diff options
61 files changed, 612 insertions, 330 deletions
diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index 2df5894353d6..cd7303d7fa25 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -1009,16 +1009,18 @@ The kernel interface functions are as follows: (*) Check call still alive. - u32 rxrpc_kernel_check_life(struct socket *sock, - struct rxrpc_call *call); + bool rxrpc_kernel_check_life(struct socket *sock, + struct rxrpc_call *call, + u32 *_life); void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call); - The first function returns a number that is updated when ACKs are received - from the peer (notably including PING RESPONSE ACKs which we can elicit by - sending PING ACKs to see if the call still exists on the server). The - caller should compare the numbers of two calls to see if the call is still - alive after waiting for a suitable interval. + The first function passes back in *_life a number that is updated when + ACKs are received from the peer (notably including PING RESPONSE ACKs + which we can elicit by sending PING ACKs to see if the call still exists + on the server). The caller should compare the numbers of two calls to see + if the call is still alive after waiting for a suitable interval. It also + returns true as long as the call hasn't yet reached the completed state. This allows the caller to work out if the server is still contactable and if the call is still alive on the server while waiting for the server to diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index 4ab8b1b6608f..a14e35d40538 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -710,10 +710,10 @@ base_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) struct sock *sk = sock->sk; int err = 0; - if (!maddr || maddr->family != AF_ISDN) + if (addr_len < sizeof(struct sockaddr_mISDN)) return -EINVAL; - if (addr_len < sizeof(struct sockaddr_mISDN)) + if (!maddr || maddr->family != AF_ISDN) return -EINVAL; lock_sock(sk); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 28eac9056211..c032bef1b776 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -32,6 +32,13 @@ #define DRV_NAME "nicvf" #define DRV_VERSION "1.0" +/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs + * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed + * this value, keeping headroom for the 14 byte Ethernet header and two + * VLAN tags (for QinQ) + */ +#define MAX_XDP_MTU (1530 - ETH_HLEN - VLAN_HLEN * 2) + /* Supported devices */ static const struct pci_device_id nicvf_id_table[] = { { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, @@ -1582,6 +1589,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) struct nicvf *nic = netdev_priv(netdev); int orig_mtu = netdev->mtu; + /* For now just support only the usual MTU sized frames, + * plus some headroom for VLAN, QinQ. + */ + if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) { + netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n", + netdev->mtu); + return -EINVAL; + } + netdev->mtu = new_mtu; if (!netif_running(netdev)) @@ -1830,8 +1846,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog) bool bpf_attached = false; int ret = 0; - /* For now just support only the usual MTU sized frames */ - if (prog && (dev->mtu > 1500)) { + /* For now just support only the usual MTU sized frames, + * plus some headroom for VLAN, QinQ. + */ + if (prog && dev->mtu > MAX_XDP_MTU) { netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n", dev->mtu); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 697c2427f2b7..a96ad20ee484 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1840,13 +1840,9 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) int ret; if (enable) { - ret = clk_prepare_enable(fep->clk_ahb); - if (ret) - return ret; - ret = clk_prepare_enable(fep->clk_enet_out); if (ret) - goto failed_clk_enet_out; + return ret; if (fep->clk_ptp) { mutex_lock(&fep->ptp_clk_mutex); @@ -1866,7 +1862,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) phy_reset_after_clk_enable(ndev->phydev); } else { - clk_disable_unprepare(fep->clk_ahb); clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { mutex_lock(&fep->ptp_clk_mutex); @@ -1885,8 +1880,6 @@ failed_clk_ref: failed_clk_ptp: if (fep->clk_enet_out) clk_disable_unprepare(fep->clk_enet_out); -failed_clk_enet_out: - clk_disable_unprepare(fep->clk_ahb); return ret; } @@ -3470,6 +3463,9 @@ fec_probe(struct platform_device *pdev) ret = clk_prepare_enable(fep->clk_ipg); if (ret) goto failed_clk_ipg; + ret = clk_prepare_enable(fep->clk_ahb); + if (ret) + goto failed_clk_ahb; fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy"); if (!IS_ERR(fep->reg_phy)) { @@ -3563,6 +3559,9 @@ failed_reset: pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); failed_regulator: + clk_disable_unprepare(fep->clk_ahb); +failed_clk_ahb: + clk_disable_unprepare(fep->clk_ipg); failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: @@ -3686,6 +3685,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); + clk_disable_unprepare(fep->clk_ahb); clk_disable_unprepare(fep->clk_ipg); return 0; @@ -3695,8 +3695,20 @@ static int __maybe_unused fec_runtime_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); + int ret; - return clk_prepare_enable(fep->clk_ipg); + ret = clk_prepare_enable(fep->clk_ahb); + if (ret) + return ret; + ret = clk_prepare_enable(fep->clk_ipg); + if (ret) + goto failed_clk_ipg; + + return 0; + +failed_clk_ipg: + clk_disable_unprepare(fep->clk_ahb); + return ret; } static const struct dev_pm_ops fec_pm_ops = { diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 51cfe95f3e24..3dfb2d131eb7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3762,6 +3762,7 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf; + netdev_features_t old_hw_features = 0; union ibmvnic_crq crq; int i; @@ -3837,24 +3838,41 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter) adapter->ip_offload_ctrl.large_rx_ipv4 = 0; adapter->ip_offload_ctrl.large_rx_ipv6 = 0; - adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO; + if (adapter->state != VNIC_PROBING) { + old_hw_features = adapter->netdev->hw_features; + adapter->netdev->hw_features = 0; + } + + adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO; if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum) - adapter->netdev->features |= NETIF_F_IP_CSUM; + adapter->netdev->hw_features |= NETIF_F_IP_CSUM; if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum) - adapter->netdev->features |= NETIF_F_IPV6_CSUM; + adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM; if ((adapter->netdev->features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) - adapter->netdev->features |= NETIF_F_RXCSUM; + adapter->netdev->hw_features |= NETIF_F_RXCSUM; if (buf->large_tx_ipv4) - adapter->netdev->features |= NETIF_F_TSO; + adapter->netdev->hw_features |= NETIF_F_TSO; if (buf->large_tx_ipv6) - adapter->netdev->features |= NETIF_F_TSO6; + adapter->netdev->hw_features |= NETIF_F_TSO6; - adapter->netdev->hw_features |= adapter->netdev->features; + if (adapter->state == VNIC_PROBING) { + adapter->netdev->features |= adapter->netdev->hw_features; + } else if (old_hw_features != adapter->netdev->hw_features) { + netdev_features_t tmp = 0; + + /* disable features no longer supported */ + adapter->netdev->features &= adapter->netdev->hw_features; + /* turn on features now supported if previously enabled */ + tmp = (old_hw_features ^ adapter->netdev->hw_features) & + adapter->netdev->hw_features; + adapter->netdev->features |= + tmp & adapter->netdev->wanted_features; + } memset(&crq, 0, sizeof(crq)); crq.control_ip_offload.first = IBMVNIC_CRQ_CMD; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index d23d53c0e284..f26a4ca29363 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -568,7 +568,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX)) return 0; - emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0); + emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0); if (!emad_wq) return -ENOMEM; mlxsw_core->emad_wq = emad_wq; @@ -1958,10 +1958,10 @@ static int __init mlxsw_core_module_init(void) { int err; - mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0); + mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0); if (!mlxsw_wq) return -ENOMEM; - mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM, + mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0, mlxsw_core_driver_name); if (!mlxsw_owq) { err = -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 9a79b5e11597..d633bef5f105 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -70,6 +70,7 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp2_sb_pool_dess[] = { {MLXSW_REG_SBXX_DIR_EGRESS, 1}, {MLXSW_REG_SBXX_DIR_EGRESS, 2}, {MLXSW_REG_SBXX_DIR_EGRESS, 3}, + {MLXSW_REG_SBXX_DIR_EGRESS, 15}, }; #define MLXSW_SP_SB_ING_TC_COUNT 8 @@ -428,6 +429,7 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = { MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI), }; static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, @@ -517,14 +519,14 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_egress[] = { MLXSW_SP_SB_CM(0, 7, 4), MLXSW_SP_SB_CM(0, 7, 4), MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), MLXSW_SP_SB_CM(1, 0xff, 4), }; @@ -671,6 +673,7 @@ static const struct mlxsw_sp_sb_pm mlxsw_sp2_sb_pms[] = { MLXSW_SP_SB_PM(0, 0), MLXSW_SP_SB_PM(0, 0), MLXSW_SP_SB_PM(0, 0), + MLXSW_SP_SB_PM(10000, 90000), }; static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 52fed8c7bf1e..902e766a8ed3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6781,7 +6781,7 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp, /* A RIF is not created for macvlan netdevs. Their MAC is used to * populate the FDB */ - if (netif_is_macvlan(dev)) + if (netif_is_macvlan(dev) || netif_is_l3_master(dev)) return 0; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index f6ce386c3036..50111f228d77 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1630,7 +1630,7 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid_index; int err = 0; - if (switchdev_trans_ph_prepare(trans)) + if (switchdev_trans_ph_commit(trans)) return 0; bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 7cde387e5ec6..51cd57ab3d95 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -2366,6 +2366,7 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size, dma_object->addr))) { vxge_os_dma_free(devh->pdev, memblock, &dma_object->acc_handle); + memblock = NULL; goto exit; } diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 43a57ec296fd..127c89b22ef0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -431,12 +431,16 @@ struct qed_qm_info { u8 num_pf_rls; }; +#define QED_OVERFLOW_BIT 1 + struct qed_db_recovery_info { struct list_head list; /* Lock to protect the doorbell recovery mechanism list */ spinlock_t lock; + bool dorq_attn; u32 db_recovery_counter; + unsigned long overflow; }; struct storm_stats { @@ -920,8 +924,7 @@ u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc); /* doorbell recovery mechanism */ void qed_db_recovery_dp(struct qed_hwfn *p_hwfn); -void qed_db_recovery_execute(struct qed_hwfn *p_hwfn, - enum qed_db_rec_exec db_exec); +void qed_db_recovery_execute(struct qed_hwfn *p_hwfn); bool qed_edpm_enabled(struct qed_hwfn *p_hwfn); /* Other Linux specific common definitions */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 9df8c4b3b54e..866cdc86a3f2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -102,11 +102,15 @@ static void qed_db_recovery_dp_entry(struct qed_hwfn *p_hwfn, /* Doorbell address sanity (address within doorbell bar range) */ static bool qed_db_rec_sanity(struct qed_dev *cdev, - void __iomem *db_addr, void *db_data) + void __iomem *db_addr, + enum qed_db_rec_width db_width, + void *db_data) { + u32 width = (db_width == DB_REC_WIDTH_32B) ? 32 : 64; + /* Make sure doorbell address is within the doorbell bar */ if (db_addr < cdev->doorbells || - (u8 __iomem *)db_addr > + (u8 __iomem *)db_addr + width > (u8 __iomem *)cdev->doorbells + cdev->db_size) { WARN(true, "Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n", @@ -159,7 +163,7 @@ int qed_db_recovery_add(struct qed_dev *cdev, } /* Sanitize doorbell address */ - if (!qed_db_rec_sanity(cdev, db_addr, db_data)) + if (!qed_db_rec_sanity(cdev, db_addr, db_width, db_data)) return -EINVAL; /* Obtain hwfn from doorbell address */ @@ -205,10 +209,6 @@ int qed_db_recovery_del(struct qed_dev *cdev, return 0; } - /* Sanitize doorbell address */ - if (!qed_db_rec_sanity(cdev, db_addr, db_data)) - return -EINVAL; - /* Obtain hwfn from doorbell address */ p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr); @@ -300,31 +300,24 @@ void qed_db_recovery_dp(struct qed_hwfn *p_hwfn) /* Ring the doorbell of a single doorbell recovery entry */ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn, - struct qed_db_recovery_entry *db_entry, - enum qed_db_rec_exec db_exec) -{ - if (db_exec != DB_REC_ONCE) { - /* Print according to width */ - if (db_entry->db_width == DB_REC_WIDTH_32B) { - DP_VERBOSE(p_hwfn, QED_MSG_SPQ, - "%s doorbell address %p data %x\n", - db_exec == DB_REC_DRY_RUN ? - "would have rung" : "ringing", - db_entry->db_addr, - *(u32 *)db_entry->db_data); - } else { - DP_VERBOSE(p_hwfn, QED_MSG_SPQ, - "%s doorbell address %p data %llx\n", - db_exec == DB_REC_DRY_RUN ? - "would have rung" : "ringing", - db_entry->db_addr, - *(u64 *)(db_entry->db_data)); - } + struct qed_db_recovery_entry *db_entry) +{ + /* Print according to width */ + if (db_entry->db_width == DB_REC_WIDTH_32B) { + DP_VERBOSE(p_hwfn, QED_MSG_SPQ, + "ringing doorbell address %p data %x\n", + db_entry->db_addr, + *(u32 *)db_entry->db_data); + } else { + DP_VERBOSE(p_hwfn, QED_MSG_SPQ, + "ringing doorbell address %p data %llx\n", + db_entry->db_addr, + *(u64 *)(db_entry->db_data)); } /* Sanity */ if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr, - db_entry->db_data)) + db_entry->db_width, db_entry->db_data)) return; /* Flush the write combined buffer. Since there are multiple doorbelling @@ -334,14 +327,12 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn, wmb(); /* Ring the doorbell */ - if (db_exec == DB_REC_REAL_DEAL || db_exec == DB_REC_ONCE) { - if (db_entry->db_width == DB_REC_WIDTH_32B) - DIRECT_REG_WR(db_entry->db_addr, - *(u32 *)(db_entry->db_data)); - else - DIRECT_REG_WR64(db_entry->db_addr, - *(u64 *)(db_entry->db_data)); - } + if (db_entry->db_width == DB_REC_WIDTH_32B) + DIRECT_REG_WR(db_entry->db_addr, + *(u32 *)(db_entry->db_data)); + else + DIRECT_REG_WR64(db_entry->db_addr, + *(u64 *)(db_entry->db_data)); /* Flush the write combined buffer. Next doorbell may come from a * different entity to the same address... @@ -350,29 +341,21 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn, } /* Traverse the doorbell recovery entry list and ring all the doorbells */ -void qed_db_recovery_execute(struct qed_hwfn *p_hwfn, - enum qed_db_rec_exec db_exec) +void qed_db_recovery_execute(struct qed_hwfn *p_hwfn) { struct qed_db_recovery_entry *db_entry = NULL; - if (db_exec != DB_REC_ONCE) { - DP_NOTICE(p_hwfn, - "Executing doorbell recovery. Counter was %d\n", - p_hwfn->db_recovery_info.db_recovery_counter); + DP_NOTICE(p_hwfn, "Executing doorbell recovery. Counter was %d\n", + p_hwfn->db_recovery_info.db_recovery_counter); - /* Track amount of times recovery was executed */ - p_hwfn->db_recovery_info.db_recovery_counter++; - } + /* Track amount of times recovery was executed */ + p_hwfn->db_recovery_info.db_recovery_counter++; /* Protect the list */ spin_lock_bh(&p_hwfn->db_recovery_info.lock); list_for_each_entry(db_entry, - &p_hwfn->db_recovery_info.list, list_entry) { - qed_db_recovery_ring(p_hwfn, db_entry, db_exec); - if (db_exec == DB_REC_ONCE) - break; - } - + &p_hwfn->db_recovery_info.list, list_entry) + qed_db_recovery_ring(p_hwfn, db_entry); spin_unlock_bh(&p_hwfn->db_recovery_info.lock); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index