perf-top: heap-buffer-overflow in elf_sec__is_text reported from ASan
Hi,
ASan reports a heap-buffer-overflow in elf_sec__is_text when using perf-top. The bug is introduced by commit 6833e0b: "perf symbols: Resolve symbols against debug file first" from Jiri Slaby.
This is the ASan output (with the source at perf/urgent).
$ make CC=clang CXX=clang++ EXTRA_CFLAGS="-g -O0 -fsanitize=address -fno-omit-frame-pointer" WERROR=0 NO_LIBPYTHON=1 DEBUG=1 NO_LIBPERL=1
[...]
# ASAN_OPTIONS=abort_on_error=1:disable_coredump=0:unmap_shadow_on_exit=1 ./perf top
=================================================================
==363148==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x61300009add6 at pc 0x00000049875c bp 0x7f4f56446440 sp 0x7f4f56445bf0
READ of size 1 at 0x61300009add6 thread T6
#0 0x49875b in StrstrCheck(void*, char*, char const*, char const*) (/home/user/linux/tools/perf/perf+0x49875b)
#1 0x4d13a2 in strstr (/home/user/linux/tools/perf/perf+0x4d13a2)
#2 0xacae36 in elf_sec__is_text /home/user/linux/tools/perf/util/symbol-elf.c:176:9
#3 0xac3ec9 in elf_sec__filter /home/user/linux/tools/perf/util/symbol-elf.c:187:9
#4 0xac2c3d in dso__load_sym /home/user/linux/tools/perf/util/symbol-elf.c:1254:20
#5 0x883981 in dso__load /home/user/linux/tools/perf/util/symbol.c:1897:9
#6 0x8e6248 in map__load /home/user/linux/tools/perf/util/map.c:332:7
#7 0x8e66e5 in map__find_symbol /home/user/linux/tools/perf/util/map.c:366:6
#8 0x7f8278 in machine__resolve /home/user/linux/tools/perf/util/event.c:707:13
#9 0x5f3d1a in perf_event__process_sample /home/user/linux/tools/perf/builtin-top.c:773:6
#10 0x5f30e4 in deliver_event /home/user/linux/tools/perf/builtin-top.c:1197:3
#11 0x908a72 in do_flush /home/user/linux/tools/perf/util/ordered-events.c:244:9
#12 0x905fae in __ordered_events__flush /home/user/linux/tools/perf/util/ordered-events.c:323:8
#13 0x9058db in ordered_events__flush /home/user/linux/tools/perf/util/ordered-events.c:341:9
#14 0x5f19b1 in process_thread /home/user/linux/tools/perf/builtin-top.c:1109:7
#15 0x7f4f6a21a298 in start_thread /usr/src/debug/glibc-2.33-16.fc34.x86_64/nptl/pthread_create.c:481:8
#16 0x7f4f697d0352 in clone ../sysdeps/unix/sysv/linux/x86_64/clone.S:950x61300009add6 is located 10 bytes to the right of 332-byte region [0x61300009ac80,0x61300009adcc) allocated by thread T6 here:
#0 0x4f3f7f in malloc (/home/user/linux/tools/perf/perf+0x4f3f7f)
#1 0x7f4f6a0a88d9 (/lib64/libelf.so.1+0xa8d9)Thread T6 created by T0 here:
#0 0x464856 in pthread_create (/home/user/linux/tools/perf/perf+0x464856)
#1 0x5f06e0 in __cmd_top /home/user/linux/tools/perf/builtin-top.c:1309:6
#2 0x5ef19f in cmd_top /home/user/linux/tools/perf/builtin-top.c:1762:11
#3 0x7b28c0 in run_builtin /home/user/linux/tools/perf/perf.c:313:11
#4 0x7b119f in handle_internal_command /home/user/linux/tools/perf/perf.c:365:8
#5 0x7b2423 in run_argv /home/user/linux/tools/perf/perf.c:409:2
#6 0x7b0c19 in main /home/user/linux/tools/perf/perf.c:539:3
#7 0x7f4f696f7b74 in __libc_start_main /usr/src/debug/glibc-2.33-16.fc34.x86_64/csu/../csu/libc-start.c:332:16SUMMARY: AddressSanitizer: heap-buffer-overflow (/home/user/linux/tools/perf/perf+0x49875b) in StrstrCheck(void*, char*, char const*, char const*) Shadow bytes around the buggy address:
0x0c268000b560: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c268000b570: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c268000b580: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c268000b590: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0c268000b5a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
=>0x0c268000b5b0: 00 00 00 00 00 00 00 00 00 04[fa]fa fa fa fa fa
