RE: [PATCH v1 05/10] gdb: introduce helper class file_reader_t

["Schimpe, Christina" <christina.schimpe@intel.com>]

Hi Matthieu,

Please find my feedback below.

> -----Original Message-----
> From: Matthieu Longo <matthieu.longo@arm.com>
> Sent: Dienstag, 7. Juli 2026 17:49
> To: gdb-patches@sourceware.org
> Cc: Luis Machado <luis.machado@amd.com>; Luis Machado
> <luis.machado.foss@gmail.com>; Andrew Burgess <aburgess@redhat.com>;
> Yury Khrustalev <yury.khrustalev@arm.com>; Pedro Alves
> <pedro@palves.net>; Tom Tromey <tom@tromey.com>; Matthieu Longo
> <matthieu.longo@arm.com>
> Subject: [PATCH v1 05/10] gdb: introduce helper class file_reader_t
> 
> Wrap all the boilerplate code required to read a file in a new helper
> class: file_reader_t. The class owns the file contents together with the file
> path, and provides convenient accessors for the data, size and typed views. It
> supports both null-terminated text files and binary files.
> 
> This helper eliminates repeated calls to target_fileio_read_stralloc and
> target_fileio_read_alloc, remove explicit memory management with
> gdb::unique_xmalloc_ptr, and simplifies the casting logic when working with
> binary data.
> 
> The patch converts some of the existing Linux, AMD64, and SPARC code that
> reads files from /proc to use file_reader_t.
> ---
>  gdb/amd64-linux-tdep.c |  12 ++---
>  gdb/linux-tdep.c       | 102 +++++++++++++++++------------------------
>  gdb/sparc64-tdep.c     |  12 ++---
>  gdb/target.h           |  65 ++++++++++++++++++++++++++
>  4 files changed, 117 insertions(+), 74 deletions(-)
> 
> diff --git a/gdb/amd64-linux-tdep.c b/gdb/amd64-linux-tdep.c index
> a5ac26654cf..e7841917eaf 100644
> --- a/gdb/amd64-linux-tdep.c
> +++ b/gdb/amd64-linux-tdep.c
> @@ -1851,14 +1851,11 @@ amd64_linux_lam_untag_mask ()
>    if (inf->fake_pid_p)
>      return DEFAULT_TAG_MASK;
> 
> -  const std::string filename = string_printf ("/proc/%d/status", inf->pid);
> -  gdb::unique_xmalloc_ptr<char> status_file
> -    = target_fileio_read_stralloc (nullptr, filename.c_str ());
> -
> -  if (status_file == nullptr)
> +  file_reader_t<char> proc_status (string_printf ("/proc/%d/status",
> + inf->pid));  if (!proc_status)
>      return DEFAULT_TAG_MASK;
> 
> -  std::string_view status_file_view (status_file.get ());
> +  std::string_view status_file_view (proc_status.data ());
>    constexpr std::string_view untag_mask_str = "untag_mask:\t";
>    const size_t found = status_file_view.find (untag_mask_str);
>    if (found != std::string::npos)
> @@ -1870,7 +1867,8 @@ amd64_linux_lam_untag_mask ()
>        unsigned long long result = std::strtoul (start, &endptr, 0);
>        if (errno != 0 || endptr == start)
>  	error (_("Failed to parse untag_mask from file %ps."),
> -	       styled_string (file_name_style.style (), filename.c_str ()));
> +	       styled_string (file_name_style.style (),
> +			      proc_status.c_filepath ()));
> 
>        return result;
>      }
> diff --git a/gdb/linux-tdep.c b/gdb/linux-tdep.c index
> b89f4ee0717..a12a69f03a2 100644
> --- a/gdb/linux-tdep.c
> +++ b/gdb/linux-tdep.c
> @@ -1661,6 +1661,12 @@ parse_smaps_data (const char *data,
>    return smaps;
>  }
> 
> +static std::vector<struct smaps_data>
> +parse_smaps_data (const file_reader_t<char> &freader) {
> +  return parse_smaps_data (freader.data (), freader.filepath ()); }
> +
>  /* Helper that checks if an address is in a memory tag page for a live
>     process.  */
> 
> @@ -1672,17 +1678,13 @@ linux_process_address_in_memtag_page
> (CORE_ADDR address)
> 
>    ptid_t ptid = current_inferior ()->first_alive_thread ();
> 
> -  std::string smaps_file = string_printf ("/proc/%ld/smaps", ptid.lwp ());
