1 files changed, 89 insertions, 283 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 99c49eeae71b..d5e7c2029d16 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -249,7 +249,7 @@ static void page_cache_free_page(struct address_space *mapping,
 		freepage(page);
 
 	if (PageTransHuge(page) && !PageHuge(page)) {
-		page_ref_sub(page, HPAGE_PMD_NR);
+		page_ref_sub(page, thp_nr_pages(page));
 		VM_BUG_ON_PAGE(page_count(page) <= 0, page);
 	} else {
 		put_page(page);
@@ -414,7 +414,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 		.range_end = end,
 	};
 
-	if (!mapping_cap_writeback_dirty(mapping) ||
+	if (!mapping_can_writeback(mapping) ||
 	    !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		return 0;
 
@@ -827,15 +827,14 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
-static int __add_to_page_cache_locked(struct page *page,
-				      struct address_space *mapping,
-				      pgoff_t offset, gfp_t gfp_mask,
-				      void **shadowp)
+noinline int __add_to_page_cache_locked(struct page *page,
+					struct address_space *mapping,
+					pgoff_t offset, gfp_t gfp,
+					void **shadowp)
 {
 	XA_STATE(xas, &mapping->i_pages, offset);
 	int huge = PageHuge(page);
 	int error;
-	void *old;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
@@ -846,25 +845,46 @@ static int __add_to_page_cache_locked(struct page *page,
 	page->index = offset;
 
 	if (!huge) {
-		error = mem_cgroup_charge(page, current->mm, gfp_mask);
+		error = mem_cgroup_charge(page, current->mm, gfp);
 		if (error)
 			goto error;
 	}
 
+	gfp &= GFP_RECLAIM_MASK;
+
 	do {
+		unsigned int order = xa_get_order(xas.xa, xas.xa_index);
+		void *entry, *old = NULL;
+
+		if (order > thp_order(page))
+			xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
+					order, gfp);
 		xas_lock_irq(&xas);
-		old = xas_load(&xas);
-		if (old && !xa_is_value(old))
-			xas_set_err(&xas, -EEXIST);
+		xas_for_each_conflict(&xas, entry) {
+			old = entry;
+			if (!xa_is_value(entry)) {
+				xas_set_err(&xas, -EEXIST);
+				goto unlock;
+			}
+		}
+
+		if (old) {
+			if (shadowp)
+				*shadowp = old;
+			/* entry may have been split before we acquired lock */
+			order = xa_get_order(xas.xa, xas.xa_index);
+			if (order > thp_order(page)) {
+				xas_split(&xas, old, order);
+				xas_reset(&xas);
+			}
+		}
+
 		xas_store(&xas, page);
 		if (xas_error(&xas))
 			goto unlock;
 
-		if (xa_is_value(old)) {
+		if (old)
 			mapping->nrexceptional--;
-			if (shadowp)
-				*shadowp = old;
-		}
 		mapping->nrpages++;
 
 		/* hugetlb pages do not participate in page cache accounting */
@@ -872,7 +892,7 @@ static int __add_to_page_cache_locked(struct page *page,
 			__inc_lruvec_page_state(page, NR_FILE_PAGES);
 unlock:
 		xas_unlock_irq(&xas);
-	} while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK));
+	} while (xas_nomem(&xas, gfp));
 
 	if (xas_error(&xas)) {
 		error = xas_error(&xas);
@@ -1425,7 +1445,7 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem
  * unlock_page - unlock a locked page
  * @page: the page
  *
- * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
+ * Unlocks the page and wakes up sleepers in wait_on_page_locked().
  * Also wakes sleepers in wait_on_page_writeback() because the wakeup
  * mechanism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
@@ -1645,19 +1665,19 @@ EXPORT_SYMBOL(page_cache_prev_miss);
 /**
  * find_get_entry - find and get a page cache entry
  * @mapping: the address_space to search
- * @offset: the page cache index
+ * @index: The page cache index.
  *
  * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned with an increased refcount.
+ * page cache page, the head page is returned with an increased refcount.
  *
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * Return: the found page or shadow entry, %NULL if nothing is found.
+ * Return: The head page or shadow entry, %NULL if nothing is found.
  */
-struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t index)
 {
-	XA_STATE(xas, &mapping->i_pages, offset);
+	XA_STATE(xas, &mapping->i_pages, index);
 	struct page *page;
 
 	rcu_read_lock();
@@ -1685,7 +1705,6 @@ repeat:
 		put_page(page);
 		goto repeat;
 	}
-	page = find_subpage(page, offset);
 out:
 	rcu_read_unlock();
 
