sprintf(name, "cf%s", tty->name);
dev = alloc_netdev(sizeof(*ser), name, caifdev_setup);
+ if (!dev)
+ return -ENOMEM;
+
ser = netdev_priv(dev);
ser->tty = tty_kref_get(tty);
ser->dev = dev;
* of counts that the SM entered the EEE LPI state. Clock 25MHz. Read only
* register. Reset on hard reset. */
#define MISC_REG_CPMU_LP_SM_ENT_CNT_P0 0xa8b8
+/* [RW 16] EEE LPI Entry Events Counter. A statistic counter with the number
+ * of counts that the SM entered the EEE LPI state. Clock 25MHz. Read only
+ * register. Reset on hard reset. */
+#define MISC_REG_CPMU_LP_SM_ENT_CNT_P1 0xa8bc
/* [RW 32] The following driver registers(1...16) represent 16 drivers and
32 clients. Each client can be controlled by one driver only. One in each
bit represent that this driver control the appropriate client (Ex: bit 5
pstats->host_port_stats_counter++;
- if (CHIP_IS_E3(bp))
- estats->eee_tx_lpi += REG_RD(bp,
- MISC_REG_CPMU_LP_SM_ENT_CNT_P0);
+ if (CHIP_IS_E3(bp)) {
+ u32 lpi_reg = BP_PORT(bp) ? MISC_REG_CPMU_LP_SM_ENT_CNT_P1
+ : MISC_REG_CPMU_LP_SM_ENT_CNT_P0;
+ estats->eee_tx_lpi += REG_RD(bp, lpi_reg);
+ }
if (!BP_NOMCP(bp)) {
u32 nig_timer_max =
if (!status) {
cfgs = (struct be_fat_conf_params *)(extfat_cmd.va +
sizeof(struct be_cmd_resp_hdr));
- for (i = 0; i < cfgs->num_modules; i++) {
- for (j = 0; j < cfgs->module[i].num_modes; j++) {
+ for (i = 0; i < le32_to_cpu(cfgs->num_modules); i++) {
+ u32 num_modes = le32_to_cpu(cfgs->module[i].num_modes);
+ for (j = 0; j < num_modes; j++) {
if (cfgs->module[i].trace_lvl[j].mode ==
MODE_UART)
cfgs->module[i].trace_lvl[j].dbg_lvl =
rxcp->pkt_type =
AMAP_GET_BITS(struct amap_eth_rx_compl_v1, cast_enc, compl);
rxcp->rss_hash =
- AMAP_GET_BITS(struct amap_eth_rx_compl_v1, rsshash, rxcp);
+ AMAP_GET_BITS(struct amap_eth_rx_compl_v1, rsshash, compl);
if (rxcp->vlanf) {
rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vtm,
compl);
rxcp->pkt_type =
AMAP_GET_BITS(struct amap_eth_rx_compl_v0, cast_enc, compl);
rxcp->rss_hash =
- AMAP_GET_BITS(struct amap_eth_rx_compl_v0, rsshash, rxcp);
+ AMAP_GET_BITS(struct amap_eth_rx_compl_v0, rsshash, compl);
if (rxcp->vlanf) {
rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vtm,
compl);
if (!status) {
cfgs = (struct be_fat_conf_params *)(extfat_cmd.va +
sizeof(struct be_cmd_resp_hdr));
- for (j = 0; j < cfgs->module[0].num_modes; j++) {
+ for (j = 0; j < le32_to_cpu(cfgs->module[0].num_modes); j++) {
if (cfgs->module[0].trace_lvl[j].mode == MODE_UART)
level = cfgs->module[0].trace_lvl[j].dbg_lvl;
}
pr_cont("\n");
if (netif_msg_pktdata(adapter) &&
- dma_unmap_len(tx_buffer, len) != 0)
+ tx_buffer->skb)
print_hex_dump(KERN_INFO, "",
DUMP_PREFIX_ADDRESS, 16, 1,
- phys_to_virt(dma_unmap_addr(tx_buffer,
- dma)),
+ tx_buffer->skb->data,
dma_unmap_len(tx_buffer, len),
true);
}
(u64)rx_buffer_info->dma,
rx_buffer_info->skb);
- if (netif_msg_pktdata(adapter)) {
+ if (netif_msg_pktdata(adapter) &&
+ rx_buffer_info->dma) {
print_hex_dump(KERN_INFO, "",
DUMP_PREFIX_ADDRESS, 16, 1,
- phys_to_virt(rx_buffer_info->dma),
+ page_address(rx_buffer_info->page) +
+ rx_buffer_info->page_offset,
ixgbe_rx_bufsz(rx_ring), true);
}
}
struct mlx4_priv *priv = mlx4_priv(dev);
if (readl(priv->catas_err.map)) {
- dump_err_buf(dev);
-
- mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
+ /* If the device is off-line, we cannot try to recover it */
+ if (pci_channel_offline(dev->pdev))
+ mod_timer(&priv->catas_err.timer,
