aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/tracepoint.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/tracepoint.c')
-rw-r--r--kernel/tracepoint.c311
1 files changed, 253 insertions, 58 deletions
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 73956eaff8a9..f23144af5743 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -15,12 +15,57 @@
#include <linux/sched/task.h>
#include <linux/static_key.h>
+enum tp_func_state {
+ TP_FUNC_0,
+ TP_FUNC_1,
+ TP_FUNC_2,
+ TP_FUNC_N,
+};
+
extern tracepoint_ptr_t __start___tracepoints_ptrs[];
extern tracepoint_ptr_t __stop___tracepoints_ptrs[];
DEFINE_SRCU(tracepoint_srcu);
EXPORT_SYMBOL_GPL(tracepoint_srcu);
+enum tp_transition_sync {
+ TP_TRANSITION_SYNC_1_0_1,
+ TP_TRANSITION_SYNC_N_2_1,
+
+ _NR_TP_TRANSITION_SYNC,
+};
+
+struct tp_transition_snapshot {
+ unsigned long rcu;
+ unsigned long srcu;
+ bool ongoing;
+};
+
+/* Protected by tracepoints_mutex */
+static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC];
+
+static void tp_rcu_get_state(enum tp_transition_sync sync)
+{
+ struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+ /* Keep the latest get_state snapshot. */
+ snapshot->rcu = get_state_synchronize_rcu();
+ snapshot->srcu = start_poll_synchronize_srcu(&tracepoint_srcu);
+ snapshot->ongoing = true;
+}
+
+static void tp_rcu_cond_sync(enum tp_transition_sync sync)
+{
+ struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+ if (!snapshot->ongoing)
+ return;
+ cond_synchronize_rcu(snapshot->rcu);
+ if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu))
+ synchronize_srcu(&tracepoint_srcu);
+ snapshot->ongoing = false;
+}
+
/* Set to 1 to enable tracepoint debug output */
static const int tracepoint_debug;
@@ -50,9 +95,15 @@ static bool ok_to_free_tracepoints;
*/
struct tp_probes {
struct rcu_head rcu;
- struct tracepoint_func probes[0];
+ struct tracepoint_func probes[];
};
+/* Called in removal of a func but failed to allocate a new tp_funcs */
+static void tp_stub_func(void)
+{
+ return;
+}
+
static inline void *allocate_probes(int count)
{
struct tp_probes *p = kmalloc(struct_size(p, probes, count),
@@ -130,8 +181,9 @@ func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func,
int prio)
{
struct tracepoint_func *old, *new;
- int nr_probes = 0;
- int pos = -1;
+ int iter_probes; /* Iterate over old probe array. */
+ int nr_probes = 0; /* Counter for probes */
+ int pos = -1; /* Insertion position into new array */
if (WARN_ON(!tp_func->func))
return ERR_PTR(-EINVAL);
@@ -140,13 +192,13 @@ func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func,
old = *funcs;
if (old) {
/* (N -> N+1), (N != 0, 1) probes */
- for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
- /* Insert before probes of lower priority */
- if (pos < 0 && old[nr_probes].prio < prio)
- pos = nr_probes;
- if (old[nr_probes].func == tp_func->func &&
- old[nr_probes].data == tp_func->data)
+ for (iter_probes = 0; old[iter_probes].func; iter_probes++) {
+ if (old[iter_probes].func == tp_stub_func)
+ continue; /* Skip stub functions. */
+ if (old[iter_probes].func == tp_func->func &&
+ old[iter_probes].data == tp_func->data)
return ERR_PTR(-EEXIST);
+ nr_probes++;
}
}
/* + 2 : one for new probe, one for NULL func */
@@ -154,20 +206,24 @@ func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func,
if (new == NULL)
return ERR_PTR(-ENOMEM);
if (old) {
- if (pos < 0) {
- pos = nr_probes;
- memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
- } else {
- /* Copy higher priority probes ahead of the new probe */
