From 2b477c00f3bd87c3286f5940cb4174d8b01ee0d5 Mon Sep 17 00:00:00 2001
From: Neil Brown <neilb@suse.com>
Date: Thu, 22 Dec 2016 12:38:06 -0500
Subject: svcrpc: free contexts immediately on PROC_DESTROY

We currently handle a client PROC_DESTROY request by turning it
CACHE_NEGATIVE, setting the expired time to now, and then waiting for
cache_clean to clean it up later.  Since we forgot to set the cache's
nextcheck value, that could take up to 30 minutes.  Also, though there's
probably no real bug in this case, setting CACHE_NEGATIVE directly like
this probably isn't a great idea in general.

So let's just remove the entry from the cache directly, and move this
bit of cache manipulation to a helper function.

Signed-off-by: Neil Brown <neilb@suse.com>
Reported-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 net/sunrpc/auth_gss/svcauth_gss.c |  4 ++--
 net/sunrpc/cache.c                | 12 ++++++++++++
 2 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 153082598522..a54a7a3d28f5 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1489,8 +1489,8 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 	case RPC_GSS_PROC_DESTROY:
 		if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq))
 			goto auth_err;
-		rsci->h.expiry_time = seconds_since_boot();
-		set_bit(CACHE_NEGATIVE, &rsci->h.flags);
+		/* Delete the entry from the cache_list and call cache_put */
+		sunrpc_cache_unhash(sn->rsc_cache, &rsci->h);
 		if (resv->iov_len + 4 > PAGE_SIZE)
 			goto drop;
 		svc_putnl(resv, RPC_SUCCESS);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 8147e8d56eb2..502b9fe9817b 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1855,3 +1855,15 @@ void sunrpc_cache_unregister_pipefs(struct cache_detail *cd)
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs);
 
+void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h)
+{
+	write_lock(&cd->hash_lock);
+	if (!hlist_unhashed(&h->cache_list)){
+		hlist_del_init(&h->cache_list);
+		cd->entries--;
+		write_unlock(&cd->hash_lock);
+		cache_put(h, cd);
+	} else
+		write_unlock(&cd->hash_lock);
+}
+EXPORT_SYMBOL_GPL(sunrpc_cache_unhash);
-- 
cgit v1.2.3


From cbaf58032efca401834518b905f528ac912449e4 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Feb 2017 11:58:15 -0500
Subject: svcrdma: Another sendto chunk list parsing update

Commit 5fdca6531434 ("svcrdma: Renovate sendto chunk list parsing")
missed a spot. svc_rdma_xdr_get_reply_hdr_len() also assumes the
Write list has only one Write chunk. There's no harm in making this
code more general.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/rpc_rdma.h        |  9 +++++++
 include/linux/sunrpc/svc_rdma.h        |  2 +-
 net/sunrpc/xprtrdma/svc_rdma_marshal.c | 49 ++++++++++++++++++----------------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c  |  3 ++-
 4 files changed, 38 insertions(+), 25 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index cfda6adcf33c..245fc59b7324 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -109,6 +109,15 @@ struct rpcrdma_msg {
 	} rm_body;
 };
 
+/*
+ * XDR sizes, in quads
+ */
+enum {
+	rpcrdma_fixed_maxsz	= 4,
+	rpcrdma_segment_maxsz	= 4,
+	rpcrdma_readchunk_maxsz	= 2 + rpcrdma_segment_maxsz,
+};
+
 /*
  * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks
  */
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 757fb963696c..551c51816352 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -218,7 +218,7 @@ extern void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *,
 					     struct rpcrdma_msg *,
 					     struct rpcrdma_msg *,
 					     enum rpcrdma_proc);
-extern int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *);
+extern unsigned int svc_rdma_xdr_get_reply_hdr_len(__be32 *rdma_resp);
 
 /* svc_rdma_recvfrom.c */
 extern int svc_rdma_recvfrom(struct svc_rqst *);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 0ba9887f3e22..4e7203439e2f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -260,32 +260,35 @@ int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt,
 	return (int)((unsigned long)va - (unsigned long)startp);
 }
 
-int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp)
+/**
+ * svc_rdma_xdr_get_reply_hdr_length - Get length of Reply transport header
+ * @rdma_resp: buffer containing Reply transport header
+ *
+ * Returns length of transport header, in bytes.
+ */
+unsigned int svc_rdma_xdr_get_reply_hdr_len(__be32 *rdma_resp)
 {
-	struct rpcrdma_write_array *wr_ary;
+	unsigned int nsegs;
+	__be32 *p;
 
-	/* There is no read-list in a reply */
+	p = rdma_resp;
 
-	/* skip write list */
-	wr_ary = (struct rpcrdma_write_array *)
-		&rmsgp->rm_body.rm_chunks[1];
-	if (wr_ary->wc_discrim)
-		wr_ary = (struct rpcrdma_write_array *)
-			&wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)].
-			wc_target.rs_length;
-	else
-		wr_ary = (struct rpcrdma_write_array *)
-			&wr_ary->wc_nchunks;
-
-	/* skip reply array */
-	if (wr_ary->wc_discrim)
-		wr_ary = (struct rpcrdma_write_array *)
-			&wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)];
-	else
-		wr_ary = (struct rpcrdma_write_array *)
-			&wr_ary->wc_nchunks;
-
-	return (unsigned long) wr_ary - (unsigned long) rmsgp;
+	/* RPC-over-RDMA V1 replies never have a Read list. */
+	p += rpcrdma_fixed_maxsz + 1;
+
+	/* Skip Write list. */
+	while (*p++ != xdr_zero) {
+		nsegs = be32_to_cpup(p++);
+		p += nsegs * rpcrdma_segment_maxsz;
+	}
+
+	/* Skip Reply chunk. */
+	if (*p++ != xdr_zero) {
+		nsegs = be32_to_cpup(p++);
+		p += nsegs * rpcrdma_segment_maxsz;
+	}
+
+	return (unsigned long)p - (unsigned long)rdma_resp;
 }
 
 void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *rmsgp, int chunks)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index ad4d286a83c5..ba76f1617965 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -476,7 +476,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
 
 	/* Prepare the SGE for the RPCRDMA Header */
 	ctxt->sge[0].lkey = rdma->sc_pd->local_dma_lkey;
-	ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
+	ctxt->sge[0].length =
+	    svc_rdma_xdr_get_reply_hdr_len((__be32 *)rdma_resp);
 	ctxt->sge[0].addr =
 	    ib_dma_map_page(rdma->sc_cm_id->device, page, 0,
 			    ctxt->sge[0].length, DMA_TO_DEVICE);
-- 
cgit v1.2.3


From 98fc21d3bfd55a36ce9eb7b32d1ce146f0d1696d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Feb 2017 11:58:23 -0500
Subject: svcrdma: Clean up RPC-over-RDMA Reply header encoder

Replace C structure-based XDR decoding with pointer arithmetic.
Pointer arithmetic is considered more portable, and is used
throughout the kernel's existing XDR encoders. The gcc optimizer
generates similar assembler code either way.