0x0c268000b5c0: fa fa fa fa fa fa fa fa 00 00 00 00 00 00 00 00
0x0c268000b5d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0c268000b5e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0c268000b5f0: 07 fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c268000b600: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd
Shadow byte legend (one shadow byte represents 8 application bytes):
Addressable: 00
Partially addressable: 01 02 03 04 05 06 07
Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb Shadow gap: cc
==363148==ABORTING
Here is some more information from the coredump:
pwndbg> p *shdr
$1 = {
sh_name = 342,
sh_type = 1,
sh_flags = 0,
sh_addr = 0,
sh_offset = 8472,
sh_size = 1140436,
sh_link = 0,
sh_info = 0,
sh_addralign = 1,
sh_entsize = 0
}
pwndbg> p *secstrs
$2 = {
d_buf = 0x6130001836c0,
d_type = ELF_T_BYTE,
d_version = 1,
d_size = 332,
d_off = 0,
d_align = 1
}
pwndbg> p syms_ss->name
$4 = 0x607000018f90 "/usr/lib/debug/usr/lib64/libglib-2.0.so.0.6800.2-2.68.2-1.fc34.x86_64.debug" pwndbg> p runtime_ss->name
$5 = 0x6070000190e0 "/root/.debug/.build-id/37/475e3b392fb3971c8ad0d9ac0a4d7e1b93c521/elf"
Furthermore, the branch in line symbol-elf.c:1241 (the one added in the referred patch) is not taken.
As you can see, sh_name is out-of-range (342 > 332). I can also provide a coredump, if it can be useful.
I have no idea of how the ELF stuff works, but I thought this may be caused by the fact that secstrs is built from runtime_ss, while shdr is built from syms_ss (since it is the change of the commit). I tried to test this theory with the following change:
tools/perf/util/symbol-elf.c +9 -1
@@ -1146,7 +1146,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,if (symstrs ==NULL ) goto out_elf_end; - sec_strndx =elf_getscn (runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); + sec_strndx =elf_getscn (elf, ehdr.e_shstrndx);if (sec_strndx ==NULL ) goto out_elf_end;
@@ -1244,6 +1244,14 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,* values for syms (invalid) and runtime (valid). */ if (shdr.sh_type ==SHT_NOBITS ) { + sec_strndx =elf_getscn (runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); +if (sec_strndx ==NULL ) + goto out_elf_end; + + secstrs =elf_getdata (sec_strndx,NULL ); +if (secstrs ==NULL ) + goto out_elf_end; + sec =elf_getscn (runtime_ss->elf, sym.st_shndx);if (!sec) goto out_elf_end;
However, it still overflows, but oddly the branch is not taken before the overflow. Is there some kind of state that gets changed in the ELF structs?
I also tried to just change line 1146 as in the diff below:
tools/perf/util/symbol-elf.c +1 -1
@@ -1146,7 +1146,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,if (symstrs ==NULL ) goto out_elf_end; - sec_strndx =elf_getscn (runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); + sec_strndx =elf_getscn (elf, ehdr.e_shstrndx);if (sec_strndx ==NULL ) goto out_elf_end;
In this case, ASan reports no overflows. So, it looks like it kinda solves the problem, but I don't know if it's correct.
What do you think?
Thanks,
Riccardo
Hi,
Quoted 3 lines · Riccardo Mancini
ASan reports a heap-buffer-overflow in
elf_sec__is_textwhen using perf-top. The bug is introduced by commit 6833e0b: "perf symbols: Resolve symbols against debug file first" from Jiri Slaby.
...
Quoted 4 lines
pwndbg> p
syms_ss->name
$4 =0x607000018f90"/usr/lib/debug/usr/lib64/libglib-2.0.so.0.6800.2-2.68.2-1.fc34.x86_64.debug" pwndbg> pruntime_ss->name
$5 =0x6070000190e0"/root/.debug/.build-id/37/475e3b392fb3971c8ad0d9ac0a4d7e1b93c521/elf"
Out of curiosity, could you post output of 'readelf -S' on both of them?
Quoted 40 lines
Furthermore, the branch in line symbol-elf.c:1241 (the one added in the referred patch) is not taken.