e23980e301b6..8848d5bed6e5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -378,6 +378,9 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn, u32 count = QED_DB_REC_COUNT; u32 usage = 1; + /* Flush any pending (e)dpms as they may never arrive */ + qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1); + /* wait for usage to zero or count to run out. This is necessary since * EDPM doorbell transactions can take multiple 64b cycles, and as such * can "split" over the pci. Possibly, the doorbell drop can happen with @@ -406,51 +409,74 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn, int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - u32 overflow; + u32 attn_ovfl, cur_ovfl; int rc; - overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY); - DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow); - if (!overflow) { - qed_db_recovery_execute(p_hwfn, DB_REC_ONCE); + attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT, + &p_hwfn->db_recovery_info.overflow); + cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY); + if (!cur_ovfl && !attn_ovfl) return 0; - } - if (qed_edpm_enabled(p_hwfn)) { + DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n", + attn_ovfl, cur_ovfl); + + if (cur_ovfl && !p_hwfn->db_bar_no_edpm) { rc = qed_db_rec_flush_queue(p_hwfn, p_ptt); if (rc) return rc; } - /* Flush any pending (e)dpm as they may never arrive */ - qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1); - /* Release overflow sticky indication (stop silently dropping everything) */ qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0); /* Repeat all last doorbells (doorbell drop recovery) */ - qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL); + qed_db_recovery_execute(p_hwfn); return 0; } -static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) +static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn) { - u32 int_sts, first_drop_reason, details, address, all_drops_reason; struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt; + u32 overflow; int rc; - int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS); - DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts); + overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY); + if (!overflow) + goto out; + + /* Run PF doorbell recovery in next periodic handler */ + set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow); + + if (!p_hwfn->db_bar_no_edpm) { + rc = qed_db_rec_flush_queue(p_hwfn, p_ptt); + if (rc) + goto out; + } + + qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0); +out: + /* Schedule the handler even if overflow was not detected */ + qed_periodic_db_rec_start(p_hwfn); +} + +static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn) +{ + u32 int_sts, first_drop_reason, details, address, all_drops_reason; + struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt; /* int_sts may be zero since all PFs were interrupted for doorbell * overflow but another one already handled it. Can abort here. If * This PF also requires overflow recovery we will be interrupted again. * The masked almost full indication may also be set. Ignoring. */ + int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS); if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL)) return 0; + DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts); + /* check if db_drop or overflow happened */ if (int_sts & (DORQ_REG_INT_STS_DB_DROP | DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) { @@ -477,11 +503,6 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4, first_drop_reason, all_drops_reason); - rc = qed_db_rec_handler(p_hwfn, p_ptt); - qed_periodic_db_rec_start(p_hwfn); - if (rc) - return rc; - /* Clear the doorbell drop details and prepare for next drop */ qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0); @@ -507,6 +528,25 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) return -EINVAL; } +static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) +{ + p_hwfn->db_recovery_info.dorq_attn = true; + qed_dorq_attn_overflow(p_hwfn); + + return qed_dorq_attn_int_sts(p_hwfn); +} + +static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn) +{ + if (p_hwfn->db_recovery_info.dorq_attn) + goto out; + + /* Call DORQ callback if the attention was missed */ + qed_dorq_attn_cb(p_hwfn); +out: + p_hwfn->db_recovery_info.dorq_attn = false; +} + /* Instead of major changes to the data-structure, we have a some 'special' * identifiers for sources that changed meaning between adapters. */ @@ -1080,6 +1120,9 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, } } + /* Handle missed DORQ attention */ + qed_dorq_attn_handler(p_hwfn); + /* Clear IGU indication for the deasserted bits */ DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_IGU_CMD + diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index 1f356ed4f761..d473b522afc5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -192,8 +192,8 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev); /** * @brief - Doorbell Recovery handler. - * Run DB_REAL_DEAL doorbell recovery in case of PF overflow - * (and flush DORQ if needed), otherwise run DB_REC_ONCE. + * Run doorbell recovery in case of PF overflow (and flush DORQ if + * needed). * * @param p_hwfn * @param p_ptt diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index f164d4acebcb..6de23b56b294 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -970,7 +970,7 @@ static void qed_update_pf_params(struct qed_dev *cdev, } } -#define QED_PERIODIC_DB_REC_COUNT 100 +#define QED_PERIODIC_DB_REC_COUNT 10 #define QED_PERIODIC_DB_REC_INTERVAL_MS 100 #define QED_PERIODIC_DB_REC_INTERVAL \ msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS) diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 5f3f42a25361..bddb2b5982dc 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -490,18 +490,17 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc) ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev); if (IS_ERR(ptp->clock)) { - rc = -EINVAL; DP_ERR(edev, "PTP clock registration failed\n"); + qede_ptp_disable(edev); + rc = -EINVAL; goto err2; } return 0; -err2: - qede_ptp_disable(edev); - ptp->clock = NULL; err1: kfree(ptp); +err2: edev->ptp = NULL; return rc; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 6ed96fdfd96d..9ce61b019aad 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1246,6 +1246,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev, goto err_option_port_add; } + /* set promiscuity level to new slave */ + if (dev->flags & IFF_PROMISC) { + err = dev_set_promiscuity(port_dev, 1); + if (err) + goto err_set_slave_promisc; + } + + /* set allmulti level to new slave */ + if (dev->flags & IFF_ALLMULTI) { + err = dev_set_allmulti(port_dev, 1); + if (err) { + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(port_dev, -1); + goto err_set_slave_promisc; + } + } + netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); dev_mc_sync_multiple(port_dev, dev); @@ -1262,6 +1279,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return 0; +err_set_slave_promisc: + __team_option_inst_del_port(team, port); + err_option_port_add: team_upper_dev_unlink(team, port); @@ -1307,6 +1327,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev) team_port_disable(team, port); list_del_rcu(&port->list); + + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(port_dev, -1); + if (dev->flags & IFF_ALLMULTI) + dev_set_allmulti(port_dev, -1); + team_upper_dev_unlink(team, port); netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5ace833de746..351af88231ad 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -911,8 +911,12 @@ static int vhost_new_umem_range(struct vhost_umem *umem, u64 start, u64 size, u64 end, u64 userspace_addr, int perm) { - struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC); + struct vhost_umem_node *tmp, *node; + if (!size) + return -EFAULT; + + node = kmalloc(sizeof(*node), GFP_ATOMIC); if (!node) return -ENOMEM; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 2c588f9bbbda..c14001b42d20 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -610,6 +610,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, bool stalled = false; u64 rtt; u32 life, last_life; + bool rxrpc_complete = false; DECLARE_WAITQUEUE(myself, current); @@ -621,7 +622,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, rtt2 = 2; timeout = rtt2; - last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); + rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life); add_wait_queue(&call->waitq, &myself); for (;;) { @@ -639,7 +640,12 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, if (afs_check_call_state(call, AFS_CALL_COMPLETE)) break; - life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); + if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) { + /* rxrpc terminated the call. */ + rxrpc_complete = true; + break; + } + if (timeout == 0 && life == last_life && signal_pending(current)) { if (stalled) @@ -663,12 +669,16 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); - /* Kill off the call if it's still live. */ if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) { - _debug("call interrupted"); - if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - RX_USER_ABORT, -EINTR, "KWI")) - afs_set_call_complete(call, -EINTR, 0); + if (rxrpc_complete) { + afs_set_call_complete(call, call->error, call->abort_code); + } else { + /* Kill off the call if it's still live. */ + _debug("call interrupted"); + if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + RX_USER_ABORT, -EINTR, "KWI")) + afs_set_call_complete(call, -EINTR, 0); + } } spin_lock_bh(&call->state_lock); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 26f69cf763f4..324e872c91d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1500,6 +1500,7 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device + * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1532,6 +1533,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, + IFF_LIVE_RENAME_OK = 1<<30, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1563,6 +1565,7 @@ enum netdev_priv_flags { #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER +#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK /** * struct net_device - The DEVICE structure. diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 2bfb87eb98ce..78c856cba4f5 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -61,10 +61,12 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); -u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *); +bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *, + u32 *); void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *); u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *, ktime_t *); +bool rxrpc_kernel_call_is_complete(struct rxrpc_call *); #endif /* _NET_RXRPC_H */ diff --git a/include/net/netrom.h b/include/net/netrom.h index 5a0714ff500f..80f15b1c1a48 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -266,7 +266,7 @@ void nr_stop_idletimer(struct sock *); int nr_t1timer_running(struct sock *); /* sysctl_net_netrom.c */ -void nr_register_sysctl(void); +int nr_register_sysctl(void); void nr_unregister_sysctl(void); #endif diff --git a/include/net/sock.h b/include/net/sock.h index 8de5ee258b93..341f8bafa0cf 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2084,12 +2084,6 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) * @p: poll_table * * See the comments in the wq_has_sleeper function. - * - * Do not derive sock from filp->private_data here. An SMC socket establishes - * an internal TCP socket that is used in the fallback case. All socket - * operations on the SMC socket are then forwarded to the TCP socket. In case of - * poll, the filp->private_data pointer references the SMC socket because the - * TCP socket has no file assigned. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) diff --git a/include/net/tls.h b/include/net/tls.h index a5a938583295..5934246b2c6f 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -307,6 +307,7 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_device_sk_destruct(struct sock *sk); +void tls_device_free_resources_tx(struct sock *sk); void tls_device_init(void); void tls_device_cleanup(void); int tls_tx_records(struct sock *sk, int flags); @@ -330,6 +331,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx, int flags); int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, int flags); +bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { @@ -379,7 +381,7 @@ tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) { #ifdef CONFIG_SOCK_VALIDATE_XMIT - return sk_fullsock(sk) & + return sk_fullsock(sk) && (smp_load_acquire(&sk->sk_validate_xmit_skb) == &tls_validate_xmit_skb); #else diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 9a580999ca57..d892b7c3cc42 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -523,12 +523,12 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, struct sock *sk = sock->sk; int err = 0; - BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); - if (!addr || addr_len < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; + BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); + lock_sock(sk); if (sk->sk_state != BT_OPEN) { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 02da21d771c9..45e7f4173bba 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2031,7 +2031,8 @@ static void br_multicast_start_querier(struct net_bridge *br, __br_multicast_open(br, query); - list_for_each_entry(port, &br->port_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(port, &br->port_list, list) { if (port->state == BR_STATE_DISABLED || port->state == BR_STATE_BLOCKING) continue; @@ -2043,6 +2044,7 @@ static void br_multicast_start_querier(struct net_bridge *br, br_multicast_enable(&port->ip6_own_query); #endif } + rcu_read_unlock(); } int br_multicast_toggle(struct net_bridge *br, unsigned long val) diff --git a/net/core/dev.c b/net/core/dev.c index fdcff29df915..f409406254dd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1184,7 +1184,21 @@ int dev_change_name(struct net_device *dev, const char *newname) BUG_ON(!dev_net(dev)); net = dev_net(dev); - if (dev->flags & IFF_UP) + + /* Some auto-enslaved devices e.g. failover slaves are + * special, as userspace might rename the device after + * the interface had been brought up and running since + * the point kernel initiated auto-enslavement. Allow + * live name change even when these slave devices are + * up and running. + * + * Typically, users of these auto-enslaving devices + * don't actually care about slave name change, as + * they are supposed to operate on master interface + * directly. + */ + if (dev->flags & IFF_UP && + likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; write_seqcount_begin(&devnet_rename_seq); diff --git a/net/core/failover.c b/net/core/failover.c index 4a92a98ccce9..b5cd3c727285 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev) goto err_upper_link; } - slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; + slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); err_upper_link: netdev_rx_handler_unregister(slave_dev); done: @@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev) netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) diff --git a/net/core/filter.c b/net/core/filter.c index fc92ebc4e200..27e61ffd9039 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4383,6 +4383,8 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, * Only binding to IP is supported. */ err = -EINVAL; + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a51cab95ba64..220c56e93659 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4948,7 +4948,7 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check, { struct if_stats_msg *ifsm; - if (nlh->nlmsg_len < sizeof(*ifsm)) { + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) { NL_SET_ERR_MSG(extack, "Invalid