Re: [RFC] elfutils: Checks for debuginfo file without .debug extension as well

[Mark Wielaard <mjw at redhat dot com>]

Hi Ravi,

My apologies for being slightly confused. I think what you are proposing
with your patch is the right thing. I am just slightly confused because
I thought the current code already did what you are proposing. So the
current code doesn't actually do what I thought it did :)

I have attached a simplified version of what I believe systemtap is
doing. It is a two step process. First it calls
dwfl_linux_kernel_report_offline to get the kernel file itself. Second
it gets the Dwarf for the kernel module, which should trigger
find_debuginfo to find the separate debug file, if needed.

It still doesn't show the full search path (for that we should hack
find_debuginfo_in_path and try_open in libdwfl/find-debuginfo.c a bit),
but it should be a start to better understand why the current search
isn't finding the separate kernel debug file.

On Wed, 2016-02-17 at 13:50 +0530, Ravi Bangoria wrote:
> On Tuesday 16 February 2016 10:15 PM, Mark Wielaard wrote:
> >> This patch adds functionality to search for file without any extension
> >> followed by searching file having .debug extension.
> > Thanks for the analysis. I do have a question though.
> >
> > The reason we are looking for the vmlinux-3.13.0-76-generic.debug
> > filename instead of the plain vmlinux-3.13.0-76-generic filename seems
> > to be because /boot/vmlinux contains a .gnu_debuginfo link with the name
> > of the debug file. But that name doesn't match?
> 
> So I should put it this way:
> 
> 'Ubuntu on powerpc' installs 'stripped' kernel 'without compressing it'
> as /boot/vmlinux. Most of the time it's assumed that vmlinux will have
> .debuginfo of .debuglink section. But this is not true here. See outputs
> below.
> 
> > What does eu-readelf --strings=.gnu_debuglink /boot/vmlinux* say?
> 
> # eu-readelf --strings=.gnu_debuglink /boot/vmlinux*
> 
> /boot/vmlinux:
> 
> eu-readelf:
> section '.gnu_debuglink' does not exist
> 
> /boot/vmlinux-3.13.0-76-generic:
> 
> eu-readelf:
> section '.gnu_debuglink' does not exist
> 
> /boot/vmlinux-4.2.0-27-generic:
> 
> eu-readelf:
> section '.gnu_debuglink' does not exist
> 
> /boot/vmlinux.old:
> 
> eu-readelf:
> section '.gnu_debuglink' does not exist

Aha, that is indeed not what I expected. Thanks.

> > Would it make sense to not put in the "correct" (without .debug suffix)
> > debugfile name in .gnu_debuglink
> 
> Yes, that should solve the problem. But changing structure of ubuntu
> kernel elf to solve stap problem doesn't look feasible to me. IIRC no
> other distro do that. I've confirmed this on RHEL. RHEL distro-kernel
> does not have .debuglink section.

OK, thanks. That is actually not what I expected. I had expected that if
there is no .debuglink section we already search for both the plain
and .debug file name. Apparently I got this wrong.

> Then you may ask how this is working in RHEL then. RHEL / Fedora on
> powerpc installs stripped uncompressed kernel as /boot/vmlinuz.
> elfutils looking for vmlinux, doesn't find it from /boot/, so it continue
> looking for file without any suffix(.debug) and it gets proper file. This is
> the case with ubunut x86 as well, except on x86, /boot/vmlinuz is
> compressed stripped image.

Aha. So Fedora/RHEL "cheats" by calling it vmlinuz while it isn't
actually compressed.

And another thing I missed is that the vmlinux file is the full
unstripped kernel image, even though it is put under /usr/debug...
So it contains the whole kernel plus the debuginfo.

> So I thought about this solution as well, renaming /boot/vmlinux to
> /boot/vmlinuz will solve the problem. But this is not appropriate. Because
> vmlinu*z* is for compressed image and we are just renaming file without
> compressing to solve stap problem.

Yeah, it is a bit cheating.

> >   or completely leaving .gnu_debuginfo
> > out (or is nothing found then?)
> 
> Not sure what does this mean. Can you please explain a bit more.

