[PATCH V3 0/2] perf symbols: Slightly improve module file executable section mappings

[PATCH V3 0/2] perf symbols: Slightly improve module file executable section mappings

[Adrian Hunter]

Hi

Currently perf does not record module section addresses except for
the .text section. In general that means perf cannot get module section
mappings correct (except for .text) when loading symbols from a kernel
module file. (Note using --kcore does not have this issue)

Here are a couple of patches to help shed light upon and slightly improve
the situation.


Changes in V3:

  Re-base

Changes in V2:

  perf tools: Make it possible to see perf's kernel and module memory mappings
    - add dump to perf report (if no browser) as well as perf script
    - add 'perf --debug kmaps' option also to dump kmaps


Adrian Hunter (2):
      perf tools: Make it possible to see perf's kernel and module memory mappings
      perf symbols: Slightly improve module file executable section mappings

 tools/perf/Documentation/perf.txt |  2 ++
 tools/perf/builtin-report.c       |  2 ++
 tools/perf/builtin-script.c       |  3 ++
 tools/perf/util/debug.c           |  3 ++
 tools/perf/util/debug.h           |  1 +
 tools/perf/util/python.c          |  1 +
 tools/perf/util/session.c         | 11 ++++++
 tools/perf/util/session.h         |  2 ++
 tools/perf/util/symbol-elf.c      | 75 +++++++++++++++++++++++++++++++++++++--
 9 files changed, 98 insertions(+), 2 deletions(-)


Regards
Adrian

[PATCH V3 1/2] perf tools: Make it possible to see perf's kernel and module memory mappings

[Adrian Hunter]

Dump kmaps if using 'perf --debug kmaps' or verbose > 2 (e.g. -vvv) for
tools 'perf script' and 'perf report' if there is no browser.

Example:

  $ perf --debug kmaps script 2>&1 >/dev/null | grep kvm.intel
  build id event received for /lib/modules/6.7.2-local/kernel/arch/x86/kvm/kvm-intel.ko: 0691d75e10e72ebbbd45a44c59f6d00a5604badf [20]
  Map: 0-3a3 4f5d8 [kvm_intel].modinfo
  Map: 0-5240 5f280 [kvm_intel]__versions
  Map: 0-30 64 [kvm_intel].note.Linux
  Map: 0-14 644c0 [kvm_intel].orc_header
  Map: 0-5297 43680 [kvm_intel].rodata
  Map: 0-5bee 3b837 [kvm_intel].text.unlikely
  Map: 0-7e0 41430 [kvm_intel].noinstr.text
  Map: 0-2080 713c0 [kvm_intel].bss
  Map: 0-26 705c8 [kvm_intel].data..read_mostly
  Map: 0-5888 6a4c0 [kvm_intel].data
  Map: 0-22 70220 [kvm_intel].data.once
  Map: 0-40 705f0 [kvm_intel].data..percpu
  Map: 0-1685 41d20 [kvm_intel].init.text
  Map: 0-4b8 6fd60 [kvm_intel].init.data
  Map: 0-380 70248 [kvm_intel]__dyndbg
  Map: 0-8 70218 [kvm_intel].exit.data
  Map: 0-438 4f980 [kvm_intel]__param
  Map: 0-5f5 4ca0f [kvm_intel].rodata.str1.1
  Map: 0-3657 493b8 [kvm_intel].rodata.str1.8
  Map: 0-e0 70640 [kvm_intel].data..ro_after_init
  Map: 0-500 70ec0 [kvm_intel].gnu.linkonce.this_module
  Map: ffffffffc13a7000-ffffffffc1421000 a0 /lib/modules/6.7.2-local/kernel/arch/x86/kvm/kvm-intel.ko

The example above shows how the module section mappings are all wrong
except for the main .text mapping at 0xffffffffc13a7000.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---


Changes in V3:
    - re-base

Changes in V2:
    - add dump to perf report (if no browser) as well as perf script
    - add 'perf --debug kmaps' option also to dump kmaps


 tools/perf/Documentation/perf.txt |  2 ++
 tools/perf/builtin-report.c       |  2 ++
 tools/perf/builtin-script.c       |  3 +++
 tools/perf/util/debug.c           |  3 +++
 tools/perf/util/debug.h           |  1 +
 tools/perf/util/python.c          |  1 +
 tools/perf/util/session.c         | 11 +++++++++++
 tools/perf/util/session.h         |  2 ++
 8 files changed, 25 insertions(+)

diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index a7cf7bc2f968..09f516f3fdfb 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -63,6 +63,8 @@ OPTIONS
                              in browser mode
           perf-event-open  - Print perf_event_open() arguments and
                              return value
+          kmaps            - Print kernel and module maps (perf script
+                             and perf report without browser)
 
 --debug-file::
 	Write debug output to a specified file.
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ccb91fe6b876..8e16fa261e6f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1766,6 +1766,8 @@ int cmd_report(int argc, const char **argv)
 	} else
 		ret = 0;
 
