diff --git a/Makefile b/Makefile index da704d903321..1130803ab93c 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 7 +SUBLEVEL = 8 EXTRAVERSION = NAME = Roaring Lionus diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 25d1eb4933d0..be7ec5a76a54 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -710,11 +710,8 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs; unsigned int pkts_compl = 0, bytes_compl = 0; struct bcm_sysport_cb *cb; - struct netdev_queue *txq; u32 hw_ind; - txq = netdev_get_tx_queue(ndev, ring->index); - /* Compute how many descriptors have been processed since last call */ hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index)); c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK; @@ -745,9 +742,6 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, ring->c_index = c_index; - if (netif_tx_queue_stopped(txq) && pkts_compl) - netif_tx_wake_queue(txq); - netif_dbg(priv, tx_done, ndev, "ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n", ring->index, ring->c_index, pkts_compl, bytes_compl); @@ -759,16 +753,33 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, struct bcm_sysport_tx_ring *ring) { + struct netdev_queue *txq; unsigned int released; unsigned long flags; + txq = netdev_get_tx_queue(priv->netdev, ring->index); + spin_lock_irqsave(&ring->lock, flags); released = __bcm_sysport_tx_reclaim(priv, ring); + if (released) + netif_tx_wake_queue(txq); + spin_unlock_irqrestore(&ring->lock, flags); return released; } +/* Locked version of the per-ring TX reclaim, but does not wake the queue */ +static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv, + struct bcm_sysport_tx_ring *ring) +{ + unsigned long flags; + + spin_lock_irqsave(&ring->lock, flags); + __bcm_sysport_tx_reclaim(priv, ring); + spin_unlock_irqrestore(&ring->lock, flags); +} + static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget) { struct bcm_sysport_tx_ring *ring = @@ -1253,7 +1264,7 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv, napi_disable(&ring->napi); netif_napi_del(&ring->napi); - bcm_sysport_tx_reclaim(priv, ring); + bcm_sysport_tx_clean(priv, ring); kfree(ring->cbs); ring->cbs = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index fb8bb027b69c..d223e7cb68ba 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1740,8 +1740,11 @@ int mlx4_en_start_port(struct net_device *dev) /* Process all completions if exist to prevent * the queues freezing if they are full */ - for (i = 0; i < priv->rx_ring_num; i++) + for (i = 0; i < priv->rx_ring_num; i++) { + local_bh_disable(); napi_schedule(&priv->rx_cq[i]->napi); + local_bh_enable(); + } netif_tx_start_all_queues(dev); netif_device_attach(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 33495d88aeb2..e7b2158bb48a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -193,6 +193,9 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, return false; } + if (unlikely(page_is_pfmemalloc(dma_info->page))) + return false; + cache->page_cache[cache->tail] = *dma_info; cache->tail = tail_next; return true; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index d942a3e6fa41..846fd4df7dab 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -211,21 +211,21 @@ MLXSW_ITEM32(pci, eqe, owner, 0x0C, 0, 1); /* pci_eqe_cmd_token * Command completion event - token */ -MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16); +MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16); /* pci_eqe_cmd_status * Command completion event - status */ -MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8); +MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8); /* pci_eqe_cmd_out_param_h * Command completion event - output parameter - higher part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32); /* pci_eqe_cmd_out_param_l * Command completion event - output parameter - lower part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index dda5761e91bc..f902c4d3de99 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -684,6 +684,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } if (eth_skb_pad(skb)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 92bda8703f87..d548f0a55174 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -314,6 +314,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } mlxsw_sx_txhdr_construct(skb, &tx_info); /* TX header is consumed by HW on the way so we shouldn't count its diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index d6a217874a8b..862f18ed6022 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1508,6 +1508,19 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) + entry / NUM_TX_DESC * DPTR_ALIGN; len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data; + /* Zero length DMA descriptors are problematic as they seem to + * terminate DMA transfers. Avoid them by simply using a length of + * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN. + * + * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of + * data by the call to skb_put_padto() above this is safe with + * respect to both the length of the first DMA descriptor (len) + * overflowing the available data and the length of the second DMA + * descriptor (skb->len - len) being negative. + */ + if (len == 0) + len = DPTR_ALIGN; + memcpy(buffer, skb->data, len); dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE); if (dma_mapping_error(ndev->dev.parent, dma_addr)) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c9140c3aeb67..ff038e507fd6 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -659,6 +659,7 @@ int netvsc_recv_callback(struct hv_device *device_obj, * policy filters on the host). Deliver these via the VF * interface in the guest. */ + rcu_read_lock(); vf_netdev = rcu_dereference(net_device_ctx->vf_netdev); if (vf_netdev && (vf_netdev->flags & IFF_UP)) net = vf_netdev; @@ -667,6 +668,7 @@ int netvsc_recv_callback(struct hv_device *device_obj, skb = netvsc_alloc_recv_skb(net, packet, csum_info, *data, vlan_tci); if (unlikely(!skb)) { ++net->stats.rx_dropped; + rcu_read_unlock(); return NVSP_STAT_FAIL; } @@ -696,6 +698,7 @@ int netvsc_recv_callback(struct hv_device *device_obj, * TODO - use NAPI? */ netif_rx(skb); + rcu_read_unlock(); return 0; } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 7869b0651576..6f38daf2d978 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -827,7 +827,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, return -EINVAL; ret = virtio_net_hdr_from_skb(skb, &vnet_hdr, - macvtap_is_little_endian(q)); + macvtap_is_little_endian(q), true); if (ret) BUG(); diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index e741bf614c4e..b0492ef2cdaa 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -21,6 +21,23 @@ MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver"); MODULE_AUTHOR("Maxime Bizon "); MODULE_LICENSE("GPL"); +static int bcm63xx_config_intr(struct phy_device *phydev) +{ + int reg, err; + + reg = phy_read(phydev, MII_BCM63XX_IR); + if (reg < 0) + return reg; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + reg &= ~MII_BCM63XX_IR_GMASK; + else + reg |= MII_BCM63XX_IR_GMASK; + + err = phy_write(phydev, MII_BCM63XX_IR, reg); + return err; +} + static int bcm63xx_config_init(struct phy_device *phydev) { int reg, err; @@ -55,7 +72,7 @@ static struct phy_driver bcm63xx_driver[] = { .