diff options
61 files changed, 355 insertions, 371 deletions
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 1983adc..a7568c3 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3498,7 +3498,8 @@ out: } static const struct ibnl_client_cbs cma_cb_table[] = { - [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats }, + [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats, + .module = THIS_MODULE }, }; static int __init cma_init(void) diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index fe10a94..da06abd 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -154,6 +154,7 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { struct netlink_dump_control c = { .dump = client->cb_table[op].dump, + .module = client->cb_table[op].module, }; return netlink_dump_start(nls, skb, nlh, &c); } diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 64d0d9c..3491d43 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1845,6 +1845,7 @@ static int __devinit amd8111e_probe_one(struct pci_dev *pdev, if((pm_cap = pci_find_capability(pdev, PCI_CAP_ID_PM))==0){ printk(KERN_ERR "amd8111e: No Power Management capability, " "exiting.\n"); + err = -ENODEV; goto err_free_reg; } @@ -1852,6 +1853,7 @@ static int __devinit amd8111e_probe_one(struct pci_dev *pdev, if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) < 0) { printk(KERN_ERR "amd8111e: DMA not supported," "exiting.\n"); + err = -ENODEV; goto err_free_reg; } diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 397596b..f195acf 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -1174,8 +1174,10 @@ static int __devinit au1000_probe(struct platform_device *pdev) snprintf(aup->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", pdev->name, aup->mac_id); aup->mii_bus->irq = kmalloc(sizeof(int)*PHY_MAX_ADDR, GFP_KERNEL); - if (aup->mii_bus->irq == NULL) + if (aup->mii_bus->irq == NULL) { + err = -ENOMEM; goto err_out; + } for (i = 0; i < PHY_MAX_ADDR; ++i) aup->mii_bus->irq[i] = PHY_POLL; @@ -1190,7 +1192,8 @@ static int __devinit au1000_probe(struct platform_device *pdev) goto err_mdiobus_reg; } - if (au1000_mii_probe(dev) != 0) + err = au1000_mii_probe(dev); + if (err != 0) goto err_out; pDBfree = NULL; @@ -1205,6 +1208,7 @@ static int __devinit au1000_probe(struct platform_device *pdev) } aup->pDBfree = pDBfree; + err = -ENODEV; for (i = 0; i < NUM_RX_DMA; i++) { pDB = au1000_GetFreeDB(aup); if (!pDB) @@ -1213,6 +1217,8 @@ static int __devinit au1000_probe(struct platform_device *pdev) aup->rx_dma_ring[i]->buff_stat = (unsigned)pDB->dma_addr; aup->rx_db_inuse[i] = pDB; } + + err = -ENODEV; for (i = 0; i < NUM_TX_DMA; i++) { pDB = au1000_GetFreeDB(aup); if (!pDB) diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index 2b4b4f5..16814b3 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -375,7 +375,6 @@ struct xgmac_priv { unsigned int tx_tail; void __iomem *base; - struct sk_buff_head rx_recycle; unsigned int dma_buf_sz; dma_addr_t dma_rx_phy; dma_addr_t dma_tx_phy; @@ -672,9 +671,7 @@ static void xgmac_rx_refill(struct xgmac_priv *priv) p = priv->dma_rx + entry; if (priv->rx_skbuff[entry] == NULL) { - skb = __skb_dequeue(&priv->rx_recycle); - if (skb == NULL) - skb = netdev_alloc_skb(priv->dev, priv->dma_buf_sz); + skb = netdev_alloc_skb(priv->dev, priv->dma_buf_sz); if (unlikely(skb == NULL)) break; @@ -887,17 +884,7 @@ static void xgmac_tx_complete(struct xgmac_priv *priv) desc_get_buf_len(p), DMA_TO_DEVICE); } - /* - * If there's room in the queue (limit it to size) - * we add this skb back into the pool, - * if it's the right size. - */ - if ((skb_queue_len(&priv->rx_recycle) < - DMA_RX_RING_SZ) && - skb_recycle_check(skb, priv->dma_buf_sz)) - __skb_queue_head(&priv->rx_recycle, skb); - else - dev_kfree_skb(skb); + dev_kfree_skb(skb); } if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) > @@ -1016,7 +1003,6 @@ static int xgmac_open(struct net_device *dev) dev->dev_addr); } - skb_queue_head_init(&priv->rx_recycle); memset(&priv->xstats, 0, sizeof(struct xgmac_extra_stats)); /* Initialize the XGMAC and descriptors */ @@ -1053,7 +1039,6 @@ static int xgmac_stop(struct net_device *dev) napi_disable(&priv->napi); writel(0, priv->base + XGMAC_DMA_INTR_ENA); - skb_queue_purge(&priv->rx_recycle); /* Disable the MAC core */ xgmac_mac_disable(priv->base); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 31752b2..a4da893 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -696,6 +696,7 @@ int t4_seeprom_wp(struct adapter *adapter, bool enable); int get_vpd_params(struct adapter *adapter, struct vpd_params *p); int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size); unsigned int t4_flash_cfg_addr(struct adapter *adapter); +int t4_load_cfg(struct adapter *adapter, const u8 *cfg_data, unsigned int size); int t4_check_fw_version(struct adapter *adapter); int t4_prep_adapter(struct adapter *adapter); int t4_port_init(struct adapter *adap, int mbox, int pf, int vf); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 6b9f6bb..604f4f8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -443,7 +443,10 @@ int dbfifo_int_thresh = 10; /* 10 == 640 entry threshold */ module_param(dbfifo_int_thresh, int, 0644); MODULE_PARM_DESC(dbfifo_int_thresh, "doorbell fifo interrupt threshold"); -int dbfifo_drain_delay = 1000; /* usecs to sleep while draining the dbfifo */ +/* + * usecs to sleep while draining the dbfifo + */ +static int dbfifo_drain_delay = 1000; module_param(dbfifo_drain_delay, int, 0644); MODULE_PARM_DESC(dbfifo_drain_delay, "usecs to sleep while draining the dbfifo"); @@ -636,7 +639,7 @@ static void name_msix_vecs(struct adapter *adap) static int request_msix_queue_irqs(struct adapter *adap) { struct sge *s = &adap->sge; - int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, msi = 2; + int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, msi_index = 2; err = request_irq(adap->msix_info[1].vec, t4_sge_intr_msix, 0, adap->msix_info[1].desc, &s->fw_evtq); @@ -644,56 +647,60 @@ static int request_msix_queue_irqs(struct adapter *adap) return err; for_each_ethrxq(s, ethqidx) { - err = request_irq(adap->msix_info[msi].vec, t4_sge_intr_msix, 0, - adap->msix_info[msi].desc, + err = request_irq(adap->msix_info[msi_index].vec, + t4_sge_intr_msix, 0, + adap->msix_info[msi_index].desc, &s->ethrxq[ethqidx].rspq); if (err) goto unwind; - msi++; + msi_index++; } for_each_ofldrxq(s, ofldqidx) { - err = request_irq(adap->msix_info[msi].vec, t4_sge_intr_msix, 0, - adap->msix_info[msi].desc, + err = request_irq(adap->msix_info[msi_index].vec, + t4_sge_intr_msix, 0, + adap->msix_info[msi_index].desc, &s->ofldrxq[ofldqidx].rspq); if (err) goto unwind; - msi++; + msi_index++; } for_each_rdmarxq(s, rdmaqidx) { - err = request_irq(adap->msix_info[msi].vec, t4_sge_intr_msix, 0, - adap->msix_info[msi].desc, + err = request_irq(adap->msix_info[msi_index].vec, + t4_sge_intr_msix, 0, + adap->msix_info[msi_index].desc, &s->rdmarxq[rdmaqidx].rspq); if (err) goto unwind; - msi++; + msi_index++; } return 0; unwind: while (--rdmaqidx >= 0) - free_irq(adap->msix_info[--msi].vec, + free_irq(adap->msix_info[--msi_index].vec, &s->rdmarxq[rdmaqidx].rspq); while (--ofldqidx >= 0) - free_irq(adap->msix_info[--msi].vec, + free_irq(adap->msix_info[--msi_index].vec, &s->ofldrxq[ofldqidx].rspq); while (--ethqidx >= 