Merge tag 'probes-v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull probes updates from Masami Hiramatsu:

 - uprobes: make trace_uprobe->nhit counter a per-CPU one

   This makes uprobe event's hit counter per-CPU for improving
   scalability on multi-core environment

 - kprobes: Remove obsoleted declaration for init_test_probes

   Remove unused init_test_probes() from header

 - Raw tracepoint probe supports raw tracepoint events on modules:
     - add a function for iterating over all tracepoints in all modules
     - add a function for iterating over tracepoints in a module
     - support raw tracepoint events on modules
     - support raw tracepoints on future loaded modules
     - add a test for tracepoint events on modules"

* tag 'probes-v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  sefltests/tracing: Add a test for tracepoint events on modules
  tracing/fprobe: Support raw tracepoints on future loaded modules
  tracing/fprobe: Support raw tracepoint events on modules
  tracepoint: Support iterating tracepoints in a loading module
  tracepoint: Support iterating over tracepoints on modules
  kprobes: Remove obsoleted declaration for init_test_probes
  uprobes: turn trace_uprobe's nhit counter to be per-CPU one

2 files changed, 151 insertions, 52 deletions

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 62e6a8f4aae9..a079abd8955b 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -21,6 +21,7 @@
 #define FPROBE_EVENT_SYSTEM "fprobes"
 #define TRACEPOINT_EVENT_SYSTEM "tracepoints"
 #define RETHOOK_MAXACTIVE_MAX 4096
+#define TRACEPOINT_STUB ERR_PTR(-ENOENT)
 
 static int trace_fprobe_create(const char *raw_command);
 static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev);
@@ -385,6 +386,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 					       const char *event,
 					       const char *symbol,
 					       struct tracepoint *tpoint,
+					       struct module *mod,
 					       int maxactive,
 					       int nargs, bool is_return)
 {
@@ -405,6 +407,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 		tf->fp.entry_handler = fentry_dispatcher;
 
 	tf->tpoint = tpoint;
+	tf->mod = mod;
 	tf->fp.nr_maxactive = maxactive;
 
 	ret = trace_probe_init(&tf->tp, event, group, false, nargs);
@@ -672,6 +675,24 @@ static int unregister_fprobe_event(struct trace_fprobe *tf)
 	return trace_probe_unregister_event_call(&tf->tp);
 }
 
+static int __regsiter_tracepoint_fprobe(struct trace_fprobe *tf)
+{
+	struct tracepoint *tpoint = tf->tpoint;
+	unsigned long ip = (unsigned long)tpoint->probestub;
+	int ret;
+
+	/*
+	 * Here, we do 2 steps to enable fprobe on a tracepoint.
+	 * At first, put __probestub_##TP function on the tracepoint
+	 * and put a fprobe on the stub function.
+	 */
+	ret = tracepoint_probe_register_prio_may_exist(tpoint,
+				tpoint->probestub, NULL, 0);
+	if (ret < 0)
+		return ret;
+	return register_fprobe_ips(&tf->fp, &ip, 1);
+}
+
 /* Internal register function - just handle fprobe and flags */
 static int __register_trace_fprobe(struct trace_fprobe *tf)
 {
@@ -698,18 +719,12 @@ static int __register_trace_fprobe(struct trace_fprobe *tf)
 		tf->fp.flags |= FPROBE_FL_DISABLED;
 
 	if (trace_fprobe_is_tracepoint(tf)) {
-		struct tracepoint *tpoint = tf->tpoint;
-		unsigned long ip = (unsigned long)tpoint->probestub;
-		/*
-		 * Here, we do 2 steps to enable fprobe on a tracepoint.
-		 * At first, put __probestub_##TP function on the tracepoint
-		 * and put a fprobe on the stub function.
-		 */
-		ret = tracepoint_probe_register_prio_may_exist(tpoint,
-					tpoint->probestub, NULL, 0);
-		if (ret < 0)
-			return ret;
-		return register_fprobe_ips(&tf->fp, &ip, 1);
+
+		/* This tracepoint is not loaded yet */
+		if (tf->tpoint == TRACEPOINT_STUB)
+			return 0;
+
+		return __regsiter_tracepoint_fprobe(tf);
 	}
 
 	/* TODO: handle filter, nofilter or symbol list */
@@ -862,20 +877,106 @@ end:
 	return ret;
 }
 
