[PATCH v3 6/8] gdb: introduce helper class target_file_reader

[Matthieu Longo <matthieu.longo@arm.com>]

Wrap all the boilerplate code required to read a file in a new helper
class: target_file_reader. 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, removes 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 target_file_reader. As a side effect,
amd64_linux_lam_untag_mask and linux_process_address_in_memtag_page
may now return earlier in case the file is empty.

Reviewed-By: Thiago Jung Bauermann <thiago.bauermann@linaro.org>
Reviewed-By: Christina Joos <christina.joos@intel.com>
---
 gdb/amd64-linux-tdep.c |  12 ++--
 gdb/linux-tdep.c       | 121 ++++++++++++++++++-----------------------
 gdb/sparc64-tdep.c     |  17 +++---
 gdb/target.h           | 116 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 183 insertions(+), 83 deletions(-)

diff --git a/gdb/amd64-linux-tdep.c b/gdb/amd64-linux-tdep.c
index 9b23db72bbe..f8d48084403 100644
--- a/gdb/amd64-linux-tdep.c
+++ b/gdb/amd64-linux-tdep.c
@@ -1848,14 +1848,12 @@ 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)
+  target_file_reader<char> proc_status
+    (string_printf ("/proc/%d/status", inf->pid));
+  if (proc_status.empty_or_error ())
     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)
@@ -1867,7 +1865,7 @@ 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_path ()));
 
       return result;
     }
diff --git a/gdb/linux-tdep.c b/gdb/linux-tdep.c
index 772b561eb96..0582e5eee64 100644
--- a/gdb/linux-tdep.c
+++ b/gdb/linux-tdep.c
@@ -1737,6 +1737,12 @@ parse_smaps_data (gdb::array_view<char> data,
   return smaps;
 }
 
+static std::vector<smaps_data>
+parse_smaps_data (const target_file_reader<char> &freader)
+{
+  return parse_smaps_data (freader.view (), freader.path ());
+}
+
 /* Helper that checks if an address is in a memory tag page for a live
    process.  */
 
@@ -1747,19 +1753,14 @@ linux_process_address_in_memtag_page (CORE_ADDR address)
     return false;
 
   ptid_t ptid = get_ptid_for_slash_proc ();
-  std::string smaps_file = string_printf ("/proc/%ld/smaps", ptid.lwp ());
-
-  LONGEST len = 0;
-  gdb::unique_xmalloc_ptr<char> data
-    = target_fileio_read_stralloc (NULL, smaps_file.c_str (), &len);
 
-  if (data == nullptr)
+  target_file_reader<char> smaps_freader
+    (string_printf ("/proc/%ld/smaps", ptid.lwp ()));
+  if (smaps_freader.empty_or_error ())
     return false;
 
   /* Parse the contents of smaps into a vector.  */
-  gdb::array_view<char> content (data.get (), len);
-  std::vector<smaps_data> smaps
-    = parse_smaps_data (content, smaps_file);
+  std::vector<smaps_data> smaps = parse_smaps_data (smaps_freader);
 
   for (const smaps_data &map : smaps)
     {
@@ -1823,17 +1824,13 @@ 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)
+      target_file_reader<char> coredump_filter_freader
+	(string_printf ("/proc/%ld/coredump_filter", ptid.lwp ()));
+      if (!coredump_filter_freader.empty_or_error ())
 	{
 	  unsigned int flags;
 
-	  sscanf (coredumpfilterdata.get (), "%x", &flags);
+	  sscanf (coredump_filter_freader.data (), "%x", &flags);
 	  filterflags = (enum filter_flag) flags;
 	}
     }
@@ -1859,7 +1856,7 @@ linux_find_memory_regions_full (struct gdbarch *gdbarch,
   std::vector<smaps_data> smaps
     = parse_smaps_data (content, maps_filename);
 
-  for (const smaps_data &map : smaps)
+  for (const smaps_data &map: smaps)
     {
       /* Invoke the callback function to create the corefile segment.  */
       if (should_dump_mapping_p (filterflags, map))
@@ -2338,9 +2335,6 @@ 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.  */
@@ -2371,25 +2365,28 @@ linux_fill_prpsinfo (struct elf_internal_linux_prpsinfo *p)
   const int leader_id = current_inferior ()->pid;
   const ptid_t live_ptid = get_ptid_for_slash_proc ();
 
-  /* Obtaining PID and filename.  */
-  xsnprintf (filename, sizeof (filename), "/proc/%ld/cmdline",
-	     live_ptid.lwp ());
   /* 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);
+  target_file_reader<gdb_byte> cmdline_freader
+    (string_printf ("/proc/%ld/cmdline", live_ptid.lwp ()));
+  if (cmdline_freader.empty_or_error ())
+    return false;
 
