blob: 57176ddd4c50ff677da5c711b8b7d14e9a020d0d [file] [log] [blame]
/*
* Copyright (c) 2009-2014 Chelsio, 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
* OpenIB.org BSD 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.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/module.h>
#include <linux/list.h>
#include <linux/workqueue.h>
#include <linux/skbuff.h>
#include <linux/timer.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/if_vlan.h>
#include <net/neighbour.h>
#include <net/netevent.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <rdma/ib_addr.h>
#include "iw_cxgb4.h"
static char *states[] = {
"idle",
"listen",
"connecting",
"mpa_wait_req",
"mpa_req_sent",
"mpa_req_rcvd",
"mpa_rep_sent",
"fpdu_mode",
"aborting",
"closing",
"moribund",
"dead",
NULL,
};
static int nocong;
module_param(nocong, int, 0644);
MODULE_PARM_DESC(nocong, "Turn of congestion control (default=0)");
static int enable_ecn;
module_param(enable_ecn, int, 0644);
MODULE_PARM_DESC(enable_ecn, "Enable ECN (default=0/disabled)");
static int dack_mode = 1;
module_param(dack_mode, int, 0644);
MODULE_PARM_DESC(dack_mode, "Delayed ack mode (default=1)");
uint c4iw_max_read_depth = 32;
module_param(c4iw_max_read_depth, int, 0644);
MODULE_PARM_DESC(c4iw_max_read_depth,
"Per-connection max ORD/IRD (default=32)");
static int enable_tcp_timestamps;
module_param(enable_tcp_timestamps, int, 0644);
MODULE_PARM_DESC(enable_tcp_timestamps, "Enable tcp timestamps (default=0)");
static int enable_tcp_sack;
module_param(enable_tcp_sack, int, 0644);
MODULE_PARM_DESC(enable_tcp_sack, "Enable tcp SACK (default=0)");
static int enable_tcp_window_scaling = 1;
module_param(enable_tcp_window_scaling, int, 0644);
MODULE_PARM_DESC(enable_tcp_window_scaling,
"Enable tcp window scaling (default=1)");
int c4iw_debug;
module_param(c4iw_debug, int, 0644);
MODULE_PARM_DESC(c4iw_debug, "Enable debug logging (default=0)");
static int peer2peer = 1;
module_param(peer2peer, int, 0644);
MODULE_PARM_DESC(peer2peer, "Support peer2peer ULPs (default=1)");
static int p2p_type = FW_RI_INIT_P2PTYPE_READ_REQ;
module_param(p2p_type, int, 0644);
MODULE_PARM_DESC(p2p_type, "RDMAP opcode to use for the RTR message: "
"1=RDMA_READ 0=RDMA_WRITE (default 1)");
static int ep_timeout_secs = 60;
module_param(ep_timeout_secs, int, 0644);
MODULE_PARM_DESC(ep_timeout_secs, "CM Endpoint operation timeout "
"in seconds (default=60)");
static int mpa_rev = 1;
module_param(mpa_rev, int, 0644);
MODULE_PARM_DESC(mpa_rev, "MPA Revision, 0 supports amso1100, "
"1 is RFC0544 spec compliant, 2 is IETF MPA Peer Connect Draft"
" compliant (default=1)");
static int markers_enabled;
module_param(markers_enabled, int, 0644);
MODULE_PARM_DESC(markers_enabled, "Enable MPA MARKERS (default(0)=disabled)");
static int crc_enabled = 1;
module_param(crc_enabled, int, 0644);
MODULE_PARM_DESC(crc_enabled, "Enable MPA CRC (default(1)=enabled)");
static int rcv_win = 256 * 1024;
module_param(rcv_win, int, 0644);
MODULE_PARM_DESC(rcv_win, "TCP receive window in bytes (default=256KB)");
static int snd_win = 128 * 1024;
module_param(snd_win, int, 0644);
MODULE_PARM_DESC(snd_win, "TCP send window in bytes (default=128KB)");
static struct workqueue_struct *workq;
static struct sk_buff_head rxq;
static struct sk_buff *get_skb(struct sk_buff *skb, int len, gfp_t gfp);
static void ep_timeout(unsigned long arg);
static void connect_reply_upcall(struct c4iw_ep *ep, int status);
static LIST_HEAD(timeout_list);
static spinlock_t timeout_lock;
static void deref_qp(struct c4iw_ep *ep)
{
c4iw_qp_rem_ref(&ep->com.qp->ibqp);
clear_bit(QP_REFERENCED, &ep->com.flags);
}
static void ref_qp(struct c4iw_ep *ep)
{
set_bit(QP_REFERENCED, &ep->com.flags);
c4iw_qp_add_ref(&ep->com.qp->ibqp);
}
static void start_ep_timer(struct c4iw_ep *ep)
{
PDBG("%s ep %p\n", __func__, ep);
if (timer_pending(&ep->timer)) {
pr_err("%s timer already started! ep %p\n",
__func__, ep);
return;
}
clear_bit(TIMEOUT, &ep->com.flags);
c4iw_get_ep(&ep->com);
ep->timer.expires = jiffies + ep_timeout_secs * HZ;
ep->timer.data = (unsigned long)ep;
ep->timer.function = ep_timeout;
add_timer(&ep->timer);
}
static int stop_ep_timer(struct c4iw_ep *ep)
{
PDBG("%s ep %p stopping\n", __func__, ep);
del_timer_sync(&ep->timer);
if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) {
c4iw_put_ep(&ep->com);
return 0;
}
return 1;
}
static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb,
struct l2t_entry *l2e)
{
int error = 0;
if (c4iw_fatal_error(rdev)) {
kfree_skb(skb);
PDBG("%s - device in error state - dropping\n", __func__);
return -EIO;
}
error = cxgb4_l2t_send(rdev->lldi.ports[0], skb, l2e);
if (error < 0)
kfree_skb(skb);
return error < 0 ? error : 0;
}
int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb)
{
int error = 0;
if (c4iw_fatal_error(rdev)) {
kfree_skb(skb);
PDBG("%s - device in error state - dropping\n", __func__);
return -EIO;
}
error = cxgb4_ofld_send(rdev->lldi.ports[0], skb);
if (error < 0)
kfree_skb(skb);
return error < 0 ? error : 0;
}
static void release_tid(struct c4iw_rdev *rdev, u32 hwtid, struct sk_buff *skb)
{
struct cpl_tid_release *req;
skb = get_skb(skb, sizeof *req, GFP_KERNEL);
if (!skb)
return;
req = (struct cpl_tid_release *) skb_put(skb, sizeof(*req));
INIT_TP_WR(req, hwtid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_TID_RELEASE, hwtid));
set_wr_txq(skb, CPL_PRIORITY_SETUP, 0);
c4iw_ofld_send(rdev, skb);
return;
}
static void set_emss(struct c4iw_ep *ep, u16 opt)
{
ep->emss = ep->com.dev->rdev.lldi.mtus[TCPOPT_MSS_G(opt)] -
((AF_INET == ep->com.remote_addr.ss_family) ?
sizeof(struct iphdr) : sizeof(struct ipv6hdr)) -
sizeof(struct tcphdr);
ep->mss = ep->emss;
if (TCPOPT_TSTAMP_G(opt))
ep->emss -= round_up(TCPOLEN_TIMESTAMP, 4);
if (ep->emss < 128)
ep->emss = 128;
if (ep->emss & 7)
PDBG("Warning: misaligned mtu idx %u mss %u emss=%u\n",
TCPOPT_MSS_G(opt), ep->mss, ep->emss);
PDBG("%s mss_idx %u mss %u emss=%u\n", __func__, TCPOPT_MSS_G(opt),
ep->mss, ep->emss);
}
static enum c4iw_ep_state state_read(struct c4iw_ep_common *epc)
{
enum c4iw_ep_state state;
mutex_lock(&epc->mutex);
state = epc->state;
mutex_unlock(&epc->mutex);
return state;
}
static void __state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new)
{
epc->state = new;
}
static void state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new)
{
mutex_lock(&epc->mutex);
PDBG("%s - %s -> %s\n", __func__, states[epc->state], states[new]);
__state_set(epc, new);
mutex_unlock(&epc->mutex);
return;
}
static void *alloc_ep(int size, gfp_t gfp)
{
struct c4iw_ep_common *epc;
epc = kzalloc(size, gfp);
if (epc) {
kref_init(&epc->kref);
mutex_init(&epc->mutex);
c4iw_init_wr_wait(&epc->wr_wait);
}
PDBG("%s alloc ep %p\n", __func__, epc);
return epc;
}
void _c4iw_free_ep(struct kref *kref)
{
struct c4iw_ep *ep;
ep = container_of(kref, struct c4iw_ep, com.kref);
PDBG("%s ep %p state %s\n", __func__, ep, states[state_read(&ep->com)]);
if (test_bit(QP_REFERENCED, &ep->com.flags))
deref_qp(ep);
if (test_bit(RELEASE_RESOURCES, &ep->com.flags)) {
remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid);
cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, ep->hwtid);
dst_release(ep->dst);
cxgb4_l2t_release(ep->l2t);
}
if (test_bit(RELEASE_MAPINFO, &ep->com.flags)) {
print_addr(&ep->com, __func__, "remove_mapinfo/mapping");
iwpm_remove_mapinfo(&ep->com.local_addr,
&ep->com.mapped_local_addr);
iwpm_remove_mapping(&ep->com.local_addr, RDMA_NL_C4IW);
}
kfree(ep);
}
static void release_ep_resources(struct c4iw_ep *ep)
{
set_bit(RELEASE_RESOURCES, &ep->com.flags);
c4iw_put_ep(&ep->com);
}
static int status2errno(int status)
{
switch (status) {
case CPL_ERR_NONE:
return 0;
case CPL_ERR_CONN_RESET:
return -ECONNRESET;
case CPL_ERR_ARP_MISS:
return -EHOSTUNREACH;
case CPL_ERR_CONN_TIMEDOUT:
return -ETIMEDOUT;
case CPL_ERR_TCAM_FULL:
return -ENOMEM;
case CPL_ERR_CONN_EXIST:
return -EADDRINUSE;
default:
return -EIO;
}
}
/*
* Try and reuse skbs already allocated...
