static int expand_corename(struct core_name *cn, int size)
{
- char *corename = krealloc(cn->corename, size, GFP_KERNEL);
+ char *corename;
+
+ size = kmalloc_size_roundup(size);
+ corename = krealloc(cn->corename, size, GFP_KERNEL);
if (!corename)
return -ENOMEM;
if (size > core_name_size) /* racy but harmless */
core_name_size = size;
- cn->size = ksize(corename);
+ cn->size = size;
cn->corename = corename;
return 0;
}
err = cn_printf(cn, "%lu",
rlimit(RLIMIT_CORE));
break;
+ /* CPU the task ran on */
+ case 'C':
+ err = cn_printf(cn, "%d", cprm->cpu);
+ break;
default:
break;
}
struct task_struct *t;
int nr = 0;
- /* ignore all signals except SIGKILL, see prepare_signal() */
+ /* Allow SIGKILL, see prepare_signal() */
start->signal->flags = SIGNAL_GROUP_EXIT;
start->signal->group_exit_code = exit_code;
start->signal->group_stop_count = 0;
if (t != current && !(t->flags & PF_POSTCOREDUMP)) {
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
- nr++;
+ /* The vhost_worker does not particpate in coredumps */
+ if ((t->flags & (PF_USER_WORKER | PF_IO_WORKER)) != PF_USER_WORKER)
+ nr++;
}
}
if (core_waiters > 0) {
struct core_thread *ptr;
- freezer_do_not_count();
- wait_for_completion(&core_state->startup);
- freezer_count();
+ wait_for_completion_state(&core_state->startup,
+ TASK_UNINTERRUPTIBLE|TASK_FREEZABLE);
/*
* Wait for all the threads to become inactive, so that
* all the thread context (extended register state, like
*/
ptr = core_state->dumper.next;
while (ptr != NULL) {
- wait_task_inactive(ptr->task, 0);
+ wait_task_inactive(ptr->task, TASK_ANY);
ptr = ptr->next;
}
}
static atomic_t core_dump_count = ATOMIC_INIT(0);
struct coredump_params cprm = {
.siginfo = siginfo,
- .regs = signal_pt_regs(),
.limit = rlimit(RLIMIT_CORE),
/*
* We must use the same mm->flags while dumping core to avoid
*/
.mm_flags = mm->flags,
.vma_meta = NULL,
+ .cpu = raw_smp_processor_id(),
};
audit_core_dumps(siginfo->si_signo);
goto close_fail;
}
} else {
- struct user_namespace *mnt_userns;
+ struct mnt_idmap *idmap;
struct inode *inode;
- int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
+ int open_flags = O_CREAT | O_WRONLY | O_NOFOLLOW |
O_LARGEFILE | O_EXCL;
if (cprm.limit < binfmt->min_coredump)
* a process dumps core while its cwd is e.g. on a vfat
* filesystem.
*/
- mnt_userns = file_mnt_user_ns(cprm.file);
- if (!uid_eq(i_uid_into_mnt(mnt_userns, inode),
- current_fsuid())) {
+ idmap = file_mnt_idmap(cprm.file);
+ if (!vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode),
+ current_fsuid())) {
pr_info_ratelimited("Core dump to %s aborted: cannot preserve file owner\n",
cn.corename);
goto close_fail;
}
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
- if (do_truncate(mnt_userns, cprm.file->f_path.dentry,
+ if (do_truncate(idmap, cprm.file->f_path.dentry,
0, 0, cprm.file))
goto close_fail;
}
EXPORT_SYMBOL(dump_skip);
#ifdef CONFIG_ELF_CORE
+static int dump_emit_page(struct coredump_params *cprm, struct page *page)
+{
+ struct bio_vec bvec;
+ struct iov_iter iter;
+ struct file *file = cprm->file;
+ loff_t pos;
+ ssize_t n;
+
+ if (!page)
+ return 0;
+
+ if (cprm->to_skip) {
+ if (!__dump_skip(cprm, cprm->to_skip))
+ return 0;
+ cprm->to_skip = 0;
+ }
+ if (cprm->written + PAGE_SIZE > cprm->limit)
+ return 0;
+ if (dump_interrupted())
+ return 0;
+ pos = file->f_pos;
+ bvec_set_page(&bvec, page, PAGE_SIZE, 0);
+ iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE);
+ n = __kernel_write_iter(cprm->file, &iter, &pos);
+ if (n != PAGE_SIZE)
+ return 0;
+ file->f_pos = pos;
+ cprm->written += PAGE_SIZE;
+ cprm->pos += PAGE_SIZE;
+
+ return 1;
+}
+
+/*
+ * If we might get machine checks from kernel accesses during the
+ * core dump, let's get those errors early rather than during the
+ * IO. This is not performance-critical enough to warrant having
+ * all the machine check logic in the iovec paths.
