[PATCH AUTOSEL 5.4 058/205] xprtrdma: Connection becomes unstable after a reconnect

[PATCH AUTOSEL 5.4 058/205] xprtrdma: Connection becomes unstable after a reconnect

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit a31b2f939219dd9bffdf01a45bd91f209f8cc369 ]

This is because xprt_request_get_cong() is allowing more than one
RPC Call to be transmitted before the first Receive on the new
connection. The first Receive fills the Receive Queue based on the
server's credit grant. Before that Receive, there is only a single
Receive WR posted because the client doesn't know the server's
credit grant.

Solution is to clear rq_cong on all outstanding rpc_rqsts when the
the cwnd is reset. This is because an RPC/RDMA credit is good for
one connection instance only.

Fixes: 75891f502f5f ("SUNRPC: Support for congestion control ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xprtrdma/transport.c |  3 +++
 net/sunrpc/xprtrdma/verbs.c     | 22 ++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 160558b4135e..c67d465dc062 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -428,8 +428,11 @@ void xprt_rdma_close(struct rpc_xprt *xprt)
 	/* Prepare @xprt for the next connection by reinitializing
 	 * its credit grant to one (see RFC 8166, Section 3.3.3).
 	 */
+	spin_lock(&xprt->transport_lock);
 	r_xprt->rx_buf.rb_credits = 1;
+	xprt->cong = 0;
 	xprt->cwnd = RPC_CWNDSHIFT;
+	spin_unlock(&xprt->transport_lock);
 
 out:
 	xprt->reestablish_timeout = 0;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 3a907537e2cf..f4b136504e96 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -75,6 +75,7 @@
  * internal functions
  */
 static void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc);
+static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt);
 static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf);
 static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt);
 static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf);
@@ -780,6 +781,7 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	trace_xprtrdma_disconnect(r_xprt, rc);
 
 	rpcrdma_xprt_drain(r_xprt);
+	rpcrdma_reqs_reset(r_xprt);
 }
 
 /* Fixed-size circular FIFO queue. This implementation is wait-free and
@@ -1042,6 +1044,26 @@ struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt, size_t size,
 	return NULL;
 }
 
+/**
+ * rpcrdma_reqs_reset - Reset all reqs owned by a transport
+ * @r_xprt: controlling transport instance
+ *
+ * ASSUMPTION: the rb_allreqs list is stable for the duration,
+ * and thus can be walked without holding rb_lock. Eg. the
+ * caller is holding the transport send lock to exclude
+ * device removal or disconnection.
+ */
+static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_req *req;
+
+	list_for_each_entry(req, &buf->rb_allreqs, rl_all) {
+		/* Credits are valid only for one connection */
+		req->rl_slot.rq_cong = 0;
+	}
+}
+
 static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt,
 					      bool temp)
 {
-- 
2.20.1

[PATCH AUTOSEL 5.4 059/205] xprtrdma: Fix MR list handling

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit c3700780a096fc66467c81076ddf7f3f11d639b5 ]

Close some holes introduced by commit 6dc6ec9e04c4 ("xprtrdma: Cache
free MRs in each rpcrdma_req") that could result in list corruption.

In addition, the result that is tabulated in @count is no longer
used, so @count is removed.

Fixes: 6dc6ec9e04c4 ("xprtrdma: Cache free MRs in each rpcrdma_req")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xprtrdma/verbs.c | 41 +++++++++++++++++++------------------
 1 file changed, 21 insertions(+), 20 deletions(-)

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index f4b136504e96..be74ff8f7873 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -79,7 +79,6 @@ static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt);
 static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf);
 static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt);
 static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf);
-static void rpcrdma_mr_free(struct rpcrdma_mr *mr);
 static struct rpcrdma_regbuf *
 rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction,
 		     gfp_t flags);
@@ -967,7 +966,7 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt)
 		mr->mr_xprt = r_xprt;
 
 		spin_lock(&buf->rb_lock);
-		list_add(&mr->mr_list, &buf->rb_mrs);
+		rpcrdma_mr_push(mr, &buf->rb_mrs);
 		list_add(&mr->mr_all, &buf->rb_all_mrs);
 		spin_unlock(&buf->rb_lock);
 	}
@@ -1185,10 +1184,19 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
  */
 void rpcrdma_req_destroy(struct rpcrdma_req *req)
 {
+	struct rpcrdma_mr *mr;
+
 	list_del(&req->rl_all);
 
