* [PATCH v5 1/3] libcxgbi: common library for cxgb3i and cxgb4i
From: kxie @ 2010-08-17 3:55 UTC (permalink / raw)
To: netdev, linux-scsi, open-iscsi
Cc: rranjan, kxie, joe, James.Bottomley, michaelc, davem
[PATCH v5 1/3] libcxgbi: common library for cxgb3i and cxgb4i
From: Karen Xie <kxie@chelsio.com>
Extracts common functions to libcxgbi.
Signed-off-by: Karen Xie <kxie@chelsio.com>
---
drivers/scsi/cxgbi/libcxgbi.c | 2610 +++++++++++++++++++++++++++++++++++++++++
drivers/scsi/cxgbi/libcxgbi.h | 753 ++++++++++++
2 files changed, 3363 insertions(+), 0 deletions(-)
create mode 100644 drivers/scsi/cxgbi/libcxgbi.c
create mode 100644 drivers/scsi/cxgbi/libcxgbi.h
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
new file mode 100644
index 0000000..db9d08a
--- /dev/null
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -0,0 +1,2610 @@
+/*
+ * libcxgbi.c: Chelsio common library for T3/T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie@chelsio.com)
+ * Written by: Rakesh Ranjan (rranjan@chelsio.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
+
+#include <linux/skbuff.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+#include <linux/pci.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+#include <linux/if_vlan.h>
+#include <linux/inet.h>
+#include <net/dst.h>
+#include <net/route.h>
+#include <linux/inetdevice.h> /* ip_dev_find */
+#include <net/tcp.h>
+
+static unsigned int dbg_level;
+
+#include "libcxgbi.h"
+
+#define DRV_MODULE_NAME "libcxgbi"
+#define DRV_MODULE_DESC "Chelsio iSCSI driver library"
+#define DRV_MODULE_VERSION "0.9.0"
+#define DRV_MODULE_RELDATE "Jun. 2010"
+
+MODULE_AUTHOR("Chelsio Communications, Inc.");
+MODULE_DESCRIPTION(DRV_MODULE_DESC);
+MODULE_VERSION(DRV_MODULE_VERSION);
+MODULE_LICENSE("GPL");
+
+module_param(dbg_level, uint, 0644);
+MODULE_PARM_DESC(dbg_level, "libiscsi debug level (default=0)");
+
+
+/*
+ * cxgbi device management
+ * maintains a list of the cxgbi devices
+ */
+static LIST_HEAD(cdev_list);
+static DEFINE_MUTEX(cdev_mutex);
+
+int cxgbi_device_portmap_create(struct cxgbi_device *cdev, unsigned int base,
+ unsigned int max_conn)
+{
+ struct cxgbi_ports_map *pmap = &cdev->pmap;
+
+ pmap->port_csk = cxgbi_alloc_big_mem(max_conn *
+ sizeof(struct cxgbi_sock *),
+ GFP_KERNEL);
+ if (!pmap->port_csk) {
+ pr_warn("cdev 0x%p, portmap OOM %u.\n", cdev, max_conn);
+ return -ENOMEM;
+ }
+
+ pmap->max_connect = max_conn;
+ pmap->sport_base = base;
+ spin_lock_init(&pmap->lock);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_portmap_create);
+
+void cxgbi_device_portmap_cleanup(struct cxgbi_device *cdev)
+{
+ struct cxgbi_ports_map *pmap = &cdev->pmap;
+ struct cxgbi_sock *csk;
+ int i;
+
+ for (i = 0; i < pmap->max_connect; i++) {
+ if (pmap->port_csk[i]) {
+ csk = pmap->port_csk[i];
+ pmap->port_csk[i] = NULL;
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "csk 0x%p, cdev 0x%p, offload down.\n",
+ csk, cdev);
+ spin_lock_bh(&csk->lock);
+ cxgbi_sock_set_flag(csk, CTPF_OFFLOAD_DOWN);
+ cxgbi_sock_closed(csk);
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_portmap_cleanup);
+
+static inline void cxgbi_device_destroy(struct cxgbi_device *cdev)
+{
+ log_debug(1 << CXGBI_DBG_DEV,
+ "cdev 0x%p, p# %u.\n", cdev, cdev->nports);
+ cxgbi_hbas_remove(cdev);
+ cxgbi_device_portmap_cleanup(cdev);
+ if (cdev->dev_ddp_cleanup)
+ cdev->dev_ddp_cleanup(cdev);
+ else
+ cxgbi_ddp_cleanup(cdev);
+ if (cdev->ddp)
+ cxgbi_ddp_cleanup(cdev);
+ if (cdev->pmap.max_connect)
+ cxgbi_free_big_mem(cdev->pmap.port_csk);
+ kfree(cdev);
+}
+
+struct cxgbi_device *cxgbi_device_register(unsigned int extra,
+ unsigned int nports)
+{
+ struct cxgbi_device *cdev;
+
+ cdev = kzalloc(sizeof(*cdev) + extra + nports *
+ (sizeof(struct cxgbi_hba *) +
+ sizeof(struct net_device *)),
+ GFP_KERNEL);
+ if (!cdev) {
+ pr_warn("nport %d, OOM.\n", nports);
+ return NULL;
+ }
+ cdev->ports = (struct net_device **)(cdev + 1);
+ cdev->hbas = (struct cxgbi_hba **)(((char*)cdev->ports) + nports *
+ sizeof(struct net_device *));
+ if (extra)
+ cdev->dd_data = ((char *)cdev->hbas) +
+ nports * sizeof(struct cxgbi_hba *);
+ spin_lock_init(&cdev->pmap.lock);
+
+ mutex_lock(&cdev_mutex);
+ list_add_tail(&cdev->list_head, &cdev_list);
+ mutex_unlock(&cdev_mutex);
+
+ log_debug(1 << CXGBI_DBG_DEV,
+ "cdev 0x%p, p# %u.\n", cdev, nports);
+ return cdev;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_register);
+
+void cxgbi_device_unregister(struct cxgbi_device *cdev)
+{
+ log_debug(1 << CXGBI_DBG_DEV,
+ "cdev 0x%p, p# %u,%s.\n",
+ cdev, cdev->nports, cdev->nports ? cdev->ports[0]->name : "");
+ mutex_lock(&cdev_mutex);
+ list_del(&cdev->list_head);
+ mutex_unlock(&cdev_mutex);
+ cxgbi_device_destroy(cdev);
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_unregister);
+
+void cxgbi_device_unregister_all(unsigned int flag)
+{
+ struct cxgbi_device *cdev, *tmp;
+
+ mutex_lock(&cdev_mutex);
+ list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+ if ((cdev->flags & flag) == flag) {
+ log_debug(1 << CXGBI_DBG_DEV,
+ "cdev 0x%p, p# %u,%s.\n",
+ cdev, cdev->nports, cdev->nports ?
+ cdev->ports[0]->name : "");
+ list_del(&cdev->list_head);
+ cxgbi_device_destroy(cdev);
+ }
+ }
+ mutex_unlock(&cdev_mutex);
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_unregister_all);
+
+struct cxgbi_device *cxgbi_device_find_by_lldev(void *lldev)
+{
+ struct cxgbi_device *cdev, *tmp;
+
+ mutex_lock(&cdev_mutex);
+ list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+ if (cdev->lldev == lldev) {
+ mutex_unlock(&cdev_mutex);
+ return cdev;
+ }
+ }
+ mutex_unlock(&cdev_mutex);
+ log_debug(1 << CXGBI_DBG_DEV,
+ "lldev 0x%p, NO match found.\n", lldev);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_find_by_lldev);
+
+static struct cxgbi_device *cxgbi_device_find_by_netdev(struct net_device *ndev,
+ int *port)
+{
+ struct cxgbi_device *cdev, *tmp;
+ int i;
+
+ if (ndev->priv_flags & IFF_802_1Q_VLAN)
+ ndev = vlan_dev_real_dev(ndev);
+
+ mutex_lock(&cdev_mutex);
+ list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+ for (i = 0; i < cdev->nports; i++) {
+ if (ndev == cdev->ports[i]) {
+ mutex_unlock(&cdev_mutex);
+ if (port)
+ *port = i;
+ return cdev;
+ }
+ }
+ }
+ mutex_unlock(&cdev_mutex);
+ log_debug(1 << CXGBI_DBG_DEV,
+ "ndev 0x%p, %s, NO match found.\n", ndev, ndev->name);
+ return NULL;
+}
+
+struct cxgbi_hba *cxgbi_hba_find_by_netdev(struct net_device *dev,
+ struct cxgbi_device *cdev)
+{
+ int i;
+
+ if (dev->priv_flags & IFF_802_1Q_VLAN)
+ dev = vlan_dev_real_dev(dev);
+
+ for (i = 0; i < cdev->nports; i++) {
+ if (cdev->hbas[i]->ndev == dev)
+ return cdev->hbas[i];
+ }
+ log_debug(1 << CXGBI_DBG_DEV,
+ "ndev 0x%p, %s, cdev 0x%p, NO match found.\n",
+ dev, dev->name, cdev);
+ return NULL;
+}
+
+void cxgbi_hbas_remove(struct cxgbi_device *cdev)
+{
+ int i;
+ struct cxgbi_hba *chba;
+
+ log_debug(1 << CXGBI_DBG_DEV,
+ "cdev 0x%p, p#%u.\n", cdev, cdev->nports);
+
+ for (i = 0; i < cdev->nports; i++) {
+ chba = cdev->hbas[i];
+ if (chba) {
+ cdev->hbas[i] = NULL;
+ iscsi_host_remove(chba->shost);
+ pci_dev_put(cdev->pdev);
+ iscsi_host_free(chba->shost);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_hbas_remove);
+
+int cxgbi_hbas_add(struct cxgbi_device *cdev, unsigned int max_lun,
+ unsigned int max_id, struct scsi_host_template *sht,
+ struct scsi_transport_template *stt)
+{
+ struct cxgbi_hba *chba;
+ struct Scsi_Host *shost;
+ int i, err;
+
+ log_debug(1 << CXGBI_DBG_DEV, "cdev 0x%p, p#%u.\n", cdev, cdev->nports);
+
+ for (i = 0; i < cdev->nports; i++) {
+ shost = iscsi_host_alloc(sht, sizeof(*chba), 1);
+ if (!shost) {
+ pr_info("0x%p, p%d, %s, host alloc failed.\n",
+ cdev, i, cdev->ports[i]->name);
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ shost->transportt = stt;
+ shost->max_lun = max_lun;
+ shost->max_id = max_id;
+ shost->max_channel = 0;
+ shost->max_cmd_len = 16;
+
+ chba = iscsi_host_priv(shost);
+ chba->cdev = cdev;
+ chba->ndev = cdev->ports[i];
+ chba->shost = shost;
+
+ log_debug(1 << CXGBI_DBG_DEV,
+ "cdev 0x%p, p#%d %s: chba 0x%p.\n",
+ cdev, i, cdev->ports[i]->name, chba);
+
+ pci_dev_get(cdev->pdev);
+ err = iscsi_host_add(shost, &cdev->pdev->dev);
+ if (err) {
+ pr_info("cdev 0x%p, p#%d %s, host add failed.\n",
+ cdev, i, cdev->ports[i]->name);
+ pci_dev_put(cdev->pdev);
+ scsi_host_put(shost);
+ goto err_out;
+ }
+
+ cdev->hbas[i] = chba;
+ }
+
+ return 0;
+
+err_out:
+ cxgbi_hbas_remove(cdev);
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_hbas_add);
+
+/*
+ * iSCSI offload
+ *
+ * - source port management
+ * To find a free source port in the port allocation map we use a very simple
+ * rotor scheme to look for the next free port.
+ *
+ * If a source port has been specified make sure that it doesn't collide with
+ * our normal source port allocation map. If it's outside the range of our
+ * allocation/deallocation scheme just let them use it.
+ *
+ * If the source port is outside our allocation range, the caller is
+ * responsible for keeping track of their port usage.
+ */
+static int sock_get_port(struct cxgbi_sock *csk)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ struct cxgbi_ports_map *pmap = &cdev->pmap;
+ unsigned int start;
+ int idx;
+
+ if (!pmap->max_connect) {
+ pr_err("cdev 0x%p, p#%u %s, NO port map.\n",
+ cdev, csk->port_id, cdev->ports[csk->port_id]->name);
+ return -EADDRNOTAVAIL;
+ }
+
+ if (csk->saddr.sin_port) {
+ pr_err("source port NON-ZERO %u.\n",
+ ntohs(csk->saddr.sin_port));
+ return -EADDRINUSE;
+ }
+
+ spin_lock_bh(&pmap->lock);
+ if (pmap->used >= pmap->max_connect) {
+ spin_unlock_bh(&pmap->lock);
+ pr_info("cdev 0x%p, p#%u %s, ALL ports used.\n",
+ cdev, csk->port_id, cdev->ports[csk->port_id]->name);
+ return -EADDRNOTAVAIL;
+ }
+
+ start = idx = pmap->next;
+ do {
+ if (++idx >= pmap->max_connect)
+ idx = 0;
+ if (!pmap->port_csk[idx]) {
+ pmap->used++;
+ csk->saddr.sin_port =
+ htons(pmap->sport_base + idx);
+ pmap->next = idx;
+ pmap->port_csk[idx] = csk;
+ spin_unlock_bh(&pmap->lock);
+ cxgbi_sock_get(csk);
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "cdev 0x%p, p#%u %s, p %u, %u.\n",
+ cdev, csk->port_id,
+ cdev->ports[csk->port_id]->name,
+ pmap->sport_base + idx, pmap->next);
+ return 0;
+ }
+ } while (idx != start);
+ spin_unlock_bh(&pmap->lock);
+
+ /* should not happen */
+ pr_warn("cdev 0x%p, p#%u %s, next %u?\n",
+ cdev, csk->port_id, cdev->ports[csk->port_id]->name,
+ pmap->next);
+ return -EADDRNOTAVAIL;
+}
+
+static void sock_put_port(struct cxgbi_sock *csk)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ struct cxgbi_ports_map *pmap = &cdev->pmap;
+
+ if (csk->saddr.sin_port) {
+ int idx = ntohs(csk->saddr.sin_port) - pmap->sport_base;
+
+ csk->saddr.sin_port = 0;
+ if (idx < 0 || idx >= pmap->max_connect) {
+ pr_err("cdev 0x%p, p#%u %s, port %u OOR.\n",
+ cdev, csk->port_id,
+ cdev->ports[csk->port_id]->name,
+ ntohs(csk->saddr.sin_port));
+ return;
+ }
+
+ spin_lock_bh(&pmap->lock);
+ pmap->port_csk[idx] = NULL;
+ pmap->used--;
+ spin_unlock_bh(&pmap->lock);
+
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "cdev 0x%p, p#%u %s, release %u.\n",
+ cdev, csk->port_id, cdev->ports[csk->port_id]->name,
+ pmap->sport_base + idx);
+
+ cxgbi_sock_put(csk);
+ }
+}
+
+/*
+ * iscsi tcp connection
+ */
+void cxgbi_sock_free_cpl_skbs(struct cxgbi_sock *csk)
+{
+ if (csk->cpl_close) {
+ kfree_skb(csk->cpl_close);
+ csk->cpl_close = NULL;
+ }
+ if (csk->cpl_abort_req) {
+ kfree_skb(csk->cpl_abort_req);
+ csk->cpl_abort_req = NULL;
+ }
+ if (csk->cpl_abort_rpl) {
+ kfree_skb(csk->cpl_abort_rpl);
+ csk->cpl_abort_rpl = NULL;
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_free_cpl_skbs);
+
+static struct cxgbi_sock *cxgbi_sock_create(struct cxgbi_device *cdev)
+{
+ struct cxgbi_sock *csk = kzalloc(sizeof(*csk), GFP_NOIO);
+
+ if (!csk) {
+ pr_info("alloc csk %zu failed.\n", sizeof(*csk));
+ return NULL;
+ }
+
+ if (cdev->csk_alloc_cpls(csk) < 0) {
+ pr_info("csk 0x%p, alloc cpls failed.\n", csk);
+ kfree(csk);
+ return NULL;
+ }
+
+ spin_lock_init(&csk->lock);
+ kref_init(&csk->refcnt);
+ skb_queue_head_init(&csk->receive_queue);
+ skb_queue_head_init(&csk->write_queue);
+ setup_timer(&csk->retry_timer, NULL, (unsigned long)csk);
+ rwlock_init(&csk->callback_lock);
+ csk->cdev = cdev;
+ csk->flags = 0;
+ cxgbi_sock_set_state(csk, CTP_CLOSED);
+
+ log_debug(1 << CXGBI_DBG_SOCK, "cdev 0x%p, new csk 0x%p.\n", cdev, csk);
+
+ return csk;
+}
+
+static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport, u8 tos)
+{
+ struct rtable *rt;
+ struct flowi fl = {
+ .oif = 0,
+ .nl_u = {
+ .ip4_u = {
+ .daddr = daddr,
+ .saddr = saddr,
+ .tos = tos }
+ },
+ .proto = IPPROTO_TCP,
+ .uli_u = {
+ .ports = {
+ .sport = sport,
+ .dport = dport }
+ }
+ };
+
+ if (ip_route_output_flow(&init_net, &rt, &fl, NULL, 0))
+ return NULL;
+
+ return rt;
+}
+
+static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
+{
+ struct sockaddr_in *daddr = (struct sockaddr_in *)dst_addr;
+ struct dst_entry *dst;
+ struct net_device *ndev;
+ struct cxgbi_device *cdev;
+ struct rtable *rt = NULL;
+ struct cxgbi_sock *csk = NULL;
+ unsigned int mtu = 0;
+ int port = 0xFFFF;
+ int err = 0;
+
+ if (daddr->sin_family != AF_INET) {
+ pr_info("address family 0x%x NOT supported.\n",
+ daddr->sin_family);
+ err = -EAFNOSUPPORT;
+ goto err_out;
+ }
+
+ rt = find_route_ipv4(0, daddr->sin_addr.s_addr, 0, daddr->sin_port, 0);
+ if (!rt) {
+ pr_info("no route to ipv4 0x%x, port %u.\n",
+ daddr->sin_addr.s_addr, daddr->sin_port);
+ err = -ENETUNREACH;
+ goto err_out;
+ }
+ dst = &rt->dst;
+ ndev = dst->neighbour->dev;
+
+ if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
+ pr_info("multi-cast route %pI4, port %u, dev %s.\n",
+ &daddr->sin_addr.s_addr, ntohs(daddr->sin_port),
+ ndev->name);
+ err = -ENETUNREACH;
+ goto rel_rt;
+ }
+
+ if (ndev->flags & IFF_LOOPBACK) {
+ ndev = ip_dev_find(&init_net, daddr->sin_addr.s_addr);
+ mtu = ndev->mtu;
+ pr_info("rt dev %s, loopback -> %s, mtu %u.\n",
+ dst->neighbour->dev->name, ndev->name, mtu);
+ }
+
+ if (ndev->priv_flags & IFF_802_1Q_VLAN) {
+ ndev = vlan_dev_real_dev(ndev);
+ pr_info("rt dev %s, vlan -> %s.\n",
+ dst->neighbour->dev->name, ndev->name);
+ }
+
+ cdev = cxgbi_device_find_by_netdev(ndev, &port);
+ if (!cdev) {
+ pr_info("dst %pI4, %s, NOT cxgbi device.\n",
+ &daddr->sin_addr.s_addr, ndev->name);
+ err = -ENETUNREACH;
+ goto rel_rt;
+ }
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "route to %pI4 :%u, ndev p#%d,%s, cdev 0x%p.\n",
+ &daddr->sin_addr.s_addr, ntohs(daddr->sin_port),
+ port, ndev->name, cdev);
+
+ csk = cxgbi_sock_create(cdev);
+ if (!csk) {
+ err = -ENOMEM;
+ goto rel_rt;
+ }
+ csk->cdev = cdev;
+ csk->port_id = port;
+ csk->mtu = mtu;
+ csk->dst = dst;
+ csk->daddr.sin_addr.s_addr = daddr->sin_addr.s_addr;
+ csk->daddr.sin_port = daddr->sin_port;
+ if (cdev->hbas[port]->ipv4addr)
+ csk->saddr.sin_addr.s_addr = cdev->hbas[port]->ipv4addr;
+ else
+ csk->saddr.sin_addr.s_addr = rt->rt_src;
+
+ return csk;
+
+rel_rt:
+ ip_rt_put(rt);
+ if (csk)
+ cxgbi_sock_closed(csk);
+err_out:
+ return ERR_PTR(err);
+}
+
+void cxgbi_sock_established(struct cxgbi_sock *csk, unsigned int snd_isn,
+ unsigned int opt)
+{
+ csk->write_seq = csk->snd_nxt = csk->snd_una = snd_isn;
+ dst_confirm(csk->dst);
+ smp_mb();
+ cxgbi_sock_set_state(csk, CTP_ESTABLISHED);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_established);
+
+static void cxgbi_inform_iscsi_conn_closing(struct cxgbi_sock *csk)
+{
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "csk 0x%p, state %u, flags 0x%lx, conn 0x%p.\n",
+ csk, csk->state, csk->flags, csk->user_data);
+
+ if (csk->state != CTP_ESTABLISHED) {
+ read_lock(&csk->callback_lock);
+ if (csk->user_data)
+ iscsi_conn_failure(csk->user_data,
+ ISCSI_ERR_CONN_FAILED);
+ read_unlock(&csk->callback_lock);
+ }
+}
+
+void cxgbi_sock_closed(struct cxgbi_sock *csk)
+{
+ log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+ csk, (csk)->state, (csk)->flags, (csk)->tid);
+ cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+ if (csk->state == CTP_ACTIVE_OPEN || csk->state == CTP_CLOSED)
+ return;
+ if (csk->saddr.sin_port)
+ sock_put_port(csk);
+ if (csk->dst)
+ dst_release(csk->dst);
+ csk->cdev->csk_release_offload_resources(csk);
+ cxgbi_sock_set_state(csk, CTP_CLOSED);
+ cxgbi_inform_iscsi_conn_closing(csk);
+ cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_closed);
+
+static void need_active_close(struct cxgbi_sock *csk)
+{
+ int data_lost;
+ int close_req = 0;
+
+ log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+ csk, (csk)->state, (csk)->flags, (csk)->tid);
+ spin_lock_bh(&csk->lock);
+ dst_confirm(csk->dst);
+ data_lost = skb_queue_len(&csk->receive_queue);
+ __skb_queue_purge(&csk->receive_queue);
+
+ if (csk->state == CTP_ACTIVE_OPEN)
+ cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+ else if (csk->state == CTP_ESTABLISHED) {
+ close_req = 1;
+ cxgbi_sock_set_state(csk, CTP_ACTIVE_CLOSE);
+ } else if (csk->state == CTP_PASSIVE_CLOSE) {
+ close_req = 1;
+ cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_2);
+ }
+
+ if (close_req) {
+ if (data_lost)
+ csk->cdev->csk_send_abort_req(csk);
+ else
+ csk->cdev->csk_send_close_req(csk);
+ }
+
+ spin_unlock_bh(&csk->lock);
+}
+
+void cxgbi_sock_fail_act_open(struct cxgbi_sock *csk, int errno)
+{
+ pr_info("csk 0x%p,%u,%lx, %pI4:%u-%pI4:%u, err %d.\n",
+ csk, csk->state, csk->flags,
+ &csk->saddr.sin_addr.s_addr, csk->saddr.sin_port,
+ &csk->daddr.sin_addr.s_addr, csk->daddr.sin_port,
+ errno);
+
+ cxgbi_sock_set_state(csk, CTP_CONNECTING);
+ csk->err = errno;
+ cxgbi_sock_closed(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_fail_act_open);
+
