Merge tag 'perf-core-for-mingo-20160901' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Support generating cross arch probes, i.e. if you specify a vmlinux
  file for different arch than the one in the host machine,

	 $ perf probe --definition function_name args

  will generate the probe definition string needed to append to the
  target machine /sys/kernel/debug/tracing/kprobes_events file, using
  scripting (Masami Hiramatsu).

- Make 'perf probe' skip the function prologue in uprobes if program
  compiled without optimization, using the same strategy as gdb and
  systemtap uses, fixing a bug where:

	$ perf probe -x ./test 'foo i'

  When 'foo(42)' was used on the "./test" executable would produce i=0
  instead of the expected i=42 (Ravi Bangoria)

- Demangle symbols for synthesized @plt entries too (Millian Wolff)

Documentation changes:

- Show default report configuration in 'perf config' example
  and docs (Millian Wolff)

Infrastructure changes:

- Make 'perf test vmlinux' tolerate the symbol aliasing pruning done when
  loading kallsyms and vmlinux (Arnaldo Carvalho de Melo)

- Improve output of 'perf test vmlinux' test, to help identify on the verbose
  output which lines are warning and which are errors (Arnaldo Carvalho de Melo)

- Prep work to stop having to pass symbol_filter_t to lots of functions,
  simplifying symtab loading routines (Arnaldo Carvalho de Melo)

- Honor symbol_conf.allow_aliases when loading kallsyms as well, it was using
  it only when loading vmlinux files (Arnaldo Carvalho de Melo)

- Fixup symbol->end before doing alias pruning when loading symbol tables
  (Arnaldo Carvalho de Melo)

- Fix error handling of lzma kernel module decompression (Shawn Lin)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

17 files changed, 480 insertions, 91 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 91c5f6e1af59..f1a6d17c5a37 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -98,6 +98,7 @@ endif
 
 libperf-$(CONFIG_DWARF) += probe-finder.o
 libperf-$(CONFIG_DWARF) += dwarf-aux.o
+libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 25a9259a6a6e..1b59e3129216 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -491,13 +491,6 @@ static struct ins *ins__find(const char *name)
 	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
 }
 
-int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	pthread_mutex_init(&notes->lock, NULL);
-	return 0;
-}
-
 int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index f67ccb027561..e96f4daed9b9 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -177,7 +177,6 @@ enum symbol_disassemble_errno {
 int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
 				 int errnum, char *buf, size_t buflen);
 