0) - free_irq(adap->msix_info[--msi].vec, &s->ethrxq[ethqidx].rspq); + free_irq(adap->msix_info[--msi_index].vec, + &s->ethrxq[ethqidx].rspq); free_irq(adap->msix_info[1].vec, &s->fw_evtq); return err; } static void free_msix_queue_irqs(struct adapter *adap) { - int i, msi = 2; + int i, msi_index = 2; struct sge *s = &adap->sge; free_irq(adap->msix_info[1].vec, &s->fw_evtq); for_each_ethrxq(s, i) - free_irq(adap->msix_info[msi++].vec, &s->ethrxq[i].rspq); + free_irq(adap->msix_info[msi_index++].vec, &s->ethrxq[i].rspq); for_each_ofldrxq(s, i) - free_irq(adap->msix_info[msi++].vec, &s->ofldrxq[i].rspq); + free_irq(adap->msix_info[msi_index++].vec, &s->ofldrxq[i].rspq); for_each_rdmarxq(s, i) - free_irq(adap->msix_info[msi++].vec, &s->rdmarxq[i].rspq); + free_irq(adap->msix_info[msi_index++].vec, &s->rdmarxq[i].rspq); } /** @@ -2535,9 +2542,8 @@ static int read_eq_indices(struct adapter *adap, u16 qid, u16 *pidx, u16 *cidx) ret = t4_mem_win_read_len(adap, addr, (__be32 *)&indices, 8); if (!ret) { - indices = be64_to_cpu(indices); - *cidx = (indices >> 25) & 0xffff; - *pidx = (indices >> 9) & 0xffff; + *cidx = (be64_to_cpu(indices) >> 25) & 0xffff; + *pidx = (be64_to_cpu(indices) >> 9) & 0xffff; } return ret; } @@ -3634,10 +3640,10 @@ static int adap_init0_no_config(struct adapter *adapter, int reset) * field selections will fit in the 36-bit budget. */ if (tp_vlan_pri_map != TP_VLAN_PRI_MAP_DEFAULT) { - int i, bits = 0; + int j, bits = 0; - for (i = TP_VLAN_PRI_MAP_FIRST; i <= TP_VLAN_PRI_MAP_LAST; i++) - switch (tp_vlan_pri_map & (1 << i)) { + for (j = TP_VLAN_PRI_MAP_FIRST; j <= TP_VLAN_PRI_MAP_LAST; j++) + switch (tp_vlan_pri_map & (1 << j)) { case 0: /* compressed filter field not enabled */ break; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 137a244..32eec15 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -380,9 +380,11 @@ static int t4_mem_win_rw(struct adapter *adap, u32 addr, __be32 *data, int dir) /* Collecting data 4 bytes at a time upto MEMWIN0_APERTURE */ for (i = 0; i < MEMWIN0_APERTURE; i = i+0x4) { if (dir) - *data++ = t4_read_reg(adap, (MEMWIN0_BASE + i)); + *data++ = (__force __be32) t4_read_reg(adap, + (MEMWIN0_BASE + i)); else - t4_write_reg(adap, (MEMWIN0_BASE + i), *data++); + t4_write_reg(adap, (MEMWIN0_BASE + i), + (__force u32) *data++); } return 0; @@ -417,7 +419,7 @@ static int t4_memory_rw(struct adapter *adap, int mtype, u32 addr, u32 len, if ((addr & 0x3) || (len & 0x3)) return -EINVAL; - data = vmalloc(MEMWIN0_APERTURE/sizeof(__be32)); + data = vmalloc(MEMWIN0_APERTURE); if (!data) return -ENOMEM; @@ -744,7 +746,7 @@ static int t4_read_flash(struct adapter *adapter, unsigned int addr, if (ret) return ret; if (byte_oriented) - *data = htonl(*data); + *data = (__force __u32) (htonl(*data)); } return 0; } @@ -992,7 +994,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) int ret, addr; unsigned int i; u8 first_page[SF_PAGE_SIZE]; - const u32 *p = (const u32 *)fw_data; + const __be32 *p = (const __be32 *)fw_data; const struct fw_hdr *hdr = (const struct fw_hdr *)fw_data; unsigned int sf_sec_size = adap->params.sf_size / adap->params.sf_nsec; unsigned int fw_img_start = adap->params.sf_fw_start; @@ -2315,7 +2317,8 @@ int t4_mem_win_read_len(struct adapter *adap, u32 addr, __be32 *data, int len) t4_read_reg(adap, PCIE_MEM_ACCESS_OFFSET); for (i = 0; i < len; i += 4) - *data++ = t4_read_reg(adap, (MEMWIN0_BASE + off + i)); + *data++ = (__force __be32) t4_read_reg(adap, + (MEMWIN0_BASE + off + i)); return 0; } diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c index 4d6fe60..d23755e 100644 --- a/drivers/net/ethernet/dec/tulip/dmfe.c +++ b/drivers/net/ethernet/dec/tulip/dmfe.c @@ -446,13 +446,17 @@ static int __devinit dmfe_init_one (struct pci_dev *pdev, /* Allocate Tx/Rx descriptor memory */ db->desc_pool_ptr = pci_alloc_consistent(pdev, sizeof(struct tx_desc) * DESC_ALL_CNT + 0x20, &db->desc_pool_dma_ptr); - if (!db->desc_pool_ptr) + if (!db->desc_pool_ptr) { + err = -ENOMEM; goto err_out_res; + } db->buf_pool_ptr = pci_alloc_consistent(pdev, TX_BUF_ALLOC * TX_DESC_CNT + 4, &db->buf_pool_dma_ptr); - if (!db->buf_pool_ptr) + if (!db->buf_pool_ptr) { + err = -ENOMEM; goto err_out_free_desc; + } db->first_tx_desc = (struct tx_desc *) db->desc_pool_ptr; db->first_tx_desc_dma = db->desc_pool_dma_ptr; @@ -462,8 +466,10 @@ static int __devinit dmfe_init_one (struct pci_dev *pdev, db->chip_id = ent->driver_data; /* IO type range. */ db->ioaddr = pci_iomap(pdev, 0, 0); - if (!db->ioaddr) + if (!db->ioaddr) { + err = -ENOMEM; goto err_out_free_buf; + } db->chip_revision = pdev->revision; db->wol_mode = 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index a1b52ec..1d03dcd 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1765,7 +1765,6 @@ static void free_skb_resources(struct gfar_private *priv) sizeof(struct rxbd8) * priv->total_rx_ring_size, priv->tx_queue[0]->tx_bd_base, priv->tx_queue[0]->tx_bd_dma_base); - skb_queue_purge(&priv->rx_recycle); } void gfar_start(struct net_device *dev) @@ -1943,8 +1942,6 @@ static int gfar_enet_open(struct net_device *dev) enable_napi(priv); - skb_queue_head_init(&priv->rx_recycle); - /* Initialize a bunch of registers */ init_registers(dev); @@ -2533,16 +2530,7 @@ static int gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) bytes_sent += skb->len; - /* If there's room in the queue (limit it to rx_buffer_size) - * we add this skb back into the pool, if it's the right size - */ - if (skb_queue_len(&priv->rx_recycle) < rx_queue->rx_ring_size && - skb_recycle_check(skb, priv->rx_buffer_size + - RXBUF_ALIGNMENT)) { - gfar_align_skb(skb); - skb_queue_head(&priv->rx_recycle, skb); - } else - dev_kfree_skb_any(skb); + dev_kfree_skb_any(skb); tx_queue->tx_skbuff[skb_dirtytx] = NULL; @@ -2608,7 +2596,7 @@ static void gfar_new_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp, static struct sk_buff *gfar_alloc_skb(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - struct sk_buff *skb = NULL; + struct sk_buff *skb; skb = netdev_alloc_skb(dev, priv->rx_buffer_size + RXBUF_ALIGNMENT); if (!skb) @@ -2621,14 +2609,7 @@ static struct sk_buff *gfar_alloc_skb(struct net_device *dev) struct sk_buff *gfar_new_skb(struct net_device *dev) { - struct gfar_private *priv = netdev_priv(dev); - struct sk_buff *skb = NULL; - - skb = skb_dequeue(&priv->rx_recycle); - if (!skb) - skb = gfar_alloc_skb(dev); - - return skb; + return gfar_alloc_skb(dev); } static inline void count_errors(unsigned short status, struct net_device *dev) @@ -2787,7 +2768,7 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) if (unlikely(!newskb)) newskb = skb; else if (skb) - skb_queue_head(&priv->rx_recycle, skb); + dev_kfree_skb(skb); } else { /* Increment the number of packets */ rx_queue->stats.rx_packets++; diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 4141ef2..22eabc1 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -1080,8 +1080,6 @@ struct gfar_private { u32 cur_filer_idx; - struct sk_buff_head rx_recycle; - /* RX queue filer rule set*/ struct ethtool_rx_list rx_list; struct mutex rx_queue_access; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 1642884..0a70bb5 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -209,14 +209,12 @@ static struct list_head *dequeue(struct list_head *lh) static struct sk_buff *get_new_skb(struct ucc_geth_private *ugeth, u8 __iomem *bd) { - struct sk_buff *skb = NULL; + struct sk_buff *skb; - skb = __skb_dequeue(&ugeth->rx_recycle); + skb = netdev_alloc_skb(ugeth->ndev, + ugeth->ug_info->uf_info.max_rx_buf_length + + UCC_GETH_RX_DATA_BUF_ALIGNMENT); if (!skb) - skb = netdev_alloc_skb(ugeth->ndev, - ugeth->ug_info->uf_info.max_rx_buf_length + - UCC_GETH_RX_DATA_BUF_ALIGNMENT); - if (skb == NULL) return NULL; /* We need the data buffer to be aligned properly. We will reserve @@ -2020,8 +2018,6 @@ static void ucc_geth_memclean(struct ucc_geth_private *ugeth) iounmap(ugeth->ug_regs); ugeth->ug_regs = NULL; } - - skb_queue_purge(&ugeth->rx_recycle); } static void ucc_geth_set_multi(struct net_device *dev) @@ -2230,8 +2226,6 @@ static int ucc_struct_init(struct ucc_geth_private *ugeth) return -ENOMEM; } - skb_queue_head_init(&ugeth->rx_recycle); - return 0; } @@ -3274,12 +3268,7 @@ static int ucc_geth_rx(struct ucc_geth_private *ugeth, u8 rxQ, int rx_work_limit if (netif_msg_rx_err(ugeth)) ugeth_err("%s, %d: ERROR!!! skb - 0x%08x", __func__, __LINE__, (u32) skb); - if (skb) { - skb->data = skb->head + NET_SKB_PAD; - skb->len = 0; - skb_reset_tail_pointer(skb); - __skb_queue_head(&ugeth->rx_recycle, skb); - } + dev_kfree_skb(skb); ugeth->rx_skbuff[rxQ][ugeth->skb_currx[rxQ]] = NULL; dev->stats.rx_dropped++; @@ -3349,13 +3338,7 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ) dev->stats.tx_packets++; - if (skb_queue_len(&ugeth->rx_recycle) < RX_BD_RING_LEN && - skb_recycle_check(skb, - ugeth->ug_info->uf_info.max_rx_buf_length + - UCC_GETH_RX_DATA_BUF_ALIGNMENT)) - __skb_queue_head(&ugeth->rx_recycle, skb); - else - dev_kfree_skb(skb); + dev_kfree_skb(skb); ugeth->tx_skbuff[txQ][ugeth->skb_dirtytx[txQ]] = NULL; ugeth->skb_dirtytx[txQ] = diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h index f71b3e7..75f3371 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.h +++ b/drivers/net/ethernet/freescale/ucc_geth.h @@ -1214,8 +1214,6 @@ struct ucc_geth_private { /* index of the first skb which hasn't been transmitted yet. */ u16 skb_dirtytx[NUM_TX_QUEUES]; - struct sk_buff_head rx_recycle; - struct ugeth_mii_info *mii_info; struct phy_device *phydev; phy_interface_t phy_interface; diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index ed5b409..d37bfd9 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -412,6 +412,8 @@ enum e1e_registers { #define E1000_DEV_ID_PCH2_LV_V 0x1503 #define E1000_DEV_ID_PCH_LPT_I217_LM 0x153A #define E1000_DEV_ID_PCH_LPT_I217_V 0x153B +#define E1000_DEV_ID_PCH_LPTLP_I218_LM 0x155A +#define E1000_DEV_ID_PCH_LPTLP_I218_V 0x1559 #define E1000_REVISION_4 4 diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fb659dd..de57a2b 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6558,6 +6558,8 @@ static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPT_I217_LM), board_pch_lpt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPT_I217_V), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_LM), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_V), board_pch_lpt }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 5bd2676..30efc9f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -410,7 +410,7 @@ static inline u16 ixgbe_desc_unused(struct ixgbe_ring *ring) #define IXGBE_TX_CTXTDESC(R, i) \ (&(((struct ixgbe_adv_tx_context_desc *)((R)->desc))[i])) -#define IXGBE_MAX_JUMBO_FRAME_SIZE 16128 +#define IXGBE_MAX_JUMBO_FRAME_SIZE 9728 /* Maximum Supported Size 9.5KB */ #ifdef IXGBE_FCOE /* Use 3K as the baby jumbo frame size for FCoE */ #define IXGBE_FCOE_JUMBO_FRAME_SIZE 3072 diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 383b4e1..4a9c9c2 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -175,7 +175,7 @@ struct ixgbevf_q_vector { #define IXGBEVF_TX_CTXTDESC(R, i) \ (&(((struct ixgbe_adv_tx_context_desc *)((R)->desc))[i])) -#define IXGBE_MAX_JUMBO_FRAME_SIZE 16128 +#define IXGBE_MAX_JUMBO_FRAME_SIZE 9728 /* Maximum Supported Size 9.5KB */ #define OTHER_VECTOR 1 #define NON_Q_VECTORS (OTHER_VECTOR) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 0ee9bd4..de1ad50 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1747,6 +1747,7 @@ err_tx_ring_allocation: **/ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) { + struct net_device *netdev = adapter->netdev; int err = 0; int vector, v_budget; @@ -1775,6 +1776,12 @@ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) ixgbevf_acquire_msix_vectors(adapter, v_budget); + err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); + if (err) + goto out; + + err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); + out: return err; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 087b9e0..84c1326 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -412,7 +412,6 @@ struct mv643xx_eth_private { u8 work_rx_refill; int skb_size; - struct sk_buff_head rx_recycle; /* * RX state. @@ -673,9 +672,7 @@ static int rxq_refill(struct rx_queue *rxq, int budget) struct rx_desc *rx_desc; int size; - skb = __skb_dequeue(&mp->rx_recycle); - if (skb == NULL) - skb = netdev_alloc_skb(mp->dev, mp->skb_size); + skb = netdev_alloc_skb(mp->dev, mp->skb_size); if (skb == NULL) { mp->oom = 1; @@ -989,14 +986,7 @@ static int txq_reclaim(struct tx_queue *txq, int budget, int force) desc->byte_cnt, DMA_TO_DEVICE); } - if (skb != NULL) { - if (skb_queue_len(&mp->rx_recycle) < - mp->rx_ring_size && - skb_recycle_check(skb, mp->skb_size)) - __skb_queue_head(&mp->rx_recycle, skb); - else - dev_kfree_skb(skb); - } + dev_kfree_skb(skb); } __netif_tx_unlock(nq); @@ -2349,8 +2339,6 @@ static int mv643xx_eth_open(struct net_device *dev) napi_enable(&mp->napi); - skb_queue_head_init(&mp->rx_recycle); - mp->int_mask = INT_EXT; for (i = 0; i < mp->rxq_count; i++) { @@ -2445,8 +2433,6 @@ static int mv643xx_eth_stop(struct net_device *dev) mib_counters_update(mp); del_timer_sync(&mp->mib_counters_timer); - skb_queue_purge(&mp->rx_recycle); - for (i = 0; i < mp->rxq_count; i++) rxq_deinit(mp->rxq + i); for (i = 0; i < mp->txq_count; i++) diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 5a30bf8..9b9c2ac 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3189,7 +3189,7 @@ static int skge_poll(struct napi_struct *napi, int to_do) if (work_done < to_do) { unsigned long flags; - napi_gro_flush(napi); + napi_gro_flush(napi, false); spin_lock_irqsave(&hw->hw_lock, flags); __napi_complete(napi); hw->intr_mask |= napimask[skge->port]; @@ -3945,8 +3945,10 @@ static int __devinit skge_probe(struct pci_dev *pdev, skge_board_name(hw), hw->chip_rev); dev = skge_devinit(hw, 0, using_dac); - if (!dev) + if (!dev) { + err = -ENOMEM; goto err_out_led_off; + } /* Some motherboards are broken and has zero in ROM. */ if (!is_valid_ether_addr(dev->dev_addr)) @@ -4153,6 +4155,13 @@ static struct dmi_system_id skge_32bit_dma_boards[] = { DMI_MATCH(DMI_BOARD_NAME, "nForce"), }, }, + { + .ident = "ASUS P5NSLI", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P5NSLI") + }, + }, {} }; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 2b0748d..78946fe 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4924,6 +4924,7 @@ static int __devinit sky2_probe(struct pci_dev *pdev, if (~reg == 0) { dev_err(&pdev->dev, "PCI configuration read error\n"); + err = -EIO; goto err_out; } @@ -4993,8 +4994,10 @@ static int __devinit sky2_probe(struct