Merge branch 'WIP.x86/asm' into x86/urgent, because the topic is ready

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 320 insertions, 52 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c0a9e310d715..01e6b3a38871 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -661,7 +661,41 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
+static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto_tp;
+	case BPF_FUNC_get_stackid:
+		return &bpf_get_stackid_proto_tp;
+	default:
+		return tracing_func_proto(func_id);
+	}
+}
+
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+				    struct bpf_insn_access_aux *info)
+{
+	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
+		return false;
+	if (type != BPF_READ)
+		return false;
+	if (off % size != 0)
+		return false;
+
+	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64));
+	return true;
+}
+
+const struct bpf_verifier_ops tracepoint_verifier_ops = {
+	.get_func_proto  = tp_prog_func_proto,
+	.is_valid_access = tp_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops tracepoint_prog_ops = {
+};
+
+BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx,
 	   struct bpf_perf_event_value *, buf, u32, size)
 {
 	int err = -EINVAL;
@@ -678,8 +712,8 @@ clear:
 	return err;
 }
 
-static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
-         .func           = bpf_perf_prog_read_value_tp,
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
+         .func           = bpf_perf_prog_read_value,
          .gpl_only       = true,
          .ret_type       = RET_INTEGER,
          .arg1_type      = ARG_PTR_TO_CTX,
@@ -687,7 +721,7 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
          .arg3_type      = ARG_CONST_SIZE,
 };
 
-static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
@@ -695,34 +729,12 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_tp;
 	case BPF_FUNC_perf_prog_read_value:
-		return &bpf_perf_prog_read_value_proto_tp;
+		return &bpf_perf_prog_read_value_proto;
 	default:
 		return tracing_func_proto(func_id);
 	}
 }
 
-static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
-				    struct bpf_insn_access_aux *info)
-{
-	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
-		return false;
-	if (type != BPF_READ)
-		return false;
-	if (off % size != 0)
-		return false;
-
-	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64));
-	return true;
-}
-
-const struct bpf_verifier_ops tracepoint_verifier_ops = {
-	.get_func_proto  = tp_prog_func_proto,
-	.is_valid_access = tp_prog_is_valid_access,
-};
-
-const struct bpf_prog_ops tracepoint_prog_ops = {
-};
-
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -779,7 +791,7 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 }
 
 const struct bpf_verifier_ops perf_event_verifier_ops = {
-	.get_func_proto		= tp_prog_func_proto,
+	.get_func_proto		= pe_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 55d6dff37daf..2c416509b834 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include "trace.h"
+#include "trace_probe.h"
 
 static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
 
@@ -237,6 +238,107 @@ void perf_trace_destroy(struct perf_event *p_event)
 	mutex_unlock(&event_mutex);
 }
 