> -
> -  gdb::unique_xmalloc_ptr<char> data
> -    = target_fileio_read_stralloc (NULL, smaps_file.c_str ());
> -
> -  if (data == nullptr)
> +  file_reader_t<char> smaps_freader
> +    (string_printf ("/proc/%ld/smaps", ptid.lwp ()));  if
> + (!smaps_freader)
>      return false;
> 
>    /* Parse the contents of smaps into a vector.  */
> -  std::vector<struct smaps_data> smaps
> -    = parse_smaps_data (data.get (), smaps_file);
> +  std::vector<struct smaps_data> smaps = parse_smaps_data
> + (smaps_freader);
> 
>    for (const smaps_data &map : smaps)
>      {
> @@ -1746,17 +1748,13 @@ linux_find_memory_regions_full (struct
> gdbarch *gdbarch,
> 
>    if (use_coredump_filter)
>      {
> -      std::string core_dump_filter_name
> -	= string_printf ("/proc/%ld/coredump_filter", ptid.lwp ());
> -
> -      gdb::unique_xmalloc_ptr<char> coredumpfilterdata
> -	= target_fileio_read_stralloc (NULL, core_dump_filter_name.c_str ());
> -
> -      if (coredumpfilterdata != NULL)
> +      file_reader_t<char> coredump_filter_freader
> +	(string_printf ("/proc/%ld/coredump_filter", ptid.lwp ()));
> +      if (coredump_filter_freader)
>  	{
>  	  unsigned int flags;
> 
> -	  sscanf (coredumpfilterdata.get (), "%x", &flags);
> +	  sscanf (coredump_filter_freader.data (), "%x", &flags);
>  	  filterflags = (enum filter_flag) flags;
>  	}
>      }
> @@ -2259,9 +2257,6 @@ linux_corefile_parse_exec_context (struct gdbarch
> *gdbarch, bfd *cbfd)  static bool  linux_fill_prpsinfo (struct
> elf_internal_linux_prpsinfo *p)  {
> -  /* The filename which we will use to obtain some info about the process.
> -     We will basically use this to store the `/proc/PID/FILENAME' file.  */
> -  char filename[100];
>    /* The basename of the executable.  */
>    const char *basename;
>    /* Temporary buffer.  */
> @@ -2285,23 +2280,24 @@ linux_fill_prpsinfo (struct
> elf_internal_linux_prpsinfo *p)
> 
>    /* Obtaining PID and filename.  */
>    pid = inferior_ptid.pid ();
> -  xsnprintf (filename, sizeof (filename), "/proc/%d/cmdline", (int) pid);
> -  /* The full name of the program which generated the corefile.  */
> -  gdb_byte *buf = nullptr;
> -  LONGEST buf_len = target_fileio_read_alloc (nullptr, filename, &buf);
> -  gdb::unique_xmalloc_ptr<char> fname ((char *)buf);
> +  file_reader_t<gdb_byte> cmdline_freader
> +    (string_printf ("/proc/%d/cmdline", pid));  if (!cmdline_freader)
> +    return false;
> 
> -  if (buf_len < 1 || fname.get () == nullptr || fname.get ()[0] == '\0')
> +  /* The full name of the program which generated the corefile.  */
> + gdb::array_view<char> cmdline = cmdline_freader.cast_view<char> ();
> + if (cmdline.size () < 1 || cmdline[0] == '\0')
>      {
>        /* No program name was read, so we won't be able to retrieve more
>  	 information about the process.  */
>        return false;
>      }
> -  if (fname.get ()[buf_len - 1] != '\0')
> +  if (cmdline[cmdline.size () - 1] != '\0')
>      {
>        warning (_("target file %s "
>  		 "does not contain a trailing null character"),
> -	       filename);
> +	       cmdline_freader.c_filepath ());
>        return false;
>      }
> 
> @@ -2311,27 +2307,23 @@ linux_fill_prpsinfo (struct
> elf_internal_linux_prpsinfo *p)
>    p->pr_pid = pid;
> 
>    /* Copying the program name.  Only the basename matters.  */
> -  basename = lbasename (fname.get ());
> +  basename = lbasename (cmdline.data ());
>    strncpy (p->pr_fname, basename, sizeof (p->pr_fname) - 1);
>    p->pr_fname[sizeof (p->pr_fname) - 1] = '\0';
> 
>    const std::string &infargs = current_inferior ()->args ();
> 
>    /* The arguments of the program.  */