pci_dev *pdev, hw->st_size = hw->ports * roundup_pow_of_two(3*RX_MAX_PENDING + TX_MAX_PENDING); hw->st_le = pci_alloc_consistent(pdev, hw->st_size * sizeof(struct sky2_status_le), &hw->st_dma); - if (!hw->st_le) + if (!hw->st_le) { + err = -ENOMEM; goto err_out_reset; + } dev_info(&pdev->dev, "Yukon-2 %s chip revision %d\n", sky2_name(hw->chip_id, buf1, sizeof(buf1)), hw->chip_rev); diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index 5b61d12..dbaaa99 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -947,8 +947,8 @@ static int __devinit natsemi_probe1 (struct pci_dev *pdev, i = register_netdev(dev); if (i) goto err_register_netdev; - - if (NATSEMI_CREATE_FILE(pdev, dspcfg_workaround)) + i = NATSEMI_CREATE_FILE(pdev, dspcfg_workaround); + if (i) goto err_create_file; if (netif_msg_drv(np)) { diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c index e01c0a0..7dfe883 100644 --- a/drivers/net/ethernet/natsemi/xtsonic.c +++ b/drivers/net/ethernet/natsemi/xtsonic.c @@ -205,6 +205,7 @@ static int __init sonic_probe1(struct net_device *dev) if (lp->descriptors == NULL) { printk(KERN_ERR "%s: couldn't alloc DMA memory for " " descriptors.\n", dev_name(lp->device)); + err = -ENOMEM; goto out; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 473ce13..24ad17e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -1601,7 +1601,8 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->netdev = netdev; adapter->pdev = pdev; - if (qlcnic_alloc_adapter_resources(adapter)) + err = qlcnic_alloc_adapter_resources(adapter); + if (err) goto err_out_free_netdev; adapter->dev_rst_time = jiffies; diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 995d0cf..1c81825 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -563,7 +563,7 @@ rx_next: if (cpr16(IntrStatus) & cp_rx_intr_mask) goto rx_status_loop; - napi_gro_flush(napi); + napi_gro_flush(napi, false); spin_lock_irqsave(&cp->lock, flags); __napi_complete(napi); cpw16_f(IntrMask, cp_intr_mask); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index bad8f2e..c8bfea0 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2438,6 +2438,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev) rtsu = platform_get_resource(pdev, IORESOURCE_MEM, 1); if (!rtsu) { dev_err(&pdev->dev, "Not found TSU resource\n"); + ret = -ENODEV; goto out_release; } mdp->tsu_addr = ioremap(rtsu->start, diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 5b3dd02..0767043f 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -640,8 +640,7 @@ static void efx_ptp_drop_time_expired_events(struct efx_nic *efx) evt = list_entry(cursor, struct efx_ptp_event_rx, link); if (time_after(jiffies, evt->expiry)) { - list_del(&evt->link); - list_add(&evt->link, &ptp->evt_free_list); + list_move(&evt->link, &ptp->evt_free_list); netif_warn(efx, hw, efx->net_dev, "PTP rx event dropped\n"); } @@ -684,8 +683,7 @@ static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx, match->state = PTP_PACKET_STATE_MATCHED; rc = PTP_PACKET_STATE_MATCHED; - list_del(&evt->link); - list_add(&evt->link, &ptp->evt_free_list); + list_move(&evt->link, &ptp->evt_free_list); break; } } @@ -820,8 +818,7 @@ static int efx_ptp_stop(struct efx_nic *efx) /* Drop any pending receive events */ spin_lock_bh(&efx->ptp_data->evt_lock); list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) { - list_del(cursor); - list_add(cursor, &efx->ptp_data->evt_free_list); + list_move(cursor, &efx->ptp_data->evt_free_list); } spin_unlock_bh(&efx->ptp_data->evt_lock); diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 203d9c6..fb9f6b3 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -478,8 +478,10 @@ static int __devinit sis900_probe(struct pci_dev *pci_dev, /* IO region. */ ioaddr = pci_iomap(pci_dev, 0, 0); - if (!ioaddr) + if (!ioaddr) { + ret = -ENOMEM; goto err_out_cleardev; + } sis_priv = netdev_priv(net_dev); sis_priv->ioaddr = ioaddr; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index e872e1d..7d51a65 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -50,7 +50,6 @@ struct stmmac_priv { unsigned int dirty_rx; struct sk_buff **rx_skbuff; dma_addr_t *rx_skbuff_dma; - struct sk_buff_head rx_recycle; struct net_device *dev; dma_addr_t dma_rx_phy; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3be8833..c6cdbc4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -747,18 +747,7 @@ static void stmmac_tx(struct stmmac_priv *priv) priv->hw->ring->clean_desc3(p); if (likely(skb != NULL)) { - /* - * If there's room in the queue (limit it to size) - * we add this skb back into the pool, - * if it's the right size. - */ - if ((skb_queue_len(&priv->rx_recycle) < - priv->dma_rx_size) && - skb_recycle_check(skb, priv->dma_buf_sz)) - __skb_queue_head(&priv->rx_recycle, skb); - else - dev_kfree_skb(skb); - + dev_kfree_skb(skb); priv->tx_skbuff[entry] = NULL; } @@ -1169,7 +1158,6 @@ static int stmmac_open(struct net_device *dev) priv->eee_enabled = stmmac_eee_init(priv); napi_enable(&priv->napi); - skb_queue_head_init(&priv->rx_recycle); netif_start_queue(dev); return 0; @@ -1222,7 +1210,6 @@ static int stmmac_release(struct net_device *dev) kfree(priv->tm); #endif napi_disable(&priv->napi); - skb_queue_purge(&priv->rx_recycle); /* Free the IRQ lines */ free_irq(dev->irq, dev); @@ -1388,10 +1375,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) if (likely(priv->rx_skbuff[entry] == NULL)) { struct sk_buff *skb; - skb = __skb_dequeue(&priv->rx_recycle); - if (skb == NULL) - skb = netdev_alloc_skb_ip_align(priv->dev, - bfsize); + skb = netdev_alloc_skb_ip_align(priv->dev, bfsize); if (unlikely(skb == NULL)) break; diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 8419bf3..275b430 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9788,6 +9788,7 @@ static int __devinit niu_pci_init_one(struct pci_dev *pdev, if (!pci_is_pcie(pdev)) { dev_err(&pdev->dev, "Cannot find PCI Express capability, aborting\n"); + err = -ENODEV; goto err_out_free_res; } diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 9ae12d0..6c8695e 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -2963,7 +2963,8 @@ static int __devinit gem_init_one(struct pci_dev *pdev, goto err_out_iounmap; } - if (gem_get_device_address(gp)) + err = gem_get_device_address(gp); + if (err) goto err_out_free_consistent; dev->netdev_ops = &gem_netdev_ops; diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c index 30087ca..6e4d4b6 100644 --- a/drivers/net/irda/irtty-sir.c +++ b/drivers/net/irda/irtty-sir.c @@ -459,8 +459,10 @@ static int irtty_open(struct tty_struct *tty) /* allocate private device info block */ priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) + if (!priv) { + ret = -ENOMEM; goto out_put; + } priv->magic = IRTTY_MAGIC; priv->tty = tty; diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c index 1a00b59..f07c340 100644 --- a/drivers/net/irda/mcs7780.c +++ b/drivers/net/irda/mcs7780.c @@ -920,8 +920,10 @@ static int mcs_probe(struct usb_interface *intf, ndev->netdev_ops = &mcs_netdev_ops; - if (!intf->cur_altsetting) + if (!intf->cur_altsetting) { + ret = -ENOMEM; goto error2; + } ret = mcs_find_endpoints(mcs, intf->cur_altsetting->endpoint, intf->cur_altsetting->desc.bNumEndpoints); diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c index 002a442..858de05 100644 --- a/drivers/net/irda/pxaficp_ir.c +++ b/drivers/net/irda/pxaficp_ir.c @@ -846,8 +846,10 @@ static int pxa_irda_probe(struct platform_device *pdev) goto err_mem_2; dev = alloc_irdadev(sizeof(struct pxa_irda)); - if (!dev) + if (!dev) { + err = -ENOMEM; goto err_mem_3; + } SET_NETDEV_DEV(dev, &pdev->dev); si = netdev_priv(dev); diff --git a/drivers/net/irda/sa1100_ir.c b/drivers/net/irda/sa1100_ir.c index e250675..42fde9e 100644 --- a/drivers/net/irda/sa1100_ir.c +++ b/drivers/net/irda/sa1100_ir.c @@ -940,8 +940,10 @@ static int sa1100_irda_probe(struct platform_device *pdev) goto err_mem_3; dev = alloc_irdadev(sizeof(struct sa1100_irda)); - if (!dev) + if (!dev) { + err = -ENOMEM; goto err_mem_4; + } SET_NETDEV_DEV(dev, &pdev->dev); diff --git a/drivers/net/irda/sh_irda.c b/drivers/net/irda/sh_irda.c index eb315b8..4b746d9 100644 --- a/drivers/net/irda/sh_irda.c +++ b/drivers/net/irda/sh_irda.c @@ -808,8 +808,8 @@ static int __devinit sh_irda_probe(struct platform_device *pdev) goto err_mem_4; platform_set_drvdata(pdev, ndev); - - if (request_irq(irq, sh_irda_irq, IRQF_DISABLED, "sh_irda", self)) { + err = request_irq(irq, sh_irda_irq, IRQF_DISABLED, "sh_irda", self); + if (err) { dev_warn(&pdev->dev, "Unable to attach sh_irda interrupt\n"); goto err_mem_4; } diff --git a/drivers/net/irda/sh_sir.c b/drivers/net/irda/sh_sir.c index 7951094..624ac19 100644 --- a/drivers/net/irda/sh_sir.c +++ b/drivers/net/irda/sh_sir.c @@ -741,6 +741,7 @@ static int __devinit sh_sir_probe(struct platform_device *pdev) self->clk = clk_get(&pdev->dev, clk_name); if (IS_ERR(self->clk)) { dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name); + err = -ENODEV; goto err_mem_3; } @@ -760,8 +761,8 @@ static int __devinit sh_sir_probe(struct platform_device *pdev) goto err_mem_4; platform_set_drvdata(pdev, ndev); - - if (request_irq(irq, sh_sir_irq, IRQF_DISABLED, "sh_sir", self)) { + err = request_irq(irq, sh_sir_irq, IRQF_DISABLED, "sh_sir", self); + if (err) { dev_warn(&pdev->dev, "Unable to attach sh_sir interrupt\n"); goto err_mem_4; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 51de9ed..8be9bf0 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -28,7 +28,6 @@ #include <linux/igmp.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> -#include <linux/version.h> #include <linux/hash.h> #include <net/ip.h> #include <net/icmp.h> @@ -1084,13 +1083,13 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_VXLAN_ID, vxlan->vni)) goto nla_put_failure; - if (vxlan->gaddr && nla_put_u32(skb, IFLA_VXLAN_GROUP, vxlan->gaddr)) + if (vxlan->gaddr && nla_put_be32(skb, IFLA_VXLAN_GROUP, vxlan->gaddr)) goto nla_put_failure; if (vxlan->link && nla_put_u32(skb, IFLA_VXLAN_LINK, vxlan->link)) goto nla_put_failure; - if (vxlan->saddr && nla_put_u32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr)) + if (vxlan->saddr && nla_put_be32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) || diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 6968b72..6d369fe 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -461,7 +461,7 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) } vma->vm_private_data = vdev; - vma->vm_flags |= (VM_IO | VM_RESERVED); + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); phys = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index e6ff12d..c0ff748 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -80,6 +80,8 @@ static inline int is_vlan_dev(struct net_device *dev) } #define vlan_tx_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT) +#define vlan_tx_nonzero_tag_present(__skb) \ + (vlan_tx_tag_present(__skb) && ((__skb)->vlan_tci & VLAN_VID_MASK)) #define vlan_tx_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) @@ -89,7 +91,7 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); -extern bool vlan_do_receive(struct sk_buff **skb, bool last_handler); +extern bool vlan_do_receive(struct sk_buff **skb); extern struct sk_buff *vlan_untag(struct sk_buff *skb); extern int vlan_vid_add(struct net_device *dev, unsigned short vid); @@ -120,10 +122,8 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev) return 0; } -static inline bool vlan_do_receive(struct sk_buff **skb, bool last_handler) +static inline bool vlan_do_receive(struct sk_buff **skb) { - if (((*skb)->vlan_tci & VLAN_VID_MASK) && last_handler) - (*skb)->pkt_type = PACKET_OTHERHOST; return false; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 01646aa..561c8bc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1497,19 +1497,25 @@ struct napi_gro_cb { /* This indicates where we are processing relative to skb->data. */ int data_offset; - /* This is non-zero if the packet may be of the same flow. */ - int same_flow; - /* This is non-zero if the packet cannot be merged with the new skb. */ int flush; /* Number of segments aggregated. */ - int count; + u16 count; + + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow; /* Free the skb? */ - int free; + u8 free; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 + + /* jiffies when first packet was created/queued */ + unsigned long age; + + /* Used in ipv6_gro_receive() */ + int proto; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) @@ -1663,7 +1669,6 @@ extern int netpoll_trap(void); #endif extern int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); -extern void skb_gro_reset_offset(struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { @@ -2157,7 +2162,7 @@ extern gro_result_t dev_gro_receive(struct napi_struct *napi, extern gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb); extern gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); -extern void napi_gro_flush(struct napi_struct *napi); +extern void napi_gro_flush(struct napi_struct *napi, bool flush_old); extern struct sk_buff * napi_get_frags(struct napi_struct *napi); extern gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, diff --git a/include/linux/netlink.h b/include/linux/netlink.h index f80c56a..6d3af05c 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -245,6 +245,8 @@ struct netlink_callback { struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); void *data; + /* the module that dump function belong to */ + struct module *module; u16 family; u16 min_dump_alloc; unsigned int prev_seq, seq; @@ -262,14 +264,24 @@ __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int fla struct netlink_dump_control { int (*dump)(struct sk_buff *skb, struct netlink_callback *); - int (*done)(struct netlink_callback*); + int (*done)(struct netlink_callback *); void *data; + struct module *module; u16 min_dump_alloc; }; -extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, - const struct nlmsghdr *nlh, - struct netlink_dump_control *control); +extern int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct netlink_dump_control *control); +static inline int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct netlink_dump_control *control) +{ + if (!control->module) + control->module = THIS_MODULE; + + return __netlink_dump_start(ssk, skb, nlh, control); +} #endif /* __KERNEL__ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b33a3a1..6a2c34e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -589,9 +589,6 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } -extern void skb_recycle(struct sk_buff *skb); -extern bool skb_recycle_check(struct sk_buff *skb, int