+void cxgbi_sock_act_open_req_arp_failure(void *handle, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk = (struct cxgbi_sock *)skb->sk;
+
+ log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+ csk, (csk)->state, (csk)->flags, (csk)->tid);
+ cxgbi_sock_get(csk);
+ spin_lock_bh(&csk->lock);
+ if (csk->state == CTP_ACTIVE_OPEN)
+ cxgbi_sock_fail_act_open(csk, -EHOSTUNREACH);
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ __kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_act_open_req_arp_failure);
+
+void cxgbi_sock_rcv_abort_rpl(struct cxgbi_sock *csk)
+{
+ cxgbi_sock_get(csk);
+ spin_lock_bh(&csk->lock);
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) {
+ if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_RCVD))
+ cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_RCVD);
+ else {
+ cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_RCVD);
+ cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_PENDING);
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_REQ_RCVD))
+ pr_err("csk 0x%p,%u,0x%lx,%u,ABT_RPL_RSS.\n",
+ csk, csk->state, csk->flags, csk->tid);
+ cxgbi_sock_closed(csk);
+ }
+ }
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_abort_rpl);
+
+void cxgbi_sock_rcv_peer_close(struct cxgbi_sock *csk)
+{
+ log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+ csk, (csk)->state, (csk)->flags, (csk)->tid);
+ cxgbi_sock_get(csk);
+ spin_lock_bh(&csk->lock);
+
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING))
+ goto done;
+
+ switch (csk->state) {
+ case CTP_ESTABLISHED:
+ cxgbi_sock_set_state(csk, CTP_PASSIVE_CLOSE);
+ break;
+ case CTP_ACTIVE_CLOSE:
+ cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_2);
+ break;
+ case CTP_CLOSE_WAIT_1:
+ cxgbi_sock_closed(csk);
+ break;
+ case CTP_ABORTING:
+ break;
+ default:
+ pr_err("csk 0x%p,%u,0x%lx,%u, bad state.\n",
+ csk, csk->state, csk->flags, csk->tid);
+ }
+ cxgbi_inform_iscsi_conn_closing(csk);
+done:
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_peer_close);
+
+void cxgbi_sock_rcv_close_conn_rpl(struct cxgbi_sock *csk, u32 snd_nxt)
+{
+ log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+ csk, (csk)->state, (csk)->flags, (csk)->tid);
+ cxgbi_sock_get(csk);
+ spin_lock_bh(&csk->lock);
+
+ csk->snd_una = snd_nxt - 1;
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING))
+ goto done;
+
+ switch (csk->state) {
+ case CTP_ACTIVE_CLOSE:
+ cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_1);
+ break;
+ case CTP_CLOSE_WAIT_1:
+ case CTP_CLOSE_WAIT_2:
+ cxgbi_sock_closed(csk);
+ break;
+ case CTP_ABORTING:
+ break;
+ default:
+ pr_err("csk 0x%p,%u,0x%lx,%u, bad state.\n",
+ csk, csk->state, csk->flags, csk->tid);
+ }
+done:
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_close_conn_rpl);
+
+void cxgbi_sock_rcv_wr_ack(struct cxgbi_sock *csk, unsigned int credits,
+ unsigned int snd_una, int seq_chk)
+{
+ log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+ "csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, snd_una %u,%d.\n",
+ csk, csk->state, csk->flags, csk->tid, credits,
+ csk->wr_cred, csk->wr_una_cred, snd_una, seq_chk);
+
+ spin_lock_bh(&csk->lock);
+
+ csk->wr_cred += credits;
+ if (csk->wr_una_cred > csk->wr_max_cred - csk->wr_cred)
+ csk->wr_una_cred = csk->wr_max_cred - csk->wr_cred;
+
+ while (credits) {
+ struct sk_buff *p = cxgbi_sock_peek_wr(csk);
+
+ if (unlikely(!p)) {
+ pr_err("csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, empty.\n",
+ csk, csk->state, csk->flags, csk->tid, credits,
+ csk->wr_cred, csk->wr_una_cred);
+ break;
+ }
+
+ if (unlikely(credits < p->csum)) {
+ pr_warn("csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, < %u.\n",
+ csk, csk->state, csk->flags, csk->tid,
+ credits, csk->wr_cred, csk->wr_una_cred,
+ p->csum);
+ p->csum -= credits;
+ break;
+ } else {
+ cxgbi_sock_dequeue_wr(csk);
+ credits -= p->csum;
+ kfree_skb(p);
+ }
+ }
+
+ cxgbi_sock_check_wr_invariants(csk);
+
+ if (seq_chk) {
+ if (unlikely(before(snd_una, csk->snd_una))) {
+ pr_warn("csk 0x%p,%u,0x%lx,%u, snd_una %u/%u.",
+ csk, csk->state, csk->flags, csk->tid, snd_una,
+ csk->snd_una);
+ goto done;
+ }
+
+ if (csk->snd_una != snd_una) {
+ csk->snd_una = snd_una;
+ dst_confirm(csk->dst);
+ }
+ }
+
+ if (skb_queue_len(&csk->write_queue)) {
+ if (csk->cdev->csk_push_tx_frames(csk, 0))
+ cxgbi_conn_tx_open(csk);
+ } else
+ cxgbi_conn_tx_open(csk);
+done:
+ spin_unlock_bh(&csk->lock);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_wr_ack);
+
+static unsigned int cxgbi_sock_find_best_mtu(struct cxgbi_sock *csk,
+ unsigned short mtu)
+{
+ int i = 0;
+
+ while (i < csk->cdev->nmtus - 1 && csk->cdev->mtus[i + 1] <= mtu)
+ ++i;
+
+ return i;
+}
+
+unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *csk, unsigned int pmtu)
+{
+ unsigned int idx;
+ struct dst_entry *dst = csk->dst;
+
+ csk->advmss = dst_metric(dst, RTAX_ADVMSS);
+
+ if (csk->advmss > pmtu - 40)
+ csk->advmss = pmtu - 40;
+ if (csk->advmss < csk->cdev->mtus[0] - 40)
+ csk->advmss = csk->cdev->mtus[0] - 40;
+ idx = cxgbi_sock_find_best_mtu(csk, csk->advmss + 40);
+
+ return idx;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_select_mss);
+
+void cxgbi_sock_skb_entail(struct cxgbi_sock *csk, struct sk_buff *skb)
+{
+ cxgbi_skcb_tcp_seq(skb) = csk->write_seq;
+ __skb_queue_tail(&csk->write_queue, skb);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_skb_entail);
+
+void cxgbi_sock_purge_wr_queue(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+
+ while ((skb = cxgbi_sock_dequeue_wr(csk)) != NULL)
+ kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_purge_wr_queue);
+
+void cxgbi_sock_check_wr_invariants(const struct cxgbi_sock *csk)
+{
+ int pending = cxgbi_sock_count_pending_wrs(csk);
+
+ if (unlikely(csk->wr_cred + pending != csk->wr_max_cred))
+ pr_err("csk 0x%p, tid %u, credit %u + %u != %u.\n",
+ csk, csk->tid, csk->wr_cred, pending, csk->wr_max_cred);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_check_wr_invariants);
+
+static int cxgbi_sock_send_pdus(struct cxgbi_sock *csk, struct sk_buff *skb)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ struct sk_buff *next;
+ int err, copied = 0;
+
+ spin_lock_bh(&csk->lock);
+
+ if (csk->state != CTP_ESTABLISHED) {
+ log_debug(1 << CXGBI_DBG_PDU_TX,
+ "csk 0x%p,%u,0x%lx,%u, EAGAIN.\n",
+ csk, csk->state, csk->flags, csk->tid);
+ err = -EAGAIN;
+ goto out_err;
+ }
+
+ if (csk->err) {
+ log_debug(1 << CXGBI_DBG_PDU_TX,
+ "csk 0x%p,%u,0x%lx,%u, EPIPE %d.\n",
+ csk, csk->state, csk->flags, csk->tid, csk->err);
+ err = -EPIPE;
+ goto out_err;
+ }
+
+ if (csk->write_seq - csk->snd_una >= cdev->snd_win) {
+ log_debug(1 << CXGBI_DBG_PDU_TX,
+ "csk 0x%p,%u,0x%lx,%u, FULL %u-%u >= %u.\n",
+ csk, csk->state, csk->flags, csk->tid, csk->write_seq,
+ csk->snd_una, cdev->snd_win);
+ err = -ENOBUFS;
+ goto out_err;
+ }
+
+ while (skb) {
+ int frags = skb_shinfo(skb)->nr_frags +
+ (skb->len != skb->data_len);
+
+ if (unlikely(skb_headroom(skb) < cdev->skb_tx_rsvd)) {
+ pr_err("csk 0x%p, skb head %u < %u.\n",
+ csk, skb_headroom(skb), cdev->skb_tx_rsvd);
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ if (frags >= SKB_WR_LIST_SIZE) {
+ pr_err("csk 0x%p, frags %d, %u,%u >%u.\n",
+ csk, skb_shinfo(skb)->nr_frags, skb->len,
+ skb->data_len, (uint)(SKB_WR_LIST_SIZE));
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ next = skb->next;
+ skb->next = NULL;
+ cxgbi_skcb_set_flag(skb, SKCBF_TX_NEED_HDR);
+ cxgbi_sock_skb_entail(csk, skb);
+ copied += skb->len;
+ csk->write_seq += skb->len +
+ cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb));
+ skb = next;
+ }
+done:
+ if (likely(skb_queue_len(&csk->write_queue)))
+ cdev->csk_push_tx_frames(csk, 1);
+ spin_unlock_bh(&csk->lock);
+ return copied;
+
+out_err:
+ if (copied == 0 && err == -EPIPE)
+ copied = csk->err ? csk->err : -EPIPE;
+ else
+ copied = err;
+ goto done;
+}
+
+/*
+ * Direct Data Placement -
+ * Directly place the iSCSI Data-In or Data-Out PDU's payload into pre-posted
+ * final destination host-memory buffers based on the Initiator Task Tag (ITT)
+ * in Data-In or Target Task Tag (TTT) in Data-Out PDUs.
+ * The host memory address is programmed into h/w in the format of pagepod
+ * entries.
+ * The location of the pagepod entry is encoded into ddp tag which is used as
+ * the base for ITT/TTT.
+ */
+
+static unsigned char ddp_page_order[DDP_PGIDX_MAX] = {0, 1, 2, 4};
+static unsigned char ddp_page_shift[DDP_PGIDX_MAX] = {12, 13, 14, 16};
+static unsigned char page_idx = DDP_PGIDX_MAX;
+
+static unsigned char sw_tag_idx_bits;
+static unsigned char sw_tag_age_bits;
+
+/*
+ * Direct-Data Placement page size adjustment
+ */
+static int ddp_adjust_page_table(void)
+{
+ int i;
+ unsigned int base_order, order;
+
+ if (PAGE_SIZE < (1UL << ddp_page_shift[0])) {
+ pr_info("PAGE_SIZE 0x%lx too small, min 0x%lx\n",
+ PAGE_SIZE, 1UL << ddp_page_shift[0]);
+ return -EINVAL;
+ }
+
+ base_order = get_order(1UL << ddp_page_shift[0]);
+ order = get_order(1UL << PAGE_SHIFT);
+
+ for (i = 0; i < DDP_PGIDX_MAX; i++) {
+ /* first is the kernel page size, then just doubling */
+ ddp_page_order[i] = order - base_order + i;
+ ddp_page_shift[i] = PAGE_SHIFT + i;
+ }
+ return 0;
+}
+
+static int ddp_find_page_index(unsigned long pgsz)
+{
+ int i;
+
+ for (i = 0; i < DDP_PGIDX_MAX; i++) {
+ if (pgsz == (1UL << ddp_page_shift[i]))
+ return i;
+ }
+ pr_info("ddp page size %lu not supported.\n", pgsz);
+ return DDP_PGIDX_MAX;
+}
+
+static void ddp_setup_host_page_size(void)
+{
+ if (page_idx == DDP_PGIDX_MAX) {
+ page_idx = ddp_find_page_index(PAGE_SIZE);
+
+ if (page_idx == DDP_PGIDX_MAX) {
+ pr_info("system PAGE %lu, update hw.\n", PAGE_SIZE);
+ if (ddp_adjust_page_table() < 0) {
+ pr_info("PAGE %lu, disable ddp.\n", PAGE_SIZE);
+ return;
+ }
+ page_idx = ddp_find_page_index(PAGE_SIZE);
+ }
+ pr_info("system PAGE %lu, ddp idx %u.\n", PAGE_SIZE, page_idx);
+ }
+}
+
+void cxgbi_ddp_page_size_factor(int *pgsz_factor)
+{
+ int i;
+
+ for (i = 0; i < DDP_PGIDX_MAX; i++)
+ pgsz_factor[i] = ddp_page_order[i];
+}
+EXPORT_SYMBOL_GPL(cxgbi_ddp_page_size_factor);
+
+/*
+ * DDP setup & teardown
+ */
+
+void cxgbi_ddp_ppod_set(struct cxgbi_pagepod *ppod,
+ struct cxgbi_pagepod_hdr *hdr,
+ struct cxgbi_gather_list *gl, unsigned int gidx)
+{
+ int i;
+
+ memcpy(ppod, hdr, sizeof(*hdr));
+ for (i = 0; i < (PPOD_PAGES_MAX + 1); i++, gidx++) {
+ ppod->addr[i] = gidx < gl->nelem ?
+ cpu_to_be64(gl->phys_addr[gidx]) : 0ULL;
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_set);
+
+void cxgbi_ddp_ppod_clear(struct cxgbi_pagepod *ppod)
+{
+ memset(ppod, 0, sizeof(*ppod));
+}
+EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_clear);
+
+static inline int ddp_find_unused_entries(struct cxgbi_ddp_info *ddp,
+ unsigned int start, unsigned int max,
+ unsigned int count,
+ struct cxgbi_gather_list *gl)
+{
+ unsigned int i, j, k;
+
+ /* not enough entries */
+ if ((max - start) < count) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "NOT enough entries %u+%u < %u.\n", start, count, max);
+ return -EBUSY;
+ }
+
+ max -= count;
+ spin_lock(&ddp->map_lock);
+ for (i = start; i < max;) {
+ for (j = 0, k = i; j < count; j++, k++) {
+ if (ddp->gl_map[k])
+ break;
+ }
+ if (j == count) {
+ for (j = 0, k = i; j < count; j++, k++)
+ ddp->gl_map[k] = gl;
+ spin_unlock(&ddp->map_lock);
+ return i;
+ }
+ i += j + 1;
+ }
+ spin_unlock(&ddp->map_lock);
+ log_debug(1 << CXGBI_DBG_DDP,
+ "NO suitable entries %u available.\n", count);
+ return -EBUSY;
+}
+
+static inline void ddp_unmark_entries(struct cxgbi_ddp_info *ddp,
+ int start, int count)
+{
+ spin_lock(&ddp->map_lock);
+ memset(&ddp->gl_map[start], 0,
+ count * sizeof(struct cxgbi_gather_list *));
+ spin_unlock(&ddp->map_lock);
+}
+
+static inline void ddp_gl_unmap(struct pci_dev *pdev,
+ struct cxgbi_gather_list *gl)
+{
+ int i;
+
+ for (i = 0; i < gl->nelem; i++)
+ dma_unmap_page(&pdev->dev, gl->phys_addr[i], PAGE_SIZE,
+ PCI_DMA_FROMDEVICE);
+}
+
+static inline int ddp_gl_map(struct pci_dev *pdev,
+ struct cxgbi_gather_list *gl)
+{
+ int i;
+
+ for (i = 0; i < gl->nelem; i++) {
+ gl->phys_addr[i] = dma_map_page(&pdev->dev, gl->pages[i], 0,
+ PAGE_SIZE,
+ PCI_DMA_FROMDEVICE);
+ if (unlikely(dma_mapping_error(&pdev->dev, gl->phys_addr[i]))) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "page %d 0x%p, 0x%p dma mapping err.\n",
+ i, gl->pages[i], pdev);
+ goto unmap;
+ }
+ }
+ return i;
+unmap:
+ if (i) {
+ unsigned int nelem = gl->nelem;
+
+ gl->nelem = i;
+ ddp_gl_unmap(pdev, gl);
+ gl->nelem = nelem;
+ }
+ return -EINVAL;
+}
+
+static void ddp_release_gl(struct cxgbi_gather_list *gl,
+ struct pci_dev *pdev)
+{
+ ddp_gl_unmap(pdev, gl);
+ kfree(gl);
+}
+
+static struct cxgbi_gather_list *ddp_make_gl(unsigned int xferlen,
+ struct scatterlist *sgl,
+ unsigned int sgcnt,
+ struct pci_dev *pdev,
+ gfp_t gfp)
+{
+ struct cxgbi_gather_list *gl;
+ struct scatterlist *sg = sgl;
+ struct page *sgpage = sg_page(sg);
+ unsigned int sglen = sg->length;
+ unsigned int sgoffset = sg->offset;
+ unsigned int npages = (xferlen + sgoffset + PAGE_SIZE - 1) >>
+ PAGE_SHIFT;
+ int i = 1, j = 0;
+
+ if (xferlen < DDP_THRESHOLD) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "xfer %u < threshold %u, no ddp.\n",
+ xferlen, DDP_THRESHOLD);
+ return NULL;
+ }
+
+ gl = kzalloc(sizeof(struct cxgbi_gather_list) +
+ npages * (sizeof(dma_addr_t) +
+ sizeof(struct page *)), gfp);
+ if (!gl) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "xfer %u, %u pages, OOM.\n", xferlen, npages);
+ return NULL;
+ }
+
+ log_debug(1 << CXGBI_DBG_DDP,
+ "xfer %u, sgl %u, gl max %u.\n", xferlen, sgcnt, npages);
+
+ gl->pages = (struct page **)&gl->phys_addr[npages];
+ gl->nelem = npages;
+ gl->length = xferlen;
+ gl->offset = sgoffset;
+ gl->pages[0] = sgpage;
+
+ for (i = 1, sg = sg_next(sgl), j = 0; i < sgcnt;
+ i++, sg = sg_next(sg)) {
+ struct page *page = sg_page(sg);
+
+ if (sgpage == page && sg->offset == sgoffset + sglen)
+ sglen += sg->length;
+ else {
+ /* make sure the sgl is fit for ddp:
+ * each has the same page size, and
+ * all of the middle pages are used completely
+ */
+ if ((j && sgoffset) || ((i != sgcnt - 1) &&
+ ((sglen + sgoffset) & ~PAGE_MASK))) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "page %d/%u, %u + %u.\n",
+ i, sgcnt, sgoffset, sglen);
+ goto error_out;
+ }
+
+ j++;
+ if (j == gl->nelem || sg->offset) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "page %d/%u, offset %u.\n",
+ j, gl->nelem, sg->offset);
+ goto error_out;
+ }
+ gl->pages[j] = page;
+ sglen = sg->length;
+ sgoffset = sg->offset;
+ sgpage = page;
+ }
+ }
+ gl->nelem = ++j;
+
+ if (ddp_gl_map(pdev, gl) < 0)
+ goto error_out;
+
+ return gl;
+
+error_out:
+ kfree(gl);
+ return NULL;
+}
+
+static void ddp_tag_release(struct cxgbi_hba *chba, u32 tag)
+{
+ struct cxgbi_device *cdev = chba->cdev;
+ struct cxgbi_ddp_info *ddp = cdev->ddp;
+ u32 idx;
+
+ idx = (tag >> PPOD_IDX_SHIFT) & ddp->idx_mask;
+ if (idx < ddp->nppods) {
+ struct cxgbi_gather_list *gl = ddp->gl_map[idx];
+ unsigned int npods;
+
+ if (!gl || !gl->nelem) {
+ pr_warn("tag 0x%x, idx %u, gl 0x%p, %u.\n",
+ tag, idx, gl, gl ? gl->nelem : 0);
+ return;
+ }
+ npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT;
+ log_debug(1 << CXGBI_DBG_DDP,
+ "tag 0x%x, release idx %u, npods %u.\n",
+ tag, idx, npods);
+ cdev->csk_ddp_clear(chba, tag, idx, npods);
+ ddp_unmark_entries(ddp, idx, npods);
+ ddp_release_gl(gl, ddp->pdev);
+ } else
+ pr_warn("tag 0x%x, idx %u > max %u.\n", tag, idx, ddp->nppods);
+}
+
+static int ddp_tag_reserve(struct cxgbi_sock *csk, unsigned int tid,
+ u32 sw_tag, u32 *tagp, struct cxgbi_gather_list *gl,
+ gfp_t gfp)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ struct cxgbi_ddp_info *ddp = cdev->ddp;
+ struct cxgbi_tag_format *tformat = &cdev->tag_format;
+ struct cxgbi_pagepod_hdr hdr;
+ unsigned int npods;
+ int idx = -1;
+ int err = -ENOMEM;
+ u32 tag;
+
+ npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT;
+ if (ddp->idx_last == ddp->nppods)
+ idx = ddp_find_unused_entries(ddp, 0, ddp->nppods,
+ npods, gl);
+ else {
+ idx = ddp_find_unused_entries(ddp, ddp->idx_last + 1,
+ ddp->nppods, npods,
+ gl);
+ if (idx < 0 && ddp->idx_last >= npods) {
+ idx = ddp_find_unused_entries(ddp, 0,
+ min(ddp->idx_last + npods, ddp->nppods),
+ npods, gl);
+ }
+ }
+ if (idx < 0) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "xferlen %u, gl %u, npods %u NO DDP.\n",
+ gl->length, gl->nelem, npods);
+ return idx;
+ }
+
+ if (cdev->csk_ddp_alloc_gl_skb) {
+ err = cdev->csk_ddp_alloc_gl_skb(ddp, idx, npods, gfp);
+ if (err < 0)
+ goto unmark_entries;
+ }
+
+ tag = cxgbi_ddp_tag_base(tformat, sw_tag);
+ tag |= idx << PPOD_IDX_SHIFT;
+
+ hdr.rsvd = 0;
+ hdr.vld_tid = htonl(PPOD_VALID_FLAG | PPOD_TID(tid));
+ hdr.pgsz_tag_clr = htonl(tag & ddp->rsvd_tag_mask);
+ hdr.max_offset = htonl(gl->length);
+ hdr.page_offset = htonl(gl->offset);
+
+ err = cdev->csk_ddp_set(csk, &hdr, idx, npods, gl);
+ if (err < 0) {
+ if (cdev->csk_ddp_free_gl_skb)
+ cdev->csk_ddp_free_gl_skb(ddp, idx, npods);
+ goto unmark_entries;
+ }
+
+ ddp->idx_last = idx;
+ log_debug(1 << CXGBI_DBG_DDP,
+ "xfer %u, gl %u,%u, tid 0x%x, tag 0x%x->0x%x(%u,%u).\n",
+ gl->length, gl->nelem, gl->offset, tid, sw_tag, tag, idx,
+ npods);
+ *tagp = tag;
+ return 0;
+
+unmark_entries:
+ ddp_unmark_entries(ddp, idx, npods);
+ return err;
+}
+
+int cxgbi_ddp_reserve(struct cxgbi_sock *csk, unsigned int *tagp,
+ unsigned int sw_tag, unsigned int xferlen,
+ struct scatterlist *sgl, unsigned int sgcnt, gfp_t gfp)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ struct cxgbi_tag_format *tformat = &cdev->tag_format;
+ struct cxgbi_gather_list *gl;
+ int err;
+
+ if (page_idx >= DDP_PGIDX_MAX || !cdev->ddp ||
+ xferlen < DDP_THRESHOLD) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "pgidx %u, xfer %u, NO ddp.\n", page_idx, xferlen);