-	while (!list_empty(&req->rl_free_mrs))
-		rpcrdma_mr_free(rpcrdma_mr_pop(&req->rl_free_mrs));
+	while ((mr = rpcrdma_mr_pop(&req->rl_free_mrs))) {
+		struct rpcrdma_buffer *buf = &mr->mr_xprt->rx_buf;
+
+		spin_lock(&buf->rb_lock);
+		list_del(&mr->mr_all);
+		spin_unlock(&buf->rb_lock);
+
+		frwr_release_mr(mr);
+	}
 
 	rpcrdma_regbuf_free(req->rl_recvbuf);
 	rpcrdma_regbuf_free(req->rl_sendbuf);
@@ -1196,24 +1204,28 @@ void rpcrdma_req_destroy(struct rpcrdma_req *req)
 	kfree(req);
 }
 
-static void
-rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf)
+/**
+ * rpcrdma_mrs_destroy - Release all of a transport's MRs
+ * @buf: controlling buffer instance
+ *
+ * Relies on caller holding the transport send lock to protect
+ * removing mr->mr_list from req->rl_free_mrs safely.
+ */
+static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf)
 {
 	struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt,
 						   rx_buf);
 	struct rpcrdma_mr *mr;
-	unsigned int count;
 
-	count = 0;
 	spin_lock(&buf->rb_lock);
 	while ((mr = list_first_entry_or_null(&buf->rb_all_mrs,
 					      struct rpcrdma_mr,
 					      mr_all)) != NULL) {
+		list_del(&mr->mr_list);
 		list_del(&mr->mr_all);
 		spin_unlock(&buf->rb_lock);
 
 		frwr_release_mr(mr);
-		count++;
 		spin_lock(&buf->rb_lock);
 	}
 	spin_unlock(&buf->rb_lock);
@@ -1286,17 +1298,6 @@ void rpcrdma_mr_put(struct rpcrdma_mr *mr)
 	rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs);
 }
 
-static void rpcrdma_mr_free(struct rpcrdma_mr *mr)
-{
-	struct rpcrdma_xprt *r_xprt = mr->mr_xprt;
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-
-	mr->mr_req = NULL;
-	spin_lock(&buf->rb_lock);
-	rpcrdma_mr_push(mr, &buf->rb_mrs);
-	spin_unlock(&buf->rb_lock);
-}
-
 /**
  * rpcrdma_buffer_get - Get a request buffer
  * @buffers: Buffer pool from which to obtain a buffer
-- 
2.20.1

[PATCH AUTOSEL 5.4 083/205] SUNRPC: Fix svcauth_gss_proxy_init()

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit 5866efa8cbfbadf3905072798e96652faf02dbe8 ]

gss_read_proxy_verf() assumes things about the XDR buffer containing
the RPC Call that are not true for buffers generated by
svc_rdma_recv().

RDMA's buffers look more like what the upper layer generates for
sending: head is a kmalloc'd buffer; it does not point to a page
whose contents are contiguous with the first page in the buffers'
page array. The result is that ACCEPT_SEC_CONTEXT via RPC/RDMA has
stopped working on Linux NFS servers that use gssproxy.

This does not affect clients that use only TCP to send their
ACCEPT_SEC_CONTEXT operation (that's all Linux clients). Other
clients, like Solaris NFS clients, send ACCEPT_SEC_CONTEXT on the
same transport as they send all other NFS operations. Such clients
can send ACCEPT_SEC_CONTEXT via RPC/RDMA.

I thought I had found every direct reference in the server RPC code
to the rqstp->rq_pages field.

Bug found at the 2019 Westford NFS bake-a-thon.