-int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
 			    int min_pcnt, int max_lines, int context);
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index a347b19c961a..faec899435f2 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1085,3 +1085,182 @@ int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
 	return -ENOTSUP;
 }
 #endif
+
+/*
+ * die_has_loclist - Check if DW_AT_location of @vr_die is a location list
+ * @vr_die: a variable DIE
+ */
+static bool die_has_loclist(Dwarf_Die *vr_die)
+{
+	Dwarf_Attribute loc;
+	int tag = dwarf_tag(vr_die);
+
+	if (tag != DW_TAG_formal_parameter &&
+	    tag != DW_TAG_variable)
+		return false;
+
+	return (dwarf_attr_integrate(vr_die, DW_AT_location, &loc) &&
+		dwarf_whatform(&loc) == DW_FORM_sec_offset);
+}
+
+/*
+ * die_is_optimized_target - Check if target program is compiled with
+ * optimization
+ * @cu_die: a CU DIE
+ *
+ * For any object in given CU whose DW_AT_location is a location list,
+ * target program is compiled with optimization. This is applicable to
+ * clang as well.
+ */
+bool die_is_optimized_target(Dwarf_Die *cu_die)
+{
+	Dwarf_Die tmp_die;
+
+	if (die_has_loclist(cu_die))
+		return true;
+
+	if (!dwarf_child(cu_die, &tmp_die) &&
+	    die_is_optimized_target(&tmp_die))
+		return true;
+
+	if (!dwarf_siblingof(cu_die, &tmp_die) &&
+	    die_is_optimized_target(&tmp_die))
+		return true;
+
+	return false;
+}
+
+/*
+ * die_search_idx - Search index of given line address
+ * @lines: Line records of single CU
+ * @nr_lines: Number of @lines
+ * @addr: address we are looking for
+ * @idx: index to be set by this function (return value)
+ *
+ * Search for @addr by looping over every lines of CU. If address
+ * matches, set index of that line in @idx. Note that single source
+ * line can have multiple line records. i.e. single source line can
+ * have multiple index.
+ */
+static bool die_search_idx(Dwarf_Lines *lines, unsigned long nr_lines,
+			   Dwarf_Addr addr, unsigned long *idx)
+{
+	unsigned long i;
+	Dwarf_Addr tmp;
+
+	for (i = 0; i < nr_lines; i++) {
+		if (dwarf_lineaddr(dwarf_onesrcline(lines, i), &tmp))
+			return false;
+
+		if (tmp == addr) {
+			*idx = i;
+			return true;
+		}
+	}
+	return false;
+}
+
+/*
+ * die_get_postprologue_addr - Search next address after function prologue
+ * @entrypc_idx: entrypc index
+ * @lines: Line records of single CU
+ * @nr_lines: Number of @lines
+ * @hignpc: high PC address of function
+ * @postprologue_addr: Next address after function prologue (return value)
+ *
+ * Look for prologue-end marker. If there is no explicit marker, return
+ * address of next line record or next source line.
+ */
+static bool die_get_postprologue_addr(unsigned long entrypc_idx,
+				      Dwarf_Lines *lines,
+				      unsigned long nr_lines,
+				      Dwarf_Addr highpc,
+				      Dwarf_Addr *postprologue_addr)
+{
+	unsigned long i;
+	int entrypc_lno, lno;
+	Dwarf_Line *line;
+	Dwarf_Addr addr;
+	bool p_end;
+
+	/* entrypc_lno is actual source line number */
+	line = dwarf_onesrcline(lines, entrypc_idx);
+	if (dwarf_lineno(line, &entrypc_lno))
+		return false;
+
+	for (i = entrypc_idx; i < nr_lines; i++) {
+		line = dwarf_onesrcline(lines, i);
+
+		if (dwarf_lineaddr(line, &addr) ||
+		    dwarf_lineno(line, &lno)    ||
+		    dwarf_lineprologueend(line, &p_end))
+			return false;
+
+		/* highpc is exclusive. [entrypc,highpc) */
+		if (addr >= highpc)
+			break;
+
+		/* clang supports prologue-end marker */
+		if (p_end)
+			break;
+
+		/* Actual next line in source */
+		if (lno != entrypc_lno)
+			break;
+
+		/*
+		 * Single source line can have multiple line records.
+		 * For Example,
+		 *     void foo() { printf("hello\n"); }
+		 * contains two line records. One points to declaration and
+		 * other points to printf() line. Variable 'lno' won't get
+		 * incremented in this case but 'i' will.
+		 */
+		if (i != entrypc_idx)
+			break;
+	}
+
+	dwarf_lineaddr(line, postprologue_addr);
+	if (*postprologue_addr >= highpc)