skb_size); - extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); extern struct sk_buff *skb_clone(struct sk_buff *skb, @@ -2645,27 +2642,6 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); -static inline bool skb_is_recycleable(const struct sk_buff *skb, int skb_size) -{ - if (irqs_disabled()) - return false; - - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) - return false; - - if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE) - return false; - - skb_size = SKB_DATA_ALIGN(skb_size + NET_SKB_PAD); - if (skb_end_offset(skb) < skb_size) - return false; - - if (skb_shared(skb) || skb_cloned(skb)) - return false; - - return true; -} - /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check diff --git a/include/net/flow.h b/include/net/flow.h index e1dd508..628e11b 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -21,6 +21,7 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_CAN_SLEEP 0x02 +#define FLOWI_FLAG_KNOWN_NH 0x04 __u32 flowic_secid; }; diff --git a/include/net/route.h b/include/net/route.h index da22243..bc40b63 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -48,7 +48,8 @@ struct rtable { int rt_genid; unsigned int rt_flags; __u16 rt_type; - __u16 rt_is_input; + __u8 rt_is_input; + __u8 rt_uses_gateway; int rt_iif; diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h index 3c5363a..bd3d8b2 100644 --- a/include/rdma/rdma_netlink.h +++ b/include/rdma/rdma_netlink.h @@ -39,6 +39,7 @@ struct rdma_cm_id_stats { struct ibnl_client_cbs { int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb); + struct module *module; }; int ibnl_init(void); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index add69d0..fbbf1fa 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -5,7 +5,7 @@ #include <linux/export.h> #include "vlan.h" -bool vlan_do_receive(struct sk_buff **skbp, bool last_handler) +bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; @@ -13,14 +13,8 @@ bool vlan_do_receive(struct sk_buff **skbp, bool last_handler) struct vlan_pcpu_stats *rx_stats; vlan_dev = vlan_find_dev(skb->dev, vlan_id); - if (!vlan_dev) { - /* Only the last call to vlan_do_receive() should change - * pkt_type to PACKET_OTHERHOST - */ - if (vlan_id && last_handler) - skb->pkt_type = PACKET_OTHERHOST; + if (!vlan_dev) return false; - } skb = *skbp = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) diff --git a/net/core/dev.c b/net/core/dev.c index 1e0a184..09cb3f6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3300,18 +3300,18 @@ ncls: && !skb_pfmemalloc_protocol(skb)) goto drop; - rx_handler = rcu_dereference(skb->dev->rx_handler); if (vlan_tx_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } - if (vlan_do_receive(&skb, !rx_handler)) + if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) goto unlock; } + rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); @@ -3331,6 +3331,9 @@ ncls: } } + if (vlan_tx_nonzero_tag_present(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; @@ -3471,17 +3474,31 @@ out: return netif_receive_skb(skb); } -inline void napi_gro_flush(struct napi_struct *napi) +/* napi->gro_list contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) { - struct sk_buff *skb, *next; + struct sk_buff *skb, *prev = NULL; - for (skb = napi->gro_list; skb; skb = next) { - next = skb->next; + /* scan list and build reverse chain */ + for (skb = napi->gro_list; skb != NULL; skb = skb->next) { + skb->prev = prev; + prev = skb; + } + + for (skb = prev; skb; skb = prev) { skb->next = NULL; + + if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) + return; + + prev = skb->prev; napi_gro_complete(skb); + napi->gro_count--; } - napi->gro_count = 0; napi->gro_list = NULL; } EXPORT_SYMBOL(napi_gro_flush); @@ -3542,6 +3559,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) napi->gro_count++; NAPI_GRO_CB(skb)->count = 1; + NAPI_GRO_CB(skb)->age = jiffies; skb_shinfo(skb)->gso_size = skb_gro_len(skb); skb->next = napi->gro_list; napi->gro_list = skb; @@ -3631,20 +3649,22 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) } EXPORT_SYMBOL(napi_skb_finish); -void skb_gro_reset_offset(struct sk_buff *skb) +static void skb_gro_reset_offset(struct sk_buff *skb) { + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + NAPI_GRO_CB(skb)->data_offset = 0; NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0; if (skb->mac_header == skb->tail && - !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) { - NAPI_GRO_CB(skb)->frag0 = - skb_frag_address(&skb_shinfo(skb)->frags[0]); - NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]); + pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); } } -EXPORT_SYMBOL(skb_gro_reset_offset); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { @@ -3876,7 +3896,7 @@ void napi_complete(struct napi_struct *n) if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state))) return; - napi_gro_flush(n); + napi_gro_flush(n, false); local_irq_save(flags); __napi_complete(n); local_irq_restore(flags); @@ -3981,8 +4001,17 @@ static void net_rx_action(struct softirq_action *h) local_irq_enable(); napi_complete(n); local_irq_disable(); - } else + } else { + if (n->gro_list) { + /* flush too old packets + * If HZ < 1000, flush all packets. + */ + local_irq_enable(); + napi_gro_flush(n, HZ >= 1000); + local_irq_disable(); + } list_move_tail(&n->poll_list, &sd->poll_list); + } } netpoll_poll_unlock(have); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index baca771..2257148 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1301,8 +1301,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) if (!dst) goto discard; - __skb_pull(skb, skb_network_offset(skb)); - if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; @@ -1312,6 +1310,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) neigh_hh_init(neigh, dst); do { + __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); @@ -1342,9 +1341,8 @@ int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb) unsigned int seq; int err; - __skb_pull(skb, skb_network_offset(skb)); - do { + __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index cdc2859..6e04b1f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -655,53 +655,6 @@ void consume_skb(struct sk_buff *skb) } EXPORT_SYMBOL(consume_skb); -/** - * skb_recycle - clean up an skb for reuse - * @skb: buffer - * - * Recycles the skb to be reused as a receive buffer. This - * function does any necessary reference count dropping, and - * cleans up the skbuff as if it just came from __alloc_skb(). - */ -void skb_recycle(struct sk_buff *skb) -{ - struct skb_shared_info *shinfo; - - skb_release_head_state(skb); - - shinfo = skb_shinfo(skb); - memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); - atomic_set(&shinfo->dataref, 1); - - memset(skb, 0, offsetof(struct sk_buff, tail)); - skb->data = skb->head + NET_SKB_PAD; - skb_reset_tail_pointer(skb); -} -EXPORT_SYMBOL(skb_recycle); - -/** - * skb_recycle_check - check if skb can be reused for receive - * @skb: buffer - * @skb_size: minimum receive buffer size - * - * Checks that the skb passed in is not shared or cloned, and - * that it is linear and its head portion at least as large as - * skb_size so that it can be recycled as a receive buffer. - * If these conditions are met, this function does any necessary - * reference count dropping and cleans up the