Fixes: 3316f0631139 ("svcrdma: Persistently allocate and DMA- ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Bill Baker <bill.baker@oracle.com>
Reviewed-by: Simo Sorce <simo@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/auth_gss/svcauth_gss.c | 84 +++++++++++++++++++++++--------
 1 file changed, 63 insertions(+), 21 deletions(-)

diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 8be2f209982b..908b60a72d95 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1075,24 +1075,32 @@ gss_read_verf(struct rpc_gss_wire_cred *gc,
 	return 0;
 }
 
-/* Ok this is really heavily depending on a set of semantics in
- * how rqstp is set up by svc_recv and pages laid down by the
- * server when reading a request. We are basically guaranteed that
- * the token lays all down linearly across a set of pages, starting
- * at iov_base in rq_arg.head[0] which happens to be the first of a
- * set of pages stored in rq_pages[].
- * rq_arg.head[0].iov_base will provide us the page_base to pass
- * to the upcall.
- */
-static inline int
-gss_read_proxy_verf(struct svc_rqst *rqstp,
-		    struct rpc_gss_wire_cred *gc, __be32 *authp,
-		    struct xdr_netobj *in_handle,
-		    struct gssp_in_token *in_token)
+static void gss_free_in_token_pages(struct gssp_in_token *in_token)
 {
-	struct kvec *argv = &rqstp->rq_arg.head[0];
 	u32 inlen;
-	int res;
+	int i;
+
+	i = 0;
+	inlen = in_token->page_len;
+	while (inlen) {
+		if (in_token->pages[i])
+			put_page(in_token->pages[i]);
+		inlen -= inlen > PAGE_SIZE ? PAGE_SIZE : inlen;
+	}
+
+	kfree(in_token->pages);
+	in_token->pages = NULL;
+}
+
+static int gss_read_proxy_verf(struct svc_rqst *rqstp,
+			       struct rpc_gss_wire_cred *gc, __be32 *authp,
+			       struct xdr_netobj *in_handle,
+			       struct gssp_in_token *in_token)
+{
+	struct kvec *argv = &rqstp->rq_arg.head[0];
+	unsigned int page_base, length;
+	int pages, i, res;
+	size_t inlen;
 
 	res = gss_read_common_verf(gc, argv, authp, in_handle);
 	if (res)
@@ -1102,10 +1110,36 @@ gss_read_proxy_verf(struct svc_rqst *rqstp,
 	if (inlen > (argv->iov_len + rqstp->rq_arg.page_len))
 		return SVC_DENIED;
 
-	in_token->pages = rqstp->rq_pages;
-	in_token->page_base = (ulong)argv->iov_base & ~PAGE_MASK;
+	pages = DIV_ROUND_UP(inlen, PAGE_SIZE);
+	in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL);
+	if (!in_token->pages)
+		return SVC_DENIED;
+	in_token->page_base = 0;
 	in_token->page_len = inlen;
+	for (i = 0; i < pages; i++) {
+		in_token->pages[i] = alloc_page(GFP_KERNEL);
+		if (!in_token->pages[i]) {
+			gss_free_in_token_pages(in_token);
+			return SVC_DENIED;
+		}
+	}
 
+	length = min_t(unsigned int, inlen, argv->iov_len);
+	memcpy(page_address(in_token->pages[0]), argv->iov_base, length);
+	inlen -= length;
+
+	i = 1;
+	page_base = rqstp->rq_arg.page_base;
+	while (inlen) {
+		length = min_t(unsigned int, inlen, PAGE_SIZE);
+		memcpy(page_address(in_token->pages[i]),
+		       page_address(rqstp->rq_arg.pages[i]) + page_base,
+		       length);
+
+		inlen -= length;
+		page_base = 0;
+		i++;
+	}
 	return 0;
 }
 
@@ -1280,8 +1314,11 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp,
 		break;
 	case GSS_S_COMPLETE:
 		status = gss_proxy_save_rsc(sn->rsc_cache, &ud, &handle);
-		if (status)
+		if (status) {
+			pr_info("%s: gss_proxy_save_rsc failed (%d)\n",
+				__func__, status);
 			goto out;
+		}
 		cli_handle.data = (u8 *)&handle;
 		cli_handle.len = sizeof(handle);
 		break;
@@ -1292,15 +1329,20 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp,
 
