Merge tag 'trace-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "The main changes in this release include:

   - Add user space specific memory reading for kprobes

   - Allow kprobes to be executed earlier in boot

  The rest are mostly just various clean ups and small fixes"

* tag 'trace-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (33 commits)
  tracing: Make trace_get_fields() global
  tracing: Let filter_assign_type() detect FILTER_PTR_STRING
  tracing: Pass type into tracing_generic_entry_update()
  ftrace/selftest: Test if set_event/ftrace_pid exists before writing
  ftrace/selftests: Return the skip code when tracing directory not configured in kernel
  tracing/kprobe: Check registered state using kprobe
  tracing/probe: Add trace_event_call accesses APIs
  tracing/probe: Add probe event name and group name accesses APIs
  tracing/probe: Add trace flag access APIs for trace_probe
  tracing/probe: Add trace_event_file access APIs for trace_probe
  tracing/probe: Add trace_event_call register API for trace_probe
  tracing/probe: Add trace_probe init and free functions
  tracing/uprobe: Set print format when parsing command
  tracing/kprobe: Set print format right after parsed command
  kprobes: Fix to init kprobes in subsys_initcall
  tracepoint: Use struct_size() in kmalloc()
  ring-buffer: Remove HAVE_64BIT_ALIGNED_ACCESS
  ftrace: Enable trampoline when rec count returns back to one
  tracing/kprobe: Do not run kprobe boot tests if kprobe_event is on cmdline
  tracing: Make a separate config for trace event self tests
  ...

9 files changed, 101 insertions, 16 deletions

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index b6866a05edd2..ed3ecfa422e1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -194,12 +194,13 @@ PROBE ARGUMENT
 --------------
 Each probe argument follows below syntax.
 
- [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
+ [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE][@user]
 
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
 '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo (*). Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal integers (x/x8/x16/x32/x64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail)
 On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
+"@user" is a special attribute which means the LOCALVAR will be treated as a user-space memory. This is only valid for kprobe event.
 
 TYPES
 -----
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0c3b55d0617d..cd1eb73cfe83 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1562,6 +1562,17 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 		str = tmp + 1;
 	}
 
+	tmp = strchr(str, '@');
+	if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */
+		if (!user_access_is_supported()) {
+			semantic_error("ftrace does not support user access\n");
+			return -EINVAL;
+		}
+		*tmp = '\0';
+		arg->user_access = true;
+		pr_debug("user_access ");
+	}
+
 	tmp = strchr(str, ':');
 	if (tmp) {	/* Type setting */
 		*tmp = '\0';
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 05c8d571a901..96a319cd2378 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -37,6 +37,7 @@ struct probe_trace_point {
 struct probe_trace_arg_ref {
 	struct probe_trace_arg_ref	*next;	/* Next reference */
 	long				offset;	/* Offset value */
+	bool				user_access;	/* User-memory access */
 };
 
 /* kprobe-tracer and uprobe-tracer tracing argument */
@@ -82,6 +83,7 @@ struct perf_probe_arg {
 	char				*var;	/* Variable name */
 	char				*type;	/* Type name */
 	struct perf_probe_arg_field	*field;	/* Structure fields */
+	bool				user_access;	/* User-memory access */
 };
 
 /* Perf probe probing event (point + arg) */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index c2998f90b23c..5b4d49382932 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -1005,6 +1005,7 @@ enum ftrace_readme {
 	FTRACE_README_PROBE_TYPE_X = 0,
 	FTRACE_README_KRETPROBE_OFFSET,
 	FTRACE_README_UPROBE_REF_CTR,
+	FTRACE_README_USER_ACCESS,
 	FTRACE_README_END,
 };
 
@@ -1017,6 +1018,7 @@ static struct {
 	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
 	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
 	DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"),
+	DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"),
 };
 
 static bool scan_ftrace_readme(enum ftrace_readme type)
@@ -1077,3 +1079,8 @@ bool uprobe_ref_ctr_is_supported(void)
 {
 	return scan_ftrace_readme(FTRACE_README_UPROBE_REF_CTR);
 }
+
+bool user_access_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_USER_ACCESS);
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 2a249182f2a6..986c1c94f64f 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -70,6 +70,7 @@ int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
 bool kretprobe_offset_is_supported(void);
 bool uprobe_ref_ctr_is_supported(void);
+bool user_access_is_supported(void);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused)
 {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 7d8c99734928..025fc4491993 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -280,7 +280,7 @@ static_var:
 
 static int convert_variable_type(Dwarf_Die *vr_die,
 				 struct probe_trace_arg *tvar,
-				 const char *cast)
+				 const char *cast, bool user_access)
 {
 	struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
 	Dwarf_Die type;
@@ -320,7 +320,8 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	pr_debug("%s type is %s.\n",
 		 dwarf_diename(vr_die), dwarf_diename(&type));
 
-	if (cast && strcmp(cast, "string") == 0) {	/* String type */
+	if (cast && (!strcmp(cast, "string") || !strcmp(cast, "ustring"))) {
+		/* String type */
 		ret = dwarf_tag(&type);
 		if (ret != DW_TAG_pointer_type &&
 		    ret != DW_TAG_array_type) {
@@ -343,6 +344,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 				pr_warning("Out of memory error\n");
 				return -ENOMEM;
 			}
+			(*ref_ptr)->user_access = user_access;
 		}
 		if (!die_compare_name(&type, "char") &&
 		    !die_compare_name(&type, "unsigned char")) {
@@ -397,7 +399,7 @@ formatted:
 static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 				    struct perf_probe_arg_field *field,
 				    struct probe_trace_arg_ref **ref_ptr,
-				    Dwarf_Die *die_mem)
+				    Dwarf_Die *die_mem, bool user_access)
 {
 	struct probe_trace_arg_ref *ref = *ref_ptr;
 	Dwarf_Die type;
@@ -434,6 +436,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 				*ref_ptr = ref;
 		}
 		ref->offset += dwarf_bytesize(&type) * field->index;
+		ref->user_access = user_access;
 		goto next;
 	} else if (tag == DW_TAG_pointer_type) {
 		/* Check the pointer and dereference */
@@ -505,17 +508,18 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 		}
 	}
 	ref->offset += (long)offs;
+	ref->user_access = user_access;
 
