[for-next][PATCH 00/26] tracing: Updates for 5.10

[for-next][PATCH 00/26] tracing: Updates for 5.10

[Steven Rostedt]

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
for-next

Head SHA1: fd264ce96c382bc2e36eb1f49ac45c5980650244


Dan Carpenter (1):
      tracing: remove a pointless assignment

Davidlohr Bueso (1):
      fgraph: Convert ret_stack tasklist scanning to rcu

Jarkko Sakkinen (1):
      kprobes: Use module_name() macro

Masami Hiramatsu (19):
      tools/bootconfig: Show bootconfig compact tree from bootconfig file
      tools/bootconfig: Add list option
      tools/bootconfig: Make all functions static
      tools/bootconfig: Add a script to generate ftrace shell-command from bootconfig
      tools/bootconfig: Add a script to generates bootconfig from ftrace
      tools/bootconfig: Add --init option for bconf2ftrace.sh
      tracing/boot: Add per-instance tracing_on option support
      Documentation: tracing: Add tracing_on option to boot-time tracer
      tracing/kprobes: Support perf-style return probe
      tracing/uprobes: Support perf-style return probe
      Documentation: tracing: Add %return suffix description
      Documentation: tracing: boot: Add an example of tracing function-calls
      selftests/ftrace: Add %return suffix tests
      kprobes: Init kprobes in early_initcall
      tracing: Define event fields early stage
      tracing: Enable adding dynamic events early stage
      tracing: Enable creating new instance early boot
      tracing/boot, kprobe, synth: Initialize boot-time tracing earlier
      Documentation: tracing: Add the startup timing of boot-time tracing

Randy Dunlap (1):
      tracing: Delete repeated words in comments

Wei Yang (2):
      tracing: toplevel d_entry already initialized
      tracing: make tracing_init_dentry() returns an integer instead of a d_entry pointer

Xianting Tian (1):
      tracing: Use __this_cpu_read() in trace_buffered_event_enable()

----
 Documentation/trace/boottime-trace.rst             |  38 ++++
 Documentation/trace/kprobetrace.rst                |   2 +
 Documentation/trace/uprobetracer.rst               |   2 +
 MAINTAINERS                                        |   1 +
 kernel/kprobes.c                                   |   2 +-
 kernel/trace/fgraph.c                              |   8 +-
 kernel/trace/ftrace.c                              |   2 +-
 kernel/trace/trace.c                               |  98 ++++++---
 kernel/trace/trace.h                               |   9 +-
 kernel/trace/trace_boot.c                          |  17 +-
 kernel/trace/trace_dynevent.c                      |  10 +-
 kernel/trace/trace_events.c                        | 110 ++++++----
 kernel/trace/trace_events_synth.c                  |  30 ++-
 kernel/trace/trace_functions.c                     |  22 +-
 kernel/trace/trace_functions_graph.c               |   8 +-
 kernel/trace/trace_hwlat.c                         |   8 +-
 kernel/trace/trace_kprobe.c                        |  41 +++-
 kernel/trace/trace_printk.c                        |   8 +-
 kernel/trace/trace_probe.h                         |   1 +
 kernel/trace/trace_stack.c                         |  12 +-
 kernel/trace/trace_stat.c                          |   8 +-
 kernel/trace/trace_uprobe.c                        |  24 +-
 kernel/trace/tracing_map.c                         |   2 +-
 tools/bootconfig/main.c                            | 147 +++++++++----
 tools/bootconfig/scripts/bconf2ftrace.sh           | 199 +++++++++++++++++
 tools/bootconfig/scripts/ftrace.sh                 | 109 +++++++++
 tools/bootconfig/scripts/ftrace2bconf.sh           | 244 +++++++++++++++++++++
 tools/bootconfig/scripts/xbc.sh                    |  56 +++++
 .../ftrace/test.d/kprobe/kprobe_syntax_errors.tc   |   6 +
 .../test.d/kprobe/kretprobe_return_suffix.tc       |  21 ++
 .../ftrace/test.d/kprobe/uprobe_syntax_errors.tc   |   6 +
 31 files changed, 1055 insertions(+), 196 deletions(-)
 create mode 100755 tools/bootconfig/scripts/bconf2ftrace.sh
 create mode 100644 tools/bootconfig/scripts/ftrace.sh
 create mode 100755 tools/bootconfig/scripts/ftrace2bconf.sh
 create mode 100644 tools/bootconfig/scripts/xbc.sh
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc

[for-next][PATCH 01/26] tools/bootconfig: Show bootconfig compact tree from bootconfig file

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Show the bootconfig compact tree from the bootconfig file
instead of an initrd if the given file has no magic number
and is smaller than 32KB.

User can use this for checking the syntax error or output
checking before applying the bootconfig to initrd.

Link: https://lkml.kernel.org/r/159704848156.175360.6621139371000789360.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/bootconfig/main.c | 81 +++++++++++++++++++++++++++++------------
 1 file changed, 58 insertions(+), 23 deletions(-)

diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index e0878f5f74b1..d165e63b5d5a 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -195,10 +195,55 @@ int load_xbc_from_initrd(int fd, char **buf)
 	return size;
 }
 
+static void show_xbc_error(const char *data, const char *msg, int pos)
+{
+	int lin = 1, col, i;
+
+	if (pos < 0) {
+		pr_err("Error: %s.\n", msg);
+		return;
+	}
+
+	/* Note that pos starts from 0 but lin and col should start from 1. */
+	col = pos + 1;
+	for (i = 0; i < pos; i++) {
+		if (data[i] == '\n') {
+			lin++;
+			col = pos - i;
+		}
+	}
+	pr_err("Parse Error: %s at %d:%d\n", msg, lin, col);
+
+}
+
+static int init_xbc_with_error(char *buf, int len)
+{
+	char *copy = strdup(buf);
+	const char *msg;
+	int ret, pos;
+
+	if (!copy)
+		return -ENOMEM;
+
+	ret = xbc_init(buf, &msg, &pos);
+	if (ret < 0)
+		show_xbc_error(copy, msg, pos);
+	free(copy);
+
+	return ret;
+}
+
 int show_xbc(const char *path)
 {
 	int ret, fd;
 	char *buf = NULL;
+	struct stat st;
+
+	ret = stat(path, &st);
+	if (ret < 0) {
+		pr_err("Failed to stat %s: %d\n", path, -errno);
+		return -errno;
+	}
 
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
@@ -207,14 +252,24 @@ int show_xbc(const char *path)
 	}
 
 	ret = load_xbc_from_initrd(fd, &buf);
+	close(fd);
 	if (ret < 0) {
 		pr_err("Failed to load a boot config from initrd: %d\n", ret);
 		goto out;
 	}
+	/* Assume a bootconfig file if it is enough small */
+	if (ret == 0 && st.st_size <= XBC_DATA_MAX) {
+		ret = load_xbc_file(path, &buf);
+		if (ret < 0) {
+			pr_err("Failed to load a boot config: %d\n", ret);
+			goto out;
+		}
+		if (init_xbc_with_error(buf, ret) < 0)
+			goto out;
+	}
 	xbc_show_compact_tree();
 	ret = 0;
 out:
-	close(fd);
 	free(buf);
 
 	return ret;
@@ -251,27 +306,6 @@ int delete_xbc(const char *path)
 	return ret;
 }
 
-static void show_xbc_error(const char *data, const char *msg, int pos)
-{
-	int lin = 1, col, i;
-
-	if (pos < 0) {
-		pr_err("Error: %s.\n", msg);
-		return;
-	}
-
-	/* Note that pos starts from 0 but lin and col should start from 1. */
-	col = pos + 1;
-	for (i = 0; i < pos; i++) {
-		if (data[i] == '\n') {
-			lin++;
-			col = pos - i;
-		}
-	}
-	pr_err("Parse Error: %s at %d:%d\n", msg, lin, col);
-
-}
-
 int apply_xbc(const char *path, const char *xbc_path)
 {
 	u32 size, csum;
@@ -352,11 +386,12 @@ int apply_xbc(const char *path, const char *xbc_path)
 int usage(void)
 {
 	printf("Usage: bootconfig [OPTIONS] <INITRD>\n"
+		"Or     bootconfig <CONFIG>\n"
 		" Apply, delete or show boot config to initrd.\n"
 		" Options:\n"
 		"		-a <config>: Apply boot config to initrd\n"
 		"		-d : Delete boot config file from initrd\n\n"
-		" If no option is given, show current applied boot config.\n");
+		" If no option is given, show the bootconfig in the given file.\n");
 	return -1;
 }
 
-- 
2.28.0

[for-next][PATCH 02/26] tools/bootconfig: Add list option

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add list option (-l) to show the bootconfig in the list style.
This is same output of /proc/bootconfig. So users can check
how their bootconfig will be shown in procfs. This will help
them to write a user-space script to parse the /proc/bootconfig.

Link: https://lkml.kernel.org/r/159704849087.175360.8761890802048625207.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/bootconfig/main.c | 52 +++++++++++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 12 deletions(-)

diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index d165e63b5d5a..78025267df20 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -14,18 +14,19 @@
 #include <linux/kernel.h>
 #include <linux/bootconfig.h>
 
-static int xbc_show_value(struct xbc_node *node)
+static int xbc_show_value(struct xbc_node *node, bool semicolon)
 {
-	const char *val;
+	const char *val, *eol;
 	char q;
 	int i = 0;
 
+	eol = semicolon ? ";\n" : "\n";
 	xbc_array_for_each_value(node, val) {
 		if (strchr(val, '"'))
 			q = '\'';
 		else
 			q = '"';
-		printf("%c%s%c%s", q, val, q, node->next ? ", " : ";\n");
+		printf("%c%s%c%s", q, val, q, node->next ? ", " : eol);
 		i++;
 	}
 	return i;
@@ -53,7 +54,7 @@ static void xbc_show_compact_tree(void)
 			continue;
 		} else if (cnode && xbc_node_is_value(cnode)) {
 			printf("%s = ", xbc_node_get_data(node));
-			xbc_show_value(cnode);
+			xbc_show_value(cnode, true);
 		} else {
 			printf("%s;\n", xbc_node_get_data(node));
 		}
@@ -77,6 +78,26 @@ static void xbc_show_compact_tree(void)
 	}
 }
 
+static void xbc_show_list(void)
+{
+	char key[XBC_KEYLEN_MAX];
+	struct xbc_node *leaf;
+	const char *val;
+	int ret = 0;
+
+	xbc_for_each_key_value(leaf, val) {
+		ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX);
+		if (ret < 0)
+			break;
+		printf("%s = ", key);
+		if (!val || val[0] == '\0') {
+			printf("\"\"\n");
+			continue;
+		}
+		xbc_show_value(xbc_node_get_child(leaf), false);
+	}
+}
+
 /* Simple real checksum */
 int checksum(unsigned char *buf, int len)
 {
@@ -233,7 +254,7 @@ static int init_xbc_with_error(char *buf, int len)
 	return ret;
 }
 
-int show_xbc(const char *path)
+int show_xbc(const char *path, bool list)
 {
 	int ret, fd;
 	char *buf = NULL;
@@ -267,7 +288,10 @@ int show_xbc(const char *path)
 		if (init_xbc_with_error(buf, ret) < 0)
 			goto out;
 	}
-	xbc_show_compact_tree();
+	if (list)
+		xbc_show_list();
+	else
+		xbc_show_compact_tree();
 	ret = 0;
 out:
 	free(buf);
@@ -390,7 +414,8 @@ int usage(void)
 		" Apply, delete or show boot config to initrd.\n"
 		" Options:\n"
 		"		-a <config>: Apply boot config to initrd\n"
-		"		-d : Delete boot config file from initrd\n\n"
+		"		-d : Delete boot config file from initrd\n"
+		"		-l : list boot config in initrd or file\n\n"
 		" If no option is given, show the bootconfig in the given file.\n");
 	return -1;
 }
@@ -399,10 +424,10 @@ int main(int argc, char **argv)
 {
 	char *path = NULL;
 	char *apply = NULL;
-	bool delete = false;
+	bool delete = false, list = false;
 	int opt;
 
-	while ((opt = getopt(argc, argv, "hda:")) != -1) {
+	while ((opt = getopt(argc, argv, "hda:l")) != -1) {
 		switch (opt) {
 		case 'd':
 			delete = true;
@@ -410,14 +435,17 @@ int main(int argc, char **argv)
 		case 'a':
 			apply = optarg;
 			break;
+		case 'l':
+			list = true;
+			break;
 		case 'h':
 		default:
 			return usage();
 		}
 	}
 
-	if (apply && delete) {
-		pr_err("Error: You can not specify both -a and -d at once.\n");
+	if ((apply && delete) || (delete && list) || (apply && list)) {
+		pr_err("Error: You can give one of -a, -d or -l at once.\n");
 		return usage();
 	}
 
@@ -433,5 +461,5 @@ int main(int argc, char **argv)
 	else if (delete)
 		return delete_xbc(path);
 
-	return show_xbc(path);
+	return show_xbc(path, list);
 }
-- 
2.28.0

[for-next][PATCH 03/26] tools/bootconfig: Make all functions static

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Make all functions static except for main(). This is just a cleanup.

