ftrace: Support full glob matching

Use glob_match() to support flexible glob wildcards (*,?) and character classes ([) for ftrace.
Since the full glob matching is slower than the current partial matching routines(*pat, pat*, *pat*), this leaves those routines and just add MATCH_GLOB for complex glob expression.

e.g.
----
[root@localhost tracing]# echo 'sched*group' > set_ftrace_filter [root@localhost tracing]# cat set_ftrace_filter sched_free_group
sched_change_group
sched_create_group
sched_online_group
sched_destroy_group
sched_offline_group
[root@localhost tracing]# echo '[Ss]y[Ss]_*' > set_ftrace_filter [root@localhost tracing]# head set_ftrace_filter sys_arch_prctl
sys_rt_sigreturn
sys_ioperm
SyS_iopl
sys_modify_ldt
SyS_mmap
SyS_set_thread_area
SyS_get_thread_area
SyS_set_tid_address
sys_fork
----

Signed-off-by Masami Hiramatsu <[email protected]>

Quoted 31 lines · On Wed, 5 Oct 2016 20:58:15 +0900 Masami Hiramatsu <[email protected]> wrote:

Use glob_match() to support flexible glob wildcards (*,?) and character classes ([) for ftrace.
Since the full glob matching is slower than the current partial matching routines(*pat, pat*, *pat*), this leaves those routines and just add MATCH_GLOB for complex glob expression.

e.g.
----
[root@localhost tracing]# echo 'sched*group' > set_ftrace_filter [root@localhost tracing]# cat set_ftrace_filter sched_free_group
sched_change_group
sched_create_group
sched_online_group
sched_destroy_group
sched_offline_group
[root@localhost tracing]# echo '[Ss]y[Ss]_*' > set_ftrace_filter [root@localhost tracing]# head set_ftrace_filter sys_arch_prctl
sys_rt_sigreturn
sys_ioperm
SyS_iopl
sys_modify_ldt
SyS_mmap
SyS_set_thread_area
SyS_get_thread_area
SyS_set_tid_address
sys_fork
----

Quoted 1 line

Signed-off-by Masami Hiramatsu <[email protected]>

Nice! Although, I probably wont get to look at this till I get back from Berlin. Please send me a friendly "ping" on the 17th.

I'll still add it to my new "todo" folder. Since, just marking patches in my inbox as todo hasn't been working out for me, I've created a separate folder for ftrace patches.

Thanks!

-- Steve

Use glob_match() to support flexible glob wildcards (*,?) and character classes ([) for ftrace.
Since the full glob matching is slower than the current partial matching routines(*pat, pat*, *pat*), this leaves those routines and just add MATCH_GLOB for complex glob expression.

e.g.
----
[root@localhost tracing]# echo 'sched*group' > set_ftrace_filter [root@localhost tracing]# cat set_ftrace_filter sched_free_group
sched_change_group
sched_create_group
sched_online_group
sched_destroy_group
sched_offline_group
[root@localhost tracing]# echo '[Ss]y[Ss]_*' > set_ftrace_filter [root@localhost tracing]# head set_ftrace_filter sys_arch_prctl
sys_rt_sigreturn
sys_ioperm
SyS_iopl
sys_modify_ldt
SyS_mmap
SyS_set_thread_area
SyS_get_thread_area
SyS_set_tid_address
sys_fork
----

Signed-off-by Masami Hiramatsu <[email protected]>

---
 Documentation/trace/events.txt     |    9 +++------
 Documentation/trace/ftrace.txt     |    9 +++------
 kernel/trace/Kconfig               |    2 ++
 kernel/trace/ftrace.c              |    4 ++++
 kernel/trace/trace.c               |    2 +-
 kernel/trace/trace.h               |    2 ++
 kernel/trace/trace_events_filter.c |   17 ++++++++++++++++-
 7 files changed, 31 insertions(+), 14 deletions(-)

Documentation/trace/events.txt +3 -6

index 08d74d7..2cc08d4 100644
@@ -189,16 +189,13 @@ And for string fields they are:
 
 ==, !=, ~
 
-The glob (~) only accepts a wild card character (*) at the start and or
-end of the string. For example:
+The glob (~) accepts a wild card character (*,?) and character classes
+([). For example:
 
   prev_comm ~ "*sh"
   prev_comm ~ "sh*"
   prev_comm ~ "*sh*"
-
-But does not allow for it to be within the string:
-
-  prev_comm ~ "ba*sh"   <-- is invalid
+  prev_comm ~ "ba*sh"
 
 5.2 Setting filters
 -------------------

Documentation/trace/ftrace.txt +3 -6

index a6b3705..b26abc7 100644
@@ -2218,16 +2218,13 @@ hrtimer_interrupt
 sys_nanosleep
 
 
-Perhaps this is not enough. The filters also allow simple wild
-cards. Only the following are currently available
+Perhaps this is not enough. The filters also allow glob(7) matching.
 
