[binutils-gdb] gdb: add extension language print_insn hook

[binutils-gdb] gdb: add extension language print_insn hook

[Andrew Burgess]

https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=e4ae302562aba1bd166919d76341fb631e2d470a

commit e4ae302562aba1bd166919d76341fb631e2d470a
Author: Andrew Burgess <andrew.burgess@embecosm.com>
Date:   Fri Sep 17 18:11:40 2021 +0100

    gdb: add extension language print_insn hook
    
    This commit is setup for the next commit.
    
    In the next commit I will add a Python API to intercept the print_insn
    calls within GDB, each print_insn call is responsible for
    disassembling, and printing one instruction.  After the next commit it
    will be possible for a user to write Python code that either wraps
    around the existing disassembler, or even, in extreme situations,
    entirely replaces the existing disassembler.
    
    This commit does not add any new Python API.
    
    What this commit does is put the extension language framework in place
    for a print_insn hook.  There's a new callback added to 'struct
    extension_language_ops', which is then filled in with nullptr for Python
    and Guile.
    
    Finally, in the disassembler, the code is restructured so that the new
    extension language function ext_lang_print_insn is called before we
    delegate to gdbarch_print_insn.
    
    After this, the next commit can focus entirely on providing a Python
    implementation of the new print_insn callback.
    
    There should be no user visible change after this commit.

Diff:
---
 gdb/disasm.c         | 29 ++++++++++++++++++++++++++---
 gdb/extension-priv.h | 15 +++++++++++++++
 gdb/extension.c      | 20 ++++++++++++++++++++
 gdb/extension.h      | 10 ++++++++++
 gdb/guile/guile.c    |  6 +++++-
 gdb/python/python.c  |  2 ++
 6 files changed, 78 insertions(+), 4 deletions(-)

diff --git a/gdb/disasm.c b/gdb/disasm.c
index 6ac84388cc3..4af40c916b2 100644
--- a/gdb/disasm.c
+++ b/gdb/disasm.c
@@ -851,6 +851,29 @@ gdb_disassemble_info::~gdb_disassemble_info ()
   disassemble_free_target (&m_di);
 }
 
+/* Wrapper around calling gdbarch_print_insn.  This function takes care of
+   first calling the extension language hooks for print_insn, and, if none
+   of the extension languages can print this instruction, calls
+   gdbarch_print_insn to do the work.
+
+   GDBARCH is the architecture to disassemble in, VMA is the address of the
+   instruction being disassembled, and INFO is the libopcodes disassembler
+   related information.  */
+
+static int
+gdb_print_insn_1 (struct gdbarch *gdbarch, CORE_ADDR vma,
+		  struct disassemble_info *info)
+{
+  /* Call into the extension languages to do the disassembly.  */
+  gdb::optional<int> length = ext_lang_print_insn (gdbarch, vma, info);
+  if (length.has_value ())
+    return *length;
+
+  /* No extension language wanted to do the disassembly, so do it
+     manually.  */
+  return gdbarch_print_insn (gdbarch, vma, info);
+}
+
 /* See disasm.h.  */
 
 bool gdb_disassembler::use_ext_lang_colorization_p = true;
@@ -864,7 +887,7 @@ gdb_disassembler::print_insn (CORE_ADDR memaddr,
   m_err_memaddr.reset ();
   m_buffer.clear ();
 
-  int length = gdbarch_print_insn (arch (), memaddr, &m_di);
+  int length = gdb_print_insn_1 (arch (), memaddr, &m_di);
 
   /* If we have successfully disassembled an instruction, styling is on, we
      think that the extension language might be able to perform styling for
@@ -899,7 +922,7 @@ gdb_disassembler::print_insn (CORE_ADDR memaddr,
 	  gdb_assert (!m_buffer.term_out ());
 	  m_buffer.~string_file ();
 	  new (&m_buffer) string_file (true);
-	  length = gdbarch_print_insn (arch (), memaddr, &m_di);
+	  length = gdb_print_insn_1 (arch (), memaddr, &m_di);
 	  gdb_assert (length > 0);
 	}
     }
@@ -1054,7 +1077,7 @@ gdb_buffered_insn_length (struct gdbarch *gdbarch,
   gdb_buffered_insn_length_init_dis (gdbarch, &di, insn, max_len, addr,
 				     &disassembler_options_holder);
 
