Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

10 files changed, 96 insertions, 76 deletions

diff --git a/net/9p/client.c b/net/9p/client.c
index 1eb580c38fbb..dd43a8289b0d 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -203,7 +203,6 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 	p9pdu_reset(req->tc);
 	p9pdu_reset(req->rc);
 
-	req->flush_tag = 0;
 	req->tc->tag = tag-1;
 	req->status = REQ_STATUS_ALLOC;
 
@@ -324,35 +323,9 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
  */
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req)
 {
-	struct p9_req_t *other_req;
-	unsigned long flags;
-
 	P9_DPRINTK(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
-
-	if (req->status == REQ_STATUS_ERROR)
-		wake_up(req->wq);
-
-	if (req->flush_tag) { 			/* flush receive path */
-		P9_DPRINTK(P9_DEBUG_9P, "<<< RFLUSH %d\n", req->tc->tag);
-		spin_lock_irqsave(&c->lock, flags);
-		other_req = p9_tag_lookup(c, req->flush_tag);
-		if (other_req->status != REQ_STATUS_FLSH) /* stale flush */
-			spin_unlock_irqrestore(&c->lock, flags);
-		else {
-			other_req->status = REQ_STATUS_FLSHD;
-			spin_unlock_irqrestore(&c->lock, flags);
-			wake_up(other_req->wq);
-		}
-		p9_free_req(c, req);
-	} else { 				/* normal receive path */
-		P9_DPRINTK(P9_DEBUG_MUX, "normal: tag %d\n", req->tc->tag);
-		spin_lock_irqsave(&c->lock, flags);
-		if (req->status != REQ_STATUS_FLSHD)
-			req->status = REQ_STATUS_RCVD;
-		spin_unlock_irqrestore(&c->lock, flags);
-		wake_up(req->wq);
-		P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
-	}
+	wake_up(req->wq);
+	P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
 }
 EXPORT_SYMBOL(p9_client_cb);
 
@@ -486,9 +459,15 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	req->flush_tag = oldtag;
 
-	/* we don't free anything here because RPC isn't complete */
+	/* if we haven't received a response for oldreq,
+	   remove it from the list. */
+	spin_lock(&c->lock);
+	if (oldreq->status == REQ_STATUS_FLSH)
+		list_del(&oldreq->req_list);
+	spin_unlock(&c->lock);
+
+	p9_free_req(c, req);
 	return 0;
 }
 
@@ -509,7 +488,6 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 	struct p9_req_t *req;
 	unsigned long flags;
 	int sigpending;
-	int flushed = 0;
 
 	P9_DPRINTK(P9_DEBUG_MUX, "client %p op %d\n", c, type);
 
@@ -546,42 +524,28 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 		goto reterr;
 	}
 
-	/* if it was a flush we just transmitted, return our tag */
-	if (type == P9_TFLUSH)
-		return req;
-again:
 	P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d\n", req->wq, tag);
 	err = wait_event_interruptible(*req->wq,
 						req->status >= REQ_STATUS_RCVD);
-	P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d (flushed=%d)\n",
-						req->wq, tag, err, flushed);
+	P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d\n",
+						req->wq, tag, err);
 
 	if (req->status == REQ_STATUS_ERROR) {
 		P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
 		err = req->t_err;
-	} else if (err == -ERESTARTSYS && flushed) {
-		P9_DPRINTK(P9_DEBUG_MUX, "flushed - going again\n");
-		goto again;
-	} else if (req->status == REQ_STATUS_FLSHD) {
-		P9_DPRINTK(P9_DEBUG_MUX, "flushed - erestartsys\n");
-		err = -ERESTARTSYS;
 	}
 
-	if ((err == -ERESTARTSYS) && (c->status == Connected) && (!flushed)) {
+	if ((err == -ERESTARTSYS) && (c->status == Connected)) {
 		P9_DPRINTK(P9_DEBUG_MUX, "flushing\n");
-		spin_lock_irqsave(&c->lock, flags);
-		if (req->status == REQ_STATUS_SENT)
-			req->status = REQ_STATUS_FLSH;
-		spin_unlock_irqrestore(&c->lock, flags);
 		sigpending = 1;
-		flushed = 1;
 		clear_thread_flag(TIF_SIGPENDING);
 
-		if (c->trans_mod->cancel(c, req)) {
-			err = p9_client_flush(c, req);
-			if (err == 0)
-				goto again;
-		}
+		if (c->trans_mod->cancel(c, req))
+			p9_client_flush(c, req);
+
+		/* if we received the response anyway, don't signal error */
+		if (req->status == REQ_STATUS_RCVD)
+			err = 0;
 	}
 
 	if (sigpending) {
@@ -1244,19 +1208,53 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 		ret->name, ret->uid, ret->gid, ret->muid, ret->extension,
 		ret->n_uid, ret->n_gid, ret->n_muid);
 