+ round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
+ else {
+ dump_err_buf(dev);
+ mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
- if (internal_err_reset) {
- spin_lock(&catas_lock);
- list_add(&priv->catas_err.list, &catas_list);
- spin_unlock(&catas_lock);
+ if (internal_err_reset) {
+ spin_lock(&catas_lock);
+ list_add(&priv->catas_err.list, &catas_list);
+ spin_unlock(&catas_lock);
- queue_work(mlx4_wq, &catas_work);
+ queue_work(mlx4_wq, &catas_work);
+ }
}
} else
mod_timer(&priv->catas_err.timer,
list_for_each_entry_safe(priv, tmppriv, &tlist, catas_err.list) {
struct pci_dev *pdev = priv->dev.pdev;
+ /* If the device is off-line, we cannot reset it */
+ if (pci_channel_offline(pdev))
+ continue;
+
ret = mlx4_restart_one(priv->dev.pdev);
/* 'priv' now is not valid */
if (ret)
static int cmd_pending(struct mlx4_dev *dev)
{
- u32 status = readl(mlx4_priv(dev)->cmd.hcr + HCR_STATUS_OFFSET);
+ u32 status;
+
+ if (pci_channel_offline(dev->pdev))
+ return -EIO;
+
+ status = readl(mlx4_priv(dev)->cmd.hcr + HCR_STATUS_OFFSET);
return (status & swab32(1 << HCR_GO_BIT)) ||
(mlx4_priv(dev)->cmd.toggle ==
mutex_lock(&cmd->hcr_mutex);
+ if (pci_channel_offline(dev->pdev)) {
+ /*
+ * Device is going through error recovery
+ * and cannot accept commands.
+ */
+ ret = -EIO;
+ goto out;
+ }
+
end = jiffies;
if (event)
end += msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS);
while (cmd_pending(dev)) {
+ if (pci_channel_offline(dev->pdev)) {
+ /*
+ * Device is going through error recovery
+ * and cannot accept commands.
+ */
+ ret = -EIO;
+ goto out;
+ }
+
if (time_after_eq(jiffies, end)) {
mlx4_err(dev, "%s:cmd_pending failed\n", __func__);
goto out;
down(&priv->cmd.poll_sem);
+ if (pci_channel_offline(dev->pdev)) {
+ /*
+ * Device is going through error recovery
+ * and cannot accept commands.
+ */
+ err = -EIO;
+ goto out;
+ }
+
err = mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
in_modifier, op_modifier, op, CMD_POLL_TOKEN, 0);
if (err)
goto out;
end = msecs_to_jiffies(timeout) + jiffies;
- while (cmd_pending(dev) && time_before(jiffies, end))
+ while (cmd_pending(dev) && time_before(jiffies, end)) {
+ if (pci_channel_offline(dev->pdev)) {
+ /*
+ * Device is going through error recovery
+ * and cannot accept commands.
+ */
+ err = -EIO;
+ goto out;
+ }
+
cond_resched();
+ }
if (cmd_pending(dev)) {
err = -ETIMEDOUT;
int out_is_imm, u32 in_modifier, u8 op_modifier,
u16 op, unsigned long timeout, int native)
{
+ if (pci_channel_offline(dev->pdev))
+ return -EIO;
+
if (!mlx4_is_mfunc(dev) || (native && mlx4_is_master(dev))) {
if (mlx4_priv(dev)->cmd.use_events)
return mlx4_cmd_wait(dev, in_param, out_param,
filter->flow_id = flow_id;
- filter->id = priv->last_filter_id++;
+ filter->id = priv->last_filter_id++ % RPS_NO_FILTER;
list_add_tail(&filter->next, &priv->filters);
hlist_add_head(&filter->filter_chain,
void __iomem *owner;
u32 ret;
+ if (pci_channel_offline(dev->pdev))
+ return -EIO;
+
owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
MLX4_OWNER_SIZE);
if (!owner) {
{
void __iomem *owner;
+ if (pci_channel_offline(dev->pdev))
+ return;
+
owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
MLX4_OWNER_SIZE);
if (!owner) {
MODULE_DEVICE_TABLE(pci, mlx4_pci_table);
+static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
+ pci_channel_state_t state)
+{
+ mlx4_remove_one(pdev);
+
+ return state == pci_channel_io_perm_failure ?
+ PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
+{
+ int ret = __mlx4_init_one(pdev, NULL);
+
+ return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
+}
+
+static struct pci_error_handlers mlx4_err_handler = {
+ .error_detected = mlx4_pci_err_detected,
+ .slot_reset = mlx4_pci_slot_reset,
+};
+
static struct pci_driver mlx4_driver = {
.name = DRV_NAME,
.id_table = mlx4_pci_table,
.probe = mlx4_init_one,
- .remove = __devexit_p(mlx4_remove_one)
+ .remove = __devexit_p(mlx4_remove_one),
+ .err_handler = &mlx4_err_handler,
};
static int __init mlx4_verify_params(void)
hw->mac.link_duplex = ecmd->duplex;
hw->phy.autoneg_advertised = ecmd->advertising;
hw->mac.autoneg = ecmd->autoneg;
- pch_gbe_hal_phy_sw_reset(hw);
/* reset the link */
if (netif_running(adapter->netdev)) {
#include <linux/ptp_classify.h>
#endif
-#define DRV_VERSION "1.00"
+#define DRV_VERSION "1.01"
const char pch_driver_version[] = DRV_VERSION;
#define PCI_DEVICE_ID_INTEL_IOH1_GBE 0x8802 /* Pci device ID */
#define DSC_INIT16 0xC000
#define PCH_GBE_DMA_ALIGN 0
#define PCH_GBE_DMA_PADDING 2
-#define PCH_GBE_WATCHDOG_PERIOD (1 * HZ) /* watchdog time */
+#define PCH_GBE_WATCHDOG_PERIOD (5 * HZ) /* watchdog time */
#define PCH_GBE_COPYBREAK_DEFAULT 256
#define PCH_GBE_PCI_BAR 1
#define PCH_GBE_RESERVE_MEMORY 0x200000 /* 2MB */
struct sk_buff *skb;
unsigned int i;
unsigned int cleaned_count = 0;
- bool cleaned = true;
+ bool cleaned = false;
+ int unused, thresh;
pr_debug("next_to_clean : %d\n", tx_ring->next_to_clean);
pr_debug("gbec_status:0x%04x dma_status:0x%04x\n",
tx_desc->gbec_status, tx_desc->dma_status);
+ unused = PCH_GBE_DESC_UNUSED(tx_ring);
+ thresh = tx_ring->count - PCH_GBE_TX_WEIGHT;
+ if ((tx_desc->gbec_status == DSC_INIT16) && (unused < thresh))
+ { /* current marked clean, tx queue filling up, do extra clean */
+ int j, k;
+ if (unused < 8) { /* tx queue nearly full */
+ pr_debug("clean_tx: transmit queue warning (%x,%x) unused=%d\n",
+ tx_ring->next_to_clean,tx_ring->next_to_use,unused);
+ }
+
+ /* current marked clean, scan for more that need cleaning. */
+ k = i;
+ for (j = 0; j < PCH_GBE_TX_WEIGHT; j++)
+ {
+ tx_desc = PCH_GBE_TX_DESC(*tx_ring, k);
+ if (tx_desc->gbec_status != DSC_INIT16) break; /*found*/
+ if (++k >= tx_ring->count) k = 0; /*increment, wrap*/
+ }
+ if (j < PCH_GBE_TX_WEIGHT) {
+ pr_debug("clean_tx: unused=%d loops=%d found tx_desc[%x,%x:%x].gbec_status=%04x\n",
+ unused,j, i,k, tx_ring->next_to_use, tx_desc->gbec_status);
+ i = k; /*found one to clean, usu gbec_status==2000.*/
+ }
+ }
+
while ((tx_desc->gbec_status & DSC_INIT16) == 0x0000) {
pr_debug("gbec_status:0x%04x\n", tx_desc->gbec_status);
buffer_info = &tx_ring->buffer_info[i];
skb = buffer_info->skb;
+ cleaned = true;
if ((tx_desc->gbec_status & PCH_GBE_TXD_GMAC_STAT_ABT)) {
adapter->stats.tx_aborted_errors++;
}
pr_debug("called pch_gbe_unmap_and_free_tx_resource() %d count\n",
cleaned_count);
- /* Recover from running out of Tx resources in xmit_frame */
- spin_lock(&tx_ring->tx_lock);
- if (unlikely(cleaned && (netif_queue_stopped(adapter->netdev)))) {
- netif_wake_queue(adapter->netdev);
- adapter->stats.tx_restart_count++;
- pr_debug("Tx wake queue\n");
- }
+ if (cleaned_count > 0) { /*skip this if nothing cleaned*/
+ /* Recover from running out of Tx resources in xmit_frame */
+ spin_lock(&tx_ring->tx_lock);