Link: https://lkml.kernel.org/r/159704850135.175360.12465608936326167517.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/bootconfig/main.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 78025267df20..eb92027817a7 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -99,7 +99,7 @@ static void xbc_show_list(void)
 }
 
 /* Simple real checksum */
-int checksum(unsigned char *buf, int len)
+static int checksum(unsigned char *buf, int len)
 {
 	int i, sum = 0;
 
@@ -111,7 +111,7 @@ int checksum(unsigned char *buf, int len)
 
 #define PAGE_SIZE	4096
 
-int load_xbc_fd(int fd, char **buf, int size)
+static int load_xbc_fd(int fd, char **buf, int size)
 {
 	int ret;
 
@@ -128,7 +128,7 @@ int load_xbc_fd(int fd, char **buf, int size)
 }
 
 /* Return the read size or -errno */
-int load_xbc_file(const char *path, char **buf)
+static int load_xbc_file(const char *path, char **buf)
 {
 	struct stat stat;
 	int fd, ret;
@@ -147,7 +147,7 @@ int load_xbc_file(const char *path, char **buf)
 	return ret;
 }
 
-int load_xbc_from_initrd(int fd, char **buf)
+static int load_xbc_from_initrd(int fd, char **buf)
 {
 	struct stat stat;
 	int ret;
@@ -254,7 +254,7 @@ static int init_xbc_with_error(char *buf, int len)
 	return ret;
 }
 
-int show_xbc(const char *path, bool list)
+static int show_xbc(const char *path, bool list)
 {
 	int ret, fd;
 	char *buf = NULL;
@@ -299,7 +299,7 @@ int show_xbc(const char *path, bool list)
 	return ret;
 }
 
-int delete_xbc(const char *path)
+static int delete_xbc(const char *path)
 {
 	struct stat stat;
 	int ret = 0, fd, size;
@@ -330,7 +330,7 @@ int delete_xbc(const char *path)
 	return ret;
 }
 
-int apply_xbc(const char *path, const char *xbc_path)
+static int apply_xbc(const char *path, const char *xbc_path)
 {
 	u32 size, csum;
 	char *buf, *data;
@@ -407,7 +407,7 @@ int apply_xbc(const char *path, const char *xbc_path)
 	return ret;
 }
 
-int usage(void)
+static int usage(void)
 {
 	printf("Usage: bootconfig [OPTIONS] <INITRD>\n"
 		"Or     bootconfig <CONFIG>\n"
-- 
2.28.0

[for-next][PATCH 04/26] tools/bootconfig: Add a script to generate ftrace shell-command from bootconfig

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add a bconf2ftrace.sh under tools/bootconfig/scripts which generates
a shell script to setup boot-time trace from bootconfig file for testing
the bootconfig.

bconf2ftrace.sh will take a bootconfig file (includes boot-time tracing)
and convert it into a shell-script which is almost same as the boot-time
tracer does.
If --apply option is given, it also tries to apply those command to the
running kernel, which requires the root privilege (or sudo).

For example, if you just want to confirm the shell commands, save
the output as below.

 # bconf2ftrace.sh ftrace.bconf > ftrace.sh

Or, you can apply it directly.

 # bconf2ftrace.sh --apply ftrace.bconf

Note that some boot-time tracing parameters under kernel.* are not able
to set via tracefs nor procfs (e.g. tp_printk, traceoff_on_warning.),
so those are ignored.

Link: https://lkml.kernel.org/r/159704851101.175360.15119132351139842345.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 MAINTAINERS                              |   1 +
 tools/bootconfig/scripts/bconf2ftrace.sh | 189 +++++++++++++++++++++++
 tools/bootconfig/scripts/xbc.sh          |  56 +++++++
 3 files changed, 246 insertions(+)
 create mode 100755 tools/bootconfig/scripts/bconf2ftrace.sh
 create mode 100644 tools/bootconfig/scripts/xbc.sh

diff --git a/MAINTAINERS b/MAINTAINERS
index 0d0862b19ce5..5bd82d7da40c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6601,6 +6601,7 @@ F:	fs/proc/bootconfig.c
 F:	include/linux/bootconfig.h
 F:	lib/bootconfig.c
 F:	tools/bootconfig/*
+F:	tools/bootconfig/scripts/*
 
 EXYNOS DP DRIVER
 M:	Jingoo Han <jingoohan1@gmail.com>
diff --git a/tools/bootconfig/scripts/bconf2ftrace.sh b/tools/bootconfig/scripts/bconf2ftrace.sh
new file mode 100755
index 000000000000..a46e984fb2ff
--- /dev/null
+++ b/tools/bootconfig/scripts/bconf2ftrace.sh
@@ -0,0 +1,189 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+usage() {
+	echo "Ftrace boottime trace test tool"
+	echo "Usage: $0 [--apply] [--debug] BOOTCONFIG-FILE"
+	echo "    --apply: Test actual apply to tracefs (need sudo)"
+	exit 1
+}
+
+[ $# -eq 0 ] && usage
+
+BCONF=
+DEBUG=
+APPLY=
+while [ x"$1" != x ]; do
+	case "$1" in
+	"--debug")
+		DEBUG=$1;;
+	"--apply")
+		APPLY=$1;;
+	*)
+		[ ! -f $1 ] && usage
+		BCONF=$1;;
+	esac
+	shift 1
+done
+
+if [ x"$APPLY" != x ]; then
+	if [ `id -u` -ne 0 ]; then
+		echo "This must be run by root user. Try sudo." 1>&2
+		exec sudo $0 $DEBUG $APPLY $BCONF
+	fi
+fi
+
+run_cmd() { # command
+	echo "$*"
+	if [ x"$APPLY" != x ]; then # apply command
+		eval $*
+	fi
+}
+
+if [ x"$DEBUG" != x ]; then
+	set -x
+fi
+
+TRACEFS=`grep -m 1 -w tracefs /proc/mounts | cut -f 2 -d " "`
+if [ -z "$TRACEFS" ]; then
+	if ! grep -wq debugfs /proc/mounts; then
+		echo "Error: No tracefs/debugfs was mounted." 1>&2
+		exit 1
+	fi
+	TRACEFS=`grep -m 1 -w debugfs /proc/mounts | cut -f 2 -d " "`/tracing
+	if [ ! -d $TRACEFS ]; then
+		echo "Error: ftrace is not enabled on this kernel." 1>&2
+		exit 1
+	fi
+fi
+
+. `dirname $0`/xbc.sh
+
+######## main #########
+set -e
+
+xbc_init $BCONF
+
+set_value_of() { # key file
+	if xbc_has_key $1; then
+		val=`xbc_get_val $1 1`
+		run_cmd "echo '$val' >> $2"
+	fi
+}
+
+set_array_of() { # key file
+	if xbc_has_key $1; then
+		xbc_get_val $1 | while read line; do
+			run_cmd "echo '$line' >> $2"
+		done
+	fi
+}
+
+compose_synth() { # event_name branch
+	echo -n "$1 "
+	xbc_get_val $2 | while read field; do echo -n "$field; "; done
+}
+
+setup_event() { # prefix group event [instance]
+	branch=$1.$2.$3
+	if [ "$4" ]; then
+		eventdir="$TRACEFS/instances/$4/events/$2/$3"
+	else
+		eventdir="$TRACEFS/events/$2/$3"
+	fi
+	case $2 in
+	kprobes)
+		xbc_get_val ${branch}.probes | while read line; do
+			run_cmd "echo 'p:kprobes/$3 $line' >> $TRACEFS/kprobe_events"
+		done
+		;;
+	synthetic)
+		run_cmd "echo '`compose_synth $3 ${branch}.fields`' >> $TRACEFS/synthetic_events"
+		;;
+	esac
+
+	set_value_of ${branch}.filter ${eventdir}/filter
+	set_array_of ${branch}.actions ${eventdir}/trigger
+
+	if xbc_has_key ${branch}.enable; then
+		run_cmd "echo 1 > ${eventdir}/enable"
+	fi
+}
+
+setup_events() { # prefix("ftrace" or "ftrace.instance.INSTANCE") [instance]
+	prefix="${1}.event"
+	if xbc_has_branch ${1}.event; then
+		for grpev in `xbc_subkeys ${1}.event 2`; do
+			setup_event $prefix ${grpev%.*} ${grpev#*.} $2
+		done
+	fi
+}
+
+size2kb() { # size[KB|MB]
+	case $1 in
+	*KB)
+		echo ${1%KB};;
+	*MB)
+		expr ${1%MB} \* 1024;;
+	*)
+		expr $1 / 1024 ;;
+	esac
+}
+
+setup_instance() { # [instance]
+	if [ "$1" ]; then
+		instance="ftrace.instance.${1}"
+		instancedir=$TRACEFS/instances/$1
+	else
+		instance="ftrace"
+		instancedir=$TRACEFS
+	fi
+
+	set_array_of ${instance}.options ${instancedir}/trace_options
+	set_value_of ${instance}.trace_clock ${instancedir}/trace_clock
+	set_value_of ${instance}.cpumask ${instancedir}/tracing_cpumask
+	set_value_of ${instance}.tracer ${instancedir}/current_tracer
+	set_array_of ${instance}.ftrace.filters \
+		${instancedir}/set_ftrace_filter
+	set_array_of ${instance}.ftrace.notrace \
+		${instancedir}/set_ftrace_notrace
+
+	if xbc_has_key ${instance}.alloc_snapshot; then
+		run_cmd "echo 1 > ${instancedir}/snapshot"
+	fi
+
+	if xbc_has_key ${instance}.buffer_size; then
+		size=`xbc_get_val ${instance}.buffer_size 1`
+		size=`eval size2kb $size`
+		run_cmd "echo $size >> ${instancedir}/buffer_size_kb"
+	fi
+
+	setup_events ${instance} $1
+	set_array_of ${instance}.events ${instancedir}/set_event
+}
+
+# ftrace global configs (kernel.*)
+if xbc_has_key "kernel.dump_on_oops"; then
+	dump_mode=`xbc_get_val "kernel.dump_on_oops" 1`
+	[ "$dump_mode" ] && dump_mode=`eval echo $dump_mode` || dump_mode=1
+	run_cmd "echo \"$dump_mode\" > /proc/sys/kernel/ftrace_dump_on_oops"
+fi
+
+set_value_of kernel.fgraph_max_depth $TRACEFS/max_graph_depth
+set_array_of kernel.fgraph_filters $TRACEFS/set_graph_function
+set_array_of kernel.fgraph_notraces $TRACEFS/set_graph_notrace
+
+# Per-instance/per-event configs
+if ! xbc_has_branch "ftrace" ; then
+	exit 0
+fi
+
+setup_instance # root instance
+
+if xbc_has_branch "ftrace.instance"; then
+	for i in `xbc_subkeys "ftrace.instance" 1`; do
+		run_cmd "mkdir -p $TRACEFS/instances/$i"
+		setup_instance $i
+	done
+fi
+
diff --git a/tools/bootconfig/scripts/xbc.sh b/tools/bootconfig/scripts/xbc.sh
new file mode 100644
index 000000000000..b8c84e654556
--- /dev/null
+++ b/tools/bootconfig/scripts/xbc.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+# bootconfig utility functions
+
+XBC_TMPFILE=
+XBC_BASEDIR=`dirname $0`
+BOOTCONFIG=${BOOTCONFIG:=$XBC_BASEDIR/../bootconfig}
+if [ ! -x "$BOOTCONFIG" ]; then
+	BOOTCONFIG=`which bootconfig`
+	if [ -z "$BOOTCONFIG" ]; then
+		echo "Erorr: bootconfig command is not found" 1>&2
+		exit 1
+	fi
+fi
+
+xbc_cleanup() {
+	if [ "$XBC_TMPFILE" ]; then
+		rm -f "$XBC_TMPFILE"
+	fi
+}
+
+xbc_init() { # bootconfig-file
+	xbc_cleanup
+	XBC_TMPFILE=`mktemp bconf-XXXX`
+	trap xbc_cleanup EXIT TERM
+
+	$BOOTCONFIG -l $1 > $XBC_TMPFILE || exit 1
+}
+
+nr_args() { # args
+	echo $#
+}
+
+xbc_get_val() { # key [maxnum]
+	if [ "$2" ]; then
+		MAXOPT="-L $2"
+	fi
+	grep "^$1 =" $XBC_TMPFILE | cut -d= -f2- | \
+		sed -e 's/", /" /g' -e "s/',/' /g" | \
+		xargs $MAXOPT -n 1 echo
+}
+
+xbc_has_key() { # key
+	grep -q "^$1 =" $XBC_TMPFILE
+}
+
+xbc_has_branch() { # prefix-key
+	grep -q "^$1" $XBC_TMPFILE
+}
+
+xbc_subkeys() { # prefix-key depth
+	__keys=`echo $1 | sed "s/\./ /g"`
+	__s=`nr_args $__keys`
+	grep "^$1" $XBC_TMPFILE | cut -d= -f1| cut -d. -f$((__s + 1))-$((__s + $2)) | uniq
+}
-- 
2.28.0

[for-next][PATCH 05/26] tools/bootconfig: Add a script to generates bootconfig from ftrace

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add a ftrace2bconf.sh under tools/bootconfig/scripts which generates
a bootconfig file from the current ftrace settings.

