[PATCH V3 0/4] arm-cs-trace-disasm.py/perf must accommodate non-zero DSO text offset

[PATCH V3 0/4] arm-cs-trace-disasm.py/perf must accommodate non-zero DSO text offset

[Steve Clevenger]

Changes in V3:
  - Rebased to linux-perf-tools branch.
  - Squash symbol-elf.c and symbol.h into same commit.
  - In map.c, merge dso__is_pie() call into existing if statement.
  - In arm-cs-trace-disasm.py, remove debug artifacts.

Changes in V2:
  - In dso__is_pie() (symbol-elf.c), Decrease indentation, add null pointer
    checks per Leo Yan review.
  - Updated mailing list distribution

Fedora 37 distributed shared binary and executable mapped files show a
zero text section offset. Starting with the Fedora 38 distribution, the
shared binary and executable mapped files show a non-zero text section
offset for some binaries. The text offset parameter is never passed into
the arm-cs-trace-disasm.py script to allow the script to adjust the
start/end address range passed to objdump. This adjustment is required
to correctly offset into the dso text section. Not doing so results in
an incorrect user instruction trace display for Fedora 38 (and later)
user trace output.

Steve Clevenger (4):
  Add dso__is_pie call to identify ELF PIE
  Force MAPPING_TYPE__IDENTIY for PIE
  Add map pgoff to python dictionary based on MAPPING_TYPE
  Adjust objdump start/end range per map pgoff parameter

 .../scripts/python/arm-cs-trace-disasm.py     |  9 ++-
 tools/perf/util/map.c                         |  4 +-
 .../scripting-engines/trace-event-python.c    | 13 +++-
 tools/perf/util/symbol-elf.c                  | 60 +++++++++++++++++++
 tools/perf/util/symbol.h                      |  1 +
 5 files changed, 79 insertions(+), 8 deletions(-)

-- 
2.25.1

[PATCH V3 4/4] Adjust objdump start/end range per map pgoff parameter

[Steve Clevenger]

Extract map_pgoff parameter from the dictionary, and adjust start/end
range passed to objdump based on the value.

The start_addr/stop_addr address checks are changed to print a warning
only if verbose == True. This script repeatedly sees a zero value passed
in for
      start_addr = cpu_data[str(cpu) + 'addr']

These zero values are not a new problem. The start_addr/stop_addr warning
clutters the instruction trace output, hence this change.

Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com>
---
 tools/perf/scripts/python/arm-cs-trace-disasm.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 7aff02d84ffb..e8cf5d80d850 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -187,6 +187,7 @@ def process_event(param_dict):
 	dso_start = get_optional(param_dict, "dso_map_start")
 	dso_end = get_optional(param_dict, "dso_map_end")
 	symbol = get_optional(param_dict, "symbol")
+	map_pgoff = get_optional(param_dict, "map_pgoff")
 
 	cpu = sample["cpu"]
 	ip = sample["ip"]
@@ -249,11 +250,13 @@ def process_event(param_dict):
 		return
 
 	if (start_addr < int(dso_start) or start_addr > int(dso_end)):
-		print("Start address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (start_addr, int(dso_start), int(dso_end), dso))
+		if (options.verbose == True):
+			print("Start address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (start_addr, int(dso_start), int(dso_end), dso))
 		return
 
 	if (stop_addr < int(dso_start) or stop_addr > int(dso_end)):
-		print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso))
+		if (options.verbose == True):
+			print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso))
 		return
 
 	if (options.objdump_name != None):
@@ -267,7 +270,7 @@ def process_event(param_dict):
 
 		dso_fname = get_dso_file_path(dso, dso_bid)
 		if path.exists(dso_fname):
-			print_disam(dso_fname, dso_vm_start, start_addr, stop_addr)
+			print_disam(dso_fname, dso_vm_start, start_addr + map_pgoff, stop_addr + map_pgoff)
 		else:
 			print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr, stop_addr))
 
-- 
2.25.1

[PATCH V3 3/4] Add map pgoff to python dictionary based on MAPPING_TYPE

[Steve Clevenger]

Add map_pgoff parameter to python dictionary so it can be seen by the
python script, arm-cs-trace-disasm.py. map_pgoff is forced to zero in
the dictionary if file type is MAPPING_TYPE__IDENTITY. Otherwise, the
map_pgoff value is directly added to the dictionary.

Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com>
---
 .../util/scripting-engines/trace-event-python.c     | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 6971dd6c231f..74b66692e3a3 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -798,7 +798,8 @@ static int set_regs_in_dict(PyObject *dict,
 static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
 			    const char *dso_field, const char *dso_bid_field,
 			    const char *dso_map_start, const char *dso_map_end,
-			    const char *sym_field, const char *symoff_field)
+			    const char *sym_field, const char *symoff_field,
+			    const char *map_pgoff)
 {
 	char sbuild_id[SBUILD_ID_SIZE];
 
@@ -814,6 +815,12 @@ static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
 			PyLong_FromUnsignedLong(map__start(al->map)));
 		pydict_set_item_string_decref(dict, dso_map_end,
 			PyLong_FromUnsignedLong(map__end(al->map)));
+		if (al->map->mapping_type == MAPPING_TYPE__DSO)
+			pydict_set_item_string_decref(dict, map_pgoff,
+					PyLong_FromUnsignedLongLong(al->map->pgoff));	
+		else
+			pydict_set_item_string_decref(dict, map_pgoff,
+				PyLong_FromUnsignedLongLong(0));		
 	}
 	if (al->sym) {
 		pydict_set_item_string_decref(dict, sym_field,
@@ -900,8 +907,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	pydict_set_item_string_decref(dict, "comm",
 			_PyUnicode_FromString(thread__comm_str(al->thread)));
 	set_sym_in_dict(dict, al, "dso", "dso_bid", "dso_map_start", "dso_map_end",
-			"symbol", "symoff");
-
+			"symbol", "symoff", "map_pgoff");
+	
 	pydict_set_item_string_decref(dict, "callchain", callchain);
 
 	brstack = python_process_brstack(sample, al->thread);
-- 
2.25.1

Re: [PATCH V3 3/4] Add map pgoff to python dictionary based on MAPPING_TYPE

[Steve Clevenger]

All, I discovered a merge problem to perf-tools-next. V4 is submitted.

Steve C.

On 8/27/2024 6:50 PM, Steve Clevenger wrote:
> Add map_pgoff parameter to python dictionary so it can be seen by the
> python script, arm-cs-trace-disasm.py. map_pgoff is forced to zero in
> the dictionary if file type is MAPPING_TYPE__IDENTITY. Otherwise, the
> map_pgoff value is directly added to the dictionary.
> 
> Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com>
> ---
>  .../util/scripting-engines/trace-event-python.c     | 13 ++++++++++---
>  1 file changed, 10 insertions(+), 3 deletions(-)
> 
> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
> index 6971dd6c231f..74b66692e3a3 100644
> --- a/tools/perf/util/scripting-engines/trace-event-python.c
> +++ b/tools/perf/util/scripting-engines/trace-event-python.c
> @@ -798,7 +798,8 @@ static int set_regs_in_dict(PyObject *dict,
>  static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
>  			    const char *dso_field, const char *dso_bid_field,
>  			    const char *dso_map_start, const char *dso_map_end,
> -			    const char *sym_field, const char *symoff_field)
> +			    const char *sym_field, const char *symoff_field,
> +			    const char *map_pgoff)
>  {
>  	char sbuild_id[SBUILD_ID_SIZE];
>  
> @@ -814,6 +815,12 @@ static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
>  			PyLong_FromUnsignedLong(map__start(al->map)));
>  		pydict_set_item_string_decref(dict, dso_map_end,
>  			PyLong_FromUnsignedLong(map__end(al->map)));
> +		if (al->map->mapping_type == MAPPING_TYPE__DSO)
> +			pydict_set_item_string_decref(dict, map_pgoff,
> +					PyLong_FromUnsignedLongLong(al->map->pgoff));	
> +		else
> +			pydict_set_item_string_decref(dict, map_pgoff,
> +				PyLong_FromUnsignedLongLong(0));		
>  	}
>  	if (al->sym) {
>  		pydict_set_item_string_decref(dict, sym_field,
> @@ -900,8 +907,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
>  	pydict_set_item_string_decref(dict, "comm",
>  			_PyUnicode_FromString(thread__comm_str(al->thread)));
>  	set_sym_in_dict(dict, al, "dso", "dso_bid", "dso_map_start", "dso_map_end",
> -			"symbol", "symoff");
> -
> +			"symbol", "symoff", "map_pgoff");
> +	
>  	pydict_set_item_string_decref(dict, "callchain", callchain);
>  
>  	brstack = python_process_brstack(sample, al->thread);

[PATCH V3 2/4] Force MAPPING_TYPE__IDENTIY for PIE

[Steve Clevenger]

Use dso__is_pie() to check whether the DSO file is a Position
Independent Executable (PIE). If PIE, change the MAPPING_TYPE to
MAPPING_TYPE__IDENTITY so a zero map pgoff (text offset) is passed
into the script.

Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com>
---
 tools/perf/util/map.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e781c8d56a9a..c846faec177b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -173,8 +173,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		assert(!dso__kernel(dso));
 		map__init(result, start, start + len, pgoff, dso, prot, flags);
 
-		if (anon || no_dso) {
-			map->mapping_type = MAPPING_TYPE__IDENTITY;
+		if (anon || no_dso || dso__is_pie(dso)) {
+			map__set_mapping_type(map, MAPPING_TYPE__IDENTITY);
 
 			/*
 			 * Set memory without DSO as loaded. All map__find_*
-- 
2.25.1

[PATCH V3 1/4] Add dso__is_pie call to identify ELF PIE

[Steve Clevenger]

Add dso__is_pie global to read the .dynamic section DT_FLAGS_1 entry for
the DF_1_PIE flag. This identifies position executable code.

Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com>
---
 tools/perf/util/symbol-elf.c | 60 ++++++++++++++++++++++++++++++++++++
 tools/perf/util/symbol.h     |  1 +
 2 files changed, 61 insertions(+)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index e398abfd13a0..0e49c1345a67 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -662,6 +662,66 @@ static int dso__synthesize_plt_got_symbols(struct dso *dso, Elf *elf,
 	return err;
 }
 
+/*
+ * Check dynamic section DT_FLAGS_1 for a Position Independent
+ * Executable (PIE).
+ */
+bool dso__is_pie(struct dso *dso)
+{
+	Elf *elf = NULL;
+	Elf_Scn *scn = NULL;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	bool is_pie = false;
+	char dso_path[PATH_MAX];
+	int fd = -1;
+
+	if (!dso || (elf_version(EV_CURRENT) == EV_NONE))
+		goto exit;	// false
+
+	dso__build_id_filename(dso, dso_path, sizeof(dso_path), false);
+
+	fd = open(dso_path, O_RDONLY);
+
+	if (fd < 0) {
+		pr_debug("%s: cannot read cached %s.\n", __func__, dso_path);
+		goto exit;	// false
+	}
+
+	elf = elf_begin(fd, ELF_C_READ, NULL);
+	gelf_getehdr(elf, &ehdr);
+
+	if (ehdr.e_type == ET_DYN) {
+		Elf_Data *data;
+		GElf_Dyn *entry;
+		int n_entries = shdr.sh_size / sizeof(GElf_Dyn);
+
+		scn = elf_section_by_name(elf, &ehdr, &shdr, ".dynamic", NULL);
+		if (!scn)
+			goto exit;	// false
+
+		data = (Elf_Data *) elf_getdata(scn, NULL);
+		if (!data || !data->d_buf)
+			goto exit;	// false
+
+		// check DT_FLAGS_1
+		for (int i = 0; i < n_entries; i++) {
+			entry = ((GElf_Dyn *) data->d_buf) + i;
+			if (entry->d_tag == DT_FLAGS_1) {
+				if ((entry->d_un.d_val & DF_1_PIE) != 0) {
+					is_pie = true;
+					break;
+				}
+			}
+		} // end for
+	}
+
+	elf_end(elf);
+	close(fd);
+exit:
+	return is_pie;
+}
+
 /*
  * We need to check if we have a .dynsym, so that we can handle the
  * .plt, synthesizing its symbols, that aren't on the symtabs (be it
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 3fb5d146d9b1..33ea2596ce31 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -127,6 +127,7 @@ void dso__insert_symbol(struct dso *dso,
 			struct symbol *sym);
 void dso__delete_symbol(struct dso *dso,
 			struct symbol *sym);
+bool dso__is_pie(struct dso *dso);
 
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
 struct symbol *dso__find_symbol_nocache(struct dso *dso, u64 addr);
-- 
2.25.1