As you can see,
sh_nameis out-of-range (342 > 332). I can also provide a coredump, if it can be useful.I have no idea of how the ELF stuff works, but I thought this may be caused by the fact that secstrs is built from
runtime_ss, while shdr is built fromsyms_ss(since it is the change of the commit). I tried to test this theory with the following change:tools/perf/util/symbol-elf.c +9
-1@@ -1146,7 +1146,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,if (symstrs ==NULL ) goto out_elf_end; - sec_strndx =elf_getscn (runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); + sec_strndx =elf_getscn (elf, ehdr.e_shstrndx);if (sec_strndx ==NULL ) goto out_elf_end;@@ -1244,6 +1244,14 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,* values for syms (invalid) and runtime (valid). */ if (shdr.sh_type ==SHT_NOBITS ) { + sec_strndx =elf_getscn (runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); +if (sec_strndx ==NULL ) + goto out_elf_end; + + secstrs =elf_getdata (sec_strndx,NULL ); +if (secstrs ==NULL ) + goto out_elf_end; + sec =elf_getscn (runtime_ss->elf, sym.st_shndx);if (!sec) goto out_elf_end;
Quoted 2 lines
However, it still overflows, but oddly the branch is not taken before the overflow. Is there some kind of state that gets changed in the ELF structs?
Something like that should work. But you should reset sec_strndx also in the else branch, IMO. So what about this?
tools/perf/util/symbol-elf.c +13 -3
@@ -1081,7 +1081,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,struct maps *kmaps = kmap ?map__kmaps (map) :NULL ;struct map *curr_map = map;struct dso *curr_dso = dso; -Elf_Data *symstrs, *secstrs; +Elf_Data *symstrs, *secstrs, *secstrs_run, *secstrs_sym;uint32_t nr_syms;int err =-1 ;uint32_t idx;
@@ -1150,8 +1150,16 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,if (sec_strndx ==NULL ) goto out_elf_end; - secstrs =elf_getdata (sec_strndx,NULL ); -if (secstrs ==NULL ) + secstrs_run =elf_getdata (sec_strndx,NULL ); +if (secstrs_run ==NULL ) + goto out_elf_end; + + sec_strndx =elf_getscn (elf, ehdr.e_shstrndx); +if (sec_strndx ==NULL ) + goto out_elf_end; + + secstrs_sym =elf_getdata (sec_strndx,NULL ); +if (secstrs_sym ==NULL ) goto out_elf_end; nr_syms = shdr.sh_size / shdr.sh_entsize;
@@ -1237,6 +1245,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,gelf_getshdr (sec, &shdr); + secstrs = secstrs_sym; +/* * We have to fallback to runtime when syms' section
header has
* NOBITS set. NOBITS results in file offset
(sh_offset) not
@@ -1249,6 +1259,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
goto out_elf_end;
gelf_getshdr(sec, &shdr);
+ secstrs = secstrs_run;
}
if (is_label && !elf_sec__filter(&shdr, secstrs))thanks,
Signature · 5 lines
js -- js suse labs
Hi,
thank you very much for your reply!
Quoted 8 lines · Jiri Slaby
Hi,
Quoted 4 lines · Riccardo Mancini
ASan reports a heap-buffer-overflow in
elf_sec__is_textwhen using perf-top. The bug is introduced by commit 6833e0b: "perf symbols: Resolve symbols against
debug file first" from Jiri Slaby....
Quoted 8 lines
Quoted 6 lines
pwndbg> p
syms_ss->name
$4 =0x607000018f90"/usr/lib/debug/usr/lib64/libglib-2.0.so.0.6800.2-2.68.2-1.fc34.x86_64.debug"
pwndbg> pruntime_ss->name
$5 =0x6070000190e0"/root/.debug/.build-id/37/475e3b392fb3971c8ad0d9ac0a4d7e1b93c521/elf"Out of curiosity, could you post output of 'readelf -S' on both of them?
Sure, I'll post it to the bottom of this email since it's quite long.
