struct perf_event *event) cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); } - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } /* - * Re-enable interrupts on a event after they were throttled - * because they were coming too fast. + * POWER-PMU does not support disabling individual counters, hence + * program their cycle counter to their max value and ignore the interrupts. */ -static void power_pmu_unthrottle(struct perf_event *event) + +static void power_pmu_start(struct perf_event *event, int ef_flags) +{ + unsigned long flags; + s64 left; + + if (!event->hw.idx || !event->hw.sample_period) + return; + + if (!(event->hw.state & PERF_HES_STOPPED)) + return; + + if (ef_flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + + local_irq_save(flags); + perf_pmu_disable(event->pmu); + + event->hw.state = 0; + left = local64_read(&event->hw.period_left); + write_pmc(event->hw.idx, left); + + perf_event_update_userpage(event); + perf_pmu_enable(event->pmu); + local_irq_restore(flags); +} + +static void power_pmu_stop(struct perf_event *event, int ef_flags) { - s64 val, left; unsigned long flags; if (!event->hw.idx || !event->hw.sample_period) return; + + if (event->hw.state & PERF_HES_STOPPED) + return; + local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); + power_pmu_read(event); - left = event->hw.sample_period; - event->hw.last_period = left; - val = 0; - if (left < 0x80000000L) - val = 0x80000000L - left; - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); + event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + write_pmc(event->hw.idx, 0); + perf_event_update_userpage(event); - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -857,10 +891,11 @@ static void power_pmu_unthrottle(struct perf_event *event) * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time */ -void power_pmu_start_txn(const struct pmu *pmu) +void power_pmu_start_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + perf_pmu_disable(pmu); cpuhw->group_flag |= PERF_EVENT_TXN; cpuhw->n_txn_start = cpuhw->n_events; } @@ -870,11 +905,12 @@ void power_pmu_start_txn(const struct pmu *pmu) * Clear the flag and pmu::enable() will perform the * schedulability test. */ -void power_pmu_cancel_txn(const struct pmu *pmu) +void power_pmu_cancel_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); cpuhw->group_flag &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); } /* @@ -882,7 +918,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu) * Perform the group schedulability test as a whole * Return 0 if success */ -int power_pmu_commit_txn(const struct pmu *pmu) +int power_pmu_commit_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw; long i, n; @@ -901,19 +937,10 @@ int power_pmu_commit_txn(const struct pmu *pmu) cpuhw->event[i]->hw.config = cpuhw->events[i]; cpuhw->group_flag &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); return 0; } -struct pmu power_pmu = { - .enable = power_pmu_enable, - .disable = power_pmu_disable, - .read = power_pmu_read, - .unthrottle = power_pmu_unthrottle, - .start_txn = power_pmu_start_txn, - .cancel_txn = power_pmu_cancel_txn, - .commit_txn = power_pmu_commit_txn, -}; - /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. @@ -1014,7 +1041,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp) return 0; } -const struct pmu *hw_perf_event_init(struct perf_event *event) +static int power_pmu_event_init(struct perf_event *event) { u64 ev; unsigned long flags; @@ -1026,25 +1053,27 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) struct cpu_hw_events *cpuhw; if (!ppmu) - return ERR_PTR(-ENXIO); + return -ENOENT; + switch (event->attr.type) { case PERF_TYPE_HARDWARE: ev = event->attr.config; if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; ev = ppmu->generic_events[ev]; break; case PERF_TYPE_HW_CACHE: err = hw_perf_cache_event(event->attr.config, &ev); if (err) - return ERR_PTR(err); + return err; break; case PERF_TYPE_RAW: ev = event->attr.config; break; default: - return ERR_PTR(-EINVAL); + return -ENOENT; } + event->hw.config_base = ev; event->hw.idx = 0; @@ -1063,7 +1092,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) * XXX we should check if the task is an idle task. */ flags = 0; - if (event->ctx->task) + if (event->attach_state & PERF_ATTACH_TASK) flags |= PPMU_ONLY_COUNT_RUN; /* @@ -1081,7 +1110,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) */ ev = normal_pmc_alternative(ev, flags); if (!ev) - return ERR_PTR(-EINVAL); + return -EINVAL; } } @@ -1095,19 +1124,19 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) n = collect_events(event->group_leader, ppmu->n_counter - 1, ctrs, events, cflags); if (n < 0) - return ERR_PTR(-EINVAL); + return -EINVAL; } events[n] = ev; ctrs[n] = event; cflags[n] = flags; if (check_excludes(ctrs, cflags, n, 1)) - return ERR_PTR(-EINVAL); + return -EINVAL; cpuhw = &get_cpu_var(cpu_hw_events); err = power_check_constraints(cpuhw, events, cflags, n + 1); put_cpu_var(cpu_hw_events); if (err) - return ERR_PTR(-EINVAL); + return -EINVAL; event->hw.config = events[n]; event->hw.event_base = cflags[n]; @@ -1132,11 +1161,23 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) } event->destroy = hw_perf_event_destroy; - if (err) - return ERR_PTR(err); - return &power_pmu; + return err; } +struct pmu power_pmu = { + .pmu_enable = power_pmu_enable, + .pmu_disable = power_pmu_disable, + .event_init = power_pmu_event_init, + .add = power_pmu_add, + .del = power_pmu_del, + .start = power_pmu_start, + .stop = power_pmu_stop, + .read = power_pmu_read, + .start_txn = power_pmu_start_txn, + .cancel_txn = power_pmu_cancel_txn, + .commit_txn = power_pmu_commit_txn, +}; + /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled @@ -1149,6 +1190,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, s64 prev, delta, left; int record = 0; + if (event->hw.state & PERF_HES_STOPPED) { + write_pmc(event->hw.idx, 0); + return; + } + /* we don't have to worry about interrupts here */ prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; @@ -1171,6 +1217,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, val = 0x80000000LL - left; } + write_pmc(event->hw.idx, val); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); + /* * Finally record data if requested. */ @@ -1183,23 +1234,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); - if (perf_event_overflow(event, nmi, &data, regs)) { - /* - * Interrupts are coming too fast - throttle them - * by setting the event to 0, so it will be - * at least 2^30 cycles until the next interrupt - * (assuming each event counts at most 2 counts - * per cycle). - */ - val = 0; - left = ~0ULL >> 1; - } + if (perf_event_overflow(event, nmi, &data, regs)) + power_pmu_stop(event, 0); } - - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); - perf_event_update_userpage(event); } /* @@ -1342,6 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu) freeze_events_kernel = MMCR0_FCHV; #endif /* CONFIG_PPC64 */ + perf_pmu_register(&power_pmu); perf_cpu_notifier(power_pmu_notifier); return 0; diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index 1ba45471ae43..7ecca59ddf77 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -156,6 +156,9 @@ static void fsl_emb_pmu_read(struct perf_event *event) { s64 val, delta, prev; + if (event->hw.state & PERF_HES_STOPPED) + return; + /* * Performance monitor interrupts come even when interrupts * are soft-disabled, as long as interrupts are hard-enabled. @@ -177,7 +180,7 @@ static void fsl_emb_pmu_read(struct perf_event *event) * Disable all events to prevent PMU interrupts and to allow * events to be added or removed. */ -void hw_perf_disable(void) +static void fsl_emb_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -216,7 +219,7 @@ void hw_perf_disable(void) * If we were previously disabled and events were added, then * put the new config on the PMU. */ -void hw_perf_enable(void) +static void fsl_emb_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -262,8 +265,8 @@ static int collect_events(struct perf_event *group, int max_count, return n; } -/* perf must be disabled, context locked on entry */ -static int fsl_emb_pmu_enable(struct perf_event *event) +/* context locked on entry */ +static int fsl_emb_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuhw; int ret = -EAGAIN; @@ -271,6 +274,7 @@ static int fsl_emb_pmu_enable(struct perf_event *event) u64 val; int i; + perf_pmu_disable(event->pmu); cpuhw = &get_cpu_var(cpu_hw_events); if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) @@ -301,6 +305,12 @@ static int fsl_emb_pmu_enable(struct perf_event *event) val = 0x80000000L - left; } local64_set(&event->hw.prev_count, val); + + if (!(flags & PERF_EF_START)) { + event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + val = 0; + } + write_pmc(i, val); perf_event_update_userpage(event); @@ -310,15 +320,17 @@ static int fsl_emb_pmu_enable(struct perf_event *event) ret = 0; out: put_cpu_var(cpu_hw_events); + perf_pmu_enable(event->pmu); return ret; } -/* perf must be disabled, context locked on entry */ -static void fsl_emb_pmu_disable(struct perf_event *event) +/* context locked on entry */ +static void fsl_emb_pmu_del(struct perf_event *event, int flags) { struct cpu_hw_events *cpuhw; int i = event->hw.idx; + perf_pmu_disable(event->pmu); if (i < 0) goto out; @@ -346,44 +358,57 @@ static void fsl_emb_pmu_disable(struct perf_event *event) cpuhw->n_events--; out: + perf_pmu_enable(event->pmu); put_cpu_var(cpu_hw_events); } -/* - * Re-enable interrupts on a event after they were throttled - * because they were coming too fast. - * - * Context is locked on entry, but perf is not disabled. - */ -static void fsl_emb_pmu_unthrottle(struct perf_event *event) +static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags) { - s64 val, left; unsigned long flags; + s64 left; if (event->hw.idx < 0 || !event->hw.sample_period) return; + + if (!