+ if (unlikely(cleaned && (netif_queue_stopped(adapter->netdev))))
+ {
+ netif_wake_queue(adapter->netdev);
+ adapter->stats.tx_restart_count++;
+ pr_debug("Tx wake queue\n");
+ }
- tx_ring->next_to_clean = i;
+ tx_ring->next_to_clean = i;
- pr_debug("next_to_clean : %d\n", tx_ring->next_to_clean);
- spin_unlock(&tx_ring->tx_lock);
+ pr_debug("next_to_clean : %d\n", tx_ring->next_to_clean);
+ spin_unlock(&tx_ring->tx_lock);
+ }
return cleaned;
}
void pch_gbe_down(struct pch_gbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
+ struct pci_dev *pdev = adapter->pdev;
struct pch_gbe_rx_ring *rx_ring = adapter->rx_ring;
/* signal that we're down so the interrupt handler does not
netif_carrier_off(netdev);
netif_stop_queue(netdev);
- pch_gbe_reset(adapter);
+ if ((pdev->error_state) && (pdev->error_state != pci_channel_io_normal))
+ pch_gbe_reset(adapter);
pch_gbe_clean_tx_ring(adapter, adapter->tx_ring);
pch_gbe_clean_rx_ring(adapter, adapter->rx_ring);
struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring;
unsigned long flags;
- if (unlikely(skb->len > (adapter->hw.mac.max_frame_size - 4))) {
- pr_err("Transfer length Error: skb len: %d > max: %d\n",
- skb->len, adapter->hw.mac.max_frame_size);
- dev_kfree_skb_any(skb);
- adapter->stats.tx_length_errors++;
- return NETDEV_TX_OK;
- }
if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) {
/* Collision - tell upper layer to requeue */
return NETDEV_TX_LOCKED;
pch_gbe_clean_rx(adapter, adapter->rx_ring, &work_done, budget);
cleaned = pch_gbe_clean_tx(adapter, adapter->tx_ring);
- if (!cleaned)
+ if (cleaned)
work_done = budget;
/* If no Tx and not enough Rx work done,
* exit the polling mode
{
int ret;
+ pr_info("EG20T PCH Gigabit Ethernet Driver - version %s\n",DRV_VERSION);
ret = pci_register_driver(&pch_gbe_driver);
if (copybreak != PCH_GBE_COPYBREAK_DEFAULT) {
if (copybreak == 0) {
config NET_VENDOR_WIZNET
bool "WIZnet devices"
+ depends on HAS_IOMEM
default y
---help---
If you have a network (Ethernet) card belonging to this class, say Y
struct work_struct work;
};
-
+#define RING_SIZE_MIN 64
static int ring_size = 128;
module_param(ring_size, int, S_IRUGO);
MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
static int __init netvsc_drv_init(void)
{
+ if (ring_size < RING_SIZE_MIN) {
+ ring_size = RING_SIZE_MIN;
+ pr_info("Increased ring_size to %d (min allowed)\n",
+ ring_size);
+ }
return vmbus_driver_register(&netvsc_drv);
}
/* Send the rndis initialization message */
ret = rndis_filter_init_device(rndis_device);
if (ret != 0) {
- /*
- * TODO: If rndis init failed, we will need to shut down the
- * channel
- */
+ rndis_filter_device_remove(dev);
+ return ret;
}
/* Get the mac address */
ret = rndis_filter_query_device_mac(rndis_device);
if (ret != 0) {
- /*
- * TODO: shutdown rndis device and the channel
- */
+ rndis_filter_device_remove(dev);
+ return ret;
}
memcpy(device_info->mac_adr, rndis_device->hw_mac_adr, ETH_ALEN);
{
struct team *team = netdev_priv(dev);
struct team_port *port;
- int err;
+ int err = 0;
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
static void cdc_ncm_txpath_bh(unsigned long param);
static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx);
static enum hrtimer_restart cdc_ncm_tx_timer_cb(struct hrtimer *hr_timer);
-static const struct driver_info cdc_ncm_info;
static struct usb_driver cdc_ncm_driver;
