1 files changed, 87 insertions, 175 deletions

diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 1dd6123070e..66f91f0d071 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -49,7 +49,9 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/seq_file.h>
+#include <linux/sunrpc/addr.h>
 
 #include "xprt_rdma.h"
 
@@ -84,131 +86,97 @@ static unsigned int max_memreg = RPCRDMA_LAST - 1;
 
 static struct ctl_table_header *sunrpc_table_header;
 
-static ctl_table xr_tunables_table[] = {
+static struct ctl_table xr_tunables_table[] = {
 	{
-		.ctl_name       = CTL_UNNUMBERED,
 		.procname	= "rdma_slot_table_entries",
 		.data		= &xprt_rdma_slot_table_entries,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &min_slot_table_size,
 		.extra2		= &max_slot_table_size
 	},
 	{
-		.ctl_name       = CTL_UNNUMBERED,
 		.procname	= "rdma_max_inline_read",
 		.data		= &xprt_rdma_max_inline_read,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-		.strategy	= &sysctl_intvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
-		.ctl_name       = CTL_UNNUMBERED,
 		.procname	= "rdma_max_inline_write",
 		.data		= &xprt_rdma_max_inline_write,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-		.strategy	= &sysctl_intvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
-		.ctl_name       = CTL_UNNUMBERED,
 		.procname	= "rdma_inline_write_padding",
 		.data		= &xprt_rdma_inline_write_padding,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &max_padding,
 	},
 	{
-		.ctl_name       = CTL_UNNUMBERED,
 		.procname	= "rdma_memreg_strategy",
 		.data		= &xprt_rdma_memreg_strategy,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &min_memreg,
 		.extra2		= &max_memreg,
 	},
 	{
-		.ctl_name       = CTL_UNNUMBERED,
 		.procname	= "rdma_pad_optimize",
 		.data		= &xprt_rdma_pad_optimize,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name = 0,
+		.proc_handler	= proc_dointvec,
 	},
+	{ },
 };
 
-static ctl_table sunrpc_table[] = {
+static struct ctl_table sunrpc_table[] = {
 	{
-		.ctl_name	= CTL_SUNRPC,
 		.procname	= "sunrpc",
 		.mode		= 0555,
 		.child		= xr_tunables_table
 	},
-	{
-		.ctl_name = 0,
-	},
+	{ },
 };
 
 #endif
 
+#define RPCRDMA_BIND_TO		(60U * HZ)
+#define RPCRDMA_INIT_REEST_TO	(5U * HZ)
+#define RPCRDMA_MAX_REEST_TO	(30U * HZ)
+#define RPCRDMA_IDLE_DISC_TO	(5U * 60 * HZ)
+
 static struct rpc_xprt_ops xprt_rdma_procs;	/* forward reference */
 
 static void
 xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 {
-	struct sockaddr_in *addr = (struct sockaddr_in *)
+	struct sockaddr *sap = (struct sockaddr *)
 					&rpcx_to_rdmad(xprt).addr;
-	char *buf;
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	char buf[64];
 
-	buf = kzalloc(20, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr);
-	xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
+	(void)rpc_ntop(sap, buf, sizeof(buf));
+	xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
 
-	buf = kzalloc(8, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 8, "%u", ntohs(addr->sin_port));
-	xprt->address_strings[RPC_DISPLAY_PORT] = buf;
+	snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
+	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);
 
 	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
 
-	buf = kzalloc(48, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 48, "addr=%pI4 port=%u proto=%s",
-			&addr->sin_addr.s_addr,
-			ntohs(addr->sin_port), "rdma");
-	xprt->address_strings[RPC_DISPLAY_ALL] = buf;
-
-	buf = kzalloc(10, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 10, "%02x%02x%02x%02x",
-			NIPQUAD(addr->sin_addr.s_addr));
-	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf;
-
-	buf = kzalloc(8, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 8, "%4hx", ntohs(addr->sin_port));
-	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
-
-	buf = kzalloc(30, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 30, "%pI4.%u.%u",
-			&addr->sin_addr.s_addr,
-			ntohs(addr->sin_port) >> 8,
-			ntohs(addr->sin_port) & 0xff);
-	xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf;
+	snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
+
+	snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
+	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
 
 	/* netid */
 	xprt->address_strings[RPC_DISPLAY_NETID] = "rdma";
@@ -237,23 +205,18 @@ xprt_rdma_connect_worker(struct work_struct *work)
 	struct rpc_xprt *xprt = &r_xprt->xprt;
 	int rc = 0;
 