- memcpy(new, old, pos * sizeof(struct tracepoint_func));
- /* Copy the rest after it. */
- memcpy(new + pos + 1, old + pos,
- (nr_probes - pos) * sizeof(struct tracepoint_func));
+ nr_probes = 0;
+ for (iter_probes = 0; old[iter_probes].func; iter_probes++) {
+ if (old[iter_probes].func == tp_stub_func)
+ continue;
+ /* Insert before probes of lower priority */
+ if (pos < 0 && old[iter_probes].prio < prio)
+ pos = nr_probes++;
+ new[nr_probes++] = old[iter_probes];
}
- } else
+ if (pos < 0)
+ pos = nr_probes++;
+ /* nr_probes now points to the end of the new array */
+ } else {
pos = 0;
+ nr_probes = 1; /* must point at end of array */
+ }
new[pos] = *tp_func;
- new[nr_probes + 1].func = NULL;
+ new[nr_probes].func = NULL;
*funcs = new;
debug_print_probes(*funcs);
return old;
@@ -188,8 +244,9 @@ static void *func_remove(struct tracepoint_func **funcs,
/* (N -> M), (N > 1, M >= 0) probes */
if (tp_func->func) {
for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
- if (old[nr_probes].func == tp_func->func &&
- old[nr_probes].data == tp_func->data)
+ if ((old[nr_probes].func == tp_func->func &&
+ old[nr_probes].data == tp_func->data) ||
+ old[nr_probes].func == tp_stub_func)
nr_del++;
}
}
@@ -208,24 +265,64 @@ static void *func_remove(struct tracepoint_func **funcs,
/* N -> M, (N > 1, M > 0) */
/* + 1 for NULL */
new = allocate_probes(nr_probes - nr_del + 1);
- if (new == NULL)
- return ERR_PTR(-ENOMEM);
- for (i = 0; old[i].func; i++)
- if (old[i].func != tp_func->func
- || old[i].data != tp_func->data)
- new[j++] = old[i];
- new[nr_probes - nr_del].func = NULL;
- *funcs = new;
+ if (new) {
+ for (i = 0; old[i].func; i++) {
+ if ((old[i].func != tp_func->func ||
+ old[i].data != tp_func->data) &&
+ old[i].func != tp_stub_func)
+ new[j++] = old[i];
+ }
+ new[nr_probes - nr_del].func = NULL;
+ *funcs = new;
+ } else {
+ /*
+ * Failed to allocate, replace the old function
+ * with calls to tp_stub_func.
+ */
+ for (i = 0; old[i].func; i++) {
+ if (old[i].func == tp_func->func &&
+ old[i].data == tp_func->data)
+ WRITE_ONCE(old[i].func, tp_stub_func);
+ }
+ *funcs = old;
+ }
}
debug_print_probes(*funcs);
return old;
}
/*
+ * Count the number of functions (enum tp_func_state) in a tp_funcs array.
+ */
+static enum tp_func_state nr_func_state(const struct tracepoint_func *tp_funcs)
+{
+ if (!tp_funcs)
+ return TP_FUNC_0;
+ if (!tp_funcs[1].func)
+ return TP_FUNC_1;
+ if (!tp_funcs[2].func)
+ return TP_FUNC_2;
+ return TP_FUNC_N; /* 3 or more */
+}
+
+static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
+{
+ void *func = tp->iterator;
+
+ /* Synthetic events do not have static call sites */
+ if (!tp->static_call_key)
+ return;
+ if (nr_func_state(tp_funcs) == TP_FUNC_1)
+ func = tp_funcs[0].func;
+ __static_call_update(tp->static_call_key, tp->static_call_tramp, func);
+}
+
+/*
* Add the probe function to a tracepoint.
*/
static int tracepoint_add_func(struct tracepoint *tp,
- struct tracepoint_func *func, int prio)
+ struct tracepoint_func *func, int prio,
+ bool warn)
{
struct tracepoint_func *old, *tp_funcs;
int ret;
@@ -240,7 +337,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
lockdep_is_held(&tracepoints_mutex));
old = func_add(&tp_funcs, func, prio);
if (IS_ERR(old)) {
- WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
+ WARN_ON_ONCE(warn && PTR_ERR(old) != -ENOMEM);
return PTR_ERR(old);
}
@@ -250,9 +347,42 @@ static int tracepoint_add_func(struct tracepoint *tp,
* a pointer to it. This array is referenced by __DO_TRACE from
* include/linux/tracepoint.h using rcu_dereference_sched().