-static const struct ethtool_ops cdc_ncm_ethtool_ops;
-
-static const struct usb_device_id cdc_devs[] = {
- { USB_INTERFACE_INFO(USB_CLASS_COMM,
- USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE),
- .driver_info = (unsigned long)&cdc_ncm_info,
- },
- {
- },
-};
-
-MODULE_DEVICE_TABLE(usb, cdc_devs);
static void
cdc_ncm_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info)
kfree(ctx);
}
+static const struct ethtool_ops cdc_ncm_ethtool_ops = {
+ .get_drvinfo = cdc_ncm_get_drvinfo,
+ .get_link = usbnet_get_link,
+ .get_msglevel = usbnet_get_msglevel,
+ .set_msglevel = usbnet_set_msglevel,
+ .get_settings = usbnet_get_settings,
+ .set_settings = usbnet_set_settings,
+ .nway_reset = usbnet_nway_reset,
+};
+
static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
{
struct cdc_ncm_ctx *ctx;
.tx_fixup = cdc_ncm_tx_fixup,
};
+/* Same as cdc_ncm_info, but with FLAG_WWAN */
+static const struct driver_info wwan_info = {
+ .description = "Mobile Broadband Network Device",
+ .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
+ | FLAG_WWAN,
+ .bind = cdc_ncm_bind,
+ .unbind = cdc_ncm_unbind,
+ .check_connect = cdc_ncm_check_connect,
+ .manage_power = cdc_ncm_manage_power,
+ .status = cdc_ncm_status,
+ .rx_fixup = cdc_ncm_rx_fixup,
+ .tx_fixup = cdc_ncm_tx_fixup,
+};
+
+static const struct usb_device_id cdc_devs[] = {
+ /* Ericsson MBM devices like F5521gw */
+ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO
+ | USB_DEVICE_ID_MATCH_VENDOR,
+ .idVendor = 0x0bdb,
+ .bInterfaceClass = USB_CLASS_COMM,
+ .bInterfaceSubClass = USB_CDC_SUBCLASS_NCM,
+ .bInterfaceProtocol = USB_CDC_PROTO_NONE,
+ .driver_info = (unsigned long) &wwan_info,
+ },
+
+ /* Generic CDC-NCM devices */
+ { USB_INTERFACE_INFO(USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&cdc_ncm_info,
+ },
+ {
+ },
+};
+MODULE_DEVICE_TABLE(usb, cdc_devs);
+
static struct usb_driver cdc_ncm_driver = {
.name = "cdc_ncm",
.id_table = cdc_devs,
.disable_hub_initiated_lpm = 1,
};
-static const struct ethtool_ops cdc_ncm_ethtool_ops = {
- .get_drvinfo = cdc_ncm_get_drvinfo,
- .get_link = usbnet_get_link,
- .get_msglevel = usbnet_get_msglevel,
- .set_msglevel = usbnet_set_msglevel,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
- .nway_reset = usbnet_nway_reset,
-};
-
module_usb_driver(cdc_ncm_driver);
MODULE_AUTHOR("Hans Petter Selasky");
.attrs = netiucv_stat_attrs,
};
-static int netiucv_add_files(struct device *dev)
-{
- int ret;
-
- IUCV_DBF_TEXT(trace, 3, __func__);
- ret = sysfs_create_group(&dev->kobj, &netiucv_attr_group);
- if (ret)
- return ret;
- ret = sysfs_create_group(&dev->kobj, &netiucv_stat_attr_group);
- if (ret)
- sysfs_remove_group(&dev->kobj, &netiucv_attr_group);
- return ret;
-}
-
-static void netiucv_remove_files(struct device *dev)
-{
- IUCV_DBF_TEXT(trace, 3, __func__);
- sysfs_remove_group(&dev->kobj, &netiucv_stat_attr_group);
- sysfs_remove_group(&dev->kobj, &netiucv_attr_group);
-}
+static const struct attribute_group *netiucv_attr_groups[] = {
+ &netiucv_stat_attr_group,
+ &netiucv_attr_group,
+ NULL,
+};
static int netiucv_register_device(struct net_device *ndev)
{
dev_set_name(dev, "net%s", ndev->name);
dev->bus = &iucv_bus;
dev->parent = iucv_root;
+ dev->groups = netiucv_attr_groups;
/*
* The release function could be called after the
* module has been unloaded. It's _only_ task is to
put_device(dev);
return ret;
}
- ret = netiucv_add_files(dev);