@@ -1693,40 +1712,37 @@ out:
 }
 
 /**
- * find_lock_entry - locate, pin and lock a page cache entry
- * @mapping: the address_space to search
- * @offset: the page cache index
+ * find_lock_entry - Locate and lock a page cache entry.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
+ * Looks up the page at @mapping & @index.  If there is a page in the
+ * cache, the head page is returned locked and with an increased refcount.
  *
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * find_lock_entry() may sleep.
- *
- * Return: the found page or shadow entry, %NULL if nothing is found.
+ * Context: May sleep.
+ * Return: The head page or shadow entry, %NULL if nothing is found.
  */
-struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t index)
 {
 	struct page *page;
 
 repeat:
-	page = find_get_entry(mapping, offset);
+	page = find_get_entry(mapping, index);
 	if (page && !xa_is_value(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
-		if (unlikely(page_mapping(page) != mapping)) {
+		if (unlikely(page->mapping != mapping)) {
 			unlock_page(page);
 			put_page(page);
 			goto repeat;
 		}
-		VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
+		VM_BUG_ON_PAGE(!thp_contains(page, index), page);
 	}
 	return page;
 }
-EXPORT_SYMBOL(find_lock_entry);
 
 /**
  * pagecache_get_page - Find and get a reference to a page.
@@ -1741,6 +1757,8 @@ EXPORT_SYMBOL(find_lock_entry);
  *
  * * %FGP_ACCESSED - The page will be marked accessed.
  * * %FGP_LOCK - The page is returned locked.
+ * * %FGP_HEAD - If the page is present and a THP, return the head page
+ *   rather than the exact page specified by the index.
  * * %FGP_CREAT - If no page is present then a new page is allocated using
  *   @gfp_mask and added to the page cache and the VM's LRU list.
  *   The page is returned locked and with an increased refcount.
@@ -1781,12 +1799,12 @@ repeat:
 		}
 
 		/* Has the page been truncated? */
-		if (unlikely(compound_head(page)->mapping != mapping)) {
+		if (unlikely(page->mapping != mapping)) {
 			unlock_page(page);
 			put_page(page);
 			goto repeat;
 		}
-		VM_BUG_ON_PAGE(page->index != index, page);
+		VM_BUG_ON_PAGE(!thp_contains(page, index), page);
 	}
 
 	if (fgp_flags & FGP_ACCESSED)
@@ -1796,11 +1814,13 @@ repeat:
 		if (page_is_idle(page))
 			clear_page_idle(page);
 	}
+	if (!(fgp_flags & FGP_HEAD))
+		page = find_subpage(page, index);
 
 no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
 		int err;
-		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp_mask |= __GFP_WRITE;
 		if (fgp_flags & FGP_NOFS)
 			gfp_mask &= ~__GFP_FS;
@@ -2179,6 +2199,14 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 	last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
 	offset = *ppos & ~PAGE_MASK;
 
+	/*
+	 * If we've already successfully copied some data, then we
+	 * can no longer safely return -EIOCBQUEUED. Hence mark
+	 * an async read NOWAIT at that point.
+	 */
+	if (written && (iocb->ki_flags & IOCB_WAITQ))
+		iocb->ki_flags |= IOCB_NOWAIT;
+
 	for (;;) {
 		struct page *page;
 		pgoff_t end_index;
@@ -2568,8 +2596,8 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	struct file *file = vmf->vma->vm_file;
 	struct file_ra_state *ra = &file->f_ra;
 	struct address_space *mapping = file->f_mapping;
+	DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
 	struct file *fpin = NULL;
-	pgoff_t offset = vmf->pgoff;
 	unsigned int mmap_miss;
 
 	/* If we don't want any read-ahead, don't bother */
@@ -2580,8 +2608,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 
 	if (vmf->vma->vm_flags & VM_SEQ_READ) {
 		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-		page_cache_sync_readahead(mapping, ra, file, offset,
-					  ra->ra_pages);
+		page_cache_sync_ra(&ractl, ra, ra->ra_pages);
 		return fpin;
 	}
 
@@ -2601,10 +2628,11 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	 * mmap read-around
 	 */
 	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-	ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
+	ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
 	ra->size = ra->ra_pages;
 	ra->async_size = ra->ra_pages / 4;
-	ra_submit(ra, mapping, file);
+	ractl._index = ra->start;
+	do_page_cache_ra(&ractl, ra->size, ra->async_size);
 	return fpin;
 }
 
@@ -2793,42 +2821,42 @@ void filemap_map_pages(struct vm_fault *vmf,
 	pgoff_t last_pgoff = start_pgoff;
 	unsigned long max_idx;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
-	struct page *page;
+	struct page *head, *page;
 	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
 
 	rcu_read_lock();
-	xas_for_each(&xas, page, end_pgoff) {
-		if (xas_retry(&xas, page))
+	xas_for_each(&xas, head, end_pgoff) {
+		if (xas_retry(&xas, head))
 			continue;
-		if (xa_is_value(page))
+		if (xa_is_value(head))
 			goto next;
 
 		/*
 		 * Check for a locked page first, as a speculative
 		 * reference may adversely influence page migration.
 		 */
-		if (PageLocked(page))
+		if (PageLocked(head))
 			goto next;
-		if (!page_cache_get_speculative(page))
+		if (!page_cache_get_speculative(head))
 			goto next;
 
 		/* Has the page moved or been split? */
-		if (unlikely(page != xas_reload(&xas)))
+		if (unlikely(head != xas_reload(&xas)))
 			goto skip;
-		page = find_subpage(page, xas.xa_index);
+		page = find_subpage(head, xas.xa_index);
 
-		if (!PageUptodate(page) ||
+		if (!PageUptodate(head) ||
 				PageReadahead(page) ||
 				PageHWPoison(page))
 			goto skip;
-		if (!trylock_page(page))
+		if (!trylock_page(head))
 			goto skip;
 
-		if (page->mapping != mapping || !PageUptodate(page))
+		if (head->mapping != mapping || !PageUptodate(head))
 			goto unlock;
 
 		max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
-		if (page->index >= max_idx)
+		if (xas.xa_index >= max_idx)
 			goto unlock;
 
 		if (mmap_miss > 0)
@@ -2840,12 +2868,12 @@ void filemap_map_pages(struct vm_fault *vmf,
 		last_pgoff = xas.xa_index;
 		if (alloc_set_pte(vmf, page))
 			goto unlock;
-		unlock_page(page);
+		unlock_page(head);
 		goto next;
 unlock:
-		unlock_page(page);
+		unlock_page(head);
 skip:
-		put_page(page);
+		put_page(head);
 next:
 		/* Huge page is mapped? No need to proceed. */
 		if (pmd_trans_huge(*vmf->pmd))
@@ -2984,7 +3012,7 @@ filler:
 		goto out;
 
 	/*
-	 * Page is not up to date and may be locked due one of the following
+	 * Page is not up to date and may be locked due to one of the following
 	 * case a: Page is being filled and the page lock is held
 	 * case b: Read/write error clearing the page uptodate status
 	 * case c: Truncation in progress (page locked)
@@ -3093,228 +3121,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-/*
- * Don't operate on ranges the page cache doesn't support, and don't exceed the
- * LFS limits.  If pos is under the limit it becomes a short access.  If it
- * exceeds the limit we return -EFBIG.
- */
-static int generic_write_check_limits(struct file *file, loff_t pos,
-				      loff_t *count)
-{
-	struct inode *inode = file->f_mapping->host;
-	loff_t max_size = inode->i_sb->s_maxbytes;
-	loff_t limit = rlimit(RLIMIT_FSIZE);
-
-	if (limit != RLIM_INFINITY) {
-		if (pos >= limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-		*count = min(*count, limit - pos);
-	}
-
-	if (!(file->f_flags & O_LARGEFILE))
-		max_size = MAX_NON_LFS;
-
-	if (unlikely(pos >= max_size))
-		return -EFBIG;
-
-	*count = min(*count, max_size - pos);
-
-	return 0;
-}
-
-/*
- * Performs necessary checks before doing a write
- *
- * Can adjust writing position or amount of bytes to write.
- * Returns appropriate error code that caller should return or
- * zero in case that write should be allowed.
- */
-inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
-	loff_t count;
-	int ret;
-
-	if (IS_SWAPFILE(inode))
-		return -ETXTBSY;
-
-	if (!iov_iter_count(from))
-		return 0;
-
-	/* FIXME: this is for backwards compatibility with 2.4 */
-	if (iocb->ki_flags & IOCB_APPEND)
-		iocb->ki_pos = i_size_read(inode);
-
-	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
-		return -EINVAL;
-
-	count = iov_iter_count(from);
-	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
-	if (ret)
-		return ret;
-
-	iov_iter_truncate(from, count);
-	return iov_iter_count(from);
-}
-EXPORT_SYMBOL(generic_write_checks);
-
-/*
- * Performs necessary checks before doing a clone.
- *
- * Can adjust amount of bytes to clone via @req_count argument.
- * Returns appropriate error code that caller should return or
- * zero in case the clone should be allowed.
- */
-int generic_remap_checks(struct file *file_in, loff_t pos_in,
-			 struct file *file_out, loff_t pos_out,
-			 loff_t *req_count, unsigned int remap_flags)
-{
-	struct inode *inode_in = file_in->f_mapping->host;
-	struct inode *inode_out = file_out->f_mapping->host;
-	uint64_t count = *req_count;
-	uint64_t bcount;
-	loff_t size_in, size_out;
-	loff_t bs = inode_out->i_sb->s_blocksize;
-	int ret;
-
-	/* The start of both ranges must be aligned to an fs block. */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
-		return -EINVAL;
-
-	/* Ensure offsets don't wrap. */
-	if (pos_in + count < pos_in || pos_out + count < pos_out)
-		return -EINVAL;
-
-	size_in = i_size_read(inode_in);
-	size_out = i_size_read(inode_out);
-
-	/* Dedupe requires both ranges to be within EOF. */
-	if ((remap_flags & REMAP_FILE_DEDUP) &&
-	    (pos_in >= size_in || pos_in + count > size_in ||
-	     pos_out >= size_out || pos_out + count > size_out))
-		return -EINVAL;
-
-	/* Ensure the infile range is within the infile. */
-	if (pos_in >= size_in)
-		return -EINVAL;
-	count = min(count, size_in - (uint64_t)pos_in);
-
-	ret = generic_write_check_limits(file_out, pos_out, &count);
-	if (ret)
-		return ret;
-
-	/*
-	 * If the user wanted us to link to the infile's EOF, round up to the
-	 * next block boundary for this check.
-	 *
-	 * Otherwise, make sure the count is also block-aligned, having
-	 * already confirmed the starting offsets' block alignment.
-	 */
-	if (pos_in + count == size_in) {
-		bcount = ALIGN(size_in, bs) - pos_in;
-	} else {
-		if (!IS_ALIGNED(count, bs))
-			count = ALIGN_DOWN(count, bs);
-		bcount = count;
-	}
-
-	/* Don't allow overlapped cloning within the same file. */
-	if (inode_in == inode_out &&
-	    pos_out + bcount > pos_in &&
-	    pos_out < pos_in + bcount)
-		return -EINVAL;
-
-	/*
-	 * We shortened the request but the caller can't deal with that, so
-	 * bounce the request back to userspace.
-	 */
-	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
-		return -EINVAL;
-
-	*req_count = count;
-	return 0;
-}
-
-
-/*
- * Performs common checks before doing a file copy/clone
- * from @file_in to @file_out.
- */
-int generic_file_rw_checks(struct file *file_in, struct file *file_out)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-
-	/* Don't copy dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	if (!(file_in->f_mode & FMODE_READ) ||
-	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND))
-		return -EBADF;
-
-	return 0;
-}
-
-/*
- * Performs necessary checks before doing a file copy
- *
- * Can adjust amount of bytes to copy via @req_count argument.
- * Returns appropriate error code that caller should return or
- * zero in case the copy should be allowed.
- */
-int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
-			     struct file *file_out, loff_t pos_out,
-			     size_t *req_count, unsigned int flags)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-	uint64_t count = *req_count;
-	loff_t size_in;
-	int ret;
-
-	ret = generic_file_rw_checks(file_in, file_out);
-	if (ret)
-		return ret;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-
-	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Ensure offsets don't wrap. */
-	if (pos_in + count < pos_in || pos_out + count < pos_out)
-		return -EOVERFLOW;
-
-	/* Shorten the copy to EOF */
-	size_in = i_size_read(inode_in);
-	if (pos_in >= size_in)
-		count = 0;
-	else
-		count = min(count, size_in - (uint64_t)pos_in);
-
-	ret = generic_write_check_limits(file_out, pos_out, &count);
-	if (ret)
-		return ret;
-
-	/* Don't allow overlapped copying within the same file. */
-	if (inode_in == inode_out &&
-	    pos_out + count > pos_in &&
-	    pos_out < pos_in + count)
-		return -EINVAL;
-
-	*req_count = count;
-	return 0;
-}
-
 int pagecache_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)