Merge branch 'page-refs' (page ref overflow)

Merge page ref overflow branch.

Jann Horn reported that he can overflow the page ref count with
sufficient memory (and a filesystem that is intentionally extremely
slow).

Admittedly it's not exactly easy.  To have more than four billion
references to a page requires a minimum of 32GB of kernel memory just
for the pointers to the pages, much less any metadata to keep track of
those pointers.  Jann needed a total of 140GB of memory and a specially
crafted filesystem that leaves all reads pending (in order to not ever
free the page references and just keep adding more).

Still, we have a fairly straightforward way to limit the two obvious
user-controllable sources of page references: direct-IO like page
references gotten through get_user_pages(), and the splice pipe page
duplication.  So let's just do that.

* branch page-refs:
  fs: prevent page refcount overflow in pipe_buf_get
  mm: prevent get_user_pages() from overflowing page refcount
  mm: add 'try_get_page()' helper function
  mm: make page ref count overflow check tighter and more explicit

Author: torvalds

fs/fuse/dev.c

@@ -2056,10 +2056,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 		rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len;
 
 	ret = -EINVAL;
-	if (rem < len) {
-		pipe_unlock(pipe);
-		goto out;
-	}
+	if (rem < len)
+		goto out_free;
 
 	rem = len;
 	while (rem) {
@@ -2077,7 +2075,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 			pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
 			pipe->nrbufs--;
 		} else {
-			pipe_buf_get(pipe, ibuf);
+			if (!pipe_buf_get(pipe, ibuf))
+				goto out_free;
+
 			*obuf = *ibuf;
 			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
 			obuf->len = rem;
@@ -2100,11 +2100,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 	ret = fuse_dev_do_write(fud, &cs, len);
 
 	pipe_lock(pipe);
+out_free:
 	for (idx = 0; idx < nbuf; idx++)
 		pipe_buf_release(pipe, &bufs[idx]);
 	pipe_unlock(pipe);
 
-out:
 	kvfree(bufs);
 	return ret;
 }

fs/pipe.c

@@ -188,9 +188,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal);
  *	in the tee() system call, when we duplicate the buffers in one
  *	pipe into another.
  */
-void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
+bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
 {
-	get_page(buf->page);
+	return try_get_page(buf->page);
 }
 EXPORT_SYMBOL(generic_pipe_buf_get);
 

fs/splice.c

@@ -1593,7 +1593,11 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 			 * Get a reference to this pipe buffer,
 			 * so we can copy the contents over.
 			 */
-			pipe_buf_get(ipipe, ibuf);
+			if (!pipe_buf_get(ipipe, ibuf)) {
+				if (ret == 0)
+					ret = -EFAULT;
+				break;
+			}
 			*obuf = *ibuf;
 
 			/*
@@ -1667,7 +1671,11 @@ static int link_pipe(struct pipe_inode_info *ipipe,
 		 * Get a reference to this pipe buffer,
 		 * so we can copy the contents over.
 		 */
-		pipe_buf_get(ipipe, ibuf);
+		if (!pipe_buf_get(ipipe, ibuf)) {
+			if (ret == 0)
+				ret = -EFAULT;
+			break;
+		}
 
 		obuf = opipe->bufs + nbuf;
 		*obuf = *ibuf;

include/linux/mm.h

@@ -966,15 +966,28 @@ static inline bool is_pci_p2pdma_page(const struct page *page)
 }
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
 
+/* 127: arbitrary random number, small enough to assemble well */
+#define page_ref_zero_or_close_to_overflow(page) \
+	((unsigned int) page_ref_count(page) + 127u <= 127u)
+
 static inline void get_page(struct page *page)
 {
 	page = compound_head(page);
 	/*
 	 * Getting a normal page or the head of a compound page
 	 * requires to already have an elevated page->_refcount.
 	 */
-	VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
+	VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page);
+	page_ref_inc(page);
+}
+
+static inline __must_check bool try_get_page(struct page *page)
+{
+	page = compound_head(page);
+	if (WARN_ON_ONCE(page_ref_count(page) <= 0))
+		return false;
 	page_ref_inc(page);
+	return true;
 }
 
 static inline void put_page(struct page *page)

include/linux/pipe_fs_i.h

@@ -101,18 +101,20 @@ struct pipe_buf_operations {
 	/*
 	 * Get a reference to the pipe buffer.
 	 */
-	void (*get)(struct pipe_inode_info *, struct pipe_buffer *);
+	bool (*get)(struct pipe_inode_info *, struct pipe_buffer *);
 };
 
 /**
  * pipe_buf_get - get a reference to a pipe_buffer
  * @pipe:	the pipe that the buffer belongs to
  * @buf:	the buffer to get a reference to
+ *
+ * Return: %true if the reference was successfully obtained.
  */
-static inline void pipe_buf_get(struct pipe_inode_info *pipe,
+static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe,
 				struct pipe_buffer *buf)
 {
-	buf->ops->get(pipe, buf);
+	return buf->ops->get(pipe, buf);
 }
 
 /**
@@ -171,7 +173,7 @@ struct pipe_inode_info *alloc_pipe_info(void);
 void free_pipe_info(struct pipe_inode_info *);
 
 /* Generic pipe buffer ops functions */
-void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
+bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);

kernel/trace/trace.c

@@ -7041,12 +7041,16 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 	buf->private = 0;
 }
 
-static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 				struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
+	if (ref->ref > INT_MAX/2)
+		return false;
+
 	ref->ref++;
+	return true;
 }
 
 /* Pipe buffer operations for a buffer. */

mm/gup.c

@@ -160,8 +160,12 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto retry;
 	}
 
-	if (flags & FOLL_GET)
-		get_page(page);
+	if (flags & FOLL_GET) {
+		if (unlikely(!try_get_page(page))) {
+			page = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+	}
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))
@@ -298,7 +302,10 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 			if (pmd_trans_unstable(pmd))
 				ret = -EBUSY;
 		} else {
-			get_page(page);
+			if (unlikely(!try_get_page(page))) {
+				spin_unlock(ptl);
+				return ERR_PTR(-ENOMEM);
+			}
 			spin_unlock(ptl);
 			lock_page(page);
 			ret = split_huge_page(page);
@@ -500,7 +507,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 		if (is_device_public_page(*page))
 			goto unmap;
 	}
-	get_page(*page);
+	if (unlikely(!try_get_page(*page))) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
 out:
 	ret = 0;
 unmap:
@@ -1545,6 +1555,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
 	}
 }
 
+/*
+ * Return the compund head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+	struct page *head = compound_head(page);
+	if (WARN_ON_ONCE(page_ref_count(head) < 0))
+		return NULL;
+	if (unlikely(!page_cache_add_speculative(head, refs)))
+		return NULL;
+	return head;
+}
+
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
@@ -1579,9 +1603,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
-		head = compound_head(page);
 
-		if (!page_cache_get_speculative(head))
+		head = try_get_compound_head(page, 1);
+		if (!head)
 			goto pte_unmap;
 
 		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
@@ -1720,8 +1744,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pmd_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pmd_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
@@ -1758,8 +1782,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pud_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pud_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
@@ -1795,8 +1819,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pgd_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pgd_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}

mm/hugetlb.c

@@ -4299,6 +4299,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
 		page = pte_page(huge_ptep_get(pte));
+
+		/*
+		 * Instead of doing 'try_get_page()' below in the same_page
+		 * loop, just check the count once here.
+		 */
+		if (unlikely(page_count(page) <= 0)) {
+			if (pages) {
+				spin_unlock(ptl);
+				remainder = 0;
+				err = -ENOMEM;
+				break;
+			}
+		}
 same_page:
 		if (pages) {
 			pages[i] = mem_map_offset(page, pfn_offset);