-  if (buf_len < 1 || fname.get () == nullptr || fname.get ()[0] == '\0')
+  /* /proc/<pid>/cmdline stores the command-line arguments as a sequence of
+     NUL-separated strings.  */
+  gdb::array_view<char> cmdline = cmdline_freader.cast_view<char> ();
+  /* The buffer points to the full name of the program which generated the
+     corefile.  */
+  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);
+      warning (_("target file %ps does not contain a trailing null character"),
+	       styled_string (file_name_style.style (),
+			      cmdline_freader.c_path ()));
       return false;
     }
 
@@ -2399,27 +2396,26 @@ linux_fill_prpsinfo (struct elf_internal_linux_prpsinfo *p)
   p->pr_pid = leader_id;
 
   /* 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", leader_id);
   /* 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')
+  const char *proc_stat = nullptr;
+  target_file_reader<char> stat_freader
+    (string_printf ("/proc/%d/stat", leader_id));
+  if (stat_freader.empty_or_error ()
+      || *(proc_stat = stat_freader.data ()) == '\0')
     {
       /* Despite being unable to read more information about the
 	 process, we return true here because at least we have its
@@ -2491,13 +2487,11 @@ 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", leader_id);
-  /* 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')
+  char *proc_status = nullptr;
+  target_file_reader<char> status_freader
+    (string_printf ("/proc/%d/status", leader_id));
+  if (status_freader.empty_or_error ()
+      || *(proc_status = status_freader.data ()) == '\0')
     {
       /* Returning true since we already have a bunch of information.  */
       return true;
@@ -2890,9 +2884,6 @@ 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;
 
@@ -2930,7 +2921,7 @@ 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
@@ -2940,15 +2931,14 @@ 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)
+  target_file_reader<char> task_maps_freader
+    (string_printf ("/proc/%ld/task/%ld/maps", pid, pid));
+  if (!task_maps_freader.empty_or_error ())
     {
       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))
 	{
@@ -2966,9 +2956,10 @@ linux_vsyscall_range_raw (struct gdbarch *gdbarch, struct mem_range *range)
 	    }
 	}
     }
-  else
+  else if (task_maps_freader.error ())
     warning (_("unable to open /proc file '%ps'"),
-	     styled_string (file_name_style.style (), filename));
+	     styled_string (file_name_style.style (),
+			    task_maps_freader.c_path ()));
 
   return false;
 }
@@ -3298,18 +3289,12 @@ linux_address_in_shadow_stack_mem_range
     return false;
 
   ptid_t ptid = get_ptid_for_slash_proc ();
-  std::string smaps_file = string_printf ("/proc/%ld/smaps", ptid.lwp ());
-
-  LONGEST len = 0;
-  gdb::unique_xmalloc_ptr<char> data
-    = target_fileio_read_stralloc (nullptr, smaps_file.c_str (), &len);
-
-  if (data == nullptr)
+  target_file_reader<char> smaps_freader
+    (string_printf ("/proc/%ld/smaps", ptid.lwp ()));
+  if (smaps_freader.empty_or_error ())
     return false;
 
-  gdb::array_view<char> content (data.get (), len);
-  const std::vector<smaps_data> smaps
-    = parse_smaps_data (content, 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..5ed45809949 100644
--- a/gdb/sparc64-tdep.c
+++ b/gdb/sparc64-tdep.c
@@ -68,6 +68,7 @@
 #include <algorithm>
 #include "cli/cli-utils.h"
 #include "cli/cli-cmds.h"
+#include "cli/cli-style.h"
 #include "auxv.h"
 
 #define MAX_PROC_NAME_SIZE sizeof("/proc/99999/lwp/9999/adi/lstatus")
@@ -301,18 +302,16 @@ adi_tag_fd ()
 static bool
 adi_is_addr_mapped (CORE_ADDR vaddr, size_t cnt)
 {
-  char filename[MAX_PROC_NAME_SIZE];
   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)
+  target_file_reader<char> adi_maps_freader
+    (string_printf ("/proc/%d/adi/maps", pid));
+  if (!adi_maps_freader.empty_or_error ())
     {
       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))
 	{
@@ -328,8 +327,10 @@ adi_is_addr_mapped (CORE_ADDR vaddr, size_t cnt)
 	    }
 	}
       }
-  else
-    warning (_("unable to open /proc file '%s'"), filename);
+  else if (adi_maps_freader.error ())
+    warning (_("unable to open /proc file '%ps'"),
+	     styled_string (file_name_style.style (),
+			    adi_maps_freader.c_path ()));
 
   return false;
 }
diff --git a/gdb/target.h b/gdb/target.h
index 38bdc68f6a3..923e5c400b7 100644
--- a/gdb/target.h
+++ b/gdb/target.h
@@ -2341,6 +2341,122 @@ 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, LONGEST *len = nullptr);
 
