mm: Protect operations adding pages to page cache with invalidate_lock

Currently, serializing operations such as page fault, read, or readahead
against hole punching is rather difficult. The basic race scheme is
like:

fallocate(FALLOC_FL_PUNCH_HOLE)			read / fault / ..
  truncate_inode_pages_range()
						  <create pages in page
						   cache here>
  <update fs block mapping and free blocks>

Now the problem is in this way read / page fault / readahead can
instantiate pages in page cache with potentially stale data (if blocks
get quickly reused). Avoiding this race is not simple - page locks do
not work because we want to make sure there are *no* pages in given
range. inode->i_rwsem does not work because page fault happens under
mmap_sem which ranks below inode->i_rwsem. Also using it for reads makes
the performance for mixed read-write workloads suffer.

So create a new rw_semaphore in the address_space - invalidate_lock -
that protects adding of pages to page cache for page faults / reads /
readahead.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>

4 files changed, 102 insertions, 37 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index acf20eca2fa4..f7f9b87d2cd0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -77,7 +77,8 @@
  *        ->i_pages lock
  *
  *  ->i_rwsem
- *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)
+ *    ->invalidate_lock		(acquired by fs in truncate path)
+ *      ->i_mmap_rwsem		(truncate->unmap_mapping_range)
  *
  *  ->mmap_lock
  *    ->i_mmap_rwsem
@@ -85,7 +86,8 @@
  *        ->i_pages lock	(arch-dependent flush_dcache_mmap_lock)
  *
  *  ->mmap_lock
- *    ->lock_page		(access_process_vm)
+ *    ->invalidate_lock		(filemap_fault)
+ *      ->lock_page		(filemap_fault, access_process_vm)
  *
  *  ->i_rwsem			(generic_perform_write)
  *    ->mmap_lock		(fault_in_pages_readable->do_page_fault)
@@ -2368,20 +2370,30 @@ static int filemap_update_page(struct kiocb *iocb,
 {
 	int error;
 
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!filemap_invalidate_trylock_shared(mapping))
+			return -EAGAIN;
+	} else {
+		filemap_invalidate_lock_shared(mapping);
+	}
+
 	if (!trylock_page(page)) {
+		error = -EAGAIN;
 		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
-			return -EAGAIN;
+			goto unlock_mapping;
 		if (!(iocb->ki_flags & IOCB_WAITQ)) {
+			filemap_invalidate_unlock_shared(mapping);
 			put_and_wait_on_page_locked(page, TASK_KILLABLE);
 			return AOP_TRUNCATED_PAGE;
 		}
 		error = __lock_page_async(page, iocb->ki_waitq);
 		if (error)
-			return error;
+			goto unlock_mapping;
 	}
 
+	error = AOP_TRUNCATED_PAGE;
 	if (!page->mapping)
-		goto truncated;
+		goto unlock;
 
 	error = 0;
 	if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
@@ -2392,15 +2404,13 @@ static int filemap_update_page(struct kiocb *iocb,
 		goto unlock;
 
 	error = filemap_read_page(iocb->ki_filp, mapping, page);
-	if (error == AOP_TRUNCATED_PAGE)
-		put_page(page);
-	return error;
-truncated:
-	unlock_page(page);
-	put_page(page);
-	return AOP_TRUNCATED_PAGE;
+	goto unlock_mapping;
 unlock:
 	unlock_page(page);
+unlock_mapping:
+	filemap_invalidate_unlock_shared(mapping);
+	if (error == AOP_TRUNCATED_PAGE)
+		put_page(page);
 	return error;
 }
 
@@ -2415,6 +2425,19 @@ static int filemap_create_page(struct file *file,
 	if (!page)
 		return -ENOMEM;
 
+	/*
+	 * Protect against truncate / hole punch. Grabbing invalidate_lock here
+	 * assures we cannot instantiate and bring uptodate new pagecache pages
+	 * after evicting page cache during truncate and before actually
+	 * freeing blocks.  Note that we could release invalidate_lock after
+	 * inserting the page into page cache as the locked page would then be
+	 * enough to synchronize with hole punching. But there are code paths
+	 * such as filemap_update_page() filling in partially uptodate pages or
+	 * ->readpages() that need to hold invalidate_lock while mapping blocks
+	 * for IO so let's hold the lock here as well to keep locking rules
+	 * simple.
+	 */
+	filemap_invalidate_lock_shared(mapping);
 	error = add_to_page_cache_lru(page, mapping, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2426,9 +2449,11 @@ static int filemap_create_page(struct file *file,
 	if (error)
 		goto error;
 
+	filemap_invalidate_unlock_shared(mapping);
 	pagevec_add(pvec, page);
 	return 0;
 error:
+	filemap_invalidate_unlock_shared(mapping);
 	put_page(page);
 	return error;
 }
@@ -2967,6 +2992,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	pgoff_t max_off;
 	struct page *page;
 	vm_fault_t ret = 0;
+	bool mapping_locked = false;
 
 	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 	if (unlikely(offset >= max_off))
@@ -2976,25 +3002,39 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 * Do we have something in the page cache already?
 	 */
 	page = find_get_page(mapping, offset);
-	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
+	if (likely(page)) {
 		/*
-		 * We found the page, so try async readahead before
-		 * waiting for the lock.
+		 * We found the page, so try async readahead before waiting for
+		 * the lock.
 		 */
-		fpin = do_async_mmap_readahead(vmf, page);
-	} else if (!page) {
+		if (!(vmf->flags & FAULT_FLAG_TRIED))
+			fpin = do_async_mmap_readahead(vmf, page);
+		if (unlikely(!PageUptodate(page))) {
+			filemap_invalidate_lock_shared(mapping);
+			mapping_locked = true;
+		}
+	} else {
 		/* No page in the page cache at all */
 		count_vm_event(PGMAJFAULT);
 		count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 		fpin = do_sync_mmap_readahead(vmf);
 retry_find:
+		/*
+		 * See comment in filemap_create_page() why we need
+		 * invalidate_lock
+		 */
+		if (!mapping_locked) {
+			filemap_invalidate_lock_shared(mapping);
+			mapping_locked = true;
+		}
 		page = pagecache_get_page(mapping, offset,
 					  FGP_CREAT|FGP_FOR_MMAP,
 					  vmf->gfp_mask);
 		if (!page) {
 			if (fpin)
 				goto out_retry;
+			filemap_invalidate_unlock_shared(mapping);
 			return VM_FAULT_OOM;
 		}
 	}
@@ -3014,8 +3054,20 @@ retry_find:
 	 * We have a locked page in the page cache, now we need to check
 	 * that it's up-to-date. If not, it is going to be due to an error.
 	 */
-	if (unlikely(!PageUptodate(page)))
+	if (unlikely(!PageUptodate(page))) {
+		/*
+		 * The page was in cache and uptodate and now it is not.
+		 * Strange but possible since we didn't hold the page lock all
+		 * the time. Let's drop everything get the invalidate lock and
+		 * try again.
+		 */
+		if (!mapping_locked) {
+			unlock_page(page);
+			put_page(page);
+			goto retry_find;
+		}
 		goto page_not_uptodate;
+	}
 
 	/*
 	 * We've made it this far and we had to drop our mmap_lock, now is the
@@ -3026,6 +3078,8 @@ retry_find:
 		unlock_page(page);
 		goto out_retry;
 	}
+	if (mapping_locked)
+		filemap_invalidate_unlock_shared(mapping);
 
 	/*
 	 * Found the page and have a reference on it.
@@ -3056,6 +3110,7 @@ page_not_uptodate:
 
 	if (!error || error == AOP_TRUNCATED_PAGE)
 		goto retry_find;
+	filemap_invalidate_unlock_shared(mapping);
 
 	return VM_FAULT_SIGBUS;
 
@@ -3067,6 +3122,8 @@ out_retry:
 	 */
 	if (page)
 		put_page(page);
+	if (mapping_locked)
+		filemap_invalidate_unlock_shared(mapping);
 	if (fpin)
 		fput(fpin);
 	return ret | VM_FAULT_RETRY;
@@ -3437,6 +3494,8 @@ out:
  *
  * If the page does not get brought uptodate, return -EIO.
  *
+ * The function expects mapping->invalidate_lock to be already held.
+ *
  * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page(struct address_space *mapping,
@@ -3460,6 +3519,8 @@ EXPORT_SYMBOL(read_cache_page);
  *
  * If the page does not get brought uptodate, return -EIO.
  *
+ * The function expects mapping->invalidate_lock to be already held.
+ *
  * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page_gfp(struct address_space *mapping,
diff --git a/mm/readahead.c b/mm/readahead.c
index d589f147f4c2..41b75d76d36e 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -192,6 +192,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	 */
 	unsigned int nofs = memalloc_nofs_save();
 
+	filemap_invalidate_lock_shared(mapping);
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
@@ -236,6 +237,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	 * will then handle the error.
 	 */
 	read_pages(ractl, &page_pool, false);
+	filemap_invalidate_unlock_shared(mapping);
 	memalloc_nofs_restore(nofs);
 }
 EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
diff --git a/mm/rmap.c b/mm/rmap.c
index a8b01929ab2e..86471aacc54a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -22,24 +22,25 @@
  *
  * inode->i_rwsem	(while writing or truncating, not reading or faulting)
  *   mm->mmap_lock
- *     page->flags PG_locked (lock_page)   * (see hugetlbfs below)
- *       hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
- *         mapping->i_mmap_rwsem
- *           hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
- *           anon_vma->rwsem
- *             mm->page_table_lock or pte_lock
- *               swap_lock (in swap_duplicate, swap_info_get)
- *                 mmlist_lock (in mmput, drain_mmlist and others)
- *                 mapping->private_lock (in __set_page_dirty_buffers)
- *                   lock_page_memcg move_lock (in __set_page_dirty_buffers)
- *                     i_pages lock (widely used)
- *                       lruvec->lru_lock (in lock_page_lruvec_irq)
- *                 inode->i_lock (in set_page_dirty's __mark_inode_dirty)
- *                 bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
- *                   sb_lock (within inode_lock in fs/fs-writeback.c)
- *                   i_pages lock (widely used, in set_page_dirty,
- *                             in arch-dependent flush_dcache_mmap_lock,
- *                             within bdi.wb->list_lock in __sync_single_inode)
+ *     mapping->invalidate_lock (in filemap_fault)
+ *       page->flags PG_locked (lock_page)   * (see hugetlbfs below)
+ *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
+ *           mapping->i_mmap_rwsem
+ *             hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
+ *             anon_vma->rwsem
+ *               mm->page_table_lock or pte_lock
+ *                 swap_lock (in swap_duplicate, swap_info_get)
+ *                   mmlist_lock (in mmput, drain_mmlist and others)
+ *                   mapping->private_lock (in __set_page_dirty_buffers)
+ *                     lock_page_memcg move_lock (in __set_page_dirty_buffers)
+ *                       i_pages lock (widely used)
+ *                         lruvec->lru_lock (in lock_page_lruvec_irq)
+ *                   inode->i_lock (in set_page_dirty's __mark_inode_dirty)
+ *                   bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
+ *                     sb_lock (within inode_lock in fs/fs-writeback.c)
+ *                     i_pages lock (widely used, in set_page_dirty,
+ *                               in arch-dependent flush_dcache_mmap_lock,
+ *                               within bdi.wb->list_lock in __sync_single_inode)
  *
  * anon_vma->rwsem,mapping->i_mmap_rwsem   (memory_failure, collect_procs_anon)
  *   ->tasklist_lock
diff --git a/mm/truncate.c b/mm/truncate.c
index 0f9becee9789..44ad5e515140 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -412,7 +412,8 @@ EXPORT_SYMBOL(truncate_inode_pages_range);
  * @mapping: mapping to truncate
  * @lstart: offset from which to truncate
  *
- * Called under (and serialised by) inode->i_rwsem.
+ * Called under (and serialised by) inode->i_rwsem and
+ * mapping->invalidate_lock.
  *
  * Note: When this function returns, there can be a page in the process of
  * deletion (inside __delete_from_page_cache()) in the specified range.  Thus