Reset to 3.12.19

11 files changed, 135 insertions, 43 deletions

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e81a1ca..1402806 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -276,6 +276,15 @@ out_eof:
 	return -EBADCOOKIE;
 }
 
+static bool
+nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
+{
+	if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))
+		return false;
+	smp_rmb();
+	return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
+}
+
 static
 int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
 {
@@ -289,8 +298,8 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 			struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 			new_pos = desc->current_index + i;
-			if (ctx->attr_gencount != nfsi->attr_gencount
-			    || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) {
+			if (ctx->attr_gencount != nfsi->attr_gencount ||
+			    !nfs_readdir_inode_mapping_valid(nfsi)) {
 				ctx->duped = 0;
 				ctx->attr_gencount = nfsi->attr_gencount;
 			} else if (new_pos < desc->ctx->pos) {
@@ -1139,7 +1148,13 @@ out_zap_parent:
 	if (inode && S_ISDIR(inode->i_mode)) {
 		/* Purge readdir caches. */
 		nfs_zap_caches(inode);
-		if (dentry->d_flags & DCACHE_DISCONNECTED)
+		/*
+		 * We can't d_drop the root of a disconnected tree:
+		 * its d_hash is on the s_anon list and d_drop() would hide
+		 * it from shrink_dcache_for_unmount(), leading to busy
+		 * inodes on unmount and further oopses.
+		 */
+		if (IS_ROOT(dentry))
 			goto out_valid;
 	}
 	/* If we have submounts, don't unhash ! */
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 91ff089..af5f3ff 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -223,14 +223,31 @@ out:
  * Synchronous I/O uses a stack-allocated iocb.  Thus we can't trust
  * the iocb is still valid here if this is a synchronous request.
  */
-static void nfs_direct_complete(struct nfs_direct_req *dreq)
+static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
 {
+	struct inode *inode = dreq->inode;
+
+	if (dreq->iocb && write) {
+		loff_t pos = dreq->iocb->ki_pos + dreq->count;
+
+		spin_lock(&inode->i_lock);
+		if (i_size_read(inode) < pos)
+			i_size_write(inode, pos);
+		spin_unlock(&inode->i_lock);
+	}
+
+	if (write)
+		nfs_zap_mapping(inode, inode->i_mapping);
+
+	inode_dio_done(inode);
+
 	if (dreq->iocb) {
 		long res = (long) dreq->error;
 		if (!res)
 			res = (long) dreq->count;
 		aio_complete(dreq->iocb, res, 0);
 	}
+
 	complete_all(&dreq->completion);
 
 	nfs_direct_req_release(dreq);
@@ -273,7 +290,7 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	}
 out_put:
 	if (put_dreq(dreq))
-		nfs_direct_complete(dreq);
+		nfs_direct_complete(dreq, false);
 	hdr->release(hdr);
 }
 
@@ -403,6 +420,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 					      loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
+	struct inode *inode = dreq->inode;
 	ssize_t result = -EINVAL;
 	size_t requested_bytes = 0;
 	unsigned long seg;
@@ -411,6 +429,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
 	desc.pg_dreq = dreq;
+	atomic_inc(&inode->i_dio_count);
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
@@ -430,12 +449,13 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
+		inode_dio_done(inode);
 		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
 
 	if (put_dreq(dreq))
-		nfs_direct_complete(dreq);
+		nfs_direct_complete(dreq, false);
 	return 0;
 }
 
@@ -473,12 +493,6 @@ out:
 	return result;
 }
 
-static void nfs_inode_dio_write_done(struct inode *inode)
-{
-	nfs_zap_mapping(inode, inode->i_mapping);
-	inode_dio_done(inode);
-}
-
 #if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
@@ -594,8 +608,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work)
 			nfs_direct_write_reschedule(dreq);
 			break;
 		default:
-			nfs_inode_dio_write_done(dreq->inode);
-			nfs_direct_complete(dreq);
+			nfs_direct_complete(dreq, true);
 	}
 }
 
@@ -611,8 +624,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work)
 
 static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
 {
-	nfs_inode_dio_write_done(inode);
-	nfs_direct_complete(dreq);
+	nfs_direct_complete(dreq, true);
 }
 #endif
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 0ee22ab..fdeeb28 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -988,11 +988,11 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 		if (ret < 0)
 			return ret;
 	}
-	spin_lock(&inode->i_lock);
-	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode)) {
+		spin_lock(&inode->i_lock);
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
-	spin_unlock(&inode->i_lock);
+		spin_unlock(&inode->i_lock);
+	}
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
 	nfs_fscache_wait_on_invalidate(inode);
 