- if (ret)
- goto out_unreg;
priv->dev = dev;
dev_set_drvdata(dev, priv);
return 0;
-
-out_unreg:
- device_unregister(dev);
- return ret;
}
static void netiucv_unregister_device(struct device *dev)
{
IUCV_DBF_TEXT(trace, 3, __func__);
- netiucv_remove_files(dev);
device_unregister(dev);
}
QETH_CARD_TEXT(card, 4, "frvaddr4");
netdev = __vlan_find_dev_deep(card->dev, vid);
+ if (!netdev)
+ return;
in_dev = in_dev_get(netdev);
if (!in_dev)
return;
QETH_CARD_TEXT(card, 4, "frvaddr6");
netdev = __vlan_find_dev_deep(card->dev, vid);
+ if (!netdev)
+ return;
in6_dev = in6_dev_get(netdev);
if (!in6_dev)
return;
const __be16 sport,
const __be16 dport)
{
- struct sock *sk;
+ struct sock *sk = skb_steal_sock(skb);
- if (unlikely(sk = skb_steal_sock(skb)))
+ if (sk)
return sk;
- else return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
- &ipv6_hdr(skb)->saddr, sport,
- &ipv6_hdr(skb)->daddr, ntohs(dport),
- inet6_iif(skb));
+
+ return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
+ &ipv6_hdr(skb)->saddr, sport,
+ &ipv6_hdr(skb)->daddr, ntohs(dport),
+ inet6_iif(skb));
}
extern struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
#if IS_ENABLED(CONFIG_IPV6)
struct inet6_protocol {
+ void (*early_demux)(struct sk_buff *skb);
+
int (*handler)(struct sk_buff *skb);
void (*err_handler)(struct sk_buff *skb,
#include <net/inet_sock.h>
#include <linux/in_route.h>
#include <linux/rtnetlink.h>
+#include <linux/rcupdate.h>
#include <linux/route.h>
#include <linux/ip.h>
#include <linux/cache.h>
return ip_route_output_key(net, fl4);
}
-extern int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin);
+extern int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
+ u8 tos, struct net_device *devin);
+
+static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
+ u8 tos, struct net_device *devin)
+{
+ int err;
+
+ rcu_read_lock();
+ err = ip_route_input_noref(skb, dst, src, tos, devin);
+ if (!err)
+ skb_dst_force(skb);
+ rcu_read_unlock();
+
+ return err;
+}
extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
int oif, u32 mark, u8 protocol, int flow_flags);
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
- ip_route_input(skb, tip, sip, 0, dev) == 0) {
+ ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
if (nexthop_nh->nh_exceptions)
free_nh_exceptions(nexthop_nh);
if (nexthop_nh->nh_rth_output)
- dst_release(&nexthop_nh->nh_rth_output->dst);
+ dst_free(&nexthop_nh->nh_rth_output->dst);
if (nexthop_nh->nh_rth_input)
- dst_release(&nexthop_nh->nh_rth_input->dst);
+ dst_free(&nexthop_nh->nh_rth_input->dst);
} endfor_nexthops(fi);
release_net(fi->fib_net);
/* skb dst is stale, drop it, and perform route lookup again */
skb_dst_drop(head);
iph = ip_hdr(head);
- err = ip_route_input(head, iph->daddr, iph->saddr,
- iph->tos, head->dev);
+ err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+ iph->tos, head->dev);
if (err)
goto out_rcu_unlock;
}
int sysctl_ip_early_demux __read_mostly = 1;
+EXPORT_SYMBOL(sysctl_ip_early_demux);
static int ip_rcv_finish(struct sk_buff *skb)
{
rcu_read_lock();
ipprot = rcu_dereference(inet_protos[protocol]);
- if (ipprot && ipprot->early_demux)
+ if (ipprot && ipprot->early_demux) {
ipprot->early_demux(skb);
+ /* must reload iph, skb->head might have changed */
+ iph = ip_hdr(skb);
+ }
rcu_read_unlock();
}
* how the packet travels inside Linux networking.
