Merge branch 'perf-probes-for-linus-2' of...

Merge branch 'perf-probes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-probes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Issue at least one memory barrier in stop_machine_text_poke()
  perf probe: Correct probe syntax on command line help
  perf probe: Add lazy line matching support
  perf probe: Show more lines after last line
  perf probe: Check function address range strictly in line finder
  perf probe: Use libdw callback routines
  perf probe: Use elfutils-libdw for analyzing debuginfo
  perf probe: Rename probe finder functions
  perf probe: Fix bugs in line range finder
  perf probe: Update perf probe document
  perf probe: Do not show --line option without dwarf support
  kprobes: Add documents of jump optimization
  kprobes/x86: Support kprobes jump optimization on x86
  x86: Add text_poke_smp for SMP cross modifying code
  kprobes/x86: Cleanup save/restore registers
  kprobes/x86: Boost probes when reentering
  kprobes: Jump optimization sysctl interface
  kprobes: Introduce kprobes jump optimization
  kprobes: Introduce generic insn_slot framework
  kprobes/x86: Cleanup RELATIVEJUMP_INSTRUCTION to RELATIVEJUMP_OPCODE

arch/Kconfig

@@ -41,6 +41,17 @@ config KPROBES
 	  for kernel debugging, non-intrusive instrumentation and testing.
 	  If in doubt, say "N".
 
+config OPTPROBES
+	bool "Kprobes jump optimization support (EXPERIMENTAL)"
+	default y
+	depends on KPROBES
+	depends on !PREEMPT
+	depends on HAVE_OPTPROBES
+	select KALLSYMS_ALL
+	help
+	  This option will allow kprobes to optimize breakpoint to
+	  a jump for reducing its overhead.
+
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
 	help
@@ -83,6 +94,8 @@ config HAVE_KPROBES
 config HAVE_KRETPROBES
 	bool
 
+config HAVE_OPTPROBES
+	bool
 #
 # An arch should select this if it provides all these things:
 #

arch/x86/Kconfig

@@ -31,6 +31,7 @@ config X86
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
 	select HAVE_KRETPROBES
+	select HAVE_OPTPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER

arch/x86/include/asm/alternative.h

@@ -165,10 +165,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
  * invalid instruction possible) or if the instructions are changed from a
  * consistent state to another consistent state atomically.
  * More care must be taken when modifying code in the SMP case because of
- * Intel's errata.
+ * Intel's errata. text_poke_smp() takes care that errata, but still
+ * doesn't support NMI/MCE handler code modifying.
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 
 #endif /* _ASM_X86_ALTERNATIVE_H */

arch/x86/include/asm/kprobes.h

@@ -32,7 +32,10 @@ struct kprobe;
 
 typedef u8 kprobe_opcode_t;
 #define BREAKPOINT_INSTRUCTION	0xcc
-#define RELATIVEJUMP_INSTRUCTION 0xe9
+#define RELATIVEJUMP_OPCODE 0xe9
+#define RELATIVEJUMP_SIZE 5
+#define RELATIVECALL_OPCODE 0xe8
+#define RELATIVE_ADDR_SIZE 4
 #define MAX_INSN_SIZE 16
 #define MAX_STACK_SIZE 64
 #define MIN_STACK_SIZE(ADDR)					       \
@@ -44,6 +47,17 @@ typedef u8 kprobe_opcode_t;
 
 #define flush_insn_slot(p)	do { } while (0)
 
+/* optinsn template addresses */
+extern kprobe_opcode_t optprobe_template_entry;
+extern kprobe_opcode_t optprobe_template_val;
+extern kprobe_opcode_t optprobe_template_call;
+extern kprobe_opcode_t optprobe_template_end;
+#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
+#define MAX_OPTINSN_SIZE 				\
+	(((unsigned long)&optprobe_template_end -	\
+	  (unsigned long)&optprobe_template_entry) +	\
+	 MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE)
+
 extern const int kretprobe_blacklist_size;
 
 void arch_remove_kprobe(struct kprobe *p);
@@ -64,6 +78,21 @@ struct arch_specific_insn {
 	int boostable;
 };
 
