1 files changed, 101 insertions, 57 deletions

diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index d90e781..d0a3c4b 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -27,6 +27,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_trans_priv.h"
+#include "xfs_buf_item.h"
 #include "xfs_log.h"
 
 
@@ -363,6 +364,9 @@ xfs_inode_to_log_dinode(
 	to->di_dmstate = from->di_dmstate;
 	to->di_flags = from->di_flags;
 
+	/* log a dummy value to ensure log structure is fully initialised */
+	to->di_next_unlinked = NULLAGINO;
+
 	if (from->di_version == 3) {
 		to->di_changecount = inode->i_version;
 		to->di_crtime.t_sec = from->di_crtime.t_sec;
@@ -403,6 +407,11 @@ xfs_inode_item_format_core(
  * the second with the on-disk inode structure, and a possible third and/or
  * fourth with the inode data/extents/b-tree root and inode attributes
  * data/extents/b-tree root.
+ *
+ * Note: Always use the 64 bit inode log format structure so we don't
+ * leave an uninitialised hole in the format item on 64 bit systems. Log
+ * recovery on 32 bit systems handles this just fine, so there's no reason
+ * for not using an initialising the properly padded structure all the time.
  */
 STATIC void
 xfs_inode_item_format(
@@ -411,8 +420,8 @@ xfs_inode_item_format(
 {
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
-	struct xfs_inode_log_format *ilf;
 	struct xfs_log_iovec	*vecp = NULL;
+	struct xfs_inode_log_format *ilf;
 
 	ASSERT(ip->i_d.di_version > 1);
 
@@ -424,7 +433,17 @@ xfs_inode_item_format(
 	ilf->ilf_boffset = ip->i_imap.im_boffset;
 	ilf->ilf_fields = XFS_ILOG_CORE;
 	ilf->ilf_size = 2; /* format + core */
-	xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
+
+	/*
+	 * make sure we don't leak uninitialised data into the log in the case
+	 * when we don't log every field in the inode.
+	 */
+	ilf->ilf_dsize = 0;
+	ilf->ilf_asize = 0;
+	ilf->ilf_pad = 0;
+	memset(&ilf->ilf_u.ilfu_uuid, 0, sizeof(ilf->ilf_u.ilfu_uuid));
+
+	xlog_finish_iovec(lv, vecp, sizeof(*ilf));
 
 	xfs_inode_item_format_core(ip, lv, &vecp);
 	xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
@@ -475,6 +494,23 @@ xfs_inode_item_unpin(
 		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
 }
 
+/*
+ * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer
+ * have been failed during writeback
+ *
+ * This informs the AIL that the inode is already flush locked on the next push,
+ * and acquires a hold on the buffer to ensure that it isn't reclaimed before
+ * dirty data makes it to disk.
+ */
+STATIC void
+xfs_inode_item_error(
+	struct xfs_log_item	*lip,
+	struct xfs_buf		*bp)
+{
+	ASSERT(xfs_isiflocked(INODE_ITEM(lip)->ili_inode));
+	xfs_set_li_failed(lip, bp);
+}
+
 STATIC uint
 xfs_inode_item_push(
 	struct xfs_log_item	*lip,
@@ -484,13 +520,28 @@ xfs_inode_item_push(
 {
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
-	struct xfs_buf		*bp = NULL;
+	struct xfs_buf		*bp = lip->li_buf;
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
 	if (xfs_ipincount(ip) > 0)
 		return XFS_ITEM_PINNED;
 
+	/*
+	 * The buffer containing this item failed to be written back
+	 * previously. Resubmit the buffer for IO.
+	 */
+	if (lip->li_flags & XFS_LI_FAILED) {
+		if (!xfs_buf_trylock(bp))
+			return XFS_ITEM_LOCKED;
+
+		if (!xfs_buf_resubmit_failed_buffers(bp, lip, buffer_list))
+			rval = XFS_ITEM_FLUSHING;
+
+		xfs_buf_unlock(bp);
+		return rval;
+	}
+
 	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
 		return XFS_ITEM_LOCKED;
 
@@ -622,7 +673,8 @@ static const struct xfs_item_ops xfs_inode_item_ops = {
 	.iop_unlock	= xfs_inode_item_unlock,
 	.iop_committed	= xfs_inode_item_committed,
 	.iop_push	= xfs_inode_item_push,
-	.iop_committing = xfs_inode_item_committing
+	.iop_committing = xfs_inode_item_committing,
+	.iop_error	= xfs_inode_item_error
 };
 
 
@@ -710,7 +762,8 @@ xfs_iflush_done(
 		 * the AIL lock.
 		 */
 		iip = INODE_ITEM(blip);
-		if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn)
+		if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
+		    (blip->li_flags & XFS_LI_FAILED))
 			need_ail++;
 
 		blip = next;
@@ -718,7 +771,8 @@ xfs_iflush_done(
 
 	/* make sure we capture the state of the initial inode. */
 	iip = INODE_ITEM(lip);
-	if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn)
+	if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) ||
+	    lip->li_flags & XFS_LI_FAILED)
 		need_ail++;
 
