From 4bd97d51a5e602ea1fbdab8c2d653513dea17115 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 20 Mar 2019 11:02:04 +0100 Subject: net: dev: rename queue selection helpers. With the following patches, we are going to use __netdev_pick_tx() in many modules. Rename it to netdev_pick_tx(), to make it clear is a public API. Also rename the existing netdev_pick_tx() to netdev_core_pick_tx(), to avoid name clashes. Suggested-by: Eric Dumazet Suggested-by: David Miller Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 26f69cf763f4..57cd2bdd9f78 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2152,9 +2152,9 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, &qdisc_xmit_lock_key); \ } -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb, - struct net_device *sb_dev); +struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, + struct sk_buff *skb, + struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev -- cgit v1.2.3-71-gd317 From b71b5837f8711dbc4bc0424cb5c75e5921be055c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 20 Mar 2019 11:02:05 +0100 Subject: packet: rework packet_pick_tx_queue() to use common code selection Currently packet_pick_tx_queue() is the only caller of ndo_select_queue() using a fallback argument other than netdev_pick_tx. Leveraging rx queue, we can obtain a similar queue selection behavior using core helpers. After this change, ndo_select_queue() is always invoked with netdev_pick_tx() as fallback. We can change ndo_select_queue() signature in a followup patch, dropping an indirect call per transmitted packet in some scenarios (e.g. TCP syn and XDP generic xmit) This changes slightly how af packet queue selection happens when PACKET_QDISC_BYPASS is set. It's now more similar to plan dev_queue_xmit() tacking in account both XPS and TC mapping. v1 -> v2: - rebased after helper name change RFC -> v1: - initialize sender_cpu to the expected value Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 5 +++-- net/packet/af_packet.c | 15 +++++++-------- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 57cd2bdd9f78..0ff28db4239f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2152,6 +2152,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, &qdisc_xmit_lock_key); \ } +u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); diff --git a/net/core/dev.c b/net/core/dev.c index 5dd3e3f7dd12..1a76b4fe9b97 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3704,8 +3704,8 @@ u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, } EXPORT_SYMBOL(dev_pick_tx_cpu_id); -static u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) +u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -3729,6 +3729,7 @@ static u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, return queue_index; } +EXPORT_SYMBOL(netdev_pick_tx); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 323655a25674..a8809dc0e1ab 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -275,24 +275,23 @@ static bool packet_use_direct_xmit(const struct packet_sock *po) return po->xmit == packet_direct_xmit; } -static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) -{ - return dev_pick_tx_cpu_id(dev, skb, sb_dev, NULL); -} - static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; + int cpu = raw_smp_processor_id(); u16 queue_index; +#ifdef CONFIG_XPS + skb->sender_cpu = cpu + 1; +#endif + skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL, - __packet_pick_tx_queue); + netdev_pick_tx); queue_index = netdev_cap_txqueue(dev, queue_index); } else { - queue_index = __packet_pick_tx_queue(dev, skb, NULL); + queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; -- cgit v1.2.3-71-gd317 From a350eccee5830d9a1f29e393a88dc05a15326d44 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 20 Mar 2019 11:02:06 +0100 Subject: net: remove 'fallback' argument from dev->ndo_select_queue() After the previous patch, all the callers of ndo_select_queue() provide as a 'fallback' argument netdev_pick_tx. The only exceptions are nested calls to ndo_select_queue(), which pass down the 'fallback' available in the current scope - still netdev_pick_tx. We can drop such argument and replace fallback() invocation with netdev_pick_tx(). This avoids an indirect call per xmit packet in some scenarios (TCP syn, UDP unconnected, XDP generic, pktgen) with device drivers implementing such ndo. It also clean the code a bit. Tested with ixgbe and CONFIG_FCOE=m With pktgen using queue xmit: threads vanilla patched (kpps) (kpps) 1 2334 2428 2 4166 4278 4 7895 8100 v1 -> v2: - rebased after helper's name change Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- drivers/infiniband/hw/hfi1/vnic_main.c | 3 +-- drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c | 6 ++---- drivers/net/bonding/bond_main.c | 3 +-- drivers/net/ethernet/amazon/ena/ena_netdev.c | 5 ++--- drivers/net/ethernet/broadcom/bcmsysport.c | 7 +++---- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 5 ++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 +-- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 5 ++--- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 ++--- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 ++--- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 7 +++---- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 5 ++--- drivers/net/ethernet/qlogic/qede/qede.h | 3 +-- drivers/net/ethernet/qlogic/qede/qede_fp.c | 5 ++--- drivers/net/ethernet/renesas/ravb_main.c | 3 +-- drivers/net/ethernet/sun/ldmvsw.c | 3 +-- drivers/net/ethernet/sun/sunvnet.c | 3 +-- drivers/net/hyperv/netvsc_drv.c | 10 ++++------ drivers/net/net_failover.c | 8 +++----- drivers/net/team/team.c | 3 +-- drivers/net/tun.c | 3 +-- drivers/net/wireless/marvell/mwifiex/main.c | 3 +-- drivers/net/xen-netback/interface.c | 6 +++--- drivers/net/xen-netfront.c | 3 +-- drivers/staging/rtl8188eu/os_dep/os_intfs.c | 3 +-- drivers/staging/rtl8723bs/os_dep/os_intfs.c | 3 +-- include/linux/netdevice.h | 12 ++++-------- net/core/dev.c | 9 +++------ net/mac80211/iface.c | 6 ++---- net/packet/af_packet.c | 3 +-- 32 files changed, 57 insertions(+), 97 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c index a922db58be14..2b07032dbdda 100644 --- a/drivers/infiniband/hw/hfi1/vnic_main.c +++ b/drivers/infiniband/hw/hfi1/vnic_main.c @@ -423,8 +423,7 @@ tx_finish: static u16 hfi1_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev); struct opa_vnic_skb_mdata *mdata; diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c index ae70cd18903e..aeff68f582d3 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c @@ -95,8 +95,7 @@ static netdev_tx_t opa_netdev_start_xmit(struct sk_buff *skb, } static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev); struct opa_vnic_skb_mdata *mdata; @@ -106,8 +105,7 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, mdata = skb_push(skb, sizeof(*mdata)); mdata->entropy = opa_vnic_calc_entropy(skb); mdata->vl = opa_vnic_get_vl(adapter, skb); - rc = adapter->rn_ops->ndo_select_queue(netdev, skb, - sb_dev, fallback); + rc = adapter->rn_ops->ndo_select_queue(netdev, skb, sb_dev); skb_pull(skb, sizeof(*mdata)); return rc; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b59708c35faf..8ddbada9e281 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4114,8 +4114,7 @@ static inline int bond_slave_override(struct bonding *bond, static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { /* This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index a6eacf2099c3..71c8cac6e44e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2258,8 +2258,7 @@ error_drop_packet: } static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { u16 qid; /* we suspect that this is good for in--kernel network services that @@ -2269,7 +2268,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, if (skb_rx_queue_recorded(skb)) qid = skb_get_rx_queue(skb); else - qid = fallback(dev, skb, NULL); + qid = netdev_pick_tx(dev, skb, NULL); return qid; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index bc3ac369cbe3..a9d3d26a7202 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2274,8 +2274,7 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = { }; static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct bcm_sysport_priv *priv = netdev_priv(dev); u16 queue = skb_get_queue_mapping(skb); @@ -2283,7 +2282,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, unsigned int q, port; if (!netdev_uses_dsa(dev)) - return fallback(dev, skb, NULL); + return netdev_pick_tx(dev, skb, NULL); /* DSA tagging layer will have configured the correct queue */ q = BRCM_TAG_GET_QUEUE(queue); @@ -2291,7 +2290,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues]; if (unlikely(!tx_ring)) - return fallback(dev, skb, NULL); + return netdev_pick_tx(dev, skb, NULL); return tx_ring->index; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index ecb1bd7eb508..6012fe61735e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1909,8 +1909,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw) } u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct bnx2x *bp = netdev_priv(dev); @@ -1932,7 +1931,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return fallback(dev, skb, NULL) % + return netdev_pick_tx(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 2462e7aa0c5d..7f8df08a7a4c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -498,8 +498,7 @@ int bnx2x_set_vf_spoofchk(struct net_device *dev, int idx, bool val); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); static inline void bnx2x_update_rx_prod(struct bnx2x *bp, struct bnx2x_fastpath *fp, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 89179e316687..3339f1f4bcdd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -979,8 +979,7 @@ freeout: } static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { int txq; @@ -1022,7 +1021,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, return txq; } - return fallback(dev, skb, NULL) % dev->real_num_tx_queues; + return netdev_pick_tx(dev, skb, NULL) % dev->real_num_tx_queues; } static int closest_timer(const struct sge *s, int time) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 60e7d7ae3787..e37a0ca0db89 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1964,8 +1964,7 @@ static void hns_nic_get_stats64(struct net_device *ndev, static u16 hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct ethhdr *eth_hdr = (struct ethhdr *)skb->data; struct hns_nic_priv *priv = netdev_priv(ndev); @@ -1975,7 +1974,7 @@ hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb, is_multicast_ether_addr(eth_hdr->h_dest)) return 0; else - return fallback(ndev, skb, NULL); + return netdev_pick_tx(ndev, skb, NULL); } static const struct net_device_ops hns_nic_netdev_ops = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 76aeed845a73..16c728984164 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8483,8 +8483,7 @@ static void ixgbe_atr(struct ixgbe_ring *ring, #ifdef IXGBE_FCOE static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct ixgbe_adapter *adapter; struct ixgbe_ring_feature *f; @@ -8514,7 +8513,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, break; /* fall through */ default: - return fallback(dev, skb, sb_dev); + return netdev_pick_tx(dev, skb, sb_dev); } f = &adapter->ring_feature[RING_F_FCOE]; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 2cbd2bd7c67c..fba54fb06e18 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -685,16 +685,15 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, } u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct mlx4_en_priv *priv = netdev_priv(dev); u16 rings_p_up = priv->num_tx_rings_p_up; if (netdev_get_num_tc(dev)) - return fallback(dev, skb, NULL); + return netdev_pick_tx(dev, skb, NULL); - return fallback(dev, skb, NULL) % rings_p_up; + return netdev_pick_tx(dev, skb, NULL) % rings_p_up; } static void mlx4_bf_copy(void __iomem *dst, const void *src, diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 8137454e2534..630f15977f09 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -698,8 +698,7 @@ void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 71c65cc17904..5c2e3276d9cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -769,8 +769,7 @@ struct mlx5e_profile { void mlx5e_build_ptys2ethtool_map(void); u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_tx_wqe *wqe, u16 pi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 25a8f8260c14..ce1406bb1512 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -110,11 +110,10 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb #endif u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { + int channel_ix = netdev_pick_tx(dev, skb, NULL); struct mlx5e_priv *priv = netdev_priv(dev); - int channel_ix = fallback(dev, skb, NULL); u16 num_channels; int up = 0; diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 63a78162cfaf..92fe226980fd 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -498,8 +498,7 @@ struct qede_reload_args { /* Datapath functions definition */ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev); u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); netdev_features_t qede_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 31b046e24565..c342b07e3a93 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1696,8 +1696,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) } u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct qede_dev *edev = netdev_priv(dev); int total_txq; @@ -1705,7 +1704,7 @@ u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc; return QEDE_TSS_COUNT(edev) ? - fallback(dev, skb, NULL) % total_txq : 0; + netdev_pick_tx(dev, skb, NULL) % total_txq : 0; } /* 8B udp header + 8B base tunnel header + 32B option length */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 8154b38c08f7..4f648394e645 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1615,8 +1615,7 @@ drop: } static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { /* If skb needs TX timestamp, it is handled in network control queue */ return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC : diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 644e42c181ee..01ea0d6f8819 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -101,8 +101,7 @@ static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb, } static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct vnet_port *port = netdev_priv(dev); diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 590172818b92..96b883f965f6 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -234,8 +234,7 @@ static struct vnet_port *vnet_tx_port_find(struct sk_buff *skb, } static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct vnet *vp = netdev_priv(dev); struct vnet_port *port = __tx_port_find(vp, skb); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index cf4897043e83..1a08679f90ce 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -308,7 +308,7 @@ static inline int netvsc_get_tx_queue(struct net_device *ndev, * If a valid queue has already been assigned, then use that. * Otherwise compute tx queue based on hash and the send table. * - * This is basically similar to default (__netdev_pick_tx) with the added step + * This is basically similar to default (netdev_pick_tx) with the added step * of using the host send_table when no other queue has been assigned. * * TODO support XPS - but get_xps_queue not exported @@ -331,8 +331,7 @@ static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb) } static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct net_device_context *ndc = netdev_priv(ndev); struct net_device *vf_netdev; @@ -344,10 +343,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, const struct net_device_ops *vf_ops = vf_netdev->netdev_ops; if (vf_ops->ndo_select_queue) - txq = vf_ops->ndo_select_queue(vf_netdev, skb, - sb_dev, fallback); + txq = vf_ops->ndo_select_queue(vf_netdev, skb, sb_dev); else - txq = fallback(vf_netdev, skb, NULL); + txq = netdev_pick_tx(vf_netdev, skb, NULL); /* Record the queue selected by VF so that it can be * used for common case where VF has more queues than diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index ed1166adaa2f..b16a1221d19b 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -115,8 +115,7 @@ static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb, static u16 net_failover_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct net_failover_info *nfo_info = netdev_priv(dev); struct net_device *primary_dev; @@ -127,10 +126,9 @@ static u16 net_failover_select_queue(struct net_device *dev, const struct net_device_ops *ops = primary_dev->netdev_ops; if (ops->ndo_select_queue) - txq = ops->ndo_select_queue(primary_dev, skb, - sb_dev, fallback); + txq = ops->ndo_select_queue(primary_dev, skb, sb_dev); else - txq = fallback(primary_dev, skb, NULL); + txq = netdev_pick_tx(primary_dev, skb, NULL); qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 6ed96fdfd96d..ee950aa48e3b 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1691,8 +1691,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/tun.c b/drivers/net/tun.c index e9ca1c088d0b..ef3b65514976 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -606,8 +606,7 @@ static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) } static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct tun_struct *tun = netdev_priv(dev); u16 ret; diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c index 20cee5c397fb..f6da8edab7f1 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.c +++ b/drivers/net/wireless/marvell/mwifiex/main.c @@ -1282,8 +1282,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev) static u16 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { skb->priority = cfg80211_classify8021d(skb, NULL); return mwifiex_1d_to_wmm_queue[skb->priority]; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 6da12518e693..783198844dd7 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -148,8 +148,7 @@ void xenvif_wake_queue(struct xenvif_queue *queue) } static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct xenvif *vif = netdev_priv(dev); unsigned int size = vif->hash.size; @@ -162,7 +161,8 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, return 0; if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) - return fallback(dev, skb, NULL) % dev->real_num_tx_queues; + return netdev_pick_tx(dev, skb, NULL) % + dev->real_num_tx_queues; xenvif_set_skb_hash(vif, skb); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index c914c24f880b..80c30321de41 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -543,8 +543,7 @@ static int xennet_count_skb_slots(struct sk_buff *skb) } static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { unsigned int num_queues = dev->real_num_tx_queues; u32 hash; diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c index 8dde5a40e253..2c088af44c8b 100644 --- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c +++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c @@ -245,8 +245,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) } static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/drivers/staging/rtl8723bs/os_dep/os_intfs.c b/drivers/staging/rtl8723bs/os_dep/os_intfs.c index 143e3f9b31aa..0a20a4e9e19a 100644 --- a/drivers/staging/rtl8723bs/os_dep/os_intfs.c +++ b/drivers/staging/rtl8723bs/os_dep/os_intfs.c @@ -404,8 +404,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0ff28db4239f..823762291ebf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -986,8 +986,7 @@ struct devlink; * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * struct net_device *sb_dev, - * select_queue_fallback_t fallback); + * struct net_device *sb_dev); * Called to decide which queue to use when device supports multiple * transmit queues. * @@ -1268,8 +1267,7 @@ struct net_device_ops { netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -2641,11 +2639,9 @@ void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); diff --git a/net/core/dev.c b/net/core/dev.c index 1a76b4fe9b97..357111431ec9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3689,16 +3689,14 @@ get_cpus_map: } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; } @@ -3748,8 +3746,7 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, sb_dev, - netdev_pick_tx); + queue_index = ops->ndo_select_queue(dev, skb, sb_dev); else queue_index = netdev_pick_tx(dev, skb, sb_dev); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 4a6ff1482a9f..f0d97eba250b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1133,8 +1133,7 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1179,8 +1178,7 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a8809dc0e1ab..741953b42f44 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -287,8 +287,7 @@ static u16 packet_pick_tx_queue(struct sk_buff *skb) #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb, NULL, - netdev_pick_tx); + queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); -- cgit v1.2.3-71-gd317 From 4feb7c7a4fbb8f63371be31cda79433c7cf3da86 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 21 Mar 2019 14:42:40 +1100 Subject: rhashtable: don't hold lock on first table throughout insertion. rhashtable_try_insert() currently holds a lock on the bucket in the first table, while also locking buckets in subsequent tables. This is unnecessary and looks like a hold-over from some earlier version of the implementation. As insert and remove always lock a bucket in each table in turn, and as insert only inserts in the final table, there cannot be any races that are not covered by simply locking a bucket in each table in turn. When an insert call reaches that last table it can be sure that there is no matchinf entry in any other table as it has searched them all, and insertion never happens anywhere but in the last table. The fact that code tests for the existence of future_tbl while holding a lock on the relevant bucket ensures that two threads inserting the same key will make compatible decisions about which is the "last" table. This simplifies the code and allows the ->rehash field to be discarded. We still need a way to ensure that a dead bucket_table is never re-linked by rhashtable_walk_stop(). This can be achieved by calling call_rcu() inside the locked region, and checking with rcu_head_after_call_rcu() in rhashtable_walk_stop() to see if the bucket table is empty and dead. Acked-by: Herbert Xu Reviewed-by: Paul E. McKenney Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 13 ------------ lib/rhashtable.c | 52 ++++++++++++++-------------------------------- 2 files changed, 16 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index ae9c0f71f311..3864193d5e2e 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -63,7 +63,6 @@ struct bucket_table { unsigned int size; unsigned int nest; - unsigned int rehash; u32 hash_rnd; unsigned int locks_mask; spinlock_t *locks; @@ -776,12 +775,6 @@ static inline int rhltable_insert( * @obj: pointer to hash head inside object * @params: hash table parameters * - * Locks down the bucket chain in both the old and new table if a resize - * is in progress to ensure that writers can't remove from the old table - * and can't insert to the new table during the atomic operation of search - * and insertion. Searches for duplicates in both the old and new table if - * a resize is in progress. - * * This lookup function may only be used for fixed key hash table (key_len * parameter set). It will BUG() if used inappropriately. * @@ -837,12 +830,6 @@ static inline void *rhashtable_lookup_get_insert_fast( * @obj: pointer to hash head inside object * @params: hash table parameters * - * Locks down the bucket chain in both the old and new table if a resize - * is in progress to ensure that writers can't remove from the old table - * and can't insert to the new table during the atomic operation of search - * and insertion. Searches for duplicates in both the old and new table if - * a resize is in progress. - * * Lookups may occur in parallel with hashtable mutations and resizing. * * Will trigger an automatic deferred table resizing if residency in the diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 0a105d4af166..776b3a82d3a1 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -197,6 +197,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, return NULL; } + rcu_head_init(&tbl->rcu); INIT_LIST_HEAD(&tbl->walkers); tbl->hash_rnd = get_random_u32(); @@ -280,10 +281,9 @@ static int rhashtable_rehash_chain(struct rhashtable *ht, while (!(err = rhashtable_rehash_one(ht, old_hash))) ; - if (err == -ENOENT) { - old_tbl->rehash++; + if (err == -ENOENT) err = 0; - } + spin_unlock_bh(old_bucket_lock); return err; @@ -330,13 +330,16 @@ static int rhashtable_rehash_table(struct rhashtable *ht) spin_lock(&ht->lock); list_for_each_entry(walker, &old_tbl->walkers, list) walker->tbl = NULL; - spin_unlock(&ht->lock); /* Wait for readers. All new readers will see the new * table, and thus no references to the old table will * remain. + * We do this inside the locked region so that + * rhashtable_walk_stop() can use rcu_head_after_call_rcu() + * to check if it should not re-link the table. */ call_rcu(&old_tbl->rcu, bucket_table_free_rcu); + spin_unlock(&ht->lock); return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0; } @@ -578,46 +581,22 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, struct bucket_table *new_tbl; struct bucket_table *tbl; unsigned int hash; - spinlock_t *lock; void *data; - tbl = rcu_dereference(ht->tbl); - - /* All insertions must grab the oldest table containing - * the hashed bucket that is yet to be rehashed. - */ - for (;;) { - hash = rht_head_hashfn(ht, tbl, obj, ht->p); - lock = rht_bucket_lock(tbl, hash); - spin_lock_bh(lock); - - if (tbl->rehash <= hash) - break; - - spin_unlock_bh(lock); - tbl = rht_dereference_rcu(tbl->future_tbl, ht); - } - - data = rhashtable_lookup_one(ht, tbl, hash, key, obj); - new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data); - if (PTR_ERR(new_tbl) != -EEXIST) - data = ERR_CAST(new_tbl); + new_tbl = rcu_dereference(ht->tbl); - while (!IS_ERR_OR_NULL(new_tbl)) { + do { tbl = new_tbl; hash = rht_head_hashfn(ht, tbl, obj, ht->p); - spin_lock_nested(rht_bucket_lock(tbl, hash), - SINGLE_DEPTH_NESTING); + spin_lock_bh(rht_bucket_lock(tbl, hash)); data = rhashtable_lookup_one(ht, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data); if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); - spin_unlock(rht_bucket_lock(tbl, hash)); - } - - spin_unlock_bh(lock); + spin_unlock_bh(rht_bucket_lock(tbl, hash)); + } while (!IS_ERR_OR_NULL(new_tbl)); if (PTR_ERR(data) == -EAGAIN) data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?: @@ -939,10 +918,11 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter) ht = iter->ht; spin_lock(&ht->lock); - if (tbl->rehash < tbl->size) - list_add(&iter->walker.list, &tbl->walkers); - else + if (rcu_head_after_call_rcu(&tbl->rcu, bucket_table_free_rcu)) + /* This bucket table is being freed, don't re-link it. */ iter->walker.tbl = NULL; + else + list_add(&iter->walker.list, &tbl->walkers); spin_unlock(&ht->lock); out: -- cgit v1.2.3-71-gd317 From f7ad68bf98506f48129267438ada1255fc4edfa2 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 21 Mar 2019 14:42:40 +1100 Subject: rhashtable: rename rht_for_each*continue as *from. The pattern set by list.h is that for_each..continue() iterators start at the next entry after the given one, while for_each..from() iterators start at the given entry. The rht_for_each*continue() iterators are documented as though the start at the 'next' entry, but actually start at the given entry, and they are used expecting that behaviour. So fix the documentation and change the names to *from for consistency with list.h Acked-by: Herbert Xu Acked-by: Miguel Ojeda Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- .clang-format | 8 ++++---- include/linux/rhashtable.h | 40 ++++++++++++++++++++-------------------- lib/rhashtable.c | 2 +- 3 files changed, 25 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/.clang-format b/.clang-format index f49620f506f1..3a4c8220df2f 100644 --- a/.clang-format +++ b/.clang-format @@ -366,14 +366,14 @@ ForEachMacros: - 'rhl_for_each_entry_rcu' - 'rhl_for_each_rcu' - 'rht_for_each' - - 'rht_for_each_continue' + - 'rht_for_each_from' - 'rht_for_each_entry' - - 'rht_for_each_entry_continue' + - 'rht_for_each_entry_from' - 'rht_for_each_entry_rcu' - - 'rht_for_each_entry_rcu_continue' + - 'rht_for_each_entry_rcu_from' - 'rht_for_each_entry_safe' - 'rht_for_each_rcu' - - 'rht_for_each_rcu_continue' + - 'rht_for_each_rcu_from' - '__rq_for_each_bio' - 'rq_for_each_segment' - 'scsi_for_each_prot_sg' diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 3864193d5e2e..86dfa417848d 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -306,13 +306,13 @@ static inline struct rhash_head __rcu **rht_bucket_insert( } /** - * rht_for_each_continue - continue iterating over hash chain + * rht_for_each_from - iterate over hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index */ -#define rht_for_each_continue(pos, head, tbl, hash) \ +#define rht_for_each_from(pos, head, tbl, hash) \ for (pos = rht_dereference_bucket(head, tbl, hash); \ !rht_is_a_nulls(pos); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) @@ -324,18 +324,18 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * @hash: the hash value / bucket index */ #define rht_for_each(pos, tbl, hash) \ - rht_for_each_continue(pos, *rht_bucket(tbl, hash), tbl, hash) + rht_for_each_from(pos, *rht_bucket(tbl, hash), tbl, hash) /** - * rht_for_each_entry_continue - continue iterating over hash chain + * rht_for_each_entry_from - iterate over hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. */ -#define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member) \ +#define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member) \ for (pos = rht_dereference_bucket(head, tbl, hash); \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) @@ -349,7 +349,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_continue(tpos, pos, *rht_bucket(tbl, hash), \ + rht_for_each_entry_from(tpos, pos, *rht_bucket(tbl, hash), \ tbl, hash, member) /** @@ -374,9 +374,9 @@ static inline struct rhash_head __rcu **rht_bucket_insert( rht_dereference_bucket(pos->next, tbl, hash) : NULL) /** - * rht_for_each_rcu_continue - continue iterating over rcu hash chain + * rht_for_each_rcu_from - iterate over rcu hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @@ -384,7 +384,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_rcu_continue(pos, head, tbl, hash) \ +#define rht_for_each_rcu_from(pos, head, tbl, hash) \ for (({barrier(); }), \ pos = rht_dereference_bucket_rcu(head, tbl, hash); \ !rht_is_a_nulls(pos); \ @@ -401,13 +401,13 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_rcu(pos, tbl, hash) \ - rht_for_each_rcu_continue(pos, *rht_bucket(tbl, hash), tbl, hash) + rht_for_each_rcu_from(pos, *rht_bucket(tbl, hash), tbl, hash) /** - * rht_for_each_entry_rcu_continue - continue iterating over rcu hash chain + * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. @@ -416,7 +416,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \ +#define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \ for (({barrier(); }), \ pos = rht_dereference_bucket_rcu(head, tbl, hash); \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ @@ -435,7 +435,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_rcu_continue(tpos, pos, *rht_bucket(tbl, hash), \ + rht_for_each_entry_rcu_from(tpos, pos, *rht_bucket(tbl, hash), \ tbl, hash, member) /** @@ -491,7 +491,7 @@ restart: hash = rht_key_hashfn(ht, tbl, key, params); head = rht_bucket(tbl, hash); do { - rht_for_each_rcu_continue(he, *head, tbl, hash) { + rht_for_each_rcu_from(he, *head, tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) @@ -625,7 +625,7 @@ slow_path: if (!pprev) goto out; - rht_for_each_continue(head, *pprev, tbl, hash) { + rht_for_each_from(head, *pprev, tbl, hash) { struct rhlist_head *plist; struct rhlist_head *list; @@ -890,7 +890,7 @@ static inline int __rhashtable_remove_fast_one( spin_lock_bh(lock); pprev = rht_bucket_var(tbl, hash); - rht_for_each_continue(he, *pprev, tbl, hash) { + rht_for_each_from(he, *pprev, tbl, hash) { struct rhlist_head *list; list = container_of(he, struct rhlist_head, rhead); @@ -1042,7 +1042,7 @@ static inline int __rhashtable_replace_fast( spin_lock_bh(lock); pprev = rht_bucket_var(tbl, hash); - rht_for_each_continue(he, *pprev, tbl, hash) { + rht_for_each_from(he, *pprev, tbl, hash) { if (he != obj_old) { pprev = &he->next; continue; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 776b3a82d3a1..f65e43fb1ff8 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -490,7 +490,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, elasticity = RHT_ELASTICITY; pprev = rht_bucket_var(tbl, hash); - rht_for_each_continue(head, *pprev, tbl, hash) { + rht_for_each_from(head, *pprev, tbl, hash) { struct rhlist_head *list; struct rhlist_head *plist; -- cgit v1.2.3-71-gd317 From 85a51f8c28b9812642d76db6889f3f39dc3fbab3 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Fri, 22 Mar 2019 09:54:00 +0800 Subject: bpf: allow helpers to return PTR_TO_SOCK_COMMON It's currently not possible to access timewait or request sockets from eBPF, since there is no way to return a PTR_TO_SOCK_COMMON from a helper. Introduce RET_PTR_TO_SOCK_COMMON to enable this behaviour. Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f02367faa58d..f62897198844 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -205,6 +205,7 @@ enum bpf_return_type { RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ + RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 868a82ad5597..a476e13201d6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3148,6 +3148,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; -- cgit v1.2.3-71-gd317 From 3b0f31f2b8c9fb348e4530b88f6b64f9621f83d6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Mar 2019 22:51:02 +0100 Subject: genetlink: make policy common to family Since maxattr is common, the policy can't really differ sanely, so make it common as well. The only user that did in fact manage to make a non-common policy is taskstats, which has to be really careful about it (since it's still using a common maxattr!). This is no longer supported, but we can fake it using pre_doit. This reduces the size of e.g. nl80211.o (which has lots of commands): text data bss dec hex filename 398745 14323 2240 415308 6564c net/wireless/nl80211.o (before) 397913 14331 2240 414484 65314 net/wireless/nl80211.o (after) -------------------------------- -832 +8 0 -824 Which is obviously just 8 bytes for each command, and an added 8 bytes for the new policy pointer. I'm not sure why the ops list is counted as .text though. Most of the code transformations were done using the following spatch: @ops@ identifier OPS; expression POLICY; @@ struct genl_ops OPS[] = { ..., { - .policy = POLICY, }, ... }; @@ identifier ops.OPS; expression ops.POLICY; identifier fam; expression M; @@ struct genl_family fam = { .ops = OPS, .maxattr = M, + .policy = POLICY, ... }; This also gets rid of devlink_nl_cmd_region_read_dumpit() accessing the cb->data as ops, which we want to change in a later genl patch. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- drivers/block/nbd.c | 5 +- drivers/net/gtp.c | 4 +- drivers/net/ieee802154/mac802154_hwsim.c | 7 +-- drivers/net/macsec.c | 11 +--- drivers/net/team/team.c | 5 +- drivers/net/wireless/mac80211_hwsim.c | 7 +-- drivers/target/target_core_user.c | 5 +- include/linux/genl_magic_func.h | 4 +- include/net/genetlink.h | 4 +- kernel/taskstats.c | 28 ++++++++- net/batman-adv/netlink.c | 19 +----- net/core/devlink.c | 43 +------------ net/hsr/hsr_netlink.c | 3 +- net/ieee802154/ieee802154.h | 2 - net/ieee802154/netlink.c | 1 + net/ieee802154/nl802154.c | 30 +-------- net/ipv4/fou.c | 4 +- net/ipv4/tcp_metrics.c | 3 +- net/ipv6/ila/ila_main.c | 5 +- net/ipv6/seg6.c | 5 +- net/l2tp/l2tp_netlink.c | 10 +-- net/ncsi/ncsi-netlink.c | 7 +-- net/netfilter/ipvs/ip_vs_ctl.c | 13 +--- net/netlabel/netlabel_calipso.c | 5 +- net/netlabel/netlabel_cipso_v4.c | 5 +- net/netlabel/netlabel_mgmt.c | 9 +-- net/netlabel/netlabel_unlabeled.c | 9 +-- net/netlink/genetlink.c | 6 +- net/nfc/netlink.c | 20 +----- net/openvswitch/conntrack.c | 4 +- net/openvswitch/datapath.c | 17 ++--- net/openvswitch/meter.c | 5 +- net/smc/smc_pnet.c | 5 +- net/tipc/netlink.c | 22 +------ net/wimax/stack.c | 5 +- net/wireless/nl80211.c | 105 +------------------------------ 36 files changed, 68 insertions(+), 374 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 90ba9f4c03f3..92b8aafb8bb4 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1999,22 +1999,18 @@ out: static const struct genl_ops nbd_connect_genl_ops[] = { { .cmd = NBD_CMD_CONNECT, - .policy = nbd_attr_policy, .doit = nbd_genl_connect, }, { .cmd = NBD_CMD_DISCONNECT, - .policy = nbd_attr_policy, .doit = nbd_genl_disconnect, }, { .cmd = NBD_CMD_RECONFIGURE, - .policy = nbd_attr_policy, .doit = nbd_genl_reconfigure, }, { .cmd = NBD_CMD_STATUS, - .policy = nbd_attr_policy, .doit = nbd_genl_status, }, }; @@ -2031,6 +2027,7 @@ static struct genl_family nbd_genl_family __ro_after_init = { .ops = nbd_connect_genl_ops, .n_ops = ARRAY_SIZE(nbd_connect_genl_ops), .maxattr = NBD_ATTR_MAX, + .policy = nbd_attr_policy, .mcgrps = nbd_mcast_grps, .n_mcgrps = ARRAY_SIZE(nbd_mcast_grps), }; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 7a145172d503..c06e31747288 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1271,20 +1271,17 @@ static const struct genl_ops gtp_genl_ops[] = { { .cmd = GTP_CMD_NEWPDP, .doit = gtp_genl_new_pdp, - .policy = gtp_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = GTP_CMD_DELPDP, .doit = gtp_genl_del_pdp, - .policy = gtp_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = GTP_CMD_GETPDP, .doit = gtp_genl_get_pdp, .dumpit = gtp_genl_dump_pdp, - .policy = gtp_genl_policy, .flags = GENL_ADMIN_PERM, }, }; @@ -1294,6 +1291,7 @@ static struct genl_family gtp_genl_family __ro_after_init = { .version = 0, .hdrsize = 0, .maxattr = GTPA_MAX, + .policy = gtp_genl_policy, .netnsok = true, .module = THIS_MODULE, .ops = gtp_genl_ops, diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index b6743f03dce0..49866737f138 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -598,37 +598,31 @@ static const struct nla_policy hwsim_genl_policy[MAC802154_HWSIM_ATTR_MAX + 1] = static const struct genl_ops hwsim_nl_ops[] = { { .cmd = MAC802154_HWSIM_CMD_NEW_RADIO, - .policy = hwsim_genl_policy, .doit = hwsim_new_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_DEL_RADIO, - .policy = hwsim_genl_policy, .doit = hwsim_del_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_GET_RADIO, - .policy = hwsim_genl_policy, .doit = hwsim_get_radio_nl, .dumpit = hwsim_dump_radio_nl, }, { .cmd = MAC802154_HWSIM_CMD_NEW_EDGE, - .policy = hwsim_genl_policy, .doit = hwsim_new_edge_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_DEL_EDGE, - .policy = hwsim_genl_policy, .doit = hwsim_del_edge_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_SET_EDGE, - .policy = hwsim_genl_policy, .doit = hwsim_set_edge_lqi, .flags = GENL_UNS_ADMIN_PERM, }, @@ -638,6 +632,7 @@ static struct genl_family hwsim_genl_family __ro_after_init = { .name = "MAC802154_HWSIM", .version = 1, .maxattr = MAC802154_HWSIM_ATTR_MAX, + .policy = hwsim_genl_policy, .module = THIS_MODULE, .ops = hwsim_nl_ops, .n_ops = ARRAY_SIZE(hwsim_nl_ops), diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 64a982563d59..947c40f112d1 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2637,60 +2637,50 @@ static const struct genl_ops macsec_genl_ops[] = { { .cmd = MACSEC_CMD_GET_TXSC, .dumpit = macsec_dump_txsc, - .policy = macsec_genl_policy, }, { .cmd = MACSEC_CMD_ADD_RXSC, .doit = macsec_add_rxsc, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSC, .doit = macsec_del_rxsc, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSC, .doit = macsec_upd_rxsc, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_TXSA, .doit = macsec_add_txsa, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_TXSA, .doit = macsec_del_txsa, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_TXSA, .doit = macsec_upd_txsa, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_RXSA, .doit = macsec_add_rxsa, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSA, .doit = macsec_del_rxsa, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSA, .doit = macsec_upd_rxsa, - .policy = macsec_genl_policy, .flags = GENL_ADMIN_PERM, }, }; @@ -2700,6 +2690,7 @@ static struct genl_family macsec_fam __ro_after_init = { .hdrsize = 0, .version = MACSEC_GENL_VERSION, .maxattr = MACSEC_ATTR_MAX, + .policy = macsec_genl_policy, .netnsok = true, .module = THIS_MODULE, .ops = macsec_genl_ops, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index ee950aa48e3b..6ad74f898832 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2725,24 +2725,20 @@ static const struct genl_ops team_nl_ops[] = { { .cmd = TEAM_CMD_NOOP, .doit = team_nl_cmd_noop, - .policy = team_nl_policy, }, { .cmd = TEAM_CMD_OPTIONS_SET, .doit = team_nl_cmd_options_set, - .policy = team_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = TEAM_CMD_OPTIONS_GET, .doit = team_nl_cmd_options_get, - .policy = team_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = TEAM_CMD_PORT_LIST_GET, .doit = team_nl_cmd_port_list_get, - .policy = team_nl_policy, .flags = GENL_ADMIN_PERM, }, }; @@ -2755,6 +2751,7 @@ static struct genl_family team_nl_family __ro_after_init = { .name = TEAM_GENL_NAME, .version = TEAM_GENL_VERSION, .maxattr = TEAM_ATTR_MAX, + .policy = team_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = team_nl_ops, diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 0838af04d681..4cc7b222859c 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3620,35 +3620,29 @@ done: static const struct genl_ops hwsim_ops[] = { { .cmd = HWSIM_CMD_REGISTER, - .policy = hwsim_genl_policy, .doit = hwsim_register_received_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = HWSIM_CMD_FRAME, - .policy = hwsim_genl_policy, .doit = hwsim_cloned_frame_received_nl, }, { .cmd = HWSIM_CMD_TX_INFO_FRAME, - .policy = hwsim_genl_policy, .doit = hwsim_tx_info_frame_received_nl, }, { .cmd = HWSIM_CMD_NEW_RADIO, - .policy = hwsim_genl_policy, .doit = hwsim_new_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = HWSIM_CMD_DEL_RADIO, - .policy = hwsim_genl_policy, .doit = hwsim_del_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = HWSIM_CMD_GET_RADIO, - .policy = hwsim_genl_policy, .doit = hwsim_get_radio_nl, .dumpit = hwsim_dump_radio_nl, }, @@ -3658,6 +3652,7 @@ static struct genl_family hwsim_genl_family __ro_after_init = { .name = "MAC80211_HWSIM", .version = 1, .maxattr = HWSIM_ATTR_MAX, + .policy = hwsim_genl_policy, .netnsok = true, .module = THIS_MODULE, .ops = hwsim_ops, diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 5831e0eecea1..845b32eaff36 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -442,25 +442,21 @@ static const struct genl_ops tcmu_genl_ops[] = { { .cmd = TCMU_CMD_SET_FEATURES, .flags = GENL_ADMIN_PERM, - .policy = tcmu_attr_policy, .doit = tcmu_genl_set_features, }, { .cmd = TCMU_CMD_ADDED_DEVICE_DONE, .flags = GENL_ADMIN_PERM, - .policy = tcmu_attr_policy, .doit = tcmu_genl_add_dev_done, }, { .cmd = TCMU_CMD_REMOVED_DEVICE_DONE, .flags = GENL_ADMIN_PERM, - .policy = tcmu_attr_policy, .doit = tcmu_genl_rm_dev_done, }, { .cmd = TCMU_CMD_RECONFIG_DEVICE_DONE, .flags = GENL_ADMIN_PERM, - .policy = tcmu_attr_policy, .doit = tcmu_genl_reconfig_dev_done, }, }; @@ -472,6 +468,7 @@ static struct genl_family tcmu_genl_family __ro_after_init = { .name = "TCM-USER", .version = 2, .maxattr = TCMU_ATTR_MAX, + .policy = tcmu_attr_policy, .mcgrps = tcmu_mcgrps, .n_mcgrps = ARRAY_SIZE(tcmu_mcgrps), .netnsok = true, diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 83f81ac53282..6cb82301d8e9 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -233,7 +233,6 @@ const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) { \ handler \ .cmd = op_name, \ - .policy = CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy), \ }, #define ZZZ_genl_ops CONCAT_(GENL_MAGIC_FAMILY, _genl_ops) @@ -290,7 +289,8 @@ static struct genl_family ZZZ_genl_family __ro_after_init = { #ifdef GENL_MAGIC_FAMILY_HDRSZ .