> -  std::string psargs = fname.get ();
> +  std::string psargs = cmdline.data ();
>    if (!infargs.empty ())
>      psargs += ' ' + infargs;
> 
>    strncpy (p->pr_psargs, psargs.c_str (), sizeof (p->pr_psargs) - 1);
>    p->pr_psargs[sizeof (p->pr_psargs) - 1] = '\0';
> 
> -  xsnprintf (filename, sizeof (filename), "/proc/%d/stat", (int) pid);
> -  /* The contents of `/proc/PID/stat'.  */
> -  gdb::unique_xmalloc_ptr<char> proc_stat_contents
> -    = target_fileio_read_stralloc (NULL, filename);
> -  char *proc_stat = proc_stat_contents.get ();
> -
> -  if (proc_stat == NULL || *proc_stat == '\0')
> +  file_reader_t<char> stat_freader (string_printf ("/proc/%d/stat",
> + pid));  char *proc_stat = stat_freader.data ();  if (!stat_freader ||
> + *proc_stat == '\0')
>      {
>        /* Despite being unable to read more information about the
>  	 process, we return true here because at least we have its @@ -
> 2403,13 +2395,9 @@ linux_fill_prpsinfo (struct elf_internal_linux_prpsinfo
> *p)
> 
>    /* Finally, obtaining the UID and GID.  For that, we read and parse the
>       contents of the `/proc/PID/status' file.  */
> -  xsnprintf (filename, sizeof (filename), "/proc/%d/status", (int) pid);
> -  /* The contents of `/proc/PID/status'.  */
> -  gdb::unique_xmalloc_ptr<char> proc_status_contents
> -    = target_fileio_read_stralloc (NULL, filename);
> -  char *proc_status = proc_status_contents.get ();
> -
> -  if (proc_status == NULL || *proc_status == '\0')
> +  file_reader_t<char> status_freader (string_printf ("/proc/%d/status",
> + pid));  char *proc_status = status_freader.data ();  if
> + (!status_freader || *proc_status == '\0')
>      {
>        /* Returning true since we already have a bunch of information.  */
>        return true;
> @@ -2802,9 +2790,6 @@ linux_gdb_signal_to_target (struct gdbarch
> *gdbarch,  static bool  linux_vsyscall_range_raw (struct gdbarch *gdbarch,
> struct mem_range *range)  {
> -  char filename[100];
> -  long pid;
> -
>    if (target_auxv_search (AT_SYSINFO_EHDR, &range->start) <= 0)
>      return false;
> 
> @@ -2842,7 +2827,7 @@ linux_vsyscall_range_raw (struct gdbarch
> *gdbarch, struct mem_range *range)
>    if (current_inferior ()->fake_pid_p)
>      return false;
> 
> -  pid = current_inferior ()->pid;
> +  long pid = current_inferior ()->pid;
> 
>    /* Note that reading /proc/PID/task/PID/maps (1) is much faster than
>       reading /proc/PID/maps (2).  The later identifies thread stacks @@ -
> 2852,15 +2837,14 @@ linux_vsyscall_range_raw (struct gdbarch *gdbarch,
> struct mem_range *range)
>       a few thousand threads, (1) takes a few milliseconds, while (2)
>       takes several seconds.  Also note that "smaps", what we read for
>       determining core dump mappings, is even slower than "maps".  */
> -  xsnprintf (filename, sizeof filename, "/proc/%ld/task/%ld/maps", pid, pid);
> -  gdb::unique_xmalloc_ptr<char> data
> -    = target_fileio_read_stralloc (NULL, filename);
> -  if (data != NULL)
> +  file_reader_t<char> task_maps_freader
> +    (string_printf ("/proc/%ld/task/%ld/maps", pid, pid));  if
> + (task_maps_freader)
>      {
>        char *line;
>        char *saveptr = NULL;
> 
> -      for (line = strtok_r (data.get (), "\n", &saveptr);
> +      for (line = strtok_r (task_maps_freader.data (), "\n", &saveptr);
>  	   line != NULL;
>  	   line = strtok_r (NULL, "\n", &saveptr))
>  	{
> @@ -2879,7 +2863,8 @@ linux_vsyscall_range_raw (struct gdbarch
> *gdbarch, struct mem_range *range)
>  	}
>      }
>    else
> -    warning (_("unable to open /proc file '%s'"), filename);
> +    warning (_("unable to open /proc file '%s'"),
> +	     task_maps_freader.c_filepath ());