*/
if (!skb_dst(skb)) {
- int err = ip_route_input(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev);
+ int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EXDEV)
NET_INC_STATS_BH(dev_net(skb->dev),
}
#endif /* CONFIG_PROC_FS */
-static inline int rt_is_expired(struct rtable *rth)
+static inline bool rt_is_expired(const struct rtable *rth)
{
return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
}
fnhe->fnhe_stamp = jiffies;
}
-static inline void rt_release_rcu(struct rcu_head *head)
+static inline void rt_free(struct rtable *rt)
{
- struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
- dst_release(dst);
+ call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
}
static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
prev = cmpxchg(p, orig, rt);
if (prev == orig) {
- dst_clone(&rt->dst);
if (orig)
- call_rcu_bh(&orig->dst.rcu_head, rt_release_rcu);
+ rt_free(orig);
+ } else {
+ /* Routes we intend to cache in the FIB nexthop have
+ * the DST_NOCACHE bit clear. However, if we are
+ * unsuccessful at storing this route into the cache
+ * we really need to set it.
+ */
+ rt->dst.flags |= DST_NOCACHE;
}
}
-static bool rt_cache_valid(struct rtable *rt)
+static bool rt_cache_valid(const struct rtable *rt)
{
- return (rt && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK);
+ return rt &&
+ rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+ !rt_is_expired(rt);
}
static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
- if (!(rt->dst.flags & DST_HOST))
+ if (!(rt->dst.flags & DST_NOCACHE))
rt_cache_route(nh, rt);
}
bool nopolicy, bool noxfrm, bool will_cache)
{
return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
- (will_cache ? 0 : DST_HOST) | DST_NOCACHE |
+ (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) |
(nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0));
}
static int __mkroute_input(struct sk_buff *skb,
const struct fib_result *res,
struct in_device *in_dev,
- __be32 daddr, __be32 saddr, u32 tos,
- struct rtable **result)
+ __be32 daddr, __be32 saddr, u32 tos)
{
struct rtable *rth;
int err;
if (!itag) {
rth = FIB_RES_NH(*res).nh_rth_input;
if (rt_cache_valid(rth)) {
- dst_hold(&rth->dst);
+ skb_dst_set_noref(skb, &rth->dst);
goto out;
}
do_cache = true;
rth->dst.output = ip_output;
rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag);
+ skb_dst_set(skb, &rth->dst);
out:
- *result = rth;
err = 0;
cleanup:
return err;
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos)
{
- struct rtable *rth = NULL;
- int err;
-
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1)
fib_select_multipath(res);
#endif
/* create a routing cache entry */
- err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth);
- if (err)
- return err;
-
- skb_dst_set(skb, &rth->dst);
- return 0;
+ return __mkroute_input(skb, res, in_dev, daddr, saddr, tos);
}
/*
if (!itag) {
rth = FIB_RES_NH(res).nh_rth_input;
if (rt_cache_valid(rth)) {
- dst_hold(&rth->dst);
- goto set_and_out;
+ skb_dst_set_noref(skb, &rth->dst);
+ err = 0;
+ goto out;
}
do_cache = true;
}
}
if (do_cache)
rt_cache_route(&FIB_RES_NH(res), rth);
-set_and_out:
skb_dst_set(skb, &rth->dst);
err = 0;
goto out;
goto out;
}
-int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
- u8 tos, struct net_device *dev)
+int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev)
{
int res;
rcu_read_unlock();
return res;
}
-EXPORT_SYMBOL(ip_route_input);
+EXPORT_SYMBOL(ip_route_input_noref);
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
struct net *net = dev_net(skb->dev);
const struct iphdr *iph;
const struct tcphdr *th;
- struct net_device *dev;
