diff options
| author | Ingo Molnar <mingo@kernel.org> | 2015-05-08 11:33:33 (GMT) |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2015-05-08 11:33:33 (GMT) |
| commit | 7ae383be81781c5e1347f71c3eb0d53ce5188200 (patch) | |
| tree | d2dfedb78cf4ee2bc9cc460af3be106b08e01050 /arch/x86/kernel | |
| parent | 2a4e90b18c256d52a7f3f77d58114f6d4e4a7f9f (diff) | |
| parent | 3e0283a53f7d2f2dae7bc4aa7f3104cb5988018f (diff) | |
| download | linux-7ae383be81781c5e1347f71c3eb0d53ce5188200.tar.xz | |
Merge branch 'linus' into x86/asm, before applying dependent patch
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/kernel')
38 files changed, 4921 insertions, 419 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index c887cd9..9bcd0b5 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -95,6 +95,7 @@ obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o +obj-$(CONFIG_X86_PMEM_LEGACY) += pmem.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 803b684..dbe76a1 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -757,7 +757,7 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu) +int __ref acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) { return _acpi_map_lsapic(handle, physid, pcpu); } diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index d9d0bd2..ab3219b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -171,8 +171,8 @@ update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu) for_each_online_cpu(cpu) { if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) continue; - __cpu_clear(this_cpu, per_cpu(cpus_in_cluster, cpu)); - __cpu_clear(cpu, per_cpu(cpus_in_cluster, this_cpu)); + cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); + cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); } free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu)); free_cpumask_var(per_cpu(ipi_mask, this_cpu)); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 80091ae..9bff687 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,8 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o perf_event_intel_cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o perf_event_intel_bts.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \ perf_event_intel_uncore_snb.o \ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index fd470eb..e4cf633 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -720,6 +720,9 @@ static void init_amd(struct cpuinfo_x86 *c) if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH)) if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM)) set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH); + + /* AMD CPUs don't reset SS attributes on SYSRET */ + set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3f70538..a62cf04 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -646,6 +646,30 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[10] = eax; } + /* Additional Intel-defined flags: level 0x0000000F */ + if (c->cpuid_level >= 0x0000000F) { + u32 eax, ebx, ecx, edx; + + /* QoS sub-leaf, EAX=0Fh, ECX=0 */ + cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); + c->x86_capability[11] = edx; + if (cpu_has(c, X86_FEATURE_CQM_LLC)) { + /* will be overridden if occupancy monitoring exists */ + c->x86_cache_max_rmid = ebx; + + /* QoS sub-leaf, EAX=0Fh, ECX=1 */ + cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); + c->x86_capability[12] = edx; + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { + c->x86_cache_max_rmid = ecx; + c->x86_cache_occ_scale = ebx; + } + } else { + c->x86_cache_max_rmid = -1; + c->x86_cache_occ_scale = -1; + } + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; @@ -834,6 +858,20 @@ static void generic_identify(struct cpuinfo_x86 *c) detect_nopl(c); } +static void x86_init_cache_qos(struct cpuinfo_x86 *c) +{ + /* + * The heavy lifting of max_rmid and cache_occ_scale are handled + * in get_cpu_cap(). Here we just set the max_rmid for the boot_cpu + * in case CQM bits really aren't there in this CPU. + */ + if (c != &boot_cpu_data) { + boot_cpu_data.x86_cache_max_rmid = + min(boot_cpu_data.x86_cache_max_rmid, + c->x86_cache_max_rmid); + } +} + /* * This does the hard work of actually picking apart the CPU stuff... */ @@ -923,6 +961,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) init_hypervisor(c); x86_init_rdrand(c); + x86_init_cache_qos(c); /* * Clear/Set all flags overriden by options, need do it diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 36ce402..d820d8e 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -27,8 +27,8 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = { -#ifdef CONFIG_XEN_PVHVM - &x86_hyper_xen_hvm, +#ifdef CONFIG_XEN + &x86_hyper_xen, #endif &x86_hyper_vmware, &x86_hyper_ms_hyperv, diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/kernel/cpu/intel_pt.h new file mode 100644 index 0000000..1c338b0 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_pt.h @@ -0,0 +1,131 @@ +/* + * Intel(R) Processor Trace PMU driver for perf + * Copyright (c) 2013-2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * Intel PT is specified in the Intel Architecture Instruction Set Extensions + * Programming Reference: + * http://software.intel.com/en-us/intel-isa-extensions + */ + +#ifndef __INTEL_PT_H__ +#define __INTEL_PT_H__ + +/* + * Single-entry ToPA: when this close to region boundary, switch + * buffers to avoid losing data. + */ +#define TOPA_PMI_MARGIN 512 + +/* + * Table of Physical Addresses bits + */ +enum topa_sz { + TOPA_4K = 0, + TOPA_8K, + TOPA_16K, + TOPA_32K, + TOPA_64K, + TOPA_128K, + TOPA_256K, + TOPA_512K, + TOPA_1MB, + TOPA_2MB, + TOPA_4MB, + TOPA_8MB, + TOPA_16MB, + TOPA_32MB, + TOPA_64MB, + TOPA_128MB, + TOPA_SZ_END, +}; + +static inline unsigned int sizes(enum topa_sz tsz) +{ + return 1 << (tsz + 12); +}; + +struct topa_entry { + u64 end : 1; + u64 rsvd0 : 1; + u64 intr : 1; + u64 rsvd1 : 1; + u64 stop : 1; + u64 rsvd2 : 1; + u64 size : 4; + u64 rsvd3 : 2; + u64 base : 36; + u64 rsvd4 : 16; +}; + +#define TOPA_SHIFT 12 +#define PT_CPUID_LEAVES 2 + +enum pt_capabilities { + PT_CAP_max_subleaf = 0, + PT_CAP_cr3_filtering, + PT_CAP_topa_output, + PT_CAP_topa_multiple_entries, + PT_CAP_payloads_lip, +}; + +struct pt_pmu { + struct pmu pmu; + u32 caps[4 * PT_CPUID_LEAVES]; +}; + +/** + * struct pt_buffer - buffer configuration; one buffer per task_struct or + * cpu, depending on perf event configuration + * @cpu: cpu for per-cpu allocation + * @tables: list of ToPA tables in this buffer + * @first: shorthand for first topa table + * @last: shorthand for last topa table + * @cur: current topa table + * @nr_pages: buffer size in pages + * @cur_idx: current output region's index within @cur table + * @output_off: offset within the current output region + * @data_size: running total of the amount of data in this buffer + * @lost: if data was lost/truncated + * @head: logical write offset inside the buffer + * @snapshot: if this is for a snapshot/overwrite counter + * @stop_pos: STOP topa entry in the buffer + * @intr_pos: INT topa entry in the buffer + * @data_pages: array of pages from perf + * @topa_index: table of topa entries indexed by page offset + */ +struct pt_buffer { + int cpu; + struct list_head tables; + struct topa *first, *last, *cur; + unsigned int cur_idx; + size_t output_off; + unsigned long nr_pages; + local_t data_size; + local_t lost; + local64_t head; + bool snapshot; + unsigned long stop_pos, intr_pos; + void **data_pages; + struct topa_entry *topa_index[0]; +}; + +/** + * struct pt - per-cpu pt context + * @handle: perf output handle + * @handle_nmi: do handle PT PMI on this cpu, there's an active event + */ +struct pt { + struct perf_output_handle handle; + int handle_nmi; +}; + +#endif /* __INTEL_PT_H__ */ diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index a041e09..d76f13d 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -404,11 +404,10 @@ static const struct file_operations mtrr_fops = { static int mtrr_seq_show(struct seq_file *seq, void *offset) { char factor; - int i, max, len; + int i, max; mtrr_type type; unsigned long base, size; - len = 0; max = num_var_ranges; for (i = 0; i < max; i++) { mtrr_if->get(i, &base, &size, &type); @@ -425,11 +424,10 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset) size >>= 20 - PAGE_SHIFT; } /* Base can be > 32bit */ - len += seq_printf(seq, "reg%02i: base=0x%06lx000 " - "(%5luMB), size=%5lu%cB, count=%d: %s\n", - i, base, base >> (20 - PAGE_SHIFT), size, - factor, mtrr_usage_table[i], - mtrr_attrib_to_str(type)); + seq_printf(seq, "reg%02i: base=0x%06lx000 (%5luMB), size=%5lu%cB, count=%d: %s\n", + i, base, base >> (20 - PAGE_SHIFT), + size, factor, + mtrr_usage_table[i], mtrr_attrib_to_str(type)); } return 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index e2888a3..87848eb 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -263,6 +263,14 @@ static void hw_perf_event_destroy(struct perf_event *event) } } +void hw_perf_lbr_event_destroy(struct perf_event *event) +{ + hw_perf_event_destroy(event); + + /* undo the lbr/bts event accounting */ + x86_del_exclusive(x86_lbr_exclusive_lbr); +} + static inline int x86_pmu_initialized(void) { return x86_pmu.handle_irq != NULL; @@ -302,6 +310,35 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) return x86_pmu_extra_regs(val, event); } +/* + * Check if we can create event of a certain type (that no conflicting events + * are present). + */ +int x86_add_exclusive(unsigned int what) +{ + int ret = -EBUSY, i; + + if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) + return 0; + + mutex_lock(&pmc_reserve_mutex); + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) + if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) + goto out; + + atomic_inc(&x86_pmu.lbr_exclusive[what]); + ret = 0; + +out: + mutex_unlock(&pmc_reserve_mutex); + return ret; +} + +void x86_del_exclusive(unsigned int what) +{ + atomic_dec(&x86_pmu.lbr_exclusive[what]); +} + int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; @@ -346,6 +383,12 @@ int x86_setup_perfctr(struct perf_event *event) /* BTS is currently only allowed for user-mode. */ if (!attr->exclude_kernel) return -EOPNOTSUPP; + + /* disallow bts if conflicting events are present */ + if (x86_add_exclusive(x86_lbr_exclusive_lbr)) + return -EBUSY; + + event->destroy = hw_perf_lbr_event_destroy; } hwc->config |= config; @@ -399,39 +442,41 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip > precise) return -EOPNOTSUPP; - /* - * check that PEBS LBR correction does not conflict with - * whatever the user is asking with attr->branch_sample_type - */ - if (event->attr.precise_ip > 1 && - x86_pmu.intel_cap.pebs_format < 2) { - u64 *br_type = &event->attr.branch_sample_type; - - if (has_branch_stack(event)) { - if (!precise_br_compat(event)) - return -EOPNOTSUPP; - - /* branch_sample_type is compatible */ - - } else { - /* - * user did not specify branch_sample_type - * - * For PEBS fixups, we capture all - * the branches at the priv level of the - * event. - */ - *br_type = PERF_SAMPLE_BRANCH_ANY; - - if (!event->attr.exclude_user) - *br_type |= PERF_SAMPLE_BRANCH_USER; - - if (!event->attr.exclude_kernel) - *br_type |= PERF_SAMPLE_BRANCH_KERNEL; - } + } + /* + * check that PEBS LBR correction does not conflict with + * whatever the user is asking with attr->branch_sample_type + */ + if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format < 2) { + u64 *br_type = &event->attr.branch_sample_type; + + if (has_branch_stack(event)) { + if (!precise_br_compat(event)) + return -EOPNOTSUPP; + + /* branch_sample_type is compatible */ + + } else { + /* + * user did not specify branch_sample_type + * + * For PEBS fixups, we capture all + * the branches at the priv level of the + * event. + */ + *br_type = PERF_SAMPLE_BRANCH_ANY; + + if (!event->attr.exclude_user) + *br_type |= PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_kernel) + *br_type |= PERF_SAMPLE_BRANCH_KERNEL; } } + if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK) + event->attach_state |= PERF_ATTACH_TASK_DATA; + /* * Generate PMC IRQs: * (keep 'enabled' bit clear for now) @@ -449,6 +494,12 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; + if (event->attr.sample_period && x86_pmu.limit_period) { + if (x86_pmu.limit_period(event, event->attr.sample_period) > + event->attr.sample_period) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -728,14 +779,17 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) struct event_constraint *c; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; - int i, wmin, wmax, num = 0; + int i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); + if (x86_pmu.start_scheduling) + x86_pmu.start_scheduling(cpuc); + for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { hwc = &cpuc->event_list[i]->hw; - c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]); + c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); hwc->constraint = c; wmin = min(wmin, c->weight); @@ -768,24 +822,30 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) /* slow path */ if (i != n) - num = perf_assign_events(cpuc->event_list, n, wmin, - wmax, assign); + unsched = perf_assign_events(cpuc->event_list, n, wmin, + wmax, assign); /* - * Mark the event as committed, so we do not put_constraint() - * in case new events are added and fail scheduling. + * In case of success (unsched = 0), mark events as committed, + * so we do not put_constraint() in case new events are added + * and fail to be scheduled + * + * We invoke the lower level commit callback to lock the resource + * + * We do not need to do all of this in case we are called to + * validate an event group (assign == NULL) */ - if (!num && assign) { + if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; e->hw.flags |= PERF_X86_EVENT_COMMITTED; + if (x86_pmu.commit_scheduling) + x86_pmu.commit_scheduling(cpuc, e, assign[i]); } } - /* - * scheduling failed or is just a simulation, - * free resources if necessary - */ - if (!assign || num) { + + if (!assign || unsched) { + for (i = 0; i < n; i++) { e = cpuc->event_list[i]; /* @@ -795,11 +855,18 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) continue; + /* + * release events that failed scheduling + */ if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, e); } } - return num ? -EINVAL : 0; + + if (x86_pmu.stop_scheduling) + x86_pmu.stop_scheduling(cpuc); + + return unsched ? -EINVAL : 0; } /* @@ -986,6 +1053,9 @@ int x86_perf_event_set_period(struct perf_event *event) if (left > x86_pmu.max_period) left = x86_pmu.max_period; + if (x86_pmu.limit_period) + left = x86_pmu.limit_period(event, left); + per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; /* @@ -1033,7 +1103,6 @@ static int x86_pmu_add(struct perf_event *event, int flags) hwc = &event->hw; - perf_pmu_disable(event->pmu); n0 = cpuc->n_events; ret = n = collect_events(cpuc, event, false); if (ret < 0) @@ -1071,7 +1140,6 @@ done_collect: ret = 0; out: - perf_pmu_enable(event->pmu); return ret; } @@ -1103,7 +1171,7 @@ static void x86_pmu_start(struct perf_event *event, int flags) void perf_event_print_debug(void) { u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed; - u64 pebs; + u64 pebs, debugctl; struct cpu_hw_events *cpuc; unsigned long flags; int cpu, idx; @@ -1121,14 +1189,20 @@ void perf_event_print_debug(void) rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow); rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed); - rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); pr_info("\n"); pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl); pr_info("CPU#%d: status: %016llx\n", cpu, status); pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); - pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); + if (x86_pmu.pebs_constraints) { + rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); + pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); + } + if (x86_pmu.lbr_nr) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + pr_info("CPU#%d: debugctl: %016llx\n", cpu, debugctl); + } } pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); @@ -1321,11 +1395,12 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - int ret = NOTIFY_OK; + int i, ret = NOTIFY_OK; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - cpuc->kfree_on_online = NULL; + for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) + cpuc->kfree_on_online[i] = NULL; if (x86_pmu.cpu_prepare) ret = x86_pmu.cpu_prepare(cpu); break; @@ -1336,7 +1411,10 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) break; case CPU_ONLINE: - kfree(cpuc->kfree_on_online); + for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) { + kfree(cpuc->kfree_on_online[i]); + cpuc->kfree_on_online[i] = NULL; + } break; case CPU_DYING: @@ -1712,7 +1790,7 @@ static int validate_event(struct perf_event *event) if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); - c = x86_pmu.get_event_constraints(fake_cpuc, event); + c = x86_pmu.get_event_constraints(fake_cpuc, -1, event); if (!c || !c->weight) ret = -EINVAL; @@ -1914,10 +1992,10 @@ static const struct attribute_group *x86_pmu_attr_groups[] = { NULL, }; -static void x86_pmu_flush_branch_stack(void) +static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) { - if (x86_pmu.flush_branch_stack) - x86_pmu.flush_branch_stack(); + if (x86_pmu.sched_task) + x86_pmu.sched_task(ctx, sched_in); } void perf_check_microcode(void) @@ -1949,7 +2027,8 @@ static struct pmu pmu = { .commit_txn = x86_pmu_commit_txn, .event_idx = x86_pmu_event_idx, - .flush_branch_stack = x86_pmu_flush_branch_stack, + .sched_task = x86_pmu_sched_task, + .task_ctx_size = sizeof(struct x86_perf_task_context), }; void arch_perf_update_userpage(struct perf_event *event, @@ -1968,13 +2047,23 @@ void arch_perf_update_userpage(struct perf_event *event, data = cyc2ns_read_begin(); + /* + * Internal timekeeping for enabled/running/stopped times + * is always in the local_clock domain. + */ userpg->cap_user_time = 1; userpg->time_mult = data->cyc2ns_mul; userpg->time_shift = data->cyc2ns_shift; userpg->time_offset = data->cyc2ns_offset - now; - userpg->cap_user_time_zero = 1; - userpg->time_zero = data->cyc2ns_offset; + /* + * cap_user_time_zero doesn't make sense when we're using a different + * time base for the records. + */ + if (event->clock == &local_clock) { + userpg->cap_user_time_zero = 1; + userpg->time_zero = data->cyc2ns_offset; + } cyc2ns_read_end(data); } diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index df525d2..6ac5cb7 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -65,13 +65,15 @@ struct event_constraint { /* * struct hw_perf_event.flags flags */ -#define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ -#define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ -#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x10 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x20 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x40 /* grant rdpmc permission */ +#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ +#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ +#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ struct amd_nb { @@ -123,8 +125,37 @@ struct intel_shared_regs { unsigned core_id; /* per-core: core id */ }; +enum intel_excl_state_type { + INTEL_EXCL_UNUSED = 0, /* counter is unused */ + INTEL_EXCL_SHARED = 1, /* counter can be used by both threads */ + INTEL_EXCL_EXCLUSIVE = 2, /* counter can be used by one thread only */ +}; + +struct intel_excl_states { + enum intel_excl_state_type init_state[X86_PMC_IDX_MAX]; + enum intel_excl_state_type state[X86_PMC_IDX_MAX]; + int num_alloc_cntrs;/* #counters allocated */ + int max_alloc_cntrs;/* max #counters allowed */ + bool sched_started; /* true if scheduling has started */ +}; + +struct intel_excl_cntrs { + raw_spinlock_t lock; + + struct intel_excl_states states[2]; + + int refcnt; /* per-core: #HT threads */ + unsigned core_id; /* per-core: core id */ +}; + #define MAX_LBR_ENTRIES 16 +enum { + X86_PERF_KFREE_SHARED = 0, + X86_PERF_KFREE_EXCL = 1, + X86_PERF_KFREE_MAX +}; + struct cpu_hw_events { /* * Generic x86 PMC bits @@ -179,6 +210,12 @@ struct cpu_hw_events { * used on Intel NHM/WSM/SNB */ struct intel_shared_regs *shared_regs; + /* + * manage exclusive counter access between hyperthread + */ + struct event_constraint *constraint_list; /* in enable order */ + struct intel_excl_cntrs *excl_cntrs; + int excl_thread_id; /* 0 or 1 */ /* * AMD specific bits @@ -187,7 +224,7 @@ struct cpu_hw_events { /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ u64 perf_ctr_virt_mask; - void *kfree_on_online; + void *kfree_on_online[X86_PERF_KFREE_MAX]; }; #define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ @@ -202,6 +239,10 @@ struct cpu_hw_events { #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) +#define INTEL_EXCLEVT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\ + 0, PERF_X86_EVENT_EXCL) + /* * The overlap flag marks event constraints with overlapping counter * masks. This is the case if the counter mask of such an event is not @@ -259,6 +300,10 @@ struct cpu_hw_events { #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) +#define INTEL_EXCLUEVT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_EXCL) + #define INTEL_PLD_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) @@ -283,22 +328,40 @@ struct cpu_hw_events { /* Check flags and event code, and set the HSW load flag */ #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \ - __EVENT_CONSTRAINT(code, n, \ + __EVENT_CONSTRAINT(code, n, \ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, \ + PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL) + /* Check flags and event code/umask, and set the HSW store flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \ __EVENT_CONSTRAINT(code, n, \ INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, \ + PERF_X86_EVENT_PEBS_ST_HSW|PERF_X86_EVENT_EXCL) + /* Check flags and event code/umask, and set the HSW load flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \ __EVENT_CONSTRAINT(code, n, \ INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, \ + PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL) + /* Check flags and event code/umask, and set the HSW N/A flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ __EVENT_CONSTRAINT(code, n, \ @@ -408,6 +471,13 @@ union x86_pmu_config { #define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value +enum { + x86_lbr_exclusive_lbr, + x86_lbr_exclusive_bts, + x86_lbr_exclusive_pt, + x86_lbr_exclusive_max, +}; + /* * struct x86_pmu - generic x86 pmu */ @@ -443,14 +513,25 @@ struct x86_pmu { u64 max_period; struct event_constraint * (*get_event_constraints)(struct cpu_hw_events *cpuc, + int idx, struct perf_event *event); void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); + + void (*commit_scheduling)(struct cpu_hw_events *cpuc, + struct perf_event *event, + int cntr); + + void (*start_scheduling)(struct cpu_hw_events *cpuc); + + void (*stop_scheduling)(struct cpu_hw_events *cpuc); + struct event_constraint *event_constraints; struct x86_pmu_quirk *quirks; int perfctr_second_write; bool late_ack; + unsigned (*limit_period)(struct perf_event *event, unsigned l); /* * sysfs attrs @@ -472,7 +553,8 @@ struct x86_pmu { void (*cpu_dead)(int cpu); void (*check_microcode)(void); - void (*flush_branch_stack)(void); + void (*sched_task)(struct perf_event_context *ctx, + bool sched_in); /* * Intel Arch Perfmon v2+ @@ -504,10 +586,15 @@ struct x86_pmu { bool lbr_double_abort; /* duplicated lbr aborts */ /* + * Intel PT/LBR/BTS are exclusive + */ + atomic_t lbr_exclusive[x86_lbr_exclusive_max]; + + /* * Extra registers for events */ struct extra_reg *extra_regs; - unsigned int er_flags; + unsigned int flags; /* * Intel host/guest support (KVM) @@ -515,6 +602,13 @@ struct x86_pmu { struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr); }; +struct x86_perf_task_context { + u64 lbr_from[MAX_LBR_ENTRIES]; + u64 lbr_to[MAX_LBR_ENTRIES]; + int lbr_callstack_users; + int lbr_stack_state; +}; + #define x86_add_quirk(func_) \ do { \ static struct x86_pmu_quirk __quirk __initdata = { \ @@ -524,8 +618,13 @@ do { \ x86_pmu.quirks = &__quirk; \ } while (0) -#define ERF_NO_HT_SHARING 1 -#define ERF_HAS_RSP_1 2 +/* + * x86_pmu flags + */ +#define PMU_FL_NO_HT_SHARING 0x1 /* no hyper-threading resource sharing */ +#define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */ +#define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ +#define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -546,6 +645,12 @@ static struct perf_pmu_events_attr event_attr_##v = { \ extern struct x86_pmu x86_pmu __read_mostly; +static inline bool x86_pmu_has_lbr_callstack(void) +{ + return x86_pmu.lbr_sel_map && + x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0; +} + DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); int x86_perf_event_set_period(struct perf_event *event); @@ -588,6 +693,12 @@ static inline int x86_pmu_rdpmc_index(int index) return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index; } +int x86_add_exclusive(unsigned int what); + +void x86_del_exclusive(unsigned int what); + +void hw_perf_lbr_event_destroy(struct perf_event *event); + int x86_setup_perfctr(struct perf_event *event); int x86_pmu_hw_config(struct perf_event *event); @@ -674,10 +785,34 @@ static inline int amd_pmu_init(void) #ifdef CONFIG_CPU_SUP_INTEL +static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) +{ + /* user explicitly requested branch sampling */ + if (has_branch_stack(event)) + return true; + + /* implicit branch sampling to correct PEBS skid */ + if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && + x86_pmu.intel_cap.pebs_format < 2) + return true; + + return false; +} + +static inline bool intel_pmu_has_bts(struct perf_event *event) +{ + if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS && + !event->attr.freq && event->hw.sample_period == 1) + return true; + + return false; +} + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * -x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event); +x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event); struct intel_shared_regs *allocate_shared_regs(int cpu); @@ -727,13 +862,15 @@ void intel_pmu_pebs_disable_all(void); void intel_ds_init(void); +void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); + void intel_pmu_lbr_reset(void); void intel_pmu_lbr_enable(struct perf_event *event); void intel_pmu_lbr_disable(struct perf_event *event); -void intel_pmu_lbr_enable_all(void); +void intel_pmu_lbr_enable_all(bool pmi); void intel_pmu_lbr_disable_all(void); @@ -747,8 +884,18 @@ void intel_pmu_lbr_init_atom(void); void intel_pmu_lbr_init_snb(void); +void intel_pmu_lbr_init_hsw(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); +void intel_pt_interrupt(void); + +int intel_bts_interrupt(void); + +void intel_bts_enable_local(void); + +void intel_bts_disable_local(void); + int p4_pmu_init(void); int p6_pmu_init(void); @@ -758,6 +905,10 @@ int knc_pmu_init(void); ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); +static inline int is_ht_workaround_enabled(void) +{ + return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED); +} #else /* CONFIG_CPU_SUP_INTEL */ static inline void reserve_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 2892631..1cee5d2 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -382,6 +382,7 @@ static int amd_pmu_cpu_prepare(int cpu) static void amd_pmu_cpu_starting(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; struct amd_nb *nb; int i, nb_id; @@ -399,7 +400,7 @@ static void amd_pmu_cpu_starting(int cpu) continue; if (nb->nb_id == nb_id) { - cpuc->kfree_on_online = cpuc->amd_nb; + *onln = cpuc->amd_nb; cpuc->amd_nb = nb; break; } @@ -429,7 +430,8 @@ static void amd_pmu_cpu_dead(int cpu) } static struct event_constraint * -amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { /* * if not NB event or no NB, then no constraints @@ -537,7 +539,8 @@ static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); static struct event_constraint * -amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) +amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; unsigned int event_code = amd_get_event_code(hwc); diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index a61f5c6..989d3c2 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -796,7 +796,7 @@ static int setup_ibs_ctl(int ibs_eilvt_off) * the IBS interrupt vector is handled by perf_ibs_cpu_notifier that * is using the new offset. */ -static int force_ibs_eilvt_setup(void) +static void force_ibs_eilvt_setup(void) { int offset; int ret; @@ -811,26 +811,24 @@ static int force_ibs_eilvt_setup(void) if (offset == APIC_EILVT_NR_MAX) { printk(KERN_DEBUG "No EILVT entry available\n"); - return -EBUSY; + return; } ret = setup_ibs_ctl(offset); if (ret) goto out; - if (!ibs_eilvt_valid()) { - ret = -EFAULT; + if (!ibs_eilvt_valid()) goto out; - } pr_info("IBS: LVT offset %d assigned\n", offset); - return 0; + return; out: preempt_disable(); put_eilvt(offset); preempt_enable(); - return ret; + return; } static void ibs_eilvt_setup(void) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 2589906..960e85d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/watchdog.h> #include <asm/cpufeature.h> #include <asm/hardirq.h> @@ -113,6 +114,12 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -131,15 +138,12 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ - /* - * Errata BV98 -- MEM_*_RETIRED events can leak between counters of SMT - * siblings; disable these events because they can corrupt unrelated - * counters. - */ - INTEL_EVENT_CONSTRAINT(0xd0, 0x0), /* MEM_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0x0), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0x0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0x0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -217,6 +221,21 @@ static struct event_constraint intel_hsw_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + + EVENT_CONSTRAINT_END +}; + +struct event_constraint intel_bdw_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ + INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */ EVENT_CONSTRAINT_END }; @@ -415,6 +434,202 @@ static __initconst const u64 snb_hw_cache_event_ids }; +/* + * Notes on the events: + * - data reads do not include code reads (comparable to earlier tables) + * - data counts include speculative execution (except L1 write, dtlb, bpu) + * - remote node access includes remote memory, remote cache, remote mmio. + * - prefetches are not included in the counts because they are not + * reliably counted. + */ + +#define HSW_DEMAND_DATA_RD BIT_ULL(0) +#define HSW_DEMAND_RFO BIT_ULL(1) +#define HSW_ANY_RESPONSE BIT_ULL(16) +#define HSW_SUPPLIER_NONE BIT_ULL(17) +#define HSW_L3_MISS_LOCAL_DRAM BIT_ULL(22) +#define HSW_L3_MISS_REMOTE_HOP0 BIT_ULL(27) +#define HSW_L3_MISS_REMOTE_HOP1 BIT_ULL(28) +#define HSW_L3_MISS_REMOTE_HOP2P BIT_ULL(29) +#define HSW_L3_MISS (HSW_L3_MISS_LOCAL_DRAM| \ + HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \ + HSW_L3_MISS_REMOTE_HOP2P) +#define HSW_SNOOP_NONE BIT_ULL(31) +#define HSW_SNOOP_NOT_NEEDED BIT_ULL(32) +#define HSW_SNOOP_MISS BIT_ULL(33) +#define HSW_SNOOP_HIT_NO_FWD BIT_ULL(34) +#define HSW_SNOOP_HIT_WITH_FWD BIT_ULL(35) +#define HSW_SNOOP_HITM BIT_ULL(36) +#define HSW_SNOOP_NON_DRAM BIT_ULL(37) +#define HSW_ANY_SNOOP (HSW_SNOOP_NONE| \ + HSW_SNOOP_NOT_NEEDED|HSW_SNOOP_MISS| \ + HSW_SNOOP_HIT_NO_FWD|HSW_SNOOP_HIT_WITH_FWD| \ + HSW_SNOOP_HITM|HSW_SNOOP_NON_DRAM) +#define HSW_SNOOP_DRAM (HSW_ANY_SNOOP & ~HSW_SNOOP_NON_DRAM) +#define HSW_DEMAND_READ HSW_DEMAND_DATA_RD +#define HSW_DEMAND_WRITE HSW_DEMAND_RFO +#define HSW_L3_MISS_REMOTE (HSW_L3_MISS_REMOTE_HOP0|\ + HSW_L3_MISS_REMOTE_HOP1|HSW_L3_MISS_REMOTE_HOP2P) +#define HSW_LLC_ACCESS HSW_ANY_RESPONSE + +#define BDW_L3_MISS_LOCAL BIT(26) +#define BDW_L3_MISS (BDW_L3_MISS_LOCAL| \ + HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \ + HSW_L3_MISS_REMOTE_HOP2P) + + +static __initconst const u64 hsw_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x280, /* ICACHE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x108, /* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x6085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0x185, /* ITLB_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + +static __initconst const u64 hsw_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_READ| + HSW_LLC_ACCESS, + [ C(RESULT_MISS) ] = HSW_DEMAND_READ| + HSW_L3_MISS|HSW_ANY_SNOOP, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE| + HSW_LLC_ACCESS, + [ C(RESULT_MISS) ] = HSW_DEMAND_WRITE| + HSW_L3_MISS|HSW_ANY_SNOOP, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_READ| + HSW_L3_MISS_LOCAL_DRAM| + HSW_SNOOP_DRAM, + [ C(RESULT_MISS) ] = HSW_DEMAND_READ| + HSW_L3_MISS_REMOTE| + HSW_SNOOP_DRAM, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE| + HSW_L3_MISS_LOCAL_DRAM| + HSW_SNOOP_DRAM, + [ C(RESULT_MISS) ] = HSW_DEMAND_WRITE| + HSW_L3_MISS_REMOTE| + HSW_SNOOP_DRAM, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -1029,21 +1244,10 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; -static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) -{ - /* user explicitly requested branch sampling */ - if (has_branch_stack(event)) - return true; - - /* implicit branch sampling to correct PEBS skid */ - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && - x86_pmu.intel_cap.pebs_format < 2) - return true; - - return false; -} - -static void intel_pmu_disable_all(void) +/* + * Use from PMIs where the LBRs are already disabled. + */ +static void __intel_pmu_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1051,17 +1255,24 @@ static void intel_pmu_disable_all(void) if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); + else + intel_bts_disable_local(); intel_pmu_pebs_disable_all(); +} + +static void intel_pmu_disable_all(void) +{ + __intel_pmu_disable_all(); intel_pmu_lbr_disable_all(); } -static void intel_pmu_enable_all(int added) +static void __intel_pmu_enable_all(int added, bool pmi) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); intel_pmu_pebs_enable_all(); - intel_pmu_lbr_enable_all(); + intel_pmu_lbr_enable_all(pmi); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask); @@ -1073,7 +1284,13 @@ static void intel_pmu_enable_all(int added) return; intel_pmu_enable_bts(event->hw.config); - } + } else + intel_bts_enable_local(); +} + +static void intel_pmu_enable_all(int added) +{ + __intel_pmu_enable_all(added, false); } /* @@ -1207,7 +1424,7 @@ static void intel_pmu_disable_event(struct perf_event *event) * must disable before any actual event * because any event may be combined with LBR */ - if (intel_pmu_needs_lbr_smpl(event)) + if (needs_branch_stack(event)) intel_pmu_lbr_disable(event); if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { @@ -1268,7 +1485,7 @@ static void intel_pmu_enable_event(struct perf_event *event) * must enabled before any actual event * because any event may be combined with LBR */ - if (intel_pmu_needs_lbr_smpl(event)) + if (needs_branch_stack(event)) intel_pmu_lbr_enable(event); if (event->attr.exclude_host) @@ -1334,6 +1551,18 @@ static void intel_pmu_reset(void) if (ds) ds->bts_index = ds->bts_buffer_base; + /* Ack all overflows and disable fixed counters */ + if (x86_pmu.version >= 2) { + intel_pmu_ack_status(intel_pmu_get_status()); + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); + } + + /* Reset LBRs and LBR freezing */ + if (x86_pmu.lbr_nr) { + update_debugctlmsr(get_debugctlmsr() & + ~(DEBUGCTLMSR_FREEZE_LBRS_ON_PMI|DEBUGCTLMSR_LBR)); + } + local_irq_restore(flags); } @@ -1357,8 +1586,9 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) */ if (!x86_pmu.late_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); - intel_pmu_disable_all(); + __intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); + handled += intel_bts_interrupt(); status = intel_pmu_get_status(); if (!status) goto done; @@ -1399,6 +1629,14 @@ again: } /* + * Intel PT + */ + if (__test_and_clear_bit(55, (unsigned long *)&status)) { + handled++; + intel_pt_interrupt(); + } + + /* * Checkpointed counters can lead to 'spurious' PMIs because the * rollback caused by the PMI will have cleared the overflow status * bit. Therefore always force probe these counters. @@ -1433,7 +1671,7 @@ again: goto again; done: - intel_pmu_enable_all(0); + __intel_pmu_enable_all(0, true); /* * Only unmask the NMI after the overflow counters * have been reset. This avoids spurious NMIs on @@ -1464,7 +1702,7 @@ intel_bts_constraints(struct perf_event *event) static int intel_alt_er(int idx) { - if (!(x86_pmu.er_flags & ERF_HAS_RSP_1)) + if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1)) return idx; if (idx == EXTRA_REG_RSP_0) @@ -1624,7 +1862,8 @@ intel_shared_regs_constraints(struct cpu_hw_events *cpuc, } struct event_constraint * -x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { struct event_constraint *c; @@ -1641,7 +1880,8 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) } static struct event_constraint * -intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +__intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { struct event_constraint *c; @@ -1657,7 +1897,278 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event if (c) return c; - return x86_get_event_constraints(cpuc, event); + return x86_get_event_constraints(cpuc, idx, event); +} + +static void +intel_start_scheduling(struct cpu_hw_events *cpuc) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xl, *xlo; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; /* sibling thread */ + + /* + * nothing needed if in group validation mode + */ + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + + /* + * no exclusion needed + */ + if (!excl_cntrs) + return; + + xlo = &excl_cntrs->states[o_tid]; + xl = &excl_cntrs->states[tid]; + + xl->sched_started = true; + xl->num_alloc_cntrs = 0; + /* + * lock shared state until we are done scheduling + * in stop_event_scheduling() + * makes scheduling appear as a transaction + */ + WARN_ON_ONCE(!irqs_disabled()); + raw_spin_lock(&excl_cntrs->lock); + + /* + * save initial state of sibling thread + */ + memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state)); +} + +static void +intel_stop_scheduling(struct cpu_hw_events *cpuc) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xl, *xlo; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; /* sibling thread */ + + /* + * nothing needed if in group validation mode + */ + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + /* + * no exclusion needed + */ + if (!excl_cntrs) + return; + + xlo = &excl_cntrs->states[o_tid]; + xl = &excl_cntrs->states[tid]; + + /* + * make new sibling thread state visible + */ + memcpy(xlo->state, xlo->init_state, sizeof(xlo->state)); + + xl->sched_started = false; + /* + * release shared state lock (acquired in intel_start_scheduling()) + */ + raw_spin_unlock(&excl_cntrs->lock); +} + +static struct event_constraint * +intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, + int idx, struct event_constraint *c) +{ + struct event_constraint *cx; + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xl, *xlo; + int is_excl, i; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; /* alternate */ + + /* + * validating a group does not require + * enforcing cross-thread exclusion + */ + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return c; + + /* + * no exclusion needed + */ + if (!excl_cntrs) + return c; + /* + * event requires exclusive counter access + * across HT threads + */ + is_excl = c->flags & PERF_X86_EVENT_EXCL; + + /* + * xl = state of current HT + * xlo = state of sibling HT + */ + xl = &excl_cntrs->states[tid]; + xlo = &excl_cntrs->states[o_tid]; + + /* + * do not allow scheduling of more than max_alloc_cntrs + * which is set to half the available generic counters. + * this helps avoid counter starvation of sibling thread + * by ensuring at most half the counters cannot be in + * exclusive mode. There is not designated counters for the + * limits. Any N/2 counters can be used. This helps with + * events with specifix counter constraints + */ + if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs) + return &emptyconstraint; + + cx = c; + + /* + * because we modify the constraint, we need + * to make a copy. Static constraints come + * from static const tables. + * + * only needed when constraint has not yet + * been cloned (marked dynamic) + */ + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { + + /* sanity check */ + if (idx < 0) + return &emptyconstraint; + + /* + * grab pre-allocated constraint entry + */ + cx = &cpuc->constraint_list[idx]; + + /* + * initialize dynamic constraint + * with static constraint + */ + memcpy(cx, c, sizeof(*cx)); + + /* + * mark constraint as dynamic, so we + * can free it later on + */ + cx->flags |= PERF_X86_EVENT_DYNAMIC; + } + + /* + * From here on, the constraint is dynamic. + * Either it was just allocated above, or it + * was allocated during a earlier invocation + * of this function + */ + + /* + * Modify static constraint with current dynamic + * state of thread + * + * EXCLUSIVE: sibling counter measuring exclusive event + * SHARED : sibling counter measuring non-exclusive event + * UNUSED : sibling counter unused + */ + for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) { + /* + * exclusive event in sibling counter + * our corresponding counter cannot be used + * regardless of our event + */ + if (xl->state[i] == INTEL_EXCL_EXCLUSIVE) + __clear_bit(i, cx->idxmsk); + /* + * if measuring an exclusive event, sibling + * measuring non-exclusive, then counter cannot + * be used + */ + if (is_excl && xl->state[i] == INTEL_EXCL_SHARED) + __clear_bit(i, cx->idxmsk); + } + + /* + * recompute actual bit weight for scheduling algorithm + */ + cx->weight = hweight64(cx->idxmsk64); + + /* + * if we return an empty mask, then switch + * back to static empty constraint to avoid + * the cost of freeing later on + */ + if (cx->weight == 0) + cx = &emptyconstraint; + + return cx; +} + +static struct event_constraint * +intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c1 = event->hw.constraint; + struct event_constraint *c2; + + /* + * first time only + * - static constraint: no change across incremental scheduling calls + * - dynamic constraint: handled by intel_get_excl_constraints() + */ + c2 = __intel_get_event_constraints(cpuc, idx, event); + if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) { + bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX); + c1->weight = c2->weight; + c2 = c1; + } + + if (cpuc->excl_cntrs) + return intel_get_excl_constraints(cpuc, event, idx, c2); + + return c2; +} + +static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xlo, *xl; + unsigned long flags = 0; /* keep compiler happy */ + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; + + /* + * nothing needed if in group validation mode + */ + if (cpuc->is_fake) + return; + + WARN_ON_ONCE(!excl_cntrs); + + if (!excl_cntrs) + return; + + xl = &excl_cntrs->states[tid]; + xlo = &excl_cntrs->states[o_tid]; + + /* + * put_constraint may be called from x86_schedule_events() + * which already has the lock held so here make locking + * conditional + */ + if (!xl->sched_started) + raw_spin_lock_irqsave(&excl_cntrs->lock, flags); + + /* + * if event was actually assigned, then mark the + * counter state as unused now + */ + if (hwc->idx >= 0) + xlo->state[hwc->idx] = INTEL_EXCL_UNUSED; + + if (!xl->sched_started) + raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags); } static void @@ -1678,7 +2189,57 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { + struct event_constraint *c = event->hw.constraint; + intel_put_shared_regs_event_constraints(cpuc, event); + + /* + * is PMU has exclusive counter restrictions, then + * all events are subject to and must call the + * put_excl_constraints() routine + */ + if (c && cpuc->excl_cntrs) + intel_put_excl_constraints(cpuc, event); + + /* cleanup dynamic constraint */ + if (c && (c->flags & PERF_X86_EVENT_DYNAMIC)) + event->hw.constraint = NULL; +} + +static void intel_commit_scheduling(struct cpu_hw_events *cpuc, + struct perf_event *event, int cntr) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct event_constraint *c = event->hw.constraint; + struct intel_excl_states *xlo, *xl; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; + int is_excl; + + if (cpuc->is_fake || !c) + return; + + is_excl = c->flags & PERF_X86_EVENT_EXCL; + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) + return; + + WARN_ON_ONCE(!excl_cntrs); + + if (!excl_cntrs) + return; + + xl = &excl_cntrs->states[tid]; + xlo = &excl_cntrs->states[o_tid]; + + WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock)); + + if (cntr >= 0) { + if (is_excl) + xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE; + else + xlo->init_state[cntr] = INTEL_EXCL_SHARED; + } } static void intel_pebs_aliases_core2(struct perf_event *event) @@ -1747,10 +2308,21 @@ static int intel_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip && x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); - if (intel_pmu_needs_lbr_smpl(event)) { + if (needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); if (ret) return ret; + + /* + * BTS is set up earlier in this path, so don't account twice + */ + if (!intel_pmu_has_bts(event)) { + /* disallow lbr if conflicting events are present */ + if (x86_add_exclusive(x86_lbr_exclusive_lbr)) + return -EBUSY; + + event->destroy = hw_perf_lbr_event_destroy; + } } if (event->attr.type != PERF_TYPE_RAW) @@ -1891,9 +2463,12 @@ static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); static struct event_constraint * -hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { - struct event_constraint *c = intel_get_event_constraints(cpuc, event); + struct event_constraint *c; + + c = intel_get_event_constraints(cpuc, idx, event); /* Handle special quirk on in_tx_checkpointed only in counter 2 */ if (event->hw.config & HSW_IN_TX_CHECKPOINTED) { @@ -1905,6 +2480,32 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) return c; } +/* + * Broadwell: + * + * The INST_RETIRED.ALL period always needs to have lowest 6 bits cleared + * (BDM55) and it must not use a period smaller than 100 (BDM11). We combine + * the two to enforce a minimum period of 128 (the smallest value that has bits + * 0-5 cleared and >= 100). + * + * Because of how the code in x86_perf_event_set_period() works, the truncation + * of the lower 6 bits is 'harmless' as we'll occasionally add a longer period + * to make up for the 'lost' events due to carrying the 'error' in period_left. + * + * Therefore the effective (average) period matches the requested period, + * despite coarser hardware granularity. + */ +static unsigned bdw_limit_period(struct perf_event *event, unsigned left) +{ + if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == + X86_CONFIG(.event=0xc0, .umask=0x01)) { + if (left < 128) + left = 128; + left &= ~0x3fu; + } + return left; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -1932,34 +2533,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config) return x86_event_sysfs_show(page, config, event); } -static __initconst const struct x86_pmu core_pmu = { - .name = "core", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, - .enable_all = core_pmu_enable_all, - .enable = core_pmu_enable_event, - .disable = x86_pmu_disable_event, - .hw_config = x86_pmu_hw_config, - .schedule_events = x86_schedule_events, - .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, - .perfctr = MSR_ARCH_PERFMON_PERFCTR0, - .event_map = intel_pmu_event_map, - .max_events = ARRAY_SIZE(intel_perfmon_event_map), - .apic = 1, - /* - * Intel PMCs cannot be accessed sanely above 32 bit width, - * so we install an artificial 1<<31 period regardless of - * the generic event period: - */ - .max_period = (1ULL << 31) - 1, - .get_event_constraints = intel_get_event_constraints, - .put_event_constraints = intel_put_event_constraints, - .event_constraints = intel_core_event_constraints, - .guest_get_msrs = core_guest_get_msrs, - .format_attrs = intel_arch_formats_attr, - .events_sysfs_show = intel_event_sysfs_show, -}; - struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; @@ -1979,16 +2552,52 @@ struct intel_shared_regs *allocate_shared_regs(int cpu) return regs; } +static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) +{ + struct intel_excl_cntrs *c; + int i; + + c = kzalloc_node(sizeof(struct intel_excl_cntrs), + GFP_KERNEL, cpu_to_node(cpu)); + if (c) { + raw_spin_lock_init(&c->lock); + for (i = 0; i < X86_PMC_IDX_MAX; i++) { + c->states[0].state[i] = INTEL_EXCL_UNUSED; + c->states[0].init_state[i] = INTEL_EXCL_UNUSED; + + c->states[1].state[i] = INTEL_EXCL_UNUSED; + c->states[1].init_state[i] = INTEL_EXCL_UNUSED; + } + c->core_id = -1; + } + return c; +} + static int intel_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map)) - return NOTIFY_OK; + if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { + cpuc->shared_regs = allocate_shared_regs(cpu); + if (!cpuc->shared_regs) + return NOTIFY_BAD; + } - cpuc->shared_regs = allocate_shared_regs(cpu); - if (!cpuc->shared_regs) - return NOTIFY_BAD; + if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { + size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); + + cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); + if (!cpuc->constraint_list) + return NOTIFY_BAD; + + cpuc->excl_cntrs = allocate_excl_cntrs(cpu); + if (!cpuc->excl_cntrs) { + kfree(cpuc->constraint_list); + kfree(cpuc->shared_regs); + return NOTIFY_BAD; + } + cpuc->excl_thread_id = 0; + } return NOTIFY_OK; } @@ -2010,13 +2619,15 @@ static void intel_pmu_cpu_starting(int cpu) if (!cpuc->shared_regs) return; - if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) { + if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { + void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; + for_each_cpu(i, topology_thread_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - cpuc->kfree_on_online = cpuc->shared_regs; + *onln = cpuc->shared_regs; cpuc->shared_regs = pc; break; } @@ -2027,6 +2638,44 @@ static void intel_pmu_cpu_starting(int cpu) if (x86_pmu.lbr_sel_map) cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; + + if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { + int h = x86_pmu.num_counters >> 1; + + for_each_cpu(i, topology_thread_cpumask(cpu)) { + struct intel_excl_cntrs *c; + + c = per_cpu(cpu_hw_events, i).excl_cntrs; + if (c && c->core_id == core_id) { + cpuc->kfree_on_online[1] = cpuc->excl_cntrs; + cpuc->excl_cntrs = c; + cpuc->excl_thread_id = 1; + break; + } + } + cpuc->excl_cntrs->core_id = core_id; + cpuc->excl_cntrs->refcnt++; + /* + * set hard limit to half the number of generic counters + */ + cpuc->excl_cntrs->states[0].max_alloc_cntrs = h; + cpuc->excl_cntrs->states[1].max_alloc_cntrs = h; + } +} + +static void free_excl_cntrs(int cpu) +{ + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + struct intel_excl_cntrs *c; + + c = cpuc->excl_cntrs; + if (c) { + if (c->core_id == -1 || --c->refcnt == 0) + kfree(c); + cpuc->excl_cntrs = NULL; + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; + } } static void intel_pmu_cpu_dying(int cpu) @@ -2041,19 +2690,9 @@ static void intel_pmu_cpu_dying(int cpu) cpuc->shared_regs = NULL; } - fini_debug_store_on_cpu(cpu); -} + free_excl_cntrs(cpu); -static void intel_pmu_flush_branch_stack(void) -{ - /* - * Intel LBR does not tag entries with the - * PID of the current task, then we need to - * flush it on ctxsw - * For now, we simply reset it - */ - if (x86_pmu.lbr_nr) - intel_pmu_lbr_reset(); + fini_debug_store_on_cpu(cpu); } PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); @@ -2076,6 +2715,44 @@ static struct attribute *intel_arch3_formats_attr[] = { NULL, }; +static __initconst const struct x86_pmu core_pmu = { + .name = "core", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = core_pmu_enable_all, + .enable = core_pmu_enable_event, + .disable = x86_pmu_disable_event, + .hw_config = x86_pmu_hw_config, + .schedule_events = x86_schedule_events, + .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, + .perfctr = MSR_ARCH_PERFMON_PERFCTR0, + .event_map = intel_pmu_event_map, + .max_events = ARRAY_SIZE(intel_perfmon_event_map), + .apic = 1, + /* + * Intel PMCs cannot be accessed sanely above 32-bit width, + * so we install an artificial 1<<31 period regardless of + * the generic event period: + */ + .max_period = (1ULL<<31) - 1, + .get_event_constraints = intel_get_event_constraints, + .put_event_constraints = intel_put_event_constraints, + .event_constraints = intel_core_event_constraints, + .guest_get_msrs = core_guest_get_msrs, + .format_attrs = intel_arch_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, + + /* + * Virtual (or funny metal) CPU can define x86_pmu.extra_regs + * together with PMU version 1 and thus be using core_pmu with + * shared_regs. We need following callbacks here to allocate + * it properly. + */ + .cpu_prepare = intel_pmu_cpu_prepare, + .cpu_starting = intel_pmu_cpu_starting, + .cpu_dying = intel_pmu_cpu_dying, +}; + static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, @@ -2107,7 +2784,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, - .flush_branch_stack = intel_pmu_flush_branch_stack, + .sched_task = intel_pmu_lbr_sched_task, }; static __init void intel_clovertown_quirk(void) @@ -2264,6 +2941,27 @@ static __init void intel_nehalem_quirk(void) } } +/* + * enable software workaround for errata: + * SNB: BJ122 + * IVB: BV98 + * HSW: HSD29 + * + * Only needed when HT is enabled. However detecting + * if HT is enabled is difficult (model specific). So instead, + * we enable the workaround in the early boot, and verify if + * it is needed in a later initcall phase once we have valid + * topology information to check if HT is actually enabled + */ +static __init void intel_ht_bug(void) +{ + x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED; + + x86_pmu.commit_scheduling = intel_commit_scheduling; + x86_pmu.start_scheduling = intel_start_scheduling; + x86_pmu.stop_scheduling = intel_stop_scheduling; +} + EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") @@ -2443,7 +3141,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_slm_event_constraints; x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; x86_pmu.extra_regs = intel_slm_extra_regs; - x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; pr_cont("Silvermont events, "); break; @@ -2461,7 +3159,7 @@ __init int intel_pmu_init(void) x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints; x86_pmu.extra_regs = intel_westmere_extra_regs; - x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.cpu_events = nhm_events_attrs; @@ -2478,6 +3176,7 @@ __init int intel_pmu_init(void) case 42: /* 32nm SandyBridge */ case 45: /* 32nm SandyBridge-E/EN/EP */ x86_add_quirk(intel_sandybridge_quirk); + x86_add_quirk(intel_ht_bug); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, @@ -2492,9 +3191,11 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_snbep_extra_regs; else x86_pmu.extra_regs = intel_snb_extra_regs; + + /* all extra regs are per-cpu when HT is on */ - x86_pmu.er_flags |= ERF_HAS_RSP_1; - x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.cpu_events = snb_events_attrs; @@ -2510,6 +3211,7 @@ __init int intel_pmu_init(void) case 58: /* 22nm IvyBridge */ case 62: /* 22nm IvyBridge-EP/EX */ + x86_add_quirk(intel_ht_bug); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); /* dTLB-load-misses on IVB is different than SNB */ @@ -2528,8 +3230,8 @@ __init int intel_pmu_init(void) else x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ - x86_pmu.er_flags |= ERF_HAS_RSP_1; - x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.cpu_events = snb_events_attrs; @@ -2545,19 +3247,20 @@ __init int intel_pmu_init(void) case 63: /* 22nm Haswell Server */ case 69: /* 22nm Haswell ULT */ case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + x86_add_quirk(intel_ht_bug); x86_pmu.late_ack = true; - memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); - intel_pmu_lbr_init_snb(); + intel_pmu_lbr_init_hsw(); x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; /* all extra regs are per-cpu when HT is on */ - x86_pmu.er_flags |= ERF_HAS_RSP_1; - x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; @@ -2566,6 +3269,39 @@ __init int intel_pmu_init(void) pr_cont("Haswell events, "); break; + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + /* L3_MISS_LOCAL_DRAM is BIT(26) in Broadwell */ + hw_cache_extra_regs[C(LL)][C(OP_READ)][C(RESULT_MISS)] = HSW_DEMAND_READ | + BDW_L3_MISS|HSW_SNOOP_DRAM; + hw_cache_extra_regs[C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = HSW_DEMAND_WRITE|BDW_L3_MISS| + HSW_SNOOP_DRAM; + hw_cache_extra_regs[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = HSW_DEMAND_READ| + BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM; + hw_cache_extra_regs[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = HSW_DEMAND_WRITE| + BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM; + + intel_pmu_lbr_init_hsw(); + + x86_pmu.event_constraints = intel_bdw_event_constraints; + x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.extra_regs = intel_snbep_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.limit_period = bdw_limit_period; + pr_cont("Broadwell events, "); + break; + default: switch (x86_pmu.version) { case 1: @@ -2651,3 +3387,47 @@ __init int intel_pmu_init(void) return 0; } + +/* + * HT bug: phase 2 init + * Called once we have valid topology information to check + * whether or not HT is enabled + * If HT is off, then we disable the workaround + */ +static __init int fixup_ht_bug(void) +{ + int cpu = smp_processor_id(); + int w, c; + /* + * problem not present on this CPU model, nothing to do + */ + if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED)) + return 0; + + w = cpumask_weight(topology_thread_cpumask(cpu)); + if (w > 1) { + pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n"); + return 0; + } + + watchdog_nmi_disable_all(); + + x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); + + x86_pmu.commit_scheduling = NULL; + x86_pmu.start_scheduling = NULL; + x86_pmu.stop_scheduling = NULL; + + watchdog_nmi_enable_all(); + + get_online_cpus(); + + for_each_online_cpu(c) { + free_excl_cntrs(c); + } + + put_online_cpus(); + pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n"); + return 0; +} +subsys_initcall(fixup_ht_bug) diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c new file mode 100644 index 0000000..ac1f0c5 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -0,0 +1,525 @@ +/* + * BTS PMU driver for perf + * Copyright (c) 2013-2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#undef DEBUG + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/debugfs.h> +#include <linux/device.h> +#include <linux/coredump.h> + +#include <asm-generic/sizes.h> +#include <asm/perf_event.h> + +#include "perf_event.h" + +struct bts_ctx { + struct perf_output_handle handle; + struct debug_store ds_back; + int started; +}; + +static DEFINE_PER_CPU(struct bts_ctx, bts_ctx); + +#define BTS_RECORD_SIZE 24 +#define BTS_SAFETY_MARGIN 4080 + +struct bts_phys { + struct page *page; + unsigned long size; + unsigned long offset; + unsigned long displacement; +}; + +struct bts_buffer { + size_t real_size; /* multiple of BTS_RECORD_SIZE */ + unsigned int nr_pages; + unsigned int nr_bufs; + unsigned int cur_buf; + bool snapshot; + local_t data_size; + local_t lost; + local_t head; + unsigned long end; + void **data_pages; + struct bts_phys buf[0]; +}; + +struct pmu bts_pmu; + +void intel_pmu_enable_bts(u64 config); +void intel_pmu_disable_bts(void); + +static size_t buf_size(struct page *page) +{ + return 1 << (PAGE_SHIFT + page_private(page)); +} + +static void * +bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) +{ + struct bts_buffer *buf; + struct page *page; + int node = (cpu == -1) ? cpu : cpu_to_node(cpu); + unsigned long offset; + size_t size = nr_pages << PAGE_SHIFT; + int pg, nbuf, pad; + + /* count all the high order buffers */ + for (pg = 0, nbuf = 0; pg < nr_pages;) { + page = virt_to_page(pages[pg]); + if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1)) + return NULL; + pg += 1 << page_private(page); + nbuf++; + } + + /* + * to avoid interrupts in overwrite mode, only allow one physical + */ + if (overwrite && nbuf > 1) + return NULL; + + buf = kzalloc_node(offsetof(struct bts_buffer, buf[nbuf]), GFP_KERNEL, node); + if (!buf) + return NULL; + + buf->nr_pages = nr_pages; + buf->nr_bufs = nbuf; + buf->snapshot = overwrite; + buf->data_pages = pages; + buf->real_size = size - size % BTS_RECORD_SIZE; + + for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) { + unsigned int __nr_pages; + + page = virt_to_page(pages[pg]); + __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; + buf->buf[nbuf].page = page; + buf->buf[nbuf].offset = offset; + buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); + buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement; + pad = buf->buf[nbuf].size % BTS_RECORD_SIZE; + buf->buf[nbuf].size -= pad; + + pg += __nr_pages; + offset += __nr_pages << PAGE_SHIFT; + } + + return buf; +} + +static void bts_buffer_free_aux(void *data) +{ + kfree(data); +} + +static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx) +{ + return buf->buf[idx].offset + buf->buf[idx].displacement; +} + +static void +bts_config_buffer(struct bts_buffer *buf) +{ + int cpu = raw_smp_processor_id(); + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct bts_phys *phys = &buf->buf[buf->cur_buf]; + unsigned long index, thresh = 0, end = phys->size; + struct page *page = phys->page; + + index = local_read(&buf->head); + + if (!buf->snapshot) { + if (buf->end < phys->offset + buf_size(page)) + end = buf->end - phys->offset - phys->displacement; + + index -= phys->offset + phys->displacement; + + if (end - index > BTS_SAFETY_MARGIN) + thresh = end - BTS_SAFETY_MARGIN; + else if (end - index > BTS_RECORD_SIZE) + thresh = end - BTS_RECORD_SIZE; + else + thresh = end; + } + + ds->bts_buffer_base = (u64)(long)page_address(page) + phys->displacement; + ds->bts_index = ds->bts_buffer_base + index; + ds->bts_absolute_maximum = ds->bts_buffer_base + end; + ds->bts_interrupt_threshold = !buf->snapshot + ? ds->bts_buffer_base + thresh + : ds->bts_absolute_maximum + BTS_RECORD_SIZE; +} + +static void bts_buffer_pad_out(struct bts_phys *phys, unsigned long head) +{ + unsigned long index = head - phys->offset; + + memset(page_address(phys->page) + index, 0, phys->size - index); +} + +static bool bts_buffer_is_full(struct bts_buffer *buf, struct bts_ctx *bts) +{ + if (buf->snapshot) + return false; + + if (local_read(&buf->data_size) >= bts->handle.size || + bts->handle.size - local_read(&buf->data_size) < BTS_RECORD_SIZE) + return true; + + return false; +} + +static void bts_update(struct bts_ctx *bts) +{ + int cpu = raw_smp_processor_id(); + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct bts_buffer *buf = perf_get_aux(&bts->handle); + unsigned long index = ds->bts_index - ds->bts_buffer_base, old, head; + + if (!buf) + return; + + head = index + bts_buffer_offset(buf, buf->cur_buf); + old = local_xchg(&buf->head, head); + + if (!buf->snapshot) { + if (old == head) + return; + + if (ds->bts_index >= ds->bts_absolute_maximum) + local_inc(&buf->lost); + + /* + * old and head are always in the same physical buffer, so we + * can subtract them to get the data size. + */ + local_add(head - old, &buf->data_size); + } else { + local_set(&buf->data_size, head); + } +} + +static void __bts_event_start(struct perf_event *event) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf = perf_get_aux(&bts->handle); + u64 config = 0; + + if (!buf || bts_buffer_is_full(buf, bts)) + return; + + event->hw.state = 0; + + if (!buf->snapshot) + config |= ARCH_PERFMON_EVENTSEL_INT; + if (!event->attr.exclude_kernel) + config |= ARCH_PERFMON_EVENTSEL_OS; + if (!event->attr.exclude_user) + config |= ARCH_PERFMON_EVENTSEL_USR; + + bts_config_buffer(buf); + + /* + * local barrier to make sure that ds configuration made it + * before we enable BTS + */ + wmb(); + + intel_pmu_enable_bts(config); +} + +static void bts_event_start(struct perf_event *event, int flags) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + __bts_event_start(event); + + /* PMI handler: this counter is running and likely generating PMIs */ + ACCESS_ONCE(bts->started) = 1; +} + +static void __bts_event_stop(struct perf_event *event) +{ + /* + * No extra synchronization is mandated by the documentation to have + * BTS data stores globally visible. + */ + intel_pmu_disable_bts(); + + if (event->hw.state & PERF_HES_STOPPED) + return; + + ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED; +} + +static void bts_event_stop(struct perf_event *event, int flags) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + /* PMI handler: don't restart this counter */ + ACCESS_ONCE(bts->started) = 0; + + __bts_event_stop(event); + + if (flags & PERF_EF_UPDATE) + bts_update(bts); +} + +void intel_bts_enable_local(void) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + if (bts->handle.event && bts->started) + __bts_event_start(bts->handle.event); +} + +void intel_bts_disable_local(void) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + if (bts->handle.event) + __bts_event_stop(bts->handle.event); +} + +static int +bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle) +{ + unsigned long head, space, next_space, pad, gap, skip, wakeup; + unsigned int next_buf; + struct bts_phys *phys, *next_phys; + int ret; + + if (buf->snapshot) + return 0; + + head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); + if (WARN_ON_ONCE(head != local_read(&buf->head))) + return -EINVAL; + + phys = &buf->buf[buf->cur_buf]; + space = phys->offset + phys->displacement + phys->size - head; + pad = space; + if (space > handle->size) { + space = handle->size; + space -= space % BTS_RECORD_SIZE; + } + if (space <= BTS_SAFETY_MARGIN) { + /* See if next phys buffer has more space */ + next_buf = buf->cur_buf + 1; + if (next_buf >= buf->nr_bufs) + next_buf = 0; + next_phys = &buf->buf[next_buf]; + gap = buf_size(phys->page) - phys->displacement - phys->size + + next_phys->displacement; + skip = pad + gap; + if (handle->size >= skip) { + next_space = next_phys->size; + if (next_space + skip > handle->size) { + next_space = handle->size - skip; + next_space -= next_space % BTS_RECORD_SIZE; + } + if (next_space > space || !space) { + if (pad) + bts_buffer_pad_out(phys, head); + ret = perf_aux_output_skip(handle, skip); + if (ret) + return ret; + /* Advance to next phys buffer */ + phys = next_phys; + space = next_space; + head = phys->offset + phys->displacement; + /* + * After this, cur_buf and head won't match ds + * anymore, so we must not be racing with + * bts_update(). + */ + buf->cur_buf = next_buf; + local_set(&buf->head, head); + } + } + } + + /* Don't go far beyond wakeup watermark */ + wakeup = BTS_SAFETY_MARGIN + BTS_RECORD_SIZE + handle->wakeup - + handle->head; + if (space > wakeup) { + space = wakeup; + space -= space % BTS_RECORD_SIZE; + } + + buf->end = head + space; + + /* + * If we have no space, the lost notification would have been sent when + * we hit absolute_maximum - see bts_update() + */ + if (!space) + return -ENOSPC; + + return 0; +} + +int intel_bts_interrupt(void) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct perf_event *event = bts->handle.event; + struct bts_buffer *buf; + s64 old_head; + int err; + + if (!event || !bts->started) + return 0; + + buf = perf_get_aux(&bts->handle); + /* + * Skip snapshot counters: they don't use the interrupt, but + * there's no other way of telling, because the pointer will + * keep moving + */ + if (!buf || buf->snapshot) + return 0; + + old_head = local_read(&buf->head); + bts_update(bts); + + /* no new data */ + if (old_head == local_read(&buf->head)) + return 0; + + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), + !!local_xchg(&buf->lost, 0)); + + buf = perf_aux_output_begin(&bts->handle, event); + if (!buf) + return 1; + + err = bts_buffer_reset(buf, &bts->handle); + if (err) + perf_aux_output_end(&bts->handle, 0, false); + + return 1; +} + +static void bts_event_del(struct perf_event *event, int mode) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf = perf_get_aux(&bts->handle); + + bts_event_stop(event, PERF_EF_UPDATE); + + if (buf) { + if (buf->snapshot) + bts->handle.head = + local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), + !!local_xchg(&buf->lost, 0)); + } + + cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; + cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; +} + +static int bts_event_add(struct perf_event *event, int mode) +{ + struct bts_buffer *buf; + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int ret = -EBUSY; + + event->hw.state = PERF_HES_STOPPED; + + if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + return -EBUSY; + + if (bts->handle.event) + return -EBUSY; + + buf = perf_aux_output_begin(&bts->handle, event); + if (!buf) + return -EINVAL; + + ret = bts_buffer_reset(buf, &bts->handle); + if (ret) { + perf_aux_output_end(&bts->handle, 0, false); + return ret; + } + + bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; + bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; + bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; + + if (mode & PERF_EF_START) { + bts_event_start(event, 0); + if (hwc->state & PERF_HES_STOPPED) { + bts_event_del(event, 0); + return -EBUSY; + } + } + + return 0; +} + +static void bts_event_destroy(struct perf_event *event) +{ + x86_del_exclusive(x86_lbr_exclusive_bts); +} + +static int bts_event_init(struct perf_event *event) +{ + if (event->attr.type != bts_pmu.type) + return -ENOENT; + + if (x86_add_exclusive(x86_lbr_exclusive_bts)) + return -EBUSY; + + event->destroy = bts_event_destroy; + + return 0; +} + +static void bts_event_read(struct perf_event *event) +{ +} + +static __init int bts_init(void) +{ + if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts) + return -ENODEV; + + bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE; + bts_pmu.task_ctx_nr = perf_sw_context; + bts_pmu.event_init = bts_event_init; + bts_pmu.add = bts_event_add; + bts_pmu.del = bts_event_del; + bts_pmu.start = bts_event_start; + bts_pmu.stop = bts_event_stop; + bts_pmu.read = bts_event_read; + bts_pmu.setup_aux = bts_buffer_setup_aux; + bts_pmu.free_aux = bts_buffer_free_aux; + + return perf_pmu_register(&bts_pmu, "intel_bts", -1); +} + +module_init(bts_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c new file mode 100644 index 0000000..e4d1b8b --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -0,0 +1,1379 @@ +/* + * Intel Cache Quality-of-Service Monitoring (CQM) support. + * + * Based very, very heavily on work by Peter Zijlstra. + */ + +#include <linux/perf_event.h> +#include <linux/slab.h> +#include <asm/cpu_device_id.h> +#include "perf_event.h" + +#define MSR_IA32_PQR_ASSOC 0x0c8f +#define MSR_IA32_QM_CTR 0x0c8e +#define MSR_IA32_QM_EVTSEL 0x0c8d + +static unsigned int cqm_max_rmid = -1; +static unsigned int cqm_l3_scale; /* supposedly cacheline size */ + +struct intel_cqm_state { + raw_spinlock_t lock; + int rmid; + int cnt; +}; + +static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); + +/* + * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. + * Also protects event->hw.cqm_rmid + * + * Hold either for stability, both for modification of ->hw.cqm_rmid. + */ +static DEFINE_MUTEX(cache_mutex); +static DEFINE_RAW_SPINLOCK(cache_lock); + +/* + * Groups of events that have the same target(s), one RMID per group. + */ +static LIST_HEAD(cache_groups); + +/* + * Mask of CPUs for reading CQM values. We only need one per-socket. + */ +static cpumask_t cqm_cpumask; + +#define RMID_VAL_ERROR (1ULL << 63) +#define RMID_VAL_UNAVAIL (1ULL << 62) + +#define QOS_L3_OCCUP_EVENT_ID (1 << 0) + +#define QOS_EVENT_MASK QOS_L3_OCCUP_EVENT_ID + +/* + * This is central to the rotation algorithm in __intel_cqm_rmid_rotate(). + * + * This rmid is always free and is guaranteed to have an associated + * near-zero occupancy value, i.e. no cachelines are tagged with this + * RMID, once __intel_cqm_rmid_rotate() returns. + */ +static unsigned int intel_cqm_rotation_rmid; + +#define INVALID_RMID (-1) + +/* + * Is @rmid valid for programming the hardware? + * + * rmid 0 is reserved by the hardware for all non-monitored tasks, which + * means that we should never come across an rmid with that value. + * Likewise, an rmid value of -1 is used to indicate "no rmid currently + * assigned" and is used as part of the rotation code. + */ +static inline bool __rmid_valid(unsigned int rmid) +{ + if (!rmid || rmid == INVALID_RMID) + return false; + + return true; +} + +static u64 __rmid_read(unsigned int rmid) +{ + u64 val; + + /* + * Ignore the SDM, this thing is _NOTHING_ like a regular perfcnt, + * it just says that to increase confusion. + */ + wrmsr(MSR_IA32_QM_EVTSEL, QOS_L3_OCCUP_EVENT_ID, rmid); + rdmsrl(MSR_IA32_QM_CTR, val); + + /* + * Aside from the ERROR and UNAVAIL bits, assume this thing returns + * the number of cachelines tagged with @rmid. + */ + return val; +} + +enum rmid_recycle_state { + RMID_YOUNG = 0, + RMID_AVAILABLE, + RMID_DIRTY, +}; + +struct cqm_rmid_entry { + unsigned int rmid; + enum rmid_recycle_state state; + struct list_head list; + unsigned long queue_time; +}; + +/* + * cqm_rmid_free_lru - A least recently used list of RMIDs. + * + * Oldest entry at the head, newest (most recently used) entry at the + * tail. This list is never traversed, it's only used to keep track of + * the lru order. That is, we only pick entries of the head or insert + * them on the tail. + * + * All entries on the list are 'free', and their RMIDs are not currently + * in use. To mark an RMID as in use, remove its entry from the lru + * list. + * + * + * cqm_rmid_limbo_lru - list of currently unused but (potentially) dirty RMIDs. + * + * This list is contains RMIDs that no one is currently using but that + * may have a non-zero occupancy value associated with them. The + * rotation worker moves RMIDs from the limbo list to the free list once + * the occupancy value drops below __intel_cqm_threshold. + * + * Both lists are protected by cache_mutex. + */ +static LIST_HEAD(cqm_rmid_free_lru); +static LIST_HEAD(cqm_rmid_limbo_lru); + +/* + * We use a simple array of pointers so that we can lookup a struct + * cqm_rmid_entry in O(1). This alleviates the callers of __get_rmid() + * and __put_rmid() from having to worry about dealing with struct + * cqm_rmid_entry - they just deal with rmids, i.e. integers. + * + * Once this array is initialized it is read-only. No locks are required + * to access it. + * + * All entries for all RMIDs can be looked up in the this array at all + * times. + */ +static struct cqm_rmid_entry **cqm_rmid_ptrs; + +static inline struct cqm_rmid_entry *__rmid_entry(int rmid) +{ + struct cqm_rmid_entry *entry; + + entry = cqm_rmid_ptrs[rmid]; + WARN_ON(entry->rmid != rmid); + + return entry; +} + +/* + * Returns < 0 on fail. + * + * We expect to be called with cache_mutex held. + */ +static int __get_rmid(void) +{ + struct cqm_rmid_entry *entry; + + lockdep_assert_held(&cache_mutex); + + if (list_empty(&cqm_rmid_free_lru)) + return INVALID_RMID; + + entry = list_first_entry(&cqm_rmid_free_lru, struct cqm_rmid_entry, list); + list_del(&entry->list); + + return entry->rmid; +} + +static void __put_rmid(unsigned int rmid) +{ + struct cqm_rmid_entry *entry; + + lockdep_assert_held(&cache_mutex); + + WARN_ON(!__rmid_valid(rmid)); + entry = __rmid_entry(rmid); + + entry->queue_time = jiffies; + entry->state = RMID_YOUNG; + + list_add_tail(&entry->list, &cqm_rmid_limbo_lru); +} + +static int intel_cqm_setup_rmid_cache(void) +{ + struct cqm_rmid_entry *entry; + unsigned int nr_rmids; + int r = 0; + + nr_rmids = cqm_max_rmid + 1; + cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) * + nr_rmids, GFP_KERNEL); + if (!cqm_rmid_ptrs) + return -ENOMEM; + + for (; r <= cqm_max_rmid; r++) { + struct cqm_rmid_entry *entry; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto fail; + + INIT_LIST_HEAD(&entry->list); + entry->rmid = r; + cqm_rmid_ptrs[r] = entry; + + list_add_tail(&entry->list, &cqm_rmid_free_lru); + } + + /* + * RMID 0 is special and is always allocated. It's used for all + * tasks that are not monitored. + */ + entry = __rmid_entry(0); + list_del(&entry->list); + + mutex_lock(&cache_mutex); + intel_cqm_rotation_rmid = __get_rmid(); + mutex_unlock(&cache_mutex); + + return 0; +fail: + while (r--) + kfree(cqm_rmid_ptrs[r]); + + kfree(cqm_rmid_ptrs); + return -ENOMEM; +} + +/* + * Determine if @a and @b measure the same set of tasks. + * + * If @a and @b measure the same set of tasks then we want to share a + * single RMID. + */ +static bool __match_event(struct perf_event *a, struct perf_event *b) +{ + /* Per-cpu and task events don't mix */ + if ((a->attach_state & PERF_ATTACH_TASK) != + (b->attach_state & PERF_ATTACH_TASK)) + return false; + +#ifdef CONFIG_CGROUP_PERF + if (a->cgrp != b->cgrp) + return false; +#endif + + /* If not task event, we're machine wide */ + if (!(b->attach_state & PERF_ATTACH_TASK)) + return true; + + /* + * Events that target same task are placed into the same cache group. + */ + if (a->hw.target == b->hw.target) + return true; + + /* + * Are we an inherited event? + */ + if (b->parent == a) + return true; + + return false; +} + +#ifdef CONFIG_CGROUP_PERF +static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) +{ + if (event->attach_state & PERF_ATTACH_TASK) + return perf_cgroup_from_task(event->hw.target); + + return event->cgrp; +} +#endif + +/* + * Determine if @a's tasks intersect with @b's tasks + * + * There are combinations of events that we explicitly prohibit, + * + * PROHIBITS + * system-wide -> cgroup and task + * cgroup -> system-wide + * -> task in cgroup + * task -> system-wide + * -> task in cgroup + * + * Call this function before allocating an RMID. + */ +static bool __conflict_event(struct perf_event *a, struct perf_event *b) +{ +#ifdef CONFIG_CGROUP_PERF + /* + * We can have any number of cgroups but only one system-wide + * event at a time. + */ + if (a->cgrp && b->cgrp) { + struct perf_cgroup *ac = a->cgrp; + struct perf_cgroup *bc = b->cgrp; + + /* + * This condition should have been caught in + * __match_event() and we should be sharing an RMID. + */ + WARN_ON_ONCE(ac == bc); + + if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || + cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) + return true; + + return false; + } + + if (a->cgrp || b->cgrp) { + struct perf_cgroup *ac, *bc; + + /* + * cgroup and system-wide events are mutually exclusive + */ + if ((a->cgrp && !(b->attach_state & PERF_ATTACH_TASK)) || + (b->cgrp && !(a->attach_state & PERF_ATTACH_TASK))) + return true; + + /* + * Ensure neither event is part of the other's cgroup + */ + ac = event_to_cgroup(a); + bc = event_to_cgroup(b); + if (ac == bc) + return true; + + /* + * Must have cgroup and non-intersecting task events. + */ + if (!ac || !bc) + return false; + + /* + * We have cgroup and task events, and the task belongs + * to a cgroup. Check for for overlap. + */ + if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || + cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) + return true; + + return false; + } +#endif + /* + * If one of them is not a task, same story as above with cgroups. + */ + if (!(a->attach_state & PERF_ATTACH_TASK) || + !(b->attach_state & PERF_ATTACH_TASK)) + return true; + + /* + * Must be non-overlapping. + */ + return false; +} + +struct rmid_read { + unsigned int rmid; + atomic64_t value; +}; + +static void __intel_cqm_event_count(void *info); + +/* + * Exchange the RMID of a group of events. + */ +static unsigned int +intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid) +{ + struct perf_event *event; + unsigned int old_rmid = group->hw.cqm_rmid; + struct list_head *head = &group->hw.cqm_group_entry; + + lockdep_assert_held(&cache_mutex); + + /* + * If our RMID is being deallocated, perform a read now. + */ + if (__rmid_valid(old_rmid) && !__rmid_valid(rmid)) { + struct rmid_read rr = { + .value = ATOMIC64_INIT(0), + .rmid = old_rmid, + }; + + on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, + &rr, 1); + local64_set(&group->count, atomic64_read(&rr.value)); + } + + raw_spin_lock_irq(&cache_lock); + + group->hw.cqm_rmid = rmid; + list_for_each_entry(event, head, hw.cqm_group_entry) + event->hw.cqm_rmid = rmid; + + raw_spin_unlock_irq(&cache_lock); + + return old_rmid; +} + +/* + * If we fail to assign a new RMID for intel_cqm_rotation_rmid because + * cachelines are still tagged with RMIDs in limbo, we progressively + * increment the threshold until we find an RMID in limbo with <= + * __intel_cqm_threshold lines tagged. This is designed to mitigate the + * problem where cachelines tagged with an RMID are not steadily being + * evicted. + * + * On successful rotations we decrease the threshold back towards zero. + * + * __intel_cqm_max_threshold provides an upper bound on the threshold, + * and is measured in bytes because it's exposed to userland. + */ +static unsigned int __intel_cqm_threshold; +static unsigned int __intel_cqm_max_threshold; + +/* + * Test whether an RMID has a zero occupancy value on this cpu. + */ +static void intel_cqm_stable(void *arg) +{ + struct cqm_rmid_entry *entry; + + list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { + if (entry->state != RMID_AVAILABLE) + break; + + if (__rmid_read(entry->rmid) > __intel_cqm_threshold) + entry->state = RMID_DIRTY; + } +} + +/* + * If we have group events waiting for an RMID that don't conflict with + * events already running, assign @rmid. + */ +static bool intel_cqm_sched_in_event(unsigned int rmid) +{ + struct perf_event *leader, *event; + + lockdep_assert_held(&cache_mutex); + + leader = list_first_entry(&cache_groups, struct perf_event, + hw.cqm_groups_entry); + event = leader; + + list_for_each_entry_continue(event, &cache_groups, + hw.cqm_groups_entry) { + if (__rmid_valid(event->hw.cqm_rmid)) + continue; + + if (__conflict_event(event, leader)) + continue; + + intel_cqm_xchg_rmid(event, rmid); + return true; + } + + return false; +} + +/* + * Initially use this constant for both the limbo queue time and the + * rotation timer interval, pmu::hrtimer_interval_ms. + * + * They don't need to be the same, but the two are related since if you + * rotate faster than you recycle RMIDs, you may run out of available + * RMIDs. + */ +#define RMID_DEFAULT_QUEUE_TIME 250 /* ms */ + +static unsigned int __rmid_queue_time_ms = RMID_DEFAULT_QUEUE_TIME; + +/* + * intel_cqm_rmid_stabilize - move RMIDs from limbo to free list + * @nr_available: number of freeable RMIDs on the limbo list + * + * Quiescent state; wait for all 'freed' RMIDs to become unused, i.e. no + * cachelines are tagged with those RMIDs. After this we can reuse them + * and know that the current set of active RMIDs is stable. + * + * Return %true or %false depending on whether stabilization needs to be + * reattempted. + * + * If we return %true then @nr_available is updated to indicate the + * number of RMIDs on the limbo list that have been queued for the + * minimum queue time (RMID_AVAILABLE), but whose data occupancy values + * are above __intel_cqm_threshold. + */ +static bool intel_cqm_rmid_stabilize(unsigned int *available) +{ + struct cqm_rmid_entry *entry, *tmp; + + lockdep_assert_held(&cache_mutex); + + *available = 0; + list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { + unsigned long min_queue_time; + unsigned long now = jiffies; + + /* + * We hold RMIDs placed into limbo for a minimum queue + * time. Before the minimum queue time has elapsed we do + * not recycle RMIDs. + * + * The reasoning is that until a sufficient time has + * passed since we stopped using an RMID, any RMID + * placed onto the limbo list will likely still have + * data tagged in the cache, which means we'll probably + * fail to recycle it anyway. + * + * We can save ourselves an expensive IPI by skipping + * any RMIDs that have not been queued for the minimum + * time. + */ + min_queue_time = entry->queue_time + + msecs_to_jiffies(__rmid_queue_time_ms); + + if (time_after(min_queue_time, now)) + break; + + entry->state = RMID_AVAILABLE; + (*available)++; + } + + /* + * Fast return if none of the RMIDs on the limbo list have been + * sitting on the queue for the minimum queue time. + */ + if (!*available) + return false; + + /* + * Test whether an RMID is free for each package. + */ + on_each_cpu_mask(&cqm_cpumask, intel_cqm_stable, NULL, true); + + list_for_each_entry_safe(entry, tmp, &cqm_rmid_limbo_lru, list) { + /* + * Exhausted all RMIDs that have waited min queue time. + */ + if (entry->state == RMID_YOUNG) + break; + + if (entry->state == RMID_DIRTY) + continue; + + list_del(&entry->list); /* remove from limbo */ + + /* + * The rotation RMID gets priority if it's + * currently invalid. In which case, skip adding + * the RMID to the the free lru. + */ + if (!