+ */
+#ifdef copy_mc_to_kernel
+
+#define dump_page_alloc() alloc_page(GFP_KERNEL)
+#define dump_page_free(x) __free_page(x)
+static struct page *dump_page_copy(struct page *src, struct page *dst)
+{
+ void *buf = kmap_local_page(src);
+ size_t left = copy_mc_to_kernel(page_address(dst), buf, PAGE_SIZE);
+ kunmap_local(buf);
+ return left ? NULL : dst;
+}
+
+#else
+
+/* We just want to return non-NULL; it's never used. */
+#define dump_page_alloc() ERR_PTR(-EINVAL)
+#define dump_page_free(x) ((void)(x))
+static inline struct page *dump_page_copy(struct page *src, struct page *dst)
+{
+ return src;
+}
+#endif
+
int dump_user_range(struct coredump_params *cprm, unsigned long start,
unsigned long len)
{
unsigned long addr;
+ struct page *dump_page;
+
+ dump_page = dump_page_alloc();
+ if (!dump_page)
+ return 0;
for (addr = start; addr < start + len; addr += PAGE_SIZE) {
struct page *page;
- int stop;
/*
* To avoid having to allocate page tables for virtual address
*/
page = get_dump_page(addr);
if (page) {
- void *kaddr = kmap_local_page(page);
-
- stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
- kunmap_local(kaddr);
+ int stop = !dump_emit_page(cprm, dump_page_copy(page, dump_page));
put_page(page);
- if (stop)
+ if (stop) {
+ dump_page_free(dump_page);
return 0;
+ }
} else {
dump_skip(cprm, PAGE_SIZE);
}
}
+ dump_page_free(dump_page);
return 1;
}
#endif
.mode = 0644,
.proc_handler = proc_dointvec,
},
- { }
};
static int __init init_fs_coredump_sysctls(void)
return vma->vm_end - vma->vm_start;
}
-static struct vm_area_struct *first_vma(struct task_struct *tsk,
- struct vm_area_struct *gate_vma)
-{
- struct vm_area_struct *ret = tsk->mm->mmap;
-
- if (ret)
- return ret;
- return gate_vma;
-}
-
/*
* Helper function for iterating across a vma list. It ensures that the caller
* will visit `gate_vma' prior to terminating the search.
*/
-static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
+static struct vm_area_struct *coredump_next_vma(struct vma_iterator *vmi,
+ struct vm_area_struct *vma,
struct vm_area_struct *gate_vma)
{
- struct vm_area_struct *ret;
-
- ret = this_vma->vm_next;
- if (ret)
- return ret;
- if (this_vma == gate_vma)
+ if (gate_vma && (vma == gate_vma))
return NULL;
+
+ vma = vma_next(vmi);
+ if (vma)
+ return vma;
return gate_vma;
}
*/
static bool dump_vma_snapshot(struct coredump_params *cprm)
{
- struct vm_area_struct *vma, *gate_vma;
+ struct vm_area_struct *gate_vma, *vma = NULL;
struct mm_struct *mm = current->mm;
- int i;
+ VMA_ITERATOR(vmi, mm, 0);
+ int i = 0;
/*
* Once the stack expansion code is fixed to not change VMA bounds
return false;
}
- for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
- vma = next_vma(vma, gate_vma), i++) {
+ while ((vma = coredump_next_vma(&vmi, vma, gate_vma)) != NULL) {
struct core_vma_metadata *m = cprm->vma_meta + i;
m->start = vma->vm_start;
m->flags = vma->vm_flags;
m->dump_size = vma_dump_size(vma, cprm->mm_flags);
m->pgoff = vma->vm_pgoff;
-
m->file = vma->vm_file;
if (m->file)
get_file(m->file);
+ i++;
}
mmap_write_unlock(mm);