uprobe: use original page when all uprobes are removed

Currently, uprobe swaps the target page with a anonymous page in both
install_breakpoint() and remove_breakpoint().  When all uprobes on a page
are removed, the given mm is still using an anonymous page (not the
original page).

This patch allows uprobe to use original page when possible (all uprobes
on the page are already removed, and the original page is in page cache
and uptodate).

As suggested by Oleg, we unmap the old_page and let the original page
fault in.

Link: http://lkml.kernel.org/r/20190815164525.1848545-3-songliubraving@fb.comSigned-off-by: Song Liu <songliubraving@fb.com>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

kernel/events/uprobes.c

@@ -143,10 +143,12 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
  *
  * @vma:      vma that holds the pte pointing to page
  * @addr:     address the old @page is mapped at
- * @page:     the cowed page we are replacing by kpage
- * @kpage:    the modified page we replace page by
+ * @old_page: the page we are replacing by new_page
+ * @new_page: the modified page we replace page by
  *
- * Returns 0 on success, -EFAULT on failure.
+ * If @new_page is NULL, only unmap @old_page.
+ *
+ * Returns 0 on success, negative error code otherwise.
  */
 static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 				struct page *old_page, struct page *new_page)
@@ -166,10 +168,12 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	VM_BUG_ON_PAGE(PageTransHuge(old_page), old_page);
 
-	err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, &memcg,
-			false);
-	if (err)
-		return err;
+	if (new_page) {
+		err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL,
+					    &memcg, false);
+		if (err)
+			return err;
+	}
 
 	/* For try_to_free_swap() and munlock_vma_page() below */
 	lock_page(old_page);
@@ -177,15 +181,20 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	mmu_notifier_invalidate_range_start(&range);
 	err = -EAGAIN;
 	if (!page_vma_mapped_walk(&pvmw)) {
-		mem_cgroup_cancel_charge(new_page, memcg, false);
+		if (new_page)
+			mem_cgroup_cancel_charge(new_page, memcg, false);
 		goto unlock;
 	}
 	VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
 
-	get_page(new_page);
-	page_add_new_anon_rmap(new_page, vma, addr, false);
-	mem_cgroup_commit_charge(new_page, memcg, false, false);
-	lru_cache_add_active_or_unevictable(new_page, vma);
+	if (new_page) {
+		get_page(new_page);
+		page_add_new_anon_rmap(new_page, vma, addr, false);
+		mem_cgroup_commit_charge(new_page, memcg, false, false);
+		lru_cache_add_active_or_unevictable(new_page, vma);
+	} else
+		/* no new page, just dec_mm_counter for old_page */
+		dec_mm_counter(mm, MM_ANONPAGES);
 
 	if (!PageAnon(old_page)) {
 		dec_mm_counter(mm, mm_counter_file(old_page));
@@ -194,8 +203,9 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	flush_cache_page(vma, addr, pte_pfn(*pvmw.pte));
 	ptep_clear_flush_notify(vma, addr, pvmw.pte);
-	set_pte_at_notify(mm, addr, pvmw.pte,
-			mk_pte(new_page, vma->vm_page_prot));
+	if (new_page)
+		set_pte_at_notify(mm, addr, pvmw.pte,
+				  mk_pte(new_page, vma->vm_page_prot));
 
 	page_remove_rmap(old_page, false);
 	if (!page_mapped(old_page))
@@ -488,6 +498,10 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 		ref_ctr_updated = 1;
 	}
 
+	ret = 0;
+	if (!is_register && !PageAnon(old_page))
+		goto put_old;
+
 	ret = anon_vma_prepare(vma);
 	if (ret)
 		goto put_old;
@@ -501,8 +515,30 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	copy_highpage(new_page, old_page);
 	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 
+	if (!is_register) {
+		struct page *orig_page;
+		pgoff_t index;
+
+		VM_BUG_ON_PAGE(!PageAnon(old_page), old_page);
+
+		index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT;
+		orig_page = find_get_page(vma->vm_file->f_inode->i_mapping,
+					  index);
+
+		if (orig_page) {
+			if (PageUptodate(orig_page) &&
+			    pages_identical(new_page, orig_page)) {
+				/* let go new_page */
+				put_page(new_page);
+				new_page = NULL;
+			}
+			put_page(orig_page);
+		}
+	}
+
 	ret = __replace_page(vma, vaddr, old_page, new_page);
-	put_page(new_page);
+	if (new_page)
+		put_page(new_page);
 put_old:
 	put_page(old_page);