diff options
Diffstat (limited to 'kernel/events')
| -rw-r--r-- | kernel/events/core.c | 689 | ||||
| -rw-r--r-- | kernel/events/ring_buffer.c | 29 | ||||
| -rw-r--r-- | kernel/events/uprobes.c | 372 |
3 files changed, 665 insertions, 425 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c index 0bb21659e252..f34c99f8ce8f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1270,6 +1270,10 @@ static void put_ctx(struct perf_event_context *ctx) if (ctx->task && ctx->task != TASK_TOMBSTONE) put_task_struct(ctx->task); call_rcu(&ctx->rcu_head, free_ctx); + } else { + smp_mb__after_atomic(); /* pairs with wait_var_event() */ + if (ctx->task == TASK_TOMBSTONE) + wake_up_var(&ctx->refcount); } } @@ -2167,7 +2171,7 @@ static void perf_put_aux_event(struct perf_event *event) * If the event is an aux_event, tear down all links to * it from other events. */ - for_each_sibling_event(iter, event->group_leader) { + for_each_sibling_event(iter, event) { if (iter->aux_event != event) continue; @@ -2325,7 +2329,11 @@ static void perf_child_detach(struct perf_event *event) if (WARN_ON_ONCE(!parent_event)) return; + /* + * Can't check this from an IPI, the holder is likey another CPU. + * lockdep_assert_held(&parent_event->child_mutex); + */ sync_child_event(event); list_del_init(&event->child_list); @@ -2343,6 +2351,11 @@ event_filter_match(struct perf_event *event) perf_cgroup_match(event); } +static inline bool is_event_in_freq_mode(struct perf_event *event) +{ + return event->attr.freq && event->attr.sample_freq; +} + static void event_sched_out(struct perf_event *event, struct perf_event_context *ctx) { @@ -2380,7 +2393,7 @@ event_sched_out(struct perf_event *event, struct perf_event_context *ctx) if (!is_software_event(event)) cpc->active_oncpu--; - if (event->attr.freq && event->attr.sample_freq) { + if (is_event_in_freq_mode(event)) { ctx->nr_freq--; epc->nr_freq--; } @@ -2450,7 +2463,9 @@ ctx_time_update_event(struct perf_event_context *ctx, struct perf_event *event) #define DETACH_GROUP 0x01UL #define DETACH_CHILD 0x02UL -#define DETACH_DEAD 0x04UL +#define DETACH_EXIT 0x04UL +#define DETACH_REVOKE 0x08UL +#define DETACH_DEAD 0x10UL /* * Cross CPU call to remove a performance event @@ -2465,6 +2480,7 @@ __perf_remove_from_context(struct perf_event *event, void *info) { struct perf_event_pmu_context *pmu_ctx = event->pmu_ctx; + enum perf_event_state state = PERF_EVENT_STATE_OFF; unsigned long flags = (unsigned long)info; ctx_time_update(cpuctx, ctx); @@ -2473,16 +2489,22 @@ __perf_remove_from_context(struct perf_event *event, * Ensure event_sched_out() switches to OFF, at the very least * this avoids raising perf_pending_task() at this time. */ - if (flags & DETACH_DEAD) + if (flags & DETACH_EXIT) + state = PERF_EVENT_STATE_EXIT; + if (flags & DETACH_REVOKE) + state = PERF_EVENT_STATE_REVOKED; + if (flags & DETACH_DEAD) { event->pending_disable = 1; + state = PERF_EVENT_STATE_DEAD; + } event_sched_out(event, ctx); + perf_event_set_state(event, min(event->state, state)); + if (flags & DETACH_GROUP) perf_group_detach(event); if (flags & DETACH_CHILD) perf_child_detach(event); list_del_event(event, ctx); - if (flags & DETACH_DEAD) - event->state = PERF_EVENT_STATE_DEAD; if (!pmu_ctx->nr_events) { pmu_ctx->rotate_necessary = 0; @@ -2623,6 +2645,41 @@ void perf_event_disable_inatomic(struct perf_event *event) static void perf_log_throttle(struct perf_event *event, int enable); static void perf_log_itrace_start(struct perf_event *event); +static void perf_event_unthrottle(struct perf_event *event, bool start) +{ + event->hw.interrupts = 0; + if (start) + event->pmu->start(event, 0); + if (event == event->group_leader) + perf_log_throttle(event, 1); +} + +static void perf_event_throttle(struct perf_event *event) +{ + event->pmu->stop(event, 0); + event->hw.interrupts = MAX_INTERRUPTS; + if (event == event->group_leader) + perf_log_throttle(event, 0); +} + +static void perf_event_unthrottle_group(struct perf_event *event, bool skip_start_event) +{ + struct perf_event *sibling, *leader = event->group_leader; + + perf_event_unthrottle(leader, skip_start_event ? leader != event : true); + for_each_sibling_event(sibling, leader) + perf_event_unthrottle(sibling, skip_start_event ? sibling != event : true); +} + +static void perf_event_throttle_group(struct perf_event *event) +{ + struct perf_event *sibling, *leader = event->group_leader; + + perf_event_throttle(leader); + for_each_sibling_event(sibling, leader) + perf_event_throttle(sibling); +} + static int event_sched_in(struct perf_event *event, struct perf_event_context *ctx) { @@ -2651,10 +2708,8 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx) * ticks already, also for a heavily scheduling task there is little * guarantee it'll get a tick in a timely manner. */ - if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) { - perf_log_throttle(event, 1); - event->hw.interrupts = 0; - } + if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) + perf_event_unthrottle(event, false); perf_pmu_disable(event->pmu); @@ -2669,7 +2724,7 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx) if (!is_software_event(event)) cpc->active_oncpu++; - if (event->attr.freq && event->attr.sample_freq) { + if (is_event_in_freq_mode(event)) { ctx->nr_freq++; epc->nr_freq++; } @@ -3938,7 +3993,7 @@ static int merge_sched_in(struct perf_event *event, void *data) perf_event_set_state(event, PERF_EVENT_STATE_ERROR); if (*perf_event_fasync(event)) - event->pending_kill = POLL_HUP; + event->pending_kill = POLL_ERR; perf_event_wakeup(event); } else { @@ -4232,14 +4287,10 @@ static void perf_adjust_freq_unthr_events(struct list_head *event_list) hwc = &event->hw; - if (hwc->interrupts == MAX_INTERRUPTS) { - hwc->interrupts = 0; - perf_log_throttle(event, 1); - if (!event->attr.freq || !event->attr.sample_freq) - event->pmu->start(event, 0); - } + if (hwc->interrupts == MAX_INTERRUPTS) + perf_event_unthrottle_group(event, is_event_in_freq_mode(event)); - if (!event->attr.freq || !event->attr.sample_freq) + if (!is_event_in_freq_mode(event)) continue; /* @@ -4511,7 +4562,8 @@ out: static void perf_remove_from_owner(struct perf_event *event); static void perf_event_exit_event(struct perf_event *event, - struct perf_event_context *ctx); + struct perf_event_context *ctx, + bool revoke); /* * Removes all events from the current task that have been marked @@ -4538,7 +4590,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx) modified = true; - perf_event_exit_event(event, ctx); + perf_event_exit_event(event, ctx, false); } raw_spin_lock_irqsave(&ctx->lock, flags); @@ -5120,6 +5172,7 @@ static bool is_sb_event(struct perf_event *event) attr->context_switch || attr->text_poke || attr->bpf_event) return true; + return false; } @@ -5513,33 +5566,11 @@ static bool exclusive_event_installable(struct