+struct __find_tracepoint_cb_data {
+	const char *tp_name;
+	struct tracepoint *tpoint;
+	struct module *mod;
+};
+
+static void __find_tracepoint_module_cb(struct tracepoint *tp, struct module *mod, void *priv)
+{
+	struct __find_tracepoint_cb_data *data = priv;
+
+	if (!data->tpoint && !strcmp(data->tp_name, tp->name)) {
+		data->tpoint = tp;
+		if (!data->mod) {
+			data->mod = mod;
+			if (!try_module_get(data->mod)) {
+				data->tpoint = NULL;
+				data->mod = NULL;
+			}
+		}
+	}
+}
+
+static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
+{
+	struct __find_tracepoint_cb_data *data = priv;
+
+	if (!data->tpoint && !strcmp(data->tp_name, tp->name))
+		data->tpoint = tp;
+}
+
+/*
+ * Find a tracepoint from kernel and module. If the tracepoint is in a module,
+ * this increments the module refcount to prevent unloading until the
+ * trace_fprobe is registered to the list. After registering the trace_fprobe
+ * on the trace_fprobe list, the module refcount is decremented because
+ * tracepoint_probe_module_cb will handle it.
+ */
+static struct tracepoint *find_tracepoint(const char *tp_name,
+					  struct module **tp_mod)
+{
+	struct __find_tracepoint_cb_data data = {
+		.tp_name = tp_name,
+		.mod = NULL,
+	};
+
+	for_each_kernel_tracepoint(__find_tracepoint_cb, &data);
+
+	if (!data.tpoint && IS_ENABLED(CONFIG_MODULES)) {
+		for_each_module_tracepoint(__find_tracepoint_module_cb, &data);
+		*tp_mod = data.mod;
+	}
+
+	return data.tpoint;
+}
+
 #ifdef CONFIG_MODULES
+static void reenable_trace_fprobe(struct trace_fprobe *tf)
+{
+	struct trace_probe *tp = &tf->tp;
+
+	list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
+		__enable_trace_fprobe(tf);
+	}
+}
+
+static struct tracepoint *find_tracepoint_in_module(struct module *mod,
+						    const char *tp_name)
+{
+	struct __find_tracepoint_cb_data data = {
+		.tp_name = tp_name,
+		.mod = mod,
+	};
+
+	for_each_tracepoint_in_module(mod, __find_tracepoint_module_cb, &data);
+	return data.tpoint;
+}
+
 static int __tracepoint_probe_module_cb(struct notifier_block *self,
 					unsigned long val, void *data)
 {
 	struct tp_module *tp_mod = data;
+	struct tracepoint *tpoint;
 	struct trace_fprobe *tf;
 	struct dyn_event *pos;
 
-	if (val != MODULE_STATE_GOING)
+	if (val != MODULE_STATE_GOING && val != MODULE_STATE_COMING)
 		return NOTIFY_DONE;
 
 	mutex_lock(&event_mutex);
 	for_each_trace_fprobe(tf, pos) {
-		if (tp_mod->mod == tf->mod) {
+		if (val == MODULE_STATE_COMING && tf->tpoint == TRACEPOINT_STUB) {
+			tpoint = find_tracepoint_in_module(tp_mod->mod, tf->symbol);
+			if (tpoint) {
+				tf->tpoint = tpoint;
+				tf->mod = tp_mod->mod;
+				if (!WARN_ON_ONCE(__regsiter_tracepoint_fprobe(tf)) &&
+				    trace_probe_is_enabled(&tf->tp))
+					reenable_trace_fprobe(tf);
+			}
+		} else if (val == MODULE_STATE_GOING && tp_mod->mod == tf->mod) {
 			tracepoint_probe_unregister(tf->tpoint,
 					tf->tpoint->probestub, NULL);
 			tf->tpoint = NULL;
@@ -892,30 +993,6 @@ static struct notifier_block tracepoint_module_nb = {
 };
 #endif /* CONFIG_MODULES */
 
