Merge tag 'nfsd-5.12-2' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd fixes from Chuck Lever:
 "Miscellaneous NFSD fixes for v5.12-rc"

* tag 'nfsd-5.12-2' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux:
  svcrdma: Revert "svcrdma: Reduce Receive doorbell rate"
  NFSD: fix error handling in NFSv4.0 callbacks
  NFSD: fix dest to src mount in inter-server COPY
  Revert "nfsd4: a client's own opens needn't prevent delegations"
  Revert "nfsd4: remove check_conflicting_opens warning"
  rpc: fix NULL dereference on kmalloc failure
  sunrpc: fix refcount leak for rpc auth modules
  NFSD: Repair misuse of sv_lock in 5.10.16-rt30.
  nfsd: don't abort copies early
  fs: nfsd: fix kconfig dependency warning for NFSD_V4
  svcrdma: disable timeouts on rdma backchannel
  nfsd: Don't keep looking up unhashed files in the nfsd file cache

12 files changed, 75 insertions, 99 deletions

diff --git a/fs/locks.c b/fs/locks.c
index 99ca97e81b7a..6125d2de39b8 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1808,9 +1808,6 @@ check_conflicting_open(struct file *filp, const long arg, int flags)
 
 	if (flags & FL_LAYOUT)
 		return 0;
-	if (flags & FL_DELEG)
-		/* We leave these checks to the caller. */
-		return 0;
 
 	if (arg == F_RDLCK)
 		return inode_is_open_for_write(inode) ? -EAGAIN : 0;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 821e5913faee..d6cff5fbe705 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -73,6 +73,7 @@ config NFSD_V4
 	select NFSD_V3
 	select FS_POSIX_ACL
 	select SUNRPC_GSS
+	select CRYPTO
 	select CRYPTO_MD5
 	select CRYPTO_SHA256
 	select GRACE_PERIOD
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 53fcbf79bdca..7629248fdd53 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -898,6 +898,8 @@ nfsd_file_find_locked(struct inode *inode, unsigned int may_flags,
 			continue;
 		if (!nfsd_match_cred(nf->nf_cred, current_cred()))
 			continue;
+		if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags))
+			continue;
 		if (nfsd_file_get(nf) != NULL)
 			return nf;
 	}
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 052be5bf9ef5..7325592b456e 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1189,6 +1189,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
 		switch (task->tk_status) {
 		case -EIO:
 		case -ETIMEDOUT:
+		case -EACCES:
 			nfsd4_mark_cb_down(clp, task->tk_status);
 		}
 		break;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index acdb3cd806a1..dd9f38d072dd 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1302,7 +1302,7 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
 			struct nfsd_file *dst)
 {
 	nfs42_ssc_close(src->nf_file);
-	/* 'src' is freed by nfsd4_do_async_copy */
+	fput(src->nf_file);
 	nfsd_file_put(dst);
 	mntput(ss_mnt);
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 423fd6683f3a..97447a64bad0 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4940,31 +4940,6 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 	return fl;
 }
 
-static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
-						struct nfs4_file *fp)
-{
-	struct nfs4_clnt_odstate *co;
-	struct file *f = fp->fi_deleg_file->nf_file;
-	struct inode *ino = locks_inode(f);
-	int writes = atomic_read(&ino->i_writecount);
-
-	if (fp->fi_fds[O_WRONLY])
-		writes--;
-	if (fp->fi_fds[O_RDWR])
-		writes--;
-	if (writes > 0)
-		return -EAGAIN;
-	spin_lock(&fp->fi_lock);
-	list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
-		if (co->co_client != clp) {
-			spin_unlock(&fp->fi_lock);
-			return -EAGAIN;
-		}
-	}
-	spin_unlock(&fp->fi_lock);
-	return 0;
-}
-
 static struct nfs4_delegation *
 nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		    struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
@@ -4984,12 +4959,9 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 
 	nf = find_readable_file(fp);
 	if (!nf) {
-		/*
-		 * We probably could attempt another open and get a read
-		 * delegation, but for now, don't bother until the
-		 * client actually sends us one.
-		 */
-		return ERR_PTR(-EAGAIN);
+		/* We should always have a readable file here */
+		WARN_ON_ONCE(1);
+		return ERR_PTR(-EBADF);
 	}
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -5019,19 +4991,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 	if (!fl)
 		goto out_clnt_odstate;
 
-	status = nfsd4_check_conflicting_opens(clp, fp);
-	if (status) {
-		locks_free_lock(fl);
-		goto out_clnt_odstate;
-	}
 	status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
 	if (fl)
 		locks_free_lock(fl);
 	if (status)
 		goto out_clnt_odstate;
-	status = nfsd4_check_conflicting_opens(clp, fp);
-	if (status)
-		goto out_clnt_odstate;
 