Quoted 46 lines
Quoted 46 lines
Furthermore, the branch in line symbol-elf.c:1241 (the one added in the referred
patch) is not taken.As you can see,
sh_nameis out-of-range (342 > 332). I can also provide a coredump, if it can be useful.I have no idea of how the ELF stuff works, but I thought this may be caused by the fact that secstrs is built from
runtime_ss, while shdr is built fromsyms_ss
(since it is the change of the commit). I tried to test this theory with the following change:tools/perf/util/symbol-elf.c +0
-0@@ -1146,7 +1146,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, if (symstrs == NULL) goto out_elf_end;
- sec_strndx =elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); + sec_strndx =elf_getscn(elf, ehdr.e_shstrndx);
if (sec_strndx== NULL)
gotoout_elf_end;tools/perf/util/symbol-elf.c +8
-0@@ -1244,6 +1244,14 @@ int dso__load_sym(struct dso *dso, struct map *map,struct symsrc *syms_ss, * values for syms (invalid) and runtime (valid). */ if (shdr.sh_type == SHT_NOBITS) { + sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss- >ehdr.e_shstrndx); + if (sec_strndx == NULL) + goto out_elf_end; + + secstrs = elf_getdata(sec_strndx, NULL); + if (secstrs == NULL) + goto out_elf_end; + sec = elf_getscn(runtime_ss->elf, sym.st_shndx);if (!sec)
gotoout_elf_end;
Quoted 5 lines
Quoted 2 lines
However, it still overflows, but oddly the branch is not taken before the overflow. Is there some kind of state that gets changed in the ELF structs?
Something like that should work. But you should reset
sec_strndxalso in the else branch, IMO.
Oops, that was embarassing. I completely forgot that it was inside a loop.
Quoted 54 lines
So what about this?
tools/perf/util/symbol-elf.c +1
-1@@ -1081,7 +1081,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct maps *kmaps = kmap ? map__kmaps(map) : NULL; struct map *curr_map = map; struct dso *curr_dso = dso; - Elf_Data *symstrs, *secstrs; + Elf_Data *symstrs, *secstrs, *secstrs_run, *secstrs_sym; uint32_t nr_syms; int err = -1;
uint32_tidx;tools/perf/util/symbol-elf.c +10
-2@@ -1150,8 +1150,16 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, if (sec_strndx == NULL) goto out_elf_end; - secstrs = elf_getdata(sec_strndx, NULL); - if (secstrs == NULL) + secstrs_run = elf_getdata(sec_strndx, NULL); + if (secstrs_run == NULL) + goto out_elf_end; + + sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); + if (sec_strndx == NULL) + goto out_elf_end; + + secstrs_sym = elf_getdata(sec_strndx, NULL); + if (secstrs_sym == NULL) goto out_elf_end;
nr_syms= shdr.sh_size / shdr.sh_entsize;tools/perf/util/symbol-elf.c +2
-0@@ -1237,6 +1245,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, gelf_getshdr(sec, &shdr); + secstrs = secstrs_sym; + /** We have to fallback to runtime when syms' section header has
* NOBITS set. NOBITS results in file offset (sh_offset) nottools/perf/util/symbol-elf.c +1
-0@@ -1249,6 +1259,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, goto out_elf_end; gelf_getshdr(sec, &shdr); + secstrs = secstrs_run; }
Quoted 1 line
if (
is_label&& !elf_sec__filter(&shdr, secstrs))
It works, thanks!
Quoted 5 lines
thanks,
Signature · 1 line
js
Here are the ELF sections of the two files causing the bug:
# readelf -S /usr/lib/debug/usr/lib64/libglib-2.0.so.0.6800.2-2.68.2-1.fc34.x86_64.debug There are 43 section headers, starting at offset 0x386ed0:
Section Headers:
[Nr] Name Type Address Offset
Size EntSize Flags Link Info Align
[ 0] NULL 0000000000000000 00000000
0000000000000000 0000000000000000 0 0 0
[ 1] .note.gnu.pr[...] NOTE 00000000000002a8 000002a8
0000000000000020 0000000000000000 A 0 0 8
[ 2] .note.gnu.bu[...] NOTE 00000000000002c8 000002c8
