应用程序在运行过程中由于各种异常或者bug导致退出,在满足一定条件下产生一个core文件。
通常core文件包含了程序运行时内存、寄存器状态、堆栈指针、内存管理信息以及函数调用堆栈信息。
core就是程序当前工作转改存储生成的一个文件,通过工具分析这个文件,可以定位到程序异常退出的时候对应的堆栈调用等信息,找出问题点并解决。
如果需要使用需要通过ulimit进行设置,可以通过ulimit -c查看当前系统是否支持coredump。如果为0,则表示coredump被关闭。
通过ulimit -c unlimited可以打开coredump。
coredump文件默认存储位置与可执行文件在同一目录下,文件名为core。
可以通过/proc/sys/kernel/core_pattern进行设置。
%p 出Core进程的PID
%u 出Core进程的UID
%s 造成Core的signal号
%t 出Core的时间,从1970-01-0100:00:00开始的秒数
%e 出Core进程对应的可执行文件名
通过echo "core-%e-%p-%s-%t" > /proc/sys/kernel/core_pattern。
在每个进程下都有coredump_filter节点/proc/
通过配置coredump_filter可以选择需在coredump的时候,将哪些内容dump到core文件中。
- (bit 0) anonymous private memory
- (bit 1) anonymous shared memory
- (bit 2) file-backed private memory
- (bit 3) file-backed shared memory
- (bit 4) ELF header pages in file-backed private memory areas (it is effective only if the bit 2 is cleared)
- (bit 5) hugetlb private memory
- (bit 6) hugetlb shared memory
- (bit 7) DAX private memory
- (bit 8) DAX shared memory
coredump_filter的默认值是0x33,也即发生coredump时会将所有anonymous内存、ELF头页面、hugetlb private memory内容保存。
coredump_filter可以被子进程继承,可以echo 0xXX > /proc/self/coredump_filter设置当前进程的coredump_filter。
static ssize_t proc_coredump_filter_write(struct file *file,
const char __user *buf,
size_t count,
loff_t *ppos)
{
...
ret = kstrtouint_from_user(buf, count, 0, &val);-------------------------将buf转换成val值。
if (ret < 0)
return ret;
...
for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
if (val & mask)
set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);------------------将coredump_filter的值映射到mm->flags上,后续coredump时使用。
else
clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
}
...
}
其中MMF_DUMP_FILTER_SHIFT为2,所以flags和coredump_filter存在如下对应关系。
#define MMF_DUMP_ANON_PRIVATE 2
#define MMF_DUMP_ANON_SHARED 3
#define MMF_DUMP_MAPPED_PRIVATE 4
#define MMF_DUMP_MAPPED_SHARED 5
#define MMF_DUMP_ELF_HEADERS 6
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED 8
#define MMF_DUMP_DAX_PRIVATE 9
#define MMF_DUMP_DAX_SHARED 10
在do_signal()中根据信号判断是否触发coredump,当然还跟coredump limit、mm->flags等等相关。
满足coredump条件后,由do_coredump()进行coredump文件生成,核心是由binfmt->core_dump()进行的。
在内核返回用户空间的时候,会调用do_signal()处理信号。
static void do_signal(struct pt_regs *regs, int syscall)
{
unsigned int retval = 0, continue_addr = 0, restart_addr = 0;
struct ksignal ksig;
...
if (get_signal(&ksig)) {
...
}
...
}
int get_signal(struct ksignal *ksig)
{
...
for (;;) {
struct k_sigaction *ka;
...
signr = dequeue_signal(current, ¤t->blocked, &ksig->info);
...
/* Trace actually delivered signals. */
trace_signal_deliver(signr, &ksig->info, ka);
...
if (sig_kernel_coredump(signr)) {
if (print_fatal_signals)------------------------------可以通过kernel.print-fatal-signals = 1进行设置,对应的节点是/proc/sys/kernel/print-fatal-signals。
print_fatal_signal(ksig->info.si_signo);----------打印当前信号及当前场景的栈信息。
proc_coredump_connector(current);
do_coredump(&ksig->info);
}
...