+ return -EINVAL;
+ }
+
+ if (!cxgbi_sw_tag_usable(tformat, sw_tag)) {
+ log_debug(1 << CXGBI_DBG_DDP,
+ "sw_tag 0x%x NOT usable.\n", sw_tag);
+ return -EINVAL;
+ }
+
+ gl = ddp_make_gl(xferlen, sgl, sgcnt, cdev->pdev, gfp);
+ if (!gl)
+ return -ENOMEM;
+
+ err = ddp_tag_reserve(csk, csk->tid, sw_tag, tagp, gl, gfp);
+ if (err < 0)
+ ddp_release_gl(gl, cdev->pdev);
+
+ return err;
+}
+
+static void ddp_destroy(struct kref *kref)
+{
+ struct cxgbi_ddp_info *ddp = container_of(kref,
+ struct cxgbi_ddp_info,
+ refcnt);
+ struct cxgbi_device *cdev = ddp->cdev;
+ int i = 0;
+
+ pr_info("kref 0, destroy ddp 0x%p, cdev 0x%p.\n", ddp, cdev);
+
+ while (i < ddp->nppods) {
+ struct cxgbi_gather_list *gl = ddp->gl_map[i];
+
+ if (gl) {
+ int npods = (gl->nelem + PPOD_PAGES_MAX - 1)
+ >> PPOD_PAGES_SHIFT;
+ pr_info("cdev 0x%p, ddp %d + %d.\n", cdev, i, npods);
+ kfree(gl);
+ if (cdev->csk_ddp_free_gl_skb)
+ cdev->csk_ddp_free_gl_skb(ddp, i, npods);
+ i += npods;
+ } else
+ i++;
+ }
+ cxgbi_free_big_mem(ddp);
+}
+
+int cxgbi_ddp_cleanup(struct cxgbi_device *cdev)
+{
+ struct cxgbi_ddp_info *ddp = cdev->ddp;
+
+ log_debug(1 << CXGBI_DBG_DDP,
+ "cdev 0x%p, release ddp 0x%p.\n", cdev, ddp);
+ cdev->ddp = NULL;
+ if (ddp)
+ return kref_put(&ddp->refcnt, ddp_destroy);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_ddp_cleanup);
+
+int cxgbi_ddp_init(struct cxgbi_device *cdev,
+ unsigned int llimit, unsigned int ulimit,
+ unsigned int max_txsz, unsigned int max_rxsz)
+{
+ struct cxgbi_ddp_info *ddp;
+ unsigned int ppmax, bits;
+
+ ppmax = (ulimit - llimit + 1) >> PPOD_SIZE_SHIFT;
+ bits = __ilog2_u32(ppmax) + 1;
+ if (bits > PPOD_IDX_MAX_SIZE)
+ bits = PPOD_IDX_MAX_SIZE;
+ ppmax = (1 << (bits - 1)) - 1;
+
+ ddp = cxgbi_alloc_big_mem(sizeof(struct cxgbi_ddp_info) +
+ ppmax * (sizeof(struct cxgbi_gather_list *) +
+ sizeof(struct sk_buff *)),
+ GFP_KERNEL);
+ if (!ddp) {
+ pr_warn("cdev 0x%p, ddp ppmax %u OOM.\n", cdev, ppmax);
+ return -ENOMEM;
+ }
+ ddp->gl_map = (struct cxgbi_gather_list **)(ddp + 1);
+ ddp->gl_skb = (struct sk_buff **)(((char *)ddp->gl_map) +
+ ppmax * sizeof(struct cxgbi_gather_list *));
+ cdev->ddp = ddp;
+
+ spin_lock_init(&ddp->map_lock);
+ kref_init(&ddp->refcnt);
+
+ ddp->cdev = cdev;
+ ddp->pdev = cdev->pdev;
+ ddp->llimit = llimit;
+ ddp->ulimit = ulimit;
+ ddp->max_txsz = min_t(unsigned int, max_txsz, ULP2_MAX_PKT_SIZE);
+ ddp->max_rxsz = min_t(unsigned int, max_rxsz, ULP2_MAX_PKT_SIZE);
+ ddp->nppods = ppmax;
+ ddp->idx_last = ppmax;
+ ddp->idx_bits = bits;
+ ddp->idx_mask = (1 << bits) - 1;
+ ddp->rsvd_tag_mask = (1 << (bits + PPOD_IDX_SHIFT)) - 1;
+
+ cdev->tag_format.sw_bits = sw_tag_idx_bits + sw_tag_age_bits;
+ cdev->tag_format.rsvd_bits = ddp->idx_bits;
+ cdev->tag_format.rsvd_shift = PPOD_IDX_SHIFT;
+ cdev->tag_format.rsvd_mask = (1 << cdev->tag_format.rsvd_bits) - 1;
+
+ pr_info("%s tag format, sw %u, rsvd %u,%u, mask 0x%x.\n",
+ cdev->ports[0]->name, cdev->tag_format.sw_bits,
+ cdev->tag_format.rsvd_bits, cdev->tag_format.rsvd_shift,
+ cdev->tag_format.rsvd_mask);
+
+ cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+ ddp->max_txsz - ISCSI_PDU_NONPAYLOAD_LEN);
+ cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+ ddp->max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN);
+
+ log_debug(1 << CXGBI_DBG_DDP,
+ "%s max payload size: %u/%u, %u/%u.\n",
+ cdev->ports[0]->name, cdev->tx_max_size, ddp->max_txsz,
+ cdev->rx_max_size, ddp->max_rxsz);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_ddp_init);
+
+/*
+ * APIs interacting with open-iscsi libraries
+ */
+
+static unsigned char padding[4];
+
+static void task_release_itt(struct iscsi_task *task, itt_t hdr_itt)
+{
+ struct scsi_cmnd *sc = task->sc;
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_hba *chba = cconn->chba;
+ struct cxgbi_tag_format *tformat = &chba->cdev->tag_format;
+ u32 tag = ntohl((__force u32)hdr_itt);
+
+ log_debug(1 << CXGBI_DBG_DDP,
+ "cdev 0x%p, release tag 0x%x.\n", chba->cdev, tag);
+ if (sc &&
+ (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) &&
+ cxgbi_is_ddp_tag(tformat, tag))
+ ddp_tag_release(chba, tag);
+}
+
+static int task_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt)
+{
+ struct scsi_cmnd *sc = task->sc;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_session *sess = conn->session;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_hba *chba = cconn->chba;
+ struct cxgbi_tag_format *tformat = &chba->cdev->tag_format;
+ u32 sw_tag = (sess->age << cconn->task_idx_bits) | task->itt;
+ u32 tag = 0;
+ int err = -EINVAL;
+
+ if (sc &&
+ (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE)) {
+ err = cxgbi_ddp_reserve(cconn->cep->csk, &tag, sw_tag,
+ scsi_in(sc)->length,
+ scsi_in(sc)->table.sgl,
+ scsi_in(sc)->table.nents,
+ GFP_ATOMIC);
+ if (err < 0)
+ log_debug(1 << CXGBI_DBG_DDP,
+ "csk 0x%p, R task 0x%p, %u,%u, no ddp.\n",
+ cconn->cep->csk, task, scsi_in(sc)->length,
+ scsi_in(sc)->table.nents);
+ }
+
+ if (err < 0)
+ tag = cxgbi_set_non_ddp_tag(tformat, sw_tag);
+ /* the itt need to sent in big-endian order */
+ *hdr_itt = (__force itt_t)htonl(tag);
+
+ log_debug(1 << CXGBI_DBG_DDP,
+ "cdev 0x%p, task 0x%p, 0x%x(0x%x,0x%x)->0x%x/0x%x.\n",
+ chba->cdev, task, sw_tag, task->itt, sess->age, tag, *hdr_itt);
+ return 0;
+}
+
+void cxgbi_parse_pdu_itt(struct iscsi_conn *conn, itt_t itt, int *idx, int *age)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ u32 tag = ntohl((__force u32) itt);
+ u32 sw_bits;
+
+ sw_bits = cxgbi_tag_nonrsvd_bits(&cdev->tag_format, tag);
+ if (idx)
+ *idx = sw_bits & ((1 << cconn->task_idx_bits) - 1);
+ if (age)
+ *age = (sw_bits >> cconn->task_idx_bits) & ISCSI_AGE_MASK;
+
+ log_debug(1 << CXGBI_DBG_DDP,
+ "cdev 0x%p, tag 0x%x/0x%x, -> 0x%x(0x%x,0x%x).\n",
+ cdev, tag, itt, sw_bits, idx ? *idx : 0xFFFFF,
+ age ? *age : 0xFF);
+}
+EXPORT_SYMBOL_GPL(cxgbi_parse_pdu_itt);
+
+void cxgbi_conn_tx_open(struct cxgbi_sock *csk)
+{
+ struct iscsi_conn *conn = csk->user_data;
+
+ if (conn) {
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "csk 0x%p, cid %d.\n", csk, conn->id);
+ iscsi_conn_queue_work(conn);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_tx_open);
+
+/*
+ * pdu receive, interact with libiscsi_tcp
+ */
+static inline int read_pdu_skb(struct iscsi_conn *conn,
+ struct sk_buff *skb,
+ unsigned int offset,
+ int offloaded)
+{
+ int status = 0;
+ int bytes_read;
+
+ bytes_read = iscsi_tcp_recv_skb(conn, skb, offset, offloaded, &status);
+ switch (status) {
+ case ISCSI_TCP_CONN_ERR:
+ pr_info("skb 0x%p, off %u, %d, TCP_ERR.\n",
+ skb, offset, offloaded);
+ return -EIO;
+ case ISCSI_TCP_SUSPENDED:
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "skb 0x%p, off %u, %d, TCP_SUSPEND, rc %d.\n",
+ skb, offset, offloaded, bytes_read);
+ /* no transfer - just have caller flush queue */
+ return bytes_read;
+ case ISCSI_TCP_SKB_DONE:
+ pr_info("skb 0x%p, off %u, %d, TCP_SKB_DONE.\n",
+ skb, offset, offloaded);
+ /*
+ * pdus should always fit in the skb and we should get
+ * segment done notifcation.
+ */
+ iscsi_conn_printk(KERN_ERR, conn, "Invalid pdu or skb.");
+ return -EFAULT;
+ case ISCSI_TCP_SEGMENT_DONE:
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "skb 0x%p, off %u, %d, TCP_SEG_DONE, rc %d.\n",
+ skb, offset, offloaded, bytes_read);
+ return bytes_read;
+ default:
+ pr_info("skb 0x%p, off %u, %d, invalid status %d.\n",
+ skb, offset, offloaded, status);
+ return -EINVAL;
+ }
+}
+
+static int skb_read_pdu_bhs(struct iscsi_conn *conn, struct sk_buff *skb)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "conn 0x%p, skb 0x%p, len %u, flag 0x%lx.\n",
+ conn, skb, skb->len, cxgbi_skcb_flags(skb));
+
+ if (!iscsi_tcp_recv_segment_is_hdr(tcp_conn)) {
+ pr_info("conn 0x%p, skb 0x%p, not hdr.\n", conn, skb);
+ iscsi_conn_failure(conn, ISCSI_ERR_PROTO);
+ return -EIO;
+ }
+
+ if (conn->hdrdgst_en &&
+ cxgbi_skcb_test_flag(skb, SKCBF_RX_HCRC_ERR)) {
+ pr_info("conn 0x%p, skb 0x%p, hcrc.\n", conn, skb);
+ iscsi_conn_failure(conn, ISCSI_ERR_HDR_DGST);
+ return -EIO;
+ }
+
+ return read_pdu_skb(conn, skb, 0, 0);
+}
+
+static int skb_read_pdu_data(struct iscsi_conn *conn, struct sk_buff *lskb,
+ struct sk_buff *skb, unsigned int offset)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ bool offloaded = 0;
+ int opcode = tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK;
+
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "conn 0x%p, skb 0x%p, len %u, flag 0x%lx.\n",
+ conn, skb, skb->len, cxgbi_skcb_flags(skb));
+
+ if (conn->datadgst_en &&
+ cxgbi_skcb_test_flag(lskb, SKCBF_RX_DCRC_ERR)) {
+ pr_info("conn 0x%p, skb 0x%p, dcrc 0x%lx.\n",
+ conn, lskb, cxgbi_skcb_flags(lskb));
+ iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST);
+ return -EIO;
+ }
+
+ if (iscsi_tcp_recv_segment_is_hdr(tcp_conn))
+ return 0;
+
+ /* coalesced, add header digest length */
+ if (lskb == skb && conn->hdrdgst_en)
+ offset += ISCSI_DIGEST_SIZE;
+
+ if (cxgbi_skcb_test_flag(lskb, SKCBF_RX_DATA_DDPD))
+ offloaded = 1;
+
+ if (opcode == ISCSI_OP_SCSI_DATA_IN)
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "skb 0x%p, op 0x%x, itt 0x%x, %u %s ddp'ed.\n",
+ skb, opcode, ntohl(tcp_conn->in.hdr->itt),
+ tcp_conn->in.datalen, offloaded ? "is" : "not");
+
+ return read_pdu_skb(conn, skb, offset, offloaded);
+}
+
+static void csk_return_rx_credits(struct cxgbi_sock *csk, int copied)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ int must_send;
+ u32 credits;
+
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "csk 0x%p,%u,0x%lu,%u, seq %u, wup %u, thre %u, %u.\n",
+ csk, csk->state, csk->flags, csk->tid, csk->copied_seq,
+ csk->rcv_wup, cdev->rx_credit_thres,
+ cdev->rcv_win);
+
+ if (csk->state != CTP_ESTABLISHED)
+ return;
+
+ credits = csk->copied_seq - csk->rcv_wup;
+ if (unlikely(!credits))
+ return;
+ if (unlikely(cdev->rx_credit_thres == 0))
+ return;
+
+ must_send = credits + 16384 >= cdev->rcv_win;
+ if (must_send || credits >= cdev->rx_credit_thres)
+ csk->rcv_wup += cdev->csk_send_rx_credits(csk, credits);
+}
+
+void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ struct iscsi_conn *conn = csk->user_data;
+ struct sk_buff *skb;
+ unsigned int read = 0;
+ int err = 0;
+
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "csk 0x%p, conn 0x%p.\n", csk, conn);
+
+ if (unlikely(!conn || conn->suspend_rx)) {
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "csk 0x%p, conn 0x%p, id %d, suspend_rx %lu!\n",
+ csk, conn, conn ? conn->id : 0xFF,
+ conn ? conn->suspend_rx : 0xFF);
+ read_unlock(&csk->callback_lock);
+ return;
+ }
+
+ while (!err) {
+ read_lock(&csk->callback_lock);
+ skb = skb_peek(&csk->receive_queue);
+ if (!skb ||
+ !(cxgbi_skcb_test_flag(skb, SKCBF_RX_STATUS))) {
+ if (skb)
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "skb 0x%p, NOT ready 0x%lx.\n",
+ skb, cxgbi_skcb_flags(skb));
+ read_unlock(&csk->callback_lock);
+ break;
+ }
+ __skb_unlink(skb, &csk->receive_queue);
+ read_unlock(&csk->callback_lock);
+
+ read += cxgbi_skcb_rx_pdulen(skb);
+ log_debug(1 << CXGBI_DBG_PDU_RX,
+ "csk 0x%p, skb 0x%p,%u,f 0x%lx, pdu len %u.\n",
+ csk, skb, skb->len, cxgbi_skcb_flags(skb),
+ cxgbi_skcb_rx_pdulen(skb));
+
+ if (cxgbi_skcb_test_flag(skb, SKCBF_RX_COALESCED)) {
+ err = skb_read_pdu_bhs(conn, skb);
+ if (err < 0)
+ break;
+ err = skb_read_pdu_data(conn, skb, skb,
+ err + cdev->skb_rx_extra);
+ } else {
+ err = skb_read_pdu_bhs(conn, skb);
+ if (err < 0)
+ break;
+ if (cxgbi_skcb_test_flag(skb, SKCBF_RX_DATA)) {
+ struct sk_buff *dskb;
+
+ read_lock(&csk->callback_lock);
+ dskb = skb_peek(&csk->receive_queue);
+ if (!dskb) {
+ read_unlock(&csk->callback_lock);
+ pr_err("csk 0x%p, NO data.\n", csk);
+ err = -EAGAIN;
+ break;
+ }
+ __skb_unlink(dskb, &csk->receive_queue);
+ read_unlock(&csk->callback_lock);
+
+ err = skb_read_pdu_data(conn, skb, dskb, 0);
+ __kfree_skb(dskb);
+ } else
+ err = skb_read_pdu_data(conn, skb, skb, 0);
+ }
+ if (err < 0)
+ break;
+
+ __kfree_skb(skb);
+ }
+
+ log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, read %u.\n", csk, read);
+ if (read) {
+ csk->copied_seq += read;
+ csk_return_rx_credits(csk, read);
+ conn->rxdata_octets += read;
+ }
+
+ if (err < 0) {
+ pr_info("csk 0x%p, 0x%p, rx failed %d.\n", csk, conn, err);
+ iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_pdu_ready);
+
+static int sgl_seek_offset(struct scatterlist *sgl, unsigned int sgcnt,
+ unsigned int offset, unsigned int *off,
+ struct scatterlist **sgp)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, sgcnt, i) {
+ if (offset < sg->length) {
+ *off = offset;
+ *sgp = sg;
+ return 0;
+ }
+ offset -= sg->length;
+ }
+ return -EFAULT;
+}
+
+static int sgl_read_to_frags(struct scatterlist *sg, unsigned int sgoffset,
+ unsigned int dlen, skb_frag_t *frags,
+ int frag_max)
+{
+ unsigned int datalen = dlen;
+ unsigned int sglen = sg->length - sgoffset;
+ struct page *page = sg_page(sg);
+ int i;
+
+ i = 0;
+ do {
+ unsigned int copy;
+
+ if (!sglen) {
+ sg = sg_next(sg);
+ if (!sg) {
+ pr_warn("sg %d NULL, len %u/%u.\n",
+ i, datalen, dlen);
+ return -EINVAL;
+ }
+ sgoffset = 0;
+ sglen = sg->length;
+ page = sg_page(sg);
+
+ }
+ copy = min(datalen, sglen);
+ if (i && page == frags[i - 1].page &&
+ sgoffset + sg->offset ==
+ frags[i - 1].page_offset + frags[i - 1].size) {
+ frags[i - 1].size += copy;
+ } else {
+ if (i >= frag_max) {
+ pr_warn("too many pages %u, dlen %u.\n",
+ frag_max, dlen);
+ return -EINVAL;
+ }
+
+ frags[i].page = page;
+ frags[i].page_offset = sg->offset + sgoffset;
+ frags[i].size = copy;
+ i++;
+ }
+ datalen -= copy;
+ sgoffset += copy;
+ sglen -= copy;
+ } while (datalen);
+
+ return i;
+}
+
+int cxgbi_conn_alloc_pdu(struct iscsi_task *task, u8 opcode)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = task->dd_data + sizeof(*tcp_task);
+ struct scsi_cmnd *sc = task->sc;
+ int headroom = SKB_TX_ISCSI_PDU_HEADER_MAX;
+
+ tcp_task->dd_data = tdata;
+ task->hdr = NULL;
+
+ if (SKB_MAX_HEAD(cdev->skb_tx_rsvd) > (512 * MAX_SKB_FRAGS) &&
+ (opcode == ISCSI_OP_SCSI_DATA_OUT ||
+ (opcode == ISCSI_OP_SCSI_CMD &&
+ (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_TO_DEVICE))))
+ /* data could goes into skb head */
+ headroom += min_t(unsigned int,
+ SKB_MAX_HEAD(cdev->skb_tx_rsvd),
+ conn->max_xmit_dlength);
+
+ tdata->skb = alloc_skb(cdev->skb_tx_rsvd + headroom, GFP_ATOMIC);
+ if (!tdata->skb) {
+ pr_warn("alloc skb %u+%u, opcode 0x%x failed.\n",
+ cdev->skb_tx_rsvd, headroom, opcode);
+ return -ENOMEM;
+ }
+
+ skb_reserve(tdata->skb, cdev->skb_tx_rsvd);
+ task->hdr = (struct iscsi_hdr *)tdata->skb->data;
+ task->hdr_max = SKB_TX_ISCSI_PDU_HEADER_MAX; /* BHS + AHS */
+
+ /* data_out uses scsi_cmd's itt */
+ if (opcode != ISCSI_OP_SCSI_DATA_OUT)
+ task_reserve_itt(task, &task->hdr->itt);
+
+ log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
+ "task 0x%p, op 0x%x, skb 0x%p,%u+%u/%u, itt 0x%x.\n",
+ task, opcode, tdata->skb, cdev->skb_tx_rsvd, headroom,
+ conn->max_xmit_dlength, ntohl(task->hdr->itt));
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_alloc_pdu);
+
+static inline void tx_skb_setmode(struct sk_buff *skb, int hcrc, int dcrc)
+{
+ u8 submode = 0;
+
+ if (hcrc)
+ submode |= 1;
+ if (dcrc)
+ submode |= 2;
+ cxgbi_skcb_ulp_mode(skb) = (ULP2_MODE_ISCSI << 4) | submode;
+}
+
+int cxgbi_conn_init_pdu(struct iscsi_task *task, unsigned int offset,
+ unsigned int count)
+{
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = tcp_task->dd_data;
+ struct sk_buff *skb = tdata->skb;
+ unsigned int datalen = count;
+ int i, padlen = iscsi_padding(count);
+ struct page *pg;
+
+ log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
+ "task 0x%p,0x%p, skb 0x%p, 0x%x,0x%x,0x%x, %u+%u.\n",
+ task, task->sc, skb, (*skb->data) & ISCSI_OPCODE_MASK,
+ ntohl(task->cmdsn), ntohl(task->hdr->itt), offset, count);
+
+ skb_put(skb, task->hdr_len);
+ tx_skb_setmode(skb, conn->hdrdgst_en, datalen ? conn->datadgst_en : 0);
+ if (!count)
+ return 0;
+
+ if (task->sc) {
+ struct scsi_data_buffer *sdb = scsi_out(task->sc);
+ struct scatterlist *sg = NULL;
+ int err;
+
+ tdata->offset = offset;
+ tdata->count = count;
+ err = sgl_seek_offset(
+ sdb->table.sgl, sdb->table.nents,
+ tdata->offset, &tdata->sgoffset, &sg);
+ if (err < 0) {
+ pr_warn("tpdu, sgl %u, bad offset %u/%u.\n",
+ sdb->table.nents, tdata->offset, sdb->length);
+ return err;
+ }
+ err = sgl_read_to_frags(sg, tdata->sgoffset, tdata->count,
+ tdata->frags, MAX_PDU_FRAGS);
+ if (err < 0) {
+ pr_warn("tpdu, sgl %u, bad offset %u + %u.\n",
+ sdb->table.nents, tdata->offset, tdata->count);
+ return err;
+ }
+ tdata->nr_frags = err;
+
+ if (tdata->nr_frags > MAX_SKB_FRAGS ||
+ (padlen && tdata->nr_frags == MAX_SKB_FRAGS)) {
+ char *dst = skb->data + task->hdr_len;
+ skb_frag_t *frag = tdata->frags;
+
+ /* data fits in the skb's headroom */
+ for (i = 0; i < tdata->nr_frags; i++, frag++) {
+ char *src = kmap_atomic(frag->page,
+ KM_SOFTIRQ0);
+
+ memcpy(dst, src+frag->page_offset, frag->size);
+ dst += frag->size;
+ kunmap_atomic(src, KM_SOFTIRQ0);
+ }
+ if (padlen) {
+ memset(dst, 0, padlen);
+ padlen = 0;
+ }
+ skb_put(skb, count + padlen);
+ } else {
+ /* data fit into frag_list */
+ for (i = 0; i < tdata->nr_frags; i++)
+ get_page(tdata->frags[i].page);
+
+ memcpy(skb_shinfo(skb)->frags, tdata->frags,
+ sizeof(skb_frag_t) * tdata->nr_frags);
+ skb_shinfo(skb)->nr_frags = tdata->nr_frags;
+ skb->len += count;
+ skb->data_len += count;
+ skb->truesize += count;
+ }
+
+ } else {
+ pg = virt_to_page(task->data);
+
+ get_page(pg);
+ skb_fill_page_desc(skb, 0, pg, offset_in_page(task->data),
+ count);
+ skb->len += count;
+ skb->data_len += count;
+ skb->truesize += count;
+ }
+
+ if (padlen) {
+ i = skb_shinfo(skb)->nr_frags;