To read the ftrace settings, ftrace2bconf.sh requires the root
privilege (or sudo). The ftrace2bconf.sh will output the bootconfig
to stdout and error messages to stderr, so usually you'll run it as

 # ftrace2bconf.sh > ftrace.bconf

Note that some ftrace configurations are not supported. For example,
function-call/callgraph trace/notrace settings are not supported because
the wildcard has been expanded and lost in the ftrace anymore.

Link: https://lkml.kernel.org/r/159704852163.175360.16738029520293360558.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/bootconfig/scripts/ftrace2bconf.sh | 244 +++++++++++++++++++++++
 1 file changed, 244 insertions(+)
 create mode 100755 tools/bootconfig/scripts/ftrace2bconf.sh

diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh
new file mode 100755
index 000000000000..6c0d4b61e0c2
--- /dev/null
+++ b/tools/bootconfig/scripts/ftrace2bconf.sh
@@ -0,0 +1,244 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+usage() {
+	echo "Dump boot-time tracing bootconfig from ftrace"
+	echo "Usage: $0 [--debug] [ > BOOTCONFIG-FILE]"
+	exit 1
+}
+
+DEBUG=
+while [ x"$1" != x ]; do
+	case "$1" in
+	"--debug")
+		DEBUG=$1;;
+	-*)
+		usage
+		;;
+	esac
+	shift 1
+done
+
+if [ x"$DEBUG" != x ]; then
+	set -x
+fi
+
+TRACEFS=`grep -m 1 -w tracefs /proc/mounts | cut -f 2 -d " "`
+if [ -z "$TRACEFS" ]; then
+	if ! grep -wq debugfs /proc/mounts; then
+		echo "Error: No tracefs/debugfs was mounted."
+		exit 1
+	fi
+	TRACEFS=`grep -m 1 -w debugfs /proc/mounts | cut -f 2 -d " "`/tracing
+	if [ ! -d $TRACEFS ]; then
+		echo "Error: ftrace is not enabled on this kernel." 1>&2
+		exit 1
+	fi
+fi
+
+######## main #########
+
+set -e
+
+emit_kv() { # key =|+= value
+	echo "$@"
+}
+
+global_options() {
+	val=`cat $TRACEFS/max_graph_depth`
+	[ $val != 0 ] && emit_kv kernel.fgraph_max_depth = $val
+	if grep -qv "^#" $TRACEFS/set_graph_function $TRACEFS/set_graph_notrace ; then
+		cat 1>&2 << EOF
+# WARN: kernel.fgraph_filters and kernel.fgraph_notrace are not supported, since the wild card expression was expanded and lost from memory.
+EOF
+	fi
+}
+
+kprobe_event_options() {
+	cat $TRACEFS/kprobe_events | while read p args; do
+		case $p in
+		r*)
+		cat 1>&2 << EOF
+# WARN: A return probe found but it is not supported by bootconfig. Skip it.
+EOF
+		continue;;
+		esac
+		p=${p#*:}
+		event=${p#*/}
+		group=${p%/*}
+		if [ $group != "kprobes" ]; then
+			cat 1>&2 << EOF
+# WARN: kprobes group name $group is changed to "kprobes" for bootconfig.
+EOF
+		fi
+		emit_kv $PREFIX.event.kprobes.$event.probes += $args
+	done
+}
+
+synth_event_options() {
+	cat $TRACEFS/synthetic_events | while read event fields; do
+		emit_kv $PREFIX.event.synthetic.$event.fields = `echo $fields | sed "s/;/,/g"`
+	done
+}
+
+# Variables resolver
+DEFINED_VARS=
+UNRESOLVED_EVENTS=
+
+defined_vars() { # event-dir
+	grep "^hist" $1/trigger | grep -o ':[a-zA-Z0-9]*='
+}
+referred_vars() {
+	grep "^hist" $1/trigger | grep -o '$[a-zA-Z0-9]*'
+}
+
+per_event_options() { # event-dir
+	evdir=$1
+	# Check the special event which has no filter and no trigger
+	[ ! -f $evdir/filter ] && return
+
+	if grep -q "^hist:" $evdir/trigger; then
+		# hist action can refer the undefined variables
+		__vars=`defined_vars $evdir`
+		for v in `referred_vars $evdir`; do
+			if echo $DEFINED_VARS $__vars | grep -vqw ${v#$}; then
+				# $v is not defined yet, defer it
+				UNRESOLVED_EVENTS="$UNRESOLVED_EVENTS $evdir"
+				return;
+			fi
+		done
+		DEFINED_VARS="$DEFINED_VARS "`defined_vars $evdir`
+	fi
+	grep -v "^#" $evdir/trigger | while read action active; do
+		emit_kv $PREFIX.event.$group.$event.actions += \'$action\'
+	done
+
+	# enable is not checked; this is done by set_event in the instance.
+	val=`cat $evdir/filter`
+	if [ "$val" != "none" ]; then
+		emit_kv $PREFIX.event.$group.$event.filter = "$val"
+	fi
+}
+
+retry_unresolved() {
+	unresolved=$UNRESOLVED_EVENTS
+	UNRESOLVED_EVENTS=
+	for evdir in $unresolved; do
+		event=${evdir##*/}
+		group=${evdir%/*}; group=${group##*/}
+		per_event_options $evdir
+	done
+}
+
+event_options() {
+	# PREFIX and INSTANCE must be set
+	if [ $PREFIX = "ftrace" ]; then
+		# define the dynamic events
+		kprobe_event_options
+		synth_event_options
+	fi
+	for group in `ls $INSTANCE/events/` ; do
+		[ ! -d $INSTANCE/events/$group ] && continue
+		for event in `ls $INSTANCE/events/$group/` ;do
+			[ ! -d $INSTANCE/events/$group/$event ] && continue
+			per_event_options $INSTANCE/events/$group/$event
+		done
+	done
+	retry=0
+	while [ $retry -lt 3 ]; do
+		retry_unresolved
+		retry=$((retry + 1))
+	done
+	if [ "$UNRESOLVED_EVENTS" ]; then
+		cat 1>&2 << EOF
+! ERROR: hist triggers in $UNRESOLVED_EVENTS use some undefined variables.
+EOF
+	fi
+}
+
+is_default_trace_option() { # option
+grep -qw $1 << EOF
+print-parent
+nosym-offset
+nosym-addr
+noverbose
+noraw
+nohex
+nobin
+noblock
+trace_printk
+annotate
+nouserstacktrace
+nosym-userobj
+noprintk-msg-only
+context-info
+nolatency-format
+record-cmd
+norecord-tgid
+overwrite
+nodisable_on_free
+irq-info
+markers
+noevent-fork
+nopause-on-trace
+function-trace
+nofunction-fork
+nodisplay-graph
+nostacktrace
+notest_nop_accept
+notest_nop_refuse
+EOF
+}
+
+instance_options() { # [instance-name]
+	if [ $# -eq 0 ]; then
+		PREFIX="ftrace"
+		INSTANCE=$TRACEFS
+	else
+		PREFIX="ftrace.instance.$1"
+		INSTANCE=$TRACEFS/instances/$1
+	fi
+	val=
+	for i in `cat $INSTANCE/trace_options`; do
+		is_default_trace_option $i && continue
+		val="$val, $i"
+	done
+	[ "$val" ] && emit_kv $PREFIX.options = "${val#,}"
+	val="local"
+	for i in `cat $INSTANCE/trace_clock` ; do
+		[ "${i#*]}" ] && continue
+		i=${i%]}; val=${i#[}
+	done
+	[ $val != "local" ] && emit_kv $PREFIX.trace_clock = $val
+	val=`cat $INSTANCE/buffer_size_kb`
+	if echo $val | grep -vq "expanded" ; then
+		emit_kv $PREFIX.buffer_size = $val"KB"
+	fi
+	if grep -q "is allocated" $INSTANCE/snapshot ; then
+		emit_kv $PREFIX.alloc_snapshot
+	fi
+	val=`cat $INSTANCE/tracing_cpumask`
+	if [ `echo $val | sed -e s/f//g`x != x ]; then
+		emit_kv $PREFIX.cpumask = $val
+	fi
+
+	val=
+	for i in `cat $INSTANCE/set_event`; do
+		val="$val, $i"
+	done
+	[ "$val" ] && emit_kv $PREFIX.events = "${val#,}"
+	val=`cat $INSTANCE/current_tracer`
+	[ $val != nop ] && emit_kv $PREFIX.tracer = $val
+	if grep -qv "^#" $INSTANCE/set_ftrace_filter $INSTANCE/set_ftrace_notrace; then
+		cat 1>&2 << EOF
+# WARN: kernel.ftrace.filters and kernel.ftrace.notrace are not supported, since the wild card expression was expanded and lost from memory.
+EOF
+	fi
+	event_options
+}
+
+global_options
+instance_options
+for i in `ls $TRACEFS/instances` ; do
+	instance_options $i
+done
-- 
2.28.0

[for-next][PATCH 06/26] tools/bootconfig: Add --init option for bconf2ftrace.sh

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Since the ftrace current setting may conflict with the new setting
from bootconfig, add the --init option to initialize ftrace before
setting for bconf2ftrace.sh.

E.g.
 $ bconf2ftrace.sh --init boottrace.bconf

This initialization method copied from selftests/ftrace.

Link: https://lkml.kernel.org/r/159704853203.175360.17029578033994278231.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/bootconfig/scripts/bconf2ftrace.sh |  12 ++-
 tools/bootconfig/scripts/ftrace.sh       | 109 +++++++++++++++++++++++
 2 files changed, 120 insertions(+), 1 deletion(-)
 create mode 100644 tools/bootconfig/scripts/ftrace.sh

diff --git a/tools/bootconfig/scripts/bconf2ftrace.sh b/tools/bootconfig/scripts/bconf2ftrace.sh
index a46e984fb2ff..595e164dc352 100755
--- a/tools/bootconfig/scripts/bconf2ftrace.sh
+++ b/tools/bootconfig/scripts/bconf2ftrace.sh
@@ -3,8 +3,9 @@
 
 usage() {
 	echo "Ftrace boottime trace test tool"
-	echo "Usage: $0 [--apply] [--debug] BOOTCONFIG-FILE"
+	echo "Usage: $0 [--apply|--init] [--debug] BOOTCONFIG-FILE"
 	echo "    --apply: Test actual apply to tracefs (need sudo)"
+	echo "    --init:  Initialize ftrace before applying (imply --apply)"
 	exit 1
 }
 
@@ -13,12 +14,16 @@ usage() {
 BCONF=
 DEBUG=
 APPLY=
+INIT=
 while [ x"$1" != x ]; do
 	case "$1" in
 	"--debug")
 		DEBUG=$1;;
 	"--apply")
 		APPLY=$1;;
+	"--init")
+		APPLY=$1
+		INIT=$1;;
 	*)
 		[ ! -f $1 ] && usage
 		BCONF=$1;;
@@ -57,6 +62,11 @@ if [ -z "$TRACEFS" ]; then
 	fi
 fi
 
+if [ x"$INIT" != x ]; then
+	. `dirname $0`/ftrace.sh
+	(cd $TRACEFS; initialize_ftrace)
+fi
+
 . `dirname $0`/xbc.sh
 
