diff options
Diffstat (limited to 'kernel/events')
| -rw-r--r-- | kernel/events/callchain.c | 2 | ||||
| -rw-r--r-- | kernel/events/core.c | 92 | ||||
| -rw-r--r-- | kernel/events/uprobes.c | 30 |
3 files changed, 85 insertions, 39 deletions
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index e9fdb5203de5..c04917cad1bf 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -11,6 +11,8 @@ #include <linux/perf_event.h> #include <linux/slab.h> +#include <linux/sched/task_stack.h> + #include "internal.h" struct callchain_cpus_entries { diff --git a/kernel/events/core.c b/kernel/events/core.c index 77a932b54a64..ff01cba86f43 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -46,6 +46,8 @@ #include <linux/filter.h> #include <linux/namei.h> #include <linux/parser.h> +#include <linux/sched/clock.h> +#include <linux/sched/mm.h> #include "internal.h" @@ -455,7 +457,7 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec(table, write, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) return ret; @@ -996,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event, */ #define PERF_CPU_HRTIMER (1000 / HZ) /* - * function must be called with interrupts disbled + * function must be called with interrupts disabled */ static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr) { @@ -3522,6 +3524,8 @@ static void perf_event_enable_on_exec(int ctxn) if (enabled) { clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); + } else { + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); } perf_ctx_unlock(cpuctx, ctx); @@ -4252,7 +4256,7 @@ int perf_event_release_kernel(struct perf_event *event) raw_spin_lock_irq(&ctx->lock); /* - * Mark this even as STATE_DEAD, there is no external reference to it + * Mark this event as STATE_DEAD, there is no external reference to it * anymore. * * Anybody acquiring event->child_mutex after the below loop _must_ @@ -4925,9 +4929,9 @@ unlock: rcu_read_unlock(); } -static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int perf_mmap_fault(struct vm_fault *vmf) { - struct perf_event *event = vma->vm_file->private_data; + struct perf_event *event = vmf->vma->vm_file->private_data; struct ring_buffer *rb; int ret = VM_FAULT_SIGBUS; @@ -4950,7 +4954,7 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) goto unlock; get_page(vmf->page); - vmf->page->mapping = vma->vm_file->f_mapping; + vmf->page->mapping = vmf->vma->vm_file->f_mapping; vmf->page->index = vmf->pgoff; ret = 0; @@ -9955,6 +9959,7 @@ SYSCALL_DEFINE5(perf_event_open, * of swizzling perf_event::ctx. */ perf_remove_from_context(group_leader, 0); + put_ctx(gctx); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { @@ -9993,13 +9998,6 @@ SYSCALL_DEFINE5(perf_event_open, perf_event__state_init(group_leader); perf_install_in_context(ctx, group_leader, group_leader->cpu); get_ctx(ctx); - - /* - * Now that all events are installed in @ctx, nothing - * references @gctx anymore, so drop the last reference we have - * on it. - */ - put_ctx(gctx); } /* @@ -10419,21 +10417,22 @@ void perf_event_free_task(struct task_struct *task) continue; mutex_lock(&ctx->mutex); -again: - list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, - group_entry) - perf_free_event(event, ctx); + 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[ctxn], 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->flexible_groups, - group_entry) + list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) perf_free_event(event, ctx); - if (!list_empty(&ctx->pinned_groups) || - !list_empty(&ctx->flexible_groups)) - goto again; - mutex_unlock(&ctx->mutex); - put_ctx(ctx); } } @@ -10471,7 +10470,12 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) } /* - * inherit a event from parent task to child task: + * Inherit a event from parent task to child task. + * + * Returns: + * - valid pointer on success + * - NULL for orphaned events + * - IS_ERR() on error */ static struct perf_event * inherit_event(struct perf_event *parent_event, @@ -10565,6 +10569,16 @@ inherit_event(struct perf_event *parent_event, return child_event; } +/* + * Inherits an event group. + * + * This will quietly suppress orphaned events; !inherit_event() is not an error. + * This matches with perf_event_release_kernel() removing all child events. + * + * Returns: + * - 0 on success + * - <0 on error + */ static int inherit_group(struct perf_event *parent_event, struct task_struct *parent, struct perf_event_context *parent_ctx, @@ -10579,6 +10593,11 @@ static int inherit_group(struct perf_event *parent_event, child, NULL, child_ctx); if (IS_ERR(leader)) return PTR_ERR(leader); + /* + * @leader can be NULL here because of is_orphaned_event(). In this + * case inherit_event() will create individual events, similar to what + * perf_group_detach() would do anyway. + */ list_for_each_entry(sub, &parent_event->sibling_list, group_entry) { child_ctr = inherit_event(sub, parent, parent_ctx, child, leader, child_ctx); @@ -10588,6 +10607,17 @@ static int inherit_group(struct perf_event *parent_event, return 0; } +/* + * Creates the child task context and tries to inherit the event-group. + * + * Clears @inherited_all on !attr.inherited or error. Note that we'll leave + * inherited_all set when we 'fail' to inherit an orphaned event; this is + * consistent with perf_event_release_kernel() removing all child events. + * + * Returns: + * - 0 on success + * - <0 on error + */ static int inherit_task_group(struct perf_event *event, struct task_struct *parent, struct perf_event_context *parent_ctx, @@ -10610,7 +10640,6 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, * First allocate and initialize a context for the * child. */ - child_ctx = alloc_perf_context(parent_ctx->pmu, child); if (!child_ctx) return -ENOMEM; @@ -10672,7 +10701,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } /* @@ -10688,7 +10717,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } raw_spin_lock_irqsave(&parent_ctx->lock, flags); @@ -10716,6 +10745,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) } raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); +out_unlock: mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); @@ -10959,5 +10989,11 @@ struct cgroup_subsys perf_event_cgrp_subsys = { .css_alloc = perf_cgroup_css_alloc, .css_free = perf_cgroup_css_free, .attach = perf_cgroup_attach, + /* + * Implicitly enable on dfl hierarchy so that perf events can + * always be filtered by cgroup2 path as long as perf_event + * controller is not mounted on a legacy hierarchy. + */ + .implicit_on_dfl = true, }; #endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index d416f3baf392..0e137f98a50c 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -27,6 +27,8 @@ #include <linux/pagemap.h> /* read_mapping_page */ #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/coredump.h> #include <linux/export.h> #include <linux/rmap.h> /* anon_vma_prepare */ #include <linux/mmu_notifier.h> /* set_pte_at_notify */ @@ -153,14 +155,19 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, struct page *old_page, struct page *new_page) { struct mm_struct *mm = vma->vm_mm; - spinlock_t *ptl; - pte_t *ptep; + struct page_vma_mapped_walk pvmw = { + .page = old_page, + .vma = vma, + .address = addr, + }; int err; /* For mmu_notifiers */ const unsigned long mmun_start = addr; const unsigned long mmun_end = addr + PAGE_SIZE; struct mem_cgroup *memcg; + VM_BUG_ON_PAGE(PageTransHuge(old_page), old_page); + err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, &memcg, false); if (err) @@ -171,11 +178,11 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); err = -EAGAIN; - ptep = page_check_address(old_page, mm, addr, &ptl, 0); - if (!ptep) { + if (!page_vma_mapped_walk(&pvmw)) { mem_cgroup_cancel_charge(new_page, memcg, false); goto unlock; } + VM_BUG_ON_PAGE(addr != pvmw.address, old_page); get_page(new_page); page_add_new_anon_rmap(new_page, vma, addr, false); @@ -187,14 +194,15 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, inc_mm_counter(mm, MM_ANONPAGES); } - flush_cache_page(vma, addr, pte_pfn(*ptep)); - ptep_clear_flush_notify(vma, addr, ptep); - set_pte_at_notify(mm, addr, ptep, mk_pte(new_page, vma->vm_page_prot)); + flush_cache_page(vma, addr, pte_pfn(*pvmw.pte)); + ptep_clear_flush_notify(vma, addr, pvmw.pte); + set_pte_at_notify(mm, addr, pvmw.pte, + mk_pte(new_page, vma->vm_page_prot)); page_remove_rmap(old_page, false); if (!page_mapped(old_page)) try_to_free_swap(old_page); - pte_unmap_unlock(ptep, ptl); + page_vma_mapped_walk_done(&pvmw); if (vma->vm_flags & VM_LOCKED) munlock_vma_page(old_page); @@ -300,8 +308,8 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, retry: /* Read the page with vaddr into memory */ - ret = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page, - &vma, NULL); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, + FOLL_FORCE | FOLL_SPLIT, &old_page, &vma, NULL); if (ret <= 0) return ret; @@ -741,7 +749,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register) continue; } - if (!atomic_inc_not_zero(&vma->vm_mm->mm_users)) + if (!mmget_not_zero(vma->vm_mm)) continue; info = prev; |