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
+ virt_to_page(padding), offset_in_page(padding),
+ padlen);
+
+ skb->data_len += padlen;
+ skb->truesize += padlen;
+ skb->len += padlen;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_init_pdu);
+
+int cxgbi_conn_xmit_pdu(struct iscsi_task *task)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = tcp_task->dd_data;
+ struct sk_buff *skb = tdata->skb;
+ unsigned int datalen;
+ int err;
+
+ if (!skb) {
+ log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
+ "task 0x%p, skb NULL.\n", task);
+ return 0;
+ }
+
+ datalen = skb->data_len;
+ tdata->skb = NULL;
+ err = cxgbi_sock_send_pdus(cconn->cep->csk, skb);
+ if (err > 0) {
+ int pdulen = err;
+
+ log_debug(1 << CXGBI_DBG_PDU_TX,
+ "task 0x%p,0x%p, skb 0x%p, len %u/%u, rv %d.\n",
+ task, task->sc, skb, skb->len, skb->data_len, err);
+
+ if (task->conn->hdrdgst_en)
+ pdulen += ISCSI_DIGEST_SIZE;
+
+ if (datalen && task->conn->datadgst_en)
+ pdulen += ISCSI_DIGEST_SIZE;
+
+ task->conn->txdata_octets += pdulen;
+ return 0;
+ }
+
+ if (err == -EAGAIN || err == -ENOBUFS) {
+ log_debug(1 << CXGBI_DBG_PDU_TX,
+ "task 0x%p, skb 0x%p, len %u/%u, %d EAGAIN.\n",
+ task, skb, skb->len, skb->data_len, err);
+ /* reset skb to send when we are called again */
+ tdata->skb = skb;
+ return err;
+ }
+
+ kfree_skb(skb);
+ log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
+ "itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
+ task->itt, skb, skb->len, skb->data_len, err);
+ iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
+ iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_xmit_pdu);
+
+void cxgbi_cleanup_task(struct iscsi_task *task)
+{
+ struct cxgbi_task_data *tdata = task->dd_data +
+ sizeof(struct iscsi_tcp_task);
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "task 0x%p, skb 0x%p, itt 0x%x.\n",
+ task, tdata->skb, task->hdr_itt);
+
+ /* never reached the xmit task callout */
+ if (tdata->skb)
+ __kfree_skb(tdata->skb);
+ memset(tdata, 0, sizeof(*tdata));
+
+ task_release_itt(task, task->hdr_itt);
+ iscsi_tcp_cleanup_task(task);
+}
+EXPORT_SYMBOL_GPL(cxgbi_cleanup_task);
+
+void cxgbi_get_conn_stats(struct iscsi_cls_conn *cls_conn,
+ struct iscsi_stats *stats)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+
+ stats->txdata_octets = conn->txdata_octets;
+ stats->rxdata_octets = conn->rxdata_octets;
+ stats->scsicmd_pdus = conn->scsicmd_pdus_cnt;
+ stats->dataout_pdus = conn->dataout_pdus_cnt;
+ stats->scsirsp_pdus = conn->scsirsp_pdus_cnt;
+ stats->datain_pdus = conn->datain_pdus_cnt;
+ stats->r2t_pdus = conn->r2t_pdus_cnt;
+ stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt;
+ stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt;
+ stats->digest_err = 0;
+ stats->timeout_err = 0;
+ stats->custom_length = 1;
+ strcpy(stats->custom[0].desc, "eh_abort_cnt");
+ stats->custom[0].value = conn->eh_abort_cnt;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_conn_stats);
+
+static int cxgbi_conn_max_xmit_dlength(struct iscsi_conn *conn)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ unsigned int headroom = SKB_MAX_HEAD(cdev->skb_tx_rsvd);
+ unsigned int max_def = 512 * MAX_SKB_FRAGS;
+ unsigned int max = max(max_def, headroom);
+
+ max = min(cconn->chba->cdev->tx_max_size, max);
+ if (conn->max_xmit_dlength)
+ conn->max_xmit_dlength = min(conn->max_xmit_dlength, max);
+ else
+ conn->max_xmit_dlength = max;
+ cxgbi_align_pdu_size(conn->max_xmit_dlength);
+
+ return 0;
+}
+
+static int cxgbi_conn_max_recv_dlength(struct iscsi_conn *conn)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ unsigned int max = cconn->chba->cdev->rx_max_size;
+
+ cxgbi_align_pdu_size(max);
+
+ if (conn->max_recv_dlength) {
+ if (conn->max_recv_dlength > max) {
+ pr_err("MaxRecvDataSegmentLength %u > %u.\n",
+ conn->max_recv_dlength, max);
+ return -EINVAL;
+ }
+ conn->max_recv_dlength = min(conn->max_recv_dlength, max);
+ cxgbi_align_pdu_size(conn->max_recv_dlength);
+ } else
+ conn->max_recv_dlength = max;
+
+ return 0;
+}
+
+int cxgbi_set_conn_param(struct iscsi_cls_conn *cls_conn,
+ enum iscsi_param param, char *buf, int buflen)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+ struct iscsi_session *session = conn->session;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_sock *csk = cconn->cep->csk;
+ int value, err = 0;
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "cls_conn 0x%p, param %d, buf(%d) %s.\n",
+ cls_conn, param, buflen, buf);
+
+ switch (param) {
+ case ISCSI_PARAM_HDRDGST_EN:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && conn->hdrdgst_en)
+ err = csk->cdev->csk_ddp_setup_digest(csk, csk->tid,
+ conn->hdrdgst_en,
+ conn->datadgst_en, 0);
+ break;
+ case ISCSI_PARAM_DATADGST_EN:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && conn->datadgst_en)
+ err = csk->cdev->csk_ddp_setup_digest(csk, csk->tid,
+ conn->hdrdgst_en,
+ conn->datadgst_en, 0);
+ break;
+ case ISCSI_PARAM_MAX_R2T:
+ sscanf(buf, "%d", &value);
+ if (value <= 0 || !is_power_of_2(value))
+ return -EINVAL;
+ if (session->max_r2t == value)
+ break;
+ iscsi_tcp_r2tpool_free(session);
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && iscsi_tcp_r2tpool_alloc(session))
+ return -ENOMEM;
+ case ISCSI_PARAM_MAX_RECV_DLENGTH:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err)
+ err = cxgbi_conn_max_recv_dlength(conn);
+ break;
+ case ISCSI_PARAM_MAX_XMIT_DLENGTH:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err)
+ err = cxgbi_conn_max_xmit_dlength(conn);
+ break;
+ default:
+ return iscsi_set_param(cls_conn, param, buf, buflen);
+ }
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_set_conn_param);
+
+int cxgbi_get_conn_param(struct iscsi_cls_conn *cls_conn,
+ enum iscsi_param param, char *buf)
+{
+ struct iscsi_conn *iconn = cls_conn->dd_data;
+ int len;
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "cls_conn 0x%p, param %d.\n", cls_conn, param);
+
+ switch (param) {
+ case ISCSI_PARAM_CONN_PORT:
+ spin_lock_bh(&iconn->session->lock);
+ len = sprintf(buf, "%hu\n", iconn->portal_port);
+ spin_unlock_bh(&iconn->session->lock);
+ break;
+ case ISCSI_PARAM_CONN_ADDRESS:
+ spin_lock_bh(&iconn->session->lock);
+ len = sprintf(buf, "%s\n", iconn->portal_address);
+ spin_unlock_bh(&iconn->session->lock);
+ break;
+ default:
+ return iscsi_conn_get_param(cls_conn, param, buf);
+ }
+ return len;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_conn_param);
+
+struct iscsi_cls_conn *
+cxgbi_create_conn(struct iscsi_cls_session *cls_session, u32 cid)
+{
+ struct iscsi_cls_conn *cls_conn;
+ struct iscsi_conn *conn;
+ struct iscsi_tcp_conn *tcp_conn;
+ struct cxgbi_conn *cconn;
+
+ cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*cconn), cid);
+ if (!cls_conn)
+ return NULL;
+
+ conn = cls_conn->dd_data;
+ tcp_conn = conn->dd_data;
+ cconn = tcp_conn->dd_data;
+ cconn->iconn = conn;
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "cid %u(0x%x), cls 0x%p,0x%p, conn 0x%p,0x%p,0x%p.\n",
+ cid, cid, cls_session, cls_conn, conn, tcp_conn, cconn);
+
+ return cls_conn;
+}
+EXPORT_SYMBOL_GPL(cxgbi_create_conn);
+
+int cxgbi_bind_conn(struct iscsi_cls_session *cls_session,
+ struct iscsi_cls_conn *cls_conn,
+ u64 transport_eph, int is_leading)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct iscsi_endpoint *ep;
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_sock *csk;
+ int err;
+
+ ep = iscsi_lookup_endpoint(transport_eph);
+ if (!ep)
+ return -EINVAL;
+
+ /* setup ddp pagesize */
+ cep = ep->dd_data;
+ csk = cep->csk;
+ err = csk->cdev->csk_ddp_setup_pgidx(csk, csk->tid, page_idx, 0);
+ if (err < 0)
+ return err;
+
+ err = iscsi_conn_bind(cls_session, cls_conn, is_leading);
+ if (err)
+ return -EINVAL;
+
+ /* calculate the tag idx bits needed for this conn based on cmds_max */
+ cconn->task_idx_bits = (__ilog2_u32(conn->session->cmds_max - 1)) + 1;
+
+ write_lock(&csk->callback_lock);
+ csk->user_data = conn;
+ cconn->chba = cep->chba;
+ cconn->cep = cep;
+ cep->cconn = cconn;
+ write_unlock(&csk->callback_lock);
+
+ cxgbi_conn_max_xmit_dlength(conn);
+ cxgbi_conn_max_recv_dlength(conn);
+
+ spin_lock_bh(&conn->session->lock);
+ sprintf(conn->portal_address, "%pI4", &csk->daddr.sin_addr.s_addr);
+ conn->portal_port = ntohs(csk->daddr.sin_port);
+ spin_unlock_bh(&conn->session->lock);
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "cls 0x%p,0x%p, ep 0x%p, cconn 0x%p, csk 0x%p.\n",
+ cls_session, cls_conn, ep, cconn, csk);
+ /* init recv engine */
+ iscsi_tcp_hdr_recv_prep(tcp_conn);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_bind_conn);
+
+struct iscsi_cls_session *cxgbi_create_session(struct iscsi_endpoint *ep,
+ u16 cmds_max, u16 qdepth,
+ u32 initial_cmdsn)
+{
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_hba *chba;
+ struct Scsi_Host *shost;
+ struct iscsi_cls_session *cls_session;
+ struct iscsi_session *session;
+
+ if (!ep) {
+ pr_err("missing endpoint.\n");
+ return NULL;
+ }
+
+ cep = ep->dd_data;
+ chba = cep->chba;
+ shost = chba->shost;
+
+ BUG_ON(chba != iscsi_host_priv(shost));
+
+ cls_session = iscsi_session_setup(chba->cdev->itp, shost,
+ cmds_max, 0,
+ sizeof(struct iscsi_tcp_task) +
+ sizeof(struct cxgbi_task_data),
+ initial_cmdsn, ISCSI_MAX_TARGET);
+ if (!cls_session)
+ return NULL;
+
+ session = cls_session->dd_data;
+ if (iscsi_tcp_r2tpool_alloc(session))
+ goto remove_session;
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "ep 0x%p, cls sess 0x%p.\n", ep, cls_session);
+ return cls_session;
+
+remove_session:
+ iscsi_session_teardown(cls_session);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_create_session);
+
+void cxgbi_destroy_session(struct iscsi_cls_session *cls_session)
+{
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "cls sess 0x%p.\n", cls_session);
+
+ iscsi_tcp_r2tpool_free(cls_session->dd_data);
+ iscsi_session_teardown(cls_session);
+}
+EXPORT_SYMBOL_GPL(cxgbi_destroy_session);
+
+int cxgbi_set_host_param(struct Scsi_Host *shost, enum iscsi_host_param param,
+ char *buf, int buflen)
+{
+ struct cxgbi_hba *chba = iscsi_host_priv(shost);
+
+ if (!chba->ndev) {
+ shost_printk(KERN_ERR, shost, "Could not get host param. "
+ "netdev for host not set.\n");
+ return -ENODEV;
+ }
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "shost 0x%p, hba 0x%p,%s, param %d, buf(%d) %s.\n",
+ shost, chba, chba->ndev->name, param, buflen, buf);
+
+ switch (param) {
+ case ISCSI_HOST_PARAM_IPADDRESS:
+ {
+ __be32 addr = in_aton(buf);
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "hba %s, req. ipv4 %pI4.\n", chba->ndev->name, &addr);
+ cxgbi_set_iscsi_ipv4(chba, addr);
+ return 0;
+ }
+ case ISCSI_HOST_PARAM_HWADDRESS:
+ case ISCSI_HOST_PARAM_NETDEV_NAME:
+ return 0;
+ default:
+ return iscsi_host_set_param(shost, param, buf, buflen);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_set_host_param);
+
+int cxgbi_get_host_param(struct Scsi_Host *shost, enum iscsi_host_param param,
+ char *buf)
+{
+ struct cxgbi_hba *chba = iscsi_host_priv(shost);
+ int len = 0;
+
+ if (!chba->ndev) {
+ shost_printk(KERN_ERR, shost, "Could not get host param. "
+ "netdev for host not set.\n");
+ return -ENODEV;
+ }
+
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "shost 0x%p, hba 0x%p,%s, param %d.\n",
+ shost, chba, chba->ndev->name, param);
+
+ switch (param) {
+ case ISCSI_HOST_PARAM_HWADDRESS:
+ len = sysfs_format_mac(buf, chba->ndev->dev_addr, 6);
+ break;
+ case ISCSI_HOST_PARAM_NETDEV_NAME:
+ len = sprintf(buf, "%s\n", chba->ndev->name);
+ break;
+ case ISCSI_HOST_PARAM_IPADDRESS:
+ {
+ __be32 addr;
+
+ addr = cxgbi_get_iscsi_ipv4(chba);
+ len = sprintf(buf, "%pI4", &addr);
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "hba %s, ipv4 %pI4.\n", chba->ndev->name, &addr);
+ break;
+ }
+ default:
+ return iscsi_host_get_param(shost, param, buf);
+ }
+
+ return len;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_host_param);
+
+struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *shost,
+ struct sockaddr *dst_addr,
+ int non_blocking)
+{
+ struct iscsi_endpoint *ep;
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_hba *hba = NULL;
+ struct cxgbi_sock *csk;
+ int err = -EINVAL;
+
+ log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_SOCK,
+ "shost 0x%p, non_blocking %d, dst_addr 0x%p.\n",
+ shost, non_blocking, dst_addr);
+
+ if (shost) {
+ hba = iscsi_host_priv(shost);
+ if (!hba) {
+ pr_info("shost 0x%p, priv NULL.\n", shost);
+ goto err_out;
+ }
+ }
+
+ csk = cxgbi_check_route(dst_addr);
+ if (IS_ERR(csk))
+ return (struct iscsi_endpoint *)csk;
+ cxgbi_sock_get(csk);
+
+ if (!hba)
+ hba = csk->cdev->hbas[csk->port_id];
+ else if (hba != csk->cdev->hbas[csk->port_id]) {
+ pr_info("Could not connect through requested host %u"
+ "hba 0x%p != 0x%p (%u).\n",
+ shost->host_no, hba,
+ csk->cdev->hbas[csk->port_id], csk->port_id);
+ err = -ENOSPC;
+ goto release_conn;
+ }
+
+ err = sock_get_port(csk);
+ if (err)
+ goto release_conn;
+
+ cxgbi_sock_set_state(csk, CTP_CONNECTING);
+ err = csk->cdev->csk_init_act_open(csk);
+ if (err)
+ goto release_conn;
+
+ if (cxgbi_sock_is_closing(csk)) {
+ err = -ENOSPC;
+ pr_info("csk 0x%p is closing.\n", csk);
+ goto release_conn;
+ }
+
+ ep = iscsi_create_endpoint(sizeof(*cep));
+ if (!ep) {
+ err = -ENOMEM;
+ pr_info("iscsi alloc ep, OOM.\n");
+ goto release_conn;
+ }
+
+ cep = ep->dd_data;
+ cep->csk = csk;
+ cep->chba = hba;
+
+ log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_SOCK,
+ "ep 0x%p, cep 0x%p, csk 0x%p, hba 0x%p,%s.\n",
+ ep, cep, csk, hba, hba->ndev->name);
+ return ep;
+
+release_conn:
+ cxgbi_sock_put(csk);
+ cxgbi_sock_closed(csk);
+err_out:
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_connect);
+
+int cxgbi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms)
+{
+ struct cxgbi_endpoint *cep = ep->dd_data;
+ struct cxgbi_sock *csk = cep->csk;
+
+ if (!cxgbi_sock_is_established(csk))
+ return 0;
+ return 1;
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_poll);
+
+void cxgbi_ep_disconnect(struct iscsi_endpoint *ep)
+{
+ struct cxgbi_endpoint *cep = ep->dd_data;
+ struct cxgbi_conn *cconn = cep->cconn;
+ struct cxgbi_sock *csk = cep->csk;
+
+ log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_SOCK,
+ "ep 0x%p, cep 0x%p, cconn 0x%p, csk 0x%p,%u,0x%lx.\n",
+ ep, cep, cconn, csk, csk->state, csk->flags);
+
+ if (cconn && cconn->iconn) {
+ iscsi_suspend_tx(cconn->iconn);
+ write_lock_bh(&csk->callback_lock);
+ cep->csk->user_data = NULL;
+ cconn->cep = NULL;
+ write_unlock_bh(&csk->callback_lock);
+ }
+ iscsi_destroy_endpoint(ep);
+
+ if (likely(csk->state >= CTP_ESTABLISHED))
+ need_active_close(csk);
+ else
+ cxgbi_sock_closed(csk);
+
+ cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_disconnect);
+
+int cxgbi_iscsi_init(struct iscsi_transport *itp,
+ struct scsi_transport_template **stt)
+{
+ *stt = iscsi_register_transport(itp);
+ if (*stt == NULL) {
+ pr_err("unable to register %s transport 0x%p.\n",
+ itp->name, itp);
+ return -ENODEV;
+ }
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "%s, registered iscsi transport 0x%p.\n",
+ itp->name, stt);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_iscsi_init);
+
+void cxgbi_iscsi_cleanup(struct iscsi_transport *itp,
+ struct scsi_transport_template **stt)
+{
+ if (*stt) {
+ log_debug(1 << CXGBI_DBG_ISCSI,
+ "de-register transport 0x%p, %s, stt 0x%p.\n",
+ itp, itp->name, *stt);
+ *stt = NULL;
+ iscsi_unregister_transport(itp);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_iscsi_cleanup);
+
+static int __init libcxgbi_init_module(void)
+{
+ sw_tag_idx_bits = (__ilog2_u32(ISCSI_ITT_MASK)) + 1;
+ sw_tag_age_bits = (__ilog2_u32(ISCSI_AGE_MASK)) + 1;
+
+ pr_info("tag itt 0x%x, %u bits, age 0x%x, %u bits.\n",
+ ISCSI_ITT_MASK, sw_tag_idx_bits,
+ ISCSI_AGE_MASK, sw_tag_age_bits);
+
+ ddp_setup_host_page_size();
+ return 0;
+}
+
+static void __exit libcxgbi_exit_module(void)
+{
+ cxgbi_device_unregister_all(0xFF);
+ return;
+}
+
+module_init(libcxgbi_init_module);
+module_exit(libcxgbi_exit_module);
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
new file mode 100644
index 0000000..40551f3
--- /dev/null
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -0,0 +1,753 @@
+/*
+ * libcxgbi.h: Chelsio common library for T3/T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie@chelsio.com)
+ * Written by: Rakesh Ranjan (rranjan@chelsio.com)
+ */
+
+#ifndef __LIBCXGBI_H__
+#define __LIBCXGBI_H__
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/debugfs.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/scatterlist.h>
+#include <linux/skbuff.h>
+#include <linux/vmalloc.h>
+#include <scsi/scsi_device.h>
+#include <scsi/libiscsi_tcp.h>
+
+enum cxgbi_dbg_flag {
+ CXGBI_DBG_ISCSI,
+ CXGBI_DBG_DDP,
+ CXGBI_DBG_TOE,
+ CXGBI_DBG_SOCK,
+
+ CXGBI_DBG_PDU_TX,
+ CXGBI_DBG_PDU_RX,
+ CXGBI_DBG_DEV,
+};
+
+#define log_debug(level, fmt, ...) \
+ do { \
+ if (dbg_level & (level)) \
+ pr_info(fmt, ##__VA_ARGS__); \
+ } while (0)
+
+/* max. connections per adapter */
+#define CXGBI_MAX_CONN 16384
+
+/* always allocate rooms for AHS */
+#define SKB_TX_ISCSI_PDU_HEADER_MAX \
+ (sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE)
+
+#define ISCSI_PDU_NONPAYLOAD_LEN 312 /* bhs(48) + ahs(256) + digest(8)*/
+
+/*
+ * align pdu size to multiple of 512 for better performance
+ */
+#define cxgbi_align_pdu_size(n) do { n = (n) & (~511); } while (0)
+
+#define ULP2_MODE_ISCSI 2
+
+#define ULP2_MAX_PKT_SIZE 16224
+#define ULP2_MAX_PDU_PAYLOAD \
+ (ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_LEN)
+
+/*
+ * For iscsi connections HW may inserts digest bytes into the pdu. Those digest
+ * bytes are not sent by the host but are part of the TCP payload and therefore
+ * consume TCP sequence space.