-	if (!xprt->shutdown) {
-		xprt_clear_connected(xprt);
-
-		dprintk("RPC:       %s: %sconnect\n", __func__,
-				r_xprt->rx_ep.rep_connected != 0 ? "re" : "");
-		rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia);
-		if (rc)
-			goto out;
-	}
-	goto out_clear;
+	current->flags |= PF_FSTRANS;
+	xprt_clear_connected(xprt);
 
-out:
-	xprt_wake_pending_tasks(xprt, rc);
+	dprintk("RPC:       %s: %sconnect\n", __func__,
+			r_xprt->rx_ep.rep_connected != 0 ? "re" : "");
+	rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia);
+	if (rc)
+		xprt_wake_pending_tasks(xprt, rc);
 
-out_clear:
 	dprintk("RPC:       %s: exit\n", __func__);
 	xprt_clear_connecting(xprt);
+	current->flags &= ~PF_FSTRANS;
 }
 
 /*
@@ -271,27 +234,20 @@ static void
 xprt_rdma_destroy(struct rpc_xprt *xprt)
 {
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	int rc;
 
 	dprintk("RPC:       %s: called\n", __func__);
 
-	cancel_delayed_work(&r_xprt->rdma_connect);
-	flush_scheduled_work();
+	cancel_delayed_work_sync(&r_xprt->rdma_connect);
 
 	xprt_clear_connected(xprt);
 
 	rpcrdma_buffer_destroy(&r_xprt->rx_buf);
-	rc = rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia);
-	if (rc)
-		dprintk("RPC:       %s: rpcrdma_ep_destroy returned %i\n",
-			__func__, rc);
+	rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia);
 	rpcrdma_ia_close(&r_xprt->rx_ia);
 
 	xprt_rdma_free_addresses(xprt);
 
-	kfree(xprt->slot);
-	xprt->slot = NULL;
-	kfree(xprt);
+	xprt_free(xprt);
 
 	dprintk("RPC:       %s: returning\n", __func__);
 
@@ -323,29 +279,20 @@ xprt_setup_rdma(struct xprt_create *args)
 		return ERR_PTR(-EBADF);
 	}
 
-	xprt = kzalloc(sizeof(struct rpcrdma_xprt), GFP_KERNEL);
+	xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt),
+			xprt_rdma_slot_table_entries,
+			xprt_rdma_slot_table_entries);
 	if (xprt == NULL) {
 		dprintk("RPC:       %s: couldn't allocate rpcrdma_xprt\n",
 			__func__);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	xprt->max_reqs = xprt_rdma_slot_table_entries;
-	xprt->slot = kcalloc(xprt->max_reqs,
-				sizeof(struct rpc_rqst), GFP_KERNEL);
-	if (xprt->slot == NULL) {
-		dprintk("RPC:       %s: couldn't allocate %d slots\n",
-			__func__, xprt->max_reqs);
-		kfree(xprt);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	/* 60 second timeout, no retries */
 	xprt->timeout = &xprt_rdma_default_timeout;
-	xprt->bind_timeout = (60U * HZ);
-	xprt->connect_timeout = (60U * HZ);
-	xprt->reestablish_timeout = (5U * HZ);
-	xprt->idle_timeout = (5U * 60 * HZ);
+	xprt->bind_timeout = RPCRDMA_BIND_TO;
+	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
+	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
 
 	xprt->resvport = 0;		/* privileged port not needed */
 	xprt->tsh_size = 0;		/* RPC-RDMA handles framing */
@@ -445,12 +392,11 @@ out4:
 	xprt_rdma_free_addresses(xprt);
 	rc = -EINVAL;
 out3:
-	(void) rpcrdma_ep_destroy(new_ep, &new_xprt->rx_ia);
+	rpcrdma_ep_destroy(new_ep, &new_xprt->rx_ia);
 out2:
 	rpcrdma_ia_close(&new_xprt->rx_ia);
 out1:
-	kfree(xprt->slot);
-	kfree(xprt);
+	xprt_free(xprt);
 	return ERR_PTR(rc);
 }
 