__rmid_valid(intel_cqm_rotation_rmid)) { + intel_cqm_rotation_rmid = entry->rmid; + continue; + } + + /* + * If we have groups waiting for RMIDs, hand + * them one now provided they don't conflict. + */ + if (intel_cqm_sched_in_event(entry->rmid)) + continue; + + /* + * Otherwise place it onto the free list. + */ + list_add_tail(&entry->list, &cqm_rmid_free_lru); + } + + + return __rmid_valid(intel_cqm_rotation_rmid); +} + +/* + * Pick a victim group and move it to the tail of the group list. + * @next: The first group without an RMID + */ +static void __intel_cqm_pick_and_rotate(struct perf_event *next) +{ + struct perf_event *rotor; + unsigned int rmid; + + lockdep_assert_held(&cache_mutex); + + rotor = list_first_entry(&cache_groups, struct perf_event, + hw.cqm_groups_entry); + + /* + * The group at the front of the list should always have a valid + * RMID. If it doesn't then no groups have RMIDs assigned and we + * don't need to rotate the list. + */ + if (next == rotor) + return; + + rmid = intel_cqm_xchg_rmid(rotor, INVALID_RMID); + __put_rmid(rmid); + + list_rotate_left(&cache_groups); +} + +/* + * Deallocate the RMIDs from any events that conflict with @event, and + * place them on the back of the group list. + */ +static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) +{ + struct perf_event *group, *g; + unsigned int rmid; + + lockdep_assert_held(&cache_mutex); + + list_for_each_entry_safe(group, g, &cache_groups, hw.cqm_groups_entry) { + if (group == event) + continue; + + rmid = group->hw.cqm_rmid; + + /* + * Skip events that don't have a valid RMID. + */ + if (!__rmid_valid(rmid)) + continue; + + /* + * No conflict? No problem! Leave the event alone. + */ + if (!__conflict_event(group, event)) + continue; + + intel_cqm_xchg_rmid(group, INVALID_RMID); + __put_rmid(rmid); + } +} + +/* + * Attempt to rotate the groups and assign new RMIDs. + * + * We rotate for two reasons, + * 1. To handle the scheduling of conflicting events + * 2. To recycle RMIDs + * + * Rotating RMIDs is complicated because the hardware doesn't give us + * any clues. + * + * There's problems with the hardware interface; when you change the + * task:RMID map cachelines retain their 'old' tags, giving a skewed + * picture. In order to work around this, we must always keep one free + * RMID - intel_cqm_rotation_rmid. + * + * Rotation works by taking away an RMID from a group (the old RMID), + * and assigning the free RMID to another group (the new RMID). We must + * then wait for the old RMID to not be used (no cachelines tagged). + * This ensure that all cachelines are tagged with 'active' RMIDs. At + * this point we can start reading values for the new RMID and treat the + * old RMID as the free RMID for the next rotation. + * + * Return %true or %false depending on whether we did any rotating. + */ +static bool __intel_cqm_rmid_rotate(void) +{ + struct perf_event *group, *start = NULL; + unsigned int threshold_limit; + unsigned int nr_needed = 0; + unsigned int nr_available; + bool rotated = false; + + mutex_lock(&cache_mutex); + +again: + /* + * Fast path through this function if there are no groups and no + * RMIDs that need cleaning. + */ + if (list_empty(&cache_groups) && list_empty(&cqm_rmid_limbo_lru)) + goto out; + + list_for_each_entry(group, &cache_groups, hw.cqm_groups_entry) { + if (!__rmid_valid(group->hw.cqm_rmid)) { + if (!start) + start = group; + nr_needed++; + } + } + + /* + * We have some event groups, but they all have RMIDs assigned + * and no RMIDs need cleaning. + */ + if (!nr_needed && list_empty(&cqm_rmid_limbo_lru)) + goto out; + + if (!nr_needed) + goto stabilize; + + /* + * We have more event groups without RMIDs than available RMIDs, + * or we have event groups that conflict with the ones currently + * scheduled. + * + * We force deallocate the rmid of the group at the head of + * cache_groups. The first event group without an RMID then gets + * assigned intel_cqm_rotation_rmid. This ensures we always make + * forward progress. + * + * Rotate the cache_groups list so the previous head is now the + * tail. + */ + __intel_cqm_pick_and_rotate(start); + + /* + * If the rotation is going to succeed, reduce the threshold so + * that we don't needlessly reuse dirty RMIDs. + */ + if (__rmid_valid(intel_cqm_rotation_rmid)) { + intel_cqm_xchg_rmid(start, intel_cqm_rotation_rmid); + intel_cqm_rotation_rmid = __get_rmid(); + + intel_cqm_sched_out_conflicting_events(start); + + if (__intel_cqm_threshold) + __intel_cqm_threshold--; + } + + rotated = true; + +stabilize: + /* + * We now need to stablize the RMID we freed above (if any) to + * ensure that the next time we rotate we have an RMID with zero + * occupancy value. + * + * Alternatively, if we didn't need to perform any rotation, + * we'll have a bunch of RMIDs in limbo that need stabilizing. + */ + threshold_limit = __intel_cqm_max_threshold / cqm_l3_scale; + + while (intel_cqm_rmid_stabilize(&nr_available) && + __intel_cqm_threshold < threshold_limit) { + unsigned int steal_limit; + + /* + * Don't spin if nobody is actively waiting for an RMID, + * the rotation worker will be kicked as soon as an + * event needs an RMID anyway. + */ + if (!nr_needed) + break; + + /* Allow max 25% of RMIDs to be in limbo. */ + steal_limit = (cqm_max_rmid + 1) / 4; + + /* + * We failed to stabilize any RMIDs so our rotation + * logic is now stuck. In order to make forward progress + * we have a few options: + * + * 1. rotate ("steal") another RMID + * 2. increase the threshold + * 3. do nothing + * + * We do both of 1. and 2. until we hit the steal limit. + * + * The steal limit prevents all RMIDs ending up on the + * limbo list. This can happen if every RMID has a + * non-zero occupancy above threshold_limit, and the + * occupancy values aren't dropping fast enough. + * + * Note that there is prioritisation at work here - we'd + * rather increase the number of RMIDs on the limbo list + * than increase the threshold, because increasing the + * threshold skews the event data (because we reuse + * dirty RMIDs) - threshold bumps are a last resort. + */ + if (nr_available < steal_limit) + goto again; + + __intel_cqm_threshold++; + } + +out: + mutex_unlock(&cache_mutex); + return rotated; +} + +static void intel_cqm_rmid_rotate(struct work_struct *work); + +static DECLARE_DELAYED_WORK(intel_cqm_rmid_work, intel_cqm_rmid_rotate); + +static struct pmu intel_cqm_pmu; + +static void intel_cqm_rmid_rotate(struct work_struct *work) +{ + unsigned long delay; + + __intel_cqm_rmid_rotate(); + + delay = msecs_to_jiffies(intel_cqm_pmu.hrtimer_interval_ms); + schedule_delayed_work(&intel_cqm_rmid_work, delay); +} + +/* + * Find a group and setup RMID. + * + * If we're part of a group, we use the group's RMID. + */ +static void intel_cqm_setup_event(struct perf_event *event, + struct perf_event **group) +{ + struct perf_event *iter; + unsigned int rmid; + bool conflict = false; + + list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { + rmid = iter->hw.cqm_rmid; + + if (__match_event(iter, event)) { + /* All tasks in a group share an RMID */ + event->hw.cqm_rmid = rmid; + *group = iter; + return; + } + + /* + * We only care about conflicts for events that are + * actually scheduled in (and hence have a valid RMID). + */ + if (__conflict_event(iter, event) && __rmid_valid(rmid)) + conflict = true; + } + + if (conflict) + rmid = INVALID_RMID; + else + rmid = __get_rmid(); + + event->hw.cqm_rmid = rmid; +} + +static void intel_cqm_event_read(struct perf_event *event) +{ + unsigned long flags; + unsigned int rmid; + u64 val; + + /* + * Task events are handled by intel_cqm_event_count(). + */ + if (event->cpu == -1) + return; + + raw_spin_lock_irqsave(&cache_lock, flags); + rmid = event->hw.cqm_rmid; + + if (!__rmid_valid(rmid)) + goto out; + + val = __rmid_read(rmid); + + /* + * Ignore this reading on error states and do not update the value. + */ + if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) + goto out; + + local64_set(&event->count, val); +out: + raw_spin_unlock_irqrestore(&cache_lock, flags); +} + +static void __intel_cqm_event_count(void *info) +{ + struct rmid_read *rr = info; + u64 val; + + val = __rmid_read(rr->rmid); + + if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) + return; + + atomic64_add(val, &rr->value); +} + +static inline bool cqm_group_leader(struct perf_event *event) +{ + return !list_empty(&event->hw.cqm_groups_entry); +} + +static u64 intel_cqm_event_count(struct perf_event *event) +{ + unsigned long flags; + struct rmid_read rr = { + .value = ATOMIC64_INIT(0), + }; + + /* + * We only need to worry about task events. System-wide events + * are handled like usual, i.e. entirely with + * intel_cqm_event_read(). + */ + if (event->cpu != -1) + return __perf_event_count(event); + + /* + * Only the group leader gets to report values. This stops us + * reporting duplicate values to userspace, and gives us a clear + * rule for which task gets to report the values. + * + * Note that it is impossible to attribute these values to + * specific packages - we forfeit that ability when we create + * task events. + */ + if (!cqm_group_leader(event)) + return 0; + + /* + * Notice that we don't perform the reading of an RMID + * atomically, because we can't hold a spin lock across the + * IPIs. + * + * Speculatively perform the read, since @event might be + * assigned a different (possibly invalid) RMID while we're + * busying performing the IPI calls. It's therefore necessary to + * check @event's RMID afterwards, and if it has changed, + * discard the result of the read. + */ + rr.rmid = ACCESS_ONCE(event->hw.cqm_rmid); + + if (!__rmid_valid(rr.rmid)) + goto out; + + on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, &rr, 1); + + raw_spin_lock_irqsave(&cache_lock, flags); + if (event->hw.cqm_rmid == rr.rmid) + local64_set(&event->count, atomic64_read(&rr.value)); + raw_spin_unlock_irqrestore(&cache_lock, flags); +out: + return __perf_event_count(event); +} + +static void intel_cqm_event_start(struct perf_event *event, int mode) +{ + struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); + unsigned int rmid = event->hw.cqm_rmid; + unsigned long flags; + + if (!(event->hw.cqm_state & PERF_HES_STOPPED)) + return; + + event->hw.cqm_state &= ~PERF_HES_STOPPED; + + raw_spin_lock_irqsave(&state->lock, flags); + + if (state->cnt++) + WARN_ON_ONCE(state->rmid != rmid); + else + WARN_ON_ONCE(state->rmid); + + state->rmid = rmid; + wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid); + + raw_spin_unlock_irqrestore(&state->lock, flags); +} + +static void intel_cqm_event_stop(struct perf_event *event, int mode) +{ + struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); + unsigned long flags; + + if (event->hw.cqm_state & PERF_HES_STOPPED) + return; + + event->hw.cqm_state |= PERF_HES_STOPPED; + + raw_spin_lock_irqsave(&state->lock, flags); + intel_cqm_event_read(event); + + if (!--state->cnt) { + state->rmid = 0; + wrmsrl(MSR_IA32_PQR_ASSOC, 0); + } else { + WARN_ON_ONCE(!state->rmid); + } + + raw_spin_unlock_irqrestore(&state->lock, flags); +} + +static int intel_cqm_event_add(struct perf_event *event, int mode) +{ + unsigned long flags; + unsigned int rmid; + + raw_spin_lock_irqsave(&cache_lock, flags); + + event->hw.cqm_state = PERF_HES_STOPPED; + rmid = event->hw.cqm_rmid; + + if (__rmid_valid(rmid) && (mode & PERF_EF_START)) + intel_cqm_event_start(event, mode); + + raw_spin_unlock_irqrestore(&cache_lock, flags); + + return 0; +} + +static void intel_cqm_event_del(struct perf_event *event, int mode) +{ + intel_cqm_event_stop(event, mode); +} + +static void intel_cqm_event_destroy(struct perf_event *event) +{ + struct perf_event *group_other = NULL; + + mutex_lock(&cache_mutex); + + /* + * If there's another event in this group... + */ + if (!list_empty(&event->hw.cqm_group_entry)) { + group_other = list_first_entry(&event->hw.cqm_group_entry, + struct perf_event, + hw.cqm_group_entry); + list_del(&event->hw.cqm_group_entry); + } + + /* + * And we're the group leader.. + */ + if (cqm_group_leader(event)) { + /* + * If there was a group_other, make that leader, otherwise + * destroy the group and return the RMID. + */ + if (group_other) { + list_replace(&event->hw.cqm_groups_entry, + &group_other->hw.cqm_groups_entry); + } else { + unsigned int rmid = event->hw.cqm_rmid; + + if (__rmid_valid(rmid)) + __put_rmid(rmid); + list_del(&event->hw.cqm_groups_entry); + } + } + + mutex_unlock(&cache_mutex); +} + +static int intel_cqm_event_init(struct perf_event *event) +{ + struct perf_event *group = NULL; + bool rotate = false; + + if (event->attr.type != intel_cqm_pmu.type) + return -ENOENT; + + if (event->attr.config & ~QOS_EVENT_MASK) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + INIT_LIST_HEAD(&event->hw.cqm_group_entry); + INIT_LIST_HEAD(&event->hw.cqm_groups_entry); + + event->destroy = intel_cqm_event_destroy; + + mutex_lock(&cache_mutex); + + /* Will also set rmid */ + intel_cqm_setup_event(event, &group); + + if (group) { + list_add_tail(&event->hw.cqm_group_entry, + &group->hw.cqm_group_entry); + } else { + list_add_tail(&event->hw.cqm_groups_entry, + &cache_groups); + + /* + * All RMIDs are either in use or have recently been + * used. Kick the rotation worker to clean/free some. + * + * We only do this for the group leader, rather than for + * every event in a group to save on needless work. + */ + if (!__rmid_valid(event->hw.cqm_rmid)) + rotate = true; + } + + mutex_unlock(&cache_mutex); + + if (rotate) + schedule_delayed_work(&intel_cqm_rmid_work, 0); + + return 0; +} + +EVENT_ATTR_STR(llc_occupancy, intel_cqm_llc, "event=0x01"); +EVENT_ATTR_STR(llc_occupancy.per-pkg, intel_cqm_llc_pkg, "1"); +EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes"); +EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL); +EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1"); + +static struct attribute *intel_cqm_events_attr[] = { + EVENT_PTR(intel_cqm_llc), + EVENT_PTR(intel_cqm_llc_pkg), + EVENT_PTR(intel_cqm_llc_unit), + EVENT_PTR(intel_cqm_llc_scale), + EVENT_PTR(intel_cqm_llc_snapshot), + NULL, +}; + +static struct attribute_group intel_cqm_events_group = { + .name = "events", + .attrs = intel_cqm_events_attr, +}; + +PMU_FORMAT_ATTR(event, "config:0-7"); +static struct attribute *intel_cqm_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group intel_cqm_format_group = { + .name = "format", + .attrs = intel_cqm_formats_attr, +}; + +static ssize_t +max_recycle_threshold_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + ssize_t rv; + + mutex_lock(&cache_mutex); + rv = snprintf(page, PAGE_SIZE-1, "%u\n", __intel_cqm_max_threshold); + mutex_unlock(&cache_mutex); + + return rv; +} + +static ssize_t +max_recycle_threshold_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned int bytes, cachelines; + int ret; + + ret = kstrtouint(buf, 0, &bytes); + if (ret) + return ret; + + mutex_lock(&cache_mutex); + + __intel_cqm_max_threshold = bytes; + cachelines = bytes / cqm_l3_scale; + + /* + * The new maximum takes effect immediately. + */ + if (__intel_cqm_threshold > cachelines) + __intel_cqm_threshold = cachelines; + + mutex_unlock(&cache_mutex); + + return count; +} + +static DEVICE_ATTR_RW(max_recycle_threshold); + +static struct attribute *intel_cqm_attrs[] = { + &dev_attr_max_recycle_threshold.attr, + NULL, +}; + +static const struct attribute_group intel_cqm_group = { + .attrs = intel_cqm_attrs, +}; + +static const struct attribute_group *intel_cqm_attr_groups[] = { + &intel_cqm_events_group, + &intel_cqm_format_group, + &intel_cqm_group, + NULL, +}; + +static struct pmu intel_cqm_pmu = { + .hrtimer_interval_ms = RMID_DEFAULT_QUEUE_TIME, + .attr_groups = intel_cqm_attr_groups, + .task_ctx_nr = perf_sw_context, + .event_init = intel_cqm_event_init, + .add = intel_cqm_event_add, + .del = intel_cqm_event_del, + .start = intel_cqm_event_start, + .stop = intel_cqm_event_stop, + .read = intel_cqm_event_read, + .count = intel_cqm_event_count, +}; + +static inline void cqm_pick_event_reader(int cpu) +{ + int phys_id = topology_physical_package_id(cpu); + int i; + + for_each_cpu(i, &cqm_cpumask) { + if (phys_id == topology_physical_package_id(i)) + return; /* already got reader for this socket */ + } + + cpumask_set_cpu(cpu, &cqm_cpumask); +} + +static void intel_cqm_cpu_prepare(unsigned int cpu) +{ + struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct cpuinfo_x86 *c = &cpu_data(cpu); + + raw_spin_lock_init(&state->lock); + state->rmid = 0; + state->cnt = 0; + + WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); + WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); +} + +static void intel_cqm_cpu_exit(unsigned int cpu) +{ + int phys_id = topology_physical_package_id(cpu); + int i; + + /* + * Is @cpu a designated cqm reader? + */ + if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask)) + return; + + for_each_online_cpu(i) { + if (i == cpu) + continue; + + if (phys_id == topology_physical_package_id(i)) { + cpumask_set_cpu(i, &cqm_cpumask); + break; + } + } +} + +static int intel_cqm_cpu_notifier(struct notifier_block *nb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + intel_cqm_cpu_prepare(cpu); + break; + case CPU_DOWN_PREPARE: + intel_cqm_cpu_exit(cpu); + break; + case CPU_STARTING: + cqm_pick_event_reader(cpu); + break; + } + + return NOTIFY_OK; +} + +static const struct x86_cpu_id intel_cqm_match[] = { + { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_OCCUP_LLC }, + {} +}; + +static int __init intel_cqm_init(void) +{ + char *str, scale[20]; + int i, cpu, ret; + + if (!x86_match_cpu(intel_cqm_match)) + return -ENODEV; + + cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale; + + /* + * It's possible that not all resources support the same number + * of RMIDs. Instead of making scheduling much more complicated + * (where we have to match a task's RMID to a cpu that supports + * that many RMIDs) just find the minimum RMIDs supported across + * all cpus. + * + * Also, check that the scales match on all cpus. + */ + cpu_notifier_register_begin(); + + for_each_online_cpu(cpu) { + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86_cache_max_rmid < cqm_max_rmid) + cqm_max_rmid = c->x86_cache_max_rmid; + + if (c->x86_cache_occ_scale != cqm_l3_scale) { + pr_err("Multiple LLC scale values, disabling\n"); + ret = -EINVAL; + goto out; + } + } + + /* + * A reasonable upper limit on the max threshold is the number + * of lines tagged per RMID if all RMIDs have the same number of + * lines tagged in the LLC. + * + * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. + */ + __intel_cqm_max_threshold = + boot_cpu_data.x86_cache_size * 1024 / (cqm_max_rmid + 1); + + snprintf(scale, sizeof(scale), "%u", cqm_l3_scale); + str = kstrdup(scale, GFP_KERNEL); + if (!str) { + ret = -ENOMEM; + goto out; + } + + event_attr_intel_cqm_llc_scale.event_str = str; + + ret = intel_cqm_setup_rmid_cache(); + if (ret) + goto out; + + for_each_online_cpu(i) { + intel_cqm_cpu_prepare(i); + cqm_pick_event_reader(i); + } + + __perf_cpu_notifier(intel_cqm_cpu_notifier); + + ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1); + if (ret) + pr_err("Intel CQM perf registration failed: %d\n", ret); + else + pr_info("Intel CQM monitoring enabled\n"); + +out: + cpu_notifier_register_done(); + + return ret; +} +device_initcall(intel_cqm_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 0739833..813f75d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -461,7 +461,8 @@ void intel_pmu_enable_bts(u64 config) debugctlmsr |= DEBUGCTLMSR_TR; debugctlmsr |= DEBUGCTLMSR_BTS; - debugctlmsr |= DEBUGCTLMSR_BTINT; + if (config & ARCH_PERFMON_EVENTSEL_INT) + debugctlmsr |= DEBUGCTLMSR_BTINT; if (!