}
spin_unlock_irq(&sighand->siglock);
ksig->sig = signr;
return ksig->sig > 0;
}
#define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK)
#define SIG_KERNEL_COREDUMP_MASK (\
rt_sigmask(SIGQUIT) | rt_sigmask(SIGILL) | \
rt_sigmask(SIGTRAP) | rt_sigmask(SIGABRT) | \
rt_sigmask(SIGFPE) | rt_sigmask(SIGSEGV) | \
rt_sigmask(SIGBUS) | rt_sigmask(SIGSYS) | \
rt_sigmask(SIGXCPU) | rt_sigmask(SIGXFSZ) | \
SIGEMT_MASK )
在get_signal()中,判断信号是否会导致coredump。这些信号包括SIGQUIT、SIGILL、SIGTRAP、SIGABRT、SIGFPE、SIGSEGV、SIGBUS、SIGSYS、SIGXCPU、SIGXFSZ。
“终止w/core”表示在进程当前工作目录的core文件中复制了该进程的存储图像(该文件名为core,由此可以看出这种功能很久之前就是UNIX功能的一部分)。
void proc_coredump_connector(struct task_struct *task)
{
struct cn_msg *msg;
struct proc_event *ev;
__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
memset(&ev->event_data, 0, sizeof(ev->event_data));
ev->timestamp_ns = ktime_get_ns();
ev->what = PROC_EVENT_COREDUMP;
ev->event_data.coredump.process_pid = task->pid;
ev->event_data.coredump.process_tgid = task->tgid;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
msg->flags = 0; /* not used */
send_msg(msg);
}
void do_coredump(const siginfo_t *siginfo)
{
struct core_state core_state;
struct core_name cn;
struct mm_struct *mm = current->mm;
struct linux_binfmt * binfmt;
const struct cred *old_cred;
struct cred *cred;
int retval = 0;
int ispipe;
struct files_struct *displaced;
/* require nonrelative corefile path and be extra careful */
bool need_suid_safe = false;
bool core_dumped = false;
static atomic_t core_dump_count = ATOMIC_INIT(0);
struct coredump_params cprm = {
.siginfo = siginfo,
.regs = signal_pt_regs(),
.limit = rlimit(RLIMIT_CORE),-----------------------------------获取系统对于coredump的限制。
/*
* We must use the same mm->flags while dumping core to avoid
* inconsistency of bit flags, since this flag is not protected
* by any locks.
*/
.mm_flags = mm->flags,
};
audit_core_dumps(siginfo->si_signo);
binfmt = mm->binfmt;------------------------------------------------获取当前进程所使用的程序加载器。
if (!binfmt || !binfmt->core_dump)
goto fail;
if (!__get_dumpable(cprm.mm_flags))---------------------------------从当前进程的mm->flags中取低两位判断是否可以coredump,SUID_DUMP_DISABLE(0)不可以,其他情况都可以。
goto fail;
cred = prepare_creds();
if (!cred)
goto fail;
/*
* We cannot trust fsuid as being the "true" uid of the process
* nor do we know its entire history. We only know it was tainted
* so we dump it as root in mode 2, and only into a controlled
* environment (pipe handler or fully qualified path).