(event->hw.state & PERF_HES_STOPPED)) + return; + + if (ef_flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + local_irq_save(flags); - perf_disable(); - fsl_emb_pmu_read(event); - left = event->hw.sample_period; - event->hw.last_period = left; - val = 0; - if (left < 0x80000000L) - val = 0x80000000L - left; - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); + perf_pmu_disable(event->pmu); + + event->hw.state = 0; + left = local64_read(&event->hw.period_left); + write_pmc(event->hw.idx, left); + perf_event_update_userpage(event); - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } -static struct pmu fsl_emb_pmu = { - .enable = fsl_emb_pmu_enable, - .disable = fsl_emb_pmu_disable, - .read = fsl_emb_pmu_read, - .unthrottle = fsl_emb_pmu_unthrottle, -}; +static void fsl_emb_pmu_stop(struct perf_event *event, int ef_flags) +{ + unsigned long flags; + + if (event->hw.idx < 0 || !event->hw.sample_period) + return; + + if (event->hw.state & PERF_HES_STOPPED) + return; + + local_irq_save(flags); + perf_pmu_disable(event->pmu); + + fsl_emb_pmu_read(event); + event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + write_pmc(event->hw.idx, 0); + + perf_event_update_userpage(event); + perf_pmu_enable(event->pmu); + local_irq_restore(flags); +} /* * Release the PMU if this is the last perf_event. @@ -428,7 +453,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp) return 0; } -const struct pmu *hw_perf_event_init(struct perf_event *event) +static int fsl_emb_pmu_event_init(struct perf_event *event) { u64 ev; struct perf_event *events[MAX_HWEVENTS]; @@ -441,14 +466,14 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) case PERF_TYPE_HARDWARE: ev = event->attr.config; if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; ev = ppmu->generic_events[ev]; break; case PERF_TYPE_HW_CACHE: err = hw_perf_cache_event(event->attr.config, &ev); if (err) - return ERR_PTR(err); + return err; break; case PERF_TYPE_RAW: @@ -456,12 +481,12 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) break; default: - return ERR_PTR(-EINVAL); + return -ENOENT; } event->hw.config = ppmu->xlate_event(ev); if (!(event->hw.config & FSL_EMB_EVENT_VALID)) - return ERR_PTR(-EINVAL); + return -EINVAL; /* * If this is in a group, check if it can go on with all the @@ -473,7 +498,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) n = collect_events(event->group_leader, ppmu->n_counter - 1, events); if (n < 0) - return ERR_PTR(-EINVAL); + return -EINVAL; } if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) { @@ -484,7 +509,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) } if (num_restricted >= ppmu->n_restricted) - return ERR_PTR(-EINVAL); + return -EINVAL; } event->hw.idx = -1; @@ -497,7 +522,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) if (event->attr.exclude_kernel) event->hw.config_base |= PMLCA_FCS; if (event->attr.exclude_idle) - return ERR_PTR(-ENOTSUPP); + return -ENOTSUPP; event->hw.last_period = event->hw.sample_period; local64_set(&event->hw.period_left, event->hw.last_period); @@ -523,11 +548,20 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) } event->destroy = hw_perf_event_destroy; - if (err) - return ERR_PTR(err); - return &fsl_emb_pmu; + return err; } +static struct pmu fsl_emb_pmu = { + .pmu_enable = fsl_emb_pmu_enable, + .pmu_disable = fsl_emb_pmu_disable, + .event_init = fsl_emb_pmu_event_init, + .add = fsl_emb_pmu_add, + .del = fsl_emb_pmu_del, + .start = fsl_emb_pmu_start, + .stop = fsl_emb_pmu_stop, + .read = fsl_emb_pmu_read, +}; + /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled @@ -540,6 +574,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, s64 prev, delta, left; int record = 0; + if (event->hw.state & PERF_HES_STOPPED) { + write_pmc(event->hw.idx, 0); + return; + } + /* we don't have to worry about interrupts here */ prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; @@ -562,6 +601,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, val = 0x80000000LL - left; } + write_pmc(event->hw.idx, val); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); + /* * Finally