 	/*
@@ -731,22 +785,30 @@ xfs_iflush_done(
 	 * holding the lock before removing the inode from the AIL.
 	 */
 	if (need_ail) {
-		struct xfs_log_item *log_items[need_ail];
-		int i = 0;
+		bool			mlip_changed = false;
+
+		/* this is an opencoded batch version of xfs_trans_ail_delete */
 		spin_lock(&ailp->xa_lock);
 		for (blip = lip; blip; blip = blip->li_bio_list) {
-			iip = INODE_ITEM(blip);
-			if (iip->ili_logged &&
-			    blip->li_lsn == iip->ili_flush_lsn) {
-				log_items[i++] = blip;
+			if (INODE_ITEM(blip)->ili_logged &&
+			    blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn)
+				mlip_changed |= xfs_ail_delete_one(ailp, blip);
+			else {
+				xfs_clear_li_failed(blip);
 			}
-			ASSERT(i <= need_ail);
 		}
-		/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
-		xfs_trans_ail_delete_bulk(ailp, log_items, i,
-					  SHUTDOWN_CORRUPT_INCORE);
-	}
 
+		if (mlip_changed) {
+			if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
+				xlog_assign_tail_lsn_locked(ailp->xa_mount);
+			if (list_empty(&ailp->xa_ail))
+				wake_up_all(&ailp->xa_empty);
+		}
+		spin_unlock(&ailp->xa_lock);
+
+		if (mlip_changed)
+			xfs_log_space_wake(ailp->xa_mount);
+	}
 
 	/*
 	 * clean up and unlock the flush lock now we are done. We can clear the
@@ -811,48 +873,30 @@ xfs_istale_done(
 }
 
 /*
- * convert an xfs_inode_log_format struct from either 32 or 64 bit versions
- * (which can have different field alignments) to the native version
+ * convert an xfs_inode_log_format struct from the old 32 bit version
+ * (which can have different field alignments) to the native 64 bit version
  */
 int
 xfs_inode_item_format_convert(
-	xfs_log_iovec_t		*buf,
-	xfs_inode_log_format_t	*in_f)
+	struct xfs_log_iovec		*buf,
+	struct xfs_inode_log_format	*in_f)
 {
-	if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) {
-		xfs_inode_log_format_32_t *in_f32 = buf->i_addr;
-
-		in_f->ilf_type = in_f32->ilf_type;
-		in_f->ilf_size = in_f32->ilf_size;
-		in_f->ilf_fields = in_f32->ilf_fields;
-		in_f->ilf_asize = in_f32->ilf_asize;
-		in_f->ilf_dsize = in_f32->ilf_dsize;
-		in_f->ilf_ino = in_f32->ilf_ino;
-		/* copy biggest field of ilf_u */
-		memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
-		       in_f32->ilf_u.ilfu_uuid.__u_bits,
-		       sizeof(uuid_t));
-		in_f->ilf_blkno = in_f32->ilf_blkno;
-		in_f->ilf_len = in_f32->ilf_len;
-		in_f->ilf_boffset = in_f32->ilf_boffset;
-		return 0;
-	} else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){
-		xfs_inode_log_format_64_t *in_f64 = buf->i_addr;
-
-		in_f->ilf_type = in_f64->ilf_type;
-		in_f->ilf_size = in_f64->ilf_size;
-		in_f->ilf_fields = in_f64->ilf_fields;
-		in_f->ilf_asize = in_f64->ilf_asize;
-		in_f->ilf_dsize = in_f64->ilf_dsize;
-		in_f->ilf_ino = in_f64->ilf_ino;
-		/* copy biggest field of ilf_u */
-		memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
-		       in_f64->ilf_u.ilfu_uuid.__u_bits,
-		       sizeof(uuid_t));
-		in_f->ilf_blkno = in_f64->ilf_blkno;
-		in_f->ilf_len = in_f64->ilf_len;
-		in_f->ilf_boffset = in_f64->ilf_boffset;
-		return 0;
-	}
-	return -EFSCORRUPTED;
+	struct xfs_inode_log_format_32	*in_f32 = buf->i_addr;
+
+	if (buf->i_len != sizeof(*in_f32))
+		return -EFSCORRUPTED;
+
+	in_f->ilf_type = in_f32->ilf_type;
+	in_f->ilf_size = in_f32->ilf_size;
+	in_f->ilf_fields = in_f32->ilf_fields;
+	in_f->ilf_asize = in_f32->ilf_asize;
+	in_f->ilf_dsize = in_f32->ilf_dsize;
+	in_f->ilf_ino = in_f32->ilf_ino;
+	/* copy biggest field of ilf_u */
+	memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
+	       in_f32->ilf_u.ilfu_uuid.__u_bits, sizeof(uuid_t));
+	in_f->ilf_blkno = in_f32->ilf_blkno;
+	in_f->ilf_len = in_f32->ilf_len;
+	in_f->ilf_boffset = in_f32->ilf_boffset;
+	return 0;
 }