* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
+ * 3 - disallow all unpriv perf event use
*/
-int sysctl_perf_event_paranoid __read_mostly = 2;
+#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT
+int sysctl_perf_event_paranoid __read_mostly = 3;
+#else
+int sysctl_perf_event_paranoid __read_mostly = 1;
+#endif
/* Minimum for 512 kiB + 1 user control page */
int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
-
lockdep_assert_held(&ctx->lock);
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
{
struct perf_event *group_leader = event->group_leader, *pos;
+ lockdep_assert_held(&event->ctx->lock);
+
/*
* We can have double attach due to group movement in perf_event_open.
*/
struct perf_event *sibling, *tmp;
struct list_head *list = NULL;
+ lockdep_assert_held(&event->ctx->lock);
+
/*
* We can have double detach due to exit/hot-unplug + close.
*/
*/
static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
{
- lockdep_assert_held(&event->ctx->mutex);
+ struct perf_event_context *ctx = event->ctx;
+
+ lockdep_assert_held(&ctx->mutex);
event_function_call(event, __perf_remove_from_context, (void *)flags);
+
+ /*
+ * The above event_function_call() can NO-OP when it hits
+ * TASK_TOMBSTONE. In that case we must already have been detached
+ * from the context (by perf_event_exit_event()) but the grouping
+ * might still be in-tact.
+ */
+ WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
+ if ((flags & DETACH_GROUP) &&
+ (event->attach_state & PERF_ATTACH_GROUP)) {
+ /*
+ * Since in that case we cannot possibly be scheduled, simply
+ * detach now.
+ */
+ raw_spin_lock_irq(&ctx->lock);
+ perf_group_detach(event);
+ raw_spin_unlock_irq(&ctx->lock);
+ }
}
/*
int ret;
};
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
{
- int event_cpu = event->oncpu;
u16 local_pkg, event_pkg;
if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
- event_pkg = topology_physical_package_id(event_cpu);
- local_pkg = topology_physical_package_id(local_cpu);
+ int local_cpu = smp_processor_id();
+
+ event_pkg = topology_physical_package_id(event_cpu);
+ local_pkg = topology_physical_package_id(local_cpu);
if (event_pkg == local_pkg)
return local_cpu;
static int perf_event_read(struct perf_event *event, bool group)
{
- int ret = 0, cpu_to_read, local_cpu;
+ int event_cpu, ret = 0;
/*
* If event is enabled and currently active on a CPU, update the
.ret = 0,
};
- local_cpu = get_cpu();
- cpu_to_read = find_cpu_to_read(event, local_cpu);
- put_cpu();
+ event_cpu = READ_ONCE(event->oncpu);
+ if ((unsigned)event_cpu >= nr_cpu_ids)
+ return 0;
+
+ preempt_disable();
+ event_cpu = __perf_event_read_cpu(event, event_cpu);
/*
* Purposely ignore the smp_call_function_single() return
* value.
*
- * If event->oncpu isn't a valid CPU it means the event got
+ * If event_cpu isn't a valid CPU it means the event got
* scheduled out and that will have updated the event count.
*
* Therefore, either way, we'll have an up-to-date event count
* after this.
*/
- (void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+ (void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+ preempt_enable();
ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
char *buf = NULL;
char *name;
+ if (vma->vm_flags & VM_READ)
+ prot |= PROT_READ;
+ if (vma->vm_flags & VM_WRITE)
+ prot |= PROT_WRITE;
+ if (vma->vm_flags & VM_EXEC)
+ prot |= PROT_EXEC;
+
+ if (vma->vm_flags & VM_MAYSHARE)
+ flags = MAP_SHARED;
+ else
+ flags = MAP_PRIVATE;
+
+ if (vma->vm_flags & VM_DENYWRITE)
+ flags |= MAP_DENYWRITE;
+ if (vma->vm_flags & VM_MAYEXEC)
+ flags |= MAP_EXECUTABLE;
+ if (vma->vm_flags & VM_LOCKED)
+ flags |= MAP_LOCKED;
+ if (vma->vm_flags & VM_HUGETLB)
+ flags |= MAP_HUGETLB;
+
if (file) {
struct inode *inode;
dev_t dev;
maj = MAJOR(dev);
min = MINOR(dev);
- if (vma->vm_flags & VM_READ)
- prot |= PROT_READ;
- if (vma->vm_flags & VM_WRITE)
- prot |= PROT_WRITE;
- if (vma->vm_flags & VM_EXEC)
- prot |= PROT_EXEC;
-
- if (vma->vm_flags & VM_MAYSHARE)
- flags = MAP_SHARED;
- else
- flags = MAP_PRIVATE;
-
- if (vma->vm_flags & VM_DENYWRITE)
- flags |= MAP_DENYWRITE;
- if (vma->vm_flags & VM_MAYEXEC)
- flags |= MAP_EXECUTABLE;
- if (vma->vm_flags & VM_LOCKED)
- flags |= MAP_LOCKED;
- if (vma->vm_flags & VM_HUGETLB)
- flags |= MAP_HUGETLB;
-
goto got_name;
} else {
if (vma->vm_ops && vma->vm_ops->name) {
if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
+ if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
err = perf_copy_attr(attr_uptr, &attr);
if (err)
return err;
continue;
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[ctxn], NULL);
+ WRITE_ONCE(ctx->task, TASK_TOMBSTONE);
+ put_task_struct(task); /* cannot be last */
+ raw_spin_unlock_irq(&ctx->lock);
again:
list_for_each_entry_safe(event, tmp, &ctx->pinned_groups,
group_entry)