perf probe: Add lazy line matching support

------------

Probe points are defined by following syntax.

 "[EVENT=]FUNC[+OFFS|:RLN|%return][@SRC]|SRC:ALN [ARG ...]"

    1) Define event based on function name

     [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]

    2) Define event based on source file with line number

     [EVENT=]SRC:ALN [ARG ...]

    3) Define event based on source file with lazy pattern

     [EVENT=]SRC;PTN [ARG ...]

'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.

'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, 'RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. In addition, 'SRC' specifies a source file which has that function.

It is also possible to specify a probe point by the source line number by using 'SRC:ALN' syntax, where 'SRC' is the source file path and 'ALN' is the line number.

'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.

It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.

'ARG' specifies the arguments of this probe point. You can use the name of local variable, or kprobe-tracer argument format (e.g. $retval, %ax, etc).

LINE SYNTAX

many lines to show by using 'NUM'.

So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.

LAZY MATCHING

-------------

 The lazy line matching is similar to glob matching but ignoring spaces in both of pattern and target. So this accepts wildcards('*', '?') and character classes(e.g. [a-z], [!A-Z]).

e.g.

 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on.

This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)

EXAMPLES

--------

Display which lines in schedule() can be probed:

 this will add one or more probes which has the name start with "schedule".

 Add probes on lines in schedule() function which calls update_rq_clock().

 ./perf probe 'schedule;update_rq_clock*'

 or

 ./perf probe --add='schedule;update_rq_clock*'

Delete all probes on schedule().

 ./perf probe --del='schedule*'

		opt_del_probe_event),

	OPT_CALLBACK('a', "add", NULL,

#ifdef NO_DWARF_SUPPORT

		"[EVENT=]FUNC[+OFFS|%return] [ARG ...]",

		"[EVENT=]FUNC[+OFF|%return] [ARG ...]",

#else

		"[EVENT=]FUNC[+OFFS|%return|:RLN][@SRC]|SRC:ALN [ARG ...]",

		"[EVENT=]FUNC[+OFF|%return|:RL|;PT][@SRC]|SRC:AL|SRC;PT"

		" [ARG ...]",

#endif

		"probe point definition, where\n"

		"\t\tGROUP:\tGroup name (optional)\n"

		"\t\tEVENT:\tEvent name\n"

		"\t\tFUNC:\tFunction name\n"

		"\t\tOFFS:\tOffset from function entry (in byte)\n"

		"\t\tOFF:\tOffset from function entry (in byte)\n"

		"\t\t%return:\tPut the probe at function return\n"

#ifdef NO_DWARF_SUPPORT

		"\t\tARG:\tProbe argument (only \n"

#else

		"\t\tSRC:\tSource code path\n"

		"\t\tRLN:\tRelative line number from function entry.\n"

		"\t\tALN:\tAbsolute line number in file.\n"

		"\t\tRL:\tRelative line number from function entry.\n"

		"\t\tAL:\tAbsolute line number in file.\n"

		"\t\tPT:\tLazy expression of line code.\n"

		"\t\tARG:\tProbe argument (local variable name or\n"

#endif

		"\t\t\tkprobe-tracer argument format.)\n",

	char c, nc = 0;

	/*

	 * <Syntax>

	 * perf probe [EVENT=]SRC:LN

	 * perf probe [EVENT=]FUNC[+OFFS|%return][@SRC]

	 * perf probe [EVENT=]SRC[:LN|;PTN]

	 * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]

	 *

	 * TODO:Group name support

	 */

	ptr = strchr(arg, '=');

	if (ptr) {	/* Event name */

	ptr = strpbrk(arg, ";=@+%");

	if (ptr && *ptr == '=') {	/* Event name */

		*ptr = '\0';

		tmp = ptr + 1;

		ptr = strchr(arg, ':');

		arg = tmp;

	}

	ptr = strpbrk(arg, ":+@%");

	ptr = strpbrk(arg, ";:+@%");

	if (ptr) {

		nc = *ptr;

		*ptr++ = '\0';

	while (ptr) {

		arg = ptr;

		c = nc;

		ptr = strpbrk(arg, ":+@%");

		if (c == ';') {	/* Lazy pattern must be the last part */

			pp->lazy_line = strdup(arg);

			break;

		}

		ptr = strpbrk(arg, ";:+@%");

		if (ptr) {

			nc = *ptr;

