Re: [PATCH v5 14/25] Refactor parsing of /proc/<pid>/smaps

[Simon Marchi <simon.marchi@polymtl.ca>]

> +/* See linux-tdep.h.  */
> +
> +bool
> +linux_address_in_memtag_page (CORE_ADDR address)
> +{
> +  if (current_inferior ()->fake_pid_p)
> +    return false;
> +
> +  pid_t pid = current_inferior ()->pid;
> +
> +  std::string smaps_file = string_printf ("/proc/%d/smaps", pid);
> +
> +  gdb::unique_xmalloc_ptr<char> data
> +    = target_fileio_read_stralloc (NULL, smaps_file.c_str ());
> +
> +  if (data == nullptr)
> +    return false;
> +
> +  std::vector<struct smaps_data> smaps;
> +
> +  /* Parse the contents of smaps into a vector.  */
> +  smaps = parse_smaps_data (data.get (), smaps_file);

Declare and assign the vector directly:

  std::vector<smaps_data> smaps = ...;

> +
> +  for (const smaps_data &map : smaps)
> +    {
> +      /* Is the address within [start_address, end_address) in a page
> +	 mapped with memory tagging?  */
> +      if (address >= map.start_address
> +	  && address < map.end_address
> +	  && map.vmflags.memory_tagging)
> +	return true;
> +    }
> +
> +  return false;
> +}
> +
>  /* List memory regions in the inferior for a corefile.  */
>  
>  static int
> @@ -1319,137 +1521,50 @@ linux_find_memory_regions_full (struct gdbarch *gdbarch,
>        /* Older Linux kernels did not support /proc/PID/smaps.  */
>        maps_filename = string_printf ("/proc/%d/maps", pid);
>        data = target_fileio_read_stralloc (NULL, maps_filename.c_str ());
> -    }
> -
> -  if (data != NULL)
> -    {
> -      char *line, *t;
> -
> -      line = strtok_r (data.get (), "\n", &t);
> -      while (line != NULL)
> -	{
> -	  ULONGEST addr, endaddr, offset, inode;
> -	  const char *permissions, *device, *filename;
> -	  struct smaps_vmflags v;
> -	  size_t permissions_len, device_len;
> -	  int read, write, exec, priv;
> -	  int has_anonymous = 0;
> -	  int should_dump_p = 0;
> -	  int mapping_anon_p;
> -	  int mapping_file_p;
> -
> -	  memset (&v, 0, sizeof (v));
> -	  read_mapping (line, &addr, &endaddr, &permissions, &permissions_len,
> -			&offset, &device, &device_len, &inode, &filename);
> -	  mapping_anon_p = mapping_is_anonymous_p (filename);
> -	  /* If the mapping is not anonymous, then we can consider it
> -	     to be file-backed.  These two states (anonymous or
> -	     file-backed) seem to be exclusive, but they can actually
> -	     coexist.  For example, if a file-backed mapping has
> -	     "Anonymous:" pages (see more below), then the Linux
> -	     kernel will dump this mapping when the user specified
> -	     that she only wants anonymous mappings in the corefile
> -	     (*even* when she explicitly disabled the dumping of
> -	     file-backed mappings).  */
> -	  mapping_file_p = !mapping_anon_p;
> -
> -	  /* Decode permissions.  */
> -	  read = (memchr (permissions, 'r', permissions_len) != 0);
> -	  write = (memchr (permissions, 'w', permissions_len) != 0);
> -	  exec = (memchr (permissions, 'x', permissions_len) != 0);
> -	  /* 'private' here actually means VM_MAYSHARE, and not
> -	     VM_SHARED.  In order to know if a mapping is really
> -	     private or not, we must check the flag "sh" in the
> -	     VmFlags field.  This is done by decode_vmflags.  However,
> -	     if we are using a Linux kernel released before the commit
> -	     834f82e2aa9a8ede94b17b656329f850c1471514 (3.10), we will
> -	     not have the VmFlags there.  In this case, there is
> -	     really no way to know if we are dealing with VM_SHARED,
> -	     so we just assume that VM_MAYSHARE is enough.  */
> -	  priv = memchr (permissions, 'p', permissions_len) != 0;
> -
> -	  /* Try to detect if region should be dumped by parsing smaps
> -	     counters.  */
> -	  for (line = strtok_r (NULL, "\n", &t);
> -	       line != NULL && line[0] >= 'A' && line[0] <= 'Z';
> -	       line = strtok_r (NULL, "\n", &t))
> -	    {
> -	      char keyword[64 + 1];
>  
> -	      if (sscanf (line, "%64s", keyword) != 1)
> -		{
> -		  warning (_("Error parsing {s,}maps file '%s'"),
> -			   maps_filename.c_str ());
> -		  break;
> -		}
> +      if (data == nullptr)
> +	return 1;
> +    }
>  
> -	      if (strcmp (keyword, "Anonymous:") == 0)
> -		{
> -		  /* Older Linux kernels did not support the
> -		     "Anonymous:" counter.  Check it here.  */
> -		  has_anonymous = 1;
> -		}
> -	      else if (strcmp (keyword, "VmFlags:") == 0)
> -		decode_vmflags (line, &v);
> +  std::vector<struct smaps_data> smaps;
>  
> -	      if (strcmp (keyword, "AnonHugePages:") == 0
> -		  || strcmp (keyword, "Anonymous:") == 0)
> -		{
> -		  unsigned long number;
> -
> -		  if (sscanf (line, "%*s%lu", &number) != 1)
> -		    {
> -		      warning (_("Error parsing {s,}maps file '%s' number"),
> -			       maps_filename.c_str ());
> -		      break;
> -		    }
> -		  if (number > 0)
> -		    {
> -		      /* Even if we are dealing with a file-backed
> -			 mapping, if it contains anonymous pages we
> -			 consider it to be *also* an anonymous
> -			 mapping, because this is what the Linux
> -			 kernel does:
> -
> -			 // Dump segments that have been written to.
> -			 if (vma->anon_vma && FILTER(ANON_PRIVATE))
> -			 	goto whole;
> -
> -			 Note that if the mapping is already marked as
> -			 file-backed (i.e., mapping_file_p is
> -			 non-zero), then this is a special case, and
> -			 this mapping will be dumped either when the
> -			 user wants to dump file-backed *or* anonymous
> -			 mappings.  */
> -		      mapping_anon_p = 1;
> -		    }
> -		}
> -	    }
> +  /* Parse the contents of smaps into a vector.  */
> +  smaps = parse_smaps_data (data.get (), maps_filename.c_str ());

Likewise here.

>  
> -	  if (has_anonymous)
> -	    should_dump_p = should_dump_mapping_p (filterflags, &v, priv,
> -						   mapping_anon_p,
> -						   mapping_file_p,
> -						   filename, addr, offset);
> -	  else
> -	    {
> -	      /* Older Linux kernels did not support the "Anonymous:" counter.
> -		 If it is missing, we can't be sure - dump all the pages.  */
> -	      should_dump_p = 1;
> -	    }
> +  for (const struct smaps_data map : smaps)

You are missing the & to make it a reference (otherwise it makes a copy
of each item as it iterates, I don't think you want that.

Otherwise, LGTM.

Simon