*/
static struct sk_buff *get_skb(struct sk_buff *skb, int len, gfp_t gfp)
{
if (skb && !skb_is_nonlinear(skb) && !skb_cloned(skb)) {
skb_trim(skb, 0);
skb_get(skb);
skb_reset_transport_header(skb);
} else {
skb = alloc_skb(len, gfp);
}
t4_set_arp_err_handler(skb, NULL, NULL);
return skb;
}
static struct net_device *get_real_dev(struct net_device *egress_dev)
{
return rdma_vlan_dev_real_dev(egress_dev) ? : egress_dev;
}
static int our_interface(struct c4iw_dev *dev, struct net_device *egress_dev)
{
int i;
egress_dev = get_real_dev(egress_dev);
for (i = 0; i < dev->rdev.lldi.nports; i++)
if (dev->rdev.lldi.ports[i] == egress_dev)
return 1;
return 0;
}
static struct dst_entry *find_route6(struct c4iw_dev *dev, __u8 *local_ip,
__u8 *peer_ip, __be16 local_port,
__be16 peer_port, u8 tos,
__u32 sin6_scope_id)
{
struct dst_entry *dst = NULL;
if (IS_ENABLED(CONFIG_IPV6)) {
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
memcpy(&fl6.daddr, peer_ip, 16);
memcpy(&fl6.saddr, local_ip, 16);
if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
fl6.flowi6_oif = sin6_scope_id;
dst = ip6_route_output(&init_net, NULL, &fl6);
if (!dst)
goto out;
if (!our_interface(dev, ip6_dst_idev(dst)->dev) &&
!(ip6_dst_idev(dst)->dev->flags & IFF_LOOPBACK)) {
dst_release(dst);
dst = NULL;
}
}
out:
return dst;
}
static struct dst_entry *find_route(struct c4iw_dev *dev, __be32 local_ip,
__be32 peer_ip, __be16 local_port,
__be16 peer_port, u8 tos)
{
struct rtable *rt;
struct flowi4 fl4;
struct neighbour *n;
rt = ip_route_output_ports(&init_net, &fl4, NULL, peer_ip, local_ip,
peer_port, local_port, IPPROTO_TCP,
tos, 0);
if (IS_ERR(rt))
return NULL;
n = dst_neigh_lookup(&rt->dst, &peer_ip);
if (!n)
return NULL;
if (!our_interface(dev, n->dev) &&
!(n->dev->flags & IFF_LOOPBACK)) {
neigh_release(n);
dst_release(&rt->dst);
return NULL;
}
neigh_release(n);
return &rt->dst;
}
static void arp_failure_discard(void *handle, struct sk_buff *skb)
{
PDBG("%s c4iw_dev %p\n", __func__, handle);
kfree_skb(skb);
}
/*
* Handle an ARP failure for an active open.
*/
static void act_open_req_arp_failure(void *handle, struct sk_buff *skb)
{
struct c4iw_ep *ep = handle;
printk(KERN_ERR MOD "ARP failure duing connect\n");
kfree_skb(skb);
connect_reply_upcall(ep, -EHOSTUNREACH);
state_set(&ep->com, DEAD);
remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
dst_release(ep->dst);
cxgb4_l2t_release(ep->l2t);
c4iw_put_ep(&ep->com);
}
/*
* Handle an ARP failure for a CPL_ABORT_REQ. Change it into a no RST variant
* and send it along.
*/
static void abort_arp_failure(void *handle, struct sk_buff *skb)
{
struct c4iw_rdev *rdev = handle;
struct cpl_abort_req *req = cplhdr(skb);
PDBG("%s rdev %p\n", __func__, rdev);
req->cmd = CPL_ABORT_NO_RST;
c4iw_ofld_send(rdev, skb);
}
static void send_flowc(struct c4iw_ep *ep, struct sk_buff *skb)
{
unsigned int flowclen = 80;
struct fw_flowc_wr *flowc;
int i;
skb = get_skb(skb, flowclen, GFP_KERNEL);
flowc = (struct fw_flowc_wr *)__skb_put(skb, flowclen);
flowc->op_to_nparams = cpu_to_be32(FW_WR_OP_V(FW_FLOWC_WR) |
FW_FLOWC_WR_NPARAMS_V(8));
flowc->flowid_len16 = cpu_to_be32(FW_WR_LEN16_V(DIV_ROUND_UP(flowclen,
16)) | FW_WR_FLOWID_V(ep->hwtid));
flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN;
flowc->mnemval[0].val = cpu_to_be32(FW_PFVF_CMD_PFN_V
(ep->com.dev->rdev.lldi.pf));
flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH;
flowc->mnemval[1].val = cpu_to_be32(ep->tx_chan);
flowc->mnemval[2].mnemonic = FW_FLOWC_MNEM_PORT;
flowc->mnemval[2].val = cpu_to_be32(ep->tx_chan);
flowc->mnemval[3].mnemonic = FW_FLOWC_MNEM_IQID;
flowc->mnemval[3].val = cpu_to_be32(ep->rss_qid);
flowc->mnemval[4].mnemonic = FW_FLOWC_MNEM_SNDNXT;
flowc->mnemval[4].val = cpu_to_be32(ep->snd_seq);
flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT;
flowc->mnemval[5].val = cpu_to_be32(ep->rcv_seq);
flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF;
flowc->mnemval[6].val = cpu_to_be32(ep->snd_win);
flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS;
flowc->mnemval[7].val = cpu_to_be32(ep->emss);
/* Pad WR to 16 byte boundary */
flowc->mnemval[8].mnemonic = 0;
flowc->mnemval[8].val = 0;
for (i = 0; i < 9; i++) {
flowc->mnemval[i].r4[0] = 0;
flowc->mnemval[i].r4[1] = 0;
flowc->mnemval[i].r4[2] = 0;
}
set_wr_txq(skb, CPL_PRIORITY_DATA, ep->txq_idx);
c4iw_ofld_send(&ep->com.dev->rdev, skb);
}
static int send_halfclose(struct c4iw_ep *ep, gfp_t gfp)
{
struct cpl_close_con_req *req;
struct sk_buff *skb;
int wrlen = roundup(sizeof *req, 16);
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
skb = get_skb(NULL, wrlen, gfp);
if (!skb) {
printk(KERN_ERR MOD "%s - failed to alloc skb\n", __func__);
return -ENOMEM;
}
set_wr_txq(skb, CPL_PRIORITY_DATA, ep->txq_idx);
t4_set_arp_err_handler(skb, NULL, arp_failure_discard);
req = (struct cpl_close_con_req *) skb_put(skb, wrlen);
memset(req, 0, wrlen);
INIT_TP_WR(req, ep->hwtid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ,
ep->hwtid));
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
static int send_abort(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
{
struct cpl_abort_req *req;
int wrlen = roundup(sizeof *req, 16);
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
skb = get_skb(skb, wrlen, gfp);
if (!skb) {
printk(KERN_ERR MOD "%s - failed to alloc skb.\n",
__func__);
return -ENOMEM;
}
set_wr_txq(skb, CPL_PRIORITY_DATA, ep->txq_idx);
t4_set_arp_err_handler(skb, &ep->com.dev->rdev, abort_arp_failure);
req = (struct cpl_abort_req *) skb_put(skb, wrlen);
memset(req, 0, wrlen);
INIT_TP_WR(req, ep->hwtid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ, ep->hwtid));
req->cmd = CPL_ABORT_SEND_RST;
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
/*
* c4iw_form_pm_msg - Form a port mapper message with mapping info
*/
static void c4iw_form_pm_msg(struct c4iw_ep *ep,
struct iwpm_sa_data *pm_msg)
{
memcpy(&pm_msg->loc_addr, &ep->com.local_addr,
sizeof(ep->com.local_addr));
memcpy(&pm_msg->rem_addr, &ep->com.remote_addr,
sizeof(ep->com.remote_addr));
}
/*
* c4iw_form_reg_msg - Form a port mapper message with dev info
*/
static void c4iw_form_reg_msg(struct c4iw_dev *dev,
struct iwpm_dev_data *pm_msg)
{
memcpy(pm_msg->dev_name, dev->ibdev.name, IWPM_DEVNAME_SIZE);
memcpy(pm_msg->if_name, dev->rdev.lldi.ports[0]->name,
IWPM_IFNAME_SIZE);
}
static void c4iw_record_pm_msg(struct c4iw_ep *ep,
struct iwpm_sa_data *pm_msg)
{
memcpy(&ep->com.mapped_local_addr, &pm_msg->mapped_loc_addr,
sizeof(ep->com.mapped_local_addr));
memcpy(&ep->com.mapped_remote_addr, &pm_msg->mapped_rem_addr,
sizeof(ep->com.mapped_remote_addr));
}
static void best_mtu(const unsigned short *mtus, unsigned short mtu,
unsigned int *idx, int use_ts, int ipv6)
{
unsigned short hdr_size = (ipv6 ?
sizeof(struct ipv6hdr) :
sizeof(struct iphdr)) +
sizeof(struct tcphdr) +
(use_ts ?
round_up(TCPOLEN_TIMESTAMP, 4) : 0);
unsigned short data_size = mtu - hdr_size;
cxgb4_best_aligned_mtu(mtus, hdr_size, data_size, 8, idx);
}
static int send_connect(struct c4iw_ep *ep)
{
struct cpl_act_open_req *req;
struct cpl_t5_act_open_req *t5_req;
struct cpl_act_open_req6 *req6;
struct cpl_t5_act_open_req6 *t5_req6;
struct sk_buff *skb;
u64 opt0;
u32 opt2;
unsigned int mtu_idx;
int wscale;
int wrlen;
int sizev4 = is_t4(ep->com.dev->rdev.lldi.adapter_type) ?
sizeof(struct cpl_act_open_req) :
sizeof(struct cpl_t5_act_open_req);
int sizev6 = is_t4(ep->com.dev->rdev.lldi.adapter_type) ?
sizeof(struct cpl_act_open_req6) :
sizeof(struct cpl_t5_act_open_req6);
struct sockaddr_in *la = (struct sockaddr_in *)
&ep->com.mapped_local_addr;
struct sockaddr_in *ra = (struct sockaddr_in *)
&ep->com.mapped_remote_addr;
struct sockaddr_in6 *la6 = (struct sockaddr_in6 *)
&ep->com.mapped_local_addr;
struct sockaddr_in6 *ra6 = (struct sockaddr_in6 *)
&ep->com.mapped_remote_addr;
int win;
wrlen = (ep->com.remote_addr.ss_family == AF_INET) ?
roundup(sizev4, 16) :
roundup(sizev6, 16);
PDBG("%s ep %p atid %u\n", __func__, ep, ep->atid);
skb = get_skb(NULL, wrlen, GFP_KERNEL);
if (!skb) {
printk(KERN_ERR MOD "%s - failed to alloc skb.\n",
__func__);
return -ENOMEM;
}
set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx);
best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
enable_tcp_timestamps,
(AF_INET == ep->com.remote_addr.ss_family) ? 0 : 1);
wscale = compute_wscale(rcv_win);
/*
* Specify the largest window that will fit in opt0. The
* remainder will be specified in the rx_data_ack.