+struct arch_optimized_insn {
+	/* copy of the original instructions */
+	kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE];
+	/* detour code buffer */
+	kprobe_opcode_t *insn;
+	/* the size of instructions copied to detour code buffer */
+	size_t size;
+};
+
+/* Return true (!0) if optinsn is prepared for optimization. */
+static inline int arch_prepared_optinsn(struct arch_optimized_insn *optinsn)
+{
+	return optinsn->size;
+}
+
 struct prev_kprobe {
 	struct kprobe *kp;
 	unsigned long status;

arch/x86/kernel/alternative.c

@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
+#include <linux/stop_machine.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -572,3 +573,62 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 	local_irq_restore(flags);
 	return addr;
 }
+
+/*
+ * Cross-modifying kernel text with stop_machine().
+ * This code originally comes from immediate value.
+ */
+static atomic_t stop_machine_first;
+static int wrote_text;
+
+struct text_poke_params {
+	void *addr;
+	const void *opcode;
+	size_t len;
+};
+
+static int __kprobes stop_machine_text_poke(void *data)
+{
+	struct text_poke_params *tpp = data;
+
+	if (atomic_dec_and_test(&stop_machine_first)) {
+		text_poke(tpp->addr, tpp->opcode, tpp->len);
+		smp_wmb();	/* Make sure other cpus see that this has run */
+		wrote_text = 1;
+	} else {
+		while (!wrote_text)
+			cpu_relax();
+		smp_mb();	/* Load wrote_text before following execution */
+	}
+
+	flush_icache_range((unsigned long)tpp->addr,
+			   (unsigned long)tpp->addr + tpp->len);
+	return 0;
+}
+
+/**
+ * text_poke_smp - Update instructions on a live kernel on SMP
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Modify multi-byte instruction by using stop_machine() on SMP. This allows
+ * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying
+ * should be allowed, since stop_machine() does _not_ protect code against
+ * NMI and MCE.
+ *
+ * Note: Must be called under get_online_cpus() and text_mutex.
+ */
+void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
+{
+	struct text_poke_params tpp;
+
+	tpp.addr = addr;
+	tpp.opcode = opcode;
+	tpp.len = len;
+	atomic_set(&stop_machine_first, 1);
+	wrote_text = 0;
+	stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+	return addr;
+}
+

include/linux/kprobes.h

@@ -122,6 +122,11 @@ struct kprobe {
 /* Kprobe status flags */
 #define KPROBE_FLAG_GONE	1 /* breakpoint has already gone */
 #define KPROBE_FLAG_DISABLED	2 /* probe is temporarily disabled */
+#define KPROBE_FLAG_OPTIMIZED	4 /*
+				   * probe is really optimized.
+				   * NOTE:
+				   * this flag is only for optimized_kprobe.
+				   */
 
 /* Has this kprobe gone ? */
 static inline int kprobe_gone(struct kprobe *p)
@@ -134,6 +139,12 @@ static inline int kprobe_disabled(struct kprobe *p)
 {
 	return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE);
 }
+
+/* Is this kprobe really running optimized path ? */
+static inline int kprobe_optimized(struct kprobe *p)
+{
+	return p->flags & KPROBE_FLAG_OPTIMIZED;
+}
 /*
  * Special probe type that uses setjmp-longjmp type tricks to resume
  * execution at a specified entry with a matching prototype corresponding
@@ -249,6 +260,39 @@ extern kprobe_opcode_t *get_insn_slot(void);
 extern void free_insn_slot(kprobe_opcode_t *slot, int dirty);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 
+#ifdef CONFIG_OPTPROBES
+/*
+ * Internal structure for direct jump optimized probe
+ */
+struct optimized_kprobe {
+	struct kprobe kp;
+	struct list_head list;	/* list for optimizing queue */
+	struct arch_optimized_insn optinsn;
+};
+
+/* Architecture dependent functions for direct jump optimization */
+extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn);
+extern int arch_check_optimized_kprobe(struct optimized_kprobe *op);
+extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op);
+extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op);
+extern int  arch_optimize_kprobe(struct optimized_kprobe *op);
+extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
+extern kprobe_opcode_t *get_optinsn_slot(void);
+extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty);
+extern int arch_within_optimized_kprobe(struct optimized_kprobe *op,
+					unsigned long addr);
+
+extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs);
+
+#ifdef CONFIG_SYSCTL
+extern int sysctl_kprobes_optimization;
+extern int proc_kprobes_optimization_handler(struct ctl_table *table,
+					     int write, void __user *buffer,
+					     size_t *length, loff_t *ppos);
+#endif
+
+#endif /* CONFIG_OPTPROBES */
+
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
 struct kprobe *get_kprobe(void *addr);
 void kretprobe_hash_lock(struct task_struct *tsk,

kernel/sysctl.c

@@ -50,6 +50,7 @@
 #include <linux/ftrace.h>
 #include <linux/slow-work.h>
 #include <linux/perf_event.h>
+#include <linux/kprobes.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -1449,6 +1450,17 @@ static struct ctl_table debug_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+#endif
+#if defined(CONFIG_OPTPROBES)
+	{
+		.procname	= "kprobes-optimization",
+		.data		= &sysctl_kprobes_optimization,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_kprobes_optimization_handler,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif
 	{ }
 };

tools/perf/Documentation/perf-probe.txt

@@ -41,7 +41,8 @@ OPTIONS
 
 -d::
 --del=::
-	Delete a probe event.
+	Delete probe events. This accepts glob wildcards('*', '?') and character
+	classes(e.g. [a-z], [!A-Z]).
 