   <match>*  - will match functions that begin with <match>
   *<match>  - will match functions that end with <match>
   *<match>* - will match functions that have <match> in it
-
-These are the only wild cards which are supported.
-
-  <match>*<match> will not work.
+  <match1>*<match2> - will match functions that begin with
+                      <match1> and end with <match2>
 
 Note: It is better to use quotes to enclose the wild cards,
       otherwise the shell may expand the parameters into names

kernel/trace/Kconfig +2 -0

index ba33267..aa6eb15 100644
@@ -70,6 +70,7 @@ config FTRACE_NMI_ENTER
 
 config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
+        select GLOB
 	bool
 
 config CONTEXT_SWITCH_TRACER

@@ -133,6 +134,7 @@ config FUNCTION_TRACER
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
+        select GLOB
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation

kernel/trace/ftrace.c +4 -0

index 84752c8..5741184 100644
@@ -3493,6 +3493,10 @@ static int ftrace_match(char *str, struct ftrace_glob *g)
 		    memcmp(str + slen - g->len, g->search, g->len) == 0)
 			matched = 1;
 		break;
+	case MATCH_GLOB:
+		if (glob_match(g->search, str))
+			matched = 1;
+		break;
 	}
 
 	return matched;

kernel/trace/trace.c +1 -1

index 37824d9..ae343e7 100644
@@ -4065,7 +4065,7 @@ static const char readme_msg[] =
 	"\n  available_filter_functions - list of functions that can be filtered on\n"
 	"  set_ftrace_filter\t- echo function name in here to only trace these\n"
 	"\t\t\t  functions\n"
-	"\t     accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+	"\t     accepts: func_full_name or glob-matching-pattern\n"
 	"\t     modules: Can select a group via module\n"
 	"\t      Format: :mod:<module-name>\n"
 	"\t     example: echo :mod:ext3 > set_ftrace_filter\n"

kernel/trace/trace.h +2 -0

index f783df4..eac2eda 100644
@@ -15,6 +15,7 @@
 #include <linux/trace_events.h>
 #include <linux/compiler.h>
 #include <linux/trace_seq.h>
+#include <linux/glob.h>
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */

@@ -1252,6 +1253,7 @@ enum regex_type {
 	MATCH_FRONT_ONLY,
 	MATCH_MIDDLE_ONLY,
 	MATCH_END_ONLY,
+	MATCH_GLOB,
 };
 
 struct regex {

kernel/trace/trace_events_filter.c +16 -1

index 9daa9b3..e1c7e2c 100644
@@ -344,6 +344,12 @@ static int regex_match_end(char *str, struct regex *r, int len)
 	return 0;
 }
 
+static int regex_match_glob(char *str, struct regex *r, int len __maybe_unused)
+{
+	if (glob_match(r->pattern, str))
+		return 1;
+	return 0;
+}
 /**
  * filter_parse_regex - parse a basic regex
  * @buff:   the raw regex

@@ -380,14 +386,20 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
 			if (!i) {
 				*search = buff + 1;
 				type = MATCH_END_ONLY;
-			} else {
+			} else if (i == len - 1) {
 				if (type == MATCH_END_ONLY)
 					type = MATCH_MIDDLE_ONLY;
 				else
 					type = MATCH_FRONT_ONLY;
 				buff[i] = 0;
 				break;
+			} else {	/* pattern continues, use full glob */
+				type = MATCH_GLOB;
+				break;
 			}
+		} else if (strchr("[?\\", buff[i])) {
+			type = MATCH_GLOB;
+			break;
 		}
 	}
 

@@ -420,6 +432,9 @@ static void filter_build_regex(struct filter_pred *pred)
 	case MATCH_END_ONLY:
 		r->match = regex_match_end;
 		break;
+	case MATCH_GLOB:
+		r->match = regex_match_glob;
+		break;
 	}
 
 	pred->not ^= not;

Use glob_match() to support flexible glob wildcards (*,?) and character classes ([) for ftrace.
Since the full glob matching is slower than the current partial matching routines(*pat, pat*, *pat*), this leaves those routines and just add MATCH_GLOB for complex glob expression.

e.g.
----
[root@localhost tracing]# echo 'sched*group' > set_ftrace_filter [root@localhost tracing]# cat set_ftrace_filter sched_free_group
sched_change_group
sched_create_group
sched_online_group
sched_destroy_group
sched_offline_group
[root@localhost tracing]# echo '[Ss]y[Ss]_*' > set_ftrace_filter [root@localhost tracing]# head set_ftrace_filter sys_arch_prctl
sys_rt_sigreturn
sys_ioperm
SyS_iopl
sys_modify_ldt
SyS_mmap
SyS_set_thread_area
SyS_get_thread_area
SyS_set_tid_address
sys_fork
----

Signed-off-by Masami Hiramatsu <[email protected]>

---
 Documentation/trace/events.txt     |    9 +++------
 Documentation/trace/ftrace.txt     |    9 +++------
 kernel/trace/Kconfig               |    2 ++
 kernel/trace/ftrace.c              |    4 ++++
 kernel/trace/trace.c               |    2 +-
 kernel/trace/trace.h               |    2 ++
 kernel/trace/trace_events_filter.c |   17 ++++++++++++++++-
 7 files changed, 31 insertions(+), 14 deletions(-)