-  int result = gdbarch_print_insn (gdbarch, addr, &di);
+  int result = gdb_print_insn_1 (gdbarch, addr, &di);
   disassemble_free_target (&di);
   return result;
 }
diff --git a/gdb/extension-priv.h b/gdb/extension-priv.h
index d9450b51231..7c74e721c57 100644
--- a/gdb/extension-priv.h
+++ b/gdb/extension-priv.h
@@ -263,6 +263,21 @@ struct extension_language_ops
      contents, or an empty optional.  */
   gdb::optional<std::string> (*colorize_disasm) (const std::string &content,
 						 gdbarch *gdbarch);
+
+  /* Print a single instruction from ADDRESS in architecture GDBARCH.  INFO
+     is the standard libopcodes disassembler_info structure.  Bytes for the
+     instruction being printed should be read using INFO->read_memory_func
+     as the actual instruction bytes might be in a buffer.
+
+     Use INFO->fprintf_func to print the results of the disassembly, and
+     return the length of the instruction.
+
+     If no instruction can be disassembled then return an empty value and
+     other extension languages will get a chance to perform the
+     disassembly.  */
+  gdb::optional<int> (*print_insn) (struct gdbarch *gdbarch,
+				    CORE_ADDR address,
+				    struct disassemble_info *info);
 };
 
 /* State necessary to restore a signal handler to its previous value.  */
diff --git a/gdb/extension.c b/gdb/extension.c
index 8f39b86e952..5a805bea00e 100644
--- a/gdb/extension.c
+++ b/gdb/extension.c
@@ -924,6 +924,26 @@ ext_lang_colorize_disasm (const std::string &content, gdbarch *gdbarch)
   return result;
 }
 
+/* See extension.h.  */
+
+gdb::optional<int>
+ext_lang_print_insn (struct gdbarch *gdbarch, CORE_ADDR address,
+		     struct disassemble_info *info)
+{
+  for (const struct extension_language_defn *extlang : extension_languages)
+    {
+      if (extlang->ops == nullptr
+	  || extlang->ops->print_insn == nullptr)
+	continue;
+      gdb::optional<int> length
+	= extlang->ops->print_insn (gdbarch, address, info);
+      if (length.has_value ())
+	return length;
+    }
+
+  return {};
+}
+
 /* Called via an observer before gdb prints its prompt.
    Iterate over the extension languages giving them a chance to
    change the prompt.  The first one to change the prompt wins,
diff --git a/gdb/extension.h b/gdb/extension.h
index 7eb89530c44..47839ea50be 100644
--- a/gdb/extension.h
+++ b/gdb/extension.h
@@ -327,6 +327,16 @@ extern gdb::optional<std::string> ext_lang_colorize
 extern gdb::optional<std::string> ext_lang_colorize_disasm
   (const std::string &content, gdbarch *gdbarch);
 
+/* Calls extension_language_ops::print_insn for each extension language,
+   returning the result from the first extension language that returns a
+   non-empty result (any further extension languages are not then called).
+
+   All arguments are forwarded to extension_language_ops::print_insn, see
+   that function for a full description.  */
+
+extern gdb::optional<int> ext_lang_print_insn
+  (struct gdbarch *gdbarch, CORE_ADDR address, struct disassemble_info *info);
+
 #if GDB_SELF_TEST
 namespace selftests {
 extern void (*hook_set_active_ext_lang) ();
diff --git a/gdb/guile/guile.c b/gdb/guile/guile.c
index c7be48fb739..14b191ded62 100644
--- a/gdb/guile/guile.c
+++ b/gdb/guile/guile.c
@@ -130,8 +130,12 @@ static const struct extension_language_ops guile_extension_ops =
   gdbscm_breakpoint_has_cond,
   gdbscm_breakpoint_cond_says_stop,
 
-  NULL, /* gdbscm_check_quit_flag, */
   NULL, /* gdbscm_set_quit_flag, */
+  NULL, /* gdbscm_check_quit_flag, */
+  NULL, /* gdbscm_before_prompt, */
+  NULL, /* gdbscm_get_matching_xmethod_workers */
+  NULL, /* gdbscm_colorize */
+  NULL, /* gdbscm_print_insn */
 };
 #endif
 
diff --git a/gdb/python/python.c b/gdb/python/python.c
index 9bef2252e88..97de5f5cee5 100644
--- a/gdb/python/python.c
+++ b/gdb/python/python.c
@@ -166,6 +166,8 @@ static const struct extension_language_ops python_extension_ops =
   gdbpy_colorize,
 
   gdbpy_colorize_disasm,
+
+  NULL, /* gdbpy_print_insn, */
 };
 
 #endif /* HAVE_PYTHON */