+		dwarf_lineaddr(dwarf_onesrcline(lines, i - 1),
+			       postprologue_addr);
+
+	return true;
+}
+
+/*
+ * die_skip_prologue - Use next address after prologue as probe location
+ * @sp_die: a subprogram DIE
+ * @cu_die: a CU DIE
+ * @entrypc: entrypc of the function
+ *
+ * Function prologue prepares stack and registers before executing function
+ * logic. When target program is compiled without optimization, function
+ * parameter information is only valid after prologue. When we probe entrypc
+ * of the function, and try to record function parameter, it contains
+ * garbage value.
+ */
+void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
+		       Dwarf_Addr *entrypc)
+{
+	size_t nr_lines = 0;
+	unsigned long entrypc_idx = 0;
+	Dwarf_Lines *lines = NULL;
+	Dwarf_Addr postprologue_addr;
+	Dwarf_Addr highpc;
+
+	if (dwarf_highpc(sp_die, &highpc))
+		return;
+
+	if (dwarf_getsrclines(cu_die, &lines, &nr_lines))
+		return;
+
+	if (!die_search_idx(lines, nr_lines, *entrypc, &entrypc_idx))
+		return;
+
+	if (!die_get_postprologue_addr(entrypc_idx, lines, nr_lines,
+				       highpc, &postprologue_addr))
+		return;
+
+	*entrypc = postprologue_addr;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index dc0ce1adb075..8b6d2f83af02 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -125,4 +125,12 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 /* Get the name and type of given variable DIE, stored as "type\tname" */
 int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
 int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
+
+/* Check if target program is compiled with optimization */
+bool die_is_optimized_target(Dwarf_Die *cu_die);
+
+/* Use next address after prologue as probe location */
+void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
+		       Dwarf_Addr *entrypc);
+
 #endif
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
new file mode 100644
index 000000000000..62bc4a86a970
--- /dev/null
+++ b/tools/perf/util/dwarf-regs.c
@@ -0,0 +1,59 @@
+/*
+ * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
+ *
+ * Written by: Masami Hiramatsu <mhiramat@kernel.org>
+ */
+
+#include <util.h>
+#include <debug.h>
+#include <dwarf-regs.h>
+#include <elf.h>
+
+#ifndef EM_AARCH64
+#define EM_AARCH64	183  /* ARM 64 bit */
+#endif
+
+/* Define const char * {arch}_register_tbl[] */
+#define DEFINE_DWARF_REGSTR_TABLE
+#include "../arch/x86/include/dwarf-regs-table.h"
+#include "../arch/arm/include/dwarf-regs-table.h"
+#include "../arch/arm64/include/dwarf-regs-table.h"
+#include "../arch/sh/include/dwarf-regs-table.h"
+#include "../arch/powerpc/include/dwarf-regs-table.h"
+#include "../arch/s390/include/dwarf-regs-table.h"
+#include "../arch/sparc/include/dwarf-regs-table.h"
+#include "../arch/xtensa/include/dwarf-regs-table.h"
+
+#define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL)
+
+/* Return architecture dependent register string (for kprobe-tracer) */
+const char *get_dwarf_regstr(unsigned int n, unsigned int machine)
+{
+	switch (machine) {
+	case EM_NONE:	/* Generic arch - use host arch */
+		return get_arch_regstr(n);
+	case EM_386:
+		return __get_dwarf_regstr(x86_32_regstr_tbl, n);
+	case EM_X86_64:
+		return __get_dwarf_regstr(x86_64_regstr_tbl, n);
+	case EM_ARM:
+		return __get_dwarf_regstr(arm_regstr_tbl, n);
+	case EM_AARCH64:
+		return __get_dwarf_regstr(aarch64_regstr_tbl, n);
+	case EM_SH:
+		return __get_dwarf_regstr(sh_regstr_tbl, n);
+	case EM_S390:
+		return __get_dwarf_regstr(s390_regstr_tbl, n);
+	case EM_PPC:
+	case EM_PPC64:
+		return __get_dwarf_regstr(powerpc_regstr_tbl, n);
+	case EM_SPARC:
+	case EM_SPARCV9:
+		return __get_dwarf_regstr(sparc_regstr_tbl, n);
+	case EM_XTENSA:
+		return __get_dwarf_regstr(xtensa_regstr_tbl, n);
+	default:
+		pr_err("ELF MACHINE %x is not supported.\n", machine);
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 3674e77ad640..9111e0666950 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -122,7 +122,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 			if (!node)
 				break;
 
