Use NT_FILE note section for reading core target memory

In his reviews of my v1 and v2 corefile related patches, Pedro
identified two cases which weren't handled by those patches.

In https://sourceware.org/pipermail/gdb-patches/2020-May/168826.html,
Pedro showed that debugging a core file in which mmap() is used to
create a new mapping over an existing file-backed mapping will
produce incorrect results.  I.e, for his example, GDB would
show:

(gdb) disassemble main
Dump of assembler code for function main:
   0x00000000004004e6 <+0>:	push   %rbp
   0x00000000004004e7 <+1>:	mov    %rsp,%rbp
=> 0x00000000004004ea <+4>:	callq  0x4003f0 <abort@plt>
End of assembler dump.

This sort of looks like it might be correct, but is not due to the
fact that mmap(...MAP_FIXED...) was used to create a mapping (of all
zeros) on top of the .text section.  So, the correct result should be:

(gdb) disassemble main
Dump of assembler code for function main:
   0x00000000004004e6 <+0>:	add    %al,(%rax)
   0x00000000004004e8 <+2>:	add    %al,(%rax)
=> 0x00000000004004ea <+4>:	add    %al,(%rax)
   0x00000000004004ec <+6>:	add    %al,(%rax)
   0x00000000004004ee <+8>:	add    %al,(%rax)
End of assembler dump.

The other case that Pedro found involved an attempted examination of a
particular section in the test case from gdb.base/corefile.exp.  On
Fedora 27 or 28, the following behavior may be observed:

(gdb) info proc mappings
Mapped address spaces:

          Start Addr           End Addr       Size     Offset objfile
...
      0x7ffff7839000     0x7ffff7a38000   0x1ff000   0x1b5000 /usr/lib64/libc-2.27.so
...
(gdb) x/4x 0x7ffff7839000
0x7ffff7839000:	Cannot access memory at address 0x7ffff7839000

FYI, this section appears to be unrelocated vtable data.  See
https://sourceware.org/pipermail/gdb-patches/2020-May/168331.html for
a detailed analysis.

The important thing here is that GDB should be able to access this
address since it should be backed by the shared library.  I.e. it
should do this:

(gdb) x/4x 0x7ffff7839000
0x7ffff7839000:	0x0007ddf0	0x00000000	0x0007dba0	0x00000000

Both of these cases are fixed with this commit.

In a nutshell, this commit opens a "binary" target BFD for each of the
files that are mentioned in an NT_FILE / .note.linuxcore.file note
section.  It then uses these mappings instead of the file stratum
mappings that GDB has used in the past.

If this note section doesn't exist or is mangled for some reason, then
GDB will use the file stratum as before.  Should this happen, then
we can expect both of the above problems to again be present.

See the code comments in the commit for other details.

gdb/ChangeLog:

	* corelow.c (solist.h, unordered_map): Include.
	(class core_target): Add field m_core_file_mappings and
	method build_file_mappings.
	(core_target::core_target): Call build_file_mappings.
	(core_target::~core_target): Free memory associated with
	m_core_file_mappings.
	(core_target::build_file_mappings): New method.
	(core_target::xfer_partial): Use m_core_file_mappings
	for memory transfers.
	* linux-tdep.c (linux_read_core_file_mappings): New
	function.
	(linux_core_info_proc_mappings): Rewrite to use
	linux_read_core_file_mappings.
	(linux_init_abi): Register linux_read_core_file_mappings.

1 files changed, 136 insertions, 67 deletions

diff --git a/gdb/linux-tdep.c b/gdb/linux-tdep.c
index fd4337f..2ca9f59 100644
--- a/gdb/linux-tdep.c
+++ b/gdb/linux-tdep.c
@@ -1018,106 +1018,174 @@ linux_info_proc (struct gdbarch *gdbarch, const char *args,
     }
 }
 
-/* Implement "info proc mappings" for a corefile.  */
+/* Implementation of `gdbarch_read_core_file_mappings', as defined in
+   gdbarch.h.
+   
+   This function reads the NT_FILE note (which BFD turns into the
+   section ".note.linuxcore.file").  The format of this note / section
+   is described as follows in the Linux kernel sources in
+   fs/binfmt_elf.c:
+   
+      long count     -- how many files are mapped
+      long page_size -- units for file_ofs
+      array of [COUNT] elements of
+	long start
+	long end
+	long file_ofs
+      followed by COUNT filenames in ASCII: "FILE1" NUL "FILE2" NUL...
+      
+   CBFD is the BFD of the core file.
+
+   PRE_LOOP_CB is the callback function to invoke prior to starting
+   the loop which processes individual entries.  This callback will
+   only be executed after the note has been examined in enough
+   detail to verify that it's not malformed in some way.
+   
+   LOOP_CB is the callback function that will be executed once
+   for each mapping.  */
 
