diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/syscall.c | 7 | ||||
-rw-r--r-- | kernel/events/core.c | 752 | ||||
-rw-r--r-- | kernel/events/hw_breakpoint.c | 8 | ||||
-rw-r--r-- | kernel/events/internal.h | 33 | ||||
-rw-r--r-- | kernel/events/ring_buffer.c | 327 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 8 | ||||
-rw-r--r-- | kernel/trace/Makefile | 1 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 222 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 10 | ||||
-rw-r--r-- | kernel/trace/trace_uprobe.c | 10 | ||||
-rw-r--r-- | kernel/watchdog.c | 28 |
11 files changed, 1226 insertions, 180 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 536edc2..504c10b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -16,6 +16,7 @@ #include <linux/file.h> #include <linux/license.h> #include <linux/filter.h> +#include <linux/version.h> static LIST_HEAD(bpf_map_types); @@ -467,7 +468,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_buf +#define BPF_PROG_LOAD_LAST_FIELD kern_version static int bpf_prog_load(union bpf_attr *attr) { @@ -492,6 +493,10 @@ static int bpf_prog_load(union bpf_attr *attr) if (attr->insn_cnt >= BPF_MAXINSNS) return -EINVAL; + if (type == BPF_PROG_TYPE_KPROBE && + attr->kern_version != LINUX_VERSION_CODE) + return -EINVAL; + /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) diff --git a/kernel/events/core.c b/kernel/events/core.c index 2fabc06..06917d5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -34,14 +34,16 @@ #include <linux/syscalls.h> #include <linux/anon_inodes.h> #include <linux/kernel_stat.h> +#include <linux/cgroup.h> #include <linux/perf_event.h> #include <linux/ftrace_event.h> #include <linux/hw_breakpoint.h> #include <linux/mm_types.h> -#include <linux/cgroup.h> #include <linux/module.h> #include <linux/mman.h> #include <linux/compat.h> +#include <linux/bpf.h> +#include <linux/filter.h> #include "internal.h" @@ -153,7 +155,7 @@ enum event_type_t { */ struct static_key_deferred perf_sched_events __read_mostly; static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); -static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events); +static DEFINE_PER_CPU(int, perf_sched_cb_usages); static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; @@ -327,6 +329,11 @@ static inline u64 perf_clock(void) return local_clock(); } +static inline u64 perf_event_clock(struct perf_event *event) +{ + return event->clock(); +} + static inline struct perf_cpu_context * __get_cpu_context(struct perf_event_context *ctx) { @@ -351,32 +358,6 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, #ifdef CONFIG_CGROUP_PERF -/* - * perf_cgroup_info keeps track of time_enabled for a cgroup. - * This is a per-cpu dynamically allocated data structure. - */ -struct perf_cgroup_info { - u64 time; - u64 timestamp; -}; - -struct perf_cgroup { - struct cgroup_subsys_state css; - struct perf_cgroup_info __percpu *info; -}; - -/* - * Must ensure cgroup is pinned (css_get) before calling - * this function. In other words, we cannot call this function - * if there is no cgroup event for the current CPU context. - */ -static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) -{ - return container_of(task_css(task, perf_event_cgrp_id), - struct perf_cgroup, css); -} - static inline bool perf_cgroup_match(struct perf_event *event) { @@ -905,6 +886,15 @@ static void get_ctx(struct perf_event_context *ctx) WARN_ON(!atomic_inc_not_zero(&ctx->refcount)); } +static void free_ctx(struct rcu_head *head) +{ + struct perf_event_context *ctx; + + ctx = container_of(head, struct perf_event_context, rcu_head); + kfree(ctx->task_ctx_data); + kfree(ctx); +} + static void put_ctx(struct perf_event_context *ctx) { if (atomic_dec_and_test(&ctx->refcount)) { @@ -912,7 +902,7 @@ static void put_ctx(struct perf_event_context *ctx) put_ctx(ctx->parent_ctx); if (ctx->task) put_task_struct(ctx->task); - kfree_rcu(ctx, rcu_head); + call_rcu(&ctx->rcu_head, free_ctx); } } @@ -1239,9 +1229,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) if (is_cgroup_event(event)) ctx->nr_cgroups++; - if (has_branch_stack(event)) - ctx->nr_branch_stack++; - list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; if (event->attr.inherit_stat) @@ -1408,9 +1395,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) cpuctx->cgrp = NULL; } - if (has_branch_stack(event)) - ctx->nr_branch_stack--; - ctx->nr_events--; if (event->attr.inherit_stat) ctx->nr_stat--; @@ -1847,6 +1831,7 @@ static void perf_set_shadow_time(struct perf_event *event, #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); +static void perf_log_itrace_start(struct perf_event *event); static int event_sched_in(struct perf_event *event, @@ -1881,6 +1866,12 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); + event->tstamp_running += tstamp - event->tstamp_stopped; + + perf_set_shadow_time(event, ctx, tstamp); + + perf_log_itrace_start(event); + if (event->pmu->add(event, PERF_EF_START)) { event->state = PERF_EVENT_STATE_INACTIVE; event->oncpu = -1; @@ -1888,10 +1879,6 @@ event_sched_in(struct perf_event *event, goto out; } - event->tstamp_running += tstamp - event->tstamp_stopped; - - perf_set_shadow_time(event, ctx, tstamp); - if (!is_software_event(event)) cpuctx->active_oncpu++; if (!ctx->nr_active++) @@ -2559,6 +2546,9 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, next->perf_event_ctxp[ctxn] = ctx; ctx->task = next; next_ctx->task = task; + + swap(ctx->task_ctx_data, next_ctx->task_ctx_data); + do_switch = 0; perf_event_sync_stat(ctx, next_ctx); @@ -2577,6 +2567,56 @@ unlock: } } +void perf_sched_cb_dec(struct pmu *pmu) +{ + this_cpu_dec(perf_sched_cb_usages); +} + +void perf_sched_cb_inc(struct pmu *pmu) +{ + this_cpu_inc(perf_sched_cb_usages); +} + +/* + * This function provides the context switch callback to the lower code + * layer. It is invoked ONLY when the context switch callback is enabled. + */ +static void perf_pmu_sched_task(struct task_struct *prev, + struct task_struct *next, + bool sched_in) +{ + struct perf_cpu_context *cpuctx; + struct pmu *pmu; + unsigned long flags; + + if (prev == next) + return; + + local_irq_save(flags); + + rcu_read_lock(); + + list_for_each_entry_rcu(pmu, &pmus, entry) { + if (pmu->sched_task) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + + perf_pmu_disable(pmu); + + pmu->sched_task(cpuctx->task_ctx, sched_in); + + perf_pmu_enable(pmu); + + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); + } + } + + rcu_read_unlock(); + + local_irq_restore(flags); +} + #define for_each_task_context_nr(ctxn) \ for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++) @@ -2596,6 +2636,9 @@ void __perf_event_task_sched_out(struct