IIUC, before your change, if the file was empty, we did not show a warning, since
target_fileio_read_stralloc handles the case like this:
"Empty objects are returned as allocated but empty strings."

Based on your file_reader_t implementation, I think we get here in case we can
open the file but the file is empty. Not sure if in that case the file can be empty
at all, but it is a behavioural change that should be avoided in my opinion.
There are further similar cases in this patch. 
Would it make sense to change the file_reader_t bool operator to return true in case the
file is empty? Maybe we could then additionally introduce a new method bool empty ().

>    return false;
>  }
> @@ -3168,16 +3153,11 @@ linux_address_in_shadow_stack_mem_range
> 
>    const int pid = current_inferior ()->pid;
> 
> -  std::string smaps_file = string_printf ("/proc/%d/smaps", pid);
> -
> -  gdb::unique_xmalloc_ptr<char> data
> -    = target_fileio_read_stralloc (nullptr, smaps_file.c_str ());
> -
> -  if (data == nullptr)
> +  file_reader_t<char> smaps_freader (string_printf ("/proc/%d/smaps",
> + pid));  if (!smaps_freader)
>      return false;
> 
> -  const std::vector<smaps_data> smaps
> -    = parse_smaps_data (data.get (), smaps_file);
> +  const std::vector<smaps_data> smaps = parse_smaps_data
> + (smaps_freader);
> 
>    auto find_addr_mem_range = [&addr] (const smaps_data &map)
>      {
> diff --git a/gdb/sparc64-tdep.c b/gdb/sparc64-tdep.c index
> 93db3417a2a..811b76f27d8 100644
> --- a/gdb/sparc64-tdep.c
> +++ b/gdb/sparc64-tdep.c
> @@ -305,14 +305,13 @@ adi_is_addr_mapped (CORE_ADDR vaddr, size_t
> cnt)
>    size_t i = 0;
> 
>    pid_t pid = inferior_ptid.pid ();
> -  snprintf (filename, sizeof filename, "/proc/%ld/adi/maps", (long) pid);
> -  gdb::unique_xmalloc_ptr<char> data
> -    = target_fileio_read_stralloc (NULL, filename);
> -  if (data)
> +  file_reader_t<char> adi_maps_freader
> +    (string_printf ("/proc/%d/adi/maps", pid));  if (adi_maps_freader)
>      {
>        adi_stat_t adi_stat = get_adi_info (pid);
>        char *saveptr;
> -      for (char *line = strtok_r (data.get (), "\n", &saveptr);
> +      for (char *line = strtok_r (adi_maps_freader.data (), "\n",
> + &saveptr);
>  	   line;
>  	   line = strtok_r (NULL, "\n", &saveptr))
>  	{
> @@ -329,7 +328,8 @@ adi_is_addr_mapped (CORE_ADDR vaddr, size_t cnt)
>  	}
>        }
>    else
> -    warning (_("unable to open /proc file '%s'"), filename);
> +    warning (_("unable to open /proc file '%s'"),
> +	     adi_maps_freader.c_filepath ());
> 
>    return false;
>  }
> diff --git a/gdb/target.h b/gdb/target.h index 4215553033c..d6fc101f205
> 100644
> --- a/gdb/target.h
> +++ b/gdb/target.h
> @@ -2338,6 +2338,71 @@ extern LONGEST target_fileio_read_alloc (struct
> inferior *inf,  extern gdb::unique_xmalloc_ptr<char>
> target_fileio_read_stralloc
>      (struct inferior *inf, const char *filename, size_t *len = nullptr);
> 
> +/* Helper class for reading a file.  */ template <typename T> class
> +file_reader_t {
> +  /* The filepath of the file being read.  */
> +  std::string m_filepath;
> +  /* Smart pointer to the data.  */
> +  gdb::unique_xmalloc_ptr<T> m_data;
> +  /* Size of the data.  */
> +  size_t m_size;
> +
> +public:
> +  file_reader_t (const std::string &filepath)
> +    : m_filepath (filepath)
> +    , m_size (0)
> +  {
> +    if constexpr (std::is_same_v<T, char>)
> +      m_data = target_fileio_read_stralloc (nullptr, m_filepath.c_str (),
> +					    &m_size);
> +    else
> +      {
> +	gdb_byte *buf = nullptr;
> +	m_size = target_fileio_read_alloc (nullptr, m_filepath.c_str (), &buf);
> +	m_data = gdb::unique_xmalloc_ptr<T> (reinterpret_cast<T *>(buf));
> +      }
> +  }
> +
> +  /* Return true if the file was read successfully.  */  operator bool
> + () const noexcept  { return m_data != nullptr && m_size > 0; }