*/
if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) {--------------区分SUID_DUMP_USER和SUID_DUMP_ROOT。
/* Setuid core dump mode */
cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */
need_suid_safe = true;
}
retval = coredump_wait(siginfo->si_signo, &core_state);
if (retval < 0)
goto fail_creds;
old_cred = override_creds(cred);
ispipe = format_corename(&cn, &cprm);-------------------------------根据core_pattern判断是否是ispipe,然后根据core_pattern的设置生成coredump文件名称。
if (ispipe) {-------------------------------------------------------通过管道处理coredump信息。
int dump_count;
char **helper_argv;
struct subprocess_info *sub_info;
if (ispipe < 0) {
printk(KERN_WARNING "format_corename failed\n");
printk(KERN_WARNING "Aborting core\n");
goto fail_unlock;
}
if (cprm.limit == 1) {
printk(KERN_WARNING
"Process %d(%s) has RLIMIT_CORE set to 1\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Aborting core\n");
goto fail_unlock;
}
cprm.limit = RLIM_INFINITY;
dump_count = atomic_inc_return(&core_dump_count);
if (core_pipe_limit && (core_pipe_limit < dump_count)) {
printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Skipping core dump\n");
goto fail_dropcount;
}
helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL);----------将cn.corename参数进行拆分。
if (!helper_argv) {
printk(KERN_WARNING "%s failed to allocate memory\n",
__func__);
goto fail_dropcount;
}
retval = -ENOMEM;
sub_info = call_usermodehelper_setup(helper_argv[0],
helper_argv, NULL, GFP_KERNEL,
umh_pipe_setup, NULL, &cprm);---------------------通过usermodehelper调用用户空间的helper_argv[0]程序进行core_pattern。
if (sub_info)
retval = call_usermodehelper_exec(sub_info,
UMH_WAIT_EXEC);-----------------------------UMH_WAIT_EXEC表示在内核exec用户空间程序之后就退出,此时用户空间程序就通过pipe等待接收数据。
argv_free(helper_argv);
if (retval) {
printk(KERN_INFO "Core dump to |%s pipe failed\n",
cn.corename);
goto close_fail;
}
} else {
struct inode *inode;
int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
O_LARGEFILE | O_EXCL;
if (cprm.limit < binfmt->min_coredump)
goto fail_unlock;
if (need_suid_safe && cn.corename[0] != '/') {
printk(KERN_WARNING "Pid %d(%s) can only dump core "\
"to fully qualified path!\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Skipping core dump\n");
goto fail_unlock;
}
if (!need_suid_safe) {
mm_segment_t old_fs;
old_fs = get_fs();
set_fs(KERNEL_DS);
/*
* If it doesn't exist, that's fine. If there's some
* other problem, we'll catch it at the filp_open().
*/
(void) sys_unlink((const char __user *)cn.corename);
set_fs(old_fs);
}
if (need_suid_safe) {---------------------------------------------创建coredump文件。
struct path root;
task_lock(&init_task);
get_fs_root(init_task.fs, &root);
task_unlock(&init_task);
cprm.file = file_open_root(root.dentry, root.mnt,
cn.corename, open_flags, 0600);
path_put(&root);
} else {
cprm.file = filp_open(cn.corename, open_flags, 0600);
}
if (IS_ERR(cprm.file))
goto fail_unlock;
inode = file_inode(cprm.file);
if (inode->i_nlink > 1)------------------------------------------coredummp文件不能有多个硬链接。
goto close_fail;
if (d_unhashed(cprm.file->f_path.dentry))
goto close_fail;
if (!S_ISREG(inode->i_mode))--------------------------------------coredump文件必须为普通文件。
goto close_fail;
if (!uid_eq(inode->i_uid, current_fsuid()))
goto close_fail;
if ((inode->i_mode & 0677) != 0600)
goto close_fail;
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))-----------------------coredump文件必须可写。
goto close_fail;
if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
goto close_fail;
}
/* get us an unshared descriptor table; almost always a no-op */
retval = unshare_files(&displaced);
if (retval)
goto close_fail;
if (displaced)