(config & ARCH_PERFMON_EVENTSEL_OS)) debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS; @@ -557,6 +558,8 @@ struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -564,6 +567,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -587,6 +592,8 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -602,6 +609,8 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -611,6 +620,10 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END @@ -622,6 +635,10 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END @@ -633,16 +650,16 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ - INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ - INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 58f1a94..94e5b50 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -39,6 +39,7 @@ static enum { #define LBR_IND_JMP_BIT 6 /* do not capture indirect jumps */ #define LBR_REL_JMP_BIT 7 /* do not capture relative jumps */ #define LBR_FAR_BIT 8 /* do not capture far branches */ +#define LBR_CALL_STACK_BIT 9 /* enable call stack */ #define LBR_KERNEL (1 << LBR_KERNEL_BIT) #define LBR_USER (1 << LBR_USER_BIT) @@ -49,6 +50,7 @@ static enum { #define LBR_REL_JMP (1 << LBR_REL_JMP_BIT) #define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) #define LBR_FAR (1 << LBR_FAR_BIT) +#define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT) #define LBR_PLM (LBR_KERNEL | LBR_USER) @@ -69,33 +71,31 @@ static enum { #define LBR_FROM_FLAG_IN_TX (1ULL << 62) #define LBR_FROM_FLAG_ABORT (1ULL << 61) -#define for_each_branch_sample_type(x) \ - for ((x) = PERF_SAMPLE_BRANCH_USER; \ - (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1) - /* * x86control flow change classification * x86control flow changes include branches, interrupts, traps, faults */ enum { - X86_BR_NONE = 0, /* unknown */ - - X86_BR_USER = 1 << 0, /* branch target is user */ - X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ - - X86_BR_CALL = 1 << 2, /* call */ - X86_BR_RET = 1 << 3, /* return */ - X86_BR_SYSCALL = 1 << 4, /* syscall */ - X86_BR_SYSRET = 1 << 5, /* syscall return */ - X86_BR_INT = 1 << 6, /* sw interrupt */ - X86_BR_IRET = 1 << 7, /* return from interrupt */ - X86_BR_JCC = 1 << 8, /* conditional */ - X86_BR_JMP = 1 << 9, /* jump */ - X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ - X86_BR_IND_CALL = 1 << 11,/* indirect calls */ - X86_BR_ABORT = 1 << 12,/* transaction abort */ - X86_BR_IN_TX = 1 << 13,/* in transaction */ - X86_BR_NO_TX = 1 << 14,/* not in transaction */ + X86_BR_NONE = 0, /* unknown */ + + X86_BR_USER = 1 << 0, /* branch target is user */ + X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ + + X86_BR_CALL = 1 << 2, /* call */ + X86_BR_RET = 1 << 3, /* return */ + X86_BR_SYSCALL = 1 << 4, /* syscall */ + X86_BR_SYSRET = 1 << 5, /* syscall return */ + X86_BR_INT = 1 << 6, /* sw interrupt */ + X86_BR_IRET = 1 << 7, /* return from interrupt */ + X86_BR_JCC = 1 << 8, /* conditional */ + X86_BR_JMP = 1 << 9, /* jump */ + X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ + X86_BR_IND_CALL = 1 << 11,/* indirect calls */ + X86_BR_ABORT = 1 << 12,/* transaction abort */ + X86_BR_IN_TX = 1 << 13,/* in transaction */ + X86_BR_NO_TX = 1 << 14,/* not in transaction */ + X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ + X86_BR_CALL_STACK = 1 << 16,/* call stack */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -112,13 +112,15 @@ enum { X86_BR_JMP |\ X86_BR_IRQ |\ X86_BR_ABORT |\ - X86_BR_IND_CALL) + X86_BR_IND_CALL |\ + X86_BR_ZERO_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) #define X86_BR_ANY_CALL \ (X86_BR_CALL |\ X86_BR_IND_CALL |\ + X86_BR_ZERO_CALL |\ X86_BR_SYSCALL |\ X86_BR_IRQ |\ X86_BR_INT) @@ -130,17 +132,32 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc); * otherwise it becomes near impossible to get a reliable stack. */ -static void __intel_pmu_lbr_enable(void) +static void __intel_pmu_lbr_enable(bool pmi) { - u64 debugctl; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 debugctl, lbr_select = 0, orig_debugctl; - if (cpuc->lbr_sel) - wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config); + /* + * No need to reprogram LBR_SELECT in a PMI, as it + * did not change. + */ + if (cpuc->lbr_sel && !pmi) { + lbr_select = cpuc->lbr_sel->config; + wrmsrl(MSR_LBR_SELECT, lbr_select); + } rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); - debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + orig_debugctl = debugctl; + debugctl |= DEBUGCTLMSR_LBR; + /* + * LBR callstack does not work well with FREEZE_LBRS_ON_PMI. + * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions + * may cause superfluous increase/decrease of LBR_TOS. + */ + if (!(lbr_select & LBR_CALL_STACK)) + debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; + if (orig_debugctl != debugctl) + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); } static void __intel_pmu_lbr_disable(void) @@ -181,9 +198,116 @@ void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_64(); } +/* + * TOS = most recently recorded branch + */ +static inline u64 intel_pmu_lbr_tos(void) +{ + u64 tos; + + rdmsrl(x86_pmu.lbr_tos, tos); + return tos; +} + +enum { + LBR_NONE, + LBR_VALID, +}; + +static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) +{ + int i; + unsigned lbr_idx, mask; + u64 tos; + + if (task_ctx->lbr_callstack_users == 0 || + task_ctx->lbr_stack_state == LBR_NONE) { + intel_pmu_lbr_reset(); + return; + } + + mask = x86_pmu.lbr_nr - 1; + tos = intel_pmu_lbr_tos(); + for (i = 0; i < x86_pmu.lbr_nr; i++) { + lbr_idx = (tos - i) & mask; + wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); + wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + } + task_ctx->lbr_stack_state = LBR_NONE; +} + +static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) +{ + int i; + unsigned lbr_idx, mask; + u64 tos; + + if (task_ctx->lbr_callstack_users == 0) { + task_ctx->lbr_stack_state = LBR_NONE; + return; + } + + mask = x86_pmu.lbr_nr - 1; + tos = intel_pmu_lbr_tos(); + for (i = 0; i < x86_pmu.lbr_nr; i++) { + lbr_idx = (tos - i) & mask; + rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); + rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + } + task_ctx->lbr_stack_state = LBR_VALID; +} + +void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_task_context *task_ctx; + + if (!x86_pmu.lbr_nr) + return; + + /* + * If LBR callstack feature is enabled and the stack was saved when + * the task was scheduled out, restore the stack. Otherwise flush + * the LBR stack. + */ + task_ctx = ctx ? ctx->task_ctx_data : NULL; + if (task_ctx) { + if (sched_in) { + __intel_pmu_lbr_restore(task_ctx); + cpuc->lbr_context = ctx; + } else { + __intel_pmu_lbr_save(task_ctx); + } + return; + } + + /* + * When sampling the branck stack in system-wide, it may be + * necessary to flush the stack on context switch. This happens + * when the branch stack does not tag its entries with the pid + * of the current task. Otherwise it becomes impossible to + * associate a branch entry with a task. This ambiguity is more + * likely to appear when the branch stack supports priv level + * filtering and the user sets it to monitor only at the user + * level (which could be a useful measurement in system-wide + * mode). In that case, the risk is high of having a branch + * stack with branch from multiple tasks. + */ + if (sched_in) { + intel_pmu_lbr_reset(); + cpuc->lbr_context = ctx; + } +} + +static inline bool branch_user_callstack(unsigned br_sel) +{ + return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK); +} + void intel_pmu_lbr_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_task_context *task_ctx; if (!x86_pmu.lbr_nr) return; @@ -198,18 +322,33 @@ void intel_pmu_lbr_enable(struct perf_event *event) } cpuc->br_sel = event->hw.branch_reg.reg; + if (branch_user_callstack(cpuc->br_sel) && event->ctx && + event->ctx->task_ctx_data) { + task_ctx = event->ctx->task_ctx_data; + task_ctx->lbr_callstack_users++; + } + cpuc->lbr_users++; + perf_sched_cb_inc(event->ctx->pmu); } void intel_pmu_lbr_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_task_context *task_ctx; if (!x86_pmu.lbr_nr) return; + if (branch_user_callstack(cpuc->br_sel) && event->ctx && + event->ctx->task_ctx_data) { + task_ctx = event->ctx->task_ctx_data; + task_ctx->lbr_callstack_users--; + } + cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); + perf_sched_cb_dec(event->ctx->pmu); if (cpuc->enabled && !cpuc->lbr_users) { __intel_pmu_lbr_disable(); @@ -218,12 +357,12 @@ void intel_pmu_lbr_disable(struct perf_event *event) } } -void intel_pmu_lbr_enable_all(void) +void intel_pmu_lbr_enable_all(bool pmi) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_users) - __intel_pmu_lbr_enable(); + __intel_pmu_lbr_enable(pmi); } void intel_pmu_lbr_disable_all(void) @@ -234,18 +373,6 @@ void intel_pmu_lbr_disable_all(void) __intel_pmu_lbr_disable(); } -/* - * TOS = most recently recorded branch - */ -static inline u64 intel_pmu_lbr_tos(void) -{ - u64 tos; - - rdmsrl(x86_pmu.lbr_tos, tos); - - return tos; -} - static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) { unsigned long mask = x86_pmu.lbr_nr - 1; @@ -350,7 +477,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -387,11 +514,21 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_COND) mask |= X86_BR_JCC; + if (br_type & PERF_SAMPLE_BRANCH_CALL_STACK) { + if (!x86_pmu_has_lbr_callstack()) + return -EOPNOTSUPP; + if (mask & ~(X86_BR_USER | X86_BR_KERNEL)) + return -EINVAL; + mask |= X86_BR_CALL | X86_BR_IND_CALL | X86_BR_RET | + X86_BR_CALL_STACK; + } + /* * stash actual user request into reg, it may * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; + return 0; } /* @@ -403,14 +540,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) { struct hw_perf_event_extra *reg; u64 br_type = event->attr.branch_sample_type; - u64 mask = 0, m; - u64 v; + u64 mask = 0, v; + int i; - for_each_branch_sample_type(m) { - if (!(br_type & m)) + for (i = 0; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) { + if (!(br_type & (1ULL << i))) continue; - v = x86_pmu.lbr_sel_map[m]; + v = x86_pmu.lbr_sel_map[i]; if (v == LBR_NOT_SUPP) return -EOPNOTSUPP; @@ -420,8 +557,12 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) reg = &event->hw.branch_reg; reg->idx = EXTRA_REG_LBR; - /* LBR_SELECT operates in suppress mode so invert mask */ - reg->config = ~mask & x86_pmu.lbr_sel_mask; + /* + * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate + * in suppress mode. So LBR_SELECT should be set to + * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK) + */ + reg->config = mask ^ x86_pmu.lbr_sel_mask; return 0; } @@ -439,7 +580,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - intel_pmu_setup_sw_lbr_filter(event); + ret = intel_pmu_setup_sw_lbr_filter(event); + if (ret) + return ret; /* * setup HW LBR filter, if any @@ -568,6 +711,12 @@ static int branch_type(unsigned long from, unsigned long to, int abort) ret = X86_BR_INT; break; case 0xe8: /* call near rel */ + insn_get_immediate(&insn); + if (insn.immediate1.value == 0) { + /* zero length call */ + ret = X86_BR_ZERO_CALL; + break; + } case 0x9a: /* call far absolute */ ret = X86_BR_CALL; break; @@ -678,35 +827,49 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) /* * Map interface branch filters onto LBR filters */ -static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { - [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, - [PERF_SAMPLE_BRANCH_USER] = LBR_USER, - [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, - [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, - [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_REL_JMP - | LBR_IND_JMP | LBR_FAR, +static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { + [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV_SHIFT] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_RETURN | LBR_REL_JMP + | LBR_IND_JMP | LBR_FAR, /* * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches */ - [PERF_SAMPLE_BRANCH_ANY_CALL] = + [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR, /* * NHM/WSM erratum: must include IND_JMP to capture IND_CALL */ - [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP, - [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP, + [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, }; -static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { - [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, - [PERF_SAMPLE_BRANCH_USER] = LBR_USER, - [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, - [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, - [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_FAR, - [PERF_SAMPLE_BRANCH_ANY_CALL] = LBR_REL_CALL | LBR_IND_CALL - | LBR_FAR, - [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL, - [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, +static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { + [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV_SHIFT] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_RETURN | LBR_FAR, + [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_REL_CALL | LBR_IND_CALL + | LBR_FAR, + [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, + [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, +}; + +static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { + [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV_SHIFT] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_RETURN | LBR_FAR, + [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_REL_CALL | LBR_IND_CALL + | LBR_FAR, + [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, + [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL + | LBR_RETURN | LBR_CALL_STACK, }; /* core */ @@ -765,6 +928,20 @@ void __init intel_pmu_lbr_init_snb(void) pr_cont("16-deep LBR, "); } +/* haswell */ +void intel_pmu_lbr_init_hsw(void) +{ + x86_pmu.lbr_nr = 16; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = hsw_lbr_sel_map; + + pr_cont("16-deep LBR, "); +} + /* atom */ void __init intel_pmu_lbr_init_atom(void) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c new file mode 100644 index 0000000..ffe666c --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -0,0 +1,1100 @@ +/* + * Intel(R) Processor Trace PMU driver for perf + * Copyright (c) 2013-2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * Intel PT is specified in the Intel Architecture Instruction Set Extensions + * Programming Reference: + * http://software.intel.com/en-us/intel-isa-extensions + */ + +#undef DEBUG + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/device.h> + +#include <asm/perf_event.h> +#include <asm/insn.h> +#include <asm/io.h> + +#include "perf_event.h" +#include "intel_pt.h" + +static DEFINE_PER_CPU(struct pt, pt_ctx); + +static struct pt_pmu pt_pmu; + +enum cpuid_regs { + CR_EAX = 0, + CR_ECX, + CR_EDX, + CR_EBX +}; + +/* + * Capabilities of Intel PT hardware, such as number of address bits or + * supported output schemes, are cached and exported to userspace as "caps" + * attribute group of pt pmu device + * (/sys/bus/event_source/devices/intel_pt/caps/) so that userspace can store + * relevant bits together with intel_pt traces. + * + * These are necessary for both trace decoding (payloads_lip, contains address + * width encoded in IP-related packets), and event configuration (bitmasks with + * permitted values for certain bit fields). + */ +#define PT_CAP(_n, _l, _r, _m) \ + [PT_CAP_ ## _n] = { .name = __stringify(_n), .leaf = _l, \ + .reg = _r, .mask = _m } + +static struct pt_cap_desc { + const char *name; + u32 leaf; + u8 reg; + u32 mask; +} pt_caps[] = { + PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff), + PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)), + PT_CAP(topa_output, 0, CR_ECX, BIT(0)), + PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), + PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)), +}; + +static u32 pt_cap_get(enum pt_capabilities cap) +{ + struct pt_cap_desc *cd = &pt_caps[cap]; + u32 c = pt_pmu.caps[cd->leaf * 4 + cd->reg]; + unsigned int shift = __ffs(cd->mask); + + return (c & cd->mask) >> shift; +} + +static ssize_t pt_cap_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ea = + container_of(attr, struct dev_ext_attribute, attr); + enum pt_capabilities cap = (long)ea->var; + + return snprintf(buf, PAGE_SIZE, "%x\n", pt_cap_get(cap)); +} + +static struct attribute_group pt_cap_group = { + .name = "caps", +}; + +PMU_FORMAT_ATTR(tsc, "config:10" ); +PMU_FORMAT_ATTR(noretcomp, "config:11" ); + +static struct attribute *pt_formats_attr[] = { + &format_attr_tsc.attr, + &format_attr_noretcomp.attr, + NULL, +}; + +static struct attribute_group pt_format_group = { + .name = "format", + .attrs = pt_formats_attr, +}; + +static const struct attribute_group *pt_attr_groups[] = { + &pt_cap_group, + &pt_format_group, + NULL, +}; + +static int __init pt_pmu_hw_init(void) +{ + struct dev_ext_attribute *de_attrs; + struct attribute **attrs; + size_t size; + int ret; + long i; + + attrs = NULL; + ret = -ENODEV; + if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) + goto fail; + + for (i = 0; i < PT_CPUID_LEAVES; i++) { + cpuid_count(20, i, + &pt_pmu.caps[CR_EAX + i*4], + &pt_pmu.caps[CR_EBX + i*4], + &pt_pmu.caps[CR_ECX + i*4], + &pt_pmu.caps[CR_EDX + i*4]); + } + + ret = -ENOMEM; + size = sizeof(struct attribute *) * (ARRAY_SIZE(pt_caps)+1); + attrs = kzalloc(size, GFP_KERNEL); + if (!attrs) + goto fail; + + size = sizeof(struct dev_ext_attribute) * (ARRAY_SIZE(pt_caps)+1); + de_attrs = kzalloc(size, GFP_KERNEL); + if (!de_attrs) + goto fail; + + for (i = 0; i < ARRAY_SIZE(pt_caps); i++) { + struct dev_ext_attribute *de_attr = de_attrs + i; + + de_attr->attr.attr.name = pt_caps[i].name; + + sysfs_attr_init(&de_attrs->attr.attr); + + de_attr->attr.attr.mode = S_IRUGO; + de_attr->attr.show = pt_cap_show; + de_attr->var = (void *)i; + + attrs[i] = &de_attr->attr.attr; + } + + pt_cap_group.attrs = attrs; + + return 0; + +fail: + kfree(attrs); + + return ret; +} + +#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC) + +static bool pt_event_valid(struct perf_event *event) +{ + u64 config = event->attr.config; + + if ((config & PT_CONFIG_MASK) != config) + return false; + + return true; +} + +/* + * PT configuration helpers + * These all are cpu affine and operate on a local PT + */ + +static bool pt_is_running(void) +{ + u64 ctl; + + rdmsrl(MSR_IA32_RTIT_CTL, ctl); + + return !!(ctl & RTIT_CTL_TRACEEN); +} + +static void pt_config(struct perf_event *event) +{ + u64 reg; + + reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; + + if (!event->attr.exclude_kernel) + reg |= RTIT_CTL_OS; + if (!event->attr.exclude_user) + reg |= RTIT_CTL_USR; + + reg |= (event->attr.config & PT_CONFIG_MASK); + + wrmsrl(MSR_IA32_RTIT_CTL, reg); +} + +static void pt_config_start(bool start) +{ + u64 ctl; + + rdmsrl(MSR_IA32_RTIT_CTL, ctl); + if (start) + ctl |= RTIT_CTL_TRACEEN; + else + ctl &= ~RTIT_CTL_TRACEEN; + wrmsrl(MSR_IA32_RTIT_CTL, ctl); + + /* + * A wrmsr that disables trace generation serializes other PT + * registers and causes all data packets to be written to memory, + * but a fence is required for the data to become globally visible. + * + * The below WMB, separating data store and aux_head store matches + * the consumer's RMB that separates aux_head load and data load. + */ + if (!start) + wmb(); +} + +static void pt_config_buffer(void *buf, unsigned int topa_idx, + unsigned int output_off) +{ + u64 reg; + + wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, virt_to_phys(buf)); + + reg = 0x7f | ((u64)topa_idx << 7) | ((u64)output_off << 32); + + wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg); +} + +/* + * Keep ToPA table-related metadata on the same page as the actual table, + * taking up a few words from the top + */ + +#define TENTS_PER_PAGE (((PAGE_SIZE - 40) / sizeof(struct topa_entry)) - 1) + +/** + * struct topa - page-sized ToPA table with metadata at the top + * @table: actual ToPA table entries, as understood by PT hardware + * @list: linkage to struct pt_buffer's list of tables + * @phys: physical address of this page + * @offset: offset of the first entry in this table in the buffer + * @size: total size of all entries in this table + * @last: index of the last initialized entry in this table + */ +struct topa { + struct topa_entry table[TENTS_PER_PAGE]; + struct list_head list; + u64 phys; + u64 offset; + size_t size; + int last; +}; + +/* make -1 stand for the last table entry */ +#define TOPA_ENTRY(t, i) ((i) == -1 ? &(t)->table[(t)->last] : &(t)->table[(i)]) + +/** + * topa_alloc() - allocate page-sized ToPA table + * @cpu: CPU on which to allocate. + * @gfp: Allocation flags. + * + * Return: On success, return the pointer to ToPA table page. + */ +static struct topa *topa_alloc(int cpu, gfp_t gfp) +{ + int node = cpu_to_node(cpu); + struct topa *topa; + struct page *p; + + p = alloc_pages_node(node, gfp | __GFP_ZERO, 0); + if (!p) + return NULL; + + topa = page_address(p); + topa->last = 0; + topa->phys = page_to_phys(p); + + /* + * In case of singe-entry ToPA, always put the self-referencing END + * link as the 2nd entry in the table + */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) { + TOPA_ENTRY(topa, 1)->base = topa->phys >> TOPA_SHIFT; + TOPA_ENTRY(topa, 1)->end = 1; + } + + return topa; +} + +/** + * topa_free() - free a page-sized ToPA table + * @topa: Table to deallocate. + */ +static void topa_free(struct topa *topa) +{ + free_page((unsigned long)topa); +} + +/** + * topa_insert_table() - insert a ToPA table into a buffer + * @buf: PT buffer that's being extended. + * @topa: New topa table to be inserted. + * + * If it's the first table in this buffer, set up buffer's pointers + * accordingly; otherwise, add a END=1 link entry to @topa to the current + * "last" table and adjust the last table pointer to @topa. + */ +static void topa_insert_table(struct pt_buffer *buf, struct topa *topa) +{ + struct topa *last = buf->last; + + list_add_tail(&topa->list, &buf->tables); + + if (!buf->first) { + buf->first = buf->last = buf->cur = topa; + return; + } + + topa->offset = last->offset + last->size; + buf->last = topa; + + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + return; + + BUG_ON(last->last != TENTS_PER_PAGE - 1); + + TOPA_ENTRY(last, -1)->base = topa->phys >> TOPA_SHIFT; + TOPA_ENTRY(last, -1)->end = 1; +} + +/** + * topa_table_full() - check if a ToPA table is filled up + * @topa: ToPA table. + */ +static bool topa_table_full(struct topa *topa) +{ + /* single-entry ToPA is a special case */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + return !!topa->last; + + return topa->last == TENTS_PER_PAGE - 1; +} + +/** + * topa_insert_pages() - create a list of ToPA tables + * @buf: PT buffer being initialized. + * @gfp: Allocation flags. + * + * This initializes a list of ToPA tables with entries from + * the data_pages provided by rb_alloc_aux(). + * + * Return: 0 on success or error code. + */ +static int topa_insert_pages(struct pt_buffer *buf, gfp_t gfp) +{ + struct topa *topa = buf->last; + int order = 0; + struct page *p; + + p = virt_to_page(buf->data_pages[buf->nr_pages]); + if (PagePrivate(p)) + order = page_private(p); + + if (topa_table_full(topa)) { + topa = topa_alloc(buf->cpu, gfp); + if (!topa) + return -ENOMEM; + + topa_insert_table(buf, topa); + } + + TOPA_ENTRY(topa, -1)->base = page_to_phys(p) >> TOPA_SHIFT; + TOPA_ENTRY(topa, -1)->size = order; + if (!buf->snapshot && !pt_cap_get(PT_CAP_topa_multiple_entries)) { + TOPA_ENTRY(topa, -1)->intr = 1; + TOPA_ENTRY(topa, -1)->stop = 1; + } + + topa->last++; + topa->size += sizes(order); + + buf->nr_pages += 1ul << order; + + return 0; +} + +/** + * pt_topa_dump() - print ToPA tables and their entries + * @buf: PT buffer. + */ +static void pt_topa_dump(struct pt_buffer *buf) +{ + struct topa *topa; + + list_for_each_entry(topa, &buf->tables, list) { + int i; + + pr_debug("# table @%p (%016Lx), off %llx size %zx\n", topa->table, + topa->phys, topa->offset, topa->size); + for (i = 0; i < TENTS_PER_PAGE; i++) { + pr_debug("# entry @%p (%lx sz %u %c%c%c) raw=%16llx\n", + &topa->table[i], + (unsigned long)topa->table[i].base << TOPA_SHIFT, + sizes(topa->table[i].size), + topa->table[i].end ? 