struct sock *sk;
if (skb->pkt_type != PACKET_HOST)
if (th->doff < sizeof(struct tcphdr) / 4)
return;
- if (!pskb_may_pull(skb, ip_hdrlen(skb) + th->doff * 4))
- return;
-
- dev = skb->dev;
sk = __inet_lookup_established(net, &tcp_hashinfo,
iph->saddr, th->source,
iph->daddr, ntohs(th->dest),
- dev->ifindex);
+ skb->skb_iif);
if (sk) {
skb->sk = sk;
skb->destructor = sock_edemux;
if (dst)
dst = dst_check(dst, 0);
if (dst &&
- icsk->rx_dst_ifindex == dev->ifindex)
+ icsk->rx_dst_ifindex == skb->skb_iif)
skb_dst_set_noref(skb, dst);
}
}
if (skb_dst(skb) == NULL) {
const struct iphdr *iph = ip_hdr(skb);
- if (ip_route_input(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev))
+ if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev))
goto drop;
}
return dst_input(skb);
-inline int ip6_rcv_finish( struct sk_buff *skb)
+int ip6_rcv_finish(struct sk_buff *skb)
{
- if (skb_dst(skb) == NULL)
+ if (sysctl_ip_early_demux && !skb_dst(skb)) {
+ const struct inet6_protocol *ipprot;
+
+ rcu_read_lock();
+ ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
+ if (ipprot && ipprot->early_demux)
+ ipprot->early_demux(skb);
+ rcu_read_unlock();
+ }
+ if (!skb_dst(skb))
ip6_route_input(skb);
return dst_input(skb);
goto discard_it;
}
+static void tcp_v6_early_demux(struct sk_buff *skb)
+{
+ const struct ipv6hdr *hdr;
+ const struct tcphdr *th;
+ struct sock *sk;
+
+ if (skb->pkt_type != PACKET_HOST)
+ return;
+
+ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
+ return;
+
+ hdr = ipv6_hdr(skb);
+ th = tcp_hdr(skb);
+
+ if (th->doff < sizeof(struct tcphdr) / 4)
+ return;
+
+ sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
+ &hdr->saddr, th->source,
+ &hdr->daddr, ntohs(th->dest),
+ inet6_iif(skb));
+ if (sk) {
+ skb->sk = sk;
+ skb->destructor = sock_edemux;
+ if (sk->sk_state != TCP_TIME_WAIT) {
+ struct dst_entry *dst = sk->sk_rx_dst;
+ struct inet_sock *icsk = inet_sk(sk);
+ if (dst)
+ dst = dst_check(dst, 0);
+ if (dst &&
+ icsk->rx_dst_ifindex == inet6_iif(skb))
+ skb_dst_set_noref(skb, dst);
+ }
+ }
+}
+
static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp6_timewait_sock),
.twsk_unique = tcp_twsk_unique,
};
static const struct inet6_protocol tcpv6_protocol = {
+ .early_demux = tcp_v6_early_demux,
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.gso_send_check = tcp_v6_gso_send_check,
* successfully, add it to the interface list.
*/
- if (dev->name == NULL) {
- err = -EINVAL;
- } else {
+#ifdef WANDEBUG
+ printk(KERN_INFO "%s: registering interface %s...\n",
+ wanrouter_modname, dev->name);
+#endif
- #ifdef WANDEBUG
- printk(KERN_INFO "%s: registering interface %s...\n",
- wanrouter_modname, dev->name);
- #endif
-
- err = register_netdev(dev);
- if (!err) {
- struct net_device *slave = NULL;
- unsigned long smp_flags=0;
-
- lock_adapter_irq(&wandev->lock, &smp_flags);
-
- if (wandev->dev == NULL) {
- wandev->dev = dev;
- } else {
- for (slave=wandev->dev;
- DEV_TO_SLAVE(slave);
- slave = DEV_TO_SLAVE(slave))
- DEV_TO_SLAVE(slave) = dev;
- }
- ++wandev->ndev;
-
- unlock_adapter_irq(&wandev->lock, &smp_flags);
- err = 0; /* done !!! */
- goto out;
+ err = register_netdev(dev);
+ if (!err) {
+ struct net_device *slave = NULL;
+ unsigned long smp_flags=0;
+
+ lock_adapter_irq(&wandev->lock, &smp_flags);
+
+ if (wandev->dev == NULL) {
+ wandev->dev = dev;
+ } else {
+ for (slave=wandev->dev;
+ DEV_TO_SLAVE(slave);
+ slave = DEV_TO_SLAVE(slave))
+ DEV_TO_SLAVE(slave) = dev;
}
+ ++wandev->ndev;
+
+ unlock_adapter_irq(&wandev->lock, &smp_flags);
+ err = 0; /* done !!! */
+ goto out;
}
if (wandev->del_if)
wandev->del_if(wandev, dev);