perf_event *event, static void perf_free_addr_filters(struct perf_event *event); -static void perf_pending_task_sync(struct perf_event *event) -{ - struct callback_head *head = &event->pending_task; - - if (!event->pending_work) - return; - /* - * If the task is queued to the current task's queue, we - * obviously can't wait for it to complete. Simply cancel it. - */ - if (task_work_cancel(current, head)) { - event->pending_work = 0; - local_dec(&event->ctx->nr_no_switch_fast); - return; - } - - /* - * All accesses related to the event are within the same RCU section in - * perf_pending_task(). The RCU grace period before the event is freed - * will make sure all those accesses are complete by then. - */ - rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE); -} - /* vs perf_event_alloc() error */ static void __free_event(struct perf_event *event) { + struct pmu *pmu = event->pmu; + if (event->attach_state & PERF_ATTACH_CALLCHAIN) put_callchain_buffers(); @@ -5569,6 +5600,7 @@ static void __free_event(struct perf_event *event) * put_pmu_ctx() needs an event->ctx reference, because of * epc->ctx. */ + WARN_ON_ONCE(!pmu); WARN_ON_ONCE(!event->ctx); WARN_ON_ONCE(event->pmu_ctx->ctx != event->ctx); put_pmu_ctx(event->pmu_ctx); @@ -5581,8 +5613,13 @@ static void __free_event(struct perf_event *event) if (event->ctx) put_ctx(event->ctx); - if (event->pmu) - module_put(event->pmu->module); + if (pmu) { + module_put(pmu->module); + scoped_guard (spinlock, &pmu->events_lock) { + list_del(&event->pmu_list); + wake_up_var(pmu); + } + } call_rcu(&event->rcu_head, free_event_rcu); } @@ -5594,7 +5631,6 @@ static void _free_event(struct perf_event *event) { irq_work_sync(&event->pending_irq); irq_work_sync(&event->pending_disable_irq); - perf_pending_task_sync(event); unaccount_event(event); @@ -5620,13 +5656,13 @@ static void _free_event(struct perf_event *event) /* * Used to free events which have a known refcount of 1, such as in error paths - * where the event isn't exposed yet and inherited events. + * of inherited events. */ static void free_event(struct perf_event *event) { if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1, - "unexpected event refcount: %ld; ptr=%p\n", - atomic_long_read(&event->refcount), event)) { + "unexpected event refcount: %ld; ptr=%p\n", + atomic_long_read(&event->refcount), event)) { /* leak to avoid use-after-free */ return; } @@ -5687,10 +5723,17 @@ static void perf_remove_from_owner(struct perf_event *event) static void put_event(struct perf_event *event) { + struct perf_event *parent; + if (!atomic_long_dec_and_test(&event->refcount)) return; + parent = event->parent; _free_event(event); + + /* Matches the refcount bump in inherit_event() */ + if (parent) + put_event(parent); } /* @@ -5702,7 +5745,6 @@ int perf_event_release_kernel(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct perf_event *child, *tmp; - LIST_HEAD(free_list); /* * If we got here through err_alloc: free_event(event); we will not @@ -5731,15 +5773,17 @@ int perf_event_release_kernel(struct perf_event *event) * Thus this guarantees that we will in fact observe and kill _ALL_ * child events. */ - perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD); + if (event->state > PERF_EVENT_STATE_REVOKED) { + perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD); + } else { + event->state = PERF_EVENT_STATE_DEAD; + } perf_event_ctx_unlock(event, ctx); again: mutex_lock(&event->child_mutex); list_for_each_entry(child, &event->child_list, child_list) { - void *var = NULL; - /* * Cannot change, child events are not migrated, see the * comment with perf_event_ctx_lock_nested(). @@ -5772,50 +5816,30 @@ again: tmp = list_first_entry_or_null(&event->child_list, struct perf_event, child_list); if (tmp == child) { - perf_remove_from_context(child, DETACH_GROUP); - list_move(&child->child_list, &free_list); - /* - * This matches the refcount bump in inherit_event(); - * this can't be the last reference. - */ - put_event(event); + perf_remove_from_context(child, DETACH_GROUP | DETACH_CHILD); } else { - var = &ctx->refcount; + child = NULL; } mutex_unlock(&event->child_mutex); mutex_unlock(&ctx->mutex); - put_ctx(ctx); - if (var) { - /* - * If perf_event_free_task() has deleted all events from the - * ctx while the child_mutex got released above, make sure to - * notify about the preceding put_ctx(). - */ - smp_mb(); /* pairs with wait_var_event() */ - wake_up_var(var); + if (child) { + /* Last reference unless ->pending_task work is pending */ + put_event(child); } + put_ctx(ctx); + goto again; } mutex_unlock(&event->child_mutex); - list_for_each_entry_safe(child, tmp, &free_list, child_list) { - void *var = &child->ctx->refcount; - - list_del(&child->child_list); - free_event(child); - - /* - * Wake any perf_event_free_task() waiting for this event to be - * freed. - */ - smp_mb(); /* pairs with wait_var_event() */ - wake_up_var(var); - } - no_ctx: - put_event(event); /* Must be the 'last' reference */ + /* + * Last reference unless ->pending_task work is pending on this event + * or any of its children. + */ + put_event(event); return 0; } EXPORT_SYMBOL_GPL(perf_event_release_kernel); @@ -6081,14 +6105,20 @@ static __poll_t perf_poll(struct file *file, poll_table *wait) struct perf_buffer *rb; __poll_t events = EPOLLHUP; + if (event->state <= PERF_EVENT_STATE_REVOKED) + return EPOLLERR; + poll_wait(file, &event->waitq, wait); + if (event->state <= PERF_EVENT_STATE_REVOKED) + return EPOLLERR; + if (is_event_hup(event)) return events; if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR && event->attr.pinned)) - return events; + return EPOLLERR; /* * Pin the event->rb by taking event->mmap_mutex; otherwise @@ -6180,14 +6210,6 @@ static void __perf_event_period(struct perf_event *event, active = (event->state == PERF_EVENT_STATE_ACTIVE); if (active) { perf_pmu_disable(event->pmu); - /* - * We could be throttled; unthrottle now to avoid the tick - * trying to unthrottle while we already re-started the event. - */ - if (event->hw.interrupts == MAX_INTERRUPTS) { - event->hw.interrupts = 0; - perf_log_throttle(event, 1); - } event->pmu->stop(event, PERF_EF_UPDATE); } @@ -6195,6 +6217,14 @@ static void __perf_event_period(struct perf_event *event, if (active) { event->pmu->start(event, PERF_EF_RELOAD); + /* + * Once the period is force-reset, the event starts immediately. + * But the event/group could be throttled. Unthrottle the + * event/group now to avoid the next tick trying to unthrottle + * while we already re-started the event/group. + */ + if (event->hw.interrupts == MAX_INTERRUPTS) + perf_event_unthrottle_group(event, true); perf_pmu_enable(event->pmu); } } @@ -6252,12 +6282,18 @@ static int perf_event_set_output(struct perf_event *event, static int perf_event_set_filter(struct