 static void
-linux_core_info_proc_mappings (struct gdbarch *gdbarch, const char *args)
+linux_read_core_file_mappings (struct gdbarch *gdbarch,
+			       struct bfd *cbfd,
+			       gdb::function_view<void (ULONGEST count)>
+			         pre_loop_cb,
+			       gdb::function_view<void (int num,
+			                                ULONGEST start,
+							ULONGEST end,
+							ULONGEST file_ofs,
+							const char *filename,
+							const void *other)>
+				 loop_cb)
 {
-  asection *section;
-  ULONGEST count, page_size;
-  unsigned char *descdata, *filenames, *descend;
-  size_t note_size;
-  unsigned int addr_size_bits, addr_size;
-  struct gdbarch *core_gdbarch = gdbarch_from_bfd (core_bfd);
-  /* We assume this for reading 64-bit core files.  */
+  /* Ensure that ULONGEST is big enough for reading 64-bit core files.  */
   gdb_static_assert (sizeof (ULONGEST) >= 8);
 
-  section = bfd_get_section_by_name (core_bfd, ".note.linuxcore.file");
-  if (section == NULL)
-    {
-      warning (_("unable to find mappings in core file"));
-      return;
-    }
+  /* It's not required that the NT_FILE note exists, so return silently
+     if it's not found.  Beyond this point though, we'll complain
+     if problems are found.  */
+  asection *section = bfd_get_section_by_name (cbfd, ".note.linuxcore.file");
+  if (section == nullptr)
+    return;
 
-  addr_size_bits = gdbarch_addr_bit (core_gdbarch);
-  addr_size = addr_size_bits / 8;
-  note_size = bfd_section_size (section);
+  unsigned int addr_size_bits = gdbarch_addr_bit (gdbarch);
+  unsigned int addr_size = addr_size_bits / 8;
+  size_t note_size = bfd_section_size (section);
 
   if (note_size < 2 * addr_size)
-    error (_("malformed core note - too short for header"));
+    {
+      warning (_("malformed core note - too short for header"));
+      return;
+    }
 
-  gdb::def_vector<unsigned char> contents (note_size);
+  gdb::def_vector<gdb_byte> contents (note_size);
   if (!bfd_get_section_contents (core_bfd, section, contents.data (),
 				 0, note_size))
-    error (_("could not get core note contents"));
+    {
+      warning (_("could not get core note contents"));
+      return;
+    }
 
-  descdata = contents.data ();
-  descend = descdata + note_size;
+  gdb_byte *descdata = contents.data ();
+  char *descend = (char *) descdata + note_size;
 
   if (descdata[note_size - 1] != '\0')
-    error (_("malformed note - does not end with \\0"));
+    {
+      warning (_("malformed note - does not end with \\0"));
+      return;
+    }
 
-  count = bfd_get (addr_size_bits, core_bfd, descdata);
+  ULONGEST count = bfd_get (addr_size_bits, core_bfd, descdata);
   descdata += addr_size;
 
-  page_size = bfd_get (addr_size_bits, core_bfd, descdata);
+  ULONGEST page_size = bfd_get (addr_size_bits, core_bfd, descdata);
   descdata += addr_size;
 
   if (note_size < 2 * addr_size + count * 3 * addr_size)
-    error (_("malformed note - too short for supplied file count"));
-
-  printf_filtered (_("Mapped address spaces:\n\n"));
-  if (gdbarch_addr_bit (gdbarch) == 32)
-    {
-      printf_filtered ("\t%10s %10s %10s %10s %s\n",
-		       "Start Addr",
-		       "  End Addr",
-		       "      Size", "    Offset", "objfile");
-    }
-  else
     {
-      printf_filtered ("  %18s %18s %10s %10s %s\n",
-		       "Start Addr",
-		       "  End Addr",
-		       "      Size", "    Offset", "objfile");
+      warning (_("malformed note - too short for supplied file count"));
+      return;
     }
 