record data if requested. */ @@ -571,23 +615,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - if (perf_event_overflow(event, nmi, &data, regs)) { - /* - * Interrupts are coming too fast - throttle them - * by setting the event to 0, so it will be - * at least 2^30 cycles until the next interrupt - * (assuming each event counts at most 2 counts - * per cycle). - */ - val = 0; - left = ~0ULL >> 1; - } + if (perf_event_overflow(event, nmi, &data, regs)) + fsl_emb_pmu_stop(event, 0); } - - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); - perf_event_update_userpage(event); } static void perf_event_interrupt(struct pt_regs *regs) @@ -651,5 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) pr_info("%s performance monitor hardware support registered\n", pmu->name); + perf_pmu_register(&fsl_emb_pmu); + return 0; } diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 8eff48e20dba..3fee685de4df 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -169,9 +169,11 @@ static int p970_marked_instr_event(u64 event) switch (unit) { case PM_VPU: mask = 0x4c; /* byte 0 bits 2,3,6 */ + break; case PM_LSU0: /* byte 2 bits 0,2,3,4,6; all of byte 1 */ mask = 0x085dff00; + break; case PM_LSU1L: mask = 0x50 << 24; /* byte 3 bits 4,6 */ break; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b1c648a36b03..84906d3fc860 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -517,7 +517,6 @@ struct task_struct *__switch_to(struct task_struct *prev, account_system_vtime(current); account_process_vtime(current); - calculate_steal_time(); /* * We can't take a PMU exception inside _switch() since there is a @@ -1298,14 +1297,3 @@ unsigned long randomize_et_dyn(unsigned long base) return ret; } - -#ifdef CONFIG_SMP -int arch_sd_sibling_asym_packing(void) -{ - if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { - printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); - return SD_ASYM_PACKING; - } - return 0; -} -#endif diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index fed9bf6187d1..c3c6a8857544 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -66,6 +66,7 @@ int __initdata iommu_is_off; int __initdata iommu_force_on; unsigned long tce_alloc_start, tce_alloc_end; +u64 ppc64_rma_size; #endif static int __init early_parse_mem(char *p) @@ -98,7 +99,7 @@ static void __init move_device_tree(void) if ((memory_limit && (start + size) > memory_limit) || overlaps_crashkernel(start, size)) { - p = __va(memblock_alloc_base(size, PAGE_SIZE, memblock.rmo_size)); + p = __va(memblock_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); initial_boot_params = (struct boot_param_header *)p; DBG("Moved device tree to 0x%p\n", p); @@ -492,7 +493,7 @@ static int __init early_init_dt_scan_memory_ppc(unsigned long node, void __init early_init_dt_add_memory_arch(u64 base, u64 size) { -#if defined(CONFIG_PPC64) +#ifdef CONFIG_PPC64 if (iommu_is_off) { if (base >= 0x80000000ul) return; @@ -501,9 +502,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) } #endif - memblock_add(base, size); - + /* First MEMBLOCK added, do some special initializations */ + if (memstart_addr == ~(phys_addr_t)0) + setup_initial_memory_limit(base, size); memstart_addr = min((u64)memstart_addr, base); + + /* Add the chunk to the MEMBLOCK list */ + memblock_add(base, size); } u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align) @@ -655,7 +660,6 @@ static void __init phyp_dump_reserve_mem(void) static inline void __init phyp_dump_reserve_mem(void) {} #endif /* CONFIG_PHYP_DUMP && CONFIG_PPC_RTAS */ - void __init early_init_devtree(void *params) { phys_addr_t limit; @@ -683,6 +687,7 @@ void __init early_init_devtree(void *params) /* Scan memory nodes and rebuild MEMBLOCKs */ memblock_init(); + of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 11f3cd9c832f..286d9783d93f 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1681,7 +1681,7 @@ long do_syscall_trace_enter(struct pt_regs *regs) if (unlikely(current->audit_context)) { #ifdef CONFIG_PPC64 - if (!test_thread_flag(TIF_32BIT)) + if (!is_32bit_task()) audit_syscall_entry(AUDIT_ARCH_PPC64, regs->gpr[0], regs->gpr[3], regs->gpr[4], diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 41048de3c6c3..8fe8bc61c10a 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -805,7 +805,7 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } -static int rtas_ibm_suspend_me(struct rtas_args *args) +int rtas_ibm_suspend_me(struct rtas_args *args) { long state; long rc; @@ -855,7 +855,7 @@ static int rtas_ibm_suspend_me(struct rtas_args *args) return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ -static int