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = bcm_phy_ack_intr, - .config_intr = bcm_phy_config_intr, + .config_intr = bcm63xx_config_intr, }, { /* same phy as above, with just a different OUI */ .phy_id = 0x002bdc00, @@ -67,7 +84,7 @@ static struct phy_driver bcm63xx_driver[] = { .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = bcm_phy_ack_intr, - .config_intr = bcm_phy_config_intr, + .config_intr = bcm63xx_config_intr, } }; module_phy_driver(bcm63xx_driver); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index db6acecabeaa..18402d79539e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1374,7 +1374,7 @@ static ssize_t tun_put_user(struct tun_struct *tun, return -EINVAL; ret = virtio_net_hdr_from_skb(skb, &gso, - tun_is_little_endian(tun)); + tun_is_little_endian(tun), true); if (ret) { struct skb_shared_info *sinfo = skb_shinfo(skb); pr_err("unexpected GSO type: " diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index dd623f674487..b82be816256c 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -531,6 +531,7 @@ static const struct driver_info wwan_info = { #define SAMSUNG_VENDOR_ID 0x04e8 #define LENOVO_VENDOR_ID 0x17ef #define NVIDIA_VENDOR_ID 0x0955 +#define HP_VENDOR_ID 0x03f0 static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -677,6 +678,13 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* HP lt2523 (Novatel E371) - handled by qmi_wwan */ +{ + USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* AnyDATA ADU960S - handled by qmi_wwan */ { USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6fe1cdb0174f..24d5272cdce5 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -654,6 +654,13 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* HP lt2523 (Novatel E371) */ + USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&qmi_wwan_info, + }, { /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */ USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 4b5cb162442b..90b426c5ffce 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -32,7 +32,7 @@ #define NETNEXT_VERSION "08" /* Information for net */ -#define NET_VERSION "6" +#define NET_VERSION "7" #define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION #define DRIVER_AUTHOR "Realtek linux nic maintainers " @@ -1730,7 +1730,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc) u8 checksum = CHECKSUM_NONE; u32 opts2, opts3; - if (tp->version == RTL_VER_01 || tp->version == RTL_VER_02) + if (!(tp->netdev->features & NETIF_F_RXCSUM)) goto return_result; opts2 = le32_to_cpu(rx_desc->opts2); @@ -3572,6 +3572,8 @@ static bool delay_autosuspend(struct r8152 *tp) */ if (!sw_linking && tp->rtl_ops.in_nway(tp)) return true; + else if (!skb_queue_empty(&tp->tx_queue)) + return true; else return false; } @@ -4358,6 +4360,11 @@ static int rtl8152_probe(struct usb_interface *intf, NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + if (tp->version == RTL_VER_01) { + netdev->features &= ~NETIF_F_RXCSUM; + netdev->hw_features &= ~NETIF_F_RXCSUM; + } + netdev->ethtool_ops = &ops; netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index cbf1c613c67a..51fc0c33a62f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -840,7 +840,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) hdr = skb_vnet_hdr(skb); if (virtio_net_hdr_from_skb(skb, &hdr->hdr, - virtio_is_little_endian(vi->vdev))) + virtio_is_little_endian(vi->vdev), false)) BUG(); if (vi->mergeable_rx_bufs) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 2ba01ca02c9c..0fafaa9d903b 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2887,7 +2887,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, memcpy(&vxlan->cfg, conf, sizeof(*conf)); if (!vxlan->cfg.dst_port) { if (conf->flags & VXLAN_F_GPE) - vxlan->cfg.dst_port = 4790; /* IANA assigned VXLAN-GPE port */ + vxlan->cfg.dst_port = htons(4790); /* IANA VXLAN-GPE port */ else vxlan->cfg.dst_port = default_port; } diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 5050056a0b06..9f06a211e157 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -95,10 +95,7 @@ unsigned int xfs_alloc_set_aside( struct xfs_mount *mp) { - unsigned int blocks; - - blocks = 4 + (mp->m_sb.sb_agcount * XFS_ALLOC_AGFL_RESERVE); - return blocks; + return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + 4); } /* @@ -365,36 +362,12 @@ xfs_alloc_fix_len( return; ASSERT(rlen >= args->minlen && rlen <= args->maxlen); ASSERT(rlen % args->prod == args->mod); + ASSERT(args->pag->pagf_freeblks + args->pag->pagf_flcount >= + rlen + args->minleft); args->len = rlen; } /* - * Fix up length if there is too little space left in the a.g. - * Return 1 if ok, 0 if too little, should give up. - */ -STATIC int -xfs_alloc_fix_minleft( - xfs_alloc_arg_t *args) /* allocation argument structure */ -{ - xfs_agf_t *agf; /* a.g. freelist header */ - int diff; /* free space difference */ - - if (args->minleft == 0) - return 1; - agf = XFS_BUF_TO_AGF(args->agbp); - diff = be32_to_cpu(agf->agf_freeblks) - - args->len - args->minleft; - if (diff >= 0) - return 1; - args->len += diff; /* shrink the allocated space */ - /* casts to (int) catch length underflows */ - if ((int)args->len >= (int)args->minlen) - return 1; - args->agbno = NULLAGBLOCK; - return 0; -} - -/* * Update the two btrees, logically removing from freespace the extent * starting at rbno, rlen blocks. The extent is contained within the * actual (current) free extent fbno for flen blocks. @@ -689,8 +662,6 @@ xfs_alloc_ag_vextent( xfs_alloc_arg_t *args) /* argument structure for allocation */ { int error=0; - xfs_extlen_t reservation; - xfs_extlen_t oldmax; ASSERT(args->minlen > 0); ASSERT(args->maxlen > 0); @@ -699,20 +670,6 @@ xfs_alloc_ag_vextent( ASSERT(args->alignment > 0); /* - * Clamp maxlen to the amount of free space minus any reservations - * that have been made. - */ - oldmax = args->maxlen; - reservation = xfs_ag_resv_needed(args->pag, args->resv); - if (args->maxlen > args->pag->pagf_freeblks - reservation) - args->maxlen = args->pag->pagf_freeblks - reservation; - if (args->maxlen == 0) { - args->agbno = NULLAGBLOCK; - args->maxlen = oldmax; - return 0; - } - - /* * Branch to correct routine based on the type. */ args->wasfromfl = 0; @@ -731,8 +688,6 @@ xfs_alloc_ag_vextent( /* NOTREACHED */ } - args->maxlen = oldmax; - if (error || args->agbno == NULLAGBLOCK) return error; @@ -841,9 +796,6 @@ xfs_alloc_ag_vextent_exact( args->len = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen) - args->agbno; xfs_alloc_fix_len(args); - if (!xfs_alloc_fix_minleft(args)) - goto not_found; - ASSERT(args->agbno + args->len <= tend); /* @@ -1149,12 +1101,7 @@ xfs_alloc_ag_vextent_near( XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); ASSERT(ltbno + ltlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length)); args->len = blen; - if (!xfs_alloc_fix_minleft(args)) { - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); - trace_xfs_alloc_near_nominleft(args); - return 0; - } - blen = args->len; + /* * We are allocating starting at bnew for blen blocks. */ @@ -1346,12 +1293,6 @@ xfs_alloc_ag_vextent_near( */ args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen); xfs_alloc_fix_len(args); - if (!xfs_alloc_fix_minleft(args)) { - trace_xfs_alloc_near_nominleft(args); - xfs_btree_del_cursor(bno_cur_lt, XFS_BTREE_NOERROR); - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); - return 0; - } rlen = args->len; (void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment, args->datatype, ltbnoa, ltlena, <new); @@ -1553,8 +1494,6 @@ xfs_alloc_ag_vextent_size( } xfs_alloc_fix_len(args); - if (!xfs_alloc_fix_minleft(args)) - goto out_nominleft; rlen = args->len; XFS_WANT_CORRUPTED_GOTO(args->mp, rlen <= flen, error0); /* @@ -2056,7 +1995,7 @@ xfs_alloc_space_available( int flags) { struct xfs_perag *pag = args->pag; - xfs_extlen_t longest; + xfs_extlen_t alloc_len, longest; xfs_extlen_t reservation; /* blocks that are still reserved */ int available; @@ -2066,17 +2005,28 @@ xfs_alloc_space_available( reservation = xfs_ag_resv_needed(pag, args->resv); /* do we have enough contiguous free space for the allocation? */ + alloc_len = args->minlen + (args->alignment - 1) + args->minalignslop; longest = xfs_alloc_longest_free_extent(args->mp, pag, min_free, reservation); - if ((args->minlen + args->alignment + args->minalignslop - 1) > longest) + if (longest < alloc_len) return false; /* do we have enough free space remaining for the allocation? */ available = (int)(pag->pagf_freeblks + pag->pagf_flcount - - reservation - min_free - args->total); - if (available < (int)args->minleft || available <= 0) + reservation - min_free - args->minleft); + if (available < (int)max(args->total, alloc_len)) return false; + /* + * Clamp maxlen to the amount of free space available for the actual + * extent allocation. + */ + if (available < (int)args->maxlen && !(flags & XFS_ALLOC_FLAG_CHECK)) { + args->maxlen = available; + ASSERT(args->maxlen > 0); + ASSERT(args->maxlen >= args->minlen); + } + return true; } @@ -2122,7 +2072,8 @@ xfs_alloc_fix_freelist( } need = xfs_alloc_min_freelist(mp, pag); - if (!xfs_alloc_space_available(args, need, flags)) + if (!xfs_alloc_space_available(args, need, flags | + XFS_ALLOC_FLAG_CHECK)) goto out_agbp_relse; /* @@ -2638,12 +2589,10 @@ xfs_alloc_vextent( xfs_agblock_t agsize; /* allocation group size */ int error; int flags; /* XFS_ALLOC_FLAG_... locking flags */ - xfs_extlen_t minleft;/* minimum left value, temp copy */ xfs_mount_t *mp; /* mount structure pointer */ xfs_agnumber_t sagno; /* starting allocation group number */ xfs_alloctype_t type; /* input allocation type */ int bump_rotor = 0; - int no_min = 0; xfs_agnumber_t rotorstep = xfs_rotorstep; /* inode32 agf stepper */ mp = args->mp; @@ -2672,7 +2621,6 @@ xfs_alloc_vextent( trace_xfs_alloc_vextent_badargs(args); return 0; } - minleft = args->minleft; switch (type) { case XFS_ALLOCTYPE_THIS_AG: @@ -2683,9 +2631,7 @@ xfs_alloc_vextent( */ args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno); args->pag = xfs_perag_get(mp, args->agno); - args->minleft = 0; error = xfs_alloc_fix_freelist(args, 0); - args->minleft = minleft; if (error) { trace_xfs_alloc_vextent_nofix(args); goto error0; @@ -2750,9 +2696,7 @@ xfs_alloc_vextent( */ for (;;) { args->pag = xfs_perag_get(mp, args->agno); - if (no_min) args->minleft = 0; error = xfs_alloc_fix_freelist(args, flags); - args->minleft = minleft; if (error) { trace_xfs_alloc_vextent_nofix(args); goto error0; @@ -2792,20 +2736,17 @@ xfs_alloc_vextent( * or switch to non-trylock mode. */ if (args->agno == sagno) { - if (no_min == 1) { + if (flags == 0) { args->agbno = NULLAGBLOCK; trace_xfs_alloc_vextent_allfailed(args); break; } - if (flags == 0) { - no_min = 1; - } else { - flags = 0; - if (type == XFS_ALLOCTYPE_START_BNO) { - args->agbno = XFS_FSB_TO_AGBNO(mp, - args->fsbno); - args->type = XFS_ALLOCTYPE_NEAR_BNO; - } + + flags = 0; + if (type == XFS_ALLOCTYPE_START_BNO) { + args->agbno = XFS_FSB_TO_AGBNO(mp, + args->fsbno); + args->type = XFS_ALLOCTYPE_NEAR_BNO; } } xfs_perag_put(args->pag); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 7c404a6b0ae3..1d0f48a501a3 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -56,7 +56,7 @@ typedef unsigned int xfs_alloctype_t; #define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/ #define XFS_ALLOC_FLAG_NORMAP 0x00000004 /* don't modify the rmapbt */ #define XFS_ALLOC_FLAG_NOSHRINK 0x00000008 /* don't shrink the freelist */ - +#define XFS_ALLOC_FLAG_CHECK 0x00000010 /* test only, don't modify args */ /* * Argument structure for xfs_alloc routines. diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index af1ecb19121e..6622d46ddec3 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -131,9 +131,6 @@ xfs_attr_get( if (XFS_FORCED_SHUTDOWN(ip->i_mount)) return -EIO; - if (!xfs_inode_hasattr(ip)) - return -ENOATTR; - error = xfs_attr_args_init(&args, ip, name, flags); if (error) return error; @@ -392,9 +389,6 @@ xfs_attr_remove( if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; - if (!xfs_inode_hasattr(dp)) - return -ENOATTR; - error = xfs_attr_args_init(&args, dp, name, flags); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 89d727b659fc..f52fd63fce19 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3720,7 +3720,7 @@ xfs_bmap_btalloc( align = xfs_get_cowextsz_hint(ap->ip); else if (xfs_alloc_is_userdata(ap->datatype)) align = xfs_get_extsz_hint(ap->ip); - if (unlikely(align)) { + if (align) { error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0, ap->eof, 0, ap->conv, &ap->offset, &ap->length); @@ -3792,7 +3792,7 @@ xfs_bmap_btalloc( args.minlen = ap->minlen; } /* apply extent size hints if obtained earlier */ - if (unlikely(align)) { + if (align) { args.prod = align; if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod))) args.mod = (xfs_extlen_t)(args.prod - args.mod); @@ -3903,7 +3903,6 @@ xfs_bmap_btalloc( args.fsbno = 0; args.type = XFS_ALLOCTYPE_FIRST_AG; args.total = ap->minlen; - args.minleft = 0; if ((error = xfs_alloc_vextent(&args))) return error; ap->dfops->dop_low = true; @@ -4437,8 +4436,6 @@ xfs_bmapi_allocate( if (error) return error; - if (bma->dfops->dop_low) - bma->minleft = 0; if (bma->cur) bma->cur->bc_private.b.firstblock = *bma->firstblock; if (bma->blkno == NULLFSBLOCK) @@ -4610,8 +4607,6 @@ xfs_bmapi_write( int n; /* current extent index */ xfs_fileoff_t obno; /* old block number (offset) */ int whichfork; /* data or attr fork */ - char inhole; /* current location is hole in file */ - char wasdelay; /* old extent was delayed */ #ifdef DEBUG xfs_fileoff_t orig_bno; /* original block number value */ @@ -4697,22 +4692,44 @@ xfs_bmapi_write( bma.firstblock = firstblock; while (bno < end && n < *nmap) { - inhole = eof || bma.got.br_startoff > bno; - wasdelay = !inhole && isnullstartblock(bma.got.br_startblock); + bool need_alloc = false, wasdelay = false; - /* - * Make sure we only reflink into a hole. - */ - if (flags & XFS_BMAPI_REMAP) - ASSERT(inhole); - if (flags & XFS_BMAPI_COWFORK) - ASSERT(!inhole); + /* in hole or beyoned EOF? */ + if (eof || bma.got.br_startoff > bno) { + if (flags & XFS_BMAPI_DELALLOC) { + /* + * For the COW fork we can reasonably get a + * request for converting an extent that races + * with other threads already having converted + * part of it, as there converting COW to + * regular blocks is not protected using the + * IOLOCK. + */ + ASSERT(flags & XFS_BMAPI_COWFORK); + if (!(flags & XFS_BMAPI_COWFORK)) { + error = -EIO; + goto error0; + } + + if (eof || bno >= end) + break; + } else { + need_alloc = true; + } + } else { + /* + * Make sure we only reflink into a hole. + */ + ASSERT(!(flags & XFS_BMAPI_REMAP)); + if (isnullstartblock(bma.got.br_startblock)) + wasdelay = true; + } /* * First, deal with the hole before the allocated space * that we found, if any. */ - if (inhole || wasdelay) { + if (need_alloc || wasdelay) { bma.eof = eof; bma.conv = !!(flags & XFS_BMAPI_CONVERT); bma.wasdel = wasdelay; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index d6d175a4fdec..e7d40b39f18f 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -110,6 +110,9 @@ struct xfs_extent_free_item /* Map something in the CoW fork. */ #define XFS_BMAPI_COWFORK 0x200 +/* Only convert delalloc space, don't allocate entirely new extents */ +#define XFS_BMAPI_DELALLOC 0x400 + #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ { XFS_BMAPI_METADATA, "METADATA" }, \ @@ -120,7 +123,8 @@ struct xfs_extent_free_item { XFS_BMAPI_CONVERT, "CONVERT" }, \ { XFS_BMAPI_ZERO, "ZERO" }, \ { XFS_BMAPI_REMAP, "REMAP" }, \ - { XFS_BMAPI_COWFORK, "COWFORK" } + { XFS_BMAPI_COWFORK, "COWFORK" }, \ + { XFS_BMAPI_DELALLOC, "DELALLOC" } static inline int xfs_bmapi_aflag(int w) diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 049fa597ae91..f76c1693ff01 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -502,12 +502,11 @@ xfs_bmbt_alloc_block( if (args.fsbno == NULLFSBLOCK && args.minleft) { /* * Could not find an AG with enough free space to satisfy - * a full btree split. Try again without minleft and if + * a full btree split. Try again and if * successful activate the lowspace algorithm. */ args.fsbno = 0; args.type = XFS_ALLOCTYPE_FIRST_AG; - args.minleft = 0; error = xfs_alloc_vextent(&args); if (error) goto error0; diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 20a96dd5af7e..7825d78d4587 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -36,21 +36,29 @@ struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2, XFS_DIR3_FT_DIR }; /* - * @mode, if set, indicates that the type field needs to be set up. - * This uses the transformation from file mode to DT_* as defined in linux/fs.h - * for file type specification. This will be propagated into the directory - * structure if appropriate for the given operation and filesystem config. + * Convert inode mode to directory entry filetype */ -const unsigned char xfs_mode_to_ftype[S_IFMT >> S_SHIFT] = { - [0] = XFS_DIR3_FT_UNKNOWN, - [S_IFREG >> S_SHIFT] = XFS_DIR3_FT_REG_FILE, - [S_IFDIR >> S_SHIFT] = XFS_DIR3_FT_DIR, - [S_IFCHR >> S_SHIFT] = XFS_DIR3_FT_CHRDEV, - [S_IFBLK >> S_SHIFT] = XFS_DIR3_FT_BLKDEV, - [S_IFIFO >> S_SHIFT] = XFS_DIR3_FT_FIFO, - [S_IFSOCK >> S_SHIFT] = XFS_DIR3_FT_SOCK, - [S_IFLNK >> S_SHIFT] = XFS_DIR3_FT_SYMLINK, -}; +unsigned char xfs_mode_to_ftype(int mode) +{ + switch (mode & S_IFMT) { + case S_IFREG: + return XFS_DIR3_FT_REG_FILE; + case S_IFDIR: + return XFS_DIR3_FT_DIR; + case S_IFCHR: + return XFS_DIR3_FT_CHRDEV; + case S_IFBLK: + return XFS_DIR3_FT_BLKDEV; + case S_IFIFO: + return XFS_DIR3_FT_FIFO; + case S_IFSOCK: + return XFS_DIR3_FT_SOCK; + case S_IFLNK: + return XFS_DIR3_FT_SYMLINK; + default: + return XFS_DIR3_FT_UNKNOWN; + } +} /* * ASCII case-insensitive (ie. A-Z) support for directories that was @@ -631,7 +639,8 @@ xfs_dir2_isblock( if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK))) return rval; rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize; - ASSERT(rval == 0 || args->dp->i_d.di_size == args->geo->blksize); + if (rval != 0 && args->dp->i_d.di_size != args->geo->blksize) + return -EFSCORRUPTED; *vp = rval; return 0; } diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index becc926c3e3d..ae0d55bf6500 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -18,6 +18,9 @@ #ifndef __XFS_DIR2_H__ #define __XFS_DIR2_H__ +#include "xfs_da_format.h" +#include "xfs_da_btree.h" + struct xfs_defer_ops; struct xfs_da_args; struct xfs_inode; @@ -32,10 +35,9 @@ struct xfs_dir2_data_unused; extern struct xfs_name xfs_name_dotdot; /* - * directory filetype conversion tables. + * Convert inode mode to directory entry filetype */ -#define S_SHIFT 12 -extern const unsigned char xfs_mode_to_ftype[]; +extern unsigned char xfs_mode_to_ftype(int mode); /* * directory operations vector for encode/decode routines diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index c906e50515f0..37ee7f01a35d 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -29,6 +29,7 @@ #include "xfs_icache.h" #include "xfs_trans.h" #include "xfs_ialloc.h" +#include "xfs_dir2.h" /* * Check that none of the inode's in the buffer have a next @@ -386,6 +387,7 @@ xfs_dinode_verify( struct xfs_inode *ip, struct xfs_dinode *dip) { + uint16_t mode; uint16_t flags; uint64_t flags2; @@ -396,8 +398,12 @@ xfs_dinode_verify( if (be64_to_cpu(dip->di_size) & (1ULL << 63)) return false; - /* No zero-length symlinks. */ - if (S_ISLNK(be16_to_cpu(dip->di_mode)) && dip->di_size == 0) + mode = be16_to_cpu(dip->di_mode); + if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN) + return false; + + /* No zero-length symlinks/dirs. */ + if ((S_ISLNK(mode) || S_ISDIR(mode)) && dip->di_size == 0) return false; /* only version 3 or greater inodes are extensively verified here */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 2580262e4ea0..584ec896a533 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -242,7 +242,7 @@ xfs_mount_validate_sb( sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG || sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_blocksize != (1 << sbp->sb_blocklog) || - sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG || + sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_inodesize < XFS_DINODE_MIN_SIZE || sbp->sb_inodesize > XFS_DINODE_MAX_SIZE || sbp->sb_inodelog < XFS_DINODE_MIN_LOG || diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 0670a8bd5818..efb8ccd6bbf2 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -528,7 +528,6 @@ xfs_getbmap( xfs_bmbt_irec_t *map; /* buffer for user's data */ xfs_mount_t *mp; /* file system mount point */ int nex; /* # of user extents can do */ - int nexleft; /* # of user extents left */ int subnex; /* # of bmapi's can do */ int nmap; /* number of map entries */ struct getbmapx *out; /* output structure */ @@ -686,10 +685,8 @@ xfs_getbmap( goto out_free_map; } - nexleft = nex; - do { - nmap = (nexleft > subnex) ? subnex : nexleft; + nmap = (nex> subnex) ? subnex : nex; error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset), XFS_BB_TO_FSB(mp, bmv->bmv_length), map, &nmap, bmapi_flags); @@ -697,8 +694,8 @@ xfs_getbmap( goto out_free_map; ASSERT(nmap <= subnex); - for (i = 0; i < nmap && nexleft && bmv->bmv_length && - cur_ext < bmv->bmv_count; i++) { + for (i = 0; i < nmap && bmv->bmv_length && + cur_ext < bmv->bmv_count - 1; i++) { out[cur_ext].bmv_oflags = 0; if (map[i].br_state == XFS_EXT_UNWRITTEN) out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC; @@ -760,16 +757,27 @@ xfs_getbmap( continue; } + /* + * In order to report shared extents accurately, + * we report each distinct shared/unshared part + * of a single bmbt record using multiple bmap + * extents. To make that happen, we iterate the + * same map array item multiple times, each + * time trimming out the subextent that we just + * reported. + * + * Because of this, we must check the out array + * index (cur_ext) directly against bmv_count-1 + * to avoid overflows. + */ if (inject_map.br_startblock != NULLFSBLOCK) { map[i] = inject_map; i--; - } else - nexleft--; + } bmv->bmv_entries++; cur_ext++; } - } while (nmap && nexleft && bmv->bmv_length && - cur_ext < bmv->bmv_count); + } while (nmap && bmv->bmv_length && cur_ext < bmv->bmv_count - 1); out_free_map: kmem_free(map); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index b5b9bffe3520..d7a67d7fbc7f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -423,6 +423,7 @@ xfs_buf_allocate_memory( out_free_pages: for (i = 0; i < bp->b_page_count; i++) __free_page(bp->b_pages[i]); + bp->b_flags &= ~_XBF_PAGES; return error; } diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 7a30b8f11db7..9d06cc30e875 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -710,6 +710,10 @@ xfs_dq_get_next_id( /* Simple advance */ next_id = *id + 1; + /* If we'd wrap past the max ID, stop */ + if (next_id < *id) + return -ENOENT; + /* If new ID is within the current chunk, advancing it sufficed */ if (next_id % mp->m_quotainfo->qi_dqperchunk) { *id = next_id; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 15a83813b708..cdc6bdd495be 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -681,7 +681,7 @@ xfs_iomap_write_allocate( xfs_trans_t *tp; int nimaps; int error = 0; - int flags = 0; + int flags = XFS_BMAPI_DELALLOC; int nres; if (whichfork == XFS_COW_FORK) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 405a65cd9d6b..f5e0f608e245 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -98,12 +98,27 @@ xfs_init_security( static void xfs_dentry_to_name( struct xfs_name *namep, + struct dentry *dentry) +{ + namep->name = dentry->d_name.name; + namep->len = dentry->d_name.len; + namep->type = XFS_DIR3_FT_UNKNOWN; +} + +static int +xfs_dentry_mode_to_name( + struct xfs_name *namep, struct dentry *dentry, int mode) { namep->name = dentry->d_name.name; namep->len = dentry->d_name.len; - namep->type = xfs_mode_to_ftype[(mode & S_IFMT) >> S_SHIFT]; + namep->type = xfs_mode_to_ftype(mode); + + if (unlikely(namep->type == XFS_DIR3_FT_UNKNOWN)) + return -EFSCORRUPTED; + + return 0; } STATIC void @@ -119,7 +134,7 @@ xfs_cleanup_inode( * xfs_init_security we must back out. * ENOSPC can hit here, among other things. */ - xfs_dentry_to_name(&teardown, dentry, 0); + xfs_dentry_to_name(&teardown, dentry); xfs_remove(XFS_I(dir), &teardown, XFS_I(inode)); } @@ -154,8 +169,12 @@ xfs_generic_create( if (error) return error; + /* Verify mode is valid also for tmpfile case */ + error = xfs_dentry_mode_to_name(&name, dentry, mode); + if (unlikely(error)) + goto out_free_acl; + if (!tmpfile) { - xfs_dentry_to_name(&name, dentry, mode); error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip); } else { error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip); @@ -248,7 +267,7 @@ xfs_vn_lookup( if (dentry->d_name.len >= MAXNAMELEN) return ERR_PTR(-ENAMETOOLONG); - xfs_dentry_to_name(&name, dentry, 0); + xfs_dentry_to_name(&name, dentry); error = xfs_lookup(XFS_I(dir), &name, &cip, NULL); if (unlikely(error)) { if (unlikely(error != -ENOENT)) @@ -275,7 +294,7 @@ xfs_vn_ci_lookup( if (dentry->d_name.len >= MAXNAMELEN) return ERR_PTR(-ENAMETOOLONG); - xfs_dentry_to_name(&xname, dentry, 0); + xfs_dentry_to_name(&xname, dentry); error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name); if (unlikely(error)) { if (unlikely(error != -ENOENT)) @@ -310,7 +329,9 @@ xfs_vn_link( struct xfs_name name; int error; - xfs_dentry_to_name(&name, dentry, inode->i_mode); + error = xfs_dentry_mode_to_name(&name, dentry, inode->i_mode); + if (unlikely(error)) + return error; error = xfs_link(XFS_I(dir), XFS_I(inode), &name); if (unlikely(error)) @@ -329,7 +350,7 @@ xfs_vn_unlink( struct xfs_name name; int error; - xfs_dentry_to_name(&name, dentry, 0); + xfs_dentry_to_name(&name, dentry); error = xfs_remove(XFS_I(dir), &name, XFS_I(d_inode(dentry))); if (error) @@ -359,7 +380,9 @@ xfs_vn_symlink( mode = S_IFLNK | (irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO); - xfs_dentry_to_name(&name, dentry, mode); + error = xfs_dentry_mode_to_name(&name, dentry, mode); + if (unlikely(error)) + goto out; error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip); if (unlikely(error)) @@ -395,6 +418,7 @@ xfs_vn_rename( { struct inode *new_inode = d_inode(ndentry); int omode = 0; + int error; struct xfs_name oname; struct xfs_name nname; @@ -405,8 +429,14 @@ xfs_vn_rename( if (flags & RENAME_EXCHANGE) omode = d_inode(ndentry)->i_mode; - xfs_dentry_to_name(&oname, odentry, omode); - xfs_dentry_to_name(&nname, ndentry, d_inode(odentry)->i_mode); + error = xfs_dentry_mode_to_name(&oname, odentry, omode); + if (omode && unlikely(error)) + return error; + + error = xfs_dentry_mode_to_name(&nname, ndentry, + d_inode(odentry)->i_mode); + if (unlikely(error)) + return error; return xfs_rename(XFS_I(odir), &oname, XFS_I(d_inode(odentry)), XFS_I(ndir), &nname, diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 68640fb63a54..1455b25205a8 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -330,11 +330,11 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y) } #define ASSERT_ALWAYS(expr) \ - (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__)) + (likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__)) #ifdef DEBUG #define ASSERT(expr) \ - (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__)) + (likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__)) #ifndef STATIC # define STATIC noinline @@ -345,7 +345,7 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y) #ifdef XFS_WARN #define ASSERT(expr) \ - (unlikely(expr) ? (void)0 : asswarn(#expr, __FILE__, __LINE__)) + (likely(expr) ? (void)0 : asswarn(#expr, __FILE__, __LINE__)) #ifndef STATIC # define STATIC static noinline diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 3b74fa011bb1..4017aa967331 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -3324,12 +3324,8 @@ xfs_log_force( xfs_mount_t *mp, uint flags) { - int error; - trace_xfs_log_force(mp, 0, _RET_IP_); - error = _xfs_log_force(mp, flags, NULL); - if (error) - xfs_warn(mp, "%s: error %d returned.", __func__, error); + _xfs_log_force(mp, flags, NULL); } /* @@ -3473,12 +3469,8 @@ xfs_log_force_lsn( xfs_lsn_t lsn, uint flags) { - int error; - trace_xfs_log_force(mp, lsn, _RET_IP_); - error = _xfs_log_force_lsn(mp, lsn, flags, NULL); - if (error) - xfs_warn(mp, "%s: error %d returned.", __func__, error); + _xfs_log_force_lsn(mp, lsn, flags, NULL); } /* diff --git a/include/linux/tcp.h b/include/linux/tcp.h index a17ae7b85218..647532b0eb03 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -62,8 +62,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { + union { + u8 val[TCP_FASTOPEN_COOKIE_MAX]; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr addr; +#endif + }; s8 len; - u8 val[TCP_FASTOPEN_COOKIE_MAX]; bool exp; /* In RFC6994 experimental option format */ }; diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 1c912f85e041..f211c348e592 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, - bool little_endian) + bool little_endian, + bool has_data_valid) { memset(hdr, 0, sizeof(*hdr)); @@ -91,7 +92,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, skb_checksum_start_offset(skb)); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); - } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + } else if (has_data_valid && + skb->ip_summed == CHECKSUM_UNNECESSARY) { hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index ea3f80f58fd6..fc7c0dbdd1ff 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -43,13 +43,12 @@ struct lwtunnel_encap_ops { int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); int (*xmit)(struct sk_buff *skb); + + struct module *owner; }; #ifdef CONFIG_LWTUNNEL -static inline void lwtstate_free(struct lwtunnel_state *lws) -{ - kfree(lws); -} +void lwtstate_free(struct lwtunnel_state *lws); static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) @@ -106,6 +105,8 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); +int lwtunnel_valid_encap_type(u16 encap_type); +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len); int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, @@ -169,6 +170,15 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, return -EOPNOTSUPP; } +static inline int lwtunnel_valid_encap_type(u16 encap_type) +{ + return -EOPNOTSUPP; +} +static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len) +{ + return -EOPNOTSUPP; +} + static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index 655a7d4c96e1..983f0b5e14f1 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -264,7 +264,7 @@ void ax25_disconnect(ax25_cb *ax25, int reason) { ax25_clear_queues(ax25); - if (!sock_flag(ax25->sk, SOCK_DESTROY)) + if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY)) ax25_stop_heartbeat(ax25); ax25_stop_t1timer(ax25); ax25_stop_t2timer(ax25); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e99037c6f7b7..04741064a173 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -781,20 +781,6 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int br_dev_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) -{ - struct net_bridge *br = netdev_priv(dev); - - if (tb[IFLA_ADDRESS]) { - spin_lock_bh(&br->lock); - br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); - spin_unlock_bh(&br->lock); - } - - return register_netdevice(dev); -} - static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], @@ -1093,6 +1079,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return 0; } +static int br_dev_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_bridge *br = netdev_priv(dev); + int err; + + if (tb[IFLA_ADDRESS]) { + spin_lock_bh(&br->lock); + br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); + spin_unlock_bh(&br->lock); + } + + err = br_changelink(dev, tb, data); + if (err) + return err; + + return register_netdevice(dev); +} + static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ diff --git a/net/core/dev.c b/net/core/dev.c index e1d731fdc72c..df51c50927ab 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2815,9 +2815,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); - } else if (illegal_highdma(skb->dev, skb)) { - features &= ~NETIF_F_SG; } + if (illegal_highdma(skb->dev, skb)) + features &= ~NETIF_F_SG; return features; } diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index e5f84c26ba1a..afa64f086d87 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -26,6 +26,7 @@ #include #include #include +#include #ifdef CONFIG_MODULES @@ -65,6 +66,15 @@ EXPORT_SYMBOL(lwtunnel_state_alloc); static const struct lwtunnel_encap_ops __rcu * lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; +void lwtstate_free(struct lwtunnel_state *lws) +{ + const struct lwtunnel_encap_ops *ops = lwtun_encaps[lws->type]; + + kfree(lws); + module_put(ops->owner); +} +EXPORT_SYMBOL(lwtstate_free); + int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, unsigned int num) { @@ -110,25 +120,77 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type, ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); + if (likely(ops && ops->build_state && try_module_get(ops->owner))) { + ret = ops->build_state(dev, encap, family, cfg, lws); + if (ret) + module_put(ops->owner); + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_build_state); + +int lwtunnel_valid_encap_type(u16 encap_type) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return ret; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + rcu_read_unlock(); #ifdef CONFIG_MODULES if (!ops) { const char *encap_type_str = lwtunnel_encap_str(encap_type); if (encap_type_str) { - rcu_read_unlock(); + __rtnl_unlock(); request_module("rtnl-lwt-%s", encap_type_str); + rtnl_lock(); + rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); + rcu_read_unlock(); } } #endif - if (likely(ops && ops->build_state)) - ret = ops->build_state(dev, encap, family, cfg, lws); - rcu_read_unlock(); + return ops ? 