axle-zsim-nvmain

zsim-nvmain整合
内核版本3.18
【下载地址】
解压目录下
1.修改install.sh （pin2.13网址不存在了） 或者删除掉pin的下载

PINVER=pin-2.14-71313-gcc.4.4.7-linux

(主要是下载nvmain)
2.按照https://mp.csdn.net/mdeditor/84853344# 安装相关库

3.配置环境变量

vim env.sh

#!/bin/sh
PINPATH=/home/taya/zsim-nvmain/axle-zsim-nvmain-master/pin_kit
NVMAINPATH=/home/taya/zsim-nvmain/axle-zsim-nvmain-master/nvmain
ZSIMPATH=/home/taya/zsim-nvmain/axle-zsim-nvmain-master
BOOST=/usr/local
HDF5=/home/taya/zsim-nvmain/hdf5-1.8.0/hdf5
LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$PINPATH/intel64/lib:$PINPATH/intel64/runtime:$PINPATH/intel64/lib:$PINPATH/intel64/lib-ext:$BOOST/lib:$HDF5/lib:/usr/local/gmp-4.3.2/lib:/usr/local/mpfr-2.4.2/lib:/usr/local/mpc-0.8.1/lib
INCLUDE=$INCLUDE:$HDF5/include
LIBRARY_PATH=$LIBRARY_PATH:$HDF5/lib
CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:$HDF5/include
export ZSIMPATH PINPATH NVMAINPATH LD_LIBRARY_PATH BOOST CPLUS_INCLUDE_PATH LIBRARY_PATH SIMPOINT_DIR

source env.sh

4编译 scons -j4

大部分遇到的问题，参考这里

https://blog.csdn.net/u013129143/article/details/84853344
https://blog.csdn.net/qqq_11101/article/details/78481377

有一部分编译syntax的错误在这里列出

vim SConstruct
将# Boost regex 部分改成 （原来的链接有问题）

# Boost regex
BOOST = os.environ["BOOST"]
include_path = os.environ['BOOST']+"/include"
lib_path = os.environ['BOOST']+"/lib"
env["CPPPATH"] += [include_path]
env["LIBPATH"] += [lib_path]
env["LIBS"] += ["boost_regex"]

将 env[“CXX” ] = os.environ[“CXX”]
env[“cc” ] = os.environ[“cc”] 改成
env[‘CXX’] = ‘g++’
env[‘CC’] = ‘g++’

src文件下 debug_zsim.cpp
-#include <libelf/gelf.h>
+#include <gelf.h>

5.运行过程问题

内核大于3.14版本会出现vdso找不到。因为3.14版本后的vdso 地址变了

首先到src目录 vim parse_vdso.cpp

/*
 * parse_vdso.c: Linux reference vDSO parser
 * Written by Andrew Lutomirski, 2011.
 *
 * This code is meant to be linked in to various programs that run on Linux.
 * As such, it is available with as few restrictions as possible.  This file
 * is licensed under the Creative Commons Zero License, version 1.0,
 * available at http://creativecommons.org/publicdomain/zero/1.0/legalcode
 *
 * The vDSO is a regular ELF DSO that the kernel maps into user space when
 * it starts a program.  It works equally well in statically and dynamically
 * linked binaries.
 *
 * This code is tested on x86_64.  In principle it should work on any 64-bit
 * architecture that has a vDSO.
 */

#include <stdbool.h>
#include <stdint.h>
#include <string.h>
#include <elf.h>

/*
 * To use this vDSO parser, first call one of the vdso_init_* functions.
 * If you've already parsed auxv, then pass the value of AT_SYSINFO_EHDR
 * to vdso_init_from_sysinfo_ehdr.  Otherwise pass auxv to vdso_init_from_auxv.
 * Then call vdso_sym for each symbol you want.  For example, to look up
 * gettimeofday on x86_64, use:
 *
 *     <some pointer> = vdso_sym("LINUX_2.6", "gettimeofday");
 * or
 *     <some pointer> = vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
 *
 * vdso_sym will return 0 if the symbol doesn't exist or if the init function
 * failed or was not called.  vdso_sym is a little slow, so its return value
 * should be cached.
 *
 * vdso_sym is threadsafe; the init functions are not.
 *
 * These are the prototypes:
 */
extern void vdso_init_from_auxv(void *auxv);
extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
extern void *vdso_sym(const char *version, const char *name);


/* And here's the code. */

#ifndef __x86_64__
# error Not yet ported to non-x86_64 architectures
#endif

static struct vdso_info
{
  bool valid;

  /* Load information */
  uintptr_t load_addr;
  uintptr_t load_offset;  /* load_addr - recorded vaddr */

  /* Symbol table */
  Elf64_Sym *symtab;
  const char *symstrings;
  Elf64_Word *bucket, *chain;
  Elf64_Word nbucket, nchain;