+ */
+static const unsigned int ulp2_extra_len[] = { 0, 4, 4, 8 };
+static inline unsigned int cxgbi_ulp_extra_len(int submode)
+{
+ return ulp2_extra_len[submode & 3];
+}
+
+/*
+ * struct pagepod_hdr, pagepod - pagepod format
+ */
+
+#define CPL_RX_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */
+#define CPL_RX_DDP_STATUS_PAD_SHIFT 19 /* pad error */
+#define CPL_RX_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */
+#define CPL_RX_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */
+
+struct cxgbi_pagepod_hdr {
+ u32 vld_tid;
+ u32 pgsz_tag_clr;
+ u32 max_offset;
+ u32 page_offset;
+ u64 rsvd;
+};
+
+#define PPOD_PAGES_MAX 4
+struct cxgbi_pagepod {
+ struct cxgbi_pagepod_hdr hdr;
+ u64 addr[PPOD_PAGES_MAX + 1];
+};
+
+struct cxgbi_tag_format {
+ unsigned char sw_bits;
+ unsigned char rsvd_bits;
+ unsigned char rsvd_shift;
+ unsigned char filler[1];
+ u32 rsvd_mask;
+};
+
+struct cxgbi_gather_list {
+ unsigned int tag;
+ unsigned int length;
+ unsigned int offset;
+ unsigned int nelem;
+ struct page **pages;
+ dma_addr_t phys_addr[0];
+};
+
+struct cxgbi_ddp_info {
+ struct kref refcnt;
+ struct cxgbi_device *cdev;
+ struct pci_dev *pdev;
+ unsigned int max_txsz;
+ unsigned int max_rxsz;
+ unsigned int llimit;
+ unsigned int ulimit;
+ unsigned int nppods;
+ unsigned int idx_last;
+ unsigned char idx_bits;
+ unsigned char filler[3];
+ unsigned int idx_mask;
+ unsigned int rsvd_tag_mask;
+ spinlock_t map_lock;
+ struct cxgbi_gather_list **gl_map;
+ struct sk_buff **gl_skb;
+};
+
+#define DDP_PGIDX_MAX 4
+#define DDP_THRESHOLD 2048
+
+#define PPOD_PAGES_SHIFT 2 /* 4 pages per pod */
+
+#define PPOD_SIZE sizeof(struct cxgbi_pagepod) /* 64 */
+#define PPOD_SIZE_SHIFT 6
+
+#define ULPMEM_DSGL_MAX_NPPODS 16 /* 1024/PPOD_SIZE */
+#define ULPMEM_IDATA_MAX_NPPODS 4 /* 256/PPOD_SIZE */
+#define PCIE_MEMWIN_MAX_NPPODS 16 /* 1024/PPOD_SIZE */
+
+#define PPOD_COLOR_SHIFT 0
+#define PPOD_COLOR(x) ((x) << PPOD_COLOR_SHIFT)
+
+#define PPOD_IDX_SHIFT 6
+#define PPOD_IDX_MAX_SIZE 24
+
+#define PPOD_TID_SHIFT 0
+#define PPOD_TID(x) ((x) << PPOD_TID_SHIFT)
+
+#define PPOD_TAG_SHIFT 6
+#define PPOD_TAG(x) ((x) << PPOD_TAG_SHIFT)
+
+#define PPOD_VALID_SHIFT 24
+#define PPOD_VALID(x) ((x) << PPOD_VALID_SHIFT)
+#define PPOD_VALID_FLAG PPOD_VALID(1U)
+
+#define W_TCB_ULP_TYPE 0
+#define TCB_ULP_TYPE_SHIFT 0
+#define TCB_ULP_TYPE_MASK 0xfULL
+#define TCB_ULP_TYPE(x) ((x) << TCB_ULP_TYPE_SHIFT)
+
+#define W_TCB_ULP_RAW 0
+#define TCB_ULP_RAW_SHIFT 4
+#define TCB_ULP_RAW_MASK 0xffULL
+#define TCB_ULP_RAW(x) ((x) << TCB_ULP_RAW_SHIFT)
+
+/*
+ * sge_opaque_hdr -
+ * Opaque version of structure the SGE stores at skb->head of TX_DATA packets
+ * and for which we must reserve space.
+ */
+struct sge_opaque_hdr {
+ void *dev;
+ dma_addr_t addr[MAX_SKB_FRAGS + 1];
+};
+
+struct cxgbi_sock {
+ struct cxgbi_device *cdev;
+
+ int tid;
+ int atid;
+ unsigned long flags;
+ unsigned int mtu;
+ unsigned short rss_qid;
+ unsigned short txq_idx;
+ unsigned short advmss;
+ unsigned int tx_chan;
+ unsigned int rx_chan;
+ unsigned int mss_idx;
+ unsigned int smac_idx;
+ unsigned char port_id;
+ int wr_max_cred;
+ int wr_cred;
+ int wr_una_cred;
+ unsigned char hcrc_len;
+ unsigned char dcrc_len;
+
+ void *l2t;
+ struct sk_buff *wr_pending_head;
+ struct sk_buff *wr_pending_tail;
+ struct sk_buff *cpl_close;
+ struct sk_buff *cpl_abort_req;
+ struct sk_buff *cpl_abort_rpl;
+ struct sk_buff *skb_ulp_lhdr;
+ spinlock_t lock;
+ struct kref refcnt;
+ unsigned int state;
+ struct sockaddr_in saddr;
+ struct sockaddr_in daddr;
+ struct dst_entry *dst;
+ struct sk_buff_head receive_queue;
+ struct sk_buff_head write_queue;
+ struct timer_list retry_timer;
+ int err;
+ rwlock_t callback_lock;
+ void *user_data;
+
+ u32 rcv_nxt;
+ u32 copied_seq;
+ u32 rcv_wup;
+ u32 snd_nxt;
+ u32 snd_una;
+ u32 write_seq;
+};
+
+/*
+ * connection states
+ */
+enum cxgbi_sock_states{
+ CTP_CLOSED,
+ CTP_CONNECTING,
+ CTP_ACTIVE_OPEN,
+ CTP_ESTABLISHED,
+ CTP_ACTIVE_CLOSE,
+ CTP_PASSIVE_CLOSE,
+ CTP_CLOSE_WAIT_1,
+ CTP_CLOSE_WAIT_2,
+ CTP_ABORTING,
+};
+
+/*
+ * Connection flags -- many to track some close related events.
+ */
+enum cxgbi_sock_flags {
+ CTPF_ABORT_RPL_RCVD, /*received one ABORT_RPL_RSS message */
+ CTPF_ABORT_REQ_RCVD, /*received one ABORT_REQ_RSS message */
+ CTPF_ABORT_RPL_PENDING, /* expecting an abort reply */
+ CTPF_TX_DATA_SENT, /* already sent a TX_DATA WR */
+ CTPF_ACTIVE_CLOSE_NEEDED,/* need to be closed */
+ CTPF_HAS_ATID, /* reserved atid */
+ CTPF_HAS_TID, /* reserved hw tid */
+ CTPF_OFFLOAD_DOWN, /* offload function off */
+};
+
+struct cxgbi_skb_rx_cb {
+ __u32 ddigest;
+ __u32 pdulen;
+};
+
+struct cxgbi_skb_tx_cb {
+ void *l2t;
+ struct sk_buff *wr_next;
+};
+
+enum cxgbi_skcb_flags {
+ SKCBF_TX_NEED_HDR, /* packet needs a header */
+ SKCBF_RX_COALESCED, /* received whole pdu */
+ SKCBF_RX_HDR, /* recieved pdu header */
+ SKCBF_RX_DATA, /* recieved pdu payload */
+ SKCBF_RX_STATUS, /* recieved ddp status */
+ SKCBF_RX_DATA_DDPD, /* pdu payload ddp'd */
+ SKCBF_RX_HCRC_ERR, /* header digest error */
+ SKCBF_RX_DCRC_ERR, /* data digest error */
+ SKCBF_RX_PAD_ERR, /* padding byte error */
+};
+
+struct cxgbi_skb_cb {
+ unsigned char ulp_mode;
+ unsigned long flags;
+ unsigned int seq;
+ union {
+ struct cxgbi_skb_rx_cb rx;
+ struct cxgbi_skb_tx_cb tx;
+ };
+};
+
+#define CXGBI_SKB_CB(skb) ((struct cxgbi_skb_cb *)&((skb)->cb[0]))
+#define cxgbi_skcb_flags(skb) (CXGBI_SKB_CB(skb)->flags)
+#define cxgbi_skcb_ulp_mode(skb) (CXGBI_SKB_CB(skb)->ulp_mode)
+#define cxgbi_skcb_tcp_seq(skb) (CXGBI_SKB_CB(skb)->seq)
+#define cxgbi_skcb_rx_ddigest(skb) (CXGBI_SKB_CB(skb)->rx.ddigest)
+#define cxgbi_skcb_rx_pdulen(skb) (CXGBI_SKB_CB(skb)->rx.pdulen)
+#define cxgbi_skcb_tx_wr_next(skb) (CXGBI_SKB_CB(skb)->tx.wr_next)
+
+static inline void cxgbi_skcb_set_flag(struct sk_buff *skb,
+ enum cxgbi_skcb_flags flag)
+{
+ __set_bit(flag, &(cxgbi_skcb_flags(skb)));
+}
+
+static inline void cxgbi_skcb_clear_flag(struct sk_buff *skb,
+ enum cxgbi_skcb_flags flag)
+{
+ __clear_bit(flag, &(cxgbi_skcb_flags(skb)));
+}
+
+static inline int cxgbi_skcb_test_flag(struct sk_buff *skb,
+ enum cxgbi_skcb_flags flag)
+{
+ return test_bit(flag, &(cxgbi_skcb_flags(skb)));
+}
+
+static inline void cxgbi_sock_set_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ __set_bit(flag, &csk->flags);
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "csk 0x%p,%u,0x%lx, bit %d.\n",
+ csk, csk->state, csk->flags, flag);
+}
+
+static inline void cxgbi_sock_clear_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ __clear_bit(flag, &csk->flags);
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "csk 0x%p,%u,0x%lx, bit %d.\n",
+ csk, csk->state, csk->flags, flag);
+}
+
+static inline int cxgbi_sock_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ if (csk == NULL)
+ return 0;
+ return test_bit(flag, &csk->flags);
+}
+
+static inline void cxgbi_sock_set_state(struct cxgbi_sock *csk, int state)
+{
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "csk 0x%p,%u,0x%lx, state -> %u.\n",
+ csk, csk->state, csk->flags, state);
+ csk->state = state;
+}
+
+static inline void cxgbi_sock_free(struct kref *kref)
+{
+ struct cxgbi_sock *csk = container_of(kref,
+ struct cxgbi_sock,
+ refcnt);
+ if (csk) {
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "free csk 0x%p, state %u, flags 0x%lx\n",
+ csk, csk->state, csk->flags);
+ kfree(csk);
+ }
+}
+
+static inline void __cxgbi_sock_put(const char *fn, struct cxgbi_sock *csk)
+{
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "%s, put csk 0x%p, ref %u-1.\n",
+ fn, csk, atomic_read(&csk->refcnt.refcount));
+ kref_put(&csk->refcnt, cxgbi_sock_free);
+}
+#define cxgbi_sock_put(csk) __cxgbi_sock_put(__func__, csk)
+
+static inline void __cxgbi_sock_get(const char *fn, struct cxgbi_sock *csk)
+{
+ log_debug(1 << CXGBI_DBG_SOCK,
+ "%s, get csk 0x%p, ref %u+1.\n",
+ fn, csk, atomic_read(&csk->refcnt.refcount));
+ kref_get(&csk->refcnt);
+}
+#define cxgbi_sock_get(csk) __cxgbi_sock_get(__func__, csk)
+
+static inline int cxgbi_sock_is_closing(struct cxgbi_sock *csk)
+{
+ return csk->state >= CTP_ACTIVE_CLOSE;
+}
+
+static inline int cxgbi_sock_is_established(struct cxgbi_sock *csk)
+{
+ return csk->state == CTP_ESTABLISHED;
+}
+
+static inline void cxgbi_sock_purge_write_queue(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+
+ while ((skb = __skb_dequeue(&csk->write_queue)))
+ __kfree_skb(skb);
+}
+
+static inline unsigned int cxgbi_sock_compute_wscale(unsigned int win)
+{
+ unsigned int wscale = 0;
+
+ while (wscale < 14 && (65535 << wscale) < win)
+ wscale++;
+ return wscale;
+}
+
+static inline struct sk_buff *alloc_cpl(int cpl_len, int dlen, gfp_t gfp)
+{
+ int wrlen = roundup(cpl_len, 16);
+ struct sk_buff *skb = alloc_skb(wrlen + dlen, gfp);
+
+ if (skb) {
+ __skb_put(skb, wrlen);
+ memset(skb->head, 0, wrlen + dlen);
+ } else
+ pr_info("alloc cpl skb %u+%u, OOM.\n", cpl_len, dlen);
+ return skb;
+}
+
+
+/*
+ * The number of WRs needed for an skb depends on the number of fragments
+ * in the skb and whether it has any payload in its main body. This maps the
+ * length of the gather list represented by an skb into the # of necessary WRs.
+ * The extra two fragments are for iscsi bhs and payload padding.
+ */
+#define SKB_WR_LIST_SIZE (MAX_SKB_FRAGS + 2)
+
+static inline void cxgbi_sock_reset_wr_list(struct cxgbi_sock *csk)
+{
+ csk->wr_pending_head = csk->wr_pending_tail = NULL;
+}
+
+static inline void cxgbi_sock_enqueue_wr(struct cxgbi_sock *csk,
+ struct sk_buff *skb)
+{
+ cxgbi_skcb_tx_wr_next(skb) = NULL;
+ /*
+ * We want to take an extra reference since both us and the driver
+ * need to free the packet before it's really freed. We know there's
+ * just one user currently so we use atomic_set rather than skb_get
+ * to avoid the atomic op.
+ */
+ atomic_set(&skb->users, 2);
+
+ if (!csk->wr_pending_head)
+ csk->wr_pending_head = skb;
+ else
+ cxgbi_skcb_tx_wr_next(csk->wr_pending_tail) = skb;
+ csk->wr_pending_tail = skb;
+}
+
+static inline int cxgbi_sock_count_pending_wrs(const struct cxgbi_sock *csk)
+{
+ int n = 0;
+ const struct sk_buff *skb = csk->wr_pending_head;
+
+ while (skb) {
+ n += skb->csum;
+ skb = cxgbi_skcb_tx_wr_next(skb);
+ }
+ return n;
+}
+
+static inline struct sk_buff *cxgbi_sock_peek_wr(const struct cxgbi_sock *csk)
+{
+ return csk->wr_pending_head;
+}
+
+static inline struct sk_buff *cxgbi_sock_dequeue_wr(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb = csk->wr_pending_head;
+
+ if (likely(skb)) {
+ csk->wr_pending_head = cxgbi_skcb_tx_wr_next(skb);
+ cxgbi_skcb_tx_wr_next(skb) = NULL;
+ }
+ return skb;
+}
+
+void cxgbi_sock_check_wr_invariants(const struct cxgbi_sock *);
+void cxgbi_sock_purge_wr_queue(struct cxgbi_sock *);
+void cxgbi_sock_skb_entail(struct cxgbi_sock *, struct sk_buff *);
+void cxgbi_sock_fail_act_open(struct cxgbi_sock *, int);
+void cxgbi_sock_act_open_req_arp_failure(void *, struct sk_buff *);
+void cxgbi_sock_closed(struct cxgbi_sock *);
+void cxgbi_sock_established(struct cxgbi_sock *, unsigned int, unsigned int);
+void cxgbi_sock_rcv_abort_rpl(struct cxgbi_sock *);
+void cxgbi_sock_rcv_peer_close(struct cxgbi_sock *);
+void cxgbi_sock_rcv_close_conn_rpl(struct cxgbi_sock *, u32);
+void cxgbi_sock_rcv_wr_ack(struct cxgbi_sock *, unsigned int, unsigned int,
+ int);
+unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *, unsigned int);
+void cxgbi_sock_free_cpl_skbs(struct cxgbi_sock *);
+
+struct cxgbi_hba {
+ struct net_device *ndev;
+ struct Scsi_Host *shost;
+ struct cxgbi_device *cdev;
+ __be32 ipv4addr;
+ unsigned char port_id;
+};
+
+struct cxgbi_ports_map {
+ unsigned int max_connect;
+ unsigned int used;
+ unsigned short sport_base;
+ spinlock_t lock;
+ unsigned int next;
+ struct cxgbi_sock **port_csk;
+};
+
+#define CXGBI_FLAG_DEV_T3 0x1
+#define CXGBI_FLAG_DEV_T4 0x2
+#define CXGBI_FLAG_ADAPTER_RESET 0x4
+#define CXGBI_FLAG_IPV4_SET 0x10
+struct cxgbi_device {
+ struct list_head list_head;
+ unsigned int flags;
+ struct net_device **ports;
+ void *lldev;
+ struct cxgbi_hba **hbas;
+ const unsigned short *mtus;
+ unsigned char nmtus;
+ unsigned char nports;
+ struct pci_dev *pdev;
+ struct dentry *debugfs_root;
+ struct iscsi_transport *itp;
+
+ unsigned int pfvf;
+ unsigned int snd_win;
+ unsigned int rcv_win;
+ unsigned int rx_credit_thres;
+ unsigned int skb_tx_rsvd;
+ unsigned int skb_rx_extra; /* for msg coalesced mode */
+ unsigned int tx_max_size;
+ unsigned int rx_max_size;
+ struct cxgbi_ports_map pmap;
+ struct cxgbi_tag_format tag_format;
+ struct cxgbi_ddp_info *ddp;
+
+ void (*dev_ddp_cleanup)(struct cxgbi_device *);
+ void (*csk_ddp_free_gl_skb)(struct cxgbi_ddp_info *, int, int);
+ int (*csk_ddp_alloc_gl_skb)(struct cxgbi_ddp_info *, int, int, gfp_t);
+ int (*csk_ddp_set)(struct cxgbi_sock *, struct cxgbi_pagepod_hdr *,
+ unsigned int, unsigned int,
+ struct cxgbi_gather_list *);
+ void (*csk_ddp_clear)(struct cxgbi_hba *,
+ unsigned int, unsigned int, unsigned int);
+ int (*csk_ddp_setup_digest)(struct cxgbi_sock *,
+ unsigned int, int, int, int);
+ int (*csk_ddp_setup_pgidx)(struct cxgbi_sock *,
+ unsigned int, int, bool);
+
+ void (*csk_release_offload_resources)(struct cxgbi_sock *);
+ int (*csk_rx_pdu_ready)(struct cxgbi_sock *, struct sk_buff *);
+ u32 (*csk_send_rx_credits)(struct cxgbi_sock *, u32);
+ int (*csk_push_tx_frames)(struct cxgbi_sock *, int);
+ void (*csk_send_abort_req)(struct cxgbi_sock *);
+ void (*csk_send_close_req)(struct cxgbi_sock *);
+ int (*csk_alloc_cpls)(struct cxgbi_sock *);
+ int (*csk_init_act_open)(struct cxgbi_sock *);
+
+ void *dd_data;
+};
+#define cxgbi_cdev_priv(cdev) ((cdev)->dd_data)
+
+struct cxgbi_conn {
+ struct cxgbi_endpoint *cep;
+ struct iscsi_conn *iconn;
+ struct cxgbi_hba *chba;
+ u32 task_idx_bits;
+};
+
+struct cxgbi_endpoint {
+ struct cxgbi_conn *cconn;
+ struct cxgbi_hba *chba;
+ struct cxgbi_sock *csk;
+};
+
+#define MAX_PDU_FRAGS ((ULP2_MAX_PDU_PAYLOAD + 512 - 1) / 512)
+struct cxgbi_task_data {
+ unsigned short nr_frags;
+ skb_frag_t frags[MAX_PDU_FRAGS];
+ struct sk_buff *skb;
+ unsigned int offset;
+ unsigned int count;
+ unsigned int sgoffset;
+};
+
+static inline int cxgbi_is_ddp_tag(struct cxgbi_tag_format *tformat, u32 tag)
+{
+ return !(tag & (1 << (tformat->rsvd_bits + tformat->rsvd_shift - 1)));
+}
+
+static inline int cxgbi_sw_tag_usable(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ sw_tag >>= (32 - tformat->rsvd_bits);
+ return !sw_tag;
+}
+
+static inline u32 cxgbi_set_non_ddp_tag(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+ u32 mask = (1 << shift) - 1;
+
+ if (sw_tag && (sw_tag & ~mask)) {
+ u32 v1 = sw_tag & ((1 << shift) - 1);
+ u32 v2 = (sw_tag >> (shift - 1)) << shift;
+
+ return v2 | v1 | 1 << shift;
+ }
+
+ return sw_tag | 1 << shift;
+}
+
+static inline u32 cxgbi_ddp_tag_base(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ u32 mask = (1 << tformat->rsvd_shift) - 1;
+
+ if (sw_tag && (sw_tag & ~mask)) {
+ u32 v1 = sw_tag & mask;
+ u32 v2 = sw_tag >> tformat->rsvd_shift;
+
+ v2 <<= tformat->rsvd_bits + tformat->rsvd_shift;
+
+ return v2 | v1;
+ }
+
+ return sw_tag;
+}
+
+static inline u32 cxgbi_tag_rsvd_bits(struct cxgbi_tag_format *tformat,
+ u32 tag)
+{
+ if (cxgbi_is_ddp_tag(tformat, tag))
+ return (tag >> tformat->rsvd_shift) & tformat->rsvd_mask;
+
+ return 0;
+}
+
+static inline u32 cxgbi_tag_nonrsvd_bits(struct cxgbi_tag_format *tformat,
+ u32 tag)
+{
+ unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+ u32 v1, v2;
+
+ if (cxgbi_is_ddp_tag(tformat, tag)) {
+ v1 = tag & ((1 << tformat->rsvd_shift) - 1);
+ v2 = (tag >> (shift + 1)) << tformat->rsvd_shift;
+ } else {
+ u32 mask = (1 << shift) - 1;
+ tag &= ~(1 << shift);
+ v1 = tag & mask;
+ v2 = (tag >> 1) & ~mask;
+ }
+ return v1 | v2;
+}
+
+static inline void *cxgbi_alloc_big_mem(unsigned int size,
+ gfp_t gfp)
+{
+ void *p = kmalloc(size, gfp);
+ if (!p)
+ p = vmalloc(size);
+ if (p)
+ memset(p, 0, size);
+ return p;
+}
+
+static inline void cxgbi_free_big_mem(void *addr)
+{
+ if (is_vmalloc_addr(addr))
+ vfree(addr);
+ else
+ kfree(addr);
+}
+
+static inline void cxgbi_set_iscsi_ipv4(struct cxgbi_hba *chba, __be32 ipaddr)
+{
+ if (chba->cdev->flags & CXGBI_FLAG_IPV4_SET)
+ chba->ipv4addr = ipaddr;
+ else
+ pr_info("set iscsi ipv4 NOT supported, using %s ipv4.\n",
+ chba->ndev->name);
+}
+
+static inline __be32 cxgbi_get_iscsi_ipv4(struct cxgbi_hba *chba)
+{
+ return chba->ipv4addr;
+}
+
+struct cxgbi_device *cxgbi_device_register(unsigned int, unsigned int);
+void cxgbi_device_unregister(struct cxgbi_device *);
+void cxgbi_device_unregister_all(unsigned int flag);
+struct cxgbi_device *cxgbi_device_find_by_lldev(void *);
+int cxgbi_hbas_add(struct cxgbi_device *, unsigned int, unsigned int,
+ struct scsi_host_template *,
+ struct scsi_transport_template *);
+void cxgbi_hbas_remove(struct cxgbi_device *);
+
+int cxgbi_device_portmap_create(struct cxgbi_device *cdev, unsigned int base,
+ unsigned int max_conn);
+void cxgbi_device_portmap_cleanup(struct cxgbi_device *cdev);
+
+void cxgbi_conn_tx_open(struct cxgbi_sock *);
+void cxgbi_conn_pdu_ready(struct cxgbi_sock *);
+int cxgbi_conn_alloc_pdu(struct iscsi_task *, u8);
+int cxgbi_conn_init_pdu(struct iscsi_task *, unsigned int , unsigned int);
+int cxgbi_conn_xmit_pdu(struct iscsi_task *);
+
+void cxgbi_cleanup_task(struct iscsi_task *task);
+
+void cxgbi_get_conn_stats(struct iscsi_cls_conn *, struct iscsi_stats *);
+int cxgbi_set_conn_param(struct iscsi_cls_conn *,
+ enum iscsi_param, char *, int);
+int cxgbi_get_conn_param(struct iscsi_cls_conn *, enum iscsi_param, char *);
+struct iscsi_cls_conn *cxgbi_create_conn(struct iscsi_cls_session *, u32);
+int cxgbi_bind_conn(struct iscsi_cls_session *,
+ struct iscsi_cls_conn *, u64, int);
+void cxgbi_destroy_session(struct iscsi_cls_session *);
+struct iscsi_cls_session *cxgbi_create_session(struct iscsi_endpoint *,
+ u16, u16, u32);
+int cxgbi_set_host_param(struct Scsi_Host *,
+ enum iscsi_host_param, char *, int);
+int cxgbi_get_host_param(struct Scsi_Host *, enum iscsi_host_param, char *);
+struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *,
+ struct sockaddr *, int);
+int cxgbi_ep_poll(struct iscsi_endpoint *, int);
+void cxgbi_ep_disconnect(struct iscsi_endpoint *);
+
+int cxgbi_iscsi_init(struct iscsi_transport *,
+ struct scsi_transport_template **);
+void cxgbi_iscsi_cleanup(struct iscsi_transport *,
+ struct scsi_transport_template **);
+void cxgbi_parse_pdu_itt(struct iscsi_conn *, itt_t, int *, int *);
+int cxgbi_ddp_init(struct cxgbi_device *, unsigned int, unsigned int,
+ unsigned int, unsigned int);
+int cxgbi_ddp_cleanup(struct cxgbi_device *);
+void cxgbi_ddp_page_size_factor(int *);
+void cxgbi_ddp_ppod_clear(struct cxgbi_pagepod *);
+void cxgbi_ddp_ppod_set(struct cxgbi_pagepod *, struct cxgbi_pagepod_hdr *,
+ struct cxgbi_gather_list *, unsigned int);
+#endif /*__LIBCXGBI_H__*/
^ permalink raw reply related
* Re: [PATCH 1/42] drivers/net/wan: Adjust confusing if indentation
From: David Miller @ 2010-08-17 3:57 UTC (permalink / raw)
To: khc; +Cc: julia, netdev, linux-kernel, kernel-janitors
In-Reply-To: <m37hk21tv2.fsf@intrepid.localdomain>
From: Krzysztof Halasa <khc@pm.waw.pl>
Date: Sat, 07 Aug 2010 14:37:37 +0200
> Julia Lawall <julia@diku.dk> writes:
>
>> drivers/net/wan/c101.c | 2 +-
>> drivers/net/wan/n2.c | 2 +-
>> drivers/net/wan/pci200syn.c | 2 +-
>
> Fully Acked-by: Krzysztof Hałasa <khc@pm.waw.pl>
Please don't use non-standard commit tags like this "Fully Acked-by:"
thing, otherwise automated tools won't notice and pick them up
properly.