@@ -1018,6 +1018,7 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
+	unsigned long *bitlock = &nfsi->flags;
 	int ret = 0;
 
 	/* swapfiles are not supposed to be shared. */
@@ -1029,12 +1030,46 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 		if (ret < 0)
 			goto out;
 	}
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
-		trace_nfs_invalidate_mapping_enter(inode);
-		ret = nfs_invalidate_mapping(inode, mapping);
-		trace_nfs_invalidate_mapping_exit(inode, ret);
+
+	/*
+	 * We must clear NFS_INO_INVALID_DATA first to ensure that
+	 * invalidations that come in while we're shooting down the mappings
+	 * are respected. But, that leaves a race window where one revalidator
+	 * can clear the flag, and then another checks it before the mapping
+	 * gets invalidated. Fix that by serializing access to this part of
+	 * the function.
+	 *
+	 * At the same time, we need to allow other tasks to see whether we
+	 * might be in the middle of invalidating the pages, so we only set
+	 * the bit lock here if it looks like we're going to be doing that.
+	 */
+	for (;;) {
+		ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
+				  nfs_wait_bit_killable, TASK_KILLABLE);
+		if (ret)
+			goto out;
+		spin_lock(&inode->i_lock);
+		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+			break;
+		spin_unlock(&inode->i_lock);
+		goto out;
 	}
 
+	set_bit(NFS_INO_INVALIDATING, bitlock);
+	smp_wmb();
+	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+	spin_unlock(&inode->i_lock);
+	trace_nfs_invalidate_mapping_enter(inode);
+	ret = nfs_invalidate_mapping(inode, mapping);
+	trace_nfs_invalidate_mapping_exit(inode, ret);
+
+	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
+	smp_mb__after_clear_bit();
+	wake_up_bit(bitlock, NFS_INO_INVALIDATING);
 out:
 	return ret;
 }
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 4a1aafb..4612291 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -289,8 +289,8 @@ getout:
 	return acl;
 }
 
-static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
-		  struct posix_acl *dfacl)
+static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+			       struct posix_acl *dfacl)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs_fattr *fattr;
@@ -373,6 +373,15 @@ out:
 	return status;
 }
 
+int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+		struct posix_acl *dfacl)
+{
+	int ret;
+	ret = __nfs3_proc_setacls(inode, acl, dfacl);
+	return (ret == -EOPNOTSUPP) ? 0 : ret;
+
+}
+
 int nfs3_proc_setacl(struct inode *inode, int type, struct posix_acl *acl)
 {
 	struct posix_acl *alloc = NULL, *dfacl = NULL;
@@ -406,7 +415,7 @@ int nfs3_proc_setacl(struct inode *inode, int type, struct posix_acl *acl)
 		if (IS_ERR(alloc))
 			goto fail;
 	}
-	status = nfs3_proc_setacls(inode, acl, dfacl);
+	status = __nfs3_proc_setacls(inode, acl, dfacl);
 	posix_acl_release(alloc);
 	return status;
 
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 28842ab..fdfd591 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -249,6 +249,7 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 extern int nfs41_setup_sequence(struct nfs4_session *session,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		struct rpc_task *task);
+extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
 extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index b86464b..394b0a0 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -335,8 +335,11 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
 	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
 
 	if (test_bit(NFS_IOHDR_REDO, &rdata->header->flags) &&
-	    task->tk_status == 0)
+	    task->tk_status == 0) {
+		if (rdata->res.seq_res.sr_slot != NULL)
+			nfs41_sequence_done(task, &rdata->res.seq_res);
 		return;
+	}
 
 	/* Note this may cause RPC to be resent */
 	rdata->header->mds_ops->rpc_call_done(task, data);
@@ -442,8 +445,11 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
 	struct nfs_write_data *wdata = data;
 
 	if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
-	    task->tk_status == 0)
+	    task->tk_status == 0) {
+		if (wdata->res.seq_res.sr_slot != NULL)
+			nfs41_sequence_done(task, &wdata->res.seq_res);
 		return;
+	}
 