  /* Version table */
  Elf64_Versym *versym;
  Elf64_Verdef *verdef;
} vdso_info;

/* Straight from the ELF specification. */
static unsigned long elf_hash(const char *name)
{
  unsigned long h = 0;
  while (*name)
  {
    h = (h << 4) + *name++;
    unsigned long g = h & 0xf0000000;
    if (g)
      h ^= g >> 24;
    h &= ~g;
  }
  return h;
}

void vdso_init_from_sysinfo_ehdr(uintptr_t base)
{
  size_t i;
  bool found_vaddr = false;

  vdso_info.valid = false;

  vdso_info.load_addr = base;

  Elf64_Ehdr *hdr = (Elf64_Ehdr*)base;
  Elf64_Phdr *pt = (Elf64_Phdr*)(vdso_info.load_addr + hdr->e_phoff);
  Elf64_Dyn *dyn = 0;

  /*
   * We need two things from the segment table: the load offset
   * and the dynamic table.
   */
  for (i = 0; i < hdr->e_phnum; i++)
  {
    if (pt[i].p_type == PT_LOAD && !found_vaddr) {
      found_vaddr = true;
      vdso_info.load_offset =  base
        + (uintptr_t)pt[i].p_offset
        - (uintptr_t)pt[i].p_vaddr;
    } else if (pt[i].p_type == PT_DYNAMIC) {
      dyn = (Elf64_Dyn*)(base + pt[i].p_offset);
    }
  }

  if (!found_vaddr || !dyn)
    return;  /* Failed */

  /*
   * Fish out the useful bits of the dynamic table.
   */
  Elf64_Word *hash = 0;
  vdso_info.symstrings = 0;
  vdso_info.symtab = 0;
  vdso_info.versym = 0;
  vdso_info.verdef = 0;
  for (i = 0; dyn[i].d_tag != DT_NULL; i++) {
    switch (dyn[i].d_tag) {
    case DT_STRTAB:
      vdso_info.symstrings = (const char *)
        ((uintptr_t)dyn[i].d_un.d_ptr
         + vdso_info.load_offset);
      break;
    case DT_SYMTAB:
      vdso_info.symtab = (Elf64_Sym *)
        ((uintptr_t)dyn[i].d_un.d_ptr
         + vdso_info.load_offset);
      break;
    case DT_HASH:
      hash = (Elf64_Word *)
        ((uintptr_t)dyn[i].d_un.d_ptr
         + vdso_info.load_offset);
      break;
    case DT_VERSYM:
      vdso_info.versym = (Elf64_Versym *)
        ((uintptr_t)dyn[i].d_un.d_ptr
         + vdso_info.load_offset);
      break;
    case DT_VERDEF:
      vdso_info.verdef = (Elf64_Verdef *)
        ((uintptr_t)dyn[i].d_un.d_ptr
         + vdso_info.load_offset);
      break;
    }
  }
  if (!vdso_info.symstrings || !vdso_info.symtab || !hash)
    return;  /* Failed */

  if (!vdso_info.verdef)
    vdso_info.versym = 0;

  /* Parse the hash table header. */
  vdso_info.nbucket = hash[0];
  vdso_info.nchain = hash[1];
  vdso_info.bucket = &hash[2];
  vdso_info.chain = &hash[vdso_info.nbucket + 2];

  /* That's all we need. */
  vdso_info.valid = true;
}

static bool vdso_match_version(Elf64_Versym ver,
             const char *name, Elf64_Word hash)
{
  /*
   * This is a helper function to check if the version indexed by
   * ver matches name (which hashes to hash).
   *
   * The version definition table is a mess, and I don't know how
   * to do this in better than linear time without allocating memory
   * to build an index.  I also don't know why the table has
   * variable size entries in the first place.
   *
   * For added fun, I can't find a comprehensible specification of how
   * to parse all the weird flags in the table.
   *
   * So I just parse the whole table every time.
   */

  /* First step: find the version definition */
  ver &= 0x7fff;  /* Apparently bit 15 means "hidden" */
  Elf64_Verdef *def = vdso_info.verdef;
  while(true) {
    if ((def->vd_flags & VER_FLG_BASE) == 0
        && (def->vd_ndx & 0x7fff) == ver)
      break;

    if (def->vd_next == 0)
      return false;  /* No definition. */

    def = (Elf64_Verdef *)((char *)def + def->vd_next);
  }

  /* Now figure out whether it matches. */
  Elf64_Verdaux *aux = (Elf64_Verdaux*)((char *)def + def->vd_aux);
  return def->vd_hash == hash
    && !strcmp(name, vdso_info.symstrings + aux->vda_name);
}

void *vdso_sym(const char *version, const char *name)
{
  unsigned long ver_hash;
  if (!vdso_info.valid)
    return 0;

  ver_hash = elf_hash(version);
  Elf64_Word chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket];

  for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) {
    Elf64_Sym *sym = &vdso_info.symtab[chain];

