1 files changed, 225 insertions, 11 deletions

diff --git a/fs/coredump.c b/fs/coredump.c
index 76e7c10edfc0..0cd9056d79cc 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -840,17 +840,17 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 	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;
-	}
+
+
+	if (dump_interrupted())
+		return 0;
+	n = __kernel_write(file, addr, nr, &pos);
+	if (n != nr)
+		return 0;
+	file->f_pos = pos;
+	cprm->written += n;
+	cprm->pos += n;
+
 	return 1;
 }
 EXPORT_SYMBOL(dump_emit);
@@ -876,6 +876,40 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
 }
 EXPORT_SYMBOL(dump_skip);
 
+#ifdef CONFIG_ELF_CORE
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+		    unsigned long len)
+{
+	unsigned long addr;
+
+	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
+		struct page *page;
+		int stop;
+
+		/*
+		 * To avoid having to allocate page tables for virtual address
+		 * ranges that have never been used yet, and also to make it
+		 * easy to generate sparse core files, use a helper that returns
+		 * NULL when encountering an empty page table entry that would
+		 * otherwise have been filled with the zero page.
+		 */
+		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)
+			return 0;
+	}
+	return 1;
+}
+#endif
+
 int dump_align(struct coredump_params *cprm, int align)
 {
 	unsigned mod = cprm->pos & (align - 1);
@@ -902,3 +936,183 @@ void dump_truncate(struct coredump_params *cprm)
 	}
 }
 EXPORT_SYMBOL(dump_truncate);
+
+/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+	/* Any vsyscall mappings? */
+	if (vma == get_gate_vma(vma->vm_mm))
+		return true;
+
+	/*
+	 * Assume that all vmas with a .name op should always be dumped.
+	 * If this changes, a new vm_ops field can easily be added.
+	 */
+	if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
+		return true;
+
+	/*
+	 * arch_vma_name() returns non-NULL for special architecture mappings,
+	 * such as vDSO sections.
+	 */
+	if (arch_vma_name(vma))
+		return true;
+
+	return false;
+}
+
+/*
+ * Decide how much of @vma's contents should be included in a core dump.
+ */
+static unsigned long vma_dump_size(struct vm_area_struct *vma,
+				   unsigned long mm_flags)
+{
+#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
+
+	/* always dump the vdso and vsyscall sections */
+	if (always_dump_vma(vma))
+		goto whole;
+
+	if (vma->vm_flags & VM_DONTDUMP)
+		return 0;
+
+	/* support for DAX */
+	if (vma_is_dax(vma)) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
+			goto whole;
+		return 0;
+	}
+
+	/* Hugetlb memory check */
+	if (is_vm_hugetlb_page(vma)) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+			goto whole;
+		return 0;
+	}
+
+	/* Do not dump I/O mapped devices or special mappings */
+	if (vma->vm_flags & VM_IO)
+		return 0;
+
+	/* By default, dump shared memory if mapped from an anonymous file. */
+	if (vma->vm_flags & VM_SHARED) {
+		if (file_inode(vma->vm_file)->i_nlink == 0 ?
+		    FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
+			goto whole;
+		return 0;
+	}
+
+	/* Dump segments that have been written to.  */
+	if ((!IS_ENABLED(CONFIG_MMU) || vma->anon_vma) && FILTER(ANON_PRIVATE))
+		goto whole;
+	if (vma->vm_file == NULL)
+		return 0;
+
+	if (FILTER(MAPPED_PRIVATE))
+		goto whole;
+
+	/*
+	 * If this is the beginning of an executable file mapping,
+	 * dump the first page to aid in determining what was mapped here.
+	 */
+	if (FILTER(ELF_HEADERS) &&
+	    vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ) &&
+	    (READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0)
+		return PAGE_SIZE;
+
+#undef	FILTER
+
+	return 0;
+
+whole:
+	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,
+				       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)
+		return NULL;
+	return gate_vma;
+}
+
+/*
+ * Under the mmap_lock, take a snapshot of relevant information about the task's
+ * VMAs.
+ */
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+		      struct core_vma_metadata **vma_meta,
+		      size_t *vma_data_size_ptr)
+{
+	struct vm_area_struct *vma, *gate_vma;
+	struct mm_struct *mm = current->mm;
+	int i;
+	size_t vma_data_size = 0;
+
+	/*
+	 * Once the stack expansion code is fixed to not change VMA bounds
+	 * under mmap_lock in read mode, this can be changed to take the
+	 * mmap_lock in read mode.
+	 */
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	gate_vma = get_gate_vma(mm);
+	*vma_count = mm->map_count + (gate_vma ? 1 : 0);
+
+	*vma_meta = kvmalloc_array(*vma_count, sizeof(**vma_meta), GFP_KERNEL);
+	if (!*vma_meta) {
+		mmap_write_unlock(mm);
+		return -ENOMEM;
+	}
+
+	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
+			vma = next_vma(vma, gate_vma), i++) {
+		struct core_vma_metadata *m = (*vma_meta) + i;
+
+		m->start = vma->vm_start;
+		m->end = vma->vm_end;
+		m->flags = vma->vm_flags;
+		m->dump_size = vma_dump_size(vma, cprm->mm_flags);
+
+		vma_data_size += m->dump_size;
+	}
+
+	mmap_write_unlock(mm);
+
+	if (WARN_ON(i != *vma_count))
+		return -EFAULT;
+
+	*vma_data_size_ptr = vma_data_size;
+	return 0;
+}