perf_event *event, void __user *arg); static int perf_copy_attr(struct perf_event_attr __user *uattr, struct perf_event_attr *attr); +static int __perf_event_set_bpf_prog(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie); static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg) { void (*func)(struct perf_event *); u32 flags = arg; + if (event->state <= PERF_EVENT_STATE_REVOKED) + return -ENODEV; + switch (cmd) { case PERF_EVENT_IOC_ENABLE: func = _perf_event_enable; @@ -6314,7 +6350,7 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon if (IS_ERR(prog)) return PTR_ERR(prog); - err = perf_event_set_bpf_prog(event, prog, 0); + err = __perf_event_set_bpf_prog(event, prog, 0); if (err) { bpf_prog_put(prog); return err; @@ -6633,9 +6669,22 @@ void ring_buffer_put(struct perf_buffer *rb) call_rcu(&rb->rcu_head, rb_free_rcu); } +typedef void (*mapped_f)(struct perf_event *event, struct mm_struct *mm); + +#define get_mapped(event, func) \ +({ struct pmu *pmu; \ + mapped_f f = NULL; \ + guard(rcu)(); \ + pmu = READ_ONCE(event->pmu); \ + if (pmu) \ + f = pmu->func; \ + f; \ +}) + static void perf_mmap_open(struct vm_area_struct *vma) { struct perf_event *event = vma->vm_file->private_data; + mapped_f mapped = get_mapped(event, event_mapped); atomic_inc(&event->mmap_count); atomic_inc(&event->rb->mmap_count); @@ -6643,8 +6692,8 @@ static void perf_mmap_open(struct vm_area_struct *vma) if (vma->vm_pgoff) atomic_inc(&event->rb->aux_mmap_count); - if (event->pmu->event_mapped) - event->pmu->event_mapped(event, vma->vm_mm); + if (mapped) + mapped(event, vma->vm_mm); } static void perf_pmu_output_stop(struct perf_event *event); @@ -6660,14 +6709,16 @@ static void perf_pmu_output_stop(struct perf_event *event); static void perf_mmap_close(struct vm_area_struct *vma) { struct perf_event *event = vma->vm_file->private_data; + mapped_f unmapped = get_mapped(event, event_unmapped); struct perf_buffer *rb = ring_buffer_get(event); struct user_struct *mmap_user = rb->mmap_user; int mmap_locked = rb->mmap_locked; unsigned long size = perf_data_size(rb); bool detach_rest = false; - if (event->pmu->event_unmapped) - event->pmu->event_unmapped(event, vma->vm_mm); + /* FIXIES vs perf_pmu_unregister() */ + if (unmapped) + unmapped(event, vma->vm_mm); /* * The AUX buffer is strictly a sub-buffer, serialize using aux_mutex @@ -6860,6 +6911,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) unsigned long nr_pages; long user_extra = 0, extra = 0; int ret, flags = 0; + mapped_f mapped; /* * Don't allow mmap() of inherited per-task counters. This would @@ -6890,6 +6942,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) mutex_lock(&event->mmap_mutex); ret = -EINVAL; + /* + * This relies on __pmu_detach_event() taking mmap_mutex after marking + * the event REVOKED. Either we observe the state, or __pmu_detach_event() + * will detach the rb created here. + */ + if (event->state <= PERF_EVENT_STATE_REVOKED) { + ret = -ENODEV; + goto unlock; + } + if (vma->vm_pgoff == 0) { nr_pages -= 1; @@ -7068,8 +7130,9 @@ aux_unlock: if (!ret) ret = map_range(rb, vma); - if (!ret && event->pmu->event_mapped) - event->pmu->event_mapped(event, vma->vm_mm); + mapped = get_mapped(event, event_mapped); + if (mapped) + mapped(event, vma->vm_mm); return ret; } @@ -7080,6 +7143,9 @@ static int perf_fasync(int fd, struct file *filp, int on) struct perf_event *event = filp->private_data; int retval; + if (event->state <= PERF_EVENT_STATE_REVOKED) + return -ENODEV; + inode_lock(inode); retval = fasync_helper(fd, filp, on, &event->fasync); inode_unlock(inode); @@ -7231,12 +7297,6 @@ static void perf_pending_task(struct callback_head *head) int rctx; /* - * All accesses to the event must belong to the same implicit RCU read-side - * critical section as the ->pending_work reset. See comment in - * perf_pending_task_sync(). - */ - rcu_read_lock(); - /* * If we 'fail' here, that's OK, it means recursion is already disabled * and we won't recurse 'further'. */ @@ -7246,9 +7306,8 @@ static void perf_pending_task(struct callback_head *head) event->pending_work = 0; perf_sigtrap(event); local_dec(&event->ctx->nr_no_switch_fast); - rcuwait_wake_up(&event->pending_work_wait); } - rcu_read_unlock(); + put_event(event); if (rctx >= 0) perf_swevent_put_recursion_context(rctx); @@ -9966,7 +10025,7 @@ void perf_event_text_poke(const void *addr, const void *old_bytes, void perf_event_itrace_started(struct perf_event *event) { - event->attach_state |= PERF_ATTACH_ITRACE; + WRITE_ONCE(event->attach_state, event->attach_state | PERF_ATTACH_ITRACE); } static void perf_log_itrace_start(struct perf_event *event) @@ -10049,14 +10108,13 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle) hwc->interrupts = 1; } else { hwc->interrupts++; - if (unlikely(throttle && - hwc->interrupts > max_samples_per_tick)) { - __this_cpu_inc(perf_throttled_count); - tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); - hwc->interrupts = MAX_INTERRUPTS; - perf_log_throttle(event, 0); - ret = 1; - } + } + + if (unlikely(throttle && hwc->interrupts >= max_samples_per_tick)) { + __this_cpu_inc(perf_throttled_count); + tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); + perf_event_throttle_group(event); + ret = 1; } if (event->attr.freq) { @@ -10243,6 +10301,7 @@ static int __perf_event_overflow(struct perf_event *event, !task_work_add(current, &event->pending_task, notify_mode)) { event->pending_work = pending_id; local_inc(&event->ctx->nr_no_switch_fast); + WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount)); event->pending_addr = 0; if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR)) @@ -11088,11 +11147,15 @@ static inline bool perf_event_is_tracing(struct perf_event *event) return false; } -int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, - u64 bpf_cookie) +static int __perf_event_set_bpf_prog(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie) { bool is_kprobe, is_uprobe, is_tracepoint, is_syscall_tp; + if (event->state <= PERF_EVENT_STATE_REVOKED) + return -ENODEV; + if (!perf_event_is_tracing(event)) return perf_event_set_bpf_handler(event, prog, bpf_cookie); @@ -11127,6 +11190,20 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, return perf_event_attach_bpf_prog(event, prog, bpf_cookie); } +int perf_event_set_bpf_prog(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie) +{ + struct perf_event_context *ctx; + int ret; + + ctx = perf_event_ctx_lock(event); + ret = __perf_event_set_bpf_prog(event, prog, bpf_cookie); + perf_event_ctx_unlock(event, ctx); + + return ret; +} + void perf_event_free_bpf_prog(struct perf_event *event) { if (!event->prog) @@ -11149,7 +11226,15 @@ static void perf_event_free_filter(struct perf_event *event) { } -int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, +static int __perf_event_set_bpf_prog(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie) +{ + return -ENOENT; +} + +int perf_event_set_bpf_prog(struct perf_event *event, + struct bpf_prog *prog, u64 bpf_cookie) { return -ENOENT; @@ -12254,6 +12339,9 @@ int perf_pmu_register(struct pmu *_pmu, const char *name, int type) if (!pmu->event_idx) pmu->event_idx = perf_event_idx_default; + INIT_LIST_HEAD(&pmu->events); + spin_lock_init(&pmu->events_lock); + /* * Now that the PMU is complete, make it visible to perf_try_init_event(). */ @@ -12267,21 +12355,143 @@ int perf_pmu_register(struct pmu *_pmu, const char *name, int type) } EXPORT_SYMBOL_GPL(perf_pmu_register); -void perf_pmu_unregister(struct pmu *pmu) +static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event, + struct perf_event_context *ctx) +{ + /* + * De-schedule the event and mark it REVOKED. + */ + perf_event_exit_event(event, ctx, true); + + /* + * All _free_event() bits that rely on event->pmu: + * + * Notably, perf_mmap() relies on the ordering here. + */ + scoped_guard (mutex, &event->mmap_mutex) { + WARN_ON_ONCE(pmu->event_unmapped); + /* + * Mostly an empty lock sequence, such that perf_mmap(), which + * relies on mmap_mutex, is sure to observe the state change. + */ + } + + perf_event_free_bpf_prog(event); + perf_free_addr_filters(event); + + if (event->destroy) { + event->destroy(event); + event->destroy = NULL; + } + + if (event->pmu_ctx) { + put_pmu_ctx(event->pmu_ctx); + event->pmu_ctx = NULL; + } + + exclusive_event_destroy(event); + module_put(pmu->module); + + event->pmu = NULL; /* force fault instead of UAF */ +} + +static void pmu_detach_event(struct pmu *pmu, struct perf_event *event) +{ + struct perf_event_context *ctx; + + ctx = perf_event_ctx_lock(event); + __pmu_detach_event(pmu, event, ctx); + perf_event_ctx_unlock(event, ctx); + + scoped_guard (spinlock, &pmu->events_lock) + list_del(&event->pmu_list); +} + +static struct perf_event *pmu_get_event(struct pmu *pmu) +{ + struct perf_event *event; + + guard(spinlock)(&pmu->events_lock); + list_for_each_entry(event, &pmu->events, pmu_list) { + if (atomic_long_inc_not_zero(&event->refcount)) + return event; + } + + return NULL; +} + +static bool pmu_empty(struct pmu *pmu) +{ + guard(spinlock)(&pmu->events_lock); + return list_empty(&pmu->events); +} + +static void pmu_detach_events(struct pmu *pmu) +{ + struct perf_event *event; + + for (;;) { + event = pmu_get_event(pmu); + if (!event) + break; + + pmu_detach_event(pmu, event); + put_event(event); + } + + /* + * wait for pending _free_event()s + */ + wait_var_event(pmu, pmu_empty(pmu)); +} + +int perf_pmu_unregister(struct pmu *pmu) { scoped_guard (mutex, &pmus_lock) { + if (!idr_cmpxchg(&pmu_idr, pmu->type, pmu, NULL)) + return -EINVAL; + list_del_rcu(&pmu->entry); - idr_remove(&pmu_idr, pmu->type); } /* * We dereference the pmu list under both SRCU and regular RCU, so * synchronize against both of those. + * + * Notably, the entirety of event creation, from perf_init_event() + * (which will now fail, because of the above) until + * perf_install_in_context() should be under SRCU such that + * this synchronizes against event creation. This avoids trying to + * detach events that are not fully formed. */ synchronize_srcu(&pmus_srcu); synchronize_rcu(); + if (pmu->event_unmapped && !pmu_empty(pmu)) { + /* + * Can't force remove events when pmu::event_unmapped() + * is used in perf_mmap_close(). + */ + guard(mutex)(&pmus_lock); + idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu); + list_add_rcu(&pmu->entry, &pmus); + return -EBUSY; + } + + scoped_guard (mutex, &pmus_lock) + idr_remove(&pmu_idr, pmu->type); + + /* + * PMU is removed from the pmus list, so no new events will + * be created, now take care of the existing ones. + */ + pmu_detach_events(pmu); + + /* + * PMU is unused, make it go away. + */ perf_pmu_free(pmu); + return 0; } EXPORT_SYMBOL_GPL(perf_pmu_unregister); @@ -12375,7 +12585,7 @@ static struct pmu *perf_init_event(struct perf_event *event) struct pmu *pmu; int type, ret; - guard(srcu)(&pmus_srcu); + guard(srcu)(&pmus_srcu); /* pmu idr/list access */ /* * Save original type before calling pmu->event_init() since certain @@ -12599,13 +12809,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, INIT_LIST_HEAD(&event->active_entry); INIT_LIST_HEAD(&event->addr_filters.list); INIT_HLIST_NODE(&event->hlist_entry); + INIT_LIST_HEAD(&event->pmu_list); init_waitqueue_head(&event->waitq); init_irq_work(&event->pending_irq, perf_pending_irq); event->pending_disable_irq = IRQ_WORK_INIT_HARD(perf_pending_disable); init_task_work(&event->pending_task, perf_pending_task); - rcuwait_init(&event->pending_work_wait); mutex_init(&event->mmap_mutex); raw_spin_lock_init(&event->addr_filters.lock); @@ -12671,7 +12881,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, hwc = &event->hw; hwc->sample_period = attr->sample_period; - if (attr->freq && attr->sample_freq) + if (is_event_in_freq_mode(event)) hwc->sample_period = 1; hwc->last_period = hwc->sample_period; @@ -12778,6 +12988,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, /* symmetric to unaccount_event() in _free_event() */ account_event(event); + /* + * Event creation should be under SRCU, see perf_pmu_unregister(). + */ + lockdep_assert_held(&pmus_srcu); + scoped_guard (spinlock, &pmu->events_lock) + list_add(&event->pmu_list, &pmu->events); + return_ptr(event); } @@ -12977,6 +13194,9 @@ set: goto unlock; if (output_event) { + if (output_event->state <= PERF_EVENT_STATE_REVOKED) + goto unlock; + /* get the rb we want to redirect to */ rb = ring_buffer_get(output_event); if (!rb) @@ -13158,6 +13378,11 @@ SYSCALL_DEFINE5(perf_event_open, if (event_fd < 0) return event_fd; + /* + * Event creation should be under SRCU, see perf_pmu_unregister(). + */ + guard(srcu)(&pmus_srcu); + CLASS(fd, group)(group_fd); // group_fd == -1 => empty if (group_fd != -1) { if (!is_perf_file(group)) { @@ -13165,6 +13390,10 @@ SYSCALL_DEFINE5(perf_event_open, goto err_fd; } group_leader = fd_file(group)->private_data; + if (group_leader->state <= PERF_EVENT_STATE_REVOKED) { + err = -ENODEV; + goto err_fd; + } if (flags & PERF_FLAG_FD_OUTPUT) output_event = group_leader; if (flags & PERF_FLAG_FD_NO_GROUP) @@ -13461,7 +13690,7 @@ err_cred: if (task) up_read(&task->signal->exec_update_lock); err_alloc: - free_event(event); + put_event(event); err_task: if (task) put_task_struct(task); @@ -13498,6 +13727,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, if (attr->aux_output || attr->aux_action) return ERR_PTR(-EINVAL); + /* + * Event creation should be under SRCU, see perf_pmu_unregister(). + */ + guard(srcu)(&pmus_srcu); + event = perf_event_alloc(attr, cpu, task, NULL, NULL, overflow_handler, context, -1); if (IS_ERR(event)) { @@ -13569,7 +13803,7 @@ err_unlock: perf_unpin_context(ctx); put_ctx(ctx); err_alloc: - free_event(event); + put_event(event); err: return ERR_PTR(err); } @@ -13709,10 +13943,12 @@ static void sync_child_event(struct perf_event *child_event) } static void -perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx) +perf_event_exit_event(struct perf_event *event, + struct perf_event_context *ctx, bool revoke) { struct perf_event *parent_event = event->parent; - unsigned long detach_flags = 0; + unsigned long detach_flags = DETACH_EXIT; + unsigned int attach_state; if (parent_event) { /* @@ -13727,28 +13963,38 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx) * Do destroy all inherited groups, we don't care about those * and being thorough is better. */ - detach_flags = DETACH_GROUP | DETACH_CHILD; + detach_flags |= DETACH_GROUP | DETACH_CHILD; mutex_lock(&parent_event->child_mutex); + /* PERF_ATTACH_ITRACE might be set concurrently */ + attach_state = READ_ONCE(event->attach_state); } - perf_remove_from_context(event, detach_flags); - - raw_spin_lock_irq(&ctx->lock); - if (event->state > PERF_EVENT_STATE_EXIT) - perf_event_set_state(event, PERF_EVENT_STATE_EXIT); - raw_spin_unlock_irq(&ctx->lock); + if (revoke) + detach_flags |= DETACH_GROUP | DETACH_REVOKE; + perf_remove_from_context(event, detach_flags); /* * Child events can be freed. */ if (parent_event) { mutex_unlock(&parent_event->child_mutex); + /* - * Kick perf_poll() for is_event_hup(); + * Match the refcount initialization. Make sure it doesn't happen + * twice if pmu_detach_event() calls it on an already exited task. */ - perf_event_wakeup(parent_event); - free_event(event); - put_event(parent_event); + if (attach_state & PERF_ATTACH_CHILD) { + /* + * Kick perf_poll() for is_event_hup(); + */ + perf_event_wakeup(parent_event); + /* + * pmu_detach_event() will have an extra refcount. + * perf_pending_task() might have one too. + */ + put_event(event); + } + return; } @@ -13758,15 +14004,13 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx) perf_event_wakeup(event); } -static void perf_event_exit_task_context(struct task_struct *child) +static void perf_event_exit_task_context(struct task_struct *task, bool exit) { - struct perf_event_context *child_ctx, *clone_ctx = NULL; + struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_event *child_event, *next; - WARN_ON_ONCE(child != current); - - child_ctx = perf_pin_task_context(child); - if (!child_ctx) + ctx = perf_pin_task_context(task); + if (!ctx) return; /* @@ -13779,27 +14023,28 @@ static void perf_event_exit_task_context(struct task_struct *child) * without ctx::mutex (it cannot because of the move_group double mutex * lock thing). See the comments in perf_install_in_context(). */ - mutex_lock(&child_ctx->mutex); + mutex_lock(&ctx->mutex); /* * In a single ctx::lock section, de-schedule the events and detach the * context from the task such that we cannot ever get it scheduled back * in. */ - raw_spin_lock_irq(&child_ctx->lock); - task_ctx_sched_out(child_ctx, NULL, EVENT_ALL); + raw_spin_lock_irq(&ctx->lock); + if (exit) + task_ctx_sched_out(ctx, NULL, EVENT_ALL); /* * Now that the context is inactive, destroy the task <-> ctx relation * and mark the context dead. */ - RCU_INIT_POINTER(child->perf_event_ctxp, NULL); - put_ctx(child_ctx); /* cannot be last */ - WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE); - put_task_struct(current); /* cannot be last */ + RCU_INIT_POINTER(task->perf_event_ctxp, NULL); + put_ctx(ctx); /* cannot be last */ + WRITE_ONCE(ctx->task, TASK_TOMBSTONE); + put_task_struct(task); /* cannot be last */ - clone_ctx = unclone_ctx(child_ctx); - raw_spin_unlock_irq(&child_ctx->lock); + clone_ctx = unclone_ctx(ctx); + raw_spin_unlock_irq(&ctx->lock); if (clone_ctx) put_ctx(clone_ctx); @@ -13809,28 +14054,48 @@ static void perf_event_exit_task_context(struct task_struct *child) * won't get any samples after PERF_RECORD_EXIT. We can however still * get a few PERF_RECORD_READ events. */ - perf_event_task(child, child_ctx, 0); + if (exit) + perf_event_task(task, ctx, 0); - list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) - perf_event_exit_event(child_event, child_ctx); + list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry) + perf_event_exit_event(child_event, ctx, false); - mutex_unlock(&child_ctx->mutex); + mutex_unlock(&ctx->mutex); - put_ctx(child_ctx); + if (!exit) { + /* + * perf_event_release_kernel() could still have a reference on + * this context. In that case we must wait for these events to + * have been freed (in particular all their references to this + * task must've been dropped). + * + * Without this copy_process() will unconditionally free this + * task (irrespective of its reference count) and + * _free_event()'s put_task_struct(event->hw.target) will be a + * use-after-free. + * + * Wait for all events to drop their context reference. + */ + wait_var_event(&ctx->refcount, + refcount_read(&ctx->refcount) == 1); + } + put_ctx(ctx); } /* - * When a child task exits, feed back event values to parent events. + * When a task exits, feed back event values to parent events. * * Can be called with exec_update_lock held when called from * setup_new_exec(). */ -void perf_event_exit_task(struct task_struct *child) +void perf_event_exit_task(struct task_struct *task) { struct perf_event *event, *tmp; - mutex_lock(&child->perf_event_mutex); - list_for_each_entry_safe(event, tmp, &child->perf_event_list, + WARN_ON_ONCE(task != current); + + mutex_lock(&task->perf_event_mutex); + list_for_each_entry_safe(event, tmp, &task->perf_event_list, owner_entry) { list_del_init(&event->owner_entry); @@ -13841,44 +14106,23 @@ void perf_event_exit_task(struct task_struct *child) */ smp_store_release(&event->owner, NULL); } - mutex_unlock(&child->perf_event_mutex); + mutex_unlock(&task->perf_event_mutex); - perf_event_exit_task_context(child); + perf_event_exit_task_context(task, true); /* * The perf_event_exit_task_context calls perf_event_task - * with child's task_ctx, which generates EXIT events for - * child contexts and sets child->perf_event_ctxp[] to NULL. + * with task's task_ctx, which generates EXIT events for + * task contexts and sets task->perf_event_ctxp[] to NULL. * At this point we need to send EXIT events to cpu contexts. */ - perf_event_task(child, NULL, 0); + perf_event_task(task, NULL, 0); /* * Detach the perf_ctx_data for the system-wide event. */ guard(percpu_read)(&global_ctx_data_rwsem); - detach_task_ctx_data(child); -} - -static void perf_free_event(struct perf_event *event, - struct perf_event_context *ctx) -{ - struct perf_event *parent = event->parent; - - if (WARN_ON_ONCE(!parent)) - return; - - mutex_lock(&parent->child_mutex); - list_del_init(&event->child_list); - mutex_unlock(&parent->child_mutex); - - put_event(parent); - - raw_spin_lock_irq(&ctx->lock); - perf_group_detach(event); - list_del_event(event, ctx); - raw_spin_unlock_irq(&ctx->lock); - free_event(event); + detach_task_ctx_data(task); } /* @@ -13890,48 +14134,7 @@ static void perf_free_event(struct perf_event *event, */ void perf_event_free_task(struct task_struct *task) { - struct perf_event_context *ctx; - struct perf_event *event, *tmp; - - ctx = rcu_access_pointer(task->perf_event_ctxp); - if (!ctx) - return; - - mutex_lock(&ctx->mutex); - raw_spin_lock_irq(&ctx->lock); - /* - * Destroy the task <-> ctx relation and mark the context dead. - * - * This is important because even though the task hasn't been - * exposed yet the context has been (through child_list). - */ - RCU_INIT_POINTER(task->perf_event_ctxp, NULL); - WRITE_ONCE(ctx->task, TASK_TOMBSTONE); - put_task_struct(task); /* cannot be last */ - raw_spin_unlock_irq(&ctx->lock); - - - list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) - perf_free_event(event, ctx); - - mutex_unlock(&ctx->mutex); - - /* - * perf_event_release_kernel() could've stolen some of our - * child events and still have them on its free_list. In that - * case we must wait for these events to have been freed (in - * particular all their references to this task must've been - * dropped). - * - * Without this copy_process() will unconditionally free this - * task (irrespective of its reference count) and - * _free_event()'s put_task_struct(event->hw.target) will be a - * use-after-free. - * - * Wait for all events to drop their context reference. - */ - wait_var_event(&ctx->refcount, refcount_read(&ctx->refcount) == 1); - put_ctx(ctx); /* must be last */ + perf_event_exit_task_context(task, false); } void perf_event_delayed_put(struct task_struct *task) @@ -14008,6 +14211,14 @@ inherit_event(struct perf_event *parent_event, if (parent_event->parent) parent_event = parent_event->parent; + if (parent_event->state <= PERF_EVENT_STATE_REVOKED) + return NULL; + + /* + * Event creation should be under SRCU, see perf_pmu_unregister(). + */ + guard(srcu)(&pmus_srcu); + child_event = perf_event_alloc(&parent_event->attr, parent_event->cpu, child, @@ -14016,6 +14227,9 @@ inherit_event(struct perf_event *parent_event, if (IS_ERR(child_event)) return child_event; + get_ctx(child_ctx); + child_event->ctx = child_ctx; + pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event); if (IS_ERR(pmu_ctx)) { free_event(child_event); @@ -14037,8 +14251,6 @@ inherit_event(struct perf_event *parent_event, return NULL; } - get_ctx(child_ctx); - /* * Make the child state follow the state of the parent event, * not its attr.disabled bit. We hold the parent's mutex, @@ -14059,7 +14271,6 @@ inherit_event(struct perf_event *parent_event, local64_set(&hwc->period_left, sample_period); } - child_event->ctx = child_ctx; child_event->overflow_handler = parent_event->overflow_handler; child_event->overflow_handler_context = parent_event->overflow_handler_context; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 5130b119d0ae..d2aef87c7e9f 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -679,7 +679,15 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, { bool overwrite = !(flags & RING_BUFFER_WRITABLE); int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu); - int ret = -ENOMEM, max_order; + bool use_contiguous_pages = event->pmu->capabilities & ( + PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_PREFER_LARGE); + /* + * Initialize max_order to 0 for page allocation. This allocates single + * pages to minimize memory fragmentation. This is overridden if the + * PMU needs or prefers contiguous pages (use_contiguous_pages = true). + */ + int max_order = 0; + int ret = -ENOMEM; if (!has_aux(event)) return -EOPNOTSUPP; @@ -689,8 +697,8 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, if (!overwrite) { /* - * Watermark defaults to half the buffer, and so does the - * max_order, to aid PMU drivers in double buffering. + * Watermark defaults to half the buffer, to aid PMU drivers + * in double buffering. */ if (!watermark) watermark = min_t(unsigned long, @@ -698,16 +706,19 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, (unsigned long)nr_pages << (PAGE_SHIFT - 1)); /* - * Use aux_watermark as the basis for chunking to - * help PMU drivers honor the watermark. + * If using contiguous pages, use aux_watermark as the basis + * for chunking to help PMU drivers honor the watermark. */ - max_order = get_order(watermark); + if (use_contiguous_pages) + max_order = get_order(watermark); } else { /* - * We need to start with the max_order that fits in nr_pages, - * not the other way around, hence ilog2() and not get_order. + * If using contiguous pages, 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); + if (use_contiguous_pages) + max_order = ilog2(nr_pages); watermark = 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 615b4e6d22c7..4c965ba77f9f 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -29,6 +29,7 @@ #include <linux/workqueue.h> #include <linux/srcu.h> #include <linux/oom.h> /* check_stable_address_space */ +#include <linux/pagewalk.h> #include <linux/uprobes.h> @@ -152,91 +153,6 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr) } /** - * __replace_page - replace page in vma by new page. - * based on replace_page in mm/ksm.c - * - * @vma: vma that holds the pte pointing to page - * @addr: address the old @page is mapped at - * @old_page: the page we are replacing by new_page - * @new_page: the modified page we replace page by - * - * If @new_page is NULL, only unmap @old_page. - * - * Returns 0 on success, negative error code otherwise. - */ -static int __replace_page(struct vm_area_struct *vma, unsigned long addr, - struct page *old_page, struct page *new_page) -{ - struct folio *old_folio = page_folio(old_page); - struct folio *new_folio; - struct mm_struct *mm = vma->vm_mm; - DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0); - int err; - struct mmu_notifier_range range; - pte_t pte; - - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, - addr + PAGE_SIZE); - - if (new_page) { - new_folio = page_folio(new_page); - err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL); - if (err) - return err; - } - - /* For folio_free_swap() below */ - folio_lock(old_folio); - - mmu_notifier_invalidate_range_start(&range); - err = -EAGAIN; - if (!page_vma_mapped_walk(&pvmw)) - goto unlock; - VM_BUG_ON_PAGE(addr != pvmw.address, old_page); - pte = ptep_get(pvmw.pte); - - /* - * Handle PFN swap PTES, such as device-exclusive ones, that actually - * map pages: simply trigger GUP again to fix it up. - */ - if (unlikely(!pte_present(pte))) { - page_vma_mapped_walk_done(&pvmw); - goto unlock; - } - - if (new_page) { - folio_get(new_folio); - folio_add_new_anon_rmap(new_folio, vma, addr, RMAP_EXCLUSIVE); - folio_add_lru_vma(new_folio, vma); - } else - /* no new page, just dec_mm_counter for old_page */ - dec_mm_counter(mm, MM_ANONPAGES); - - if (!folio_test_anon(old_folio)) { - dec_mm_counter(mm, mm_counter_file(old_folio)); - inc_mm_counter(mm, MM_ANONPAGES); - } - - flush_cache_page(vma, addr, pte_pfn(pte)); - ptep_clear_flush(vma, addr, pvmw.pte); - if (new_page) - set_pte_at(mm, addr, pvmw.pte, - mk_pte(new_page, vma->vm_page_prot)); - - folio_remove_rmap_pte(old_folio, old_page, vma); - if (!folio_mapped(old_folio)) - folio_free_swap(old_folio); - page_vma_mapped_walk_done(&pvmw); - folio_put(old_folio); - - err = 0; - unlock: - mmu_notifier_invalidate_range_end(&range); - folio_unlock(old_folio); - return err; -} - -/** * is_swbp_insn - check if instruction is breakpoint instruction. * @insn: instruction to be checked. * Default implementation of is_swbp_insn @@ -463,6 +379,95 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, return ret; } +static bool orig_page_is_identical(struct vm_area_struct *vma, + unsigned long vaddr, struct page *page, bool *pmd_mappable) +{ + const pgoff_t index = vaddr_to_offset(vma, vaddr) >> PAGE_SHIFT; + struct folio *orig_folio = filemap_get_folio(vma->vm_file->f_mapping, + index); + struct page *orig_page; + bool identical; + + if (IS_ERR(orig_folio)) + return false; + orig_page = folio_file_page(orig_folio, index); + + *pmd_mappable = folio_test_pmd_mappable(orig_folio); + identical = folio_test_uptodate(orig_folio) && + pages_identical(page, orig_page); + folio_put(orig_folio); + return identical; +} + +static int __uprobe_write_opcode(struct vm_area_struct *vma, + struct folio_walk *fw, struct folio *folio, + unsigned long opcode_vaddr, uprobe_opcode_t opcode) +{ + const unsigned long vaddr = opcode_vaddr & PAGE_MASK; + const bool is_register = !!is_swbp_insn(&opcode); + bool pmd_mappable; + + /* For now, we'll only handle PTE-mapped folios. */ + if (fw->level != FW_LEVEL_PTE) + return -EFAULT; + + /* + * See can_follow_write_pte(): we'd actually prefer a writable PTE here, + * but the VMA might not be writable. + */ + if (!pte_write(fw->pte)) { + if (!PageAnonExclusive(fw->page)) + return -EFAULT; + if (unlikely(userfaultfd_pte_wp(vma, fw->pte))) + return -EFAULT; + /* SOFTDIRTY is handled via pte_mkdirty() below. */ + } + + /* + * We'll temporarily unmap the page and flush the TLB, such that we can + * modify the page atomically. + */ + flush_cache_page(vma, vaddr, pte_pfn(fw->pte)); + fw->pte = ptep_clear_flush(vma, vaddr, fw->ptep); + copy_to_page(fw->page, opcode_vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + + /* + * When unregistering, we may only zap a PTE if uffd is disabled and + * there are no unexpected folio references ... + */ + if (is_register || userfaultfd_missing(vma) || + (folio_ref_count(folio) != folio_mapcount(folio) + 1 + + folio_test_swapcache(folio) * folio_nr_pages(folio))) + goto remap; + + /* + * ... and the mapped page is identical to the original page that + * would get faulted in on next access. + */ + if (!orig_page_is_identical(vma, vaddr, fw->page, &pmd_mappable)) + goto remap; + + dec_mm_counter(vma->vm_mm, MM_ANONPAGES); + folio_remove_rmap_pte(folio, fw->page, vma); + if (!folio_mapped(folio) && folio_test_swapcache(folio) && + folio_trylock(folio)) { + folio_free_swap(folio); + folio_unlock(folio); + } + folio_put(folio); + + return pmd_mappable; +remap: + /* + * Make sure that our copy_to_page() changes become visible before the + * set_pte_at() write. + */ + smp_wmb(); + /* We modified the page. Make sure to mark the PTE dirty. */ + set_pte_at(vma->vm_mm, vaddr, fw->ptep, pte_mkdirty(fw->pte)); + return 0; +} + /* * NOTE: * Expect the breakpoint instruction to be the smallest size instruction for @@ -474,146 +479,146 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, * * uprobe_write_opcode - write the opcode at a given virtual address. * @auprobe: arch specific probepoint information. - * @mm: the probed process address space. - * @vaddr: the virtual address to store the opcode. - * @opcode: opcode to be written at @vaddr. + * @vma: the probed virtual memory area. + * @opcode_vaddr: the virtual address to store the opcode. + * @opcode: opcode to be written at @opcode_vaddr. * * Called with mm->mmap_lock held for read or write. * Return 0 (success) or a negative errno. */ -int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, - unsigned long vaddr, uprobe_opcode_t opcode) +int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma, + const unsigned long opcode_vaddr, uprobe_opcode_t opcode) { + const unsigned long vaddr = opcode_vaddr & PAGE_MASK; + struct mm_struct *mm = vma->vm_mm; struct uprobe *uprobe; - struct page *old_page, *new_page; - struct vm_area_struct *vma; int ret, is_register, ref_ctr_updated = 0; - bool orig_page_huge = false; unsigned int gup_flags = FOLL_FORCE; + struct mmu_notifier_range range; + struct folio_walk fw; + struct folio *folio; + struct page *page; is_register = is_swbp_insn(&opcode); uprobe = container_of(auprobe, struct uprobe, arch); -retry: + if (WARN_ON_ONCE(!is_cow_mapping(vma->vm_flags))) + return -EINVAL; + + /* + * When registering, we have to break COW to get an exclusive anonymous + * page that we can safely modify. Use FOLL_WRITE to trigger a write + * fault if required. When unregistering, we might be lucky and the + * anon page is already gone. So defer write faults until really + * required. Use FOLL_SPLIT_PMD, because __uprobe_write_opcode() + * cannot deal with PMDs yet. + */ if (is_register) - gup_flags |= FOLL_SPLIT_PMD; - /* Read the page with vaddr into memory */ - old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma); - if (IS_ERR(old_page)) - return PTR_ERR(old_page); + gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD; - ret = verify_opcode(old_page, vaddr, &opcode); +retry: + ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &page, NULL); if (ret <= 0) - goto put_old; - - if (is_zero_page(old_page)) { - ret = -EINVAL; - goto put_old; - } + goto out; + folio = page_folio(page); - if (WARN(!is_register && PageCompound(old_page), - "uprobe unregister should never work on compound page\n")) { - ret = -EINVAL; - goto put_old; + ret = verify_opcode(page, opcode_vaddr, &opcode); + if (ret <= 0) { + folio_put(folio); + goto out; } /* We are going to replace instruction, update ref_ctr. */ if (!ref_ctr_updated && uprobe->ref_ctr_offset) { ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); - if (ret) - goto put_old; + if (ret) { + folio_put(folio); + goto out; + } ref_ctr_updated = 1; } ret = 0; - if (!is_register && !PageAnon(old_page)) - goto put_old; - - ret = anon_vma_prepare(vma); - if (ret) - goto put_old; - - ret = -ENOMEM; - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); - if (!new_page) - goto