 	/* If this member is unnamed, we need to reuse this field */
 	if (!dwarf_diename(die_mem))
 		return convert_variable_fields(die_mem, varname, field,
-						&ref, die_mem);
+						&ref, die_mem, user_access);
 
 next:
 	/* Converting next field */
 	if (field->next)
 		return convert_variable_fields(die_mem, field->name,
-					field->next, &ref, die_mem);
+				field->next, &ref, die_mem, user_access);
 	else
 		return 0;
 }
@@ -541,11 +545,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
 					      pf->pvar->field, &pf->tvar->ref,
-					      &die_mem);
+					      &die_mem, pf->pvar->user_access);
 		vr_die = &die_mem;
 	}
 	if (ret == 0)
-		ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type);
+		ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type,
+					    pf->pvar->user_access);
 	/* *expr will be cached in libdw. Don't free it. */
 	return ret;
 }
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 6d5e9e87c4b7..063ecb290a5a 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -23,9 +23,15 @@ echo "		            If <dir> is -, all logs output in console only"
 exit $1
 }
 
+# default error
+err_ret=1
+
+# kselftest skip code is 4
+err_skip=4
+
 errexit() { # message
   echo "Error: $1" 1>&2
-  exit 1
+  exit $err_ret
 }
 
 # Ensuring user privilege
@@ -116,11 +122,31 @@ parse_opts() { # opts
 }
 
 # Parameters
-DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1`
-if [ -z "$DEBUGFS_DIR" ]; then
-    TRACING_DIR=`grep tracefs /proc/mounts | cut -f2 -d' ' | head -1`
-else
-    TRACING_DIR=$DEBUGFS_DIR/tracing
+TRACING_DIR=`grep tracefs /proc/mounts | cut -f2 -d' ' | head -1`
+if [ -z "$TRACING_DIR" ]; then
+    DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1`
+    if [ -z "$DEBUGFS_DIR" ]; then
+	# If tracefs exists, then so does /sys/kernel/tracing
+	if [ -d "/sys/kernel/tracing" ]; then
+	    mount -t tracefs nodev /sys/kernel/tracing ||
+	      errexit "Failed to mount /sys/kernel/tracing"
+	    TRACING_DIR="/sys/kernel/tracing"
+	# If debugfs exists, then so does /sys/kernel/debug
+	elif [ -d "/sys/kernel/debug" ]; then
+	    mount -t debugfs nodev /sys/kernel/debug ||
+	      errexit "Failed to mount /sys/kernel/debug"
+	    TRACING_DIR="/sys/kernel/debug/tracing"
+	else
+	    err_ret=$err_skip
+	    errexit "debugfs and tracefs are not configured in this kernel"
+	fi
+    else
+	TRACING_DIR="$DEBUGFS_DIR/tracing"
+    fi
+fi
+if [ ! -d "$TRACING_DIR" ]; then
+    err_ret=$err_skip
+    errexit "ftrace is not configured in this kernel"
 fi
 
 TOP_DIR=`absdir $0`
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index 779ec11f61bd..1d96c5f7e402 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -91,8 +91,8 @@ initialize_ftrace() { # Reset ftrace to initial-state
     reset_events_filter
     reset_ftrace_filter
     disable_events
-    echo > set_event_pid	# event tracer is always on
-    echo > set_ftrace_pid
+    [ -f set_event_pid ] && echo > set_event_pid
+    [ -f set_ftrace_pid ] && echo > set_ftrace_pid
     [ -f set_ftrace_filter ] && echo | tee set_ftrace_*
     [ -f set_graph_function ] && echo | tee set_graph_*
     [ -f stack_trace_filter ] && echo > stack_trace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
new file mode 100644
index 000000000000..0f60087583d8
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event user-memory access
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+grep -q '\$arg<N>' README || exit_unresolved # depends on arch
+grep -A10 "fetcharg:" README | grep -q 'ustring' || exit_unsupported
+grep -A10 "fetcharg:" README | grep -q '\[u\]<offset>' || exit_unsupported
+
+:;: "user-memory access syntax and ustring working on user memory";:
+echo 'p:myevent do_sys_open path=+0($arg2):ustring path2=+u0($arg2):string' \
+	> kprobe_events
+
+grep myevent kprobe_events | \
+	grep -q 'path=+0($arg2):ustring path2=+u0($arg2):string'
+echo 1 > events/kprobes/myevent/enable
+echo > /dev/null
+echo 0 > events/kprobes/myevent/enable
+
+grep myevent trace | grep -q 'path="/dev/null" path2="/dev/null"'
+
+:;: "user-memory access syntax and ustring not working with kernel memory";:
+echo 'p:myevent vfs_symlink path=+0($arg3):ustring path2=+u0($arg3):string' \
+	> kprobe_events
+echo 1 > events/kprobes/myevent/enable
+ln -s foo $TMPDIR/bar
+echo 0 > events/kprobes/myevent/enable
+
+grep myevent trace | grep -q 'path=(fault) path2=(fault)'
+
+exit 0