[Tarantool-patches] [PATCH luajit v4] dbg: display fast function name along with ffid

[Mikhail Elhimov via Tarantool-patches <tarantool-patches@dev.tarantool.org>]

Part of tarantool/tarantool#4808
---
Changes in v4:
  * Adjusted mapping of enum member to name ('_' is replaced with '.' only if it is not preceded by another '_')
  * Added tests of various ff (including unknown)
  * Reduced code duplication
  * Fixed typos

Changes in v3:
  * Fixed fast function regexp in tests

Changes in v2:
  * Format is changed to 'ffname (#ffid)'
  * Replaced single '_' with '.' in ffname
  * Adjusted tests to check mapping

This patch is to be applied after https://lists.tarantool.org/pipermail/tarantool-patches/2026-September/030791.html.

Branch: https://github.com/tarantool/luajit/tree/elhimov/gh-4808-display-fast-function-name
Related issue: https://github.com/tarantool/tarantool/issues/4808

 src/luajit_dbg.py                             |  36 +++--
 .../debug-extension-tests.py                  | 125 ++++++++++++++----
 2 files changed, 119 insertions(+), 42 deletions(-)

diff --git a/src/luajit_dbg.py b/src/luajit_dbg.py
index 7c2d085f..1d553fb9 100644
--- a/src/luajit_dbg.py
+++ b/src/luajit_dbg.py
@@ -1121,6 +1121,11 @@ def frames(L):
 # LuaJIT macro implementations and structure access.
 
 
+# Get FastFunc enum members and replace any single '_' with '.'.
+FF_NAMES = EnumBasedList('FastFunc', 'FF__MAX', lambda x:
+                         re.sub('(?<!_)_', '.', cut_prefix(x, 'FF_')))
+
+
 def mref(typename, obj):
     return dbg.cast(typename, obj['ptr64'] if LJ_GC64 else obj['ptr32'])
 
@@ -1693,6 +1698,11 @@ def ir_kint64(ir):
 
 # Dumpers.
 
+def dump_fast_function(ffid):
+    ffname = FF_NAMES[ffid] if ffid < len(FF_NAMES) else 'unknown'
+    return 'fast function {} (#{})'.format(ffname, ffid)
+
+
 # GCobj dumpers.
 
 def dump_lj_gco_str(gcobj):
@@ -1716,7 +1726,7 @@ def dump_lj_gco_proto(gcobj):
 
 def dump_lj_gco_func(gcobj):
     func = dbg.cast('struct GCfuncC *', gcobj)
-    ffid = func['ffid']
+    ffid = int(func['ffid'])
 
     if ffid == 0:
         pt = funcproto(func)
@@ -1729,7 +1739,7 @@ def dump_lj_gco_func(gcobj):
     elif ffid == 1:
         return 'C function @ {}'.format(strx64(func['f']))
     else:
-        return 'fast function #{}'.format(int(ffid))
+        return dump_fast_function(ffid)
 
 
 def dump_lj_gco_trace(gcobj):
@@ -2063,7 +2073,7 @@ def dump_proto(proto):
     startbc = proto_bc(proto)
     func_loc = proto_loc(proto)
     # Location has the following format: '{chunk}:{firstline}'.
-    dump = '{func_loc}-{lastline}\n'.format(
+    dump = '{func_loc}-{lastline}'.format(
         func_loc=func_loc,
         lastline=proto['firstline'] + proto['numline'],
     )
@@ -2072,22 +2082,22 @@ def dump_proto(proto):
         return '=> ' + str(npc_from + delta).zfill(4)
 
     for bcnum in range(0, int(proto['sizebc'])):
-        dump += (str(bcnum).zfill(4) + ' ' + dump_bc(
+        dump += '\n' + str(bcnum).zfill(4) + ' ' + dump_bc(
             startbc[bcnum], jmp_format=jmp_format, jmp_ctx=bcnum, proto=proto,
-        ) + '\n')
+        )
     return dump
 
 
 def dump_func(func):
-    ffid = func['ffid']
+    ffid = int(func['ffid'])
 
     if ffid == 0:
         pt = funcproto(func)
         return dump_proto(pt)
     elif ffid == 1:
-        return 'C function @ {}\n'.format(strx64(func['f']))
+        return 'C function @ {}'.format(strx64(func['f']))
     else:
-        return 'fast function #{}\n'.format(int(ffid))
+        return dump_fast_function(ffid)
 