0000000000000024 0000000000000000 A 0 0 4
[ 3] .gnu.hash NOBITS 00000000000002f0 000002f0
000000000000341c 0000000000000000 A 4 0 8
[ 4] .dynsym NOBITS 0000000000003710 000002f0
000000000000bdd8 0000000000000018 A 5 1 8
[ 5] .dynstr NOBITS 000000000000f4e8 000002f0
0000000000009a40 0000000000000000 A 0 0 1
[ 6] .gnu.version NOBITS 0000000000018f28 000002f0
0000000000000fd2 0000000000000002 A 4 0 2
[ 7] .gnu.version_r NOBITS 0000000000019f00 000002f0
0000000000000150 0000000000000000 A 5 2 8
[ 8] .rela.dyn NOBITS 000000000001a050 000002f0
0000000000000e88 0000000000000018 A 4 0 8
[ 9] .rela.plt NOBITS 000000000001aed8 000002f0
0000000000001548 0000000000000018 AI 4 23 8
[10] .init NOBITS 000000000001d000 000002f0
000000000000001b 0000000000000000 AX 0 0 4
[11] .plt NOBITS 000000000001d020 000002f0
0000000000000e40 0000000000000010 AX 0 0 16
[12] .plt.sec NOBITS 000000000001de60 000002f0
0000000000000e30 0000000000000010 AX 0 0 16
[13] .text NOBITS 000000000001ec90 000002f0
000000000008d842 0000000000000000 AX 0 0 16
[14] .fini NOBITS 00000000000ac4d4 000002f0
000000000000000d 0000000000000000 AX 0 0 4
[15] .rodata NOBITS 00000000000ad000 00000300
000000000006878c 0000000000000000 A 0 0 32
[16] .stapsdt.base NOBITS 000000000011578c 00000300
0000000000000001 0000000000000000 A 0 0 1
[17] .eh_frame_hdr NOBITS 0000000000115790 00000300
000000000000470c 0000000000000000 A 0 0 4
[18] .eh_frame NOBITS 0000000000119ea0 00000300
000000000001ba00 0000000000000000 A 0 0 8
[19] .init_array NOBITS 00000000001373a8 00000300
0000000000000010 0000000000000008 WA 0 0 8
[20] .fini_array NOBITS 00000000001373b8 00000300
0000000000000008 0000000000000008 WA 0 0 8
[21] .data.rel.ro NOBITS 00000000001373c0 00000300
0000000000000240 0000000000000000 WA 0 0 32
[22] .dynamic NOBITS 0000000000137600 00000300
0000000000000210 0000000000000010 WA 5 0 8
[23] .got NOBITS 0000000000137810 00000300
00000000000007e0 0000000000000008 WA 0 0 8
[24] .data NOBITS 0000000000138000 00000300
00000000000005f8 0000000000000000 WA 0 0 32
[25] .probes NOBITS 00000000001385f8 00000300
0000000000000060 0000000000000000 WA 0 0 2
[26] .bss NOBITS 0000000000138660 00000300
0000000000000d10 0000000000000000 WA 0 0 32
[27] .comment PROGBITS 0000000000000000 00000300
000000000000005c 0000000000000001 MS 0 0 1
[28] .note.stapsdt NOTE 0000000000000000 0000035c
0000000000001554 0000000000000000 0 0 4
[29] .gnu.build.a[...] NOTE 000000000013b370 000018b0
00000000000005c8 0000000000000000 0 0 4
[30] .debug_aranges PROGBITS 0000000000000000 00001e78
00000000000002a0 0000000000000000 0 0 1
[31] .debug_info PROGBITS 0000000000000000 00002118
00000000001166d4 0000000000000000 0 0 1
[32] .debug_abbrev PROGBITS 0000000000000000 001187ec
000000000000dad6 0000000000000000 0 0 1
[33] .debug_line PROGBITS 0000000000000000 001262c2
000000000006cff4 0000000000000000 0 0 1
[34] .debug_str PROGBITS 0000000000000000 001932b6
000000000000d853 0000000000000001 MS 0 0 1
[35] .debug_line_str PROGBITS 0000000000000000 001a0b09
0000000000001037 0000000000000001 MS 0 0 1
[36] .debug_loclists PROGBITS 0000000000000000 001a1b40
00000000000c5cfc 0000000000000000 0 0 1
[37] .debug_rnglists PROGBITS 0000000000000000 0026783c
0000000000016ff6 0000000000000000 0 0 1
[38] .gdb_index PROGBITS 0000000000000000 0027e832
0000000000028f3a 0000000000000000 0 0 1
[39] .gnu_debugaltlink PROGBITS 0000000000000000 002a776c
000000000000003a 0000000000000000 0 0 1
[40] .symtab SYMTAB 0000000000000000 002a77a8
00000000000a3b18 0000000000000018 41 25913 8
[41] .strtab STRTAB 0000000000000000 0034b2c0
000000000003ba35 0000000000000000 0 0 1
[42] .shstrtab STRTAB 0000000000000000 00386cf5