			*ptr++ = '\0';

		case ':':	/* Line number */

			pp->line = strtoul(arg, &tmp, 0);

			if (*tmp != '\0')

				semantic_error("There is non-digit charactor"

				semantic_error("There is non-digit char"

					       " in line number.");

			break;

		case '+':	/* Byte offset from a symbol */

			pp->offset = strtoul(arg, &tmp, 0);

			if (*tmp != '\0')

				semantic_error("There is non-digit charactor"

				semantic_error("There is non-digit character"

						" in offset.");

			break;

		case '@':	/* File name */

				semantic_error("SRC@SRC is not allowed.");

			pp->file = strdup(arg);

			DIE_IF(pp->file == NULL);

			if (ptr)

				semantic_error("@SRC must be the last "

					       "option.");

			break;

		case '%':	/* Probe places */

			if (strcmp(arg, "return") == 0) {

	}

	/* Exclusion check */

	if (pp->lazy_line && pp->line)

		semantic_error("Lazy pattern can't be used with line number.");

	if (pp->lazy_line && pp->offset)

		semantic_error("Lazy pattern can't be used with offset.");

	if (pp->line && pp->offset)

		semantic_error("Offset can't be used with line number.");

	if (!pp->line && pp->file && !pp->function)

		semantic_error("File always requires line number.");

	if (!pp->line && !pp->lazy_line && pp->file && !pp->function)

		semantic_error("File always requires line number or "

			       "lazy pattern.");

	if (pp->offset && !pp->function)

		semantic_error("Offset requires an entry function.");

	if (pp->retprobe && !pp->function)

		semantic_error("Return probe requires an entry function.");

	if ((pp->offset || pp->line) && pp->retprobe)

		semantic_error("Offset/Line can't be used with return probe.");

	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe)

		semantic_error("Offset/Line/Lazy pattern can't be used with "

			       "return probe.");

	pr_debug("symbol:%s file:%s line:%d offset:%d, return:%d\n",

		 pp->function, pp->file, pp->line, pp->offset, pp->retprobe);

	pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n",

		 pp->function, pp->file, pp->line, pp->offset, pp->retprobe,

		 pp->lazy_line);

}

/* Parse perf-probe event definition */

		free(pp->function);

	if (pp->file)

		free(pp->file);

	if (pp->lazy_line)

		free(pp->lazy_line);

	for (i = 0; i < pp->nr_args; i++)

		free(pp->args[i]);

	if (pp->args)

#include <stdarg.h>

#include <ctype.h>

#include "string.h"

#include "event.h"

#include "debug.h"

#include "util.h"

	return 0;

}

/* Find the fileno of the target file. */

static int cu_find_fileno(Dwarf_Die *cu_die, const char *fname)

/* Line number list operations */

/* Add a line to line number list */

static void line_list__add_line(struct list_head *head, unsigned int line)

{

	struct line_node *ln;

	struct list_head *p;

	/* Reverse search, because new line will be the last one */

	list_for_each_entry_reverse(ln, head, list) {

		if (ln->line < line) {

			p = &ln->list;

			goto found;

		} else if (ln->line == line)	/* Already exist */

			return ;

	}

	/* List is empty, or the smallest entry */

	p = head;

found:

	pr_debug("line list: add a line %u\n", line);

	ln = zalloc(sizeof(struct line_node));

	DIE_IF(ln == NULL);

	ln->line = line;

	INIT_LIST_HEAD(&ln->list);

	list_add(&ln->list, p);

}

/* Check if the line in line number list */

static int line_list__has_line(struct list_head *head, unsigned int line)

{

	struct line_node *ln;

	/* Reverse search, because new line will be the last one */

	list_for_each_entry(ln, head, list)

		if (ln->line == line)

			return 1;

	return 0;

}

/* Init line number list */

static void line_list__init(struct list_head *head)

{

	INIT_LIST_HEAD(head);

}

/* Free line number list */

static void line_list__free(struct list_head *head)

{

	struct line_node *ln;

	while (!list_empty(head)) {

		ln = list_first_entry(head, struct line_node, list);

		list_del(&ln->list);

		free(ln);

	}

}

/* Dwarf wrappers */

/* Find the realpath of the target file. */

static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)

