1 files changed, 20 insertions, 3 deletions

diff --git a/mm/mremap.c b/mm/mremap.c
index cd8a1b199ef9..cfec004c4ff9 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -152,6 +152,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	new_ptl = pte_lockptr(mm, new_pmd);
 	if (new_ptl != old_ptl)
 		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 
 	for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
@@ -222,7 +223,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
 		if (!new_pmd)
 			break;
-		if (pmd_trans_huge(*old_pmd)) {
+		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd)) {
 			if (extent == HPAGE_PMD_SIZE) {
 				bool moved;
 				/* See comment in move_ptes() */
@@ -383,6 +384,19 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 	if (!vma || vma->vm_start > addr)
 		return ERR_PTR(-EFAULT);
 
+	/*
+	 * !old_len is a special case where an attempt is made to 'duplicate'
+	 * a mapping.  This makes no sense for private mappings as it will
+	 * instead create a fresh/new mapping unrelated to the original.  This
+	 * is contrary to the basic idea of mremap which creates new mappings
+	 * based on the original.  There are no known use cases for this
+	 * behavior.  As a result, fail such attempts.
+	 */
+	if (!old_len && !(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) {
+		pr_warn_once("%s (%d): attempted to duplicate a private mapping with mremap.  This is not supported.\n", current->comm, current->pid);
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (is_vm_hugetlb_page(vma))
 		return ERR_PTR(-EINVAL);
 
@@ -428,6 +442,7 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 		unsigned long new_addr, unsigned long new_len, bool *locked,
 		struct vm_userfaultfd_ctx *uf,
+		struct list_head *uf_unmap_early,
 		struct list_head *uf_unmap)
 {
 	struct mm_struct *mm = current->mm;
@@ -446,7 +461,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	if (addr + old_len > new_addr && new_addr + new_len > addr)
 		goto out;
 
-	ret = do_munmap(mm, new_addr, new_len, NULL);
+	ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
 	if (ret)
 		goto out;
 
@@ -514,6 +529,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	unsigned long charged = 0;
 	bool locked = false;
 	struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
+	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
@@ -541,7 +557,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 
 	if (flags & MREMAP_FIXED) {
 		ret = mremap_to(addr, old_len, new_addr, new_len,
-				&locked, &uf, &uf_unmap);
+				&locked, &uf, &uf_unmap_early, &uf_unmap);
 		goto out;
 	}
 
@@ -621,6 +637,7 @@ out:
 	up_write(&current->mm->mmap_sem);
 	if (locked && new_len > old_len)
 		mm_populate(new_addr + old_len, new_len - old_len);
+	userfaultfd_unmap_complete(mm, &uf_unmap_early);
 	mremap_userfaultfd_complete(&uf, addr, new_addr, old_len);
 	userfaultfd_unmap_complete(mm, &uf_unmap);
 	return ret;