put_files_struct(displaced);
if (!dump_interrupted()) {
file_start_write(cprm.file);
core_dumped = binfmt->core_dump(&cprm);---------------------------调用对应程序加载器的core_dump进行处理,将数据写入到cprm.file中。
file_end_write(cprm.file);
}
if (ispipe && core_pipe_limit)
wait_for_dump_helpers(cprm.file);
close_fail:
if (cprm.file)
filp_close(cprm.file, NULL);
fail_dropcount:
if (ispipe)
atomic_dec(&core_dump_count);
fail_unlock:
kfree(cn.corename);
coredump_finish(mm, core_dumped);
revert_creds(old_cred);
fail_creds:
put_cred(cred);
fail:
return;
}
format_corename()根据core_pattern中的设置,生成coredump文件名。并且判断coredump文件生成方式,ispipe为真则通过管道传输给其他应用处理;否则直接保存成文件。
static int format_corename(struct core_name *cn, struct coredump_params *cprm)
{
const struct cred *cred = current_cred();
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');------------------------------------------|表示通过pipe处理coredump文件。
int pid_in_pattern = 0;
int err = 0;
cn->used = 0;
cn->corename = NULL;
if (expand_corename(cn, core_name_size))
return -ENOMEM;
cn->corename[0] = '\0';
if (ispipe)
++pat_ptr;
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
if (*pat_ptr != '%') {
err = cn_printf(cn, "%c", *pat_ptr++);
} else {
switch (*++pat_ptr) {
/* single % at the end, drop that */
case 0:
goto out;
/* Double percent, output one percent */
case '%':
err = cn_printf(cn, "%c", '%');
break;
/* pid */
case 'p':
pid_in_pattern = 1;
err = cn_printf(cn, "%d",
task_tgid_vnr(current));-------------------------%p表示记录当前进程组的pid。
break;
/* global pid */
case 'P':-------------------------------------------------------%P表示记录当前进程组的pid。
err = cn_printf(cn, "%d",
task_tgid_nr(current));
break;
case 'i':
err = cn_printf(cn, "%d",
task_pid_vnr(current));--------------------------%i表示记录当前线程的pid。
break;
case 'I':------------------------------------------------------%I表示记录当前线程的pid。
err = cn_printf(cn, "%d",
task_pid_nr(current));
break;
/* uid */
case 'u':-------------------------------------------------------%u表示当前用户id。
err = cn_printf(cn, "%u",
from_kuid(&init_user_ns,
cred->uid));
break;
/* gid */
case 'g':-------------------------------------------------------%g表示group id。
err = cn_printf(cn, "%u",
from_kgid(&init_user_ns,
cred->gid));
break;
case 'd':
err = cn_printf(cn, "%d",
__get_dumpable(cprm->mm_flags));------------------------%d表示dump的用户类型:SUID_DUMP_DISABLE/SUID_DUMP_USER/SUID_DUMP_ROOT。
break;
/* signal that caused the coredump */
case 's':
err = cn_printf(cn, "%d",
cprm->siginfo->si_signo);----------------------------%s记录产生coredump的信号。
break;
/* UNIX time of coredump */
case 't': {
time64_t time;
time = ktime_get_real_seconds();
err = cn_printf(cn, "%lld", time);---------------------------%t记录产生coredump的时间。
break;
}
/* hostname */
case 'h':--------------------------------------------------------%h记录主机名。
down_read(&uts_sem);
err = cn_esc_printf(cn, "%s",
utsname()->nodename);
up_read(&uts_sem);
break;
/* executable */
case 'e':
err = cn_esc_printf(cn, "%s", current->comm);----------------%e记录进程中comm名称。
break;
case 'E':
err = cn_print_exe_file(cn);---------------------------------%E记录可执行文件名称。
break;
/* core limit size */
case 'c':
err = cn_printf(cn, "%lu",
rlimit(RLIMIT_CORE));------------------------------%c记录coredump的limit值。
break;
default:
break;
}
++pat_ptr;
}
if (err)
return err;
}
out:
if (!ispipe && !pid_in_pattern && core_uses_pid) {
err = cn_printf(cn, ".%d", task_tgid_vnr(current));
if (err)
return err;
}
return ispipe;
}
所以core_%e(%I)_%E(%p)_sig(%s)_time(%t)写入到core_pattern表示core_线程名(线程pid)_进程名(进程pid)_sig(信号值)_time(异常时间点)。
umh_pipe_setup()创建了一个管道,这个管道给内核coredump和用户空间程序搭建了一个桥梁。
内核coredump的数据写入管道,用户空间程序在管道另一端接收进行处理。
static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