0 : -EOPNOTSUPP; +} +EXPORT_SYMBOL(lwtunnel_valid_encap_type); - return ret; +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) +{ + struct rtnexthop *rtnh = (struct rtnexthop *)attr; + struct nlattr *nla_entype; + struct nlattr *attrs; + struct nlattr *nla; + u16 encap_type; + int attrlen; + + while (rtnh_ok(rtnh, remaining)) { + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + attrs = rtnh_attrs(rtnh); + nla = nla_find(attrs, attrlen, RTA_ENCAP); + nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); + + if (nla_entype) { + encap_type = nla_get_u16(nla_entype); + + if (lwtunnel_valid_encap_type(encap_type) != 0) + return -EOPNOTSUPP; + } + } + rtnh = rtnh_next(rtnh, &remaining); + } + + return 0; } -EXPORT_SYMBOL(lwtunnel_build_state); +EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 30e2e21d7619..3ff9d97cf56b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1201,6 +1201,8 @@ int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); + netif_device_detach(slave_dev); + if (p->phy) { phy_stop(p->phy); p->old_pause = -1; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 3e4f183fc241..5b03d7f3b255 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -676,6 +677,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: + err = lwtunnel_valid_encap_type_attr(nla_data(attr), + nla_len(attr)); + if (err < 0) + goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; @@ -690,6 +695,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + if (err < 0) + goto errout; break; } } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a8508b79b406..6a4068031aaa 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1278,8 +1278,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif - if (fi->fib_nh->nh_lwtstate) - lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); + if (fi->fib_nh->nh_lwtstate && + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0) + goto nla_put_failure; } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1315,8 +1316,10 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif - if (nh->nh_lwtstate) - lwtunnel_fill_encap(skb, nh->nh_lwtstate); + if (nh->nh_lwtstate && + lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index fed3d29f9eb3..0fd1976ab63b 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -313,6 +313,7 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { .fill_encap = ip_tun_fill_encap_info, .get_encap_size = ip_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, + .owner = THIS_MODULE, }; static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { @@ -403,6 +404,7 @@ static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { .fill_encap = ip6_tun_fill_encap_info, .get_encap_size = ip6_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, + .owner = THIS_MODULE, }; void __init ip_tunnel_core_init(void) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8197b06d9aaa..d851cae27dac 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2440,7 +2440,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4->flowi4_tos; - r->rtm_table = table_id; + r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 4e777a3243f9..dd2560c83a85 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -113,7 +113,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, struct tcp_fastopen_cookie tmp; if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { - struct in6_addr *buf = (struct in6_addr *) tmp.val; + struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) @@ -205,6 +205,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, * scaled. So correct it appropriately. */ tp->snd_wnd = ntohs(tcp_hdr(skb)->window); + tp->max_window = tp->snd_wnd; /* Activate the retrans timer so that SYNACK can be retransmitted. * The request socket is not added to the ehash diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4bc5ba3ae452..95dfcba38ff6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5515,8 +5515,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); @@ -5525,7 +5524,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf) dev_disable_change(idev); } } - rcu_read_unlock(); } static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index e50c27a93e17..f3db364fc853 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -164,6 +164,7 @@ static const struct lwtunnel_encap_ops ila_encap_ops = { .fill_encap = ila_fill_encap_info, .get_encap_size = ila_encap_nlsize, .cmp_encap = ila_encap_cmp, + .owner = THIS_MODULE, }; int ila_lwt_init(void) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index d76674efe523..f95437f1087c 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1108,7 +1108,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, t->parms.name); goto tx_err_dst_release; } - mtu = dst_mtu(dst) - psh_hlen; + mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen; if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; @@ -1117,7 +1117,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, mtu = IPV6_MIN_MTU; if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - if (skb->len > mtu && !skb_is_gso(skb)) { + if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1b57e11e6e0d..bff4460f17be 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2885,6 +2885,11 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); + + err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, + cfg->fc_mp_len); + if (err < 0) + goto errout; } if (tb[RTA_PREF]) { @@ -2898,9 +2903,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; - if (tb[RTA_ENCAP_TYPE]) + if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + if (err < 0) + goto errout; + } + if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); @@ -3306,7 +3316,8 @@ static int rt6_fill_node(struct net *net, if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) goto nla_put_failure; - lwtunnel_fill_encap(skb, rt->dst.lwtstate); + if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 15fe97644ffe..5b77377e5a15 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -98,18 +98,19 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) } EXPORT_SYMBOL_GPL(mpls_pkt_too_big); -static u32 mpls_multipath_hash(struct mpls_route *rt, - struct sk_buff *skb, bool bos) +static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) { struct mpls_entry_decoded dec; + unsigned int mpls_hdr_len = 0; struct mpls_shim_hdr *hdr; bool eli_seen = false; int label_index; u32 hash = 0; - for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos; + for (label_index = 0; label_index < MAX_MP_SELECT_LABELS; label_index++) { - if (!pskb_may_pull(skb, sizeof(*hdr) * label_index)) + mpls_hdr_len += sizeof(*hdr); + if (!pskb_may_pull(skb, mpls_hdr_len)) break; /* Read and decode the current label */ @@ -134,37 +135,38 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, eli_seen = true; } - bos = dec.bos; - if (bos && pskb_may_pull(skb, sizeof(*hdr) * label_index + - sizeof(struct iphdr))) { + if (!dec.bos) + continue; + + /* found bottom label; does skb have room for a header? */ + if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) { const struct iphdr *v4hdr; - v4hdr = (const struct iphdr *)(mpls_hdr(skb) + - label_index); + v4hdr = (const struct iphdr *)(hdr + 1); if (v4hdr->version == 4) { hash = jhash_3words(ntohl(v4hdr->saddr), ntohl(v4hdr->daddr), v4hdr->protocol, hash); } else if (v4hdr->version == 6 && - pskb_may_pull(skb, sizeof(*hdr) * label_index + - sizeof(struct ipv6hdr))) { + pskb_may_pull(skb, mpls_hdr_len + + sizeof(struct ipv6hdr))) { const struct ipv6hdr *v6hdr; - v6hdr = (const struct ipv6hdr *)(mpls_hdr(skb) + - label_index); - + v6hdr = (const struct ipv6hdr *)(hdr + 1); hash = __ipv6_addr_jhash(&v6hdr->saddr, hash); hash = __ipv6_addr_jhash(&v6hdr->daddr, hash); hash = jhash_1word(v6hdr->nexthdr, hash); } } + + break; } return hash; } static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, - struct sk_buff *skb, bool bos) + struct sk_buff *skb) { int alive = ACCESS_ONCE(rt->rt_nhn_alive); u32 hash = 0; @@ -180,7 +182,7 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, if (alive <= 0) return NULL; - hash = mpls_multipath_hash(rt, skb, bos); + hash = mpls_multipath_hash(rt, skb); nh_index = hash % alive; if (alive == rt->rt_nhn) goto out; @@ -278,17 +280,11 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, hdr = mpls_hdr(skb); dec = mpls_entry_decode(hdr); - /* Pop the label */ - skb_pull(skb, sizeof(*hdr)); - skb_reset_network_header(skb); - - skb_orphan(skb); - rt = mpls_route_input_rcu(net, dec.label); if (!rt) goto drop; - nh = mpls_select_multipath(rt, skb, dec.bos); + nh = mpls_select_multipath(rt, skb); if (!nh) goto drop; @@ -297,6 +293,12 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, if (!mpls_output_possible(out_dev)) goto drop; + /* Pop the label */ + skb_pull(skb, sizeof(*hdr)); + skb_reset_network_header(skb); + + skb_orphan(skb); + if (skb_warn_if_lro(skb)) goto drop; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index cf52cf30ac4b..bc9aaf58c7cc 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -218,6 +218,7 @@ static const struct lwtunnel_encap_ops mpls_iptun_ops = { .fill_encap = mpls_fill_encap_info, .get_encap_size = mpls_encap_nlsize, .cmp_encap = mpls_encap_cmp, + .owner = THIS_MODULE, }; static int __init mpls_iptunnel_init(void) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index fecefa2dc94e..eab210bb1ef0 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -514,7 +514,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, int hooknum, nh_off, err = NF_ACCEPT; nh_off = skb_network_offset(skb); - skb_pull(skb, nh_off); + skb_pull_rcsum(skb, nh_off); /* See HOOK2MANIP(). */ if (maniptype == NF_NAT_MANIP_SRC) @@ -579,6 +579,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, err = nf_nat_packet(ct, ctinfo, hooknum, skb); push: skb_push(skb, nh_off); + skb_postpush_rcsum(skb, skb->data, nh_off); return err; } @@ -890,7 +891,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, /* The conntrack module expects to be working at L3. */ nh_ofs = skb_network_offset(skb); - skb_pull(skb, nh_ofs); + skb_pull_rcsum(skb, nh_ofs); if (key->ip.frag != OVS_FRAG_TYPE_NONE) { err = handle_fragments(net, key, info->zone.id, skb); @@ -904,6 +905,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, err = ovs_ct_lookup(net, key, info, skb); skb_push(skb, nh_ofs); + skb_postpush_rcsum(skb, skb->data, nh_ofs); if (err) kfree_skb(skb); return err; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index dd2332390c45..94e4a5941d89 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1972,7 +1972,7 @@ static int __packet_rcv_vnet(const struct sk_buff *skb, { *vnet_hdr = (const struct virtio_net_hdr) { 0 }; - if (virtio_net_hdr_from_skb(skb, vnet_hdr, vio_le())) + if (virtio_net_hdr_from_skb(skb, vnet_hdr, vio_le(), true)) BUG(); return 0; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f893d180da1c..c6c2a93cc2a2 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -903,8 +903,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, goto err; } act->order = i; - if (event == RTM_GETACTION) - act->tcfa_refcnt++; list_add_tail(&act->list, &actions); } @@ -917,7 +915,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, return ret; } err: - tcf_action_destroy(&actions, 0); + if (event != RTM_GETACTION) + tcf_action_destroy(&actions, 0); return ret; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2358f2690ec5..2d03d5bcb5b9 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -995,6 +995,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) unsigned int hash; struct unix_address *addr; struct hlist_head *list; + struct path path = { NULL, NULL }; err = -EINVAL; if (sunaddr->sun_family != AF_UNIX) @@ -1010,9 +1011,20 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; + if (sun_path[0]) { + umode_t mode = S_IFSOCK | + (SOCK_INODE(sock)->i_mode & ~current_umask()); + err = unix_mknod(sun_path, mode, &path); + if (err) { + if (err == -EEXIST) + err = -EADDRINUSE; + goto out; + } + } + err = mutex_lock_interruptible(&u->bindlock); if (err) - goto out; + goto out_put; err = -EINVAL; if (u->addr) @@ -1029,16 +1041,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) atomic_set(&addr->refcnt, 1); if (sun_path[0]) { - struct path path; - umode_t mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); - if (err) { - if (err == -EEXIST) - err = -EADDRINUSE; - unix_release_addr(addr); - goto out_up; - } addr->hash = UNIX_HASH_SIZE; hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); @@ -1065,6 +1067,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) spin_unlock(&unix_table_lock); out_up: mutex_unlock(&u->bindlock); +out_put: + if (err) + path_put(&path); out: return err; }