+#ifdef CONFIG_KPROBE_EVENTS
+int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
+{
+	int ret;
+	char *func = NULL;
+	struct trace_event_call *tp_event;
+
+	if (p_event->attr.kprobe_func) {
+		func = kzalloc(KSYM_NAME_LEN, GFP_KERNEL);
+		if (!func)
+			return -ENOMEM;
+		ret = strncpy_from_user(
+			func, u64_to_user_ptr(p_event->attr.kprobe_func),
+			KSYM_NAME_LEN);
+		if (ret < 0)
+			goto out;
+
+		if (func[0] == '\0') {
+			kfree(func);
+			func = NULL;
+		}
+	}
+
+	tp_event = create_local_trace_kprobe(
+		func, (void *)(unsigned long)(p_event->attr.kprobe_addr),
+		p_event->attr.probe_offset, is_retprobe);
+	if (IS_ERR(tp_event)) {
+		ret = PTR_ERR(tp_event);
+		goto out;
+	}
+
+	ret = perf_trace_event_init(tp_event, p_event);
+	if (ret)
+		destroy_local_trace_kprobe(tp_event);
+out:
+	kfree(func);
+	return ret;
+}
+
+void perf_kprobe_destroy(struct perf_event *p_event)
+{
+	perf_trace_event_close(p_event);
+	perf_trace_event_unreg(p_event);
+
+	destroy_local_trace_kprobe(p_event->tp_event);
+}
+#endif /* CONFIG_KPROBE_EVENTS */
+
+#ifdef CONFIG_UPROBE_EVENTS
+int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe)
+{
+	int ret;
+	char *path = NULL;
+	struct trace_event_call *tp_event;
+
+	if (!p_event->attr.uprobe_path)
+		return -EINVAL;
+	path = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+	ret = strncpy_from_user(
+		path, u64_to_user_ptr(p_event->attr.uprobe_path), PATH_MAX);
+	if (ret < 0)
+		goto out;
+	if (path[0] == '\0') {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	tp_event = create_local_trace_uprobe(
+		path, p_event->attr.probe_offset, is_retprobe);
+	if (IS_ERR(tp_event)) {
+		ret = PTR_ERR(tp_event);
+		goto out;
+	}
+
+	/*
+	 * local trace_uprobe need to hold event_mutex to call
+	 * uprobe_buffer_enable() and uprobe_buffer_disable().
+	 * event_mutex is not required for local trace_kprobes.
+	 */
+	mutex_lock(&event_mutex);
+	ret = perf_trace_event_init(tp_event, p_event);
+	if (ret)
+		destroy_local_trace_uprobe(tp_event);
+	mutex_unlock(&event_mutex);
+out:
+	kfree(path);
+	return ret;
+}
+
+void perf_uprobe_destroy(struct perf_event *p_event)
+{
+	mutex_lock(&event_mutex);
+	perf_trace_event_close(p_event);
+	perf_trace_event_unreg(p_event);
+	mutex_unlock(&event_mutex);
+	destroy_local_trace_uprobe(p_event->tp_event);
+}
+#endif /* CONFIG_UPROBE_EVENTS */
+
 int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct trace_event_call *tp_event = p_event->tp_event;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1fad24acd444..1cd3fb4d70f8 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -462,6 +462,14 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 			disable_kprobe(&tk->rp.kp);
 		wait = 1;
 	}
+
+	/*
+	 * if tk is not added to any list, it must be a local trace_kprobe
+	 * created with perf_event_open. We don't need to wait for these
+	 * trace_kprobes
+	 */
+	if (list_empty(&tk->list))
+		wait = 0;
  out:
 	if (wait) {
 		/*
@@ -659,7 +667,7 @@ static int create_trace_kprobe(int argc, char **argv)
 	char *symbol = NULL, *event = NULL, *group = NULL;
 	int maxactive = 0;
 	char *arg;
-	unsigned long offset = 0;
+	long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
 
@@ -747,7 +755,7 @@ static int create_trace_kprobe(int argc, char **argv)
 		symbol = argv[1];
 		/* TODO: support .init module functions */
 		ret = traceprobe_split_symbol_offset(symbol, &offset);
-		if (ret) {
+		if (ret || offset < 0 || offset > UINT_MAX) {
 			pr_info("Failed to parse either an address or a symbol.\n");
 			return ret;
 		}
@@ -1358,12 +1366,9 @@ static struct trace_event_functions kprobe_funcs = {
 	.trace		= print_kprobe_event
 };
 