*/
win = ep->rcv_win >> 10;
if (win > RCV_BUFSIZ_M)
win = RCV_BUFSIZ_M;
opt0 = (nocong ? NO_CONG_F : 0) |
KEEP_ALIVE_F |
DELACK_F |
WND_SCALE_V(wscale) |
MSS_IDX_V(mtu_idx) |
L2T_IDX_V(ep->l2t->idx) |
TX_CHAN_V(ep->tx_chan) |
SMAC_SEL_V(ep->smac_idx) |
DSCP_V(ep->tos) |
ULP_MODE_V(ULP_MODE_TCPDDP) |
RCV_BUFSIZ_V(win);
opt2 = RX_CHANNEL_V(0) |
CCTRL_ECN_V(enable_ecn) |
RSS_QUEUE_VALID_F | RSS_QUEUE_V(ep->rss_qid);
if (enable_tcp_timestamps)
opt2 |= TSTAMPS_EN_F;
if (enable_tcp_sack)
opt2 |= SACK_EN_F;
if (wscale && enable_tcp_window_scaling)
opt2 |= WND_SCALE_EN_F;
if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
opt2 |= T5_OPT_2_VALID_F;
opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
}
t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure);
if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) {
if (ep->com.remote_addr.ss_family == AF_INET) {
req = (struct cpl_act_open_req *) skb_put(skb, wrlen);
INIT_TP_WR(req, 0);
OPCODE_TID(req) = cpu_to_be32(
MK_OPCODE_TID(CPL_ACT_OPEN_REQ,
((ep->rss_qid << 14) | ep->atid)));
req->local_port = la->sin_port;
req->peer_port = ra->sin_port;
req->local_ip = la->sin_addr.s_addr;
req->peer_ip = ra->sin_addr.s_addr;
req->opt0 = cpu_to_be64(opt0);
req->params = cpu_to_be32(cxgb4_select_ntuple(
ep->com.dev->rdev.lldi.ports[0],
ep->l2t));
req->opt2 = cpu_to_be32(opt2);
} else {
req6 = (struct cpl_act_open_req6 *)skb_put(skb, wrlen);
INIT_TP_WR(req6, 0);
OPCODE_TID(req6) = cpu_to_be32(
MK_OPCODE_TID(CPL_ACT_OPEN_REQ6,
((ep->rss_qid<<14)|ep->atid)));
req6->local_port = la6->sin6_port;
req6->peer_port = ra6->sin6_port;
req6->local_ip_hi = *((__be64 *)
(la6->sin6_addr.s6_addr));
req6->local_ip_lo = *((__be64 *)
(la6->sin6_addr.s6_addr + 8));
req6->peer_ip_hi = *((__be64 *)
(ra6->sin6_addr.s6_addr));
req6->peer_ip_lo = *((__be64 *)
(ra6->sin6_addr.s6_addr + 8));
req6->opt0 = cpu_to_be64(opt0);
req6->params = cpu_to_be32(cxgb4_select_ntuple(
ep->com.dev->rdev.lldi.ports[0],
ep->l2t));
req6->opt2 = cpu_to_be32(opt2);
}
} else {
u32 isn = (prandom_u32() & ~7UL) - 1;
if (peer2peer)
isn += 4;
if (ep->com.remote_addr.ss_family == AF_INET) {
t5_req = (struct cpl_t5_act_open_req *)
skb_put(skb, wrlen);
INIT_TP_WR(t5_req, 0);
OPCODE_TID(t5_req) = cpu_to_be32(
MK_OPCODE_TID(CPL_ACT_OPEN_REQ,
((ep->rss_qid << 14) | ep->atid)));
t5_req->local_port = la->sin_port;
t5_req->peer_port = ra->sin_port;
t5_req->local_ip = la->sin_addr.s_addr;
t5_req->peer_ip = ra->sin_addr.s_addr;
t5_req->opt0 = cpu_to_be64(opt0);
t5_req->params = cpu_to_be64(FILTER_TUPLE_V(
cxgb4_select_ntuple(
ep->com.dev->rdev.lldi.ports[0],
ep->l2t)));
t5_req->rsvd = cpu_to_be32(isn);
PDBG("%s snd_isn %u\n", __func__,
be32_to_cpu(t5_req->rsvd));
t5_req->opt2 = cpu_to_be32(opt2);
} else {
t5_req6 = (struct cpl_t5_act_open_req6 *)
skb_put(skb, wrlen);
INIT_TP_WR(t5_req6, 0);
OPCODE_TID(t5_req6) = cpu_to_be32(
MK_OPCODE_TID(CPL_ACT_OPEN_REQ6,
((ep->rss_qid<<14)|ep->atid)));
t5_req6->local_port = la6->sin6_port;
t5_req6->peer_port = ra6->sin6_port;
t5_req6->local_ip_hi = *((__be64 *)
(la6->sin6_addr.s6_addr));
t5_req6->local_ip_lo = *((__be64 *)
(la6->sin6_addr.s6_addr + 8));
t5_req6->peer_ip_hi = *((__be64 *)
(ra6->sin6_addr.s6_addr));
t5_req6->peer_ip_lo = *((__be64 *)
(ra6->sin6_addr.s6_addr + 8));
t5_req6->opt0 = cpu_to_be64(opt0);
t5_req6->params = cpu_to_be64(FILTER_TUPLE_V(
cxgb4_select_ntuple(
ep->com.dev->rdev.lldi.ports[0],
ep->l2t)));
t5_req6->rsvd = cpu_to_be32(isn);
PDBG("%s snd_isn %u\n", __func__,
be32_to_cpu(t5_req6->rsvd));
t5_req6->opt2 = cpu_to_be32(opt2);
}
}
set_bit(ACT_OPEN_REQ, &ep->com.history);
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
static void send_mpa_req(struct c4iw_ep *ep, struct sk_buff *skb,
u8 mpa_rev_to_use)
{
int mpalen, wrlen;
struct fw_ofld_tx_data_wr *req;
struct mpa_message *mpa;
struct mpa_v2_conn_params mpa_v2_params;
PDBG("%s ep %p tid %u pd_len %d\n", __func__, ep, ep->hwtid, ep->plen);
BUG_ON(skb_cloned(skb));
mpalen = sizeof(*mpa) + ep->plen;
if (mpa_rev_to_use == 2)
mpalen += sizeof(struct mpa_v2_conn_params);
wrlen = roundup(mpalen + sizeof *req, 16);
skb = get_skb(skb, wrlen, GFP_KERNEL);
if (!skb) {
connect_reply_upcall(ep, -ENOMEM);
return;
}
set_wr_txq(skb, CPL_PRIORITY_DATA, ep->txq_idx);
req = (struct fw_ofld_tx_data_wr *)skb_put(skb, wrlen);
memset(req, 0, wrlen);
req->op_to_immdlen = cpu_to_be32(
FW_WR_OP_V(FW_OFLD_TX_DATA_WR) |
FW_WR_COMPL_F |
FW_WR_IMMDLEN_V(mpalen));
req->flowid_len16 = cpu_to_be32(
FW_WR_FLOWID_V(ep->hwtid) |
FW_WR_LEN16_V(wrlen >> 4));
req->plen = cpu_to_be32(mpalen);
req->tunnel_to_proxy = cpu_to_be32(
FW_OFLD_TX_DATA_WR_FLUSH_F |
FW_OFLD_TX_DATA_WR_SHOVE_F);
mpa = (struct mpa_message *)(req + 1);
memcpy(mpa->key, MPA_KEY_REQ, sizeof(mpa->key));
mpa->flags = (crc_enabled ? MPA_CRC : 0) |
(markers_enabled ? MPA_MARKERS : 0) |
(mpa_rev_to_use == 2 ? MPA_ENHANCED_RDMA_CONN : 0);
mpa->private_data_size = htons(ep->plen);
mpa->revision = mpa_rev_to_use;
if (mpa_rev_to_use == 1) {
ep->tried_with_mpa_v1 = 1;
ep->retry_with_mpa_v1 = 0;
}
if (mpa_rev_to_use == 2) {
mpa->private_data_size = htons(ntohs(mpa->private_data_size) +
sizeof (struct mpa_v2_conn_params));
PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird,
ep->ord);
mpa_v2_params.ird = htons((u16)ep->ird);
mpa_v2_params.ord = htons((u16)ep->ord);
if (peer2peer) {
mpa_v2_params.ird |= htons(MPA_V2_PEER2PEER_MODEL);
if (p2p_type == FW_RI_INIT_P2PTYPE_RDMA_WRITE)
mpa_v2_params.ord |=
htons(MPA_V2_RDMA_WRITE_RTR);
else if (p2p_type == FW_RI_INIT_P2PTYPE_READ_REQ)
mpa_v2_params.ord |=
htons(MPA_V2_RDMA_READ_RTR);
}
memcpy(mpa->private_data, &mpa_v2_params,
sizeof(struct mpa_v2_conn_params));
if (ep->plen)
memcpy(mpa->private_data +
sizeof(struct mpa_v2_conn_params),
ep->mpa_pkt + sizeof(*mpa), ep->plen);
} else
if (ep->plen)
memcpy(mpa->private_data,
ep->mpa_pkt + sizeof(*mpa), ep->plen);
/*
* Reference the mpa skb. This ensures the data area
* will remain in memory until the hw acks the tx.
* Function fw4_ack() will deref it.
*/
skb_get(skb);
t4_set_arp_err_handler(skb, NULL, arp_failure_discard);
BUG_ON(ep->mpa_skb);
ep->mpa_skb = skb;
c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
start_ep_timer(ep);
__state_set(&ep->com, MPA_REQ_SENT);
ep->mpa_attr.initiator = 1;
ep->snd_seq += mpalen;
return;
}
static int send_mpa_reject(struct c4iw_ep *ep, const void *pdata, u8 plen)
{
int mpalen, wrlen;
struct fw_ofld_tx_data_wr *req;
struct mpa_message *mpa;
struct sk_buff *skb;
struct mpa_v2_conn_params mpa_v2_params;
PDBG("%s ep %p tid %u pd_len %d\n", __func__, ep, ep->hwtid, ep->plen);
mpalen = sizeof(*mpa) + plen;
if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn)
mpalen += sizeof(struct mpa_v2_conn_params);
wrlen = roundup(mpalen + sizeof *req, 16);
skb = get_skb(NULL, wrlen, GFP_KERNEL);
if (!skb) {
printk(KERN_ERR MOD "%s - cannot alloc skb!\n", __func__);
return -ENOMEM;
}
set_wr_txq(skb, CPL_PRIORITY_DATA, ep->txq_idx);
req = (struct fw_ofld_tx_data_wr *)skb_put(skb, wrlen);
memset(req, 0, wrlen);
req->op_to_immdlen = cpu_to_be32(
FW_WR_OP_V(FW_OFLD_TX_DATA_WR) |
FW_WR_COMPL_F |
FW_WR_IMMDLEN_V(mpalen));
req->flowid_len16 = cpu_to_be32(
FW_WR_FLOWID_V(ep->hwtid) |
FW_WR_LEN16_V(wrlen >> 4));
req->plen = cpu_to_be32(mpalen);
req->tunnel_to_proxy = cpu_to_be32(
FW_OFLD_TX_DATA_WR_FLUSH_F |
FW_OFLD_TX_DATA_WR_SHOVE_F);
mpa = (struct mpa_message *)(req + 1);
memset(mpa, 0, sizeof(*mpa));
memcpy(mpa->key, MPA_KEY_REP, sizeof(mpa->key));
mpa->flags = MPA_REJECT;
mpa->revision = ep->mpa_attr.version;
mpa->private_data_size = htons(plen);
if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) {
mpa->flags |= MPA_ENHANCED_RDMA_CONN;
mpa->private_data_size = htons(ntohs(mpa->private_data_size) +
sizeof (struct mpa_v2_conn_params));
mpa_v2_params.ird = htons(((u16)ep->ird) |
(peer2peer ? MPA_V2_PEER2PEER_MODEL :
0));
mpa_v2_params.ord = htons(((u16)ep->ord) | (peer2peer ?
(p2p_type ==
FW_RI_INIT_P2PTYPE_RDMA_WRITE ?
MPA_V2_RDMA_WRITE_RTR : p2p_type ==
FW_RI_INIT_P2PTYPE_READ_REQ ?
MPA_V2_RDMA_READ_RTR : 0) : 0));
memcpy(mpa->private_data, &mpa_v2_params,
sizeof(struct mpa_v2_conn_params));
if (ep->plen)
memcpy(mpa->private_data +
sizeof(struct mpa_v2_conn_params), pdata, plen);
} else
if (plen)
memcpy(mpa->private_data, pdata, plen);
/*
* Reference the mpa skb again. This ensures the data area
* will remain in memory until the hw acks the tx.
* Function fw4_ack() will deref it.
*/
skb_get(skb);
set_wr_txq(skb, CPL_PRIORITY_DATA, ep->txq_idx);
t4_set_arp_err_handler(skb, NULL, arp_failure_discard);
BUG_ON(ep->mpa_skb);
ep->mpa_skb = skb;
ep->snd_seq += mpalen;
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
static int send_mpa_reply(struct c4iw_ep *ep, const void *pdata, u8 plen)
{
int mpalen, wrlen;
struct fw_ofld_tx_data_wr *req;
struct mpa_message *mpa;
struct sk_buff *skb;
struct mpa_v2_conn_params mpa_v2_params;
PDBG("%s ep %p tid %u pd_len %d\n", __func__, ep, ep->hwtid, ep->plen);
mpalen = sizeof(*mpa) + plen;
if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn)
mpalen += sizeof(struct mpa_v2_conn_params);
wrlen = roundup(mpalen + sizeof *req, 16);
skb = get_skb(NULL, wrlen, GFP_KERNEL);
if (!skb) {
printk(KERN_ERR MOD "%s - cannot alloc skb!\n", __func__);
return -ENOMEM;
}
set_wr_txq(skb, CPL_PRIORITY_DATA, ep->txq_idx);
req = (struct fw_ofld_tx_data_wr *) skb_put(skb, wrlen);
memset(req, 0, wrlen);
req->op_to_immdlen = cpu_to_be32(
FW_WR_OP_V(FW_OFLD_TX_DATA_WR) |
FW_WR_COMPL_F |
FW_WR_IMMDLEN_V(mpalen));
req->flowid_len16 = cpu_to_be32(
FW_WR_FLOWID_V(ep->hwtid) |
FW_WR_LEN16_V(wrlen >> 4));
req->plen = cpu_to_be32(mpalen);
req->tunnel_to_proxy = cpu_to_be32(
FW_OFLD_TX_DATA_WR_FLUSH_F |
FW_OFLD_TX_DATA_WR_SHOVE_F);
mpa = (struct mpa_message *)(req + 1);
memset(mpa, 0, sizeof(*mpa));
memcpy(mpa->key, MPA_KEY_REP, sizeof(mpa->key));
mpa->flags = (ep->mpa_attr.crc_enabled ? MPA_CRC : 0) |
(markers_enabled ? MPA_MARKERS : 0);
mpa->revision = ep->mpa_attr.version;
mpa->private_data_size = htons(plen);
if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) {
mpa->flags |= MPA_ENHANCED_RDMA_CONN;
mpa->private_data_size = htons(ntohs(mpa->private_data_size) +
sizeof (struct mpa_v2_conn_params));
mpa_v2_params.ird = htons((u16)ep->ird);
mpa_v2_params.ord = htons((u16)ep->ord);
if (peer2peer && (ep->mpa_attr.p2p_type !=
FW_RI_INIT_P2PTYPE_DISABLED)) {
mpa_v2_params.ird |= htons(MPA_V2_PEER2PEER_MODEL);
if (p2p_type == FW_RI_INIT_P2PTYPE_RDMA_WRITE)
mpa_v2_params.ord |=
htons(MPA_V2_RDMA_WRITE_RTR);
else if (p2p_type == FW_RI_INIT_P2PTYPE_READ_REQ)
mpa_v2_params.ord |=
htons(MPA_V2_RDMA_READ_RTR);
}
memcpy(mpa->private_data, &mpa_v2_params,
sizeof(struct mpa_v2_conn_params));
if (ep->plen)
memcpy(mpa->private_data +
sizeof(struct mpa_v2_conn_params), pdata, plen);
} else
if (plen)
memcpy(mpa->private_data, pdata, plen);
/*
* Reference the mpa skb. This ensures the data area
* will remain in memory until the hw acks the tx.
* Function fw4_ack() will deref it.
*/
skb_get(skb);
t4_set_arp_err_handler(skb, NULL, arp_failure_discard);
ep->mpa_skb = skb;
__state_set(&ep->com, MPA_REP_SENT);
ep->snd_seq += mpalen;
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
static int act_establish(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *ep;
struct cpl_act_establish *req = cplhdr(skb);
unsigned int tid = GET_TID(req);
unsigned int atid = TID_TID_G(ntohl(req->tos_atid));
struct tid_info *t = dev->rdev.lldi.tids;
ep = lookup_atid(t, atid);
PDBG("%s ep %p tid %u snd_isn %u rcv_isn %u\n", __func__, ep, tid,
be32_to_cpu(req->snd_isn), be32_to_cpu(req->rcv_isn));
mutex_lock(&ep->com.mutex);
dst_confirm(ep->dst);
/* setup the hwtid for this connection */
ep->hwtid = tid;
cxgb4_insert_tid(t, ep, tid);
insert_handle(dev, &dev->hwtid_idr, ep, ep->hwtid);
ep->snd_seq = be32_to_cpu(req->snd_isn);
ep->rcv_seq = be32_to_cpu(req->rcv_isn);
set_emss(ep, ntohs(req->tcp_opt));
/* dealloc the atid */
remove_handle(ep->com.dev, &ep->com.dev->atid_idr, atid);
cxgb4_free_atid(t, atid);
set_bit(ACT_ESTAB, &ep->com.history);
/* start MPA negotiation */
send_flowc(ep, NULL);
if (ep->retry_with_mpa_v1)
send_mpa_req(ep, skb, 1);
else
send_mpa_req(ep, skb, mpa_rev);
mutex_unlock(&ep->com.mutex);
return 0;
}
static void close_complete_upcall(struct c4iw_ep *ep, int status)
{
struct iw_cm_event event;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_CLOSE;
event.status = status;
if (ep->com.cm_id) {
PDBG("close complete delivered ep %p cm_id %p tid %u\n",
ep, ep->com.cm_id, ep->hwtid);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
ep->com.cm_id->rem_ref(ep->com.cm_id);
ep->com.cm_id = NULL;
set_bit(CLOSE_UPCALL, &ep->com.history);
}
}
static int abort_connection(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
{
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
__state_set(&ep->com, ABORTING);
set_bit(ABORT_CONN, &ep->com.history);
return send_abort(ep, skb, gfp);
}
static void peer_close_upcall(struct c4iw_ep *ep)
{
struct iw_cm_event event;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_DISCONNECT;
if (ep->com.cm_id) {
PDBG("peer close delivered ep %p cm_id %p tid %u\n",
ep, ep->com.cm_id, ep->hwtid);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
set_bit(DISCONN_UPCALL, &ep->com.history);
}
}
static void peer_abort_upcall(struct c4iw_ep *ep)
{
struct iw_cm_event event;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_CLOSE;
event.status = -ECONNRESET;
if (ep->com.cm_id) {
PDBG("abort delivered ep %p cm_id %p tid %u\n", ep,
ep->com.cm_id, ep->hwtid);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
ep->com.cm_id->rem_ref(ep->com.cm_id);
ep->com.cm_id = NULL;
set_bit(ABORT_UPCALL, &ep->com.history);
}
}
static void connect_reply_upcall(struct c4iw_ep *ep, int status)
{
struct iw_cm_event event;
PDBG("%s ep %p tid %u status %d\n", __func__, ep, ep->hwtid, status);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_CONNECT_REPLY;
event.status = status;
memcpy(&event.local_addr, &ep->com.local_addr,
sizeof(ep->com.local_addr));
memcpy(&event.remote_addr, &ep->com.remote_addr,
sizeof(ep->com.remote_addr));
if ((status == 0) || (status == -ECONNREFUSED)) {
if (!ep->tried_with_mpa_v1) {
/* this means MPA_v2 is used */
event.private_data_len = ep->plen -
sizeof(struct mpa_v2_conn_params);
event.private_data = ep->mpa_pkt +
sizeof(struct mpa_message) +
sizeof(struct mpa_v2_conn_params);
} else {
/* this means MPA_v1 is used */
event.private_data_len = ep->plen;
event.private_data = ep->mpa_pkt +
sizeof(struct mpa_message);
}
}
PDBG("%s ep %p tid %u status %d\n", __func__, ep,
ep->hwtid, status);
set_bit(CONN_RPL_UPCALL, &ep->com.history);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
if (status < 0) {
ep->com.cm_id->rem_ref(ep->com.cm_id);
ep->com.cm_id = NULL;
}
}
static int connect_request_upcall(struct c4iw_ep *ep)
{
struct iw_cm_event event;
int ret;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_CONNECT_REQUEST;
memcpy(&event.local_addr, &ep->com.local_addr,
sizeof(ep->com.local_addr));
memcpy(&event.remote_addr, &ep->com.remote_addr,
sizeof(ep->com.remote_addr));
event.provider_data = ep;
if (!ep->tried_with_mpa_v1) {
/* this means MPA_v2 is used */
event.ord = ep->ord;
event.ird = ep->ird;
event.private_data_len = ep->plen -
sizeof(struct mpa_v2_conn_params);
event.private_data = ep->mpa_pkt + sizeof(struct mpa_message) +
sizeof(struct mpa_v2_conn_params);
} else {
/* this means MPA_v1 is used. Send max supported */
event.ord = cur_max_read_depth(ep->com.dev);
event.ird = cur_max_read_depth(ep->com.dev);
event.private_data_len = ep->plen;
event.private_data = ep->mpa_pkt + sizeof(struct mpa_message);
}
c4iw_get_ep(&ep->com);
ret = ep->parent_ep->com.cm_id->event_handler(ep->parent_ep->com.cm_id,
&event);
if (ret)
c4iw_put_ep(&ep->com);
set_bit(CONNREQ_UPCALL, &ep->com.history);
c4iw_put_ep(&ep->parent_ep->com);
return ret;
}
static void established_upcall(struct c4iw_ep *ep)
{
struct iw_cm_event event;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_ESTABLISHED;
event.ird = ep->ird;
event.ord = ep->ord;
if (ep->com.cm_id) {
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
set_bit(ESTAB_UPCALL, &ep->com.history);
}
}
static int update_rx_credits(struct c4iw_ep *ep, u32 credits)
{
struct cpl_rx_data_ack *req;
struct sk_buff *skb;
int wrlen = roundup(sizeof *req, 16);
PDBG("%s ep %p tid %u credits %u\n", __func__, ep, ep->hwtid, credits);
skb = get_skb(NULL, wrlen, GFP_KERNEL);
if (!skb) {
printk(KERN_ERR MOD "update_rx_credits - cannot alloc skb!\n");
return 0;
}
/*
* If we couldn't specify the entire rcv window at connection setup
* due to the limit in the number of bits in the RCV_BUFSIZ field,
* then add the overage in to the credits returned.
*/
if (ep->rcv_win > RCV_BUFSIZ_M * 1024)
credits += ep->rcv_win - RCV_BUFSIZ_M * 1024;
req = (struct cpl_rx_data_ack *) skb_put(skb, wrlen);
memset(req, 0, wrlen);
INIT_TP_WR(req, ep->hwtid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK,
ep->hwtid));
req->credit_dack = cpu_to_be32(credits | RX_FORCE_ACK_F |
RX_DACK_CHANGE_F |
RX_DACK_MODE_V(dack_mode));
set_wr_txq(skb, CPL_PRIORITY_ACK, ep->ctrlq_idx);
c4iw_ofld_send(&ep->com.dev->rdev, skb);
return credits;
}
#define RELAXED_IRD_NEGOTIATION 1
static int process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
{
struct mpa_message *mpa;
struct mpa_v2_conn_params *mpa_v2_params;
u16 plen;
u16 resp_ird, resp_ord;
u8 rtr_mismatch = 0, insuff_ird = 0;
struct c4iw_qp_attributes attrs;
enum c4iw_qp_attr_mask mask;
int err;
int disconnect = 0;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
/*
* Stop mpa timer. If it expired, then
* we ignore the MPA reply. process_timeout()
* will abort the connection.
*/
if (stop_ep_timer(ep))
return 0;
/*
* If we get more than the supported amount of private data
* then we must fail this connection.
*/
if (ep->mpa_pkt_len + skb->len > sizeof(ep->mpa_pkt)) {
err = -EINVAL;
goto err;
}
/*
* copy the new data into our accumulation buffer.
*/
skb_copy_from_linear_data(skb, &(ep->mpa_pkt[ep->mpa_pkt_len]),
skb->len);
ep->mpa_pkt_len += skb->len;
/*
* if we don't even have the mpa message, then bail.
*/
if (ep->mpa_pkt_len < sizeof(*mpa))
return 0;
mpa = (struct mpa_message *) ep->mpa_pkt;
/* Validate MPA header. */
if (mpa->revision > mpa_rev) {
printk(KERN_ERR MOD "%s MPA version mismatch. Local = %d,"
" Received = %d\n", __func__, mpa_rev, mpa->revision);
err = -EPROTO;
goto err;
}
if (memcmp(mpa->key, MPA_KEY_REP, sizeof(mpa->key))) {
err = -EPROTO;
goto err;
}
plen = ntohs(mpa->private_data_size);
/*
* Fail if there's too much private data.
*/
if (plen > MPA_MAX_PRIVATE_DATA) {
err = -EPROTO;
goto err;
}
/*
* If plen does not account for pkt size
*/
if (ep->mpa_pkt_len > (sizeof(*mpa) + plen)) {
err = -EPROTO;
goto err;
}
ep->plen = (u8) plen;
/*
* If we don't have all the pdata yet, then bail.
* We'll continue process when more data arrives.
*/
if (ep->mpa_pkt_len < (sizeof(*mpa) + plen))
return 0;
if (mpa->flags & MPA_REJECT) {
err = -ECONNREFUSED;
goto err;
}
/*
* If we get here we have accumulated the entire mpa
* start reply message including private data. And
* the MPA header is valid.
*/
__state_set(&ep->com, FPDU_MODE);
ep->mpa_attr.crc_enabled = (mpa->flags & MPA_CRC) | crc_enabled ? 1 : 0;
ep->mpa_attr.recv_marker_enabled = markers_enabled;
ep->mpa_attr.xmit_marker_enabled = mpa->flags & MPA_MARKERS ? 1 : 0;
ep->mpa_attr.version = mpa->revision;
ep->mpa_attr.p2p_type = FW_RI_INIT_P2PTYPE_DISABLED;
if (mpa->revision == 2) {
ep->mpa_attr.enhanced_rdma_conn =
mpa->flags & MPA_ENHANCED_RDMA_CONN ? 1 : 0;
if (ep->mpa_attr.enhanced_rdma_conn) {
mpa_v2_params = (struct mpa_v2_conn_params *)
(ep->mpa_pkt + sizeof(*mpa));
resp_ird = ntohs(mpa_v2_params->ird) &
MPA_V2_IRD_ORD_MASK;
resp_ord = ntohs(mpa_v2_params->ord) &
MPA_V2_IRD_ORD_MASK;
PDBG("%s responder ird %u ord %u ep ird %u ord %u\n",
__func__, resp_ird, resp_ord, ep->ird, ep->ord);
/*
* This is a double-check. Ideally, below checks are
* not required since ird/ord stuff has been taken
* care of in c4iw_accept_cr
*/
if (ep->ird < resp_ord) {
if (RELAXED_IRD_NEGOTIATION && resp_ord <=
ep->com.dev->rdev.lldi.max_ordird_qp)
ep->ird = resp_ord;
else
insuff_ird = 1;
} else if (ep->ird > resp_ord) {
ep->ird = resp_ord;
}
if (ep->ord > resp_ird) {
if (RELAXED_IRD_NEGOTIATION)
ep->ord = resp_ird;
else
insuff_ird = 1;
}
if (insuff_ird) {
err = -ENOMEM;
ep->ird = resp_ord;
ep->ord = resp_ird;
}
if (ntohs(mpa_v2_params->ird) &
MPA_V2_PEER2PEER_MODEL) {
if (ntohs(mpa_v2_params->ord) &
MPA_V2_RDMA_WRITE_RTR)
ep->mpa_attr.p2p_type =
FW_RI_INIT_P2PTYPE_RDMA_WRITE;
else if (ntohs(mpa_v2_params->ord) &
MPA_V2_RDMA_READ_RTR)
ep->mpa_attr.p2p_type =
FW_RI_INIT_P2PTYPE_READ_REQ;
}
}
} else if (mpa->revision == 1)
if (peer2peer)
ep->mpa_attr.p2p_type = p2p_type;
PDBG("%s - crc_enabled=%d, recv_marker_enabled=%d, "
"xmit_marker_enabled=%d, version=%d p2p_type=%d local-p2p_type = "
"%d\n", __func__, ep->mpa_attr.crc_enabled,
ep->mpa_attr.recv_marker_enabled,
ep->mpa_attr.xmit_marker_enabled, ep->mpa_attr.version,
ep->mpa_attr.p2p_type, p2p_type);
/*
* If responder's RTR does not match with that of initiator, assign
* FW_RI_INIT_P2PTYPE_DISABLED in mpa attributes so that RTR is not
* generated when moving QP to RTS state.
* A TERM message will be sent after QP has moved to RTS state
*/
if ((ep->mpa_attr.version == 2) && peer2peer &&
(ep->mpa_attr.p2p_type != p2p_type)) {
ep->mpa_attr.p2p_type = FW_RI_INIT_P2PTYPE_DISABLED;
rtr_mismatch = 1;
}
attrs.mpa_attr = ep->mpa_attr;
attrs.max_ird = ep->ird;
attrs.max_ord = ep->ord;
attrs.llp_stream_handle = ep;
attrs.next_state = C4IW_QP_STATE_RTS;
mask = C4IW_QP_ATTR_NEXT_STATE |
C4IW_QP_ATTR_LLP_STREAM_HANDLE | C4IW_QP_ATTR_MPA_ATTR |
C4IW_QP_ATTR_MAX_IRD | C4IW_QP_ATTR_MAX_ORD;
/* bind QP and TID with INIT_WR */
err = c4iw_modify_qp(ep->com.qp->rhp,
ep->com.qp, mask, &attrs, 1);
if (err)
goto err;
/*
* If responder's RTR requirement did not match with what initiator
* supports, generate TERM message
*/
if (rtr_mismatch) {
printk(KERN_ERR "%s: RTR mismatch, sending TERM\n", __func__);
attrs.layer_etype = LAYER_MPA | DDP_LLP;
attrs.ecode = MPA_NOMATCH_RTR;
attrs.next_state = C4IW_QP_STATE_TERMINATE;
attrs.send_term = 1;
err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
err = -ENOMEM;
disconnect = 1;
goto out;
}
/*
* Generate TERM if initiator IRD is not sufficient for responder
* provided ORD. Currently, we do the same behaviour even when
* responder provided IRD is also not sufficient as regards to
* initiator ORD.
*/
if (insuff_ird) {
printk(KERN_ERR "%s: Insufficient IRD, sending TERM\n",
__func__);
attrs.layer_etype = LAYER_MPA | DDP_LLP;
attrs.ecode = MPA_INSUFF_IRD;
attrs.next_state = C4IW_QP_STATE_TERMINATE;
attrs.send_term = 1;
err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
err = -ENOMEM;
disconnect = 1;
goto out;
}
goto out;
err:
__state_set(&ep->com, ABORTING);
send_abort(ep, skb, GFP_KERNEL);
out:
connect_reply_upcall(ep, err);
return disconnect;
}
static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
{
struct mpa_message *mpa;
struct mpa_v2_conn_params *mpa_v2_params;
u16 plen;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
/*
* If we get more than the supported amount of private data
* then we must fail this connection.
*/
if (ep->mpa_pkt_len + skb->len > sizeof(ep->mpa_pkt)) {
(void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
PDBG("%s enter (%s line %u)\n", __func__, __FILE__, __LINE__);
/*
* Copy the new data into our accumulation buffer.
*/
skb_copy_from_linear_data(skb, &(ep->mpa_pkt[ep->mpa_pkt_len]),
skb->len);
ep->mpa_pkt_len += skb->len;
/*
* If we don't even have the mpa message, then bail.
* We'll continue process when more data arrives.
*/
if (ep->mpa_pkt_len < sizeof(*mpa))
return;
PDBG("%s enter (%s line %u)\n", __func__, __FILE__, __LINE__);
mpa = (struct mpa_message *) ep->mpa_pkt;
/*
* Validate MPA Header.
*/
if (mpa->revision > mpa_rev) {
printk(KERN_ERR MOD "%s MPA version mismatch. Local = %d,"
" Received = %d\n", __func__, mpa_rev, mpa->revision);
(void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
if (memcmp(mpa->key, MPA_KEY_REQ, sizeof(mpa->key))) {
(void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
plen = ntohs(mpa->private_data_size);
/*
* Fail if there's too much private data.
*/
if (plen > MPA_MAX_PRIVATE_DATA) {
(void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
/*
* If plen does not account for pkt size
*/
if (ep->mpa_pkt_len > (sizeof(*mpa) + plen)) {
(void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
ep->plen = (u8) plen;
/*
* If we don't have all the pdata yet, then bail.
*/
if (ep->mpa_pkt_len < (sizeof(*mpa) + plen))
return;
/*
* If we get here we have accumulated the entire mpa
* start reply message including private data.
*/
ep->mpa_attr.initiator = 0;
ep->mpa_attr.crc_enabled = (mpa->flags & MPA_CRC) | crc_enabled ? 1 : 0;
ep->mpa_attr.recv_marker_enabled = markers_enabled;
ep->mpa_attr.xmit_marker_enabled = mpa->flags & MPA_MARKERS ? 1 : 0;
ep->mpa_attr.version = mpa->revision;
if (mpa->revision == 1)
ep->tried_with_mpa_v1 = 1;
ep->mpa_attr.p2p_type = FW_RI_INIT_P2PTYPE_DISABLED;
if (mpa->revision == 2) {
ep->mpa_attr.enhanced_rdma_conn =
mpa->flags & MPA_ENHANCED_RDMA_CONN ? 1 : 0;
if (ep->mpa_attr.enhanced_rdma_conn) {
mpa_v2_params = (struct mpa_v2_conn_params *)
(ep->mpa_pkt + sizeof(*mpa));
ep->ird = ntohs(mpa_v2_params->ird) &
MPA_V2_IRD_ORD_MASK;
ep->ord = ntohs(mpa_v2_params->ord) &
MPA_V2_IRD_ORD_MASK;
PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird,
ep->ord);
if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL)
if (peer2peer) {
if (ntohs(mpa_v2_params->ord) &
MPA_V2_RDMA_WRITE_RTR)
ep->mpa_attr.p2p_type =
FW_RI_INIT_P2PTYPE_RDMA_WRITE;
else if (ntohs(mpa_v2_params->ord) &
MPA_V2_RDMA_READ_RTR)
ep->mpa_attr.p2p_type =
FW_RI_INIT_P2PTYPE_READ_REQ;
}
}
} else if (mpa->revision == 1)
if (peer2peer)
ep->mpa_attr.p2p_type = p2p_type;
PDBG("%s - crc_enabled=%d, recv_marker_enabled=%d, "
"xmit_marker_enabled=%d, version=%d p2p_type=%d\n", __func__,
ep->mpa_attr.crc_enabled, ep->mpa_attr.recv_marker_enabled,
ep->mpa_attr.xmit_marker_enabled, ep->mpa_attr.version,
ep->mpa_attr.p2p_type);
/*
* If the endpoint timer already expired, then we ignore
* the start request. process_timeout() will abort
* the connection.
*/
if (!stop_ep_timer(ep)) {
__state_set(&ep->com, MPA_REQ_RCVD);
/* drive upcall */
mutex_lock_nested(&ep->parent_ep->com.mutex,
SINGLE_DEPTH_NESTING);
if (ep->parent_ep->com.state != DEAD) {
if (connect_request_upcall(ep))
abort_connection(ep, skb, GFP_KERNEL);
} else {
abort_connection(ep, skb, GFP_KERNEL);
}
mutex_unlock(&ep->parent_ep->com.mutex);
}
return;
}
static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *ep;
struct cpl_rx_data *hdr = cplhdr(skb);
unsigned int dlen = ntohs(hdr->len);
unsigned int tid = GET_TID(hdr);
struct tid_info *t = dev->rdev.lldi.tids;
__u8 status = hdr->status;
int disconnect = 0;
ep = lookup_tid(t, tid);
if (!ep)
return 0;
PDBG("%s ep %p tid %u dlen %u\n", __func__, ep, ep->hwtid, dlen);
skb_pull(skb, sizeof(*hdr));
skb_trim(skb, dlen);
mutex_lock(&ep->com.mutex);
/* update RX credits */
update_rx_credits(ep, dlen);
switch (ep->com.state) {
case MPA_REQ_SENT:
ep->rcv_seq += dlen;
disconnect = process_mpa_reply(ep, skb);
break;
case MPA_REQ_WAIT:
ep->rcv_seq += dlen;
process_mpa_request(ep, skb);
break;
case FPDU_MODE: {
struct c4iw_qp_attributes attrs;
BUG_ON(!ep->com.qp);
if (status)
pr_err("%s Unexpected streaming data." \
" qpid %u ep %p state %d tid %u status %d\n",
__func__, ep->com.qp->wq.sq.qid, ep,
ep->com.state, ep->hwtid, status);
attrs.next_state = C4IW_QP_STATE_TERMINATE;
c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
disconnect = 1;
break;
}
default:
break;
}
mutex_unlock(&ep->com.mutex);
if (disconnect)
c4iw_ep_disconnect(ep, 0, GFP_KERNEL);
return 0;
}
static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *ep;
struct cpl_abort_rpl_rss *rpl = cplhdr(skb);
int release = 0;
unsigned int tid = GET_TID(rpl);
struct tid_info *t = dev->rdev.lldi.tids;
ep = lookup_tid(t, tid);
if (!ep) {
printk(KERN_WARNING MOD "Abort rpl to freed endpoint\n");
return 0;
}
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
mutex_lock(&ep->com.mutex);
switch (ep->com.state) {
case ABORTING:
c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
__state_set(&ep->com, DEAD);
release = 1;
break;
default:
printk(KERN_ERR "%s ep %p state %d\n",
__func__, ep, ep->com.state);
break;
}
mutex_unlock(&ep->com.mutex);
if (release)
release_ep_resources(ep);
return 0;
}
static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
{
struct sk_buff *skb;
struct fw_ofld_connection_wr *req;
unsigned int mtu_idx;
int wscale;
struct sockaddr_in *sin;
int win;
skb = get_skb(NULL, sizeof(*req), GFP_KERNEL);
req = (struct fw_ofld_connection_wr *)__skb_put(skb, sizeof(*req));
memset(req, 0, sizeof(*req));
req->op_compl = htonl(WR_OP_V(FW_OFLD_CONNECTION_WR));
req->len16_pkd = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*req), 16)));
req->le.filter = cpu_to_be32(cxgb4_select_ntuple(
ep->com.dev->rdev.lldi.ports[0],
ep->l2t));
sin = (struct sockaddr_in *)&ep->com.mapped_local_addr;
req->le.lport = sin->sin_port;
req->le.u.ipv4.lip = sin->sin_addr.s_addr;
sin = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
req->le.pport = sin->sin_port;
req->le.u.ipv4.pip = sin->sin_addr.s_addr;
req->tcb.t_state_to_astid =
htonl(FW_OFLD_CONNECTION_WR_T_STATE_V(TCP_SYN_SENT) |
FW_OFLD_CONNECTION_WR_ASTID_V(atid));
req->tcb.cplrxdataack_cplpassacceptrpl =
htons(FW_OFLD_CONNECTION_WR_CPLRXDATAACK_F);
req->tcb.tx_max = (__force __be32) jiffies;
req->tcb.rcv_adv = htons(1);
best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
enable_tcp_timestamps,
(AF_INET == ep->com.remote_addr.ss_family) ? 0 : 1);
wscale = compute_wscale(rcv_win);
/*
* Specify the largest window that will fit in opt0. The
* remainder will be specified in the rx_data_ack.
*/
win = ep->rcv_win >> 10;
if (win > RCV_BUFSIZ_M)
win = RCV_BUFSIZ_M;
req->tcb.opt0 = (__force __be64) (TCAM_BYPASS_F |
(nocong ? NO_CONG_F : 0) |
KEEP_ALIVE_F |
DELACK_F |
WND_SCALE_V(wscale) |
MSS_IDX_V(mtu_idx) |
L2T_IDX_V(ep->l2t->idx) |
TX_CHAN_V(ep->tx_chan) |
SMAC_SEL_V(ep->smac_idx) |
DSCP_V(ep->tos) |
ULP_MODE_V(ULP_MODE_TCPDDP) |
RCV_BUFSIZ_V(win));
req->tcb.opt2 = (__force __be32) (PACE_V(1) |
TX_QUEUE_V(ep->com.dev->rdev.lldi.tx_modq[ep->tx_chan]) |
RX_CHANNEL_V(0) |
CCTRL_ECN_V(enable_ecn) |
RSS_QUEUE_VALID_F | RSS_QUEUE_V(ep->rss_qid));
if (enable_tcp_timestamps)
req->tcb.opt2 |= (__force __be32)TSTAMPS_EN_F;
if (enable_tcp_sack)
req->tcb.opt2 |= (__force __be32)SACK_EN_F;
if (wscale && enable_tcp_window_scaling)
req->tcb.opt2 |= (__force __be32)WND_SCALE_EN_F;
req->tcb.opt0 = cpu_to_be64((__force u64)req->tcb.opt0);
req->tcb.opt2 = cpu_to_be32((__force u32)req->tcb.opt2);
set_wr_txq(skb, CPL_PRIORITY_CONTROL, ep->ctrlq_idx);
set_bit(ACT_OFLD_CONN, &ep->com.history);
c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
/*
* Return whether a failed active open has allocated a TID
*/
static inline int act_open_has_tid(int status)
{
return status != CPL_ERR_TCAM_FULL && status != CPL_ERR_CONN_EXIST &&
status != CPL_ERR_ARP_MISS;
}
/* Returns whether a CPL status conveys negative advice.
*/
static int is_neg_adv(unsigned int status)
{
return status == CPL_ERR_RTX_NEG_ADVICE ||
status == CPL_ERR_PERSIST_NEG_ADVICE ||
status == CPL_ERR_KEEPALV_NEG_ADVICE;
}
static char *neg_adv_str(unsigned int status)
{
switch (status) {
case CPL_ERR_RTX_NEG_ADVICE:
return "Retransmit timeout";
case CPL_ERR_PERSIST_NEG_ADVICE:
return "Persist timeout";
case CPL_ERR_KEEPALV_NEG_ADVICE:
return "Keepalive timeout";
default:
return "Unknown";
}
}
static void set_tcp_window(struct c4iw_ep *ep, struct port_info *pi)
{
ep->snd_win = snd_win;
ep->rcv_win = rcv_win;
PDBG("%s snd_win %d rcv_win %d\n", __func__, ep->snd_win, ep->rcv_win);
}
#define ACT_OPEN_RETRY_COUNT 2
static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
struct dst_entry *dst, struct c4iw_dev *cdev,
bool clear_mpa_v1)
{
struct neighbour *n;
int err, step;
struct net_device *pdev;
n = dst_neigh_lookup(dst, peer_ip);
if (!n)
return -ENODEV;
rcu_read_lock();
err = -ENOMEM;
if (n->dev->flags & IFF_LOOPBACK) {
if (iptype == 4)
pdev = ip_dev_find(&init_net, *(__be32 *)peer_ip);
else if (IS_ENABLED(CONFIG_IPV6))
for_each_netdev(&init_net, pdev) {
if (ipv6_chk_addr(&init_net,
(struct in6_addr *)peer_ip,
pdev, 1))
break;
}
else
pdev = NULL;
if (!pdev) {
err = -ENODEV;
goto out;
}
ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
n, pdev, 0);
if (!ep->l2t)
goto out;
ep->mtu = pdev->mtu;
ep->tx_chan = cxgb4_port_chan(pdev);
ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
step = cdev->rdev.lldi.ntxq /
cdev->rdev.lldi.nchan;
ep->txq_idx = cxgb4_port_idx(pdev) * step;
step = cdev->rdev.lldi.nrxq /
cdev->rdev.lldi.nchan;
ep->ctrlq_idx = cxgb4_port_idx(pdev);
ep->rss_qid = cdev->rdev.lldi.rxq_ids[
cxgb4_port_idx(pdev) * step];
set_tcp_window(ep, (struct port_info *)netdev_priv(pdev));
dev_put(pdev);
} else {
pdev = get_real_dev(n->dev);
ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
n, pdev, 0);
if (!ep->l2t)
goto out;
ep->mtu = dst_mtu(dst);
ep->tx_chan = cxgb4_port_chan(pdev);
ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
step = cdev->rdev.lldi.ntxq /
cdev->rdev.lldi.nchan;
ep->txq_idx = cxgb4_port_idx(pdev) * step;
ep->ctrlq_idx = cxgb4_port_idx(pdev);
step = cdev->rdev.lldi.nrxq /
cdev->rdev.lldi.nchan;
ep->rss_qid = cdev->rdev.lldi.rxq_ids[
cxgb4_port_idx(pdev) * step];
set_tcp_window(ep, (struct port_info *)netdev_priv(pdev));
if (clear_mpa_v1) {
ep->retry_with_mpa_v1 = 0;
ep->tried_with_mpa_v1 = 0;
}
}
err = 0;
out:
rcu_read_unlock();
neigh_release(n);
return err;
}
static int c4iw_reconnect(struct c4iw_ep *ep)
{
int err = 0;
struct sockaddr_in *laddr = (struct sockaddr_in *)
&ep->com.cm_id->local_addr;
struct sockaddr_in *raddr = (struct sockaddr_in *)
&ep->com.cm_id->remote_addr;
struct sockaddr_in6 *laddr6 = (struct sockaddr_in6 *)
&ep->com.cm_id->local_addr;
struct sockaddr_in6 *raddr6 = (struct sockaddr_in6 *)
&ep->com.cm_id->remote_addr;
int iptype;
__u8 *ra;
PDBG("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id);
init_timer(&ep->timer);
/*
* Allocate an active TID to initiate a TCP connection.
*/
ep->atid = cxgb4_alloc_atid(ep->com.dev->rdev.lldi.tids, ep);
if (ep->atid == -1) {
pr_err("%s - cannot alloc atid.\n", __func__);
err = -ENOMEM;
goto fail2;
}
insert_handle(ep->com.dev, &ep->com.dev->atid_idr, ep, ep->atid);
/* find a route */
if (ep->com.cm_id->local_addr.ss_family == AF_INET) {
ep->dst = find_route(ep->com.dev, laddr->sin_addr.s_addr,
raddr->sin_addr.s_addr, laddr->sin_port,
raddr->sin_port, 0);
iptype = 4;
ra = (__u8 *)&raddr->sin_addr;
} else {
ep->dst = find_route6(ep->com.dev, laddr6->sin6_addr.s6_addr,
raddr6->sin6_addr.s6_addr,
laddr6->sin6_port, raddr6->sin6_port, 0,
raddr6->sin6_scope_id);
iptype = 6;
ra = (__u8 *)&raddr6->sin6_addr;
}
if (!ep->dst) {
pr_err("%s - cannot find route.\n", __func__);
err = -EHOSTUNREACH;
goto fail3;
}
err = import_ep(ep, iptype, ra, ep->dst, ep->com.dev, false);
if (err) {
pr_err("%s - cannot alloc l2e.\n", __func__);
goto fail4;
}
PDBG("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n",
__func__, ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid,
ep->l2t->idx);
state_set(&ep->com, CONNECTING);
ep->tos = 0;
/* send connect request to rnic */
err = send_connect(ep);
if (!err)
goto out;
cxgb4_l2t_release(ep->l2t);
fail4:
dst_release(ep->dst);
fail3:
remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
fail2:
/*
* remember to send notification to upper layer.
* We are in here so the upper layer is not aware that this is
* re-connect attempt and so, upper layer is still waiting for
* response of 1st connect request.
*/
connect_reply_upcall(ep, -ECONNRESET);
c4iw_put_ep(&ep->com);
out:
return err;
}
static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *ep;
struct cpl_act_open_rpl *rpl = cplhdr(skb);
unsigned int atid = TID_TID_G(AOPEN_ATID_G(
ntohl(rpl->atid_status)));
struct tid_info *t = dev->rdev.lldi.tids;
int status = AOPEN_STATUS_G(ntohl(rpl->atid_status));
struct sockaddr_in *la;
struct sockaddr_in *ra;
struct sockaddr_in6 *la6;
struct sockaddr_in6 *ra6;
ep = lookup_atid(t, atid);
la = (struct sockaddr_in *)&ep->com.mapped_local_addr;
ra = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
la6 = (struct sockaddr_in6 *)&ep->com.mapped_local_addr;
ra6 = (struct sockaddr_in6 *)&ep->com.mapped_remote_addr;
PDBG("%s ep %p atid %u status %u errno %d\n", __func__, ep, atid,
status, status2errno(status));
if (is_neg_adv(status)) {
dev_warn(&dev->rdev.lldi.pdev->dev,
"Connection problems for atid %u status %u (%s)\n",
atid, status, neg_adv_str(status));
return 0;
}
set_bit(ACT_OPEN_RPL, &ep->com.history);
/*
* Log interesting failures.
*/
switch (status) {
case CPL_ERR_CONN_RESET:
case CPL_ERR_CONN_TIMEDOUT:
break;
case CPL_ERR_TCAM_FULL:
mutex_lock(&dev->rdev.stats.lock);
dev->rdev.stats.tcam_full++;
mutex_unlock(&dev->rdev.stats.lock);
if (ep->com.local_addr.ss_family == AF_INET &&
dev->rdev.lldi.enable_fw_ofld_conn) {
send_fw_act_open_req(ep,
TID_TID_G(AOPEN_ATID_G(
ntohl(rpl->atid_status))));
return 0;
}
break;
case CPL_ERR_CONN_EXIST:
if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
set_bit(ACT_RETRY_INUSE, &ep->com.history);
remove_handle(ep->com.dev, &ep->com.dev->atid_idr,
atid);
cxgb4_free_atid(t, atid);
dst_release(ep->dst);
cxgb4_l2t_release(ep->l2t);
c4iw_reconnect(ep);
return 0;
}
break;
default:
if (ep->com.local_addr.ss_family == AF_INET) {
pr_info("Active open failure - atid %u status %u errno %d %pI4:%u->%pI4:%u\n",
atid, status, status2errno(status),
&la->sin_addr.s_addr, ntohs(la->sin_port),
&ra->sin_addr.s_addr, ntohs(ra->sin_port));
} else {
pr_info("Active open failure - atid %u status %u errno %d %pI6:%u->%pI6:%u\n",
atid, status, status2errno(status),
la6->sin6_addr.s6_addr, ntohs(la6->sin6_port),
ra6->sin6_addr.s6_addr, ntohs(ra6->sin6_port));
}
break;
}
connect_reply_upcall(ep, status2errno(status));
state_set(&ep->com, DEAD);
if (status && act_open_has_tid(status))
cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, GET_TID(rpl));
remove_handle(ep->com.dev, &ep->com.dev->atid_idr, atid);
cxgb4_free_atid(t, atid);
dst_release(ep->dst);
cxgb4_l2t_release(ep->l2t);
c4iw_put_ep(&ep->com);
return 0;
}
static int pass_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct cpl_pass_open_rpl *rpl = cplhdr(skb);
struct tid_info *t = dev->rdev.lldi.tids;
unsigned int stid = GET_TID(rpl);
struct c4iw_listen_ep *ep = lookup_stid(t, stid);
if (!ep) {
PDBG("%s stid %d lookup failure!\n", __func__, stid);
goto out;
}
PDBG("%s ep %p status %d error %d\n", __func__, ep,
rpl->status, status2errno(rpl->status));
c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
out:
return 0;
}
static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct cpl_close_listsvr_rpl *rpl = cplhdr(skb);
struct tid_info *t = dev->rdev.lldi.tids;
unsigned int stid = GET_TID(rpl);
struct c4iw_listen_ep *ep = lookup_stid(t, stid);
PDBG("%s ep %p\n", __func__, ep);
c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
return 0;
}
static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
struct cpl_pass_accept_req *req)
{
struct cpl_pass_accept_rpl *rpl;
unsigned int mtu_idx;
u64 opt0;
u32 opt2;
int wscale;
struct cpl_t5_pass_accept_rpl *rpl5 = NULL;
int win;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
BUG_ON(skb_cloned(skb));
skb_get(skb);
rpl = cplhdr(skb);
if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
skb_trim(skb, roundup(sizeof(*rpl5), 16));
rpl5 = (void *)rpl;
INIT_TP_WR(rpl5, ep->hwtid);
} else {
skb_trim(skb, sizeof(*rpl));
INIT_TP_WR(rpl, ep->hwtid);
}
OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
ep->hwtid));
best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
enable_tcp_timestamps && req->tcpopt.tstamp,
(AF_INET == ep->com.remote_addr.ss_family) ? 0 : 1);
wscale = compute_wscale(rcv_win);
/*
* Specify the largest window that will fit in opt0. The
* remainder will be specified in the rx_data_ack.