Byte-swapping before a memory store on x86 typically results in an
instruction pipeline stall. Avoid byte-swapping when encoding a new
header.

svcrdma currently doesn't alter a connection's credit grant value
after the connection has been accepted, so it is effectively a
constant. Cache the byte-swapped value in a separate field.

Christoph suggested pulling the header encoding logic into the only
function that uses it.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          |  7 ++-----
 net/sunrpc/xprtrdma/svc_rdma_marshal.c   | 18 +-----------------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c    | 19 ++++++++++++-------
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  1 +
 4 files changed, 16 insertions(+), 29 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 551c51816352..25ecf92cae96 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -141,7 +141,8 @@ struct svcxprt_rdma {
 	atomic_t             sc_sq_avail;	/* SQEs ready to be consumed */
 	unsigned int	     sc_sq_depth;	/* Depth of SQ */
 	unsigned int	     sc_rq_depth;	/* Depth of RQ */
-	u32		     sc_max_requests;	/* Forward credits */
+	__be32		     sc_fc_credits;	/* Forward credits */
+	u32		     sc_max_requests;	/* Max requests */
 	u32		     sc_max_bc_requests;/* Backward credits */
 	int                  sc_max_req_size;	/* Size of each RQ WR buf */
 
@@ -214,10 +215,6 @@ extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int);
 extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int);
 extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int,
 					    __be32, __be64, u32);
-extern void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *,
-					     struct rpcrdma_msg *,
-					     struct rpcrdma_msg *,
-					     enum rpcrdma_proc);
 extern unsigned int svc_rdma_xdr_get_reply_hdr_len(__be32 *rdma_resp);
 
 /* svc_rdma_recvfrom.c */
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 4e7203439e2f..c7d15b1126ce 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -249,7 +249,7 @@ int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt,
 
 	*va++ = rmsgp->rm_xid;
 	*va++ = rmsgp->rm_vers;
-	*va++ = cpu_to_be32(xprt->sc_max_requests);
+	*va++ = xprt->sc_fc_credits;
 	*va++ = rdma_error;
 	*va++ = cpu_to_be32(err);
 	if (err == ERR_VERS) {
@@ -329,19 +329,3 @@ void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary,
 	seg->rs_offset = rs_offset;
 	seg->rs_length = cpu_to_be32(write_len);
 }
-
-void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt,
-				  struct rpcrdma_msg *rdma_argp,
-				  struct rpcrdma_msg *rdma_resp,
-				  enum rpcrdma_proc rdma_type)
-{
-	rdma_resp->rm_xid = rdma_argp->rm_xid;
-	rdma_resp->rm_vers = rdma_argp->rm_vers;
-	rdma_resp->rm_credit = cpu_to_be32(xprt->sc_max_requests);
-	rdma_resp->rm_type = cpu_to_be32(rdma_type);
-
-	/* Encode <nul> chunks lists */
-	rdma_resp->rm_body.rm_chunks[0] = xdr_zero;
-	rdma_resp->rm_body.rm_chunks[1] = xdr_zero;
-	rdma_resp->rm_body.rm_chunks[2] = xdr_zero;
-}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index ba76f1617965..515221b16d09 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -560,12 +560,12 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 	struct rpcrdma_msg *rdma_argp;
 	struct rpcrdma_msg *rdma_resp;
 	struct rpcrdma_write_array *wr_ary, *rp_ary;
-	enum rpcrdma_proc reply_type;
 	int ret;
 	int inline_bytes;
 	struct page *res_page;
 	struct svc_rdma_req_map *vec;
 	u32 inv_rkey;
+	__be32 *p;
 
 	dprintk("svcrdma: sending response for rqstp=%p\n", rqstp);
 
@@ -597,12 +597,17 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 	if (!res_page)
 		goto err0;
 	rdma_resp = page_address(res_page);
-	if (rp_ary)
-		reply_type = RDMA_NOMSG;
-	else
-		reply_type = RDMA_MSG;
-	svc_rdma_xdr_encode_reply_header(rdma, rdma_argp,
-					 rdma_resp, reply_type);
+
+	p = &rdma_resp->rm_xid;
+	*p++ = rdma_argp->rm_xid;
+	*p++ = rdma_argp->rm_vers;
+	*p++ = rdma->sc_fc_credits;
+	*p++ = rp_ary ? rdma_nomsg : rdma_msg;
+
+	/* Start with empty chunks */
+	*p++ = xdr_zero;
+	*p++ = xdr_zero;
+	*p   = xdr_zero;
 
 	/* Send any write-chunk data and build resp write-list */
 	if (wr_ary) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index ca2799af05a6..174928fe5f83 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -1002,6 +1002,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	newxprt->sc_max_req_size = svcrdma_max_req_size;
 	newxprt->sc_max_requests = min_t(u32, dev->attrs.max_qp_wr,
 					 svcrdma_max_requests);
+	newxprt->sc_fc_credits = cpu_to_be32(newxprt->sc_max_requests);
 	newxprt->sc_max_bc_requests = min_t(u32, dev->attrs.max_qp_wr,
 					    svcrdma_max_bc_requests);
 	newxprt->sc_rq_depth = newxprt->sc_max_requests +
-- 
cgit v1.2.3


From 647e18e3bd0308b38d5341fc08cd70ed1ce28a71 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Feb 2017 11:58:32 -0500
Subject: svcrdma: Clean up RPC-over-RDMA Call header decoder

Replace C structure-based XDR decoding with pointer arithmetic.
Pointer arithmetic is considered more portable.

Rename the "decode" functions. Nothing is decoded here, they
perform only transport header sanity checking. Use existing XDR
naming conventions to help readability.