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -5113,6 +5077,17 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
 				goto out_no_deleg;
 			if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
 				goto out_no_deleg;
+			/*
+			 * Also, if the file was opened for write or
+			 * create, there's a good chance the client's
+			 * about to write to it, resulting in an
+			 * immediate recall (since we don't support
+			 * write delegations):
+			 */
+			if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
+				goto out_no_deleg;
+			if (open->op_create == NFS4_OPEN_CREATE)
+				goto out_no_deleg;
 			break;
 		default:
 			goto out_no_deleg;
@@ -5389,7 +5364,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
 		cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
 		if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
-				cps->cpntf_time > cutoff)
+				cps->cpntf_time < cutoff)
 			_free_cpntf_state_locked(nn, cps);
 	}
 	spin_unlock(&nn->s2s_cp_lock);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 7c693b31965e..1e76ed688044 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -104,7 +104,6 @@ struct svcxprt_rdma {
 
 	wait_queue_head_t    sc_send_wait;	/* SQ exhaustion waitlist */
 	unsigned long	     sc_flags;
-	u32		     sc_pending_recvs;
 	struct list_head     sc_read_complete_q;
 	struct work_struct   sc_work;
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index bd4678db9d76..6dff64374bfe 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1825,11 +1825,14 @@ static int
 svcauth_gss_release(struct svc_rqst *rqstp)
 {
 	struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data;
-	struct rpc_gss_wire_cred *gc = &gsd->clcred;
+	struct rpc_gss_wire_cred *gc;
 	struct xdr_buf *resbuf = &rqstp->rq_res;
 	int stat = -EINVAL;
 	struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id);
 
+	if (!gsd)
+		goto out;
+	gc = &gsd->clcred;
 	if (gc->gc_proc != RPC_GSS_PROC_DATA)
 		goto out;
 	/* Release can be called twice, but we only wrap once. */
@@ -1870,10 +1873,10 @@ out_err:
 	if (rqstp->rq_cred.cr_group_info)
 		put_group_info(rqstp->rq_cred.cr_group_info);
 	rqstp->rq_cred.cr_group_info = NULL;
-	if (gsd->rsci)
+	if (gsd && gsd->rsci) {
 		cache_put(&gsd->rsci->h, sn->rsc_cache);
-	gsd->rsci = NULL;
-
+		gsd->rsci = NULL;
+	}
 	return stat;
 }
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 61fb8a18552c..d76dc9d95d16 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1413,7 +1413,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 
  sendit:
 	if (svc_authorise(rqstp))
-		goto close;
+		goto close_xprt;
 	return 1;		/* Caller can now send it */
 
 release_dropit:
@@ -1425,6 +1425,8 @@ release_dropit:
 	return 0;
 
  close:
+	svc_authorise(rqstp);
+close_xprt:
 	if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
 		svc_close_xprt(rqstp->rq_xprt);
 	dprintk("svc: svc_process close\n");
@@ -1433,7 +1435,7 @@ release_dropit:
 err_short_len:
 	svc_printk(rqstp, "short len %zd, dropping request\n",
 			argv->iov_len);
-	goto close;
+	goto close_xprt;
 
 err_bad_rpc:
 	serv->sv_stats->rpcbadfmt++;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index dcc50ae54550..3cdd71a8df1e 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1060,7 +1060,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st
 	struct svc_xprt *xprt;
 	int ret = 0;
 
-	spin_lock(&serv->sv_lock);
+	spin_lock_bh(&serv->sv_lock);
 	list_for_each_entry(xprt, xprt_list, xpt_list) {
 		if (xprt->xpt_net != net)
 			continue;
@@ -1068,7 +1068,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
 		svc_xprt_enqueue(xprt);
 	}
-	spin_unlock(&serv->sv_lock);
+	spin_unlock_bh(&serv->sv_lock);
 	return ret;
 }
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 4a1edbb4028e..9150df35fb6f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -252,9 +252,9 @@ xprt_setup_rdma_bc(struct xprt_create *args)
 	xprt->timeout = &xprt_rdma_bc_timeout;
 	xprt_set_bound(xprt);
 	xprt_set_connected(xprt);
-	xprt->bind_timeout = RPCRDMA_BIND_TO;
-	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
-	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
+	xprt->bind_timeout = 0;
+	xprt->reestablish_timeout = 0;
+	xprt->idle_timeout = 0;
 
 	xprt->prot = XPRT_TRANSPORT_BC_RDMA;
 	xprt->ops = &xprt_rdma_bc_procs;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 6d28f23ceb35..7d34290e2ff8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -266,46 +266,33 @@ void svc_rdma_release_rqst(struct svc_rqst *rqstp)
 		svc_rdma_recv_ctxt_put(rdma, ctxt);
 }
 
