diff options
52 files changed, 392 insertions, 239 deletions
@@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 8 -SUBLEVEL = 7 +SUBLEVEL = 8 EXTRAVERSION = -gnu NAME = Psychotic Stoned Sheep diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index ee655ed1f..1e8fceb30 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -53,10 +53,8 @@ static inline __sum16 csum_fold(__wsum sum) return (__force __sum16)(~((__force u32)sum + tmp) >> 16); } -static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, - unsigned short len, - unsigned short proto, - __wsum sum) +static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) { #ifdef __powerpc64__ unsigned long s = (__force u32)sum; @@ -83,10 +81,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, * computes the checksum of the TCP/UDP pseudo-header * returns a 16-bit checksum, already complemented */ -static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, - unsigned short len, - unsigned short proto, - __wsum sum) +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) { return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); } diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 277b112b8..48145be75 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -41,7 +41,7 @@ config CFQ_GROUP_IOSCHED config IOSCHED_BFQ tristate "BFQ I/O scheduler" - default n + default y ---help--- The BFQ I/O scheduler distributes bandwidth among all processes according to their weights, regardless of the @@ -57,7 +57,7 @@ config BFQ_GROUP_IOSCHED choice prompt "Default I/O scheduler" - default DEFAULT_CFQ + default DEFAULT_BFQ help Select the I/O scheduler which will be used by default for all block devices. diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 9dbfcc0ab..5ff64afd6 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -63,6 +63,8 @@ enum ipoib_flush_level { enum { IPOIB_ENCAP_LEN = 4, + IPOIB_PSEUDO_LEN = 20, + IPOIB_HARD_LEN = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN, IPOIB_UD_HEAD_SIZE = IB_GRH_BYTES + IPOIB_ENCAP_LEN, IPOIB_UD_RX_SG = 2, /* max buffer needed for 4K mtu */ @@ -134,15 +136,21 @@ struct ipoib_header { u16 reserved; }; -struct ipoib_cb { - struct qdisc_skb_cb qdisc_cb; - u8 hwaddr[INFINIBAND_ALEN]; +struct ipoib_pseudo_header { + u8 hwaddr[INFINIBAND_ALEN]; }; -static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb) +static inline void skb_add_pseudo_hdr(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb)); - return (struct ipoib_cb *)skb->cb; + char *data = skb_push(skb, IPOIB_PSEUDO_LEN); + + /* + * only the ipoib header is present now, make room for a dummy + * pseudo header and set skb field accordingly + */ + memset(data, 0, IPOIB_PSEUDO_LEN); + skb_reset_mac_header(skb); + skb_pull(skb, IPOIB_HARD_LEN); } /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */ diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 4ad297d3d..339a1eecd 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level, #define IPOIB_CM_RX_DELAY (3 * 256 * HZ) #define IPOIB_CM_RX_UPDATE_MASK (0x3) +#define IPOIB_CM_RX_RESERVE (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN) + static struct ib_qp_attr ipoib_cm_err_attr = { .qp_state = IB_QPS_ERR }; @@ -146,15 +148,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev, struct sk_buff *skb; int i; - skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12); + skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16)); if (unlikely(!skb)) return NULL; /* - * IPoIB adds a 4 byte header. So we need 12 more bytes to align the + * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the * IP header to a multiple of 16. */ - skb_reserve(skb, 12); + skb_reserve(skb, IPOIB_CM_RX_RESERVE); mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE, DMA_FROM_DEVICE); @@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) if (wc->byte_len < IPOIB_CM_COPYBREAK) { int dlen = wc->byte_len; - small_skb = dev_alloc_skb(dlen + 12); + small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE); if (small_skb) { - skb_reserve(small_skb, 12); + skb_reserve(small_skb, IPOIB_CM_RX_RESERVE); ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0], dlen, DMA_FROM_DEVICE); skb_copy_from_linear_data(skb, small_skb->data, dlen); @@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) copied: skb->protocol = ((struct ipoib_header *) skb->data)->proto; - skb_reset_mac_header(skb); - skb_pull(skb, IPOIB_ENCAP_LEN); + skb_add_pseudo_hdr(skb); ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index be11d5d5b..830fecb69 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -128,16 +128,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); - skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN); + skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN); if (unlikely(!skb)) return NULL; /* - * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte - * header. So we need 4 more bytes to get to 48 and align the - * IP header to a multiple of 16. + * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is + * 64 bytes aligned */ - skb_reserve(skb, 4); + skb_reserve(skb, sizeof(struct ipoib_pseudo_header)); mapping = priv->rx_ring[id].mapping; mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size, @@ -253,8 +252,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) skb_pull(skb, IB_GRH_BYTES); skb->protocol = ((struct ipoib_header *) skb->data)->proto; - skb_reset_mac_header(skb); - skb_pull(skb, IPOIB_ENCAP_LEN); + skb_add_pseudo_hdr(skb); ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index cc1c1b062..823a528ef 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -925,9 +925,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, ipoib_neigh_free(neigh); goto err_drop; } - if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) + if (skb_queue_len(&neigh->queue) < + IPOIB_MAX_PATH_REC_QUEUE) { + /* put pseudoheader back on for next time */ + skb_push(skb, IPOIB_PSEUDO_LEN); __skb_queue_tail(&neigh->queue, skb); - else { + } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; @@ -964,7 +967,7 @@ err_drop: } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, - struct ipoib_cb *cb) + struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_path *path; @@ -972,16 +975,18 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, spin_lock_irqsave(&priv->lock, flags); - path = __path_find(dev, cb->hwaddr + 4); + path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->valid) { int new_path = 0; if (!path) { - path = path_rec_create(dev, cb->hwaddr + 4); + path = path_rec_create(dev, phdr->hwaddr + 4); new_path = 1; } if (path) { if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + /* put pseudoheader back on for next time */ + skb_push(skb, IPOIB_PSEUDO_LEN); __skb_queue_tail(&path->queue, skb); } else { ++dev->stats.tx_dropped; @@ -1009,10 +1014,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, be16_to_cpu(path->pathrec.dlid)); spin_unlock_irqrestore(&priv->lock, flags); - ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr)); + ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr)); return; } else if ((path->query || !path_rec_start(dev, path)) && skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + /* put pseudoheader back on for next time */ + skb_push(skb, IPOIB_PSEUDO_LEN); __skb_queue_tail(&path->queue, skb); } else { ++dev->stats.tx_dropped; @@ -1026,13 +1033,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_neigh *neigh; - struct ipoib_cb *cb = ipoib_skb_cb(skb); + struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; + phdr = (struct ipoib_pseudo_header *) skb->data; + skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; - if (unlikely(cb->hwaddr[4] == 0xff)) { + if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && @@ -1045,13 +1054,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ - cb->hwaddr[8] = (priv->pkey >> 8) & 0xff; - cb->hwaddr[9] = priv->pkey & 0xff; + phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; + phdr->hwaddr[9] = priv->pkey & 0xff; - neigh = ipoib_neigh_get(dev, cb->hwaddr); + neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; - ipoib_mcast_send(dev, cb->hwaddr, skb); + ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } @@ -1060,16 +1069,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): - neigh = ipoib_neigh_get(dev, cb->hwaddr); + neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { - neigh_add_path(skb, cb->hwaddr, dev); + neigh_add_path(skb, phdr->hwaddr, dev); return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ - unicast_arp_send(skb, dev, cb); + unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ @@ -1086,11 +1095,13 @@ send_using_neigh: goto unref; } } else if (neigh->ah) { - ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr)); + ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + /* put pseudoheader back on for next time */ + skb_push(skb, sizeof(*phdr)); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); @@ -1122,8 +1133,8 @@ static int ipoib_hard_header(struct sk_buff *skb, unsigned short type, const void *daddr, const void *saddr, unsigned len) { + struct ipoib_pseudo_header *phdr; struct ipoib_header *header; - struct ipoib_cb *cb = ipoib_skb_cb(skb); header = (struct ipoib_header *) skb_push(skb, sizeof *header); @@ -1132,12 +1143,13 @@ static int ipoib_hard_header(struct sk_buff *skb, /* * we don't rely on dst_entry structure, always stuff the - * destination address into skb->cb so we can figure out where + * destination address into skb hard header so we can figure out where * to send the packet later. */ - memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN); + phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr)); + memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); - return sizeof *header; + return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) @@ -1759,7 +1771,7 @@ void ipoib_setup(struct net_device *dev) dev->flags |= IFF_BROADCAST | IFF_MULTICAST; - dev->hard_header_len = IPOIB_ENCAP_LEN; + dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = ipoib_sendq_size * 2; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index d3394b6ad..1909dd252 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -796,9 +796,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) __ipoib_mcast_add(dev, mcast); list_add_tail(&mcast->list, &priv->multicast_list); } - if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) + if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) { + /* put pseudoheader back on for next time */ + skb_push(skb, sizeof(struct ipoib_pseudo_header)); skb_queue_tail(&mcast->pkt_queue, skb); - else { + } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 692ee248e..3474de576 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -913,13 +913,11 @@ fec_restart(struct net_device *ndev) * enet-mac reset will reset mac address registers too, * so need to reconfigure it. */ - if (fep->quirks & FEC_QUIRK_ENET_MAC) { - memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN); - writel((__force u32)cpu_to_be32(temp_mac[0]), - fep->hwp + FEC_ADDR_LOW); - writel((__force u32)cpu_to_be32(temp_mac[1]), - fep->hwp + FEC_ADDR_HIGH); - } + memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN); + writel((__force u32)cpu_to_be32(temp_mac[0]), + fep->hwp + FEC_ADDR_LOW); + writel((__force u32)cpu_to_be32(temp_mac[1]), + fep->hwp + FEC_ADDR_HIGH); /* Clear any outstanding interrupt. */ writel(0xffffffff, fep->hwp + FEC_IEVENT); @@ -1432,14 +1430,14 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) skb_put(skb, pkt_len - 4); data = skb->data; + if (!is_copybreak && need_swap) + swap_buffer(data, pkt_len); + #if !defined(CONFIG_M5272) if (fep->quirks & FEC_QUIRK_HAS_RACC) data = skb_pull_inline(skb, 2); #endif - if (!is_copybreak && need_swap) - swap_buffer(data, pkt_len); - /* Extract the enhanced buffer descriptor */ ebdp = NULL; if (fep->bufdesc_ex) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 132cea655..e3be7e44f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -127,7 +127,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, /* For TX we use the same irq per ring we assigned for the RX */ struct mlx4_en_cq *rx_cq; - + int xdp_index; + + /* The xdp tx irq must align with the rx ring that forwards to + * it, so reindex these from 0. This should only happen when + * tx_ring_num is not a multiple of rx_ring_num. + */ + xdp_index = (priv->xdp_ring_num - priv->tx_ring_num) + cq_idx; + if (xdp_index >= 0) + cq_idx = xdp_index; cq_idx = cq_idx % priv->rx_ring_num; rx_cq = priv->rx_cq[cq_idx]; cq->vector = rx_cq->vector; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 3c20e87bb..16af1ce99 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -453,7 +453,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); - pp = ptype->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out_unlock: diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 3ba29fc80..c4d9653ca 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -624,15 +624,18 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, packet->total_data_buflen); skb->protocol = eth_type_trans(skb, net); - if (csum_info) { - /* We only look at the IP checksum here. - * Should we be dropping the packet if checksum - * failed? How do we deal with other checksums - TCP/UDP? - */ - if (csum_info->receive.ip_checksum_succeeded) + + /* skb is already created with CHECKSUM_NONE */ + skb_checksum_none_assert(skb); + + /* + * In Linux, the IP checksum is always checked. + * Do L4 checksum offload if enabled and present. + */ + if (csum_info && (net->features & NETIF_F_RXCSUM)) { + if (csum_info->receive.tcp_checksum_succeeded || + csum_info->receive.udp_checksum_succeeded) skb->ip_summed = CHECKSUM_UNNECESSARY; - else - skb->ip_summed = CHECKSUM_NONE; } if (vlan_tci & VLAN_TAG_PRESENT) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 351e701eb..b72ddc61e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -397,6 +397,14 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) #define DEFAULT_ENCRYPT false #define DEFAULT_ENCODING_SA 0 +static bool send_sci(const struct macsec_secy *secy) +{ + const struct macsec_tx_sc *tx_sc = &secy->tx_sc; + + return tx_sc->send_sci || + (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb); +} + static sci_t make_sci(u8 *addr, __be16 port) { sci_t sci; @@ -437,15 +445,15 @@ static unsigned int macsec_extra_len(bool sci_present) /* Fill SecTAG according to IEEE 802.1AE-2006 10.5.3 */ static void macsec_fill_sectag(struct macsec_eth_header *h, - const struct macsec_secy *secy, u32 pn) + const struct macsec_secy *secy, u32 pn, + bool sci_present) { const struct macsec_tx_sc *tx_sc = &secy->tx_sc; - memset(&h->tci_an, 0, macsec_sectag_len(tx_sc->send_sci)); + memset(&h->tci_an, 0, macsec_sectag_len(sci_present)); h->eth.h_proto = htons(ETH_P_MACSEC); - if (tx_sc->send_sci || - (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb)) { + if (sci_present) { h->tci_an |= MACSEC_TCI_SC; memcpy(&h->secure_channel_id, &secy->sci, sizeof(h->secure_channel_id)); @@ -650,6 +658,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; struct macsec_dev *macsec = macsec_priv(dev); + bool sci_present; u32 pn; secy = &macsec->secy; @@ -687,7 +696,8 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, unprotected_len = skb->len; eth = eth_hdr(skb); - hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(tx_sc->send_sci)); + sci_present = send_sci(secy); + hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(sci_present)); memmove(hh, eth, 2 * ETH_ALEN); pn = tx_sa_update_pn(tx_sa, secy); @@ -696,7 +706,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, kfree_skb(skb); return ERR_PTR(-ENOLINK); } - macsec_fill_sectag(hh, secy, pn); + macsec_fill_sectag(hh, secy, pn, sci_present); macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN); skb_put(skb, secy->icv_len); @@ -726,10 +736,10 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, skb_to_sgvec(skb, sg, 0, skb->len); if (tx_sc->encrypt) { - int len = skb->len - macsec_hdr_len(tx_sc->send_sci) - + int len = skb->len - macsec_hdr_len(sci_present) - secy->icv_len; aead_request_set_crypt(req, sg, sg, len, iv); - aead_request_set_ad(req, macsec_hdr_len(tx_sc->send_sci)); + aead_request_set_ad(req, macsec_hdr_len(sci_present)); } else { aead_request_set_crypt(req, sg, sg, 0, iv); aead_request_set_ad(req, skb->len - secy->icv_len); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index c6f66832a..f424b867f 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -608,6 +608,21 @@ void phy_start_machine(struct phy_device *phydev) } /** + * phy_trigger_machine - trigger the state machine to run + * + * @phydev: the phy_device struct + * + * Description: There has been a change in state which requires that the + * state machine runs. + */ + +static void phy_trigger_machine(struct phy_device *phydev) +{ + cancel_delayed_work_sync(&phydev->state_queue); + queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0); +} + +/** * phy_stop_machine - stop the PHY state machine tracking * @phydev: target phy_device struct * @@ -639,6 +654,8 @@ static void phy_error(struct phy_device *phydev) mutex_lock(&phydev->lock); phydev->state = PHY_HALTED; mutex_unlock(&phydev->lock); + + phy_trigger_machine(phydev); } /** @@ -800,8 +817,7 @@ void phy_change(struct work_struct *work) } /* reschedule state queue work to run as soon as possible */ - cancel_delayed_work_sync(&phydev->state_queue); - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0); + phy_trigger_machine(phydev); return; ignore: @@ -890,6 +906,8 @@ void phy_start(struct phy_device *phydev) /* if phy was suspended, bring the physical link up again */ if (do_resume) phy_resume(phydev); + + phy_trigger_machine(phydev); } EXPORT_SYMBOL(phy_start); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 6e6583205..5ae664c02 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -584,7 +584,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, } } - pp = eth_gro_receive(head, skb); + pp = call_gro_receive(eth_gro_receive, head, skb); flush = 0; out: diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index d637c933c..58a97d420 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -193,6 +193,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) if (err) break; + memset(&precise_offset, 0, sizeof(precise_offset)); ts = ktime_to_timespec64(xtstamp.device); precise_offset.device.sec = ts.tv_sec; precise_offset.device.nsec = ts.tv_nsec; diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index ca86c885d..3aaea713b 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2233,7 +2233,7 @@ struct megasas_instance_template { }; #define MEGASAS_IS_LOGICAL(scp) \ - (scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1 + ((scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1) #define MEGASAS_DEV_INDEX(scp) \ (((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \ diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index c1ed25adb..71e489937 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -1713,16 +1713,13 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) goto out_done; } - switch (scmd->cmnd[0]) { - case SYNCHRONIZE_CACHE: - /* - * FW takes care of flush cache on its own - * No need to send it down - */ + /* + * FW takes care of flush cache on its own for Virtual Disk. + * No need to send it down for VD. For JBOD send SYNCHRONIZE_CACHE to FW. + */ + if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) && MEGASAS_IS_LOGICAL(scmd)) { scmd->result = DID_OK << 16; goto out_done; - default: - break; } return instance->instancet->build_and_issue_cmd(instance, scmd); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 6443cfba7..dc3b5962d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -789,6 +789,7 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep, req->trb = trb; req->trb_dma = dwc3_trb_dma_offset(dep, trb); req->first_trb_index = dep->trb_enqueue; + dep->queued_requests++; } dwc3_ep_inc_enq(dep); @@ -841,8 +842,6 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep, trb->ctrl |= DWC3_TRB_CTRL_HWO; - dep->queued_requests++; - trace_dwc3_prepare_trb(dep, trb); } @@ -1963,7 +1962,9 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, unsigned int s_pkt = 0; unsigned int trb_status; - dep->queued_requests--; + if (req->trb == trb) + dep->queued_requests--; + trace_dwc3_complete_trb(dep, trb); /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e8d79d4eb..e942c67ea 