Straight-line the hot path:
 - relocate the dprintk call sites out of line
 - remove unnecessary byte-swapping
 - reduce count of conditional branches

Deprecate RDMA_MSGP. It's not properly spec'd by RFC5666, and
therefore never used by any V1 client.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 net/sunrpc/xprtrdma/svc_rdma_marshal.c | 232 +++++++++++----------------------
 1 file changed, 79 insertions(+), 153 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index c7d15b1126ce..1c4aabf0f657 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016 Oracle. All rights reserved.
  * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -47,102 +48,43 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
-/*
- * Decodes a read chunk list. The expected format is as follows:
- *    descrim  : xdr_one
- *    position : __be32 offset into XDR stream
- *    handle   : __be32 RKEY
- *    . . .
- *  end-of-list: xdr_zero
- */
-static __be32 *decode_read_list(__be32 *va, __be32 *vaend)
+static __be32 *xdr_check_read_list(__be32 *p, __be32 *end)
 {
-	struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va;
+	__be32 *next;
 
-	while (ch->rc_discrim != xdr_zero) {
-		if (((unsigned long)ch + sizeof(struct rpcrdma_read_chunk)) >
-		    (unsigned long)vaend) {
-			dprintk("svcrdma: vaend=%p, ch=%p\n", vaend, ch);
+	while (*p++ != xdr_zero) {
+		next = p + rpcrdma_readchunk_maxsz - 1;
+		if (next > end)
 			return NULL;
-		}
-		ch++;
+		p = next;
 	}
-	return &ch->rc_position;
+	return p;
 }
 
-/*
- * Decodes a write chunk list. The expected format is as follows:
- *    descrim  : xdr_one
- *    nchunks  : <count>
- *       handle   : __be32 RKEY           ---+
- *       length   : __be32 <len of segment>  |
- *       offset   : remove va                + <count>
- *       . . .                               |
- *                                        ---+
- */
-static __be32 *decode_write_list(__be32 *va, __be32 *vaend)
+static __be32 *xdr_check_write_list(__be32 *p, __be32 *end)
 {
-	unsigned long start, end;
-	int nchunks;
-
-	struct rpcrdma_write_array *ary =
-		(struct rpcrdma_write_array *)va;
-
-	/* Check for not write-array */
-	if (ary->wc_discrim == xdr_zero)
-		return &ary->wc_nchunks;
+	__be32 *next;
 
-	if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) >
-	    (unsigned long)vaend) {
-		dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
-		return NULL;
-	}
-	nchunks = be32_to_cpu(ary->wc_nchunks);
-
-	start = (unsigned long)&ary->wc_array[0];
-	end = (unsigned long)vaend;
-	if (nchunks < 0 ||
-	    nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) ||
-	    (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) {
-		dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-			ary, nchunks, vaend);
-		return NULL;
+	while (*p++ != xdr_zero) {
+		next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz;
+		if (next > end)
+			return NULL;
+		p = next;
 	}
-	/*
-	 * rs_length is the 2nd 4B field in wc_target and taking its
-	 * address skips the list terminator
-	 */
-	return &ary->wc_array[nchunks].wc_target.rs_length;
+	return p;
 }
 
-static __be32 *decode_reply_array(__be32 *va, __be32 *vaend)
+static __be32 *xdr_check_reply_chunk(__be32 *p, __be32 *end)
 {
-	unsigned long start, end;
-	int nchunks;
-	struct rpcrdma_write_array *ary =
-		(struct rpcrdma_write_array *)va;
-
-	/* Check for no reply-array */
-	if (ary->wc_discrim == xdr_zero)
-		return &ary->wc_nchunks;
-
-	if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) >
-	    (unsigned long)vaend) {
-		dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
-		return NULL;
-	}
-	nchunks = be32_to_cpu(ary->wc_nchunks);
-
-	start = (unsigned long)&ary->wc_array[0];
-	end = (unsigned long)vaend;
-	if (nchunks < 0 ||
-	    nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) ||
-	    (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) {
-		dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
-			ary, nchunks, vaend);
-		return NULL;
+	__be32 *next;
+
+	if (*p++ != xdr_zero) {
+		next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz;
+		if (next > end)
+			return NULL;
+		p = next;
 	}
-	return (__be32 *)&ary->wc_array[nchunks];
+	return p;
 }
 
 /**
@@ -158,87 +100,71 @@ static __be32 *decode_reply_array(__be32 *va, __be32 *vaend)
  */
 int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg)
 {
-	struct rpcrdma_msg *rmsgp;
-	__be32 *va, *vaend;
-	unsigned int len;
-	u32 hdr_len;
+	__be32 *p, *end, *rdma_argp;
+	unsigned int hdr_len;
 
 	/* Verify that there's enough bytes for header + something */
-	if (rq_arg->len <= RPCRDMA_HDRLEN_ERR) {
-		dprintk("svcrdma: header too short = %d\n",
-			rq_arg->len);
-		return -EINVAL;
-	}
+	if (rq_arg->len <= RPCRDMA_HDRLEN_ERR)
+		goto out_short;
 
-	rmsgp = (struct rpcrdma_msg *)rq_arg->head[0].iov_base;
-	if (rmsgp->rm_vers != rpcrdma_version) {
-		dprintk("%s: bad version %u\n", __func__,
-			be32_to_cpu(rmsgp->rm_vers));
-		return -EPROTONOSUPPORT;
-	}
+	rdma_argp = rq_arg->head[0].iov_base;
+	if (*(rdma_argp + 1) != rpcrdma_version)
+		goto out_version;
 
-	switch (be32_to_cpu(rmsgp->rm_type)) {
-	case RDMA_MSG:
-	case RDMA_NOMSG:
+	switch (*(rdma_argp + 3)) {
+	case rdma_msg:
+	case rdma_nomsg:
 		break;
 
-	case RDMA_DONE:
-		/* Just drop it */
-		dprintk("svcrdma: dropping RDMA_DONE message\n");
-		return 0;
-
-	case RDMA_ERROR:
-		/* Possible if this is a backchannel reply.
-		 * XXX: We should cancel this XID, though.
-		 */
-		dprintk("svcrdma: dropping RDMA_ERROR message\n");
-		return 0;
-
-	case RDMA_MSGP:
-		/* Pull in the extra for the padded case, bump our pointer */
-		rmsgp->rm_body.rm_padded.rm_align =
-			be32_to_cpu(rmsgp->rm_body.rm_padded.rm_align);
-		rmsgp->rm_body.rm_padded.rm_thresh =
-			be32_to_cpu(rmsgp->rm_body.rm_padded.rm_thresh);
-
-		va = &rmsgp->rm_body.rm_padded.rm_pempty[4];
-		rq_arg->head[0].iov_base = va;
-		len = (u32)((unsigned long)va - (unsigned long)rmsgp);
-		rq_arg->head[0].iov_len -= len;
-		if (len > rq_arg->len)
-			return -EINVAL;
-		return len;
-	default:
-		dprintk("svcrdma: bad rdma procedure (%u)\n",
-			be32_to_cpu(rmsgp->rm_type));
-		return -EINVAL;
-	}
+	case rdma_done:
+		goto out_drop;
 