rtas_ibm_suspend_me(struct rtas_args *args) +int rtas_ibm_suspend_me(struct rtas_args *args) { return -ENOSYS; } @@ -969,7 +969,7 @@ void __init rtas_initialize(void) */ #ifdef CONFIG_PPC64 if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) { - rtas_region = min(memblock.rmo_size, RTAS_INSTANTIATE_MAX); + rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX); ibm_suspend_me_token = rtas_token("ibm,suspend-me"); } #endif diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 67a84d8f118d..2b442e6c21e6 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -716,6 +716,7 @@ static const struct file_operations rtas_flash_operations = { .write = rtas_flash_write, .open = rtas_excl_open, .release = rtas_flash_release, + .llseek = default_llseek, }; static const struct file_operations manage_flash_operations = { @@ -724,6 +725,7 @@ static const struct file_operations manage_flash_operations = { .write = manage_flash_write, .open = rtas_excl_open, .release = rtas_excl_release, + .llseek = default_llseek, }; static const struct file_operations validate_flash_operations = { @@ -732,6 +734,7 @@ static const struct file_operations validate_flash_operations = { .write = validate_flash_write, .open = rtas_excl_open, .release = validate_flash_release, + .llseek = default_llseek, }; static int __init rtas_flash_init(void) diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 638883e23e3a..0438f819fe6b 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -354,6 +354,7 @@ static const struct file_operations proc_rtas_log_operations = { .poll = rtas_log_poll, .open = rtas_log_open, .release = rtas_log_release, + .llseek = noop_llseek, }; static int enable_surveillance(int timeout) diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 93666f9cabf1..1d2fbc905303 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -46,7 +46,7 @@ extern void bootx_init(unsigned long r4, unsigned long phys); -int boot_cpuid; +int boot_cpuid = -1; EXPORT_SYMBOL_GPL(boot_cpuid); int boot_cpuid_phys; @@ -246,7 +246,7 @@ static void __init irqstack_early_init(void) unsigned int i; /* interrupt stacks must be in lowmem, we get that for free on ppc32 - * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ + * as the memblock is limited to lowmem by default */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e72690ec9b87..2a178b0ebcdf 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -486,7 +486,7 @@ static void __init emergency_stack_init(void) * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. */ - limit = min(slb0_limit(), memblock.rmo_size); + limit = min(slb0_limit(), ppc64_rma_size); for_each_possible_cpu(i) { unsigned long sp; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 0008bc58e826..68034bbf2e4f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -508,9 +508,6 @@ int __devinit start_secondary(void *unused) if (smp_ops->take_timebase) smp_ops->take_timebase(); - if (system_state > SYSTEM_BOOTING) - snapshot_timebase(); - secondary_cpu_time_init(); ipi_call_lock(); @@ -575,11 +572,18 @@ void __init smp_cpus_done(unsigned int max_cpus) free_cpumask_var(old_mask); - snapshot_timebases(); - dump_numa_cpu_topology(); } +int arch_sd_sibling_asym_packing(void) +{ + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + return SD_ASYM_PACKING; + } + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU int __cpu_disable(void) { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 8533b3b83f5d..010406958d97 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -53,7 +53,7 @@ #include <linux/posix-timers.h> #include <linux/irq.h> #include <linux/delay.h> -#include <linux/perf_event.h> +#include <linux/irq_work.h> #include <asm/trace.h> #include <asm/io.h> @@ -161,10 +161,9 @@ extern struct timezone sys_tz; static long timezone_offset; unsigned long ppc_proc_freq; -EXPORT_SYMBOL(ppc_proc_freq); +EXPORT_SYMBOL_GPL(ppc_proc_freq); unsigned long ppc_tb_freq; - -static DEFINE_PER_CPU(u64, last_jiffy); +EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* @@ -185,6 +184,8 @@ DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta); cputime_t cputime_one_jiffy; +void (*dtl_consumer)(struct dtl_entry *, u64); + static void calc_cputime_factors(void) { struct div_result res; @@ -200,62 +201,153 @@ static void calc_cputime_factors(void) } /* - * Read the PURR on systems that have it, otherwise the timebase. + * Read the SPURR on systems that have it, otherwise the PURR, + * or if that doesn't exist return the timebase value passed in. */ -static u64 read_purr(void) +static u64 read_spurr(u64 tb) { + if (cpu_has_feature(CPU_FTR_SPURR)) + return mfspr(SPRN_SPURR); if (cpu_has_feature(CPU_FTR_PURR)) return