The following commit has been merged in the master branch: commit f1e7b73acc26e8908af783bcd3a9900fd80688f5 Merge: 218774dc341f219bfcf940304a081b121a0e8099 fc16e884a2320198b8cb7bc2fdcf6b4485e79709 Author: David S. Miller davem@davemloft.net Date: Tue Jan 29 15:32:13 2013 -0500

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Bring in the 'net' tree so that we can get some ipv4/ipv6 bug fixes that some net-next work will build upon.

Signed-off-by: David S. Miller davem@davemloft.net

diff --combined MAINTAINERS index a7aadea,76ae4aa..b5ab4d9 --- a/MAINTAINERS +++ b/MAINTAINERS @@@ -1972,9 -1972,9 +1972,9 @@@ S: Maintaine F: drivers/usb/host/ohci-ep93xx.c

CIRRUS LOGIC CS4270 SOUND DRIVER - M: Timur Tabi timur@freescale.com + M: Timur Tabi timur@tabi.org L: alsa-devel@alsa-project.org (moderated for non-subscribers) - S: Supported + S: Odd Fixes F: sound/soc/codecs/cs4270*

CLEANCACHE API @@@ -2966,7 -2966,7 +2966,7 @@@ S: Maintaine F: drivers/net/ethernet/i825xx/eexpress.*

ETHERNET BRIDGE - M: Stephen Hemminger shemminger@vyatta.com + M: Stephen Hemminger stephen@networkplumber.org L: bridge@lists.linux-foundation.org L: netdev@vger.kernel.org W: http://www.linuxfoundation.org/en/Net:Bridge @@@ -2974,6 -2974,11 +2974,6 @@@ S: Maintaine F: include/linux/netfilter_bridge/ F: net/bridge/

-ETHERTEAM 16I DRIVER -M: Mika Kuoppala miku@iki.fi -S: Maintained -F: drivers/net/ethernet/fujitsu/eth16i.c - EXT2 FILE SYSTEM M: Jan Kara jack@suse.cz L: linux-ext4@vger.kernel.org @@@ -3186,9 -3191,9 +3186,9 @@@ F: include/uapi/video F: include/uapi/linux/fb.h

FREESCALE DIU FRAMEBUFFER DRIVER - M: Timur Tabi timur@freescale.com + M: Timur Tabi timur@tabi.org L: linux-fbdev@vger.kernel.org - S: Supported + S: Maintained F: drivers/video/fsl-diu-fb.*

FREESCALE DMA DRIVER @@@ -3223,9 -3228,8 +3223,8 @@@ F: drivers/net/ethernet/freescale/fs_en F: include/linux/fs_enet_pd.h

FREESCALE QUICC ENGINE LIBRARY - M: Timur Tabi timur@freescale.com L: linuxppc-dev@lists.ozlabs.org - S: Supported + S: Orphan F: arch/powerpc/sysdev/qe_lib/ F: arch/powerpc/include/asm/*qe.h

@@@ -3244,16 -3248,16 +3243,16 @@@ S: Maintaine F: drivers/net/ethernet/freescale/ucc_geth*

FREESCALE QUICC ENGINE UCC UART DRIVER - M: Timur Tabi timur@freescale.com + M: Timur Tabi timur@tabi.org L: linuxppc-dev@lists.ozlabs.org - S: Supported + S: Maintained F: drivers/tty/serial/ucc_uart.c

FREESCALE SOC SOUND DRIVERS - M: Timur Tabi timur@freescale.com + M: Timur Tabi timur@tabi.org L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: linuxppc-dev@lists.ozlabs.org - S: Supported + S: Maintained F: sound/soc/fsl/fsl* F: sound/soc/fsl/mpc8610_hpcd.c

@@@ -4901,7 -4905,7 +4900,7 @@@ S: Maintaine

MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) M: Mirko Lindner mlindner@marvell.com - M: Stephen Hemminger shemminger@vyatta.com + M: Stephen Hemminger stephen@networkplumber.org L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/marvell/sk* @@@ -5176,7 -5180,7 +5175,7 @@@ S: Supporte F: drivers/infiniband/hw/nes/

NETEM NETWORK EMULATOR - M: Stephen Hemminger shemminger@vyatta.com + M: Stephen Hemminger stephen@networkplumber.org L: netem@lists.linux-foundation.org S: Maintained F: net/sched/sch_netem.c @@@ -5365,6 -5369,13 +5364,6 @@@ F: include/linux/sunrpc F: include/uapi/linux/nfs* F: include/uapi/linux/sunrpc/

-NI5010 NETWORK DRIVER -M: Jan-Pascal van Best janpascal@vanbest.org -M: Andreas Mohr andi@lisas.de -L: netdev@vger.kernel.org -S: Maintained -F: drivers/net/ethernet/racal/ni5010.* - NILFS2 FILESYSTEM M: KONISHI Ryusuke konishi.ryusuke@lab.ntt.co.jp L: linux-nilfs@vger.kernel.org @@@ -6574,7 -6585,7 +6573,7 @@@ F: drivers/media/platform/s3c-camif F: include/media/s3c_camif.h

SERIAL DRIVERS - M: Alan Cox alan@linux.intel.com + M: Greg Kroah-Hartman gregkh@linuxfoundation.org L: linux-serial@vger.kernel.org S: Maintained F: drivers/tty/serial diff --combined drivers/net/can/c_can/c_can.c index 57eb1e7,58607f1..285f763 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@@ -39,7 -39,6 +39,7 @@@ #include <linux/can.h> #include <linux/can/dev.h> #include <linux/can/error.h> +#include <linux/can/led.h>

#include "c_can.h"

@@@ -478,8 -477,6 +478,8 @@@ static int c_can_read_msg_object(struc stats->rx_packets++; stats->rx_bytes += frame->can_dlc;

+ can_led_event(dev, CAN_LED_EVENT_RX); + return 0; }

@@@ -754,7 -751,6 +754,7 @@@ static void c_can_do_tx(struct net_devi C_CAN_IFACE(MSGCTRL_REG, 0)) & IF_MCONT_DLC_MASK; stats->tx_packets++; + can_led_event(dev, CAN_LED_EVENT_TX); c_can_inval_msg_object(dev, 0, msg_obj_no); } else { break; @@@ -964,7 -960,7 +964,7 @@@ static int c_can_handle_bus_err(struct break; case LEC_ACK_ERROR: netdev_dbg(dev, "ack error\n"); - cf->data[2] |= (CAN_ERR_PROT_LOC_ACK | + cf->data[3] |= (CAN_ERR_PROT_LOC_ACK | CAN_ERR_PROT_LOC_ACK_DEL); break; case LEC_BIT1_ERROR: @@@ -977,7 -973,7 +977,7 @@@ break; case LEC_CRC_ERROR: netdev_dbg(dev, "CRC error\n"); - cf->data[2] |= (CAN_ERR_PROT_LOC_CRC_SEQ | + cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ | CAN_ERR_PROT_LOC_CRC_DEL); break; default: @@@ -1119,8 -1115,6 +1119,8 @@@ static int c_can_open(struct net_devic

napi_enable(&priv->napi);

+ can_led_event(dev, CAN_LED_EVENT_OPEN); + /* start the c_can controller */ c_can_start(dev);

@@@ -1149,8 -1143,6 +1149,8 @@@ static int c_can_close(struct net_devic c_can_reset_ram(priv, false); c_can_pm_runtime_put_sync(priv);

+ can_led_event(dev, CAN_LED_EVENT_STOP); + return 0; }

@@@ -1276,8 -1268,6 +1276,8 @@@ int register_c_can_dev(struct net_devic err = register_candev(dev); if (err) c_can_pm_runtime_disable(priv); + else + devm_can_led_init(dev);

return err; } diff --combined drivers/net/can/ti_hecc.c index f52a975,300581b..f21fc37 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@@ -50,7 -50,6 +50,7 @@@

#include <linux/can/dev.h> #include <linux/can/error.h> +#include <linux/can/led.h> #include <linux/can/platform/ti_hecc.h>