-	/* The chunk list may contain either a read chunk list or a write
-	 * chunk list and a reply chunk list.
-	 */
-	va = &rmsgp->rm_body.rm_chunks[0];
-	vaend = (__be32 *)((unsigned long)rmsgp + rq_arg->len);
-	va = decode_read_list(va, vaend);
-	if (!va) {
-		dprintk("svcrdma: failed to decode read list\n");
-		return -EINVAL;
-	}
-	va = decode_write_list(va, vaend);
-	if (!va) {
-		dprintk("svcrdma: failed to decode write list\n");
-		return -EINVAL;
-	}
-	va = decode_reply_array(va, vaend);
-	if (!va) {
-		dprintk("svcrdma: failed to decode reply chunk\n");
-		return -EINVAL;
+	case rdma_error:
+		goto out_drop;
+
+	default:
+		goto out_proc;
 	}
 
-	rq_arg->head[0].iov_base = va;
-	hdr_len = (unsigned long)va - (unsigned long)rmsgp;
+	end = (__be32 *)((unsigned long)rdma_argp + rq_arg->len);
+	p = xdr_check_read_list(rdma_argp + 4, end);
+	if (!p)
+		goto out_inval;
+	p = xdr_check_write_list(p, end);
+	if (!p)
+		goto out_inval;
+	p = xdr_check_reply_chunk(p, end);
+	if (!p)
+		goto out_inval;
+	if (p > end)
+		goto out_inval;
+
+	rq_arg->head[0].iov_base = p;
+	hdr_len = (unsigned long)p - (unsigned long)rdma_argp;
 	rq_arg->head[0].iov_len -= hdr_len;
 	return hdr_len;
+
+out_short:
+	dprintk("svcrdma: header too short = %d\n", rq_arg->len);
+	return -EINVAL;
+
+out_version:
+	dprintk("svcrdma: bad xprt version: %u\n",
+		be32_to_cpup(rdma_argp + 1));
+	return -EPROTONOSUPPORT;
+
+out_drop:
+	dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n");
+	return 0;
+
+out_proc:
+	dprintk("svcrdma: bad rdma procedure (%u)\n",
+		be32_to_cpup(rdma_argp + 3));
+	return -EINVAL;
+
+out_inval:
+	dprintk("svcrdma: failed to parse transport header\n");
+	return -EINVAL;
 }
 
 int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt,
-- 
cgit v1.2.3


From c2ccf64a6c4bf3bcbf4e6e6b94a51500991022a1 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Feb 2017 11:58:40 -0500
Subject: svcrdma: Clean up backchannel send header encoding

Replace C structure-based XDR decoding with pointer arithmetic.
Pointer arithmetic is considered more portable.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 288e35c2d8f4..b1bc7a796782 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -200,19 +200,20 @@ rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst)
 {
 	struct rpc_xprt *xprt = rqst->rq_xprt;
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	struct rpcrdma_msg *headerp = (struct rpcrdma_msg *)rqst->rq_buffer;
+	__be32 *p;
 	int rc;
 
 	/* Space in the send buffer for an RPC/RDMA header is reserved
 	 * via xprt->tsh_size.
 	 */
-	headerp->rm_xid = rqst->rq_xid;
-	headerp->rm_vers = rpcrdma_version;
-	headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_bc_max_requests);
-	headerp->rm_type = rdma_msg;
-	headerp->rm_body.rm_chunks[0] = xdr_zero;
-	headerp->rm_body.rm_chunks[1] = xdr_zero;
-	headerp->rm_body.rm_chunks[2] = xdr_zero;
+	p = rqst->rq_buffer;
+	*p++ = rqst->rq_xid;
+	*p++ = rpcrdma_version;
+	*p++ = cpu_to_be32(r_xprt->rx_buf.rb_bc_max_requests);
+	*p++ = rdma_msg;
+	*p++ = xdr_zero;
+	*p++ = xdr_zero;
+	*p   = xdr_zero;
 
 #ifdef SVCRDMA_BACKCHANNEL_DEBUG
 	pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer);
-- 
cgit v1.2.3


From aba7d14ba18c93a2ab37d50b057a885964ef285c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Feb 2017 11:58:48 -0500
Subject: svcrdma: Remove unused sc_dto_q field

Clean up. Commit be99bb11400c ("svcrdma: Use new CQ API for
RPC-over-RDMA server send CQs") removed code that used the sc_dto_q
field, but neglected to remove sc_dto_q at the same time.

Fixes: be99bb11400c ("svcrdma: Use new CQ API for RPC-over- ...")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          | 1 -
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 1 -
 2 files changed, 2 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 25ecf92cae96..f77a7bc1612c 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -172,7 +172,6 @@ struct svcxprt_rdma {
 
 	wait_queue_head_t    sc_send_wait;	/* SQ exhaustion waitlist */
 	unsigned long	     sc_flags;
-	struct list_head     sc_dto_q;		/* DTO tasklet I/O pending Q */
 	struct list_head     sc_read_complete_q;
 	struct work_struct   sc_work;
 };
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 174928fe5f83..023eaa01157f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -557,7 +557,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 		return NULL;
 	svc_xprt_init(&init_net, &svc_rdma_class, &cma_xprt->sc_xprt, serv);
 	INIT_LIST_HEAD(&cma_xprt->sc_accept_q);
-	INIT_LIST_HEAD(&cma_xprt->sc_dto_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_frmr_q);
-- 
cgit v1.2.3


From a3ab867fa64f9aedb3b01d570db5b43d2fc355fc Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Feb 2017 11:58:56 -0500
Subject: svcrdma: Combine list fields in struct svc_rdma_op_ctxt