skbuff as if it - * just came from __alloc_skb(). - */ -bool skb_recycle_check(struct sk_buff *skb, int skb_size) -{ - if (!skb_is_recycleable(skb, skb_size)) - return false; - - skb_recycle(skb); - - return true; -} -EXPORT_SYMBOL(skb_recycle_check); - static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { new->tstamp = old->tstamp; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 68c93d1..825c608 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -322,7 +322,8 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); - if (!r && !fib_num_tclassid_users(dev_net(dev))) { + if (!r && !fib_num_tclassid_users(dev_net(dev)) && + (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { *itag = 0; return 0; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2677530..71b125c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -840,6 +840,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) change_nexthops(fi) { nexthop_nh->nh_parent = fi; nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *); + if (!nexthop_nh->nh_pcpu_rth_output) + goto failure; } endfor_nexthops(fi) if (cfg->fc_mx) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f0c5b9c..d34ce29 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -406,7 +406,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && rt->rt_gateway) + if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; return &rt->dst; @@ -442,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && rt->rt_gateway) + if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; rcu_read_unlock(); return &rt->dst; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index ab09b12..694de3b 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -85,7 +85,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) + if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 24a29a3..6537a40 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -193,7 +193,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt->rt_gateway ? rt->rt_gateway : ip_hdr(skb)->daddr; + nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr); neigh = __ipv4_neigh_lookup_noref(dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &nexthop, dev, false); @@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl) skb_dst_set_noref(skb, &rt->dst); packet_routed: - if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway) + if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ff62206..1a0da8d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -802,7 +802,8 @@ void ip_rt_send_redirect(struct sk_buff *skb) net = dev_net(rt->dst.dev); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); if (!peer) { - icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); + icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, + rt_nexthop(rt, ip_hdr(skb)->daddr)); return; } @@ -827,7 +828,9 @@ void ip_rt_send_redirect(struct sk_buff *skb) time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->rate_tokens)))) { - icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); + __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); + + icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->rate_tokens; #ifdef CONFIG_IP_ROUTE_VERBOSE @@ -835,7 +838,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) peer->rate_tokens == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), - &ip_hdr(skb)->daddr, &rt->rt_gateway); + &ip_hdr(skb)->daddr, &gw); #endif } out_put_peer: @@ -904,22 +907,32 @@ out: kfree_skb(skb); return 0; } -static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) +static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { + struct dst_entry *dst = &rt->dst; struct fib_result res; + if (dst->dev->mtu < mtu) + return; + if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; + if (!rt->rt_pmtu) { + dst->obsolete = DST_OBSOLETE_KILL; + } else { + rt->rt_pmtu = mtu; + dst->expires = max(1UL, jiffies + ip_rt_mtu_expires); + } + rcu_read_lock(); - if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) { + if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, 0, mtu, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); - return mtu; } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, @@ -929,14 +942,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); - mtu = __ip_rt_update_pmtu(rt, &fl4, mtu); - - if (!rt->rt_pmtu) { - dst->obsolete = DST_OBSOLETE_KILL; - } else { - rt->rt_pmtu = mtu; - rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires); - } + __ip_rt_update_pmtu(rt, &fl4, mtu); } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, @@ -1120,7 +1126,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - if (rt->rt_gateway && mtu > 576) + if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1171,7 +1177,9 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; rt->rt_gateway = fnhe->fnhe_gw; - } + rt->rt_uses_gateway = 1; + } else if (!rt->rt_gateway) + rt->rt_gateway = daddr; orig = rcu_dereference(fnhe->fnhe_rth); rcu_assign_pointer(fnhe->fnhe_rth, rt); @@ -1180,13 +1188,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, fnhe->fnhe_stamp = jiffies; ret = true; - } else { - /* Routes we intend to cache in nexthop exception 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; } spin_unlock_bh(&fnhe_lock); @@ -1201,8 +1202,6 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) if (rt_is_input_route(rt)) { p = (struct rtable **)&nh->nh_rth_input; } else { - if (!nh->nh_pcpu_rth_output) - goto nocache; p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output); } orig = *p; @@ -1211,16 +1210,8 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) if (prev == orig) { if (orig) 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. - */ -nocache: - rt->dst.flags |= DST_NOCACHE; + } else ret = false; - } return ret; } @@ -1281,8 +1272,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, if (fi) { struct fib_nh *nh = &FIB_RES_NH(*res); - if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) + if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) { rt->rt_gateway = nh->nh_gw; + rt->rt_uses_gateway = 1; + } dst_init_metrics(&rt->dst, fi->fib_metrics, true); #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; @@ -1291,8 +1284,18 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, cached = rt_bind_exception(rt, fnhe, daddr); else if (!