Sorry, silly confusing typo. I meant leaving out .gnu_debuglink. But it
is already not there.

Thanks,

Mark

// gcc -Wall -o dwfl_find_kernel -ldw dwfl_find_kernel.c

#include <inttypes.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/utsname.h>
#include <elfutils/libdwfl.h>

static char *kernel_file = NULL;
static int
setup_report_kernel (const char* modname, const char* filename)
{
  printf ("setup report modname: %s, filename: %s\n", modname, filename);

  /* We are only interested in the kernel.  */
  if (modname != NULL && strcmp (modname, "kernel") == 0)
    {
      /* We will get a null filename for modname == "kernel" if the
	 kernel couldn't be found.  We still want to stop, not
	 interested in any modules being found.  */
      if (filename == NULL)
	return -1;

      /* Copy the kernel file name and tell dwfl we want this module.  */
      kernel_file = strdup (filename);
      return 1;
    }

  /* Once we have seen the kernel we don't need any more modules.  We
     are not interested in any kernel modules.  */
  if (kernel_file != NULL)
    return -1;

  /* We don't need this module.  But we haven't seen the kernel yet,
     continue.  */
  return 0;
}

static char *kernel_dwarf_file = NULL;
static int
getdwarf_kernel (Dwfl_Module *mod, void **userdata,
		 const char *name, Dwarf_Addr base,
		 Dwarf *dw, Dwarf_Addr bias,
		 void *arg)
{
  printf ("getdwarf name: %s\n", name);

  if (name != NULL && strcmp (name, "kernel") == 0)
    {
      if (dw == NULL)
	{
	  printf ("kernel without DWARF\n");
	  return DWARF_CB_ABORT;
	}

      const char *mainfile, *debugfile;
      dwfl_module_info (mod, NULL, NULL, NULL, NULL, NULL,
			&mainfile, &debugfile);
      printf ("mainfile: %s, debugfile: %s\n", mainfile, debugfile);
      if (debugfile != NULL)
	kernel_dwarf_file = strdup (debugfile);
      else
	kernel_dwarf_file = strdup (mainfile);
    }

  return DWARF_CB_OK;
}

int
main (int argc, char **argv)
{
  char *release;
  if (argc > 1)
    release = argv[1];
  else
    {
      struct utsname uts;
      if (uname (&uts) != 0)
	{
	  perror ("uname failed");
	  return -1;
	}
      release = uts.release;
    }

  char *debuginfo_path;
  if (argc > 2)
    debuginfo_path = argv[2];
  else
    debuginfo_path = "+:.debug:/usr/lib/debug";

  printf ("Finding kernel release: %s\n", release);
  printf ("Debuginfo path: %s\n", debuginfo_path);

  Dwfl_Callbacks kernel_callbacks =
  {
    dwfl_linux_kernel_find_elf,
    dwfl_standard_find_debuginfo,
    dwfl_offline_section_address,
    (char **) & debuginfo_path
  };

  Dwfl *dwfl = dwfl_begin (&kernel_callbacks);
  if (dwfl == NULL)
    {
      printf ("dwfl_begin: %s\n", dwfl_errmsg (-1));
      return -1;
    }

  dwfl_report_begin (dwfl);
  dwfl_linux_kernel_report_offline (dwfl, release, &setup_report_kernel);
  dwfl_report_end(dwfl, NULL, NULL);

  if (kernel_file == NULL)
    {
      printf ("Couldn't find kernel\n");
      return -1;
    }

  printf ("Found kernel file: %s\n", kernel_file);

  ptrdiff_t p = 0;
  do
    p = dwfl_getdwarf (dwfl, &getdwarf_kernel, NULL, p);
  while (p > 0);

  if (kernel_dwarf_file == NULL)
    {
      printf ("Couldn't get kernel DWARF\n");
      return -1;
    }

  printf ("Found kernel DWARF file: %s\n", kernel_dwarf_file);

  dwfl_end (dwfl);
  free (kernel_file);
  free (kernel_dwarf_file);
  return 0;
}