put_old; - - __SetPageUptodate(new_page); - copy_highpage(new_page, old_page); - copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + if (unlikely(!folio_test_anon(folio))) { + VM_WARN_ON_ONCE(is_register); + folio_put(folio); + goto out; + } if (!is_register) { - struct page *orig_page; - pgoff_t index; - - VM_BUG_ON_PAGE(!PageAnon(old_page), old_page); - - index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT; - orig_page = find_get_page(vma->vm_file->f_inode->i_mapping, - index); - - if (orig_page) { - if (PageUptodate(orig_page) && - pages_identical(new_page, orig_page)) { - /* let go new_page */ - put_page(new_page); - new_page = NULL; - - if (PageCompound(orig_page)) - orig_page_huge = true; - } - put_page(orig_page); - } + /* + * In the common case, we'll be able to zap the page when + * unregistering. So trigger MMU notifiers now, as we won't + * be able to do it under PTL. + */ + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, + vaddr, vaddr + PAGE_SIZE); + mmu_notifier_invalidate_range_start(&range); + } + + ret = -EAGAIN; + /* Walk the page tables again, to perform the actual update. */ + if (folio_walk_start(&fw, vma, vaddr, 0)) { + if (fw.page == page) + ret = __uprobe_write_opcode(vma, &fw, folio, opcode_vaddr, opcode); + folio_walk_end(&fw, vma); } - ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page); - if (new_page) - put_page(new_page); -put_old: - put_page(old_page); + if (!is_register) + mmu_notifier_invalidate_range_end(&range); - if (unlikely(ret == -EAGAIN)) + folio_put(folio); + switch (ret) { + case -EFAULT: + gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD; + fallthrough; + case -EAGAIN: goto retry; + default: + break; + } +out: /* Revert back reference counter if instruction update failed. */ - if (ret && is_register && ref_ctr_updated) + if (ret < 0 && is_register && ref_ctr_updated) update_ref_ctr(uprobe, mm, -1); /* try collapse pmd for compound page */ - if (!ret && orig_page_huge) + if (ret > 0) collapse_pte_mapped_thp(mm, vaddr, false); - return ret; + return ret < 0 ? ret : 0; } /** * set_swbp - store breakpoint at a given address. * @auprobe: arch specific probepoint information. - * @mm: the probed process address space. + * @vma: the probed virtual memory area. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, store the breakpoint instruction at @vaddr. * Return 0 (success) or a negative errno. */ -int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) +int __weak set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma, + unsigned long vaddr) { - return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN); + return uprobe_write_opcode(auprobe, vma, vaddr, UPROBE_SWBP_INSN); } /** * set_orig_insn - Restore the original instruction. - * @mm: the probed process address space. + * @vma: the probed virtual memory area. * @auprobe: arch specific probepoint information. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ -int __weak -set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) +int __weak set_orig_insn(struct arch_uprobe *auprobe, + struct vm_area_struct *vma, unsigned long vaddr) { - return uprobe_write_opcode(auprobe, mm, vaddr, + return uprobe_write_opcode(auprobe, vma, vaddr, *(uprobe_opcode_t *)&auprobe->insn); } @@ -1134,10 +1139,10 @@ static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm) return ret; } -static int -install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long vaddr) +static int install_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma, + unsigned long vaddr) { + struct mm_struct *mm = vma->vm_mm; bool first_uprobe; int ret; @@ -1153,7 +1158,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, if (first_uprobe) set_bit(MMF_HAS_UPROBES, &mm->flags); - ret = set_swbp(&uprobe->arch, mm, vaddr); + ret = set_swbp(&uprobe->arch, vma, vaddr); if (!ret) clear_bit(MMF_RECALC_UPROBES, &mm->flags); else if (first_uprobe) @@ -1162,11 +1167,13 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, return ret; } -static int -remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) +static int remove_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma, + unsigned long vaddr) { + struct mm_struct *mm = vma->vm_mm; + set_bit(MMF_RECALC_UPROBES, &mm->flags); - return set_orig_insn(&uprobe->arch, mm, vaddr); + return set_orig_insn(&uprobe->arch, vma, vaddr); } struct map_info { @@ -1296,10 +1303,10 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) if (is_register) { /* consult only the "caller", new consumer. */ if (consumer_filter(new, mm)) - err = install_breakpoint(uprobe, mm, vma, info->vaddr); + err = install_breakpoint(uprobe, vma, info->vaddr); } else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) { if (!filter_chain(uprobe, mm)) - err |= remove_breakpoint(uprobe, mm, info->vaddr); + err |= remove_breakpoint(uprobe, vma, info->vaddr); } unlock: @@ -1472,7 +1479,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) continue; vaddr = offset_to_vaddr(vma, uprobe->offset); - err |= remove_breakpoint(uprobe, mm, vaddr); + err |= remove_breakpoint(uprobe, vma, vaddr); } mmap_read_unlock(mm); @@ -1610,7 +1617,7 @@ int uprobe_mmap(struct vm_area_struct *vma) if (!fatal_signal_pending(current) && filter_chain(uprobe, vma->vm_mm)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); - install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); + install_breakpoint(uprobe, vma, vaddr); } put_uprobe(uprobe); } @@ -1956,6 +1963,9 @@ static void free_ret_instance(struct uprobe_task *utask, * to-be-reused return instances for future uretprobes. If ri_timer() * happens to be running right now, though, we fallback to safety and * just perform RCU-delated freeing of ri. + * Admittedly, this is a rather simple use of seqcount, but it nicely + * abstracts away all the necessary memory barriers, so we use + * a well-supported kernel primitive here. */ if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) { /* immediate reuse of ri without RCU GP is OK */ @@ -2016,12 +2026,20 @@ static void ri_timer(struct timer_list *timer) /* RCU protects return_instance from freeing. */ guard(rcu)(); - write_seqcount_begin(&utask->ri_seqcount); + /* + * See free_ret_instance() for notes on seqcount use. + * We also employ raw API variants to avoid lockdep false-positive + * warning complaining about enabled preemption. The timer can only be + * invoked once for a uprobe_task. Therefore there can only be one + * writer. The reader does not require an even sequence count to make + * progress, so it is OK to remain preemptible on PREEMPT_RT. + */ + raw_write_seqcount_begin(&utask->ri_seqcount); for_each_ret_instance_rcu(ri, utask->return_instances) hprobe_expire(&ri->hprobe, false); - write_seqcount_end(&utask->ri_seqcount); + raw_write_seqcount_end(&utask->ri_seqcount); } static struct uprobe_task *alloc_utask(void) |