@@ -482,45 +428,24 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port)
 }
 
 static void
-xprt_rdma_connect(struct rpc_task *task)
+xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 {
-	struct rpc_xprt *xprt = (struct rpc_xprt *)task->tk_xprt;
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 
-	if (!xprt_test_and_set_connecting(xprt)) {
-		if (r_xprt->rx_ep.rep_connected != 0) {
-			/* Reconnect */
-			schedule_delayed_work(&r_xprt->rdma_connect,
-				xprt->reestablish_timeout);
-			xprt->reestablish_timeout <<= 1;
-			if (xprt->reestablish_timeout > (30 * HZ))
-				xprt->reestablish_timeout = (30 * HZ);
-			else if (xprt->reestablish_timeout < (5 * HZ))
-				xprt->reestablish_timeout = (5 * HZ);
-		} else {
-			schedule_delayed_work(&r_xprt->rdma_connect, 0);
-			if (!RPC_IS_ASYNC(task))
-				flush_scheduled_work();
-		}
-	}
-}
-
-static int
-xprt_rdma_reserve_xprt(struct rpc_task *task)
-{
-	struct rpc_xprt *xprt = task->tk_xprt;
-	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	int credits = atomic_read(&r_xprt->rx_buf.rb_credits);
-
-	/* == RPC_CWNDSCALE @ init, but *after* setup */
-	if (r_xprt->rx_buf.rb_cwndscale == 0UL) {
-		r_xprt->rx_buf.rb_cwndscale = xprt->cwnd;
-		dprintk("RPC:       %s: cwndscale %lu\n", __func__,
-			r_xprt->rx_buf.rb_cwndscale);
-		BUG_ON(r_xprt->rx_buf.rb_cwndscale <= 0);
+	if (r_xprt->rx_ep.rep_connected != 0) {
+		/* Reconnect */
+		schedule_delayed_work(&r_xprt->rdma_connect,
+			xprt->reestablish_timeout);
+		xprt->reestablish_timeout <<= 1;
+		if (xprt->reestablish_timeout > RPCRDMA_MAX_REEST_TO)
+			xprt->reestablish_timeout = RPCRDMA_MAX_REEST_TO;
+		else if (xprt->reestablish_timeout < RPCRDMA_INIT_REEST_TO)
+			xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
+	} else {
+		schedule_delayed_work(&r_xprt->rdma_connect, 0);
+		if (!RPC_IS_ASYNC(task))
+			flush_delayed_work(&r_xprt->rdma_connect);
 	}
-	xprt->cwnd = credits * r_xprt->rx_buf.rb_cwndscale;
-	return xprt_reserve_xprt_cong(task);
 }
 
 /*
@@ -534,11 +459,12 @@ xprt_rdma_reserve_xprt(struct rpc_task *task)
 static void *
 xprt_rdma_allocate(struct rpc_task *task, size_t size)
 {
-	struct rpc_xprt *xprt = task->tk_xprt;
+	struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt;
 	struct rpcrdma_req *req, *nreq;
 
 	req = rpcrdma_buffer_get(&rpcx_to_rdmax(xprt)->rx_buf);
-	BUG_ON(NULL == req);
+	if (req == NULL)
+		return NULL;
 
 	if (size > req->rl_size) {
 		dprintk("RPC:       %s: size %zd too large for buffer[%zd]: "
@@ -562,18 +488,6 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 		 * If the allocation or registration fails, the RPC framework
 		 * will (doggedly) retry.
 		 */
-		if (rpcx_to_rdmax(xprt)->rx_ia.ri_memreg_strategy ==
-				RPCRDMA_BOUNCEBUFFERS) {
-			/* forced to "pure inline" */
-			dprintk("RPC:       %s: too much data (%zd) for inline "
-					"(r/w max %d/%d)\n", __func__, size,
-					rpcx_to_rdmad(xprt).inline_rsize,
-					rpcx_to_rdmad(xprt).inline_wsize);
-			size = req->rl_size;
-			rpc_exit(task, -EIO);		/* fail the operation */
-			rpcx_to_rdmax(xprt)->rx_stats.failed_marshal_count++;
-			goto out;
-		}
 		if (task->tk_flags & RPC_TASK_SWAPPER)
 			nreq = kmalloc(sizeof *req + size, GFP_ATOMIC);
 		else
@@ -602,7 +516,6 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 		req = nreq;
 	}
 	dprintk("RPC:       %s: size %zd, request 0x%p\n", __func__, size, req);
-out:
 	req->rl_connect_cookie = 0;	/* our reserved value */
 	return req->rl_xdr_buf;
 
@@ -638,9 +551,7 @@ xprt_rdma_free(void *buffer)
 		__func__, rep, (rep && rep->rr_func) ? " (with waiter)" : "");
 
