On Mon, 29 Mar 2021, Jiri Slaby wrote:

> Any ideas on this?
> 
> On 11. 01. 21, 7:31, Jiri Slaby wrote:
> > Hi,
> > 
> > this e-mails is a follow-up of my report at:
> > https://bugzilla.suse.com/show_bug.cgi?id=1180681
> > 
> > There is a problem with *@plt symbols in some libraries, they are unresolved
> > by perf (memcmp@plt in this case):
> >  >     0.26%  main2    /usr/lib64/libstdc++.so.6.0.28            0xa51a0 
> >             l [.] 0x00000000000a51a0
> > 
> > On the other hand, plt symbols in other libraries are fine (memset@plt in
> > this case):
> >  >     0.17%  main2    /usr/lib64/libantlr4-runtime.so.4.8       0x4ed10 
> >             l [.] memset@plt
> > 
> > I dumped memcmp's .plt.rela entries in perf:
> > /usr/lib64/libantlr4-runtime.so.4.8: 154th addr=4e9d0 plt_off=4e020 hdr=10
> > entry=10
> > /usr/lib64/libstdc++.so.6.0.28: 772th addr=a1070 plt_off=9e020 hdr=10
> > entry=10
> > 
> > The difference (offset) of stdc++'s memcmp is 0xa51a0 (correct) - 0xa1070
> > (perf's computed) = 0x4130.
> > 
> > The problem is perf assumes nth entry of .plt.rela to correspond to nth
> > function in .plt, but memcmp is in .plt.sec in libstdc++.so:
> > 
> >  >Relocation section '.rela.plt' at offset 0x97900 contains 1018 entries:
> >  >     Offset             Info             Type               Symbol's 
> > Value  Symbol's Name + Addend
> >  > ...
> >  > 00000000001dc838  0000007800000007 R_X86_64_JUMP_SLOT 
> > 0000000000000000 memcmp@GLIBC_2.2.5 + 0
> > 
> > Perf does this with the rela entries:
> > https://github.com/torvalds/linux/blob/f5e6c330254ae691f6d7befe61c786eb5056007e/tools/perf/util/symbol-elf.c#L385 
> > 
> > It takes a symbol index from sym.r_info. Then it resolves its name from
> > .dynsym, appending "@plt" to it. Then this name is added to perf's symbol
> > table along with address which is computed as .rela.plt index multiplied by
> > entry size (shdr_plt.sh_entsize) plus plt header (shdr_plt.sh_entsize on
> > x86_64 too).
> > 
> > And from this comes (almost) the offset above:
> >  >$ objdump -h /usr/lib64/libstdc++.so.6|grep -E ' .plt(\.sec)? '
> >  >  12 .plt          00003fb0  000000000009e020  000000000009e020 
> > 0009e020  2**4
> >  >  14 .plt.sec      00003fa0  00000000000a2160  00000000000a2160 
> > 000a2160  2**4
> > 
> > 0xa2160-0x9e020 = 0x4140. I assume the 0x10 difference is that perf adds
> > shdr_plt.sh_entsize (0x10) to the offset to skip the first .plt entry
> > (header).
> > 
> > Richard writes:
> > ======
> > .plt.sec is IIRC the "second" (sec) PLT entry - the one that will be used on
> > the second call (and on).  This is used / emitted for ELF object
> > instrumented for Intel CET.  The details escape me for the moment but I hope
> > the x86 ABI documents this (and the constraints) in detail.

I just checked and the x86_64 psABI doesn't say anything about .plt.sec

> > ======
> > 
> > How should perf find out whether to consider .plt or .plt.sec? Or generally,
> > how to properly find an address of *@plt symbols like memcmp@plt above?
> > thanks,
> 
> 
> 

-- 
Richard Biener <rguenther@suse.de>
SUSE Software Solutions Germany GmbH, Maxfeldstrasse 5, 90409 Nuernberg,
Germany; GF: Felix Imendörffer; HRB 36809 (AG Nuernberg)