 	/* Got an answer to the upcall; use it: */
 	if (gss_write_init_verf(sn->rsc_cache, rqstp,
-				&cli_handle, &ud.major_status))
+				&cli_handle, &ud.major_status)) {
+		pr_info("%s: gss_write_init_verf failed\n", __func__);
 		goto out;
+	}
 	if (gss_write_resv(resv, PAGE_SIZE,
 			   &cli_handle, &ud.out_token,
-			   ud.major_status, ud.minor_status))
+			   ud.major_status, ud.minor_status)) {
+		pr_info("%s: gss_write_resv failed\n", __func__);
 		goto out;
+	}
 
 	ret = SVC_COMPLETE;
 out:
+	gss_free_in_token_pages(&ud.in_token);
 	gssp_free_upcall_data(&ud);
 	return ret;
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 133/205] nfsd: Fix cld_net->cn_tfm initialization

[Sasha Levin]

From: Scott Mayhew <smayhew@redhat.com>

[ Upstream commit 18b9a895e652979b70f9c20565394a69354dfebc ]

Don't assign an error pointer to cld_net->cn_tfm, otherwise an oops will
occur in nfsd4_remove_cld_pipe().

Also, move the initialization of cld_net->cn_tfm so that it occurs after
the check to see if nfsdcld is running.  This is necessary because
nfsd4_client_tracking_init() looks for -ETIMEDOUT to determine whether
to use the "old" nfsdcld tracking ops.

Fixes: 6ee95d1c8991 ("nfsd: add support for upcall version 2")
Reported-by: Jamie Heilman <jamie@audible.transient.net>
Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfsd/nfs4recover.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index cdc75ad4438b..c35c0ebaf722 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1578,6 +1578,7 @@ nfsd4_cld_tracking_init(struct net *net)
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	bool running;
 	int retries = 10;
+	struct crypto_shash *tfm;
 
 	status = nfs4_cld_state_init(net);
 	if (status)
@@ -1586,11 +1587,6 @@ nfsd4_cld_tracking_init(struct net *net)
 	status = __nfsd4_init_cld_pipe(net);
 	if (status)
 		goto err_shutdown;
-	nn->cld_net->cn_tfm = crypto_alloc_shash("sha256", 0, 0);
-	if (IS_ERR(nn->cld_net->cn_tfm)) {
-		status = PTR_ERR(nn->cld_net->cn_tfm);
-		goto err_remove;
-	}
 
 	/*
 	 * rpc pipe upcalls take 30 seconds to time out, so we don't want to
@@ -1607,6 +1603,12 @@ nfsd4_cld_tracking_init(struct net *net)
 		status = -ETIMEDOUT;
 		goto err_remove;
 	}
+	tfm = crypto_alloc_shash("sha256", 0, 0);
+	if (IS_ERR(tfm)) {
+		status = PTR_ERR(tfm);
+		goto err_remove;
+	}
+	nn->cld_net->cn_tfm = tfm;
 
 	status = nfsd4_cld_get_version(nn);
 	if (status == -EOPNOTSUPP)
-- 
2.20.1

[PATCH AUTOSEL 5.4 134/205] nfsd: v4 support requires CRYPTO_SHA256

[Sasha Levin]

From: Scott Mayhew <smayhew@redhat.com>

[ Upstream commit a2e2f2dc77a18d2b0f450fb7fcb4871c9f697822 ]

The new nfsdcld client tracking operations use sha256 to compute hashes
of the kerberos principals, so make sure CRYPTO_SHA256 is enabled.

Fixes: 6ee95d1c8991 ("nfsd: add support for upcall version 2")
Reported-by: Jamie Heilman <jamie@audible.transient.net>
Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfsd/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 10cefb0c07c7..c4b1a89b8845 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -73,7 +73,7 @@ config NFSD_V4
 	select NFSD_V3
 	select FS_POSIX_ACL
 	select SUNRPC_GSS
-	select CRYPTO
+	select CRYPTO_SHA256
 	select GRACE_PERIOD
 	help
 	  This option enables support in your system's NFS server for
-- 
2.20.1

[PATCH AUTOSEL 5.4 140/205] NFSv4.x: Handle bad/dead sessions correctly in nfs41_sequence_process()

[Sasha Levin]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

[ Upstream commit 5c441544f045e679afd6c3c6d9f7aaf5fa5f37b0 ]

If the server returns a bad or dead session error, the we don't want
to update the session slot number, but just immediately schedule
recovery and allow it to proceed.