+/* Helper class for reading the content of a file on the target.  */
+template <typename T>
+class target_file_reader
+{
+  /* The path of the file being read.  */
+  std::string m_path;
+
+  /* Smart pointer to the data.  */
+  gdb::unique_xmalloc_ptr<T> m_data;
+
+  /* Number of bytes read.  */
+  LONGEST m_size;
+
+public:
+  /* Read the content of the file associated to PATH from the filesystem as
+     seen by INF.  If INF is NULL, use the filesystem seen by the debugger
+     (GDB or, for remote targets, the remote stub).  */
+  target_file_reader (const std::string &path, struct inferior *inf = nullptr)
+    : m_path (path)
+    , m_size (0)
+  {
+    /* The interface of target_fileio_read_stralloc and target_fileio_read_alloc
+       may appear inconsistent, but the difference is intentional.
+
+       On error, both functions return nullptr and set the size to a negative
+       value.  For a successful read of an empty file, however, the size is zero
+       and their return values differ:
+	 - target_fileio_read_stralloc returns an allocated empty string rather
+	   than nullptr.  The allocation contains the terminating '\0'.
+	 - target_fileio_read_alloc simply returns nullptr.
+
+       Hence, an assert in .data(), .view () and .cast_view () enforcing no
+       error but a valid buffer address.
+	 gdb_assert (!error () && m_data != nullptr);  */
+    if constexpr (std::is_same_v<T, char>)
+      m_data = target_fileio_read_stralloc (inf, m_path.c_str (), &m_size);
+    else
+      {
+	gdb_byte *buf = nullptr;
+	m_size = target_fileio_read_alloc (inf, m_path.c_str (), &buf);
+	m_data = gdb::unique_xmalloc_ptr<T> (reinterpret_cast<T *>(buf));
+      }
+  }
+
+  target_file_reader (target_file_reader &&) = default;
+  target_file_reader &operator= (target_file_reader &&) = default;
+
+  DISABLE_COPY_AND_ASSIGN (target_file_reader);
+
+  /* Return true if the file was read successfully but contained no data.  */
+  bool empty () const noexcept
+  { return m_size == 0; }
+
+  /* Return true if the file could not be read.  */
+  bool error () const noexcept
+  { return m_size < 0; }
+
+  /* Return true if an error occurred or the file was read successfully
+     but is empty.  */
+  bool empty_or_error () const noexcept
+  { return empty () || error (); }
+
+  /* Return a pointer to the data.  */
+  T *data () const noexcept
+  {
+    gdb_assert (!error () && m_data != nullptr);
+    return m_data.get ();
+  }
+
+  /* Return the number of bytes read.  */
+  LONGEST size () const noexcept
+  {
+    gdb_assert (!error ());
+    /* 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 view of the data.  */
+  gdb::array_view<T> view () const noexcept
+  {
+    gdb_assert (!error () && m_data != nullptr);
+    return gdb::array_view<T> (m_data.get (), size ());
+  }
+
+  /* Return a view of the data, reinterpreted as objects of type U.
+     The size of the underlying storage must be an exact multiple of sizeof (U),
+     and the storage must be suitably aligned for U.  */
+  template <typename U>
+  gdb::array_view<U> cast_view () const noexcept
+  {
+    gdb_assert (!error () && m_data != nullptr);
+
+    size_t nbytes = size () * sizeof (T);
+
+    /* The number of bytes must be a multiple of sizeof(U).
+       Do not silently discard trailing bytes.  */
+    gdb_assert (nbytes % sizeof (U) == 0);
+
+    /* The underlying storage must satisfy U's alignment requirement.  */
+    gdb_assert (reinterpret_cast<uintptr_t> (m_data.get ()) % alignof (U) == 0);
+
+    return gdb::array_view<U> (reinterpret_cast<U *> (m_data.get ()),
+			       nbytes / sizeof (U));
+  }
+
+  /* Return the path of the file that was read.  */
+  const std::string &path () const noexcept
+  { return m_path; }
+
+  /* Return the path of the file that was read as a C string.  */
+  const char *c_path () const noexcept
+  { return m_path.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