Clean up: The free list and the dto_q list fields are never used at
the same time. Reduce the size of struct svc_rdma_op_ctxt by
combining these fields.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          |  3 +--
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  | 14 ++++++--------
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 33 +++++++++++++++-----------------
 3 files changed, 22 insertions(+), 28 deletions(-)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index f77a7bc1612c..b105f73e3ca2 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -70,7 +70,7 @@ extern atomic_t rdma_stat_sq_prod;
  * completes.
  */
 struct svc_rdma_op_ctxt {
-	struct list_head free;
+	struct list_head list;
 	struct svc_rdma_op_ctxt *read_hdr;
 	struct svc_rdma_fastreg_mr *frmr;
 	int hdr_count;
@@ -78,7 +78,6 @@ struct svc_rdma_op_ctxt {
 	struct ib_cqe cqe;
 	struct ib_cqe reg_cqe;
 	struct ib_cqe inv_cqe;
-	struct list_head dto_q;
 	u32 byte_len;
 	u32 position;
 	struct svcxprt_rdma *xprt;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 172b537f8cfc..b9ccd73631a9 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -608,18 +608,16 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 
 	spin_lock_bh(&rdma_xprt->sc_rq_dto_lock);
 	if (!list_empty(&rdma_xprt->sc_read_complete_q)) {
-		ctxt = list_entry(rdma_xprt->sc_read_complete_q.next,
-				  struct svc_rdma_op_ctxt,
-				  dto_q);
-		list_del_init(&ctxt->dto_q);
+		ctxt = list_first_entry(&rdma_xprt->sc_read_complete_q,
+					struct svc_rdma_op_ctxt, list);
+		list_del(&ctxt->list);
 		spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
 		rdma_read_complete(rqstp, ctxt);
 		goto complete;
 	} else if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
-		ctxt = list_entry(rdma_xprt->sc_rq_dto_q.next,
-				  struct svc_rdma_op_ctxt,
-				  dto_q);
-		list_del_init(&ctxt->dto_q);
+		ctxt = list_first_entry(&rdma_xprt->sc_rq_dto_q,
+					struct svc_rdma_op_ctxt, list);
+		list_del(&ctxt->list);
 	} else {
 		atomic_inc(&rdma_stat_rq_starve);
 		clear_bit(XPT_DATA, &xprt->xpt_flags);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 023eaa01157f..87b8b5a10324 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -157,8 +157,7 @@ static struct svc_rdma_op_ctxt *alloc_ctxt(struct svcxprt_rdma *xprt,
 	ctxt = kmalloc(sizeof(*ctxt), flags);
 	if (ctxt) {
 		ctxt->xprt = xprt;
-		INIT_LIST_HEAD(&ctxt->free);
-		INIT_LIST_HEAD(&ctxt->dto_q);
+		INIT_LIST_HEAD(&ctxt->list);
 	}
 	return ctxt;
 }
@@ -180,7 +179,7 @@ static bool svc_rdma_prealloc_ctxts(struct svcxprt_rdma *xprt)
 			dprintk("svcrdma: No memory for RDMA ctxt\n");
 			return false;
 		}
-		list_add(&ctxt->free, &xprt->sc_ctxts);
+		list_add(&ctxt->list, &xprt->sc_ctxts);
 	}
 	return true;
 }
@@ -195,8 +194,8 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
 		goto out_empty;
 
 	ctxt = list_first_entry(&xprt->sc_ctxts,
-				struct svc_rdma_op_ctxt, free);
-	list_del_init(&ctxt->free);
+				struct svc_rdma_op_ctxt, list);
+	list_del(&ctxt->list);
 	spin_unlock_bh(&xprt->sc_ctxt_lock);
 
 out:
@@ -256,7 +255,7 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
 
 	spin_lock_bh(&xprt->sc_ctxt_lock);
 	xprt->sc_ctxt_used--;
-	list_add(&ctxt->free, &xprt->sc_ctxts);
+	list_add(&ctxt->list, &xprt->sc_ctxts);
 	spin_unlock_bh(&xprt->sc_ctxt_lock);
 }
 
@@ -266,8 +265,8 @@ static void svc_rdma_destroy_ctxts(struct svcxprt_rdma *xprt)
 		struct svc_rdma_op_ctxt *ctxt;
 
 		ctxt = list_first_entry(&xprt->sc_ctxts,
-					struct svc_rdma_op_ctxt, free);
-		list_del(&ctxt->free);
+					struct svc_rdma_op_ctxt, list);
+		list_del(&ctxt->list);
 		kfree(ctxt);
 	}
 }
@@ -404,7 +403,7 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	/* All wc fields are now known to be valid */
 	ctxt->byte_len = wc->byte_len;
 	spin_lock(&xprt->sc_rq_dto_lock);
-	list_add_tail(&ctxt->dto_q, &xprt->sc_rq_dto_q);
+	list_add_tail(&ctxt->list, &xprt->sc_rq_dto_q);
 	spin_unlock(&xprt->sc_rq_dto_lock);
 
 	set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
@@ -525,7 +524,7 @@ void svc_rdma_wc_read(struct ib_cq *cq, struct ib_wc *wc)
 
 		read_hdr = ctxt->read_hdr;
 		spin_lock(&xprt->sc_rq_dto_lock);
-		list_add_tail(&read_hdr->dto_q,
+		list_add_tail(&read_hdr->list,
 			      &xprt->sc_read_complete_q);
 		spin_unlock(&xprt->sc_rq_dto_lock);
 
@@ -1213,20 +1212,18 @@ static void __svc_rdma_free(struct work_struct *work)
 	 */
 	while (!list_empty(&rdma->sc_read_complete_q)) {
 		struct svc_rdma_op_ctxt *ctxt;
-		ctxt = list_entry(rdma->sc_read_complete_q.next,
-				  struct svc_rdma_op_ctxt,
-				  dto_q);
-		list_del_init(&ctxt->dto_q);
+		ctxt = list_first_entry(&rdma->sc_read_complete_q,
+					struct svc_rdma_op_ctxt, list);
+		list_del(&ctxt->list);
 		svc_rdma_put_context(ctxt, 1);
 	}
 
 	/* Destroy queued, but not processed recv completions */
 	while (!list_empty(&rdma->sc_rq_dto_q)) {
 		struct svc_rdma_op_ctxt *ctxt;
-		ctxt = list_entry(rdma->sc_rq_dto_q.next,
-				  struct svc_rdma_op_ctxt,
-				  dto_q);
-		list_del_init(&ctxt->dto_q);
+		ctxt = list_first_entry(&rdma->sc_rq_dto_q,
+					struct svc_rdma_op_ctxt, list);
+		list_del(&ctxt->list);
 		svc_rdma_put_context(ctxt, 1);
 	}
 
-- 
cgit v1.2.3


From 81fa3275f95ac357188fe3ca81b8e7c75360c88d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Feb 2017 11:59:04 -0500
Subject: svcrdma: Poll CQs in "workqueue" mode

svcrdma calls svc_xprt_put() in its completion handlers, which
currently run in IRQ context.