 -l::
 --list::
@@ -50,17 +51,29 @@ OPTIONS
 -L::
 --line=::
 	Show source code lines which can be probed. This needs an argument
-	which specifies a range of the source code.
+	which specifies a range of the source code. (see LINE SYNTAX for detail)
+
+-f::
+--force::
+	Forcibly add events with existing name.
 
 PROBE SYNTAX
 ------------
 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
@@ -76,6 +89,41 @@ and 'ALN2' is end line number in the file. It is also possible to specify how
 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:
+
+ ./perf probe --line schedule
+
+Add a probe on schedule() function 12th line with recording cpu local variable:
+
+ ./perf probe schedule:12 cpu
+ or
+ ./perf probe --add='schedule:12 cpu'
+
+ 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*'
+
+
 SEE ALSO
 --------
 linkperf:perf-trace[1], linkperf:perf-record[1]

tools/perf/Makefile

@@ -500,12 +500,12 @@ else
 	msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
 endif
 
-ifneq ($(shell sh -c "(echo '\#ifndef _MIPS_SZLONG'; echo '\#define _MIPS_SZLONG 0'; echo '\#endif'; echo '\#include <dwarf.h>'; echo '\#include <libdwarf.h>'; echo 'int main(void) { Dwarf_Debug dbg; Dwarf_Error err; Dwarf_Ranges *rng; dwarf_init(0, DW_DLC_READ, 0, 0, &dbg, &err); dwarf_get_ranges(dbg, 0, &rng, 0, 0, &err); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/libdwarf -ldwarf -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-	msg := $(warning No libdwarf.h found or old libdwarf.h found, disables dwarf support. Please install libdwarf-dev/libdwarf-devel >= 20081231);
-	BASIC_CFLAGS += -DNO_LIBDWARF
+ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+	msg := $(warning No libdw.h found or old libdw.h found, disables dwarf support. Please install elfutils-devel/elfutils-dev);
+	BASIC_CFLAGS += -DNO_DWARF_SUPPORT
 else
-	BASIC_CFLAGS += -I/usr/include/libdwarf
-	EXTLIBS += -lelf -ldwarf
+	BASIC_CFLAGS += -I/usr/include/elfutils
+	EXTLIBS += -lelf -ldw
 	LIB_OBJS += util/probe-finder.o
 endif
 

tools/perf/builtin-probe.c

@@ -128,7 +128,7 @@ static void evaluate_probe_point(struct probe_point *pp)
 		    pp->function);
 }
 
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
 static int open_vmlinux(void)
 {
 	if (map__load(session.kmaps[MAP__FUNCTION], NULL) < 0) {
@@ -156,14 +156,16 @@ static const char * const probe_usage[] = {
 	"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
 	"perf probe [<options>] --del '[GROUP:]EVENT' ...",
 	"perf probe --list",
+#ifndef NO_DWARF_SUPPORT
 	"perf probe --line 'LINEDESC'",
+#endif
 	NULL
 };
 
 static const struct option options[] = {
 	OPT_BOOLEAN('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 #endif
@@ -172,30 +174,32 @@ static const struct option options[] = {
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
 		opt_del_probe_event),
 	OPT_CALLBACK('a', "add", NULL,
-#ifdef NO_LIBDWARF
-		"[EVENT=]FUNC[+OFFS|%return] [ARG ...]",
+#ifdef NO_DWARF_SUPPORT
+		"[EVENT=]FUNC[+OFF|%return] [ARG ...]",
 #else
-		"[EVENT=]FUNC[+OFFS|%return|:RLN][@SRC]|SRC:ALN [ARG ...]",
+		"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|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_LIBDWARF
+#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",
 		opt_add_probe_event),
 	OPT_BOOLEAN('f', "force", &session.force_add, "forcibly add events"
 		    " with existing name"),
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
 	OPT_CALLBACK('L', "line", NULL,
 		     "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]",
 		     "Show source code lines.", opt_show_lines),
@@ -223,7 +227,7 @@ static void init_vmlinux(void)
 int cmd_probe(int argc, const char **argv, const char *prefix __used)
 {
 	int i, ret;
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
 	int fd;
 #endif
 	struct probe_point *pp;
@@ -259,7 +263,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 		return 0;
 	}
 
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
 	if (session.show_lines) {
 		if (session.nr_probe != 0 || session.dellist) {
 			pr_warning("  Error: Don't use --line with"
@@ -290,9 +294,9 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 	init_vmlinux();
 
 	if (session.need_dwarf)
-#ifdef NO_LIBDWARF
+#ifdef NO_DWARF_SUPPORT
 		die("Debuginfo-analysis is not supported");
-#else	/* !NO_LIBDWARF */
+#else	/* !NO_DWARF_SUPPORT */
 		pr_debug("Some probes require debuginfo.\n");
 
 	fd = open_vmlinux();
@@ -312,7 +316,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 			continue;
 
 		lseek(fd, SEEK_SET, 0);
-		ret = find_probepoint(fd, pp);
+		ret = find_probe_point(fd, pp);
 		if (ret > 0)
 			continue;
 		if (ret == 0) {	/* No error but failed to find probe point. */
@@ -333,7 +337,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 	close(fd);
 
 end_dwarf:
-#endif /* !NO_LIBDWARF */
+#endif /* !NO_DWARF_SUPPORT */
 
 	/* Synthesize probes without dwarf */
 	for (i = 0; i < session.nr_probe; i++) {

tools/perf/util/probe-event.c

@@ -119,14 +119,14 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 	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, ':');
@@ -139,7 +139,7 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		arg = tmp;
 	}
 
-	ptr = strpbrk(arg, ":+@%");
+	ptr = strpbrk(arg, ";:+@%");
 	if (ptr) {
 		nc = *ptr;
 		*ptr++ = '\0';
@@ -156,7 +156,11 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 	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';
@@ -165,13 +169,13 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		case ':':	/* Line number */
 			pp->line = strtoul(arg, &tmp, 0);
 			if (*tmp != '\0')
-				semantic_error("There is non-digit charactor"
-						" in line number.");
+				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 */
@@ -179,9 +183,6 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 				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) {
@@ -196,11 +197,18 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 	}
 
 	/* 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.");
@@ -208,11 +216,13 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 	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 */
@@ -458,6 +468,8 @@ static void clear_probe_point(struct probe_point *pp)
 		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)
@@ -719,6 +731,7 @@ void del_trace_kprobe_events(struct strlist *dellist)
 }
 
 #define LINEBUF_SIZE 256
+#define NR_ADDITIONAL_LINES 2
 
 static void show_one_line(FILE *fp, unsigned int l, bool skip, bool show_num)
 {
@@ -779,5 +792,11 @@ void show_line_range(struct line_range *lr)
 			show_one_line(fp, (l++) - lr->offset, false, false);
 		show_one_line(fp, (l++) - lr->offset, false, true);
 	}
+
+	if (lr->end == INT_MAX)
+		lr->end = l + NR_ADDITIONAL_LINES;
+	while (l < lr->end && !feof(fp))
+		show_one_line(fp, (l++) - lr->offset, false, false);
+
 	fclose(fp);
 }

tools/perf/util/probe-finder.h

 #ifndef _PROBE_FINDER_H
 #define _PROBE_FINDER_H
 
+#include <stdbool.h>
 #include "util.h"
 
 #define MAX_PATH_LEN		 256
@@ -20,6 +21,7 @@ struct probe_point {
 	/* Inputs */
 	char			*file;			/* File name */
 	int			line;			/* Line number */
+	char			*lazy_line;		/* Lazy line pattern */
 
 	char			*function;		/* Function name */
 	int			offset;			/* Offset bytes */
@@ -46,53 +48,46 @@ struct line_range {
 	char			*function;		/* Function name */
 	unsigned int		start;			/* Start line number */
 	unsigned int		end;			/* End line number */
-	unsigned int		offset;			/* Start line offset */
+	int			offset;			/* Start line offset */
 	char			*path;			/* Real path name */
 	struct list_head	line_list;		/* Visible lines */
 };
 
-#ifndef NO_LIBDWARF
-extern int find_probepoint(int fd, struct probe_point *pp);
+#ifndef NO_DWARF_SUPPORT
+extern int find_probe_point(int fd, struct probe_point *pp);
 extern int find_line_range(int fd, struct line_range *lr);
 
-/* Workaround for undefined _MIPS_SZLONG bug in libdwarf.h: */
-#ifndef _MIPS_SZLONG
-# define _MIPS_SZLONG		0
-#endif
-
 #include <dwarf.h>
-#include <libdwarf.h>
+#include <libdw.h>
 
 struct probe_finder {
-	struct probe_point	*pp;			/* Target probe point */
+	struct probe_point	*pp;		/* Target probe point */
 
 	/* For function searching */
-	Dwarf_Addr		addr;			/* Address */
-	Dwarf_Unsigned		fno;			/* File number */
-	Dwarf_Unsigned		lno;			/* Line number */
-	Dwarf_Off		inl_offs;		/* Inline offset */
-	Dwarf_Die		cu_die;			/* Current CU */
+	Dwarf_Addr		addr;		/* Address */
+	const char		*fname;		/* File name */
+	int			lno;		/* Line number */
+	Dwarf_Die		cu_die;		/* Current CU */
 
 	/* For variable searching */
-	Dwarf_Addr		cu_base;		/* Current CU base address */
-	Dwarf_Locdesc		fbloc;			/* Location of Current Frame Base */
-	const char		*var;			/* Current variable name */
-	char			*buf;			/* Current output buffer */
-	int			len;			/* Length of output buffer */
+	Dwarf_Op		*fb_ops;	/* Frame base attribute */
+	Dwarf_Addr		cu_base;	/* Current CU base address */
+	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 {
-	struct line_range	*lr;			/* Target line range */
-
-	Dwarf_Unsigned		fno;			/* File number */
-	Dwarf_Unsigned		lno_s;			/* Start line number */
-	Dwarf_Unsigned		lno_e;			/* End line number */
-	Dwarf_Addr		addr_s;			/* Start address */
-	Dwarf_Addr		addr_e;			/* End address */
-	Dwarf_Die		cu_die;			/* Current CU */
+	struct line_range	*lr;		/* Target line range */
+
+	const char		*fname;		/* File name */
+	int			lno_s;		/* Start line number */
+	int			lno_e;		/* End line number */
+	Dwarf_Die		cu_die;		/* Current CU */
 	int			found;
 };
 
-#endif /* NO_LIBDWARF */
+#endif /* NO_DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */

tools/perf/util/string.c

@@ -265,21 +265,21 @@ error:
 	return false;
 }
 
-/**
- * strglobmatch - glob expression pattern matching
- * @str: the target string to match
- * @pat: the pattern string to match
- *
- * This returns true if the @str matches @pat. @pat can includes wildcards
- * ('*','?') and character classes ([CHARS], complementation and ranges are
- * also supported). Also, this supports escape character ('\') to use special
- * characters as normal character.
- *
- * Note: if @pat syntax is broken, this always returns false.
- */
-bool strglobmatch(const char *str, const char *pat)
+/* Glob/lazy pattern matching */
+static bool __match_glob(const char *str, const char *pat, bool ignore_space)
 {
 	while (*str && *pat && *pat != '*') {
+		if (ignore_space) {
+			/* Ignore spaces for lazy matching */
+			if (isspace(*str)) {
+				str++;
+				continue;
+			}
+			if (isspace(*pat)) {
+				pat++;
+				continue;
+			}
+		}
 		if (*pat == '?') {	/* Matches any single character */
 			str++;
 			pat++;
@@ -308,3 +308,32 @@ bool strglobmatch(const char *str, const char *pat)
 	return !*str && !*pat;
 }
 
+/**
+ * strglobmatch - glob expression pattern matching
+ * @str: the target string to match
+ * @pat: the pattern string to match
+ *
+ * This returns true if the @str matches @pat. @pat can includes wildcards
+ * ('*','?') and character classes ([CHARS], complementation and ranges are
+ * also supported). Also, this supports escape character ('\') to use special
+ * characters as normal character.
+ *
+ * Note: if @pat syntax is broken, this always returns false.
+ */
+bool strglobmatch(const char *str, const char *pat)
+{
+	return __match_glob(str, pat, false);
+}
+
+/**
+ * strlazymatch - matching pattern strings lazily with glob pattern
+ * @str: the target string to match
+ * @pat: the pattern string to match
+ *
+ * This is similar to strglobmatch, except this ignores spaces in
+ * the target string.
+ */
+bool strlazymatch(const char *str, const char *pat)
+{
+	return __match_glob(str, pat, true);
+}

tools/perf/util/string.h

@@ -10,6 +10,7 @@ s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
 
 #define _STR(x) #x
 #define STR(x) _STR(x)