 ######## main #########
diff --git a/tools/bootconfig/scripts/ftrace.sh b/tools/bootconfig/scripts/ftrace.sh
new file mode 100644
index 000000000000..186eed923041
--- /dev/null
+++ b/tools/bootconfig/scripts/ftrace.sh
@@ -0,0 +1,109 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+clear_trace() { # reset trace output
+    echo > trace
+}
+
+disable_tracing() { # stop trace recording
+    echo 0 > tracing_on
+}
+
+enable_tracing() { # start trace recording
+    echo 1 > tracing_on
+}
+
+reset_tracer() { # reset the current tracer
+    echo nop > current_tracer
+}
+
+reset_trigger_file() {
+    # remove action triggers first
+    grep -H ':on[^:]*(' $@ |
+    while read line; do
+        cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["`
+	file=`echo $line | cut -f1 -d:`
+	echo "!$cmd" >> $file
+    done
+    grep -Hv ^# $@ |
+    while read line; do
+        cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["`
+	file=`echo $line | cut -f1 -d:`
+	echo "!$cmd" > $file
+    done
+}
+
+reset_trigger() { # reset all current setting triggers
+    if [ -d events/synthetic ]; then
+        reset_trigger_file events/synthetic/*/trigger
+    fi
+    reset_trigger_file events/*/*/trigger
+}
+
+reset_events_filter() { # reset all current setting filters
+    grep -v ^none events/*/*/filter |
+    while read line; do
+	echo 0 > `echo $line | cut -f1 -d:`
+    done
+}
+
+reset_ftrace_filter() { # reset all triggers in set_ftrace_filter
+    if [ ! -f set_ftrace_filter ]; then
+      return 0
+    fi
+    echo > set_ftrace_filter
+    grep -v '^#' set_ftrace_filter | while read t; do
+	tr=`echo $t | cut -d: -f2`
+	if [ "$tr" = "" ]; then
+	    continue
+	fi
+	if ! grep -q "$t" set_ftrace_filter; then
+		continue;
+	fi
+	name=`echo $t | cut -d: -f1 | cut -d' ' -f1`
+	if [ $tr = "enable_event" -o $tr = "disable_event" ]; then
+	    tr=`echo $t | cut -d: -f2-4`
+	    limit=`echo $t | cut -d: -f5`
+	else
+	    tr=`echo $t | cut -d: -f2`
+	    limit=`echo $t | cut -d: -f3`
+	fi
+	if [ "$limit" != "unlimited" ]; then
+	    tr="$tr:$limit"
+	fi
+	echo "!$name:$tr" > set_ftrace_filter
+    done
+}
+
+disable_events() {
+    echo 0 > events/enable
+}
+
+clear_synthetic_events() { # reset all current synthetic events
+    grep -v ^# synthetic_events |
+    while read line; do
+        echo "!$line" >> synthetic_events
+    done
+}
+
+initialize_ftrace() { # Reset ftrace to initial-state
+# As the initial state, ftrace will be set to nop tracer,
+# no events, no triggers, no filters, no function filters,
+# no probes, and tracing on.
+    disable_tracing
+    reset_tracer
+    reset_trigger
+    reset_events_filter
+    reset_ftrace_filter
+    disable_events
+    [ -f set_event_pid ] && echo > set_event_pid
+    [ -f set_ftrace_pid ] && echo > set_ftrace_pid
+    [ -f set_ftrace_notrace ] && echo > set_ftrace_notrace
+    [ -f set_graph_function ] && echo | tee set_graph_*
+    [ -f stack_trace_filter ] && echo > stack_trace_filter
+    [ -f kprobe_events ] && echo > kprobe_events
+    [ -f uprobe_events ] && echo > uprobe_events
+    [ -f synthetic_events ] && echo > synthetic_events
+    [ -f snapshot ] && echo 0 > snapshot
+    clear_trace
+    enable_tracing
+}
-- 
2.28.0

[for-next][PATCH 07/26] tracing: toplevel d_entry already initialized

[Steven Rostedt]

From: Wei Yang <richard.weiyang@linux.alibaba.com>

Currently we have following call flow:

    tracer_init_tracefs()
        tracing_init_dentry()
        event_trace_init()
            tracing_init_dentry()

This shows tracing_init_dentry() is called twice in this flow and this
is not necessary.

Let's remove the second one when it is for sure be properly initialized.

Link: https://lkml.kernel.org/r/20200712011036.70948-4-richard.weiyang@linux.alibaba.com

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index a85effb2373b..ee25d849ebba 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3434,7 +3434,6 @@ early_initcall(event_trace_enable_again);
 __init int event_trace_init(void)
 {
 	struct trace_array *tr;
-	struct dentry *d_tracer;
 	struct dentry *entry;
 	int ret;
 
@@ -3442,11 +3441,7 @@ __init int event_trace_init(void)
 	if (!tr)
 		return -ENODEV;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
-		return 0;
-
-	entry = tracefs_create_file("available_events", 0444, d_tracer,
+	entry = tracefs_create_file("available_events", 0444, NULL,
 				    tr, &ftrace_avail_fops);
 	if (!entry)
 		pr_warn("Could not create tracefs 'available_events' entry\n");
@@ -3457,7 +3452,7 @@ __init int event_trace_init(void)
 	if (trace_define_common_fields())
 		pr_warn("tracing: Failed to allocate common fields");
 
-	ret = early_event_add_tracer(d_tracer, tr);
+	ret = early_event_add_tracer(NULL, tr);
 	if (ret)
 		return ret;
 
-- 
2.28.0

[for-next][PATCH 08/26] tracing: make tracing_init_dentry() returns an integer instead of a d_entry pointer

[Steven Rostedt]

From: Wei Yang <richard.weiyang@linux.alibaba.com>

Current tracing_init_dentry() return a d_entry pointer, while is not
necessary. This function returns NULL on success or error on failure,
which means there is no valid d_entry pointer return.

Let's return 0 on success and negative value for error.

Link: https://lkml.kernel.org/r/20200712011036.70948-5-richard.weiyang@linux.alibaba.com

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c                 | 36 ++++++++++++++--------------
 kernel/trace/trace.h                 |  2 +-
 kernel/trace/trace_dynevent.c        |  8 +++----
 kernel/trace/trace_events_synth.c    |  9 +++----
 kernel/trace/trace_functions_graph.c |  8 +++----
 kernel/trace/trace_hwlat.c           |  8 +++----
 kernel/trace/trace_kprobe.c          | 10 ++++----
 kernel/trace/trace_printk.c          |  8 +++----
 kernel/trace/trace_stack.c           | 12 +++++-----
 kernel/trace/trace_stat.c            |  8 +++----
 kernel/trace/trace_uprobe.c          |  9 ++++---
 11 files changed, 57 insertions(+), 61 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2a7c26345e83..29a9034b38d0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8971,21 +8971,21 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
  * directory. It is called via fs_initcall() by any of the boot up code
  * and expects to return the dentry of the top level tracing directory.
  */
-struct dentry *tracing_init_dentry(void)
+int tracing_init_dentry(void)
 {
 	struct trace_array *tr = &global_trace;
 
 	if (security_locked_down(LOCKDOWN_TRACEFS)) {
 		pr_warn("Tracing disabled due to lockdown\n");
-		return ERR_PTR(-EPERM);
+		return -EPERM;
 	}
 
 	/* The top level trace array uses  NULL as parent */
 	if (tr->dir)
-		return NULL;
+		return 0;
 
 	if (WARN_ON(!tracefs_initialized()))
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	/*
 	 * As there may still be users that expect the tracing
@@ -8996,7 +8996,7 @@ struct dentry *tracing_init_dentry(void)
 	tr->dir = debugfs_create_automount("tracing", NULL,
 					   trace_automount, NULL);
 
-	return NULL;
+	return 0;
 }
 
 extern struct trace_eval_map *__start_ftrace_eval_maps[];
@@ -9083,48 +9083,48 @@ static struct notifier_block trace_module_nb = {
 
 static __init int tracer_init_tracefs(void)
 {
-	struct dentry *d_tracer;
+	int ret;
 
 	trace_access_lock_init();
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return 0;
 
 	event_trace_init();
 
-	init_tracer_tracefs(&global_trace, d_tracer);
-	ftrace_init_tracefs_toplevel(&global_trace, d_tracer);
+	init_tracer_tracefs(&global_trace, NULL);
+	ftrace_init_tracefs_toplevel(&global_trace, NULL);
 
-	trace_create_file("tracing_thresh", 0644, d_tracer,
+	trace_create_file("tracing_thresh", 0644, NULL,
 			&global_trace, &tracing_thresh_fops);
 
-	trace_create_file("README", 0444, d_tracer,
+	trace_create_file("README", 0444, NULL,
 			NULL, &tracing_readme_fops);
 
-	trace_create_file("saved_cmdlines", 0444, d_tracer,
+	trace_create_file("saved_cmdlines", 0444, NULL,
 			NULL, &tracing_saved_cmdlines_fops);
 
-	trace_create_file("saved_cmdlines_size", 0644, d_tracer,
+	trace_create_file("saved_cmdlines_size", 0644, NULL,
 			  NULL, &tracing_saved_cmdlines_size_fops);
 
-	trace_create_file("saved_tgids", 0444, d_tracer,
+	trace_create_file("saved_tgids", 0444, NULL,
 			NULL, &tracing_saved_tgids_fops);
 
 	trace_eval_init();
 
-	trace_create_eval_file(d_tracer);
+	trace_create_eval_file(NULL);
 
 #ifdef CONFIG_MODULES
 	register_module_notifier(&trace_module_nb);
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
+	trace_create_file("dyn_ftrace_total_info", 0444, NULL,
 			NULL, &tracing_dyn_info_fops);
 #endif
 
-	create_trace_instances(d_tracer);
+	create_trace_instances(NULL);
 
 	update_tracer_options(&global_trace);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 610d21355526..0d3a405fe446 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -737,7 +737,7 @@ struct dentry *trace_create_file(const char *name,
 				 void *data,
 				 const struct file_operations *fops);
 
-struct dentry *tracing_init_dentry(void);
+int tracing_init_dentry(void);
 
 struct ring_buffer_event;
 
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 9f2e8520b748..9442a9bb080e 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -206,14 +206,14 @@ static const struct file_operations dynamic_events_ops = {
 /* Make a tracefs interface for controlling dynamic events */
 static __init int init_dynamic_event(void)
 {
-	struct dentry *d_tracer;
 	struct dentry *entry;
+	int ret;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("dynamic_events", 0644, d_tracer,
+	entry = tracefs_create_file("dynamic_events", 0644, NULL,
 				    NULL, &dynamic_events_ops);
 
 	/* Event list interface */
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index c6cca0d1d584..f86a2aa0bccd 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1757,7 +1757,6 @@ static const struct file_operations synth_events_fops = {
 static __init int trace_events_synth_init(void)
 {
 	struct dentry *entry = NULL;
-	struct dentry *d_tracer;
 	int err = 0;
 
 	err = dyn_event_register(&synth_event_ops);
@@ -1766,13 +1765,11 @@ static __init int trace_events_synth_init(void)
 		return err;
 	}
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer)) {
-		err = PTR_ERR(d_tracer);
+	err = tracing_init_dentry();
+	if (err)
 		goto err;
-	}
 
-	entry = tracefs_create_file("synthetic_events", 0644, d_tracer,
+	entry = tracefs_create_file("synthetic_events", 0644, NULL,
 				    NULL, &synth_events_fops);
 	if (!entry) {
 		err = -ENODEV;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 4a9c49c08ec9..60d66278aa0d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1336,13 +1336,13 @@ static const struct file_operations graph_depth_fops = {
 
 static __init int init_graph_tracefs(void)
 {
-	struct dentry *d_tracer;
+	int ret;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return 0;
 
-	trace_create_file("max_graph_depth", 0644, d_tracer,
+	trace_create_file("max_graph_depth", 0644, NULL,
 			  NULL, &graph_depth_fops);
 
 	return 0;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 17873e5d0353..c9ad5c6fbaad 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -538,14 +538,14 @@ static const struct file_operations window_fops = {
  */
 static int init_tracefs(void)
 {
-	struct dentry *d_tracer;
+	int ret;
 	struct dentry *top_dir;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return -ENOMEM;
 
-	top_dir = tracefs_create_dir("hwlat_detector", d_tracer);
+	top_dir = tracefs_create_dir("hwlat_detector", NULL);
 	if (!top_dir)
 		return -ENOMEM;
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index aefb6065b508..feca9b19cd74 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1901,14 +1901,14 @@ subsys_initcall(init_kprobe_trace_early);
 /* Make a tracefs interface for controlling probe points */
 static __init int init_kprobe_trace(void)
 {
-	struct dentry *d_tracer;
+	int ret;
 	struct dentry *entry;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("kprobe_events", 0644, d_tracer,
+	entry = tracefs_create_file("kprobe_events", 0644, NULL,
 				    NULL, &kprobe_events_ops);
 
 	/* Event list interface */
@@ -1916,7 +1916,7 @@ static __init int init_kprobe_trace(void)
 		pr_warn("Could not create tracefs 'kprobe_events' entry\n");
 
 	/* Profile interface */
-	entry = tracefs_create_file("kprobe_profile", 0444, d_tracer,
+	entry = tracefs_create_file("kprobe_profile", 0444, NULL,
 				    NULL, &kprobe_profile_ops);
 
 	if (!entry)
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index d4e31e969206..71b2e0fdc3e0 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -367,13 +367,13 @@ static const struct file_operations ftrace_formats_fops = {
 
 static __init int init_trace_printk_function_export(void)
 {
-	struct dentry *d_tracer;
+	int ret;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return 0;
 
-	trace_create_file("printk_formats", 0444, d_tracer,
+	trace_create_file("printk_formats", 0444, NULL,
 				    NULL, &ftrace_formats_fops);
 
 	return 0;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 98bba4764c52..c408423e5d65 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -554,20 +554,20 @@ __setup("stacktrace", enable_stacktrace);
 
 static __init int stack_trace_init(void)
 {
-	struct dentry *d_tracer;
+	int ret;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return 0;
 
-	trace_create_file("stack_max_size", 0644, d_tracer,
+	trace_create_file("stack_max_size", 0644, NULL,
 			&stack_trace_max_size, &stack_max_size_fops);
 
-	trace_create_file("stack_trace", 0444, d_tracer,
+	trace_create_file("stack_trace", 0444, NULL,
 			NULL, &stack_trace_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("stack_trace_filter", 0644, d_tracer,
+	trace_create_file("stack_trace_filter", 0644, NULL,
 			  &trace_ops, &stack_trace_filter_fops);
 #endif
 
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index d1fa19773cc8..8d141c3825a9 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -276,13 +276,13 @@ static const struct file_operations tracing_stat_fops = {
 
 static int tracing_stat_init(void)
 {
-	struct dentry *d_tracing;
+	int ret;
 
-	d_tracing = tracing_init_dentry();
-	if (IS_ERR(d_tracing))
+	ret = tracing_init_dentry();
+	if (ret)
 		return -ENODEV;
 