{
struct file *files[2];
struct coredump_params *cp = (struct coredump_params *)info->data;
int err = create_pipe_files(files, 0);----------------------------创建一个pipe管道,files[0]是管道的读端;files[1]是管道的写端。
if (err)
return err;
cp->file = files[1];----------------------------------------------cp->file指向管道的写端,后面coredump写入这里。
err = replace_fd(0, files[0], 0);---------------------------------这里将files[0]作为usermodehelper执行程序的输入,coredump的数据通过管道给用户空间程序接收。
fput(files[0]);
/* and disallow core files too */
current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
return err;
}
int create_pipe_files(struct file **res, int flags)
{
int err;
struct inode *inode = get_pipe_inode();
struct file *f;
struct path path;
static struct qstr name = { .name = "" };
if (!inode)
return -ENFILE;
err = -ENOMEM;
path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name);
if (!path.dentry)
goto err_inode;
path.mnt = mntget(pipe_mnt);
d_instantiate(path.dentry, inode);
f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);------------------------创建管道的写一端。
if (IS_ERR(f)) {
err = PTR_ERR(f);
goto err_dentry;
}
f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
f->private_data = inode->i_pipe;
res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);--------------------创建管道的读一端。
if (IS_ERR(res[0])) {
err = PTR_ERR(res[0]);
goto err_file;
}
path_get(&path);
res[0]->private_data = inode->i_pipe;
res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
res[1] = f;
return 0;
err_file:
put_filp(f);
err_dentry:
free_pipe_info(inode->i_pipe);
path_put(&path);
return err;
err_inode:
free_pipe_info(inode->i_pipe);
iput(inode);
return err;
}
int replace_fd(unsigned fd, struct file *file, unsigned flags)
{
int err;
struct files_struct *files = current->files;
if (!file)
return __close_fd(files, fd);
if (fd >= rlimit(RLIMIT_NOFILE))
return -EBADF;
spin_lock(&files->file_lock);
err = expand_files(files, fd);
if (unlikely(err < 0))
goto out_unlock;
return do_dup2(files, file, fd, flags);
out_unlock:
spin_unlock(&files->file_lock);
return err;
}
linux内核支持多种linux_binfmt,这里最常用的是ELF。
所以do_coredump()中的binfmt即为elf_format,binfmt->core_dump()即为elf_coredump()。
elf_core_dump()将当前进程的vma区域进行dummp,附加相关的头信息等。保存成文件。
static struct linux_binfmt elf_format = {
.module = THIS_MODULE,
.load_binary = load_elf_binary,
.load_shlib = load_elf_library,
.core_dump = elf_core_dump,
.min_coredump = ELF_EXEC_PAGESIZE,
};
static int elf_core_dump(struct coredump_params *cprm)
{
int has_dumped = 0;
mm_segment_t fs;
int segs, i;
size_t vma_data_size = 0;
struct vm_area_struct *vma, *gate_vma;
struct elfhdr *elf = NULL;
loff_t offset = 0, dataoff;
struct elf_note_info info = { };
struct elf_phdr *phdr4note = NULL;
struct elf_shdr *shdr4extnum = NULL;
Elf_Half e_phnum;
elf_addr_t e_shoff;
elf_addr_t *vma_filesz = NULL;
elf = kmalloc(sizeof(*elf), GFP_KERNEL);-----------------------申请存放elfhdr空间。
if (!elf)
goto out;
segs = current->mm->map_count;---------------------------------通过current->mm->map_count得到当前进程已映射的内存段数量。
segs += elf_core_extra_phdrs();--------------------------------增加附加段数量。
gate_vma = get_gate_vma(current->mm);--------------------------增加一个segment给vma使用。
if (gate_vma != NULL)
segs++;
/* for notes section */
segs++;--------------------------------------------------------保留一个segment给PT_NOTE使用。
/* If segs > PN_XNUM(0xffff), then e_phnum overflows. To avoid
* this, kernel supports extended numbering. Have a look at
* include/linux/elf.h for further information. */
e_phnum = segs > PN_XNUM ? PN_XNUM : segs;
/*
* Collect all the non-memory information about the process for the
* notes. This also sets up the file header.
