Flipping Bits in Memory Without Accessing Them: An Experimental Study of DRAM Disturbance Errors

1. Rowhammer Introduction
2. Rowhammer Principle
3. Track And Fix 

code1a:
    mov (X), %eax  // Read from address X
    mov (Y), %ebx  // Read from address Y
    clflush (X)  // Flush cache for address X
    clflush (Y)  // Flush cache for address Y
    jmp code1a 

1. 地址选择: 地址X和地址Y必须印射到内存的不同row但是又是在同一bank上，即相邻行
每个DRAM芯片包含了很多行(row)的单元。访问一个byte在内存中涉及到将数据从row传输到芯片的"row buffer"中(放电操作)，当读取或者写入row buffer的内容后，再把row buffer内容传输到原来的row单元里(充电操作)。这种"激活"一个row的操作(放电和充电)可以干扰到临近的row。如果这样做足够多的次数，临近row的自动刷新操作(一般是每64ms)可能会让临近row的位产生变化。
row buffer作为缓存，如果地址X和Y指向相同的row，那code1a将会从row buffer中读取信息而不用任何"激活"操作 
每个DRAM的bank都有自己的"当前已激活的row"，所以如果地址X和地址Y指向不同的bank，code1a将会从那些bank的row buffer中读取信息而不用反复的激活row。所以，如果地址X和地址Y指向同一bank上不同的row，code1a会导致X和Y不断的被激活，这被称为ROWHAMMERING 

3. 绕过缓存: 没有了code1a中的CLFLUSH指令的话，内存读操作(mov)只会操作CPU的高速缓存。CLFLUSH刷新缓存的操作强制让内存的访问直接指向DRAM，而这会导致不断有row被重复的激活

http://linux.cn/article-5030-qqmail.html
http://www.ddrdetective.com/row-hammer/

./make.sh
./rowhammer_test

#define __STDC_FORMAT_MACROS

#include <assert.h>
#include <inttypes.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/time.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>


const size_t mem_size = 1 << 30;
const int toggles = 540000;

char *g_mem;

char *pick_addr() 
{
  size_t offset = (rand() << 12) % mem_size;
  return g_mem + offset;
}

class Timer 
{
  struct timeval start_time_;

 public:
  Timer() 
  {
    // Note that we use gettimeofday() (with microsecond resolution)
    // rather than clock_gettime() (with nanosecond resolution) so
    // that this works on Mac OS X, because OS X doesn‘t provide
    // clock_gettime() and we don‘t really need nanosecond resolution.
    int rc = gettimeofday(&start_time_, NULL);
    assert(rc == 0);
  }

  double get_diff() 
  {
    struct timeval end_time;
    int rc = gettimeofday(&end_time, NULL);
    assert(rc == 0);
    return (end_time.tv_sec - start_time_.tv_sec
            + (double) (end_time.tv_usec - start_time_.tv_usec) / 1e6);
  }

  void print_iters(uint64_t iterations) 
  {
    double total_time = get_diff();
    double iter_time = total_time / iterations;
    printf("  %.3f nanosec per iteration: %g sec for %" PRId64 " iterations\n",
           iter_time * 1e9, total_time, iterations);
  }
};

//读取指定长度的内存bit位，即触发"放电操作"
static void toggle(int iterations, int addr_count) 
{
  Timer t;
  for (int j = 0; j < iterations; j++) 
  {
    uint32_t *addrs[addr_count];
    for (int a = 0; a < addr_count; a++)
    {
      //选取不同row，但是同一bank的内存bit，可能并不一定是相邻行
      addrs[a] = (uint32_t *) pick_addr();
    } 

    uint32_t sum = 0;
    //循环toggles = 540000次，进行物理内存读取
    for (int i = 0; i < toggles; i++) 
    {
      for (int a = 0; a < addr_count; a++)
      {
        //读取addr_count长度的内存块
        sum += *addrs[a] + 1;
      } 
      for (int a = 0; a < addr_count; a++)
      {
        //清除addr_count长度内存块的对应的CPU高速缓存
        asm volatile("clflush (%0)" : : "r" (addrs[a]) : "memory");
      } 
    }