-	stat_dir = tracefs_create_dir("trace_stat", d_tracing);
+	stat_dir = tracefs_create_dir("trace_stat", NULL);
 	if (!stat_dir) {
 		pr_warn("Could not create tracefs 'trace_stat' entry\n");
 		return -ENOMEM;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index f4286c9bdeb4..56729c6b6614 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1625,21 +1625,20 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call)
 /* Make a trace interface for controling probe points */
 static __init int init_uprobe_trace(void)
 {
-	struct dentry *d_tracer;
 	int ret;
 
 	ret = dyn_event_register(&trace_uprobe_ops);
 	if (ret)
 		return ret;
 
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer))
+	ret = tracing_init_dentry();
+	if (ret)
 		return 0;
 
-	trace_create_file("uprobe_events", 0644, d_tracer,
+	trace_create_file("uprobe_events", 0644, NULL,
 				    NULL, &uprobe_events_ops);
 	/* Profile interface */
-	trace_create_file("uprobe_profile", 0444, d_tracer,
+	trace_create_file("uprobe_profile", 0444, NULL,
 				    NULL, &uprobe_profile_ops);
 	return 0;
 }
-- 
2.28.0

[for-next][PATCH 09/26] tracing: Delete repeated words in comments

[Steven Rostedt]

From: Randy Dunlap <rdunlap@infradead.org>

Drop repeated words in kernel/trace/.
{and, the, not}

Link: https://lkml.kernel.org/r/20200807033259.13778-1-rdunlap@infradead.org

Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c             | 2 +-
 kernel/trace/trace.c              | 2 +-
 kernel/trace/trace_dynevent.c     | 2 +-
 kernel/trace/trace_events_synth.c | 2 +-
 kernel/trace/tracing_map.c        | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 603255f5f085..84f32dbc7be8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2402,7 +2402,7 @@ struct ftrace_ops direct_ops = {
  *
  * If the record has the FTRACE_FL_REGS set, that means that it
  * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
- * is not not set, then it wants to convert to the normal callback.
+ * is not set, then it wants to convert to the normal callback.
  *
  * Returns the address of the trampoline to set to
  */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 29a9034b38d0..8fac7d6db222 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9287,7 +9287,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	}
 
 	/*
-	 * We need to stop all tracing on all CPUS to read the
+	 * We need to stop all tracing on all CPUS to read
 	 * the next buffer. This is a bit expensive, but is
 	 * not done often. We fill all what we can read,
 	 * and then release the locks again.
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 9442a9bb080e..5fa49cfd2bb6 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -402,7 +402,7 @@ void dynevent_arg_init(struct dynevent_arg *arg,
  * whitespace, all followed by a separator, if applicable.  After the
  * first arg string is successfully appended to the command string,
  * the optional @operator is appended, followed by the second arg and
- * and optional @separator.  If no separator was specified when
+ * optional @separator.  If no separator was specified when
  * initializing the arg, a space will be appended.
  */
 void dynevent_arg_pair_init(struct dynevent_arg_pair *arg_pair,
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index f86a2aa0bccd..7c765e80e974 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1211,7 +1211,7 @@ __synth_event_trace_start(struct trace_event_file *file,
 	 * ENABLED bit is set (which attaches the probe thus allowing
 	 * this code to be called, etc).  Because this is called
 	 * directly by the user, we don't have that but we still need
-	 * to honor not logging when disabled.  For the the iterated
+	 * to honor not logging when disabled.  For the iterated
 	 * trace case, we save the enabed state upon start and just
 	 * ignore the following data calls.
 	 */
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 74738c9856f1..4b50fc0cb12c 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -260,7 +260,7 @@ int tracing_map_add_var(struct tracing_map *map)
  * to use cmp_fn.
  *
  * A key can be a subset of a compound key; for that purpose, the
- * offset param is used to describe where within the the compound key
+ * offset param is used to describe where within the compound key
  * the key referenced by this key field resides.
  *
  * Return: The index identifying the field in the map and associated
-- 
2.28.0

[for-next][PATCH 10/26] tracing: Use __this_cpu_read() in trace_buffered_event_enable()

[Steven Rostedt]

From: Xianting Tian <tian.xianting@h3c.com>

The code is executed with preemption disabled, so it's
safe to use __this_cpu_read().

Link: https://lkml.kernel.org/r/20200813112803.12256-1-tian.xianting@h3c.com

Signed-off-by: Xianting Tian <tian.xianting@h3c.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8fac7d6db222..1c4ca25944ba 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2511,7 +2511,7 @@ void trace_buffered_event_enable(void)
 
 		preempt_disable();
 		if (cpu == smp_processor_id() &&
-		    this_cpu_read(trace_buffered_event) !=
+		    __this_cpu_read(trace_buffered_event) !=
 		    per_cpu(trace_buffered_event, cpu))
 			WARN_ON_ONCE(1);
 		preempt_enable();
-- 
2.28.0

[for-next][PATCH 11/26] kprobes: Use module_name() macro

[Steven Rostedt]

From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>

It is advised to use module_name() macro instead of dereferencing mod->name
directly. This makes sense for consistencys sake and also it prevents a
hard dependency to CONFIG_MODULES.

Link: https://lkml.kernel.org/r/20200818050857.117998-1-jarkko.sakkinen@linux.intel.com

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: linux-mm@kvack.org
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>,
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Will Deacon <will@kernel.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index feca9b19cd74..f8e46929ceba 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -106,9 +106,10 @@ static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk)
 static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk,
 						 struct module *mod)
 {
-	int len = strlen(mod->name);
+	int len = strlen(module_name(mod));
 	const char *name = trace_kprobe_symbol(tk);
-	return strncmp(mod->name, name, len) == 0 && name[len] == ':';
+
+	return strncmp(module_name(mod), name, len) == 0 && name[len] == ':';
 }
 
 static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
@@ -688,7 +689,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
 			if (ret)
 				pr_warn("Failed to re-register probe %s on %s: %d\n",
 					trace_probe_name(&tk->tp),
-					mod->name, ret);
+					module_name(mod), ret);
 		}
 	}
 	mutex_unlock(&event_mutex);
-- 
2.28.0

[for-next][PATCH 12/26] tracing: remove a pointless assignment

[Steven Rostedt]

From: Dan Carpenter <dan.carpenter@oracle.com>

The "tr" is a stack variable so setting it to NULL before a return is
a no-op.  Delete the assignment.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1c4ca25944ba..55b829863127 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8799,7 +8799,6 @@ static int __remove_instance(struct trace_array *tr)
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
-	tr = NULL;
 
 	return 0;
 }
-- 
2.28.0

[for-next][PATCH 13/26] fgraph: Convert ret_stack tasklist scanning to rcu

[Steven Rostedt]

From: Davidlohr Bueso <dave@stgolabs.net>

It seems that alloc_retstack_tasklist() can also take a lockless
approach for scanning the tasklist, instead of using the big global
tasklist_lock. For this we also kill another deprecated and rcu-unsafe
tsk->thread_group user replacing it with for_each_process_thread(),
maintaining semantics.

Here tasklist_lock does not protect anything other than the list
against concurrent fork/exit. And considering that the whole thing
is capped by FTRACE_RETSTACK_ALLOC_SIZE (32), it should not be a
problem to have a pontentially stale, yet stable, list. The task cannot
go away either, so we don't risk racing with ftrace_graph_exit_task()
which clears the retstack.

The tsk->ret_stack management is not protected by tasklist_lock, being
serialized with the corresponding publish/subscribe barriers against
concurrent ftrace_push_return_trace(). In addition this plays nicer
with cachelines by avoiding two atomic ops in the uncontended case.

Link: https://lkml.kernel.org/r/20200907013326.9870-1-dave@stgolabs.net

Acked-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/fgraph.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 1af321dec0f1..5658f13037b3 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -387,8 +387,8 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 		}
 	}
 
-	read_lock(&tasklist_lock);
-	do_each_thread(g, t) {
+	rcu_read_lock();
+	for_each_process_thread(g, t) {
 		if (start == end) {
 			ret = -EAGAIN;
 			goto unlock;
@@ -403,10 +403,10 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 			smp_wmb();
 			t->ret_stack = ret_stack_list[start++];
 		}
-	} while_each_thread(g, t);
+	}
 
 unlock:
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 free:
 	for (i = start; i < end; i++)
 		kfree(ret_stack_list[i]);
-- 
2.28.0

[for-next][PATCH 14/26] tracing/boot: Add per-instance tracing_on option support

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add per-instance tracing_on option, which will be useful with
traceon/traceoff event trigger actions. For example, if we
disable tracing_on by default and set traceon and traceoff on
a pair of events, we can trace functions between the pair of
events.

Link: https://lkml.kernel.org/r/159972811538.428528.2561315102284268611.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_boot.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index fa0fc08c6ef8..d52d441a17e8 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -40,6 +40,16 @@ trace_boot_set_instance_options(struct trace_array *tr, struct xbc_node *node)
 			pr_err("Failed to set option: %s\n", buf);
 	}
 
+	p = xbc_node_find_value(node, "tracing_on", NULL);
+	if (p && *p != '\0') {
+		if (kstrtoul(p, 10, &v))
+			pr_err("Failed to set tracing on: %s\n", p);
+		if (v)
+			tracer_tracing_on(tr);
+		else
+			tracer_tracing_off(tr);
+	}
+
 	p = xbc_node_find_value(node, "trace_clock", NULL);
 	if (p && *p != '\0') {
 		if (tracing_set_clock(tr, p) < 0)
-- 
2.28.0

[for-next][PATCH 15/26] Documentation: tracing: Add tracing_on option to boot-time tracer

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add tracing_on option description to the boot-time tracer.

Link: https://lkml.kernel.org/r/159978523520.485820.9250337223076929279.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/boottime-trace.rst | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/trace/boottime-trace.rst b/Documentation/trace/boottime-trace.rst
index dcb390075ca1..9bc8aceb8c0a 100644
--- a/Documentation/trace/boottime-trace.rst
+++ b/Documentation/trace/boottime-trace.rst
@@ -61,6 +61,10 @@ These options can be used for each instance including global ftrace node.
 ftrace.[instance.INSTANCE.]options = OPT1[, OPT2[...]]
    Enable given ftrace options.
 
+ftrace.[instance.INSTANCE.]tracing_on = 0|1
+   Enable/Disable tracing on this instance when starting boot-time tracing.
+   (you can enable it by the "traceon" event trigger action)
+
 ftrace.[instance.INSTANCE.]trace_clock = CLOCK
    Set given CLOCK to ftrace's trace_clock.
 
-- 
2.28.0

[for-next][PATCH 16/26] tracing/kprobes: Support perf-style return probe

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Support perf-style return probe ("SYMBOL%return") for kprobe events.
This will allow boot-time tracing user to define a return probe event.

Link: https://lkml.kernel.org/r/159972813535.428528.4437029657208468954.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c        |  2 +-
 kernel/trace/trace_kprobe.c | 18 +++++++++++++++++-
 kernel/trace/trace_probe.h  |  1 +
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 55b829863127..ca6da462326d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5122,7 +5122,7 @@ static const char readme_msg[] =
 	"\t           -:[<group>/]<event>\n"
 #ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
-  "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n"
+  "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n"
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
   "   place (uprobe): <path>:<offset>[(ref_ctr_offset)]\n"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f8e46929ceba..9d46415296eb 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -718,6 +718,9 @@ static int trace_kprobe_create(int argc, const char *argv[])
 	 *      p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
 	 *  - Add kretprobe:
 	 *      r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
+	 *    Or
+	 *      p:[GRP/]EVENT] [MOD:]KSYM[+0]%return [FETCHARGS]
+	 *
 	 * Fetch args:
 	 *  $retval	: fetch return value
 	 *  $stack	: fetch stack address
@@ -747,7 +750,6 @@ static int trace_kprobe_create(int argc, const char *argv[])
 	switch (argv[0][0]) {
 	case 'r':
 		is_return = true;
-		flags |= TPARG_FL_RETURN;
 		break;
 	case 'p':
 		break;
@@ -805,12 +807,26 @@ static int trace_kprobe_create(int argc, const char *argv[])
 		symbol = kstrdup(argv[1], GFP_KERNEL);
 		if (!symbol)
 			return -ENOMEM;
+
+		tmp = strchr(symbol, '%');
+		if (tmp) {
+			if (!strcmp(tmp, "%return")) {
+				*tmp = '\0';
+				is_return = true;
+			} else {
+				trace_probe_log_err(tmp - symbol, BAD_ADDR_SUFFIX);
+				goto parse_error;
+			}
+		}
+
 		/* TODO: support .init module functions */
 		ret = traceprobe_split_symbol_offset(symbol, &offset);
 		if (ret || offset < 0 || offset > UINT_MAX) {
 			trace_probe_log_err(0, BAD_PROBE_ADDR);
 			goto parse_error;
 		}
+		if (is_return)
+			flags |= TPARG_FL_RETURN;
 		if (kprobe_on_func_entry(NULL, symbol, offset))
 			flags |= TPARG_FL_FENTRY;
 		if (offset && is_return && !(flags & TPARG_FL_FENTRY)) {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index a22b62813f8c..04d00987da69 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -404,6 +404,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(MAXACT_TOO_BIG,	"Maxactive is too big"),		\
 	C(BAD_PROBE_ADDR,	"Invalid probed address or symbol"),	\
 	C(BAD_RETPROBE,		"Retprobe address must be an function entry"), \
+	C(BAD_ADDR_SUFFIX,	"Invalid probed address suffix"), \
 	C(NO_GROUP_NAME,	"Group name is not specified"),		\
 	C(GROUP_TOO_LONG,	"Group name is too long"),		\
 	C(BAD_GROUP_NAME,	"Group name must follow the same rules as C identifiers"), \
-- 
2.28.0

[for-next][PATCH 17/26] tracing/uprobes: Support perf-style return probe

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Support perf-style return probe ("SYMBOL%return") for uprobe events
as same as kprobe events does.