Documentation/trace/events.txt +3 -6

index 08d74d7..2cc08d4 100644
@@ -189,16 +189,13 @@ And for string fields they are:
 
 ==, !=, ~
 
-The glob (~) only accepts a wild card character (*) at the start and or
-end of the string. For example:
+The glob (~) accepts a wild card character (*,?) and character classes
+([). For example:
 
   prev_comm ~ "*sh"
   prev_comm ~ "sh*"
   prev_comm ~ "*sh*"
-
-But does not allow for it to be within the string:
-
-  prev_comm ~ "ba*sh"   <-- is invalid
+  prev_comm ~ "ba*sh"
 
 5.2 Setting filters
 -------------------

Documentation/trace/ftrace.txt +3 -6

index a6b3705..b26abc7 100644
@@ -2218,16 +2218,13 @@ hrtimer_interrupt
 sys_nanosleep
 
 
-Perhaps this is not enough. The filters also allow simple wild
-cards. Only the following are currently available
+Perhaps this is not enough. The filters also allow glob(7) matching.
 
   <match>*  - will match functions that begin with <match>
   *<match>  - will match functions that end with <match>
   *<match>* - will match functions that have <match> in it
-
-These are the only wild cards which are supported.
-
-  <match>*<match> will not work.
+  <match1>*<match2> - will match functions that begin with
+                      <match1> and end with <match2>
 
 Note: It is better to use quotes to enclose the wild cards,
       otherwise the shell may expand the parameters into names

kernel/trace/Kconfig +2 -0

index ba33267..aa6eb15 100644
@@ -70,6 +70,7 @@ config FTRACE_NMI_ENTER
 
 config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
+        select GLOB
 	bool
 
 config CONTEXT_SWITCH_TRACER

@@ -133,6 +134,7 @@ config FUNCTION_TRACER
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
+        select GLOB
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation

kernel/trace/ftrace.c +4 -0

index 84752c8..5741184 100644
@@ -3493,6 +3493,10 @@ static int ftrace_match(char *str, struct ftrace_glob *g)
 		    memcmp(str + slen - g->len, g->search, g->len) == 0)
 			matched = 1;
 		break;
+	case MATCH_GLOB:
+		if (glob_match(g->search, str))
+			matched = 1;
+		break;
 	}
 
 	return matched;

kernel/trace/trace.c +1 -1

index 37824d9..ae343e7 100644
@@ -4065,7 +4065,7 @@ static const char readme_msg[] =
 	"\n  available_filter_functions - list of functions that can be filtered on\n"
 	"  set_ftrace_filter\t- echo function name in here to only trace these\n"
 	"\t\t\t  functions\n"
-	"\t     accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+	"\t     accepts: func_full_name or glob-matching-pattern\n"
 	"\t     modules: Can select a group via module\n"
 	"\t      Format: :mod:<module-name>\n"
 	"\t     example: echo :mod:ext3 > set_ftrace_filter\n"

kernel/trace/trace.h +2 -0

index f783df4..eac2eda 100644
@@ -15,6 +15,7 @@
 #include <linux/trace_events.h>
 #include <linux/compiler.h>
 #include <linux/trace_seq.h>
+#include <linux/glob.h>
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */

@@ -1252,6 +1253,7 @@ enum regex_type {
 	MATCH_FRONT_ONLY,
 	MATCH_MIDDLE_ONLY,
 	MATCH_END_ONLY,
+	MATCH_GLOB,
 };
 
 struct regex {

kernel/trace/trace_events_filter.c +16 -1

index 9daa9b3..e1c7e2c 100644
@@ -344,6 +344,12 @@ static int regex_match_end(char *str, struct regex *r, int len)
 	return 0;
 }
 
+static int regex_match_glob(char *str, struct regex *r, int len __maybe_unused)
+{
+	if (glob_match(r->pattern, str))
+		return 1;
+	return 0;
+}
 /**
  * filter_parse_regex - parse a basic regex
  * @buff:   the raw regex

@@ -380,14 +386,20 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
 			if (!i) {
 				*search = buff + 1;
 				type = MATCH_END_ONLY;
-			} else {
+			} else if (i == len - 1) {
 				if (type == MATCH_END_ONLY)
 					type = MATCH_MIDDLE_ONLY;
 				else
 					type = MATCH_FRONT_ONLY;
 				buff[i] = 0;
 				break;
+			} else {	/* pattern continues, use full glob */
+				type = MATCH_GLOB;
+				break;
 			}
+		} else if (strchr("[?\\", buff[i])) {
+			type = MATCH_GLOB;
+			break;
 		}
 	}
 

@@ -420,6 +432,9 @@ static void filter_build_regex(struct filter_pred *pred)
 	case MATCH_END_ONLY:
 		r->match = regex_match_end;
 		break;
+	case MATCH_GLOB:
+		r->match = regex_match_glob;
+		break;
 	}
 
 	pred->not ^= not;