*/
if (!fill_note_info(elf, e_phnum, &info, cprm->siginfo, cprm->regs))-----fill_note_info()填充info信息。
goto cleanup;
has_dumped = 1;
fs = get_fs();
set_fs(KERNEL_DS);------------------------------------------------------在内核中操作用户空间文件,需要将地址方位扩大。具体参见《Linux内核访问用户空间文件:get_fs()/set_fs()的使用》
offset += sizeof(*elf); /* Elf header */
offset += segs * sizeof(struct elf_phdr); /* Program headers */
/* Write notes phdr entry */
{
size_t sz = get_note_info_size(&info);
sz += elf_coredump_extra_notes_size();
phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL);
if (!phdr4note)
goto end_coredump;
fill_elf_note_phdr(phdr4note, sz, offset);
offset += sz;
}
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
vma_filesz = kmalloc_array(segs - 1, sizeof(*vma_filesz), GFP_KERNEL);
if (!vma_filesz)
goto end_coredump;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
unsigned long dump_size;
dump_size = vma_dump_size(vma, cprm->mm_flags);----------------------mm_flags对应coredump_filter,用于确定哪些vma需要dump,哪些忽略掉。
vma_filesz[i++] = dump_size;
vma_data_size += dump_size;
}
offset += vma_data_size;
offset += elf_core_extra_data_size();
e_shoff = offset;
if (e_phnum == PN_XNUM) {
shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
if (!shdr4extnum)
goto end_coredump;
fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
}
offset = dataoff;
if (!dump_emit(cprm, elf, sizeof(*elf)))---------------------------写入elf头到cprm->file文件,在使用pipe的情况下,这些数据都交给usermodehelper启动的用户空间程序进行处理。
goto end_coredump;
if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))---------------写入phdr4node到cprm->file文件。
goto end_coredump;
/* Write program headers for segments dump */
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
struct elf_phdr phdr;
phdr.p_type = PT_LOAD;
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
phdr.p_filesz = vma_filesz[i++];
phdr.p_memsz = vma->vm_end - vma->vm_start;
offset += phdr.p_filesz;
phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
if (vma->vm_flags & VM_WRITE)
phdr.p_flags |= PF_W;
if (vma->vm_flags & VM_EXEC)
phdr.p_flags |= PF_X;
phdr.p_align = ELF_EXEC_PAGESIZE;
if (!dump_emit(cprm, &phdr, sizeof(phdr)))
goto end_coredump;
}
if (!elf_core_write_extra_phdrs(cprm, offset))
goto end_coredump;
/* write out the notes section */
if (!write_note_info(&info, cprm))
goto end_coredump;
if (elf_coredump_extra_notes_write(cprm))
goto end_coredump;
/* Align to page */
if (!dump_skip(cprm, dataoff - cprm->pos))
goto end_coredump;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
unsigned long addr;
unsigned long end;
end = vma->vm_start + vma_filesz[i++];
for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
struct page *page;
int stop;
page = get_dump_page(addr);
if (page) {
void *kaddr = kmap(page);
stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
kunmap(page);
put_page(page);
} else
stop = !dump_skip(cprm, PAGE_SIZE);