task_struct *task, { int ctxn; + if (__this_cpu_read(perf_sched_cb_usages)) + perf_pmu_sched_task(task, next, false); + for_each_task_context_nr(ctxn) perf_event_context_sched_out(task, ctxn, next); @@ -2755,64 +2798,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, } /* - * 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. Flushing may mean dropping the existing - * entries or stashing them somewhere in the PMU specific code layer. - * - * This function provides the context switch callback to the lower code - * layer. It is invoked ONLY when there is at least one system-wide context - * with at least one active event using taken branch sampling. - */ -static void perf_branch_stack_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cpu_context *cpuctx; - struct pmu *pmu; - unsigned long flags; - - /* no need to flush branch stack if not changing task */ - if (prev == task) - return; - - local_irq_save(flags); - - rcu_read_lock(); - - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - - /* - * check if the context has at least one - * event using PERF_SAMPLE_BRANCH_STACK - */ - if (cpuctx->ctx.nr_branch_stack > 0 - && pmu->flush_branch_stack) { - - perf_ctx_lock(cpuctx, cpuctx->task_ctx); - - perf_pmu_disable(pmu); - - pmu->flush_branch_stack(); - - perf_pmu_enable(pmu); - - perf_ctx_unlock(cpuctx, cpuctx->task_ctx); - } - } - - rcu_read_unlock(); - - local_irq_restore(flags); -} - -/* * Called from scheduler to add the events of the current task * with interrupts disabled. * @@ -2844,9 +2829,8 @@ void __perf_event_task_sched_in(struct task_struct *prev, if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) perf_cgroup_sched_in(prev, task); - /* check for system-wide branch_stack events */ - if (atomic_read(this_cpu_ptr(&perf_branch_stack_events))) - perf_branch_stack_sched_in(prev, task); + if (__this_cpu_read(perf_sched_cb_usages)) + perf_pmu_sched_task(prev, task, true); } static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) @@ -3220,7 +3204,10 @@ static void __perf_event_read(void *info) static inline u64 perf_event_count(struct perf_event *event) { - return local64_read(&event->count) + atomic64_read(&event->child_count); + if (event->pmu->count) + return event->pmu->count(event); + + return __perf_event_count(event); } static u64 perf_event_read(struct perf_event *event) @@ -3321,12 +3308,15 @@ errout: * Returns a matching context with refcount and pincount. */ static struct perf_event_context * -find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) +find_get_context(struct pmu *pmu, struct task_struct *task, + struct perf_event *event) { struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_cpu_context *cpuctx; + void *task_ctx_data = NULL; unsigned long flags; int ctxn, err; + int cpu = event->cpu; if (!task) { /* Must be root to operate on a CPU event: */ @@ -3354,11 +3344,24 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) if (ctxn < 0) goto errout; + if (event->attach_state & PERF_ATTACH_TASK_DATA) { + task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL); + if (!task_ctx_data) { + err = -ENOMEM; + goto errout; + } + } + retry: ctx = perf_lock_task_context(task, ctxn, &flags); if (ctx) { clone_ctx = unclone_ctx(ctx); ++ctx->pin_count; + + if (task_ctx_data && !ctx->task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } raw_spin_unlock_irqrestore(&ctx->lock, flags); if (clone_ctx) @@ -3369,6 +3372,11 @@ retry: if (!ctx) goto errout; + if (task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } + err = 0; mutex_lock(&task->perf_event_mutex); /* @@ -3395,13 +3403,16 @@ retry: } } + kfree(task_ctx_data); return ctx; errout: + kfree(task_ctx_data); return ERR_PTR(err); } static void perf_event_free_filter(struct perf_event *event); +static void perf_event_free_bpf_prog(struct perf_event *event); static void free_event_rcu(struct rcu_head *head) { @@ -3411,10 +3422,10 @@ static void free_event_rcu(struct rcu_head *head) if (event->ns) put_pid_ns(event->ns); perf_event_free_filter(event); + perf_event_free_bpf_prog(event); kfree(event); } -static void ring_buffer_put(struct ring_buffer *rb); static void ring_buffer_attach(struct perf_event *event, struct ring_buffer *rb); @@ -3423,10 +3434,6 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu) if (event->parent) return; - if (has_branch_stack(event)) { - if (!(event->attach_state & PERF_ATTACH_TASK)) - atomic_dec(&per_cpu(perf_branch_stack_events, cpu)); - } if (is_cgroup_event(event)) atomic_dec(&per_cpu(perf_cgroup_events, cpu)); } @@ -3454,6 +3461,91 @@ static void unaccount_event(struct perf_event *event) unaccount_event_cpu(event, event->cpu); } +/* + * The following implement mutual exclusion of events on "exclusive" pmus + * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled + * at a time, so we disallow creating events that might conflict, namely: + * + * 1) cpu-wide events in the presence of per-task events, + * 2) per-task events in the presence of cpu-wide events, + * 3) two matching events on the same context. + * + * The former two cases are handled in the allocation path (perf_event_alloc(), + * __free_event()), the latter -- before the first perf_install_in_context(). + */ +static int exclusive_event_init(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return 0; + + /* + * Prevent co-existence of per-task and cpu-wide events on the + * same exclusive pmu. + * + * Negative pmu::exclusive_cnt means there are cpu-wide + * events on this "exclusive" pmu, positive means there are + * per-task events. + * + * Since this is called in perf_event_alloc() path, event::ctx + * doesn't exist yet; it is, however, safe to use PERF_ATTACH_TASK + * to mean "per-task event", because unlike other attach states it + * never gets cleared. + */ + if (event->attach_state & PERF_ATTACH_TASK) { + if (!atomic_inc_unless_negative(&pmu->exclusive_cnt)) + return -EBUSY; + } else { + if (!atomic_dec_unless_positive(&pmu->exclusive_cnt)) + return -EBUSY; + } + + return 0; +} + +static void exclusive_event_destroy(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return; + + /* see comment in exclusive_event_init() */ + if (event->attach_state & PERF_ATTACH_TASK) + atomic_dec(&pmu->exclusive_cnt); + else + atomic_inc(&pmu->exclusive_cnt); +} + +static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) +{ + if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && + (e1->cpu == e2->cpu || + e1->cpu == -1 || + e2->cpu == -1)) + return true; + return false; +} + +/* Called under the same ctx::mutex as perf_install_in_context() */ +static bool exclusive_event_installable(struct perf_event *event, + struct perf_event_context *ctx) +{ + struct perf_event *iter_event; + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return true; + + list_for_each_entry(iter_event, &ctx->event_list, event_entry) { + if (exclusive_event_match(iter_event, event)) + return false; + } + + return true; +} + static void __free_event(struct perf_event *event) { if (!event->parent) { @@ -3467,8 +3559,10 @@ static void __free_event(struct perf_event *event) if (event->ctx) put_ctx(event->ctx); - if (event->pmu) + if (event->pmu) { + exclusive_event_destroy(event); module_put(event->pmu->module); + } call_rcu(&event->rcu_head, free_event_rcu); } @@ -3927,6 +4021,7 @@ static inline int perf_fget_light(int fd, struct fd *p) static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event); static int perf_event_set_filter(struct perf_event *event, void __user *arg); +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd); static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg) { @@ -3980,6 +4075,9 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon case PERF_EVENT_IOC_SET_FILTER: return perf_event_set_filter(event, (void __user *)arg); + case PERF_EVENT_IOC_SET_BPF: + return perf_event_set_bpf_prog(event, arg); + default: return -ENOTTY; } @@ -4096,6 +4194,8 @@ static void perf_event_init_userpage(struct perf_event *event) /* Allow new userspace to detect that bit 0 is deprecated */ userpg->cap_bit0_is_deprecated = 1; userpg->size = offsetof(struct perf_event_mmap_page, __reserved); + userpg->data_offset = PAGE_SIZE; + userpg->data_size = perf_data_size(rb); unlock: rcu_read_unlock(); @@ -4263,7 +4363,7 @@ static void rb_free_rcu(struct rcu_head *rcu_head) rb_free(rb); } -static struct ring_buffer *ring_buffer_get(struct perf_event *event) +struct ring_buffer *ring_buffer_get(struct perf_event *event) { struct ring_buffer *rb; @@ -4278,7 +4378,7 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event) return rb; } -static void ring_buffer_put(struct ring_buffer *rb) +void ring_buffer_put(struct ring_buffer *rb) { if (!atomic_dec_and_test(&rb->refcount)) return; @@ -4295,6 +4395,9 @@ static void perf_mmap_open(struct vm_area_struct *vma) atomic_inc(&event->mmap_count); atomic_inc(&event->rb->mmap_count); + if (vma->vm_pgoff) + atomic_inc(&event->rb->aux_mmap_count); + if (event->pmu->event_mapped) event->pmu->event_mapped(event); } @@ -4319,6 +4422,20 @@ static void perf_mmap_close(struct vm_area_struct *vma) if (event->pmu->event_unmapped) event->pmu->event_unmapped(event); + /* + * rb->aux_mmap_count will always drop before rb->mmap_count and + * event->mmap_count, so it is ok to use event->mmap_mutex to + * serialize with perf_mmap here. + */ + if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff && + atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) { + atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); + vma->vm_mm->pinned_vm -= rb->aux_mmap_locked; + + rb_free_aux(rb); + mutex_unlock(&event->mmap_mutex); + } + atomic_dec(&rb->mmap_count); if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) @@ -4392,7 +4509,7 @@ out_put: static const struct vm_operations_struct perf_mmap_vmops = { .open = perf_mmap_open, - .close = perf_mmap_close, + .close = perf_mmap_close, /* non mergable */ .fault = perf_mmap_fault, .page_mkwrite = perf_mmap_fault, }; @@ -4403,10 +4520,10 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) unsigned long user_locked, user_lock_limit; struct user_struct *user = current_user(); unsigned long locked, lock_limit; - struct ring_buffer *rb; + struct ring_buffer *rb = NULL; unsigned long vma_size; unsigned long nr_pages; - long user_extra, extra; + long user_extra = 0, extra = 0; int ret = 0, flags = 0; /* @@ -4421,7 +4538,66 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma_size = vma->vm_end - vma->vm_start; - nr_pages = (vma_size / PAGE_SIZE) - 1; + + if (vma->vm_pgoff == 0) { + nr_pages = (vma_size / PAGE_SIZE) - 1; + } else { + /* + * AUX area mapping: if rb->aux_nr_pages != 0, it's already + * mapped, all subsequent mappings should have the same size + * and offset. Must be above the normal perf buffer. + */ + u64 aux_offset, aux_size; + + if (!event->rb) + return -EINVAL; + + nr_pages = vma_size / PAGE_SIZE; + + mutex_lock(&event->mmap_mutex); + ret = -EINVAL; + + rb = event->rb; + if (!rb) + goto aux_unlock; + + aux_offset = ACCESS_ONCE(rb->user_page->aux_offset); + aux_size = ACCESS_ONCE(rb->user_page->aux_size); + + if (aux_offset < perf_data_size(rb) + PAGE_SIZE) + goto aux_unlock; + + if (aux_offset != vma->vm_pgoff << PAGE_SHIFT) + goto aux_unlock; + + /* already mapped with a different offset */ + if (rb_has_aux(rb) && rb->aux_pgoff != vma->vm_pgoff) + goto aux_unlock; + + if (aux_size != vma_size || aux_size != nr_pages * PAGE_SIZE) + goto aux_unlock; + + /* already mapped with a different size */ + if (rb_has_aux(rb) && rb->aux_nr_pages != nr_pages) + goto aux_unlock; + + if (!is_power_of_2(nr_pages)) + goto aux_unlock; + + if (!atomic_inc_not_zero(&rb->mmap_count)) + goto aux_unlock; + + if (rb_has_aux(rb)) { + atomic_inc(&rb->aux_mmap_count); + ret = 0; + goto unlock; + } + + atomic_set(&rb->aux_mmap_count, 1); + user_extra = nr_pages; + + goto accounting; + } /* * If we have rb pages ensure they're a power-of-two number, so we @@ -4433,9 +4609,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) if (vma_size != PAGE_SIZE * (1 + nr_pages)) return -EINVAL; - if (vma->vm_pgoff != 0) - return -EINVAL; - WARN_ON_ONCE(event->ctx->parent_ctx); again: mutex_lock(&event->mmap_mutex); @@ -4459,6 +4632,8 @@ again: } user_extra = nr_pages + 1; + +accounting: user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10); /* @@ -4468,7 +4643,6 @@ again: user_locked = atomic_long_read(&user->locked_vm) + user_extra; - extra = 0; if (user_locked > user_lock_limit) extra = user_locked - user_lock_limit; @@ -4482,35 +4656,46 @@ again: goto unlock; } - WARN_ON(event->rb); + WARN_ON(!rb && event->rb); if (vma->vm_flags & VM_WRITE) flags |= RING_BUFFER_WRITABLE; - rb = rb_alloc(nr_pages, - event->attr.watermark ? event->attr.wakeup_watermark : 0, - event->cpu, flags); - if (!rb) { - ret = -ENOMEM; - goto unlock; - } + rb = rb_alloc(nr_pages, + event->attr.watermark ? event->attr.wakeup_watermark : 0, + event->cpu, flags); - atomic_set(&rb->mmap_count, 1); - rb->mmap_locked = extra; - rb->mmap_user = get_current_user(); + if (!rb) { + ret = -ENOMEM; + goto unlock; + } - atomic_long_add(user_extra, &user->locked_vm); - vma->vm_mm->pinned_vm += extra; + atomic_set(&rb->mmap_count, 1); + rb->mmap_user = get_current_user(); + rb->mmap_locked = extra; - ring_buffer_attach(event, rb); + ring_buffer_attach(event, rb); - perf_event_init_userpage(event); - perf_event_update_userpage(event); + perf_event_init_userpage(event); + perf_event_update_userpage(event); + } else { + ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages, + event->attr.aux_watermark, flags); + if (!ret) + rb->aux_mmap_locked = extra; + } unlock: - if (!ret) + if (!ret) { + atomic_long_add(user_extra, &user->locked_vm); + vma->vm_mm->pinned_vm += extra; + atomic_inc(&event->mmap_count); + } else if (rb) { + atomic_dec(&rb->mmap_count); + } +aux_unlock: mutex_unlock(&event->mmap_mutex); /* @@ -4766,7 +4951,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header, } if (sample_type & PERF_SAMPLE_TIME) - data->time = perf_clock(); + data->time = perf_event_clock(event); if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) data->id = primary_event_id(event); @@ -5344,6 +5529,8 @@ static void perf_event_task_output(struct perf_event *event, task_event->event_id.tid = perf_event_tid(event, task); task_event->event_id.ptid = perf_event_tid(event, current); + task_event->event_id.time = perf_event_clock(event); + perf_output_put(&handle, task_event->event_id); perf_event__output_id_sample(event, &handle, &sample); @@ -5377,7 +5564,7 @@ static void perf_event_task(struct task_struct *task, /* .ppid */ /* .tid */ /* .ptid */ - .time = perf_clock(), + /* .time */ }, }; @@ -5732,6 +5919,40 @@ void perf_event_mmap(struct vm_area_struct *vma) perf_event_mmap_event(&mmap_event); } +void perf_event_aux_event(struct perf_event *event, unsigned long head, + unsigned long size, u64 flags) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u64 offset; + u64 size; + u64 flags; + } rec = { + .header = { + .type = PERF_RECORD_AUX, + .misc = 0, + .size = sizeof(rec), + }, + .offset = head, + .size = size, + .flags = flags, + }; + int ret; + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + /* * IRQ throttle logging */ @@ -5753,7 +5974,7 @@ static void perf_log_throttle(struct perf_event *event, int enable) .misc = 0, .size = sizeof(throttle_event), }, - .time = perf_clock(), + .time = perf_event_clock(event), .id = primary_event_id(event), .stream_id = event->id, }; @@ -5773,6 +5994,44 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_output_end(&handle); } +static void perf_log_itrace_start(struct perf_event *event) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u32 pid; + u32 tid; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) || + event->hw.itrace_started) + return; + + event->hw.itrace_started = 1; + + rec.header.type = PERF_RECORD_ITRACE_START; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.pid = perf_event_pid(event, current); + rec.tid = perf_event_tid(event, current); + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + /* * Generic event overflow handling, sampling. */ @@ -6133,6 +6392,7 @@ static int perf_swevent_add(struct perf_event *event, int flags) } hlist_add_head_rcu(&event->hlist_entry, head); + perf_event_update_userpage(event); return 0; } @@ -6296,6 +6556,8 @@ static int perf_swevent_init(struct perf_event *event) static struct pmu perf_swevent = { .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_NMI, + .event_init = perf_swevent_init, .add = perf_swevent_add, .del = perf_swevent_del, @@ -6449,6 +6711,49 @@ static void perf_event_free_filter(struct perf_event *event) ftrace_profile_free_filter(event); } +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) +{ + struct bpf_prog *prog; + + if (event->attr.type != PERF_TYPE_TRACEPOINT) + return -EINVAL; + + if (event->tp_event->prog) + return -EEXIST; + + if (!(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) + /* bpf programs can only be attached to kprobes */ + return -EINVAL; + + prog = bpf_prog_get(prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (prog->aux->prog_type != BPF_PROG_TYPE_KPROBE) { + /* valid fd, but invalid bpf program type */ + bpf_prog_put(prog); + return -EINVAL; + } + + event->tp_event->prog = prog; + + return 0; +} + +static void perf_event_free_bpf_prog(struct perf_event *event) +{ + struct bpf_prog *prog; + + if (!event->tp_event) + return; + + prog = event->tp_event->prog; + if (prog) { + event->tp_event->prog = NULL; + bpf_prog_put(prog); + } +} + #else static inline void perf_tp_register(void) @@ -6464,6 +6769,14 @@ static void perf_event_free_filter(struct perf_event *event) { } +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) +{ + return -ENOENT; +} + +static void perf_event_free_bpf_prog(struct perf_event *event) +{ +} #endif /* CONFIG_EVENT_TRACING */ #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -6602,6 +6915,7 @@ static int cpu_clock_event_add(struct perf_event *event, int flags) { if (flags & PERF_EF_START) cpu_clock_event_start(event, flags); + perf_event_update_userpage(event); return 0; } @@ -6638,6 +6952,8 @@ static int cpu_clock_event_init(struct perf_event *event) static struct pmu perf_cpu_clock = { .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_NMI, + .event_init = cpu_clock_event_init, .add = cpu_clock_event_add, .del = cpu_clock_event_del, @@ -6676,6 +6992,7 @@ static int task_clock_event_add(struct perf_event *event, int flags) { if (flags & PERF_EF_START) task_clock_event_start(event, flags); + perf_event_update_userpage(event); return 0; } @@ -6716,6 +7033,8 @@ static int task_clock_event_init(struct perf_event *event) static struct pmu perf_task_clock = { .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_NMI, + .event_init = task_clock_event_init, .add = task_clock_event_add, .del = task_clock_event_del, @@ -6993,6 +7312,7 @@ got_cpu_context: pmu->event_idx = perf_event_idx_default; list_add_rcu(&pmu->entry, &pmus); + atomic_set(&pmu->exclusive_cnt, 0); ret = 0; unlock: mutex_unlock(&pmus_lock); @@ -7037,12 +7357,23 @@ EXPORT_SYMBOL_GPL(perf_pmu_unregister); static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) { + struct perf_event_context *ctx = NULL; int ret; if (!try_module_get(pmu->module)) return -ENODEV; + + if (event->group_leader != event) { + ctx = perf_event_ctx_lock(event->group_leader); + BUG_ON(!ctx); + } + event->pmu = pmu; ret = pmu->event_init(event); + + if (ctx) + perf_event_ctx_unlock(event->group_leader, ctx); + if (ret) module_put(pmu->module); @@ -7089,10 +7420,6 @@ static void account_event_cpu(struct perf_event *event, int cpu) if (event->parent) return; - if (has_branch_stack(event)) { - if (!