00000000000001d4 0000000000000000 0 0 1Key to Flags:
W (write), A (alloc), X (execute), M (merge), S (strings), I (info), L (link order), O (extra OS processing required), G (group), T (TLS), C (compressed), x (unknown), o (OS specific), E (exclude), l (large), p (processor specific)
# sudo readelf -S /root/.debug/.build-id/37/475e3b392fb3971c8ad0d9ac0a4d7e1b93c521/elf There are 32 section headers, starting at offset 0x13d088:
Section Headers:
[Nr] Name Type Address Offset
Size EntSize Flags Link Info Align
[ 0] NULL 0000000000000000 00000000
0000000000000000 0000000000000000 0 0 0
[ 1] .note.gnu.pr[...] NOTE 00000000000002a8 000002a8
0000000000000020 0000000000000000 A 0 0 8
[ 2] .note.gnu.bu[...] NOTE 00000000000002c8 000002c8
0000000000000024 0000000000000000 A 0 0 4
[ 3] .gnu.hash GNU_HASH 00000000000002f0 000002f0
000000000000341c 0000000000000000 A 4 0 8
[ 4] .dynsym DYNSYM 0000000000003710 00003710
000000000000bdd8 0000000000000018 A 5 1 8
[ 5] .dynstr STRTAB 000000000000f4e8 0000f4e8
0000000000009a40 0000000000000000 A 0 0 1
[ 6] .gnu.version VERSYM 0000000000018f28 00018f28
0000000000000fd2 0000000000000002 A 4 0 2
[ 7] .gnu.version_r VERNEED 0000000000019f00 00019f00
0000000000000150 0000000000000000 A 5 2 8
[ 8] .rela.dyn RELA 000000000001a050 0001a050
0000000000000e88 0000000000000018 A 4 0 8
[ 9] .rela.plt RELA 000000000001aed8 0001aed8
0000000000001548 0000000000000018 AI 4 23 8
[10] .init PROGBITS 000000000001d000 0001d000
000000000000001b 0000000000000000 AX 0 0 4
[11] .plt PROGBITS 000000000001d020 0001d020
0000000000000e40 0000000000000010 AX 0 0 16
[12] .plt.sec PROGBITS 000000000001de60 0001de60
0000000000000e30 0000000000000010 AX 0 0 16
[13] .text PROGBITS 000000000001ec90 0001ec90
000000000008d842 0000000000000000 AX 0 0 16
[14] .fini PROGBITS 00000000000ac4d4 000ac4d4
000000000000000d 0000000000000000 AX 0 0 4
[15] .rodata PROGBITS 00000000000ad000 000ad000
000000000006878c 0000000000000000 A 0 0 32
[16] .stapsdt.base PROGBITS 000000000011578c 0011578c
0000000000000001 0000000000000000 A 0 0 1
[17] .eh_frame_hdr PROGBITS 0000000000115790 00115790
000000000000470c 0000000000000000 A 0 0 4
[18] .eh_frame PROGBITS 0000000000119ea0 00119ea0
000000000001ba00 0000000000000000 A 0 0 8
[19] .init_array INIT_ARRAY 00000000001373a8 001363a8
0000000000000010 0000000000000008 WA 0 0 8
[20] .fini_array FINI_ARRAY 00000000001373b8 001363b8
0000000000000008 0000000000000008 WA 0 0 8
[21] .data.rel.ro PROGBITS 00000000001373c0 001363c0
0000000000000240 0000000000000000 WA 0 0 32
[22] .dynamic DYNAMIC 0000000000137600 00136600
0000000000000210 0000000000000010 WA 5 0 8
[23] .got PROGBITS 0000000000137810 00136810
00000000000007e0 0000000000000008 WA 0 0 8
[24] .data PROGBITS 0000000000138000 00137000
00000000000005f8 0000000000000000 WA 0 0 32
[25] .probes PROGBITS 00000000001385f8 001375f8
0000000000000060 0000000000000000 WA 0 0 2
[26] .bss NOBITS 0000000000138660 00137658
0000000000000d10 0000000000000000 WA 0 0 32
[27] .note.stapsdt NOTE 0000000000000000 00137658
0000000000001554 0000000000000000 0 0 4
[28] .gnu.build.a[...] NOTE 000000000013b370 00138bac
00000000000005c8 0000000000000000 0 0 4
[29] .gnu_debuglink PROGBITS 0000000000000000 00139174
0000000000000038 0000000000000000 0 0 4
[30] .gnu_debugdata PROGBITS 0000000000000000 001391ac
0000000000003d90 0000000000000000 0 0 1
[31] .shstrtab STRTAB 0000000000000000 0013cf3c
000000000000014c 0000000000000000 0 0 1Key to Flags:
W (write), A (alloc), X (execute), M (merge), S (strings), I (info), L (link order), O (extra OS processing required), G (group), T (TLS), C (compressed), x (unknown), o (OS specific), E (exclude), l (large), p (processor specific)
Thanks,
Riccardo