Thanks.
^ permalink raw reply
* Re: [PATCH] net/sched: add ACT_CSUM action to update packets checksums
From: Eric Dumazet @ 2010-08-17 5:19 UTC (permalink / raw)
To: Grégoire Baron; +Cc: netdev, David Miller
In-Reply-To: <20100816211542.GA21083@n7mm.org>
Le lundi 16 août 2010 à 23:15 +0200, Grégoire Baron a écrit :
> net/sched: add ACT_CSUM action to update packets checksums
>
> ACT_CSUM can be called just after ACT_PEDIT in order to re-compute some
> altered checksums in IPv4 and IPv6 packets. The following checksums are
> supported by this patch:
> - IPv4: IPv4 header, ICMP, IGMP, TCP, UDP & UDPLite
> - IPv6: ICMPv6, TCP, UDP & UDPLite
> It's possible to request in the same action to update different kind of
> checksums, if the packets flow mix TCP, UDP and UDPLite, ...
>
> An example of usage is done in the associated iproute2 patch.
>
> Signed-off-by: Gregoire Baron <baronchon@n7mm.org>
Impressive :)
One style note :
> +
> + switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
> + case IPPROTO_ICMP:
> + {
> + if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP)
> + if (!tcf_csum_ipv4_icmp(skb, iph,
> + iph->ihl * 4, ntohs(iph->tot_len)))
> + goto fail;
> + break;
> + }
> + case IPPROTO_IGMP:
> + {
> + if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP)
> + if (!tcf_csum_ipv4_igmp(skb, iph,
> + iph->ihl * 4, ntohs(iph->tot_len)))
> + goto fail;
> + break;
> + }
You add extra block delimiters (thus two lines) per switch cases, while
not necessary. Please remove them.
And one note about tcf_csum_dump()
static int tcf_csum_dump(struct sk_buff *skb,
struct tc_action *a, int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_csum *p = a->priv;
struct tc_csum *opt;
struct tcf_t t;
int s;
s = sizeof(*opt);
/* netlink spinlocks held above us - must use ATOMIC */
opt = kzalloc(s, GFP_ATOMIC);
if (unlikely(!opt))
return -ENOBUFS;
Please dont use kzalloc() here for such a small variable (24 bytes), use
an automatic one (on stack)
struct tc_csum parms = {
.update_flags = p->update_flags,
.index = p->tcf_index,
.action = p->tcf_action,
.refcnt = p->tcf_refcnt - ref,
.bindcnt = p->tcf_bindcnt - bind,
};
(Using such a construct make sure holes are zero filled, thus we dont
leak kernel memory to user)
NLA_PUT(skb, TCA_CSUM_PARMS, sizeof(parms), &parms);
Hmm, I can see existing code have some leaks, I'll post a separate
patch...
^ permalink raw reply
* Re: BUG: IPv6 stops working after a while, needs ip ne del command to reset
From: Thomas Habets @ 2010-08-17 5:35 UTC (permalink / raw)
To: Thomas Habets; +Cc: Eric Dumazet, linux-kernel, netdev
In-Reply-To: <alpine.DEB.1.10.1008161224510.13728@red.crap.retrofitta.se>
On Mon, 16 Aug 2010, Thomas Habets wrote:
> Am I not allowed to add addresses to lo? That I've deconfigured this address
> and rebooted the box to check if this matters.
It didn't help.
> I will re-check ethtool and Cisco router output for mismatches when it breaks
> again to make sure that there's no change or errors counting up.
IPv6 is currently not working and it's still 1000 Full on both sides
("show int GiX/Y" and "ethtool eth0").
No errors in "ethtool -S eth0" or "show int GiX/Y".
"ethtool eth0" output is the same as yesterday.
Here's the addresses and routing table as they are now, and have been
since reboot:
$ ip -6 a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qlen 1000
inet6 2a00:800:752:1::5c:2/112 scope global
valid_lft forever preferred_lft forever
inet6 fe80::224:81ff:fea3:4424/64 scope link
valid_lft forever preferred_lft forever
$ ip -6 r sh
2a00:800:752:1::5c:0/112 dev eth0 proto kernel metric 256 mtu 1500
advmss 1440 hoplimit 4294967295
fe80::/64 dev eth0 proto kernel metric 256 mtu 1500 advmss 1440
hoplimit 4294967295
default via 2a00:800:752:1::5c:1 dev eth0 metric 1024 mtu 1500 advmss
1440 hoplimit 4294967295
$ ip -6 ne sh
2a00:800:752:1::5c:1 dev eth0 lladdr 00:22:55:17:4b:80 router STALE
[try ping6 again, no reply]
$ ip -6 ne sh
2a00:800:752:1::5c:1 dev eth0 lladdr 00:22:55:17:4b:80 router DELAY
[try ping6 again, no reply]
$ ip -6 ne sh
2a00:800:752:1::5c:1 dev eth0 lladdr 00:22:55:17:4b:80 router REACHABLE
[try ping6 again, no reply]
Configured network with /etc/network/interfaces:
auto lo
iface lo inet loopback
allow-hotplug eth0
iface eth0 inet static
address x.x.x.x
netmask 255.255.255.252
broadcast x.x.x.x
gateway x.x.x.x
up ip a a 2a00:800:752:1::5c:2/112 dev eth0
up ip r a default via 2a00:800:752:1::5c:1
dns-nameservers x.x.x.x
dns-search xxxx.net
---------
typedef struct me_s {
char name[] = { "Thomas Habets" };
char email[] = { "thomas@habets.pp.se" };
char kernel[] = { "Linux" };
char *pgpKey[] = { "http://www.habets.pp.se/pubkey.txt" };
char pgp[] = { "A8A3 D1DD 4AE0 8467 7FDE 0945 286A E90A AD48 E854" };
char coolcmd[] = { "echo '. ./_&. ./_'>_;. ./_" };
} me_t;
^ permalink raw reply
* Re: [PATCH 10/16] drivers/net/wireless/wl12xx: Use available error codes
From: Luciano Coelho @ 2010-08-17 5:42 UTC (permalink / raw)
To: ext Julia Lawall
Cc: John W. Linville, linux-wireless@vger.kernel.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
kernel-janitors@vger.kernel.org
In-Reply-To: <Pine.LNX.4.64.1008161827140.19313@ask.diku.dk>
On Mon, 2010-08-16 at 18:27 +0200, ext Julia Lawall wrote:
> From: Julia Lawall <julia@diku.dk>
>
> Error codes are stored in ret, but the return value is always 0. Return
> ret instead.
>
> The semantic match that finds this problem is as follows:
> (http://coccinelle.lip6.fr/)
>
> // <smpl>
> @r@
> local idexpression x;
> constant C;
> @@
>
> if (...) { ...
> x = -C
> ... when != x
> (
> return <+...x...+>;
> |
> return NULL;
> |
> return;
> |
> * return ...;
> )
> }
> // </smpl>
>
> Signed-off-by: Julia Lawall <julia@diku.dk>
>
> ---
This was indeed a bug. Thanks!
Acked-by: Luciano Coelho <luciano.coelho@nokia.com>
--
Cheers,
Luca.
^ permalink raw reply
* Re: BUG: IPv6 stops working after a while, needs ip ne del command to reset
From: Eric Dumazet @ 2010-08-17 6:00 UTC (permalink / raw)
To: Thomas Habets; +Cc: linux-kernel, netdev
In-Reply-To: <alpine.DEB.1.10.1008170719180.21857@red.crap.retrofitta.se>
Le mardi 17 août 2010 à 07:35 +0200, Thomas Habets a écrit :
> On Mon, 16 Aug 2010, Thomas Habets wrote:
> > Am I not allowed to add addresses to lo? That I've deconfigured this address
> > and rebooted the box to check if this matters.
>
> It didn't help.
>
> > I will re-check ethtool and Cisco router output for mismatches when it breaks
> > again to make sure that there's no change or errors counting up.
>
> IPv6 is currently not working and it's still 1000 Full on both sides
> ("show int GiX/Y" and "ethtool eth0").
> No errors in "ethtool -S eth0" or "show int GiX/Y".
>
> "ethtool eth0" output is the same as yesterday.
>
> Here's the addresses and routing table as they are now, and have been
> since reboot:
>
> $ ip -6 a
> 1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436
> inet6 ::1/128 scope host
> valid_lft forever preferred_lft forever
> 2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qlen 1000
> inet6 2a00:800:752:1::5c:2/112 scope global
> valid_lft forever preferred_lft forever
> inet6 fe80::224:81ff:fea3:4424/64 scope link
> valid_lft forever preferred_lft forever
>
>
> $ ip -6 r sh
> 2a00:800:752:1::5c:0/112 dev eth0 proto kernel metric 256 mtu 1500
> advmss 1440 hoplimit 4294967295
>
> fe80::/64 dev eth0 proto kernel metric 256 mtu 1500 advmss 1440
> hoplimit 4294967295
>
> default via 2a00:800:752:1::5c:1 dev eth0 metric 1024 mtu 1500 advmss
> 1440 hoplimit 4294967295
>
> $ ip -6 ne sh
> 2a00:800:752:1::5c:1 dev eth0 lladdr 00:22:55:17:4b:80 router STALE
>
> [try ping6 again, no reply]
>
> $ ip -6 ne sh
> 2a00:800:752:1::5c:1 dev eth0 lladdr 00:22:55:17:4b:80 router DELAY
>
> [try ping6 again, no reply]
>
> $ ip -6 ne sh
> 2a00:800:752:1::5c:1 dev eth0 lladdr 00:22:55:17:4b:80 router REACHABLE
>
This seems a bit different than previous mail. Apparently discovery now
works ?
Could you have a tcpdump on both sides ?
Maybe your host is OK, but other side drops your ICMP packets ?
> [try ping6 again, no reply]
>
> Configured network with /etc/network/interfaces:
>
> auto lo
> iface lo inet loopback
>
> allow-hotplug eth0
> iface eth0 inet static
> address x.x.x.x
> netmask 255.255.255.252
> broadcast x.x.x.x
> gateway x.x.x.x
> up ip a a 2a00:800:752:1::5c:2/112 dev eth0
> up ip r a default via 2a00:800:752:1::5c:1
> dns-nameservers x.x.x.x
> dns-search xxxx.net
^ permalink raw reply
* [PATCH] net sched: fix some kernel memory leaks
From: Eric Dumazet @ 2010-08-17 6:04 UTC (permalink / raw)
To: David Miller; +Cc: netdev
We leak at least 32bits of kernel memory to user land in tc dump,
because we dont init all fields (capab ?) of the dumped structure.
Use C99 initializers so that holes and non explicit fields are zeroed.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/sched/act_gact.c | 21 ++++++++++++---------
net/sched/act_mirred.c | 15 ++++++++-------
net/sched/act_nat.c | 22 +++++++++++-----------
net/sched/act_simple.c | 11 ++++++-----
net/sched/act_skbedit.c | 11 ++++++-----
5 files changed, 43 insertions(+), 37 deletions(-)
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 8406c66..c2ed90a 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -152,21 +152,24 @@ static int tcf_gact(struct sk_buff *skb, struct tc_action *a, struct tcf_result
static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
- struct tc_gact opt;
struct tcf_gact *gact = a->priv;
+ struct tc_gact opt = {
+ .index = gact->tcf_index,
+ .refcnt = gact->tcf_refcnt - ref,
+ .bindcnt = gact->tcf_bindcnt - bind,
+ .action = gact->tcf_action,
+ };
struct tcf_t t;
- opt.index = gact->tcf_index;
- opt.refcnt = gact->tcf_refcnt - ref;
- opt.bindcnt = gact->tcf_bindcnt - bind;
- opt.action = gact->tcf_action;
NLA_PUT(skb, TCA_GACT_PARMS, sizeof(opt), &opt);
#ifdef CONFIG_GACT_PROB
if (gact->tcfg_ptype) {
- struct tc_gact_p p_opt;
- p_opt.paction = gact->tcfg_paction;
- p_opt.pval = gact->tcfg_pval;
- p_opt.ptype = gact->tcfg_ptype;
+ struct tc_gact_p p_opt = {
+ .paction = gact->tcfg_paction,
+ .pval = gact->tcfg_pval,
+ .ptype = gact->tcfg_ptype,
+ };
+
NLA_PUT(skb, TCA_GACT_PROB, sizeof(p_opt), &p_opt);
}
#endif
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 11f195a..0c311be 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -219,15 +219,16 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, i
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_mirred *m = a->priv;
- struct tc_mirred opt;
+ struct tc_mirred opt = {
+ .index = m->tcf_index,
+ .action = m->tcf_action,
+ .refcnt = m->tcf_refcnt - ref,
+ .bindcnt = m->tcf_bindcnt - bind,
+ .eaction = m->tcfm_eaction,
+ .ifindex = m->tcfm_ifindex,
+ };
struct tcf_t t;
- opt.index = m->tcf_index;
- opt.action = m->tcf_action;
- opt.refcnt = m->tcf_refcnt - ref;
- opt.bindcnt = m->tcf_bindcnt - bind;
- opt.eaction = m->tcfm_eaction;
- opt.ifindex = m->tcfm_ifindex;
NLA_PUT(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt);
t.install = jiffies_to_clock_t(jiffies - m->tcf_tm.install);
t.lastuse = jiffies_to_clock_t(jiffies - m->tcf_tm.lastuse);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 509a2d5..186eb83 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -272,19 +272,19 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_nat *p = a->priv;
- struct tc_nat opt;
+ struct tc_nat opt = {
+ .old_addr = p->old_addr,
+ .new_addr = p->new_addr,
+ .mask = p->mask,
+ .flags = p->flags,
+
+ .index = p->tcf_index,
+ .action = p->tcf_action,
+ .refcnt = p->tcf_refcnt - ref,
+ .bindcnt = p->tcf_bindcnt - bind,
+ };
struct tcf_t t;
- opt.old_addr = p->old_addr;
- opt.new_addr = p->new_addr;
- opt.mask = p->mask;
- opt.flags = p->flags;
-
- opt.index = p->tcf_index;
- opt.action = p->tcf_action;
- opt.refcnt = p->tcf_refcnt - ref;
- opt.bindcnt = p->tcf_bindcnt - bind;
-
NLA_PUT(skb, TCA_NAT_PARMS, sizeof(opt), &opt);
t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 4a1d640..97e84f3 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -164,13 +164,14 @@ static inline int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_defact *d = a->priv;
- struct tc_defact opt;
+ struct tc_defact opt = {
+ .index = d->tcf_index,
+ .refcnt = d->tcf_refcnt - ref,
+ .bindcnt = d->tcf_bindcnt - bind,
+ .action = d->tcf_action,
+ };
struct tcf_t t;
- opt.index = d->tcf_index;
- opt.refcnt = d->tcf_refcnt - ref;
- opt.bindcnt = d->tcf_bindcnt - bind;
- opt.action = d->tcf_action;
NLA_PUT(skb, TCA_DEF_PARMS, sizeof(opt), &opt);
NLA_PUT_STRING(skb, TCA_DEF_DATA, d->tcfd_defdata);
t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install);
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index e9607fe..66cbf4e 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -159,13 +159,14 @@ static inline int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbedit *d = a->priv;
- struct tc_skbedit opt;
+ struct tc_skbedit opt = {
+ .index = d->tcf_index,
+ .refcnt = d->tcf_refcnt - ref,
+ .bindcnt = d->tcf_bindcnt - bind,
+ .action = d->tcf_action,
+ };
struct tcf_t t;
- opt.index = d->tcf_index;
- opt.refcnt = d->tcf_refcnt - ref;
- opt.bindcnt = d->tcf_bindcnt - bind;
- opt.action = d->tcf_action;
NLA_PUT(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt);
if (d->flags & SKBEDIT_F_PRIORITY)
NLA_PUT(skb, TCA_SKBEDIT_PRIORITY, sizeof(d->priority),
^ permalink raw reply related
* [PATCH] netfilter: don't disable BH again in BH disabled context
From: Changli Gao @ 2010-08-17 6:41 UTC (permalink / raw)
To: Patrick McHardy; +Cc: David S. Miller, netfilter-devel, netdev, Changli Gao
All the matches and targets of iptables, ip6tables are in BH disabled
context, since xt_info_rdlock_bh() disables BH.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
---
net/ipv4/netfilter/ipt_LOG.c | 8 ++++----
net/ipv4/netfilter/ipt_ULOG.c | 6 +++---
net/ipv6/netfilter/ip6t_LOG.c | 8 ++++----
net/netfilter/xt_RATEEST.c | 4 ++--
net/netfilter/xt_connlimit.c | 4 ++--
net/netfilter/xt_dccp.c | 8 ++++----
net/netfilter/xt_limit.c | 6 +++---
net/netfilter/xt_quota.c | 4 ++--
net/netfilter/xt_rateest.c | 8 ++++----
net/netfilter/xt_recent.c | 4 ++--
10 files changed, 30 insertions(+), 30 deletions(-)
diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c
index 915fc17..3ea7cfa 100644
--- a/net/ipv4/netfilter/ipt_LOG.c
+++ b/net/ipv4/netfilter/ipt_LOG.c
@@ -337,12 +337,12 @@ static void dump_packet(const struct nf_loginfo *info,
/* Max length: 15 "UID=4294967295 " */
if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) {
- read_lock_bh(&skb->sk->sk_callback_lock);
+ read_lock(&skb->sk->sk_callback_lock);
if (skb->sk->sk_socket && skb->sk->sk_socket->file)
printk("UID=%u GID=%u ",
skb->sk->sk_socket->file->f_cred->fsuid,
skb->sk->sk_socket->file->f_cred->fsgid);
- read_unlock_bh(&skb->sk->sk_callback_lock);
+ read_unlock(&skb->sk->sk_callback_lock);
}
/* Max length: 16 "MARK=0xFFFFFFFF " */
@@ -422,7 +422,7 @@ ipt_log_packet(u_int8_t pf,
if (!loginfo)
loginfo = &default_loginfo;
- spin_lock_bh(&log_lock);
+ spin_lock(&log_lock);
printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level,
prefix,
in ? in->name : "",
@@ -447,7 +447,7 @@ ipt_log_packet(u_int8_t pf,
dump_packet(loginfo, skb, 0);
printk("\n");
- spin_unlock_bh(&log_lock);
+ spin_unlock(&log_lock);
}
static unsigned int
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 446e0f4..f2dd9eb 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -180,7 +180,7 @@ static void ipt_ulog_packet(unsigned int hooknum,
ub = &ulog_buffers[groupnum];
- spin_lock_bh(&ulog_lock);
+ spin_lock(&ulog_lock);
if (!ub->skb) {
if (!(ub->skb = ulog_alloc_skb(size)))
@@ -264,7 +264,7 @@ static void ipt_ulog_packet(unsigned int hooknum,
ulog_send(groupnum);
}
- spin_unlock_bh(&ulog_lock);
+ spin_unlock(&ulog_lock);
return;
@@ -272,7 +272,7 @@ nlmsg_failure:
pr_debug("error during NLMSG_PUT\n");
alloc_failure:
pr_debug("Error building netlink message\n");
- spin_unlock_bh(&ulog_lock);
+ spin_unlock(&ulog_lock);
}
static unsigned int
diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c
index 0a07ae7..c517239 100644
--- a/net/ipv6/netfilter/ip6t_LOG.c
+++ b/net/ipv6/netfilter/ip6t_LOG.c
@@ -360,12 +360,12 @@ static void dump_packet(const struct nf_loginfo *info,
/* Max length: 15 "UID=4294967295 " */
if ((logflags & IP6T_LOG_UID) && recurse && skb->sk) {
- read_lock_bh(&skb->sk->sk_callback_lock);
+ read_lock(&skb->sk->sk_callback_lock);
if (skb->sk->sk_socket && skb->sk->sk_socket->file)
printk("UID=%u GID=%u ",
skb->sk->sk_socket->file->f_cred->fsuid,
skb->sk->sk_socket->file->f_cred->fsgid);
- read_unlock_bh(&skb->sk->sk_callback_lock);
+ read_unlock(&skb->sk->sk_callback_lock);
}
/* Max length: 16 "MARK=0xFFFFFFFF " */
@@ -445,7 +445,7 @@ ip6t_log_packet(u_int8_t pf,
if (!loginfo)
loginfo = &default_loginfo;
- spin_lock_bh(&log_lock);
+ spin_lock(&log_lock);
printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level,
prefix,
in ? in->name : "",
@@ -457,7 +457,7 @@ ip6t_log_packet(u_int8_t pf,
dump_packet(loginfo, skb, skb_network_offset(skb), 1);
printk("\n");
- spin_unlock_bh(&log_lock);
+ spin_unlock(&log_lock);
}
static unsigned int
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index de079ab..74a602b 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -87,10 +87,10 @@ xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par)
const struct xt_rateest_target_info *info = par->targinfo;
struct gnet_stats_basic_packed *stats = &info->est->bstats;
- spin_lock_bh(&info->est->lock);
+ spin_lock(&info->est->lock);
stats->bytes += skb->len;
stats->packets++;
- spin_unlock_bh(&info->est->lock);
+ spin_unlock(&info->est->lock);
return XT_CONTINUE;
}
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 5c5b6b9..6851b98 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -199,10 +199,10 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
addr.ip = iph->saddr;
}
- spin_lock_bh(&info->data->lock);
+ spin_lock(&info->data->lock);
connections = count_them(net, info->data, tuple_ptr, &addr,
&info->mask, par->family);
- spin_unlock_bh(&info->data->lock);
+ spin_unlock(&info->data->lock);
if (connections < 0) {
/* kmalloc failed, drop it entirely */
diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c
index b63d2a3..3472f97 100644
--- a/net/netfilter/xt_dccp.c
+++ b/net/netfilter/xt_dccp.c
@@ -52,7 +52,7 @@ dccp_find_option(u_int8_t option,
if (!optlen)
return false;
- spin_lock_bh(&dccp_buflock);
+ spin_lock(&dccp_buflock);
op = skb_header_pointer(skb, protoff + optoff, optlen, dccp_optbuf);
if (op == NULL) {
/* If we don't have the whole header, drop packet. */
@@ -61,7 +61,7 @@ dccp_find_option(u_int8_t option,
for (i = 0; i < optlen; ) {
if (op[i] == option) {
- spin_unlock_bh(&dccp_buflock);
+ spin_unlock(&dccp_buflock);
return true;
}
@@ -71,11 +71,11 @@ dccp_find_option(u_int8_t option,
i += op[i+1]?:1;
}
- spin_unlock_bh(&dccp_buflock);
+ spin_unlock(&dccp_buflock);
return false;
partial:
- spin_unlock_bh(&dccp_buflock);
+ spin_unlock(&dccp_buflock);
invalid:
*hotdrop = true;
return false;
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index 32b7a57..08894a4 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -71,7 +71,7 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
struct xt_limit_priv *priv = r->master;
unsigned long now = jiffies;
- spin_lock_bh(&limit_lock);
+ spin_lock(&limit_lock);
priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY;
if (priv->credit > r->credit_cap)
priv->credit = r->credit_cap;
@@ -79,11 +79,11 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (priv->credit >= r->cost) {
/* We're not limited. */
priv->credit -= r->cost;
- spin_unlock_bh(&limit_lock);
+ spin_unlock(&limit_lock);
return true;
}
- spin_unlock_bh(&limit_lock);
+ spin_unlock(&limit_lock);
return false;
}
diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c
index 70eb2b4..ba2042d 100644
--- a/net/netfilter/xt_quota.c
+++ b/net/netfilter/xt_quota.c
@@ -28,7 +28,7 @@ quota_mt(const struct sk_buff *skb, struct xt_action_param *par)
struct xt_quota_priv *priv = q->master;
bool ret = q->flags & XT_QUOTA_INVERT;
- spin_lock_bh(&priv->lock);
+ spin_lock(&priv->lock);
if (priv->quota >= skb->len) {
priv->quota -= skb->len;
ret = !ret;
@@ -36,7 +36,7 @@ quota_mt(const struct sk_buff *skb, struct xt_action_param *par)
/* we do not allow even small packets from now on */
priv->quota = 0;
}
- spin_unlock_bh(&priv->lock);
+ spin_unlock(&priv->lock);
return ret;
}
diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c
index 76a0831..d69a280 100644
--- a/net/netfilter/xt_rateest.c
+++ b/net/netfilter/xt_rateest.c
@@ -22,7 +22,7 @@ xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par)
u_int32_t bps1, bps2, pps1, pps2;
bool ret = true;
- spin_lock_bh(&info->est1->lock);
+ spin_lock(&info->est1->lock);
r = &info->est1->rstats;
if (info->flags & XT_RATEEST_MATCH_DELTA) {
bps1 = info->bps1 >= r->bps ? info->bps1 - r->bps : 0;
@@ -31,13 +31,13 @@ xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par)
bps1 = r->bps;
pps1 = r->pps;
}
- spin_unlock_bh(&info->est1->lock);
+ spin_unlock(&info->est1->lock);
if (info->flags & XT_RATEEST_MATCH_ABS) {
bps2 = info->bps2;
pps2 = info->pps2;
} else {
- spin_lock_bh(&info->est2->lock);
+ spin_lock(&info->est2->lock);
r = &info->est2->rstats;
if (info->flags & XT_RATEEST_MATCH_DELTA) {
bps2 = info->bps2 >= r->bps ? info->bps2 - r->bps : 0;
@@ -46,7 +46,7 @@ xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par)
bps2 = r->bps;
pps2 = r->pps;
}
- spin_unlock_bh(&info->est2->lock);
+ spin_unlock(&info->est2->lock);
}
switch (info->mode) {
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 76aec6a..5ddd90d 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -259,7 +259,7 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (par->out != NULL && skb->sk == NULL)
ttl++;
- spin_lock_bh(&recent_lock);
+ spin_lock(&recent_lock);
t = recent_table_lookup(recent_net, info->name);
e = recent_entry_lookup(t, &addr, par->family,
(info->check_set & XT_RECENT_TTL) ? ttl : 0);
@@ -302,7 +302,7 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
e->ttl = ttl;
}
out:
- spin_unlock_bh(&recent_lock);
+ spin_unlock(&recent_lock);
return ret;
}
^ permalink raw reply related
* [PATCH] netfilter: use NFPROTO_IPV4 instead of AF_INET
From: Changli Gao @ 2010-08-17 6:47 UTC (permalink / raw)
To: Patrick McHardy; +Cc: David S. Miller, netfilter-devel, netdev, Changli Gao
The field family of xt_target should be NFPROTO_IPV4, though NFPROTO_IPV4
and AF_INET are the same.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
---
net/netfilter/xt_TPROXY.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index c61294d..21bb2af 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -76,7 +76,7 @@ static int tproxy_tg_check(const struct xt_tgchk_param *par)
static struct xt_target tproxy_tg_reg __read_mostly = {
.name = "TPROXY",
- .family = AF_INET,
+ .family = NFPROTO_IPV4,
.table = "mangle",
.target = tproxy_tg,
.targetsize = sizeof(struct xt_tproxy_target_info),
^ permalink raw reply related
* Re: [PATCH] netfilter: don't disable BH again in BH disabled context
From: Eric Dumazet @ 2010-08-17 6:55 UTC (permalink / raw)
To: Changli Gao; +Cc: Patrick McHardy, David S. Miller, netfilter-devel, netdev
In-Reply-To: <1282027297-9998-1-git-send-email-xiaosuo@gmail.com>
Le mardi 17 août 2010 à 14:41 +0800, Changli Gao a écrit :
> All the matches and targets of iptables, ip6tables are in BH disabled
> context, since xt_info_rdlock_bh() disables BH.