However, svc_xprt_put() is meant to be invoked in process context,
not in IRQ context. After the last transport reference is gone, it
directly calls a transport release function that expects to run in
process context.

Change the CQ polling modes to IB_POLL_WORKQUEUE so that svcrdma
invokes svc_xprt_put() only in process context. As an added benefit,
bottom half-disabled spin locking can be eliminated from I/O paths.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  |  6 +++---
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 26 +++++++++++++-------------
 2 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index b9ccd73631a9..f7b2daf72a86 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -606,12 +606,12 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 
 	dprintk("svcrdma: rqstp=%p\n", rqstp);
 
-	spin_lock_bh(&rdma_xprt->sc_rq_dto_lock);
+	spin_lock(&rdma_xprt->sc_rq_dto_lock);
 	if (!list_empty(&rdma_xprt->sc_read_complete_q)) {
 		ctxt = list_first_entry(&rdma_xprt->sc_read_complete_q,
 					struct svc_rdma_op_ctxt, list);
 		list_del(&ctxt->list);
-		spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
+		spin_unlock(&rdma_xprt->sc_rq_dto_lock);
 		rdma_read_complete(rqstp, ctxt);
 		goto complete;
 	} else if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
@@ -623,7 +623,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		clear_bit(XPT_DATA, &xprt->xpt_flags);
 		ctxt = NULL;
 	}
-	spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
+	spin_unlock(&rdma_xprt->sc_rq_dto_lock);
 	if (!ctxt) {
 		/* This is the EAGAIN path. The svc_recv routine will
 		 * return -EAGAIN, the nfsd thread will go to call into
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 87b8b5a10324..ab2fd5377f94 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -188,7 +188,7 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
 {
 	struct svc_rdma_op_ctxt *ctxt = NULL;
 
-	spin_lock_bh(&xprt->sc_ctxt_lock);
+	spin_lock(&xprt->sc_ctxt_lock);
 	xprt->sc_ctxt_used++;
 	if (list_empty(&xprt->sc_ctxts))
 		goto out_empty;
@@ -196,7 +196,7 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
 	ctxt = list_first_entry(&xprt->sc_ctxts,
 				struct svc_rdma_op_ctxt, list);
 	list_del(&ctxt->list);
-	spin_unlock_bh(&xprt->sc_ctxt_lock);
+	spin_unlock(&xprt->sc_ctxt_lock);
 
 out:
 	ctxt->count = 0;
@@ -208,15 +208,15 @@ out_empty:
 	/* Either pre-allocation missed the mark, or send
 	 * queue accounting is broken.
 	 */
-	spin_unlock_bh(&xprt->sc_ctxt_lock);
+	spin_unlock(&xprt->sc_ctxt_lock);
 
 	ctxt = alloc_ctxt(xprt, GFP_NOIO);
 	if (ctxt)
 		goto out;
 
-	spin_lock_bh(&xprt->sc_ctxt_lock);
+	spin_lock(&xprt->sc_ctxt_lock);
 	xprt->sc_ctxt_used--;
-	spin_unlock_bh(&xprt->sc_ctxt_lock);
+	spin_unlock(&xprt->sc_ctxt_lock);
 	WARN_ONCE(1, "svcrdma: empty RDMA ctxt list?\n");
 	return NULL;
 }
@@ -253,10 +253,10 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
 		for (i = 0; i < ctxt->count; i++)
 			put_page(ctxt->pages[i]);
 
-	spin_lock_bh(&xprt->sc_ctxt_lock);
+	spin_lock(&xprt->sc_ctxt_lock);
 	xprt->sc_ctxt_used--;
 	list_add(&ctxt->list, &xprt->sc_ctxts);
-	spin_unlock_bh(&xprt->sc_ctxt_lock);
+	spin_unlock(&xprt->sc_ctxt_lock);
 }
 
 static void svc_rdma_destroy_ctxts(struct svcxprt_rdma *xprt)
@@ -921,14 +921,14 @@ struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_fastreg_mr *frmr = NULL;
 
-	spin_lock_bh(&rdma->sc_frmr_q_lock);
+	spin_lock(&rdma->sc_frmr_q_lock);
 	if (!list_empty(&rdma->sc_frmr_q)) {
 		frmr = list_entry(rdma->sc_frmr_q.next,
 				  struct svc_rdma_fastreg_mr, frmr_list);
 		list_del_init(&frmr->frmr_list);
 		frmr->sg_nents = 0;
 	}
-	spin_unlock_bh(&rdma->sc_frmr_q_lock);
+	spin_unlock(&rdma->sc_frmr_q_lock);
 	if (frmr)
 		return frmr;
 
@@ -941,10 +941,10 @@ void svc_rdma_put_frmr(struct svcxprt_rdma *rdma,
 	if (frmr) {
 		ib_dma_unmap_sg(rdma->sc_cm_id->device,
 				frmr->sg, frmr->sg_nents, frmr->direction);
-		spin_lock_bh(&rdma->sc_frmr_q_lock);
+		spin_lock(&rdma->sc_frmr_q_lock);
 		WARN_ON_ONCE(!list_empty(&frmr->frmr_list));
 		list_add(&frmr->frmr_list, &rdma->sc_frmr_q);
-		spin_unlock_bh(&rdma->sc_frmr_q_lock);
+		spin_unlock(&rdma->sc_frmr_q_lock);
 	}
 }
 
@@ -1026,13 +1026,13 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 		goto errout;
 	}
 	newxprt->sc_sq_cq = ib_alloc_cq(dev, newxprt, newxprt->sc_sq_depth,
-					0, IB_POLL_SOFTIRQ);
+					0, IB_POLL_WORKQUEUE);
 	if (IS_ERR(newxprt->sc_sq_cq)) {
 		dprintk("svcrdma: error creating SQ CQ for connect request\n");
 		goto errout;
 	}
 	newxprt->sc_rq_cq = ib_alloc_cq(dev, newxprt, newxprt->sc_rq_depth,
-					0, IB_POLL_SOFTIRQ);
+					0, IB_POLL_WORKQUEUE);
 	if (IS_ERR(newxprt->sc_rq_cq)) {
 		dprintk("svcrdma: error creating RQ CQ for connect request\n");
 		goto errout;
-- 
cgit v1.2.3


From 471a930ad7d1b868456e835a67169a661ec73f65 Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Wed, 8 Feb 2017 09:54:33 +0800
Subject: SUNRPC: Drop all entries from cache_detail when cache_purge()

User always free the cache_detail after sunrpc_destroy_cache_detail(),
so, it must cleanup up entries that left in the cache_detail,
otherwise, NULL reference may be caused when using the left entries.