-  filenames = descdata + count * 3 * addr_size;
-  while (--count > 0)
+  char *filenames = (char *) descdata + count * 3 * addr_size;
+
+  /* Make sure that the correct number of filenames exist.  Complain
+     if there aren't enough or are too many.  */
+  char *f = filenames;
+  for (int i = 0; i < count; i++)
     {
-      ULONGEST start, end, file_ofs;
+      if (f >= descend)
+        {
+	  warning (_("malformed note - filename area is too small"));
+	  return;
+	}
+      f += strnlen (f, descend - f) + 1;
+    }
+  /* Complain, but don't return early if the filename area is too big.  */
+  if (f != descend)
+    warning (_("malformed note - filename area is too big"));
 
-      if (filenames == descend)
-	error (_("malformed note - filenames end too early"));
+  pre_loop_cb (count);
 
-      start = bfd_get (addr_size_bits, core_bfd, descdata);
+  for (int i = 0; i < count; i++)
+    {
+      ULONGEST start = bfd_get (addr_size_bits, core_bfd, descdata);
       descdata += addr_size;
-      end = bfd_get (addr_size_bits, core_bfd, descdata);
+      ULONGEST end = bfd_get (addr_size_bits, core_bfd, descdata);
       descdata += addr_size;
-      file_ofs = bfd_get (addr_size_bits, core_bfd, descdata);
+      ULONGEST file_ofs
+        = bfd_get (addr_size_bits, core_bfd, descdata) * page_size;
       descdata += addr_size;
+      char * filename = filenames;
+      filenames += strlen ((char *) filenames) + 1;
 
-      file_ofs *= page_size;
-
-      if (gdbarch_addr_bit (gdbarch) == 32)
-	printf_filtered ("\t%10s %10s %10s %10s %s\n",
-			 paddress (gdbarch, start),
-			 paddress (gdbarch, end),
-			 hex_string (end - start),
-			 hex_string (file_ofs),
-			 filenames);
-      else
-	printf_filtered ("  %18s %18s %10s %10s %s\n",
-			 paddress (gdbarch, start),
-			 paddress (gdbarch, end),
-			 hex_string (end - start),
-			 hex_string (file_ofs),
-			 filenames);
-
-      filenames += 1 + strlen ((char *) filenames);
+      loop_cb (i, start, end, file_ofs, filename, nullptr);
     }
 }
 
+/* Implement "info proc mappings" for a corefile.  */
+
+static void
+linux_core_info_proc_mappings (struct gdbarch *gdbarch, const char *args)
+{
+  linux_read_core_file_mappings (gdbarch, core_bfd,
+    [=] (ULONGEST count)
+      {
+	printf_filtered (_("Mapped address spaces:\n\n"));
+	if (gdbarch_addr_bit (gdbarch) == 32)
+	  {
+	    printf_filtered ("\t%10s %10s %10s %10s %s\n",
+			     "Start Addr",
+			     "  End Addr",
+			     "      Size", "    Offset", "objfile");
+	  }
+	else
+	  {
+	    printf_filtered ("  %18s %18s %10s %10s %s\n",
+			     "Start Addr",
+			     "  End Addr",
+			     "      Size", "    Offset", "objfile");
+	  }
+      },
+    [=] (int num, ULONGEST start, ULONGEST end, ULONGEST file_ofs,
+         const char *filename, const void *other)
+      {
+	if (gdbarch_addr_bit (gdbarch) == 32)
+	  printf_filtered ("\t%10s %10s %10s %10s %s\n",
+			   paddress (gdbarch, start),
+			   paddress (gdbarch, end),
+			   hex_string (end - start),
+			   hex_string (file_ofs),
+			   filename);
+	else
+	  printf_filtered ("  %18s %18s %10s %10s %s\n",
+			   paddress (gdbarch, start),
+			   paddress (gdbarch, end),
+			   hex_string (end - start),
+			   hex_string (file_ofs),
+			   filename);
+      });
+}
+
 /* Implement "info proc" for a corefile.  */
 
 static void
@@ -2472,6 +2540,7 @@ linux_init_abi (struct gdbarch_info info, struct gdbarch *gdbarch)
   set_gdbarch_info_proc (gdbarch, linux_info_proc);
   set_gdbarch_core_info_proc (gdbarch, linux_core_info_proc);
   set_gdbarch_core_xfer_siginfo (gdbarch, linux_core_xfer_siginfo);
+  set_gdbarch_read_core_file_mappings (gdbarch, linux_read_core_file_mappings);
   set_gdbarch_find_memory_regions (gdbarch, linux_find_memory_regions);
   set_gdbarch_make_corefile_notes (gdbarch, linux_make_corefile_notes);
   set_gdbarch_has_shared_address_space (gdbarch,