+	if (!use_browser && (verbose > 2 || debug_kmaps))
+		perf_session__dump_kmaps(session);
 error:
 	if (report.ptime_range) {
 		itrace_synth_opts__clear_time_range(&itrace_synth_opts);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index af63b7c37c8a..24baa8284add 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -4378,6 +4378,9 @@ int cmd_script(int argc, const char **argv)
 
 	flush_scripting();
 
+	if (verbose > 2 || debug_kmaps)
+		perf_session__dump_kmaps(session);
+
 out_delete:
 	if (script.ptime_range) {
 		itrace_synth_opts__clear_time_range(&itrace_synth_opts);
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index e282b4ceb4d2..c39ee0fcb8cf 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -33,6 +33,7 @@
 #endif
 
 int verbose;
+int debug_kmaps;
 int debug_peo_args;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
@@ -229,6 +230,7 @@ static struct sublevel_option debug_opts[] = {
 	{ .name = "stderr",		.value_ptr = &redirect_to_stderr},
 	{ .name = "data-convert",	.value_ptr = &debug_data_convert },
 	{ .name = "perf-event-open",	.value_ptr = &debug_peo_args },
+	{ .name = "kmaps",		.value_ptr = &debug_kmaps },
 	{ .name = NULL, }
 };
 
@@ -267,6 +269,7 @@ int perf_quiet_option(void)
 	/* For debug variables that are used as bool types, set to 0. */
 	redirect_to_stderr = 0;
 	debug_peo_args = 0;
+	debug_kmaps = 0;
 
 	return 0;
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index de8870980d44..35a7a5ae762e 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 
 extern int verbose;
+extern int debug_kmaps;
 extern int debug_peo_args;
 extern bool quiet, dump_trace;
 extern int debug_ordered_events;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 8761f51b5c7c..075c0f79b1b9 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -181,6 +181,7 @@ int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused)
  * implementing 'verbose' and 'eprintf'.
  */
 int verbose;
+int debug_kmaps;
 int debug_peo_args;
 
 int eprintf(int level, int var, const char *fmt, ...);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 199d3e8df315..06d0bd7fb459 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2720,6 +2720,17 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
 	return machine__fprintf(&session->machines.host, fp);
 }
 
+void perf_session__dump_kmaps(struct perf_session *session)
+{
+	int save_verbose = verbose;
+
+	fflush(stdout);
+	fprintf(stderr, "Kernel and module maps:\n");
+	verbose = 0; /* Suppress verbose to print a summary only */
+	maps__fprintf(machine__kernel_maps(&session->machines.host), stderr);
+	verbose = save_verbose;
+}
+
 struct evsel *perf_session__find_first_evtype(struct perf_session *session,
 					      unsigned int type)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index ee3715e8563b..5064c6ec11e7 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -133,6 +133,8 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp,
 				       bool skip_empty);
 
+void perf_session__dump_kmaps(struct perf_session *session);
+
 struct evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
-- 
2.34.1

[PATCH V3 2/2] perf symbols: Slightly improve module file executable section mappings

[Adrian Hunter]

Currently perf does not record module section addresses except for
the .text section. In general that means perf cannot get module section
mappings correct (except for .text) when loading symbols from a kernel
module file. (Note using --kcore does not have this issue)

Improve that situation slightly by identifying executable sections that
use the same mapping as the .text section. That happens when an
executable section comes directly after the .text section, both in memory
and on file, something that can be determined by following the same layout
rules used by the kernel, refer kernel layout_sections(). Note whether
that happens is somewhat arbitrary, so this is not a final solution.

Example from tracing a virtual machine process:

 Before:

  $ perf script | grep unknown
         CPU 0/KVM    1718   203.511270:     318341 cpu-cycles:P:  ffffffffc13e8a70 [unknown] (/lib/modules/6.7.2-local/kernel/arch/x86/kvm/kvm-intel.ko)
  $ perf script -vvv 2>&1 >/dev/null | grep kvm.intel | grep 'noinstr.text\|ffff'
  Map: 0-7e0 41430 [kvm_intel].noinstr.text
  Map: ffffffffc13a7000-ffffffffc1421000 a0 /lib/modules/6.7.2-local/kernel/arch/x86/kvm/kvm-intel.ko

 After:

  $ perf script | grep 203.511270
         CPU 0/KVM    1718   203.511270:     318341 cpu-cycles:P:  ffffffffc13e8a70 vmx_vmexit+0x0 (/lib/modules/6.7.2-local/kernel/arch/x86/kvm/kvm-intel.ko)
  $ perf script -vvv 2>&1 >/dev/null | grep kvm.intel | grep 'noinstr.text\|ffff'
  Map: ffffffffc13a7000-ffffffffc1421000 a0 /lib/modules/6.7.2-local/kernel/arch/x86/kvm/kvm-intel.ko

Reported-by: Like Xu <like.xu.linux@gmail.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/symbol-elf.c | 75 +++++++++++++++++++++++++++++++++++-
 1 file changed, 73 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 4b934ed3bfd1..95773c32796d 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -23,6 +23,7 @@
 #include <linux/ctype.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
+#include <linux/string.h>
 #include <symbol/kallsyms.h>
 #include <internal/lib.h>
 
