Linux-libre 4.1.5-gnupck-4.1.5-gnu

8 files changed, 91 insertions, 31 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 0366e9e25..7c39f19bd 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -642,7 +642,7 @@ static inline bool fast_dput(struct dentry *dentry)
 
 	/*
 	 * If we have a d_op->d_delete() operation, we sould not
-	 * let the dentry count go to zero, so use "put__or_lock".
+	 * let the dentry count go to zero, so use "put_or_lock".
 	 */
 	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE))
 		return lockref_put_or_lock(&dentry->d_lockref);
@@ -697,7 +697,7 @@ static inline bool fast_dput(struct dentry *dentry)
 	 */
 	smp_rmb();
 	d_flags = ACCESS_ONCE(dentry->d_flags);
-	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST;
+	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED;
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
@@ -776,6 +776,9 @@ repeat:
 	if (unlikely(d_unhashed(dentry)))
 		goto kill_it;
 
+	if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
+		goto kill_it;
+
 	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
 		if (dentry->d_op->d_delete(dentry))
 			goto kill_it;
diff --git a/fs/namespace.c b/fs/namespace.c
index 18fe976ea..777b4819c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1351,6 +1351,36 @@ enum umount_tree_flags {
 	UMOUNT_PROPAGATE = 2,
 	UMOUNT_CONNECTED = 4,
 };
+
+static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how)
+{
+	/* Leaving mounts connected is only valid for lazy umounts */
+	if (how & UMOUNT_SYNC)
+		return true;
+
+	/* A mount without a parent has nothing to be connected to */
+	if (!mnt_has_parent(mnt))
+		return true;
+
+	/* Because the reference counting rules change when mounts are
+	 * unmounted and connected, umounted mounts may not be
+	 * connected to mounted mounts.
+	 */
+	if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT))
+		return true;
+
+	/* Has it been requested that the mount remain connected? */
+	if (how & UMOUNT_CONNECTED)
+		return false;
+
+	/* Is the mount locked such that it needs to remain connected? */
+	if (IS_MNT_LOCKED(mnt))
+		return false;
+
+	/* By default disconnect the mount */
+	return true;
+}
+
 /*
  * mount_lock must be held
  * namespace_sem must be held for write
@@ -1388,10 +1418,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		if (how & UMOUNT_SYNC)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 
-		disconnect = !(((how & UMOUNT_CONNECTED) &&
-				mnt_has_parent(p) &&
-				(p->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) ||
-			       IS_MNT_LOCKED_AND_LAZY(p));
+		disconnect = disconnect_mount(p, how);
 
 		pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt,
 				 disconnect ? &unmounted : NULL);
@@ -1528,11 +1555,8 @@ void __detach_mounts(struct dentry *dentry)
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
-			struct mount *p, *tmp;
-			list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts,  mnt_child) {
-				hlist_add_head(&p->mnt_umount.s_list, &unmounted);
-				umount_mnt(p);
-			}
+			hlist_add_head(&mnt->mnt_umount.s_list, &unmounted);
+			umount_mnt(mnt);
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f734562c6..5d25b9d97 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1242,9 +1242,11 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		cur_size = i_size_read(inode);
 		new_isize = nfs_size_to_loff_t(fattr->size);
-		if (cur_size != new_isize && nfsi->nrequests == 0)
+		if (cur_size != new_isize)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
 	}
+	if (nfsi->nrequests != 0)
+		invalid &= ~NFS_INO_REVAL_PAGECACHE;
 
 	/* Have any file permissions changed? */
 	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
@@ -1682,8 +1684,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			invalid |= NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_DATA
 				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL
-				| NFS_INO_REVAL_PAGECACHE;
+				| NFS_INO_INVALID_ACL;
 			if (S_ISDIR(inode->i_mode))
 				nfs_force_lookup_revalidate(inode);
 			inode->i_version = fattr->change_attr;
@@ -1715,7 +1716,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			if ((nfsi->nrequests == 0) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-				invalid &= ~NFS_INO_REVAL_PAGECACHE;
 			}
 			dprintk("NFS: isize change on server for file %s/%ld "
 					"(%Ld to %Ld)\n",
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 55e1e3af2..d3f205126 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1204,12 +1204,15 @@ static bool nfs_need_update_open_stateid(struct nfs4_state *state,
 
 static void nfs_resync_open_stateid_locked(struct nfs4_state *state)
 {
+	if (!(state->n_wronly || state->n_rdonly || state->n_rdwr))
+		return;
 	if (state->n_wronly)
 		set_bit(NFS_O_WRONLY_STATE, &state->flags);
 	if (state->n_rdonly)
 		set_bit(NFS_O_RDONLY_STATE, &state->flags);
 	if (state->n_rdwr)
 		set_bit(NFS_O_RDWR_STATE, &state->flags);
+	set_bit(NFS_OPEN_STATE, &state->flags);
 }
 