Link: https://lkml.kernel.org/r/159972814601.428528.7641183316212425445.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c        |  2 +-
 kernel/trace/trace_uprobe.c | 15 ++++++++++++++-
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ca6da462326d..c35fcd2f2529 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5125,7 +5125,7 @@ static const char readme_msg[] =
   "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n"
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
-  "   place (uprobe): <path>:<offset>[(ref_ctr_offset)]\n"
+  "   place (uprobe): <path>:<offset>[%return][(ref_ctr_offset)]\n"
 #endif
 	"\t     args: <name>=fetcharg[:type]\n"
 	"\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n"
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 56729c6b6614..3cf7128e1ad3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -528,7 +528,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 
 /*
  * Argument syntax:
- *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
+ *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET[%return][(REF)] [FETCHARGS]
  */
 static int trace_uprobe_create(int argc, const char **argv)
 {
@@ -617,6 +617,19 @@ static int trace_uprobe_create(int argc, const char **argv)
 		}
 	}
 
+	/* Check if there is %return suffix */
+	tmp = strchr(arg, '%');
+	if (tmp) {
+		if (!strcmp(tmp, "%return")) {
+			*tmp = '\0';
+			is_return = true;
+		} else {
+			trace_probe_log_err(tmp - filename, BAD_ADDR_SUFFIX);
+			ret = -EINVAL;
+			goto fail_address_parse;
+		}
+	}
+
 	/* Parse uprobe offset. */
 	ret = kstrtoul(arg, 0, &offset);
 	if (ret) {
-- 
2.28.0

[for-next][PATCH 18/26] Documentation: tracing: Add %return suffix description

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add a description of the %return suffix option for kprobe event and
uprobe event.

Link: https://lkml.kernel.org/r/159972815624.428528.10450874184415697524.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/kprobetrace.rst  | 2 ++
 Documentation/trace/uprobetracer.rst | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index c1709165c553..a18eb97a263c 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -30,6 +30,7 @@ Synopsis of kprobe_events
 
   p[:[GRP/]EVENT] [MOD:]SYM[+offs]|MEMADDR [FETCHARGS]	: Set a probe
   r[MAXACTIVE][:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS]	: Set a return probe
+  p:[GRP/]EVENT] [MOD:]SYM[+0]%return [FETCHARGS]	: Set a return probe
   -:[GRP/]EVENT						: Clear a probe
 
  GRP		: Group name. If omitted, use "kprobes" for it.
@@ -37,6 +38,7 @@ Synopsis of kprobe_events
 		  based on SYM+offs or MEMADDR.
  MOD		: Module name which has given SYM.
  SYM[+offs]	: Symbol+offset where the probe is inserted.
+ SYM%return	: Return address of the symbol
  MEMADDR	: Address where the probe is inserted.
  MAXACTIVE	: Maximum number of instances of the specified function that
 		  can be probed simultaneously, or 0 for the default value
diff --git a/Documentation/trace/uprobetracer.rst b/Documentation/trace/uprobetracer.rst
index 98cde99939d7..a8e5938f609e 100644
--- a/Documentation/trace/uprobetracer.rst
+++ b/Documentation/trace/uprobetracer.rst
@@ -28,6 +28,7 @@ Synopsis of uprobe_tracer
 
   p[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] : Set a uprobe
   r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] : Set a return uprobe (uretprobe)
+  p[:[GRP/]EVENT] PATH:OFFSET%return [FETCHARGS] : Set a return uprobe (uretprobe)
   -:[GRP/]EVENT                           : Clear uprobe or uretprobe event
 
   GRP           : Group name. If omitted, "uprobes" is the default value.
@@ -35,6 +36,7 @@ Synopsis of uprobe_tracer
                   on PATH+OFFSET.
   PATH          : Path to an executable or a library.
   OFFSET        : Offset where the probe is inserted.
+  OFFSET%return : Offset where the return probe is inserted.
 
   FETCHARGS     : Arguments. Each probe can have up to 128 args.
    %REG         : Fetch register REG
-- 
2.28.0

[for-next][PATCH 19/26] Documentation: tracing: boot: Add an example of tracing function-calls

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add an example of tracing function calls on a specific function.

Link: https://lkml.kernel.org/r/159972816669.428528.12390560334549382316.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/boottime-trace.rst | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/Documentation/trace/boottime-trace.rst b/Documentation/trace/boottime-trace.rst
index 9bc8aceb8c0a..ab3bfd67197c 100644
--- a/Documentation/trace/boottime-trace.rst
+++ b/Documentation/trace/boottime-trace.rst
@@ -168,6 +168,26 @@ is for tracing functions starting with "user\_", and others tracing
 The instance node also accepts event nodes so that each instance
 can customize its event tracing.
 
+With the trigger action and kprobes, you can trace function-graph while
+a function is called. For example, this will trace all function calls in
+the pci_proc_init()::
+
+  ftrace {
+        tracing_on = 0
+        tracer = function_graph
+        event.kprobes {
+                start_event {
+                        probes = "pci_proc_init"
+                        actions = "traceon"
+                }
+                end_event {
+                        probes = "pci_proc_init%return"
+                        actions = "traceoff"
+                }
+        }
+  }
+
+
 This boot-time tracing also supports ftrace kernel parameters via boot
 config.
 For example, following kernel parameters::
-- 
2.28.0

[for-next][PATCH 20/26] selftests/ftrace: Add %return suffix tests

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add kprobe %return suffix testcase and syntax error tests
for %return suffix.

Link: https://lkml.kernel.org/r/159972817653.428528.9180599115849301184.stgit@devnote2

Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 .../test.d/kprobe/kprobe_syntax_errors.tc     |  6 ++++++
 .../test.d/kprobe/kretprobe_return_suffix.tc  | 21 +++++++++++++++++++
 .../test.d/kprobe/uprobe_syntax_errors.tc     |  6 ++++++
 3 files changed, 33 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index b4d834675e59..56b3f36c722b 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -97,4 +97,10 @@ check_error 'p:kprobes/testevent _do_fork ^abcd=\"foo"'	# DIFF_ARG_TYPE
 check_error '^p:kprobes/testevent _do_fork abcd=\1'	# SAME_PROBE
 fi
 
+# %return suffix errors
+if grep -q "place (kretprobe): .*%return.*" README; then
+check_error 'p vfs_read^%hoge'		# BAD_ADDR_SUFFIX
+check_error 'p ^vfs_read+10%return'	# BAD_RETPROBE
+fi
+
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc
new file mode 100644
index 000000000000..f07bd15cc033
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc
@@ -0,0 +1,21 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kretprobe %%return suffix test
+# requires: kprobe_events '<symbol>[+<offset>]%return':README
+
+# Test for kretprobe by "r"
+echo 'r:myprobeaccept vfs_read' > kprobe_events
+RESULT1=`cat kprobe_events`
+
+# Test for kretprobe by "%return"
+echo 'p:myprobeaccept vfs_read%return' > kprobe_events
+RESULT2=`cat kprobe_events`
+
+if [ "$RESULT1" != "$RESULT2" ]; then
+	echo "Error: %return suffix didn't make a return probe."
+	echo "r-command: $RESULT1"
+	echo "%return: $RESULT2"
+	exit_fail
+fi
+
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
index 7b5b60c3c5a2..f5e3f9e4a01f 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
@@ -17,4 +17,10 @@ check_error 'p /bin/sh:10(10)^a'	# BAD_REFCNT_SUFFIX
 check_error 'p /bin/sh:10 ^@+ab'	# BAD_FILE_OFFS
 check_error 'p /bin/sh:10 ^@symbol'	# SYM_ON_UPROBE
 
+# %return suffix error
+if grep -q "place (uprobe): .*%return.*" README; then
+check_error 'p /bin/sh:10^%hoge'	# BAD_ADDR_SUFFIX
+check_error 'p /bin/sh:10(10)^%return'	# BAD_REFCNT_SUFFIX
+fi
+
 exit 0
-- 
2.28.0

[for-next][PATCH 21/26] kprobes: Init kprobes in early_initcall

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Init kprobes feature in early_initcall as same as jump_label and
dynamic_debug does, so that we can use kprobes events in earlier
boot stage.

Link: https://lkml.kernel.org/r/159974151897.478751.8342374158615496628.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/kprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d750e025d1ff..9303881aac84 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2529,7 +2529,7 @@ static int __init init_kprobes(void)
 		init_test_probes();
 	return err;
 }
-subsys_initcall(init_kprobes);
+early_initcall(init_kprobes);
 
 #ifdef CONFIG_DEBUG_FS
 static void report_probe(struct seq_file *pi, struct kprobe *p,
-- 
2.28.0

[for-next][PATCH 22/26] tracing: Define event fields early stage

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Define event fields at early stage so that boot-time tracing can
access the event fields (like per-event filter setting).

Link: https://lkml.kernel.org/r/159974152862.478751.2023768466808361350.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 92 ++++++++++++++++++++++---------------
 1 file changed, 55 insertions(+), 37 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index ee25d849ebba..8e87fbab6930 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2123,12 +2123,48 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	return NULL;
 }
 
+static int
+event_define_fields(struct trace_event_call *call)
+{
+	struct list_head *head;
+	int ret = 0;
+
+	/*
+	 * Other events may have the same class. Only update
+	 * the fields if they are not already defined.
+	 */
+	head = trace_get_fields(call);
+	if (list_empty(head)) {
+		struct trace_event_fields *field = call->class->fields_array;
+		unsigned int offset = sizeof(struct trace_entry);
+
+		for (; field->type; field++) {
+			if (field->type == TRACE_FUNCTION_TYPE) {
+				field->define_fields(call);
+				break;
+			}
+
+			offset = ALIGN(offset, field->align);
+			ret = trace_define_field(call, field->type, field->name,
+						 offset, field->size,
+						 field->is_signed, field->filter_type);
+			if (WARN_ON_ONCE(ret)) {
+				pr_err("error code is %d\n", ret);
+				break;
+			}
+
+			offset += field->size;
+		}
+	}
+
+	return ret;
+}
+
 static int
 event_create_dir(struct dentry *parent, struct trace_event_file *file)
 {
 	struct trace_event_call *call = file->event_call;
 	struct trace_array *tr = file->tr;
-	struct list_head *head;
 	struct dentry *d_events;
 	const char *name;
 	int ret;
@@ -2162,35 +2198,10 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 				  &ftrace_event_id_fops);
 #endif
 
-	/*
-	 * Other events may have the same class. Only update
-	 * the fields if they are not already defined.
-	 */
-	head = trace_get_fields(call);
-	if (list_empty(head)) {
-		struct trace_event_fields *field = call->class->fields_array;
-		unsigned int offset = sizeof(struct trace_entry);
-
-		for (; field->type; field++) {
-			if (field->type == TRACE_FUNCTION_TYPE) {
-				ret = field->define_fields(call);
-				break;
-			}
-
-			offset = ALIGN(offset, field->align);
-			ret = trace_define_field(call, field->type, field->name,
-						 offset, field->size,
-						 field->is_signed, field->filter_type);
-			if (ret)
-				break;
-
-			offset += field->size;
-		}
-		if (ret < 0) {
-			pr_warn("Could not initialize trace point events/%s\n",
-				name);
-			return -1;
-		}
+	ret = event_define_fields(call);
+	if (ret < 0) {
+		pr_warn("Could not initialize trace point events/%s\n", name);
+		return ret;
 	}
 
 	/*
@@ -2493,7 +2504,7 @@ __trace_early_add_new_event(struct trace_event_call *call,
 	if (!file)
 		return -ENOMEM;
 
-	return 0;
+	return event_define_fields(call);
 }
 
 struct ftrace_module_file_ops;
@@ -3431,6 +3442,18 @@ static __init int event_trace_enable_again(void)
 
 early_initcall(event_trace_enable_again);
 
+/* Init fields which doesn't related to the tracefs */
+static __init int event_trace_init_fields(void)
+{
+	if (trace_define_generic_fields())
+		pr_warn("tracing: Failed to allocated generic fields");
+
+	if (trace_define_common_fields())
+		pr_warn("tracing: Failed to allocate common fields");
+
+	return 0;
+}
+
 __init int event_trace_init(void)
 {
 	struct trace_array *tr;
@@ -3446,12 +3469,6 @@ __init int event_trace_init(void)
 	if (!entry)
 		pr_warn("Could not create tracefs 'available_events' entry\n");
 
-	if (trace_define_generic_fields())
-		pr_warn("tracing: Failed to allocated generic fields");
-
-	if (trace_define_common_fields())
-		pr_warn("tracing: Failed to allocate common fields");
-
 	ret = early_event_add_tracer(NULL, tr);
 	if (ret)
 		return ret;
@@ -3469,6 +3486,7 @@ void __init trace_event_init(void)
 	event_trace_memsetup();
 	init_ftrace_syscalls();
 	event_trace_enable();
+	event_trace_init_fields();
 }
 
 #ifdef CONFIG_EVENT_TRACE_STARTUP_TEST
-- 
2.28.0

[for-next][PATCH 23/26] tracing: Enable adding dynamic events early stage

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Split the event fields initialization from creating new event directory.
This allows the boot-time tracing to define dynamic events before
initializing events directory on tracefs.