 
 # FFI dumpers.
@@ -2669,7 +2679,7 @@ function:
     '''
 
     def execute(self, arg):
-        dbg.write('{}'.format(dump_func(dbg.cast('GCfuncC *', dbg.eval(arg)))))
+        dbg.write(dump_func(dbg.cast('GCfuncC *', dbg.eval(arg))) + '\n')
 
 
 class LJGC(dbg.LJBase):
@@ -2713,7 +2723,7 @@ the type and some info related to it.
 * LJ_TFUNC: <LFUNC|CFUNC|FFUNC>
   <LFUNC>: Lua function @ <gcr>, <nupvals> upvalues, <chunk:line>
   <CFUNC>: C function <mcode address>
-  <FFUNC>: fast function #<ffid>
+  <FFUNC>: fast function <ffname> (#<ffid>)
 * LJ_TTRACE: trace <traceno> @ <gcr>
 * LJ_TCDATA: cdata @ <gcr>
 * LJ_TTAB: table @ <gcr> (asize: <asize>, hmask: <hmask>)
@@ -2786,9 +2796,7 @@ function:
     '''
 
     def execute(self, arg):
-        dbg.write('{}'.format(
-            dump_proto(dbg.cast('GCproto *', dbg.eval(arg)))
-        ))
+        dbg.write(dump_proto(dbg.cast('GCproto *', dbg.eval(arg))) + '\n')
 
 
 class LJDumpStack(dbg.LJBase):
@@ -2932,7 +2940,7 @@ the type and some info related to it.
 * LJ_TFUNC: <LFUNC|CFUNC|FFUNC>
   <LFUNC>: Lua function @ <gcr>, <nupvals> upvalues, <chunk:line>
   <CFUNC>: C function <mcode address>
-  <FFUNC>: fast function #<ffid>
+  <FFUNC>: fast function <ffname> (#<ffid>)
 * LJ_TTRACE: trace <traceno> @ <gcr>
 * LJ_TCDATA: cdata @ <gcr>
 * LJ_TTAB: table @ <gcr> (asize: <asize>, hmask: <hmask>)
diff --git a/test/tarantool-debugger-tests/debug-extension-tests.py b/test/tarantool-debugger-tests/debug-extension-tests.py
index 5e369f00..b6e51185 100644
--- a/test/tarantool-debugger-tests/debug-extension-tests.py
+++ b/test/tarantool-debugger-tests/debug-extension-tests.py
@@ -35,6 +35,10 @@ if LLDB:
         '--source-quietly',
         '--source'
     ]
+
+    def modify_obj_cmd(obj, val):
+        return 'expression {} = {}'.format(obj, val)
+
 else:
     # GDB.
     INFERIOR_ARGS = '--args'
@@ -43,6 +47,9 @@ else:
     # Don't run any initialization scripts.
     RUN_CMD_FILE = ['--batch', '--nx', '--quiet', '--command']
 
+    def modify_obj_cmd(obj, val):
+        return 'set var {} = {}'.format(obj, val)
+
 TEST_VERBOSE = os.getenv('DEBUGGER_TEST_VERBOSE', default=False)
 
 RX_ADDR = r'0x[a-f0-9]+'
@@ -320,13 +327,31 @@ class TestLJStackFunc(TestCaseBase):
     pattern = STACK_RX
 
 
+FFUNC_ARGS = (
+    'print,\n'
+    'math.min,\n'
+    'getmetatable(io.stdout).close,\n'
+    'getmetatable(io.stdout).__gc,\n'
+    'getmetatable(io.stdout).__tostring,\n'
+)
+
+
+FFUNC_RX = (
+    r'fast function print \(#[0-9]+\)\n'
+    r'fast function math.min \(#[0-9]+\)\n'
+    r'fast function io.method.close \(#[0-9]+\)\n'
+    r'fast function io.method.__gc \(#[0-9]+\)\n'
+    r'fast function io.method.__tostring \(#[0-9]+\)\n'
+)
+
+
 # Sorted in LJT order.
 GCO_ARGS = (
     '"hello",\n'
     'coroutine.create(function() end),\n'
     'function() end,\n'
-    'require,\n'
-    'print,\n'
+    'require,\n' +
+    FFUNC_ARGS +
     'ffi.new("int*"),\n'
     '{1},\n'
     'newproxy(),\n'
@@ -337,8 +362,8 @@ GCO_RX = (
     r'string \"hello\" @ ' + RX_ADDR + r'\n'
     r'thread @ ' + RX_ADDR + r'\n'
     r'Lua function @ ' + RX_ADDR + r', [0-9]+ upvalues, .+:[0-9]+\n'
-    r'C function @ ' + RX_ADDR + r'\n'
-    r'fast function #[0-9]+\n'
+    r'C function @ ' + RX_ADDR + r'\n' +
+    FFUNC_RX +
     r'cdata @ ' + RX_ADDR + r' \[\d+\] <int \*> 0x0\n'
     r'table @ ' + RX_ADDR + r' \(asize: \d+, hmask: ' + RX_HASH + r'\)\n'
     r'userdata @ ' + RX_ADDR + r'\n'
@@ -347,26 +372,15 @@ GCO_RX = (
 