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2154,7 +2154,10 @@ struct napi_gro_cb { /* Used to determine if flush_id can be ignored */ u8 is_atomic:1; - /* 5 bit hole */ + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; + + /* 1 bit hole */ /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -2165,6 +2168,40 @@ struct napi_gro_cb { #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) +#define GRO_RECURSION_LIMIT 15 +static inline int gro_recursion_inc_test(struct sk_buff *skb) +{ + return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; +} + +typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); +static inline struct sk_buff **call_gro_receive(gro_receive_t cb, + struct sk_buff **head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(head, skb); +} + +typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **, + struct sk_buff *); +static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct sk_buff **head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(sk, head, skb); +} + struct packet_type { __be16 type; /* This is really htons(ether_type). */ struct net_device *dev; /* NULL is wildcarded here */ @@ -3862,7 +3899,7 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, ldev = netdev_all_lower_get_next(dev, &(iter))) #define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \ - for (iter = (dev)->all_adj_list.lower.next, \ + for (iter = &(dev)->all_adj_list.lower, \ ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \ ldev; \ ldev = netdev_all_lower_get_next_rcu(dev, &(iter))) diff --git a/include/net/ip.h b/include/net/ip.h index 9742b92dc..156b0c11b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -549,7 +549,7 @@ int ip_options_rcv_srr(struct sk_buff *skb); */ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); -void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset); +void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6); int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, @@ -571,7 +571,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { - ip_cmsg_recv_offset(msg, skb, 0); + ip_cmsg_recv_offset(msg, skb, 0, 0); } bool icmp_global_allow(void); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index d97305d0e..0a2d27012 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -32,6 +32,7 @@ struct route_info { #define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008 #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 +#define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 262f0379d..5a78be518 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -350,7 +350,7 @@ struct rtnexthop { #define RTNH_F_OFFLOAD 8 /* offloaded route */ #define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */ -#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN) +#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD) /* Macros to handle hexthops */ diff --git a/kernel/sched/MuQSS.c b/kernel/sched/MuQSS.c index 7c4ddc734..e256bd60a 100644 --- a/kernel/sched/MuQSS.c +++ b/kernel/sched/MuQSS.c @@ -137,7 +137,7 @@ void print_scheduler_version(void) { - printk(KERN_INFO "MuQSS CPU scheduler v0.120 by Con Kolivas.\n"); + printk(KERN_INFO "MuQSS CPU scheduler v0.140 by Con Kolivas.\n"); } /* @@ -3507,6 +3507,12 @@ static inline struct task_struct * is locked so entries will always be accurate. */ if (!sched_interactive) { + /* + * Don't reschedule balance across nodes unless the CPU + * is idle. + */ + if (edt != idle && rq->cpu_locality[other_rq->cpu] > 3) + break; if (entries <= best_entries) continue; } else if (!entries) @@ -3531,8 +3537,8 @@ static inline struct task_struct key = other_rq->node.next[0]->key; /* Reevaluate key after locking */ if (unlikely(key >= best_key)) { - if (i) - unlock_rq(other_rq); + /* This will always be when rq != other_rq */ + unlock_rq(other_rq); continue; } @@ -3806,13 +3812,8 @@ static void __sched notrace __schedule(bool preempt) struct task_struct *to_wakeup; to_wakeup = wq_worker_sleeping(prev); - if (to_wakeup) { - /* This shouldn't happen, but does */ - if (WARN_ONCE((to_wakeup == prev), "Waking up prev as worker\n")) - deactivate = false; - else - try_to_wake_up_local(to_wakeup); - } + if (to_wakeup) + try_to_wake_up_local(to_wakeup); } } switch_count = &prev->nvcsw; @@ -4869,13 +4870,11 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) struct task_struct *p; int retval; - get_online_cpus(); rcu_read_lock(); p = find_process_by_pid(pid); if (!p) { rcu_read_unlock(); - put_online_cpus(); return -ESRCH; } @@ -4932,7 +4931,6 @@ out_free_cpus_allowed: free_cpumask_var(cpus_allowed); out_put_task: put_task_struct(p); - put_online_cpus(); return retval; } @@ -5526,6 +5524,7 @@ void init_idle(struct task_struct *idle, int cpu) init_idle_preempt_count(idle, cpu); ftrace_graph_init_idle_task(idle, cpu); + vtime_init_idle(idle, cpu); #ifdef CONFIG_SMP sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif @@ -5692,16 +5691,16 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask, bool check) { const struct cpumask *cpu_valid_mask = cpu_active_mask; - bool running_wrong = false; + bool queued = false, running_wrong = false, kthread; struct cpumask old_mask; - bool queued = false; unsigned long flags; struct rq *rq; int ret = 0; rq = task_rq_lock(p, &flags); - if (p->flags & PF_KTHREAD) { + kthread = !!(p->flags & PF_KTHREAD); + if (kthread) { /* * Kernel threads are allowed on online && !active CPUs */ @@ -5730,7 +5729,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, _do_set_cpus_allowed(p, new_mask); - if (p->flags & PF_KTHREAD) { + if (kthread) { /* * For kernel threads that do indeed end up on online && * !active we want to ensure they are strict per-cpu threads. @@ -5748,7 +5747,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, /* Task is running on the wrong cpu now, reschedule it. */ if (rq == this_rq()) { set_tsk_need_resched(p); - running_wrong = true; + running_wrong = kthread; } else resched_task(p); } else { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 96db64bde..e2e71587f 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1464,7 +1464,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base) * Check, if the next hrtimer event is before the next timer wheel * event: */ -static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) +static u64 cmp_next_hrtimer_event(struct timer_base *base, u64 basem, u64 expires) { u64 nextevt = hrtimer_get_next_event(); @@ -1482,6 +1482,9 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) if (nextevt <= basem) return basem; + if (nextevt < expires && nextevt - basem <= TICK_NSEC) + base->is_idle = false; + /* * Round up to the next jiffie. High resolution timers are * off, so the hrtimers are expired in the tick and we need to @@ -1545,7 +1548,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) } spin_unlock(&base->lock); - return