*/
- rcu_assign_pointer(tp->funcs, tp_funcs);
- if (!static_key_enabled(&tp->key))
- static_key_slow_inc(&tp->key);
+ switch (nr_func_state(tp_funcs)) {
+ case TP_FUNC_1: /* 0->1 */
+ /*
+ * Make sure new static func never uses old data after a
+ * 1->0->1 transition sequence.
+ */
+ tp_rcu_cond_sync(TP_TRANSITION_SYNC_1_0_1);
+ /* Set static call to first function */
+ tracepoint_update_call(tp, tp_funcs);
+ /* Both iterator and static call handle NULL tp->funcs */
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ static_key_enable(&tp->key);
+ break;
+ case TP_FUNC_2: /* 1->2 */
+ /* Set iterator static call */
+ tracepoint_update_call(tp, tp_funcs);
+ /*
+ * Iterator callback installed before updating tp->funcs.
+ * Requires ordering between RCU assign/dereference and
+ * static call update/call.
+ */
+ fallthrough;
+ case TP_FUNC_N: /* N->N+1 (N>1) */
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>1) transition sequence.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
+
release_probes(old);
return 0;
}
@@ -271,25 +401,91 @@ static int tracepoint_remove_func(struct tracepoint *tp,
tp_funcs = rcu_dereference_protected(tp->funcs,
lockdep_is_held(&tracepoints_mutex));
old = func_remove(&tp_funcs, func);
- if (IS_ERR(old)) {
- WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
+ if (WARN_ON_ONCE(IS_ERR(old)))
return PTR_ERR(old);
- }
- if (!tp_funcs) {
+ if (tp_funcs == old)
+ /* Failed allocating new tp_funcs, replaced func with stub */
+ return 0;
+
+ switch (nr_func_state(tp_funcs)) {
+ case TP_FUNC_0: /* 1->0 */
/* Removed last function */
if (tp->unregfunc && static_key_enabled(&tp->key))
tp->unregfunc();
- if (static_key_enabled(&tp->key))
- static_key_slow_dec(&tp->key);
+ static_key_disable(&tp->key);
+ /* Set iterator static call */
+ tracepoint_update_call(tp, tp_funcs);
+ /* Both iterator and static call handle NULL tp->funcs */
+ rcu_assign_pointer(tp->funcs, NULL);
+ /*
+ * Make sure new static func never uses old data after a
+ * 1->0->1 transition sequence.
+ */
+ tp_rcu_get_state(TP_TRANSITION_SYNC_1_0_1);
+ break;
+ case TP_FUNC_1: /* 2->1 */
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>2) transition sequence. If the first
+ * element's data has changed, then force the synchronization
+ * to prevent current readers that have loaded the old data
+ * from calling the new function.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ tp_rcu_cond_sync(TP_TRANSITION_SYNC_N_2_1);
+ /* Set static call to first function */
+ tracepoint_update_call(tp, tp_funcs);
+ break;
+ case TP_FUNC_2: /* N->N-1 (N>2) */
+ fallthrough;
+ case TP_FUNC_N:
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>2) transition sequence.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
}
- rcu_assign_pointer(tp->funcs, tp_funcs);
release_probes(old);
return 0;
}
/**
+ * tracepoint_probe_register_prio_may_exist - Connect a probe to a tracepoint with priority
+ * @tp: tracepoint
+ * @probe: probe handler
+ * @data: tracepoint data
+ * @prio: priority of this function over other registered functions
+ *
+ * Same as tracepoint_probe_register_prio() except that it will not warn
+ * if the tracepoint is already registered.
