diff options
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r-- | arch/powerpc/kernel/align.c | 4 | ||||
-rw-r--r-- | arch/powerpc/kernel/asm-offsets.c | 8 | ||||
-rw-r--r-- | arch/powerpc/kernel/dma.c | 18 | ||||
-rw-r--r-- | arch/powerpc/kernel/entry_64.S | 40 | ||||
-rw-r--r-- | arch/powerpc/kernel/fpu.S | 10 | ||||
-rw-r--r-- | arch/powerpc/kernel/lparcfg.c | 14 | ||||
-rw-r--r-- | arch/powerpc/kernel/paca.c | 70 | ||||
-rw-r--r-- | arch/powerpc/kernel/ppc970-pmu.c | 2 | ||||
-rw-r--r-- | arch/powerpc/kernel/process.c | 12 | ||||
-rw-r--r-- | arch/powerpc/kernel/ptrace.c | 2 | ||||
-rw-r--r-- | arch/powerpc/kernel/smp.c | 14 | ||||
-rw-r--r-- | arch/powerpc/kernel/time.c | 272 | ||||
-rw-r--r-- | arch/powerpc/kernel/vdso.c | 6 |
13 files changed, 286 insertions, 186 deletions
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 1c0607ddccc0..c63494090854 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -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)); diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 84d6367ec003..f368c075c90b 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 @@ -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/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/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 50362b6ef6e9..8d9e3b9cda64 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); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index d0a26f1770fe..1e068a46e6c3 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, unsigned long) { } +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 @@ -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/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/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/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..bcb738b9ff8c 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -164,8 +164,6 @@ unsigned long ppc_proc_freq; EXPORT_SYMBOL(ppc_proc_freq); unsigned long ppc_tb_freq; -static DEFINE_PER_CPU(u64, last_jiffy); - #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Factors for converting from cputime_t (timebase ticks) to @@ -185,6 +183,8 @@ 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 +200,153 @@ 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 +356,26 @@ 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; @@ -585,8 +577,6 @@ 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(); 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; |