    // Sanity check.  We don‘t expect this to fail, because reading
    // these rows refreshes them.
    if (sum != 0)
    {
      printf("error: sum=%x\n", sum);
      exit(1);
    }
  }
  t.print_iters(iterations * addr_count * toggles);
}

void main_prog() 
{
  g_mem = (char *) mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_ANON | MAP_PRIVATE, -1, 0);
  assert(g_mem != MAP_FAILED);

  printf("clear\n");
  //初始化对应的内存区( [g_mem ~ g_mem + mem_size] )为初始值: 0XFF
  memset(g_mem, 0xff, mem_size);

  Timer t;
  int iter = 0;
  //无限循环，在大多数时候，需要触发这个漏洞需要较多的尝试
  for (;;) 
  {
    printf("Iteration %i (after %.2fs)\n", iter++, t.get_diff());
    //循环10次，每次8byte内存单位
    toggle(10, 8);

    Timer check_timer;
    printf("check\n");
    uint64_t *end = (uint64_t *) (g_mem + mem_size);
    uint64_t *ptr;
    int errors = 0;
    for (ptr = (uint64_t *) g_mem; ptr < end; ptr++) 
    {
      uint64_t got = *ptr;
      if (got != ~(uint64_t) 0) 
      {
        printf("error at %p: got 0x%" PRIx64 "\n", ptr, got);
        errors++;
      }
    }
    printf("  (check took %fs)\n", check_timer.get_diff());
    if (errors)
      exit(1);
  }
}


int main() 
{
  // In case we are running as PID 1, we fork() a subprocess to run
  // the test in.  Otherwise, if process 1 exits or crashes, this will
  // cause a kernel panic (which can cause a reboot or just obscure
  // log output and prevent console scrollback from working).
  int pid = fork();
  if (pid == 0) 
  {
    main_prog();
    _exit(1);
  }

  int status;
  if (waitpid(pid, &status, 0) == pid) 
  {
    printf("** exited with status %i (0x%x)\n", status, status);
  }

  for (;;) 
  {
    sleep(999);
  }
  return 0;
}

// Small test program to systematically check through the memory to find bit
// flips by double-sided row hammering.
//
// Compilation instructions:
//   g++ -std=c++11 [filename]
//
// ./double_sided_rowhammer [-t nsecs] [-p percentage]
//
// Hammers for nsecs seconds, acquires the described fraction of memory (0.0 to 0.9 or so).

#include <asm/unistd.h>
#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
#include <linux/kernel-page-flags.h>
#include <map>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/mount.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/sysinfo.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>
#include <vector>

// The fraction of physical memory that should be mapped for testing.
double fraction_of_physical_memory = 0.3;

// The time to hammer before aborting. Defaults to one hour.
uint64_t number_of_seconds_to_hammer = 3600;

// The number of memory reads to try.
uint64_t number_of_reads = 1000*1024;

// Obtain the size of the physical memory of the system.
uint64_t GetPhysicalMemorySize() {
  struct sysinfo info;
  sysinfo( &info );
  return (size_t)info.totalram * (size_t)info.mem_unit;
}

// If physical_address is in the range, put (physical_address, virtual_address)
// into the map.
bool PutPointerIfInAddressRange(const std::pair<uint64_t, uint64_t>& range,
    uint64_t physical_address, uint8_t* virtual_address,
    std::map<uint64_t, uint8_t*>& pointers) {
  if (physical_address >= range.first && physical_address <= range.second) {
    printf("[!] Found desired physical address %lx at virtual %lx\n", 
        (uint64_t)physical_address, (uint64_t)virtual_address);
    pointers[physical_address] = virtual_address;
    return true;
  }
  return false;
}

bool IsRangeInMap(const std::pair<uint64_t, uint64_t>& range,
    const std::map<uint64_t, uint8_t*>& mapping) {
  for (uint64_t check = range.first; check <= range.second; check += 0x1000) {
    if (mapping.find(check) == mapping.end()) {
      printf("[!] Failed to find physical memory at %lx\n", check);
      return false;
    }
  }
  return true;
}

uint64_t GetPageFrameNumber(int pagemap, uint8_t* virtual_address) {
  // Read the entry in the pagemap.
  uint64_t value;
  int got = pread(pagemap, &value, 8,
                  (reinterpret_cast<uintptr_t>(virtual_address) / 0x1000) * 8);
  assert(got == 8);
  uint64_t page_frame_number = value & ((1ULL << 54)-1);
  return page_frame_number;
}

void SetupMapping(uint64_t* mapping_size, void** mapping) {
  *mapping_size = 
    static_cast<uint64_t>((static_cast<double>(GetPhysicalMemorySize()) * 
          fraction_of_physical_memory));