+ */
+int tracepoint_probe_register_prio_may_exist(struct tracepoint *tp, void *probe,
+ void *data, int prio)
+{
+ struct tracepoint_func tp_func;
+ int ret;
+
+ mutex_lock(&tracepoints_mutex);
+ tp_func.func = probe;
+ tp_func.data = data;
+ tp_func.prio = prio;
+ ret = tracepoint_add_func(tp, &tp_func, prio, false);
+ mutex_unlock(&tracepoints_mutex);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_register_prio_may_exist);
+
+/**
* tracepoint_probe_register_prio - Connect a probe to a tracepoint with priority
* @tp: tracepoint
* @probe: probe handler
@@ -312,7 +508,7 @@ int tracepoint_probe_register_prio(struct tracepoint *tp, void *probe,
tp_func.func = probe;
tp_func.data = data;
tp_func.prio = prio;
- ret = tracepoint_add_func(tp, &tp_func, prio);
+ ret = tracepoint_add_func(tp, &tp_func, prio, true);
mutex_unlock(&tracepoints_mutex);
return ret;
}
@@ -375,13 +571,14 @@ static void for_each_tracepoint_range(
bool trace_module_has_bad_taint(struct module *mod)
{
return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) |
- (1 << TAINT_UNSIGNED_MODULE));
+ (1 << TAINT_UNSIGNED_MODULE) |
+ (1 << TAINT_TEST));
}
static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list);
/**
- * register_tracepoint_notifier - register tracepoint coming/going notifier
+ * register_tracepoint_module_notifier - register tracepoint coming/going notifier
* @nb: notifier block
*
* Notifiers registered with this function are called on module
@@ -407,7 +604,7 @@ end:
EXPORT_SYMBOL_GPL(register_tracepoint_module_notifier);
/**
- * unregister_tracepoint_notifier - unregister tracepoint coming/going notifier
+ * unregister_tracepoint_module_notifier - unregister tracepoint coming/going notifier
* @nb: notifier block
*
* The notifier block callback should expect a "struct tp_module" data
@@ -443,7 +640,6 @@ static void tp_module_going_check_quiescent(struct tracepoint *tp, void *priv)
static int tracepoint_module_coming(struct module *mod)
{
struct tp_module *tp_mod;
- int ret = 0;
if (!mod->num_tracepoints)
return 0;
@@ -451,23 +647,22 @@ static int tracepoint_module_coming(struct module *mod)
/*
* We skip modules that taint the kernel, especially those with different
* module headers (for forced load), to make sure we don't cause a crash.
- * Staging, out-of-tree, and unsigned GPL modules are fine.
+ * Staging, out-of-tree, unsigned GPL, and test modules are fine.
*/
if (trace_module_has_bad_taint(mod))
return 0;
- mutex_lock(&tracepoint_module_list_mutex);
+
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
- if (!tp_mod) {
- ret = -ENOMEM;
- goto end;
- }
+ if (!tp_mod)
+ return -ENOMEM;
tp_mod->mod = mod;
+
+ mutex_lock(&tracepoint_module_list_mutex);
list_add_tail(&tp_mod->list, &tracepoint_module_list);
blocking_notifier_call_chain(&tracepoint_notify_list,
MODULE_STATE_COMING, tp_mod);
-end:
mutex_unlock(&tracepoint_module_list_mutex);
- return ret;
+ return 0;
}
static void tracepoint_module_going(struct module *mod)
@@ -521,7 +716,7 @@ static int tracepoint_module_notify(struct notifier_block *self,
case MODULE_STATE_UNFORMED:
break;
}
- return ret;
+ return notifier_from_errno(ret);
}
static struct notifier_block tracepoint_module_nb = {
@@ -567,7 +762,7 @@ int syscall_regfunc(void)
if (!sys_tracepoint_refcount) {
read_lock(&tasklist_lock);
for_each_process_thread(p, t) {
- set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+ set_task_syscall_work(t, SYSCALL_TRACEPOINT);
}
read_unlock(&tasklist_lock);
}
@@ -584,7 +779,7 @@ void syscall_unregfunc(void)
if (!sys_tracepoint_refcount) {
read_lock(&tasklist_lock);
for_each_process_thread(p, t) {
- clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+ clear_task_syscall_work(t, SYSCALL_TRACEPOINT);
}
read_unlock(&tasklist_lock);
}