    /* Check for a defined global or weak function w/ right name. */
    if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
      continue;
    if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL &&
        ELF64_ST_BIND(sym->st_info) != STB_WEAK)
      continue;
    if (sym->st_shndx == SHN_UNDEF)
      continue;
    if (strcmp(name, vdso_info.symstrings + sym->st_name))
      continue;

    /* Check symbol version. */
    if (vdso_info.versym
        && !vdso_match_version(vdso_info.versym[chain],
             version, ver_hash))
      continue;

    return (void *)(vdso_info.load_offset + sym->st_value);
  }

  return 0;
}

void vdso_init_from_auxv(void *auxv)
{
  Elf64_auxv_t *elf_auxv = (Elf64_auxv_t *) auxv;
  for (int i = 0; elf_auxv[i].a_type != AT_NULL; i++)
  {
    if (elf_auxv[i].a_type == AT_SYSINFO_EHDR) {
      vdso_init_from_sysinfo_ehdr(elf_auxv[i].a_un.a_val);
      return;
    }
  }

  vdso_info.valid = false;
}

然后修改src下的zsim.cpp

static uintptr_t vsyscallEnd;
static bool vsyscallWarned = false;

- void VdsoInsertFunc(IMG vi, const char* fName, VdsoFunc func) {
-    ADDRINT baseAddr = IMG_LowAddress(vi);
-   RTN rtn = RTN_FindByName(vi, fName);
-    if (rtn == RTN_Invalid()) {
+// Helper function from parse_vsdo.cpp
+extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
+extern void *vdso_sym(const char *version, const char *name);

+void VdsoInsertFunc(const char* fName, VdsoFunc func) {
+   ADDRINT vdsoFuncAddr = (ADDRINT) vdso_sym("LINUX_2.6", fName);
+    if (vdsoFuncAddr == 0) {
        warn("Did not find %s in vDSO", fName);
    } else {
-        ADDRINT rtnAddr = RTN_Address(rtn) - baseAddr + vdsoStart;
-        vdsoEntryMap[rtnAddr] = func;
+        vdsoEntryMap[vdsoFuncAddr] = func;
    }
}

@@ -683,33 +685,21 @@ void VdsoInit() {
        ........
        return;
    }

    ~~
    ---
    // Write it out
    std::stringstream file_ss;
    file_ss << zinfo->outputDir << "/vdso.dso." << procIdx;
    const char* file = file_ss.str().c_str();
    FILE* vf = fopen(file, "w");
    fwrite(reinterpret_cast<void*>(vdso.start), 1, vdsoEnd-vdsoStart, vf);
    fclose(vf);
    // Load it and analyze it
    IMG vi = IMG_Open(file);
    if (!IMG_Valid(vi)) panic("Loaded vDSO not valid");
    ---------
    ~~ 
 +   vdso_init_from_sysinfo_ehdr(vdsoStart);

-    VdsoInsertFunc(vi, "clock_gettime", VF_CLOCK_GETTIME);
-    VdsoInsertFunc(vi, "__vdso_clock_gettime", VF_CLOCK_GETTIME);
+    VdsoInsertFunc("clock_gettime", VF_CLOCK_GETTIME);
+   VdsoInsertFunc("__vdso_clock_gettime", VF_CLOCK_GETTIME);

-    VdsoInsertFunc(vi, "gettimeofday", VF_GETTIMEOFDAY);
-    VdsoInsertFunc(vi, "__vdso_gettimeofday", VF_GETTIMEOFDAY);
+    VdsoInsertFunc("gettimeofday", VF_GETTIMEOFDAY);
+   VdsoInsertFunc("__vdso_gettimeofday", VF_GETTIMEOFDAY);

-    VdsoInsertFunc(vi, "time", VF_TIME);
-    VdsoInsertFunc(vi, "__vdso_time", VF_TIME);
+    VdsoInsertFunc("time", VF_TIME);
+   VdsoInsertFunc("__vdso_time", VF_TIME);

-    VdsoInsertFunc(vi, "getcpu", VF_GETCPU);
-    VdsoInsertFunc(vi, "__vdso_getcpu", VF_GETCPU);
+    VdsoInsertFunc("getcpu", VF_GETCPU);
+    VdsoInsertFunc("__vdso_getcpu", VF_GETCPU);

    info("vDSO info initialized");
-    IMG_Close(vi);
-    remove(file);

    Section vsyscall = FindSection("vsyscall");
    vsyscallStart = vsyscall.start;

参考：

https://blog.csdn.net/u013129143/article/details/84853344
https://blog.csdn.net/qqq_11101/article/details/78481377
https://github.com/s5z/zsim/commit/769b59d5adb84a27bd7088f7379a7e7e2ff8269d