We can/should then remove handling in other places

Fixes: 3453d5708b33 ("NFSv4.1: Avoid false retries when RPC calls are interrupted")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfs/nfs4proc.c | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index caacf5e7f5e1..a591aaf31071 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -521,9 +521,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_DEADSESSION:
 		case -NFS4ERR_SEQ_FALSE_RETRY:
 		case -NFS4ERR_SEQ_MISORDERED:
-			dprintk("%s ERROR: %d Reset session\n", __func__,
-				errorcode);
-			nfs4_schedule_session_recovery(clp->cl_session, errorcode);
+			/* Handled in nfs41_sequence_process() */
 			goto wait_on_recovery;
 #endif /* defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
@@ -782,6 +780,7 @@ static int nfs41_sequence_process(struct rpc_task *task,
 	struct nfs4_session *session;
 	struct nfs4_slot *slot = res->sr_slot;
 	struct nfs_client *clp;
+	int status;
 	int ret = 1;
 
 	if (slot == NULL)
@@ -793,8 +792,13 @@ static int nfs41_sequence_process(struct rpc_task *task,
 	session = slot->table->session;
 
 	trace_nfs4_sequence_done(session, res);
+
+	status = res->sr_status;
+	if (task->tk_status == -NFS4ERR_DEADSESSION)
+		status = -NFS4ERR_DEADSESSION;
+
 	/* Check the SEQUENCE operation status */
-	switch (res->sr_status) {
+	switch (status) {
 	case 0:
 		/* Mark this sequence number as having been acked */
 		nfs4_slot_sequence_acked(slot, slot->seq_nr);
@@ -866,6 +870,10 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		 */
 		slot->seq_nr = slot->seq_nr_highest_sent;
 		goto out_retry;
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		goto session_recover;
 	default:
 		/* Just update the slot sequence no. */
 		slot->seq_done = 1;
@@ -876,8 +884,10 @@ static int nfs41_sequence_process(struct rpc_task *task,
 out_noaction:
 	return ret;
 session_recover:
-	nfs4_schedule_session_recovery(session, res->sr_status);
-	goto retry_nowait;
+	nfs4_schedule_session_recovery(session, status);
+	dprintk("%s ERROR: %d Reset session\n", __func__, status);
+	nfs41_sequence_free_slot(res);
+	goto out;
 retry_new_seq:
 	++slot->seq_nr;
 retry_nowait:
@@ -2188,7 +2198,6 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 		case -NFS4ERR_BAD_HIGH_SLOT:
 		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 		case -NFS4ERR_DEADSESSION:
-			nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
 			return -EAGAIN;
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_STALE_STATEID:
@@ -7820,6 +7829,15 @@ nfs41_same_server_scope(struct nfs41_server_scope *a,
 static void
 nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 {
+	struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+	struct nfs_client *clp = args->client;
+
+	switch (task->tk_status) {
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+		nfs4_schedule_session_recovery(clp->cl_session,
+				task->tk_status);
+	}
 }
 
 static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
@@ -8867,8 +8885,6 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 	case -NFS4ERR_BADSESSION:
 	case -NFS4ERR_DEADSESSION:
 	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-		nfs4_schedule_session_recovery(clp->cl_session,
-				task->tk_status);
 		break;
 	default:
 		nfs4_schedule_lease_recovery(clp);
-- 
2.20.1

[PATCH AUTOSEL 5.4 149/205] SUNRPC: Fix another issue with MIC buffer space

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit e8d70b321ecc9b23d09b8df63e38a2f73160c209 ]

xdr_shrink_pagelen() BUG's when @len is larger than buf->page_len.
This can happen when xdr_buf_read_mic() is given an xdr_buf with
a small page array (like, only a few bytes).

Instead, just cap the number of bytes that xdr_shrink_pagelen()
will move.

Fixes: 5f1bc39979d ("SUNRPC: Fix buffer handling of GSS MIC ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xdr.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 14ba9e72a204..f3104be8ff5d 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -436,13 +436,12 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len)
 }
 
 /**
- * xdr_shrink_pagelen
+ * xdr_shrink_pagelen - shrinks buf->pages by up to @len bytes
  * @buf: xdr_buf
  * @len: bytes to remove from buf->pages
  *
- * Shrinks XDR buffer's page array buf->pages by
- * 'len' bytes. The extra data is not lost, but is instead
- * moved into the tail.
+ * The extra data is not lost, but is instead moved into buf->tail.
+ * Returns the actual number of bytes moved.
  */
 static unsigned int
 xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
@@ -455,8 +454,8 @@ xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
 
 	result = 0;
 	tail = buf->tail;
-	BUG_ON (len > pglen);
-
+	if (len > buf->page_len)
+		len = buf-> page_len;
 	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;
 
 	/* Shift the tail first */
-- 
2.20.1

[PATCH AUTOSEL 5.4 165/205] SUNRPC: Fix backchannel latency metrics

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit 8729aaba74626c4ebce3abf1b9e96bb62d2958ca ]

I noticed that for callback requests, the reported backlog latency
is always zero, and the rtt value is crazy big. The problem was that
rqst->rq_xtime is never set for backchannel requests.

Fixes: 78215759e20d ("SUNRPC: Make RTT measurement more ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 1 +
 net/sunrpc/xprtsock.c                      | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index d1fcc41d5eb5..908e78bb87c6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -195,6 +195,7 @@ rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst)
 	pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer);
 #endif
 
+	rqst->rq_xtime = ktime_get();
 	rc = svc_rdma_bc_sendto(rdma, rqst, ctxt);
 	if (rc) {
 		svc_rdma_send_ctxt_put(rdma, ctxt);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 70e52f567b2a..5361b98f31ae 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2659,6 +2659,8 @@ static int bc_sendto(struct rpc_rqst *req)
 		.iov_len	= sizeof(marker),
 	};
 
+	req->rq_xtime = ktime_get();
+
 	len = kernel_sendmsg(transport->sock, &msg, &iov, 1, iov.iov_len);
 	if (len != iov.iov_len)
 		return -EAGAIN;
@@ -2684,7 +2686,6 @@ static int bc_send_request(struct rpc_rqst *req)
 	struct svc_xprt	*xprt;
 	int len;
 
-	dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid));
 	/*
 	 * Get the server socket associated with this callback xprt
 	 */
-- 
2.20.1

[PATCH AUTOSEL 5.4 198/205] NFSD fixing possible null pointer derefering in copy offload

[Sasha Levin]

From: Olga Kornievskaia <olga.kornievskaia@gmail.com>

[ Upstream commit 18f428d4e2f7eff162d80b2b21689496c4e82afd ]

Static checker revealed possible error path leading to possible
NULL pointer dereferencing.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: e0639dc5805a: ("NFSD introduce async copy feature")
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfsd/nfs4proc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 38c0aeda500e..4798667af647 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1298,7 +1298,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 out:
 	return status;
 out_err:
-	cleanup_async_copy(async_copy);
+	if (async_copy)
+		cleanup_async_copy(async_copy);
 	goto out;
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 199/205] nfsd: depend on CRYPTO_MD5 for legacy client tracking

[Sasha Levin]

From: Patrick Steinhardt <ps@pks.im>

[ Upstream commit 38a2204f5298620e8a1c3b1dc7b831425106dbc0 ]

The legacy client tracking infrastructure of nfsd makes use of MD5 to
derive a client's recovery directory name. As the nfsd module doesn't
declare any dependency on CRYPTO_MD5, though, it may fail to allocate
the hash if the kernel was compiled without it. As a result, generation
of client recovery directories will fail with the following error:

    NFSD: unable to generate recoverydir name

The explicit dependency on CRYPTO_MD5 was removed as redundant back in
6aaa67b5f3b9 (NFSD: Remove redundant "select" clauses in fs/Kconfig
2008-02-11) as it was already implicitly selected via RPCSEC_GSS_KRB5.
This broke when RPCSEC_GSS_KRB5 was made optional for NFSv4 in commit
df486a25900f (NFS: Fix the selection of security flavours in Kconfig) at
a later point.

Fix the issue by adding back an explicit dependency on CRYPTO_MD5.

Fixes: df486a25900f (NFS: Fix the selection of security flavours in Kconfig)
Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfsd/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index c4b1a89b8845..f2f81561ebb6 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_MD5
 	select CRYPTO_SHA256
 	select GRACE_PERIOD
 	help
-- 
2.20.1