--- zzzz-none-000/linux-3.10.107/arch/sparc/kernel/perf_event.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/sparc/kernel/perf_event.c 2021-02-04 17:41:59.000000000 +0000 @@ -9,7 +9,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra */ #include @@ -21,7 +21,7 @@ #include #include -#include +#include #include #include #include @@ -108,9 +108,9 @@ /* Enabled/disable state. */ int enabled; - unsigned int group_flag; + unsigned int txn_flags; }; -DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; +static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; /* An event map describes the characteristics of a performance * counter event. In particular it gives the encoding as well as @@ -737,25 +737,9 @@ { u64 pcr; - /* There seems to be an internal latch on the overflow event - * on SPARC-T4 that prevents it from triggering unless you - * update the PIC exactly as we do here. The requirement - * seems to be that you have to turn off event counting in the - * PCR around the PIC update. - * - * For example, after the following sequence: - * - * 1) set PIC to -1 - * 2) enable event counting and overflow reporting in PCR - * 3) overflow triggers, softint 15 handler invoked - * 4) clear OV bit in PCR - * 5) write PIC to -1 - * - * a subsequent overflow event will not trigger. This - * sequence works on SPARC-T3 and previous chips. - */ pcr = pcr_ops->read_pcr(idx); - pcr_ops->write_pcr(idx, PCR_N4_PICNPT); + /* ensure ov and ntc are reset */ + pcr &= ~(PCR_N4_OV | PCR_N4_NTC); pcr_ops->write_pic(idx, val & 0xffffffff); @@ -792,6 +776,29 @@ .num_pic_regs = 4, }; +static const struct sparc_pmu sparc_m7_pmu = { + .event_map = niagara4_event_map, + .cache_map = &niagara4_cache_map, + .max_events = ARRAY_SIZE(niagara4_perfmon_event_map), + .read_pmc = sparc_vt_read_pmc, + .write_pmc = sparc_vt_write_pmc, + .upper_shift = 5, + .lower_shift = 5, + .event_mask = 0x7ff, + .user_bit = PCR_N4_UTRACE, + .priv_bit = PCR_N4_STRACE, + + /* We explicitly don't support hypervisor tracing. */ + .hv_bit = 0, + + .irq_bit = PCR_N4_TOE, + .upper_nop = 0, + .lower_nop = 0, + .flags = 0, + .max_hw_events = 4, + .num_pcrs = 4, + .num_pic_regs = 4, +}; static const struct sparc_pmu *sparc_pmu __read_mostly; static u64 event_encoding(u64 event_id, int idx) @@ -1008,7 +1015,7 @@ static void sparc_pmu_enable(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; if (cpuc->enabled) @@ -1026,7 +1033,7 @@ static void sparc_pmu_disable(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; if (!cpuc->enabled) @@ -1060,7 +1067,7 @@ static void sparc_pmu_start(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = active_event_index(cpuc, event); if (flags & PERF_EF_RELOAD) { @@ -1075,7 +1082,7 @@ static void sparc_pmu_stop(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = active_event_index(cpuc, event); if (!(event->hw.state & PERF_HES_STOPPED)) { @@ -1091,7 +1098,7 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned long flags; int i; @@ -1126,7 +1133,7 @@ static void sparc_pmu_read(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = active_event_index(cpuc, event); struct hw_perf_event *hwc = &event->hw; @@ -1138,7 +1145,7 @@ static void perf_stop_nmi_watchdog(void *unused) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; stop_nmi_watchdog(NULL); @@ -1146,7 +1153,7 @@ cpuc->pcr[i] = pcr_ops->read_pcr(i); } -void perf_event_grab_pmc(void) +static void perf_event_grab_pmc(void) { if (atomic_inc_not_zero(&active_events)) return; @@ -1162,7 +1169,7 @@ mutex_unlock(&pmc_grab_mutex); } -void perf_event_release_pmc(void) +static void perf_event_release_pmc(void) { if (atomic_dec_and_mutex_lock(&active_events, &pmc_grab_mutex)) { if (atomic_read(&nmi_active) == 0) @@ -1349,7 +1356,7 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int n0, ret = -EAGAIN; unsigned long flags; @@ -1372,7 +1379,7 @@ * skip the schedulability test here, it will be performed * at commit time(->commit_txn) as a whole */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto nocheck; if (check_excludes(cpuc->event, n0, 1)) @@ -1487,12 +1494,17 @@ * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time */ -static void sparc_pmu_start_txn(struct pmu *pmu) +static void sparc_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); + + WARN_ON_ONCE(cpuhw->txn_flags); /* txn already in flight */ + + cpuhw->txn_flags = txn_flags; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; perf_pmu_disable(pmu); - cpuhw->group_flag |= PERF_EVENT_TXN; } /* @@ -1502,9 +1514,16 @@ */ static void sparc_pmu_cancel_txn(struct pmu *pmu) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); + unsigned int txn_flags; + + WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */ + + txn_flags = cpuhw->txn_flags; + cpuhw->txn_flags = 0; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; - cpuhw->group_flag &= ~PERF_EVENT_TXN; perf_pmu_enable(pmu); } @@ -1515,20 +1534,26 @@ */ static int sparc_pmu_commit_txn(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int n; if (!sparc_pmu) return -EINVAL; - cpuc = &__get_cpu_var(cpu_hw_events); + WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ + + if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) { + cpuc->txn_flags = 0; + return 0; + } + n = cpuc->n_events; if (check_excludes(cpuc->event, 0, n)) return -EINVAL; if (sparc_check_constraints(cpuc->event, cpuc->events, n)) return -EAGAIN; - cpuc->group_flag &= ~PERF_EVENT_TXN; + cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; } @@ -1592,7 +1617,7 @@ regs = args->regs; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); /* If the PMU has the TOE IRQ enable bits, we need to do a * dummy write to the %pcr to clear the overflow bits and thus @@ -1653,18 +1678,26 @@ sparc_pmu = &niagara2_pmu; return true; } - if (!strcmp(sparc_pmu_type, "niagara4")) { + if (!strcmp(sparc_pmu_type, "niagara4") || + !strcmp(sparc_pmu_type, "niagara5")) { sparc_pmu = &niagara4_pmu; return true; } + if (!strcmp(sparc_pmu_type, "sparc-m7")) { + sparc_pmu = &sparc_m7_pmu; + return true; + } return false; } -int __init init_hw_perf_events(void) +static int __init init_hw_perf_events(void) { + int err; + pr_info("Performance events: "); - if (!supported_pmu()) { + err = pcr_arch_init(); + if (err || !supported_pmu()) { pr_cont("No support for PMU type '%s'\n", sparc_pmu_type); return 0; } @@ -1676,7 +1709,7 @@ return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) @@ -1726,17 +1759,31 @@ } while (entry->nr < PERF_MAX_STACK_DEPTH); } +static inline int +valid_user_frame(const void __user *fp, unsigned long size) +{ + /* addresses should be at least 4-byte aligned */ + if (((unsigned long) fp) & 3) + return 0; + + return (__range_not_ok(fp, size, TASK_SIZE) == 0); +} + static void perf_callchain_user_64(struct perf_callchain_entry *entry, struct pt_regs *regs) { unsigned long ufp; - ufp = regs->u_regs[UREG_I6] + STACK_BIAS; + ufp = regs->u_regs[UREG_FP] + STACK_BIAS; do { - struct sparc_stackf *usf, sf; + struct sparc_stackf __user *usf; + struct sparc_stackf sf; unsigned long pc; - usf = (struct sparc_stackf *) ufp; + usf = (struct sparc_stackf __user *)ufp; + if (!valid_user_frame(usf, sizeof(sf))) + break; + if (__copy_from_user_inatomic(&sf, usf, sizeof(sf))) break; @@ -1751,22 +1798,24 @@ { unsigned long ufp; - ufp = regs->u_regs[UREG_I6] & 0xffffffffUL; + ufp = regs->u_regs[UREG_FP] & 0xffffffffUL; do { unsigned long pc; if (thread32_stack_is_64bit(ufp)) { - struct sparc_stackf *usf, sf; + struct sparc_stackf __user *usf; + struct sparc_stackf sf; ufp += STACK_BIAS; - usf = (struct sparc_stackf *) ufp; + usf = (struct sparc_stackf __user *)ufp; if (__copy_from_user_inatomic(&sf, usf, sizeof(sf))) break; pc = sf.callers_pc & 0xffffffff; ufp = ((unsigned long) sf.fp) & 0xffffffff; } else { - struct sparc_stackf32 *usf, sf; - usf = (struct sparc_stackf32 *) ufp; + struct sparc_stackf32 __user *usf; + struct sparc_stackf32 sf; + usf = (struct sparc_stackf32 __user *)ufp; if (__copy_from_user_inatomic(&sf, usf, sizeof(sf))) break; pc = sf.callers_pc; @@ -1779,14 +1828,30 @@ void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { + u64 saved_fault_address = current_thread_info()->fault_address; + u8 saved_fault_code = get_thread_fault_code(); + mm_segment_t old_fs; + perf_callchain_store(entry, regs->tpc); if (!current->mm) return; + old_fs = get_fs(); + set_fs(USER_DS); + flushw_user(); + + pagefault_disable(); + if (test_thread_flag(TIF_32BIT)) perf_callchain_user_32(entry, regs); else perf_callchain_user_64(entry, regs); + + pagefault_enable(); + + set_fs(old_fs); + set_thread_fault_code(saved_fault_code); + current_thread_info()->fault_address = saved_fault_address; }