Link: https://lkml.kernel.org/r/159974153790.478751.3475515065034825374.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 8e87fbab6930..42c0e7df6e70 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -38,6 +38,7 @@ DEFINE_MUTEX(event_mutex);
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_generic_fields);
 static LIST_HEAD(ftrace_common_fields);
+static bool eventdir_initialized;
 
 #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
 
@@ -2486,7 +2487,10 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
 	if (!file)
 		return -ENOMEM;
 
-	return event_create_dir(tr->event_dir, file);
+	if (eventdir_initialized)
+		return event_create_dir(tr->event_dir, file);
+	else
+		return event_define_fields(call);
 }
 
 /*
@@ -3478,6 +3482,9 @@ __init int event_trace_init(void)
 	if (ret)
 		pr_warn("Failed to register trace events module notifier\n");
 #endif
+
+	eventdir_initialized = true;
+
 	return 0;
 }
 
-- 
2.28.0

[for-next][PATCH 24/26] tracing: Enable creating new instance early boot

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Enable creating new trace_array instance in early boot stage.
If the instances directory is not created, postpone it until
the tracefs is initialized.

Link: https://lkml.kernel.org/r/159974154763.478751.6289753509587233103.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c           | 53 +++++++++++++++++++++++++++-------
 kernel/trace/trace.h           |  7 +++++
 kernel/trace/trace_functions.c | 22 +++++++++-----
 3 files changed, 63 insertions(+), 19 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c35fcd2f2529..6211a13b3327 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8636,6 +8636,24 @@ struct trace_array *trace_array_find_get(const char *instance)
 	return tr;
 }
 
+static int trace_array_create_dir(struct trace_array *tr)
+{
+	int ret;
+
+	tr->dir = tracefs_create_dir(tr->name, trace_instance_dir);
+	if (!tr->dir)
+		return -EINVAL;
+
+	ret = event_trace_add_tracer(tr->dir, tr);
+	if (ret)
+		tracefs_remove(tr->dir);
+
+	init_tracer_tracefs(tr, tr->dir);
+	__update_tracer_options(tr);
+
+	return ret;
+}
+
 static struct trace_array *trace_array_create(const char *name)
 {
 	struct trace_array *tr;
@@ -8671,30 +8689,27 @@ static struct trace_array *trace_array_create(const char *name)
 	if (allocate_trace_buffers(tr, trace_buf_size) < 0)
 		goto out_free_tr;
 
-	tr->dir = tracefs_create_dir(name, trace_instance_dir);
-	if (!tr->dir)
-		goto out_free_tr;
-
-	ret = event_trace_add_tracer(tr->dir, tr);
-	if (ret) {
-		tracefs_remove(tr->dir);
+	if (ftrace_allocate_ftrace_ops(tr) < 0)
 		goto out_free_tr;
-	}
 
 	ftrace_init_trace_array(tr);
 
-	init_tracer_tracefs(tr, tr->dir);
 	init_trace_flags_index(tr);
-	__update_tracer_options(tr);
+
+	if (trace_instance_dir) {
+		ret = trace_array_create_dir(tr);
+		if (ret)
+			goto out_free_tr;
+	}
 
 	list_add(&tr->list, &ftrace_trace_arrays);
 
 	tr->ref++;
 
-
 	return tr;
 
  out_free_tr:
+	ftrace_free_ftrace_ops(tr);
 	free_trace_buffers(tr);
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
@@ -8852,11 +8867,27 @@ static int instance_rmdir(const char *name)
 
 static __init void create_trace_instances(struct dentry *d_tracer)
 {
+	struct trace_array *tr;
+
 	trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer,
 							 instance_mkdir,
 							 instance_rmdir);
 	if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n"))
 		return;
+
+	mutex_lock(&event_mutex);
+	mutex_lock(&trace_types_lock);
+
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (!tr->name)
+			continue;
+		if (MEM_FAIL(trace_array_create_dir(tr) < 0,
+			     "Failed to create instance directory\n"))
+			break;
+	}
+
+	mutex_unlock(&trace_types_lock);
+	mutex_unlock(&event_mutex);
 }
 
 static void
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0d3a405fe446..525434145eea 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1125,6 +1125,8 @@ extern int ftrace_is_dead(void);
 int ftrace_create_function_files(struct trace_array *tr,
 				 struct dentry *parent);
 void ftrace_destroy_function_files(struct trace_array *tr);
+int ftrace_allocate_ftrace_ops(struct trace_array *tr);
+void ftrace_free_ftrace_ops(struct trace_array *tr);
 void ftrace_init_global_array_ops(struct trace_array *tr);
 void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
 void ftrace_reset_array_ops(struct trace_array *tr);
@@ -1146,6 +1148,11 @@ ftrace_create_function_files(struct trace_array *tr,
 {
 	return 0;
 }
+static inline int ftrace_allocate_ftrace_ops(struct trace_array *tr)
+{
+	return 0;
+}
+static inline void ftrace_free_ftrace_ops(struct trace_array *tr) { }
 static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
 static inline __init void
 ftrace_init_global_array_ops(struct trace_array *tr) { }
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index dd4dff71d89a..2c2126e1871d 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -34,10 +34,14 @@ enum {
 	TRACE_FUNC_OPT_STACK	= 0x1,
 };
 
-static int allocate_ftrace_ops(struct trace_array *tr)
+int ftrace_allocate_ftrace_ops(struct trace_array *tr)
 {
 	struct ftrace_ops *ops;
 
+	/* The top level array uses the "global_ops" */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+		return 0;
+
 	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
 	if (!ops)
 		return -ENOMEM;
@@ -48,15 +52,19 @@ static int allocate_ftrace_ops(struct trace_array *tr)
 
 	tr->ops = ops;
 	ops->private = tr;
+
 	return 0;
 }
 
+void ftrace_free_ftrace_ops(struct trace_array *tr)
+{
+	kfree(tr->ops);
+	tr->ops = NULL;
+}
 
 int ftrace_create_function_files(struct trace_array *tr,
 				 struct dentry *parent)
 {
-	int ret;
-
 	/*
 	 * The top level array uses the "global_ops", and the files are
 	 * created on boot up.
@@ -64,9 +72,8 @@ int ftrace_create_function_files(struct trace_array *tr,
 	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
 		return 0;
 
-	ret = allocate_ftrace_ops(tr);
-	if (ret)
-		return ret;
+	if (!tr->ops)
+		return -EINVAL;
 
 	ftrace_create_filter_files(tr->ops, parent);
 
@@ -76,8 +83,7 @@ int ftrace_create_function_files(struct trace_array *tr,
 void ftrace_destroy_function_files(struct trace_array *tr)
 {
 	ftrace_destroy_filter_files(tr->ops);
-	kfree(tr->ops);
-	tr->ops = NULL;
+	ftrace_free_ftrace_ops(tr);
 }
 
 static int function_trace_init(struct trace_array *tr)
-- 
2.28.0

[for-next][PATCH 25/26] tracing/boot, kprobe, synth: Initialize boot-time tracing earlier

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Initialize boot-time tracing in core_initcall_sync instead of
fs_initcall, and initialize required tracers (kprobes and synth)
in core_initcall. This will allow the boot-time tracing to trace
__init code from the beginning of postcore_initcall stage.

Link: https://lkml.kernel.org/r/159974155727.478751.7486926132902849578.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_boot.c         |  7 +++++--
 kernel/trace/trace_events_synth.c | 19 ++++++++++++++-----
 kernel/trace/trace_kprobe.c       |  6 +++---
 3 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index d52d441a17e8..754e3cf2df3a 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -340,5 +340,8 @@ static int __init trace_boot_init(void)
 
 	return 0;
 }
-
-fs_initcall(trace_boot_init);
+/*
+ * Start tracing at the end of core-initcall, so that it starts tracing
+ * from the beginning of postcore_initcall.
+ */
+core_initcall_sync(trace_boot_init);
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 7c765e80e974..a9cd7793f7ea 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1754,17 +1754,26 @@ static const struct file_operations synth_events_fops = {
 	.release        = seq_release,
 };
 
-static __init int trace_events_synth_init(void)
+/*
+ * Register dynevent at core_initcall. This allows kernel to setup kprobe
+ * events in postcore_initcall without tracefs.
+ */
+static __init int trace_events_synth_init_early(void)
 {
-	struct dentry *entry = NULL;
 	int err = 0;
 
 	err = dyn_event_register(&synth_event_ops);
-	if (err) {
+	if (err)
 		pr_warn("Could not register synth_event_ops\n");
-		return err;
-	}
 
+	return err;
+}
+core_initcall(trace_events_synth_init_early);
+
+static __init int trace_events_synth_init(void)
+{
+	struct dentry *entry = NULL;
+	int err = 0;
 	err = tracing_init_dentry();
 	if (err)
 		goto err;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 9d46415296eb..b911e9f6d9f5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1897,8 +1897,8 @@ static __init void setup_boot_kprobe_events(void)
 }
 
 /*
- * Register dynevent at subsys_initcall. This allows kernel to setup kprobe
- * events in fs_initcall without tracefs.
+ * Register dynevent at core_initcall. This allows kernel to setup kprobe
+ * events in postcore_initcall without tracefs.
  */
 static __init int init_kprobe_trace_early(void)
 {
@@ -1913,7 +1913,7 @@ static __init int init_kprobe_trace_early(void)
 
 	return 0;
 }
-subsys_initcall(init_kprobe_trace_early);
+core_initcall(init_kprobe_trace_early);
 
 /* Make a tracefs interface for controlling probe points */
 static __init int init_kprobe_trace(void)
-- 
2.28.0

[for-next][PATCH 26/26] Documentation: tracing: Add the startup timing of boot-time tracing

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add the note about when to start the boot-time tracing.
This will be needed for the people who wants to trace
earlier boot sequence.

Link: https://lkml.kernel.org/r/159974156678.478751.10215894815285734481.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/boottime-trace.rst | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/Documentation/trace/boottime-trace.rst b/Documentation/trace/boottime-trace.rst
index ab3bfd67197c..89b64334929b 100644
--- a/Documentation/trace/boottime-trace.rst
+++ b/Documentation/trace/boottime-trace.rst
@@ -120,6 +120,20 @@ instance node, but those are also visible from other instances. So please
 take care for event name conflict.
 
 
+When to Start
+=============
+
+All boot-time tracing options starting with ``ftrace`` will be enabled at the
+end of core_initcall. This means you can trace the events from postcore_initcall.
+Most of the subsystems and architecture dependent drivers will be initialized
+after that (arch_initcall or subsys_initcall). Thus, you can trace those with
+boot-time tracing.
+If you want to trace events before core_initcall, you can use the options
+starting with ``kernel``. Some of them will be enabled eariler than the initcall
+processing (for example,. ``kernel.ftrace=function`` and ``kernel.trace_event``
+will start before the initcall.)
+
+
 Examples
 ========
 
-- 
2.28.0

Re: [for-next][PATCH 24/26] tracing: Enable creating new instance early boot

[Masami Hiramatsu]

Hi Steve,

Sorry, I found that this is not enough for setting up the instance.
It seems that an instance is created but the events of the instance
are not created (and maybe reset when initializing the tracefs).
Let me fix it.