@@ -1329,6 +1330,58 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	return -1;
 }
 
+static bool is_exe_text(int flags)
+{
+	return (flags & (SHF_ALLOC | SHF_EXECINSTR)) == (SHF_ALLOC | SHF_EXECINSTR);
+}
+
+/*
+ * Some executable module sections like .noinstr.text might be laid out with
+ * .text so they can use the same mapping (memory address to file offset).
+ * Check if that is the case. Refer to kernel layout_sections(). Return the
+ * maximum offset.
+ */
+static u64 max_text_section(Elf *elf, GElf_Ehdr *ehdr)
+{
+	Elf_Scn *sec = NULL;
+	GElf_Shdr shdr;
+	u64 offs = 0;
+
+	/* Doesn't work for some arch */
+	if (ehdr->e_machine == EM_PARISC ||
+	    ehdr->e_machine == EM_ALPHA)
+		return 0;
+
+	/* ELF is corrupted/truncated, avoid calling elf_strptr. */
+	if (!elf_rawdata(elf_getscn(elf, ehdr->e_shstrndx), NULL))
+		return 0;
+
+	while ((sec = elf_nextscn(elf, sec)) != NULL) {
+		char *sec_name;
+
+		if (!gelf_getshdr(sec, &shdr))
+			break;
+
+		if (!is_exe_text(shdr.sh_flags))
+			continue;
+
+		/* .init and .exit sections are not placed with .text */
+		sec_name = elf_strptr(elf, ehdr->e_shstrndx, shdr.sh_name);
+		if (!sec_name ||
+		    strstarts(sec_name, ".init") ||
+		    strstarts(sec_name, ".exit"))
+			break;
+
+		/* Must be next to previous, assumes .text is first */
+		if (offs && PERF_ALIGN(offs, shdr.sh_addralign ?: 1) != shdr.sh_offset)
+			break;
+
+		offs = shdr.sh_offset + shdr.sh_size;
+	}
+
+	return offs;
+}
+
 /**
  * ref_reloc_sym_not_found - has kernel relocation symbol been found.
  * @kmap: kernel maps and relocation reference symbol
@@ -1368,7 +1421,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 				      struct maps *kmaps, struct kmap *kmap,
 				      struct dso **curr_dsop, struct map **curr_mapp,
 				      const char *section_name,
-				      bool adjust_kernel_syms, bool kmodule, bool *remap_kernel)
+				      bool adjust_kernel_syms, bool kmodule, bool *remap_kernel,
+				      u64 max_text_sh_offset)
 {
 	struct dso *curr_dso = *curr_dsop;
 	struct map *curr_map;
@@ -1424,6 +1478,17 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 	if (!kmap)
 		return 0;
 
+	/*
+	 * perf does not record module section addresses except for .text, but
+	 * some sections can use the same mapping as .text.
+	 */
+	if (kmodule && adjust_kernel_syms && is_exe_text(shdr->sh_flags) &&
+	    shdr->sh_offset <= max_text_sh_offset) {
+		*curr_mapp = map;
+		*curr_dsop = dso;
+		return 0;
+	}
+
 	snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name);
 
 	curr_map = maps__find_by_name(kmaps, dso_name);
@@ -1497,6 +1562,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	Elf *elf;
 	int nr = 0;
 	bool remap_kernel = false, adjust_kernel_syms = false;
+	u64 max_text_sh_offset = 0;
 
 	if (kmap && !kmaps)
 		return -1;
@@ -1584,6 +1650,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		remap_kernel = true;
 		adjust_kernel_syms = dso->adjust_symbols;
 	}
+
+	if (kmodule && adjust_kernel_syms)
+		max_text_sh_offset = max_text_section(runtime_ss->elf, &runtime_ss->ehdr);
+
 	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
 		struct symbol *f;
 		const char *elf_name = elf_sym__name(&sym, symstrs);
@@ -1673,7 +1743,8 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 		if (dso->kernel) {
 			if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map,
-						       section_name, adjust_kernel_syms, kmodule, &remap_kernel))
+						       section_name, adjust_kernel_syms, kmodule,
+						       &remap_kernel, max_text_sh_offset))
 				goto out_elf_end;
 		} else if ((used_opd && runtime_ss->adjust_symbols) ||
 			   (!used_opd && syms_ss->adjust_symbols)) {
-- 
2.34.1

Re: [PATCH V3 0/2] perf symbols: Slightly improve module file executable section mappings

[Namhyung Kim]

On Thu, 8 Feb 2024 10:53:24 +0200, Adrian Hunter wrote:
> Currently perf does not record module section addresses except for
> the .text section. In general that means perf cannot get module section
> mappings correct (except for .text) when loading symbols from a kernel
> module file. (Note using --kcore does not have this issue)
> 
> Here are a couple of patches to help shed light upon and slightly improve
> the situation.
> 
> [...]

Applied to perf-tools-next, thanks!

Best regards,
-- 
Namhyung Kim <namhyung@kernel.org>