 	/*
-	 * Finish the deregistration. When using mw bind, this was
-	 * begun in rpcrdma_reply_handler(). In all other modes, we
-	 * do it here, in thread context. The process is considered
+	 * Finish the deregistration.  The process is considered
 	 * complete when the rr_func vector becomes NULL - this
 	 * was put in place during rpcrdma_reply_handler() - the wait
 	 * call below will not block if the dereg is "done". If
@@ -649,12 +560,7 @@ xprt_rdma_free(void *buffer)
 	for (i = 0; req->rl_nchunks;) {
 		--req->rl_nchunks;
 		i += rpcrdma_deregister_external(
-			&req->rl_segments[i], r_xprt, NULL);
-	}
-
-	if (rep && wait_event_interruptible(rep->rr_unbind, !rep->rr_func)) {
-		rep->rr_func = NULL;	/* abandon the callback */
-		req->rl_reply = NULL;
+			&req->rl_segments[i], r_xprt);
 	}
 
 	if (req->rl_iov.length == 0) {	/* see allocate above */
@@ -686,16 +592,15 @@ static int
 xprt_rdma_send_request(struct rpc_task *task)
 {
 	struct rpc_rqst *rqst = task->tk_rqstp;
-	struct rpc_xprt *xprt = task->tk_xprt;
+	struct rpc_xprt *xprt = rqst->rq_xprt;
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	int rc;
 
-	/* marshal the send itself */
-	if (req->rl_niovs == 0 && rpcrdma_marshal_req(rqst) != 0) {
-		r_xprt->rx_stats.failed_marshal_count++;
-		dprintk("RPC:       %s: rpcrdma_marshal_req failed\n",
-			__func__);
-		return -EIO;
+	if (req->rl_niovs == 0) {
+		rc = rpcrdma_marshal_req(rqst);
+		if (rc < 0)
+			goto failed_marshal;
 	}
 
 	if (req->rl_reply == NULL) 		/* e.g. reconnection */
@@ -715,10 +620,16 @@ xprt_rdma_send_request(struct rpc_task *task)
 	if (rpcrdma_ep_post(&r_xprt->rx_ia, &r_xprt->rx_ep, req))
 		goto drop_connection;
 
-	task->tk_bytes_sent += rqst->rq_snd_buf.len;
+	rqst->rq_xmit_bytes_sent += rqst->rq_snd_buf.len;
 	rqst->rq_bytes_sent = 0;
 	return 0;
 
+failed_marshal:
+	r_xprt->rx_stats.failed_marshal_count++;
+	dprintk("RPC:       %s: rpcrdma_marshal_req failed, status %i\n",
+		__func__, rc);
+	if (rc == -EIO)
+		return -EIO;
 drop_connection:
 	xprt_disconnect_done(xprt);
 	return -ENOTCONN;	/* implies disconnect */
@@ -764,8 +675,9 @@ static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
  */
 
 static struct rpc_xprt_ops xprt_rdma_procs = {
-	.reserve_xprt		= xprt_rdma_reserve_xprt,
+	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong, /* sunrpc/xprt.c */
+	.alloc_slot		= xprt_alloc_slot,
 	.release_request	= xprt_release_rqst_cong,       /* ditto */
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def, /* ditto */
 	.rpcbind		= rpcb_getport_async,	/* sunrpc/rpcb_clnt.c */
@@ -791,7 +703,7 @@ static void __exit xprt_rdma_cleanup(void)
 {
 	int rc;
 
-	dprintk(KERN_INFO "RPCRDMA Module Removed, deregister RPC RDMA transport\n");
+	dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n");
 #ifdef RPC_DEBUG
 	if (sunrpc_table_header) {
 		unregister_sysctl_table(sunrpc_table_header);
@@ -813,14 +725,14 @@ static int __init xprt_rdma_init(void)
 	if (rc)
 		return rc;
 
-	dprintk(KERN_INFO "RPCRDMA Module Init, register RPC RDMA transport\n");
+	dprintk("RPCRDMA Module Init, register RPC RDMA transport\n");
 
-	dprintk(KERN_INFO "Defaults:\n");
-	dprintk(KERN_INFO "\tSlots %d\n"
+	dprintk("Defaults:\n");
+	dprintk("\tSlots %d\n"
 		"\tMaxInlineRead %d\n\tMaxInlineWrite %d\n",
 		xprt_rdma_slot_table_entries,
 		xprt_rdma_max_inline_read, xprt_rdma_max_inline_write);
-	dprintk(KERN_INFO "\tPadding %d\n\tMemreg %d\n",
+	dprintk("\tPadding %d\n\tMemreg %d\n",
 		xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy);
 
 #ifdef RPC_DEBUG