 static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 282b39369..7b4552678 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1110,8 +1110,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 			nfs_list_remove_request(req);
 			if (__nfs_pageio_add_request(desc, req))
 				continue;
-			if (desc->pg_error < 0)
+			if (desc->pg_error < 0) {
+				list_splice_tail(&head, &mirror->pg_list);
+				mirror->pg_recoalesce = 1;
 				return 0;
+			}
 			break;
 		}
 	} while (mirror->pg_recoalesce);
diff --git a/fs/pnode.h b/fs/pnode.h
index 7114ce6e6..0fcdbe7ca 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -20,8 +20,6 @@
 #define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
 #define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
 #define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
-#define IS_MNT_LOCKED_AND_LAZY(m) \
-	(((m)->mnt.mnt_flags & (MNT_LOCKED|MNT_SYNC_UMOUNT)) == MNT_LOCKED)
 
 #define CL_EXPIRE    		0x01
 #define CL_SLAVE     		0x02
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 20de88d1b..dd714037c 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -159,11 +159,10 @@ xfs_attr3_rmt_write_verify(
 	struct xfs_buf	*bp)
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_buf_log_item	*bip = bp->b_fspriv;
+	int		blksize = mp->m_attr_geo->blksize;
 	char		*ptr;
 	int		len;
 	xfs_daddr_t	bno;
-	int		blksize = mp->m_attr_geo->blksize;
 
 	/* no verification of non-crc buffers */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -175,16 +174,22 @@ xfs_attr3_rmt_write_verify(
 	ASSERT(len >= blksize);
 
 	while (len > 0) {
+		struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr;
+
 		if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
 			xfs_buf_ioerror(bp, -EFSCORRUPTED);
 			xfs_verifier_error(bp);
 			return;
 		}
-		if (bip) {
-			struct xfs_attr3_rmt_hdr *rmt;
 
-			rmt = (struct xfs_attr3_rmt_hdr *)ptr;
-			rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+		/*
+		 * Ensure we aren't writing bogus LSNs to disk. See
+		 * xfs_attr3_rmt_hdr_set() for the explanation.
+		 */
+		if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) {
+			xfs_buf_ioerror(bp, -EFSCORRUPTED);
+			xfs_verifier_error(bp);
+			return;
 		}
 		xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
 
@@ -221,6 +226,18 @@ xfs_attr3_rmt_hdr_set(
 	rmt->rm_owner = cpu_to_be64(ino);
 	rmt->rm_blkno = cpu_to_be64(bno);
 
+	/*
+	 * Remote attribute blocks are written synchronously, so we don't
+	 * have an LSN that we can stamp in them that makes any sense to log
+	 * recovery. To ensure that log recovery handles overwrites of these
+	 * blocks sanely (i.e. once they've been freed and reallocated as some
+	 * other type of metadata) we need to ensure that the LSN has a value
+	 * that tells log recovery to ignore the LSN and overwrite the buffer
+	 * with whatever is in it's log. To do this, we use the magic
+	 * NULLCOMMITLSN to indicate that the LSN is invalid.
+	 */
+	rmt->rm_lsn = cpu_to_be64(NULLCOMMITLSN);
+
 	return sizeof(struct xfs_attr3_rmt_hdr);
 }
 
@@ -434,14 +451,21 @@ xfs_attr_rmtval_set(
 
 		/*
 		 * Allocate a single extent, up to the size of the value.
+		 *
+		 * Note that we have to consider this a data allocation as we
+		 * write the remote attribute without logging the contents.
+		 * Hence we must ensure that we aren't using blocks that are on
+		 * the busy list so that we don't overwrite blocks which have
+		 * recently been freed but their transactions are not yet
+		 * committed to disk. If we overwrite the contents of a busy
+		 * extent and then crash then the block may not contain the
+		 * correct metadata after log recovery occurs.
 		 */
 		xfs_bmap_init(args->flist, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt,
-				  XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
-				  args->firstblock, args->total, &map, &nmap,
-				  args->flist);
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
+				  args->total, &map, &nmap, args->flist);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
 						&committed);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 4f5784f85..a5d03396d 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1887,9 +1887,14 @@ xlog_recover_get_buf_lsn(
 		uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid;
 		break;
 	case XFS_ATTR3_RMT_MAGIC:
-		lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
-		uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid;
-		break;
+		/*
+		 * Remote attr blocks are written synchronously, rather than
+		 * being logged. That means they do not contain a valid LSN
+		 * (i.e. transactionally ordered) in them, and hence any time we
+		 * see a buffer to replay over the top of a remote attribute
+		 * block we should simply do so.
+		 */
+		goto recover_immediately;
 	case XFS_SB_MAGIC:
 		lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
 		uuid = &((struct xfs_dsb *)blk)->sb_uuid;