-static int register_kprobe_event(struct trace_kprobe *tk)
+static inline void init_trace_event_call(struct trace_kprobe *tk,
+					 struct trace_event_call *call)
 {
-	struct trace_event_call *call = &tk->tp.call;
-	int ret;
-
-	/* Initialize trace_event_call */
 	INIT_LIST_HEAD(&call->class->fields);
 	if (trace_kprobe_is_return(tk)) {
 		call->event.funcs = &kretprobe_funcs;
@@ -1372,6 +1377,19 @@ static int register_kprobe_event(struct trace_kprobe *tk)
 		call->event.funcs = &kprobe_funcs;
 		call->class->define_fields = kprobe_event_define_fields;
 	}
+
+	call->flags = TRACE_EVENT_FL_KPROBE;
+	call->class->reg = kprobe_register;
+	call->data = tk;
+}
+
+static int register_kprobe_event(struct trace_kprobe *tk)
+{
+	struct trace_event_call *call = &tk->tp.call;
+	int ret = 0;
+
+	init_trace_event_call(tk, call);
+
 	if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
 		return -ENOMEM;
 	ret = register_trace_event(&call->event);
@@ -1379,9 +1397,6 @@ static int register_kprobe_event(struct trace_kprobe *tk)
 		kfree(call->print_fmt);
 		return -ENODEV;
 	}
-	call->flags = TRACE_EVENT_FL_KPROBE;
-	call->class->reg = kprobe_register;
-	call->data = tk;
 	ret = trace_add_event_call(call);
 	if (ret) {
 		pr_info("Failed to register kprobe event: %s\n",
@@ -1403,6 +1418,66 @@ static int unregister_kprobe_event(struct trace_kprobe *tk)
 	return ret;
 }
 
+#ifdef CONFIG_PERF_EVENTS
+/* create a trace_kprobe, but don't add it to global lists */
+struct trace_event_call *
+create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
+			  bool is_return)
+{
+	struct trace_kprobe *tk;
+	int ret;
+	char *event;
+
+	/*
+	 * local trace_kprobes are not added to probe_list, so they are never
+	 * searched in find_trace_kprobe(). Therefore, there is no concern of
+	 * duplicated name here.
+	 */
+	event = func ? func : "DUMMY_EVENT";
+
+	tk = alloc_trace_kprobe(KPROBE_EVENT_SYSTEM, event, (void *)addr, func,
+				offs, 0 /* maxactive */, 0 /* nargs */,
+				is_return);
+
+	if (IS_ERR(tk)) {
+		pr_info("Failed to allocate trace_probe.(%d)\n",
+			(int)PTR_ERR(tk));
+		return ERR_CAST(tk);
+	}
+
+	init_trace_event_call(tk, &tk->tp.call);
+
+	if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = __register_trace_kprobe(tk);
+	if (ret < 0)
+		goto error;
+
+	return &tk->tp.call;
+error:
+	free_trace_kprobe(tk);
+	return ERR_PTR(ret);
+}
+
+void destroy_local_trace_kprobe(struct trace_event_call *event_call)
+{
+	struct trace_kprobe *tk;
+
+	tk = container_of(event_call, struct trace_kprobe, tp.call);
+
+	if (trace_probe_is_enabled(&tk->tp)) {
+		WARN_ON(1);
+		return;
+	}
+
+	__unregister_trace_kprobe(tk);
+	free_trace_kprobe(tk);
+}
+#endif /* CONFIG_PERF_EVENTS */
+
 /* Make a tracefs interface for controlling probe points */
 static __init int init_kprobe_trace(void)
 {
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index d59357308677..daf54bda4dc8 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -320,7 +320,7 @@ static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
 }
 
 /* Split symbol and offset. */
-int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
+int traceprobe_split_symbol_offset(char *symbol, long *offset)
 {
 	char *tmp;
 	int ret;
@@ -328,13 +328,11 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
 	if (!offset)
 		return -EINVAL;
 
-	tmp = strchr(symbol, '+');
+	tmp = strpbrk(symbol, "+-");
 	if (tmp) {
-		/* skip sign because kstrtoul doesn't accept '+' */
-		ret = kstrtoul(tmp + 1, 0, offset);
+		ret = kstrtol(tmp, 0, offset);
 		if (ret)
 			return ret;
-
 		*tmp = '\0';
 	} else
 		*offset = 0;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index e101c5bb9eda..75daff22ccea 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -365,7 +365,7 @@ extern int traceprobe_conflict_field_name(const char *name,
 extern void traceprobe_update_arg(struct probe_arg *arg);
 extern void traceprobe_free_probe_arg(struct probe_arg *arg);
 
-extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset);
+extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
 