#define DRV_NAME "ti_hecc" @@@ -594,7 -593,6 +594,7 @@@ static int ti_hecc_rx_pkt(struct ti_hec spin_unlock_irqrestore(&priv->mbx_lock, flags);

stats->rx_bytes += cf->can_dlc; + can_led_event(priv->ndev, CAN_LED_EVENT_RX); netif_receive_skb(skb); stats->rx_packets++;

@@@ -748,12 -746,12 +748,12 @@@ static int ti_hecc_error(struct net_dev } if (err_status & HECC_CANES_CRCE) { hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE); - cf->data[2] |= CAN_ERR_PROT_LOC_CRC_SEQ | + cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ | CAN_ERR_PROT_LOC_CRC_DEL; } if (err_status & HECC_CANES_ACKE) { hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE); - cf->data[2] |= CAN_ERR_PROT_LOC_ACK | + cf->data[3] |= CAN_ERR_PROT_LOC_ACK | CAN_ERR_PROT_LOC_ACK_DEL; } } @@@ -798,7 -796,6 +798,7 @@@ static irqreturn_t ti_hecc_interrupt(in stats->tx_bytes += hecc_read_mbx(priv, mbxno, HECC_CANMCF) & 0xF; stats->tx_packets++; + can_led_event(ndev, CAN_LED_EVENT_TX); can_get_echo_skb(ndev, mbxno); --priv->tx_tail; } @@@ -854,8 -851,6 +854,8 @@@ static int ti_hecc_open(struct net_devi return err; }

+ can_led_event(ndev, CAN_LED_EVENT_OPEN); + ti_hecc_start(ndev); napi_enable(&priv->napi); netif_start_queue(ndev); @@@ -874,8 -869,6 +874,8 @@@ static int ti_hecc_close(struct net_dev close_candev(ndev); ti_hecc_transceiver_switch(priv, 0);

+ can_led_event(ndev, CAN_LED_EVENT_STOP); + return 0; }

@@@ -968,9 -961,6 +968,9 @@@ static int ti_hecc_probe(struct platfor dev_err(&pdev->dev, "register_candev() failed\n"); goto probe_exit_clk; } + + devm_can_led_init(ndev); + dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%u)\n", priv->base, (u32) ndev->irq);

diff --combined drivers/net/ethernet/calxeda/xgmac.c index a345e24,f7f0290..a170065 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@@ -548,6 -548,10 +548,10 @@@ static int desc_get_rx_status(struct xg return -1; }

+ /* All frames should fit into a single buffer */ + if (!(status & RXDESC_FIRST_SEG) || !(status & RXDESC_LAST_SEG)) + return -1; + /* Check if packet has checksum already */ if ((status & RXDESC_FRAME_TYPE) && (status & RXDESC_EXT_STATUS) && !(ext_status & RXDESC_IP_PAYLOAD_MASK)) @@@ -1459,6 -1463,7 +1463,6 @@@ static int xgmac_set_mac_address(struc if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL;

- dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);

xgmac_set_mac_addr(ioaddr, dev->dev_addr, 0); diff --combined drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 424f8ed,c306df7..c6c05bf --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@@ -1994,9 -1994,20 +1994,20 @@@ static int set_coalesce(struct net_devi { const struct port_info *pi = netdev_priv(dev); struct adapter *adap = pi->adapter; - - return set_rxq_intr_params(adap, &adap->sge.ethrxq[pi->first_qset].rspq, - c->rx_coalesce_usecs, c->rx_max_coalesced_frames); + struct sge_rspq *q; + int i; + int r = 0; + + for (i = pi->first_qset; i < pi->first_qset + pi->nqsets; i++) { + q = &adap->sge.ethrxq[i].rspq; + r = set_rxq_intr_params(adap, q, c->rx_coalesce_usecs, + c->rx_max_coalesced_frames); + if (r) { + dev_err(&dev->dev, "failed to set coalesce %d\n", r); + break; + } + } + return r; }

static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) @@@ -4016,7 -4027,8 +4027,7 @@@ static int adap_init0_no_config(struct VFRES_NEQ, VFRES_NETHCTRL, VFRES_NIQFLINT, VFRES_NIQ, VFRES_TC, VFRES_NVI, - FW_PFVF_CMD_CMASK_GET( - FW_PFVF_CMD_CMASK_MASK), + FW_PFVF_CMD_CMASK_MASK, pfvfres_pmask( adapter, pf, vf), VFRES_NEXACTF, @@@ -5130,7 -5142,7 +5141,7 @@@ static int __init cxgb4_init_module(voi /* Debugfs support is optional, just warn if this fails */ cxgb4_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); if (!cxgb4_debugfs_root) - pr_warning("could not create debugfs entry, continuing\n"); + pr_warn("could not create debugfs entry, continuing\n");

ret = pci_register_driver(&cxgb4_driver); if (ret < 0) diff --combined drivers/net/ethernet/mellanox/mlx4/en_tx.c index 3c5ffd2,6771b69..30724d8 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@@ -515,6 -515,10 +515,6 @@@ static void build_inline_wqe(struct mlx wmb(); inl->byte_count = cpu_to_be32(1 << 31 | (skb->len - spc)); } - tx_desc->ctrl.vlan_tag = cpu_to_be16(*vlan_tag); - tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN * - (!!vlan_tx_tag_present(skb)); - tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f; }

u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb) @@@ -588,21 -592,7 +588,21 @@@ netdev_tx_t mlx4_en_xmit(struct sk_buf netif_tx_stop_queue(ring->tx_queue); priv->port_stats.queue_stopped++;

- return NETDEV_TX_BUSY; + /* If queue was emptied after the if, and before the + * stop_queue - need to wake the queue, or else it will remain + * stopped forever. + * Need a memory barrier to make sure ring->cons was not + * updated before queue was stopped. + */ + wmb(); + + if (unlikely(((int)(ring->prod - ring->cons)) <= + ring->size - HEADROOM - MAX_DESC_TXBBS)) { + netif_tx_wake_queue(ring->tx_queue); + priv->port_stats.wake_queue++; + } else { + return NETDEV_TX_BUSY; + } }

/* Track current inflight packets for performance analysis */ @@@ -640,10 -630,15 +640,15 @@@ ring->tx_csum++; }

- /* Copy dst mac address to wqe */ - ethh = (struct ethhdr *)skb->data; - tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest); - tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2)); + if (mlx4_is_mfunc(mdev->dev) || priv->validate_loopback) { + /* Copy dst mac address to wqe. This allows loopback in eSwitch, + * so that VFs and PF can communicate with each other + */ + ethh = (struct ethhdr *)skb->data; + tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest); + tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2)); + } + /* Handle LSO (TSO) packets */ if (lso_header_size) { /* Mark opcode as LSO */ diff --combined drivers/net/ethernet/mellanox/mlx4/main.c index 983fd3d,a6542d7..f1ee52d --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@@ -1790,15 -1790,8 +1790,8 @@@ static void mlx4_enable_msi_x(struct ml int i;

if (msi_x) { - /* In multifunction mode each function gets 2 msi-X vectors - * one for data path completions anf the other for asynch events - * or command completions */ - if (mlx4_is_mfunc(dev)) { - nreq = 2; - } else { - nreq = min_t(int, dev->caps.num_eqs - - dev->caps.reserved_eqs, nreq); - } + nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, + nreq);

entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); if (!entries) @@@ -2169,8 -2162,7 +2162,8 @@@ slave_start dev->num_slaves = MLX4_MAX_NUM_SLAVES; else { dev->num_slaves = 0; - if (mlx4_multi_func_init(dev)) { + err = mlx4_multi_func_init(dev); + if (err) { mlx4_err(dev, "Failed to init slave mfunc" " interface, aborting.\n"); goto err_cmd; @@@ -2194,8 -2186,7 +2187,8 @@@ /* In master functions, the communication channel must be initialized * after obtaining its address from fw */ if (mlx4_is_master(dev)) { - if (mlx4_multi_func_init(dev)) { + err = mlx4_multi_func_init(dev); + if (err) { mlx4_err(dev, "Failed to init master mfunc" "interface, aborting.\n"); goto err_close; @@@ -2212,7 -2203,6 +2205,7 @@@ mlx4_enable_msi_x(dev); if ((mlx4_is_mfunc(dev)) && !(dev->flags & MLX4_FLAG_MSI_X)) { + err = -ENOSYS; mlx4_err(dev, "INTx is not supported in multi-function mode." " aborting.\n"); goto err_free_eq; diff --combined drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 8e40ea0,69e321a..7a849fc --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@@ -501,11 -501,12 +501,11 @@@ netxen_read_mac_addr(struct netxen_adap for (i = 0; i < 6; i++) netdev->dev_addr[i] = *(p + 5 - i);

- memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); memcpy(adapter->mac_addr, netdev->dev_addr, netdev->addr_len);

/* set station address */

- if (!is_valid_ether_addr(netdev->perm_addr)) + if (!is_valid_ether_addr(netdev->dev_addr)) dev_warn(&pdev->dev, "Bad MAC address %pM.\n", netdev->dev_addr);

return 0; @@@ -1962,10 -1963,12 +1962,12 @@@ unwind while (--i >= 0) { nf = &pbuf->frag_array[i+1]; pci_unmap_page(pdev, nf->dma, nf->length, PCI_DMA_TODEVICE); + nf->dma = 0ULL; }

nf = &pbuf->frag_array[0]; pci_unmap_single(pdev, nf->dma, skb_headlen(skb), PCI_DMA_TODEVICE); + nf->dma = 0ULL;

out_err: return -ENOMEM; diff --combined drivers/net/ethernet/realtek/r8169.c index 97fdbb1,1170232..4208f28 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@@ -83,7 -83,7 +83,7 @@@ static const int multicast_filter_limi #define R8169_REGS_SIZE 256 #define R8169_NAPI_WEIGHT 64 #define NUM_TX_DESC 64 /* Number of Tx descriptor registers */ -#define NUM_RX_DESC 256 /* Number of Rx descriptor registers */ +#define NUM_RX_DESC 256U /* Number of Rx descriptor registers */ #define R8169_TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc)) #define R8169_RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc))

@@@ -727,6 -727,7 +727,6 @@@ struct rtl8169_private u16 mac_version; u32 cur_rx; /* Index into the Rx descriptor buffer of next Rx pkt. */ u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */ - u32 dirty_rx; u32 dirty_tx; struct rtl8169_stats rx_stats; struct rtl8169_stats tx_stats; @@@ -1825,8 -1826,6 +1825,6 @@@ static void rtl8169_rx_vlan_tag(struct

if (opts2 & RxVlanTag) __vlan_hwaccel_put_tag(skb, swab16(opts2 & 0xffff)); - - desc->opts2 = 0; }

static int rtl8169_gset_tbi(struct net_device *dev, struct ethtool_cmd *cmd) @@@ -4176,7 -4175,7 +4174,7 @@@ static void rtl_init_rxcfg(struct rtl81

static void rtl8169_init_ring_indexes(struct rtl8169_private *tp) { - tp->dirty_tx = tp->dirty_rx = tp->cur_tx = tp->cur_rx = 0; + tp->dirty_tx = tp->cur_tx = tp->cur_rx = 0; }

static void rtl_hw_jumbo_enable(struct rtl8169_private *tp) @@@ -5919,7 -5918,7 +5917,7 @@@ static void rtl8169_pcierr_interrupt(st PCI_STATUS_REC_TARGET_ABORT | PCI_STATUS_SIG_TARGET_ABORT));

/* The infamous DAC f*ckup only happens at boot time */ - if ((tp->cp_cmd & PCIDAC) && !tp->dirty_rx && !tp->cur_rx) { + if ((tp->cp_cmd & PCIDAC) && !tp->cur_rx) { void __iomem *ioaddr = tp->mmio_addr;

netif_info(tp, intr, dev, "disabling PCI DAC\n"); @@@ -6034,8 -6033,10 +6032,8 @@@ static int rtl_rx(struct net_device *de unsigned int count;

cur_rx = tp->cur_rx; - rx_left = NUM_RX_DESC + tp->dirty_rx - cur_rx; - rx_left = min(rx_left, budget);

- for (; rx_left > 0; rx_left--, cur_rx++) { + for (rx_left = min(budget, NUM_RX_DESC); rx_left > 0; rx_left--, cur_rx++) { unsigned int entry = cur_rx % NUM_RX_DESC; struct RxDesc *desc = tp->RxDescArray + entry; u32 status; @@@ -6061,8 -6062,6 +6059,6 @@@ !(status & (RxRWT | RxFOVF)) && (dev->features & NETIF_F_RXALL)) goto process_pkt; - - rtl8169_mark_to_asic(desc, rx_buf_sz); } else { struct sk_buff *skb; dma_addr_t addr; @@@ -6083,16 -6082,14 +6079,14 @@@ process_pkt if (unlikely(rtl8169_fragmented_frame(status))) { dev->stats.rx_dropped++; dev->stats.rx_length_errors++; - rtl8169_mark_to_asic(desc, rx_buf_sz); - continue; + goto release_descriptor; }

skb = rtl8169_try_rx_copy(tp->Rx_databuff[entry], tp, pkt_size, addr); - rtl8169_mark_to_asic(desc, rx_buf_sz); if (!skb) { dev->stats.rx_dropped++; - continue; + goto release_descriptor; }

rtl8169_rx_csum(skb, status); @@@ -6108,18 -6105,17 +6102,15 @@@ tp->rx_stats.bytes += pkt_size; u64_stats_update_end(&tp->rx_stats.syncp); } - - /* Work around for AMD plateform. */ - if ((desc->opts2 & cpu_to_le32(0xfffe000)) && - (tp->mac_version == RTL_GIGA_MAC_VER_05)) { - desc->opts2 = 0; - cur_rx++; - } + release_descriptor: + desc->opts2 = 0; + wmb(); + rtl8169_mark_to_asic(desc, rx_buf_sz); }

count = cur_rx - tp->cur_rx; tp->cur_rx = cur_rx;

- tp->dirty_rx += count; - return count; }

@@@ -6943,6 -6939,7 +6934,6 @@@ rtl_init_one(struct pci_dev *pdev, cons /* Get MAC address */ for (i = 0; i < ETH_ALEN; i++) dev->dev_addr[i] = RTL_R8(MAC0 + i); - memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);

SET_ETHTOOL_OPS(dev, &rtl8169_ethtool_ops); dev->watchdog_timeo = RTL8169_TX_TIMEOUT; diff --combined drivers/net/hyperv/netvsc_drv.c index a9975c7,8264f0e..d5202a4 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@@ -304,9 -304,9 +304,9 @@@ int netvsc_recv_callback(struct hv_devi static void netvsc_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) { - strcpy(info->driver, KBUILD_MODNAME); - strcpy(info->version, HV_DRV_VERSION); - strcpy(info->fw_version, "N/A"); + strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); + strlcpy(info->version, HV_DRV_VERSION, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); }

static int netvsc_change_mtu(struct net_device *ndev, int mtu) @@@ -349,7 -349,7 +349,7 @@@ static int netvsc_set_mac_addr(struct n struct net_device_context *ndevctx = netdev_priv(ndev); struct hv_device *hdev = ndevctx->device_ctx; struct sockaddr *addr = p; - char save_adr[14]; + char save_adr[ETH_ALEN]; unsigned char save_aatype; int err;

diff --combined drivers/net/macvlan.c index 1047e58,d3fb97d..7b44ebd --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@@ -375,6 -375,7 +375,6 @@@ static int macvlan_set_mac_address(stru

if (!(dev->flags & IFF_UP)) { /* Just copy in the new address */ - dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); } else { /* Rehash and update the device filters */ @@@ -585,8 -586,8 +585,8 @@@ static int macvlan_fdb_del(struct ndms static void macvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { - snprintf(drvinfo->driver, 32, "macvlan"); - snprintf(drvinfo->version, 32, "0.1"); + strlcpy(drvinfo->driver, "macvlan", sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, "0.1", sizeof(drvinfo->version)); }

static int macvlan_ethtool_get_settings(struct net_device *dev, @@@ -764,22 -765,16 +764,22 @@@ int macvlan_common_newlink(struct net * memcpy(dev->dev_addr, lowerdev->dev_addr, ETH_ALEN); }

+ err = netdev_upper_dev_link(lowerdev, dev); + if (err) + goto destroy_port; + port->count += 1; err = register_netdevice(dev); if (err < 0) - goto destroy_port; + goto upper_dev_unlink;

list_add_tail(&vlan->list, &port->vlans); netif_stacked_transfer_operstate(lowerdev, dev);

return 0;

+upper_dev_unlink: + netdev_upper_dev_unlink(lowerdev, dev); destroy_port: port->count -= 1; if (!port->count) @@@ -803,7 -798,6 +803,7 @@@ void macvlan_dellink(struct net_device

list_del(&vlan->list); unregister_netdevice_queue(dev, head); + netdev_upper_dev_unlink(vlan->lowerdev, dev); } EXPORT_SYMBOL_GPL(macvlan_dellink);

@@@ -828,7 -822,10 +828,10 @@@ static int macvlan_changelink(struct ne

static size_t macvlan_get_size(const struct net_device *dev) { - return nla_total_size(4); + return (0 + + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + ); }

static int macvlan_fill_info(struct sk_buff *skb, diff --combined drivers/net/tun.c index 293ce8d,cc09b67..8d208dd --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@@ -109,11 -109,11 +109,11 @@@ struct tap_filter unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; };

- /* 1024 is probably a high enough limit: modern hypervisors seem to support on - * the order of 100-200 CPUs so this leaves us some breathing space if we want - * to match a queue per guest CPU. - */ - #define MAX_TAP_QUEUES 1024 + /* DEFAULT_MAX_NUM_RSS_QUEUES were choosed to let the rx/tx queues allocated for + * the netdevice to be fit in one page. So we can make sure the success of + * memory allocation. TODO: increase the limit. */ + #define MAX_TAP_QUEUES DEFAULT_MAX_NUM_RSS_QUEUES + #define MAX_TAP_FLOWS 4096

#define TUN_FLOW_EXPIRE (3 * HZ)

@@@ -186,6 -186,7 +186,7 @@@ struct tun_struct unsigned int numdisabled; struct list_head disabled; void *security; + u32 flow_count; };

static inline u32 tun_hashfn(u32 rxhash) @@@ -219,6 -220,7 +220,7 @@@ static struct tun_flow_entry *tun_flow_ e->queue_index = queue_index; e->tun = tun; hlist_add_head_rcu(&e->hash_link, head); + ++tun->flow_count; } return e; } @@@ -229,6 -231,7 +231,7 @@@ static void tun_flow_delete(struct tun_ e->rxhash, e->queue_index); hlist_del_rcu(&e->hash_link); kfree_rcu(e, rcu); + --tun->flow_count; }

static void tun_flow_flush(struct tun_struct *tun) @@@ -318,7 -321,8 +321,8 @@@ static void tun_flow_update(struct tun_ e->updated = jiffies; } else { spin_lock_bh(&tun->lock); - if (!tun_flow_find(head, rxhash)) + if (!tun_flow_find(head, rxhash) && + tun->flow_count < MAX_TAP_FLOWS) tun_flow_create(tun, head, rxhash, queue_index);

if (!timer_pending(&tun->flow_gc_timer)) @@@ -1005,7 -1009,6 +1009,7 @@@ static int zerocopy_sg_from_iovec(struc skb->data_len += len; skb->len += len; skb->truesize += truesize; + skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; atomic_add(truesize, &skb->sk->sk_wmem_alloc); while (len) { int off = base & ~PAGE_MASK; @@@ -1151,18 -1154,16 +1155,18 @@@ static ssize_t tun_get_user(struct tun_ }

if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { + unsigned short gso_type = 0; + pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_TCPV6: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + gso_type = SKB_GSO_UDP; break; default: tun->dev->stats.rx_frame_errors++; @@@ -1171,10 -1172,9 +1175,10 @@@ }

if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + gso_type |= SKB_GSO_TCP_ECN;

skb_shinfo(skb)->gso_size = gso.gso_size; + skb_shinfo(skb)->gso_type |= gso_type; if (skb_shinfo(skb)->gso_size == 0) { tun->dev->stats.rx_frame_errors++; kfree_skb(skb); @@@ -1587,6 -1587,8 +1591,8 @@@ static int tun_set_iff(struct net *net else { char *name; unsigned long flags = 0; + int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? + MAX_TAP_QUEUES : 1;

if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@@ -1610,8 -1612,8 +1616,8 @@@ name = ifr->ifr_name;

dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, - tun_setup, - MAX_TAP_QUEUES, MAX_TAP_QUEUES); + tun_setup, queues, queues); + if (!dev) return -ENOMEM;

diff --combined drivers/net/usb/cdc_ncm.c index 016aa6f,9197b2c..b5ad7ea --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@@ -65,9 -65,9 +65,9 @@@ cdc_ncm_get_drvinfo(struct net_device * { struct usbnet *dev = netdev_priv(net);

- strncpy(info->driver, dev->driver_name, sizeof(info->driver)); - strncpy(info->version, DRIVER_VERSION, sizeof(info->version)); - strncpy(info->fw_version, dev->driver_info->description, + strlcpy(info->driver, dev->driver_name, sizeof(info->driver)); + strlcpy(info->version, DRIVER_VERSION, sizeof(info->version)); + strlcpy(info->fw_version, dev->driver_info->description, sizeof(info->fw_version)); usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); } @@@ -435,6 -435,13 +435,13 @@@ advance len -= temp; }

+ /* some buggy devices have an IAD but no CDC Union */ + if (!ctx->union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) { + ctx->control = intf; + ctx->data = usb_ifnum_to_if(dev->udev, intf->cur_altsetting->desc.bInterfaceNumber + 1); + dev_dbg(&intf->dev, "CDC Union missing - got slave from IAD\n"); + } + /* check if we got everything */ if ((ctx->control == NULL) || (ctx->data == NULL) || ((!ctx->mbim_desc) && ((ctx->ether_desc == NULL) || (ctx->control != intf)))) @@@ -497,7 -504,8 +504,8 @@@ error2: usb_set_intfdata(ctx->control, NULL); usb_set_intfdata(ctx->data, NULL); - usb_driver_release_interface(driver, ctx->data); + if (ctx->data != ctx->control) + usb_driver_release_interface(driver, ctx->data); error: cdc_ncm_free((struct cdc_ncm_ctx *)dev->data[0]); dev->data[0] = 0; @@@ -1155,6 -1163,20 +1163,20 @@@ static const struct driver_info wwan_in .tx_fixup = cdc_ncm_tx_fixup, };

+ /* Same as wwan_info, but with FLAG_NOARP */ + static const struct driver_info wwan_noarp_info = { + .description = "Mobile Broadband Network Device (NO ARP)", + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_WWAN | FLAG_NOARP, + .bind = cdc_ncm_bind, + .unbind = cdc_ncm_unbind, + .check_connect = cdc_ncm_check_connect, + .manage_power = usbnet_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 @@@ -1194,6 -1216,13 +1216,13 @@@ .driver_info = (unsigned long)&wwan_info, },

+ /* Infineon(now Intel) HSPA Modem platform */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1519, 0x0443, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_noarp_info, + }, + /* Generic CDC-NCM devices */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), diff --combined drivers/net/usb/dm9601.c index 0794004,d7e9944..174e5ec --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@@ -45,6 -45,12 +45,12 @@@ #define DM_MCAST_ADDR 0x16 /* 8 bytes */ #define DM_GPR_CTRL 0x1e #define DM_GPR_DATA 0x1f + #define DM_CHIP_ID 0x2c + #define DM_MODE_CTRL 0x91 /* only on dm9620 */ + + /* chip id values */ + #define ID_DM9601 0 + #define ID_DM9620 1

#define DM_MAX_MCAST 64 #define DM_MCAST_SIZE 8 @@@ -53,7 -59,6 +59,6 @@@ #define DM_RX_OVERHEAD 7 /* 3 byte header + 4 byte crc tail */ #define DM_TIMEOUT 1000

- static int dm_read(struct usbnet *dev, u8 reg, u16 length, void *data) { int err; @@@ -84,32 -89,23 +89,23 @@@ static int dm_write(struct usbnet *dev

static int dm_write_reg(struct usbnet *dev, u8 reg, u8 value) { - return usbnet_write_cmd(dev, DM_WRITE_REGS, + return usbnet_write_cmd(dev, DM_WRITE_REG, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, reg, NULL, 0); }

- static void dm_write_async_helper(struct usbnet *dev, u8 reg, u8 value, - u16 length, void *data) + static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) { usbnet_write_cmd_async(dev, DM_WRITE_REGS, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - value, reg, data, length); - } - - static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) - { - netdev_dbg(dev->net, "dm_write_async() reg=0x%02x length=%d\n", reg, length); - - dm_write_async_helper(dev, reg, 0, length, data); + 0, reg, data, length); }

static void dm_write_reg_async(struct usbnet *dev, u8 reg, u8 value) { - netdev_dbg(dev->net, "dm_write_reg_async() reg=0x%02x value=0x%02x\n", - reg, value); - - dm_write_async_helper(dev, reg, value, 0, NULL); + usbnet_write_cmd_async(dev, DM_WRITE_REG, + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, + value, reg, NULL, 0); }

static int dm_read_shared_word(struct usbnet *dev, int phy, u8 reg, __le16 *value) @@@ -122,7 -118,7 +118,7 @@@ dm_write_reg(dev, DM_SHARED_CTRL, phy ? 0xc : 0x4);

for (i = 0; i < DM_TIMEOUT; i++) { - u8 tmp; + u8 tmp = 0;

udelay(1); ret = dm_read_reg(dev, DM_SHARED_CTRL, &tmp); @@@ -165,7 -161,7 +161,7 @@@ static int dm_write_shared_word(struct dm_write_reg(dev, DM_SHARED_CTRL, phy ? 0x1a : 0x12);

for (i = 0; i < DM_TIMEOUT; i++) { - u8 tmp; + u8 tmp = 0;

udelay(1); ret = dm_read_reg(dev, DM_SHARED_CTRL, &tmp); @@@ -358,7 -354,7 +354,7 @@@ static const struct net_device_ops dm96 static int dm9601_bind(struct usbnet *dev, struct usb_interface *intf) { int ret; - u8 mac[ETH_ALEN]; + u8 mac[ETH_ALEN], id;

ret = usbnet_get_endpoints(dev, intf); if (ret) @@@ -399,6 -395,24 +395,24 @@@ __dm9601_set_mac_address(dev); }

+ if (dm_read_reg(dev, DM_CHIP_ID, &id) < 0) { + netdev_err(dev->net, "Error reading chip ID\n"); + ret = -ENODEV; + goto out; + } + + /* put dm9620 devices in dm9601 mode */ + if (id == ID_DM9620) { + u8 mode; + + if (dm_read_reg(dev, DM_MODE_CTRL, &mode) < 0) { + netdev_err(dev->net, "Error reading MODE_CTRL\n"); + ret = -ENODEV; + goto out; + } + dm_write_reg(dev, DM_MODE_CTRL, mode & 0x7f); + } + /* power up phy */ dm_write_reg(dev, DM_GPR_CTRL, 1); dm_write_reg(dev, DM_GPR_DATA, 0); @@@ -581,6 -595,10 +595,10 @@@ static const struct usb_device_id produ USB_DEVICE(0x0a46, 0x9000), /* DM9000E */ .driver_info = (unsigned long)&dm9601_info, }, + { + USB_DEVICE(0x0a46, 0x9620), /* DM9620 USB to Fast Ethernet Adapter */ + .driver_info = (unsigned long)&dm9601_info, + }, {}, // END };

diff --combined drivers/net/virtio_net.c index 58914c8,35c00c5..eda2042 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@@ -26,6 -26,7 +26,7 @@@ #include <linux/scatterlist.h> #include <linux/if_vlan.h> #include <linux/slab.h> + #include <linux/cpu.h>

static int napi_weight = 128; module_param(napi_weight, int, 0444); @@@ -123,6 -124,12 +124,12 @@@ struct virtnet_info

/* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; + + /* Per-cpu variable to show the mapping from CPU to virtqueue */ + int __percpu *vq_index; + + /* CPU hot plug notifier */ + struct notifier_block nb; };

struct skb_vnet_hdr { @@@ -220,7 -227,6 +227,7 @@@ static void set_skb_frag(struct sk_buf skb->len += size; skb->truesize += PAGE_SIZE; skb_shinfo(skb)->nr_frags++; + skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; *len -= size; }

@@@ -380,18 -386,16 +387,18 @@@ static void receive_buf(struct receive_ ntohs(skb->protocol), skb->len, skb->pkt_type);

if (hdr->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) { + unsigned short gso_type = 0; + pr_debug("GSO!\n"); switch (hdr->hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_UDP: - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + gso_type = SKB_GSO_UDP; break; case VIRTIO_NET_HDR_GSO_TCPV6: - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + gso_type = SKB_GSO_TCPV6; break; default: net_warn_ratelimited("%s: bad gso type %u.\n", @@@ -400,7 -404,7 +407,7 @@@ }

if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + gso_type |= SKB_GSO_TCP_ECN;

skb_shinfo(skb)->gso_size = hdr->hdr.gso_size; if (skb_shinfo(skb)->gso_size == 0) { @@@ -408,7 -412,6 +415,7 @@@ goto frame_err; }

+ skb_shinfo(skb)->gso_type |= gso_type; /* Header must be checked, and gso_segs computed. */ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; skb_shinfo(skb)->gso_segs = 0; @@@ -757,77 -760,19 +764,77 @@@ static netdev_tx_t start_xmit(struct sk return NETDEV_TX_OK; }

+/* + * Send command via the control virtqueue and check status. Commands + * supported by the hypervisor, as indicated by feature bits, should + * never fail unless improperly formated. + */ +static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, + struct scatterlist *data, int out, int in) +{ + struct scatterlist *s, sg[VIRTNET_SEND_COMMAND_SG_MAX + 2]; + struct virtio_net_ctrl_hdr ctrl; + virtio_net_ctrl_ack status = ~0; + unsigned int tmp; + int i; + + /* Caller should know better */ + BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) || + (out + in > VIRTNET_SEND_COMMAND_SG_MAX)); + + out++; /* Add header */ + in++; /* Add return status */ + + ctrl.class = class; + ctrl.cmd = cmd; + + sg_init_table(sg, out + in); + + sg_set_buf(&sg[0], &ctrl, sizeof(ctrl)); + for_each_sg(data, s, out + in - 2, i) + sg_set_buf(&sg[i + 1], sg_virt(s), s->length); + sg_set_buf(&sg[out + in - 1], &status, sizeof(status)); + + BUG_ON(virtqueue_add_buf(vi->cvq, sg, out, in, vi, GFP_ATOMIC) < 0); + + virtqueue_kick(vi->cvq); + + /* Spin for a response, the kick causes an ioport write, trapping + * into the hypervisor, so the request should be handled immediately. + */ + while (!virtqueue_get_buf(vi->cvq, &tmp)) + cpu_relax(); + + return status == VIRTIO_NET_OK; +} + static int virtnet_set_mac_address(struct net_device *dev, void *p) { struct virtnet_info *vi = netdev_priv(dev); struct virtio_device *vdev = vi->vdev; int ret; + struct sockaddr *addr = p; + struct scatterlist sg;

- ret = eth_mac_addr(dev, p); + ret = eth_prepare_mac_addr_change(dev, p); if (ret) return ret;

- if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) + if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { + sg_init_one(&sg, addr->sa_data, dev->addr_len); + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, + VIRTIO_NET_CTRL_MAC_ADDR_SET, + &sg, 1, 0)) { + dev_warn(&vdev->dev, + "Failed to set mac address by vq command.\n"); + return -EINVAL; + } + } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) { vdev->config->set(vdev, offsetof(struct virtio_net_config, mac), - dev->dev_addr, dev->addr_len); + addr->sa_data, dev->addr_len); + } + + eth_commit_mac_addr_change(dev, p);

return 0; } @@@ -881,6 -826,51 +888,6 @@@ static void virtnet_netpoll(struct net_ } #endif

-/* - * Send command via the control virtqueue and check status. Commands - * supported by the hypervisor, as indicated by feature bits, should - * never fail unless improperly formated. - */ -static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, - struct scatterlist *data, int out, int in) -{ - struct scatterlist *s, sg[VIRTNET_SEND_COMMAND_SG_MAX + 2]; - struct virtio_net_ctrl_hdr ctrl; - virtio_net_ctrl_ack status = ~0; - unsigned int tmp; - int i; - - /* Caller should know better */ - BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) || - (out + in > VIRTNET_SEND_COMMAND_SG_MAX)); - - out++; /* Add header */ - in++; /* Add return status */ - - ctrl.class = class; - ctrl.cmd = cmd; - - sg_init_table(sg, out + in); - - sg_set_buf(&sg[0], &ctrl, sizeof(ctrl)); - for_each_sg(data, s, out + in - 2, i) - sg_set_buf(&sg[i + 1], sg_virt(s), s->length); - sg_set_buf(&sg[out + in - 1], &status, sizeof(status)); - - BUG_ON(virtqueue_add_buf(vi->cvq, sg, out, in, vi, GFP_ATOMIC) < 0); - - virtqueue_kick(vi->cvq); - - /* - * Spin for a response, the kick causes an ioport write, trapping - * into the hypervisor, so the request should be handled immediately. - */ - while (!virtqueue_get_buf(vi->cvq, &tmp)) - cpu_relax(); - - return status == VIRTIO_NET_OK; -} - static void virtnet_ack_link_announce(struct virtnet_info *vi) { rtnl_lock(); @@@ -1030,32 -1020,75 +1037,75 @@@ static int virtnet_vlan_rx_kill_vid(str return 0; }

- static void virtnet_set_affinity(struct virtnet_info *vi, bool set) + static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu) { int i; + int cpu; + + if (vi->affinity_hint_set) { + for (i = 0; i < vi->max_queue_pairs; i++) { + virtqueue_set_affinity(vi->rq[i].vq, -1); + virtqueue_set_affinity(vi->sq[i].vq, -1); + } + + vi->affinity_hint_set = false; + } + + i = 0; + for_each_online_cpu(cpu) { + if (cpu == hcpu) { + *per_cpu_ptr(vi->vq_index, cpu) = -1; + } else { + *per_cpu_ptr(vi->vq_index, cpu) = + ++i % vi->curr_queue_pairs; + } + } + } + + static void virtnet_set_affinity(struct virtnet_info *vi) + { + int i; + int cpu;

/* In multiqueue mode, when the number of cpu is equal to the number of * queue pairs, we let the queue pairs to be private to one cpu by * setting the affinity hint to eliminate the contention. */ - if ((vi->curr_queue_pairs == 1 || - vi->max_queue_pairs != num_online_cpus()) && set) { - if (vi->affinity_hint_set) - set = false; - else - return; + if (vi->curr_queue_pairs == 1 || + vi->max_queue_pairs != num_online_cpus()) { + virtnet_clean_affinity(vi, -1); + return; }

- for (i = 0; i < vi->max_queue_pairs; i++) { - int cpu = set ? i : -1; + i = 0; + for_each_online_cpu(cpu) { virtqueue_set_affinity(vi->rq[i].vq, cpu); virtqueue_set_affinity(vi->sq[i].vq, cpu); + *per_cpu_ptr(vi->vq_index, cpu) = i; + i++; }

- if (set) - vi->affinity_hint_set = true; - else - vi->affinity_hint_set = false; + vi->affinity_hint_set = true; + } + + static int virtnet_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) + { + struct virtnet_info *vi = container_of(nfb, struct virtnet_info, nb); + + switch(action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + case CPU_DEAD: + virtnet_set_affinity(vi); + break; + case CPU_DOWN_PREPARE: + virtnet_clean_affinity(vi, (long)hcpu); + break; + default: + break; + } + return NOTIFY_OK; }

static void virtnet_get_ringparam(struct net_device *dev, @@@ -1099,13 -1132,15 +1149,15 @@@ static int virtnet_set_channels(struct if (queue_pairs > vi->max_queue_pairs) return -EINVAL;

+ get_online_cpus(); err = virtnet_set_queues(vi, queue_pairs); if (!err) { netif_set_real_num_tx_queues(dev, queue_pairs); netif_set_real_num_rx_queues(dev, queue_pairs);

- virtnet_set_affinity(vi, true); + virtnet_set_affinity(vi); } + put_online_cpus();

return err; } @@@ -1144,12 -1179,19 +1196,19 @@@ static int virtnet_change_mtu(struct ne

/* To avoid contending a lock hold by a vcpu who would exit to host, select the * txq based on the processor id. */ static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb) { - int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : - smp_processor_id(); + int txq; + struct virtnet_info *vi = netdev_priv(dev); + + if (skb_rx_queue_recorded(skb)) { + txq = skb_get_rx_queue(skb); + } else { + txq = *__this_cpu_ptr(vi->vq_index); + if (txq == -1) + txq = 0; + }

while (unlikely(txq >= dev->real_num_tx_queues)) txq -= dev->real_num_tx_queues; @@@ -1265,7 -1307,7 +1324,7 @@@ static void virtnet_del_vqs(struct virt { struct virtio_device *vdev = vi->vdev;

- virtnet_set_affinity(vi, false); + virtnet_clean_affinity(vi, -1);

vdev->config->del_vqs(vdev);

@@@ -1388,7 -1430,10 +1447,10 @@@ static int init_vqs(struct virtnet_inf if (ret) goto err_free;

- virtnet_set_affinity(vi, true); + get_online_cpus(); + virtnet_set_affinity(vi); + put_online_cpus(); + return 0;

err_free: @@@ -1470,6 -1515,10 +1532,10 @@@ static int virtnet_probe(struct virtio_ if (vi->stats == NULL) goto free;

+ vi->vq_index = alloc_percpu(int); + if (vi->vq_index == NULL) + goto free_stats; + mutex_init(&vi->config_lock); vi->config_enable = true; INIT_WORK(&vi->config_work, virtnet_config_changed_work); @@@ -1493,7 -1542,7 +1559,7 @@@ /* Allocate/initialize the rx/tx queues, and invoke find_vqs */ err = init_vqs(vi); if (err) - goto free_stats; + goto free_index;

netif_set_real_num_tx_queues(dev, 1); netif_set_real_num_rx_queues(dev, 1); @@@ -1516,6 -1565,13 +1582,13 @@@ } }

+ vi->nb.notifier_call = &virtnet_cpu_callback; + err = register_hotcpu_notifier(&vi->nb); + if (err) { + pr_debug("virtio_net: registering cpu notifier failed\n"); + goto free_recv_bufs; + } + /* Assume link up if device can't report link status, otherwise get link status from config. */ if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { @@@ -1537,6 -1593,8 +1610,8 @@@ free_recv_bufs free_vqs: cancel_delayed_work_sync(&vi->refill); virtnet_del_vqs(vi); + free_index: + free_percpu(vi->vq_index); free_stats: free_percpu(vi->stats); free: @@@ -1560,6 -1618,8 +1635,8 @@@ static void virtnet_remove(struct virti { struct virtnet_info *vi = vdev->priv;

+ unregister_hotcpu_notifier(&vi->nb); + /* Prevent config work handler from accessing the device. */ mutex_lock(&vi->config_lock); vi->config_enable = false; @@@ -1571,6 -1631,7 +1648,7 @@@

flush_work(&vi->config_work);

+ free_percpu(vi->vq_index); free_percpu(vi->stats); free_netdev(vi->dev); } @@@ -1645,7 -1706,6 +1723,7 @@@ static unsigned int features[] = VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, + VIRTIO_NET_F_CTRL_MAC_ADDR, };

static struct virtio_driver virtio_net_driver = { diff --combined net/batman-adv/distributed-arp-table.c index 7485a78,183f97a..ea0bd31 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@@ -1,4 -1,4 +1,4 @@@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@@ -738,6 -738,7 +738,7 @@@ static uint16_t batadv_arp_get_type(str struct arphdr *arphdr; struct ethhdr *ethhdr; __be32 ip_src, ip_dst; + uint8_t *hw_src, *hw_dst; uint16_t type = 0;

/* pull the ethernet header */ @@@ -777,9 -778,23 +778,23 @@@ ip_src = batadv_arp_ip_src(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); if (ipv4_is_loopback(ip_src) || ipv4_is_multicast(ip_src) || - ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst)) + ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst) || + ipv4_is_zeronet(ip_src) || ipv4_is_lbcast(ip_src) || + ipv4_is_zeronet(ip_dst) || ipv4_is_lbcast(ip_dst)) goto out;

+ hw_src = batadv_arp_hw_src(skb, hdr_size); + if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src)) + goto out; + + /* we don't care about the destination MAC address in ARP requests */ + if (arphdr->ar_op != htons(ARPOP_REQUEST)) { + hw_dst = batadv_arp_hw_dst(skb, hdr_size); + if (is_zero_ether_addr(hw_dst) || + is_multicast_ether_addr(hw_dst)) + goto out; + } + type = ntohs(arphdr->ar_op); out: return type; @@@ -1012,6 -1027,8 +1027,8 @@@ bool batadv_dat_snoop_incoming_arp_repl */ ret = !batadv_is_my_client(bat_priv, hw_dst); out: + if (ret) + kfree_skb(skb); /* if ret == false -> packet has to be delivered to the interface */ return ret; } diff --combined net/ipv4/ip_gre.c index 801e023,e81b1ca..00a14b9 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@@ -738,7 -738,7 +738,7 @@@ drop static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; const struct iphdr *tiph; struct flowi4 fl4; u8 tos; @@@ -756,8 -756,6 +756,8 @@@ skb_checksum_help(skb)) goto tx_error;

+ old_iph = ip_hdr(skb); + if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0;

@@@ -820,8 -818,8 +820,8 @@@

ttl = tiph->ttl; tos = tiph->tos; - if (tos == 1) { - tos = 0; + if (tos & 0x1) { + tos &= ~0x1; if (skb->protocol == htons(ETH_P_IP)) tos = old_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) @@@ -965,8 -963,12 +965,12 @@@ ptr--; } if (tunnel->parms.o_flags&GRE_CSUM) { + int offset = skb_transport_offset(skb); + *ptr = 0; - *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, + skb->len - offset, + 0)); } }

diff --combined net/ipv4/tcp_ipv4.c index bbbdcc5,70b09ef..5a1cfc6 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@@ -369,11 -369,10 +369,10 @@@ void tcp_v4_err(struct sk_buff *icmp_sk * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk) && - type != ICMP_DEST_UNREACH && - code != ICMP_FRAG_NEEDED) - NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); - + if (sock_owned_by_user(sk)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); + } if (sk->sk_state == TCP_CLOSE) goto out;

@@@ -657,8 -656,7 +656,8 @@@ static void tcp_v4_send_reset(struct so * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, ip_hdr(skb)->daddr, + &tcp_hashinfo, ip_hdr(skb)->saddr, + th->source, ip_hdr(skb)->daddr, ntohs(th->source), inet_iif(skb)); /* don't send rst if it can't find key */ if (!sk1) @@@ -1569,7 -1567,7 +1568,7 @@@ int tcp_v4_conn_request(struct sock *sk goto drop_and_free;

if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb); + TCP_ECN_create_request(req, skb, sock_net(sk));

if (want_cookie) { isn = cookie_v4_init_sequence(sk, skb, &req->mss); @@@ -2075,7 -2073,6 +2074,7 @@@ do_time_wait case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (sk2) { @@@ -2890,7 -2887,6 +2889,7 @@@ EXPORT_SYMBOL(tcp_prot)

static int __net_init tcp_sk_init(struct net *net) { + net->ipv4.sysctl_tcp_ecn = 2; return 0; }

diff --combined net/ipv4/udp.c index e0610e4,1f4d405..6791aac --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@@ -139,7 -139,6 +139,7 @@@ static int udp_lib_lport_inuse(struct n { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk);

sk_nulls_for_each(sk2, node, &hslot->head) if (net_eq(sock_net(sk2), net) && @@@ -148,8 -147,6 +148,8 @@@ (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { if (bitmap) __set_bit(udp_sk(sk2)->udp_port_hash >> log, @@@ -172,7 -169,6 +172,7 @@@ static int udp_lib_lport_inuse2(struct { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); int res = 0;

spin_lock(&hslot2->lock); @@@ -183,8 -179,6 +183,8 @@@ (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { res = 1; break; @@@ -343,26 -337,26 +343,26 @@@ static inline int compute_score(struct !ipv6_only_sock(sk)) { struct inet_sock *inet = inet_sk(sk);

- score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_rcv_saddr) { if (inet->inet_rcv_saddr != daddr) return -1; - score += 2; + score += 4; } if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@@ -371,6 -365,7 +371,6 @@@ /* * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) */ -#define SCORE2_MAX (1 + 2 + 2 + 2) static inline int compute_score2(struct sock *sk, struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif) @@@ -385,21 -380,21 +385,21 @@@ if (inet->inet_num != hnum) return -1;

- score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@@ -414,29 -409,19 +414,29 @@@ static struct sock *udp4_lib_lookup2(st { struct sock *sk, *result; struct hlist_nulls_node *node; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0;

begin: result = NULL; - badness = -1; + badness = 0; udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { score = compute_score2(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { result = sk; badness = score; - if (score == SCORE2_MAX) - goto exact_match; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@@ -446,7 -431,9 +446,7 @@@ */ if (get_nulls_value(node) != slot2) goto begin; - if (result) { -exact_match: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@@ -470,8 -457,7 +470,8 @@@ struct sock *__udp4_lib_lookup(struct n unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0;

rcu_read_lock(); if (hslot->count > 10) { @@@ -500,24 -486,13 +500,24 @@@ } begin: result = NULL; - badness = -1; + badness = 0; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@@ -996,7 -971,7 +996,7 @@@ back_from_confirm sizeof(struct udphdr), &ipc, &rt, msg->msg_flags); err = PTR_ERR(skb); - if (skb && !IS_ERR(skb)) + if (!IS_ERR_OR_NULL(skb)) err = udp_send_skb(skb, fl4); goto out; } @@@ -1977,6 -1952,7 +1977,7 @@@ struct proto udp_prot = .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .backlog_rcv = __udp_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, diff --combined net/ipv6/ip6_output.c index 7dea45a,0c7c03d..906b7e6 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@@ -56,6 -56,8 +56,6 @@@ #include <net/checksum.h> #include <linux/mroute6.h>

-int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); - int __ip6_local_out(struct sk_buff *skb) { int len; @@@ -86,8 -88,7 +86,8 @@@ static int ip6_finish_output2(struct sk struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct neighbour *neigh; - struct rt6_info *rt; + struct in6_addr *nexthop; + int ret;

skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@@ -122,17 -123,10 +122,17 @@@ skb->len); }