{

	Dwarf_Files *files;

	size_t nfiles, i;

	int ret;

	if (!fname)

		return -EINVAL;

		return NULL;

	ret = dwarf_getsrcfiles(cu_die, &files, &nfiles);

	if (ret == 0) {

	if (ret != 0)

		return NULL;

	for (i = 0; i < nfiles; i++) {

		src = dwarf_filesrc(files, i, NULL, NULL);

			if (strtailcmp(src, fname) == 0) {

				ret = (int)i;	/*???: +1 or not?*/

		if (strtailcmp(src, fname) == 0)

			break;

	}

		}

		if (ret)

			pr_debug("found fno: %d\n", ret);

	}

	return ret;

	return src;

}

struct __addr_die_search_param {

	}

}

/* Find lines which match lazy pattern */

static int find_lazy_match_lines(struct list_head *head,

				 const char *fname, const char *pat)

{

	char *fbuf, *p1, *p2;

	int fd, line, nlines = 0;

	struct stat st;

	fd = open(fname, O_RDONLY);

	if (fd < 0)

		die("failed to open %s", fname);

	DIE_IF(fstat(fd, &st) < 0);

	fbuf = malloc(st.st_size + 2);

	DIE_IF(fbuf == NULL);

	DIE_IF(read(fd, fbuf, st.st_size) < 0);

	close(fd);

	fbuf[st.st_size] = '\n';	/* Dummy line */

	fbuf[st.st_size + 1] = '\0';

	p1 = fbuf;

	line = 1;

	while ((p2 = strchr(p1, '\n')) != NULL) {

		*p2 = '\0';

		if (strlazymatch(p1, pat)) {

			line_list__add_line(head, line);

			nlines++;

		}

		line++;

		p1 = p2 + 1;

	}

	free(fbuf);

	return nlines;

}

/* Find probe points from lazy pattern  */

static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)

{

	Dwarf_Lines *lines;

	Dwarf_Line *line;

	size_t nlines, i;

	Dwarf_Addr addr;

	Dwarf_Die die_mem;

	int lineno;

	int ret;

	if (list_empty(&pf->lcache)) {

		/* Matching lazy line pattern */

		ret = find_lazy_match_lines(&pf->lcache, pf->fname,

					    pf->pp->lazy_line);

		if (ret <= 0)

			die("No matched lines found in %s.", pf->fname);

	}

	ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);

	DIE_IF(ret != 0);

	for (i = 0; i < nlines; i++) {

		line = dwarf_onesrcline(lines, i);

		dwarf_lineno(line, &lineno);

		if (!line_list__has_line(&pf->lcache, lineno))

			continue;

		/* TODO: Get fileno from line, but how? */

		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)

			continue;

		ret = dwarf_lineaddr(line, &addr);

		DIE_IF(ret != 0);

		if (sp_die) {

			/* Address filtering 1: does sp_die include addr? */

			if (!dwarf_haspc(sp_die, addr))

				continue;

			/* Address filtering 2: No child include addr? */

			if (die_get_inlinefunc(sp_die, addr, &die_mem))

				continue;

		}

		pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n",

			 (int)i, lineno, (unsigned long long)addr);

		pf->addr = addr;

		show_probe_point(sp_die, pf);

		/* Continuing, because target line might be inlined. */

	}

	/* TODO: deallocate lines, but how? */

}

static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)

{

	struct probe_finder *pf = (struct probe_finder *)data;

	struct probe_point *pp = pf->pp;

	if (pp->lazy_line)

		find_probe_point_lazy(in_die, pf);

	else {

		/* Get probe address */

		pf->addr = die_get_entrypc(in_die);

		pf->addr += pp->offset;

	pr_debug("found inline addr: 0x%jx\n", (uintmax_t)pf->addr);

		pr_debug("found inline addr: 0x%jx\n",

			 (uintmax_t)pf->addr);

		show_probe_point(in_die, pf);

	}

	return DWARF_CB_OK;

}

	    die_compare_name(sp_die, pp->function) != 0)

		return 0;

	if (pp->line) { /* Function relative line */

	pf->fname = dwarf_decl_file(sp_die);

	if (pp->line) { /* Function relative line */

		dwarf_decl_line(sp_die, &pf->lno);

		pf->lno += pp->line;

		find_probe_point_by_line(pf);