 /* Sum up total data length for dynamic arraies (strings) */
 static nokprobe_inline int
@@ -416,3 +416,14 @@ store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs,
 }
 
 extern int set_print_fmt(struct trace_probe *tp, bool is_return);
+
+#ifdef CONFIG_PERF_EVENTS
+extern struct trace_event_call *
+create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
+			  bool is_return);
+extern void destroy_local_trace_kprobe(struct trace_event_call *event_call);
+
+extern struct trace_event_call *
+create_local_trace_uprobe(char *name, unsigned long offs, bool is_return);
+extern void destroy_local_trace_uprobe(struct trace_event_call *event_call);
+#endif
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 268029ae1be6..2014f4351ae0 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1292,16 +1292,25 @@ static struct trace_event_functions uprobe_funcs = {
 	.trace		= print_uprobe_event
 };
 
-static int register_uprobe_event(struct trace_uprobe *tu)
+static inline void init_trace_event_call(struct trace_uprobe *tu,
+					 struct trace_event_call *call)
 {
-	struct trace_event_call *call = &tu->tp.call;
-	int ret;
-
-	/* Initialize trace_event_call */
 	INIT_LIST_HEAD(&call->class->fields);
 	call->event.funcs = &uprobe_funcs;
 	call->class->define_fields = uprobe_event_define_fields;
 
+	call->flags = TRACE_EVENT_FL_UPROBE;
+	call->class->reg = trace_uprobe_register;
+	call->data = tu;
+}
+
+static int register_uprobe_event(struct trace_uprobe *tu)
+{
+	struct trace_event_call *call = &tu->tp.call;
+	int ret = 0;
+
+	init_trace_event_call(tu, call);
+
 	if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
 		return -ENOMEM;
 
@@ -1311,9 +1320,6 @@ static int register_uprobe_event(struct trace_uprobe *tu)
 		return -ENODEV;
 	}
 
-	call->flags = TRACE_EVENT_FL_UPROBE;
-	call->class->reg = trace_uprobe_register;
-	call->data = tu;
 	ret = trace_add_event_call(call);
 
 	if (ret) {
@@ -1339,6 +1345,70 @@ static int unregister_uprobe_event(struct trace_uprobe *tu)
 	return 0;
 }
 
+#ifdef CONFIG_PERF_EVENTS
+struct trace_event_call *
+create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
+{
+	struct trace_uprobe *tu;
+	struct inode *inode;
+	struct path path;
+	int ret;
+
+	ret = kern_path(name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	inode = igrab(d_inode(path.dentry));
+	path_put(&path);
+
+	if (!inode || !S_ISREG(inode->i_mode)) {
+		iput(inode);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * local trace_kprobes are not added to probe_list, so they are never
+	 * searched in find_trace_kprobe(). Therefore, there is no concern of
+	 * duplicated name "DUMMY_EVENT" here.
+	 */
+	tu = alloc_trace_uprobe(UPROBE_EVENT_SYSTEM, "DUMMY_EVENT", 0,
+				is_return);
+
+	if (IS_ERR(tu)) {
+		pr_info("Failed to allocate trace_uprobe.(%d)\n",
+			(int)PTR_ERR(tu));
+		return ERR_CAST(tu);
+	}
+
+	tu->offset = offs;
+	tu->inode = inode;
+	tu->filename = kstrdup(name, GFP_KERNEL);
+	init_trace_event_call(tu, &tu->tp.call);
+
+	if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	return &tu->tp.call;
+error:
+	free_trace_uprobe(tu);
+	return ERR_PTR(ret);
+}
+
+void destroy_local_trace_uprobe(struct trace_event_call *event_call)
+{
+	struct trace_uprobe *tu;
+
+	tu = container_of(event_call, struct trace_uprobe, tp.call);
+
+	kfree(tu->tp.call.print_fmt);
+	tu->tp.call.print_fmt = NULL;
+
+	free_trace_uprobe(tu);
+}
+#endif /* CONFIG_PERF_EVENTS */
+
 /* Make a trace interface for controling probe points */
 static __init int init_uprobe_trace(void)
 {