header for stats dump"); return -EINVAL; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 79e98e21cdd7..12ce6c526d72 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -121,6 +121,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) struct guehdr *guehdr; void *data; u16 doffset = 0; + u8 proto_ctype; if (!fou) return 1; @@ -212,13 +213,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(guehdr->control)) return gue_control_message(skb, guehdr); + proto_ctype = guehdr->proto_ctype; __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); if (iptunnel_pull_offloads(skb)) goto drop; - return -guehdr->proto_ctype; + return -proto_ctype; drop: kfree_skb(skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a5da63e5faa2..88ce038dd495 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1185,9 +1185,23 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) static void ipv4_link_failure(struct sk_buff *skb) { + struct ip_options opt; struct rtable *rt; + int res; - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + /* Recompile ip options since IPCB may not be valid anymore. + */ + memset(&opt, 0, sizeof(opt)); + opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + + if (res) + return; + + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); rt = skb_rtable(skb); if (rt) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 359da68d7c06..477cb4aa456c 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -49,9 +49,8 @@ #define DCTCP_MAX_ALPHA 1024U struct dctcp { - u32 acked_bytes_ecn; - u32 acked_bytes_total; - u32 prior_snd_una; + u32 old_delivered; + u32 old_delivered_ce; u32 prior_rcv_nxt; u32 dctcp_alpha; u32 next_seq; @@ -73,8 +72,8 @@ static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) { ca->next_seq = tp->snd_nxt; - ca->acked_bytes_ecn = 0; - ca->acked_bytes_total = 0; + ca->old_delivered = tp->delivered; + ca->old_delivered_ce = tp->delivered_ce; } static void dctcp_init(struct sock *sk) @@ -86,7 +85,6 @@ static void dctcp_init(struct sock *sk) sk->sk_state == TCP_CLOSE)) { struct dctcp *ca = inet_csk_ca(sk); - ca->prior_snd_una = tp->snd_una; ca->prior_rcv_nxt = tp->rcv_nxt; ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); @@ -118,37 +116,25 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct dctcp *ca = inet_csk_ca(sk); - u32 acked_bytes = tp->snd_una - ca->prior_snd_una; - - /* If ack did not advance snd_una, count dupack as MSS size. - * If ack did update window, do not count it at all. - */ - if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE)) - acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss; - if (acked_bytes) { - ca->acked_bytes_total += acked_bytes; - ca->prior_snd_una = tp->snd_una; - - if (flags & CA_ACK_ECE) - ca->acked_bytes_ecn += acked_bytes; - } /* Expired RTT */ if (!before(tp->snd_una, ca->next_seq)) { - u64 bytes_ecn = ca->acked_bytes_ecn; + u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; u32 alpha = ca->dctcp_alpha; /* alpha = (1 - g) * alpha + g * F */ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); - if (bytes_ecn) { + if (delivered_ce) { + u32 delivered = tp->delivered - ca->old_delivered; + /* If dctcp_shift_g == 1, a 32bit value would overflow - * after 8 Mbytes. + * after 8 M packets. */ - bytes_ecn <<= (10 - dctcp_shift_g); - do_div(bytes_ecn, max(1U, ca->acked_bytes_total)); + delivered_ce <<= (10 - dctcp_shift_g); + delivered_ce /= max(1U, delivered); - alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA); + alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA); } /* dctcp_alpha can be read from dctcp_get_info() without * synchro, so we ask compiler to not use dctcp_alpha @@ -200,6 +186,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct dctcp *ca = inet_csk_ca(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* Fill it also in case of VEGASINFO due to req struct limits. * We can still correctly retrieve it later. @@ -211,8 +198,10 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, info->dctcp.dctcp_enabled = 1; info->dctcp.dctcp_ce_state = (u16) ca->ce_state; info->dctcp.dctcp_alpha = ca->dctcp_alpha; - info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn; - info->dctcp.dctcp_ab_tot = ca->acked_bytes_total; + info->dctcp.dctcp_ab_ecn = tp->mss_cache * + (tp->delivered_ce - ca->old_delivered_ce); + info->dctcp.dctcp_ab_tot = tp->mss_cache * + (tp->delivered - ca->old_delivered); } *attr = INET_DIAG_DCTCPINFO; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b444483cdb2b..622eeaf5732b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1047,6 +1047,8 @@ static void udp_v6_flush_pending_frames(struct sock *sk) static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; /* The following checks are replicated from __ip6_datagram_connect() * and intended to prevent BPF program called below from accessing * bytes that are out of the bound specified by user in addr_len. diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index b99e73a7e7e0..2017b7d780f5 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -320,14 +320,13 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) struct llc_sap *sap; int rc = -EINVAL; - dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); - lock_sock(sk); if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (unlikely(addr->sllc_family != AF_LLC)) goto out; + dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; rcu_read_lock(); if (sk->sk_bound_dev_if) { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f28e937320a3..216ab915dd54 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -988,7 +988,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; - unsigned long groups = nladdr->nl_groups; + unsigned long groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) @@ -996,6 +996,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nladdr->nl_family != AF_NETLINK) return -EINVAL; + groups = nladdr->nl_groups; /* Only superuser is allowed to listen multicasts */ if (groups) { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 1d3144d19903..71ffd1a6dc7c 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1392,18 +1392,22 @@ static int __init nr_proto_init(void) int i; int rc = proto_register(&nr_proto, 0); - if (rc != 0) - goto out; + if (rc) + return rc; if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n"); - return -1; + pr_err("NET/ROM: %s - nr_ndevs parameter too large\n", + __func__); + rc = -EINVAL; + goto unregister_proto; } dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL); - if (dev_nr == NULL) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n"); - return -1; + if (!dev_nr) { + pr_err("NET/ROM: %s - unable to allocate device array\n", + __func__); + rc = -ENOMEM; + goto unregister_proto; } for (i = 0; i < nr_ndevs; i++) { @@ -1413,13 +1417,13 @@ static int __init nr_proto_init(void) sprintf(name, "nr%d", i); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup); if (!dev) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n"); + rc = -ENOMEM; goto fail; } dev->base_addr = i; - if (register_netdev(dev)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n"); + rc = register_netdev(dev); + if (rc) { free_netdev(dev); goto fail; } @@ -1427,36 +1431,64 @@ static int __init nr_proto_init(void) dev_nr[i] = dev; } - if (sock_register(&nr_family_ops)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n"); + rc = sock_register(&nr_family_ops); + if (rc) goto fail; - } - register_netdevice_notifier(&nr_dev_notifier); + rc = register_netdevice_notifier(&nr_dev_notifier); + if (rc) + goto out_sock; ax25_register_pid(&nr_pid); ax25_linkfail_register(&nr_linkfail_notifier); #ifdef CONFIG_SYSCTL - nr_register_sysctl(); + rc = nr_register_sysctl(); + if (rc) + goto out_sysctl; #endif nr_loopback_init(); - proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops); - proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops); - proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops); -out: - return rc; + rc = -ENOMEM; + if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops)) + goto proc_remove1; + if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net, + &nr_neigh_seqops)) + goto proc_remove2; + if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net, + &nr_node_seqops)) + goto proc_remove3; + + return 0; + +proc_remove3: + remove_proc_entry("nr_neigh", init_net.proc_net); +proc_remove2: + remove_proc_entry("nr", init_net.proc_net); +proc_remove1: + + nr_loopback_clear(); + nr_rt_free(); + +#ifdef CONFIG_SYSCTL + nr_unregister_sysctl(); +out_sysctl: +#endif + ax25_linkfail_release(&nr_linkfail_notifier); + ax25_protocol_release(AX25_P_NETROM); + unregister_netdevice_notifier(&nr_dev_notifier); +out_sock: + sock_unregister(PF_NETROM); fail: while (--i >= 0) { unregister_netdev(dev_nr[i]); free_netdev(dev_nr[i]); } kfree(dev_nr); +unregister_proto: proto_unregister(&nr_proto); - rc = -1; - goto out; + return rc; } module_init(nr_proto_init); diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c index 215ad22a9647..93d13f019981 100644 --- a/net/netrom/nr_loopback.c +++ b/net/netrom/nr_loopback.c @@ -70,7 +70,7 @@ static void nr_loopback_timer(struct timer_list *unused) } } -void __exit nr_loopback_clear(void) +void nr_loopback_clear(void) { del_timer_sync(&loopback_timer); skb_queue_purge(&loopback_queue); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 6485f593e2f0..b76aa668a94b 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -953,7 +953,7 @@ const struct seq_operations nr_neigh_seqops = { /* * Free all memory associated with the nodes and routes lists. */ -void __exit nr_rt_free(void) +void nr_rt_free(void) { struct nr_neigh *s = NULL; struct nr_node *t = NULL; diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c index ba1c368b3f18..771011b84270 100644 --- a/net/netrom/sysctl_net_netrom.c +++ b/net/netrom/sysctl_net_netrom.c @@ -146,9 +146,12 @@ static struct ctl_table nr_table[] = { { } }; -void __init nr_register_sysctl(void) +int __init nr_register_sysctl(void) { nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table); + if (!nr_table_header) + return -ENOMEM; + return 0; } void nr_unregister_sysctl(void) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index d6cc97fbbbb0..2b969f99ef13 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -543,6 +543,9 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, struct rds_sock *rs = rds_sk_to_rs(sk); int ret = 0; + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; + lock_sock(sk); switch (uaddr->sa_family) { diff --git a/net/rds/bind.c b/net/rds/bind.c index 17c9d9f0c848..0f4398e7f2a7 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -173,6 +173,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* We allow an RDS socket to be bound to either IPv4 or IPv6 * address. */ + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; if (uaddr->sa_family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 96f2952bbdfd..ae8c5d7f3bf1 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -135,7 +135,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr; struct rxrpc_local *local; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - u16 service_id = srx->srx_service; + u16 service_id; int ret; _enter("%p,%p,%d", rx, saddr, len); @@ -143,6 +143,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) ret = rxrpc_validate_address(rx, srx, len); if (ret < 0) goto error; + service_id = srx->srx_service; lock_sock(&rx->sk); @@ -370,18 +371,22 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * rxrpc_kernel_check_life - Check to see whether a call is still alive * @sock: The socket the call is on * @call: The call to check + * @_life: Where to store the life value * * Allow a kernel service to find out whether a call is still alive - ie. we're - * getting ACKs from the server. Returns a number representing the life state - * which can be compared to that returned by a previous call. + * getting ACKs from the server. Passes back in *_life a number representing + * the life state which can be compared to that returned by a previous call and + * return true if the call is still alive. * * If the life state stalls, rxrpc_kernel_probe_life() should be called and * then 2RTT waited. */ -u32 rxrpc_kernel_check_life(const struct socket *sock, - const struct rxrpc_call *call) +bool rxrpc_kernel_check_life(const struct socket *sock, + const struct rxrpc_call *call, + u32 *_life) { - return call->acks_latest; + *_life = call->acks_latest; + return call->state != RXRPC_CALL_COMPLETE; } EXPORT_SYMBOL(rxrpc_kernel_check_life); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 4b1a534d290a..062ca9dc29b8 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -654,6 +654,7 @@ struct rxrpc_call { u8 ackr_reason; /* reason to ACK */ u16 ackr_skew; /* skew on packet being ACK'd */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ + rxrpc_serial_t ackr_first_seq; /* first sequence number received */ rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index b6fca8ebb117..8d31fb4c51e1 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -153,7 +153,8 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, * pass a connection-level abort onto all calls on that connection */ static void rxrpc_abort_calls(struct rxrpc_connection *conn, - enum rxrpc_call_completion compl) + enum rxrpc_call_completion compl, + rxrpc_serial_t serial) { struct rxrpc_call *call; int i; @@ -173,6 +174,9 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, call->call_id, 0, conn->abort_code, conn->error); + else + trace_rxrpc_rx_abort(call, serial, + conn->abort_code); if (rxrpc_set_call_completion(call, compl, conn->abort_code, conn->error)) @@ -213,8 +217,6 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, conn->state = RXRPC_CONN_LOCALLY_ABORTED; spin_unlock_bh(&conn->state_lock); - rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED); - msg.msg_name = &conn->params.peer->srx.transport; msg.msg_namelen = conn->params.peer->srx.transport_len; msg.msg_control = NULL; @@ -242,6 +244,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, len = iov[0].iov_len + iov[1].iov_len; serial = atomic_inc_return(&conn->serial); + rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial); whdr.serial = htonl(serial); _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code); @@ -321,7 +324,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, conn->error = -ECONNABORTED; conn->abort_code = abort_code; conn->state = RXRPC_CONN_REMOTELY_ABORTED; - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED); + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); return -ECONNABORTED; case RXRPC_PACKET_TYPE_CHALLENGE: diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9128aa0e40aa..4c6f9d0a00e7 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -837,7 +837,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, u8 acks[RXRPC_MAXACKS]; } buf; rxrpc_serial_t acked_serial; - rxrpc_seq_t first_soft_ack, hard_ack; + rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; _enter(""); @@ -851,13 +851,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, acked_serial = ntohl(buf.ack.serial); first_soft_ack = ntohl(buf.ack.firstPacket); + prev_pkt = ntohl(buf.ack.previousPacket); hard_ack = first_soft_ack - 1; nr_acks = buf.ack.nAcks; summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? buf.ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial, - first_soft_ack, ntohl(buf.ack.previousPacket), + first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE) @@ -878,8 +879,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, rxrpc_propose_ack_respond_to_ack); } - /* Discard any out-of-order or duplicate ACKs. */ - if (before_eq(sp->hdr.serial, call->acks_latest)) + /* Discard any out-of-order or duplicate ACKs (outside lock). */ + if (before(first_soft_ack, call->ackr_first_seq) || + before(prev_pkt, call->ackr_prev_seq)) return; buf.info.rxMTU = 0; @@ -890,12 +892,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, spin_lock(&call->input_lock); - /* Discard any out-of-order or duplicate ACKs. */ - if (before_eq(sp->hdr.serial, call->acks_latest)) + /* Discard any out-of-order or duplicate ACKs (inside lock). */ + if (before(first_soft_ack, call->ackr_first_seq) || + before(prev_pkt, call->ackr_prev_seq)) goto out; call->acks_latest_ts = skb->tstamp; call->acks_latest = sp->hdr.serial; + call->ackr_first_seq = first_soft_ack; + call->ackr_prev_seq = prev_pkt; + /* Parse rwind and mtu sizes if provided. */ if (buf.info.rxMTU) rxrpc_input_ackinfo(call, skb, &buf.info); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index bc05af89fc38..6e84d878053c 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -157,6 +157,11 @@ void rxrpc_error_report(struct sock *sk) _enter("%p{%d}", sk, local->debug_id); + /* Clear the outstanding error value on the socket so that it doesn't + * cause kernel_sendmsg() to return it later. + */ + sock_error(sk); + skb = sock_dequeue_err_skb(sk); if (!skb) { _leave("UDP socket errqueue empty"); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 46c9312085b1..bec64deb7b0a 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -152,12 +152,13 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call, } /* - * Queue a DATA packet for transmission, set the resend timeout and send the - * packet immediately + * Queue a DATA packet for transmission, set the resend timeout and send + * the packet immediately. Returns the error from rxrpc_send_data_packet() + * in case the caller wants to do something with it. */ -static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, - struct sk_buff *skb, bool last, - rxrpc_notify_end_tx_t notify_end_tx) +static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, + struct sk_buff *skb, bool last, + rxrpc_notify_end_tx_t notify_end_tx) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long now; @@ -250,7 +251,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, out: rxrpc_free_skb(skb, rxrpc_skb_tx_freed); - _leave(""); + _leave(" = %d", ret); + return ret; } /* @@ -423,9 +425,10 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (ret < 0) goto out; - rxrpc_queue_packet(rx, call, skb, - !msg_data_left(msg) && !more, - notify_end_tx); + ret = rxrpc_queue_packet(rx, call, skb, + !msg_data_left(msg) && !more, + notify_end_tx); + /* Should check for failure here */ skb = NULL; } } while (msg_data_left(msg) > 0); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9874e60c9b0d..4583fa914e62 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4847,7 +4847,8 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr, } /* Validate addr_len before calling common connect/connectx routine. */ - af = sctp_get_af_specific(addr->sa_family); + af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL : + sctp_get_af_specific(addr->sa_family); if (!af || addr_len < af->sockaddr_len) { err = -EINVAL; } else { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 77ef53596d18..6f869ef49b32 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -167,10 +167,9 @@ static int smc_release(struct socket *sock) if (sk->sk_state == SMC_CLOSED) { if (smc->clcsock) { - mutex_lock(&smc->clcsock_release_lock); - sock_release(smc->clcsock); - smc->clcsock = NULL; - mutex_unlock(&smc->clcsock_release_lock); + release_sock(sk); + smc_clcsock_release(smc); + lock_sock(sk); } if (!smc->use_fallback) smc_conn_free(&smc->conn); @@ -446,10 +445,19 @@ static void smc_link_save_peer_info(struct smc_link *link, link->peer_mtu = clc->qp_mtu; } +static void smc_switch_to_fallback(struct smc_sock *smc) +{ + smc->use_fallback = true; + if (smc->sk.sk_socket && smc->sk.sk_socket->file) { + smc->clcsock->file = smc->sk.sk_socket->file; + smc->clcsock->file->private_data = smc->clcsock; + } +} + /* fall back during connect */ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { - smc->use_fallback = true; + smc_switch_to_fallback(smc); smc->fallback_rsn = reason_code; smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) @@ -775,10 +783,14 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = -rc; out: - if (smc->sk.sk_err) - smc->sk.sk_state_change(&smc->sk); - else - smc->sk.sk_write_space(&smc->sk); + if (!sock_flag(&smc->sk, SOCK_DEAD)) { + if (smc->sk.sk_err) { + smc->sk.sk_state_change(&smc->sk); + } else { /* allow polling before and after fallback decision */ + smc->clcsock->sk->sk_write_space(smc->clcsock->sk); + smc->sk.sk_write_space(&smc->sk); + } + } kfree(smc->connect_info); smc->connect_info = NULL; release_sock(&smc->sk); @@ -872,11 +884,11 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) if (rc < 0) lsk->sk_err = -rc; if (rc < 0 || lsk->sk_state == SMC_CLOSED) { + new_sk->sk_prot->unhash(new_sk); if (new_clcsock) sock_release(new_clcsock); new_sk->sk_state = SMC_CLOSED; sock_set_flag(new_sk, SOCK_DEAD); - new_sk->sk_prot->unhash(new_sk); sock_put(new_sk); /* final */ *new_smc = NULL; goto out; @@ -927,16 +939,21 @@ struct sock *smc_accept_dequeue(struct sock *parent, smc_accept_unlink(new_sk); if (new_sk->sk_state == SMC_CLOSED) { + new_sk->sk_prot->unhash(new_sk); if (isk->clcsock) { sock_release(isk->clcsock); isk->clcsock = NULL; } - new_sk->sk_prot->unhash(new_sk); sock_put(new_sk); /* final */ continue; } - if (new_sock) + if (new_sock) { sock_graft(new_sk, new_sock); + if (isk->use_fallback) { + smc_sk(new_sk)->clcsock->file = new_sock->file; + isk->clcsock->file->private_data = isk->clcsock; + } + } return new_sk; } return NULL; @@ -956,6 +973,7 @@ void smc_close_non_accepted(struct sock *sk) sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; } + sk->sk_prot->unhash(sk); if (smc->clcsock) { struct socket *tcp; @@ -971,7 +989,6 @@ void smc_close_non_accepted(struct sock *sk) smc_conn_free(&smc->conn); } release_sock(sk); - sk->sk_prot->unhash(sk); sock_put(sk); /* final sock_put */ } @@ -1037,13 +1054,13 @@ static void smc_listen_out(struct smc_sock *new_smc) struct smc_sock *lsmc = new_smc->listen_smc; struct sock *newsmcsk = &new_smc->sk; - lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); if (lsmc->sk.sk_state == SMC_LISTEN) { + lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); + release_sock(&lsmc->sk); } else { /* no longer listening */ smc_close_non_accepted(newsmcsk); } - release_sock(&lsmc->sk); /* Wake up accept */ lsmc->sk.sk_data_ready(&lsmc->sk); @@ -1087,7 +1104,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, return; } smc_conn_free(&new_smc->conn); - new_smc->use_fallback = true; + smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = reason_code; if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code) < 0) { @@ -1237,6 +1254,9 @@ static void smc_listen_work(struct work_struct *work) int rc = 0; u8 ibport; + if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) + return smc_listen_out_err(new_smc); + if (new_smc->use_fallback) { smc_listen_out_connected(new_smc); return; @@ -1244,7 +1264,7 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { - new_smc->use_fallback = true; + smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC; smc_listen_out_connected(new_smc); return; @@ -1501,7 +1521,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT) { - smc->use_fallback = true; + smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { rc = -EINVAL; @@ -1703,7 +1723,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ if (sk->sk_state == SMC_INIT) { - smc->use_fallback = true; + smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { if (!smc->use_fallback) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 2ad37e998509..fc06720b53c1 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -21,6 +21,22 @@ #define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ) +/* release the clcsock that is assigned to the smc_sock */ +void smc_clcsock_release(struct smc_sock *smc) +{ + struct socket *tcp; + + if (smc->listen_smc && current_work() != &smc->smc_listen_work) + cancel_work_sync(&smc->smc_listen_work); + mutex_lock(&smc->clcsock_release_lock); + if (smc->clcsock) { + tcp = smc->clcsock; + smc->clcsock = NULL; + sock_release(tcp); + } + mutex_unlock(&smc->clcsock_release_lock); +} + static void smc_close_cleanup_listen(struct sock *parent) { struct sock *sk; @@ -321,6 +337,7 @@ static void smc_close_passive_work(struct work_struct *work) close_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_cdc_conn_state_flags *rxflags; + bool release_clcsock = false; struct sock *sk = &smc->sk; int old_state; @@ -400,13 +417,13 @@ wakeup: if ((sk->sk_state == SMC_CLOSED) && (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { smc_conn_free(conn); - if (smc->clcsock) { - sock_release(smc->clcsock); - smc->clcsock = NULL; - } + if (smc->clcsock) + release_clcsock = true; } } release_sock(sk); + if (release_clcsock) + smc_clcsock_release(smc); sock_put(sk); /* sock_hold done by schedulers of close_work */ } diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h index 19eb6a211c23..e0e3b5df25d2 100644 --- a/net/smc/smc_close.h +++ b/net/smc/smc_close.h @@ -23,5 +23,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc); int smc_close_active(struct smc_sock *smc); int smc_close_shutdown_write(struct smc_sock *smc); void smc_close_init(struct smc_sock *smc); +void smc_clcsock_release(struct smc_sock *smc); #endif /* SMC_CLOSE_H */ diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 2fff79db1a59..e89e918b88e0 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -289,6 +289,11 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, INIT_LIST_HEAD(&smcd->vlan); smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)", WQ_MEM_RECLAIM, name); + if (!smcd->event_wq) { + kfree(smcd->conn); + kfree(smcd); + return NULL; + } return smcd; } EXPORT_SYMBOL_GPL(smcd_alloc_dev); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 8d2f6296279c..0285c7f9e79b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -603,7 +603,8 @@ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); - return smc_pnet_remove_by_pnetid(net, NULL); + smc_pnet_remove_by_pnetid(net, NULL); + return 0; } /* SMC_PNETID generic netlink operation definition */ diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 860dcfb95ee4..fa6c977b4c41 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -140,13 +140,11 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* We are going to append to the frags_list of head. * Need to unshare the frag_list. */ - if (skb_has_frag_list(head)) { - err = skb_unclone(head, GFP_ATOMIC); - if (err) { - STRP_STATS_INCR(strp->stats.mem_fail); - desc->error = err; - return 0; - } + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + STRP_STATS_INCR(strp->stats.mem_fail); + desc->error = err; + return 0; } if (unlikely(skb_shinfo(head)->frag_list)) { diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index bff241f03525..89993afe0fbd 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -909,7 +909,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg, for (; i < TIPC_NAMETBL_SIZE; i++) { head = &tn->nametbl->services[i]; - if (*last_type) { + if (*last_type || + (!i && *last_key && (*last_lower == *last_key))) { service = tipc_service_find(net, *last_type); if (!service) return -EPIPE; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 135a7ee9db03..9f3bdbc1e593 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,8 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock); static void tls_device_free_ctx(struct tls_context *ctx) { - if (ctx->tx_conf == TLS_HW) + if (ctx->tx_conf == TLS_HW) { kfree(tls_offload_ctx_tx(ctx)); + kfree(ctx->tx.rec_seq); + kfree(ctx->tx.iv); + } if (ctx->rx_conf == TLS_HW) kfree(tls_offload_ctx_rx(ctx)); @@ -216,6 +219,13 @@ void tls_device_sk_destruct(struct sock *sk) } EXPORT_SYMBOL(tls_device_sk_destruct); +void tls_device_free_resources_tx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_free_partial_record(sk, tls_ctx); +} + static void tls_append_frag(struct tls_record_info *record, struct page_frag *pfrag, int size) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index df921a2904b9..9547cea0ce3b 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -208,6 +208,26 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, return tls_push_sg(sk, ctx, sg, offset, flags); } +bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx) +{ + struct scatterlist *sg; + + sg = ctx->partially_sent_record; + if (!sg) + return false; + + while (1) { + put_page(sg_page(sg)); + sk_mem_uncharge(sk, sg->length); + + if (sg_is_last(sg)) + break; + sg++; + } + ctx->partially_sent_record = NULL; + return true; +} + static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); @@ -267,6 +287,10 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); tls_sw_free_resources_tx(sk); +#ifdef CONFIG_TLS_DEVICE + } else if (ctx->tx_conf == TLS_HW) { + tls_device_free_resources_tx(sk); +#endif } if (ctx->rx_conf == TLS_SW) { diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 20b191227969..b50ced862f6f 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2052,20 +2052,7 @@ void tls_sw_free_resources_tx(struct sock *sk) /* Free up un-sent records in tx_list. First, free * the partially sent record if any at head of tx_list. */ - if (tls_ctx->partially_sent_record) { - struct scatterlist *sg = tls_ctx->partially_sent_record; - - while (1) { - put_page(sg_page(sg)); - sk_mem_uncharge(sk, sg->length); - - if (sg_is_last(sg)) - break; - sg++; - } - - tls_ctx->partially_sent_record = NULL; - + if (tls_free_partial_record(sk, tls_ctx)) { rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); list_del(&rec->list); diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index c4cf6e6d800e..a6c196c8534c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -11,6 +11,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS=" rif_set_addr_test + rif_vrf_set_addr_test rif_inherit_bridge_addr_test rif_non_inherit_bridge_addr_test vlan_interface_deletion_test @@ -98,6 +99,25 @@ rif_set_addr_test() ip link set dev $swp1 addr $swp1_mac } +rif_vrf_set_addr_test() +{ + # Test that it is possible to set an IP address on a VRF upper despite + # its random MAC address. + RET=0 + + ip link add name vrf-test type vrf table 10 + ip link set dev $swp1 master vrf-test + + ip -4 address add 192.0.2.1/24 dev vrf-test + check_err $? "failed to set IPv4 address on VRF" + ip -6 address add 2001:db8:1::1/64 dev vrf-test + check_err $? "failed to set IPv6 address on VRF" + + log_test "RIF - setting IP address on VRF" + + ip link del dev vrf-test +} + rif_inherit_bridge_addr_test() { RET=0 diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 1080ff55a788..0d2a5f4f1e63 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -605,6 +605,39 @@ run_cmd() return $rc } +check_expected() +{ + local out="$1" + local expected="$2" + local rc=0 + + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route6() @@ -652,31 +685,7 @@ check_route6() pfx=$1 out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } route_cleanup() @@ -725,7 +734,7 @@ route_setup() ip -netns ns2 addr add 172.16.103.2/24 dev veth4 ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 - set +ex + set +e } # assumption is that basic add of a single path route works @@ -960,7 +969,8 @@ ipv6_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route6 "" + out=$($IP -6 ro ls match 2001:db8:104::/64) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" @@ -1091,38 +1101,13 @@ check_route() local pfx local expected="$1" local out - local rc=0 set -- $expected pfx=$1 [ "${pfx}" = "unreachable" ] && pfx=$2 out=$($IP ro ls match ${pfx}) - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } # assumption is that basic add of a single path route works @@ -1387,7 +1372,8 @@ ipv4_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route "" + out=$($IP ro ls match 172.16.104.0/24) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" |