Also, NeriBrown suggests "write a stand-alone cache_purge()."

v3, move the cache_fresh_unlocked() out of write lock,
v2, a stand-alone cache_purge(), not only for sunrpc_destroy_cache_detail

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 net/sunrpc/cache.c | 41 ++++++++++++++++++++++++++---------------
 1 file changed, 26 insertions(+), 15 deletions(-)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 502b9fe9817b..f5d6c60aae26 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -362,11 +362,6 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd)
 	cache_purge(cd);
 	spin_lock(&cache_list_lock);
 	write_lock(&cd->hash_lock);
-	if (cd->entries) {
-		write_unlock(&cd->hash_lock);
-		spin_unlock(&cache_list_lock);
-		goto out;
-	}
 	if (current_detail == cd)
 		current_detail = NULL;
 	list_del_init(&cd->others);
@@ -376,9 +371,6 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd)
 		/* module must be being unloaded so its safe to kill the worker */
 		cancel_delayed_work_sync(&cache_cleaner);
 	}
-	return;
-out:
-	printk(KERN_ERR "RPC: failed to unregister %s cache\n", cd->name);
 }
 EXPORT_SYMBOL_GPL(sunrpc_destroy_cache_detail);
 
@@ -497,13 +489,32 @@ EXPORT_SYMBOL_GPL(cache_flush);
 
 void cache_purge(struct cache_detail *detail)
 {
-	time_t now = seconds_since_boot();
-	if (detail->flush_time >= now)
-		now = detail->flush_time + 1;
-	/* 'now' is the maximum value any 'last_refresh' can have */
-	detail->flush_time = now;
-	detail->nextcheck = seconds_since_boot();
-	cache_flush();
+	struct cache_head *ch = NULL;
+	struct hlist_head *head = NULL;
+	struct hlist_node *tmp = NULL;
+	int i = 0;
+
+	write_lock(&detail->hash_lock);
+	if (!detail->entries) {
+		write_unlock(&detail->hash_lock);
+		return;
+	}
+
+	dprintk("RPC: %d entries in %s cache\n", detail->entries, detail->name);
+	for (i = 0; i < detail->hash_size; i++) {
+		head = &detail->hash_table[i];
+		hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
+			hlist_del_init(&ch->cache_list);
+			detail->entries--;
+
+			set_bit(CACHE_CLEANED, &ch->flags);
+			write_unlock(&detail->hash_lock);
+			cache_fresh_unlocked(ch, detail);
+			cache_put(ch, detail);
+			write_lock(&detail->hash_lock);
+		}
+	}
+	write_unlock(&detail->hash_lock);
 }
 EXPORT_SYMBOL_GPL(cache_purge);
 
-- 
cgit v1.2.3


From 05a45a2db42543c5f1a32e08f545aebbd7cb4790 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Fri, 24 Feb 2017 13:25:22 -0500
Subject: sunrpc: turn bitfield flags in svc_version into bools

It's just simpler to read this way, IMO. Also, no need to explicitly
set vs_hidden to false in the nfsacl ones.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfs/callback_xdr.c      | 4 ++--
 fs/nfsd/nfs2acl.c          | 1 -
 fs/nfsd/nfs3acl.c          | 1 -
 fs/nfsd/nfs4proc.c         | 2 +-
 include/linux/sunrpc/svc.h | 9 +++++----
 net/sunrpc/svc.c           | 2 +-
 6 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'net/sunrpc')

diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index eb094c6011d8..e9836f611d9c 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -1083,7 +1083,7 @@ struct svc_version nfs4_callback_version1 = {
 	.vs_proc = nfs4_callback_procedures1,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
-	.vs_hidden = 1,
+	.vs_hidden = true,
 };
 
 struct svc_version nfs4_callback_version4 = {
@@ -1092,5 +1092,5 @@ struct svc_version nfs4_callback_version4 = {
 	.vs_proc = nfs4_callback_procedures1,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
-	.vs_hidden = 1,
+	.vs_hidden = true,
 };
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index d08cd88155c7..838f90f3f890 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -376,5 +376,4 @@ struct svc_version	nfsd_acl_version2 = {
 		.vs_proc	= nfsd_acl_procedures2,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
-		.vs_hidden	= 0,
 };
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 0c890347cde3..dcb5f79076c0 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -266,6 +266,5 @@ struct svc_version	nfsd_acl_version3 = {
 		.vs_proc	= nfsd_acl_procedures3,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
-		.vs_hidden	= 0,
 };
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 02750a4c8770..89e582fa58cd 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2542,7 +2542,7 @@ struct svc_version	nfsd_version4 = {
 		.vs_proc	= nfsd_procedures4,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS4_SVC_XDRSIZE,
-		.vs_rpcb_optnl	= 1,
+		.vs_rpcb_optnl	= true,
 };
 
 /*
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 7321ae933867..96467c95f02e 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -400,10 +400,11 @@ struct svc_version {
 	struct svc_procedure *	vs_proc;	/* per-procedure info */
 	u32			vs_xdrsize;	/* xdrsize needed for this version */
 
-	unsigned int		vs_hidden : 1,	/* Don't register with portmapper.
-						 * Only used for nfsacl so far. */
-				vs_rpcb_optnl:1;/* Don't care the result of register.
-						 * Only used for nfsv4. */
+	/* Don't register with rpcbind */
+	bool			vs_hidden;
+
+	/* Don't care if the rpcbind registration fails */
+	bool			vs_rpcb_optnl;
 
 	/* Override dispatch function (e.g. when caching replies).
 	 * A return value of 0 means drop the request. 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 75f290bddca1..85bcdea67a3f 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -385,7 +385,7 @@ static int svc_uses_rpcbind(struct svc_serv *serv)
 		for (i = 0; i < progp->pg_nvers; i++) {
 			if (progp->pg_vers[i] == NULL)
 				continue;
-			if (progp->pg_vers[i]->vs_hidden == 0)
+			if (!progp->pg_vers[i]->vs_hidden)
 				return 1;
 		}
 	}
-- 
cgit v1.2.3


From 362142b25843fb059941aaa01b91501d5d8652cc Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Fri, 24 Feb 2017 13:25:23 -0500
Subject: sunrpc: flag transports as having congestion control

NFSv4 requires a transport protocol with congestion control in most
cases.