-struct __find_tracepoint_cb_data {
-	const char *tp_name;
-	struct tracepoint *tpoint;
-};
-
-static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
-{
-	struct __find_tracepoint_cb_data *data = priv;
-
-	if (!data->tpoint && !strcmp(data->tp_name, tp->name))
-		data->tpoint = tp;
-}
-
-static struct tracepoint *find_tracepoint(const char *tp_name)
-{
-	struct __find_tracepoint_cb_data data = {
-		.tp_name = tp_name,
-	};
-
-	for_each_kernel_tracepoint(__find_tracepoint_cb, &data);
-
-	return data.tpoint;
-}
-
 static int parse_symbol_and_return(int argc, const char *argv[],
 				   char **symbol, bool *is_return,
 				   bool is_tracepoint)
@@ -996,6 +1073,7 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	char abuf[MAX_BTF_ARGS_LEN];
 	char *dbuf = NULL;
 	bool is_tracepoint = false;
+	struct module *tp_mod = NULL;
 	struct tracepoint *tpoint = NULL;
 	struct traceprobe_parse_context ctx = {
 		.flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE,
@@ -1080,15 +1158,20 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 
 	if (is_tracepoint) {
 		ctx.flags |= TPARG_FL_TPOINT;
-		tpoint = find_tracepoint(symbol);
-		if (!tpoint) {
+		tpoint = find_tracepoint(symbol, &tp_mod);
+		if (tpoint) {
+			ctx.funcname = kallsyms_lookup(
+				(unsigned long)tpoint->probestub,
+				NULL, NULL, NULL, sbuf);
+		} else if (IS_ENABLED(CONFIG_MODULES)) {
+				/* This *may* be loaded afterwards */
+				tpoint = TRACEPOINT_STUB;
+				ctx.funcname = symbol;
+		} else {
 			trace_probe_log_set_index(1);
 			trace_probe_log_err(0, NO_TRACEPOINT);
 			goto parse_error;
 		}
-		ctx.funcname = kallsyms_lookup(
-				(unsigned long)tpoint->probestub,
-				NULL, NULL, NULL, sbuf);
 	} else
 		ctx.funcname = symbol;
 
@@ -1110,8 +1193,8 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		goto out;
 
 	/* setup a probe */
-	tf = alloc_trace_fprobe(group, event, symbol, tpoint, maxactive,
-				argc, is_return);
+	tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod,
+				maxactive, argc, is_return);
 	if (IS_ERR(tf)) {
 		ret = PTR_ERR(tf);
 		/* This must return -ENOMEM, else there is a bug */
@@ -1119,10 +1202,6 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		goto out;	/* We know tf is not allocated */
 	}
 
-	if (is_tracepoint)
-		tf->mod = __module_text_address(
-				(unsigned long)tf->tpoint->probestub);
-
 	/* parse arguments */
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
 		trace_probe_log_set_index(i + 2);
@@ -1155,6 +1234,8 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	}
 
 out:
+	if (tp_mod)
+		module_put(tp_mod);
 	traceprobe_finish_parse(&ctx);
 	trace_probe_log_clear();
 	kfree(new_argv);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index f7443e996b1b..c40531d2cbad 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/rculist.h>
 #include <linux/filter.h>
+#include <linux/percpu.h>
 
 #include "trace_dynevent.h"
 #include "trace_probe.h"
@@ -62,7 +63,7 @@ struct trace_uprobe {
 	struct uprobe			*uprobe;
 	unsigned long			offset;
 	unsigned long			ref_ctr_offset;
-	unsigned long			nhit;
+	unsigned long __percpu		*nhits;
 	struct trace_probe		tp;
 };
 
@@ -337,6 +338,12 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	if (!tu)
 		return ERR_PTR(-ENOMEM);
 
+	tu->nhits = alloc_percpu(unsigned long);
+	if (!tu->nhits) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
 	ret = trace_probe_init(&tu->tp, event, group, true, nargs);
 	if (ret < 0)
 		goto error;
@@ -349,6 +356,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	return tu;
 
 error:
+	free_percpu(tu->nhits);
 	kfree(tu);
 
 	return ERR_PTR(ret);
@@ -362,6 +370,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
 	path_put(&tu->path);
 	trace_probe_cleanup(&tu->tp);
 	kfree(tu->filename);
+	free_percpu(tu->nhits);
 	kfree(tu);
 }
 
@@ -815,13 +824,21 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
 	struct dyn_event *ev = v;
 	struct trace_uprobe *tu;
+	unsigned long nhits;
+	int cpu;
 
 	if (!is_trace_uprobe(ev))
 		return 0;
 
 	tu = to_trace_uprobe(ev);
+
+	nhits = 0;
+	for_each_possible_cpu(cpu) {
+		nhits += per_cpu(*tu->nhits, cpu);
+	}
+
 	seq_printf(m, "  %s %-44s %15lu\n", tu->filename,
-			trace_probe_name(&tu->tp), tu->nhit);
+		   trace_probe_name(&tu->tp), nhits);
 	return 0;
 }
 
@@ -1508,7 +1525,8 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 	int ret = 0;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
-	tu->nhit++;
+
+	this_cpu_inc(*tu->nhits);
 
 	udd.tu = tu;
 	udd.bp_addr = instruction_pointer(regs);