-			if (node->sym && node->sym->ignore)
+			if (node->sym && node->sym->idle)
 				goto next;
 
 			printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
@@ -181,7 +181,7 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
 	if (cursor != NULL) {
 		printed += sample__fprintf_callchain(sample, left_alignment,
 						     print_opts, cursor, fp);
-	} else if (!(al->sym && al->sym->ignore)) {
+	} else if (!(al->sym && al->sym->idle)) {
 		printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
 
 		if (print_ip)
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 07c644ed64c4..43bfd8da7919 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -3,6 +3,12 @@
 
 #ifdef HAVE_DWARF_SUPPORT
 const char *get_arch_regstr(unsigned int n);
+/*
+ * get_dwarf_regstr - Returns ftrace register string from DWARF regnum
+ * n: DWARF register number
+ * machine: ELF machine signature (EM_*)
+ */
+const char *get_dwarf_regstr(unsigned int n, unsigned int machine);
 #endif
 
 #ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 95a1acb61245..9ddea5cecd94 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -29,6 +29,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 	lzma_action action = LZMA_RUN;
 	lzma_stream strm   = LZMA_STREAM_INIT;
 	lzma_ret ret;
+	int err = -1;
 
 	u8 buf_in[BUFSIZE];
 	u8 buf_out[BUFSIZE];
@@ -45,7 +46,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 	if (ret != LZMA_OK) {
 		pr_err("lzma: lzma_stream_decoder failed %s (%d)\n",
 			lzma_strerror(ret), ret);
-		return -1;
+		goto err_fclose;
 	}
 
 	strm.next_in   = NULL;
@@ -60,7 +61,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 			if (ferror(infile)) {
 				pr_err("lzma: read error: %s\n", strerror(errno));
-				return -1;
+				goto err_fclose;
 			}
 
 			if (feof(infile))
@@ -74,7 +75,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 			if (writen(output_fd, buf_out, write_size) != write_size) {
 				pr_err("lzma: write error: %s\n", strerror(errno));
-				return -1;
+				goto err_fclose;
 			}
 
 			strm.next_out  = buf_out;
@@ -83,13 +84,15 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 		if (ret != LZMA_OK) {
 			if (ret == LZMA_STREAM_END)
-				return 0;
+				break;
 
 			pr_err("lzma: failed %s\n", lzma_strerror(ret));
-			return -1;
+			goto err_fclose;
 		}
 	}
 
+	err = 0;
+err_fclose:
 	fclose(infile);
-	return 0;
+	return err;
 }
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28733962cd80..a543e9ca581c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -674,6 +674,10 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 	char *tmp;
 	int i, skipped = 0;
 
+	/* Skip post process if the target is an offline kernel */
+	if (symbol_conf.ignore_vmlinux_buildid)
+		return 0;
+
 	reloc_sym = kernel_get_ref_reloc_sym();
 	if (!reloc_sym) {
 		pr_warning("Relocated base symbol is not found!\n");
@@ -1614,19 +1618,27 @@ out:
 	return ret;
 }
 
+/* Returns true if *any* ARG is either C variable, $params or $vars. */
+bool perf_probe_with_var(struct perf_probe_event *pev)
+{
+	int i = 0;
+
+	for (i = 0; i < pev->nargs; i++)
+		if (is_c_varname(pev->args[i].var)              ||
+		    !strcmp(pev->args[i].var, PROBE_ARG_PARAMS) ||
+		    !strcmp(pev->args[i].var, PROBE_ARG_VARS))
+			return true;
+	return false;
+}
+
 /* Return true if this perf_probe_event requires debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
 {
-	int i;
-
 	if (pev->point.file || pev->point.line || pev->point.lazy_line)
 		return true;
 
-	for (i = 0; i < pev->nargs; i++)
-		if (is_c_varname(pev->args[i].var) ||
-		    !strcmp(pev->args[i].var, "$params") ||
-		    !strcmp(pev->args[i].var, "$vars"))
-			return true;
+	if (perf_probe_with_var(pev))
+		return true;
 
 	return false;
 }
@@ -3207,6 +3219,52 @@ int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 	return 0;
 }
 