  *mapping = mmap(NULL, *mapping_size, PROT_READ | PROT_WRITE,
      MAP_POPULATE | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
  assert(*mapping != (void*)-1);

  // Initialize the mapping so that the pages are non-empty.
  printf("[!] Initializing large memory mapping ...");
  for (uint64_t index = 0; index < *mapping_size; index += 0x1000) {
    uint64_t* temporary = reinterpret_cast<uint64_t*>(
        static_cast<uint8_t*>(*mapping) + index);
    temporary[0] = index;
  }
  printf("done\n");
}

// Build a memory mapping that is big enough to cover all of physical memory.
bool GetMappingsForPhysicalRanges(
    const std::pair<uint64_t, uint64_t>& physical_range_A_to_hammer, 
    std::map<uint64_t, uint8_t*>& pointers_to_hammer_A,
    const std::pair<uint64_t, uint64_t>& physical_range_B_to_hammer,
    std::map<uint64_t, uint8_t*>& pointers_to_hammer_B,
    const std::pair<uint64_t, uint64_t>& physical_range_to_check,
    std::map<uint64_t, uint8_t*>& pointers_to_range_to_check,
    void** out_mapping) {

  uint64_t mapping_size;
  void* mapping;
  SetupMapping(&mapping_size, &mapping);

  int pagemap = open("/proc/self/pagemap", O_RDONLY);
  assert(pagemap >= 0);

  // Don‘t assert if opening this fails, the code needs to run under usermode.
  int kpageflags = open("/proc/kpageflags", O_RDONLY);

  // Iterate over the entire mapping, identifying the physical addresses for 
  // each 4k-page.
  for (uint64_t offset = 0; offset < mapping_size; offset += 0x1000) {
    uint8_t* virtual_address = static_cast<uint8_t*>(mapping) + offset;
    uint64_t page_frame_number = GetPageFrameNumber(pagemap, virtual_address);
    // Read the flags for this page if we have access to kpageflags.
    uint64_t page_flags = 0;
    if (kpageflags >= 0) {
      int got = pread(kpageflags, &page_flags, 8, page_frame_number * 8);
      assert(got == 8);
    }

    uint64_t physical_address;
    if (page_flags & KPF_HUGE) {
      printf("[!] %lx is on huge page\n", (uint64_t)virtual_address);
      physical_address = (page_frame_number * 0x1000) + 
        (reinterpret_cast<uintptr_t>(virtual_address) & (0x200000-1));
    } else {
      physical_address = (page_frame_number * 0x1000) + 
       (reinterpret_cast<uintptr_t>(virtual_address) & 0xFFF);
    }

    //printf("[!] %lx is %lx\n", (uint64_t)virtual_address, 
    //    (uint64_t)physical_address);
    PutPointerIfInAddressRange(physical_range_A_to_hammer, physical_address,
       virtual_address, pointers_to_hammer_A);
    PutPointerIfInAddressRange(physical_range_B_to_hammer, physical_address,
       virtual_address, pointers_to_hammer_B);
    PutPointerIfInAddressRange(physical_range_to_check, physical_address,
       virtual_address, pointers_to_range_to_check);
  }
  // Check if all physical addresses the caller asked for are in the resulting
  // map.
  if (IsRangeInMap(physical_range_A_to_hammer, pointers_to_hammer_A)
      && IsRangeInMap(physical_range_B_to_hammer, pointers_to_hammer_B)
      && IsRangeInMap(physical_range_to_check, pointers_to_range_to_check)) {
    return true;
  }
  return false;
}