+	p9_free_req(clnt, req);
+	return ret;
+
 free_and_error:
 	p9_free_req(clnt, req);
 error:
-	return ret;
+	kfree(ret);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(p9_client_stat);
 
+static int p9_client_statsize(struct p9_wstat *wst, int optional)
+{
+	int ret;
+
+	/* size[2] type[2] dev[4] qid[13] */
+	/* mode[4] atime[4] mtime[4] length[8]*/
+	/* name[s] uid[s] gid[s] muid[s] */
+	ret = 2+2+4+13+4+4+4+8+2+2+2+2;
+
+	if (wst->name)
+		ret += strlen(wst->name);
+	if (wst->uid)
+		ret += strlen(wst->uid);
+	if (wst->gid)
+		ret += strlen(wst->gid);
+	if (wst->muid)
+		ret += strlen(wst->muid);
+
+	if (optional) {
+		ret += 2+4+4+4;	/* extension[s] n_uid[4] n_gid[4] n_muid[4] */
+		if (wst->extension)
+			ret += strlen(wst->extension);
+	}
+
+	return ret;
+}
+
 int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
 {
 	int err;
 	struct p9_req_t *req;
 	struct p9_client *clnt;
 
+	err = 0;
+	clnt = fid->clnt;
+	wst->size = p9_client_statsize(wst, clnt->dotu);
 	P9_DPRINTK(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid);
 	P9_DPRINTK(P9_DEBUG_9P,
 		"     sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
@@ -1268,10 +1266,8 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
 		wst->atime, wst->mtime, (unsigned long long)wst->length,
 		wst->name, wst->uid, wst->gid, wst->muid, wst->extension,
 		wst->n_uid, wst->n_gid, wst->n_muid);
-	err = 0;
-	clnt = fid->clnt;
 
-	req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, 0, wst);
+	req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size, wst);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index c613ed08a5ee..a2a1814c7a8d 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -213,8 +213,8 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
 	spin_unlock_irqrestore(&m->client->lock, flags);
 
 	list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
-		list_del(&req->req_list);
 		P9_DPRINTK(P9_DEBUG_ERROR, "call back req %p\n", req);
+		list_del(&req->req_list);
 		p9_client_cb(m->client, req);
 	}
 }
@@ -336,7 +336,8 @@ static void p9_read_work(struct work_struct *work)
 			"mux %p pkt: size: %d bytes tag: %d\n", m, n, tag);
 
 		m->req = p9_tag_lookup(m->client, tag);
-		if (!m->req) {
+		if (!m->req || (m->req->status != REQ_STATUS_SENT &&
+					m->req->status != REQ_STATUS_FLSH)) {
 			P9_DPRINTK(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
 								 tag);
 			err = -EIO;
@@ -361,10 +362,11 @@ static void p9_read_work(struct work_struct *work)
 	if ((m->req) && (m->rpos == m->rsize)) { /* packet is read in */
 		P9_DPRINTK(P9_DEBUG_TRANS, "got new packet\n");
 		spin_lock(&m->client->lock);
+		if (m->req->status != REQ_STATUS_ERROR)
+			m->req->status = REQ_STATUS_RCVD;
 		list_del(&m->req->req_list);
 		spin_unlock(&m->client->lock);
 		p9_client_cb(m->client, m->req);
-
 		m->rbuf = NULL;
 		m->rpos = 0;
 		m->rsize = 0;
@@ -454,6 +456,7 @@ static void p9_write_work(struct work_struct *work)
 		req = list_entry(m->unsent_req_list.next, struct p9_req_t,
 			       req_list);
 		req->status = REQ_STATUS_SENT;
+		P9_DPRINTK(P9_DEBUG_TRANS, "move req %p\n", req);
 		list_move_tail(&req->req_list, &m->req_list);
 
 		m->wbuf = req->tc->sdata;
@@ -683,12 +686,13 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 	P9_DPRINTK(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
 
 	spin_lock(&client->lock);
-	list_del(&req->req_list);
 
 	if (req->status == REQ_STATUS_UNSENT) {
+		list_del(&req->req_list);
 		req->status = REQ_STATUS_FLSHD;
 		ret = 0;
-	}
+	} else if (req->status == REQ_STATUS_SENT)
+		req->status = REQ_STATUS_FLSH;
 
 	spin_unlock(&client->lock);
 
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 7fa0eb20b2f6..ac4990041ebb 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -295,6 +295,7 @@ handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma,
 		goto err_out;
 
 	req->rc = c->rc;
+	req->status = REQ_STATUS_RCVD;
 	p9_client_cb(client, req);
 
 	return;
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 2d7781ec663b..bb8579a141a8 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -134,6 +134,7 @@ static void req_done(struct virtqueue *vq)
 		P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc);
 		P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
 		req = p9_tag_lookup(chan->client, rc->tag);
+		req->status = REQ_STATUS_RCVD;
 		p9_client_cb(chan->client, req);
 	}
 }
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 619f0a30a4e5..71794449ca4e 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -638,7 +638,7 @@ struct rds_message *rds_send_get_message(struct rds_connection *,
 void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force);
 