if (stop)
goto end_coredump;
}
}
dump_truncate(cprm);
if (!elf_core_write_extra_data(cprm))
goto end_coredump;
if (e_phnum == PN_XNUM) {
if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum)))
goto end_coredump;
}
end_coredump:
set_fs(fs);
cleanup:
free_note_info(&info);
kfree(shdr4extnum);
kfree(vma_filesz);
kfree(phdr4note);
kfree(elf);
out:
return has_dumped;
}
int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
{
struct file *file = cprm->file;
loff_t pos = file->f_pos;
ssize_t n;
if (cprm->written + nr > cprm->limit)
return 0;
while (nr) {
if (dump_interrupted())
return 0;
n = __kernel_write(file, addr, nr, &pos);
if (n <= 0)
return 0;
file->f_pos = pos;
cprm->written += n;
cprm->pos += n;
nr -= n;
}
return 1;
}
判断一个文件是否是coredump文件,可以通过readelf命令,如果类型是CORE(Core file)。
或者通过file命令进行判断。
参考文档:《Core file 文件格式(Linux Coredump文件结构)》,GDB解析coredump文件参考《GDB如何从Coredump文件恢复动态库信息》。
下面创建一个简单产生coredump的示例,然后通过gdb进行分析。
#include
#include
#include
#include
int myfunc(int i) {
*(int*)(NULL) = i; /* line 7 */
return i - 1;
}
int main(int argc, char **argv) {
/* Setup some memory. */
char data_ptr[] = "string in data segment";
char *mmap_ptr;
char *text_ptr = "string in text segment";
(void)argv;
mmap_ptr = (char *)malloc(sizeof(data_ptr) + 1);
strcpy(mmap_ptr, data_ptr);
mmap_ptr[10] = 'm';
mmap_ptr[11] = 'm';
mmap_ptr[12] = 'a';
mmap_ptr[13] = 'p';
printf("text addr: %p\n", text_ptr);
printf("data addr: %p\n", data_ptr);
printf("mmap addr: %p\n", mmap_ptr);
/* Call a function to prepare a stack trace. */
return myfunc(argc);
}
使用如下命令编译,-ggdb3表示产生更多适合GDB的调试信息,3是最高等级。
gcc -ggdb3 -std=c99 -Wall -Wextra -pedantic -o main.out main.c
通过ulimit -c unlimited打开coredump功能,执行./main.out产生core文件。
text addr: 0x4007d4
data addr: 0x7ffff28fdc30
mmap addr: 0x10bb010
Segmentation fault (core dumped)
通过gdb ./main.out core,显示了进程由于什么信号导致的coredump(SIGSEGV)?在哪个文件(main.cc)?在哪个函数(myfunc())?具体位置的代码?等等信息。
GNU gdb (Ubuntu 7.11.1-0ubuntu1~16.5) 7.11.1...
Reading symbols from ./main.out...done.
[New LWP 8651]
Core was generated by `./main.out'.
Program terminated with signal SIGSEGV, Segmentation fault.
#0 0x0000000000400635 in myfunc (i=1) at main.c:7
7 *(int*)(NULL) = i; /* line 7 */
关于core+gdb更详细的分析方法可以参考《通过core+gdb离线分析》,在分析过程中需要加载动态库可以参考《GDB动态库搜索路径》。
在/etc/profile中,打开对coredump的配置以及对core_pattern进行配置:
sysctl -p -q -e
ulimit -c unlimited
配置/etc/sysctl.conf文件:
kernel.core_pattern=|/usr/bin/coredump_helper.sh core_%e_%I_%p_sig_%s_time_%t.gz
kernel.core_uses_pid=1
增加处理coredump文件的脚本:
#!/bin/sh
if [ ! -d "/var/coredump" ];then
mkdir -p /var/coredump
fi
gzip > "/var/coredump/$1"
最终在/var/coredump目录下生成core_<线程名>_<线程ID>_<进程ID>_sig_<信号值>_time_
至此大概总结了,对coredump的设置(ulimit/core_pattern/coredump_filter)?触发coredump的条件(SIG_KERNEL_COREDUMP_MASK )?coredump生成core文件流程(do_coredump())?gdb如何识别core文件(《GDB如何从Coredump文件恢复动态库信息》)?如何通过gdb分析core文件发现问题(gdb->backtrace)?