uint64_t HammerAddressesStandard(
    const std::pair<uint64_t, uint64_t>& first_range,
    const std::pair<uint64_t, uint64_t>& second_range,
    uint64_t number_of_reads) {
  volatile uint64_t* first_pointer =
      reinterpret_cast<uint64_t*>(first_range.first);
  volatile uint64_t* second_pointer =
      reinterpret_cast<uint64_t*>(second_range.first);
  uint64_t sum = 0;

  while (number_of_reads-- > 0) {
    sum += first_pointer[0];
    sum += second_pointer[0];
    asm volatile(
        "clflush (%0);\n\t"
        "clflush (%1);\n\t"
        : : "r" (first_pointer), "r" (second_pointer) : "memory");
  }
  return sum;
}

typedef uint64_t(HammerFunction)(
    const std::pair<uint64_t, uint64_t>& first_range,
    const std::pair<uint64_t, uint64_t>& second_range,
    uint64_t number_of_reads);

// A comprehensive test that attempts to hammer adjacent rows for a given 
// assumed row size (and assumptions of sequential physical addresses for 
// various rows.
uint64_t HammerAllReachablePages(uint64_t presumed_row_size, 
    void* memory_mapping, uint64_t memory_mapping_size, HammerFunction* hammer,
    uint64_t number_of_reads) {
  // This vector will be filled with all the pages we can get access to for a
  // given row size.
  std::vector<std::vector<uint8_t*>> pages_per_row;
  uint64_t total_bitflips = 0;

  pages_per_row.resize(memory_mapping_size / presumed_row_size);
  int pagemap = open("/proc/self/pagemap", O_RDONLY);
  assert(pagemap >= 0);

  printf("[!] Identifying rows for accessible pages ... ");
  for (uint64_t offset = 0; offset < memory_mapping_size; offset += 0x1000) {
    uint8_t* virtual_address = static_cast<uint8_t*>(memory_mapping) + offset;
    uint64_t page_frame_number = GetPageFrameNumber(pagemap, virtual_address);
    uint64_t physical_address = page_frame_number * 0x1000;
    uint64_t presumed_row_index = physical_address / presumed_row_size;
    //printf("[!] put va %lx pa %lx into row %ld\n", (uint64_t)virtual_address,
    //    physical_address, presumed_row_index);
    if (presumed_row_index > pages_per_row.size()) {
      pages_per_row.resize(presumed_row_index);
    }
    pages_per_row[presumed_row_index].push_back(virtual_address);
    //printf("[!] done\n");
  }
  printf("Done\n");

  // We should have some pages for most rows now.
  for (uint64_t row_index = 0; row_index + 2 < pages_per_row.size(); 
      ++row_index) {
    if ((pages_per_row[row_index].size() != 64) || 
        (pages_per_row[row_index+2].size() != 64)) {
      printf("[!] Can‘t hammer row %ld - only got %ld/%ld pages "
          "in the rows above/below\n",
          row_index+1, pages_per_row[row_index].size(), 
          pages_per_row[row_index+2].size());
      continue;
    } else if (pages_per_row[row_index+1].size() == 0) {
      printf("[!] Can‘t hammer row %ld, got no pages from that row\n", 
          row_index+1);
      continue;
    }
    printf("[!] Hammering rows %ld/%ld/%ld of %ld (got %ld/%ld/%ld pages)\n", 
        row_index, row_index+1, row_index+2, pages_per_row.size(), 
        pages_per_row[row_index].size(), pages_per_row[row_index+1].size(), 
        pages_per_row[row_index+2].size());
    // Iterate over all pages we have for the first row.
    for (uint8_t* first_row_page : pages_per_row[row_index]) {
      // Iterate over all pages we have for the second row.
      for (uint8_t* second_row_page : pages_per_row[row_index+2]) {
        // Set all the target pages to 0xFF.
        for (uint8_t* target_page : pages_per_row[row_index+1]) {
          memset(target_page, 0xFF, 0x1000);
        }
        // Now hammer the two pages we care about.
        std::pair<uint64_t, uint64_t> first_page_range(
            reinterpret_cast<uint64_t>(first_row_page), 
            reinterpret_cast<uint64_t>(first_row_page+0x1000));
        std::pair<uint64_t, uint64_t> second_page_range(
            reinterpret_cast<uint64_t>(second_row_page),
            reinterpret_cast<uint64_t>(second_row_page+0x1000));
        hammer(first_page_range, second_page_range, number_of_reads);
        // Now check the target pages.
        uint64_t number_of_bitflips_in_target = 0;
        for (const uint8_t* target_page : pages_per_row[row_index+1]) {
          for (uint32_t index = 0; index < 0x1000; ++index) {
            if (target_page[index] != 0xFF) {
              ++number_of_bitflips_in_target;
            }
          }
        }
        if (number_of_bitflips_in_target > 0) {
          printf("[!] Found %ld flips in row %ld (%lx to %lx) when hammering "
              "%lx and %lx\n", number_of_bitflips_in_target, row_index+1,
              ((row_index+1)*presumed_row_size), 
              ((row_index+2)*presumed_row_size)-1,
              GetPageFrameNumber(pagemap, first_row_page)*0x1000, 
              GetPageFrameNumber(pagemap, second_row_page)*0x1000);
          total_bitflips += number_of_bitflips_in_target;
        }
      }
    }
  }
  return total_bitflips;
}

//Hammer所有可访问的物理内存行
void HammerAllReachableRows(HammerFunction* hammer, uint64_t number_of_reads) 
{
  uint64_t mapping_size;
  void* mapping;
  SetupMapping(&mapping_size, &mapping);

  HammerAllReachablePages(1024*256, mapping, mapping_size, hammer, number_of_reads);
}

void HammeredEnough(int sig) 
{
  printf("[!] Spent %ld seconds hammering, exiting now.\n", number_of_seconds_to_hammer);
  fflush(stdout);
  fflush(stderr);
  exit(0);
}

int main(int argc, char** argv) 
{
  // Turn off stdout buffering when it is a pipe.
  setvbuf(stdout, NULL, _IONBF, 0);

  int opt;
  while ((opt = getopt(argc, argv, "t:p:")) != -1) 
  {
    switch (opt) {
      case ‘t‘:
        number_of_seconds_to_hammer = atoi(optarg);
        break;
      case ‘p‘:
        fraction_of_physical_memory = atof(optarg);
        break;
      default:
        fprintf(stderr, "Usage: %s [-t nsecs] [-p percent]\n", argv[0]);
        exit(EXIT_FAILURE);
    }
  }

  signal(SIGALRM, HammeredEnough);

  printf("[!] Starting the testing process...\n");
  alarm(number_of_seconds_to_hammer);
  HammerAllReachableRows(&HammerAddressesStandard, number_of_reads);
}

http://en.wikipedia.org/wiki/Dynamic_random-access_memory 
http://users.ece.cmu.edu/~yoonguk/papers/kim-isca14.pdf
https://github.com/google/rowhammer-test
http://en.wikipedia.org/wiki/Row_hammer

1. Two times (2x) refresh
is a mitigation that has been commonly implemented on server based chipsets from Intel since the introduction of Sandy Bridge and is the suggested default. This reduces the row refresh time by the memory controller from 64ms to 32ms and shrinks the potential window for a row hammer, or other gate pass type memory error to be introduced.

2. Pseudo Target Row Refresh (pTRR)
available in modern memory and chipsets. pTRR does not introduce any performance and power impact.

3. Increased Patrol Scub timers
systems that are equipped with ECC memory will often have a BIOS option that allows the administrator to set an interval at which the CPU will utilize the checksum data stored on each ECC DIMM module to ensure that the contents of memory are valid, and correcting any bit errors that may have been introduced.  The number of correctable errors will vary based on architecture and ECC variant.  Administrator’s may consider reducing the patrol scrub timers from the standard 20 minute interval to a lower value.

http://www.ddrdetective.com/files/3314/1036/5702/Description_of_the_Row_Hammer_feature_on_the_FS2800_DDR_Detective.pdf
http://blogs.cisco.com/security/mitigations-available-for-the-dram-row-hammer-vulnerability