>
Its a thing that might change in a future version. Not a hard fact.
You can probably change iptables to allow softirqs while processing
OUTPUT chains.
We had some attempts in the past to switch to RCU.
It failed at that time because of some RCU implementation details, but
with recent RCU changes, we might try again, and have a clean
implementation, allowing softirqs.
So your patch would need to be reverted.
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH resend] netfilter: nf_nat_core: don't check if the tuple is used if there is no other choice
From: Changli Gao @ 2010-08-17 7:21 UTC (permalink / raw)
To: Patrick McHardy; +Cc: David S. Miller, netfilter-devel, netdev, Changli Gao
Eliminate nf_nat_used_tuple() to save some CPU cycles when there is no other
choice.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
net/ipv4/netfilter/nf_nat_core.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 037a3a6..c370b21 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -262,11 +262,17 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
proto = __nf_nat_proto_find(orig_tuple->dst.protonum);
/* Only bother mapping if it's not already in range and unique */
- if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM) &&
- (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) ||
- proto->in_range(tuple, maniptype, &range->min, &range->max)) &&
- !nf_nat_used_tuple(tuple, ct))
- goto out;
+ if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
+ if (range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) {
+ if (proto->in_range(tuple, maniptype, &range->min,
+ &range->max) &&
+ (range->min.all == range->max.all ||
+ !nf_nat_used_tuple(tuple, ct)))
+ goto out;
+ } else if (!nf_nat_used_tuple(tuple, ct)) {
+ goto out;
+ }
+ }
/* Last change: get protocol to try to obtain unique tuple. */
proto->unique_tuple(tuple, range, maniptype, ct);
^ permalink raw reply related
* [PATCH v2 resend] nf_nat: no IP_NAT_RANGE_MAP_IPS flags when alloc_null_binding()
From: Changli Gao @ 2010-08-17 7:24 UTC (permalink / raw)
To: Patrick McHardy; +Cc: David S. Miller, netfilter-devel, netdev, Changli Gao
When alloc_null_binding(), no IP_NAT_RNAGE_MAP_IPS in flags means no IP address
translation is needed. It isn't necessary to specify the address explicitly.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
---
v2: Initialize range.flags only instead of the whole structure.
net/ipv4/netfilter/nf_nat_rule.c | 17 ++++++++---------
1 file changed, 8 insertions(+), 9 deletions(-)
diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c
index ebbd319..21c3042 100644
--- a/net/ipv4/netfilter/nf_nat_rule.c
+++ b/net/ipv4/netfilter/nf_nat_rule.c
@@ -106,16 +106,15 @@ alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
/* Force range to this IP; let proto decide mapping for
per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
- Use reply in case it's already been mangled (eg local packet).
*/
- __be32 ip
- = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
- ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip
- : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
- struct nf_nat_range range
- = { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } };
-
- pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, &ip);
+ struct nf_nat_range range;
+
+ range.flags = 0;
+ pr_debug("Allocating NULL binding for %p (%pI4)\n", ct,
+ HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ?
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip :
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
+
return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
}
^ permalink raw reply related
* [PATCH v2 resend] netfilter: ipt_REJECT can't send TCP reset
From: Changli Gao @ 2010-08-17 7:26 UTC (permalink / raw)
To: Patrick McHardy
Cc: David S. Miller, Alexey Kuznetsov, Pekka Savola (ipv6),
James Morris, Hideaki YOSHIFUJI, netfilter-devel, netdev,
Changli Gao
ip_route_me_harder can't create the route cache when the outdev is the same
with the indev for the skbs whichout a valid protocol set.
__mkroute_input functions has this check:
1998 if (skb->protocol != htons(ETH_P_IP)) {
1999 /* Not IP (i.e. ARP). Do not create route, if it is
2000 * invalid for proxy arp. DNAT routes are always valid.
2001 *
2002 * Proxy arp feature have been extended to allow, ARP
2003 * replies back to the same interface, to support
2004 * Private VLAN switch technologies. See arp.c.
2005 */
2006 if (out_dev == in_dev &&
2007 IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
2008 err = -EINVAL;
2009 goto cleanup;
2010 }
2011 }
This patch gives the new skb a valid protocol to bypass this check. In order
to make ipt_REJECT work with bridges, you also need to enable ip_forward.
This patch also fixes a regression. When we used skb_copy_expand(), we
didn't have this issue stated above, as the protocol was properly set.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
---
v2: updated changelog
net/ipv4/netfilter/ipt_REJECT.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index b254daf..43eec80 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook)
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
+ nskb->protocol = htons(ETH_P_IP);
if (ip_route_me_harder(nskb, addr_type))
goto free_nskb;
^ permalink raw reply related
* Re: [PATCH] netfilter: don't disable BH again in BH disabled context
From: Jan Engelhardt @ 2010-08-17 8:29 UTC (permalink / raw)
To: Changli Gao; +Cc: Patrick McHardy, David S. Miller, netfilter-devel, netdev
In-Reply-To: <1282027297-9998-1-git-send-email-xiaosuo@gmail.com>
On Tuesday 2010-08-17 08:41, Changli Gao wrote:
>All the matches and targets of iptables, ip6tables are in BH disabled
>context, since xt_info_rdlock_bh() disables BH.
Does it not nest automatically?
^ permalink raw reply
* Re: [PATCH 1/5] ptp: Added a brand new class driver for ptp clocks.
From: Richard Cochran @ 2010-08-17 8:32 UTC (permalink / raw)
To: Arnd Bergmann
Cc: linuxppc-dev, Rodolfo Giometti, netdev, devicetree-discuss,
linux-kernel, linux-arm-kernel, Krzysztof Halasa
In-Reply-To: <201008162159.39734.arnd@arndb.de>
On Mon, Aug 16, 2010 at 09:59:39PM +0200, Arnd Bergmann wrote:
> Why does it matter how long it takes to read the clock? I wasn't thinking
> of replacing the system clock with this, just exposing the additional
> clock as a new clockid_t value that can be accessed using the existing
> syscalls.
Okay, now I see. You are suggesting this:
clock_gettime(CLOCK_PTP, &ts);
clock_settime(CLOCK_PTP, &ts);
I like this. If there is agreement about it, I am happy to implement
the PTP stuff that way.
> Why did you not want to add syscalls? Adding ioctls instead of syscalls
> does not make the interface better, just less visible.
I bet that, had I posted patch set with new syscalls, someone would
have said, "You are adding new syscalls. Can't you just use a char
device instead!"
If you add syscalls and introduce CLOCK_PTP, then you add it to
everyone's kernel, even those people who never heard of PTP. A char
device has the advantage that can it be simply ignored. Also, a
syscall has got to have the right form from the very beginning. If the
next generation of PTP hardware looks very different, then it is not
that much of a crime to change an ioctl interface, provided it has
versioning.
Richard
^ permalink raw reply
* [PATCH RESEND 0/3] netfilter: xtables: inclusion of condition match and target
From: Luciano Coelho @ 2010-08-17 8:36 UTC (permalink / raw)
To: kaber; +Cc: netfilter-devel, netdev, jengelh, sameo, janne.ylalehto
Hi,
I'm resending these three patches now that the net-next is open for development
again. These patches include the xt_condition match and target.
Please integrate if everything is okay.
Cheers,
Luca.
Luciano Coelho (3):
netfilter: xtables: inclusion of xt_condition
netfilter: xt_condition: change the value from boolean to u32
netfilter: xt_condition: add condition target support
include/linux/netfilter/Kbuild | 1 +
include/linux/netfilter/xt_condition.h | 26 +++
net/netfilter/Kconfig | 11 +
net/netfilter/Makefile | 1 +
net/netfilter/xt_condition.c | 357 ++++++++++++++++++++++++++++++++
5 files changed, 396 insertions(+), 0 deletions(-)
create mode 100644 include/linux/netfilter/xt_condition.h
create mode 100644 net/netfilter/xt_condition.c
^ permalink raw reply
* [PATCH RESEND 2/3] netfilter: xt_condition: change the value from boolean to u32
From: Luciano Coelho @ 2010-08-17 8:36 UTC (permalink / raw)
To: kaber; +Cc: netfilter-devel, netdev, jengelh, sameo, janne.ylalehto
In-Reply-To: <1282034213-1829-1-git-send-email-luciano.coelho@nokia.com>
Previously the condition match was using boolean values for the condition,
which is a bit limited, so this patch changes the value to a u32.
This is not a problem at the moment, since only userspace can set the
condition and it can do more advanced checks before setting the value. But
when the condition target gets implemented, having a u32 value will make it
much more flexible.
Signed-off-by: Luciano Coelho <luciano.coelho@nokia.com>
---
include/linux/netfilter/xt_condition.h | 3 +-
net/netfilter/xt_condition.c | 54 +++++++++++++++++---------------
2 files changed, 31 insertions(+), 26 deletions(-)
diff --git a/include/linux/netfilter/xt_condition.h b/include/linux/netfilter/xt_condition.h
index 4faf3ca..c4fe899 100644
--- a/include/linux/netfilter/xt_condition.h
+++ b/include/linux/netfilter/xt_condition.h
@@ -4,8 +4,9 @@
#include <linux/types.h>
struct xt_condition_mtinfo {
- char name[31];
+ char name[27];
__u8 invert;
+ __u32 value;
/* Used internally by the kernel */
void *condvar __attribute__((aligned(8)));
diff --git a/net/netfilter/xt_condition.c b/net/netfilter/xt_condition.c
index a78d832..cc9ada9 100644
--- a/net/netfilter/xt_condition.c
+++ b/net/netfilter/xt_condition.c
@@ -48,7 +48,7 @@ struct condition_variable {
struct list_head list;
struct proc_dir_entry *status_proc;
unsigned int refcount;
- bool enabled;
+ u32 value;
};
struct condition_net {
@@ -71,32 +71,36 @@ static int condition_proc_read(char __user *buffer, char **start, off_t offset,
{
const struct condition_variable *var = data;
- buffer[0] = var->enabled ? '1' : '0';
- buffer[1] = '\n';
- if (length >= 2)
- *eof = true;
- return 2;
+ return snprintf(buffer, length, "%u\n", var->value);
}
-static int condition_proc_write(struct file *file, const char __user *buffer,
+static int condition_proc_write(struct file *file, const char __user *input,
unsigned long length, void *data)
{
struct condition_variable *var = data;
- char newval;
-
- if (length > 0) {
- if (get_user(newval, buffer) != 0)
- return -EFAULT;
- /* Match only on the first character */
- switch (newval) {
- case '0':
- var->enabled = false;
- break;
- case '1':
- var->enabled = true;
- break;
- }
- }
+ /* the longest possible string is MAX_UINT in octal */
+ char buf[sizeof("+037777777777")];
+ unsigned long long value;
+
+ if (length == 0)
+ return 0;
+
+ if (length > sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(buf, input, length) != 0)
+ return -EFAULT;
+
+ buf[length - 1] = '\0';
+
+ if (strict_strtoull(buf, 0, &value) != 0)
+ return -EINVAL;
+
+ if (value > (u32) value)
+ return -ERANGE;
+
+ var->value = value;
+
return length;
}
@@ -106,7 +110,7 @@ condition_mt(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_condition_mtinfo *info = par->matchinfo;
const struct condition_variable *var = info->condvar;
- return var->enabled ^ info->invert;
+ return (var->value == info->value) ^ info->invert;
}
static int condition_mt_check(const struct xt_mtchk_param *par)
@@ -156,7 +160,7 @@ static int condition_mt_check(const struct xt_mtchk_param *par)
}
var->refcount = 1;
- var->enabled = false;
+ var->value = 0;
var->status_proc->data = var;
var->status_proc->read_proc = condition_proc_read;
var->status_proc->write_proc = condition_proc_write;
@@ -190,7 +194,7 @@ static void condition_mt_destroy(const struct xt_mtdtor_param *par)
static struct xt_match condition_mt_reg __read_mostly = {
.name = "condition",
- .revision = 1,
+ .revision = 2,
.family = NFPROTO_UNSPEC,
.matchsize = sizeof(struct xt_condition_mtinfo),
.match = condition_mt,
--
1.7.0.4
^ permalink raw reply related
* [PATCH RESEND 3/3] netfilter: xt_condition: add condition target support
From: Luciano Coelho @ 2010-08-17 8:36 UTC (permalink / raw)
To: kaber; +Cc: netfilter-devel, netdev, jengelh, sameo, janne.ylalehto
In-Reply-To: <1282034213-1829-1-git-send-email-luciano.coelho@nokia.com>
This patch implements a condition target to the xt_condition module,
which let's the user set netfilter rules that change the variables
used by the condition match. Originally, the condition match only
allowed the variable to be changed via procfs. This new target makes
it easy to change the condition value depending on the rules set.
Signed-off-by: Luciano Coelho <luciano.coelho@nokia.com>
---
include/linux/netfilter/xt_condition.h | 13 ++-
net/netfilter/Kconfig | 19 ++--
net/netfilter/Makefile | 2 +-
net/netfilter/xt_condition.c | 194 +++++++++++++++++++++++---------
4 files changed, 165 insertions(+), 63 deletions(-)
diff --git a/include/linux/netfilter/xt_condition.h b/include/linux/netfilter/xt_condition.h
index c4fe899..946d43a 100644
--- a/include/linux/netfilter/xt_condition.h
+++ b/include/linux/netfilter/xt_condition.h
@@ -3,8 +3,10 @@
#include <linux/types.h>
+#define XT_CONDITION_MAX_NAME_SIZE 27
+
struct xt_condition_mtinfo {
- char name[27];
+ char name[XT_CONDITION_MAX_NAME_SIZE];
__u8 invert;
__u32 value;
@@ -12,4 +14,13 @@ struct xt_condition_mtinfo {
void *condvar __attribute__((aligned(8)));
};
+struct condition_tginfo {
+ char name[XT_CONDITION_MAX_NAME_SIZE];
+ __u8 padding;
+ __u32 value;
+
+ /* Used internally by the kernel */
+ void *condvar __attribute__((aligned(8)));
+};
+
#endif /* _XT_CONDITION_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 5044dd6..d9a17eb 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -310,6 +310,17 @@ config NETFILTER_XT_MARK
"Use netfilter MARK value as routing key") and can also be used by
other subsystems to change their behavior.
+config NETFILTER_XT_CONDITION
+ tristate '"condition" match and target support'
+ depends on NETFILTER_ADVANCED
+ depends on PROC_FS
+ ---help---
+ This option adds the "CONDITION" target and "condition" match.
+
+ It allows you to match rules against condition variables
+ stored in the /proc/net/nf_condition directory. It also allows
+ you to set the variables using the target.
+
config NETFILTER_XT_CONNMARK
tristate 'ctmark target and match support'
depends on NF_CONNTRACK
@@ -621,14 +632,6 @@ config NETFILTER_XT_MATCH_COMMENT
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
-config NETFILTER_XT_MATCH_CONDITION
- tristate '"condition" match support'
- depends on NETFILTER_ADVANCED
- depends on PROC_FS
- ---help---
- This option allows you to match firewall rules against condition
- variables stored in the /proc/net/nf_condition directory.
-
config NETFILTER_XT_MATCH_CONNBYTES
tristate '"connbytes" per-connection counter match support'
depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index bbf72bb..146a05f 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
# combos
obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
+obj-$(CONFIG_NETFILTER_XT_CONDITION) += xt_condition.o
# targets
obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o
@@ -67,7 +68,6 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o
# matches
obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
-obj-$(CONFIG_NETFILTER_XT_MATCH_CONDITION) += xt_condition.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o
diff --git a/net/netfilter/xt_condition.c b/net/netfilter/xt_condition.c
index cc9ada9..06205aa 100644
--- a/net/netfilter/xt_condition.c
+++ b/net/netfilter/xt_condition.c
@@ -2,15 +2,20 @@
* "condition" match extension for Xtables
*
* Description: This module allows firewall rules to match using
- * condition variables available through procfs.
+ * condition variables available through procfs. It also allows
+ * target rules to set the condition variable.
*
* Authors:
* Stephane Ouellette <ouellettes [at] videotron ca>, 2002-10-22
* Massimiliano Hofer <max [at] nucleus it>, 2006-05-15
+ * Luciano Coelho <luciano.coelho@nokia.com>, 2010-08-11
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License; either version 2
* or 3 of the License, as published by the Free Software Foundation.
+ *
+ * Portion Copyright 2010 Nokia Corporation and/or its subsidiary(-ies).