*/
win = ep->rcv_win >> 10;
if (win > RCV_BUFSIZ_M)
win = RCV_BUFSIZ_M;
opt0 = (nocong ? NO_CONG_F : 0) |
KEEP_ALIVE_F |
DELACK_F |
WND_SCALE_V(wscale) |
MSS_IDX_V(mtu_idx) |
L2T_IDX_V(ep->l2t->idx) |
TX_CHAN_V(ep->tx_chan) |
SMAC_SEL_V(ep->smac_idx) |
DSCP_V(ep->tos >> 2) |
ULP_MODE_V(ULP_MODE_TCPDDP) |
RCV_BUFSIZ_V(win);
opt2 = RX_CHANNEL_V(0) |
RSS_QUEUE_VALID_F | RSS_QUEUE_V(ep->rss_qid);
if (enable_tcp_timestamps && req->tcpopt.tstamp)
opt2 |= TSTAMPS_EN_F;
if (enable_tcp_sack && req->tcpopt.sack)
opt2 |= SACK_EN_F;
if (wscale && enable_tcp_window_scaling)
opt2 |= WND_SCALE_EN_F;
if (enable_ecn) {
const struct tcphdr *tcph;
u32 hlen = ntohl(req->hdr_len);
tcph = (const void *)(req + 1) + ETH_HDR_LEN_G(hlen) +
IP_HDR_LEN_G(hlen);
if (tcph->ece && tcph->cwr)
opt2 |= CCTRL_ECN_V(1);
}
if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
u32 isn = (prandom_u32() & ~7UL) - 1;
opt2 |= T5_OPT_2_VALID_F;
opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
rpl5 = (void *)rpl;
memset(&rpl5->iss, 0, roundup(sizeof(*rpl5)-sizeof(*rpl), 16));
if (peer2peer)
isn += 4;
rpl5->iss = cpu_to_be32(isn);
PDBG("%s iss %u\n", __func__, be32_to_cpu(rpl5->iss));
}
rpl->opt0 = cpu_to_be64(opt0);
rpl->opt2 = cpu_to_be32(opt2);
set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx);
t4_set_arp_err_handler(skb, NULL, arp_failure_discard);
c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
return;
}
static void reject_cr(struct c4iw_dev *dev, u32 hwtid, struct sk_buff *skb)
{
PDBG("%s c4iw_dev %p tid %u\n", __func__, dev, hwtid);
BUG_ON(skb_cloned(skb));
skb_trim(skb, sizeof(struct cpl_tid_release));
release_tid(&dev->rdev, hwtid, skb);
return;
}
static void get_4tuple(struct cpl_pass_accept_req *req, int *iptype,
__u8 *local_ip, __u8 *peer_ip,
__be16 *local_port, __be16 *peer_port)
{
int eth_len = ETH_HDR_LEN_G(be32_to_cpu(req->hdr_len));
int ip_len = IP_HDR_LEN_G(be32_to_cpu(req->hdr_len));
struct iphdr *ip = (struct iphdr *)((u8 *)(req + 1) + eth_len);
struct ipv6hdr *ip6 = (struct ipv6hdr *)((u8 *)(req + 1) + eth_len);
struct tcphdr *tcp = (struct tcphdr *)
((u8 *)(req + 1) + eth_len + ip_len);
if (ip->version == 4) {
PDBG("%s saddr 0x%x daddr 0x%x sport %u dport %u\n", __func__,
ntohl(ip->saddr), ntohl(ip->daddr), ntohs(tcp->source),
ntohs(tcp->dest));
*iptype = 4;
memcpy(peer_ip, &ip->saddr, 4);
memcpy(local_ip, &ip->daddr, 4);
} else {
PDBG("%s saddr %pI6 daddr %pI6 sport %u dport %u\n", __func__,
ip6->saddr.s6_addr, ip6->daddr.s6_addr, ntohs(tcp->source),
ntohs(tcp->dest));
*iptype = 6;
memcpy(peer_ip, ip6->saddr.s6_addr, 16);
memcpy(local_ip, ip6->daddr.s6_addr, 16);
}
*peer_port = tcp->source;
*local_port = tcp->dest;
return;
}
static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *child_ep = NULL, *parent_ep;
struct cpl_pass_accept_req *req = cplhdr(skb);
unsigned int stid = PASS_OPEN_TID_G(ntohl(req->tos_stid));
struct tid_info *t = dev->rdev.lldi.tids;
unsigned int hwtid = GET_TID(req);
struct dst_entry *dst;
__u8 local_ip[16], peer_ip[16];
__be16 local_port, peer_port;
int err;
u16 peer_mss = ntohs(req->tcpopt.mss);
int iptype;
unsigned short hdrs;
parent_ep = lookup_stid(t, stid);
if (!parent_ep) {
PDBG("%s connect request on invalid stid %d\n", __func__, stid);
goto reject;
}
if (state_read(&parent_ep->com) != LISTEN) {
printk(KERN_ERR "%s - listening ep not in LISTEN\n",
__func__);
goto reject;
}
get_4tuple(req, &iptype, local_ip, peer_ip, &local_port, &peer_port);
/* Find output route */
if (iptype == 4) {
PDBG("%s parent ep %p hwtid %u laddr %pI4 raddr %pI4 lport %d rport %d peer_mss %d\n"
, __func__, parent_ep, hwtid,
local_ip, peer_ip, ntohs(local_port),
ntohs(peer_port), peer_mss);
dst = find_route(dev, *(__be32 *)local_ip, *(__be32 *)peer_ip,
local_port, peer_port,
PASS_OPEN_TOS_G(ntohl(req->tos_stid)));
} else {
PDBG("%s parent ep %p hwtid %u laddr %pI6 raddr %pI6 lport %d rport %d peer_mss %d\n"
, __func__, parent_ep, hwtid,
local_ip, peer_ip, ntohs(local_port),
ntohs(peer_port), peer_mss);
dst = find_route6(dev, local_ip, peer_ip, local_port, peer_port,
PASS_OPEN_TOS_G(ntohl(req->tos_stid)),
((struct sockaddr_in6 *)
&parent_ep->com.local_addr)->sin6_scope_id);
}
if (!dst) {
printk(KERN_ERR MOD "%s - failed to find dst entry!\n",
__func__);
goto reject;
}
child_ep = alloc_ep(sizeof(*child_ep), GFP_KERNEL);
if (!child_ep) {
printk(KERN_ERR MOD "%s - failed to allocate ep entry!\n",
__func__);
dst_release(dst);
goto reject;
}
err = import_ep(child_ep, iptype, peer_ip, dst, dev, false);
if (err) {
printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
__func__);
dst_release(dst);
kfree(child_ep);
goto reject;
}
hdrs = sizeof(struct iphdr) + sizeof(struct tcphdr) +
((enable_tcp_timestamps && req->tcpopt.tstamp) ? 12 : 0);
if (peer_mss && child_ep->mtu > (peer_mss + hdrs))
child_ep->mtu = peer_mss + hdrs;
state_set(&child_ep->com, CONNECTING);
child_ep->com.dev = dev;
child_ep->com.cm_id = NULL;
if (iptype == 4) {
struct sockaddr_in *sin = (struct sockaddr_in *)
&child_ep->com.local_addr;
sin->sin_family = PF_INET;
sin->sin_port = local_port;
sin->sin_addr.s_addr = *(__be32 *)local_ip;
sin = (struct sockaddr_in *)&child_ep->com.remote_addr;
sin->sin_family = PF_INET;
sin->sin_port = peer_port;
sin->sin_addr.s_addr = *(__be32 *)peer_ip;
} else {
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
&child_ep->com.local_addr;
sin6->sin6_family = PF_INET6;
sin6->sin6_port = local_port;
memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
sin6 = (struct sockaddr_in6 *)&child_ep->com.remote_addr;
sin6->sin6_family = PF_INET6;
sin6->sin6_port = peer_port;
memcpy(sin6->sin6_addr.s6_addr, peer_ip, 16);
}
c4iw_get_ep(&parent_ep->com);
child_ep->parent_ep = parent_ep;
child_ep->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid));
child_ep->dst = dst;
child_ep->hwtid = hwtid;
PDBG("%s tx_chan %u smac_idx %u rss_qid %u\n", __func__,
child_ep->tx_chan, child_ep->smac_idx, child_ep->rss_qid);
init_timer(&child_ep->timer);
cxgb4_insert_tid(t, child_ep, hwtid);
insert_handle(dev, &dev->hwtid_idr, child_ep, child_ep->hwtid);
accept_cr(child_ep, skb, req);
set_bit(PASS_ACCEPT_REQ, &child_ep->com.history);
goto out;
reject:
reject_cr(dev, hwtid, skb);
out:
return 0;
}
static int pass_establish(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *ep;
struct cpl_pass_establish *req = cplhdr(skb);
struct tid_info *t = dev->rdev.lldi.tids;
unsigned int tid = GET_TID(req);
ep = lookup_tid(t, tid);
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
ep->snd_seq = be32_to_cpu(req->snd_isn);
ep->rcv_seq = be32_to_cpu(req->rcv_isn);
PDBG("%s ep %p hwtid %u tcp_opt 0x%02x\n", __func__, ep, tid,
ntohs(req->tcp_opt));
set_emss(ep, ntohs(req->tcp_opt));
dst_confirm(ep->dst);
state_set(&ep->com, MPA_REQ_WAIT);
start_ep_timer(ep);
send_flowc(ep, skb);
set_bit(PASS_ESTAB, &ep->com.history);
return 0;
}
static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct cpl_peer_close *hdr = cplhdr(skb);
struct c4iw_ep *ep;
struct c4iw_qp_attributes attrs;
int disconnect = 1;
int release = 0;
struct tid_info *t = dev->rdev.lldi.tids;
unsigned int tid = GET_TID(hdr);
int ret;
ep = lookup_tid(t, tid);
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
dst_confirm(ep->dst);
set_bit(PEER_CLOSE, &ep->com.history);
mutex_lock(&ep->com.mutex);
switch (ep->com.state) {
case MPA_REQ_WAIT:
__state_set(&ep->com, CLOSING);
break;
case MPA_REQ_SENT:
__state_set(&ep->com, CLOSING);
connect_reply_upcall(ep, -ECONNRESET);
break;
case MPA_REQ_RCVD:
/*
* We're gonna mark this puppy DEAD, but keep
* the reference on it until the ULP accepts or
* rejects the CR. Also wake up anyone waiting
* in rdma connection migration (see c4iw_accept_cr()).
*/
__state_set(&ep->com, CLOSING);
PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
break;
case MPA_REP_SENT:
__state_set(&ep->com, CLOSING);
PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
break;
case FPDU_MODE:
start_ep_timer(ep);
__state_set(&ep->com, CLOSING);
attrs.next_state = C4IW_QP_STATE_CLOSING;
ret = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
if (ret != -ECONNRESET) {
peer_close_upcall(ep);
disconnect = 1;
}
break;
case ABORTING:
disconnect = 0;
break;
case CLOSING:
__state_set(&ep->com, MORIBUND);
disconnect = 0;
break;
case MORIBUND:
(void)stop_ep_timer(ep);
if (ep->com.cm_id && ep->com.qp) {
attrs.next_state = C4IW_QP_STATE_IDLE;
c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
}
close_complete_upcall(ep, 0);
__state_set(&ep->com, DEAD);
release = 1;
disconnect = 0;
break;
case DEAD:
disconnect = 0;
break;
default:
BUG_ON(1);
}
mutex_unlock(&ep->com.mutex);
if (disconnect)
c4iw_ep_disconnect(ep, 0, GFP_KERNEL);
if (release)
release_ep_resources(ep);
return 0;
}