 	/* Note this may cause RPC to be resent */
 	wdata->header->mds_ops->rpc_call_done(task, data);
@@ -1216,17 +1222,17 @@ static void filelayout_recover_commit_reqs(struct list_head *dst,
 	struct pnfs_commit_bucket *b;
 	int i;
 
-	/* NOTE cinfo->lock is NOT held, relying on fact that this is
-	 * only called on single thread per dreq.
-	 * Can't take the lock because need to do pnfs_put_lseg
-	 */
+	spin_lock(cinfo->lock);
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
 		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
+			spin_unlock(cinfo->lock);
 			pnfs_put_lseg(b->wlseg);
 			b->wlseg = NULL;
+			spin_lock(cinfo->lock);
 		}
 	}
 	cinfo->ds->nwritten = 0;
+	spin_unlock(cinfo->lock);
 }
 
 static unsigned int
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index c7c295e5..efac602 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -95,7 +95,7 @@ same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
 		b6 = (struct sockaddr_in6 *)addr2;
 
 		/* LINKLOCAL addresses must have matching scope_id */
-		if (ipv6_addr_scope(&a6->sin6_addr) ==
+		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
 		    IPV6_ADDR_SCOPE_LINKLOCAL &&
 		    a6->sin6_scope_id != b6->sin6_scope_id)
 			return false;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a536517..bcd42fb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -585,7 +585,7 @@ out_unlock:
 		nfs41_server_notify_highest_slotid_update(session->clp);
 }
 
-static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
 	struct nfs4_session *session;
 	struct nfs4_slot *slot;
@@ -685,6 +685,7 @@ out_retry:
 	rpc_delay(task, NFS4_POLL_RETRY_MAX);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs41_sequence_done);
 
 static int nfs4_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)
@@ -5779,21 +5780,20 @@ struct nfs_release_lockowner_data {
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server;
 	struct nfs_release_lockowner_args args;
-	struct nfs4_sequence_args seq_args;
-	struct nfs4_sequence_res seq_res;
+	struct nfs_release_lockowner_res res;
 };
 
 static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs_release_lockowner_data *data = calldata;
 	nfs40_setup_sequence(data->server,
-				&data->seq_args, &data->seq_res, task);
+				&data->args.seq_args, &data->res.seq_res, task);
 }
 
 static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs_release_lockowner_data *data = calldata;
-	nfs40_sequence_done(task, &data->seq_res);
+	nfs40_sequence_done(task, &data->res.seq_res);
 }
 
 static void nfs4_release_lockowner_release(void *calldata)
@@ -5822,7 +5822,6 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
 	data = kmalloc(sizeof(*data), GFP_NOFS);
 	if (!data)
 		return -ENOMEM;
-	nfs4_init_sequence(&data->seq_args, &data->seq_res, 0);
 	data->lsp = lsp;
 	data->server = server;
 	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
@@ -5830,6 +5829,8 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
 	data->args.lock_owner.s_dev = server->s_dev;
 
 	msg.rpc_argp = &data->args;
+	msg.rpc_resp = &data->res;
+	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
 	rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
 	return 0;
 }
@@ -7273,7 +7274,14 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		return;
 
 	server = NFS_SERVER(lrp->args.inode);
-	if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+	switch (task->tk_status) {
+	default:
+		task->tk_status = 0;
+	case 0:
+		break;
+	case -NFS4ERR_DELAY:
+		if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN)
+			break;
 		rpc_restart_call_prepare(task);
 		return;
 	}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b2f842d..1c2beb1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3405,7 +3405,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint
 {
 	__be32 *p;
 
-	*res = ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL;
+	*res = 0;
 	if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U)))
 		return -EIO;
 	if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) {
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 89fe741..59f838c 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -36,6 +36,7 @@
 	__print_flags(v, "|", \
 			{ 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \
 			{ 1 << NFS_INO_STALE, "STALE" }, \
+			{ 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
 			{ 1 << NFS_INO_FLUSHING, "FLUSHING" }, \
 			{ 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
 			{ 1 << NFS_INO_COMMIT, "COMMIT" }, \
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 28466be..c6aa89f 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -909,9 +909,14 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx)
  */
 static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 {
+	struct nfs_inode *nfsi = NFS_I(inode);
+
 	if (nfs_have_delegated_attributes(inode))
 		goto out;
-	if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+	if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+		return false;
+	smp_rmb();
+	if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
 		return false;
 out:
 	return PageUptodate(page) != 0;