/*
 * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the BSD-type
 * license below:
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 *      Redistributions of source code must retain the above copyright
 *      notice, this list of conditions and the following disclaimer.
 *
 *      Redistributions in binary form must reproduce the above
 *      copyright notice, this list of conditions and the following
 *      disclaimer in the documentation and/or other materials provided
 *      with the distribution.
 *
 *      Neither the name of the Network Appliance, Inc. nor the names of
 *      its contributors may be used to endorse or promote products
 *      derived from this software without specific prior written
 *      permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * Author: Tom Tucker <tom@opengridcomputing.com>
 */

#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/debug.h>
#include <asm/unaligned.h>
#include <linux/sunrpc/rpc_rdma.h>
#include <linux/sunrpc/svc_rdma.h>

#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)
{
	struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va;

	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);
			return NULL;
		}
		ch++;
	}
	return &ch->rc_position;
}

/*
 * 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)
{
	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;

	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;
	}
	/*
	 * 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;
}

static __be32 *decode_reply_array(__be32 *va, __be32 *vaend)
{
	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;
	}
	return (__be32 *)&ary->wc_array[nchunks];
}

/**
 * svc_rdma_xdr_decode_req - Parse incoming RPC-over-RDMA header
 * @rq_arg: Receive buffer
 *
 * On entry, xdr->head[0].iov_base points to first byte in the
 * RPC-over-RDMA header.
 *
 * On successful exit, head[0] points to first byte past the
 * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message.
 * The length of the RPC-over-RDMA header is returned.
 */
int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg)
{
	struct rpcrdma_msg *rmsgp;
	__be32 *va, *vaend;
	unsigned int len;
	u32 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;
	}

	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;
	}

	switch (be32_to_cpu(rmsgp->rm_type)) {
	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;
	}

	/* 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;
	}

	rq_arg->head[0].iov_base = va;
	hdr_len = (unsigned long)va - (unsigned long)rmsgp;
	rq_arg->head[0].iov_len -= hdr_len;
	return hdr_len;
}

int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt,
			      struct rpcrdma_msg *rmsgp,
			      enum rpcrdma_errcode err, __be32 *va)
{
	__be32 *startp = va;

	*va++ = rmsgp->rm_xid;
	*va++ = rmsgp->rm_vers;
	*va++ = cpu_to_be32(xprt->sc_max_requests);
	*va++ = rdma_error;
	*va++ = cpu_to_be32(err);
	if (err == ERR_VERS) {
		*va++ = rpcrdma_version;
		*va++ = rpcrdma_version;
	}

	return (int)((unsigned long)va - (unsigned long)startp);
}

int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp)
{
	struct rpcrdma_write_array *wr_ary;

	/* There is no read-list in a reply */

	/* 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;
}

void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *rmsgp, int chunks)
{
	struct rpcrdma_write_array *ary;

	/* no read-list */
	rmsgp->rm_body.rm_chunks[0] = xdr_zero;

	/* write-array discrim */
	ary = (struct rpcrdma_write_array *)
		&rmsgp->rm_body.rm_chunks[1];
	ary->wc_discrim = xdr_one;
	ary->wc_nchunks = cpu_to_be32(chunks);

	/* write-list terminator */
	ary->wc_array[chunks].wc_target.rs_handle = xdr_zero;

	/* reply-array discriminator */
	ary->wc_array[chunks].wc_target.rs_length = xdr_zero;
}

void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary,
				 int chunks)
{
	ary->wc_discrim = xdr_one;
	ary->wc_nchunks = cpu_to_be32(chunks);
}

void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary,
				     int chunk_no,
				     __be32 rs_handle,
				     __be64 rs_offset,
				     u32 write_len)
{
	struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target;
	seg->rs_handle = rs_handle;
	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;
}
gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-03 16:23:57 -0500'>2017-02-03</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=38ab52e8e1e2dd65f2d349f82553335813b638d2'>tcp: clear pfmemalloc on outgoing skb</a></td><td>Eric Dumazet</td><td>1</td><td><span class='deletions'>-0</span>/<span class='insertions'>+7</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
Josef Bacik diagnosed following problem :

   I was seeing random disconnects while testing NBD over loopback.
   This turned out to be because NBD sets pfmemalloc on it's socket,
   however the receiving side is a user space application so does not
   have pfmemalloc set on its socket. This means that
   sk_filter_trim_cap will simply drop this packet, under the
   assumption that the other side will simply retransmit. Well we do
   retransmit, and then the packet is just dropped again for the same
   reason.

It seems the better way to address this problem is to clear pfmemalloc
in the TCP transmit path. pfmemalloc strict control really makes sense
on the receive path.

Signed-off-by: Eric Dumazet &lt;edumazet@google.com&gt;
Acked-by: Josef Bacik &lt;jbacik@fb.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-03 11:19:34 -0500'>2017-02-03</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=3541f9e8bdebce02458882b66b638d7302c1f616'>tcp: add tcp_mss_clamp() helper</a></td><td>Eric Dumazet</td><td>3</td><td><span class='deletions'>-19</span>/<span class='insertions'>+7</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
Small cleanup factorizing code doing the TCP_MAXSEG clamping.