	} else if (!dwarf_func_inline(sp_die)) {

		/* Real function */

		if (pp->lazy_line)

			find_probe_point_lazy(sp_die, pf);

		else {

			pf->addr = die_get_entrypc(sp_die);

			pf->addr += pp->offset;

			/* TODO: Check the address in this function */

			show_probe_point(sp_die, pf);

		}

	} else

		/* Inlined function: search instances */

		dwarf_func_inline_instances(sp_die, probe_point_inline_cb, pf);

	size_t cuhl;

	Dwarf_Die *diep;

	Dwarf *dbg;

	int fno = 0;

	dbg = dwarf_begin(fd, DWARF_C_READ);

	if (!dbg)

	pp->found = 0;

	off = 0;

	line_list__init(&pf.lcache);

	/* Loop on CUs (Compilation Unit) */

	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {

		/* Get the DIE(Debugging Information Entry) of this CU */

		/* Check if target file is included. */

		if (pp->file)

			fno = cu_find_fileno(&pf.cu_die, pp->file);

			pf.fname = cu_find_realpath(&pf.cu_die, pp->file);

		else

			fno = 0;

			pf.fname = NULL;

		if (!pp->file || fno) {

		if (!pp->file || pf.fname) {

			/* Save CU base address (for frame_base) */

			ret = dwarf_lowpc(&pf.cu_die, &pf.cu_base);

			if (ret != 0)

				pf.cu_base = 0;

			if (pp->function)

				find_probe_point_by_func(&pf);

			else if (pp->lazy_line)

				find_probe_point_lazy(NULL, &pf);

			else {

				pf.lno = pp->line;

				find_probe_point_by_line(&pf);

		}

		off = noff;

	}

	line_list__free(&pf.lcache);

	dwarf_end(dbg);

	return pp->found;

}

static void line_range_add_line(struct line_range *lr, unsigned int line)

{

	struct line_node *ln;

	struct list_head *p;

	/* Reverse search, because new line will be the last one */

	list_for_each_entry_reverse(ln, &lr->line_list, list) {

		if (ln->line < line) {

			p = &ln->list;

			goto found;

		} else if (ln->line == line)	/* Already exist */

			return ;

	}

	/* List is empty, or the smallest entry */

	p = &lr->line_list;

found:

	pr_debug("Debug: add a line %u\n", line);

	ln = zalloc(sizeof(struct line_node));

	DIE_IF(ln == NULL);

	ln->line = line;

	INIT_LIST_HEAD(&ln->list);

	list_add(&ln->list, p);

}

/* Find line range from its line number */

static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)

{

	const char *src;

	Dwarf_Die die_mem;

	INIT_LIST_HEAD(&lf->lr->line_list);

	line_list__init(&lf->lr->line_list);

	ret = dwarf_getsrclines(&lf->cu_die, &lines, &nlines);

	DIE_IF(ret != 0);

		/* Copy real path */

		if (!lf->lr->path)

			lf->lr->path = strdup(src);

		line_range_add_line(lf->lr, (unsigned int)lineno);

		line_list__add_line(&lf->lr->line_list, (unsigned int)lineno);

	}

	/* Update status */

	if (!list_empty(&lf->lr->line_list))

	size_t cuhl;

	Dwarf_Die *diep;

	Dwarf *dbg;

	int fno;

	dbg = dwarf_begin(fd, DWARF_C_READ);

	if (!dbg)

		/* Check if target file is included. */

		if (lr->file)

			fno = cu_find_fileno(&lf.cu_die, lr->file);

			lf.fname = cu_find_realpath(&lf.cu_die, lr->file);

		else

			fno = 0;

			lf.fname = 0;

		if (!lr->file || fno) {

		if (!lr->file || lf.fname) {

			if (lr->function)

				find_line_range_by_func(&lf);

			else {

				lf.fname = lr->file;

				lf.lno_s = lr->start;

				if (!lr->end)

					lf.lno_e = INT_MAX;

	/* Inputs */

	char			*file;			/* File name */

	int			line;			/* Line number */

	char			*lazy_line;		/* Lazy line pattern */

	char			*function;		/* Function name */

	int			offset;			/* Offset bytes */

	const char		*var;		/* Current variable name */

	char			*buf;		/* Current output buffer */

	int			len;		/* Length of output buffer */

	struct list_head	lcache;		/* Line cache for lazy match */

};

struct line_finder {