[Tarantool-patches] [PATCH luajit v1] memprof: group allocations on traces by trace number

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

When luajit executes a trace, it's id is stored in virtual machine
state. So, we can treat this trace number as allocation event source
in memprof and report allocation events from traces as well.

Previously all the allocations from traces were marked as INTERNAL.

This patch introduces functionality described above by adding new
allocation source type named ASOURCE_TRACE. If at the moment when
allocation event occur vmstate indicates that trace is executed,
trace id is streamed to binary file:

| loc-trace := trace-no
| trace-no  := <ULEB128>

Also, memory profiler parser was tuned to recognize this source type by
extending <loc> structure: field trace, representing trace id, was
added.

Now, for example, all the allocation events happened in trace with id 42,
will be reported at source 'TRACE [42]' and not at 'INTERNAL' source.

Closes tarantool/tarantool#5814
---

Issue: https://github.com/tarantool/tarantool/issues/5814
Branch: https://github.com/tarantool/luajit/tree/shishqa/gh-5814-group-allocations-on-trace-by-trace-number

 src/lj_memprof.c        | 16 ++++++++--------
 src/lj_memprof.h        |  9 ++++++---
 tools/memprof/parse.lua | 18 +++++++++++-------
 tools/utils/symtab.lua  |  5 +++++
 4 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/src/lj_memprof.c b/src/lj_memprof.c
index 2c1ef3b8..0cbc0ed7 100644
--- a/src/lj_memprof.c
+++ b/src/lj_memprof.c
@@ -146,6 +146,13 @@ static void memprof_write_func(struct memprof *mp, uint8_t aevent)
     lua_assert(0);
 }
 
+static void memprof_write_trace(struct memprof *mp, uint8_t aevent)
+{
+  struct lj_wbuf *out = &mp->out;
+  lj_wbuf_addbyte(out, aevent | ASOURCE_TRACE);
+  lj_wbuf_addu64(out, (uint64_t)mp->g->vmstate); /* write traceno. */
+}
+
 static void memprof_write_hvmstate(struct memprof *mp, uint8_t aevent)
 {
   lj_wbuf_addbyte(&mp->out, aevent | ASOURCE_INT);
@@ -163,14 +170,7 @@ static const memprof_writer memprof_writers[] = {
   memprof_write_hvmstate, /* LJ_VMST_RECORD */
   memprof_write_hvmstate, /* LJ_VMST_OPT */
   memprof_write_hvmstate, /* LJ_VMST_ASM */
-  /*
-  ** XXX: In ideal world, we should report allocations from traces as well.
-  ** But since traces must follow the semantics of the original code,
-  ** behaviour of Lua and JITted code must match 1:1 in terms of allocations,
-  ** which makes using memprof with enabled JIT virtually redundant.
-  ** Hence use the stub below.
-  */
-  memprof_write_hvmstate /* LJ_VMST_TRACE */
+  memprof_write_trace /* LJ_VMST_TRACE */
 };
 
 static void memprof_write_caller(struct memprof *mp, uint8_t aevent)
diff --git a/src/lj_memprof.h b/src/lj_memprof.h
index 3417475d..13125536 100644
--- a/src/lj_memprof.h
+++ b/src/lj_memprof.h
@@ -69,11 +69,13 @@
 ** event-realloc  := event-header loc? oaddr osize naddr nsize
 ** event-free     := event-header loc? oaddr osize
 ** event-header   := <BYTE>
-** loc            := loc-lua | loc-c
+** loc            := loc-lua | loc-c | loc-trace
 ** loc-lua        := sym-addr line-no
 ** loc-c          := sym-addr
+** loc-trace      := trace-no
 ** sym-addr       := <ULEB128>
 ** line-no        := <ULEB128>
+** trace-no       := <ULEB128>
 ** oaddr          := <ULEB128>
 ** naddr          := <ULEB128>
 ** osize          := <ULEB128>
@@ -90,8 +92,8 @@
 **
 ** event-header: [FUUUSSEE]
 **  * EE   : 2 bits for representing allocation event type (AEVENT_*)
-**  * SS   : 2 bits for representing allocation source type (ASOURCE_*)
-**  * UUU  : 3 unused bits
+**  * SSS  : 3 bits for representing allocation source type (ASOURCE_*)
+**  * UU   : 2 unused bits
 **  * F    : 0 for regular events, 1 for epilogue's *F*inal header
 **           (if F is set to 1, all other bits are currently ignored)
 */
@@ -105,6 +107,7 @@
 #define ASOURCE_INT   ((uint8_t)(1 << 2))
 #define ASOURCE_LFUNC ((uint8_t)(2 << 2))
 #define ASOURCE_CFUNC ((uint8_t)(3 << 2))
+#define ASOURCE_TRACE ((uint8_t)(4 << 2))
 
 #define LJM_EPILOGUE_HEADER 0x80
 
diff --git a/tools/memprof/parse.lua b/tools/memprof/parse.lua
index 12e2758f..2bd491c8 100644
--- a/tools/memprof/parse.lua
+++ b/tools/memprof/parse.lua
@@ -24,8 +24,9 @@ local AEVENT_MASK = 0x3
 local ASOURCE_INT = lshift(1, 2)
 local ASOURCE_LFUNC = lshift(2, 2)
 local ASOURCE_CFUNC = lshift(3, 2)
+local ASOURCE_TRACE = lshift(4, 2)
 
-local ASOURCE_MASK = lshift(0x3, 2)
+local ASOURCE_MASK = lshift(0x7, 2)
 
 local M = {}
 
@@ -59,20 +60,23 @@ local function link_to_previous(heap_chunk, e, nsize)
   end
 end
 
-local function id_location(addr, line)
-  return string_format("f%#xl%d", addr, line), {
+local function id_location(addr, line, trace)
+  return string_format("f%#xl%dxt%d", addr, line, trace), {
     addr = addr,
     line = line,
+    trace = trace,
   }
 end
 
 local function parse_location(reader, asource)
   if asource == ASOURCE_INT then
-    return id_location(0, 0)
+    return id_location(0, 0, 0)
   elseif asource == ASOURCE_CFUNC then
-    return id_location(reader:read_uleb128(), 0)
+    return id_location(reader:read_uleb128(), 0, 0)
   elseif asource == ASOURCE_LFUNC then
-    return id_location(reader:read_uleb128(), reader:read_uleb128())
+    return id_location(reader:read_uleb128(), reader:read_uleb128(), 0)
+  elseif asource == ASOURCE_TRACE then
+    return id_location(0, 0, reader:read_uleb128())
   end
   error("Unknown asource "..asource)
 end
@@ -140,7 +144,7 @@ local parsers = {
 }
 
 local function ev_header_is_valid(evh)
-  return evh <= 0x0f or evh == LJM_EPILOGUE_HEADER
+  return evh <= 0x1f or evh == LJM_EPILOGUE_HEADER
 end
 
 -- Splits event header into event type (aka aevent = allocation
diff --git a/tools/utils/symtab.lua b/tools/utils/symtab.lua
index 3ed1dd13..6121177f 100644
--- a/tools/utils/symtab.lua
+++ b/tools/utils/symtab.lua
@@ -75,6 +75,11 @@ end
 
 function M.demangle(symtab, loc)
   local addr = loc.addr
+  local trace = loc.trace
+
+  if trace ~= 0 then
+    return string_format("TRACE [%d]", trace)
+  end
 
   if addr == 0 then
     return "INTERNAL"
-- 
2.32.0