-static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma,
-				   unsigned int wanted, bool temp)
+static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma,
+				struct svc_rdma_recv_ctxt *ctxt)
 {
-	const struct ib_recv_wr *bad_wr = NULL;
-	struct svc_rdma_recv_ctxt *ctxt;
-	struct ib_recv_wr *recv_chain;
 	int ret;
 
-	recv_chain = NULL;
-	while (wanted--) {
-		ctxt = svc_rdma_recv_ctxt_get(rdma);
-		if (!ctxt)
-			break;
-
-		trace_svcrdma_post_recv(ctxt);
-		ctxt->rc_temp = temp;
-		ctxt->rc_recv_wr.next = recv_chain;
-		recv_chain = &ctxt->rc_recv_wr;
-		rdma->sc_pending_recvs++;
-	}
-	if (!recv_chain)
-		return false;
-
-	ret = ib_post_recv(rdma->sc_qp, recv_chain, &bad_wr);
+	trace_svcrdma_post_recv(ctxt);
+	ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, NULL);
 	if (ret)
 		goto err_post;
-	return true;
+	return 0;
 
 err_post:
-	while (bad_wr) {
-		ctxt = container_of(bad_wr, struct svc_rdma_recv_ctxt,
-				    rc_recv_wr);
-		bad_wr = bad_wr->next;
-		svc_rdma_recv_ctxt_put(rdma, ctxt);
-	}
-
 	trace_svcrdma_rq_post_err(rdma, ret);
-	/* Since we're destroying the xprt, no need to reset
-	 * sc_pending_recvs. */
-	return false;
+	svc_rdma_recv_ctxt_put(rdma, ctxt);
+	return ret;
+}
+
+static int svc_rdma_post_recv(struct svcxprt_rdma *rdma)
+{
+	struct svc_rdma_recv_ctxt *ctxt;
+
+	if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags))
+		return 0;
+	ctxt = svc_rdma_recv_ctxt_get(rdma);
+	if (!ctxt)
+		return -ENOMEM;
+	return __svc_rdma_post_recv(rdma, ctxt);
 }
 
 /**
@@ -316,7 +303,20 @@ err_post:
  */
 bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma)
 {
-	return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests, true);
+	struct svc_rdma_recv_ctxt *ctxt;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < rdma->sc_max_requests; i++) {
+		ctxt = svc_rdma_recv_ctxt_get(rdma);
+		if (!ctxt)
+			return false;
+		ctxt->rc_temp = true;
+		ret = __svc_rdma_post_recv(rdma, ctxt);
+		if (ret)
+			return false;
+	}
+	return true;
 }
 
 /**
@@ -324,6 +324,8 @@ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma)
  * @cq: Completion Queue context
  * @wc: Work Completion object
  *
+ * NB: The svc_xprt/svcxprt_rdma is pinned whenever it's possible that
+ * the Receive completion handler could be running.
  */
 static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 {
@@ -331,8 +333,6 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_recv_ctxt *ctxt;
 
-	rdma->sc_pending_recvs--;
-
 	/* WARNING: Only wc->wr_cqe and wc->status are reliable */
 	ctxt = container_of(cqe, struct svc_rdma_recv_ctxt, rc_cqe);
 
@@ -340,6 +340,9 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	if (wc->status != IB_WC_SUCCESS)
 		goto flushed;
 
+	if (svc_rdma_post_recv(rdma))
+		goto post_err;
+
 	/* All wc fields are now known to be valid */
 	ctxt->rc_byte_len = wc->byte_len;
 
@@ -350,18 +353,11 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	spin_unlock(&rdma->sc_rq_dto_lock);
 	if (!test_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags))
 		svc_xprt_enqueue(&rdma->sc_xprt);
-
-	if (!test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags) &&
-	    rdma->sc_pending_recvs < rdma->sc_max_requests)
-		if (!svc_rdma_refresh_recvs(rdma, RPCRDMA_MAX_RECV_BATCH,
-					    false))
-			goto post_err;
-
 	return;
 
 flushed:
-	svc_rdma_recv_ctxt_put(rdma, ctxt);
 post_err:
+	svc_rdma_recv_ctxt_put(rdma, ctxt);
 	set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
 	svc_xprt_enqueue(&rdma->sc_xprt);
 }