 class TestLJTV(TestCaseBase):
     location = 'lj_cf_print'
-    extension_cmds = (
-        'lj-tv L->base\n'
-        'lj-tv L->base + 1\n'
-        'lj-tv L->base + 2\n'
-        'lj-tv L->base + 3\n'
-        'lj-tv L->base + 4\n'
-        'lj-tv L->base + 5\n'
-        'lj-tv L->base + 6\n'
-        'lj-tv L->base + 7\n'
-        'lj-tv L->base + 8\n'
-        'lj-tv L->base + 9\n'
-        'lj-tv L->base + 10\n'
-        'lj-tv L->base + 11\n'
-        'lj-tv L->base + 12\n'
-        'lj-tv L->base + 13\n'
+    extension_cmds = ''.join(
+        ('lj-tv L->base+{}\n'.format(i)
+         for i in range(4 + GCO_ARGS.count('\n') + 2))
     )
 
     # Sorted in LJT order.
     lua_script = (
         'local ffi = require("ffi")\n'
+        'local math = require("math")\n'
         'print(\n'
         '  nil,\n'
         '  false,\n'
@@ -422,19 +436,14 @@ class TestLJTab(TestCaseBase):
 
 class TestLJGCo(TestCaseBase):
     location = 'lj_cf_print'
-    extension_cmds = (
-        'lj-gco ' + gcval('L->base + 0') + '\n'
-        'lj-gco ' + gcval('L->base + 1') + '\n'
-        'lj-gco ' + gcval('L->base + 2') + '\n'
-        'lj-gco ' + gcval('L->base + 3') + '\n'
-        'lj-gco ' + gcval('L->base + 4') + '\n'
-        'lj-gco ' + gcval('L->base + 5') + '\n'
-        'lj-gco ' + gcval('L->base + 6') + '\n'
-        'lj-gco ' + gcval('L->base + 7') + '\n'
+    extension_cmds = ''.join(
+        ('lj-gco ' + gcval('L->base + {}'.format(i)) + '\n'
+         for i in range(GCO_ARGS.count('\n')))
     )
 
     lua_script = (
         'local ffi = require("ffi")\n'
+        'local math = require("math")\n'
         'print(\n' +
         GCO_ARGS +
         '  1\n'  # Stub for the pattern.
@@ -444,6 +453,66 @@ class TestLJGCo(TestCaseBase):
     pattern = GCO_RX
 
 
+class TestLJGCoFFUnknown(TestCaseBase):
+    location = 'lj_cf_print'
+
+    val = '((GCfuncC *)' + gcval('L->base') + ')'
+    extension_cmds = (
+        'lj-gco ' + val + '\n' +
+        modify_obj_cmd(val + '->ffid', 242) + '\n'
+        'lj-gco ' + val + '\n' +
+        modify_obj_cmd(val + '->ffid', 253) + '\n'
+        'lj-gco ' + val + '\n'
+    )
+
+    lua_script = 'print(pcall)'
+
+    pattern = (
+        r'fast function pcall \(#[0-9]+\)\n'
+        r'fast function unknown \(#242\)\n'
+        r'fast function unknown \(#253\)\n'
+    )
+
+
+class TestLJFuncFFKnown(TestCaseBase):
+    location = 'lj_cf_print'
+    extension_cmds = ''.join(
+        ('lj-func ' + gcval('L->base + {}'.format(i)) + '\n'
+         for i in range(FFUNC_ARGS.count('\n')))
+    )
+
+    lua_script = (
+        'local math = require("math")\n'
+        'print(\n' +
+        FFUNC_ARGS +
+        '  1\n'  # Stub for the pattern.
+        ')\n'
+    )
+
+    pattern = FFUNC_RX
+
+
+class TestLJFuncFFUnknown(TestCaseBase):
+    location = 'lj_cf_print'
+
+    val = '((GCfuncC *)' + gcval('L->base') + ')'
+    extension_cmds = (
+        'lj-func ' + val + '\n' +
+        modify_obj_cmd(val + '->ffid', 242) + '\n'
+        'lj-func ' + val + '\n' +
+        modify_obj_cmd(val + '->ffid', 253) + '\n'
+        'lj-func ' + val + '\n'
+    )
+
+    lua_script = 'print(pcall)'
+
+    pattern = (
+        r'fast function pcall \(#[0-9]+\)\n'
+        r'fast function unknown \(#242\)\n'
+        r'fast function unknown \(#253\)\n'
+    )
+
+
 PROTO_FUNC_SCRIPT = (
     'local uvname = false\n'
     'local function testf(...)\n'
-- 
2.43.0