mfspr(SPRN_PURR); - return mftb(); + return tb; } +#ifdef CONFIG_PPC_SPLPAR + /* - * Read the SPURR on systems that have it, otherwise the purr + * Scan the dispatch trace log and count up the stolen time. + * Should be called with interrupts disabled. */ -static u64 read_spurr(u64 purr) +static u64 scan_dispatch_log(u64 stop_tb) { - /* - * cpus without PURR won't have a SPURR - * We already know the former when we use this, so tell gcc - */ - if (cpu_has_feature(CPU_FTR_PURR) && cpu_has_feature(CPU_FTR_SPURR)) - return mfspr(SPRN_SPURR); - return purr; + u64 i = local_paca->dtl_ridx; + struct dtl_entry *dtl = local_paca->dtl_curr; + struct dtl_entry *dtl_end = local_paca->dispatch_log_end; + struct lppaca *vpa = local_paca->lppaca_ptr; + u64 tb_delta; + u64 stolen = 0; + u64 dtb; + + if (i == vpa->dtl_idx) + return 0; + while (i < vpa->dtl_idx) { + if (dtl_consumer) + dtl_consumer(dtl, i); + dtb = dtl->timebase; + tb_delta = dtl->enqueue_to_dispatch_time + + dtl->ready_to_enqueue_time; + barrier(); + if (i + N_DISPATCH_LOG < vpa->dtl_idx) { + /* buffer has overflowed */ + i = vpa->dtl_idx - N_DISPATCH_LOG; + dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); + continue; + } + if (dtb > stop_tb) + break; + stolen += tb_delta; + ++i; + ++dtl; + if (dtl == dtl_end) + dtl = local_paca->dispatch_log; + } + local_paca->dtl_ridx = i; + local_paca->dtl_curr = dtl; + return stolen; } /* + * Accumulate stolen time by scanning the dispatch trace log. + * Called on entry from user mode. + */ +void accumulate_stolen_time(void) +{ + u64 sst, ust; + + sst = scan_dispatch_log(get_paca()->starttime_user); + ust = scan_dispatch_log(get_paca()->starttime); + get_paca()->system_time -= sst; + get_paca()->user_time -= ust; + get_paca()->stolen_time += ust + sst; +} + +static inline u64 calculate_stolen_time(u64 stop_tb) +{ + u64 stolen = 0; + + if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) { + stolen = scan_dispatch_log(stop_tb); + get_paca()->system_time -= stolen; + } + + stolen += get_paca()->stolen_time; + get_paca()->stolen_time = 0; + return stolen; +} + +#else /* CONFIG_PPC_SPLPAR */ +static inline u64 calculate_stolen_time(u64 stop_tb) +{ + return 0; +} + +#endif /* CONFIG_PPC_SPLPAR */ + +/* * Account time for a transition between system, hard irq * or soft irq state. */ void account_system_vtime(struct task_struct *tsk) { - u64 now, nowscaled, delta, deltascaled, sys_time; + u64 now, nowscaled, delta, deltascaled; unsigned long flags; + u64 stolen, udelta, sys_scaled, user_scaled; local_irq_save(flags); - now = read_purr(); + now = mftb(); nowscaled = read_spurr(now); - delta = now - get_paca()->startpurr; + get_paca()->system_time += now - get_paca()->starttime; + get_paca()->starttime = now; deltascaled = nowscaled - get_paca()->startspurr; - get_paca()->startpurr = now; get_paca()->startspurr = nowscaled; - if (!in_interrupt()) { - /* deltascaled includes both user and system time. - * Hence scale it based on the purr ratio to estimate - * the system time */ - sys_time = get_paca()->system_time; - if (get_paca()->user_time) - deltascaled = deltascaled * sys_time / - (sys_time + get_paca()->user_time); - delta += sys_time; - get_paca()->system_time = 0; + + stolen = calculate_stolen_time(now); + + delta = get_paca()->system_time; + get_paca()->system_time = 0; + udelta = get_paca()->user_time - get_paca()->utime_sspurr; + get_paca()->utime_sspurr = get_paca()->user_time; + + /* + * Because we don't read the SPURR on every kernel entry/exit, + * deltascaled includes both user and system SPURR ticks. + * Apportion these ticks to system SPURR ticks and user + * SPURR ticks in the same ratio as the system time (delta) + * and user time (udelta) values obtained from the timebase + * over the same interval. The system ticks get accounted here; + * the user ticks get saved up in paca->user_time_scaled to be + * used by account_process_tick. + */ + sys_scaled = delta; + user_scaled = udelta; + if (deltascaled != delta + udelta) { + if (udelta) { + sys_scaled = deltascaled * delta / (delta + udelta); + user_scaled = deltascaled - sys_scaled; + } else { + sys_scaled = deltascaled; + } + } + get_paca()->user_time_scaled += user_scaled; + + if (in_irq() || idle_task(smp_processor_id()) != tsk) { + account_system_time(tsk, 0, delta, sys_scaled); + if (stolen) + account_steal_time(stolen); + } else { + account_idle_time(delta + stolen); } - if (in_irq() || idle_task(smp_processor_id()) != tsk) - account_system_time(tsk, 0, delta, deltascaled); - else - account_idle_time(delta); - __get_cpu_var(cputime_last_delta) = delta; - __get_cpu_var(cputime_scaled_last_delta) = deltascaled; local_irq_restore(flags); } EXPORT_SYMBOL_GPL(account_system_vtime); @@ -265,125 +357,26 @@ EXPORT_SYMBOL_GPL(account_system_vtime); * by the exception entry and exit code to the generic process * user and system time records. * Must be called with interrupts disabled. + * Assumes that account_system_vtime() has been called recently + * (i.e. since the last entry from usermode) so that + * get_paca()->user_time_scaled is up to date. */ void account_process_tick(struct task_struct *tsk, int user_tick) { cputime_t utime, utimescaled; utime = get_paca()->user_time; + utimescaled = get_paca()->user_time_scaled; get_paca()->user_time = 0; - utimescaled = cputime_to_scaled(utime); + get_paca()->user_time_scaled = 0; + get_paca()->utime_sspurr = 0; account_user_time(tsk, utime, utimescaled); } -/* - * Stuff for accounting stolen time. - */ -struct cpu_purr_data { - int initialized; /* thread is running */ - u64 tb; /* last TB value read */ - u64 purr; /* last PURR value read */ - u64 spurr; /* last SPURR value read */ -}; - -/* - * Each entry in the cpu_purr_data array is manipulated only by its - * "owner" cpu -- usually in the timer interrupt but also occasionally - * in process context for cpu online. As long as cpus do not touch - * each others' cpu_purr_data, disabling local interrupts is - * sufficient to serialize accesses. - */ -static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data); - -static void snapshot_tb_and_purr(void *data) -{ - unsigned long flags; - struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data); - - local_irq_save(flags); - p->tb = get_tb_or_rtc(); - p->purr = mfspr(SPRN_PURR); - wmb(); - p->initialized = 1; - local_irq_restore(flags); -} - -/* - * Called during boot when all cpus have come up. - */ -void snapshot_timebases(void) -{ - if (!cpu_has_feature(CPU_FTR_PURR)) - return; - on_each_cpu(snapshot_tb_and_purr, NULL, 1); -} - -/* - * Must be called with interrupts disabled. - */ -void calculate_steal_time(void) -{ - u64 tb, purr; - s64 stolen; - struct cpu_purr_data *pme; - - pme = &__get_cpu_var(cpu_purr_data); - if (!pme->initialized) - return; /* !CPU_FTR_PURR or early in early boot */ - tb = mftb(); - purr = mfspr(SPRN_PURR); - stolen = (tb - pme->tb) - (purr - pme->purr); - if (stolen > 0) { - if (idle_task(smp_processor_id()) != current) - account_steal_time(stolen); - else - account_idle_time(stolen); - } - pme->tb = tb; - pme->purr = purr; -} - -#ifdef CONFIG_PPC_SPLPAR -/* - * Must be called before the cpu is added to the online map when - * a cpu is being brought up at runtime. - */ -static void snapshot_purr(void) -{ - struct cpu_purr_data *pme; - unsigned long flags; - - if (!cpu_has_feature(CPU_FTR_PURR)) - return; - local_irq_save(flags); - pme = &__get_cpu_var(cpu_purr_data); - pme->tb = mftb(); - pme->purr = mfspr(SPRN_PURR); - pme->initialized = 1; - local_irq_restore(flags); -} - -#endif /* CONFIG_PPC_SPLPAR */ - #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */ #define calc_cputime_factors() -#define calculate_steal_time() do { } while (0) #endif -#if !(defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR)) -#define snapshot_purr() do { } while (0) -#endif - -/* - * Called when a cpu comes up after the system has finished booting, - * i.e. as a result of a hotplug cpu action. - */ -void snapshot_timebase(void) -{ - __get_cpu_var(last_jiffy) = get_tb_or_rtc(); - snapshot_purr(); -} - void __delay(unsigned long loops) { unsigned long start; @@ -493,60 +486,60 @@ void __init iSeries_time_init_early(void) } #endif /* CONFIG_PPC_ISERIES */ -#ifdef CONFIG_PERF_EVENTS +#ifdef CONFIG_IRQ_WORK /* * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */ #ifdef CONFIG_PPC64 -static inline unsigned long test_perf_event_pending(void) +static inline unsigned long test_irq_work_pending(void) { unsigned long x; asm volatile("lbz %0,%1(13)" : "=r" (x) - : "i" (offsetof(struct paca_struct, perf_event_pending))); + : "i" (offsetof(struct paca_struct, irq_work_pending))); return x; } -static inline void set_perf_event_pending_flag(void) +static inline void set_irq_work_pending_flag(void) { asm volatile("stb %0,%1(13)" : : "r" (1), - "i" (offsetof(struct paca_struct, perf_event_pending))); + "i" (offsetof(struct paca_struct, irq_work_pending))); } -static inline void clear_perf_event_pending(void) +static inline void clear_irq_work_pending(void) { asm volatile("stb %0,%1(13)" : : "r" (0), - "i" (offsetof(struct paca_struct, perf_event_pending))); + "i" (offsetof(struct paca_struct, irq_work_pending))); } #else /* 32-bit */ -DEFINE_PER_CPU(u8, perf_event_pending); +DEFINE_PER_CPU(u8, irq_work_pending); -#define set_perf_event_pending_flag() __get_cpu_var(perf_event_pending) = 1 -#define test_perf_event_pending() __get_cpu_var(perf_event_pending) -#define clear_perf_event_pending() __get_cpu_var(perf_event_pending) = 0 +#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1 +#define test_irq_work_pending() __get_cpu_var(irq_work_pending) +#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0 #endif /* 32 vs 64 bit */ -void set_perf_event_pending(void) +void set_irq_work_pending(void) { preempt_disable(); - set_perf_event_pending_flag(); + set_irq_work_pending_flag(); set_dec(1); preempt_enable(); } -#else /* CONFIG_PERF_EVENTS */ +#else /* CONFIG_IRQ_WORK */ -#define test_perf_event_pending() 0 -#define clear_perf_event_pending() +#define test_irq_work_pending() 0 +#define clear_irq_work_pending() -#endif /* CONFIG_PERF_EVENTS */ +#endif /* CONFIG_IRQ_WORK */ /* * For iSeries shared processors, we have to let the hypervisor @@ -585,11 +578,9 @@ void timer_interrupt(struct pt_regs * regs) old_regs = set_irq_regs(regs); irq_enter(); - calculate_steal_time(); - - if (test_perf_event_pending()) { - clear_perf_event_pending(); - perf_event_do_pending(); + if (test_irq_work_pending()) { + clear_irq_work_pending(); + irq_work_run(); } #ifdef CONFIG_PPC_ISERIES diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index a45a63c3a0c7..1b2cdc8eec90 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -538,6 +538,11 @@ int machine_check_e500(struct pt_regs *regs) return 0; } + +int machine_check_generic(struct pt_regs *regs) +{ + return 0; +} #elif defined(CONFIG_E200) int machine_check_e200(struct pt_regs *regs) { diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 13002fe206e7..fd8728729abc 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -159,7 +159,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma) { int i; - if (!vma || test_thread_flag(TIF_32BIT)) { + if (!vma || is_32bit_task()) { printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase); for (i=0; i<vdso32_pages; i++) { struct page *pg = virt_to_page(vdso32_kbase + @@ -170,7 +170,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma) dump_one_vdso_page(pg, upg); } } - if (!vma || !test_thread_flag(TIF_32BIT)) { + if (!vma || !is_32bit_task()) { printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase); for (i=0; i<vdso64_pages; i++) { struct page *pg = virt_to_page(vdso64_kbase + @@ -200,7 +200,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) return 0; #ifdef CONFIG_PPC64 - if (test_thread_flag(TIF_32BIT)) { + if (is_32bit_task()) { vdso_pagelist = vdso32_pagelist; vdso_pages = vdso32_pages; vdso_base = VDSO32_MBASE; diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 51ead52141bd..9a7946c41738 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -14,10 +14,10 @@ obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) GCOV_PROFILE := n -EXTRA_CFLAGS := -shared -fno-common -fno-builtin -EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ +ccflags-y := -shared -fno-common -fno-builtin +ccflags-y += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) -EXTRA_AFLAGS := -D__VDSO32__ -s +asflags-y := -D__VDSO32__ -s obj-y += vdso32_wrapper.o extra-y += vdso32.lds diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 79da65d44a2a..8c500d8622e4 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -9,10 +9,10 @@ obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) GCOV_PROFILE := n -EXTRA_CFLAGS := -shared -fno-common -fno-builtin -EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ +ccflags-y := -shared -fno-common -fno-builtin +ccflags-y += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) -EXTRA_AFLAGS := -D__VDSO64__ -s +asflags-y := -D__VDSO64__ -s obj-y += vdso64_wrapper.o extra-y += vdso64.lds diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index fa3469ddaef8..d692989a4318 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1184,7 +1184,12 @@ EXPORT_SYMBOL(vio_unregister_driver); /* vio_dev refcount hit 0 */ static void __devinit vio_dev_release(struct device *dev) { - /* XXX should free TCE table */ + struct iommu_table *tbl = get_iommu_table_base(dev); + + /* iSeries uses a common table for all vio devices */ + if (!firmware_has_feature(FW_FEATURE_ISERIES) && tbl) + iommu_free_table(tbl, dev->of_node ? + dev->of_node->full_name : dev_name(dev)); of_node_put(dev->of_node); kfree(to_vio_dev(dev)); } @@ -1254,8 +1259,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) if (device_register(&viodev->dev)) { printk(KERN_ERR "%s: failed to register device %s\n", __func__, dev_name(&viodev->dev)); - /* XXX free TCE table */ - kfree(viodev); + put_device(&viodev->dev); return NULL; } |