'E' : ' ', + topa->table[i].intr ? 'I' : ' ', + topa->table[i].stop ? 'S' : ' ', + *(u64 *)&topa->table[i]); + if ((pt_cap_get(PT_CAP_topa_multiple_entries) && + topa->table[i].stop) || + topa->table[i].end) + break; + } + } +} + +/** + * pt_buffer_advance() - advance to the next output region + * @buf: PT buffer. + * + * Advance the current pointers in the buffer to the next ToPA entry. + */ +static void pt_buffer_advance(struct pt_buffer *buf) +{ + buf->output_off = 0; + buf->cur_idx++; + + if (buf->cur_idx == buf->cur->last) { + if (buf->cur == buf->last) + buf->cur = buf->first; + else + buf->cur = list_entry(buf->cur->list.next, struct topa, + list); + buf->cur_idx = 0; + } +} + +/** + * pt_update_head() - calculate current offsets and sizes + * @pt: Per-cpu pt context. + * + * Update buffer's current write pointer position and data size. + */ +static void pt_update_head(struct pt *pt) +{ + struct pt_buffer *buf = perf_get_aux(&pt->handle); + u64 topa_idx, base, old; + + /* offset of the first region in this table from the beginning of buf */ + base = buf->cur->offset + buf->output_off; + + /* offset of the current output region within this table */ + for (topa_idx = 0; topa_idx < buf->cur_idx; topa_idx++) + base += sizes(buf->cur->table[topa_idx].size); + + if (buf->snapshot) { + local_set(&buf->data_size, base); + } else { + old = (local64_xchg(&buf->head, base) & + ((buf->nr_pages << PAGE_SHIFT) - 1)); + if (base < old) + base += buf->nr_pages << PAGE_SHIFT; + + local_add(base - old, &buf->data_size); + } +} + +/** + * pt_buffer_region() - obtain current output region's address + * @buf: PT buffer. + */ +static void *pt_buffer_region(struct pt_buffer *buf) +{ + return phys_to_virt(buf->cur->table[buf->cur_idx].base << TOPA_SHIFT); +} + +/** + * pt_buffer_region_size() - obtain current output region's size + * @buf: PT buffer. + */ +static size_t pt_buffer_region_size(struct pt_buffer *buf) +{ + return sizes(buf->cur->table[buf->cur_idx].size); +} + +/** + * pt_handle_status() - take care of possible status conditions + * @pt: Per-cpu pt context. + */ +static void pt_handle_status(struct pt *pt) +{ + struct pt_buffer *buf = perf_get_aux(&pt->handle); + int advance = 0; + u64 status; + + rdmsrl(MSR_IA32_RTIT_STATUS, status); + + if (status & RTIT_STATUS_ERROR) { + pr_err_ratelimited("ToPA ERROR encountered, trying to recover\n"); + pt_topa_dump(buf); + status &= ~RTIT_STATUS_ERROR; + } + + if (status & RTIT_STATUS_STOPPED) { + status &= ~RTIT_STATUS_STOPPED; + + /* + * On systems that only do single-entry ToPA, hitting STOP + * means we are already losing data; need to let the decoder + * know. + */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries) || + buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) { + local_inc(&buf->lost); + advance++; + } + } + + /* + * Also on single-entry ToPA implementations, interrupt will come + * before the output reaches its output region's boundary. + */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries) && !buf->snapshot && + pt_buffer_region_size(buf) - buf->output_off <= TOPA_PMI_MARGIN) { + void *head = pt_buffer_region(buf); + + /* everything within this margin needs to be zeroed out */ + memset(head + buf->output_off, 0, + pt_buffer_region_size(buf) - + buf->output_off); + advance++; + } + + if (advance) + pt_buffer_advance(buf); + + wrmsrl(MSR_IA32_RTIT_STATUS, status); +} + +/** + * pt_read_offset() - translate registers into buffer pointers + * @buf: PT buffer. + * + * Set buffer's output pointers from MSR values. + */ +static void pt_read_offset(struct pt_buffer *buf) +{ + u64 offset, base_topa; + + rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, base_topa); + buf->cur = phys_to_virt(base_topa); + + rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, offset); + /* offset within current output region */ + buf->output_off = offset >> 32; + /* index of current output region within this table */ + buf->cur_idx = (offset & 0xffffff80) >> 7; +} + +/** + * pt_topa_next_entry() - obtain index of the first page in the next ToPA entry + * @buf: PT buffer. + * @pg: Page offset in the buffer. + * + * When advancing to the next output region (ToPA entry), given a page offset + * into the buffer, we need to find the offset of the first page in the next + * region. + */ +static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) +{ + struct topa_entry *te = buf->topa_index[pg]; + + /* one region */ + if (buf->first == buf->last && buf->first->last == 1) + return pg; + + do { + pg++; + pg &= buf->nr_pages - 1; + } while (buf->topa_index[pg] == te); + + return pg; +} + +/** + * pt_buffer_reset_markers() - place interrupt and stop bits in the buffer + * @buf: PT buffer. + * @handle: Current output handle. + * + * Place INT and STOP marks to prevent overwriting old data that the consumer + * hasn't yet collected. + */ +static int pt_buffer_reset_markers(struct pt_buffer *buf, + struct perf_output_handle *handle) + +{ + unsigned long idx, npages, end; + + if (buf->snapshot) + return 0; + + /* can't stop in the middle of an output region */ + if (buf->output_off + handle->size + 1 < + sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) + return -EINVAL; + + + /* single entry ToPA is handled by marking all regions STOP=1 INT=1 */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + return 0; + + /* clear STOP and INT from current entry */ + buf->topa_index[buf->stop_pos]->stop = 0; + buf->topa_index[buf->intr_pos]->intr = 0; + + if (pt_cap_get(PT_CAP_topa_multiple_entries)) { + npages = (handle->size + 1) >> PAGE_SHIFT; + end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages; + /*if (end > handle->wakeup >> PAGE_SHIFT) + end = handle->wakeup >> PAGE_SHIFT;*/ + idx = end & (buf->nr_pages - 1); + buf->stop_pos = idx; + idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1; + idx &= buf->nr_pages - 1; + buf->intr_pos = idx; + } + + buf->topa_index[buf->stop_pos]->stop = 1; + buf->topa_index[buf->intr_pos]->intr = 1; + + return 0; +} + +/** + * pt_buffer_setup_topa_index() - build topa_index[] table of regions + * @buf: PT buffer. + * + * topa_index[] references output regions indexed by offset into the + * buffer for purposes of quick reverse lookup. + */ +static void pt_buffer_setup_topa_index(struct pt_buffer *buf) +{ + struct topa *cur = buf->first, *prev = buf->last; + struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), + *te_prev = TOPA_ENTRY(prev, prev->last - 1); + int pg = 0, idx = 0, ntopa = 0; + + while (pg < buf->nr_pages) { + int tidx; + + /* pages within one topa entry */ + for (tidx = 0; tidx < 1 << te_cur->size; tidx++, pg++) + buf->topa_index[pg] = te_prev; + + te_prev = te_cur; + + if (idx == cur->last - 1) { + /* advance to next topa table */ + idx = 0; + cur = list_entry(cur->list.next, struct topa, list); + ntopa++; + } else + idx++; + te_cur = TOPA_ENTRY(cur, idx); + } + +} + +/** + * pt_buffer_reset_offsets() - adjust buffer's write pointers from aux_head + * @buf: PT buffer. + * @head: Write pointer (aux_head) from AUX buffer. + * + * Find the ToPA table and entry corresponding to given @head and set buffer's + * "current" pointers accordingly. + */ +static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) +{ + int pg; + + if (buf->snapshot) + head &= (buf->nr_pages << PAGE_SHIFT) - 1; + + pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1); + pg = pt_topa_next_entry(buf, pg); + + buf->cur = (struct topa *)((unsigned long)buf->topa_index[pg] & PAGE_MASK); + buf->cur_idx = ((unsigned long)buf->topa_index[pg] - + (unsigned long)buf->cur) / sizeof(struct topa_entry); + buf->output_off = head & (sizes(buf->cur->table[buf->cur_idx].size) - 1); + + local64_set(&buf->head, head); + local_set(&buf->data_size, 0); +} + +/** + * pt_buffer_fini_topa() - deallocate ToPA structure of a buffer + * @buf: PT buffer. + */ +static void pt_buffer_fini_topa(struct pt_buffer *buf) +{ + struct topa *topa, *iter; + + list_for_each_entry_safe(topa, iter, &buf->tables, list) { + /* + * right now, this is in free_aux() path only, so + * no need to unlink this table from the list + */ + topa_free(topa); + } +} + +/** + * pt_buffer_init_topa() - initialize ToPA table for pt buffer + * @buf: PT buffer. + * @size: Total size of all regions within this ToPA. + * @gfp: Allocation flags. + */ +static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages, + gfp_t gfp) +{ + struct topa *topa; + int err; + + topa = topa_alloc(buf->cpu, gfp); + if (!topa) + return -ENOMEM; + + topa_insert_table(buf, topa); + + while (buf->nr_pages < nr_pages) { + err = topa_insert_pages(buf, gfp); + if (err) { + pt_buffer_fini_topa(buf); + return -ENOMEM; + } + } + + pt_buffer_setup_topa_index(buf); + + /* link last table to the first one, unless we're double buffering */ + if (pt_cap_get(PT_CAP_topa_multiple_entries)) { + TOPA_ENTRY(buf->last, -1)->base = buf->first->phys >> TOPA_SHIFT; + TOPA_ENTRY(buf->last, -1)->end = 1; + } + + pt_topa_dump(buf); + return 0; +} + +/** + * pt_buffer_setup_aux() - set up topa tables for a PT buffer + * @cpu: Cpu on which to allocate, -1 means current. + * @pages: Array of pointers to buffer pages passed from perf core. + * @nr_pages: Number of pages in the buffer. + * @snapshot: If this is a snapshot/overwrite counter. + * + * This is a pmu::setup_aux callback that sets up ToPA tables and all the + * bookkeeping for an AUX buffer. + * + * Return: Our private PT buffer structure. + */ +static void * +pt_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool snapshot) +{ + struct pt_buffer *buf; + int node, ret; + + if (!nr_pages) + return NULL; + + if (cpu == -1) + cpu = raw_smp_processor_id(); + node = cpu_to_node(cpu); + + buf = kzalloc_node(offsetof(struct pt_buffer, topa_index[nr_pages]), + GFP_KERNEL, node); + if (!buf) + return NULL; + + buf->cpu = cpu; + buf->snapshot = snapshot; + buf->data_pages = pages; + + INIT_LIST_HEAD(&buf->tables); + + ret = pt_buffer_init_topa(buf, nr_pages, GFP_KERNEL); + if (ret) { + kfree(buf); + return NULL; + } + + return buf; +} + +/** + * pt_buffer_free_aux() - perf AUX deallocation path callback + * @data: PT buffer. + */ +static void pt_buffer_free_aux(void *data) +{ + struct pt_buffer *buf = data; + + pt_buffer_fini_topa(buf); + kfree(buf); +} + +/** + * pt_buffer_is_full() - check if the buffer is full + * @buf: PT buffer. + * @pt: Per-cpu pt handle. + * + * If the user hasn't read data from the output region that aux_head + * points to, the buffer is considered full: the user needs to read at + * least this region and update aux_tail to point past it. + */ +static bool pt_buffer_is_full(struct pt_buffer *buf, struct pt *pt) +{ + if (buf->snapshot) + return false; + + if (local_read(&buf->data_size) >= pt->handle.size) + return true; + + return false; +} + +/** + * intel_pt_interrupt() - PT PMI handler + */ +void intel_pt_interrupt(void) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf; + struct perf_event *event = pt->handle.event; + + /* + * There may be a dangling PT bit in the interrupt status register + * after PT has been disabled by pt_event_stop(). Make sure we don't + * do anything (particularly, re-enable) for this event here. + */ + if (!ACCESS_ONCE(pt->handle_nmi)) + return; + + pt_config_start(false); + + if (!event) + return; + + buf = perf_get_aux(&pt->handle); + if (!buf) + return; + + pt_read_offset(buf); + + pt_handle_status(pt); + + pt_update_head(pt); + + perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0), + local_xchg(&buf->lost, 0)); + + if (!event->hw.state) { + int ret; + + buf = perf_aux_output_begin(&pt->handle, event); + if (!buf) { + event->hw.state = PERF_HES_STOPPED; + return; + } + + pt_buffer_reset_offsets(buf, pt->handle.head); + ret = pt_buffer_reset_markers(buf, &pt->handle); + if (ret) { + perf_aux_output_end(&pt->handle, 0, true); + return; + } + + pt_config_buffer(buf->cur->table, buf->cur_idx, + buf->output_off); + wrmsrl(MSR_IA32_RTIT_STATUS, 0); + pt_config(event); + } +} + +/* + * PMU callbacks + */ + +static void pt_event_start(struct perf_event *event, int mode) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf = perf_get_aux(&pt->handle); + + if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) { + event->hw.state = PERF_HES_STOPPED; + return; + } + + ACCESS_ONCE(pt->handle_nmi) = 1; + event->hw.state = 0; + + pt_config_buffer(buf->cur->table, buf->cur_idx, + buf->output_off); + wrmsrl(MSR_IA32_RTIT_STATUS, 0); + pt_config(event); +} + +static void pt_event_stop(struct perf_event *event, int mode) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + + /* + * Protect against the PMI racing with disabling wrmsr, + * see comment in intel_pt_interrupt(). + */ + ACCESS_ONCE(pt->handle_nmi) = 0; + pt_config_start(false); + + if (event->hw.state == PERF_HES_STOPPED) + return; + + event->hw.state = PERF_HES_STOPPED; + + if (mode & PERF_EF_UPDATE) { + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf = perf_get_aux(&pt->handle); + + if (!buf) + return; + + if (WARN_ON_ONCE(pt->handle.event != event)) + return; + + pt_read_offset(buf); + + pt_handle_status(pt); + + pt_update_head(pt); + } +} + +static void pt_event_del(struct perf_event *event, int mode) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf; + + pt_event_stop(event, PERF_EF_UPDATE); + + buf = perf_get_aux(&pt->handle); + + if (buf) { + if (buf->snapshot) + pt->handle.head = + local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0), + local_xchg(&buf->lost, 0)); + } +} + +static int pt_event_add(struct perf_event *event, int mode) +{ + struct pt_buffer *buf; + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct hw_perf_event *hwc = &event->hw; + int ret = -EBUSY; + + if (pt->handle.event) + goto fail; + + buf = perf_aux_output_begin(&pt->handle, event); + ret = -EINVAL; + if (!buf) + goto fail_stop; + + pt_buffer_reset_offsets(buf, pt->handle.head); + if (!buf->snapshot) { + ret = pt_buffer_reset_markers(buf, &pt->handle); + if (ret) + goto fail_end_stop; + } + + if (mode & PERF_EF_START) { + pt_event_start(event, 0); + ret = -EBUSY; + if (hwc->state == PERF_HES_STOPPED) + goto fail_end_stop; + } else { + hwc->state = PERF_HES_STOPPED; + } + + return 0; + +fail_end_stop: + perf_aux_output_end(&pt->handle, 0, true); +fail_stop: + hwc->state = PERF_HES_STOPPED; +fail: + return ret; +} + +static void pt_event_read(struct perf_event *event) +{ +} + +static void pt_event_destroy(struct perf_event *event) +{ + x86_del_exclusive(x86_lbr_exclusive_pt); +} + +static int pt_event_init(struct perf_event *event) +{ + if (event->attr.type != pt_pmu.pmu.type) + return -ENOENT; + + if (!pt_event_valid(event)) + return -EINVAL; + + if (x86_add_exclusive(x86_lbr_exclusive_pt)) + return -EBUSY; + + event->destroy = pt_event_destroy; + + return 0; +} + +static __init int pt_init(void) +{ + int ret, cpu, prior_warn = 0; + + BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE); + get_online_cpus(); + for_each_online_cpu(cpu) { + u64 ctl; + + ret = rdmsrl_safe_on_cpu(cpu, MSR_IA32_RTIT_CTL, &ctl); + if (!ret && (ctl & RTIT_CTL_TRACEEN)) + prior_warn++; + } + put_online_cpus(); + + if (prior_warn) { + x86_add_exclusive(x86_lbr_exclusive_pt); + pr_warn("PT is enabled at boot time, doing nothing\n"); + + return -EBUSY; + } + + ret = pt_pmu_hw_init(); + if (ret) + return ret; + + if (!pt_cap_get(PT_CAP_topa_output)) { + pr_warn("ToPA output is not supported on this CPU\n"); + return -ENODEV; + } + + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + pt_pmu.pmu.capabilities = + PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF; + + pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE; + pt_pmu.pmu.attr_groups = pt_attr_groups; + pt_pmu.pmu.task_ctx_nr = perf_sw_context; + pt_pmu.pmu.event_init = pt_event_init; + pt_pmu.pmu.add = pt_event_add; + pt_pmu.pmu.del = pt_event_del; + pt_pmu.pmu.start = pt_event_start; + pt_pmu.pmu.stop = pt_event_stop; + pt_pmu.pmu.read = pt_event_read; + pt_pmu.pmu.setup_aux = pt_buffer_setup_aux; + pt_pmu.pmu.free_aux = pt_buffer_free_aux; + ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1); + + return ret; +} + +module_init(pt_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index c4bb8b8..999289b9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -62,6 +62,14 @@ #define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ +#define NR_RAPL_DOMAINS 0x4 +static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { + "pp0-core", + "package", + "dram", + "pp1-gpu", +}; + /* Clients have PP0, PKG */ #define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\ 1<<RAPL_IDX_PKG_NRG_STAT|\ @@ -112,7 +120,6 @@ static struct perf_pmu_events_attr event_attr_##v = { \ struct rapl_pmu { spinlock_t lock; - int hw_unit; /* 1/2^hw_unit Joule */ int n_active; /* number of active events */ struct list_head active_list; struct pmu *pmu; /* pointer to rapl_pmu_class */ @@ -120,6 +127,7 @@ struct rapl_pmu { struct hrtimer hrtimer; }; +static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; /* 1/2^hw_unit Joule */ static struct pmu rapl_pmu_class; static cpumask_t rapl_cpu_mask; static int rapl_cntr_mask; @@ -127,6 +135,7 @@ static int rapl_cntr_mask; static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); +static struct x86_pmu_quirk *rapl_quirks; static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; @@ -134,15 +143,28 @@ static inline u64 rapl_read_counter(struct perf_event *event) return raw; } -static inline u64 rapl_scale(u64 v) +#define rapl_add_quirk(func_) \ +do { \ + static struct x86_pmu_quirk __quirk __initdata = { \ + .func = func_, \ + }; \ + __quirk.next = rapl_quirks; \ + rapl_quirks = &__quirk; \ +} while (0) + +static inline u64 rapl_scale(u64 v, int cfg) { + if (cfg > NR_RAPL_DOMAINS) { + pr_warn("invalid domain %d, failed to scale data\n", cfg); + return v; + } /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit); + return v << (32 - rapl_hw_unit[cfg - 1]); } static u64 rapl_event_update(struct perf_event *event) @@ -173,7 +195,7 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - sdelta = rapl_scale(delta); + sdelta = rapl_scale(delta, event->hw.config); local64_add(sdelta, &event->count); @@ -546,12 +568,22 @@ static void rapl_cpu_init(int cpu) cpumask_set_cpu(cpu, &rapl_cpu_mask); } +static __init void rapl_hsw_server_quirk(void) +{ + /* + * DRAM domain on HSW server has fixed energy unit which can be + * different than the unit from power unit MSR. + * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 + * of 2. Datasheet, September 2014, Reference Number: 330784-001 " + */ + rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16; +} + static int rapl_cpu_prepare(int cpu) { struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); int phys_id = topology_physical_package_id(cpu); u64 ms; - u64 msr_rapl_power_unit_bits; if (pmu) return 0; @@ -559,24 +591,13 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; - /* protect rdmsrl() to handle virtualization */ - if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) - return -1; - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -1; - spin_lock_init(&pmu->lock); INIT_LIST_HEAD(&pmu->active_list); - /* - * grab power unit as: 1/2^unit Joules - * - * we cache in local PMU instance - */ - pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; pmu->pmu = &rapl_pmu_class; /* @@ -586,8 +607,8 @@ static int rapl_cpu_prepare(int cpu) * divide interval by 2 to avoid lockstep (2 * 100) * if hw unit is 32, then we use 2 ms 1/200/2 */ - if (pmu->hw_unit < 32) - ms = (1000 / (2 * 100)) * (1ULL << (32 - pmu->hw_unit - 1)); + if (rapl_hw_unit[0] < 32) + ms = (1000 / (2 * 100)) * (1ULL << (32 - rapl_hw_unit[0] - 1)); else ms = 2; @@ -655,6 +676,20 @@ static int rapl_cpu_notifier(struct notifier_block *self, return NOTIFY_OK; } +static int rapl_check_hw_unit(void) +{ + u64 msr_rapl_power_unit_bits; + int i; + + /* protect rdmsrl() to handle virtualization */ + if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + return -1; + for (i = 0; i < NR_RAPL_DOMAINS; i++) + rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + + return 0; +} + static const struct x86_cpu_id rapl_cpu_match[] = { [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, [1] = {}, @@ -664,6 +699,8 @@ static int __init rapl_pmu_init(void) { struct rapl_pmu *pmu; int cpu, ret; + struct x86_pmu_quirk *quirk; + int i; /* * check for Intel processor family 6 @@ -678,6 +715,11 @@ static int __init rapl_pmu_init(void) rapl_cntr_mask = RAPL_IDX_CLN; rapl_pmu_events_group.attrs = rapl_events_cln_attr; break; + case 63: /* Haswell-Server */ + rapl_add_quirk(rapl_hsw_server_quirk); + rapl_cntr_mask = RAPL_IDX_SRV; + rapl_pmu_events_group.attrs = rapl_events_srv_attr; + break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ rapl_cntr_mask = RAPL_IDX_HSW; @@ -693,7 +735,13 @@ static int __init rapl_pmu_init(void) /* unsupported */ return 0; } + ret = rapl_check_hw_unit(); + if (ret) + return ret; + /* run cpu model quirks */ + for (quirk = rapl_quirks; quirk; quirk = quirk->next) + quirk->func(); cpu_notifier_register_begin(); for_each_online_cpu(cpu) { @@ -714,14 +762,18 @@ static int __init rapl_pmu_init(void) pmu = __this_cpu_read(rapl_pmu); - pr_info("RAPL PMU detected, hw unit 2^-%d Joules," + pr_info("RAPL PMU detected," " API unit is 2^-32 Joules," " %d fixed counters" " %llu ms ovfl timer\n", - pmu->hw_unit, hweight32(rapl_cntr_mask), ktime_to_ms(pmu->timer_interval)); - + for (i = 0; i < NR_RAPL_DOMAINS; i++) { + if (rapl_cntr_mask & (1 << i)) { + pr_info("hw unit of domain %s 2^-%d Joules\n", + rapl_domain_names[i], rapl_hw_unit[i]); + } + } out: cpu_notifier_register_done(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 3001015..4562e9e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -1,6 +1,13 @@ /* Nehalem/SandBridge/Haswell uncore support */ #include "perf_event_intel_uncore.h" +/* Uncore IMC PCI IDs */ +#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 +#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154 +#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150 +#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 +#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 + /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff #define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 @@ -472,6 +479,10 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ }, }; @@ -502,6 +513,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver), /* 3rd Gen Core processor */ IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ + IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ { /* end marker */ } }; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index 21af6149e..12d9548 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -1132,8 +1132,7 @@ static int snbep_pci2phy_map_init(int devid) } } - if (ubox_dev) - pci_dev_put(ubox_dev); + pci_dev_put(ubox_dev); return err ? pcibios_err_to_errno(err) : 0; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 6063909..3d423a1 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -41,6 +41,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, + { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7d46bb2..e2ce85d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -149,6 +149,9 @@ static void __init e820_print_type(u32 type) case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PRAM: + printk(KERN_CONT "persistent (type %u)", type); + break; default: printk(KERN_CONT "type %u", type); break; @@ -343,7 +346,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, * continue building up new bios map based on this * information */ - if (current_type != last_type) { + if (current_type != last_type || current_type == E820_PRAM) { if (last_type != 0) { new_bios[new_bios_entry].size = change_point[chgidx]->addr - last_addr; @@ -688,6 +691,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) register_nosave_region(pfn, PFN_UP(ei->addr)); pfn = PFN_DOWN(ei->addr + ei->size); + if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) register_nosave_region(PFN_UP(ei->addr), pfn); @@ -748,7 +752,7 @@ u64 __init early_reserve_e820(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) +static unsigned long __init e820_end_pfn(unsigned long limit_pfn) { int i; unsigned long last_pfn = 0; @@ -759,7 +763,11 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) unsigned long start_pfn; unsigned long end_pfn; - if (ei->type != type) + /* + * Persistent memory is accounted as ram for purposes of + * establishing max_pfn and mem_map. + */ + if (ei->type != E820_RAM && ei->type != E820_PRAM) continue; start_pfn = ei->addr >> PAGE_SHIFT; @@ -784,12 +792,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) } unsigned long __init e820_end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); + return e820_end_pfn(MAX_ARCH_PFN); } unsigned long __init e820_end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM); + return e820_end_pfn(1UL << (32-PAGE_SHIFT)); } static void early_panic(char *msg) @@ -866,6 +874,9 @@ static int __init parse_memmap_one(char *p) } else if (*p == '$') { start_at = memparse(p+1, &p); e820_add_region(start_at, mem_size, E820_RESERVED); + } else if (*p == '!') { + start_at = memparse(p+1, &p); + e820_add_region(start_at, mem_size, E820_PRAM); } else e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); @@ -907,6 +918,7 @@ static inline const char *e820_type_to_string(int e820_type) case E820_ACPI: return "ACPI Tables"; case E820_NVS: return "ACPI Non-volatile Storage"; case E820_UNUSABLE: return "Unusable memory"; + case E820_PRAM: return "Persistent RAM"; default: return "reserved"; } } @@ -940,7 +952,9 @@ void __init e820_reserve_resources(void) * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) { + if (((e820.map[i].type != E820_RESERVED) && + (e820.map[i].type != E820_PRAM)) || + res->start < (1ULL<<20)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 49ff55e..89427d8 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -375,12 +375,6 @@ static int __init setup_early_printk(char *buf) if (!strncmp(buf, "xen", 3)) early_console_register(&xenboot_console, keep); #endif -#ifdef CONFIG_EARLY_PRINTK_INTEL_MID - if (!strncmp(buf, "hsu", 3)) { - hsu_early_console_init(buf + 3); - early_console_register(&early_hsu_console, keep); - } -#endif #ifdef CONFIG_EARLY_PRINTK_EFI if (!strncmp(buf, "efi", 3)) early_console_register(&early_efi_console, keep); diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 60705b03..7423e3e 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -295,6 +295,15 @@ system_call_fastpath: * rflags from r11 (but RF and VM bits are forced to 0), * cs and ss are loaded from MSRs. * Restoration of rflags re-enables interrupts. + * + * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss + * descriptor is not reinitialized. This means that we should + * avoid SYSRET with SS == NULL, which could happen if we schedule, + * exit the kernel, and re-enter using an interrupt vector. (All + * interrupt entries on x86_64 set SS to NULL.) We prevent that + * from happening by reloading SS in __switch_to. (Actually + * detecting the failure in 64-bit userspace is tricky but can be + * done.) */ USERGS_SYSRET64 diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 367f39d..00918327 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -341,7 +341,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct xsave_struct *xsave = &target->thread.fpu.state->xsave; + struct xsave_struct *xsave; int ret; if (!cpu_has_xsave) @@ -351,6 +351,8 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + xsave = &target->thread.fpu.state->xsave; + /* * Copy the 48bytes defined by the software first into the xstate * memory layout in the thread struct, so that we can copy the entire @@ -369,7 +371,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct xsave_struct *xsave = &target->thread.fpu.state->xsave; + struct xsave_struct *xsave; int ret; if (!cpu_has_xsave) @@ -379,6 +381,8 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + xsave = &target->thread.fpu.state->xsave; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); /* * mxcsr reserved bits must be masked to zero for security reasons. diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 24d0796..1deffe6 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -354,6 +354,7 @@ int __copy_instruction(u8 *dest, u8 *src) { struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; + int length; unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src); @@ -361,16 +362,18 @@ int __copy_instruction(u8 *dest, u8 *src) return 0; kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); + length = insn.length; + /* Another subsystem puts a breakpoint, failed to recover */ if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; - memcpy(dest, insn.kaddr, insn.length); + memcpy(dest, insn.kaddr, length); #ifdef CONFIG_X86_64 if (insn_rip_relative(&insn)) { s64 newdisp; u8 *disp; - kernel_insn_init(&insn, dest, insn.length); + kernel_insn_init(&insn, dest, length); insn_get_displacement(&insn); /* * The copied instruction uses the %rip-relative addressing @@ -394,7 +397,7 @@ int __copy_instruction(u8 *dest, u8 *src) *(s32 *) disp = (s32) newdisp; } #endif - return insn.length; + return length; } static int arch_copy_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e354cc6..9435620 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -513,7 +513,7 @@ void __init kvm_guest_init(void) * can get false positives too easily, for example if the host is * overcommitted. */ - watchdog_enable_hardlockup_detector(false); + hardlockup_detector_disable(); } static noinline uint32_t __kvm_cpuid_base(void) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 7563114..58bcfb6 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -445,7 +445,7 @@ struct pv_mmu_ops pv_mmu_ops = { .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, -#if PAGETABLE_LEVELS >= 3 +#if CONFIG_PGTABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE .set_pte_atomic = native_set_pte_atomic, .pte_clear = native_pte_clear, @@ -456,13 +456,13 @@ struct pv_mmu_ops pv_mmu_ops = { .pmd_val = PTE_IDENT, .make_pmd = PTE_IDENT, -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 .pud_val = PTE_IDENT, .make_pud = PTE_IDENT, .set_pgd = native_set_pgd, #endif -#endif /* PAGETABLE_LEVELS >= 3 */ +#endif /* CONFIG_PGTABLE_LEVELS >= 3 */ .pte_val = PTE_IDENT, .pgd_val = PTE_IDENT, diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c new file mode 100644 index 0000000..3420c87 --- /dev/null +++ b/arch/x86/kernel/pmem.c @@ -0,0 +1,53 @@ +/* + * Copyright (c) 2015, Christoph Hellwig. + */ +#include <linux/memblock.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <asm/e820.h> +#include <asm/page_types.h> +#include <asm/setup.h> + +static __init void register_pmem_device(struct resource *res) +{ + struct platform_device *pdev; + int error; + + pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO); + if (!pdev) + return; + + error = platform_device_add_resources(pdev, res, 1); + if (error) + goto out_put_pdev; + + error = platform_device_add(pdev); + if (error) + goto out_put_pdev; + return; + +out_put_pdev: + dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n"); + platform_device_put(pdev); +} + +static __init int register_pmem_devices(void) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (ei->type == E820_PRAM) { + struct resource res = { + .flags = IORESOURCE_MEM, + .start = ei->addr, + .end = ei->addr + ei->size - 1, + }; + register_pmem_device(&res); + } + } + + return 0; +} +device_initcall(register_pmem_devices); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 8213da6..6e338e3 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -57,7 +57,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif }; -EXPORT_PER_CPU_SYMBOL_GPL(cpu_tss); +EXPORT_PER_CPU_SYMBOL(cpu_tss); #ifdef CONFIG_X86_64 static DEFINE_PER_CPU(unsigned char, is_idle); @@ -156,11 +156,13 @@ void flush_thread(void) /* FPU state will be reallocated lazily at the first use. */ drop_fpu(tsk); free_thread_xstate(tsk); - } else if (!used_math()) { - /* kthread execs. TODO: cleanup this horror. */ - if (WARN_ON(init_fpu(tsk))) - force_sig(SIGKILL, tsk); - user_fpu_begin(); + } else { + if (!tsk_used_math(tsk)) { + /* kthread execs. TODO: cleanup this horror. */ + if (WARN_ON(init_fpu(tsk))) + force_sig(SIGKILL, tsk); + user_fpu_begin(); + } restore_init_xstate(); } } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4baaa97..ddfdbf7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -419,6 +419,34 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); + if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { + /* + * AMD CPUs have a misfeature: SYSRET sets the SS selector but + * does not update the cached descriptor. As a result, if we + * do SYSRET while SS is NULL, we'll end up in user mode with + * SS apparently equal to __USER_DS but actually unusable. + * + * The straightforward workaround would be to fix it up just + * before SYSRET, but that would slow down the system call + * fast paths. Instead, we ensure that SS is never NULL in + * system call context. We do this by replacing NULL SS + * selectors at every context switch. SYSCALL sets up a valid + * SS, so the only way to get NULL is to re-enter the kernel + * from CPL 3 through an interrupt. Since that can't happen + * in the same task as a running syscall, we are guaranteed to + * context switch between every interrupt vector entry and a + * subsequent SYSRET. + * + * We read SS first because SS reads are much faster than + * writes. Out of caution, we force SS to __KERNEL_DS even if + * it previously had a different non-NULL value. + */ + unsigned short ss_sel; + savesegment(ss, ss_sel); + if (ss_sel != __KERNEL_DS) + loadsegment(ss, __KERNEL_DS); + } + return prev_p; } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index e5ecd20..2f355d2 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,46 +141,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } -static struct pvclock_vsyscall_time_info *pvclock_vdso_info; - -static struct pvclock_vsyscall_time_info * -pvclock_get_vsyscall_user_time_info(int cpu) -{ - if (!pvclock_vdso_info) { - BUG(); - return NULL; - } - - return &pvclock_vdso_info[cpu]; -} - -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -{ - return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -} - #ifdef CONFIG_X86_64 -static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, - void *v) -{ - struct task_migration_notifier *mn = v; - struct pvclock_vsyscall_time_info *pvti; - - pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); - - /* this is NULL when pvclock vsyscall is not initialized */ - if (unlikely(pvti == NULL)) - return NOTIFY_DONE; - - pvti->migrate_count++; - - return NOTIFY_DONE; -} - -static struct notifier_block pvclock_migrate = { - .notifier_call = pvclock_task_migrate, -}; - /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - pvclock_vdso_info = i; - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } - - register_task_migration_notifier(&pvclock_migrate); - return 0; } #endif diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 3e58186..1ea14fd 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -593,24 +593,10 @@ badframe: return 0; } -/* - * OK, we're invoking a handler: - */ -static int signr_convert(int sig) -{ -#ifdef CONFIG_X86_32 - struct thread_info *info = current_thread_info(); - - if (info->exec_domain && info->exec_domain->signal_invmap && sig < 32) - return info->exec_domain->signal_invmap[sig]; -#endif /* CONFIG_X86_32 */ - return sig; -} - static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { - int usig = signr_convert(ksig->sig); + int usig = ksig->sig; sigset_t *set = sigmask_to_save(); compat_sigset_t *cset = (compat_sigset_t *) set; @@ -630,7 +616,8 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { - bool failed; + bool stepping, failed; + /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { /* If so, check system call restarting.. */ @@ -654,12 +641,13 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) } /* - * If TF is set due to a debugger (TIF_FORCED_TF), clear the TF - * flag so that register information in the sigcontext is correct. + * If TF is set due to a debugger (TIF_FORCED_TF), clear TF now + * so that register information in the sigcontext is correct and + * then notify the tracer before entering the signal handler. */ - if (unlikely(regs->flags & X86_EFLAGS_TF) && - likely(test_and_clear_thread_flag(TIF_FORCED_TF))) - regs->flags &= ~X86_EFLAGS_TF; + stepping = test_thread_flag(TIF_SINGLESTEP); + if (stepping) + user_disable_single_step(current); failed = (setup_rt_frame(ksig, regs) < 0); if (!failed) { @@ -670,10 +658,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * it might disable possible debug exception from the * signal handler. * - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. + * Clear TF for the case when it wasn't set by debugger to + * avoid the recursive send_sigtrap() in SIGTRAP handler. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); /* @@ -682,7 +668,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) if (used_math()) fpu_reset_state(current); } - signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); + signal_setup_done(failed, ksig, stepping); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7035f6b..50e547e 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,9 +77,6 @@ #include <asm/realmode.h> #include <asm/misc.h> -/* State of each CPU */ -DEFINE_PER_CPU(int, cpu_state) = { 0 }; - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); @@ -257,7 +254,7 @@ static void notrace start_secondary(void *unused) lock_vector_lock(); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); - per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; + cpu_set_state_online(smp_processor_id()); x86_platform.nmi_init(); /* enable local interrupts */ @@ -954,7 +951,10 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) */ mtrr_save_state(); - per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + /* x86 CPUs take themselves offline, so delayed offline is OK. */ + err = cpu_check_up_prepare(cpu); + if (err && err != -EBUSY) + return err; /* the FPU context is blank, nobody can own it */ __cpu_disable_lazy_restore(cpu); @@ -1197,7 +1197,7 @@ void __init native_smp_prepare_boot_cpu(void) switch_to_new_gdt(me); /* already set me in cpu_online_mask in boot_cpu_init() */ cpumask_set_cpu(me, cpu_callout_mask); - per_cpu(cpu_state, me) = CPU_ONLINE; + cpu_set_state_online(me); } void __init native_smp_cpus_done(unsigned int max_cpus) @@ -1324,14 +1324,10 @@ static void __ref remove_cpu_from_maps(int cpu) numa_remove_cpu(cpu); } -static DEFINE_PER_CPU(struct completion, die_complete); - void cpu_disable_common(void) { int cpu = smp_processor_id(); - init_completion(&per_cpu(die_complete, smp_processor_id())); - remove_siblinginfo(cpu); /* It's now safe to remove this processor from the online map */ @@ -1355,24 +1351,27 @@ int native_cpu_disable(void) return 0; } -void cpu_die_common(unsigned int cpu) +int common_cpu_die(unsigned int cpu) { - wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ); -} + int ret = 0; -void native_cpu_die(unsigned int cpu) -{ /* We don't do anything here: idle task is faking death itself. */ - cpu_die_common(cpu); - /* They ack this in play_dead() by setting CPU_DEAD */ - if (per_cpu(cpu_state, cpu) == CPU_DEAD) { + if (cpu_wait_death(cpu, 5)) { if (system_state == SYSTEM_RUNNING) pr_info("CPU %u is now offline\n", cpu); } else { pr_err("CPU %u didn't die...\n", cpu); + ret = -1; } + + return ret; +} + +void native_cpu_die(unsigned int cpu) +{ + common_cpu_die(cpu); } void play_dead_common(void) @@ -1381,10 +1380,8 @@ void play_dead_common(void) reset_lazy_tlbstate(); amd_e400_remove_cpu(raw_smp_processor_id()); - mb(); /* Ack it */ - __this_cpu_write(cpu_state, CPU_DEAD); - complete(&per_cpu(die_complete, smp_processor_id())); + (void)cpu_report_death(); /* * With physical CPU hotplug, we should halt the cpu diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c index b79133a..5ecbfe5 100644 --- a/arch/x86/kernel/test_rodata.c +++ b/arch/x86/kernel/test_rodata.c @@ -57,7 +57,7 @@ int rodata_test(void) /* test 3: check the value hasn't changed */ /* If this test fails, we managed to overwrite the data */ if (!rodata_test_data) { - printk(KERN_ERR "rodata_test: Test 3 failes (end data)\n"); + printk(KERN_ERR "rodata_test: Test 3 fails (end data)\n"); return -ENODEV; } /* test 4: check if the rodata section is 4Kb aligned */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f4fa991..324ab52 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -123,7 +123,7 @@ enum ctx_state ist_enter(struct pt_regs *regs) * but we need to notify RCU. */ rcu_nmi_enter(); - prev_state = IN_KERNEL; /* the value is irrelevant. */ + prev_state = CONTEXT_KERNEL; /* the value is irrelevant. */ } /* |