(event->attach_state & PERF_ATTACH_TASK)) - atomic_inc(&per_cpu(perf_branch_stack_events, cpu)); - } if (is_cgroup_event(event)) atomic_inc(&per_cpu(perf_cgroup_events, cpu)); } @@ -7131,7 +7458,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, struct perf_event *group_leader, struct perf_event *parent_event, perf_overflow_handler_t overflow_handler, - void *context) + void *context, int cgroup_fd) { struct pmu *pmu; struct perf_event *event; @@ -7186,18 +7513,18 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (task) { event->attach_state = PERF_ATTACH_TASK; - - if (attr->type == PERF_TYPE_TRACEPOINT) - event->hw.tp_target = task; -#ifdef CONFIG_HAVE_HW_BREAKPOINT /* - * hw_breakpoint is a bit difficult here.. + * XXX pmu::event_init needs to know what task to account to + * and we cannot use the ctx information because we need the + * pmu before we get a ctx. */ - else if (attr->type == PERF_TYPE_BREAKPOINT) - event->hw.bp_target = task; -#endif + event->hw.target = task; } + event->clock = &local_clock; + if (parent_event) + event->clock = parent_event->clock; + if (!overflow_handler && parent_event) { overflow_handler = parent_event->overflow_handler; context = parent_event->overflow_handler_context; @@ -7224,6 +7551,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP)) goto err_ns; + if (!has_branch_stack(event)) + event->attr.branch_sample_type = 0; + + if (cgroup_fd != -1) { + err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader); + if (err) + goto err_ns; + } + pmu = perf_init_event(event); if (!pmu) goto err_ns; @@ -7232,21 +7568,30 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, goto err_ns; } + err = exclusive_event_init(event); + if (err) + goto err_pmu; + if (!event->parent) { if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { err = get_callchain_buffers(); if (err) - goto err_pmu; + goto err_per_task; } } return event; +err_per_task: + exclusive_event_destroy(event); + err_pmu: if (event->destroy) event->destroy(event); module_put(pmu->module); err_ns: + if (is_cgroup_event(event)) + perf_detach_cgroup(event); if (event->ns) put_pid_ns(event->ns); kfree(event); @@ -7409,6 +7754,19 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) if (output_event->cpu == -1 && output_event->ctx != event->ctx) goto out; + /* + * Mixing clocks in the same buffer is trouble you don't need. + */ + if (output_event->clock != event->clock) + goto out; + + /* + * If both events generate aux data, they must be on the same PMU + */ + if (has_aux(event) && has_aux(output_event) && + event->pmu != output_event->pmu) + goto out; + set: mutex_lock(&event->mmap_mutex); /* Can't redirect output if we've got an active mmap() */ @@ -7441,6 +7799,43 @@ static void mutex_lock_double(struct mutex *a, struct mutex *b) mutex_lock_nested(b, SINGLE_DEPTH_NESTING); } +static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) +{ + bool nmi_safe = false; + + switch (clk_id) { + case CLOCK_MONOTONIC: + event->clock = &ktime_get_mono_fast_ns; + nmi_safe = true; + break; + + case CLOCK_MONOTONIC_RAW: + event->clock = &ktime_get_raw_fast_ns; + nmi_safe = true; + break; + + case CLOCK_REALTIME: + event->clock = &ktime_get_real_ns; + break; + + case CLOCK_BOOTTIME: + event->clock = &ktime_get_boot_ns; + break; + + case CLOCK_TAI: + event->clock = &ktime_get_tai_ns; + break; + + default: + return -EINVAL; + } + + if (!nmi_safe && !(event->pmu->capabilities & PERF_PMU_CAP_NO_NMI)) + return -EINVAL; + + return 0; +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -7465,6 +7860,7 @@ SYSCALL_DEFINE5(perf_event_open, int move_group = 0; int err; int f_flags = O_RDWR; + int cgroup_fd = -1; /* for future expandability... */ if (flags & ~PERF_FLAG_ALL) @@ -7530,21 +7926,16 @@ SYSCALL_DEFINE5(perf_event_open, get_online_cpus(); + if (flags & PERF_FLAG_PID_CGROUP) + cgroup_fd = pid; + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, - NULL, NULL); + NULL, NULL, cgroup_fd); if (IS_ERR(event)) { err = PTR_ERR(event); goto err_cpus; } - if (flags & PERF_FLAG_PID_CGROUP) { - err = perf_cgroup_connect(pid, event, &attr, group_leader); - if (err) { - __free_event(event); - goto err_cpus; - } - } - if (is_sampling_event(event)) { if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) { err = -ENOTSUPP; @@ -7560,6 +7951,12 @@ SYSCALL_DEFINE5(perf_event_open, */ pmu = event->pmu; + if (attr.use_clockid) { + err = perf_event_set_clock(event, attr.clockid); + if (err) + goto err_alloc; + } + if (group_leader && (is_software_event(event) != is_software_event(group_leader))) { if (is_software_event(event)) { @@ -7586,12 +7983,17 @@ SYSCALL_DEFINE5(perf_event_open, /* * Get the target context (task or percpu): */ - ctx = find_get_context(pmu, task, event->cpu); + ctx = find_get_context(pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_alloc; } + if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) { + err = -EBUSY; + goto err_context; + } + if (task) { put_task_struct(task); task = NULL; @@ -7609,6 +8011,11 @@ SYSCALL_DEFINE5(perf_event_open, */ if (group_leader->group_leader != group_leader) goto err_context; + + /* All events in a group should have the same clock */ + if (group_leader->clock != event->clock) + goto err_context; + /* * Do not allow to attach to a group in a different * task or CPU context: @@ -7709,6 +8116,13 @@ SYSCALL_DEFINE5(perf_event_open, get_ctx(ctx); } + if (!exclusive_event_installable(event, ctx)) { + err = -EBUSY; + mutex_unlock(&ctx->mutex); + fput(event_file); + goto err_context; + } + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); @@ -7781,7 +8195,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, */ event = perf_event_alloc(attr, cpu, task, NULL, NULL, - overflow_handler, context); + overflow_handler, context, -1); if (IS_ERR(event)) { err = PTR_ERR(event); goto err; @@ -7792,7 +8206,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, account_event(event); - ctx = find_get_context(event->pmu, task, cpu); + ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_free; @@ -7800,6 +8214,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); + if (!exclusive_event_installable(event, ctx)) { + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); + err = -EBUSY; + goto err_free; + } + perf_install_in_context(ctx, event, cpu); perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); @@ -8142,7 +8564,7 @@ inherit_event(struct perf_event *parent_event, parent_event->cpu, child, group_leader, parent_event, - NULL, NULL); + NULL, NULL, -1); if (IS_ERR(child_event)) return child_event; diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 9803a66..92ce5f4 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -116,12 +116,12 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type) */ static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type) { - struct task_struct *tsk = bp->hw.bp_target; + struct task_struct *tsk = bp->hw.target; struct perf_event *iter; int count = 0; list_for_each_entry(iter, &bp_task_head, hw.bp_list) { - if (iter->hw.bp_target == tsk && + if (iter->hw.target == tsk && find_slot_idx(iter) == type && (iter->cpu < 0 || cpu == iter->cpu)) count += hw_breakpoint_weight(iter); @@ -153,7 +153,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp, int nr; nr = info->cpu_pinned; - if (!bp->hw.bp_target) + if (!bp->hw.target) nr += max_task_bp_pinned(cpu, type); else nr += task_bp_pinned(cpu, bp, type); @@ -210,7 +210,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, weight = -weight; /* Pinned counter cpu profiling */ - if (!bp->hw.bp_target) { + if (!bp->hw.target) { get_bp_info(bp->cpu, type)->cpu_pinned += weight; return; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 569b2187..9f6ce9b 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -27,6 +27,7 @@ struct ring_buffer { local_t lost; /* nr records lost */ long watermark; /* wakeup watermark */ + long aux_watermark; /* poll crap */ spinlock_t event_lock; struct list_head event_list; @@ -35,6 +36,20 @@ struct ring_buffer { unsigned long mmap_locked; struct user_struct *mmap_user; + /* AUX area */ + local_t aux_head; + local_t aux_nest; + local_t aux_wakeup; + unsigned long aux_pgoff; + int aux_nr_pages; + int aux_overwrite; + atomic_t aux_mmap_count; + unsigned long aux_mmap_locked; + void (*free_aux)(void *); + atomic_t aux_refcount; + void **aux_pages; + void *aux_priv; + struct perf_event_mmap_page *user_page; void *data_pages[0]; }; @@ -43,6 +58,19 @@ extern void rb_free(struct ring_buffer *rb); extern struct ring_buffer * rb_alloc(int nr_pages, long watermark, int cpu, int flags); extern void perf_event_wakeup(struct perf_event *event); +extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, + pgoff_t pgoff, int nr_pages, long watermark, int flags); +extern void rb_free_aux(struct ring_buffer *rb); +extern struct ring_buffer *ring_buffer_get(struct perf_event *event); +extern void ring_buffer_put(struct ring_buffer *rb); + +static inline bool rb_has_aux(struct ring_buffer *rb) +{ + return !!rb->aux_nr_pages; +} + +void perf_event_aux_event(struct perf_event *event, unsigned long head, + unsigned long size, u64 flags); extern void perf_event_header__init_id(struct perf_event_header *header, @@ -81,6 +109,11 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb) return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); } +static inline unsigned long perf_aux_size(struct ring_buffer *rb) +{ + return rb->aux_nr_pages << PAGE_SHIFT; +} + #define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ static inline unsigned long \ func_name(struct perf_output_handle *handle, \ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index eadb95c..232f00f 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -243,14 +243,317 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) spin_lock_init(&rb->event_lock); } +/* + * This is called before hardware starts writing to the AUX area to + * obtain an output handle and make sure there's room in the buffer. + * When the capture completes, call perf_aux_output_end() to commit + * the recorded data to the buffer. + * + * The ordering is similar to that of perf_output_{begin,end}, with + * the exception of (B), which should be taken care of by the pmu + * driver, since ordering rules will differ depending on hardware. + */ +void *perf_aux_output_begin(struct perf_output_handle *handle, + struct perf_event *event) +{ + struct perf_event *output_event = event; + unsigned long aux_head, aux_tail; + struct ring_buffer *rb; + + if (output_event->parent) + output_event = output_event->parent; + + /* + * Since this will typically be open across pmu::add/pmu::del, we + * grab ring_buffer's refcount instead of holding rcu read lock + * to make sure it doesn't disappear under us. + */ + rb = ring_buffer_get(output_event); + if (!rb) + return NULL; + + if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount)) + goto err; + + /* + * Nesting is not supported for AUX area, make sure nested + * writers are caught early + */ + if (WARN_ON_ONCE(local_xchg(&rb->aux_nest, 1))) + goto err_put; + + aux_head = local_read(&rb->aux_head); + + handle->rb = rb; + handle->event = event; + handle->head = aux_head; + handle->size = 0; + + /* + * In overwrite mode, AUX data stores do not depend on aux_tail, + * therefore (A) control dependency barrier does not exist. The + * (B) <-> (C) ordering is still observed by the pmu driver. + */ + if (!rb->aux_overwrite) { + aux_tail = ACCESS_ONCE(rb->user_page->aux_tail); + handle->wakeup = local_read(&rb->aux_wakeup) + rb->aux_watermark; + if (aux_head - aux_tail < perf_aux_size(rb)) + handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb)); + + /* + * handle->size computation depends on aux_tail load; this forms a + * control dependency barrier separating aux_tail load from aux data + * store that will be enabled on successful return + */ + if (!handle->size) { /* A, matches D */ + event->pending_disable = 1; + perf_output_wakeup(handle); + local_set(&rb->aux_nest, 0); + goto err_put; + } + } + + return handle->rb->aux_priv; + +err_put: + rb_free_aux(rb); + +err: + ring_buffer_put(rb); + handle->event = NULL; + + return NULL; +} + +/* + * Commit the data written by hardware into the ring buffer by adjusting + * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the + * pmu driver's responsibility to observe ordering rules of the hardware, + * so that all the data is externally visible before this is called. + */ +void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, + bool truncated) +{ + struct ring_buffer *rb = handle->rb; + unsigned long aux_head; + u64 flags = 0; + + if (truncated) + flags |= PERF_AUX_FLAG_TRUNCATED; + + /* in overwrite mode, driver provides aux_head via handle */ + if (rb->aux_overwrite) { + flags |= PERF_AUX_FLAG_OVERWRITE; + + aux_head = handle->head; + local_set(&rb->aux_head, aux_head); + } else { + aux_head = local_read(&rb->aux_head); + local_add(size, &rb->aux_head); + } + + if (size || flags) { + /* + * Only send RECORD_AUX if we have something useful to communicate + */ + + perf_event_aux_event(handle->event, aux_head, size, flags); + } + + aux_head = rb->user_page->aux_head = local_read(&rb->aux_head); + + if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) { + perf_output_wakeup(handle); + local_add(rb->aux_watermark, &rb->aux_wakeup); + } + handle->event = NULL; + + local_set(&rb->aux_nest, 0); + rb_free_aux(rb); + ring_buffer_put(rb); +} + +/* + * Skip over a given number of bytes in the AUX buffer, due to, for example, + * hardware's alignment constraints. + */ +int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) +{ + struct ring_buffer *rb = handle->rb; + unsigned long aux_head; + + if (size > handle->size) + return -ENOSPC; + + local_add(size, &rb->aux_head); + + aux_head = rb->user_page->aux_head = local_read(&rb->aux_head); + if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) { + perf_output_wakeup(handle); + local_add(rb->aux_watermark, &rb->aux_wakeup); + handle->wakeup = local_read(&rb->aux_wakeup) + + rb->aux_watermark; + } + + handle->head = aux_head; + handle->size -= size; + + return 0; +} + +void *perf_get_aux(struct perf_output_handle *handle) +{ + /* this is only valid between perf_aux_output_begin and *_end */ + if (!handle->event) + return NULL; + + return handle->rb->aux_priv; +} + +#define PERF_AUX_GFP (GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY) + +static struct page *rb_alloc_aux_page(int node, int order) +{ + struct page *page; + + if (order > MAX_ORDER) + order = MAX_ORDER; + + do { + page = alloc_pages_node(node, PERF_AUX_GFP, order); + } while (!page && order--); + + if (page && order) { + /* + * Communicate the allocation size to the driver + */ + split_page(page, order); + SetPagePrivate(page); + set_page_private(page, order); + } + + return page; +} + +static void rb_free_aux_page(struct ring_buffer *rb, int idx) +{ + struct page *page = virt_to_page(rb->aux_pages[idx]); + + ClearPagePrivate(page); + page->mapping = NULL; + __free_page(page); +} + +int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, + pgoff_t pgoff, int nr_pages, long watermark, int flags) +{ + bool overwrite = !(flags & RING_BUFFER_WRITABLE); + int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu); + int ret = -ENOMEM, max_order = 0; + + if (!has_aux(event)) + return -ENOTSUPP; + + if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) { + /* + * We need to start with the max_order that fits in nr_pages, + * not the other way around, hence ilog2() and not get_order. + */ + max_order = ilog2(nr_pages); + + /* + * PMU requests more than one contiguous chunks of memory + * for SW double buffering + */ + if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) && + !overwrite) { + if (!max_order) + return -EINVAL; + + max_order--; + } + } + + rb->aux_pages = kzalloc_node(nr_pages * sizeof(void *), GFP_KERNEL, node); + if (!rb->aux_pages) + return -ENOMEM; + + rb->free_aux = event->pmu->free_aux; + for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;) { + struct page *page; + int last, order; + + order = min(max_order, ilog2(nr_pages - rb->aux_nr_pages)); + page = rb_alloc_aux_page(node, order); + if (!page) + goto out; + + for (last = rb->aux_nr_pages + (1 << page_private(page)); + last > rb->aux_nr_pages; rb->aux_nr_pages++) + rb->aux_pages[rb->aux_nr_pages] = page_address(page++); + } + + rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages, + overwrite); + if (!rb->aux_priv) + goto out; + + ret = 0; + + /* + * aux_pages (and pmu driver's private data, aux_priv) will be + * referenced in both producer's and consumer's contexts, thus + * we keep a refcount here to make sure either of the two can + * reference them safely. + */ + atomic_set(&rb->aux_refcount, 1); + + rb->aux_overwrite = overwrite; + rb->aux_watermark = watermark; + + if (!rb->aux_watermark && !rb->aux_overwrite) + rb->aux_watermark = nr_pages << (PAGE_SHIFT - 1); + +out: + if (!ret) + rb->aux_pgoff = pgoff; + else + rb_free_aux(rb); + + return ret; +} + +static void __rb_free_aux(struct ring_buffer *rb) +{ + int pg; + + if (rb->aux_priv) { + rb->free_aux(rb->aux_priv); + rb->free_aux = NULL; + rb->aux_priv = NULL; + } + + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); + + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; +} + +void rb_free_aux(struct ring_buffer *rb) +{ + if (atomic_dec_and_test(&rb->aux_refcount)) + __rb_free_aux(rb); +} + #ifndef CONFIG_PERF_USE_VMALLOC /* * Back perf_mmap() with regular GFP_KERNEL-0 pages. */ -struct page * -perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +static struct page * +__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) { if (pgoff > rb->nr_pages) return NULL; @@ -340,8 +643,8 @@ static int data_page_nr(struct ring_buffer *rb) return rb->nr_pages << page_order(rb); } -struct page * -perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +static struct page * +__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) { /* The '>' counts in the user page. */ if (pgoff > data_page_nr(rb)) @@ -416,3 +719,19 @@ fail: } #endif + +struct page * +perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +{ + if (rb->aux_nr_pages) { + /* above AUX space */ + if (pgoff > rb->aux_pgoff + rb->aux_nr_pages) + return NULL; + + /* AUX space */ + if (pgoff >= rb->aux_pgoff) + return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]); + } + + return __perf_mmap_to_page(rb, pgoff); +} diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index fedbdd7..3b9a48a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -432,6 +432,14 @@ config UPROBE_EVENT This option is required if you plan to use perf-probe subcommand of perf tools on user space applications. +config BPF_EVENTS + depends on BPF_SYSCALL + depends on KPROBE_EVENT + bool + default y + help + This allows the user to attach BPF programs to kprobe events. + config PROBE_EVENTS def_bool n diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 98f2658..9b1044e 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM),y) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c new file mode 100644 index 0000000..2d56ce5 --- /dev/null +++ b/kernel/trace/bpf_trace.c @@ -0,0 +1,222 @@ +/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/uaccess.h> +#include <linux/ctype.h> +#include "trace.h" + +static DEFINE_PER_CPU(int, bpf_prog_active); + +/** + * trace_call_bpf - invoke BPF program + * @prog: BPF program + * @ctx: opaque context pointer + * + * kprobe handlers execute BPF programs via this helper. + * Can be used from static tracepoints in the future. + * + * Return: BPF programs always return an integer which is interpreted by + * kprobe handler as: + * 0 - return from kprobe (event is filtered out) + * 1 - store kprobe event into ring buffer + * Other values are reserved and currently alias to 1 + */ +unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) +{ + unsigned int ret; + + if (in_nmi()) /* not supported yet */ + return 1; + + preempt_disable(); + + if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { + /* + * since some bpf program is already running on this cpu, + * don't call into another bpf program (same or different) + * and don't send kprobe event into ring-buffer, + * so return zero here + */ + ret = 0; + goto out; + } + + rcu_read_lock(); + ret = BPF_PROG_RUN(prog, ctx); + rcu_read_unlock(); + + out: + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + + return ret; +} +EXPORT_SYMBOL_GPL(trace_call_bpf); + +static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + void *dst = (void *) (long) r1; + int size = (int) r2; + void *unsafe_ptr = (void *) (long) r3; + + return probe_kernel_read(dst, unsafe_ptr, size); +} + +static const struct bpf_func_proto bpf_probe_read_proto = { + .func = bpf_probe_read, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE, + .arg3_type = ARG_ANYTHING, +}; + +static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + /* NMI safe access to clock monotonic */ + return ktime_get_mono_fast_ns(); +} + +static const struct bpf_func_proto bpf_ktime_get_ns_proto = { + .func = bpf_ktime_get_ns, + .gpl_only = true, + .ret_type = RET_INTEGER, +}; + +/* + * limited trace_printk() + * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed + */ +static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) +{ + char *fmt = (char *) (long) r1; + int mod[3] = {}; + int fmt_cnt = 0; + int i; + + /* + * bpf_check()->check_func_arg()->check_stack_boundary() + * guarantees that fmt points to bpf program stack, + * fmt_size bytes of it were initialized and fmt_size > 0 + */ + if (fmt[--fmt_size] != 0) + return -EINVAL; + + /* check format string for allowed specifiers */ + for (i = 0; i < fmt_size; i++) { + if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) + return -EINVAL; + + if (fmt[i] != '%') + continue; + + if (fmt_cnt >= 3) + return -EINVAL; + + /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ + i++; + if (fmt[i] == 'l') { + mod[fmt_cnt]++; + i++; + } else if (fmt[i] == 'p') { + mod[fmt_cnt]++; + i++; + if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + return -EINVAL; + fmt_cnt++; + continue; + } + + if (fmt[i] == 'l') { + mod[fmt_cnt]++; + i++; + } + + if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') + return -EINVAL; + fmt_cnt++; + } + + return __trace_printk(1/* fake ip will not be printed */, fmt, + mod[0] == 2 ? r3 : mod[0] == 1 ? (long) r3 : (u32) r3, + mod[1] == 2 ? r4 : mod[1] == 1 ? (long) r4 : (u32) r4, + mod[2] == 2 ? r5 : mod[2] == 1 ? (long) r5 : (u32) r5); +} + +static const struct bpf_func_proto bpf_trace_printk_proto = { + .func = bpf_trace_printk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_probe_read: + return &bpf_probe_read_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; + + case BPF_FUNC_trace_printk: + /* + * this program might be calling bpf_trace_printk, + * so allocate per-cpu printk buffers + */ + trace_printk_init_buffers(); + + return &bpf_trace_printk_proto; + default: + return NULL; + } +} + +/* bpf+kprobe programs can access fields of 'struct pt_regs' */ +static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type) +{ + /* check bounds */ + if (off < 0 || off >= sizeof(struct pt_regs)) + return false; + + /* only read is allowed */ + if (type != BPF_READ) + return false; + + /* disallow misaligned access */ + if (off % size != 0) + return false; + + return true; +} + +static struct bpf_verifier_ops kprobe_prog_ops = { + .get_func_proto = kprobe_prog_func_proto, + .is_valid_access = kprobe_prog_is_valid_access, +}; + +static struct bpf_prog_type_list kprobe_tl = { + .ops = &kprobe_prog_ops, + .type = BPF_PROG_TYPE_KPROBE, +}; + +static int __init register_kprobe_prog_ops(void) +{ + bpf_register_prog_type(&kprobe_tl); + return 0; +} +late_initcall(register_kprobe_prog_ops); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 9ba3f43..d0ce590 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1135,11 +1135,15 @@ static void kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct ftrace_event_call *call = &tk->tp.call; + struct bpf_prog *prog = call->prog; struct kprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; int rctx; + if (prog && !trace_call_bpf(prog, regs)) + return; + head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; @@ -1166,11 +1170,15 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs) { struct ftrace_event_call *call = &tk->tp.call; + struct bpf_prog *prog = call->prog; struct kretprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; int rctx; + if (prog && !trace_call_bpf(prog, regs)) + return; + head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; @@ -1287,7 +1295,7 @@ static int register_kprobe_event(struct trace_kprobe *tk) kfree(call->print_fmt); return -ENODEV; } - call->flags = 0; + call->flags = TRACE_EVENT_FL_KPROBE; call->class->reg = kprobe_register; call->data = tk; ret = trace_add_event_call(call); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 7486546..d60fe62 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1006,7 +1006,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) return true; list_for_each_entry(event, &filter->perf_events, hw.tp_list) { - if (event->hw.tp_target->mm == mm) + if (event->hw.target->mm == mm) return true; } @@ -1016,7 +1016,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) static inline bool uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm); + return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); } static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) @@ -1024,10 +1024,10 @@ static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) bool done; write_lock(&tu->filter.rwlock); - if (event->hw.tp_target) { + if (event->hw.target) { list_del(&event->hw.tp_list); done = tu->filter.nr_systemwide || - (event->hw.tp_target->flags & PF_EXITING) || + (event->hw.target->flags & PF_EXITING) || uprobe_filter_event(tu, event); } else { tu->filter.nr_systemwide--; @@ -1047,7 +1047,7 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) int err; write_lock(&tu->filter.rwlock); - if (event->hw.tp_target) { + if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid * uprobe_apply(). current->mm must be probed and we can rely diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 3174bf8..9a056f5 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -567,9 +567,37 @@ static void watchdog_nmi_disable(unsigned int cpu) cpu0_err = 0; } } + +void watchdog_nmi_enable_all(void) +{ + int cpu; + + if (!watchdog_user_enabled) + return; + + get_online_cpus(); + for_each_online_cpu(cpu) + watchdog_nmi_enable(cpu); + put_online_cpus(); +} + +void watchdog_nmi_disable_all(void) +{ + int cpu; + + if (!watchdog_running) + return; + + get_online_cpus(); + for_each_online_cpu(cpu) + watchdog_nmi_disable(cpu); + put_online_cpus(); +} #else static int watchdog_nmi_enable(unsigned int cpu) { return 0; } static void watchdog_nmi_disable(unsigned int cpu) { return; } +void watchdog_nmi_enable_all(void) {} +void watchdog_nmi_disable_all(void) {} #endif /* CONFIG_HARDLOCKUP_DETECTOR */ static struct smp_hotplug_thread watchdog_threads = { |