I think we should make this explicit.

> +
> +  /* Return a pointer to the data.  */
> +  T *data () const noexcept
> +  { return m_data.get (); }
> +
> +  /* Return the size of the data.  */
> +  size_t size () const noexcept
> +  {
> +    /* For char buffers, size() corresponds to the size of the read data. Some
> +       null-terminator characters are possibly scattered throughout the data.
> +       Consequently, strlen() might not reflect the actual size.  */
> +    return m_size;
> +  }
> +
> +  /* Return a span of the data.  */
> +  gdb::array_view<T> view () const noexcept  { return
> + gdb::array_view<T> (m_data.get (), size ()); }
> +
> +  /* Return a span of the data, cast to a different type.  */
> +  template <typename U>
> +  gdb::array_view<U> cast_view () const noexcept
> +  {
> +    return gdb::array_view<U> (reinterpret_cast<U *> (m_data.get ()),
> +			       size () * sizeof (T) / sizeof (U));
> +  }
> +
> +  /* Return the filepath of the file that was read.  */  const
> + std::string &filepath () const noexcept  { return m_filepath; }
> +
> +  /* Return the filepath of the file that was read as a C string.  */
> +  const char *c_filepath () const noexcept
> +  { return m_filepath.c_str (); }
> +};
> +
>  /* Invalidate the target associated with open handles that were open
>     on target TARG, since we're about to close (and maybe destroy) the
>     target.  The handles remain open from the client's perspective, but
> --
> 2.55.0
> 

Regards,
Christina

Intel Deutschland GmbH

Registered Address: Dornacher Strasse 1, 85622 Feldkirchen, Germany
Tel: +49 89 991 430, www.intel.de
Managing Directors: Harry Demas, Jeffrey Schneiderman, Yin Chong Sorrell
Chairperson of the Supervisory Board: Nicole Lau
Registered Seat: Munich
Commercial Register: Amtsgericht Muenchen HRB 186928