[Tarantool-patches] [PATCH luajit v2 2/3] memprof: extend symtab with information about .so libs

[Maxim Kokryashkin via Tarantool-patches <tarantool-patches@dev.tarantool.org>]

This commit enriches memprof's symbol table with information about loaded
".so" files. That information will provide demangling capabilities to
the parser.

The following data is stored for each ".so" library:
| SYMTAB_SO | path to .so | it's address |  CRC32 Hash  |
  1 byte                       8 bytes       8 bytes
  magic
  number

C symbol address from profile events with an address of the ".so" file will
give us an offset, and it can be used to get the symbol in that file.

CRC32 hash will be used by the parser to determine whether the shared
object that was used during the process profiling and during the process
of parsing is the same.

Part of tarantool/tarantool#5813
---
 src/lj_memprof.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++
 src/lj_memprof.h |  3 ++-
 2 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/src/lj_memprof.c b/src/lj_memprof.c
index 2c1ef3b8..c8367c95 100644
--- a/src/lj_memprof.c
+++ b/src/lj_memprof.c
@@ -5,10 +5,15 @@
 ** Copyright (C) 2015-2019 IPONWEB Ltd.
 */
 
+#define _GNU_SOURCE
+
 #define lj_memprof_c
 #define LUA_CORE
 
 #include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <link.h>
 
 #include "lj_arch.h"
 #include "lj_memprof.h"
@@ -18,12 +23,64 @@
 #include "lj_obj.h"
 #include "lj_frame.h"
 #include "lj_debug.h"
+#include "lj_utils.h"
 
 /* --------------------------------- Symtab --------------------------------- */
 
 static const unsigned char ljs_header[] = {'l', 'j', 's', LJS_CURRENT_VERSION,
 					   0x0, 0x0, 0x0};
 
+int lj_file_crc32(const char* name, uint32_t* result) 
+{
+#define CRC_BUF_SIZE 1024 * 1024
+
+  char buf[CRC_BUF_SIZE] = "";
+  size_t read_bytes = 0;
+  FILE* so = NULL;
+
+  if (result == NULL) {
+    return 1;
+  }
+
+  *result = 0xffffffff;
+
+  so = fopen(name, "rb");
+  if (!so)
+    return 1;
+
+  while (CRC_BUF_SIZE == (read_bytes = fread(buf, sizeof(*buf), CRC_BUF_SIZE, so))) {
+    *result = lj_utils_crc32(buf, CRC_BUF_SIZE, *result); 
+  }
+  
+  if(ferror(so) || !feof(so)) {
+    fclose(so);
+    return 1;
+  }
+  
+  *result = lj_utils_crc32(buf, read_bytes, *result);
+  fclose(so);
+  return 0;
+}
+
+int write_shared_obj(struct dl_phdr_info *info, size_t size, void *data)
+{
+  uint32_t so_hash = 0;
+  struct lj_wbuf *buf = data;
+
+  if (info->dlpi_name && strlen(info->dlpi_name)) {
+    if (0 != lj_file_crc32(info->dlpi_name, &so_hash))
+      // XXX: Maybe it is reasonable to print warning here
+      return 0;
+
+    lj_wbuf_addbyte(buf, SYMTAB_SO);
+    lj_wbuf_addstring(buf, info->dlpi_name);
+    lj_wbuf_addu64(buf, info->dlpi_addr);
+    lj_wbuf_addu64(buf, so_hash);
+  }
+
+  return 0;
+}
+
 static void dump_symtab(struct lj_wbuf *out, const struct global_State *g)
 {
   const GCRef *iter = &g->gc.root;
@@ -49,6 +106,9 @@ static void dump_symtab(struct lj_wbuf *out, const struct global_State *g)
     iter = &o->gch.nextgc;
   }
 
+  /* Write shared libraries. */
+  dl_iterate_phdr(write_shared_obj, out);
+
   lj_wbuf_addbyte(out, SYMTAB_FINAL);
 }
 
diff --git a/src/lj_memprof.h b/src/lj_memprof.h
index 3417475d..0cefc403 100644
--- a/src/lj_memprof.h
+++ b/src/lj_memprof.h
@@ -16,7 +16,7 @@
 #include "lj_def.h"
 #include "lj_wbuf.h"
 
-#define LJS_CURRENT_VERSION 0x1
+#define LJS_CURRENT_VERSION 0x2
 
 /*
 ** symtab format:
@@ -51,6 +51,7 @@
 */
 
 #define SYMTAB_LFUNC ((uint8_t)0)
+#define SYMTAB_SO    ((uint8_t)1)
 #define SYMTAB_FINAL ((uint8_t)0x80)
 
 #define LJM_CURRENT_FORMAT_VERSION 0x01
-- 
2.32.0