cmp_next_hrtimer_event(basem, expires); + return cmp_next_hrtimer_event(base, basem, expires); } /** diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 8de138d33..f2531ad66 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -664,7 +664,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*vhdr)); skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr)); - pp = ptype->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index c5fea9393..2136e45f5 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -972,13 +972,12 @@ static void br_multicast_enable(struct bridge_mcast_own_query *query) mod_timer(&query->timer, jiffies); } -void br_multicast_enable_port(struct net_bridge_port *port) +static void __br_multicast_enable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; - spin_lock(&br->multicast_lock); if (br->multicast_disabled || !netif_running(br->dev)) - goto out; + return; br_multicast_enable(&port->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) @@ -987,8 +986,14 @@ void br_multicast_enable_port(struct net_bridge_port *port) if (port->multicast_router == MDB_RTR_TYPE_PERM && hlist_unhashed(&port->rlist)) br_multicast_add_router(br, port); +} -out: +void br_multicast_enable_port(struct net_bridge_port *port) +{ + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + __br_multicast_enable_port(port); spin_unlock(&br->multicast_lock); } @@ -1994,8 +1999,9 @@ static void br_multicast_start_querier(struct net_bridge *br, int br_multicast_toggle(struct net_bridge *br, unsigned long val) { - int err = 0; struct net_bridge_mdb_htable *mdb; + struct net_bridge_port *port; + int err = 0; spin_lock_bh(&br->multicast_lock); if (br->multicast_disabled == !val) @@ -2023,10 +2029,9 @@ rollback: goto rollback; } - br_multicast_start_querier(br, &br->ip4_own_query); -#if IS_ENABLED(CONFIG_IPV6) - br_multicast_start_querier(br, &br->ip6_own_query); -#endif + br_multicast_open(br); + list_for_each_entry(port, &br->port_list, list) + __br_multicast_enable_port(port); unlock: spin_unlock_bh(&br->multicast_lock); diff --git a/net/core/dev.c b/net/core/dev.c index ea6312057..44b3ba462 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3035,6 +3035,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d } return head; } +EXPORT_SYMBOL_GPL(validate_xmit_skb_list); static void qdisc_pkt_len_init(struct sk_buff *skb) { @@ -4496,6 +4497,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; NAPI_GRO_CB(skb)->encap_mark = 0; + NAPI_GRO_CB(skb)->recursion_counter = 0; NAPI_GRO_CB(skb)->is_fou = 0; NAPI_GRO_CB(skb)->is_atomic = 1; NAPI_GRO_CB(skb)->gro_remcsum_start = 0; @@ -5500,10 +5502,14 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, { struct netdev_adjacent *lower; - lower = list_first_or_null_rcu(&dev->all_adj_list.lower, - struct netdev_adjacent, list); + lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->all_adj_list.lower) + return NULL; + + *iter = &lower->list; - return lower ? lower->dev : NULL; + return lower->dev; } EXPORT_SYMBOL(netdev_all_lower_get_next_rcu); @@ -5578,6 +5584,7 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, + u16 ref_nr, struct list_head *dev_list, void *private, bool master) { @@ -5587,7 +5594,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { - adj->ref_nr++; + adj->ref_nr += ref_nr; return 0; } @@ -5597,7 +5604,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->dev = adj_dev; adj->master = master; - adj->ref_nr = 1; + adj->ref_nr = ref_nr; adj->private = private; dev_hold(adj_dev); @@ -5636,6 +5643,7 @@ free_adj: static void __netdev_adjacent_dev_remove(struct net_device *dev, struct net_device *adj_dev, + u16 ref_nr, struct list_head *dev_list) { struct netdev_adjacent *adj; @@ -5648,10 +5656,10 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, BUG(); } - if (adj->ref_nr > 1) { - pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name, - adj->ref_nr-1); - adj->ref_nr--; + if (adj->ref_nr > ref_nr) { + pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name, + ref_nr, adj->ref_nr-ref_nr); + adj->ref_nr -= ref_nr; return; } @@ -5670,21 +5678,22 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, + u16 ref_nr, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; - ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, - master); + ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list, + private, master); if (ret) return ret; - ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, - false); + ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list, + private, false); if (ret) { - __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); return ret; } @@ -5692,9 +5701,10 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev, } static int __netdev_adjacent_dev_link(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + u16 ref_nr) { - return __netdev_adjacent_dev_link_lists(dev, upper_dev, + return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr, &dev->all_adj_list.upper, &upper_dev->all_adj_list.lower, NULL, false); @@ -5702,17 +5712,19 @@ static int __netdev_adjacent_dev_link(struct net_device *dev, static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, + u16 ref_nr, struct list_head *up_list, struct list_head *down_list) { - __netdev_adjacent_dev_remove(dev, upper_dev, up_list); - __netdev_adjacent_dev_remove(upper_dev, dev, down_list); + __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); + __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } static void __netdev_adjacent_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + u16 ref_nr) { - __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr, &dev->all_adj_list.upper, &upper_dev->all_adj_list.lower); } @@ -5721,17 +5733,17 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { - int ret = __netdev_adjacent_dev_link(dev, upper_dev); + int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1); if (ret) return ret; - ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, + ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower, private, master); if (ret) { - __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink(dev, upper_dev, 1); return ret; } @@ -5741,8 +5753,8 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { - __netdev_adjacent_dev_unlink(dev, upper_dev); - __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + __netdev_adjacent_dev_unlink(dev, upper_dev, 1); + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); } @@ -5795,7 +5807,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { pr_debug("Interlinking %s with %s, non-neighbour\n", i->dev->name, j->dev->name); - ret = __netdev_adjacent_dev_link(i->dev, j->dev); + ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr); if (ret) goto rollback_mesh; } @@ -5805,7 +5817,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { pr_debug("linking %s's upper device %s with %s\n", upper_dev->name, i->dev->name, dev->name); - ret = __netdev_adjacent_dev_link(dev, i->dev); + ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr); if (ret) goto rollback_upper_mesh; } @@ -5814,7 +5826,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, list_for_each_entry(i, &dev->all_adj_list.lower, list) { pr_debug("linking %s's lower device %s with %s\n", dev->name, i->dev->name, upper_dev->name); - ret = __netdev_adjacent_dev_link(i->dev, upper_dev); + ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr); if (ret) goto rollback_lower_mesh; } @@ -5832,7 +5844,7 @@ rollback_lower_mesh: list_for_each_entry(i, &dev->all_adj_list.lower, list) { if (i == to_i) break; - __netdev_adjacent_dev_unlink(i->dev, upper_dev); + __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr); } i = NULL; @@ -5842,7 +5854,7 @@ rollback_upper_mesh: list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { if (i == to_i) break; - __netdev_adjacent_dev_unlink(dev, i->dev); + __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr); } i = j = NULL; @@ -5854,7 +5866,7 @@ rollback_mesh: list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { if (i == to_i && j == to_j) break; - __netdev_adjacent_dev_unlink(i->dev, j->dev); + __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr); } if (i == to_i) break; @@ -5934,16 +5946,16 @@ void netdev_upper_dev_unlink(struct net_device *dev, */ list_for_each_entry(i, &dev->all_adj_list.lower, list) list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) - __netdev_adjacent_dev_unlink(i->dev, j->dev); + __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr); /* remove also the devices itself from lower/upper device * list */ list_for_each_entry(i, &dev->all_adj_list.lower, list) - __netdev_adjacent_dev_unlink(i->dev, upper_dev); + __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr); list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) - __netdev_adjacent_dev_unlink(dev, i->dev); + __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr); call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, &changeupper_info.info); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index bbd118b19..306b8f0e0 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -216,8 +216,8 @@ #define M_QUEUE_XMIT 2 /* Inject packet into qdisc */ /* If lock -- protects updating of if_list */ -#define if_lock(t) spin_lock(&(t->if_lock)); -#define if_unlock(t) spin_unlock(&(t->if_lock)); +#define if_lock(t) mutex_lock(&(t->if_lock)); +#define if_unlock(t) mutex_unlock(&(t->if_lock)); /* Used to help with determining the pkts on receive */ #define PKTGEN_MAGIC 0xbe9be955 @@ -423,7 +423,7 @@ struct pktgen_net { }; struct pktgen_thread { - spinlock_t if_lock; /* for list of devices */ + struct mutex if_lock; /* for list of devices */ struct list_head if_list; /* All device here */ struct list_head th_list; struct task_struct *tsk; @@ -2010,11 +2010,13 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d { struct pktgen_thread *t; + mutex_lock(&pktgen_thread_lock); + list_for_each_entry(t, &pn->pktgen_threads, th_list) { struct pktgen_dev *pkt_dev; - rcu_read_lock(); - list_for_each_entry_rcu(pkt_dev, &t->if_list, list) { + if_lock(t); + list_for_each_entry(pkt_dev, &t->if_list, list) { if (pkt_dev->odev != dev) continue; @@ -2029,8 +2031,9 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d dev->name); break; } - rcu_read_unlock(); + if_unlock(t); } + mutex_unlock(&pktgen_thread_lock); } static int pktgen_device_event(struct notifier_block *unused, @@ -2286,7 +2289,7 @@ out: static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) { - pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev); + pkt_dev->pkt_overhead = 0; pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32); pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev); pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev); @@ -2777,13 +2780,13 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, - struct pktgen_dev *pkt_dev, - unsigned int extralen) + struct pktgen_dev *pkt_dev) { + unsigned int extralen = LL_RESERVED_SPACE(dev); struct sk_buff *skb = NULL; - unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen + - pkt_dev->pkt_overhead; + unsigned int size; + size = pkt_dev->cur_pkt_size + 64 + extralen + pkt_dev->pkt_overhead; if (pkt_dev->flags & F_NODE) { int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id(); @@ -2796,8 +2799,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } + /* the caller pre-fetches from skb->data and reserves for the mac hdr */ if (likely(skb)) - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, extralen - 16); return skb; } @@ -2830,16 +2834,14 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mod_cur_headers(pkt_dev); queue_map = pkt_dev->cur_queue_map; - datalen = (odev->hard_header_len + 16) & ~0xf; - - skb = pktgen_alloc_skb(odev, pkt_dev, datalen); + skb = pktgen_alloc_skb(odev, pkt_dev); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; } prefetchw(skb->data); - skb_reserve(skb, datalen); + skb_reserve(skb, 16); /* Reserve for ethernet and IP header */ eth = (__u8 *) skb_push(skb, 14); @@ -2959,7 +2961,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, mod_cur_headers(pkt_dev); queue_map = pkt_dev->cur_queue_map; - skb = pktgen_alloc_skb(odev, pkt_dev, 16); + skb = pktgen_alloc_skb(odev, pkt_dev); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -3763,7 +3765,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) return -ENOMEM; } - spin_lock_init(&t->if_lock); + mutex_init(&t->if_lock); t->cpu = cpu; INIT_LIST_HEAD(&t->if_list); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 66dff5e3d..02acfff36 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -439,7 +439,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*eh)); skb_gro_postpull_rcsum(skb, eh, sizeof(*eh)); - pp = ptype->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 55513e654..eebbc0f2b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1388,7 +1388,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 321d57f82..5351b61ab 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -249,7 +249,7 @@ static struct sk_buff **fou_gro_receive(struct sock *sk, if (!ops || !ops->callbacks.gro_receive) goto out_unlock; - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); @@ -441,7 +441,7 @@ next_proto: if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) goto out_unlock; - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); flush = 0; out_unlock: diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index ecd1e09db..6871f59cd 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -227,7 +227,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ skb_gro_postpull_rcsum(skb, greh, grehlen); - pp = ptype->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out_unlock: diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 71a52f4d4..11ef96e21 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -98,7 +98,7 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) } static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, - int offset) + int tlen, int offset) { __wsum csum = skb->csum; @@ -106,8 +106,9 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, return; if (offset != 0) - csum = csum_sub(csum, csum_partial(skb_transport_header(skb), - offset, 0)); + csum = csum_sub(csum, + csum_partial(skb_transport_header(skb) + tlen, + offset, 0)); put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum); } @@ -153,7 +154,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) } void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, - int offset) + int tlen, int offset) { struct inet_sock *inet = inet_sk(skb->sk); unsigned int flags = inet->cmsg_flags; @@ -216,7 +217,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, } if (flags & IP_CMSG_CHECKSUM) - ip_cmsg_recv_checksum(msg, skb, offset); + ip_cmsg_recv_checksum(msg, skb, tlen, offset); } EXPORT_SYMBOL(ip_cmsg_recv_offset); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1cb67de10..80bc36b25 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -96,11 +96,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low container_of(table->data, struct net, ipv4.ping_group_range.range); unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } /* Update system visible IP port range */ @@ -109,10 +109,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig kgid_t *data = table->data; struct net *net = container_of(table->data, struct net, ipv4.ping_group_range.range); - write_seqlock(&net->ipv4.ip_local_ports.lock); + write_seqlock(&net->ipv4.ping_group_range.lock); data[0] = low; data[1] = high; - write_sequnlock(&net->ipv4.ip_local_ports.lock); + write_sequnlock(&net->ipv4.ping_group_range.lock); } /* Validate changes from /proc interface. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5fdcb8d10..c0d71e7d6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1327,7 +1327,7 @@ try_again: *addr_len = sizeof(*sin); } if (inet->cmsg_flags) - ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr) + off); + ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off); err = copied; if (flags & MSG_TRUNC) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 81f253b6f..6de9f9773 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -293,7 +293,7 @@ unflush: skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); - pp = udp_sk(sk)->gro_receive(sk, head, skb); + pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f1f5d439..f5432d65e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2995,7 +2995,7 @@ static void init_loopback(struct net_device *dev) * lo device down, release this obsolete dst and * reallocate a new router for ifa. */ - if (sp_ifa->rt->dst.obsolete > 0) { + if (!atomic_read(&sp_ifa->rt->rt6i_ref)) { ip6_rt_put(sp_ifa->rt); sp_ifa->rt = NULL; } else { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 22e90e56b..a09418bda 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -243,7 +243,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, skb_gro_postpull_rcsum(skb, iph, nlen); - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 888543deb..41489f39c 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -155,6 +155,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_ hash = HASH(&any, local); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && + ipv6_addr_any(&t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } @@ -162,6 +163,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_ hash = HASH(remote, &any); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(remote, &t->parms.raddr) && + ipv6_addr_any(&t->parms.laddr) && (t->dev->flags & IFF_UP)) return t; } @@ -1132,6 +1134,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, if (err) return err; + skb->protocol = htons(ETH_P_IPV6); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 269218aac..23153ac6c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -656,7 +656,8 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, struct net_device *dev = rt->dst.dev; if (dev && !netif_carrier_ok(dev) && - idev->cnf.ignore_routes_with_linkdown) + idev->cnf.ignore_routes_with_linkdown && + !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; if (rt6_check_expired(rt)) @@ -1050,6 +1051,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int strict = 0; strict |= flags & RT6_LOOKUP_F_IFACE; + strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; if (net->ipv6.devconf_all->forwarding == 0) strict |= RT6_LOOKUP_F_REACHABLE; @@ -1783,7 +1785,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, }; struct fib6_table *table; struct rt6_info *rt; - int flags = RT6_LOOKUP_F_IFACE; + int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_IGNORE_LINKSTATE; table = fib6_get_table(net, cfg->fc_table); if (!table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 27a968b88..40a58d7d1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1209,6 +1209,16 @@ out: return NULL; } +static void tcp_v6_restore_cb(struct sk_buff *skb) +{ + /* We need to move header back to the beginning if xfrm6_policy_check() + * and tcp_v6_fill_cb() are going to be called again. + * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. + */ + memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, + sizeof(struct inet6_skb_parm)); +} + /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * @@ -1346,6 +1356,7 @@ ipv6_pktoptions: np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { skb_set_owner_r(opt_skb, sk); + tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); @@ -1379,15 +1390,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, TCP_SKB_CB(skb)->sacked = 0; } -static void tcp_v6_restore_cb(struct sk_buff *skb) -{ - /* We need to move header back to the beginning if xfrm6_policy_check() - * and tcp_v6_fill_cb() are going to be called again. - */ - memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, - sizeof(struct inet6_skb_parm)); -} - static int tcp_v6_rcv(struct sk_buff *skb) { const struct tcphdr *th; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 19ac3a1c3..c2a8656c2 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -427,7 +427,8 @@ try_again: if (is_udp4) { if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + ip_cmsg_recv_offset(msg, skb, + sizeof(struct udphdr), off); } else { if (np->rxopt.all) ip6_datagram_recv_specific_ctl(sk, msg, skb); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 627f898c0..62bea4591 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1832,7 +1832,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* Record the max length of recvmsg() calls for future allocations */ nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, - 16384); + SKB_WITH_OVERHEAD(32768)); copied = data_skb->len; if (len < copied) { @@ -2083,8 +2083,9 @@ static int netlink_dump(struct sock *sk) if (alloc_min_size < nlk->max_recvmsg_len) { alloc_size = nlk->max_recvmsg_len; - skb = alloc_skb(alloc_size, GFP_KERNEL | - __GFP_NOWARN | __GFP_NORETRY); + skb = alloc_skb(alloc_size, + (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | + __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 33a4697d5..d2238b204 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -250,7 +250,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po); static int packet_direct_xmit(struct sk_buff *skb) { struct net_device *dev = skb->dev; - netdev_features_t features; + struct sk_buff *orig_skb = skb; struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; @@ -258,9 +258,8 @@ static int packet_direct_xmit(struct sk_buff *skb) !netif_carrier_ok(dev))) goto drop; - features = netif_skb_features(skb); - if (skb_needs_linearize(skb, features) && - __skb_linearize(skb)) + skb = validate_xmit_skb_list(skb, dev); + if (skb != orig_skb) goto drop; txq = skb_get_tx_queue(dev, skb); @@ -280,7 +279,7 @@ static int packet_direct_xmit(struct sk_buff *skb) return ret; drop: atomic_long_inc(&dev->tx_dropped); - kfree_skb(skb); + kfree_skb_list(skb); return NET_XMIT_DROP; } @@ -3952,6 +3951,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); + fanout_release(sk); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d09d06875..027ddf412 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -341,22 +341,25 @@ int tcf_register_action(struct tc_action_ops *act, if (!act->act || !act->dump || !act->init || !act->walk || !act->lookup) return -EINVAL; + /* We have to register pernet ops before making the action ops visible, + * otherwise tcf_action_init_1() could get a partially initialized + * netns. + */ + ret = register_pernet_subsys(ops); + if (ret) + return ret; + write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); + unregister_pernet_subsys(ops); return -EEXIST; } } list_add_tail(&act->head, &act_base); write_unlock(&act_mod_lock); - ret = register_pernet_subsys(ops); - if (ret) { - tcf_unregister_action(act, ops); - return ret; - } - return 0; } EXPORT_SYMBOL(tcf_register_action); @@ -367,8 +370,6 @@ int tcf_unregister_action(struct tc_action_ops *act, struct tc_action_ops *a; int err = -ENOENT; - unregister_pernet_subsys(ops); - write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (a == act) { @@ -378,6 +379,8 @@ int tcf_unregister_action(struct tc_action_ops *act, } } write_unlock(&act_mod_lock); + if (!err) + unregister_pernet_subsys(ops); return err; } EXPORT_SYMBOL(tcf_unregister_action); diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 691409de3..4ffc6c13a 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -36,6 +36,12 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, bstats_update(&v->tcf_bstats, skb); action = v->tcf_action; + /* Ensure 'data' points at mac_header prior calling vlan manipulating + * functions. + */ + if (skb_at_tc_ingress(skb)) + skb_push_rcsum(skb, skb->mac_len); + switch (v->tcfv_action) { case TCA_VLAN_ACT_POP: err = skb_vlan_pop(skb); @@ -57,6 +63,9 @@ drop: action = TC_ACT_SHOT; v->tcf_qstats.drops++; unlock: + if (skb_at_tc_ingress(skb)) + skb_pull_rcsum(skb, skb->mac_len); + spin_unlock(&v->tcf_lock); return action; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a7c564537..74bed5e9b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -344,7 +344,8 @@ replay: if (err == 0) { struct tcf_proto *next = rtnl_dereference(tp->next); - tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER); + tfilter_notify(net, skb, n, tp, + t->tcm_handle, RTM_DELTFILTER); if (tcf_destroy(tp, false)) RCU_INIT_POINTER(*back, next); } diff --git a/net/sctp/output.c b/net/sctp/output.c index 31b7bc358..81929907a 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -417,6 +417,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) __u8 has_data = 0; int gso = 0; int pktcount = 0; + int auth_len = 0; struct dst_entry *dst; unsigned char *auth = NULL; /* pointer to auth in skb data */ @@ -505,7 +506,12 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) list_for_each_entry(chunk, &packet->chunk_list, list) { int padded = WORD_ROUND(chunk->skb->len); - if (pkt_size + padded > tp->pathmtu) + if (chunk == packet->auth) + auth_len = padded; + else if (auth_len + padded + packet->overhead > + tp->pathmtu) + goto nomem; + else if (pkt_size + padded > tp->pathmtu) break; pkt_size += padded; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index d88bb2b0b..920469e7b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3422,6 +3422,12 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); + /* Report violation if chunk len overflows */ + ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + if (ch_end > skb_tail_pointer(skb)) + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); + /* Now that we know we at least have a chunk header, * do things that are type appropriate. */ @@ -3453,12 +3459,6 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, } } - /* Report violation if chunk len overflows */ - ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); - if (ch_end > skb_tail_pointer(skb)) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); - ch = (sctp_chunkhdr_t *) ch_end; } while (ch_end < skb_tail_pointer(skb)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 8ed2d99bd..baccbf3c1 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4683,7 +4683,7 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len, static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval, int __user *optlen) { - if (len <= 0) + if (len == 0) return -EINVAL; if (len > sizeof(struct sctp_event_subscribe)) len = sizeof(struct sctp_event_subscribe); @@ -6426,6 +6426,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; + if (len < 0) + return -EINVAL; + lock_sock(sk); switch (optname) { diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index a5fc9dd24..a56c5e6f4 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -774,6 +774,9 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD; int err; + if (!netif_is_bridge_port(dev)) + return -EOPNOTSUPP; + err = switchdev_port_attr_get(dev, &attr); if (err && err != -EOPNOTSUPP) return err; @@ -929,6 +932,9 @@ int switchdev_port_bridge_setlink(struct net_device *dev, struct nlattr *afspec; int err = 0; + if (!netif_is_bridge_port(dev)) + return -EOPNOTSUPP; + protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); if (protinfo) { @@ -962,6 +968,9 @@ int switchdev_port_bridge_dellink(struct net_device *dev, { struct nlattr *afspec; + if (!netif_is_bridge_port(dev)) + return -EOPNOTSUPP; + afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (afspec) |