 /* stats.c */
-DECLARE_PER_CPU(struct rds_statistics, rds_stats);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats);
 #define rds_stats_inc_which(which, member) do {		\
 	per_cpu(which, get_cpu()).member++;		\
 	put_cpu();					\
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index a0bfe53f1621..06ca058572f2 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -672,10 +672,8 @@ xprt_init_autodisconnect(unsigned long data)
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
 		goto out_abort;
 	spin_unlock(&xprt->transport_lock);
-	if (xprt_connecting(xprt))
-		xprt_release_write(xprt, NULL);
-	else
-		queue_work(rpciod_workqueue, &xprt->task_cleanup);
+	set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
+	queue_work(rpciod_workqueue, &xprt->task_cleanup);
 	return;
 out_abort:
 	spin_unlock(&xprt->transport_lock);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 629a28764da9..42a6f9f20285 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -265,7 +265,7 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
 		frmr->page_list->page_list[page_no] =
 			ib_dma_map_single(xprt->sc_cm_id->device,
 					  page_address(rqstp->rq_arg.pages[page_no]),
-					  PAGE_SIZE, DMA_TO_DEVICE);
+					  PAGE_SIZE, DMA_FROM_DEVICE);
 		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
 					 frmr->page_list->page_list[page_no]))
 			goto fatal_err;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 6c26a675435a..8b510c5e8777 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -183,6 +183,7 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
 
  fatal_err:
 	printk("svcrdma: Error fast registering memory for xprt %p\n", xprt);
+	vec->frmr = NULL;
 	svc_rdma_put_frmr(xprt, frmr);
 	return -EIO;
 }
@@ -516,6 +517,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		       "svcrdma: could not post a receive buffer, err=%d."
 		       "Closing transport %p.\n", ret, rdma);
 		set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+		svc_rdma_put_frmr(rdma, vec->frmr);
 		svc_rdma_put_context(ctxt, 0);
 		return -ENOTCONN;
 	}
@@ -606,6 +608,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	return 0;
 
  err:
+	svc_rdma_unmap_dma(ctxt);
 	svc_rdma_put_frmr(rdma, vec->frmr);
 	svc_rdma_put_context(ctxt, 1);
 	return -EIO;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 3d810e7df3fb..4b0c2fa15e0b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -520,8 +520,9 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
 	svc_xprt_get(&xprt->sc_xprt);
 	ret = ib_post_recv(xprt->sc_qp, &recv_wr, &bad_recv_wr);
 	if (ret) {
-		svc_xprt_put(&xprt->sc_xprt);
+		svc_rdma_unmap_dma(ctxt);
 		svc_rdma_put_context(ctxt, 1);
+		svc_xprt_put(&xprt->sc_xprt);
 	}
 	return ret;
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index d40ff50887aa..e18596146013 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -807,6 +807,9 @@ static void xs_reset_transport(struct sock_xprt *transport)
  *
  * This is used when all requests are complete; ie, no DRC state remains
  * on the server we want to save.
+ *
+ * The caller _must_ be holding XPRT_LOCKED in order to avoid issues with
+ * xs_reset_transport() zeroing the socket from underneath a writer.
  */
 static void xs_close(struct rpc_xprt *xprt)
 {
@@ -824,6 +827,14 @@ static void xs_close(struct rpc_xprt *xprt)
 	xprt_disconnect_done(xprt);
 }
 
+static void xs_tcp_close(struct rpc_xprt *xprt)
+{
+	if (test_and_clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state))
+		xs_close(xprt);
+	else
+		xs_tcp_shutdown(xprt);
+}
+
 /**
  * xs_destroy - prepare to shutdown a transport
  * @xprt: doomed transport
@@ -1772,6 +1783,15 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
 			xprt, -status, xprt_connected(xprt),
 			sock->sk->sk_state);
 	switch (status) {
+	default:
+		printk("%s: connect returned unhandled error %d\n",
+			__func__, status);
+	case -EADDRNOTAVAIL:
+		/* We're probably in TIME_WAIT. Get rid of existing socket,
+		 * and retry
+		 */
+		set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
+		xprt_force_disconnect(xprt);
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 	case -ENETUNREACH:
@@ -1782,10 +1802,6 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
 		xprt_clear_connecting(xprt);
 		return;
 	}
-	/* get rid of existing socket, and retry */
-	xs_tcp_shutdown(xprt);
-	printk("%s: connect returned unhandled error %d\n",
-			__func__, status);
 out_eagain:
 	status = -EAGAIN;
 out:
@@ -1994,7 +2010,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 	.buf_free		= rpc_free,
 	.send_request		= xs_tcp_send_request,
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
-	.close			= xs_tcp_shutdown,
+	.close			= xs_tcp_close,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_tcp_print_stats,
 };