(rt->dst.flags & DST_NOCACHE)) cached = rt_cache_route(nh, rt); - } - if (unlikely(!cached)) + if (unlikely(!cached)) { + /* Routes we intend to cache in nexthop exception or + * 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; + if (!rt->rt_gateway) + rt->rt_gateway = daddr; + rt_add_uncached_list(rt); + } + } else rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID @@ -1360,6 +1363,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); if (our) { rth->dst.input= ip_local_deliver; @@ -1429,7 +1433,6 @@ static int __mkroute_input(struct sk_buff *skb, return -EINVAL; } - err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res), in_dev->dev, in_dev, &itag); if (err < 0) { @@ -1439,10 +1442,13 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - if (out_dev == in_dev && err && + do_cache = res->fi && !itag; + if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) + inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) { flags |= RTCF_DOREDIRECT; + do_cache = false; + } if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -1459,15 +1465,11 @@ static int __mkroute_input(struct sk_buff *skb, } } - do_cache = false; - if (res->fi) { - if (!itag) { - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); - if (rt_cache_valid(rth)) { - skb_dst_set_noref(skb, &rth->dst); - goto out; - } - do_cache = true; + if (do_cache) { + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rt_cache_valid(rth)) { + skb_dst_set_noref(skb, &rth->dst); + goto out; } } @@ -1486,6 +1488,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); rth->dst.input = ip_forward; @@ -1656,6 +1659,7 @@ local_input: rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; @@ -1758,6 +1762,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct in_device *in_dev; u16 type = res->type; struct rtable *rth; + bool do_cache; in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) @@ -1794,24 +1799,36 @@ static struct rtable *__mkroute_output(const struct fib_result *res, } fnhe = NULL; + do_cache = fi != NULL; if (fi) { struct rtable __rcu **prth; + struct fib_nh *nh = &FIB_RES_NH(*res); - fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr); + fnhe = find_exception(nh, fl4->daddr); if (fnhe) prth = &fnhe->fnhe_rth; - else - prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output); + else { + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = __this_cpu_ptr(nh->nh_pcpu_rth_output); + } rth = rcu_dereference(*prth); if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; } } + +add: rth = rt_dst_alloc(dev_out, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM), - fi); + do_cache); if (!rth) return ERR_PTR(-ENOBUFS); @@ -1824,6 +1841,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_iif = orig_oif ? : 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); RT_CACHE_STAT_INC(out_slow_tot); @@ -2102,6 +2120,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_gateway = ort->rt_gateway; + rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); @@ -2180,12 +2199,22 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } - if (rt->rt_gateway && + if (rt->rt_uses_gateway && nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway)) goto nla_put_failure; + expires = rt->dst.expires; + if (expires) { + unsigned long now = jiffies; + + if (time_before(now, expires)) + expires -= now; + else + expires = 0; + } + memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); - if (rt->rt_pmtu) + if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; @@ -2195,13 +2224,6 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, goto nla_put_failure; error = rt->dst.error; - expires = rt->dst.expires; - if (expires) { - if (time_before(jiffies, expires)) - expires -= jiffies; - else - expires = 0; - } if (rt_is_input_route(rt)) { if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 681ea2f..05c5ab8 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -91,6 +91,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_gateway = rt->rt_gateway; + xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e22e6d8..a974247 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -822,13 +822,6 @@ out: return segs; } -struct ipv6_gro_cb { - struct napi_gro_cb napi; - int proto; -}; - -#define IPV6_GRO_CB(skb) ((struct ipv6_gro_cb *)(skb)->cb) - static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { @@ -874,28 +867,31 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, iph = ipv6_hdr(skb); } - IPV6_GRO_CB(skb)->proto = proto; + NAPI_GRO_CB(skb)->proto = proto; flush--; nlen = skb_network_header_len(skb); for (p = *head; p; p = p->next) { - struct ipv6hdr *iph2; + const struct ipv6hdr *iph2; + __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ if (!NAPI_GRO_CB(p)->same_flow) continue; iph2 = ipv6_hdr(p); + first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; - /* All fields must match except length. */ + /* All fields must match except length and Traffic Class. */ if (nlen != skb_network_header_len(p) || - memcmp(iph, iph2, offsetof(struct ipv6hdr, payload_len)) || + (first_word & htonl(0xF00FFFFF)) || memcmp(&iph->nexthdr, &iph2->nexthdr, nlen - offsetof(struct ipv6hdr, nexthdr))) { NAPI_GRO_CB(p)->same_flow = 0; continue; } - + /* flush if Traffic Class fields are different */ + NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); NAPI_GRO_CB(p)->flush |= flush; } @@ -927,7 +923,7 @@ static int ipv6_gro_complete(struct sk_buff *skb) sizeof(*iph)); rcu_read_lock(); - ops = rcu_dereference(inet6_protos[IPV6_GRO_CB(skb)->proto]); + ops = rcu_dereference(inet6_protos[NAPI_GRO_CB(skb)->proto]); if (WARN_ON(!ops || !ops->gro_complete)) goto out_unlock; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 56f6d5d..cc4c809 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -50,6 +50,7 @@ enum { * local */ IP_VS_RT_MODE_CONNECT = 8, /* Always bind route to saddr */ + IP_VS_RT_MODE_KNOWN_NH = 16,/* Route via remote addr */ }; /* @@ -113,6 +114,8 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, fl4.daddr = daddr; fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0; fl4.flowi4_tos = rtos; + fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ? + FLOWI_FLAG_KNOWN_NH : 0; retry: rt = ip_route_output_key(net, &fl4); @@ -1061,7 +1064,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(iph->tos), IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL, NULL))) + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_KNOWN_NH, NULL))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0f2e3ad..01e944a 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -169,6 +169,8 @@ static void netlink_sock_destruct(struct sock *sk) if (nlk->cb) { if (nlk->cb->done) nlk->cb->done(nlk->cb); + + module_put(nlk->cb->module); netlink_destroy_callback(nlk->cb); } @@ -1758,6 +1760,7 @@ static int netlink_dump(struct sock *sk) nlk->cb = NULL; mutex_unlock(nlk->cb_mutex); + module_put(cb->module); netlink_consume_callback(cb); return 0; @@ -1767,9 +1770,9 @@ errout_skb: return err; } -int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, - const struct nlmsghdr *nlh, - struct netlink_dump_control *control) +int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct netlink_dump_control *control) { struct netlink_callback *cb; struct sock *sk; @@ -1784,6 +1787,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->done = control->done; cb->nlh = nlh; cb->data = control->data; + cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; atomic_inc(&skb->users); cb->skb = skb; @@ -1794,19 +1798,28 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, return -ECONNREFUSED; } nlk = nlk_sk(sk); - /* A dump is in progress... */ + mutex_lock(nlk->cb_mutex); + /* A dump is in progress... */ if (nlk->cb) { mutex_unlock(nlk->cb_mutex); netlink_destroy_callback(cb); - sock_put(sk); - return -EBUSY; + ret = -EBUSY; + goto out; } + /* add reference of module which cb->dump belongs to */ + if (!try_module_get(cb->module)) { + mutex_unlock(nlk->cb_mutex); + netlink_destroy_callback(cb); + ret = -EPROTONOSUPPORT; + goto out; + } + nlk->cb = cb; mutex_unlock(nlk->cb_mutex); ret = netlink_dump(sk); - +out: sock_put(sk); if (ret) @@ -1817,7 +1830,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, */ return -EINTR; } -EXPORT_SYMBOL(netlink_dump_start); +EXPORT_SYMBOL(__netlink_dump_start); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) { |