+static int show_probe_trace_event(struct probe_trace_event *tev)
+{
+	char *buf = synthesize_probe_trace_command(tev);
+
+	if (!buf) {
+		pr_debug("Failed to synthesize probe trace event.\n");
+		return -EINVAL;
+	}
+
+	/* Showing definition always go stdout */
+	printf("%s\n", buf);
+	free(buf);
+
+	return 0;
+}
+
+int show_probe_trace_events(struct perf_probe_event *pevs, int npevs)
+{
+	struct strlist *namelist = strlist__new(NULL, NULL);
+	struct probe_trace_event *tev;
+	struct perf_probe_event *pev;
+	int i, j, ret = 0;
+
+	if (!namelist)
+		return -ENOMEM;
+
+	for (j = 0; j < npevs && !ret; j++) {
+		pev = &pevs[j];
+		for (i = 0; i < pev->ntevs && !ret; i++) {
+			tev = &pev->tevs[i];
+			/* Skip if the symbol is out of .text or blacklisted */
+			if (!tev->point.symbol && !pev->uprobes)
+				continue;
+
+			/* Set new name for tev (and update namelist) */
+			ret = probe_trace_event__set_name(tev, pev,
+							  namelist, true);
+			if (!ret)
+				ret = show_probe_trace_event(tev);
+		}
+	}
+	strlist__delete(namelist);
+
+	return ret;
+}
+
 int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
 	int i, ret = 0;
@@ -3289,24 +3347,10 @@ out:
 	return ret;
 }
 
-/* TODO: don't use a global variable for filter ... */
-static struct strfilter *available_func_filter;
-
-/*
- * If a symbol corresponds to a function with global binding and
- * matches filter return 0. For all others return 1.
- */
-static int filter_available_functions(struct map *map __maybe_unused,
-				      struct symbol *sym)
-{
-	if (strfilter__compare(available_func_filter, sym->name))
-		return 0;
-	return 1;
-}
-
 int show_available_funcs(const char *target, struct strfilter *_filter,
 					bool user)
 {
+        struct rb_node *nd;
 	struct map *map;
 	int ret;
 
@@ -3324,9 +3368,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 		return -EINVAL;
 	}
 
-	/* Load symbols with given filter */
-	available_func_filter = _filter;
-	ret = map__load(map, filter_available_functions);
+	ret = map__load(map, NULL);
 	if (ret) {
 		if (ret == -2) {
 			char *str = strfilter__string(_filter);
@@ -3343,7 +3385,14 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 
 	/* Show all (filtered) symbols */
 	setup_pager();
-	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+
+        for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) {
+		struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+
+		if (strfilter__compare(_filter, pos->sym.name))
+			printf("%s\n", pos->sym.name);
+        }
+
 end:
 	if (user) {
 		map__put(map);
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index f4f45db77c1c..8091d15113f7 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -128,6 +128,8 @@ char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 int perf_probe_event__copy(struct perf_probe_event *dst,
 			   struct perf_probe_event *src);
 
+bool perf_probe_with_var(struct perf_probe_event *pev);
+
 /* Check the perf_probe_event needs debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
 
@@ -147,6 +149,7 @@ int line_range__init(struct line_range *lr);
 int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int show_probe_trace_events(struct perf_probe_event *pevs, int npevs);
 void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int del_perf_probe_events(struct strfilter *filter);
 
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 697ef66bff91..6f931e442f14 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -73,11 +73,10 @@ static void print_both_open_warning(int kerr, int uerr)
 static int open_probe_events(const char *trace_file, bool readwrite)
 {
 	char buf[PATH_MAX];
-	const char *tracing_dir = "";
 	int ret;
 
-	ret = e_snprintf(buf, PATH_MAX, "%s/%s%s",
-			 tracing_path, tracing_dir, trace_file);
+	ret = e_snprintf(buf, PATH_MAX, "%s/%s",
+			 tracing_path, trace_file);
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index ac4740f8ee3a..8daca4fc1f8d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -171,6 +171,7 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs)
  */
 static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 				     Dwarf_Op *fb_ops, Dwarf_Die *sp_die,
+				     unsigned int machine,
 				     struct probe_trace_arg *tvar)
 {
 	Dwarf_Attribute attr;
@@ -266,7 +267,7 @@ static_var:
 	if (!tvar)
 		return ret2;
 
-	regs = get_arch_regstr(regn);
+	regs = get_dwarf_regstr(regn, machine);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
 		pr_warning("Mapping for the register number %u "
@@ -543,7 +544,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 		 dwarf_diename(vr_die));
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
-					&pf->sp_die, pf->tvar);
+					&pf->sp_die, pf->machine, pf->tvar);
 	if (ret == -ENOENT || ret == -EINVAL) {
 		pr_err("Failed to find the location of the '%s' variable at this address.\n"
 		       " Perhaps it has been optimized out.\n"
@@ -906,6 +907,38 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 	return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
 }
 
+static void skip_prologue(Dwarf_Die *sp_die, struct probe_finder *pf)
+{
+	struct perf_probe_point *pp = &pf->pev->point;
+
+	/* Not uprobe? */
+	if (!pf->pev->uprobes)
+		return;
+
+	/* Compiled with optimization? */
+	if (die_is_optimized_target(&pf->cu_die))
+		return;
+
+	/* Don't know entrypc? */
+	if (!pf->addr)
+		return;
+
+	/* Only FUNC and FUNC@SRC are eligible. */
+	if (!pp->function || pp->line || pp->retprobe || pp->lazy_line ||
+	    pp->offset || pp->abs_address)
+		return;
+
+	/* Not interested in func parameter? */
+	if (!perf_probe_with_var(pf->pev))
+		return;
+
+	pr_info("Target program is compiled without optimization. Skipping prologue.\n"
+		"Probe on address 0x%" PRIx64 " to force probing at the function entry.\n\n",
+		pf->addr);
+
+	die_skip_prologue(sp_die, &pf->cu_die, &pf->addr);
+}
+
 static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 {
 	struct probe_finder *pf = data;
@@ -968,6 +1001,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 		if (pp->lazy_line)
 			param->retval = find_probe_point_lazy(sp_die, pf);
 		else {
+			skip_prologue(sp_die, pf);
 			pf->addr += pp->offset;
 			/* TODO: Check the address in this function */
 			param->retval = call_probe_finder(sp_die, pf);
@@ -1106,11 +1140,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 				  struct probe_finder *pf)
 {
 	int ret = 0;
-
-#if _ELFUTILS_PREREQ(0, 142)
 	Elf *elf;
 	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
 
 	if (pf->cfi_eh || pf->cfi_dbg)
 		return debuginfo__find_probe_location(dbg, pf);
@@ -1123,11 +1154,18 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	if (gelf_getehdr(elf, &ehdr) == NULL)
 		return -EINVAL;
 
-	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
-	    shdr.sh_type == SHT_PROGBITS)
-		pf->cfi_eh = dwarf_getcfi_elf(elf);
+	pf->machine = ehdr.e_machine;
+
+#if _ELFUTILS_PREREQ(0, 142)
+	do {
+		GElf_Shdr shdr;
+
+		if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+		    shdr.sh_type == SHT_PROGBITS)
+			pf->cfi_eh = dwarf_getcfi_elf(elf);
 
-	pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+		pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+	} while (0);
 #endif
 
 	ret = debuginfo__find_probe_location(dbg, pf);
@@ -1155,7 +1193,7 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
 	    (tag == DW_TAG_variable && vf->vars)) {
 		if (convert_variable_location(die_mem, vf->pf->addr,
 					      vf->pf->fb_ops, &pf->sp_die,
-					      NULL) == 0) {
+					      pf->machine, NULL) == 0) {
 			vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem);
 			if (vf->args[vf->nargs].var == NULL) {
 				vf->ret = -ENOMEM;
@@ -1318,7 +1356,7 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 	    tag == DW_TAG_variable) {
 		ret = convert_variable_location(die_mem, af->pf.addr,
 						af->pf.fb_ops, &af->pf.sp_die,
-						NULL);
+						af->pf.machine, NULL);
 		if (ret == 0 || ret == -ERANGE) {
 			int ret2;
 			bool externs = !af->child;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 51137fccb9c8..f1d8558f498e 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -80,6 +80,7 @@ struct probe_finder {
 	Dwarf_CFI		*cfi_dbg;
 #endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
+	unsigned int		machine;	/* Target machine arch */
 	struct perf_probe_arg	*pvar;		/* Current target variable */
 	struct probe_trace_arg	*tvar;		/* Current result variable */
 };
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a811c13a74d6..295d3147a803 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -206,6 +206,37 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 	return NULL;
 }
 
+static bool want_demangle(bool is_kernel_sym)
+{
+	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
+}
+
+static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
+{
+	int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
+	char *demangled = NULL;
+
+	/*
+	 * We need to figure out if the object was created from C++ sources
+	 * DWARF DW_compile_unit has this, but we don't always have access
+	 * to it...
+	 */
+	if (!want_demangle(dso->kernel || kmodule))
+	    return demangled;
+
+	demangled = bfd_demangle(NULL, elf_name, demangle_flags);
+	if (demangled == NULL)
+		demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+	else if (rust_is_mangled(demangled))
+		/*
+		    * Input to Rust demangling is the BFD-demangled
+		    * name which it Rust-demangles in place.
+		    */
+		rust_demangle_sym(demangled);
+
+	return demangled;
+}
+
 #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
 	for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
 	     idx < nr_entries; \
@@ -301,11 +332,19 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 
 		elf_section__for_each_rela(reldata, pos, pos_mem, idx,
 					   nr_rel_entries) {
+			const char *elf_name = NULL;
+			char *demangled = NULL;
 			symidx = GELF_R_SYM(pos->r_info);
 			plt_offset += shdr_plt.sh_entsize;
 			gelf_getsym(syms, symidx, &sym);
+
+			elf_name = elf_sym__name(&sym, symstrs);
+			demangled = demangle_sym(dso, 0, elf_name);
+			if (demangled != NULL)
+				elf_name = demangled;
 			snprintf(sympltname, sizeof(sympltname),
-				 "%s@plt", elf_sym__name(&sym, symstrs));
+				 "%s@plt", elf_name);
+			free(demangled);
 
 			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
 					STB_GLOBAL, sympltname);
@@ -323,11 +362,19 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 		GElf_Rel pos_mem, *pos;
 		elf_section__for_each_rel(reldata, pos, pos_mem, idx,
 					  nr_rel_entries) {
+			const char *elf_name = NULL;
+			char *demangled = NULL;
 			symidx = GELF_R_SYM(pos->r_info);
 			plt_offset += shdr_plt.sh_entsize;
 			gelf_getsym(syms, symidx, &sym);
+
+			elf_name = elf_sym__name(&sym, symstrs);
+			demangled = demangle_sym(dso, 0, elf_name);
+			if (demangled != NULL)
+				elf_name = demangled;
 			snprintf(sympltname, sizeof(sympltname),
-				 "%s@plt", elf_sym__name(&sym, symstrs));
+				 "%s@plt", elf_name);
+			free(demangled);
 
 			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
 					STB_GLOBAL, sympltname);
@@ -685,7 +732,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	}
 
 	/* Always reject images with a mismatched build-id: */
-	if (dso->has_build_id) {
+	if (dso->has_build_id && !symbol_conf.ignore_vmlinux_buildid) {
 		u8 build_id[BUILD_ID_SIZE];
 
 		if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) {
@@ -775,11 +822,6 @@ static u64 ref_reloc(struct kmap *kmap)
 	return 0;
 }
 
-static bool want_demangle(bool is_kernel_sym)
-{
-	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
-}
-
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
 		GElf_Sym *sym __maybe_unused) { }
 