On an IP network, that means that NFSv4 over UDP should be forbidden.

The situation with RDMA is a bit more nuanced, but most RDMA transports
are suitable for this. For now, we assume that all RDMA transports are
suitable, but we may need to revise that at some point.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_xprt.h          | 1 +
 net/sunrpc/svcsock.c                     | 1 +
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 8 ++++++++
 3 files changed, 10 insertions(+)

(limited to 'net/sunrpc')

diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 7440290f64ac..ddb7f94a9d06 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -67,6 +67,7 @@ struct svc_xprt {
 #define XPT_CACHE_AUTH	11		/* cache auth info */
 #define XPT_LOCAL	12		/* connection from loopback interface */
 #define XPT_KILL_TEMP   13		/* call xpo_kill_temp_xprt before closing */
+#define XPT_CONG_CTRL	14		/* has congestion control */
 
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index de066acdb34e..1956b8b96b2d 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1306,6 +1306,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_tcp_class,
 		      &svsk->sk_xprt, serv);
 	set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
+	set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags);
 	if (sk->sk_state == TCP_LISTEN) {
 		dprintk("setting up TCP socket for listening\n");
 		set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index ab2fd5377f94..9d9e4e16080f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -569,6 +569,14 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 	spin_lock_init(&cma_xprt->sc_ctxt_lock);
 	spin_lock_init(&cma_xprt->sc_map_lock);
 
+	/*
+	 * Note that this implies that the underlying transport support
+	 * has some form of congestion control (see RFC 7530 section 3.1
+	 * paragraph 2). For now, we assume that all supported RDMA
+	 * transports are suitable here.
+	 */
+	set_bit(XPT_CONG_CTRL, &cma_xprt->sc_xprt.xpt_flags);
+
 	if (listener)
 		set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags);
 
-- 
cgit v1.2.3


From 5283b03ee5cd28d516646298bead09b238d92ddc Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Fri, 24 Feb 2017 13:25:24 -0500
Subject: nfs/nfsd/sunrpc: enforce transport requirements for NFSv4

NFSv4 requires a transport "that is specified to avoid network
congestion" (RFC 7530, section 3.1, paragraph 2).  In practical terms,
that means that you should not run NFSv4 over UDP. The server has never
enforced that requirement, however.

This patchset fixes this by adding a new flag to the svc_version that
states that it has these transport requirements. With that, we can check
that the transport has XPT_CONG_CTRL set before processing an RPC. If it
doesn't we reject it with RPC_PROG_MISMATCH.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfs/callback_xdr.c      |  2 ++
 fs/nfsd/nfs4proc.c         | 13 +++++++------
 include/linux/sunrpc/svc.h |  3 +++
 net/sunrpc/svc.c           | 15 +++++++++++++++
 4 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'net/sunrpc')

diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index e9836f611d9c..fd0284c1dc32 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -1084,6 +1084,7 @@ struct svc_version nfs4_callback_version1 = {
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
 	.vs_hidden = true,
+	.vs_need_cong_ctrl = true,
 };
 
 struct svc_version nfs4_callback_version4 = {
@@ -1093,4 +1094,5 @@ struct svc_version nfs4_callback_version4 = {
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
 	.vs_hidden = true,
+	.vs_need_cong_ctrl = true,
 };
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 89e582fa58cd..cbeeda1e94a2 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2537,12 +2537,13 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 };
 
 struct svc_version	nfsd_version4 = {
-		.vs_vers	= 4,
-		.vs_nproc	= 2,
-		.vs_proc	= nfsd_procedures4,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS4_SVC_XDRSIZE,
-		.vs_rpcb_optnl	= true,
+	.vs_vers		= 4,
+	.vs_nproc		= 2,
+	.vs_proc		= nfsd_procedures4,
+	.vs_dispatch		= nfsd_dispatch,
+	.vs_xdrsize		= NFS4_SVC_XDRSIZE,
+	.vs_rpcb_optnl		= true,
+	.vs_need_cong_ctrl	= true,
 };
 
 /*
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 96467c95f02e..e770abeed32d 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -406,6 +406,9 @@ struct svc_version {
 	/* Don't care if the rpcbind registration fails */
 	bool			vs_rpcb_optnl;
 
+	/* Need xprt with congestion control */
+	bool			vs_need_cong_ctrl;
+
 	/* Override dispatch function (e.g. when caching replies).
 	 * A return value of 0 means drop the request. 
 	 * vs_dispatch == NULL means use default dispatcher.
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 85bcdea67a3f..1fc3ff822168 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1169,6 +1169,21 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	  !(versp = progp->pg_vers[vers]))
 		goto err_bad_vers;
 
+	/*
+	 * Some protocol versions (namely NFSv4) require some form of
+	 * congestion control.  (See RFC 7530 section 3.1 paragraph 2)
+	 * In other words, UDP is not allowed. We mark those when setting
+	 * up the svc_xprt, and verify that here.
+	 *
+	 * The spec is not very clear about what error should be returned
+	 * when someone tries to access a server that is listening on UDP
+	 * for lower versions. RPC_PROG_MISMATCH seems to be the closest
+	 * fit.
+	 */
+	if (versp->vs_need_cong_ctrl &&
+	    !test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags))
+		goto err_bad_vers;
+
 	procp = versp->vs_proc + proc;
 	if (proc >= versp->vs_nproc || !procp->pc_func)
 		goto err_bad_proc;
-- 
cgit v1.2.3


From 7259f1dfe718234fee3f87d98d082e7f98d1d712 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Fri, 24 Feb 2017 13:25:25 -0500
Subject: sunrpc: don't register UDP port with rpcbind when version needs
 congestion control

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 net/sunrpc/svc.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'net/sunrpc')

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 1fc3ff822168..8492acb4011f 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -976,6 +976,13 @@ int svc_register(const struct svc_serv *serv, struct net *net,
 			if (vers->vs_hidden)
 				continue;
 
+			/*
+			 * Don't register a UDP port if we need congestion
+			 * control.
+			 */
+			if (vers->vs_need_cong_ctrl && proto == IPPROTO_UDP)
+				continue;
+
 			error = __svc_register(net, progp->pg_name, progp->pg_prog,
 						i, family, proto, port);
 
-- 
cgit v1.2.3