Thank you,

On Mon, 21 Sep 2020 21:24:38 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:

> From: Masami Hiramatsu <mhiramat@kernel.org>
> 
> Enable creating new trace_array instance in early boot stage.
> If the instances directory is not created, postpone it until
> the tracefs is initialized.
> 
> Link: https://lkml.kernel.org/r/159974154763.478751.6289753509587233103.stgit@devnote2
> 
> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
> ---
>  kernel/trace/trace.c           | 53 +++++++++++++++++++++++++++-------
>  kernel/trace/trace.h           |  7 +++++
>  kernel/trace/trace_functions.c | 22 +++++++++-----
>  3 files changed, 63 insertions(+), 19 deletions(-)
> 
> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> index c35fcd2f2529..6211a13b3327 100644
> --- a/kernel/trace/trace.c
> +++ b/kernel/trace/trace.c
> @@ -8636,6 +8636,24 @@ struct trace_array *trace_array_find_get(const char *instance)
>  	return tr;
>  }
>  
> +static int trace_array_create_dir(struct trace_array *tr)
> +{
> +	int ret;
> +
> +	tr->dir = tracefs_create_dir(tr->name, trace_instance_dir);
> +	if (!tr->dir)
> +		return -EINVAL;
> +
> +	ret = event_trace_add_tracer(tr->dir, tr);
> +	if (ret)
> +		tracefs_remove(tr->dir);
> +
> +	init_tracer_tracefs(tr, tr->dir);
> +	__update_tracer_options(tr);
> +
> +	return ret;
> +}
> +
>  static struct trace_array *trace_array_create(const char *name)
>  {
>  	struct trace_array *tr;
> @@ -8671,30 +8689,27 @@ static struct trace_array *trace_array_create(const char *name)
>  	if (allocate_trace_buffers(tr, trace_buf_size) < 0)
>  		goto out_free_tr;
>  
> -	tr->dir = tracefs_create_dir(name, trace_instance_dir);
> -	if (!tr->dir)
> -		goto out_free_tr;
> -
> -	ret = event_trace_add_tracer(tr->dir, tr);
> -	if (ret) {
> -		tracefs_remove(tr->dir);
> +	if (ftrace_allocate_ftrace_ops(tr) < 0)
>  		goto out_free_tr;
> -	}
>  
>  	ftrace_init_trace_array(tr);
>  
> -	init_tracer_tracefs(tr, tr->dir);
>  	init_trace_flags_index(tr);
> -	__update_tracer_options(tr);
> +
> +	if (trace_instance_dir) {
> +		ret = trace_array_create_dir(tr);
> +		if (ret)
> +			goto out_free_tr;
> +	}
>  
>  	list_add(&tr->list, &ftrace_trace_arrays);
>  
>  	tr->ref++;
>  
> -
>  	return tr;
>  
>   out_free_tr:
> +	ftrace_free_ftrace_ops(tr);
>  	free_trace_buffers(tr);
>  	free_cpumask_var(tr->tracing_cpumask);
>  	kfree(tr->name);
> @@ -8852,11 +8867,27 @@ static int instance_rmdir(const char *name)
>  
>  static __init void create_trace_instances(struct dentry *d_tracer)
>  {
> +	struct trace_array *tr;
> +
>  	trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer,
>  							 instance_mkdir,
>  							 instance_rmdir);
>  	if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n"))
>  		return;
> +
> +	mutex_lock(&event_mutex);
> +	mutex_lock(&trace_types_lock);
> +
> +	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
> +		if (!tr->name)
> +			continue;
> +		if (MEM_FAIL(trace_array_create_dir(tr) < 0,
> +			     "Failed to create instance directory\n"))
> +			break;
> +	}
> +
> +	mutex_unlock(&trace_types_lock);
> +	mutex_unlock(&event_mutex);
>  }
>  
>  static void
> diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
> index 0d3a405fe446..525434145eea 100644
> --- a/kernel/trace/trace.h
> +++ b/kernel/trace/trace.h
> @@ -1125,6 +1125,8 @@ extern int ftrace_is_dead(void);
>  int ftrace_create_function_files(struct trace_array *tr,
>  				 struct dentry *parent);
>  void ftrace_destroy_function_files(struct trace_array *tr);
> +int ftrace_allocate_ftrace_ops(struct trace_array *tr);
> +void ftrace_free_ftrace_ops(struct trace_array *tr);
>  void ftrace_init_global_array_ops(struct trace_array *tr);
>  void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
>  void ftrace_reset_array_ops(struct trace_array *tr);
> @@ -1146,6 +1148,11 @@ ftrace_create_function_files(struct trace_array *tr,
>  {
>  	return 0;
>  }
> +static inline int ftrace_allocate_ftrace_ops(struct trace_array *tr)
> +{
> +	return 0;
> +}
> +static inline void ftrace_free_ftrace_ops(struct trace_array *tr) { }
>  static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
>  static inline __init void
>  ftrace_init_global_array_ops(struct trace_array *tr) { }
> diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
> index dd4dff71d89a..2c2126e1871d 100644
> --- a/kernel/trace/trace_functions.c
> +++ b/kernel/trace/trace_functions.c
> @@ -34,10 +34,14 @@ enum {
>  	TRACE_FUNC_OPT_STACK	= 0x1,
>  };
>  
> -static int allocate_ftrace_ops(struct trace_array *tr)
> +int ftrace_allocate_ftrace_ops(struct trace_array *tr)
>  {
>  	struct ftrace_ops *ops;
>  
> +	/* The top level array uses the "global_ops" */
> +	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
> +		return 0;
> +
>  	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
>  	if (!ops)
>  		return -ENOMEM;
> @@ -48,15 +52,19 @@ static int allocate_ftrace_ops(struct trace_array *tr)
>  
>  	tr->ops = ops;
>  	ops->private = tr;
> +
>  	return 0;
>  }
>  
> +void ftrace_free_ftrace_ops(struct trace_array *tr)
> +{
> +	kfree(tr->ops);
> +	tr->ops = NULL;
> +}
>  
>  int ftrace_create_function_files(struct trace_array *tr,
>  				 struct dentry *parent)
>  {
> -	int ret;
> -
>  	/*
>  	 * The top level array uses the "global_ops", and the files are
>  	 * created on boot up.
> @@ -64,9 +72,8 @@ int ftrace_create_function_files(struct trace_array *tr,
>  	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
>  		return 0;
>  
> -	ret = allocate_ftrace_ops(tr);
> -	if (ret)
> -		return ret;
> +	if (!tr->ops)
> +		return -EINVAL;
>  
>  	ftrace_create_filter_files(tr->ops, parent);
>  
> @@ -76,8 +83,7 @@ int ftrace_create_function_files(struct trace_array *tr,
>  void ftrace_destroy_function_files(struct trace_array *tr)
>  {
>  	ftrace_destroy_filter_files(tr->ops);
> -	kfree(tr->ops);
> -	tr->ops = NULL;
> +	ftrace_free_ftrace_ops(tr);
>  }
>  
>  static int function_trace_init(struct trace_array *tr)
> -- 
> 2.28.0
> 
> 


-- 
Masami Hiramatsu <mhiramat@kernel.org>

[PATCH] tracing/boot: Initialize per-instance event list in early boot

[Masami Hiramatsu]

Initialize per-instance event list in early boot time (before
initializing instance directory on tracefs). This fixes boot-time
tracing to correctly handle the boot-time per-instance settings.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
 kernel/trace/trace.c        |    3 ++-
 kernel/trace/trace.h        |    1 +
 kernel/trace/trace_events.c |   30 ++++++++++++++++--------------
 3 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f7696db52e7d..400ed1ec3b64 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8700,7 +8700,8 @@ static struct trace_array *trace_array_create(const char *name)
 		ret = trace_array_create_dir(tr);
 		if (ret)
 			goto out_free_tr;
-	}
+	} else
+		__trace_early_add_events(tr);
 
 	list_add(&tr->list, &ftrace_trace_arrays);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e1b3061ce06d..5b887cfbe5ec 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1658,6 +1658,7 @@ extern void trace_event_enable_tgid_record(bool enable);
 extern int event_trace_init(void);
 extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
 extern int event_trace_del_tracer(struct trace_array *tr);
+extern void __trace_early_add_events(struct trace_array *tr);
 
 extern struct trace_event_file *__find_event_file(struct trace_array *tr,
 						  const char *system,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 720b0d72ea52..8ce334297bf3 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3131,14 +3131,13 @@ static inline int register_event_cmds(void) { return 0; }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /*
- * The top level array has already had its trace_event_file
- * descriptors created in order to allow for early events to
- * be recorded. This function is called after the tracefs has been
- * initialized, and we now have to create the files associated
- * to the events.
+ * The top level array and trace arrays created by boot-time tracing
+ * have already had its trace_event_file descriptors created in order
+ * to allow for early events to be recorded.
+ * This function is called after the tracefs has been initialized,
+ * and we now have to create the files associated to the events.
  */
-static __init void
-__trace_early_add_event_dirs(struct trace_array *tr)
+static void __trace_early_add_event_dirs(struct trace_array *tr)
 {
 	struct trace_event_file *file;
 	int ret;
@@ -3153,13 +3152,12 @@ __trace_early_add_event_dirs(struct trace_array *tr)
 }
 
 /*
- * For early boot up, the top trace array requires to have
- * a list of events that can be enabled. This must be done before
- * the filesystem is set up in order to allow events to be traced
- * early.
+ * For early boot up, the top trace array and the trace arrays created
+ * by boot-time tracing require to have a list of events that can be
+ * enabled. This must be done before the filesystem is set up in order
+ * to allow events to be traced early.
  */
-static __init void
-__trace_early_add_events(struct trace_array *tr)
+void __trace_early_add_events(struct trace_array *tr)
 {
 	struct trace_event_call *call;
 	int ret;
@@ -3290,7 +3288,11 @@ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
 		goto out;
 
 	down_write(&trace_event_sem);
-	__trace_add_event_dirs(tr);
+	/* If tr already has the event list, it is initialized in early boot. */
+	if (unlikely(!list_empty(&tr->events)))
+		__trace_early_add_event_dirs(tr);
+	else
+		__trace_add_event_dirs(tr);
 	up_write(&trace_event_sem);
 
  out:

Re: [PATCH] tracing/boot: Initialize per-instance event list in early boot

[Steven Rostedt]

On Fri, 25 Sep 2020 01:40:08 +0900
Masami Hiramatsu <mhiramat@kernel.org> wrote:

> Initialize per-instance event list in early boot time (before
> initializing instance directory on tracefs). This fixes boot-time
> tracing to correctly handle the boot-time per-instance settings.
> 

I added:

Fixes: 4114fbfd02f1 ("tracing: Enable creating new instance early boot")

-- Steve

> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
> ---
>  kernel/trace/trace.c        |    3 ++-
>  kernel/trace/trace.h        |    1 +
>  kernel/trace/trace_events.c |   30 ++++++++++++++++--------------
>  3 files changed, 19 insertions(+), 15 deletions(-)
> 
> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> index f7696db52e7d..400ed1ec3b64 100644
> --- a/kernel/trace/trace.c
> +++ b/kernel/trace/trace.c
> @@ -8700,7 +8700,8 @@ static struct trace_array *trace_array_create(const char *name)
>  		ret = trace_array_create_dir(tr);
>  		if (ret)
>  			goto out_free_tr;
> -	}
> +	} else
> +		__trace_early_add_events(tr);
>  
>  	list_add(&tr->list, &ftrace_trace_arrays);
>  
> diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
> index e1b3061ce06d..5b887cfbe5ec 100644
> --- a/kernel/trace/trace.h
> +++ b/kernel/trace/trace.h
> @@ -1658,6 +1658,7 @@ extern void trace_event_enable_tgid_record(bool enable);
>  extern int event_trace_init(void);
>  extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
>  extern int event_trace_del_tracer(struct trace_array *tr);
> +extern void __trace_early_add_events(struct trace_array *tr);
>  
>  extern struct trace_event_file *__find_event_file(struct trace_array *tr,
>  						  const char *system,
> diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
> index 720b0d72ea52..8ce334297bf3 100644
> --- a/kernel/trace/trace_events.c
> +++ b/kernel/trace/trace_events.c
> @@ -3131,14 +3131,13 @@ static inline int register_event_cmds(void) { return 0; }
>  #endif /* CONFIG_DYNAMIC_FTRACE */
>  
>  /*
> - * The top level array has already had its trace_event_file
> - * descriptors created in order to allow for early events to
> - * be recorded. This function is called after the tracefs has been
> - * initialized, and we now have to create the files associated
> - * to the events.
> + * The top level array and trace arrays created by boot-time tracing
> + * have already had its trace_event_file descriptors created in order
> + * to allow for early events to be recorded.
> + * This function is called after the tracefs has been initialized,
> + * and we now have to create the files associated to the events.
>   */
> -static __init void
> -__trace_early_add_event_dirs(struct trace_array *tr)
> +static void __trace_early_add_event_dirs(struct trace_array *tr)
>  {
>  	struct trace_event_file *file;
>  	int ret;
> @@ -3153,13 +3152,12 @@ __trace_early_add_event_dirs(struct trace_array *tr)
>  }
>  
>  /*
> - * For early boot up, the top trace array requires to have
> - * a list of events that can be enabled. This must be done before
> - * the filesystem is set up in order to allow events to be traced
> - * early.
> + * For early boot up, the top trace array and the trace arrays created
> + * by boot-time tracing require to have a list of events that can be
> + * enabled. This must be done before the filesystem is set up in order
> + * to allow events to be traced early.
>   */
> -static __init void
> -__trace_early_add_events(struct trace_array *tr)
> +void __trace_early_add_events(struct trace_array *tr)
>  {
>  	struct trace_event_call *call;
>  	int ret;
> @@ -3290,7 +3288,11 @@ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
>  		goto out;
>  
>  	down_write(&trace_event_sem);
> -	__trace_add_event_dirs(tr);
> +	/* If tr already has the event list, it is initialized in early boot. */
> +	if (unlikely(!list_empty(&tr->events)))
> +		__trace_early_add_event_dirs(tr);
> +	else
> +		__trace_add_event_dirs(tr);
>  	up_write(&trace_event_sem);
>  
>   out: