[XFS] Only use refcounted pages for I/O

Many block drivers (aoe, iscsi) really want refcountable pages in bios,
which is what almost everyone send down. XFS unfortunately has a few
places where it sends down buffers that may come from kmalloc, which
breaks them.

Fix the places that use kmalloc()d buffers.

SGI-PV: 964546
SGI-Modid: xfs-linux-melb:xfs-kern:28562a

Signed-Off-By: Christoph Hellwig <hch@infradead.org>
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Tim Shimmin <tes@sgi.com>

3 files changed, 32 insertions, 38 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index fe4f66a5af14..208daf58b826 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -314,7 +314,7 @@ xfs_buf_free(
 
 	ASSERT(list_empty(&bp->b_hash_list));
 
-	if (bp->b_flags & _XBF_PAGE_CACHE) {
+	if (bp->b_flags & (_XBF_PAGE_CACHE|_XBF_PAGES)) {
 		uint		i;
 
 		if ((bp->b_flags & XBF_MAPPED) && (bp->b_page_count > 1))
@@ -323,18 +323,11 @@ xfs_buf_free(
 		for (i = 0; i < bp->b_page_count; i++) {
 			struct page	*page = bp->b_pages[i];
 
-			ASSERT(!PagePrivate(page));
+			if (bp->b_flags & _XBF_PAGE_CACHE)
+				ASSERT(!PagePrivate(page));
 			page_cache_release(page);
 		}
 		_xfs_buf_free_pages(bp);
-	} else if (bp->b_flags & _XBF_KMEM_ALLOC) {
-		 /*
-		  * XXX(hch): bp->b_count_desired might be incorrect (see
-		  * xfs_buf_associate_memory for details), but fortunately
-		  * the Linux version of kmem_free ignores the len argument..
-		  */
-		kmem_free(bp->b_addr, bp->b_count_desired);
-		_xfs_buf_free_pages(bp);
 	}
 
 	xfs_buf_deallocate(bp);
@@ -764,41 +757,41 @@ xfs_buf_get_noaddr(
 	size_t			len,
 	xfs_buftarg_t		*target)
 {
-	size_t			malloc_len = len;
+	unsigned long		page_count = PAGE_ALIGN(len) >> PAGE_SHIFT;
+	int			error, i;
 	xfs_buf_t		*bp;
-	void			*data;
-	int			error;
 
 	bp = xfs_buf_allocate(0);
 	if (unlikely(bp == NULL))
 		goto fail;
 	_xfs_buf_initialize(bp, target, 0, len, 0);
 
- try_again:
-	data = kmem_alloc(malloc_len, KM_SLEEP | KM_MAYFAIL | KM_LARGE);
-	if (unlikely(data == NULL))
+	error = _xfs_buf_get_pages(bp, page_count, 0);
+	if (error)
 		goto fail_free_buf;
 
-	/* check whether alignment matches.. */
-	if ((__psunsigned_t)data !=
-	    ((__psunsigned_t)data & ~target->bt_smask)) {
-		/* .. else double the size and try again */
-		kmem_free(data, malloc_len);
-		malloc_len <<= 1;
-		goto try_again;
+	for (i = 0; i < page_count; i++) {
+		bp->b_pages[i] = alloc_page(GFP_KERNEL);
+		if (!bp->b_pages[i])
+			goto fail_free_mem;
 	}
+	bp->b_flags |= _XBF_PAGES;
 
-	error = xfs_buf_associate_memory(bp, data, len);
-	if (error)
+	error = _xfs_buf_map_pages(bp, XBF_MAPPED);
+	if (unlikely(error)) {
+		printk(KERN_WARNING "%s: failed to map pages\n",
+				__FUNCTION__);
 		goto fail_free_mem;
-	bp->b_flags |= _XBF_KMEM_ALLOC;
+	}
 
 	xfs_buf_unlock(bp);
 
-	XB_TRACE(bp, "no_daddr", data);
+	XB_TRACE(bp, "no_daddr", len);
 	return bp;
+
  fail_free_mem:
-	kmem_free(data, malloc_len);
+	while (--i >= 0)
+		__free_page(bp->b_pages[i]);
  fail_free_buf:
 	xfs_buf_free(bp);
  fail:
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index b6241f6201a5..b5908a34b15d 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -63,7 +63,7 @@ typedef enum {
 
 	/* flags used only internally */
 	_XBF_PAGE_CACHE = (1 << 17),/* backed by pagecache		   */
-	_XBF_KMEM_ALLOC = (1 << 18),/* backed by kmem_alloc()		   */
+	_XBF_PAGES = (1 << 18),	    /* backed by refcounted pages	   */
 	_XBF_RUN_QUEUES = (1 << 19),/* run block device task queue	   */
 	_XBF_DELWRI_Q = (1 << 21),   /* buffer on delwri queue		   */
 } xfs_buf_flags_t;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index c48bf61f17bd..635f99e6302f 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1199,11 +1199,18 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		*iclogp = (xlog_in_core_t *)
 			  kmem_zalloc(sizeof(xlog_in_core_t), KM_SLEEP);
 		iclog = *iclogp;
-		iclog->hic_data = (xlog_in_core_2_t *)
-			  kmem_zalloc(iclogsize, KM_SLEEP | KM_LARGE);
-
 		iclog->ic_prev = prev_iclog;
 		prev_iclog = iclog;
+
+		bp = xfs_buf_get_noaddr(log->l_iclog_size, mp->m_logdev_targp);
+		if (!XFS_BUF_CPSEMA(bp))
+			ASSERT(0);
+		XFS_BUF_SET_IODONE_FUNC(bp, xlog_iodone);
+		XFS_BUF_SET_BDSTRAT_FUNC(bp, xlog_bdstrat_cb);
+		XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
+		iclog->ic_bp = bp;
+		iclog->hic_data = bp->b_addr;
+
 		log->l_iclog_bak[i] = (xfs_caddr_t)&(iclog->ic_header);
 
 		head = &iclog->ic_header;
@@ -1216,11 +1223,6 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		INT_SET(head->h_fmt, ARCH_CONVERT, XLOG_FMT);
 		memcpy(&head->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(uuid_t));
 
-		bp = xfs_buf_get_empty(log->l_iclog_size, mp->m_logdev_targp);
-		XFS_BUF_SET_IODONE_FUNC(bp, xlog_iodone);
-		XFS_BUF_SET_BDSTRAT_FUNC(bp, xlog_bdstrat_cb);
-		XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
-		iclog->ic_bp = bp;
 
 		iclog->ic_size = XFS_BUF_SIZE(bp) - log->l_iclog_hsize;
 		iclog->ic_state = XLOG_STATE_ACTIVE;
@@ -1528,7 +1530,6 @@ xlog_dealloc_log(xlog_t *log)
 		}
 #endif
 		next_iclog = iclog->ic_next;
-		kmem_free(iclog->hic_data, log->l_iclog_size);
 		kmem_free(iclog, sizeof(xlog_in_core_t));
 		iclog = next_iclog;
 	}