+ * File modified on 2010-08-11.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
@@ -33,7 +38,8 @@ static unsigned int condition_gid_perms = 0;
MODULE_AUTHOR("Stephane Ouellette <ouellettes@videotron.ca>");
MODULE_AUTHOR("Massimiliano Hofer <max@nucleus.it>");
MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
-MODULE_DESCRIPTION("Allows rules to match against condition variables");
+MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>");
+MODULE_DESCRIPTION("Allows rules to set and match condition variables");
MODULE_LICENSE("GPL");
module_param(condition_list_perms, uint, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(condition_list_perms, "default permissions on /proc/net/nf_condition/* files");
@@ -104,29 +110,11 @@ static int condition_proc_write(struct file *file, const char __user *input,
return length;
}
-static bool
-condition_mt(const struct sk_buff *skb, struct xt_action_param *par)
-{
- const struct xt_condition_mtinfo *info = par->matchinfo;
- const struct condition_variable *var = info->condvar;
-
- return (var->value == info->value) ^ info->invert;
-}
-
-static int condition_mt_check(const struct xt_mtchk_param *par)
+static struct
+condition_variable *xt_condition_insert(const char *name,
+ struct condition_net *cond_net)
{
- struct xt_condition_mtinfo *info = par->matchinfo;
struct condition_variable *var;
- struct condition_net *cond_net = condition_pernet(par->net);
-
- /* Forbid certain names */
- if (*info->name == '\0' || *info->name == '.' ||
- info->name[sizeof(info->name)-1] != '\0' ||
- memchr(info->name, '/', sizeof(info->name)) != NULL) {
- pr_info("name not allowed or too long: \"%.*s\"\n",
- (unsigned int)sizeof(info->name), info->name);
- return -EINVAL;
- }
/*
* Let's acquire the lock, check for the condition and add it
@@ -134,29 +122,24 @@ static int condition_mt_check(const struct xt_mtchk_param *par)
*/
mutex_lock(&proc_lock);
list_for_each_entry(var, &cond_net->list, list) {
- if (strcmp(info->name, var->status_proc->name) == 0) {
+ if (strcmp(name, var->status_proc->name) == 0) {
++var->refcount;
- mutex_unlock(&proc_lock);
- info->condvar = var;
- return 0;
+ goto out;
}
}
/* At this point, we need to allocate a new condition variable. */
var = kmalloc(sizeof(struct condition_variable), GFP_KERNEL);
- if (var == NULL) {
- mutex_unlock(&proc_lock);
- return -ENOMEM;
- }
+ if (var == NULL)
+ goto out;
/* Create the condition variable's proc file entry. */
- var->status_proc = create_proc_entry(info->name,
- condition_list_perms,
+ var->status_proc = create_proc_entry(name, condition_list_perms,
cond_net->proc_dir);
if (var->status_proc == NULL) {
kfree(var);
- mutex_unlock(&proc_lock);
- return -ENOMEM;
+ var = NULL;
+ goto out;
}
var->refcount = 1;
@@ -167,17 +150,14 @@ static int condition_mt_check(const struct xt_mtchk_param *par)
var->status_proc->uid = condition_uid_perms;
var->status_proc->gid = condition_gid_perms;
list_add(&var->list, &cond_net->list);
+out:
mutex_unlock(&proc_lock);
- info->condvar = var;
- return 0;
+ return var;
}
-static void condition_mt_destroy(const struct xt_mtdtor_param *par)
+static void xt_condition_put(struct condition_variable *var,
+ struct condition_net *cond_net)
{
- const struct xt_condition_mtinfo *info = par->matchinfo;
- struct condition_variable *var = info->condvar;
- struct condition_net *cond_net = condition_pernet(par->net);
-
mutex_lock(&proc_lock);
if (--var->refcount == 0) {
list_del(&var->list);
@@ -192,6 +172,106 @@ static void condition_mt_destroy(const struct xt_mtdtor_param *par)
mutex_unlock(&proc_lock);
}
+static bool
+condition_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_condition_mtinfo *info = par->matchinfo;
+ const struct condition_variable *var = info->condvar;
+
+ return (var->value == info->value) ^ info->invert;
+}
+
+static int condition_mt_check(const struct xt_mtchk_param *par)
+{
+ struct xt_condition_mtinfo *info = par->matchinfo;
+ struct condition_variable *var;
+ struct condition_net *cond_net = condition_pernet(par->net);
+
+ /* Forbid certain names */
+ if (*info->name == '\0' || *info->name == '.' ||
+ info->name[sizeof(info->name)-1] != '\0' ||
+ memchr(info->name, '/', sizeof(info->name)) != NULL) {
+ pr_info("name not allowed or too long: \"%.*s\"\n",
+ (unsigned int)sizeof(info->name), info->name);
+ return -EINVAL;
+ }
+
+ var = xt_condition_insert(info->name, cond_net);
+ if (var == NULL)
+ return -ENOMEM;
+
+ info->condvar = var;
+ return 0;
+}
+
+static void condition_mt_destroy(const struct xt_mtdtor_param *par)
+{
+ const struct xt_condition_mtinfo *info = par->matchinfo;
+ struct condition_net *cond_net = condition_pernet(par->net);
+
+ xt_condition_put(info->condvar, cond_net);
+}
+
+static unsigned int condition_tg_target(struct sk_buff *skb,
+ const struct xt_action_param *par)
+{
+ const struct condition_tginfo *info = par->targinfo;
+ struct condition_variable *var = info->condvar;
+
+ pr_debug("setting condition %s, value %d\n",
+ info->name, info->value);
+
+ var->value = info->value;
+
+ return XT_CONTINUE;
+}
+
+static int condition_tg_checkentry(const struct xt_tgchk_param *par)
+{
+ struct condition_tginfo *info = par->targinfo;
+ struct condition_variable *var;
+ struct condition_net *cond_net = condition_pernet(par->net);
+
+ pr_debug("checkentry %s\n", info->name);
+
+ /* Forbid certain names */
+ if (*info->name == '\0' || *info->name == '.' ||
+ info->name[sizeof(info->name)-1] != '\0' ||
+ memchr(info->name, '/', sizeof(info->name)) != NULL) {
+ pr_info("name not allowed or too long: \"%.*s\"\n",
+ (unsigned int)sizeof(info->name), info->name);
+ return -EINVAL;
+ }
+
+ var = xt_condition_insert(info->name, cond_net);
+ if (var == NULL)
+ return -ENOMEM;
+
+ info->condvar = var;
+ return 0;
+}
+
+static void condition_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ const struct condition_tginfo *info = par->targinfo;
+ struct condition_net *cond_net = condition_pernet(par->net);
+
+ pr_debug("destroy %s\n", info->name);
+
+ xt_condition_put(info->condvar, cond_net);
+}
+
+static struct xt_target condition_tg_reg __read_mostly = {
+ .name = "CONDITION",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .target = condition_tg_target,
+ .targetsize = sizeof(struct condition_tginfo),
+ .checkentry = condition_tg_checkentry,
+ .destroy = condition_tg_destroy,
+ .me = THIS_MODULE,
+};
+
static struct xt_match condition_mt_reg __read_mostly = {
.name = "condition",
.revision = 2,
@@ -205,7 +285,7 @@ static struct xt_match condition_mt_reg __read_mostly = {
static const char *const dir_name = "nf_condition";
-static int __net_init condnet_mt_init(struct net *net)
+static int __net_init condnet_init(struct net *net)
{
struct condition_net *cond_net = condition_pernet(net);
@@ -216,7 +296,7 @@ static int __net_init condnet_mt_init(struct net *net)
return (cond_net->proc_dir == NULL) ? -EACCES : 0;
}
-static void __net_exit condnet_mt_exit(struct net *net)
+static void __net_exit condnet_exit(struct net *net)
{
struct condition_net *cond_net = condition_pernet(net);
struct condition_variable *var, *tmp;
@@ -234,14 +314,14 @@ static void __net_exit condnet_mt_exit(struct net *net)
remove_proc_entry(dir_name, net->proc_net);
}
-static struct pernet_operations condition_mt_netops = {
- .init = condnet_mt_init,
- .exit = condnet_mt_exit,
+static struct pernet_operations condition_netops = {
+ .init = condnet_init,
+ .exit = condnet_exit,
.id = &condition_net_id,
.size = sizeof(struct condition_net),
};
-static int __init condition_mt_init(void)
+static int __init condition_init(void)
{
int ret;
@@ -250,8 +330,15 @@ static int __init condition_mt_init(void)
if (ret < 0)
return ret;
- ret = register_pernet_subsys(&condition_mt_netops);
+ ret = xt_register_target(&condition_tg_reg);
+ if (ret < 0) {
+ xt_unregister_match(&condition_mt_reg);
+ return ret;
+ }
+
+ ret = register_pernet_subsys(&condition_netops);
if (ret < 0) {
+ xt_unregister_target(&condition_tg_reg);
xt_unregister_match(&condition_mt_reg);
return ret;
}
@@ -259,11 +346,12 @@ static int __init condition_mt_init(void)
return 0;
}
-static void __exit condition_mt_exit(void)
+static void __exit condition_exit(void)
{
- unregister_pernet_subsys(&condition_mt_netops);
+ unregister_pernet_subsys(&condition_netops);
xt_unregister_match(&condition_mt_reg);
+ xt_unregister_target(&condition_tg_reg);
}
-module_init(condition_mt_init);
-module_exit(condition_mt_exit);
+module_init(condition_init);
+module_exit(condition_exit);
--
1.7.0.4
^ permalink raw reply related
* [PATCH RESEND 1/3] netfilter: xtables: inclusion of xt_condition
From: Luciano Coelho @ 2010-08-17 8:36 UTC (permalink / raw)
To: kaber; +Cc: netfilter-devel, netdev, jengelh, sameo, janne.ylalehto
In-Reply-To: <1282034213-1829-1-git-send-email-luciano.coelho@nokia.com>
xt_condition can be used by userspace to influence decisions in rules
by means of togglable variables without having to reload the entire
ruleset.
This is a respin of the module in Xtables-addons, with support for
multiple namespaces and other small improvements. Some of the changes
were made by Jan Engelhardt.
Cc: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Luciano Coelho <luciano.coelho@nokia.com>
---
include/linux/netfilter/Kbuild | 1 +
include/linux/netfilter/xt_condition.h | 14 ++
net/netfilter/Kconfig | 8 +
net/netfilter/Makefile | 1 +
net/netfilter/xt_condition.c | 265 ++++++++++++++++++++++++++++++++
5 files changed, 289 insertions(+), 0 deletions(-)
create mode 100644 include/linux/netfilter/xt_condition.h
create mode 100644 net/netfilter/xt_condition.c
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9d40eff..ef8425e 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -28,6 +28,7 @@ header-y += xt_TEE.h
header-y += xt_TPROXY.h
header-y += xt_cluster.h
header-y += xt_comment.h
+header-y += xt_condition.h
header-y += xt_connbytes.h
header-y += xt_connlimit.h
header-y += xt_connmark.h
diff --git a/include/linux/netfilter/xt_condition.h b/include/linux/netfilter/xt_condition.h
new file mode 100644
index 0000000..4faf3ca
--- /dev/null
+++ b/include/linux/netfilter/xt_condition.h
@@ -0,0 +1,14 @@
+#ifndef _XT_CONDITION_H
+#define _XT_CONDITION_H
+
+#include <linux/types.h>
+
+struct xt_condition_mtinfo {
+ char name[31];
+ __u8 invert;
+
+ /* Used internally by the kernel */
+ void *condvar __attribute__((aligned(8)));
+};
+
+#endif /* _XT_CONDITION_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 4328825..5044dd6 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -621,6 +621,14 @@ config NETFILTER_XT_MATCH_COMMENT
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+config NETFILTER_XT_MATCH_CONDITION
+ tristate '"condition" match support'
+ depends on NETFILTER_ADVANCED
+ depends on PROC_FS
+ ---help---
+ This option allows you to match firewall rules against condition
+ variables stored in the /proc/net/nf_condition directory.
+
config NETFILTER_XT_MATCH_CONNBYTES
tristate '"connbytes" per-connection counter match support'
depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 441050f..bbf72bb 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -67,6 +67,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o
# matches
obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_CONDITION) += xt_condition.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o
diff --git a/net/netfilter/xt_condition.c b/net/netfilter/xt_condition.c
new file mode 100644
index 0000000..a78d832
--- /dev/null
+++ b/net/netfilter/xt_condition.c
@@ -0,0 +1,265 @@
+/*
+ * "condition" match extension for Xtables
+ *
+ * Description: This module allows firewall rules to match using
+ * condition variables available through procfs.
+ *
+ * Authors:
+ * Stephane Ouellette <ouellettes [at] videotron ca>, 2002-10-22
+ * Massimiliano Hofer <max [at] nucleus it>, 2006-05-15
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License; either version 2
+ * or 3 of the License, as published by the Free Software Foundation.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/version.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_condition.h>
+#include <net/netns/generic.h>
+#include <asm/uaccess.h>
+
+/* Defaults, these can be overridden on the module command-line. */
+static unsigned int condition_list_perms = S_IRUGO | S_IWUSR;
+static unsigned int condition_uid_perms = 0;
+static unsigned int condition_gid_perms = 0;
+
+MODULE_AUTHOR("Stephane Ouellette <ouellettes@videotron.ca>");
+MODULE_AUTHOR("Massimiliano Hofer <max@nucleus.it>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
+MODULE_DESCRIPTION("Allows rules to match against condition variables");
+MODULE_LICENSE("GPL");
+module_param(condition_list_perms, uint, S_IRUSR | S_IWUSR);
+MODULE_PARM_DESC(condition_list_perms, "default permissions on /proc/net/nf_condition/* files");
+module_param(condition_uid_perms, uint, S_IRUSR | S_IWUSR);
+MODULE_PARM_DESC(condition_uid_perms, "default user owner of /proc/net/nf_condition/* files");
+module_param(condition_gid_perms, uint, S_IRUSR | S_IWUSR);
+MODULE_PARM_DESC(condition_gid_perms, "default group owner of /proc/net/nf_condition/* files");
+MODULE_ALIAS("ipt_condition");
+MODULE_ALIAS("ip6t_condition");
+
+struct condition_variable {
+ struct list_head list;
+ struct proc_dir_entry *status_proc;
+ unsigned int refcount;
+ bool enabled;
+};
+
+struct condition_net {
+ struct list_head list;
+ struct proc_dir_entry *proc_dir;
+};
+
+static int condition_net_id;
+static inline struct condition_net *condition_pernet(struct net *net)
+{
+ return net_generic(net, condition_net_id);
+}
+
+/* proc_lock is a user context only semaphore used for write access */
+/* to the conditions' list. */
+static DEFINE_MUTEX(proc_lock);
+
+static int condition_proc_read(char __user *buffer, char **start, off_t offset,
+ int length, int *eof, void *data)
+{
+ const struct condition_variable *var = data;
+
+ buffer[0] = var->enabled ? '1' : '0';
+ buffer[1] = '\n';
+ if (length >= 2)
+ *eof = true;
+ return 2;
+}
+
+static int condition_proc_write(struct file *file, const char __user *buffer,
+ unsigned long length, void *data)
+{
+ struct condition_variable *var = data;
+ char newval;
+
+ if (length > 0) {
+ if (get_user(newval, buffer) != 0)
+ return -EFAULT;
+ /* Match only on the first character */
+ switch (newval) {
+ case '0':
+ var->enabled = false;
+ break;
+ case '1':
+ var->enabled = true;
+ break;
+ }
+ }
+ return length;
+}
+
+static bool
+condition_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_condition_mtinfo *info = par->matchinfo;
+ const struct condition_variable *var = info->condvar;
+
+ return var->enabled ^ info->invert;
+}
+
+static int condition_mt_check(const struct xt_mtchk_param *par)
+{
+ struct xt_condition_mtinfo *info = par->matchinfo;
+ struct condition_variable *var;
+ struct condition_net *cond_net = condition_pernet(par->net);
+
+ /* Forbid certain names */
+ if (*info->name == '\0' || *info->name == '.' ||
+ info->name[sizeof(info->name)-1] != '\0' ||
+ memchr(info->name, '/', sizeof(info->name)) != NULL) {
+ pr_info("name not allowed or too long: \"%.*s\"\n",
+ (unsigned int)sizeof(info->name), info->name);
+ return -EINVAL;
+ }
+
+ /*
+ * Let's acquire the lock, check for the condition and add it
+ * or increase the reference counter.
+ */
+ mutex_lock(&proc_lock);
+ list_for_each_entry(var, &cond_net->list, list) {
+ if (strcmp(info->name, var->status_proc->name) == 0) {
+ ++var->refcount;
+ mutex_unlock(&proc_lock);
+ info->condvar = var;
+ return 0;
+ }
+ }
+
+ /* At this point, we need to allocate a new condition variable. */
+ var = kmalloc(sizeof(struct condition_variable), GFP_KERNEL);
+ if (var == NULL) {
+ mutex_unlock(&proc_lock);
+ return -ENOMEM;
+ }
+
+ /* Create the condition variable's proc file entry. */
+ var->status_proc = create_proc_entry(info->name,
+ condition_list_perms,
+ cond_net->proc_dir);
+ if (var->status_proc == NULL) {
+ kfree(var);
+ mutex_unlock(&proc_lock);
+ return -ENOMEM;
+ }
+
+ var->refcount = 1;
+ var->enabled = false;
+ var->status_proc->data = var;
+ var->status_proc->read_proc = condition_proc_read;
+ var->status_proc->write_proc = condition_proc_write;
+ var->status_proc->uid = condition_uid_perms;
+ var->status_proc->gid = condition_gid_perms;
+ list_add(&var->list, &cond_net->list);
+ mutex_unlock(&proc_lock);
+ info->condvar = var;
+ return 0;
+}
+
+static void condition_mt_destroy(const struct xt_mtdtor_param *par)
+{
+ const struct xt_condition_mtinfo *info = par->matchinfo;
+ struct condition_variable *var = info->condvar;
+ struct condition_net *cond_net = condition_pernet(par->net);
+
+ mutex_lock(&proc_lock);
+ if (--var->refcount == 0) {
+ list_del(&var->list);
+ /* status_proc may be null in case of ns exit */
+ if (var->status_proc)
+ remove_proc_entry(var->status_proc->name,
+ cond_net->proc_dir);
+ mutex_unlock(&proc_lock);
+ kfree(var);
+ return;
+ }
+ mutex_unlock(&proc_lock);
+}
+
+static struct xt_match condition_mt_reg __read_mostly = {
+ .name = "condition",
+ .revision = 1,
+ .family = NFPROTO_UNSPEC,
+ .matchsize = sizeof(struct xt_condition_mtinfo),
+ .match = condition_mt,
+ .checkentry = condition_mt_check,
+ .destroy = condition_mt_destroy,
+ .me = THIS_MODULE,
+};
+
+static const char *const dir_name = "nf_condition";
+
+static int __net_init condnet_mt_init(struct net *net)
+{
+ struct condition_net *cond_net = condition_pernet(net);
+
+ INIT_LIST_HEAD(&cond_net->list);
+
+ cond_net->proc_dir = proc_mkdir(dir_name, net->proc_net);
+
+ return (cond_net->proc_dir == NULL) ? -EACCES : 0;
+}
+
+static void __net_exit condnet_mt_exit(struct net *net)
+{
+ struct condition_net *cond_net = condition_pernet(net);
+ struct condition_variable *var, *tmp;
+
+ mutex_lock(&proc_lock);
+ list_for_each_entry_safe(var, tmp, &cond_net->list, list) {
+ remove_proc_entry(var->status_proc->name,
+ cond_net->proc_dir);
+ /* set to null so we don't double remove in mt_destroy */
+ var->status_proc = NULL;
+ }
+
+ mutex_unlock(&proc_lock);
+
+ remove_proc_entry(dir_name, net->proc_net);
+}
+
+static struct pernet_operations condition_mt_netops = {
+ .init = condnet_mt_init,
+ .exit = condnet_mt_exit,
+ .id = &condition_net_id,
+ .size = sizeof(struct condition_net),
+};
+
+static int __init condition_mt_init(void)
+{
+ int ret;
+
+ mutex_init(&proc_lock);
+ ret = xt_register_match(&condition_mt_reg);
+ if (ret < 0)
+ return ret;
+
+ ret = register_pernet_subsys(&condition_mt_netops);
+ if (ret < 0) {
+ xt_unregister_match(&condition_mt_reg);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void __exit condition_mt_exit(void)
+{
+ unregister_pernet_subsys(&condition_mt_netops);
+ xt_unregister_match(&condition_mt_reg);
+}
+
+module_init(condition_mt_init);
+module_exit(condition_mt_exit);
--
1.7.0.4
^ permalink raw reply related
* Re: [PATCH 17/42] drivers/net/irda: Adjust confusing if indentation
From: David Miller @ 2010-08-17 8:49 UTC (permalink / raw)
To: julia; +Cc: samuel, netdev, linux-kernel, kernel-janitors
In-Reply-To: <Pine.LNX.4.64.1008052221410.31692@ask.diku.dk>
Applied.
^ permalink raw reply
* IPsec: Why do pfkey_getspi and xfrm_alloc_userspi call xfrm_find_acq_byseq?
From: Christophe Gouault @ 2010-08-17 8:46 UTC (permalink / raw)
To: netdev
Dear netdev developers,
I would like to understand why the pfkey_getspi and xfrm_alloc_userspi
functions call xfrm_find_acq_byseq() and try to find an reuse an SA in
state XFRM_STATE_ACQ with the same sequence number and destination
address as the GETSPI request.
As far as I understand, SAs in state XFRM_STATE_ACQ can only be created
as a result of a user call to GETSPI or a kernel ACQUIRE message.
- GETSPI is invoked by an application in order to create a temporary SA
with a unique SPI, typically during an IKE negotiation, to create the
inbound SA of the pair. No later GETSPI will be done on this SA.
- An acquire message is triggered by the kernel and creates a temporary
outbound SA whose SPI will be chosen by the remote IKE peer.
No later GETSPI will be done on this SA.
In which case can GETSPI find and reuse an SA that matches the message
sequence number and destination address?
A second lookup is done just after, with xfrm_find_acq (this function
uses a hash table). Wouldn't this lookup find this SA too?
The call to xfrm_find_acq_byseq is quite costly (the whole SAD is looked
up every time GETSPI is called), so I'd like to understand what its
purpose is.
Thanks in advance,
Christophe
^ permalink raw reply
* Re: [PATCH 1/42] drivers/net/wan: Adjust confusing if indentation
From: David Miller @ 2010-08-17 8:49 UTC (permalink / raw)
To: julia; +Cc: khc, netdev, linux-kernel, kernel-janitors
In-Reply-To: <Pine.LNX.4.64.1008052216400.31692@ask.diku.dk>
Applied.
^ permalink raw reply
* Re: [PATCH 7/42] net/atm: Adjust confusing if indentation
From: David Miller @ 2010-08-17 8:49 UTC (permalink / raw)
To: julia; +Cc: linux-kernel, netdev, kernel-janitors
In-Reply-To: <Pine.LNX.4.64.1008052218400.31692@ask.diku.dk>
Applied.
^ permalink raw reply
* Re: [PATCH 41/42] net/decnet: Adjust confusing if indentation
From: David Miller @ 2010-08-17 8:49 UTC (permalink / raw)
To: julia; +Cc: linux-decnet-user, linux-kernel, netdev, kernel-janitors
In-Reply-To: <Pine.LNX.4.64.1008052229200.31692@ask.diku.dk>
Applied.
^ permalink raw reply
* Re: [PATCH 18/42] drivers/net: Adjust confusing if indentation
From: David Miller @ 2010-08-17 8:49 UTC (permalink / raw)
To: julia; +Cc: netdev, linux-kernel, kernel-janitors
In-Reply-To: <Pine.LNX.4.64.1008052222000.31692@ask.diku.dk>
Applied.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox