From: David S. Miller Date: Fri, 10 Dec 2010 17:50:47 +0000 (-0800) Subject: Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/linville... X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=1e13f863ca88014d9550876c05c939fdab1017d1;hp=f435d9eea01309aa7b6c1f134569a7b5957918ae;p=mv-sheeva.git Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6 Conflicts: drivers/net/wireless/ath/ath9k/ar9003_eeprom.c --- diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index 271d524a4c8..b395ca6a49f 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -47,6 +47,26 @@ http://linux-net.osdl.org/index.php/DCCP_Testing#Experimental_DCCP_source_tree Socket options ============== +DCCP_SOCKOPT_QPOLICY_ID sets the dequeuing policy for outgoing packets. It takes +a policy ID as argument and can only be set before the connection (i.e. changes +during an established connection are not supported). Currently, two policies are +defined: the "simple" policy (DCCPQ_POLICY_SIMPLE), which does nothing special, +and a priority-based variant (DCCPQ_POLICY_PRIO). The latter allows to pass an +u32 priority value as ancillary data to sendmsg(), where higher numbers indicate +a higher packet priority (similar to SO_PRIORITY). This ancillary data needs to +be formatted using a cmsg(3) message header filled in as follows: + cmsg->cmsg_level = SOL_DCCP; + cmsg->cmsg_type = DCCP_SCM_PRIORITY; + cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t)); /* or CMSG_LEN(4) */ + +DCCP_SOCKOPT_QPOLICY_TXQLEN sets the maximum length of the output queue. A zero +value is always interpreted as unbounded queue length. If different from zero, +the interpretation of this parameter depends on the current dequeuing policy +(see above): the "simple" policy will enforce a fixed queue size by returning +EAGAIN, whereas the "prio" policy enforces a fixed queue length by dropping the +lowest-priority packet first. The default value for this parameter is +initialised from /proc/sys/net/dccp/default/tx_qlen. + DCCP_SOCKOPT_SERVICE sets the service. The specification mandates use of service codes (RFC 4340, sec. 8.1.2); if this socket option is not set, the socket will fall back to 0 (which means that no meaningful service code diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ae5522703d1..2193a5d124c 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -144,6 +144,7 @@ tcp_adv_win_scale - INTEGER Count buffering overhead as bytes/2^tcp_adv_win_scale (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale), if it is <= 0. + Possible values are [-31, 31], inclusive. Default: 2 tcp_allowed_congestion_control - STRING diff --git a/MAINTAINERS b/MAINTAINERS index 8b6ca96435e..9206cb46291 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1359,7 +1359,7 @@ F: include/net/bluetooth/ BONDING DRIVER M: Jay Vosburgh -L: bonding-devel@lists.sourceforge.net +L: netdev@vger.kernel.org W: http://sourceforge.net/projects/bonding/ S: Supported F: drivers/net/bonding/ diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c index cbe15a86c66..930051d941a 100644 --- a/drivers/atm/lanai.c +++ b/drivers/atm/lanai.c @@ -2241,11 +2241,8 @@ static int __devinit lanai_dev_open(struct atm_dev *atmdev) memcpy(atmdev->esi, eeprom_mac(lanai), ESI_LEN); lanai_timed_poll_start(lanai); printk(KERN_NOTICE DEV_LABEL "(itf %d): rev.%d, base=0x%lx, irq=%u " - "(%02X-%02X-%02X-%02X-%02X-%02X)\n", lanai->number, - (int) lanai->pci->revision, (unsigned long) lanai->base, - lanai->pci->irq, - atmdev->esi[0], atmdev->esi[1], atmdev->esi[2], - atmdev->esi[3], atmdev->esi[4], atmdev->esi[5]); + "(%pMF)\n", lanai->number, (int) lanai->pci->revision, + (unsigned long) lanai->base, lanai->pci->irq, atmdev->esi); printk(KERN_NOTICE DEV_LABEL "(itf %d): LANAI%s, serialno=%u(0x%X), " "board_rev=%d\n", lanai->number, lanai->type==lanai2 ? "2" : "HB", (unsigned int) lanai->serialno, diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c index b133378d4dc..c110f8679ba 100644 --- a/drivers/isdn/hisax/config.c +++ b/drivers/isdn/hisax/config.c @@ -1917,7 +1917,7 @@ static void EChannel_proc_rcv(struct hisax_d_if *d_if) #ifdef CONFIG_PCI #include -static struct pci_device_id hisax_pci_tbl[] __devinitdata = { +static struct pci_device_id hisax_pci_tbl[] __devinitdata __used = { #ifdef CONFIG_HISAX_FRITZPCI {PCI_VDEVICE(AVM, PCI_DEVICE_ID_AVM_A1) }, #endif diff --git a/drivers/isdn/icn/icn.c b/drivers/isdn/icn/icn.c index 2e847a90bad..f2b5bab5e6a 100644 --- a/drivers/isdn/icn/icn.c +++ b/drivers/isdn/icn/icn.c @@ -1627,7 +1627,7 @@ __setup("icn=", icn_setup); static int __init icn_init(void) { char *p; - char rev[10]; + char rev[20]; memset(&dev, 0, sizeof(icn_dev)); dev.memaddr = (membase & 0x0ffc000); @@ -1637,9 +1637,10 @@ static int __init icn_init(void) spin_lock_init(&dev.devlock); if ((p = strchr(revision, ':'))) { - strcpy(rev, p + 1); + strncpy(rev, p + 1, 20); p = strchr(rev, '$'); - *p = 0; + if (p) + *p = 0; } else strcpy(rev, " ??? "); printk(KERN_NOTICE "ICN-ISDN-driver Rev%smem=0x%08lx\n", rev, diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index a11dc735752..a20693fcb32 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -2543,10 +2543,10 @@ config PCH_GBE depends on PCI select MII ---help--- - This is a gigabit ethernet driver for Topcliff PCH. - Topcliff PCH is the platform controller hub that is used in Intel's + This is a gigabit ethernet driver for EG20T PCH. + EG20T PCH is the platform controller hub that is used in Intel's general embedded platform. - Topcliff PCH has Gigabit Ethernet interface. + EG20T PCH has Gigabit Ethernet interface. Using this interface, it is able to access system devices connected to Gigabit Ethernet. This driver enables Gigabit Ethernet function. diff --git a/drivers/net/arm/am79c961a.c b/drivers/net/arm/am79c961a.c index 62f21106efe..0c9217f48b7 100644 --- a/drivers/net/arm/am79c961a.c +++ b/drivers/net/arm/am79c961a.c @@ -340,14 +340,6 @@ am79c961_close(struct net_device *dev) return 0; } -/* - * Get the current statistics. - */ -static struct net_device_stats *am79c961_getstats (struct net_device *dev) -{ - return &dev->stats; -} - static void am79c961_mc_hash(char *addr, unsigned short *hash) { if (addr[0] & 0x01) { @@ -665,7 +657,6 @@ static const struct net_device_ops am79c961_netdev_ops = { .ndo_open = am79c961_open, .ndo_stop = am79c961_close, .ndo_start_xmit = am79c961_sendpacket, - .ndo_get_stats = am79c961_getstats, .ndo_set_multicast_list = am79c961_setmulticastlist, .ndo_tx_timeout = am79c961_timeout, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/atl1c/atl1c_hw.c b/drivers/net/atl1c/atl1c_hw.c index 919080b2c3a..1bf67200994 100644 --- a/drivers/net/atl1c/atl1c_hw.c +++ b/drivers/net/atl1c/atl1c_hw.c @@ -82,7 +82,7 @@ static int atl1c_get_permanent_address(struct atl1c_hw *hw) addr[0] = addr[1] = 0; AT_READ_REG(hw, REG_OTP_CTRL, &otp_ctrl_data); if (atl1c_check_eeprom_exist(hw)) { - if (hw->nic_type == athr_l1c || hw->nic_type == athr_l2c_b) { + if (hw->nic_type == athr_l1c || hw->nic_type == athr_l2c) { /* Enable OTP CLK */ if (!(otp_ctrl_data & OTP_CTRL_CLK_EN)) { otp_ctrl_data |= OTP_CTRL_CLK_EN; diff --git a/drivers/net/au1000_eth.c b/drivers/net/au1000_eth.c index 43489f89c14..53eff9ba6e9 100644 --- a/drivers/net/au1000_eth.c +++ b/drivers/net/au1000_eth.c @@ -155,10 +155,10 @@ static void au1000_enable_mac(struct net_device *dev, int force_reset) spin_lock_irqsave(&aup->lock, flags); if (force_reset || (!aup->mac_enabled)) { - writel(MAC_EN_CLOCK_ENABLE, &aup->enable); + writel(MAC_EN_CLOCK_ENABLE, aup->enable); au_sync_delay(2); writel((MAC_EN_RESET0 | MAC_EN_RESET1 | MAC_EN_RESET2 - | MAC_EN_CLOCK_ENABLE), &aup->enable); + | MAC_EN_CLOCK_ENABLE), aup->enable); au_sync_delay(2); aup->mac_enabled = 1; @@ -503,9 +503,9 @@ static void au1000_reset_mac_unlocked(struct net_device *dev) au1000_hard_stop(dev); - writel(MAC_EN_CLOCK_ENABLE, &aup->enable); + writel(MAC_EN_CLOCK_ENABLE, aup->enable); au_sync_delay(2); - writel(0, &aup->enable); + writel(0, aup->enable); au_sync_delay(2); aup->tx_full = 0; @@ -1119,7 +1119,7 @@ static int __devinit au1000_probe(struct platform_device *pdev) /* set a random MAC now in case platform_data doesn't provide one */ random_ether_addr(dev->dev_addr); - writel(0, &aup->enable); + writel(0, aup->enable); aup->mac_enabled = 0; pd = pdev->dev.platform_data; diff --git a/drivers/net/b44.c b/drivers/net/b44.c index c6e86315b3f..2e2b76258ab 100644 --- a/drivers/net/b44.c +++ b/drivers/net/b44.c @@ -381,11 +381,11 @@ static void b44_set_flow_ctrl(struct b44 *bp, u32 local, u32 remote) __b44_set_flow_ctrl(bp, pause_enab); } -#ifdef SSB_DRIVER_MIPS -extern char *nvram_get(char *name); +#ifdef CONFIG_BCM47XX +#include static void b44_wap54g10_workaround(struct b44 *bp) { - const char *str; + char buf[20]; u32 val; int err; @@ -394,10 +394,9 @@ static void b44_wap54g10_workaround(struct b44 *bp) * see https://dev.openwrt.org/ticket/146 * check and reset bit "isolate" */ - str = nvram_get("boardnum"); - if (!str) + if (nvram_getenv("boardnum", buf, sizeof(buf)) < 0) return; - if (simple_strtoul(str, NULL, 0) == 2) { + if (simple_strtoul(buf, NULL, 0) == 2) { err = __b44_readphy(bp, 0, MII_BMCR, &val); if (err) goto error; diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h index b61a1dfebca..9cab32328bb 100644 --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -220,7 +220,9 @@ struct be_rx_obj { struct be_rx_stats stats; u8 rss_id; bool rx_post_starved; /* Zero rx frags have been posted to BE */ - u32 cache_line_barrier[16]; + u16 last_frag_index; + u16 rsvd; + u32 cache_line_barrier[15]; }; struct be_vf_cfg { diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c index 3865b2bc65e..171a08caf2b 100644 --- a/drivers/net/benet/be_cmds.c +++ b/drivers/net/benet/be_cmds.c @@ -470,25 +470,14 @@ int be_cmd_fw_init(struct be_adapter *adapter) spin_lock(&adapter->mbox_lock); wrb = (u8 *)wrb_from_mbox(adapter); - if (lancer_chip(adapter)) { - *wrb++ = 0xFF; - *wrb++ = 0x34; - *wrb++ = 0x12; - *wrb++ = 0xFF; - *wrb++ = 0xFF; - *wrb++ = 0x78; - *wrb++ = 0x56; - *wrb = 0xFF; - } else { - *wrb++ = 0xFF; - *wrb++ = 0x12; - *wrb++ = 0x34; - *wrb++ = 0xFF; - *wrb++ = 0xFF; - *wrb++ = 0x56; - *wrb++ = 0x78; - *wrb = 0xFF; - } + *wrb++ = 0xFF; + *wrb++ = 0x12; + *wrb++ = 0x34; + *wrb++ = 0xFF; + *wrb++ = 0xFF; + *wrb++ = 0x56; + *wrb++ = 0x78; + *wrb = 0xFF; status = be_mbox_notify_wait(adapter); @@ -1285,7 +1274,7 @@ int be_cmd_multicast_set(struct be_adapter *adapter, u32 if_id, i = 0; netdev_for_each_mc_addr(ha, netdev) - memcpy(req->mac[i].byte, ha->addr, ETH_ALEN); + memcpy(req->mac[i++].byte, ha->addr, ETH_ALEN); } else { req->promiscuous = 1; } diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 102567ee68c..0b35e4a8bf1 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -911,11 +911,17 @@ static void be_rx_compl_discard(struct be_adapter *adapter, rxq_idx = AMAP_GET_BITS(struct amap_eth_rx_compl, fragndx, rxcp); num_rcvd = AMAP_GET_BITS(struct amap_eth_rx_compl, numfrags, rxcp); - for (i = 0; i < num_rcvd; i++) { - page_info = get_rx_page_info(adapter, rxo, rxq_idx); - put_page(page_info->page); - memset(page_info, 0, sizeof(*page_info)); - index_inc(&rxq_idx, rxq->len); + /* Skip out-of-buffer compl(lancer) or flush compl(BE) */ + if (likely(rxq_idx != rxo->last_frag_index && num_rcvd != 0)) { + + rxo->last_frag_index = rxq_idx; + + for (i = 0; i < num_rcvd; i++) { + page_info = get_rx_page_info(adapter, rxo, rxq_idx); + put_page(page_info->page); + memset(page_info, 0, sizeof(*page_info)); + index_inc(&rxq_idx, rxq->len); + } } } @@ -1016,9 +1022,6 @@ static void be_rx_compl_process(struct be_adapter *adapter, u8 vtm; num_rcvd = AMAP_GET_BITS(struct amap_eth_rx_compl, numfrags, rxcp); - /* Is it a flush compl that has no data */ - if (unlikely(num_rcvd == 0)) - return; skb = netdev_alloc_skb_ip_align(adapter->netdev, BE_HDR_LEN); if (unlikely(!skb)) { @@ -1075,10 +1078,6 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter, u8 pkt_type; num_rcvd = AMAP_GET_BITS(struct amap_eth_rx_compl, numfrags, rxcp); - /* Is it a flush compl that has no data */ - if (unlikely(num_rcvd == 0)) - return; - pkt_size = AMAP_GET_BITS(struct amap_eth_rx_compl, pktsize, rxcp); vlanf = AMAP_GET_BITS(struct amap_eth_rx_compl, vtp, rxcp); rxq_idx = AMAP_GET_BITS(struct amap_eth_rx_compl, fragndx, rxcp); @@ -1349,7 +1348,7 @@ static void be_rx_q_clean(struct be_adapter *adapter, struct be_rx_obj *rxo) while ((rxcp = be_rx_compl_get(rxo)) != NULL) { be_rx_compl_discard(adapter, rxo, rxcp); be_rx_compl_reset(rxcp); - be_cq_notify(adapter, rx_cq->id, true, 1); + be_cq_notify(adapter, rx_cq->id, false, 1); } /* Then free posted rx buffer that were not used */ @@ -1576,6 +1575,9 @@ static int be_rx_queues_create(struct be_adapter *adapter) adapter->big_page_size = (1 << get_order(rx_frag_size)) * PAGE_SIZE; for_all_rx_queues(adapter, rxo, i) { rxo->adapter = adapter; + /* Init last_frag_index so that the frag index in the first + * completion will never match */ + rxo->last_frag_index = 0xffff; rxo->rx_eq.max_eqd = BE_MAX_EQD; rxo->rx_eq.enable_aic = true; @@ -1697,10 +1699,9 @@ static irqreturn_t be_msix_tx_mcc(int irq, void *dev) return IRQ_HANDLED; } -static inline bool do_gro(struct be_adapter *adapter, struct be_rx_obj *rxo, - struct be_eth_rx_compl *rxcp) +static inline bool do_gro(struct be_rx_obj *rxo, + struct be_eth_rx_compl *rxcp, u8 err) { - int err = AMAP_GET_BITS(struct amap_eth_rx_compl, err, rxcp); int tcp_frame = AMAP_GET_BITS(struct amap_eth_rx_compl, tcpf, rxcp); if (err) @@ -1717,6 +1718,8 @@ static int be_poll_rx(struct napi_struct *napi, int budget) struct be_queue_info *rx_cq = &rxo->cq; struct be_eth_rx_compl *rxcp; u32 work_done; + u16 frag_index, num_rcvd; + u8 err; rxo->stats.rx_polls++; for (work_done = 0; work_done < budget; work_done++) { @@ -1724,10 +1727,22 @@ static int be_poll_rx(struct napi_struct *napi, int budget) if (!rxcp) break; - if (do_gro(adapter, rxo, rxcp)) - be_rx_compl_process_gro(adapter, rxo, rxcp); - else - be_rx_compl_process(adapter, rxo, rxcp); + err = AMAP_GET_BITS(struct amap_eth_rx_compl, err, rxcp); + frag_index = AMAP_GET_BITS(struct amap_eth_rx_compl, fragndx, + rxcp); + num_rcvd = AMAP_GET_BITS(struct amap_eth_rx_compl, numfrags, + rxcp); + + /* Skip out-of-buffer compl(lancer) or flush compl(BE) */ + if (likely(frag_index != rxo->last_frag_index && + num_rcvd != 0)) { + rxo->last_frag_index = frag_index; + + if (do_gro(rxo, rxcp, err)) + be_rx_compl_process_gro(adapter, rxo, rxcp); + else + be_rx_compl_process(adapter, rxo, rxcp); + } be_rx_compl_reset(rxcp); } @@ -2583,10 +2598,12 @@ static void be_netdev_init(struct net_device *netdev) int i; netdev->features |= NETIF_F_SG | NETIF_F_HW_VLAN_RX | NETIF_F_TSO | - NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER | NETIF_F_HW_CSUM | + NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_GRO | NETIF_F_TSO6; - netdev->vlan_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_HW_CSUM; + netdev->vlan_features |= NETIF_F_SG | NETIF_F_TSO | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; if (lancer_chip(adapter)) netdev->vlan_features |= NETIF_F_TSO6; @@ -2899,7 +2916,7 @@ static int __devinit be_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, adapter); status = be_dev_family_check(adapter); - if (!status) + if (status) goto free_netdev; adapter->netdev = netdev; diff --git a/drivers/net/bnx2x/bnx2x.h b/drivers/net/bnx2x/bnx2x.h index cfc25cf064d..7e4d682f0df 100644 --- a/drivers/net/bnx2x/bnx2x.h +++ b/drivers/net/bnx2x/bnx2x.h @@ -20,8 +20,8 @@ * (you will need to reboot afterwards) */ /* #define BNX2X_STOP_ON_ERROR */ -#define DRV_MODULE_VERSION "1.60.00-6" -#define DRV_MODULE_RELDATE "2010/11/29" +#define DRV_MODULE_VERSION "1.60.00-7" +#define DRV_MODULE_RELDATE "2010/12/08" #define BNX2X_BC_VER 0x040200 #define BNX2X_MULTI_QUEUE @@ -1336,7 +1336,7 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms, #define BNX2X_ILT_ZALLOC(x, y, size) \ do { \ - x = pci_alloc_consistent(bp->pdev, size, y); \ + x = dma_alloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \ if (x) \ memset(x, 0, size); \ } while (0) @@ -1344,7 +1344,7 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms, #define BNX2X_ILT_FREE(x, y, size) \ do { \ if (x) { \ - pci_free_consistent(bp->pdev, size, x, y); \ + dma_free_coherent(&bp->pdev->dev, size, x, y); \ x = NULL; \ y = 0; \ } \ diff --git a/drivers/net/bnx2x/bnx2x_cmn.c b/drivers/net/bnx2x/bnx2x_cmn.c index a4555edbe9c..236c00c3f56 100644 --- a/drivers/net/bnx2x/bnx2x_cmn.c +++ b/drivers/net/bnx2x/bnx2x_cmn.c @@ -1795,15 +1795,15 @@ exit_lbl: } #endif -static inline void bnx2x_set_pbd_gso_e2(struct sk_buff *skb, - struct eth_tx_parse_bd_e2 *pbd, - u32 xmit_type) +static inline void bnx2x_set_pbd_gso_e2(struct sk_buff *skb, u32 *parsing_data, + u32 xmit_type) { - pbd->parsing_data |= cpu_to_le16(skb_shinfo(skb)->gso_size) << - ETH_TX_PARSE_BD_E2_LSO_MSS_SHIFT; + *parsing_data |= (skb_shinfo(skb)->gso_size << + ETH_TX_PARSE_BD_E2_LSO_MSS_SHIFT) & + ETH_TX_PARSE_BD_E2_LSO_MSS; if ((xmit_type & XMIT_GSO_V6) && (ipv6_hdr(skb)->nexthdr == NEXTHDR_IPV6)) - pbd->parsing_data |= ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR; + *parsing_data |= ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR; } /** @@ -1848,15 +1848,15 @@ static inline void bnx2x_set_pbd_gso(struct sk_buff *skb, * @return header len */ static inline u8 bnx2x_set_pbd_csum_e2(struct bnx2x *bp, struct sk_buff *skb, - struct eth_tx_parse_bd_e2 *pbd, - u32 xmit_type) + u32 *parsing_data, u32 xmit_type) { - pbd->parsing_data |= cpu_to_le16(tcp_hdrlen(skb)/4) << - ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW_SHIFT; + *parsing_data |= ((tcp_hdrlen(skb)/4) << + ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW_SHIFT) & + ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW; - pbd->parsing_data |= cpu_to_le16(((unsigned char *)tcp_hdr(skb) - - skb->data) / 2) << - ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W_SHIFT; + *parsing_data |= ((((u8 *)tcp_hdr(skb) - skb->data) / 2) << + ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W_SHIFT) & + ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W; return skb_transport_header(skb) + tcp_hdrlen(skb) - skb->data; } @@ -1925,6 +1925,7 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) struct eth_tx_bd *tx_data_bd, *total_pkt_bd = NULL; struct eth_tx_parse_bd_e1x *pbd_e1x = NULL; struct eth_tx_parse_bd_e2 *pbd_e2 = NULL; + u32 pbd_e2_parsing_data = 0; u16 pkt_prod, bd_prod; int nbd, fp_index; dma_addr_t mapping; @@ -2046,8 +2047,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) memset(pbd_e2, 0, sizeof(struct eth_tx_parse_bd_e2)); /* Set PBD in checksum offload case */ if (xmit_type & XMIT_CSUM) - hlen = bnx2x_set_pbd_csum_e2(bp, - skb, pbd_e2, xmit_type); + hlen = bnx2x_set_pbd_csum_e2(bp, skb, + &pbd_e2_parsing_data, + xmit_type); } else { pbd_e1x = &fp->tx_desc_ring[bd_prod].parse_bd_e1x; memset(pbd_e1x, 0, sizeof(struct eth_tx_parse_bd_e1x)); @@ -2089,10 +2091,18 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) bd_prod = bnx2x_tx_split(bp, fp, tx_buf, &tx_start_bd, hlen, bd_prod, ++nbd); if (CHIP_IS_E2(bp)) - bnx2x_set_pbd_gso_e2(skb, pbd_e2, xmit_type); + bnx2x_set_pbd_gso_e2(skb, &pbd_e2_parsing_data, + xmit_type); else bnx2x_set_pbd_gso(skb, pbd_e1x, xmit_type); } + + /* Set the PBD's parsing_data field if not zero + * (for the chips newer than 57711). + */ + if (pbd_e2_parsing_data) + pbd_e2->parsing_data = cpu_to_le32(pbd_e2_parsing_data); + tx_data_bd = (struct eth_tx_bd *)tx_start_bd; /* Handle fragmented skb */ diff --git a/drivers/net/bnx2x/bnx2x_init_ops.h b/drivers/net/bnx2x/bnx2x_init_ops.h index a306b0e46b6..66df29fcf75 100644 --- a/drivers/net/bnx2x/bnx2x_init_ops.h +++ b/drivers/net/bnx2x/bnx2x_init_ops.h @@ -838,7 +838,7 @@ static void bnx2x_qm_init_ptr_table(struct bnx2x *bp, int qm_cid_count, /**************************************************************************** * SRC initializations ****************************************************************************/ - +#ifdef BCM_CNIC /* called during init func stage */ static void bnx2x_src_init_t2(struct bnx2x *bp, struct src_ent *t2, dma_addr_t t2_mapping, int src_cid_count) @@ -862,5 +862,5 @@ static void bnx2x_src_init_t2(struct bnx2x *bp, struct src_ent *t2, U64_HI((u64)t2_mapping + (src_cid_count-1) * sizeof(struct src_ent))); } - +#endif #endif /* BNX2X_INIT_OPS_H */ diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c index 1552fc3c135..0068a1dbc06 100644 --- a/drivers/net/bnx2x/bnx2x_main.c +++ b/drivers/net/bnx2x/bnx2x_main.c @@ -8957,7 +8957,7 @@ static int __devinit bnx2x_init_dev(struct pci_dev *pdev, dev->netdev_ops = &bnx2x_netdev_ops; bnx2x_set_ethtool_ops(dev); dev->features |= NETIF_F_SG; - dev->features |= NETIF_F_HW_CSUM; + dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; if (bp->flags & USING_DAC_FLAG) dev->features |= NETIF_F_HIGHDMA; dev->features |= (NETIF_F_TSO | NETIF_F_TSO_ECN); @@ -8965,7 +8965,7 @@ static int __devinit bnx2x_init_dev(struct pci_dev *pdev, dev->features |= (NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX); dev->vlan_features |= NETIF_F_SG; - dev->vlan_features |= NETIF_F_HW_CSUM; + dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; if (bp->flags & USING_DAC_FLAG) dev->vlan_features |= NETIF_F_HIGHDMA; dev->vlan_features |= (NETIF_F_TSO | NETIF_F_TSO_ECN); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0273ad0b57b..bb33b3b347f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1570,7 +1570,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* If this is the first slave, then we need to set the master's hardware * address to be the same as the slave's. */ - if (bond->slave_cnt == 0) + if (is_zero_ether_addr(bond->dev->dev_addr)) memcpy(bond->dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len); diff --git a/drivers/net/caif/caif_shm_u5500.c b/drivers/net/caif/caif_shm_u5500.c index 1cd90da86f1..32b1c6fb2de 100644 --- a/drivers/net/caif/caif_shm_u5500.c +++ b/drivers/net/caif/caif_shm_u5500.c @@ -5,7 +5,7 @@ * License terms: GNU General Public License (GPL) version 2 */ -#define pr_fmt(fmt) KBUILD_MODNAME ":" __func__ "():" fmt +#define pr_fmt(fmt) KBUILD_MODNAME ":" fmt #include #include diff --git a/drivers/net/caif/caif_shmcore.c b/drivers/net/caif/caif_shmcore.c index 19f9c065666..80511167f35 100644 --- a/drivers/net/caif/caif_shmcore.c +++ b/drivers/net/caif/caif_shmcore.c @@ -6,7 +6,7 @@ * License terms: GNU General Public License (GPL) version 2 */ -#define pr_fmt(fmt) KBUILD_MODNAME ":" __func__ "():" fmt +#define pr_fmt(fmt) KBUILD_MODNAME ":" fmt #include #include diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 080574b0fff..d5a9db60ade 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -12,6 +12,27 @@ config CAN_VCAN This driver can also be built as a module. If so, the module will be called vcan. +config CAN_SLCAN + tristate "Serial / USB serial CAN Adaptors (slcan)" + depends on CAN + default N + ---help--- + CAN driver for several 'low cost' CAN interfaces that are attached + via serial lines or via USB-to-serial adapters using the LAWICEL + ASCII protocol. The driver implements the tty linediscipline N_SLCAN. + + As only the sending and receiving of CAN frames is implemented, this + driver should work with the (serial/USB) CAN hardware from: + www.canusb.com / www.can232.com / www.mictronic.com / www.canhack.de + + Userspace tools to attach the SLCAN line discipline (slcan_attach, + slcand) can be found in the can-utils at the SocketCAN SVN, see + http://developer.berlios.de/projects/socketcan for details. + + The slcan driver supports up to 10 CAN netdevices by default which + can be changed by the 'maxdev=xx' module option. This driver can + also be built as a module. If so, the module will be called slcan. + config CAN_DEV tristate "Platform CAN drivers with Netlink support" depends on CAN diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index 90af15a4f10..07ca159ba3f 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -3,6 +3,7 @@ # obj-$(CONFIG_CAN_VCAN) += vcan.o +obj-$(CONFIG_CAN_SLCAN) += slcan.o obj-$(CONFIG_CAN_DEV) += can-dev.o can-dev-y := dev.o diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c new file mode 100644 index 00000000000..b423965a78d --- /dev/null +++ b/drivers/net/can/slcan.c @@ -0,0 +1,756 @@ +/* + * slcan.c - serial line CAN interface driver (using tty line discipline) + * + * This file is derived from linux/drivers/net/slip.c + * + * slip.c Authors : Laurence Culhane + * Fred N. van Kempen + * slcan.c Author : Oliver Hartkopp + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 59 Temple Place, Suite 330, Boston, MA 02111-1307. You can also get it + * at http://www.gnu.org/licenses/gpl.html + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + * Send feedback to + * + */ + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static __initdata const char banner[] = + KERN_INFO "slcan: serial line CAN interface driver\n"; + +MODULE_ALIAS_LDISC(N_SLCAN); +MODULE_DESCRIPTION("serial line CAN interface"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Oliver Hartkopp "); + +#define SLCAN_MAGIC 0x53CA + +static int maxdev = 10; /* MAX number of SLCAN channels; + This can be overridden with + insmod slcan.ko maxdev=nnn */ +module_param(maxdev, int, 0); +MODULE_PARM_DESC(maxdev, "Maximum number of slcan interfaces"); + +/* maximum rx buffer len: extended CAN frame with timestamp */ +#define SLC_MTU (sizeof("T1111222281122334455667788EA5F\r")+1) + +struct slcan { + int magic; + + /* Various fields. */ + struct tty_struct *tty; /* ptr to TTY structure */ + struct net_device *dev; /* easy for intr handling */ + spinlock_t lock; + + /* These are pointers to the malloc()ed frame buffers. */ + unsigned char rbuff[SLC_MTU]; /* receiver buffer */ + int rcount; /* received chars counter */ + unsigned char xbuff[SLC_MTU]; /* transmitter buffer */ + unsigned char *xhead; /* pointer to next XMIT byte */ + int xleft; /* bytes left in XMIT queue */ + + unsigned long flags; /* Flag values/ mode etc */ +#define SLF_INUSE 0 /* Channel in use */ +#define SLF_ERROR 1 /* Parity, etc. error */ + + unsigned char leased; + dev_t line; + pid_t pid; +}; + +static struct net_device **slcan_devs; + + /************************************************************************ + * SLCAN ENCAPSULATION FORMAT * + ************************************************************************/ + +/* + * A CAN frame has a can_id (11 bit standard frame format OR 29 bit extended + * frame format) a data length code (can_dlc) which can be from 0 to 8 + * and up to data bytes as payload. + * Additionally a CAN frame may become a remote transmission frame if the + * RTR-bit is set. This causes another ECU to send a CAN frame with the + * given can_id. + * + * The SLCAN ASCII representation of these different frame types is: + * * + * + * Extended frames (29 bit) are defined by capital characters in the type. + * RTR frames are defined as 'r' types - normal frames have 't' type: + * t => 11 bit data frame + * r => 11 bit RTR frame + * T => 29 bit data frame + * R => 29 bit RTR frame + * + * The is 3 (standard) or 8 (extended) bytes in ASCII Hex (base64). + * The is a one byte ASCII number ('0' - '8') + * The section has at much ASCII Hex bytes as defined by the + * + * Examples: + * + * t1230 : can_id 0x123, can_dlc 0, no data + * t4563112233 : can_id 0x456, can_dlc 3, data 0x11 0x22 0x33 + * T12ABCDEF2AA55 : extended can_id 0x12ABCDEF, can_dlc 2, data 0xAA 0x55 + * r1230 : can_id 0x123, can_dlc 0, no data, remote transmission request + * + */ + + /************************************************************************ + * STANDARD SLCAN DECAPSULATION * + ************************************************************************/ + +static int asc2nibble(char c) +{ + + if ((c >= '0') && (c <= '9')) + return c - '0'; + + if ((c >= 'A') && (c <= 'F')) + return c - 'A' + 10; + + if ((c >= 'a') && (c <= 'f')) + return c - 'a' + 10; + + return 16; /* error */ +} + +/* Send one completely decapsulated can_frame to the network layer */ +static void slc_bump(struct slcan *sl) +{ + struct sk_buff *skb; + struct can_frame cf; + int i, dlc_pos, tmp; + unsigned long ultmp; + char cmd = sl->rbuff[0]; + + if ((cmd != 't') && (cmd != 'T') && (cmd != 'r') && (cmd != 'R')) + return; + + if (cmd & 0x20) /* tiny chars 'r' 't' => standard frame format */ + dlc_pos = 4; /* dlc position tiiid */ + else + dlc_pos = 9; /* dlc position Tiiiiiiiid */ + + if (!((sl->rbuff[dlc_pos] >= '0') && (sl->rbuff[dlc_pos] < '9'))) + return; + + cf.can_dlc = sl->rbuff[dlc_pos] - '0'; /* get can_dlc from ASCII val */ + + sl->rbuff[dlc_pos] = 0; /* terminate can_id string */ + + if (strict_strtoul(sl->rbuff+1, 16, &ultmp)) + return; + + cf.can_id = ultmp; + + if (!(cmd & 0x20)) /* NO tiny chars => extended frame format */ + cf.can_id |= CAN_EFF_FLAG; + + if ((cmd | 0x20) == 'r') /* RTR frame */ + cf.can_id |= CAN_RTR_FLAG; + + *(u64 *) (&cf.data) = 0; /* clear payload */ + + for (i = 0, dlc_pos++; i < cf.can_dlc; i++) { + + tmp = asc2nibble(sl->rbuff[dlc_pos++]); + if (tmp > 0x0F) + return; + cf.data[i] = (tmp << 4); + tmp = asc2nibble(sl->rbuff[dlc_pos++]); + if (tmp > 0x0F) + return; + cf.data[i] |= tmp; + } + + + skb = dev_alloc_skb(sizeof(struct can_frame)); + if (!skb) + return; + + skb->dev = sl->dev; + skb->protocol = htons(ETH_P_CAN); + skb->pkt_type = PACKET_BROADCAST; + skb->ip_summed = CHECKSUM_UNNECESSARY; + memcpy(skb_put(skb, sizeof(struct can_frame)), + &cf, sizeof(struct can_frame)); + netif_rx(skb); + + sl->dev->stats.rx_packets++; + sl->dev->stats.rx_bytes += cf.can_dlc; +} + +/* parse tty input stream */ +static void slcan_unesc(struct slcan *sl, unsigned char s) +{ + + if ((s == '\r') || (s == '\a')) { /* CR or BEL ends the pdu */ + if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && + (sl->rcount > 4)) { + slc_bump(sl); + } + sl->rcount = 0; + } else { + if (!test_bit(SLF_ERROR, &sl->flags)) { + if (sl->rcount < SLC_MTU) { + sl->rbuff[sl->rcount++] = s; + return; + } else { + sl->dev->stats.rx_over_errors++; + set_bit(SLF_ERROR, &sl->flags); + } + } + } +} + + /************************************************************************ + * STANDARD SLCAN ENCAPSULATION * + ************************************************************************/ + +/* Encapsulate one can_frame and stuff into a TTY queue. */ +static void slc_encaps(struct slcan *sl, struct can_frame *cf) +{ + int actual, idx, i; + char cmd; + + if (cf->can_id & CAN_RTR_FLAG) + cmd = 'R'; /* becomes 'r' in standard frame format */ + else + cmd = 'T'; /* becomes 't' in standard frame format */ + + if (cf->can_id & CAN_EFF_FLAG) + sprintf(sl->xbuff, "%c%08X%d", cmd, + cf->can_id & CAN_EFF_MASK, cf->can_dlc); + else + sprintf(sl->xbuff, "%c%03X%d", cmd | 0x20, + cf->can_id & CAN_SFF_MASK, cf->can_dlc); + + idx = strlen(sl->xbuff); + + for (i = 0; i < cf->can_dlc; i++) + sprintf(&sl->xbuff[idx + 2*i], "%02X", cf->data[i]); + + strcat(sl->xbuff, "\r"); /* add terminating character */ + + /* Order of next two lines is *very* important. + * When we are sending a little amount of data, + * the transfer may be completed inside the ops->write() + * routine, because it's running with interrupts enabled. + * In this case we *never* got WRITE_WAKEUP event, + * if we did not request it before write operation. + * 14 Oct 1994 Dmitry Gorodchanin. + */ + set_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags); + actual = sl->tty->ops->write(sl->tty, sl->xbuff, strlen(sl->xbuff)); + sl->xleft = strlen(sl->xbuff) - actual; + sl->xhead = sl->xbuff + actual; + sl->dev->stats.tx_bytes += cf->can_dlc; +} + +/* + * Called by the driver when there's room for more data. If we have + * more packets to send, we send them here. + */ +static void slcan_write_wakeup(struct tty_struct *tty) +{ + int actual; + struct slcan *sl = (struct slcan *) tty->disc_data; + + /* First make sure we're connected. */ + if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev)) + return; + + if (sl->xleft <= 0) { + /* Now serial buffer is almost free & we can start + * transmission of another packet */ + sl->dev->stats.tx_packets++; + clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); + netif_wake_queue(sl->dev); + return; + } + + actual = tty->ops->write(tty, sl->xhead, sl->xleft); + sl->xleft -= actual; + sl->xhead += actual; +} + +/* Send a can_frame to a TTY queue. */ +static netdev_tx_t slc_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct slcan *sl = netdev_priv(dev); + + if (skb->len != sizeof(struct can_frame)) + goto out; + + spin_lock(&sl->lock); + if (!netif_running(dev)) { + spin_unlock(&sl->lock); + printk(KERN_WARNING "%s: xmit: iface is down\n", dev->name); + goto out; + } + if (sl->tty == NULL) { + spin_unlock(&sl->lock); + goto out; + } + + netif_stop_queue(sl->dev); + slc_encaps(sl, (struct can_frame *) skb->data); /* encaps & send */ + spin_unlock(&sl->lock); + +out: + kfree_skb(skb); + return NETDEV_TX_OK; +} + + +/****************************************** + * Routines looking at netdevice side. + ******************************************/ + +/* Netdevice UP -> DOWN routine */ +static int slc_close(struct net_device *dev) +{ + struct slcan *sl = netdev_priv(dev); + + spin_lock_bh(&sl->lock); + if (sl->tty) { + /* TTY discipline is running. */ + clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags); + } + netif_stop_queue(dev); + sl->rcount = 0; + sl->xleft = 0; + spin_unlock_bh(&sl->lock); + + return 0; +} + +/* Netdevice DOWN -> UP routine */ +static int slc_open(struct net_device *dev) +{ + struct slcan *sl = netdev_priv(dev); + + if (sl->tty == NULL) + return -ENODEV; + + sl->flags &= (1 << SLF_INUSE); + netif_start_queue(dev); + return 0; +} + +/* Hook the destructor so we can free slcan devs at the right point in time */ +static void slc_free_netdev(struct net_device *dev) +{ + int i = dev->base_addr; + free_netdev(dev); + slcan_devs[i] = NULL; +} + +static const struct net_device_ops slc_netdev_ops = { + .ndo_open = slc_open, + .ndo_stop = slc_close, + .ndo_start_xmit = slc_xmit, +}; + +static void slc_setup(struct net_device *dev) +{ + dev->netdev_ops = &slc_netdev_ops; + dev->destructor = slc_free_netdev; + + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->tx_queue_len = 10; + + dev->mtu = sizeof(struct can_frame); + dev->type = ARPHRD_CAN; + + /* New-style flags. */ + dev->flags = IFF_NOARP; + dev->features = NETIF_F_NO_CSUM; +} + +/****************************************** + Routines looking at TTY side. + ******************************************/ + +/* + * Handle the 'receiver data ready' interrupt. + * This function is called by the 'tty_io' module in the kernel when + * a block of SLCAN data has been received, which can now be decapsulated + * and sent on to some IP layer for further processing. This will not + * be re-entered while running but other ldisc functions may be called + * in parallel + */ + +static void slcan_receive_buf(struct tty_struct *tty, + const unsigned char *cp, char *fp, int count) +{ + struct slcan *sl = (struct slcan *) tty->disc_data; + + if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev)) + return; + + /* Read the characters out of the buffer */ + while (count--) { + if (fp && *fp++) { + if (!test_and_set_bit(SLF_ERROR, &sl->flags)) + sl->dev->stats.rx_errors++; + cp++; + continue; + } + slcan_unesc(sl, *cp++); + } +} + +/************************************ + * slcan_open helper routines. + ************************************/ + +/* Collect hanged up channels */ +static void slc_sync(void) +{ + int i; + struct net_device *dev; + struct slcan *sl; + + for (i = 0; i < maxdev; i++) { + dev = slcan_devs[i]; + if (dev == NULL) + break; + + sl = netdev_priv(dev); + if (sl->tty || sl->leased) + continue; + if (dev->flags & IFF_UP) + dev_close(dev); + } +} + +/* Find a free SLCAN channel, and link in this `tty' line. */ +static struct slcan *slc_alloc(dev_t line) +{ + int i; + struct net_device *dev = NULL; + struct slcan *sl; + + if (slcan_devs == NULL) + return NULL; /* Master array missing ! */ + + for (i = 0; i < maxdev; i++) { + dev = slcan_devs[i]; + if (dev == NULL) + break; + + } + + /* Sorry, too many, all slots in use */ + if (i >= maxdev) + return NULL; + + if (dev) { + sl = netdev_priv(dev); + if (test_bit(SLF_INUSE, &sl->flags)) { + unregister_netdevice(dev); + dev = NULL; + slcan_devs[i] = NULL; + } + } + + if (!dev) { + char name[IFNAMSIZ]; + sprintf(name, "slcan%d", i); + + dev = alloc_netdev(sizeof(*sl), name, slc_setup); + if (!dev) + return NULL; + dev->base_addr = i; + } + + sl = netdev_priv(dev); + + /* Initialize channel control data */ + sl->magic = SLCAN_MAGIC; + sl->dev = dev; + spin_lock_init(&sl->lock); + slcan_devs[i] = dev; + + return sl; +} + +/* + * Open the high-level part of the SLCAN channel. + * This function is called by the TTY module when the + * SLCAN line discipline is called for. Because we are + * sure the tty line exists, we only have to link it to + * a free SLCAN channel... + * + * Called in process context serialized from other ldisc calls. + */ + +static int slcan_open(struct tty_struct *tty) +{ + struct slcan *sl; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (tty->ops->write == NULL) + return -EOPNOTSUPP; + + /* RTnetlink lock is misused here to serialize concurrent + opens of slcan channels. There are better ways, but it is + the simplest one. + */ + rtnl_lock(); + + /* Collect hanged up channels. */ + slc_sync(); + + sl = tty->disc_data; + + err = -EEXIST; + /* First make sure we're not already connected. */ + if (sl && sl->magic == SLCAN_MAGIC) + goto err_exit; + + /* OK. Find a free SLCAN channel to use. */ + err = -ENFILE; + sl = slc_alloc(tty_devnum(tty)); + if (sl == NULL) + goto err_exit; + + sl->tty = tty; + tty->disc_data = sl; + sl->line = tty_devnum(tty); + sl->pid = current->pid; + + if (!test_bit(SLF_INUSE, &sl->flags)) { + /* Perform the low-level SLCAN initialization. */ + sl->rcount = 0; + sl->xleft = 0; + + set_bit(SLF_INUSE, &sl->flags); + + err = register_netdevice(sl->dev); + if (err) + goto err_free_chan; + } + + /* Done. We have linked the TTY line to a channel. */ + rtnl_unlock(); + tty->receive_room = 65536; /* We don't flow control */ + return sl->dev->base_addr; + +err_free_chan: + sl->tty = NULL; + tty->disc_data = NULL; + clear_bit(SLF_INUSE, &sl->flags); + +err_exit: + rtnl_unlock(); + + /* Count references from TTY module */ + return err; +} + +/* + * Close down a SLCAN channel. + * This means flushing out any pending queues, and then returning. This + * call is serialized against other ldisc functions. + * + * We also use this method for a hangup event. + */ + +static void slcan_close(struct tty_struct *tty) +{ + struct slcan *sl = (struct slcan *) tty->disc_data; + + /* First make sure we're connected. */ + if (!sl || sl->magic != SLCAN_MAGIC || sl->tty != tty) + return; + + tty->disc_data = NULL; + sl->tty = NULL; + if (!sl->leased) + sl->line = 0; + + /* Flush network side */ + unregister_netdev(sl->dev); + /* This will complete via sl_free_netdev */ +} + +static int slcan_hangup(struct tty_struct *tty) +{ + slcan_close(tty); + return 0; +} + +/* Perform I/O control on an active SLCAN channel. */ +static int slcan_ioctl(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct slcan *sl = (struct slcan *) tty->disc_data; + unsigned int tmp; + + /* First make sure we're connected. */ + if (!sl || sl->magic != SLCAN_MAGIC) + return -EINVAL; + + switch (cmd) { + case SIOCGIFNAME: + tmp = strlen(sl->dev->name) + 1; + if (copy_to_user((void __user *)arg, sl->dev->name, tmp)) + return -EFAULT; + return 0; + + case SIOCSIFHWADDR: + return -EINVAL; + + default: + return tty_mode_ioctl(tty, file, cmd, arg); + } +} + +static struct tty_ldisc_ops slc_ldisc = { + .owner = THIS_MODULE, + .magic = TTY_LDISC_MAGIC, + .name = "slcan", + .open = slcan_open, + .close = slcan_close, + .hangup = slcan_hangup, + .ioctl = slcan_ioctl, + .receive_buf = slcan_receive_buf, + .write_wakeup = slcan_write_wakeup, +}; + +static int __init slcan_init(void) +{ + int status; + + if (maxdev < 4) + maxdev = 4; /* Sanity */ + + printk(banner); + printk(KERN_INFO "slcan: %d dynamic interface channels.\n", maxdev); + + slcan_devs = kzalloc(sizeof(struct net_device *)*maxdev, GFP_KERNEL); + if (!slcan_devs) { + printk(KERN_ERR "slcan: can't allocate slcan device array!\n"); + return -ENOMEM; + } + + /* Fill in our line protocol discipline, and register it */ + status = tty_register_ldisc(N_SLCAN, &slc_ldisc); + if (status) { + printk(KERN_ERR "slcan: can't register line discipline\n"); + kfree(slcan_devs); + } + return status; +} + +static void __exit slcan_exit(void) +{ + int i; + struct net_device *dev; + struct slcan *sl; + unsigned long timeout = jiffies + HZ; + int busy = 0; + + if (slcan_devs == NULL) + return; + + /* First of all: check for active disciplines and hangup them. + */ + do { + if (busy) + msleep_interruptible(100); + + busy = 0; + for (i = 0; i < maxdev; i++) { + dev = slcan_devs[i]; + if (!dev) + continue; + sl = netdev_priv(dev); + spin_lock_bh(&sl->lock); + if (sl->tty) { + busy++; + tty_hangup(sl->tty); + } + spin_unlock_bh(&sl->lock); + } + } while (busy && time_before(jiffies, timeout)); + + /* FIXME: hangup is async so we should wait when doing this second + phase */ + + for (i = 0; i < maxdev; i++) { + dev = slcan_devs[i]; + if (!dev) + continue; + slcan_devs[i] = NULL; + + sl = netdev_priv(dev); + if (sl->tty) { + printk(KERN_ERR "%s: tty discipline still running\n", + dev->name); + /* Intentionally leak the control block. */ + dev->destructor = NULL; + } + + unregister_netdev(dev); + } + + kfree(slcan_devs); + slcan_devs = NULL; + + i = tty_unregister_ldisc(N_SLCAN); + if (i) + printk(KERN_ERR "slcan: can't unregister ldisc (err %d)\n", i); +} + +module_init(slcan_init); +module_exit(slcan_exit); diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c index 81475cc80e1..80c2feeefec 100644 --- a/drivers/net/cris/eth_v10.c +++ b/drivers/net/cris/eth_v10.c @@ -59,7 +59,6 @@ static struct sockaddr default_mac = { /* Information that need to be kept for each board. */ struct net_local { - struct net_device_stats stats; struct mii_if_info mii_if; /* Tx control lock. This protects the transmit buffer ring @@ -1059,7 +1058,7 @@ e100_tx_timeout(struct net_device *dev) /* remember we got an error */ - np->stats.tx_errors++; + dev->stats.tx_errors++; /* reset the TX DMA in case it has hung on something */ @@ -1157,7 +1156,7 @@ e100rxtx_interrupt(int irq, void *dev_id) * allocate a new buffer to put a packet in. */ e100_rx(dev); - np->stats.rx_packets++; + dev->stats.rx_packets++; /* restart/continue on the channel, for safety */ *R_DMA_CH1_CMD = IO_STATE(R_DMA_CH1_CMD, cmd, restart); /* clear dma channel 1 eop/descr irq bits */ @@ -1173,8 +1172,8 @@ e100rxtx_interrupt(int irq, void *dev_id) /* Report any packets that have been sent */ while (virt_to_phys(myFirstTxDesc) != *R_DMA_CH0_FIRST && (netif_queue_stopped(dev) || myFirstTxDesc != myNextTxDesc)) { - np->stats.tx_bytes += myFirstTxDesc->skb->len; - np->stats.tx_packets++; + dev->stats.tx_bytes += myFirstTxDesc->skb->len; + dev->stats.tx_packets++; /* dma is ready with the transmission of the data in tx_skb, so now we can release the skb memory */ @@ -1197,7 +1196,6 @@ static irqreturn_t e100nw_interrupt(int irq, void *dev_id) { struct net_device *dev = (struct net_device *)dev_id; - struct net_local *np = netdev_priv(dev); unsigned long irqbits = *R_IRQ_MASK0_RD; /* check for underrun irq */ @@ -1205,13 +1203,13 @@ e100nw_interrupt(int irq, void *dev_id) SETS(network_tr_ctrl_shadow, R_NETWORK_TR_CTRL, clr_error, clr); *R_NETWORK_TR_CTRL = network_tr_ctrl_shadow; SETS(network_tr_ctrl_shadow, R_NETWORK_TR_CTRL, clr_error, nop); - np->stats.tx_errors++; + dev->stats.tx_errors++; D(printk("ethernet receiver underrun!\n")); } /* check for overrun irq */ if (irqbits & IO_STATE(R_IRQ_MASK0_RD, overrun, active)) { - update_rx_stats(&np->stats); /* this will ack the irq */ + update_rx_stats(&dev->stats); /* this will ack the irq */ D(printk("ethernet receiver overrun!\n")); } /* check for excessive collision irq */ @@ -1219,7 +1217,7 @@ e100nw_interrupt(int irq, void *dev_id) SETS(network_tr_ctrl_shadow, R_NETWORK_TR_CTRL, clr_error, clr); *R_NETWORK_TR_CTRL = network_tr_ctrl_shadow; SETS(network_tr_ctrl_shadow, R_NETWORK_TR_CTRL, clr_error, nop); - np->stats.tx_errors++; + dev->stats.tx_errors++; D(printk("ethernet excessive collisions!\n")); } return IRQ_HANDLED; @@ -1250,7 +1248,7 @@ e100_rx(struct net_device *dev) spin_unlock(&np->led_lock); length = myNextRxDesc->descr.hw_len - 4; - np->stats.rx_bytes += length; + dev->stats.rx_bytes += length; #ifdef ETHDEBUG printk("Got a packet of length %d:\n", length); @@ -1268,7 +1266,7 @@ e100_rx(struct net_device *dev) /* Small packet, copy data */ skb = dev_alloc_skb(length - ETHER_HEAD_LEN); if (!skb) { - np->stats.rx_errors++; + dev->stats.rx_errors++; printk(KERN_NOTICE "%s: Memory squeeze, dropping packet.\n", dev->name); goto update_nextrxdesc; } @@ -1294,7 +1292,7 @@ e100_rx(struct net_device *dev) int align; struct sk_buff *new_skb = dev_alloc_skb(MAX_MEDIA_DATA_SIZE + 2 * L1_CACHE_BYTES); if (!new_skb) { - np->stats.rx_errors++; + dev->stats.rx_errors++; printk(KERN_NOTICE "%s: Memory squeeze, dropping packet.\n", dev->name); goto update_nextrxdesc; } @@ -1333,8 +1331,6 @@ e100_rx(struct net_device *dev) static int e100_close(struct net_device *dev) { - struct net_local *np = netdev_priv(dev); - printk(KERN_INFO "Closing %s.\n", dev->name); netif_stop_queue(dev); @@ -1366,8 +1362,8 @@ e100_close(struct net_device *dev) /* Update the statistics here. */ - update_rx_stats(&np->stats); - update_tx_stats(&np->stats); + update_rx_stats(&dev->stats); + update_tx_stats(&dev->stats); /* Stop speed/duplex timers */ del_timer(&speed_timer); @@ -1545,11 +1541,11 @@ e100_get_stats(struct net_device *dev) spin_lock_irqsave(&lp->lock, flags); - update_rx_stats(&lp->stats); - update_tx_stats(&lp->stats); + update_rx_stats(&dev->stats); + update_tx_stats(&dev->stats); spin_unlock_irqrestore(&lp->lock, flags); - return &lp->stats; + return &dev->stats; } /* diff --git a/drivers/net/cxgb4/t4_hw.c b/drivers/net/cxgb4/t4_hw.c index bb813d94aea..e97521c801e 100644 --- a/drivers/net/cxgb4/t4_hw.c +++ b/drivers/net/cxgb4/t4_hw.c @@ -2408,7 +2408,7 @@ int t4_alloc_mac_filt(struct adapter *adap, unsigned int mbox, if (index < NEXACT_MAC) ret++; else if (hash) - *hash |= (1 << hash_mac_addr(addr[i])); + *hash |= (1ULL << hash_mac_addr(addr[i])); } return ret; } diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c index 9246d2fa6cf..f54af48edb9 100644 --- a/drivers/net/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/cxgb4vf/cxgb4vf_main.c @@ -814,40 +814,48 @@ static struct net_device_stats *cxgb4vf_get_stats(struct net_device *dev) } /* - * Collect up to maxaddrs worth of a netdevice's unicast addresses into an - * array of addrss pointers and return the number collected. + * Collect up to maxaddrs worth of a netdevice's unicast addresses, starting + * at a specified offset within the list, into an array of addrss pointers and + * return the number collected. */ -static inline int collect_netdev_uc_list_addrs(const struct net_device *dev, - const u8 **addr, - unsigned int maxaddrs) +static inline unsigned int collect_netdev_uc_list_addrs(const struct net_device *dev, + const u8 **addr, + unsigned int offset, + unsigned int maxaddrs) { + unsigned int index = 0; unsigned int naddr = 0; const struct netdev_hw_addr *ha; - for_each_dev_addr(dev, ha) { - addr[naddr++] = ha->addr; - if (naddr >= maxaddrs) - break; - } + for_each_dev_addr(dev, ha) + if (index++ >= offset) { + addr[naddr++] = ha->addr; + if (naddr >= maxaddrs) + break; + } return naddr; } /* - * Collect up to maxaddrs worth of a netdevice's multicast addresses into an - * array of addrss pointers and return the number collected. + * Collect up to maxaddrs worth of a netdevice's multicast addresses, starting + * at a specified offset within the list, into an array of addrss pointers and + * return the number collected. */ -static inline int collect_netdev_mc_list_addrs(const struct net_device *dev, - const u8 **addr, - unsigned int maxaddrs) +static inline unsigned int collect_netdev_mc_list_addrs(const struct net_device *dev, + const u8 **addr, + unsigned int offset, + unsigned int maxaddrs) { + unsigned int index = 0; unsigned int naddr = 0; const struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(ha, dev) { - addr[naddr++] = ha->addr; - if (naddr >= maxaddrs) - break; - } + netdev_for_each_mc_addr(ha, dev) + if (index++ >= offset) { + addr[naddr++] = ha->addr; + if (naddr >= maxaddrs) + break; + } return naddr; } @@ -860,16 +868,20 @@ static int set_addr_filters(const struct net_device *dev, bool sleep) u64 mhash = 0; u64 uhash = 0; bool free = true; - u16 filt_idx[7]; + unsigned int offset, naddr; const u8 *addr[7]; - int ret, naddr = 0; + int ret; const struct port_info *pi = netdev_priv(dev); /* first do the secondary unicast addresses */ - naddr = collect_netdev_uc_list_addrs(dev, addr, ARRAY_SIZE(addr)); - if (naddr > 0) { + for (offset = 0; ; offset += naddr) { + naddr = collect_netdev_uc_list_addrs(dev, addr, offset, + ARRAY_SIZE(addr)); + if (naddr == 0) + break; + ret = t4vf_alloc_mac_filt(pi->adapter, pi->viid, free, - naddr, addr, filt_idx, &uhash, sleep); + naddr, addr, NULL, &uhash, sleep); if (ret < 0) return ret; @@ -877,12 +889,17 @@ static int set_addr_filters(const struct net_device *dev, bool sleep) } /* next set up the multicast addresses */ - naddr = collect_netdev_mc_list_addrs(dev, addr, ARRAY_SIZE(addr)); - if (naddr > 0) { + for (offset = 0; ; offset += naddr) { + naddr = collect_netdev_mc_list_addrs(dev, addr, offset, + ARRAY_SIZE(addr)); + if (naddr == 0) + break; + ret = t4vf_alloc_mac_filt(pi->adapter, pi->viid, free, - naddr, addr, filt_idx, &mhash, sleep); + naddr, addr, NULL, &mhash, sleep); if (ret < 0) return ret; + free = false; } return t4vf_set_addr_hash(pi->adapter, pi->viid, uhash != 0, diff --git a/drivers/net/cxgb4vf/t4vf_hw.c b/drivers/net/cxgb4vf/t4vf_hw.c index f7d7f976064..35fc803a6a0 100644 --- a/drivers/net/cxgb4vf/t4vf_hw.c +++ b/drivers/net/cxgb4vf/t4vf_hw.c @@ -1014,48 +1014,72 @@ int t4vf_alloc_mac_filt(struct adapter *adapter, unsigned int viid, bool free, unsigned int naddr, const u8 **addr, u16 *idx, u64 *hash, bool sleep_ok) { - int i, ret; + int offset, ret = 0; + unsigned nfilters = 0; + unsigned int rem = naddr; struct fw_vi_mac_cmd cmd, rpl; - struct fw_vi_mac_exact *p; - size_t len16; - if (naddr > ARRAY_SIZE(cmd.u.exact)) + if (naddr > FW_CLS_TCAM_NUM_ENTRIES) return -EINVAL; - len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd, - u.exact[naddr]), 16); - memset(&cmd, 0, sizeof(cmd)); - cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) | - FW_CMD_REQUEST | - FW_CMD_WRITE | - (free ? FW_CMD_EXEC : 0) | - FW_VI_MAC_CMD_VIID(viid)); - cmd.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) | - FW_CMD_LEN16(len16)); + for (offset = 0; offset < naddr; /**/) { + unsigned int fw_naddr = (rem < ARRAY_SIZE(cmd.u.exact) + ? rem + : ARRAY_SIZE(cmd.u.exact)); + size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd, + u.exact[fw_naddr]), 16); + struct fw_vi_mac_exact *p; + int i; - for (i = 0, p = cmd.u.exact; i < naddr; i++, p++) { - p->valid_to_idx = - cpu_to_be16(FW_VI_MAC_CMD_VALID | - FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC)); - memcpy(p->macaddr, addr[i], sizeof(p->macaddr)); - } + memset(&cmd, 0, sizeof(cmd)); + cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) | + FW_CMD_REQUEST | + FW_CMD_WRITE | + (free ? FW_CMD_EXEC : 0) | + FW_VI_MAC_CMD_VIID(viid)); + cmd.freemacs_to_len16 = + cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) | + FW_CMD_LEN16(len16)); + + for (i = 0, p = cmd.u.exact; i < fw_naddr; i++, p++) { + p->valid_to_idx = cpu_to_be16( + FW_VI_MAC_CMD_VALID | + FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC)); + memcpy(p->macaddr, addr[offset+i], sizeof(p->macaddr)); + } + + + ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl, + sleep_ok); + if (ret && ret != -ENOMEM) + break; - ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl, sleep_ok); - if (ret) - return ret; - - for (i = 0, p = rpl.u.exact; i < naddr; i++, p++) { - u16 index = FW_VI_MAC_CMD_IDX_GET(be16_to_cpu(p->valid_to_idx)); - - if (idx) - idx[i] = (index >= FW_CLS_TCAM_NUM_ENTRIES - ? 0xffff - : index); - if (index < FW_CLS_TCAM_NUM_ENTRIES) - ret++; - else if (hash) - *hash |= (1 << hash_mac_addr(addr[i])); + for (i = 0, p = rpl.u.exact; i < fw_naddr; i++, p++) { + u16 index = FW_VI_MAC_CMD_IDX_GET( + be16_to_cpu(p->valid_to_idx)); + + if (idx) + idx[offset+i] = + (index >= FW_CLS_TCAM_NUM_ENTRIES + ? 0xffff + : index); + if (index < FW_CLS_TCAM_NUM_ENTRIES) + nfilters++; + else if (hash) + *hash |= (1ULL << hash_mac_addr(addr[offset+i])); + } + + free = false; + offset += fw_naddr; + rem -= fw_naddr; } + + /* + * If there were no errors or we merely ran out of room in our MAC + * address arena, return the number of filters actually written. + */ + if (ret == 0 || ret == -ENOMEM) + ret = nfilters; return ret; } diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index dcb7f82c270..06c7d1c6751 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -31,7 +31,7 @@ char e1000_driver_name[] = "e1000"; static char e1000_driver_string[] = "Intel(R) PRO/1000 Network Driver"; -#define DRV_VERSION "7.3.21-k6-NAPI" +#define DRV_VERSION "7.3.21-k8-NAPI" const char e1000_driver_version[] = DRV_VERSION; static const char e1000_copyright[] = "Copyright (c) 1999-2006 Intel Corporation."; @@ -485,9 +485,6 @@ void e1000_down(struct e1000_adapter *adapter) struct net_device *netdev = adapter->netdev; u32 rctl, tctl; - /* signal that we're down so the interrupt handler does not - * reschedule our watchdog timer */ - set_bit(__E1000_DOWN, &adapter->flags); /* disable receives in the hardware */ rctl = er32(RCTL); @@ -508,6 +505,13 @@ void e1000_down(struct e1000_adapter *adapter) e1000_irq_disable(adapter); + /* + * Setting DOWN must be after irq_disable to prevent + * a screaming interrupt. Setting DOWN also prevents + * timers and tasks from rescheduling. + */ + set_bit(__E1000_DOWN, &adapter->flags); + del_timer_sync(&adapter->tx_fifo_stall_timer); del_timer_sync(&adapter->watchdog_timer); del_timer_sync(&adapter->phy_info_timer); diff --git a/drivers/net/ehea/ehea_ethtool.c b/drivers/net/ehea/ehea_ethtool.c index 75b099ce49c..1f37ee6b2a2 100644 --- a/drivers/net/ehea/ehea_ethtool.c +++ b/drivers/net/ehea/ehea_ethtool.c @@ -261,6 +261,13 @@ static void ehea_get_ethtool_stats(struct net_device *dev, } +static int ehea_set_flags(struct net_device *dev, u32 data) +{ + return ethtool_op_set_flags(dev, data, ETH_FLAG_LRO + | ETH_FLAG_TXVLAN + | ETH_FLAG_RXVLAN); +} + const struct ethtool_ops ehea_ethtool_ops = { .get_settings = ehea_get_settings, .get_drvinfo = ehea_get_drvinfo, @@ -273,6 +280,8 @@ const struct ethtool_ops ehea_ethtool_ops = { .get_ethtool_stats = ehea_get_ethtool_stats, .get_rx_csum = ehea_get_rx_csum, .set_settings = ehea_set_settings, + .get_flags = ethtool_op_get_flags, + .set_flags = ehea_set_flags, .nway_reset = ehea_nway_reset, /* Restart autonegotiation */ }; diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c index a84c389d3db..69f61523fcc 100644 --- a/drivers/net/ehea/ehea_main.c +++ b/drivers/net/ehea/ehea_main.c @@ -400,6 +400,7 @@ static void ehea_refill_rq1(struct ehea_port_res *pr, int index, int nr_of_wqes) skb_arr_rq1[index] = netdev_alloc_skb(dev, EHEA_L_PKT_SIZE); if (!skb_arr_rq1[index]) { + ehea_info("Unable to allocate enough skb in the array\n"); pr->rq1_skba.os_skbs = fill_wqes - i; break; } @@ -422,13 +423,20 @@ static void ehea_init_fill_rq1(struct ehea_port_res *pr, int nr_rq1a) struct net_device *dev = pr->port->netdev; int i; - for (i = 0; i < pr->rq1_skba.len; i++) { + if (nr_rq1a > pr->rq1_skba.len) { + ehea_error("NR_RQ1A bigger than skb array len\n"); + return; + } + + for (i = 0; i < nr_rq1a; i++) { skb_arr_rq1[i] = netdev_alloc_skb(dev, EHEA_L_PKT_SIZE); - if (!skb_arr_rq1[i]) + if (!skb_arr_rq1[i]) { + ehea_info("No enough memory to allocate skb array\n"); break; + } } /* Ring doorbell */ - ehea_update_rq1a(pr->qp, nr_rq1a); + ehea_update_rq1a(pr->qp, i); } static int ehea_refill_rq_def(struct ehea_port_res *pr, @@ -675,7 +683,7 @@ static void ehea_proc_skb(struct ehea_port_res *pr, struct ehea_cqe *cqe, int vlan_extracted = ((cqe->status & EHEA_CQE_VLAN_TAG_XTRACT) && pr->port->vgrp); - if (use_lro) { + if (skb->dev->features & NETIF_F_LRO) { if (vlan_extracted) lro_vlan_hwaccel_receive_skb(&pr->lro_mgr, skb, pr->port->vgrp, @@ -735,8 +743,10 @@ static int ehea_proc_rwqes(struct net_device *dev, skb = netdev_alloc_skb(dev, EHEA_L_PKT_SIZE); - if (!skb) + if (!skb) { + ehea_info("Not enough memory to allocate skb\n"); break; + } } skb_copy_to_linear_data(skb, ((char *)cqe) + 64, cqe->num_bytes_transfered - 4); @@ -777,7 +787,7 @@ static int ehea_proc_rwqes(struct net_device *dev, } cqe = ehea_poll_rq1(qp, &wqe_index); } - if (use_lro) + if (dev->features & NETIF_F_LRO) lro_flush_all(&pr->lro_mgr); pr->rx_packets += processed; @@ -3266,6 +3276,9 @@ struct ehea_port *ehea_setup_single_port(struct ehea_adapter *adapter, | NETIF_F_LLTX; dev->watchdog_timeo = EHEA_WATCH_DOG_TIMEOUT; + if (use_lro) + dev->features |= NETIF_F_LRO; + INIT_WORK(&port->reset_task, ehea_reset_port); ret = register_netdev(dev); diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index ab9f675c5b8..fe337bd121a 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -104,6 +104,8 @@ static void ri_tasklet(unsigned long dev) rcu_read_unlock(); dev_kfree_skb(skb); stats->tx_dropped++; + if (skb_queue_len(&dp->tq) != 0) + goto resched; break; } rcu_read_unlock(); diff --git a/drivers/net/irda/sh_sir.c b/drivers/net/irda/sh_sir.c index 00b38bccd6d..52a7c86af66 100644 --- a/drivers/net/irda/sh_sir.c +++ b/drivers/net/irda/sh_sir.c @@ -258,7 +258,7 @@ static int sh_sir_set_baudrate(struct sh_sir_self *self, u32 baudrate) /* Baud Rate Error Correction x 10000 */ u32 rate_err_array[] = { - 0000, 0625, 1250, 1875, + 0, 625, 1250, 1875, 2500, 3125, 3750, 4375, 5000, 5625, 6250, 6875, 7500, 8125, 8750, 9375, diff --git a/drivers/net/ixgbe/ixgbe_82599.c b/drivers/net/ixgbe/ixgbe_82599.c index 385ccebb826..6827dddc383 100644 --- a/drivers/net/ixgbe/ixgbe_82599.c +++ b/drivers/net/ixgbe/ixgbe_82599.c @@ -96,6 +96,8 @@ static void ixgbe_init_mac_link_ops_82599(struct ixgbe_hw *hw) static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) { s32 ret_val = 0; + u32 reg_anlp1 = 0; + u32 i = 0; u16 list_offset, data_offset, data_value; if (hw->phy.sfp_type != ixgbe_sfp_type_unknown) { @@ -122,14 +124,34 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) IXGBE_WRITE_FLUSH(hw); hw->eeprom.ops.read(hw, ++data_offset, &data_value); } - /* Now restart DSP by setting Restart_AN */ - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, - (IXGBE_READ_REG(hw, IXGBE_AUTOC) | IXGBE_AUTOC_AN_RESTART)); /* Release the semaphore */ ixgbe_release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); /* Delay obtaining semaphore again to allow FW access */ msleep(hw->eeprom.semaphore_delay); + + /* Now restart DSP by setting Restart_AN and clearing LMS */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, ((IXGBE_READ_REG(hw, + IXGBE_AUTOC) & ~IXGBE_AUTOC_LMS_MASK) | + IXGBE_AUTOC_AN_RESTART)); + + /* Wait for AN to leave state 0 */ + for (i = 0; i < 10; i++) { + msleep(4); + reg_anlp1 = IXGBE_READ_REG(hw, IXGBE_ANLP1); + if (reg_anlp1 & IXGBE_ANLP1_AN_STATE_MASK) + break; + } + if (!(reg_anlp1 & IXGBE_ANLP1_AN_STATE_MASK)) { + hw_dbg(hw, "sfp module setup not complete\n"); + ret_val = IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; + goto setup_sfp_out; + } + + /* Restart DSP by setting Restart_AN and return to SFI mode */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, (IXGBE_READ_REG(hw, + IXGBE_AUTOC) | IXGBE_AUTOC_LMS_10G_SERIAL | + IXGBE_AUTOC_AN_RESTART)); } setup_sfp_out: diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index f97353cdb60..fdb35d040d2 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -3800,7 +3800,7 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter) /* enable the optics for both mult-speed fiber and 82599 SFP+ fiber */ if (hw->mac.ops.enable_tx_laser && ((hw->phy.multispeed_fiber) || - ((hw->phy.type == ixgbe_media_type_fiber) && + ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) && (hw->mac.type == ixgbe_mac_82599EB)))) hw->mac.ops.enable_tx_laser(hw); @@ -4122,7 +4122,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter) /* power down the optics for multispeed fiber and 82599 SFP+ fiber */ if (hw->mac.ops.disable_tx_laser && ((hw->phy.multispeed_fiber) || - ((hw->phy.type == ixgbe_media_type_fiber) && + ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) && (hw->mac.type == ixgbe_mac_82599EB)))) hw->mac.ops.disable_tx_laser(hw); @@ -4987,6 +4987,9 @@ void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter) adapter->rx_ring[i] = NULL; } + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + ixgbe_free_q_vectors(adapter); ixgbe_reset_interrupt_capability(adapter); } @@ -7212,7 +7215,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, /* power down the optics for multispeed fiber and 82599 SFP+ fiber */ if (hw->mac.ops.disable_tx_laser && ((hw->phy.multispeed_fiber) || - ((hw->phy.type == ixgbe_media_type_fiber) && + ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) && (hw->mac.type == ixgbe_mac_82599EB)))) hw->mac.ops.disable_tx_laser(hw); diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h index ef816dd5a8f..0f80893edab 100644 --- a/drivers/net/ixgbe/ixgbe_type.h +++ b/drivers/net/ixgbe/ixgbe_type.h @@ -1470,6 +1470,8 @@ #define IXGBE_ANLP1_PAUSE 0x0C00 #define IXGBE_ANLP1_SYM_PAUSE 0x0400 #define IXGBE_ANLP1_ASM_PAUSE 0x0800 +#define IXGBE_ANLP1_AN_STATE_MASK 0x000f0000 + /* SW Semaphore Register bitmasks */ #define IXGBE_SWSM_SMBI 0x00000001 /* Driver Semaphore bit */ @@ -2641,6 +2643,7 @@ struct ixgbe_info { #define IXGBE_ERR_NO_SPACE -25 #define IXGBE_ERR_OVERTEMP -26 #define IXGBE_ERR_RAR_INDEX -27 +#define IXGBE_ERR_SFP_SETUP_NOT_COMPLETE -30 #define IXGBE_ERR_PBA_SECTION -31 #define IXGBE_ERR_INVALID_ARGUMENT -32 #define IXGBE_NOT_IMPLEMENTED 0x7FFFFFFF diff --git a/drivers/net/jme.c b/drivers/net/jme.c index c57d9a43cec..2411e72ba57 100644 --- a/drivers/net/jme.c +++ b/drivers/net/jme.c @@ -2076,12 +2076,11 @@ jme_change_mtu(struct net_device *netdev, int new_mtu) } if (new_mtu > 1900) { - netdev->features &= ~(NETIF_F_HW_CSUM | - NETIF_F_TSO | - NETIF_F_TSO6); + netdev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_TSO | NETIF_F_TSO6); } else { if (test_bit(JME_FLAG_TXCSUM, &jme->flags)) - netdev->features |= NETIF_F_HW_CSUM; + netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; if (test_bit(JME_FLAG_TSO, &jme->flags)) netdev->features |= NETIF_F_TSO | NETIF_F_TSO6; } @@ -2514,10 +2513,12 @@ jme_set_tx_csum(struct net_device *netdev, u32 on) if (on) { set_bit(JME_FLAG_TXCSUM, &jme->flags); if (netdev->mtu <= 1900) - netdev->features |= NETIF_F_HW_CSUM; + netdev->features |= + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; } else { clear_bit(JME_FLAG_TXCSUM, &jme->flags); - netdev->features &= ~NETIF_F_HW_CSUM; + netdev->features &= + ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); } return 0; @@ -2797,7 +2798,8 @@ jme_init_one(struct pci_dev *pdev, netdev->netdev_ops = &jme_netdev_ops; netdev->ethtool_ops = &jme_ethtool_ops; netdev->watchdog_timeo = TX_TIMEOUT; - netdev->features = NETIF_F_HW_CSUM | + netdev->features = NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | diff --git a/drivers/net/pch_gbe/pch_gbe_ethtool.c b/drivers/net/pch_gbe/pch_gbe_ethtool.c index c8cc32c0edc..c8c873b31a8 100644 --- a/drivers/net/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/pch_gbe/pch_gbe_ethtool.c @@ -468,18 +468,6 @@ static int pch_gbe_set_rx_csum(struct net_device *netdev, u32 data) return 0; } -/** - * pch_gbe_get_tx_csum - Report whether transmit checksums are turned on or off - * @netdev: Network interface device structure - * Returns - * true(1): Checksum On - * false(0): Checksum Off - */ -static u32 pch_gbe_get_tx_csum(struct net_device *netdev) -{ - return (netdev->features & NETIF_F_HW_CSUM) != 0; -} - /** * pch_gbe_set_tx_csum - Turn transmit checksums on or off * @netdev: Network interface device structure @@ -493,11 +481,7 @@ static int pch_gbe_set_tx_csum(struct net_device *netdev, u32 data) struct pch_gbe_adapter *adapter = netdev_priv(netdev); adapter->tx_csum = data; - if (data) - netdev->features |= NETIF_F_HW_CSUM; - else - netdev->features &= ~NETIF_F_HW_CSUM; - return 0; + return ethtool_op_set_tx_ipv6_csum(netdev, data); } /** @@ -572,7 +556,6 @@ static const struct ethtool_ops pch_gbe_ethtool_ops = { .set_pauseparam = pch_gbe_set_pauseparam, .get_rx_csum = pch_gbe_get_rx_csum, .set_rx_csum = pch_gbe_set_rx_csum, - .get_tx_csum = pch_gbe_get_tx_csum, .set_tx_csum = pch_gbe_set_tx_csum, .get_strings = pch_gbe_get_strings, .get_ethtool_stats = pch_gbe_get_ethtool_stats, diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c index afb75066b14..d7355306a73 100644 --- a/drivers/net/pch_gbe/pch_gbe_main.c +++ b/drivers/net/pch_gbe/pch_gbe_main.c @@ -1,6 +1,6 @@ /* * Copyright (C) 1999 - 2010 Intel Corporation. - * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD. + * Copyright (C) 2010 OKI SEMICONDUCTOR CO., LTD. * * This code was derived from the Intel e1000e Linux driver. * @@ -2319,7 +2319,7 @@ static int pch_gbe_probe(struct pci_dev *pdev, netdev->watchdog_timeo = PCH_GBE_WATCHDOG_PERIOD; netif_napi_add(netdev, &adapter->napi, pch_gbe_napi_poll, PCH_GBE_RX_WEIGHT); - netdev->features = NETIF_F_HW_CSUM | NETIF_F_GRO; + netdev->features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_GRO; pch_gbe_set_ethtool_ops(netdev); pch_gbe_mac_reset_hw(&adapter->hw); @@ -2358,9 +2358,9 @@ static int pch_gbe_probe(struct pci_dev *pdev, pch_gbe_check_options(adapter); if (adapter->tx_csum) - netdev->features |= NETIF_F_HW_CSUM; + netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; else - netdev->features &= ~NETIF_F_HW_CSUM; + netdev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); /* initialize the wol settings based on the eeprom settings */ adapter->wake_up_evt = PCH_GBE_WL_INIT_SETTING; @@ -2462,8 +2462,8 @@ static void __exit pch_gbe_exit_module(void) module_init(pch_gbe_init_module); module_exit(pch_gbe_exit_module); -MODULE_DESCRIPTION("OKI semiconductor PCH Gigabit ethernet Driver"); -MODULE_AUTHOR("OKI semiconductor, "); +MODULE_DESCRIPTION("EG20T PCH Gigabit ethernet Driver"); +MODULE_AUTHOR("OKI SEMICONDUCTOR, "); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, pch_gbe_pcidev_id); diff --git a/drivers/net/pch_gbe/pch_gbe_param.c b/drivers/net/pch_gbe/pch_gbe_param.c index 2510146fc56..ef0996a0eaa 100644 --- a/drivers/net/pch_gbe/pch_gbe_param.c +++ b/drivers/net/pch_gbe/pch_gbe_param.c @@ -434,8 +434,8 @@ void pch_gbe_check_options(struct pch_gbe_adapter *adapter) .err = "using default of " __MODULE_STRING(PCH_GBE_DEFAULT_TXD), .def = PCH_GBE_DEFAULT_TXD, - .arg = { .r = { .min = PCH_GBE_MIN_TXD } }, - .arg = { .r = { .max = PCH_GBE_MAX_TXD } } + .arg = { .r = { .min = PCH_GBE_MIN_TXD, + .max = PCH_GBE_MAX_TXD } } }; struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring; tx_ring->count = TxDescriptors; @@ -450,8 +450,8 @@ void pch_gbe_check_options(struct pch_gbe_adapter *adapter) .err = "using default of " __MODULE_STRING(PCH_GBE_DEFAULT_RXD), .def = PCH_GBE_DEFAULT_RXD, - .arg = { .r = { .min = PCH_GBE_MIN_RXD } }, - .arg = { .r = { .max = PCH_GBE_MAX_RXD } } + .arg = { .r = { .min = PCH_GBE_MIN_RXD, + .max = PCH_GBE_MAX_RXD } } }; struct pch_gbe_rx_ring *rx_ring = adapter->rx_ring; rx_ring->count = RxDescriptors; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index f0bd1a1aba3..e8b9c53c304 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -30,11 +30,14 @@ #include #include #include +#include #include #include #include +#define MII_MARVELL_PHY_PAGE 22 + #define MII_M1011_IEVENT 0x13 #define MII_M1011_IEVENT_CLEAR 0x0000 @@ -80,7 +83,6 @@ #define MII_88E1121_PHY_LED_CTRL 16 #define MII_88E1121_PHY_LED_PAGE 3 #define MII_88E1121_PHY_LED_DEF 0x0030 -#define MII_88E1121_PHY_PAGE 22 #define MII_M1011_PHY_STATUS 0x11 #define MII_M1011_PHY_STATUS_1000 0x8000 @@ -186,13 +188,94 @@ static int marvell_config_aneg(struct phy_device *phydev) return 0; } +#ifdef CONFIG_OF_MDIO +/* + * Set and/or override some configuration registers based on the + * marvell,reg-init property stored in the of_node for the phydev. + * + * marvell,reg-init = ,...; + * + * There may be one or more sets of : + * + * reg-page: which register bank to use. + * reg: the register. + * mask: if non-zero, ANDed with existing register value. + * value: ORed with the masked value and written to the regiser. + * + */ +static int marvell_of_reg_init(struct phy_device *phydev) +{ + const __be32 *paddr; + int len, i, saved_page, current_page, page_changed, ret; + + if (!phydev->dev.of_node) + return 0; + + paddr = of_get_property(phydev->dev.of_node, "marvell,reg-init", &len); + if (!paddr || len < (4 * sizeof(*paddr))) + return 0; + + saved_page = phy_read(phydev, MII_MARVELL_PHY_PAGE); + if (saved_page < 0) + return saved_page; + page_changed = 0; + current_page = saved_page; + + ret = 0; + len /= sizeof(*paddr); + for (i = 0; i < len - 3; i += 4) { + u16 reg_page = be32_to_cpup(paddr + i); + u16 reg = be32_to_cpup(paddr + i + 1); + u16 mask = be32_to_cpup(paddr + i + 2); + u16 val_bits = be32_to_cpup(paddr + i + 3); + int val; + + if (reg_page != current_page) { + current_page = reg_page; + page_changed = 1; + ret = phy_write(phydev, MII_MARVELL_PHY_PAGE, reg_page); + if (ret < 0) + goto err; + } + + val = 0; + if (mask) { + val = phy_read(phydev, reg); + if (val < 0) { + ret = val; + goto err; + } + val &= mask; + } + val |= val_bits; + + ret = phy_write(phydev, reg, val); + if (ret < 0) + goto err; + + } +err: + if (page_changed) { + i = phy_write(phydev, MII_MARVELL_PHY_PAGE, saved_page); + if (ret == 0) + ret = i; + } + return ret; +} +#else +static int marvell_of_reg_init(struct phy_device *phydev) +{ + return 0; +} +#endif /* CONFIG_OF_MDIO */ + static int m88e1121_config_aneg(struct phy_device *phydev) { int err, oldpage, mscr; - oldpage = phy_read(phydev, MII_88E1121_PHY_PAGE); + oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE); - err = phy_write(phydev, MII_88E1121_PHY_PAGE, + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_MSCR_PAGE); if (err < 0) return err; @@ -218,7 +301,7 @@ static int m88e1121_config_aneg(struct phy_device *phydev) return err; } - phy_write(phydev, MII_88E1121_PHY_PAGE, oldpage); + phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage); err = phy_write(phydev, MII_BMCR, BMCR_RESET); if (err < 0) @@ -229,11 +312,11 @@ static int m88e1121_config_aneg(struct phy_device *phydev) if (err < 0) return err; - oldpage = phy_read(phydev, MII_88E1121_PHY_PAGE); + oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE); - phy_write(phydev, MII_88E1121_PHY_PAGE, MII_88E1121_PHY_LED_PAGE); + phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_LED_PAGE); phy_write(phydev, MII_88E1121_PHY_LED_CTRL, MII_88E1121_PHY_LED_DEF); - phy_write(phydev, MII_88E1121_PHY_PAGE, oldpage); + phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage); err = genphy_config_aneg(phydev); @@ -244,9 +327,9 @@ static int m88e1318_config_aneg(struct phy_device *phydev) { int err, oldpage, mscr; - oldpage = phy_read(phydev, MII_88E1121_PHY_PAGE); + oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE); - err = phy_write(phydev, MII_88E1121_PHY_PAGE, + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_MSCR_PAGE); if (err < 0) return err; @@ -258,7 +341,7 @@ static int m88e1318_config_aneg(struct phy_device *phydev) if (err < 0) return err; - err = phy_write(phydev, MII_88E1121_PHY_PAGE, oldpage); + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage); if (err < 0) return err; @@ -368,6 +451,9 @@ static int m88e1111_config_init(struct phy_device *phydev) return err; } + err = marvell_of_reg_init(phydev); + if (err < 0) + return err; err = phy_write(phydev, MII_BMCR, BMCR_RESET); if (err < 0) @@ -398,7 +484,7 @@ static int m88e1118_config_init(struct phy_device *phydev) int err; /* Change address */ - err = phy_write(phydev, 0x16, 0x0002); + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, 0x0002); if (err < 0) return err; @@ -408,7 +494,7 @@ static int m88e1118_config_init(struct phy_device *phydev) return err; /* Change address */ - err = phy_write(phydev, 0x16, 0x0003); + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, 0x0003); if (err < 0) return err; @@ -420,8 +506,42 @@ static int m88e1118_config_init(struct phy_device *phydev) if (err < 0) return err; + err = marvell_of_reg_init(phydev); + if (err < 0) + return err; + /* Reset address */ - err = phy_write(phydev, 0x16, 0x0); + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, 0x0); + if (err < 0) + return err; + + err = phy_write(phydev, MII_BMCR, BMCR_RESET); + if (err < 0) + return err; + + return 0; +} + +static int m88e1149_config_init(struct phy_device *phydev) +{ + int err; + + /* Change address */ + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, 0x0002); + if (err < 0) + return err; + + /* Enable 1000 Mbit */ + err = phy_write(phydev, 0x15, 0x1048); + if (err < 0) + return err; + + err = marvell_of_reg_init(phydev); + if (err < 0) + return err; + + /* Reset address */ + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, 0x0); if (err < 0) return err; @@ -491,6 +611,10 @@ static int m88e1145_config_init(struct phy_device *phydev) } } + err = marvell_of_reg_init(phydev); + if (err < 0) + return err; + return 0; } @@ -684,6 +808,19 @@ static struct phy_driver marvell_drivers[] = { .config_intr = &marvell_config_intr, .driver = { .owner = THIS_MODULE }, }, + { + .phy_id = MARVELL_PHY_ID_88E1149R, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .name = "Marvell 88E1149R", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = &m88e1149_config_init, + .config_aneg = &m88e1118_config_aneg, + .read_status = &genphy_read_status, + .ack_interrupt = &marvell_ack_interrupt, + .config_intr = &marvell_config_intr, + .driver = { .owner = THIS_MODULE }, + }, { .phy_id = MARVELL_PHY_ID_88E1240, .phy_id_mask = MARVELL_PHY_ID_MASK, @@ -735,6 +872,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = { { 0x01410e10, 0xfffffff0 }, { 0x01410cb0, 0xfffffff0 }, { 0x01410cd0, 0xfffffff0 }, + { 0x01410e50, 0xfffffff0 }, { 0x01410e30, 0xfffffff0 }, { 0x01410e90, 0xfffffff0 }, { } diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index 0c91598ae28..b708f68471a 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -2580,16 +2580,16 @@ ppp_create_interface(struct net *net, int unit, int *retp) */ dev_net_set(dev, net); - ret = -EEXIST; mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { unit = unit_get(&pn->units_idr, ppp); if (unit < 0) { - *retp = unit; + ret = unit; goto out2; } } else { + ret = -EEXIST; if (unit_find(&pn->units_idr, unit)) goto out2; /* unit already exists */ /* @@ -2664,10 +2664,10 @@ static void ppp_shutdown_interface(struct ppp *ppp) ppp->closing = 1; ppp_unlock(ppp); unregister_netdev(ppp->dev); + unit_put(&pn->units_idr, ppp->file.index); } else ppp_unlock(ppp); - unit_put(&pn->units_idr, ppp->file.index); ppp->file.dead = 1; ppp->owner = NULL; wake_up_interruptible(&ppp->file.rwait); @@ -2855,8 +2855,7 @@ static void __exit ppp_cleanup(void) * by holding all_ppp_mutex */ -/* associate pointer with specified number */ -static int unit_set(struct idr *p, void *ptr, int n) +static int __unit_alloc(struct idr *p, void *ptr, int n) { int unit, err; @@ -2867,10 +2866,24 @@ again: } err = idr_get_new_above(p, ptr, n, &unit); - if (err == -EAGAIN) - goto again; + if (err < 0) { + if (err == -EAGAIN) + goto again; + return err; + } + + return unit; +} + +/* associate pointer with specified number */ +static int unit_set(struct idr *p, void *ptr, int n) +{ + int unit; - if (unit != n) { + unit = __unit_alloc(p, ptr, n); + if (unit < 0) + return unit; + else if (unit != n) { idr_remove(p, unit); return -EINVAL; } @@ -2881,19 +2894,7 @@ again: /* get new free unit number and associate pointer with it */ static int unit_get(struct idr *p, void *ptr) { - int unit, err; - -again: - if (!idr_pre_get(p, GFP_KERNEL)) { - printk(KERN_ERR "PPP: No free memory for idr\n"); - return -ENOMEM; - } - - err = idr_get_new_above(p, ptr, 0, &unit); - if (err == -EAGAIN) - goto again; - - return unit; + return __unit_alloc(p, ptr, 0); } /* put unit number back to a pool */ diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c index d9a76260880..e4dbbbfec72 100644 --- a/drivers/net/qlge/qlge_main.c +++ b/drivers/net/qlge/qlge_main.c @@ -62,15 +62,15 @@ static const u32 default_msg = /* NETIF_MSG_PKTDATA | */ NETIF_MSG_HW | NETIF_MSG_WOL | 0; -static int debug = 0x00007fff; /* defaults above */ -module_param(debug, int, 0); +static int debug = -1; /* defaults above */ +module_param(debug, int, 0664); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); #define MSIX_IRQ 0 #define MSI_IRQ 1 #define LEG_IRQ 2 static int qlge_irq_type = MSIX_IRQ; -module_param(qlge_irq_type, int, MSIX_IRQ); +module_param(qlge_irq_type, int, 0664); MODULE_PARM_DESC(qlge_irq_type, "0 = MSI-X, 1 = MSI, 2 = Legacy."); static int qlge_mpi_coredump; diff --git a/drivers/net/sc92031.c b/drivers/net/sc92031.c index 417adf37282..76290a8c3c1 100644 --- a/drivers/net/sc92031.c +++ b/drivers/net/sc92031.c @@ -1449,7 +1449,8 @@ static int __devinit sc92031_probe(struct pci_dev *pdev, dev->irq = pdev->irq; /* faked with skb_copy_and_csum_dev */ - dev->features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA; + dev->features = NETIF_F_SG | NETIF_F_HIGHDMA | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; dev->netdev_ops = &sc92031_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index f3e4043d70e..2166c1d0a53 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -196,7 +196,9 @@ MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value"); static void efx_remove_channels(struct efx_nic *efx); static void efx_remove_port(struct efx_nic *efx); +static void efx_init_napi(struct efx_nic *efx); static void efx_fini_napi(struct efx_nic *efx); +static void efx_fini_napi_channel(struct efx_channel *channel); static void efx_fini_struct(struct efx_nic *efx); static void efx_start_all(struct efx_nic *efx); static void efx_stop_all(struct efx_nic *efx); @@ -334,8 +336,10 @@ void efx_process_channel_now(struct efx_channel *channel) /* Disable interrupts and wait for ISRs to complete */ efx_nic_disable_interrupts(efx); - if (efx->legacy_irq) + if (efx->legacy_irq) { synchronize_irq(efx->legacy_irq); + efx->legacy_irq_enabled = false; + } if (channel->irq) synchronize_irq(channel->irq); @@ -350,6 +354,8 @@ void efx_process_channel_now(struct efx_channel *channel) efx_channel_processed(channel); napi_enable(&channel->napi_str); + if (efx->legacy_irq) + efx->legacy_irq_enabled = true; efx_nic_enable_interrupts(efx); } @@ -425,6 +431,7 @@ efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel) *channel = *old_channel; + channel->napi_dev = NULL; memset(&channel->eventq, 0, sizeof(channel->eventq)); rx_queue = &channel->rx_queue; @@ -735,9 +742,13 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) if (rc) goto rollback; + efx_init_napi(efx); + /* Destroy old channels */ - for (i = 0; i < efx->n_channels; i++) + for (i = 0; i < efx->n_channels; i++) { + efx_fini_napi_channel(other_channel[i]); efx_remove_channel(other_channel[i]); + } out: /* Free unused channel structures */ for (i = 0; i < efx->n_channels; i++) @@ -1401,6 +1412,8 @@ static void efx_start_all(struct efx_nic *efx) efx_start_channel(channel); } + if (efx->legacy_irq) + efx->legacy_irq_enabled = true; efx_nic_enable_interrupts(efx); /* Switch to event based MCDI completions after enabling interrupts. @@ -1461,8 +1474,10 @@ static void efx_stop_all(struct efx_nic *efx) /* Disable interrupts and wait for ISR to complete */ efx_nic_disable_interrupts(efx); - if (efx->legacy_irq) + if (efx->legacy_irq) { synchronize_irq(efx->legacy_irq); + efx->legacy_irq_enabled = false; + } efx_for_each_channel(channel, efx) { if (channel->irq) synchronize_irq(channel->irq); @@ -1594,7 +1609,7 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd) * **************************************************************************/ -static int efx_init_napi(struct efx_nic *efx) +static void efx_init_napi(struct efx_nic *efx) { struct efx_channel *channel; @@ -1603,18 +1618,21 @@ static int efx_init_napi(struct efx_nic *efx) netif_napi_add(channel->napi_dev, &channel->napi_str, efx_poll, napi_weight); } - return 0; +} + +static void efx_fini_napi_channel(struct efx_channel *channel) +{ + if (channel->napi_dev) + netif_napi_del(&channel->napi_str); + channel->napi_dev = NULL; } static void efx_fini_napi(struct efx_nic *efx) { struct efx_channel *channel; - efx_for_each_channel(channel, efx) { - if (channel->napi_dev) - netif_napi_del(&channel->napi_str); - channel->napi_dev = NULL; - } + efx_for_each_channel(channel, efx) + efx_fini_napi_channel(channel); } /************************************************************************** @@ -2331,9 +2349,7 @@ static int efx_pci_probe_main(struct efx_nic *efx) if (rc) goto fail1; - rc = efx_init_napi(efx); - if (rc) - goto fail2; + efx_init_napi(efx); rc = efx->type->init(efx); if (rc) { @@ -2364,7 +2380,6 @@ static int efx_pci_probe_main(struct efx_nic *efx) efx->type->fini(efx); fail3: efx_fini_napi(efx); - fail2: efx_remove_all(efx); fail1: return rc; diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h index 0d19fbfc5c2..4c12332434b 100644 --- a/drivers/net/sfc/net_driver.h +++ b/drivers/net/sfc/net_driver.h @@ -621,6 +621,7 @@ struct efx_filter_state; * @pci_dev: The PCI device * @type: Controller type attributes * @legacy_irq: IRQ number + * @legacy_irq_enabled: Are IRQs enabled on NIC (INT_EN_KER register)? * @workqueue: Workqueue for port reconfigures and the HW monitor. * Work items do not hold and must not acquire RTNL. * @workqueue_name: Name of workqueue @@ -702,6 +703,7 @@ struct efx_nic { struct pci_dev *pci_dev; const struct efx_nic_type *type; int legacy_irq; + bool legacy_irq_enabled; struct workqueue_struct *workqueue; char workqueue_name[16]; struct work_struct reset_work; diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c index 9743cff1513..399b12abe2f 100644 --- a/drivers/net/sfc/nic.c +++ b/drivers/net/sfc/nic.c @@ -1380,6 +1380,12 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id) u32 queues; int syserr; + /* Could this be ours? If interrupts are disabled then the + * channel state may not be valid. + */ + if (!efx->legacy_irq_enabled) + return result; + /* Read the ISR which also ACKs the interrupts */ efx_readd(efx, ®, FR_BZ_INT_ISR0); queues = EFX_EXTRACT_DWORD(reg, 0, 31); diff --git a/drivers/net/stmmac/stmmac_ethtool.c b/drivers/net/stmmac/stmmac_ethtool.c index f2695fd180c..fd719edc7f7 100644 --- a/drivers/net/stmmac/stmmac_ethtool.c +++ b/drivers/net/stmmac/stmmac_ethtool.c @@ -197,16 +197,6 @@ static void stmmac_ethtool_gregs(struct net_device *dev, } } -static int stmmac_ethtool_set_tx_csum(struct net_device *netdev, u32 data) -{ - if (data) - netdev->features |= NETIF_F_HW_CSUM; - else - netdev->features &= ~NETIF_F_HW_CSUM; - - return 0; -} - static u32 stmmac_ethtool_get_rx_csum(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); @@ -370,7 +360,7 @@ static struct ethtool_ops stmmac_ethtool_ops = { .get_link = ethtool_op_get_link, .get_rx_csum = stmmac_ethtool_get_rx_csum, .get_tx_csum = ethtool_op_get_tx_csum, - .set_tx_csum = stmmac_ethtool_set_tx_csum, + .set_tx_csum = ethtool_op_set_tx_ipv6_csum, .get_sg = ethtool_op_get_sg, .set_sg = ethtool_op_set_sg, .get_pauseparam = stmmac_get_pauseparam, diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c index 730a6fd79ee..c0dc78571c6 100644 --- a/drivers/net/stmmac/stmmac_main.c +++ b/drivers/net/stmmac/stmmac_main.c @@ -1494,7 +1494,8 @@ static int stmmac_probe(struct net_device *dev) dev->netdev_ops = &stmmac_netdev_ops; stmmac_set_ethtool_ops(dev); - dev->features |= (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA); + dev->features |= NETIF_F_SG | NETIF_F_HIGHDMA | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; dev->watchdog_timeo = msecs_to_jiffies(watchdog); #ifdef STMMAC_VLAN_TAG_USED /* Both mac100 and gmac support receive VLAN tag detection */ @@ -1516,6 +1517,8 @@ static int stmmac_probe(struct net_device *dev) pr_warning("\tno valid MAC address;" "please, use ifconfig or nwhwconfig!\n"); + spin_lock_init(&priv->lock); + ret = register_netdev(dev); if (ret) { pr_err("%s: ERROR %i registering the device\n", @@ -1525,9 +1528,7 @@ static int stmmac_probe(struct net_device *dev) DBG(probe, DEBUG, "%s: Scatter/Gather: %s - HW checksums: %s\n", dev->name, (dev->features & NETIF_F_SG) ? "on" : "off", - (dev->features & NETIF_F_HW_CSUM) ? "on" : "off"); - - spin_lock_init(&priv->lock); + (dev->features & NETIF_F_IP_CSUM) ? "on" : "off"); return ret; } diff --git a/drivers/net/tulip/dmfe.c b/drivers/net/tulip/dmfe.c index a9f7d5d1a26..7064e035757 100644 --- a/drivers/net/tulip/dmfe.c +++ b/drivers/net/tulip/dmfe.c @@ -688,9 +688,6 @@ static netdev_tx_t dmfe_start_xmit(struct sk_buff *skb, DMFE_DBUG(0, "dmfe_start_xmit", 0); - /* Resource flag check */ - netif_stop_queue(dev); - /* Too large packet check */ if (skb->len > MAX_PACKET_SIZE) { pr_err("big packet = %d\n", (u16)skb->len); @@ -698,6 +695,9 @@ static netdev_tx_t dmfe_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } + /* Resource flag check */ + netif_stop_queue(dev); + spin_lock_irqsave(&db->lock, flags); /* No Tx resource check, it never happen nromally */ diff --git a/drivers/net/ucc_geth.h b/drivers/net/ucc_geth.h index 05a95586f3c..055b87ab4f0 100644 --- a/drivers/net/ucc_geth.h +++ b/drivers/net/ucc_geth.h @@ -899,7 +899,8 @@ struct ucc_geth_hardware_statistics { #define UCC_GETH_UTFS_INIT 512 /* Tx virtual FIFO size */ #define UCC_GETH_UTFET_INIT 256 /* 1/2 utfs */ -#define UCC_GETH_UTFTT_INIT 512 +#define UCC_GETH_UTFTT_INIT 256 /* 1/2 utfs + due to errata */ /* Gigabit Ethernet (1000 Mbps) */ #define UCC_GETH_URFS_GIGA_INIT 4096/*2048*/ /* Rx virtual FIFO size */ diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 52ffabe6db0..6f600cced6e 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -196,6 +196,25 @@ config USB_NET_CDC_EEM IEEE 802 "local assignment" bit is set in the address, a "usbX" name is used instead. +config USB_NET_CDC_NCM + tristate "CDC NCM support" + depends on USB_USBNET + default y + help + This driver provides support for CDC NCM (Network Control Model + Device USB Class Specification). The CDC NCM specification is + available from . + + Say "y" to link the driver statically, or "m" to build a + dynamically linked module. + + This driver should work with at least the following devices: + * ST-Ericsson M700 LTE FDD/TDD Mobile Broadband Modem (ref. design) + * ST-Ericsson M5730 HSPA+ Mobile Broadband Modem (reference design) + * ST-Ericsson M570 HSPA+ Mobile Broadband Modem (reference design) + * ST-Ericsson M343 HSPA Mobile Broadband Modem (reference design) + * Ericsson F5521gw Mobile Broadband Module + config USB_NET_DM9601 tristate "Davicom DM9601 based USB 1.1 10/100 ethernet devices" depends on USB_USBNET diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index a19b0259ae1..cac17030118 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -26,4 +26,5 @@ obj-$(CONFIG_USB_CDC_PHONET) += cdc-phonet.o obj-$(CONFIG_USB_IPHETH) += ipheth.o obj-$(CONFIG_USB_SIERRA_NET) += sierra_net.o obj-$(CONFIG_USB_NET_CX82310_ETH) += cx82310_eth.o +obj-$(CONFIG_USB_NET_CDC_NCM) += cdc_ncm.o diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c new file mode 100644 index 00000000000..593c104ab19 --- /dev/null +++ b/drivers/net/usb/cdc_ncm.c @@ -0,0 +1,1213 @@ +/* + * cdc_ncm.c + * + * Copyright (C) ST-Ericsson 2010 + * Contact: Alexey Orishko + * Original author: Hans Petter Selasky + * + * USB Host Driver for Network Control Model (NCM) + * http://www.usb.org/developers/devclass_docs/NCM10.zip + * + * The NCM encoding, decoding and initialization logic + * derives from FreeBSD 8.x. if_cdce.c and if_cdcereg.h + * + * This software is available to you under a choice of one of two + * licenses. You may choose this file to be licensed under the terms + * of the GNU General Public License (GPL) Version 2 or the 2-clause + * BSD license listed below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRIVER_VERSION "30-Nov-2010" + +/* CDC NCM subclass 3.2.1 */ +#define USB_CDC_NCM_NDP16_LENGTH_MIN 0x10 + +/* Maximum NTB length */ +#define CDC_NCM_NTB_MAX_SIZE_TX 16384 /* bytes */ +#define CDC_NCM_NTB_MAX_SIZE_RX 16384 /* bytes */ + +/* Minimum value for MaxDatagramSize, ch. 6.2.9 */ +#define CDC_NCM_MIN_DATAGRAM_SIZE 1514 /* bytes */ + +#define CDC_NCM_MIN_TX_PKT 512 /* bytes */ + +/* Default value for MaxDatagramSize */ +#define CDC_NCM_MAX_DATAGRAM_SIZE 2048 /* bytes */ + +/* + * Maximum amount of datagrams in NCM Datagram Pointer Table, not counting + * the last NULL entry. Any additional datagrams in NTB would be discarded. + */ +#define CDC_NCM_DPT_DATAGRAMS_MAX 32 + +/* Restart the timer, if amount of datagrams is less than given value */ +#define CDC_NCM_RESTART_TIMER_DATAGRAM_CNT 3 + +/* The following macro defines the minimum header space */ +#define CDC_NCM_MIN_HDR_SIZE \ + (sizeof(struct usb_cdc_ncm_nth16) + sizeof(struct usb_cdc_ncm_ndp16) + \ + (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16)) + +struct connection_speed_change { + __le32 USBitRate; /* holds 3GPP downlink value, bits per second */ + __le32 DSBitRate; /* holds 3GPP uplink value, bits per second */ +} __attribute__ ((packed)); + +struct cdc_ncm_data { + struct usb_cdc_ncm_nth16 nth16; + struct usb_cdc_ncm_ndp16 ndp16; + struct usb_cdc_ncm_dpe16 dpe16[CDC_NCM_DPT_DATAGRAMS_MAX + 1]; +}; + +struct cdc_ncm_ctx { + struct cdc_ncm_data rx_ncm; + struct cdc_ncm_data tx_ncm; + struct usb_cdc_ncm_ntb_parameters ncm_parm; + struct timer_list tx_timer; + + const struct usb_cdc_ncm_desc *func_desc; + const struct usb_cdc_header_desc *header_desc; + const struct usb_cdc_union_desc *union_desc; + const struct usb_cdc_ether_desc *ether_desc; + + struct net_device *netdev; + struct usb_device *udev; + struct usb_host_endpoint *in_ep; + struct usb_host_endpoint *out_ep; + struct usb_host_endpoint *status_ep; + struct usb_interface *intf; + struct usb_interface *control; + struct usb_interface *data; + + struct sk_buff *tx_curr_skb; + struct sk_buff *tx_rem_skb; + + spinlock_t mtx; + + u32 tx_timer_pending; + u32 tx_curr_offset; + u32 tx_curr_last_offset; + u32 tx_curr_frame_num; + u32 rx_speed; + u32 tx_speed; + u32 rx_max; + u32 tx_max; + u32 max_datagram_size; + u16 tx_max_datagrams; + u16 tx_remainder; + u16 tx_modulus; + u16 tx_ndp_modulus; + u16 tx_seq; + u16 connected; + u8 data_claimed; + u8 control_claimed; +}; + +static void cdc_ncm_tx_timeout(unsigned long arg); +static const struct driver_info cdc_ncm_info; +static struct usb_driver cdc_ncm_driver; +static struct ethtool_ops cdc_ncm_ethtool_ops; + +static const struct usb_device_id cdc_devs[] = { + { USB_INTERFACE_INFO(USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&cdc_ncm_info, + }, + { + }, +}; + +MODULE_DEVICE_TABLE(usb, cdc_devs); + +static void +cdc_ncm_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) +{ + 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, + sizeof(info->fw_version)); + usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); +} + +static int +cdc_ncm_do_request(struct cdc_ncm_ctx *ctx, struct usb_cdc_notification *req, + void *data, u16 flags, u16 *actlen, u16 timeout) +{ + int err; + + err = usb_control_msg(ctx->udev, (req->bmRequestType & USB_DIR_IN) ? + usb_rcvctrlpipe(ctx->udev, 0) : + usb_sndctrlpipe(ctx->udev, 0), + req->bNotificationType, req->bmRequestType, + req->wValue, + req->wIndex, data, + req->wLength, timeout); + + if (err < 0) { + if (actlen) + *actlen = 0; + return err; + } + + if (actlen) + *actlen = err; + + return 0; +} + +static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx) +{ + struct usb_cdc_notification req; + u32 val; + __le16 max_datagram_size; + u8 flags; + u8 iface_no; + int err; + + iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber; + + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_GET_NTB_PARAMETERS; + req.wValue = 0; + req.wIndex = cpu_to_le16(iface_no); + req.wLength = cpu_to_le16(sizeof(ctx->ncm_parm)); + + err = cdc_ncm_do_request(ctx, &req, &ctx->ncm_parm, 0, NULL, 1000); + if (err) { + pr_debug("failed GET_NTB_PARAMETERS\n"); + return 1; + } + + /* read correct set of parameters according to device mode */ + ctx->rx_max = le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize); + ctx->tx_max = le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize); + ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder); + ctx->tx_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutDivisor); + ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment); + + if (ctx->func_desc != NULL) + flags = ctx->func_desc->bmNetworkCapabilities; + else + flags = 0; + + pr_debug("dwNtbInMaxSize=%u dwNtbOutMaxSize=%u " + "wNdpOutPayloadRemainder=%u wNdpOutDivisor=%u " + "wNdpOutAlignment=%u flags=0x%x\n", + ctx->rx_max, ctx->tx_max, ctx->tx_remainder, ctx->tx_modulus, + ctx->tx_ndp_modulus, flags); + + /* max count of tx datagrams without terminating NULL entry */ + ctx->tx_max_datagrams = CDC_NCM_DPT_DATAGRAMS_MAX; + + /* verify maximum size of received NTB in bytes */ + if ((ctx->rx_max < + (CDC_NCM_MIN_HDR_SIZE + CDC_NCM_MIN_DATAGRAM_SIZE)) || + (ctx->rx_max > CDC_NCM_NTB_MAX_SIZE_RX)) { + pr_debug("Using default maximum receive length=%d\n", + CDC_NCM_NTB_MAX_SIZE_RX); + ctx->rx_max = CDC_NCM_NTB_MAX_SIZE_RX; + } + + /* verify maximum size of transmitted NTB in bytes */ + if ((ctx->tx_max < + (CDC_NCM_MIN_HDR_SIZE + CDC_NCM_MIN_DATAGRAM_SIZE)) || + (ctx->tx_max > CDC_NCM_NTB_MAX_SIZE_TX)) { + pr_debug("Using default maximum transmit length=%d\n", + CDC_NCM_NTB_MAX_SIZE_TX); + ctx->tx_max = CDC_NCM_NTB_MAX_SIZE_TX; + } + + /* + * verify that the structure alignment is: + * - power of two + * - not greater than the maximum transmit length + * - not less than four bytes + */ + val = ctx->tx_ndp_modulus; + + if ((val < USB_CDC_NCM_NDP_ALIGN_MIN_SIZE) || + (val != ((-val) & val)) || (val >= ctx->tx_max)) { + pr_debug("Using default alignment: 4 bytes\n"); + ctx->tx_ndp_modulus = USB_CDC_NCM_NDP_ALIGN_MIN_SIZE; + } + + /* + * verify that the payload alignment is: + * - power of two + * - not greater than the maximum transmit length + * - not less than four bytes + */ + val = ctx->tx_modulus; + + if ((val < USB_CDC_NCM_NDP_ALIGN_MIN_SIZE) || + (val != ((-val) & val)) || (val >= ctx->tx_max)) { + pr_debug("Using default transmit modulus: 4 bytes\n"); + ctx->tx_modulus = USB_CDC_NCM_NDP_ALIGN_MIN_SIZE; + } + + /* verify the payload remainder */ + if (ctx->tx_remainder >= ctx->tx_modulus) { + pr_debug("Using default transmit remainder: 0 bytes\n"); + ctx->tx_remainder = 0; + } + + /* adjust TX-remainder according to NCM specification. */ + ctx->tx_remainder = ((ctx->tx_remainder - ETH_HLEN) & + (ctx->tx_modulus - 1)); + + /* additional configuration */ + + /* set CRC Mode */ + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_SET_CRC_MODE; + req.wValue = cpu_to_le16(USB_CDC_NCM_CRC_NOT_APPENDED); + req.wIndex = cpu_to_le16(iface_no); + req.wLength = 0; + + err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000); + if (err) + pr_debug("Setting CRC mode off failed\n"); + + /* set NTB format */ + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_SET_NTB_FORMAT; + req.wValue = cpu_to_le16(USB_CDC_NCM_NTB16_FORMAT); + req.wIndex = cpu_to_le16(iface_no); + req.wLength = 0; + + err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000); + if (err) + pr_debug("Setting NTB format to 16-bit failed\n"); + + /* set Max Datagram Size (MTU) */ + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_GET_MAX_DATAGRAM_SIZE; + req.wValue = 0; + req.wIndex = cpu_to_le16(iface_no); + req.wLength = cpu_to_le16(2); + + err = cdc_ncm_do_request(ctx, &req, &max_datagram_size, 0, NULL, 1000); + if (err) { + pr_debug(" GET_MAX_DATAGRAM_SIZE failed, using size=%u\n", + CDC_NCM_MIN_DATAGRAM_SIZE); + /* use default */ + ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE; + } else { + ctx->max_datagram_size = le16_to_cpu(max_datagram_size); + + if (ctx->max_datagram_size < CDC_NCM_MIN_DATAGRAM_SIZE) + ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE; + else if (ctx->max_datagram_size > CDC_NCM_MAX_DATAGRAM_SIZE) + ctx->max_datagram_size = CDC_NCM_MAX_DATAGRAM_SIZE; + } + + if (ctx->netdev->mtu != (ctx->max_datagram_size - ETH_HLEN)) + ctx->netdev->mtu = ctx->max_datagram_size - ETH_HLEN; + + return 0; +} + +static void +cdc_ncm_find_endpoints(struct cdc_ncm_ctx *ctx, struct usb_interface *intf) +{ + struct usb_host_endpoint *e; + u8 ep; + + for (ep = 0; ep < intf->cur_altsetting->desc.bNumEndpoints; ep++) { + + e = intf->cur_altsetting->endpoint + ep; + switch (e->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) { + case USB_ENDPOINT_XFER_INT: + if (usb_endpoint_dir_in(&e->desc)) { + if (ctx->status_ep == NULL) + ctx->status_ep = e; + } + break; + + case USB_ENDPOINT_XFER_BULK: + if (usb_endpoint_dir_in(&e->desc)) { + if (ctx->in_ep == NULL) + ctx->in_ep = e; + } else { + if (ctx->out_ep == NULL) + ctx->out_ep = e; + } + break; + + default: + break; + } + } +} + +static void cdc_ncm_free(struct cdc_ncm_ctx *ctx) +{ + if (ctx == NULL) + return; + + del_timer_sync(&ctx->tx_timer); + + if (ctx->data_claimed) { + usb_set_intfdata(ctx->data, NULL); + usb_driver_release_interface(driver_of(ctx->intf), ctx->data); + } + + if (ctx->control_claimed) { + usb_set_intfdata(ctx->control, NULL); + usb_driver_release_interface(driver_of(ctx->intf), + ctx->control); + } + + if (ctx->tx_rem_skb != NULL) { + dev_kfree_skb_any(ctx->tx_rem_skb); + ctx->tx_rem_skb = NULL; + } + + if (ctx->tx_curr_skb != NULL) { + dev_kfree_skb_any(ctx->tx_curr_skb); + ctx->tx_curr_skb = NULL; + } + + kfree(ctx); +} + +static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) +{ + struct cdc_ncm_ctx *ctx; + struct usb_driver *driver; + u8 *buf; + int len; + int temp; + u8 iface_no; + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (ctx == NULL) + goto error; + + memset(ctx, 0, sizeof(*ctx)); + + init_timer(&ctx->tx_timer); + spin_lock_init(&ctx->mtx); + ctx->netdev = dev->net; + + /* store ctx pointer in device data field */ + dev->data[0] = (unsigned long)ctx; + + /* get some pointers */ + driver = driver_of(intf); + buf = intf->cur_altsetting->extra; + len = intf->cur_altsetting->extralen; + + ctx->udev = dev->udev; + ctx->intf = intf; + + /* parse through descriptors associated with control interface */ + while ((len > 0) && (buf[0] > 2) && (buf[0] <= len)) { + + if (buf[1] != USB_DT_CS_INTERFACE) + goto advance; + + switch (buf[2]) { + case USB_CDC_UNION_TYPE: + if (buf[0] < sizeof(*(ctx->union_desc))) + break; + + ctx->union_desc = + (const struct usb_cdc_union_desc *)buf; + + ctx->control = usb_ifnum_to_if(dev->udev, + ctx->union_desc->bMasterInterface0); + ctx->data = usb_ifnum_to_if(dev->udev, + ctx->union_desc->bSlaveInterface0); + break; + + case USB_CDC_ETHERNET_TYPE: + if (buf[0] < sizeof(*(ctx->ether_desc))) + break; + + ctx->ether_desc = + (const struct usb_cdc_ether_desc *)buf; + + dev->hard_mtu = + le16_to_cpu(ctx->ether_desc->wMaxSegmentSize); + + if (dev->hard_mtu < + (CDC_NCM_MIN_DATAGRAM_SIZE - ETH_HLEN)) + dev->hard_mtu = + CDC_NCM_MIN_DATAGRAM_SIZE - ETH_HLEN; + + else if (dev->hard_mtu > + (CDC_NCM_MAX_DATAGRAM_SIZE - ETH_HLEN)) + dev->hard_mtu = + CDC_NCM_MAX_DATAGRAM_SIZE - ETH_HLEN; + break; + + case USB_CDC_NCM_TYPE: + if (buf[0] < sizeof(*(ctx->func_desc))) + break; + + ctx->func_desc = (const struct usb_cdc_ncm_desc *)buf; + break; + + default: + break; + } +advance: + /* advance to next descriptor */ + temp = buf[0]; + buf += temp; + len -= temp; + } + + /* check if we got everything */ + if ((ctx->control == NULL) || (ctx->data == NULL) || + (ctx->ether_desc == NULL)) + goto error; + + /* claim interfaces, if any */ + if (ctx->data != intf) { + temp = usb_driver_claim_interface(driver, ctx->data, dev); + if (temp) + goto error; + ctx->data_claimed = 1; + } + + if (ctx->control != intf) { + temp = usb_driver_claim_interface(driver, ctx->control, dev); + if (temp) + goto error; + ctx->control_claimed = 1; + } + + iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; + + /* reset data interface */ + temp = usb_set_interface(dev->udev, iface_no, 0); + if (temp) + goto error; + + /* initialize data interface */ + if (cdc_ncm_setup(ctx)) + goto error; + + /* configure data interface */ + temp = usb_set_interface(dev->udev, iface_no, 1); + if (temp) + goto error; + + cdc_ncm_find_endpoints(ctx, ctx->data); + cdc_ncm_find_endpoints(ctx, ctx->control); + + if ((ctx->in_ep == NULL) || (ctx->out_ep == NULL) || + (ctx->status_ep == NULL)) + goto error; + + dev->net->ethtool_ops = &cdc_ncm_ethtool_ops; + + usb_set_intfdata(ctx->data, dev); + usb_set_intfdata(ctx->control, dev); + usb_set_intfdata(ctx->intf, dev); + + temp = usbnet_get_ethernet_addr(dev, ctx->ether_desc->iMACAddress); + if (temp) + goto error; + + dev_info(&dev->udev->dev, "MAC-Address: " + "0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + dev->net->dev_addr[0], dev->net->dev_addr[1], + dev->net->dev_addr[2], dev->net->dev_addr[3], + dev->net->dev_addr[4], dev->net->dev_addr[5]); + + dev->in = usb_rcvbulkpipe(dev->udev, + ctx->in_ep->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + dev->out = usb_sndbulkpipe(dev->udev, + ctx->out_ep->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + dev->status = ctx->status_ep; + dev->rx_urb_size = ctx->rx_max; + + /* + * We should get an event when network connection is "connected" or + * "disconnected". Set network connection in "disconnected" state + * (carrier is OFF) during attach, so the IP network stack does not + * start IPv6 negotiation and more. + */ + netif_carrier_off(dev->net); + ctx->tx_speed = ctx->rx_speed = 0; + return 0; + +error: + cdc_ncm_free((struct cdc_ncm_ctx *)dev->data[0]); + dev->data[0] = 0; + dev_info(&dev->udev->dev, "Descriptor failure\n"); + return -ENODEV; +} + +static void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf) +{ + struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; + struct usb_driver *driver; + + if (ctx == NULL) + return; /* no setup */ + + driver = driver_of(intf); + + usb_set_intfdata(ctx->data, NULL); + usb_set_intfdata(ctx->control, NULL); + usb_set_intfdata(ctx->intf, NULL); + + /* release interfaces, if any */ + if (ctx->data_claimed) { + usb_driver_release_interface(driver, ctx->data); + ctx->data_claimed = 0; + } + + if (ctx->control_claimed) { + usb_driver_release_interface(driver, ctx->control); + ctx->control_claimed = 0; + } + + cdc_ncm_free(ctx); +} + +static void cdc_ncm_zero_fill(u8 *ptr, u32 first, u32 end, u32 max) +{ + if (first >= max) + return; + if (first >= end) + return; + if (end > max) + end = max; + memset(ptr + first, 0, end - first); +} + +static struct sk_buff * +cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb) +{ + struct sk_buff *skb_out; + u32 rem; + u32 offset; + u32 last_offset; + u16 n = 0; + u8 timeout = 0; + + /* if there is a remaining skb, it gets priority */ + if (skb != NULL) + swap(skb, ctx->tx_rem_skb); + else + timeout = 1; + + /* + * +----------------+ + * | skb_out | + * +----------------+ + * ^ offset + * ^ last_offset + */ + + /* check if we are resuming an OUT skb */ + if (ctx->tx_curr_skb != NULL) { + /* pop variables */ + skb_out = ctx->tx_curr_skb; + offset = ctx->tx_curr_offset; + last_offset = ctx->tx_curr_last_offset; + n = ctx->tx_curr_frame_num; + + } else { + /* reset variables */ + skb_out = alloc_skb(ctx->tx_max, GFP_ATOMIC); + if (skb_out == NULL) { + if (skb != NULL) { + dev_kfree_skb_any(skb); + ctx->netdev->stats.tx_dropped++; + } + goto exit_no_skb; + } + + /* make room for NTH and NDP */ + offset = ALIGN(sizeof(struct usb_cdc_ncm_nth16), + ctx->tx_ndp_modulus) + + sizeof(struct usb_cdc_ncm_ndp16) + + (ctx->tx_max_datagrams + 1) * + sizeof(struct usb_cdc_ncm_dpe16); + + /* store last valid offset before alignment */ + last_offset = offset; + /* align first Datagram offset correctly */ + offset = ALIGN(offset, ctx->tx_modulus) + ctx->tx_remainder; + /* zero buffer till the first IP datagram */ + cdc_ncm_zero_fill(skb_out->data, 0, offset, offset); + n = 0; + ctx->tx_curr_frame_num = 0; + } + + for (; n < ctx->tx_max_datagrams; n++) { + /* check if end of transmit buffer is reached */ + if (offset >= ctx->tx_max) + break; + + /* compute maximum buffer size */ + rem = ctx->tx_max - offset; + + if (skb == NULL) { + skb = ctx->tx_rem_skb; + ctx->tx_rem_skb = NULL; + + /* check for end of skb */ + if (skb == NULL) + break; + } + + if (skb->len > rem) { + if (n == 0) { + /* won't fit, MTU problem? */ + dev_kfree_skb_any(skb); + skb = NULL; + ctx->netdev->stats.tx_dropped++; + } else { + /* no room for skb - store for later */ + if (ctx->tx_rem_skb != NULL) { + dev_kfree_skb_any(ctx->tx_rem_skb); + ctx->netdev->stats.tx_dropped++; + } + ctx->tx_rem_skb = skb; + skb = NULL; + + /* loop one more time */ + timeout = 1; + } + break; + } + + memcpy(((u8 *)skb_out->data) + offset, skb->data, skb->len); + + ctx->tx_ncm.dpe16[n].wDatagramLength = cpu_to_le16(skb->len); + ctx->tx_ncm.dpe16[n].wDatagramIndex = cpu_to_le16(offset); + + /* update offset */ + offset += skb->len; + + /* store last valid offset before alignment */ + last_offset = offset; + + /* align offset correctly */ + offset = ALIGN(offset, ctx->tx_modulus) + ctx->tx_remainder; + + /* zero padding */ + cdc_ncm_zero_fill(skb_out->data, last_offset, offset, + ctx->tx_max); + dev_kfree_skb_any(skb); + skb = NULL; + } + + /* free up any dangling skb */ + if (skb != NULL) { + dev_kfree_skb_any(skb); + skb = NULL; + ctx->netdev->stats.tx_dropped++; + } + + ctx->tx_curr_frame_num = n; + + if (n == 0) { + /* wait for more frames */ + /* push variables */ + ctx->tx_curr_skb = skb_out; + ctx->tx_curr_offset = offset; + ctx->tx_curr_last_offset = last_offset; + goto exit_no_skb; + + } else if ((n < ctx->tx_max_datagrams) && (timeout == 0)) { + /* wait for more frames */ + /* push variables */ + ctx->tx_curr_skb = skb_out; + ctx->tx_curr_offset = offset; + ctx->tx_curr_last_offset = last_offset; + /* set the pending count */ + if (n < CDC_NCM_RESTART_TIMER_DATAGRAM_CNT) + ctx->tx_timer_pending = 2; + goto exit_no_skb; + + } else { + /* frame goes out */ + /* variables will be reset at next call */ + } + + /* check for overflow */ + if (last_offset > ctx->tx_max) + last_offset = ctx->tx_max; + + /* revert offset */ + offset = last_offset; + + /* + * If collected data size is less or equal CDC_NCM_MIN_TX_PKT bytes, + * we send buffers as it is. If we get more data, it would be more + * efficient for USB HS mobile device with DMA engine to receive a full + * size NTB, than canceling DMA transfer and receiving a short packet. + */ + if (offset > CDC_NCM_MIN_TX_PKT) + offset = ctx->tx_max; + + /* final zero padding */ + cdc_ncm_zero_fill(skb_out->data, last_offset, offset, ctx->tx_max); + + /* store last offset */ + last_offset = offset; + + if ((last_offset < ctx->tx_max) && ((last_offset % + le16_to_cpu(ctx->out_ep->desc.wMaxPacketSize)) == 0)) { + /* force short packet */ + *(((u8 *)skb_out->data) + last_offset) = 0; + last_offset++; + } + + /* zero the rest of the DPEs plus the last NULL entry */ + for (; n <= CDC_NCM_DPT_DATAGRAMS_MAX; n++) { + ctx->tx_ncm.dpe16[n].wDatagramLength = 0; + ctx->tx_ncm.dpe16[n].wDatagramIndex = 0; + } + + /* fill out 16-bit NTB header */ + ctx->tx_ncm.nth16.dwSignature = cpu_to_le32(USB_CDC_NCM_NTH16_SIGN); + ctx->tx_ncm.nth16.wHeaderLength = + cpu_to_le16(sizeof(ctx->tx_ncm.nth16)); + ctx->tx_ncm.nth16.wSequence = cpu_to_le16(ctx->tx_seq); + ctx->tx_ncm.nth16.wBlockLength = cpu_to_le16(last_offset); + ctx->tx_ncm.nth16.wFpIndex = ALIGN(sizeof(struct usb_cdc_ncm_nth16), + ctx->tx_ndp_modulus); + + memcpy(skb_out->data, &(ctx->tx_ncm.nth16), sizeof(ctx->tx_ncm.nth16)); + ctx->tx_seq++; + + /* fill out 16-bit NDP table */ + ctx->tx_ncm.ndp16.dwSignature = + cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN); + rem = sizeof(ctx->tx_ncm.ndp16) + ((ctx->tx_curr_frame_num + 1) * + sizeof(struct usb_cdc_ncm_dpe16)); + ctx->tx_ncm.ndp16.wLength = cpu_to_le16(rem); + ctx->tx_ncm.ndp16.wNextFpIndex = 0; /* reserved */ + + memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wFpIndex, + &(ctx->tx_ncm.ndp16), + sizeof(ctx->tx_ncm.ndp16)); + + memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wFpIndex + + sizeof(ctx->tx_ncm.ndp16), + &(ctx->tx_ncm.dpe16), + (ctx->tx_curr_frame_num + 1) * + sizeof(struct usb_cdc_ncm_dpe16)); + + /* set frame length */ + skb_put(skb_out, last_offset); + + /* return skb */ + ctx->tx_curr_skb = NULL; + return skb_out; + +exit_no_skb: + return NULL; +} + +static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx) +{ + /* start timer, if not already started */ + if (timer_pending(&ctx->tx_timer) == 0) { + ctx->tx_timer.function = &cdc_ncm_tx_timeout; + ctx->tx_timer.data = (unsigned long)ctx; + ctx->tx_timer.expires = jiffies + ((HZ + 999) / 1000); + add_timer(&ctx->tx_timer); + } +} + +static void cdc_ncm_tx_timeout(unsigned long arg) +{ + struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)arg; + u8 restart; + + spin_lock(&ctx->mtx); + if (ctx->tx_timer_pending != 0) { + ctx->tx_timer_pending--; + restart = 1; + } else + restart = 0; + + spin_unlock(&ctx->mtx); + + if (restart) + cdc_ncm_tx_timeout_start(ctx); + else if (ctx->netdev != NULL) + usbnet_start_xmit(NULL, ctx->netdev); +} + +static struct sk_buff * +cdc_ncm_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) +{ + struct sk_buff *skb_out; + struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; + u8 need_timer = 0; + + /* + * The Ethernet API we are using does not support transmitting + * multiple Ethernet frames in a single call. This driver will + * accumulate multiple Ethernet frames and send out a larger + * USB frame when the USB buffer is full or when a single jiffies + * timeout happens. + */ + if (ctx == NULL) + goto error; + + spin_lock(&ctx->mtx); + skb_out = cdc_ncm_fill_tx_frame(ctx, skb); + if (ctx->tx_curr_skb != NULL) + need_timer = 1; + spin_unlock(&ctx->mtx); + + /* Start timer, if there is a remaining skb */ + if (need_timer) + cdc_ncm_tx_timeout_start(ctx); + + if (skb_out) + dev->net->stats.tx_packets += ctx->tx_curr_frame_num; + return skb_out; + +error: + if (skb != NULL) + dev_kfree_skb_any(skb); + + return NULL; +} + +static int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in) +{ + struct sk_buff *skb; + struct cdc_ncm_ctx *ctx; + int sumlen; + int actlen; + int temp; + int nframes; + int x; + int offset; + + ctx = (struct cdc_ncm_ctx *)dev->data[0]; + if (ctx == NULL) + goto error; + + actlen = skb_in->len; + sumlen = CDC_NCM_NTB_MAX_SIZE_RX; + + if (actlen < (sizeof(ctx->rx_ncm.nth16) + sizeof(ctx->rx_ncm.ndp16))) { + pr_debug("frame too short\n"); + goto error; + } + + memcpy(&(ctx->rx_ncm.nth16), ((u8 *)skb_in->data), + sizeof(ctx->rx_ncm.nth16)); + + if (le32_to_cpu(ctx->rx_ncm.nth16.dwSignature) != + USB_CDC_NCM_NTH16_SIGN) { + pr_debug("invalid NTH16 signature <%u>\n", + le32_to_cpu(ctx->rx_ncm.nth16.dwSignature)); + goto error; + } + + temp = le16_to_cpu(ctx->rx_ncm.nth16.wBlockLength); + if (temp > sumlen) { + pr_debug("unsupported NTB block length %u/%u\n", temp, sumlen); + goto error; + } + + temp = le16_to_cpu(ctx->rx_ncm.nth16.wFpIndex); + if ((temp + sizeof(ctx->rx_ncm.ndp16)) > actlen) { + pr_debug("invalid DPT16 index\n"); + goto error; + } + + memcpy(&(ctx->rx_ncm.ndp16), ((u8 *)skb_in->data) + temp, + sizeof(ctx->rx_ncm.ndp16)); + + if (le32_to_cpu(ctx->rx_ncm.ndp16.dwSignature) != + USB_CDC_NCM_NDP16_NOCRC_SIGN) { + pr_debug("invalid DPT16 signature <%u>\n", + le32_to_cpu(ctx->rx_ncm.ndp16.dwSignature)); + goto error; + } + + if (le16_to_cpu(ctx->rx_ncm.ndp16.wLength) < + USB_CDC_NCM_NDP16_LENGTH_MIN) { + pr_debug("invalid DPT16 length <%u>\n", + le32_to_cpu(ctx->rx_ncm.ndp16.dwSignature)); + goto error; + } + + nframes = ((le16_to_cpu(ctx->rx_ncm.ndp16.wLength) - + sizeof(struct usb_cdc_ncm_ndp16)) / + sizeof(struct usb_cdc_ncm_dpe16)); + nframes--; /* we process NDP entries except for the last one */ + + pr_debug("nframes = %u\n", nframes); + + temp += sizeof(ctx->rx_ncm.ndp16); + + if ((temp + nframes * (sizeof(struct usb_cdc_ncm_dpe16))) > actlen) { + pr_debug("Invalid nframes = %d\n", nframes); + goto error; + } + + if (nframes > CDC_NCM_DPT_DATAGRAMS_MAX) { + pr_debug("Truncating number of frames from %u to %u\n", + nframes, CDC_NCM_DPT_DATAGRAMS_MAX); + nframes = CDC_NCM_DPT_DATAGRAMS_MAX; + } + + memcpy(&(ctx->rx_ncm.dpe16), ((u8 *)skb_in->data) + temp, + nframes * (sizeof(struct usb_cdc_ncm_dpe16))); + + for (x = 0; x < nframes; x++) { + offset = le16_to_cpu(ctx->rx_ncm.dpe16[x].wDatagramIndex); + temp = le16_to_cpu(ctx->rx_ncm.dpe16[x].wDatagramLength); + + /* + * CDC NCM ch. 3.7 + * All entries after first NULL entry are to be ignored + */ + if ((offset == 0) || (temp == 0)) { + if (!x) + goto error; /* empty NTB */ + break; + } + + /* sanity checking */ + if (((offset + temp) > actlen) || + (temp > CDC_NCM_MAX_DATAGRAM_SIZE) || (temp < ETH_HLEN)) { + pr_debug("invalid frame detected (ignored)" + "offset[%u]=%u, length=%u, skb=%p\n", + x, offset, temp, skb); + if (!x) + goto error; + break; + + } else { + skb = skb_clone(skb_in, GFP_ATOMIC); + skb->len = temp; + skb->data = ((u8 *)skb_in->data) + offset; + skb_set_tail_pointer(skb, temp); + usbnet_skb_return(dev, skb); + } + } + return 1; +error: + return 0; +} + +static void +cdc_ncm_speed_change(struct cdc_ncm_ctx *ctx, + struct connection_speed_change *data) +{ + uint32_t rx_speed = le32_to_cpu(data->USBitRate); + uint32_t tx_speed = le32_to_cpu(data->DSBitRate); + + /* + * Currently the USB-NET API does not support reporting the actual + * device speed. Do print it instead. + */ + if ((tx_speed != ctx->tx_speed) || (rx_speed != ctx->rx_speed)) { + ctx->tx_speed = tx_speed; + ctx->rx_speed = rx_speed; + + if ((tx_speed > 1000000) && (rx_speed > 1000000)) { + printk(KERN_INFO KBUILD_MODNAME + ": %s: %u mbit/s downlink " + "%u mbit/s uplink\n", + ctx->netdev->name, + (unsigned int)(rx_speed / 1000000U), + (unsigned int)(tx_speed / 1000000U)); + } else { + printk(KERN_INFO KBUILD_MODNAME + ": %s: %u kbit/s downlink " + "%u kbit/s uplink\n", + ctx->netdev->name, + (unsigned int)(rx_speed / 1000U), + (unsigned int)(tx_speed / 1000U)); + } + } +} + +static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) +{ + struct cdc_ncm_ctx *ctx; + struct usb_cdc_notification *event; + + ctx = (struct cdc_ncm_ctx *)dev->data[0]; + + if (urb->actual_length < sizeof(*event)) + return; + + /* test for split data in 8-byte chunks */ + if (test_and_clear_bit(EVENT_STS_SPLIT, &dev->flags)) { + cdc_ncm_speed_change(ctx, + (struct connection_speed_change *)urb->transfer_buffer); + return; + } + + event = urb->transfer_buffer; + + switch (event->bNotificationType) { + case USB_CDC_NOTIFY_NETWORK_CONNECTION: + /* + * According to the CDC NCM specification ch.7.1 + * USB_CDC_NOTIFY_NETWORK_CONNECTION notification shall be + * sent by device after USB_CDC_NOTIFY_SPEED_CHANGE. + */ + ctx->connected = event->wValue; + + printk(KERN_INFO KBUILD_MODNAME ": %s: network connection:" + " %sconnected\n", + ctx->netdev->name, ctx->connected ? "" : "dis"); + + if (ctx->connected) + netif_carrier_on(dev->net); + else { + netif_carrier_off(dev->net); + ctx->tx_speed = ctx->rx_speed = 0; + } + break; + + case USB_CDC_NOTIFY_SPEED_CHANGE: + if (urb->actual_length < + (sizeof(*event) + sizeof(struct connection_speed_change))) + set_bit(EVENT_STS_SPLIT, &dev->flags); + else + cdc_ncm_speed_change(ctx, + (struct connection_speed_change *) &event[1]); + break; + + default: + dev_err(&dev->udev->dev, "NCM: unexpected " + "notification 0x%02x!\n", event->bNotificationType); + break; + } +} + +static int cdc_ncm_check_connect(struct usbnet *dev) +{ + struct cdc_ncm_ctx *ctx; + + ctx = (struct cdc_ncm_ctx *)dev->data[0]; + if (ctx == NULL) + return 1; /* disconnected */ + + return !ctx->connected; +} + +static int +cdc_ncm_probe(struct usb_interface *udev, const struct usb_device_id *prod) +{ + return usbnet_probe(udev, prod); +} + +static void cdc_ncm_disconnect(struct usb_interface *intf) +{ + struct usbnet *dev = usb_get_intfdata(intf); + + if (dev == NULL) + return; /* already disconnected */ + + usbnet_disconnect(intf); +} + +static int cdc_ncm_manage_power(struct usbnet *dev, int status) +{ + dev->intf->needs_remote_wakeup = status; + return 0; +} + +static const struct driver_info cdc_ncm_info = { + .description = "CDC NCM", + .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET, + .bind = cdc_ncm_bind, + .unbind = cdc_ncm_unbind, + .check_connect = cdc_ncm_check_connect, + .manage_power = cdc_ncm_manage_power, + .status = cdc_ncm_status, + .rx_fixup = cdc_ncm_rx_fixup, + .tx_fixup = cdc_ncm_tx_fixup, +}; + +static struct usb_driver cdc_ncm_driver = { + .name = "cdc_ncm", + .id_table = cdc_devs, + .probe = cdc_ncm_probe, + .disconnect = cdc_ncm_disconnect, + .suspend = usbnet_suspend, + .resume = usbnet_resume, + .supports_autosuspend = 1, +}; + +static struct ethtool_ops cdc_ncm_ethtool_ops = { + .get_drvinfo = cdc_ncm_get_drvinfo, + .get_link = usbnet_get_link, + .get_msglevel = usbnet_get_msglevel, + .set_msglevel = usbnet_set_msglevel, + .get_settings = usbnet_get_settings, + .set_settings = usbnet_set_settings, + .nway_reset = usbnet_nway_reset, +}; + +static int __init cdc_ncm_init(void) +{ + printk(KERN_INFO KBUILD_MODNAME ": " DRIVER_VERSION "\n"); + return usb_register(&cdc_ncm_driver); +} + +module_init(cdc_ncm_init); + +static void __exit cdc_ncm_exit(void) +{ + usb_deregister(&cdc_ncm_driver); +} + +module_exit(cdc_ncm_exit); + +MODULE_AUTHOR("Hans Petter Selasky"); +MODULE_DESCRIPTION("USB CDC NCM host driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index be8cc2a8e21..93c6b5f62ac 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2993,12 +2993,14 @@ static int hso_probe(struct usb_interface *interface, case HSO_INTF_BULK: /* It's a regular bulk interface */ - if (((port_spec & HSO_PORT_MASK) == HSO_PORT_NETWORK) && - !disable_net) - hso_dev = hso_create_net_device(interface, port_spec); - else + if ((port_spec & HSO_PORT_MASK) == HSO_PORT_NETWORK) { + if (!disable_net) + hso_dev = + hso_create_net_device(interface, port_spec); + } else { hso_dev = hso_create_bulk_serial_device(interface, port_spec); + } if (!hso_dev) goto exit; break; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index c04d49e31f8..cff74b81a7d 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -391,14 +391,19 @@ static inline void rx_process (struct usbnet *dev, struct sk_buff *skb) goto error; // else network stack removes extra byte if we forced a short packet - if (skb->len) - usbnet_skb_return (dev, skb); - else { - netif_dbg(dev, rx_err, dev->net, "drop\n"); -error: - dev->net->stats.rx_errors++; - skb_queue_tail (&dev->done, skb); + if (skb->len) { + /* all data was already cloned from skb inside the driver */ + if (dev->driver_info->flags & FLAG_MULTI_PACKET) + dev_kfree_skb_any(skb); + else + usbnet_skb_return(dev, skb); + return; } + + netif_dbg(dev, rx_err, dev->net, "drop\n"); +error: + dev->net->stats.rx_errors++; + skb_queue_tail(&dev->done, skb); } /*-------------------------------------------------------------------------*/ @@ -971,7 +976,8 @@ static void tx_complete (struct urb *urb) struct usbnet *dev = entry->dev; if (urb->status == 0) { - dev->net->stats.tx_packets++; + if (!(dev->driver_info->flags & FLAG_MULTI_PACKET)) + dev->net->stats.tx_packets++; dev->net->stats.tx_bytes += entry->length; } else { dev->net->stats.tx_errors++; @@ -1044,8 +1050,13 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, if (info->tx_fixup) { skb = info->tx_fixup (dev, skb, GFP_ATOMIC); if (!skb) { - netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); - goto drop; + if (netif_msg_tx_err(dev)) { + netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); + goto drop; + } else { + /* cdc_ncm collected packet; waits for more */ + goto not_drop; + } } } length = skb->len; @@ -1067,13 +1078,18 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, /* don't assume the hardware handles USB_ZERO_PACKET * NOTE: strictly conforming cdc-ether devices should expect * the ZLP here, but ignore the one-byte packet. + * NOTE2: CDC NCM specification is different from CDC ECM when + * handling ZLP/short packets, so cdc_ncm driver will make short + * packet itself if needed. */ if (length % dev->maxpacket == 0) { if (!(info->flags & FLAG_SEND_ZLP)) { - urb->transfer_buffer_length++; - if (skb_tailroom(skb)) { - skb->data[skb->len] = 0; - __skb_put(skb, 1); + if (!(info->flags & FLAG_MULTI_PACKET)) { + urb->transfer_buffer_length++; + if (skb_tailroom(skb)) { + skb->data[skb->len] = 0; + __skb_put(skb, 1); + } } } else urb->transfer_flags |= URB_ZERO_PACKET; @@ -1122,6 +1138,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, netif_dbg(dev, tx_err, dev->net, "drop, code %d\n", retval); drop: dev->net->stats.tx_dropped++; +not_drop: if (skb) dev_kfree_skb_any (skb); usb_free_urb (urb); diff --git a/drivers/net/via-rhine.c b/drivers/net/via-rhine.c index 4930f9dbc49..5e7f069eab5 100644 --- a/drivers/net/via-rhine.c +++ b/drivers/net/via-rhine.c @@ -30,8 +30,8 @@ */ #define DRV_NAME "via-rhine" -#define DRV_VERSION "1.4.3" -#define DRV_RELDATE "2007-03-06" +#define DRV_VERSION "1.5.0" +#define DRV_RELDATE "2010-10-09" /* A few user-configurable values. @@ -100,6 +100,7 @@ static const int multicast_filter_limit = 32; #include #include #include +#include #include #include #include /* Processor type for cache alignment. */ @@ -133,6 +134,9 @@ MODULE_PARM_DESC(debug, "VIA Rhine debug level (0-7)"); MODULE_PARM_DESC(rx_copybreak, "VIA Rhine copy breakpoint for copy-only-tiny-frames"); MODULE_PARM_DESC(avoid_D3, "Avoid power state D3 (work-around for broken BIOSes)"); +#define MCAM_SIZE 32 +#define VCAM_SIZE 32 + /* Theory of Operation @@ -279,15 +283,16 @@ MODULE_DEVICE_TABLE(pci, rhine_pci_tbl); /* Offsets to the device registers. */ enum register_offsets { StationAddr=0x00, RxConfig=0x06, TxConfig=0x07, ChipCmd=0x08, - ChipCmd1=0x09, + ChipCmd1=0x09, TQWake=0x0A, IntrStatus=0x0C, IntrEnable=0x0E, MulticastFilter0=0x10, MulticastFilter1=0x14, RxRingPtr=0x18, TxRingPtr=0x1C, GFIFOTest=0x54, - MIIPhyAddr=0x6C, MIIStatus=0x6D, PCIBusConfig=0x6E, + MIIPhyAddr=0x6C, MIIStatus=0x6D, PCIBusConfig=0x6E, PCIBusConfig1=0x6F, MIICmd=0x70, MIIRegAddr=0x71, MIIData=0x72, MACRegEEcsr=0x74, ConfigA=0x78, ConfigB=0x79, ConfigC=0x7A, ConfigD=0x7B, RxMissed=0x7C, RxCRCErrs=0x7E, MiscCmd=0x81, StickyHW=0x83, IntrStatus2=0x84, + CamMask=0x88, CamCon=0x92, CamAddr=0x93, WOLcrSet=0xA0, PwcfgSet=0xA1, WOLcgSet=0xA3, WOLcrClr=0xA4, WOLcrClr1=0xA6, WOLcgClr=0xA7, PwrcsrSet=0xA8, PwrcsrSet1=0xA9, PwrcsrClr=0xAC, PwrcsrClr1=0xAD, @@ -299,6 +304,40 @@ enum backoff_bits { BackCaptureEffect=0x04, BackRandom=0x08 }; +/* Bits in the TxConfig (TCR) register */ +enum tcr_bits { + TCR_PQEN=0x01, + TCR_LB0=0x02, /* loopback[0] */ + TCR_LB1=0x04, /* loopback[1] */ + TCR_OFSET=0x08, + TCR_RTGOPT=0x10, + TCR_RTFT0=0x20, + TCR_RTFT1=0x40, + TCR_RTSF=0x80, +}; + +/* Bits in the CamCon (CAMC) register */ +enum camcon_bits { + CAMC_CAMEN=0x01, + CAMC_VCAMSL=0x02, + CAMC_CAMWR=0x04, + CAMC_CAMRD=0x08, +}; + +/* Bits in the PCIBusConfig1 (BCR1) register */ +enum bcr1_bits { + BCR1_POT0=0x01, + BCR1_POT1=0x02, + BCR1_POT2=0x04, + BCR1_CTFT0=0x08, + BCR1_CTFT1=0x10, + BCR1_CTSF=0x20, + BCR1_TXQNOBK=0x40, /* for VT6105 */ + BCR1_VIDFR=0x80, /* for VT6105 */ + BCR1_MED0=0x40, /* for VT6102 */ + BCR1_MED1=0x80, /* for VT6102 */ +}; + #ifdef USE_MMIO /* Registers we check that mmio and reg are the same. */ static const int mmio_verify_registers[] = { @@ -356,6 +395,11 @@ enum desc_status_bits { DescOwn=0x80000000 }; +/* Bits in *_desc.*_length */ +enum desc_length_bits { + DescTag=0x00010000 +}; + /* Bits in ChipCmd. */ enum chip_cmd_bits { CmdInit=0x01, CmdStart=0x02, CmdStop=0x04, CmdRxOn=0x08, @@ -365,6 +409,9 @@ enum chip_cmd_bits { }; struct rhine_private { + /* Bit mask for configured VLAN ids */ + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + /* Descriptor rings */ struct rx_desc *rx_ring; struct tx_desc *tx_ring; @@ -405,6 +452,23 @@ struct rhine_private { void __iomem *base; }; +#define BYTE_REG_BITS_ON(x, p) do { iowrite8((ioread8((p))|(x)), (p)); } while (0) +#define WORD_REG_BITS_ON(x, p) do { iowrite16((ioread16((p))|(x)), (p)); } while (0) +#define DWORD_REG_BITS_ON(x, p) do { iowrite32((ioread32((p))|(x)), (p)); } while (0) + +#define BYTE_REG_BITS_IS_ON(x, p) (ioread8((p)) & (x)) +#define WORD_REG_BITS_IS_ON(x, p) (ioread16((p)) & (x)) +#define DWORD_REG_BITS_IS_ON(x, p) (ioread32((p)) & (x)) + +#define BYTE_REG_BITS_OFF(x, p) do { iowrite8(ioread8((p)) & (~(x)), (p)); } while (0) +#define WORD_REG_BITS_OFF(x, p) do { iowrite16(ioread16((p)) & (~(x)), (p)); } while (0) +#define DWORD_REG_BITS_OFF(x, p) do { iowrite32(ioread32((p)) & (~(x)), (p)); } while (0) + +#define BYTE_REG_BITS_SET(x, m, p) do { iowrite8((ioread8((p)) & (~(m)))|(x), (p)); } while (0) +#define WORD_REG_BITS_SET(x, m, p) do { iowrite16((ioread16((p)) & (~(m)))|(x), (p)); } while (0) +#define DWORD_REG_BITS_SET(x, m, p) do { iowrite32((ioread32((p)) & (~(m)))|(x), (p)); } while (0) + + static int mdio_read(struct net_device *dev, int phy_id, int location); static void mdio_write(struct net_device *dev, int phy_id, int location, int value); static int rhine_open(struct net_device *dev); @@ -422,6 +486,14 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); static const struct ethtool_ops netdev_ethtool_ops; static int rhine_close(struct net_device *dev); static void rhine_shutdown (struct pci_dev *pdev); +static void rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid); +static void rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid); +static void rhine_set_cam(void __iomem *ioaddr, int idx, u8 *addr); +static void rhine_set_vlan_cam(void __iomem *ioaddr, int idx, u8 *addr); +static void rhine_set_cam_mask(void __iomem *ioaddr, u32 mask); +static void rhine_set_vlan_cam_mask(void __iomem *ioaddr, u32 mask); +static void rhine_init_cam_filter(struct net_device *dev); +static void rhine_update_vcam(struct net_device *dev); #define RHINE_WAIT_FOR(condition) do { \ int i=1024; \ @@ -629,6 +701,8 @@ static const struct net_device_ops rhine_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_do_ioctl = netdev_ioctl, .ndo_tx_timeout = rhine_tx_timeout, + .ndo_vlan_rx_add_vid = rhine_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = rhine_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = rhine_poll, #endif @@ -795,6 +869,10 @@ static int __devinit rhine_init_one(struct pci_dev *pdev, if (rp->quirks & rqRhineI) dev->features |= NETIF_F_SG|NETIF_F_HW_CSUM; + if (pdev->revision >= VT6105M) + dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX | + NETIF_F_HW_VLAN_FILTER; + /* dev->name not defined before register_netdev()! */ rc = register_netdev(dev); if (rc) @@ -1040,6 +1118,167 @@ static void rhine_set_carrier(struct mii_if_info *mii) netif_carrier_ok(mii->dev)); } +/** + * rhine_set_cam - set CAM multicast filters + * @ioaddr: register block of this Rhine + * @idx: multicast CAM index [0..MCAM_SIZE-1] + * @addr: multicast address (6 bytes) + * + * Load addresses into multicast filters. + */ +static void rhine_set_cam(void __iomem *ioaddr, int idx, u8 *addr) +{ + int i; + + iowrite8(CAMC_CAMEN, ioaddr + CamCon); + wmb(); + + /* Paranoid -- idx out of range should never happen */ + idx &= (MCAM_SIZE - 1); + + iowrite8((u8) idx, ioaddr + CamAddr); + + for (i = 0; i < 6; i++, addr++) + iowrite8(*addr, ioaddr + MulticastFilter0 + i); + udelay(10); + wmb(); + + iowrite8(CAMC_CAMWR | CAMC_CAMEN, ioaddr + CamCon); + udelay(10); + + iowrite8(0, ioaddr + CamCon); +} + +/** + * rhine_set_vlan_cam - set CAM VLAN filters + * @ioaddr: register block of this Rhine + * @idx: VLAN CAM index [0..VCAM_SIZE-1] + * @addr: VLAN ID (2 bytes) + * + * Load addresses into VLAN filters. + */ +static void rhine_set_vlan_cam(void __iomem *ioaddr, int idx, u8 *addr) +{ + iowrite8(CAMC_CAMEN | CAMC_VCAMSL, ioaddr + CamCon); + wmb(); + + /* Paranoid -- idx out of range should never happen */ + idx &= (VCAM_SIZE - 1); + + iowrite8((u8) idx, ioaddr + CamAddr); + + iowrite16(*((u16 *) addr), ioaddr + MulticastFilter0 + 6); + udelay(10); + wmb(); + + iowrite8(CAMC_CAMWR | CAMC_CAMEN, ioaddr + CamCon); + udelay(10); + + iowrite8(0, ioaddr + CamCon); +} + +/** + * rhine_set_cam_mask - set multicast CAM mask + * @ioaddr: register block of this Rhine + * @mask: multicast CAM mask + * + * Mask sets multicast filters active/inactive. + */ +static void rhine_set_cam_mask(void __iomem *ioaddr, u32 mask) +{ + iowrite8(CAMC_CAMEN, ioaddr + CamCon); + wmb(); + + /* write mask */ + iowrite32(mask, ioaddr + CamMask); + + /* disable CAMEN */ + iowrite8(0, ioaddr + CamCon); +} + +/** + * rhine_set_vlan_cam_mask - set VLAN CAM mask + * @ioaddr: register block of this Rhine + * @mask: VLAN CAM mask + * + * Mask sets VLAN filters active/inactive. + */ +static void rhine_set_vlan_cam_mask(void __iomem *ioaddr, u32 mask) +{ + iowrite8(CAMC_CAMEN | CAMC_VCAMSL, ioaddr + CamCon); + wmb(); + + /* write mask */ + iowrite32(mask, ioaddr + CamMask); + + /* disable CAMEN */ + iowrite8(0, ioaddr + CamCon); +} + +/** + * rhine_init_cam_filter - initialize CAM filters + * @dev: network device + * + * Initialize (disable) hardware VLAN and multicast support on this + * Rhine. + */ +static void rhine_init_cam_filter(struct net_device *dev) +{ + struct rhine_private *rp = netdev_priv(dev); + void __iomem *ioaddr = rp->base; + + /* Disable all CAMs */ + rhine_set_vlan_cam_mask(ioaddr, 0); + rhine_set_cam_mask(ioaddr, 0); + + /* disable hardware VLAN support */ + BYTE_REG_BITS_ON(TCR_PQEN, ioaddr + TxConfig); + BYTE_REG_BITS_OFF(BCR1_VIDFR, ioaddr + PCIBusConfig1); +} + +/** + * rhine_update_vcam - update VLAN CAM filters + * @rp: rhine_private data of this Rhine + * + * Update VLAN CAM filters to match configuration change. + */ +static void rhine_update_vcam(struct net_device *dev) +{ + struct rhine_private *rp = netdev_priv(dev); + void __iomem *ioaddr = rp->base; + u16 vid; + u32 vCAMmask = 0; /* 32 vCAMs (6105M and better) */ + unsigned int i = 0; + + for_each_set_bit(vid, rp->active_vlans, VLAN_N_VID) { + rhine_set_vlan_cam(ioaddr, i, (u8 *)&vid); + vCAMmask |= 1 << i; + if (++i >= VCAM_SIZE) + break; + } + rhine_set_vlan_cam_mask(ioaddr, vCAMmask); +} + +static void rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid) +{ + struct rhine_private *rp = netdev_priv(dev); + + spin_lock_irq(&rp->lock); + set_bit(vid, rp->active_vlans); + rhine_update_vcam(dev); + spin_unlock_irq(&rp->lock); +} + +static void rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) +{ + struct rhine_private *rp = netdev_priv(dev); + + spin_lock_irq(&rp->lock); + clear_bit(vid, rp->active_vlans); + rhine_update_vcam(dev); + spin_unlock_irq(&rp->lock); +} + static void init_registers(struct net_device *dev) { struct rhine_private *rp = netdev_priv(dev); @@ -1061,6 +1300,9 @@ static void init_registers(struct net_device *dev) rhine_set_rx_mode(dev); + if (rp->pdev->revision >= VT6105M) + rhine_init_cam_filter(dev); + napi_enable(&rp->napi); /* Enable interrupts by setting the interrupt mask. */ @@ -1276,16 +1518,28 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb, rp->tx_ring[entry].desc_length = cpu_to_le32(TXDESC | (skb->len >= ETH_ZLEN ? skb->len : ETH_ZLEN)); + if (unlikely(vlan_tx_tag_present(skb))) { + rp->tx_ring[entry].tx_status = cpu_to_le32((vlan_tx_tag_get(skb)) << 16); + /* request tagging */ + rp->tx_ring[entry].desc_length |= cpu_to_le32(0x020000); + } + else + rp->tx_ring[entry].tx_status = 0; + /* lock eth irq */ spin_lock_irqsave(&rp->lock, flags); wmb(); - rp->tx_ring[entry].tx_status = cpu_to_le32(DescOwn); + rp->tx_ring[entry].tx_status |= cpu_to_le32(DescOwn); wmb(); rp->cur_tx++; /* Non-x86 Todo: explicitly flush cache lines here. */ + if (vlan_tx_tag_present(skb)) + /* Tx queues are bits 7-0 (first Tx queue: bit 7) */ + BYTE_REG_BITS_ON(1 << 7, ioaddr + TQWake); + /* Wake the potentially-idle transmit channel */ iowrite8(ioread8(ioaddr + ChipCmd1) | Cmd1TxDemand, ioaddr + ChipCmd1); @@ -1437,6 +1691,21 @@ static void rhine_tx(struct net_device *dev) spin_unlock(&rp->lock); } +/** + * rhine_get_vlan_tci - extract TCI from Rx data buffer + * @skb: pointer to sk_buff + * @data_size: used data area of the buffer including CRC + * + * If hardware VLAN tag extraction is enabled and the chip indicates a 802.1Q + * packet, the extracted 802.1Q header (2 bytes TPID + 2 bytes TCI) is 4-byte + * aligned following the CRC. + */ +static inline u16 rhine_get_vlan_tci(struct sk_buff *skb, int data_size) +{ + u8 *trailer = (u8 *)skb->data + ((data_size + 3) & ~3) + 2; + return ntohs(*(u16 *)trailer); +} + /* Process up to limit frames from receive ring */ static int rhine_rx(struct net_device *dev, int limit) { @@ -1454,6 +1723,7 @@ static int rhine_rx(struct net_device *dev, int limit) for (count = 0; count < limit; ++count) { struct rx_desc *desc = rp->rx_head_desc; u32 desc_status = le32_to_cpu(desc->rx_status); + u32 desc_length = le32_to_cpu(desc->desc_length); int data_size = desc_status >> 16; if (desc_status & DescOwn) @@ -1498,6 +1768,7 @@ static int rhine_rx(struct net_device *dev, int limit) struct sk_buff *skb = NULL; /* Length should omit the CRC */ int pkt_len = data_size - 4; + u16 vlan_tci = 0; /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ @@ -1532,7 +1803,14 @@ static int rhine_rx(struct net_device *dev, int limit) rp->rx_buf_sz, PCI_DMA_FROMDEVICE); } + + if (unlikely(desc_length & DescTag)) + vlan_tci = rhine_get_vlan_tci(skb, data_size); + skb->protocol = eth_type_trans(skb, dev); + + if (unlikely(desc_length & DescTag)) + __vlan_hwaccel_put_tag(skb, vlan_tci); netif_receive_skb(skb); dev->stats.rx_bytes += pkt_len; dev->stats.rx_packets++; @@ -1596,6 +1874,11 @@ static void rhine_restart_tx(struct net_device *dev) { iowrite8(ioread8(ioaddr + ChipCmd) | CmdTxOn, ioaddr + ChipCmd); + + if (rp->tx_ring[entry].desc_length & cpu_to_le32(0x020000)) + /* Tx queues are bits 7-0 (first Tx queue: bit 7) */ + BYTE_REG_BITS_ON(1 << 7, ioaddr + TQWake); + iowrite8(ioread8(ioaddr + ChipCmd1) | Cmd1TxDemand, ioaddr + ChipCmd1); IOSYNC; @@ -1631,7 +1914,7 @@ static void rhine_error(struct net_device *dev, int intr_status) } if (intr_status & IntrTxUnderrun) { if (rp->tx_thresh < 0xE0) - iowrite8(rp->tx_thresh += 0x20, ioaddr + TxConfig); + BYTE_REG_BITS_SET((rp->tx_thresh += 0x20), 0x80, ioaddr + TxConfig); if (debug > 1) printk(KERN_INFO "%s: Transmitter underrun, Tx " "threshold now %2.2x.\n", @@ -1646,7 +1929,7 @@ static void rhine_error(struct net_device *dev, int intr_status) (intr_status & (IntrTxAborted | IntrTxUnderrun | IntrTxDescRace)) == 0) { if (rp->tx_thresh < 0xE0) { - iowrite8(rp->tx_thresh += 0x20, ioaddr + TxConfig); + BYTE_REG_BITS_SET((rp->tx_thresh += 0x20), 0x80, ioaddr + TxConfig); } if (debug > 1) printk(KERN_INFO "%s: Unspecified error. Tx " @@ -1688,7 +1971,8 @@ static void rhine_set_rx_mode(struct net_device *dev) struct rhine_private *rp = netdev_priv(dev); void __iomem *ioaddr = rp->base; u32 mc_filter[2]; /* Multicast hash filter */ - u8 rx_mode; /* Note: 0x02=accept runt, 0x01=accept errs */ + u8 rx_mode = 0x0C; /* Note: 0x02=accept runt, 0x01=accept errs */ + struct netdev_hw_addr *ha; if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ rx_mode = 0x1C; @@ -1699,10 +1983,18 @@ static void rhine_set_rx_mode(struct net_device *dev) /* Too many to match, or accept all multicasts. */ iowrite32(0xffffffff, ioaddr + MulticastFilter0); iowrite32(0xffffffff, ioaddr + MulticastFilter1); - rx_mode = 0x0C; + } else if (rp->pdev->revision >= VT6105M) { + int i = 0; + u32 mCAMmask = 0; /* 32 mCAMs (6105M and better) */ + netdev_for_each_mc_addr(ha, dev) { + if (i == MCAM_SIZE) + break; + rhine_set_cam(ioaddr, i, ha->addr); + mCAMmask |= 1 << i; + i++; + } + rhine_set_cam_mask(ioaddr, mCAMmask); } else { - struct netdev_hw_addr *ha; - memset(mc_filter, 0, sizeof(mc_filter)); netdev_for_each_mc_addr(ha, dev) { int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; @@ -1711,9 +2003,15 @@ static void rhine_set_rx_mode(struct net_device *dev) } iowrite32(mc_filter[0], ioaddr + MulticastFilter0); iowrite32(mc_filter[1], ioaddr + MulticastFilter1); - rx_mode = 0x0C; } - iowrite8(rp->rx_thresh | rx_mode, ioaddr + RxConfig); + /* enable/disable VLAN receive filtering */ + if (rp->pdev->revision >= VT6105M) { + if (dev->flags & IFF_PROMISC) + BYTE_REG_BITS_OFF(BCR1_VIDFR, ioaddr + PCIBusConfig1); + else + BYTE_REG_BITS_ON(BCR1_VIDFR, ioaddr + PCIBusConfig1); + } + BYTE_REG_BITS_ON(rx_mode, ioaddr + RxConfig); } static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) @@ -1966,7 +2264,7 @@ static int rhine_resume(struct pci_dev *pdev) if (!netif_running(dev)) return 0; - if (request_irq(dev->irq, rhine_interrupt, IRQF_SHARED, dev->name, dev)) + if (request_irq(dev->irq, rhine_interrupt, IRQF_SHARED, dev->name, dev)) printk(KERN_ERR "via-rhine %s: request_irq failed\n", dev->name); ret = pci_set_power_state(pdev, PCI_D0); diff --git a/drivers/net/vxge/vxge-ethtool.c b/drivers/net/vxge/vxge-ethtool.c index bc9bd103570..1dd3a21b3a4 100644 --- a/drivers/net/vxge/vxge-ethtool.c +++ b/drivers/net/vxge/vxge-ethtool.c @@ -1177,7 +1177,7 @@ static const struct ethtool_ops vxge_ethtool_ops = { .get_rx_csum = vxge_get_rx_csum, .set_rx_csum = vxge_set_rx_csum, .get_tx_csum = ethtool_op_get_tx_csum, - .set_tx_csum = ethtool_op_set_tx_hw_csum, + .set_tx_csum = ethtool_op_set_tx_ipv6_csum, .get_sg = ethtool_op_get_sg, .set_sg = ethtool_op_set_sg, .get_tso = ethtool_op_get_tso, diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index 8a84152e320..4877b3b8a29 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -3368,7 +3368,7 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, ndev->features |= NETIF_F_SG; - ndev->features |= NETIF_F_HW_CSUM; + ndev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; vxge_debug_init(vxge_hw_device_trace_level_get(hldev), "%s : checksuming enabled", __func__); diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index d81ad839788..cf05504d951 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -498,7 +498,6 @@ norbuff: static int x25_asy_close(struct net_device *dev) { struct x25_asy *sl = netdev_priv(dev); - int err; spin_lock(&sl->lock); if (sl->tty) @@ -507,10 +506,6 @@ static int x25_asy_close(struct net_device *dev) netif_stop_queue(dev); sl->rcount = 0; sl->xleft = 0; - err = lapb_unregister(dev); - if (err != LAPB_OK) - printk(KERN_ERR "x25_asy_close: lapb_unregister error -%d\n", - err); spin_unlock(&sl->lock); return 0; } @@ -595,6 +590,7 @@ static int x25_asy_open_tty(struct tty_struct *tty) static void x25_asy_close_tty(struct tty_struct *tty) { struct x25_asy *sl = tty->disc_data; + int err; /* First make sure we're connected. */ if (!sl || sl->magic != X25_ASY_MAGIC) @@ -605,6 +601,11 @@ static void x25_asy_close_tty(struct tty_struct *tty) dev_close(sl->dev); rtnl_unlock(); + err = lapb_unregister(sl->dev); + if (err != LAPB_OK) + printk(KERN_ERR "x25_asy_close: lapb_unregister error -%d\n", + err); + tty->disc_data = NULL; sl->tty = NULL; x25_asy_free(sl); diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index 872b1a3b21c..73a8014cacb 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -62,6 +62,7 @@ static int ar9003_hw_power_interpolate(int32_t x, int32_t *px, int32_t *py, u_int16_t np); + static const struct ar9300_eeprom ar9300_default = { .eepromVersion = 2, .templateVersion = 2, diff --git a/drivers/net/xilinx_emaclite.c b/drivers/net/xilinx_emaclite.c index 2de52d18152..de6c3086d23 100644 --- a/drivers/net/xilinx_emaclite.c +++ b/drivers/net/xilinx_emaclite.c @@ -1000,21 +1000,6 @@ static int xemaclite_close(struct net_device *dev) return 0; } -/** - * xemaclite_get_stats - Get the stats for the net_device - * @dev: Pointer to the network device - * - * This function returns the address of the 'net_device_stats' structure for the - * given network device. This structure holds usage statistics for the network - * device. - * - * Return: Pointer to the net_device_stats structure. - */ -static struct net_device_stats *xemaclite_get_stats(struct net_device *dev) -{ - return &dev->stats; -} - /** * xemaclite_send - Transmit a frame * @orig_skb: Pointer to the socket buffer to be transmitted @@ -1285,7 +1270,6 @@ static struct net_device_ops xemaclite_netdev_ops = { .ndo_start_xmit = xemaclite_send, .ndo_set_mac_address = xemaclite_set_mac_address, .ndo_tx_timeout = xemaclite_tx_timeout, - .ndo_get_stats = xemaclite_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = xemaclite_poll_controller, #endif diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 4b4da5b86ff..f442668a1e5 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -129,8 +129,9 @@ static void handle_tx(struct vhost_net *net) size_t hdr_size; struct socket *sock; - sock = rcu_dereference_check(vq->private_data, - lockdep_is_held(&vq->mutex)); + /* TODO: check that we are running from vhost_worker? + * Not sure it's worth it, it's straight-forward enough. */ + sock = rcu_dereference_check(vq->private_data, 1); if (!sock) return; diff --git a/include/linux/dccp.h b/include/linux/dccp.h index eed52bcd35d..010e2d87ed7 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -197,6 +197,21 @@ enum dccp_feature_numbers { DCCPF_MAX_CCID_SPECIFIC = 255, }; +/* DCCP socket control message types for cmsg */ +enum dccp_cmsg_type { + DCCP_SCM_PRIORITY = 1, + DCCP_SCM_QPOLICY_MAX = 0xFFFF, + /* ^-- Up to here reserved exclusively for qpolicy parameters */ + DCCP_SCM_MAX +}; + +/* DCCP priorities for outgoing/queued packets */ +enum dccp_packet_dequeueing_policy { + DCCPQ_POLICY_SIMPLE, + DCCPQ_POLICY_PRIO, + DCCPQ_POLICY_MAX +}; + /* DCCP socket options */ #define DCCP_SOCKOPT_PACKET_SIZE 1 /* XXX deprecated, without effect */ #define DCCP_SOCKOPT_SERVICE 2 @@ -210,6 +225,8 @@ enum dccp_feature_numbers { #define DCCP_SOCKOPT_CCID 13 #define DCCP_SOCKOPT_TX_CCID 14 #define DCCP_SOCKOPT_RX_CCID 15 +#define DCCP_SOCKOPT_QPOLICY_ID 16 +#define DCCP_SOCKOPT_QPOLICY_TXQLEN 17 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 @@ -458,6 +475,8 @@ struct dccp_ackvec; * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection) * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection) * @dccps_options_received - parsed set of retrieved options + * @dccps_qpolicy - TX dequeueing policy, one of %dccp_packet_dequeueing_policy + * @dccps_tx_qlen - maximum length of the TX queue * @dccps_role - role of this sock, one of %dccp_role * @dccps_hc_rx_insert_options - receiver wants to add options when acking * @dccps_hc_tx_insert_options - sender wants to add options when sending @@ -500,6 +519,8 @@ struct dccp_sock { struct ccid *dccps_hc_rx_ccid; struct ccid *dccps_hc_tx_ccid; struct dccp_options_received dccps_options_received; + __u8 dccps_qpolicy; + __u32 dccps_tx_qlen; enum dccp_role dccps_role:2; __u8 dccps_hc_rx_insert_options:1; __u8 dccps_hc_tx_insert_options:1; diff --git a/include/linux/filter.h b/include/linux/filter.h index 447a775878f..45266b75409 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -124,7 +124,9 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define SKF_AD_MARK 20 #define SKF_AD_QUEUE 24 #define SKF_AD_HATYPE 28 -#define SKF_AD_MAX 32 +#define SKF_AD_RXHASH 32 +#define SKF_AD_CPU 36 +#define SKF_AD_MAX 40 #define SKF_NET_OFF (-0x100000) #define SKF_LL_OFF (-0x200000) @@ -146,7 +148,7 @@ struct sk_buff; struct sock; extern int sk_filter(struct sock *sk, struct sk_buff *skb); -extern unsigned int sk_run_filter(struct sk_buff *skb, +extern unsigned int sk_run_filter(const struct sk_buff *skb, const struct sock_filter *filter); extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); extern int sk_detach_filter(struct sock *sk); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 2b86eaf1177..ae8fdc54e0c 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -222,7 +222,7 @@ static inline struct in_device *in_dev_get(const struct net_device *dev) static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { - return rcu_dereference_check(dev->ip_ptr, lockdep_rtnl_is_held()); + return rtnl_dereference(dev->ip_ptr); } extern void in_dev_finish_destroy(struct in_device *idev); diff --git a/include/linux/jhash.h b/include/linux/jhash.h index ced1159fa4f..47cb09edec1 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -3,129 +3,156 @@ /* jhash.h: Jenkins hash support. * - * Copyright (C) 1996 Bob Jenkins (bob_jenkins@burtleburtle.net) + * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * http://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * - * lookup2.c, by Bob Jenkins, December 1996, Public Domain. - * hash(), hash2(), hash3, and mix() are externally useful functions. - * Routines to test the hash are included if SELF_TEST is defined. - * You can use this free for any purpose. It has no warranty. + * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * - * Copyright (C) 2003 David S. Miller (davem@redhat.com) + * These are functions for producing 32-bit hashes for hash table lookup. + * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() + * are externally useful functions. Routines to test the hash are included + * if SELF_TEST is defined. You can use this free for any purpose. It's in + * the public domain. It has no warranty. + * + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) * * I've modified Bob's hash to be useful in the Linux kernel, and - * any bugs present are surely my fault. -DaveM + * any bugs present are my fault. + * Jozsef */ +#include +#include + +/* Best hash sizes are of power of two */ +#define jhash_size(n) ((u32)1<<(n)) +/* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ +#define jhash_mask(n) (jhash_size(n)-1) + +/* __jhash_mix -- mix 3 32-bit values reversibly. */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} -/* NOTE: Arguments are modified. */ -#define __jhash_mix(a, b, c) \ -{ \ - a -= b; a -= c; a ^= (c>>13); \ - b -= c; b -= a; b ^= (a<<8); \ - c -= a; c -= b; c ^= (b>>13); \ - a -= b; a -= c; a ^= (c>>12); \ - b -= c; b -= a; b ^= (a<<16); \ - c -= a; c -= b; c ^= (b>>5); \ - a -= b; a -= c; a ^= (c>>3); \ - b -= c; b -= a; b ^= (a<<10); \ - c -= a; c -= b; c ^= (b>>15); \ +/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ } -/* The golden ration: an arbitrary value */ -#define JHASH_GOLDEN_RATIO 0x9e3779b9 +/* An arbitrary initial parameter */ +#define JHASH_INITVAL 0xdeadbeef -/* The most generic version, hashes an arbitrary sequence - * of bytes. No alignment or length assumptions are made about - * the input key. +/* jhash - hash an arbitrary key + * @k: sequence of bytes as key + * @length: the length of the key + * @initval: the previous hash, or an arbitray value + * + * The generic version, hashes an arbitrary sequence of bytes. + * No alignment or length assumptions are made about the input key. + * + * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { - u32 a, b, c, len; + u32 a, b, c; const u8 *k = key; - len = length; - a = b = JHASH_GOLDEN_RATIO; - c = initval; - - while (len >= 12) { - a += (k[0] +((u32)k[1]<<8) +((u32)k[2]<<16) +((u32)k[3]<<24)); - b += (k[4] +((u32)k[5]<<8) +((u32)k[6]<<16) +((u32)k[7]<<24)); - c += (k[8] +((u32)k[9]<<8) +((u32)k[10]<<16)+((u32)k[11]<<24)); - - __jhash_mix(a,b,c); + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + length + initval; + /* All but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) { + a += __get_unaligned_cpu32(k); + b += __get_unaligned_cpu32(k + 4); + c += __get_unaligned_cpu32(k + 8); + __jhash_mix(a, b, c); + length -= 12; k += 12; - len -= 12; } - - c += length; - switch (len) { - case 11: c += ((u32)k[10]<<24); - case 10: c += ((u32)k[9]<<16); - case 9 : c += ((u32)k[8]<<8); - case 8 : b += ((u32)k[7]<<24); - case 7 : b += ((u32)k[6]<<16); - case 6 : b += ((u32)k[5]<<8); - case 5 : b += k[4]; - case 4 : a += ((u32)k[3]<<24); - case 3 : a += ((u32)k[2]<<16); - case 2 : a += ((u32)k[1]<<8); - case 1 : a += k[0]; - }; - - __jhash_mix(a,b,c); + /* Last block: affect all 32 bits of (c) */ + /* All the case statements fall through */ + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } return c; } -/* A special optimized version that handles 1 or more of u32s. - * The length parameter here is the number of u32s in the key. +/* jhash2 - hash an array of u32's + * @k: the key which must be an array of u32's + * @length: the number of u32's in the key + * @initval: the previous hash, or an arbitray value + * + * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { - u32 a, b, c, len; + u32 a, b, c; - a = b = JHASH_GOLDEN_RATIO; - c = initval; - len = length; + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; - while (len >= 3) { + /* Handle most of the key */ + while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); - k += 3; len -= 3; + length -= 3; + k += 3; } - c += length * 4; - - switch (len) { - case 2 : b += k[1]; - case 1 : a += k[0]; - }; - - __jhash_mix(a,b,c); + /* Handle the last 3 u32's: all the case statements fall through */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } return c; } -/* A special ultra-optimized versions that knows they are hashing exactly - * 3, 2 or 1 word(s). - * - * NOTE: In particular the "c += length; __jhash_mix(a,b,c);" normally - * done at the end is not done here. - */ +/* jhash_3words - hash exactly 3, 2 or 1 word(s) */ static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; + a += JHASH_INITVAL; + b += JHASH_INITVAL; c += initval; - __jhash_mix(a, b, c); + __jhash_final(a, b, c); return c; } diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 1ff81b51b65..dd3c34ebca9 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -11,6 +11,7 @@ #define MARVELL_PHY_ID_88E1118 0x01410e10 #define MARVELL_PHY_ID_88E1121R 0x01410cb0 #define MARVELL_PHY_ID_88E1145 0x01410cd0 +#define MARVELL_PHY_ID_88E1149R 0x01410e50 #define MARVELL_PHY_ID_88E1240 0x01410e30 #define MARVELL_PHY_ID_88E1318S 0x01410e90 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a9ac5dc26e3..d31bc3c9471 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1360,7 +1360,8 @@ static inline struct net_device *first_net_device(struct net *net) extern int netdev_boot_setup_check(struct net_device *dev); extern unsigned long netdev_boot_base(const char *prefix, int unit); -extern struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *hwaddr); +extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *hwaddr); extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type); extern void dev_add_pack(struct packet_type *pt); diff --git a/include/linux/snmp.h b/include/linux/snmp.h index ebb0c80ffd6..12b2b18e50c 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -230,6 +230,7 @@ enum LINUX_MIB_TCPMINTTLDROP, /* RFC 5082 */ LINUX_MIB_TCPDEFERACCEPTDROP, LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */ + LINUX_MIB_TCPTIMEWAITOVERFLOW, /* TCPTimeWaitOverflow */ __LINUX_MIB_MAX }; diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 7ae27a47381..44842c8d38c 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -97,6 +97,12 @@ struct driver_info { #define FLAG_LINK_INTR 0x0800 /* updates link (carrier) status */ +/* + * Indicates to usbnet, that USB driver accumulates multiple IP packets. + * Affects statistic (counters) and short packet handling. + */ +#define FLAG_MULTI_PACKET 0x1000 + /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 90c9e2872f2..18e5c3f6758 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -10,6 +10,7 @@ extern void unix_inflight(struct file *fp); extern void unix_notinflight(struct file *fp); extern void unix_gc(void); extern void wait_for_unix_gc(void); +extern struct sock *unix_get_socket(struct file *filp); #define UNIX_HASH_SIZE 256 @@ -56,6 +57,7 @@ struct unix_sock { spinlock_t lock; unsigned int gc_candidate : 1; unsigned int gc_maybe_cycle : 1; + unsigned char recursion_level; struct socket_wq peer_wq; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) diff --git a/include/net/dst.h b/include/net/dst.h index a5bd72646d6..85dee3a57b9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -70,7 +70,7 @@ struct dst_entry { struct dst_ops *ops; - u32 metrics[RTAX_MAX]; + u32 _metrics[RTAX_MAX]; #ifdef CONFIG_NET_CLS_ROUTE __u32 tclassid; @@ -106,7 +106,27 @@ struct dst_entry { static inline u32 dst_metric(const struct dst_entry *dst, int metric) { - return dst->metrics[metric-1]; + return dst->_metrics[metric-1]; +} + +static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) +{ + dst->_metrics[metric-1] = val; +} + +static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics) +{ + memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32)); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + dst_import_metrics(dest, src->_metrics); +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return dst->_metrics; } static inline u32 @@ -134,7 +154,7 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr static inline void set_dst_metric_rtt(struct dst_entry *dst, int metric, unsigned long rtt) { - dst->metrics[metric-1] = jiffies_to_msecs(rtt); + dst_metric_set(dst, metric, jiffies_to_msecs(rtt)); } static inline u32 diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8945f9fb192..8181498fa96 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -116,8 +116,9 @@ struct inet_sock { struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ - __be32 inet_daddr; - __be32 inet_rcv_saddr; +#define inet_daddr sk.__sk_common.skc_daddr +#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr + __be16 inet_dport; __u16 inet_num; __be32 inet_saddr; diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index a066fdd50da..17404b5388a 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -88,12 +88,6 @@ extern void inet_twdr_hangman(unsigned long data); extern void inet_twdr_twkill_work(struct work_struct *work); extern void inet_twdr_twcal_tick(unsigned long data); -#if (BITS_PER_LONG == 64) -#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 8 -#else -#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 4 -#endif - struct inet_bind_bucket; /* @@ -117,15 +111,15 @@ struct inet_timewait_sock { #define tw_hash __tw_common.skc_hash #define tw_prot __tw_common.skc_prot #define tw_net __tw_common.skc_net +#define tw_daddr __tw_common.skc_daddr +#define tw_rcv_saddr __tw_common.skc_rcv_saddr int tw_timeout; volatile unsigned char tw_substate; - /* 3 bits hole, try to pack */ unsigned char tw_rcv_wscale; + /* Socket demultiplex comparisons on incoming packets. */ - /* these five are in inet_sock */ + /* these three are in inet_sock */ __be16 tw_sport; - __be32 tw_daddr __attribute__((aligned(INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES))); - __be32 tw_rcv_saddr; __be16 tw_dport; __u16 tw_num; kmemcheck_bitfield_begin(flags); @@ -191,10 +185,10 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) return (struct inet_timewait_sock *)sk; } -static inline __be32 inet_rcv_saddr(const struct sock *sk) +static inline __be32 sk_rcv_saddr(const struct sock *sk) { - return likely(sk->sk_state != TCP_TIME_WAIT) ? - inet_sk(sk)->inet_rcv_saddr : inet_twsk(sk)->tw_rcv_saddr; +/* both inet_sk() and inet_twsk() store rcv_saddr in skc_rcv_saddr */ + return sk->__sk_common.skc_rcv_saddr; } extern void inet_twsk_put(struct inet_timewait_sock *tw); diff --git a/include/net/sock.h b/include/net/sock.h index 717cfbf649d..82e86034702 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -105,10 +105,8 @@ struct net; /** * struct sock_common - minimal network layer representation of sockets - * @skc_node: main hash linkage for various protocol lookup tables - * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol - * @skc_refcnt: reference count - * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_daddr: Foreign IPv4 addr + * @skc_rcv_saddr: Bound local IPv4 addr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_family: network address family @@ -119,20 +117,20 @@ struct net; * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket + * @skc_node: main hash linkage for various protocol lookup tables + * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol + * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * for struct sock and struct inet_timewait_sock. */ struct sock_common { - /* - * first fields are not copied in sock_copy() + /* skc_daddr and skc_rcv_saddr must be grouped : + * cf INET_MATCH() and INET_TW_MATCH() */ - union { - struct hlist_node skc_node; - struct hlist_nulls_node skc_nulls_node; - }; - atomic_t skc_refcnt; - int skc_tx_queue_mapping; + __be32 skc_daddr; + __be32 skc_rcv_saddr; union { unsigned int skc_hash; @@ -150,6 +148,18 @@ struct sock_common { #ifdef CONFIG_NET_NS struct net *skc_net; #endif + /* + * fields between dontcopy_begin/dontcopy_end + * are not copied in sock_copy() + */ + int skc_dontcopy_begin[0]; + union { + struct hlist_node skc_node; + struct hlist_nulls_node skc_nulls_node; + }; + int skc_tx_queue_mapping; + atomic_t skc_refcnt; + int skc_dontcopy_end[0]; }; /** @@ -232,7 +242,8 @@ struct sock { #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping -#define sk_copy_start __sk_common.skc_hash +#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin +#define sk_dontcopy_end __sk_common.skc_dontcopy_end #define sk_hash __sk_common.skc_hash #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state @@ -1159,6 +1170,8 @@ extern void sk_common_release(struct sock *sk); /* Initialise core socket variables */ extern void sock_init_data(struct socket *sock, struct sock *sk); +extern void sk_filter_release_rcu(struct rcu_head *rcu); + /** * sk_filter_release - release a socket filter * @fp: filter to remove @@ -1169,7 +1182,7 @@ extern void sock_init_data(struct socket *sock, struct sock *sk); static inline void sk_filter_release(struct sk_filter *fp) { if (atomic_dec_and_test(&fp->refcnt)) - kfree(fp); + call_rcu_bh(&fp->rcu, sk_filter_release_rcu); } static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 45c15f49140..798beac7f10 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -27,31 +27,16 @@ #include #include +#include #include #include #include +#include #include #include #include #include "protocol.h" -#ifndef MIN -#define MIN(a, b) (((a) < (b)) ? (a) : (b)) -#endif - -#ifndef MAX -#define MAX(a, b) (((a) > (b)) ? (a) : (b)) -#endif - -#ifndef offset_of -#define offset_of(type, memb) \ - ((unsigned long)(&((type *)0)->memb)) -#endif -#ifndef container_of -#define container_of(obj, type, memb) \ - ((type *)(((char *)obj) - offset_of(type, memb))) -#endif - static int p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...); @@ -104,7 +89,7 @@ EXPORT_SYMBOL(p9stat_free); static size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size) { - size_t len = MIN(pdu->size - pdu->offset, size); + size_t len = min(pdu->size - pdu->offset, size); memcpy(data, &pdu->sdata[pdu->offset], len); pdu->offset += len; return size - len; @@ -112,7 +97,7 @@ static size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size) static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size) { - size_t len = MIN(pdu->capacity - pdu->size, size); + size_t len = min(pdu->capacity - pdu->size, size); memcpy(&pdu->sdata[pdu->size], data, len); pdu->size += len; return size - len; @@ -121,7 +106,7 @@ static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size) static size_t pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size) { - size_t len = MIN(pdu->capacity - pdu->size, size); + size_t len = min(pdu->capacity - pdu->size, size); if (copy_from_user(&pdu->sdata[pdu->size], udata, len)) len = 0; @@ -201,7 +186,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, if (errcode) break; - size = MAX(len, 0); + size = max_t(int16_t, len, 0); *sptr = kmalloc(size + 1, GFP_KERNEL); if (*sptr == NULL) { @@ -256,8 +241,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, p9pdu_readf(pdu, proto_version, "d", count); if (!errcode) { *count = - MIN(*count, - pdu->size - pdu->offset); + min_t(int32_t, *count, + pdu->size - pdu->offset); *data = &pdu->sdata[pdu->offset]; } } @@ -421,7 +406,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, const char *sptr = va_arg(ap, const char *); int16_t len = 0; if (sptr) - len = MIN(strlen(sptr), USHRT_MAX); + len = min_t(int16_t, strlen(sptr), USHRT_MAX); errcode = p9pdu_writef(pdu, proto_version, "w", len); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 17cb0b63357..556443566e9 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -141,7 +141,7 @@ static int br_change_mtu(struct net_device *dev, int new_mtu) #ifdef CONFIG_BRIDGE_NETFILTER /* remember the MTU in the rtable for PMTU */ - br->fake_rtable.dst.metrics[RTAX_MTU - 1] = new_mtu; + dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu); #endif return 0; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 6e139209391..16f5c333596 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -124,7 +124,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) atomic_set(&rt->dst.__refcnt, 1); rt->dst.dev = br->dev; rt->dst.path = &rt->dst; - rt->dst.metrics[RTAX_MTU - 1] = 1500; + dst_metric_set(&rt->dst, RTAX_MTU, 1500); rt->dst.flags = DST_NOXFRM; rt->dst.ops = &fake_dst_ops; } diff --git a/net/ceph/Makefile b/net/ceph/Makefile index 153bdec4083..e87ef435e11 100644 --- a/net/ceph/Makefile +++ b/net/ceph/Makefile @@ -1,9 +1,6 @@ # # Makefile for CEPH filesystem. # - -ifneq ($(KERNELRELEASE),) - obj-$(CONFIG_CEPH_LIB) += libceph.o libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \ @@ -16,22 +13,3 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \ ceph_fs.o ceph_strings.o ceph_hash.o \ pagevec.o -else -#Otherwise we were called directly from the command -# line; invoke the kernel build system. - -KERNELDIR ?= /lib/modules/$(shell uname -r)/build -PWD := $(shell pwd) - -default: all - -all: - $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules - -modules_install: - $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install - -clean: - $(MAKE) -C $(KERNELDIR) M=$(PWD) clean - -endif diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c index 53d8abfa25d..bf3e6a13c21 100644 --- a/net/ceph/buffer.c +++ b/net/ceph/buffer.c @@ -19,7 +19,7 @@ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) if (b->vec.iov_base) { b->is_vmalloc = false; } else { - b->vec.iov_base = __vmalloc(len, gfp, PAGE_KERNEL); + b->vec.iov_base = __vmalloc(len, gfp | __GFP_HIGHMEM, PAGE_KERNEL); if (!b->vec.iov_base) { kfree(b); return NULL; diff --git a/net/core/datagram.c b/net/core/datagram.c index cd1e039c875..18ac112ea7a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -177,7 +177,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, * interrupt level will suddenly eat the receive_queue. * * Look at current nfs client by the way... - * However, this function was corrent in any case. 8) + * However, this function was correct in any case. 8) */ unsigned long cpu_flags; diff --git a/net/core/dev.c b/net/core/dev.c index cd243749542..d28b3a023bb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -743,34 +743,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) EXPORT_SYMBOL(dev_get_by_index); /** - * dev_getbyhwaddr - find a device by its hardware address + * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device - * is not found or a pointer to the device. The caller must hold the - * rtnl semaphore. The returned device has not had its ref count increased + * is not found or a pointer to the device. The caller must hold RCU + * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * - * BUGS: - * If the API was consistent this would be __dev_get_by_hwaddr */ -struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha) +struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *ha) { struct net_device *dev; - ASSERT_RTNL(); - - for_each_netdev(net, dev) + for_each_netdev_rcu(net, dev) if (dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) return dev; return NULL; } -EXPORT_SYMBOL(dev_getbyhwaddr); +EXPORT_SYMBOL(dev_getbyhwaddr_rcu); struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) { @@ -2025,9 +2022,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int rc = NETDEV_TX_OK; if (likely(!skb->next)) { - if (!list_empty(&ptype_all)) - dev_queue_xmit_nit(skb, dev); - /* * If device doesnt need skb->dst, release it right now while * its hot in this cpu cache @@ -2035,6 +2029,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + skb_orphan_try(skb); if (vlan_tx_tag_present(skb) && @@ -5041,10 +5038,13 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } if (features & NETIF_F_UFO) { - if (!(features & NETIF_F_GEN_CSUM)) { + /* maybe split UFO into V4 and V6? */ + if (!((features & NETIF_F_GEN_CSUM) || + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) + == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { if (name) printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_HW_CSUM feature.\n", + "since no checksum offload features.\n", name); features &= ~NETIF_F_UFO; } @@ -5109,11 +5109,21 @@ static int netif_alloc_rx_queues(struct net_device *dev) } #endif +static void netdev_init_one_queue(struct net_device *dev, + struct netdev_queue *queue, void *_unused) +{ + /* Initialize queue lock */ + spin_lock_init(&queue->_xmit_lock); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + queue->xmit_lock_owner = -1; + netdev_queue_numa_node_write(queue, -1); + queue->dev = dev; +} + static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; - int i; BUG_ON(count < 1); @@ -5125,27 +5135,10 @@ static int netif_alloc_netdev_queues(struct net_device *dev) } dev->_tx = tx; - for (i = 0; i < count; i++) { - netdev_queue_numa_node_write(&tx[i], -1); - tx[i].dev = dev; - } - return 0; -} - -static void netdev_init_one_queue(struct net_device *dev, - struct netdev_queue *queue, - void *_unused) -{ - /* Initialize queue lock */ - spin_lock_init(&queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); - queue->xmit_lock_owner = -1; -} - -static void netdev_init_queues(struct net_device *dev) -{ netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); spin_lock_init(&dev->tx_global_lock); + + return 0; } /** @@ -5184,8 +5177,6 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; - netdev_init_queues(dev); - /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 956a9f4971c..d5bc2881888 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1171,7 +1171,9 @@ static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr) return -EFAULT; if (edata.data && !(dev->features & NETIF_F_SG)) return -EINVAL; - if (edata.data && !(dev->features & NETIF_F_HW_CSUM)) + if (edata.data && !((dev->features & NETIF_F_GEN_CSUM) || + (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) + == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) return -EINVAL; return dev->ethtool_ops->set_ufo(dev, edata.data); } diff --git a/net/core/filter.c b/net/core/filter.c index a44d27f9f0f..e8a6ac411ff 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -88,7 +88,7 @@ enum { }; /* No hurry in this branch */ -static void *__load_pointer(struct sk_buff *skb, int k) +static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; @@ -97,12 +97,12 @@ static void *__load_pointer(struct sk_buff *skb, int k) else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - if (ptr >= skb->head && ptr < skb_tail_pointer(skb)) + if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL; } -static inline void *load_pointer(struct sk_buff *skb, int k, +static inline void *load_pointer(const struct sk_buff *skb, int k, unsigned int size, void *buffer) { if (k >= 0) @@ -110,7 +110,7 @@ static inline void *load_pointer(struct sk_buff *skb, int k, else { if (k >= SKF_AD_OFF) return NULL; - return __load_pointer(skb, k); + return __load_pointer(skb, k, size); } } @@ -160,17 +160,16 @@ EXPORT_SYMBOL(sk_filter); * and last instruction guaranteed to be a RET, we dont need to check * flen. (We used to pass to this function the length of filter) */ -unsigned int sk_run_filter(struct sk_buff *skb, const struct sock_filter *fentry) +unsigned int sk_run_filter(const struct sk_buff *skb, + const struct sock_filter *fentry) { void *ptr; u32 A = 0; /* Accumulator */ u32 X = 0; /* Index Register */ u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ - unsigned long memvalid = 0; u32 tmp; int k; - BUILD_BUG_ON(BPF_MEMWORDS > BITS_PER_LONG); /* * Process array of filter instructions. */ @@ -318,12 +317,10 @@ load_b: X = K; continue; case BPF_S_LD_MEM: - A = (memvalid & (1UL << K)) ? - mem[K] : 0; + A = mem[K]; continue; case BPF_S_LDX_MEM: - X = (memvalid & (1UL << K)) ? - mem[K] : 0; + X = mem[K]; continue; case BPF_S_MISC_TAX: X = A; @@ -336,11 +333,9 @@ load_b: case BPF_S_RET_A: return A; case BPF_S_ST: - memvalid |= 1UL << K; mem[K] = A; continue; case BPF_S_STX: - memvalid |= 1UL << K; mem[K] = X; continue; default: @@ -375,6 +370,12 @@ load_b: return 0; A = skb->dev->type; continue; + case SKF_AD_RXHASH: + A = skb->rxhash; + continue; + case SKF_AD_CPU: + A = raw_smp_processor_id(); + continue; case SKF_AD_NLATTR: { struct nlattr *nla; @@ -419,6 +420,66 @@ load_b: } EXPORT_SYMBOL(sk_run_filter); +/* + * Security : + * A BPF program is able to use 16 cells of memory to store intermediate + * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()) + * As we dont want to clear mem[] array for each packet going through + * sk_run_filter(), we check that filter loaded by user never try to read + * a cell if not previously written, and we check all branches to be sure + * a malicious user doesnt try to abuse us. + */ +static int check_load_and_stores(struct sock_filter *filter, int flen) +{ + u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */ + int pc, ret = 0; + + BUILD_BUG_ON(BPF_MEMWORDS > 16); + masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL); + if (!masks) + return -ENOMEM; + memset(masks, 0xff, flen * sizeof(*masks)); + + for (pc = 0; pc < flen; pc++) { + memvalid &= masks[pc]; + + switch (filter[pc].code) { + case BPF_S_ST: + case BPF_S_STX: + memvalid |= (1 << filter[pc].k); + break; + case BPF_S_LD_MEM: + case BPF_S_LDX_MEM: + if (!(memvalid & (1 << filter[pc].k))) { + ret = -EINVAL; + goto error; + } + break; + case BPF_S_JMP_JA: + /* a jump must set masks on target */ + masks[pc + 1 + filter[pc].k] &= memvalid; + memvalid = ~0; + break; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JEQ_X: + case BPF_S_JMP_JGE_K: + case BPF_S_JMP_JGE_X: + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGT_X: + case BPF_S_JMP_JSET_X: + case BPF_S_JMP_JSET_K: + /* a jump must set masks on targets */ + masks[pc + 1 + filter[pc].jt] &= memvalid; + masks[pc + 1 + filter[pc].jf] &= memvalid; + memvalid = ~0; + break; + } + } +error: + kfree(masks); + return ret; +} + /** * sk_chk_filter - verify socket filter code * @filter: filter to verify @@ -547,30 +608,23 @@ int sk_chk_filter(struct sock_filter *filter, int flen) switch (filter[flen - 1].code) { case BPF_S_RET_K: case BPF_S_RET_A: - return 0; + return check_load_and_stores(filter, flen); } return -EINVAL; } EXPORT_SYMBOL(sk_chk_filter); /** - * sk_filter_rcu_release - Release a socket filter by rcu_head + * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ -static void sk_filter_rcu_release(struct rcu_head *rcu) +void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); - sk_filter_release(fp); -} - -static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp) -{ - unsigned int size = sk_filter_len(fp); - - atomic_sub(size, &sk->sk_omem_alloc); - call_rcu_bh(&fp->rcu, sk_filter_rcu_release); + kfree(fp); } +EXPORT_SYMBOL(sk_filter_release_rcu); /** * sk_attach_filter - attach a socket filter @@ -614,7 +668,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) - sk_filter_delayed_uncharge(sk, old_fp); + sk_filter_uncharge(sk, old_fp); return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); @@ -628,7 +682,7 @@ int sk_detach_filter(struct sock *sk) sock_owned_by_user(sk)); if (filter) { rcu_assign_pointer(sk->sk_filter, NULL); - sk_filter_delayed_uncharge(sk, filter); + sk_filter_uncharge(sk, filter); ret = 0; } return ret; diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 41d99435f62..182236b2510 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -46,9 +46,7 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); lopt_size += nr_table_entries * sizeof(struct request_sock *); if (lopt_size > PAGE_SIZE) - lopt = __vmalloc(lopt_size, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL); + lopt = vzalloc(lopt_size); else lopt = kzalloc(lopt_size, GFP_KERNEL); if (lopt == NULL) diff --git a/net/core/sock.c b/net/core/sock.c index fb608011146..bcdb6ff6e62 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -992,17 +992,18 @@ static inline void sock_lock_init(struct sock *sk) /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarly, because of RCU lookups. sk_node should also be left as is. + * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif - BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) != - sizeof(osk->sk_node) + sizeof(osk->sk_refcnt) + - sizeof(osk->sk_tx_queue_mapping)); - memcpy(&nsk->sk_copy_start, &osk->sk_copy_start, - osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start)); + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); + + memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); diff --git a/net/core/timestamping.c b/net/core/timestamping.c index dac7ed687f6..b124d28ff1c 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -26,7 +26,7 @@ static struct sock_filter ptp_filter[] = { PTP_FILTER }; -static unsigned int classify(struct sk_buff *skb) +static unsigned int classify(const struct sk_buff *skb) { if (likely(skb->dev && skb->dev->phydev && diff --git a/net/dccp/Makefile b/net/dccp/Makefile index 2991efcc8de..5c8362b037e 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -1,7 +1,7 @@ obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o -dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o - +dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o \ + qpolicy.o # # CCID algorithms to be used by dccp.ko # diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 19fafd59746..48ad5d9da7c 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -243,6 +243,19 @@ extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, extern void dccp_send_sync(struct sock *sk, const u64 seq, const enum dccp_pkt_type pkt_type); +/* + * TX Packet Dequeueing Interface + */ +extern void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb); +extern bool dccp_qpolicy_full(struct sock *sk); +extern void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb); +extern struct sk_buff *dccp_qpolicy_top(struct sock *sk); +extern struct sk_buff *dccp_qpolicy_pop(struct sock *sk); +extern bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param); + +/* + * TX Packet Output and TX Timers + */ extern void dccp_write_xmit(struct sock *sk); extern void dccp_write_space(struct sock *sk); extern void dccp_flush_write_queue(struct sock *sk, long *time_budget); diff --git a/net/dccp/input.c b/net/dccp/input.c index 7d230d14ce2..15af247ea00 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -241,7 +241,8 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) dccp_update_gsr(sk, seqno); if (dh->dccph_type != DCCP_PKT_SYNC && - (ackno != DCCP_PKT_WITHOUT_ACK_SEQ)) + ackno != DCCP_PKT_WITHOUT_ACK_SEQ && + after48(ackno, dp->dccps_gar)) dp->dccps_gar = ackno; } else { unsigned long now = jiffies; diff --git a/net/dccp/output.c b/net/dccp/output.c index d96dd9d362a..784d3021054 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -242,7 +242,7 @@ static void dccp_xmit_packet(struct sock *sk) { int err, len; struct dccp_sock *dp = dccp_sk(sk); - struct sk_buff *skb = skb_dequeue(&sk->sk_write_queue); + struct sk_buff *skb = dccp_qpolicy_pop(sk); if (unlikely(skb == NULL)) return; @@ -345,7 +345,7 @@ void dccp_write_xmit(struct sock *sk) struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; - while ((skb = skb_peek(&sk->sk_write_queue))) { + while ((skb = dccp_qpolicy_top(sk))) { int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); switch (ccid_packet_dequeue_eval(rc)) { @@ -359,8 +359,7 @@ void dccp_write_xmit(struct sock *sk) dccp_xmit_packet(sk); break; case CCID_PACKET_ERR: - skb_dequeue(&sk->sk_write_queue); - kfree_skb(skb); + dccp_qpolicy_drop(sk, skb); dccp_pr_debug("packet discarded due to err=%d\n", rc); } } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index ef343d53fce..152975d942d 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -185,6 +185,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT; dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1; + dp->dccps_tx_qlen = sysctl_dccp_tx_qlen; dccp_init_xmit_timers(sk); @@ -532,6 +533,20 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_RECV_CSCOV: err = dccp_setsockopt_cscov(sk, val, true); break; + case DCCP_SOCKOPT_QPOLICY_ID: + if (sk->sk_state != DCCP_CLOSED) + err = -EISCONN; + else if (val < 0 || val >= DCCPQ_POLICY_MAX) + err = -EINVAL; + else + dp->dccps_qpolicy = val; + break; + case DCCP_SOCKOPT_QPOLICY_TXQLEN: + if (val < 0) + err = -EINVAL; + else + dp->dccps_tx_qlen = val; + break; default: err = -ENOPROTOOPT; break; @@ -639,6 +654,12 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_RECV_CSCOV: val = dp->dccps_pcrlen; break; + case DCCP_SOCKOPT_QPOLICY_ID: + val = dp->dccps_qpolicy; + break; + case DCCP_SOCKOPT_QPOLICY_TXQLEN: + val = dp->dccps_tx_qlen; + break; case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); @@ -681,6 +702,47 @@ int compat_dccp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(compat_dccp_getsockopt); #endif +static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) +{ + struct cmsghdr *cmsg = CMSG_FIRSTHDR(msg); + + /* + * Assign an (opaque) qpolicy priority value to skb->priority. + * + * We are overloading this skb field for use with the qpolicy subystem. + * The skb->priority is normally used for the SO_PRIORITY option, which + * is initialised from sk_priority. Since the assignment of sk_priority + * to skb->priority happens later (on layer 3), we overload this field + * for use with queueing priorities as long as the skb is on layer 4. + * The default priority value (if nothing is set) is 0. + */ + skb->priority = 0; + + for (; cmsg != NULL; cmsg = CMSG_NXTHDR(msg, cmsg)) { + + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + if (cmsg->cmsg_level != SOL_DCCP) + continue; + + if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX && + !dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type)) + return -EINVAL; + + switch (cmsg->cmsg_type) { + case DCCP_SCM_PRIORITY: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32))) + return -EINVAL; + skb->priority = *(__u32 *)CMSG_DATA(cmsg); + break; + default: + return -EINVAL; + } + } + return 0; +} + int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { @@ -696,8 +758,7 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, lock_sock(sk); - if (sysctl_dccp_tx_qlen && - (sk->sk_write_queue.qlen >= sysctl_dccp_tx_qlen)) { + if (dccp_qpolicy_full(sk)) { rc = -EAGAIN; goto out_release; } @@ -725,7 +786,11 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (rc != 0) goto out_discard; - skb_queue_tail(&sk->sk_write_queue, skb); + rc = dccp_msghdr_parse(msg, skb); + if (rc != 0) + goto out_discard; + + dccp_qpolicy_push(sk, skb); /* * The xmit_timer is set if the TX CCID is rate-based and will expire * when congestion control permits to release further packets into the diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c new file mode 100644 index 00000000000..63c30bfa470 --- /dev/null +++ b/net/dccp/qpolicy.c @@ -0,0 +1,137 @@ +/* + * net/dccp/qpolicy.c + * + * Policy-based packet dequeueing interface for DCCP. + * + * Copyright (c) 2008 Tomasz Grobelny + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License v2 + * as published by the Free Software Foundation. + */ +#include "dccp.h" + +/* + * Simple Dequeueing Policy: + * If tx_qlen is different from 0, enqueue up to tx_qlen elements. + */ +static void qpolicy_simple_push(struct sock *sk, struct sk_buff *skb) +{ + skb_queue_tail(&sk->sk_write_queue, skb); +} + +static bool qpolicy_simple_full(struct sock *sk) +{ + return dccp_sk(sk)->dccps_tx_qlen && + sk->sk_write_queue.qlen >= dccp_sk(sk)->dccps_tx_qlen; +} + +static struct sk_buff *qpolicy_simple_top(struct sock *sk) +{ + return skb_peek(&sk->sk_write_queue); +} + +/* + * Priority-based Dequeueing Policy: + * If tx_qlen is different from 0 and the queue has reached its upper bound + * of tx_qlen elements, replace older packets lowest-priority-first. + */ +static struct sk_buff *qpolicy_prio_best_skb(struct sock *sk) +{ + struct sk_buff *skb, *best = NULL; + + skb_queue_walk(&sk->sk_write_queue, skb) + if (best == NULL || skb->priority > best->priority) + best = skb; + return best; +} + +static struct sk_buff *qpolicy_prio_worst_skb(struct sock *sk) +{ + struct sk_buff *skb, *worst = NULL; + + skb_queue_walk(&sk->sk_write_queue, skb) + if (worst == NULL || skb->priority < worst->priority) + worst = skb; + return worst; +} + +static bool qpolicy_prio_full(struct sock *sk) +{ + if (qpolicy_simple_full(sk)) + dccp_qpolicy_drop(sk, qpolicy_prio_worst_skb(sk)); + return false; +} + +/** + * struct dccp_qpolicy_operations - TX Packet Dequeueing Interface + * @push: add a new @skb to the write queue + * @full: indicates that no more packets will be admitted + * @top: peeks at whatever the queueing policy defines as its `top' + */ +static struct dccp_qpolicy_operations { + void (*push) (struct sock *sk, struct sk_buff *skb); + bool (*full) (struct sock *sk); + struct sk_buff* (*top) (struct sock *sk); + __be32 params; + +} qpol_table[DCCPQ_POLICY_MAX] = { + [DCCPQ_POLICY_SIMPLE] = { + .push = qpolicy_simple_push, + .full = qpolicy_simple_full, + .top = qpolicy_simple_top, + .params = 0, + }, + [DCCPQ_POLICY_PRIO] = { + .push = qpolicy_simple_push, + .full = qpolicy_prio_full, + .top = qpolicy_prio_best_skb, + .params = DCCP_SCM_PRIORITY, + }, +}; + +/* + * Externally visible interface + */ +void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb) +{ + qpol_table[dccp_sk(sk)->dccps_qpolicy].push(sk, skb); +} + +bool dccp_qpolicy_full(struct sock *sk) +{ + return qpol_table[dccp_sk(sk)->dccps_qpolicy].full(sk); +} + +void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb) +{ + if (skb != NULL) { + skb_unlink(skb, &sk->sk_write_queue); + kfree_skb(skb); + } +} + +struct sk_buff *dccp_qpolicy_top(struct sock *sk) +{ + return qpol_table[dccp_sk(sk)->dccps_qpolicy].top(sk); +} + +struct sk_buff *dccp_qpolicy_pop(struct sock *sk) +{ + struct sk_buff *skb = dccp_qpolicy_top(sk); + + if (skb != NULL) { + /* Clear any skb fields that we used internally */ + skb->priority = 0; + skb_unlink(skb, &sk->sk_write_queue); + } + return skb; +} + +bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param) +{ + /* check if exactly one bit is set */ + if (!param || (param & (param - 1))) + return false; + return (qpol_table[dccp_sk(sk)->dccps_qpolicy].params & param) == param; +} diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 9ecef9968c3..0065e7e14af 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1556,6 +1556,8 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us if (r_len > sizeof(struct linkinfo_dn)) r_len = sizeof(struct linkinfo_dn); + memset(&link, 0, sizeof(link)); + switch(sock->state) { case SS_CONNECTING: link.idn_linkstate = LL_CONNECTING; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 8280e43c886..e2e926841fe 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -240,13 +240,13 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) if (dst_metric(dst, RTAX_MTU) > mtu && mtu >= min_mtu) { if (!(dst_metric_locked(dst, RTAX_MTU))) { - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); dst_set_expires(dst, dn_rt_mtu_expires); } if (!(dst_metric_locked(dst, RTAX_ADVMSS))) { u32 mss = mtu - DN_MAX_NSP_DATA_HEADER; if (dst_metric(dst, RTAX_ADVMSS) > mss) - dst->metrics[RTAX_ADVMSS-1] = mss; + dst_metric_set(dst, RTAX_ADVMSS, mss); } } } @@ -806,8 +806,7 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) if (DN_FIB_RES_GW(*res) && DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = DN_FIB_RES_GW(*res); - memcpy(rt->dst.metrics, fi->fib_metrics, - sizeof(rt->dst.metrics)); + dst_import_metrics(&rt->dst, fi->fib_metrics); } rt->rt_type = res->type; @@ -820,11 +819,11 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) if (dst_metric(&rt->dst, RTAX_MTU) == 0 || dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) - rt->dst.metrics[RTAX_MTU-1] = rt->dst.dev->mtu; + dst_metric_set(&rt->dst, RTAX_MTU, rt->dst.dev->mtu); mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst)); if (dst_metric(&rt->dst, RTAX_ADVMSS) == 0 || dst_metric(&rt->dst, RTAX_ADVMSS) > mss) - rt->dst.metrics[RTAX_ADVMSS-1] = mss; + dst_metric_set(&rt->dst, RTAX_ADVMSS, mss); return 0; } @@ -1502,7 +1501,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, RTA_PUT(skb, RTA_PREFSRC, 2, &rt->rt_local_src); if (rt->rt_daddr != rt->rt_gateway) RTA_PUT(skb, RTA_GATEWAY, 2, &rt->rt_gateway); - if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto rtattr_failure; expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, expires, diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index f8c1ae4b41f..f180371fa41 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -276,12 +277,12 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, #endif #ifdef CONFIG_ECONET_AUNUDP struct msghdr udpmsg; - struct iovec iov[msg->msg_iovlen+1]; + struct iovec iov[2]; struct aunhdr ah; struct sockaddr_in udpdest; __kernel_size_t size; - int i; mm_segment_t oldfs; + char *userbuf; #endif /* @@ -297,23 +298,14 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, mutex_lock(&econet_mutex); - if (saddr == NULL) { - struct econet_sock *eo = ec_sk(sk); - - addr.station = eo->station; - addr.net = eo->net; - port = eo->port; - cb = eo->cb; - } else { - if (msg->msg_namelen < sizeof(struct sockaddr_ec)) { - mutex_unlock(&econet_mutex); - return -EINVAL; - } - addr.station = saddr->addr.station; - addr.net = saddr->addr.net; - port = saddr->port; - cb = saddr->cb; - } + if (saddr == NULL || msg->msg_namelen < sizeof(struct sockaddr_ec)) { + mutex_unlock(&econet_mutex); + return -EINVAL; + } + addr.station = saddr->addr.station; + addr.net = saddr->addr.net; + port = saddr->port; + cb = saddr->cb; /* Look for a device with the right network number. */ dev = net2dev_map[addr.net]; @@ -328,17 +320,17 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, } } - if (len + 15 > dev->mtu) { - mutex_unlock(&econet_mutex); - return -EMSGSIZE; - } - if (dev->type == ARPHRD_ECONET) { /* Real hardware Econet. We're not worthy etc. */ #ifdef CONFIG_ECONET_NATIVE unsigned short proto = 0; int res; + if (len + 15 > dev->mtu) { + mutex_unlock(&econet_mutex); + return -EMSGSIZE; + } + dev_hold(dev); skb = sock_alloc_send_skb(sk, len+LL_ALLOCATED_SPACE(dev), @@ -351,7 +343,6 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, eb = (struct ec_cb *)&skb->cb; - /* BUG: saddr may be NULL */ eb->cookie = saddr->cookie; eb->sec = *saddr; eb->sent = ec_tx_done; @@ -415,6 +406,11 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, return -ENETDOWN; /* No socket - can't send */ } + if (len > 32768) { + err = -E2BIG; + goto error; + } + /* Make up a UDP datagram and hand it off to some higher intellect. */ memset(&udpdest, 0, sizeof(udpdest)); @@ -446,36 +442,26 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, /* tack our header on the front of the iovec */ size = sizeof(struct aunhdr); - /* - * XXX: that is b0rken. We can't mix userland and kernel pointers - * in iovec, since on a lot of platforms copy_from_user() will - * *not* work with the kernel and userland ones at the same time, - * regardless of what we do with set_fs(). And we are talking about - * econet-over-ethernet here, so "it's only ARM anyway" doesn't - * apply. Any suggestions on fixing that code? -- AV - */ iov[0].iov_base = (void *)&ah; iov[0].iov_len = size; - for (i = 0; i < msg->msg_iovlen; i++) { - void __user *base = msg->msg_iov[i].iov_base; - size_t iov_len = msg->msg_iov[i].iov_len; - /* Check it now since we switch to KERNEL_DS later. */ - if (!access_ok(VERIFY_READ, base, iov_len)) { - mutex_unlock(&econet_mutex); - return -EFAULT; - } - iov[i+1].iov_base = base; - iov[i+1].iov_len = iov_len; - size += iov_len; + + userbuf = vmalloc(len); + if (userbuf == NULL) { + err = -ENOMEM; + goto error; } + iov[1].iov_base = userbuf; + iov[1].iov_len = len; + err = memcpy_fromiovec(userbuf, msg->msg_iov, len); + if (err) + goto error_free_buf; + /* Get a skbuff (no data, just holds our cb information) */ if ((skb = sock_alloc_send_skb(sk, 0, msg->msg_flags & MSG_DONTWAIT, - &err)) == NULL) { - mutex_unlock(&econet_mutex); - return err; - } + &err)) == NULL) + goto error_free_buf; eb = (struct ec_cb *)&skb->cb; @@ -491,7 +477,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, udpmsg.msg_name = (void *)&udpdest; udpmsg.msg_namelen = sizeof(udpdest); udpmsg.msg_iov = &iov[0]; - udpmsg.msg_iovlen = msg->msg_iovlen + 1; + udpmsg.msg_iovlen = 2; udpmsg.msg_control = NULL; udpmsg.msg_controllen = 0; udpmsg.msg_flags=0; @@ -499,9 +485,13 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, oldfs = get_fs(); set_fs(KERNEL_DS); /* More privs :-) */ err = sock_sendmsg(udpsock, &udpmsg, size); set_fs(oldfs); + +error_free_buf: + vfree(userbuf); #else err = -EPROTOTYPE; #endif + error: mutex_unlock(&econet_mutex); return err; @@ -671,6 +661,11 @@ static int ec_dev_ioctl(struct socket *sock, unsigned int cmd, void __user *arg) err = 0; switch (cmd) { case SIOCSIFADDR: + if (!capable(CAP_NET_ADMIN)) { + err = -EPERM; + break; + } + edev = dev->ec_ptr; if (edev == NULL) { /* Magic up a new one. */ diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 93c91b633a5..6df6ecf4970 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -52,11 +52,11 @@ struct net_device *ieee802154_get_dev(struct net *net, switch (addr->addr_type) { case IEEE802154_ADDR_LONG: - rtnl_lock(); - dev = dev_getbyhwaddr(net, ARPHRD_IEEE802154, addr->hwaddr); + rcu_read_lock(); + dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr); if (dev) dev_hold(dev); - rtnl_unlock(); + rcu_read_unlock(); break; case IEEE802154_ADDR_SHORT: if (addr->pan_id == 0xffff || diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 7833f17b648..a2fc7b961db 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -883,7 +883,7 @@ static int arp_process(struct sk_buff *skb) dont_send = arp_ignore(in_dev, sip, tip); if (!dont_send && IN_DEV_ARPFILTER(in_dev)) - dont_send |= arp_filter(sip, tip, dev); + dont_send = arp_filter(sip, tip, dev); if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { @@ -1017,13 +1017,14 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } - if (__in_dev_get_rtnl(dev)) { - IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on); + if (__in_dev_get_rcu(dev)) { + IN_DEV_CONF_SET(__in_dev_get_rcu(dev), PROXY_ARP, on); return 0; } return -ENXIO; } +/* must be called with rcu_read_lock() */ static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { @@ -1033,7 +1034,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, if (mask && mask != htonl(0xFFFFFFFF)) return -EINVAL; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; @@ -1225,10 +1226,10 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!(r.arp_flags & ATF_NETMASK)) ((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr = htonl(0xFFFFFFFFUL); - rtnl_lock(); + rcu_read_lock(); if (r.arp_dev[0]) { err = -ENODEV; - dev = __dev_get_by_name(net, r.arp_dev); + dev = dev_get_by_name_rcu(net, r.arp_dev); if (dev == NULL) goto out; @@ -1252,12 +1253,12 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; case SIOCGARP: err = arp_req_get(&r, dev); - if (!err && copy_to_user(arg, &r, sizeof(r))) - err = -EFAULT; break; } out: - rtnl_unlock(); + rcu_read_unlock(); + if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r))) + err = -EFAULT; return err; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d9f71bae45c..3b067704ab3 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1258,7 +1258,7 @@ errout: static size_t inet_get_link_af_size(const struct net_device *dev) { - struct in_device *in_dev = __in_dev_get_rcu(dev); + struct in_device *in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return 0; @@ -1268,7 +1268,7 @@ static size_t inet_get_link_af_size(const struct net_device *dev) static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) { - struct in_device *in_dev = __in_dev_get_rcu(dev); + struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *nla; int i; @@ -1295,7 +1295,7 @@ static int inet_validate_link_af(const struct net_device *dev, struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; - if (dev && !__in_dev_get_rcu(dev)) + if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy); @@ -1319,7 +1319,7 @@ static int inet_validate_link_af(const struct net_device *dev, static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) { - struct in_device *in_dev = __in_dev_get_rcu(dev); + struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 200eb538fbb..0f280348e0f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -365,7 +365,7 @@ static struct tnode *tnode_alloc(size_t size) if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else - return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); + return vzalloc(size); } static void __tnode_vfree(struct work_struct *arg) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 06f5f8f482f..25e318153f1 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -55,7 +55,6 @@ EXPORT_SYMBOL(inet_get_local_port_range); int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb) { - const __be32 sk_rcv_saddr = inet_rcv_saddr(sk); struct sock *sk2; struct hlist_node *node; int reuse = sk->sk_reuse; @@ -75,9 +74,9 @@ int inet_csk_bind_conflict(const struct sock *sk, sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { if (!reuse || !sk2->sk_reuse || sk2->sk_state == TCP_LISTEN) { - const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); - if (!sk2_rcv_saddr || !sk_rcv_saddr || - sk2_rcv_saddr == sk_rcv_saddr) + const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); + if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || + sk2_rcv_saddr == sk_rcv_saddr(sk)) break; } } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 1b344f30b46..3c0369a3a66 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -133,8 +133,7 @@ int __inet_inherit_port(struct sock *sk, struct sock *child) } } } - sk_add_bind_node(child, &tb->owners); - inet_csk(child)->icsk_bind_hash = tb; + inet_bind_hash(child, tb, port); spin_unlock(&head->lock); return 0; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 258c98d5fa7..ff4e7a4e33e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -818,7 +818,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev !ipv4_is_multicast(tunnel->parms.iph.daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; - skb_dst(skb)->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); } } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 1b48eb1ed45..b14ec7d03b6 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -253,6 +253,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP), SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER), + SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3843c2dfde8..26ac396eaa5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1686,11 +1686,14 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, if (mtu < dst_mtu(&rth->dst)) { dst_confirm(&rth->dst); if (mtu < ip_rt_min_pmtu) { + u32 lock = dst_metric(&rth->dst, + RTAX_LOCK); mtu = ip_rt_min_pmtu; - rth->dst.metrics[RTAX_LOCK-1] |= - (1 << RTAX_MTU); + lock |= (1 << RTAX_MTU); + dst_metric_set(&rth->dst, RTAX_LOCK, + lock); } - rth->dst.metrics[RTAX_MTU-1] = mtu; + dst_metric_set(&rth->dst, RTAX_MTU, mtu); dst_set_expires(&rth->dst, ip_rt_mtu_expires); } @@ -1708,10 +1711,11 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) if (dst_mtu(dst) > mtu && mtu >= 68 && !(dst_metric_locked(dst, RTAX_MTU))) { if (mtu < ip_rt_min_pmtu) { + u32 lock = dst_metric(dst, RTAX_LOCK); mtu = ip_rt_min_pmtu; - dst->metrics[RTAX_LOCK-1] |= (1 << RTAX_MTU); + dst_metric_set(dst, RTAX_LOCK, lock | (1 << RTAX_MTU)); } - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); dst_set_expires(dst, ip_rt_mtu_expires); call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } @@ -1796,36 +1800,37 @@ static void set_class_tag(struct rtable *rt, u32 tag) static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) { + struct dst_entry *dst = &rt->dst; struct fib_info *fi = res->fi; if (fi) { if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = FIB_RES_GW(*res); - memcpy(rt->dst.metrics, fi->fib_metrics, - sizeof(rt->dst.metrics)); + dst_import_metrics(dst, fi->fib_metrics); if (fi->fib_mtu == 0) { - rt->dst.metrics[RTAX_MTU-1] = rt->dst.dev->mtu; - if (dst_metric_locked(&rt->dst, RTAX_MTU) && + dst_metric_set(dst, RTAX_MTU, dst->dev->mtu); + if (dst_metric_locked(dst, RTAX_MTU) && rt->rt_gateway != rt->rt_dst && - rt->dst.dev->mtu > 576) - rt->dst.metrics[RTAX_MTU-1] = 576; + dst->dev->mtu > 576) + dst_metric_set(dst, RTAX_MTU, 576); } #ifdef CONFIG_NET_CLS_ROUTE - rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid; + dst->tclassid = FIB_RES_NH(*res).nh_tclassid; #endif } else - rt->dst.metrics[RTAX_MTU-1]= rt->dst.dev->mtu; - - if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0) - rt->dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl; - if (dst_mtu(&rt->dst) > IP_MAX_MTU) - rt->dst.metrics[RTAX_MTU-1] = IP_MAX_MTU; - if (dst_metric(&rt->dst, RTAX_ADVMSS) == 0) - rt->dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->dst.dev->mtu - 40, - ip_rt_min_advmss); - if (dst_metric(&rt->dst, RTAX_ADVMSS) > 65535 - 40) - rt->dst.metrics[RTAX_ADVMSS-1] = 65535 - 40; + dst_metric_set(dst, RTAX_MTU, dst->dev->mtu); + + if (dst_metric(dst, RTAX_HOPLIMIT) == 0) + dst_metric_set(dst, RTAX_HOPLIMIT, sysctl_ip_default_ttl); + if (dst_mtu(dst) > IP_MAX_MTU) + dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU); + if (dst_metric(dst, RTAX_ADVMSS) == 0) + dst_metric_set(dst, RTAX_ADVMSS, + max_t(unsigned int, dst->dev->mtu - 40, + ip_rt_min_advmss)); + if (dst_metric(dst, RTAX_ADVMSS) > 65535 - 40) + dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40); #ifdef CONFIG_NET_CLS_ROUTE #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -2720,7 +2725,7 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi new->__use = 1; new->input = dst_discard; new->output = dst_discard; - memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + dst_copy_metrics(new, &ort->dst); new->dev = ort->dst.dev; if (new->dev) @@ -2827,7 +2832,7 @@ static int rt_fill_info(struct net *net, if (rt->rt_dst != rt->rt_gateway) NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway); - if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; if (rt->fl.mark) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index e91911d7aae..1b4ec21497a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -26,6 +26,8 @@ static int zero; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; +static int tcp_adv_win_scale_min = -31; +static int tcp_adv_win_scale_max = 31; /* Update system visible IP port range */ static void set_local_port_range(int range[2]) @@ -426,7 +428,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_adv_win_scale, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_adv_win_scale_min, + .extra2 = &tcp_adv_win_scale_max, }, { .procname = "tcp_tw_reuse", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2bb46d55f40..6c11eece262 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2244,7 +2244,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ - if (val < 64 || val > MAX_TCP_WINDOW) { + if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) { err = -EINVAL; break; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6d8ab1c4efc..824e8c8a17a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -734,7 +734,7 @@ void tcp_update_metrics(struct sock *sk) * Reset our results. */ if (!(dst_metric_locked(dst, RTAX_RTT))) - dst->metrics[RTAX_RTT - 1] = 0; + dst_metric_set(dst, RTAX_RTT, 0); return; } @@ -776,34 +776,38 @@ void tcp_update_metrics(struct sock *sk) if (dst_metric(dst, RTAX_SSTHRESH) && !dst_metric_locked(dst, RTAX_SSTHRESH) && (tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH)) - dst->metrics[RTAX_SSTHRESH-1] = tp->snd_cwnd >> 1; + dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1); if (!dst_metric_locked(dst, RTAX_CWND) && tp->snd_cwnd > dst_metric(dst, RTAX_CWND)) - dst->metrics[RTAX_CWND - 1] = tp->snd_cwnd; + dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd); } else if (tp->snd_cwnd > tp->snd_ssthresh && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ if (!dst_metric_locked(dst, RTAX_SSTHRESH)) - dst->metrics[RTAX_SSTHRESH-1] = - max(tp->snd_cwnd >> 1, tp->snd_ssthresh); + dst_metric_set(dst, RTAX_SSTHRESH, + max(tp->snd_cwnd >> 1, tp->snd_ssthresh)); if (!dst_metric_locked(dst, RTAX_CWND)) - dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_cwnd) >> 1; + dst_metric_set(dst, RTAX_CWND, + (dst_metric(dst, RTAX_CWND) + + tp->snd_cwnd) >> 1); } else { /* Else slow start did not finish, cwnd is non-sense, ssthresh may be also invalid. */ if (!dst_metric_locked(dst, RTAX_CWND)) - dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_ssthresh) >> 1; + dst_metric_set(dst, RTAX_CWND, + (dst_metric(dst, RTAX_CWND) + + tp->snd_ssthresh) >> 1); if (dst_metric(dst, RTAX_SSTHRESH) && !dst_metric_locked(dst, RTAX_SSTHRESH) && tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH)) - dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh; + dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh); } if (!dst_metric_locked(dst, RTAX_REORDERING)) { if (dst_metric(dst, RTAX_REORDERING) < tp->reordering && tp->reordering != sysctl_tcp_reordering) - dst->metrics[RTAX_REORDERING-1] = tp->reordering; + dst_metric_set(dst, RTAX_REORDERING, tp->reordering); } } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index dd555051ec8..4fc3387aa99 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2013,7 +2013,9 @@ get_req: } get_sk: sk_nulls_for_each_from(sk, node) { - if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) { + if (!net_eq(sock_net(sk), net)) + continue; + if (sk->sk_family == st->family) { cur = sk; goto out; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 3527b51d615..80b1f80759a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -392,7 +392,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) * socket up. We've got bigger problems than * non-graceful socket closings. */ - LIMIT_NETDEBUG(KERN_INFO "TCP: time wait bucket table overflow\n"); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW); } tcp_update_metrics(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 749b6498588..97041f24cd2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -231,11 +231,10 @@ void tcp_select_initial_window(int __space, __u32 mss, /* when initializing use the value from init_rcv_wnd * rather than the default from above */ - if (init_rcv_wnd && - (*rcv_wnd > init_rcv_wnd * mss)) - *rcv_wnd = init_rcv_wnd * mss; - else if (*rcv_wnd > init_cwnd * mss) - *rcv_wnd = init_cwnd * mss; + if (init_rcv_wnd) + *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); + else + *rcv_wnd = min(*rcv_wnd, init_cwnd * mss); } /* Set the clamp no higher than max representable value */ @@ -386,27 +385,30 @@ struct tcp_out_options { */ static u8 tcp_cookie_size_check(u8 desired) { - if (desired > 0) { + int cookie_size; + + if (desired > 0) /* previously specified */ return desired; - } - if (sysctl_tcp_cookie_size <= 0) { + + cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size); + if (cookie_size <= 0) /* no default specified */ return 0; - } - if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) { + + if (cookie_size <= TCP_COOKIE_MIN) /* value too small, specify minimum */ return TCP_COOKIE_MIN; - } - if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) { + + if (cookie_size >= TCP_COOKIE_MAX) /* value too large, specify maximum */ return TCP_COOKIE_MAX; - } - if (0x1 & sysctl_tcp_cookie_size) { + + if (cookie_size & 1) /* 8-bit multiple, illegal, fix it */ - return (u8)(sysctl_tcp_cookie_size + 0x1); - } - return (u8)sysctl_tcp_cookie_size; + cookie_size++; + + return (u8)cookie_size; } /* Write previously computed TCP options to the packet. @@ -1516,6 +1518,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; + int win_divisor; if (TCP_SKB_CB(skb)->flags & TCPHDR_FIN) goto send_now; @@ -1547,13 +1550,14 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; - if (sysctl_tcp_tso_win_divisor) { + win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); + if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ - chunk /= sysctl_tcp_tso_win_divisor; + chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b1155554bb1..4f4483e697b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1173,6 +1173,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) sizeof (struct ipv6hdr); dev->mtu = rt->rt6i_dev->mtu - sizeof (struct ipv6hdr); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu-=8; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; @@ -1361,12 +1363,17 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { + struct ip6_tnl *t; + dev->netdev_ops = &ip6_tnl_netdev_ops; dev->destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr); + t = netdev_priv(dev); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu-=8; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index e18f8413020..2342545a5ee 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1259,7 +1259,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; if (rt) - rt->dst.metrics[RTAX_HOPLIMIT-1] = ra_msg->icmph.icmp6_hop_limit; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } skip_defrtr: @@ -1377,7 +1378,7 @@ skip_linkparms: in6_dev->cnf.mtu6 = mtu; if (rt) - rt->dst.metrics[RTAX_MTU-1] = mtu; + dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 026caef0326..4aed0812b51 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -129,7 +129,6 @@ static struct rt6_info ip6_null_entry_template = { .__use = 1, .obsolete = -1, .error = -ENETUNREACH, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, }, @@ -150,7 +149,6 @@ static struct rt6_info ip6_prohibit_entry_template = { .__use = 1, .obsolete = -1, .error = -EACCES, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, }, @@ -166,7 +164,6 @@ static struct rt6_info ip6_blk_hole_entry_template = { .__use = 1, .obsolete = -1, .error = -EINVAL, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, .input = dst_discard, .output = dst_discard, }, @@ -844,7 +841,7 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl new->input = dst_discard; new->output = dst_discard; - memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + dst_copy_metrics(new, &ort->dst); new->dev = ort->dst.dev; if (new->dev) dev_hold(new->dev); @@ -928,10 +925,12 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; if (mtu < IPV6_MIN_MTU) { + u32 features = dst_metric(dst, RTAX_FEATURES); mtu = IPV6_MIN_MTU; - dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + features |= RTAX_FEATURE_ALLFRAG; + dst_metric_set(dst, RTAX_FEATURES, features); } - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } } @@ -989,9 +988,9 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->rt6i_idev = idev; rt->rt6i_nexthop = neigh; atomic_set(&rt->dst.__refcnt, 1); - rt->dst.metrics[RTAX_HOPLIMIT-1] = 255; - rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); + dst_metric_set(&rt->dst, RTAX_MTU, ipv6_get_mtu(rt->rt6i_dev)); + dst_metric_set(&rt->dst, RTAX_ADVMSS, ipv6_advmss(net, dst_mtu(&rt->dst))); rt->dst.output = ip6_output; #if 0 /* there's no chance to use these for ndisc */ @@ -1305,17 +1304,17 @@ install_route: goto out; } - rt->dst.metrics[type - 1] = nla_get_u32(nla); + dst_metric_set(&rt->dst, type, nla_get_u32(nla)); } } } if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0) - rt->dst.metrics[RTAX_HOPLIMIT-1] = -1; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1); if (!dst_mtu(&rt->dst)) - rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev); + dst_metric_set(&rt->dst, RTAX_MTU, ipv6_get_mtu(dev)); if (!dst_metric(&rt->dst, RTAX_ADVMSS)) - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); + dst_metric_set(&rt->dst, RTAX_ADVMSS, ipv6_advmss(net, dst_mtu(&rt->dst))); rt->dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; @@ -1541,9 +1540,9 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key); nrt->rt6i_nexthop = neigh_clone(neigh); /* Reset pmtu, it may be better */ - nrt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); - nrt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev), - dst_mtu(&nrt->dst)); + dst_metric_set(&nrt->dst, RTAX_MTU, ipv6_get_mtu(neigh->dev)); + dst_metric_set(&nrt->dst, RTAX_ADVMSS, ipv6_advmss(dev_net(neigh->dev), + dst_mtu(&nrt->dst))); if (ip6_ins_rt(nrt)) goto out; @@ -1602,9 +1601,12 @@ static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, would return automatically. */ if (rt->rt6i_flags & RTF_CACHE) { - rt->dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - rt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + dst_metric_set(&rt->dst, RTAX_MTU, pmtu); + if (allfrag) { + u32 features = dst_metric(&rt->dst, RTAX_FEATURES); + features |= RTAX_FEATURE_ALLFRAG; + dst_metric_set(&rt->dst, RTAX_FEATURES, features); + } dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES; goto out; @@ -1621,9 +1623,12 @@ static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, nrt = rt6_alloc_clone(rt, daddr); if (nrt) { - nrt->dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - nrt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + dst_metric_set(&nrt->dst, RTAX_MTU, pmtu); + if (allfrag) { + u32 features = dst_metric(&nrt->dst, RTAX_FEATURES); + features |= RTAX_FEATURE_ALLFRAG; + dst_metric_set(&nrt->dst, RTAX_FEATURES, features); + } /* According to RFC 1981, detecting PMTU increase shouldn't be * happened within 5 mins, the recommended timer is 10 mins. @@ -1674,7 +1679,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) rt->dst.input = ort->dst.input; rt->dst.output = ort->dst.output; - memcpy(rt->dst.metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + dst_copy_metrics(&rt->dst, &ort->dst); rt->dst.error = ort->dst.error; rt->dst.dev = ort->dst.dev; if (rt->dst.dev) @@ -1966,9 +1971,9 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->dst.output = ip6_output; rt->rt6i_dev = net->loopback_dev; rt->rt6i_idev = idev; - rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); - rt->dst.metrics[RTAX_HOPLIMIT-1] = -1; + dst_metric_set(&rt->dst, RTAX_MTU, ipv6_get_mtu(rt->rt6i_dev)); + dst_metric_set(&rt->dst, RTAX_ADVMSS, ipv6_advmss(net, dst_mtu(&rt->dst))); + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1); rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; @@ -2068,8 +2073,8 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) (dst_mtu(&rt->dst) >= arg->mtu || (dst_mtu(&rt->dst) < arg->mtu && dst_mtu(&rt->dst) == idev->cnf.mtu6))) { - rt->dst.metrics[RTAX_MTU-1] = arg->mtu; - rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu); + dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); + dst_metric_set(&rt->dst, RTAX_ADVMSS, ipv6_advmss(net, arg->mtu)); } return 0; } @@ -2295,7 +2300,7 @@ static int rt6_fill_node(struct net *net, NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } - if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; if (rt->dst.neighbour) @@ -2686,6 +2691,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2696,6 +2702,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_prohibit_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -2705,6 +2712,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_blk_hole_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255); #endif net->ipv6.sysctl.flush_delay = 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 6e48a80d0f2..8ce38f10a54 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -606,8 +606,9 @@ static int ipip6_rcv(struct sk_buff *skb) return 0; } - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + /* no tunnel matched, let upstream know, ipsec may handle it */ rcu_read_unlock(); + return 1; out: kfree_skb(skb); return 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b541a4e009f..7aad1277086 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -54,8 +54,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - __be32 sk1_rcv_saddr = inet_sk(sk)->inet_rcv_saddr; - __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); + __be32 sk1_rcv_saddr = sk_rcv_saddr(sk); + __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); int addr_type = ipv6_addr_type(sk_rcv_saddr6); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 04635e88e8e..110efb704c9 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -672,4 +672,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman "); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, SOCK_DGRAM, IPPROTO_L2TP); + +/* Use the value of SOCK_DGRAM (2) directory, because __stringify does't like + * enums + */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 58261299821..dfd3a648a55 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -316,9 +316,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (unlikely(addr->sllc_family != AF_LLC)) goto out; rc = -ENODEV; - rtnl_lock(); + rcu_read_lock(); if (sk->sk_bound_dev_if) { - llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { if (!addr->sllc_arphrd) addr->sllc_arphrd = llc->dev->type; @@ -329,14 +329,15 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) !llc_mac_match(addr->sllc_mac, llc->dev->dev_addr)) { rc = -EINVAL; - dev_put(llc->dev); llc->dev = NULL; } } } else - llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd, + llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); - rtnl_unlock(); + if (llc->dev) + dev_hold(llc->dev); + rcu_read_unlock(); if (!llc->dev) goto out; if (!addr->sllc_sap) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 422705d62b5..246a04a1323 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -167,7 +167,6 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, #define PGV_FROM_VMALLOC 1 struct pgv { char *buffer; - unsigned char flags; }; struct packet_ring_buffer { @@ -224,6 +223,13 @@ struct packet_skb_cb { #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) +static inline __pure struct page *pgv_to_page(void *addr) +{ + if (is_vmalloc_addr(addr)) + return vmalloc_to_page(addr); + return virt_to_page(addr); +} + static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union { @@ -236,11 +242,11 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) switch (po->tp_version) { case TPACKET_V1: h.h1->tp_status = status; - flush_dcache_page(virt_to_page(&h.h1->tp_status)); + flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: h.h2->tp_status = status; - flush_dcache_page(virt_to_page(&h.h2->tp_status)); + flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; default: pr_err("TPACKET version not supported\n"); @@ -263,10 +269,10 @@ static int __packet_get_status(struct packet_sock *po, void *frame) h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - flush_dcache_page(virt_to_page(&h.h1->tp_status)); + flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return h.h1->tp_status; case TPACKET_V2: - flush_dcache_page(virt_to_page(&h.h2->tp_status)); + flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return h.h2->tp_status; default: pr_err("TPACKET version not supported\n"); @@ -511,7 +517,8 @@ out_free: return err; } -static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk, +static inline unsigned int run_filter(const struct sk_buff *skb, + const struct sock *sk, unsigned int res) { struct sk_filter *filter; @@ -526,15 +533,15 @@ static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk, } /* - This function makes lazy skb cloning in hope that most of packets - are discarded by BPF. - - Note tricky part: we DO mangle shared skb! skb->data, skb->len - and skb->cb are mangled. It works because (and until) packets - falling here are owned by current CPU. Output packets are cloned - by dev_queue_xmit_nit(), input packets are processed by net_bh - sequencially, so that if we return skb to original state on exit, - we will not harm anyone. + * This function makes lazy skb cloning in hope that most of packets + * are discarded by BPF. + * + * Note tricky part: we DO mangle shared skb! skb->data, skb->len + * and skb->cb are mangled. It works because (and until) packets + * falling here are owned by current CPU. Output packets are cloned + * by dev_queue_xmit_nit(), input packets are processed by net_bh + * sequencially, so that if we return skb to original state on exit, + * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, @@ -560,11 +567,11 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, if (dev->header_ops) { /* The device has an explicit notion of ll header, - exported to higher levels. - - Otherwise, the device hides datails of it frame - structure, so that corresponding packet head - never delivered to user. + * exported to higher levels. + * + * Otherwise, the device hides details of its frame + * structure, so that corresponding packet head is + * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); @@ -799,17 +806,15 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, __packet_set_status(po, h.raw, status); smp_mb(); +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 { - struct page *p_start, *p_end; - u8 *h_end = h.raw + macoff + snaplen - 1; - - p_start = virt_to_page(h.raw); - p_end = virt_to_page(h_end); - while (p_start <= p_end) { - flush_dcache_page(p_start); - p_start++; - } + u8 *start, *end; + + end = (u8 *)PAGE_ALIGN((unsigned long)h.raw + macoff + snaplen); + for (start = h.raw; start < end; start += PAGE_SIZE) + flush_dcache_page(pgv_to_page(start)); } +#endif sk->sk_data_ready(sk, 0); @@ -915,7 +920,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, } err = -EFAULT; - page = virt_to_page(data); offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); @@ -934,11 +938,11 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, return -EFAULT; } + page = pgv_to_page(data); + data += len; flush_dcache_page(page); get_page(page); - skb_fill_page_desc(skb, - nr_frags, - page++, offset, len); + skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; @@ -2340,7 +2344,7 @@ static void free_pg_vec(struct pgv *pg_vec, unsigned int order, for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { - if (pg_vec[i].flags & PGV_FROM_VMALLOC) + if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, @@ -2351,8 +2355,7 @@ static void free_pg_vec(struct pgv *pg_vec, unsigned int order, kfree(pg_vec); } -static inline char *alloc_one_pg_vec_page(unsigned long order, - unsigned char *flags) +static inline char *alloc_one_pg_vec_page(unsigned long order) { char *buffer = NULL; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | @@ -2366,7 +2369,6 @@ static inline char *alloc_one_pg_vec_page(unsigned long order, /* * __get_free_pages failed, fall back to vmalloc */ - *flags |= PGV_FROM_VMALLOC; buffer = vzalloc((1 << order) * PAGE_SIZE); if (buffer) @@ -2375,7 +2377,6 @@ static inline char *alloc_one_pg_vec_page(unsigned long order, /* * vmalloc failed, lets dig into swap here */ - *flags = 0; gfp_flags &= ~__GFP_NORETRY; buffer = (char *)__get_free_pages(gfp_flags, order); if (buffer) @@ -2398,8 +2399,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) goto out; for (i = 0; i < block_nr; i++) { - pg_vec[i].buffer = alloc_one_pg_vec_page(order, - &pg_vec[i].flags); + pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } @@ -2409,7 +2409,6 @@ out: out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); - kfree(pg_vec); pg_vec = NULL; goto out; } @@ -2583,13 +2582,8 @@ static int packet_mmap(struct file *file, struct socket *sock, void *kaddr = rb->pg_vec[i].buffer; int pg_num; - for (pg_num = 0; pg_num < rb->pg_vec_pages; - pg_num++) { - if (rb->pg_vec[i].flags & PGV_FROM_VMALLOC) - page = vmalloc_to_page(kaddr); - else - page = virt_to_page(kaddr); - + for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { + page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6bd554323a3..842c7f3650b 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6047,7 +6047,7 @@ static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, * will suddenly eat the receive_queue. * * Look at current nfs client by the way... - * However, this function was corrent in any case. 8) + * However, this function was correct in any case. 8) */ if (flags & MSG_PEEK) { spin_lock_bh(&sk->sk_receive_queue.lock); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7ff31c60186..417d7a6c36c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1344,9 +1344,25 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +#define MAX_RECURSION_LEVEL 4 + static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) { int i; + unsigned char max_level = 0; + int unix_sock_count = 0; + + for (i = scm->fp->count - 1; i >= 0; i--) { + struct sock *sk = unix_get_socket(scm->fp->fp[i]); + + if (sk) { + unix_sock_count++; + max_level = max(max_level, + unix_sk(sk)->recursion_level); + } + } + if (unlikely(max_level > MAX_RECURSION_LEVEL)) + return -ETOOMANYREFS; /* * Need to duplicate file references for the sake of garbage @@ -1357,9 +1373,11 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - for (i = scm->fp->count-1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - return 0; + if (unix_sock_count) { + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->fp[i]); + } + return max_level; } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -1394,6 +1412,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sk_buff *skb; long timeo; struct scm_cookie tmp_scm; + int max_level; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1432,8 +1451,9 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, goto out; err = unix_scm_to_skb(siocb->scm, skb, true); - if (err) + if (err < 0) goto out_free; + max_level = err + 1; unix_get_secdata(siocb->scm, skb); skb_reset_transport_header(skb); @@ -1515,6 +1535,8 @@ restart: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); skb_queue_tail(&other->sk_receive_queue, skb); + if (max_level > unix_sk(other)->recursion_level) + unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); other->sk_data_ready(other, len); sock_put(other); @@ -1545,6 +1567,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, int sent = 0; struct scm_cookie tmp_scm; bool fds_sent = false; + int max_level; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1608,10 +1631,11 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, /* Only send the fds in the first buffer */ err = unix_scm_to_skb(siocb->scm, skb, !fds_sent); - if (err) { + if (err < 0) { kfree_skb(skb); goto out_err; } + max_level = err + 1; fds_sent = true; err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); @@ -1627,6 +1651,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, goto pipe_err_free; skb_queue_tail(&other->sk_receive_queue, skb); + if (max_level > unix_sk(other)->recursion_level) + unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); other->sk_data_ready(other, size); sent += size; @@ -1847,6 +1873,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, unix_state_lock(sk); skb = skb_dequeue(&sk->sk_receive_queue); if (skb == NULL) { + unix_sk(sk)->recursion_level = 0; if (copied >= target) goto unlock; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index c8df6fda0b1..f89f83bf828 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -96,7 +96,7 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); unsigned int unix_tot_inflight; -static struct sock *unix_get_socket(struct file *filp) +struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; struct inode *inode = filp->f_path.dentry->d_inode; @@ -259,9 +259,16 @@ static void inc_inflight_move_tail(struct unix_sock *u) } static bool gc_in_progress = false; +#define UNIX_INFLIGHT_TRIGGER_GC 16000 void wait_for_unix_gc(void) { + /* + * If number of inflight sockets is insane, + * force a garbage collect right now. + */ + if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress) + unix_gc(); wait_event(unix_gc_wait, gc_in_progress == false); } diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 4c81f6abb65..4cbc942f762 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -398,6 +398,7 @@ void __exit x25_link_free(void) list_for_each_safe(entry, tmp, &x25_neigh_list) { nb = list_entry(entry, struct x25_neigh, node); __x25_remove_neigh(nb); + dev_put(nb->dev); } write_unlock_bh(&x25_neigh_list_lock); } diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c index a2023ec5232..1e98bc0fe0a 100644 --- a/net/xfrm/xfrm_hash.c +++ b/net/xfrm/xfrm_hash.c @@ -19,7 +19,7 @@ struct hlist_head *xfrm_hash_alloc(unsigned int sz) if (sz <= PAGE_SIZE) n = kzalloc(sz, GFP_KERNEL); else if (hashdist) - n = __vmalloc(sz, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); + n = vzalloc(sz); else n = (struct hlist_head *) __get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 044e7789851..6e50ccd8c53 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1433,7 +1433,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, } xdst->route = dst; - memcpy(&dst1->metrics, &dst->metrics, sizeof(dst->metrics)); + dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { family = xfrm[i]->props.family; @@ -2271,7 +2271,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst) if (pmtu > route_mtu_cached) pmtu = route_mtu_cached; - dst->metrics[RTAX_MTU-1] = pmtu; + dst_metric_set(dst, RTAX_MTU, pmtu); } while ((dst = dst->next)); } @@ -2349,7 +2349,7 @@ static int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, mtu = xfrm_state_mtu(dst->xfrm, mtu); if (mtu > last->route_mtu_cached) mtu = last->route_mtu_cached; - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); if (last == first) break;