- rt = (struct rt6_info *) dst; - neigh = rt->n; - if (neigh) - return dst_neigh_output(dst, neigh, skb); + rcu_read_lock_bh(); + nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); + if (unlikely(!neigh)) + neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); + if (!IS_ERR(neigh)) { + ret = dst_neigh_output(dst, neigh, skb); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh();

IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@@ -222,7 -216,7 +222,7 @@@ int ip6_xmit(struct sock *sk, struct sk if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst);

- *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel; + ip6_flow_hdr(hdr, tclass, fl6->flowlabel);

hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@@ -252,6 -246,39 +252,6 @@@

EXPORT_SYMBOL(ip6_xmit);

-/* - * To avoid extra problems ND packets are send through this - * routine. It's code duplication but I really want to avoid - * extra checks since ipv6_build_header is used by TCP (which - * is for us performance critical) - */ - -int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, - const struct in6_addr *saddr, const struct in6_addr *daddr, - int proto, int len) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6hdr *hdr; - - skb->protocol = htons(ETH_P_IPV6); - skb->dev = dev; - - skb_reset_network_header(skb); - skb_put(skb, sizeof(struct ipv6hdr)); - hdr = ipv6_hdr(skb); - - *(__be32*)hdr = htonl(0x60000000); - - hdr->payload_len = htons(len); - hdr->nexthdr = proto; - hdr->hop_limit = np->hop_limit; - - hdr->saddr = *saddr; - hdr->daddr = *daddr; - - return 0; -} - static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { struct ip6_ra_chain *ra; @@@ -886,12 -913,8 +886,12 @@@ static int ip6_dst_lookup_tail(struct s * dst entry of the nexthop router */ rt = (struct rt6_info *) *dst; - n = rt->n; - if (n && !(n->nud_state & NUD_VALID)) { + rcu_read_lock_bh(); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; + rcu_read_unlock_bh(); + + if (err) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; @@@ -1190,10 -1213,10 +1190,10 @@@ int ip6_append_data(struct sock *sk, in if (dst_allfrag(rt->dst.path)) cork->flags |= IPCORK_ALLFRAG; cork->length = 0; - exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; + exthdrlen = (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; - dst_exthdrlen = rt->dst.header_len; + dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; @@@ -1525,7 -1548,9 +1525,7 @@@ int ip6_push_pending_frames(struct soc skb_reset_network_header(skb); hdr = ipv6_hdr(skb);

- *(__be32*)hdr = fl6->flowlabel | - htonl(0x60000000 | ((int)np->cork.tclass << 20)); - + ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --combined net/ipv6/ip6mr.c index acc3249,8fd154e..351ce98 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@@ -1017,50 -1017,6 +1017,50 @@@ static struct mfc6_cache *ip6mr_cache_f return NULL; }

+/* Look for a (*,*,oif) entry */ +static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt, + mifi_t mifi) +{ + int line = MFC6_HASH(&in6addr_any, &in6addr_any); + struct mfc6_cache *c; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_any(&c->mf6c_mcastgrp) && + (c->mfc_un.res.ttls[mifi] < 255)) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt, + struct in6_addr *mcastgrp, + mifi_t mifi) +{ + int line = MFC6_HASH(mcastgrp, &in6addr_any); + struct mfc6_cache *c, *proxy; + + if (ipv6_addr_any(mcastgrp)) + goto skip; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) { + if (c->mfc_un.res.ttls[mifi] < 255) + return c; + + /* It's ok if the mifi is part of the static tree */ + proxy = ip6mr_cache_find_any_parent(mrt, + c->mf6c_parent); + if (proxy && proxy->mfc_un.res.ttls[mifi] < 255) + return c; + } + +skip: + return ip6mr_cache_find_any_parent(mrt, mifi); +} + /* * Allocate a multicast cache entry */ @@@ -1291,8 -1247,7 +1291,8 @@@ ip6mr_cache_unresolved(struct mr6_tabl * MFC6 cache manipulation by user space */

-static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) +static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, + int parent) { int line; struct mfc6_cache *c, *next; @@@ -1301,9 -1256,7 +1301,9 @@@

list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == c->mf6c_parent)) { write_lock_bh(&mrt_lock); list_del(&c->list); write_unlock_bh(&mrt_lock); @@@ -1438,7 -1391,7 +1438,7 @@@ void ip6_mr_cleanup(void }

static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, - struct mf6cctl *mfc, int mrtsock) + struct mf6cctl *mfc, int mrtsock, int parent) { bool found = false; int line; @@@ -1460,9 -1413,7 +1460,9 @@@

list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == mfc->mf6cc_parent)) { found = true; break; } @@@ -1479,8 -1430,7 +1479,8 @@@ return 0; }

- if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) + if (!ipv6_addr_any(&mfc->mf6cc_mcastgrp.sin6_addr) && + !ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL;

c = ip6mr_cache_alloc(); @@@ -1646,7 -1596,7 +1646,7 @@@ struct sock *mroute6_socket(struct net

int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { - int ret; + int ret, parent = 0; struct mif6ctl vif; struct mf6cctl mfc; mifi_t mifi; @@@ -1703,21 -1653,15 +1703,21 @@@ */ case MRT6_ADD_MFC: case MRT6_DEL_MFC: + parent = -1; + case MRT6_ADD_MFC_PROXY: + case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) return -EINVAL; if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; + if (parent == 0) + parent = mfc.mf6cc_parent; rtnl_lock(); - if (optname == MRT6_DEL_MFC) - ret = ip6mr_mfc_delete(mrt, &mfc); + if (optname == MRT6_DEL_MFC || optname == MRT6_DEL_MFC_PROXY) + ret = ip6mr_mfc_delete(mrt, &mfc, parent); else - ret = ip6mr_mfc_add(net, mrt, &mfc, sk == mrt->mroute6_sk); + ret = ip6mr_mfc_add(net, mrt, &mfc, + sk == mrt->mroute6_sk, parent); rtnl_unlock(); return ret;

@@@ -1766,6 -1710,9 +1766,9 @@@ return -EINVAL; if (get_user(v, (u32 __user *)optval)) return -EFAULT; + /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ + if (v != RT_TABLE_DEFAULT && v >= 100000000) + return -EINVAL; if (sk == mrt->mroute6_sk) return -EBUSY;

@@@ -2071,29 -2018,19 +2074,29 @@@ static int ip6_mr_forward(struct net *n { int psend = -1; int vif, ct; + int true_vifi = ip6mr_find_vif(mrt, skb->dev);

vif = cache->mf6c_parent; cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len;

+ if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) { + struct mfc6_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ip6mr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif6_table[vif].dev != skb->dev) { - int true_vifi; - cache->mfc_un.res.wrong_if++; - true_vifi = ip6mr_find_vif(mrt, skb->dev);

if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@@ -2111,32 -2048,14 +2114,32 @@@ goto dont_forward; }

+forward: mrt->vif6_table[vif].pkt_in++; mrt->vif6_table[vif].bytes_in += skb->len;

/* * Forward the frame */ + if (ipv6_addr_any(&cache->mf6c_origin) && + ipv6_addr_any(&cache->mf6c_mcastgrp)) { + if (true_vifi >= 0 && + true_vifi != cache->mf6c_parent && + ipv6_hdr(skb)->hop_limit > + cache->mfc_un.res.ttls[cache->mf6c_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mf6c_parent; + goto last_forward; + } + goto dont_forward; + } for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { - if (ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((!ipv6_addr_any(&cache->mf6c_origin) || ct != true_vifi) && + ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) @@@ -2145,7 -2064,6 +2148,7 @@@ psend = ct; } } +last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, cache, psend); return 0; @@@ -2181,14 -2099,6 +2184,14 @@@ int ip6_mr_input(struct sk_buff *skb read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, + &ipv6_hdr(skb)->daddr, + vif); + }

/* * No usable cache entry @@@ -2276,13 -2186,6 +2279,13 @@@ int ip6mr_get_route(struct net *net

read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); + if (!cache && skb->dev) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, &rt->rt6i_dst.addr, + vif); + }

if (!cache) { struct sk_buff *skb2;