Signed-off-by: Eric Dumazet &lt;edumazet@google.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 23:34:19 -0500'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=8fe809a992639b2013c0d8da2ba55cdea28a959a'>net: add LINUX_MIB_PFMEMALLOCDROP counter</a></td><td>Eric Dumazet</td><td>1</td><td><span class='deletions'>-0</span>/<span class='insertions'>+1</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
Debugging issues caused by pfmemalloc is often tedious.

Add a new SNMP counter to more easily diagnose these problems.

Signed-off-by: Eric Dumazet &lt;edumazet@google.com&gt;
Cc: Josef Bacik &lt;jbacik@fb.com&gt;
Acked-by: Josef Bacik &lt;jbacik@fb.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 23:09:08 -0500'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=661091093918657ab544fb8ca91a5ab172a986dc'>net: ipv4: remove fib_lookup.h from devinet.c include list</a></td><td>David Ahern</td><td>1</td><td><span class='deletions'>-2</span>/<span class='insertions'>+0</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
nothing in devinet.c relies on fib_lookup.h; remove it from the includes

Signed-off-by: David Ahern &lt;dsa@cumulusnetworks.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 16:54:00 -0500'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=e2160156bf2a7d5018e99a9993fbcdda0abac09b'>Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net</a></td><td>David S. Miller</td><td>1</td><td><span class='deletions'>-2</span>/<span class='insertions'>+4</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
All merge conflicts were simple overlapping changes.

Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 14:31:58 +0100'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=2851940ffee313e0ff12540a8e11a8c54dea9c65'>netfilter: allow logging from non-init namespaces</a></td><td>Michal Kubeček</td><td>2</td><td><span class='deletions'>-2</span>/<span class='insertions'>+2</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
Commit 69b34fb996b2 ("netfilter: xt_LOG: add net namespace support for
xt_LOG") disabled logging packets using the LOG target from non-init
namespaces. The motivation was to prevent containers from flooding
kernel log of the host. The plan was to keep it that way until syslog
namespace implementation allows containers to log in a safe way.

However, the work on syslog namespace seems to have hit a dead end
somewhere in 2013 and there are users who want to use xt_LOG in all
network namespaces. This patch allows to do so by setting

  /proc/sys/net/netfilter/nf_log_all_netns

to a nonzero value. This sysctl is only accessible from init_net so that
one cannot switch the behaviour from inside a container.

Signed-off-by: Michal Kubecek &lt;mkubecek@suse.cz&gt;
Signed-off-by: Pablo Neira Ayuso &lt;pablo@netfilter.org&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 14:31:54 +0100'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=c74454fadd5ea6fc866ffe2c417a0dba56b2bf1c'>netfilter: add and use nf_ct_set helper</a></td><td>Florian Westphal</td><td>3</td><td><span class='deletions'>-6</span>/<span class='insertions'>+3</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
Add a helper to assign a nf_conn entry and the ctinfo bits to an sk_buff.
This avoids changing code in followup patch that merges skb-&gt;nfct and
skb-&gt;nfctinfo into skb-&gt;_nfct.

Signed-off-by: Florian Westphal &lt;fw@strlen.de&gt;
Signed-off-by: Pablo Neira Ayuso &lt;pablo@netfilter.org&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 14:31:53 +0100'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=cb9c68363efb6d1f950ec55fb06e031ee70db5fc'>skbuff: add and use skb_nfct helper</a></td><td>Florian Westphal</td><td>4</td><td><span class='deletions'>-8</span>/<span class='insertions'>+8</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
Followup patch renames skb-&gt;nfct and changes its type so add a helper to
avoid intrusive rename change later.

Signed-off-by: Florian Westphal &lt;fw@strlen.de&gt;
Signed-off-by: Pablo Neira Ayuso &lt;pablo@netfilter.org&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 14:31:51 +0100'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=6e10148c5c85629832d9156f337cbf67e96b69fe'>netfilter: reset netfilter state when duplicating packet</a></td><td>Florian Westphal</td><td>1</td><td><span class='deletions'>-1</span>/<span class='insertions'>+1</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
We should also toss nf_bridge_info, if any -- packet is leaving via
ip_local_out, also, this skb isn't bridged -- it is a locally generated
copy.  Also this avoids the need to touch this later when skb-&gt;nfct is
replaced with 'unsigned long _nfct' in followup patch.

Signed-off-by: Florian Westphal &lt;fw@strlen.de&gt;
Signed-off-by: Pablo Neira Ayuso &lt;pablo@netfilter.org&gt;


</td></tr>
<tr class='logheader'><td><span title='2017-02-02 14:31:51 +0100'>2017-02-02</span></td><td class='logsubject'><a href='/cgit.cgi/linux/net-next.git/commit/net/ipv4?id=11df4b760f11ca7528c62b1c4b870735d1c62116'>netfilter: conntrack: no need to pass ctinfo to error handler</a></td><td>Florian Westphal</td><td>1</td><td><span class='deletions'>-6</span>/<span class='insertions'>+6</span></td></tr>
<tr class='nohover-highlight'><td/><td colspan='5' class='logmsg'>
It is never accessed for reading and the only places that write to it
are the icmp(6) handlers, which also set skb-&gt;nfct (and skb-&gt;nfctinfo).

The conntrack core specifically checks for attached skb-&gt;nfct after
-&gt;error() invocation and returns early in this case.

Signed-off-by: Florian Westphal &lt;fw@strlen.de&gt;
Signed-off-by: Pablo Neira Ayuso &lt;pablo@netfilter.org&gt;


</td></tr>