@@ -1070,29 +1112,10 @@ int dso__load_sym(struct dso *dso, struct map *map,
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 		}
 new_symbol:
-		/*
-		 * We need to figure out if the object was created from C++ sources
-		 * DWARF DW_compile_unit has this, but we don't always have access
-		 * to it...
-		 */
-		if (want_demangle(dso->kernel || kmodule)) {
-			int demangle_flags = DMGL_NO_OPTS;
-			if (verbose)
-				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
-
-			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
-			if (demangled == NULL)
-				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
-			else if (rust_is_mangled(demangled))
-				/*
-				 * Input to Rust demangling is the BFD-demangled
-				 * name which it Rust-demangles in place.
-				 */
-				rust_demangle_sym(demangled);
+		demangled = demangle_sym(dso, kmodule, elf_name);
+		if (demangled != NULL)
+			elf_name = demangled;
 
-			if (demangled != NULL)
-				elf_name = demangled;
-		}
 		f = symbol__new(sym.st_value, sym.st_size,
 				GELF_ST_BIND(sym.st_info), elf_name);
 		free(demangled);
@@ -1113,9 +1136,8 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		if (!symbol_conf.allow_aliases)
-			symbols__fixup_duplicate(&dso->symbols[map->type]);
 		symbols__fixup_end(&dso->symbols[map->type]);
+		symbols__fixup_duplicate(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 37e8d20ae03e..98cd50384c32 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -9,6 +9,7 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <inttypes.h>
+#include "annotate.h"
 #include "build-id.h"
 #include "util.h"
 #include "debug.h"
@@ -152,6 +153,9 @@ void symbols__fixup_duplicate(struct rb_root *symbols)
 	struct rb_node *nd;
 	struct symbol *curr, *next;
 
+	if (symbol_conf.allow_aliases)
+		return;
+
 	nd = rb_first(symbols);
 
 	while (nd) {
@@ -235,8 +239,13 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 	if (sym == NULL)
 		return NULL;
 
-	if (symbol_conf.priv_size)
+	if (symbol_conf.priv_size) {
+		if (symbol_conf.init_annotation) {
+			struct annotation *notes = (void *)sym;
+			pthread_mutex_init(&notes->lock, NULL);
+		}
 		sym = ((void *)sym) + symbol_conf.priv_size;
+	}
 
 	sym->start   = start;
 	sym->end     = len ? start + len : start;
@@ -1234,8 +1243,8 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (kallsyms__delta(map, filename, &delta))
 		return -1;
 
-	symbols__fixup_duplicate(&dso->symbols[map->type]);
 	symbols__fixup_end(&dso->symbols[map->type]);
+	symbols__fixup_duplicate(&dso->symbols[map->type]);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
@@ -1948,6 +1957,23 @@ static bool symbol__read_kptr_restrict(void)
 	return value;
 }
 
+int symbol__annotation_init(void)
+{
+	if (symbol_conf.initialized) {
+		pr_err("Annotation needs to be init before symbol__init()\n");
+		return -1;
+	}
+
+	if (symbol_conf.init_annotation) {
+		pr_warning("Annotation being initialized multiple times\n");
+		return 0;
+	}
+
+	symbol_conf.priv_size += sizeof(struct annotation);
+	symbol_conf.init_annotation = true;
+	return 0;
+}
+
 int symbol__init(struct perf_env *env)
 {
 	const char *symfs;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 699f7cbcfe72..e54ee7c78ca3 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -57,7 +57,7 @@ struct symbol {
 	u64		end;
 	u16		namelen;
 	u8		binding;
-	bool		ignore;
+	u8		idle:1;
 	u8		arch_sym;
 	char		name[0];
 };
@@ -88,6 +88,7 @@ struct symbol_conf {
 	unsigned short	priv_size;
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
+			init_annotation,
 			force,
 			ignore_vmlinux,
 			ignore_vmlinux_buildid,
@@ -277,6 +278,8 @@ struct perf_env;
 int symbol__init(struct perf_env *env);
 void symbol__exit(void);
 void symbol__elf_init(void);
+int symbol__annotation_init(void);
+
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
 size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
 				      const struct addr_location *al,