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), #endif - .maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1, + .maxattr = ARRAY_SIZE(CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy))-1, + .policy = CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy), .ops = ZZZ_genl_ops, .n_ops = ARRAY_SIZE(ZZZ_genl_ops), .mcgrps = ZZZ_genl_mcgrps, diff --git a/include/net/genetlink.h b/include/net/genetlink.h index aa2e5888f18d..6850c7b1a3a6 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -26,6 +26,7 @@ struct genl_info; * @name: name of family * @version: protocol version * @maxattr: maximum number of attributes supported + * @policy: netlink policy * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them * @parallel_ops: operations can be called in parallel and aren't @@ -56,6 +57,7 @@ struct genl_family { unsigned int maxattr; bool netnsok; bool parallel_ops; + const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); @@ -124,14 +126,12 @@ static inline int genl_err_attr(struct genl_info *info, int err, * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags - * @policy: attribute validation policy * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps */ struct genl_ops { - const struct nla_policy *policy; int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*start)(struct netlink_callback *cb); diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 4e62a4a8fa91..1b942a7caf26 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -650,16 +650,37 @@ static const struct genl_ops taskstats_ops[] = { { .cmd = TASKSTATS_CMD_GET, .doit = taskstats_user_cmd, - .policy = taskstats_cmd_get_policy, - .flags = GENL_ADMIN_PERM, + /* policy enforced later */ + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_HASPOL, }, { .cmd = CGROUPSTATS_CMD_GET, .doit = cgroupstats_user_cmd, - .policy = cgroupstats_cmd_get_policy, + /* policy enforced later */ + .flags = GENL_CMD_CAP_HASPOL, }, }; +static int taskstats_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + const struct nla_policy *policy = NULL; + + switch (ops->cmd) { + case TASKSTATS_CMD_GET: + policy = taskstats_cmd_get_policy; + break; + case CGROUPSTATS_CMD_GET: + policy = cgroupstats_cmd_get_policy; + break; + default: + return -EINVAL; + } + + return nlmsg_validate(info->nlhdr, GENL_HDRLEN, TASKSTATS_CMD_ATTR_MAX, + policy, info->extack); +} + static struct genl_family family __ro_after_init = { .name = TASKSTATS_GENL_NAME, .version = TASKSTATS_GENL_VERSION, @@ -667,6 +688,7 @@ static struct genl_family family __ro_after_init = { .module = THIS_MODULE, .ops = taskstats_ops, .n_ops = ARRAY_SIZE(taskstats_ops), + .pre_doit = taskstats_pre_doit, }; /* Needed early in initialization */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 67a58da2e6a0..d3033a3d2a63 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1345,34 +1345,29 @@ static const struct genl_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_MESH, /* can be retrieved by unprivileged users */ - .policy = batadv_netlink_policy, .doit = batadv_netlink_get_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .doit = batadv_netlink_tp_meter_start, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER_CANCEL, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .doit = batadv_netlink_tp_meter_cancel, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_GET_ROUTING_ALGOS, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_algo_dump, }, { .cmd = BATADV_CMD_GET_HARDIF, /* can be retrieved by unprivileged users */ - .policy = batadv_netlink_policy, .dumpit = batadv_netlink_dump_hardif, .doit = batadv_netlink_get_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | @@ -1381,68 +1376,57 @@ static const struct genl_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_tt_local_dump, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_tt_global_dump, }, { .cmd = BATADV_CMD_GET_ORIGINATORS, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_orig_dump, }, { .cmd = BATADV_CMD_GET_NEIGHBORS, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_hardif_neigh_dump, }, { .cmd = BATADV_CMD_GET_GATEWAYS, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_gw_dump, }, { .cmd = BATADV_CMD_GET_BLA_CLAIM, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_bla_claim_dump, }, { .cmd = BATADV_CMD_GET_BLA_BACKBONE, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_bla_backbone_dump, }, { .cmd = BATADV_CMD_GET_DAT_CACHE, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_dat_cache_dump, }, { .cmd = BATADV_CMD_GET_MCAST_FLAGS, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .dumpit = batadv_mcast_flags_dump, }, { .cmd = BATADV_CMD_SET_MESH, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .doit = batadv_netlink_set_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_SET_HARDIF, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .doit = batadv_netlink_set_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, @@ -1450,7 +1434,6 @@ static const struct genl_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_VLAN, /* can be retrieved by unprivileged users */ - .policy = batadv_netlink_policy, .doit = batadv_netlink_get_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, @@ -1458,7 +1441,6 @@ static const struct genl_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_SET_VLAN, .flags = GENL_ADMIN_PERM, - .policy = batadv_netlink_policy, .doit = batadv_netlink_set_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, @@ -1470,6 +1452,7 @@ struct genl_family batadv_netlink_family __ro_after_init = { .name = BATADV_NL_NAME, .version = 1, .maxattr = BATADV_ATTR_MAX, + .policy = batadv_netlink_policy, .netnsok = true, .pre_doit = batadv_pre_doit, .post_doit = batadv_post_doit, diff --git a/net/core/devlink.c b/net/core/devlink.c index 78e22cea4cc7..1a65cbf1ab05 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3640,7 +3640,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { u64 ret_offset, start_offset, end_offset = 0; - const struct genl_ops *ops = cb->data; struct devlink_region *region; struct nlattr *chunks_attr; const char *region_name; @@ -3657,7 +3656,8 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, return -ENOMEM; err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize, - attrs, DEVLINK_ATTR_MAX, ops->policy, cb->extack); + attrs, DEVLINK_ATTR_MAX, devlink_nl_family.policy, + cb->extack); if (err) goto out_free; @@ -4923,7 +4923,6 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_GET, .doit = devlink_nl_cmd_get_doit, .dumpit = devlink_nl_cmd_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, @@ -4931,21 +4930,18 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_PORT_GET, .doit = devlink_nl_cmd_port_get_doit, .dumpit = devlink_nl_cmd_port_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_PORT_SET, .doit = devlink_nl_cmd_port_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, { .cmd = DEVLINK_CMD_PORT_SPLIT, .doit = devlink_nl_cmd_port_split_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NO_LOCK, @@ -4953,7 +4949,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_PORT_UNSPLIT, .doit = devlink_nl_cmd_port_unsplit_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NO_LOCK, @@ -4962,7 +4957,6 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_SB_GET, .doit = devlink_nl_cmd_sb_get_doit, .dumpit = devlink_nl_cmd_sb_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ @@ -4971,7 +4965,6 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_SB_POOL_GET, .doit = devlink_nl_cmd_sb_pool_get_doit, .dumpit = devlink_nl_cmd_sb_pool_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ @@ -4979,7 +4972,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_SB_POOL_SET, .doit = devlink_nl_cmd_sb_pool_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, @@ -4988,7 +4980,6 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, .doit = devlink_nl_cmd_sb_port_pool_get_doit, .dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ @@ -4996,7 +4987,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, .doit = devlink_nl_cmd_sb_port_pool_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, @@ -5005,7 +4995,6 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit, .dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ @@ -5013,7 +5002,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, @@ -5021,7 +5009,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, .doit = devlink_nl_cmd_sb_occ_snapshot_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, @@ -5029,7 +5016,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, .doit = devlink_nl_cmd_sb_occ_max_clear_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, @@ -5037,14 +5023,12 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_ESWITCH_GET, .doit = devlink_nl_cmd_eswitch_get_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_ESWITCH_SET, .doit = devlink_nl_cmd_eswitch_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NO_LOCK, @@ -5052,49 +5036,42 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, .doit = devlink_nl_cmd_dpipe_table_get, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, .doit = devlink_nl_cmd_dpipe_entries_get, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, .doit = devlink_nl_cmd_dpipe_headers_get, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, .doit = devlink_nl_cmd_dpipe_table_counters_set, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_RESOURCE_SET, .doit = devlink_nl_cmd_resource_set, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_RESOURCE_DUMP, .doit = devlink_nl_cmd_resource_dump, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_RELOAD, .doit = devlink_nl_cmd_reload, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NO_LOCK, @@ -5103,14 +5080,12 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_PARAM_GET, .doit = devlink_nl_cmd_param_get_doit, .dumpit = devlink_nl_cmd_param_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_PARAM_SET, .doit = devlink_nl_cmd_param_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, @@ -5118,14 +5093,12 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_PORT_PARAM_GET, .doit = devlink_nl_cmd_port_param_get_doit, .dumpit = devlink_nl_cmd_port_param_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_PORT_PARAM_SET, .doit = devlink_nl_cmd_port_param_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, @@ -5133,21 +5106,18 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_REGION_GET, .doit = devlink_nl_cmd_region_get_doit, .dumpit = devlink_nl_cmd_region_get_dumpit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_REGION_DEL, .doit = devlink_nl_cmd_region_del, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_REGION_READ, .dumpit = devlink_nl_cmd_region_read_dumpit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, @@ -5155,7 +5125,6 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_INFO_GET, .doit = devlink_nl_cmd_info_get_doit, .dumpit = devlink_nl_cmd_info_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, @@ -5163,35 +5132,30 @@ static const struct genl_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, .doit = devlink_nl_cmd_health_reporter_get_doit, .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, - .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, .doit = devlink_nl_cmd_health_reporter_set_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, .doit = devlink_nl_cmd_health_reporter_recover_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, .doit = devlink_nl_cmd_health_reporter_diagnose_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, .doit = devlink_nl_cmd_health_reporter_dump_get_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NO_LOCK, @@ -5199,7 +5163,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NO_LOCK, @@ -5207,7 +5170,6 @@ static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_FLASH_UPDATE, .doit = devlink_nl_cmd_flash_update, - .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, @@ -5217,6 +5179,7 @@ static struct genl_family devlink_nl_family __ro_after_init = { .name = DEVLINK_GENL_NAME, .version = DEVLINK_GENL_VERSION, .maxattr = DEVLINK_ATTR_MAX, + .policy = devlink_nl_policy, .netnsok = true, .pre_doit = devlink_nl_pre_doit, .post_doit = devlink_nl_post_doit, diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index b9cce0fd5696..bcc04d3e724f 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -449,14 +449,12 @@ static const struct genl_ops hsr_ops[] = { { .cmd = HSR_C_GET_NODE_STATUS, .flags = 0, - .policy = hsr_genl_policy, .doit = hsr_get_node_status, .dumpit = NULL, }, { .cmd = HSR_C_GET_NODE_LIST, .flags = 0, - .policy = hsr_genl_policy, .doit = hsr_get_node_list, .dumpit = NULL, }, @@ -467,6 +465,7 @@ static struct genl_family hsr_genl_family __ro_after_init = { .name = "HSR", .version = 1, .maxattr = HSR_A_MAX, + .policy = hsr_genl_policy, .module = THIS_MODULE, .ops = hsr_ops, .n_ops = ARRAY_SIZE(hsr_ops), diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h index a5d7515b7f62..bc147bc8e36a 100644 --- a/net/ieee802154/ieee802154.h +++ b/net/ieee802154/ieee802154.h @@ -20,7 +20,6 @@ void ieee802154_nl_exit(void); #define IEEE802154_OP(_cmd, _func) \ { \ .cmd = _cmd, \ - .policy = ieee802154_policy, \ .doit = _func, \ .dumpit = NULL, \ .flags = GENL_ADMIN_PERM, \ @@ -29,7 +28,6 @@ void ieee802154_nl_exit(void); #define IEEE802154_DUMP(_cmd, _func, _dump) \ { \ .cmd = _cmd, \ - .policy = ieee802154_policy, \ .doit = _func, \ .dumpit = _dump, \ } diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 96636e3b7aa9..098d67439b6d 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -136,6 +136,7 @@ struct genl_family nl802154_family __ro_after_init = { .name = IEEE802154_NL_NAME, .version = 1, .maxattr = IEEE802154_ATTR_MAX, + .policy = ieee802154_policy, .module = THIS_MODULE, .ops = ieee802154_ops, .n_ops = ARRAY_SIZE(ieee802154_ops), diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 99f6c254ea77..308370cfd668 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -2220,7 +2220,6 @@ static const struct genl_ops nl802154_ops[] = { .doit = nl802154_get_wpan_phy, .dumpit = nl802154_dump_wpan_phy, .done = nl802154_dump_wpan_phy_done, - .policy = nl802154_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, @@ -2229,7 +2228,6 @@ static const struct genl_ops nl802154_ops[] = { .cmd = NL802154_CMD_GET_INTERFACE, .doit = nl802154_get_interface, .dumpit = nl802154_dump_interface, - .policy = nl802154_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | NL802154_FLAG_NEED_RTNL, @@ -2237,7 +2235,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_NEW_INTERFACE, .doit = nl802154_new_interface, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, @@ -2245,7 +2242,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_DEL_INTERFACE, .doit = nl802154_del_interface, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | NL802154_FLAG_NEED_RTNL, @@ -2253,7 +2249,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_CHANNEL, .doit = nl802154_set_channel, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, @@ -2261,7 +2256,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_CCA_MODE, .doit = nl802154_set_cca_mode, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, @@ -2269,7 +2263,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_CCA_ED_LEVEL, .doit = nl802154_set_cca_ed_level, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, @@ -2277,7 +2270,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_TX_POWER, .doit = nl802154_set_tx_power, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, @@ -2285,7 +2277,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_WPAN_PHY_NETNS, .doit = nl802154_wpan_phy_netns, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, @@ -2293,7 +2284,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_PAN_ID, .doit = nl802154_set_pan_id, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2301,7 +2291,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_SHORT_ADDR, .doit = nl802154_set_short_addr, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2309,7 +2298,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_BACKOFF_EXPONENT, .doit = nl802154_set_backoff_exponent, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2317,7 +2305,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_MAX_CSMA_BACKOFFS, .doit = nl802154_set_max_csma_backoffs, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2325,7 +2312,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_MAX_FRAME_RETRIES, .doit = nl802154_set_max_frame_retries, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2333,7 +2319,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_LBT_MODE, .doit = nl802154_set_lbt_mode, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2341,7 +2326,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_ACKREQ_DEFAULT, .doit = nl802154_set_ackreq_default, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2350,7 +2334,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_SET_SEC_PARAMS, .doit = nl802154_set_llsec_params, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2359,7 +2342,6 @@ static const struct genl_ops nl802154_ops[] = { .cmd = NL802154_CMD_GET_SEC_KEY, /* TODO .doit by matching key id? */ .dumpit = nl802154_dump_llsec_key, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2367,7 +2349,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_NEW_SEC_KEY, .doit = nl802154_add_llsec_key, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2375,7 +2356,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_DEL_SEC_KEY, .doit = nl802154_del_llsec_key, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2385,7 +2365,6 @@ static const struct genl_ops nl802154_ops[] = { .cmd = NL802154_CMD_GET_SEC_DEV, /* TODO .doit by matching extended_addr? */ .dumpit = nl802154_dump_llsec_dev, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2393,7 +2372,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_NEW_SEC_DEV, .doit = nl802154_add_llsec_dev, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2401,7 +2379,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_DEL_SEC_DEV, .doit = nl802154_del_llsec_dev, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2411,7 +2388,6 @@ static const struct genl_ops nl802154_ops[] = { .cmd = NL802154_CMD_GET_SEC_DEVKEY, /* TODO doit by matching ??? */ .dumpit = nl802154_dump_llsec_devkey, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2419,7 +2395,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_NEW_SEC_DEVKEY, .doit = nl802154_add_llsec_devkey, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2427,7 +2402,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_DEL_SEC_DEVKEY, .doit = nl802154_del_llsec_devkey, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2436,7 +2410,6 @@ static const struct genl_ops nl802154_ops[] = { .cmd = NL802154_CMD_GET_SEC_LEVEL, /* TODO .doit by matching frame_type? */ .dumpit = nl802154_dump_llsec_seclevel, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2444,7 +2417,6 @@ static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_NEW_SEC_LEVEL, .doit = nl802154_add_llsec_seclevel, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2453,7 +2425,6 @@ static const struct genl_ops nl802154_ops[] = { .cmd = NL802154_CMD_DEL_SEC_LEVEL, /* TODO match frame_type only? */ .doit = nl802154_del_llsec_seclevel, - .policy = nl802154_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, @@ -2466,6 +2437,7 @@ static struct genl_family nl802154_fam __ro_after_init = { .hdrsize = 0, /* no private header */ .version = 1, /* no particular meaning now */ .maxattr = NL802154_ATTR_MAX, + .policy = nl802154_policy, .netnsok = true, .pre_doit = nl802154_pre_doit, .post_doit = nl802154_post_doit, diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 79e98e21cdd7..a23fbb52d265 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -808,20 +808,17 @@ static const struct genl_ops fou_nl_ops[] = { { .cmd = FOU_CMD_ADD, .doit = fou_nl_cmd_add_port, - .policy = fou_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = FOU_CMD_DEL, .doit = fou_nl_cmd_rm_port, - .policy = fou_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = FOU_CMD_GET, .doit = fou_nl_cmd_get_port, .dumpit = fou_nl_dump, - .policy = fou_nl_policy, }, }; @@ -830,6 +827,7 @@ static struct genl_family fou_nl_family __ro_after_init = { .name = FOU_GENL_NAME, .version = FOU_GENL_VERSION, .maxattr = FOU_ATTR_MAX, + .policy = fou_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = fou_nl_ops, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index b467a7cabf40..4ccec4c705f7 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -953,12 +953,10 @@ static const struct genl_ops tcp_metrics_nl_ops[] = { .cmd = TCP_METRICS_CMD_GET, .doit = tcp_metrics_nl_cmd_get, .dumpit = tcp_metrics_nl_dump, - .policy = tcp_metrics_nl_policy, }, { .cmd = TCP_METRICS_CMD_DEL, .doit = tcp_metrics_nl_cmd_del, - .policy = tcp_metrics_nl_policy, .flags = GENL_ADMIN_PERM, }, }; @@ -968,6 +966,7 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = { .name = TCP_METRICS_GENL_NAME, .version = TCP_METRICS_GENL_VERSION, .maxattr = TCP_METRICS_ATTR_MAX, + .policy = tcp_metrics_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = tcp_metrics_nl_ops, diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index 18fac76b9520..8d31a5066d0c 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -17,19 +17,16 @@ static const struct genl_ops ila_nl_ops[] = { { .cmd = ILA_CMD_ADD, .doit = ila_xlat_nl_cmd_add_mapping, - .policy = ila_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = ILA_CMD_DEL, .doit = ila_xlat_nl_cmd_del_mapping, - .policy = ila_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = ILA_CMD_FLUSH, .doit = ila_xlat_nl_cmd_flush, - .policy = ila_nl_policy, .flags = GENL_ADMIN_PERM, }, { @@ -38,7 +35,6 @@ static const struct genl_ops ila_nl_ops[] = { .start = ila_xlat_nl_dump_start, .dumpit = ila_xlat_nl_dump, .done = ila_xlat_nl_dump_done, - .policy = ila_nl_policy, }, }; @@ -49,6 +45,7 @@ struct genl_family ila_nl_family __ro_after_init = { .name = ILA_GENL_NAME, .version = ILA_GENL_VERSION, .maxattr = ILA_ATTR_MAX, + .policy = ila_nl_policy, .netnsok = true, .parallel_ops = true, .module = THIS_MODULE, diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 9b2f272ca164..ceff773471e7 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -399,7 +399,6 @@ static const struct genl_ops seg6_genl_ops[] = { { .cmd = SEG6_CMD_SETHMAC, .doit = seg6_genl_sethmac, - .policy = seg6_genl_policy, .flags = GENL_ADMIN_PERM, }, { @@ -407,19 +406,16 @@ static const struct genl_ops seg6_genl_ops[] = { .start = seg6_genl_dumphmac_start, .dumpit = seg6_genl_dumphmac, .done = seg6_genl_dumphmac_done, - .policy = seg6_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_SET_TUNSRC, .doit = seg6_genl_set_tunsrc, - .policy = seg6_genl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_GET_TUNSRC, .doit = seg6_genl_get_tunsrc, - .policy = seg6_genl_policy, .flags = GENL_ADMIN_PERM, }, }; @@ -429,6 +425,7 @@ static struct genl_family seg6_genl_family __ro_after_init = { .name = SEG6_GENL_NAME, .version = SEG6_GENL_VERSION, .maxattr = SEG6_ATTR_MAX, + .policy = seg6_genl_policy, .netnsok = true, .parallel_ops = true, .ops = seg6_genl_ops, diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index edbd5d1fbcde..77595fcc9f75 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -916,57 +916,48 @@ static const struct genl_ops l2tp_nl_ops[] = { { .cmd = L2TP_CMD_NOOP, .doit = l2tp_nl_cmd_noop, - .policy = l2tp_nl_policy, /* can be retrieved by unprivileged users */ }, { .cmd = L2TP_CMD_TUNNEL_CREATE, .doit = l2tp_nl_cmd_tunnel_create, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_DELETE, .doit = l2tp_nl_cmd_tunnel_delete, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_MODIFY, .doit = l2tp_nl_cmd_tunnel_modify, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_GET, .doit = l2tp_nl_cmd_tunnel_get, .dumpit = l2tp_nl_cmd_tunnel_dump, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_CREATE, .doit = l2tp_nl_cmd_session_create, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_DELETE, .doit = l2tp_nl_cmd_session_delete, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_MODIFY, .doit = l2tp_nl_cmd_session_modify, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_GET, .doit = l2tp_nl_cmd_session_get, .dumpit = l2tp_nl_cmd_session_dump, - .policy = l2tp_nl_policy, .flags = GENL_ADMIN_PERM, }, }; @@ -976,6 +967,7 @@ static struct genl_family l2tp_nl_family __ro_after_init = { .version = L2TP_GENL_VERSION, .hdrsize = 0, .maxattr = L2TP_ATTR_MAX, + .policy = l2tp_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = l2tp_nl_ops, diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index bad17bba8ba7..367b2f6513e0 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -723,38 +723,32 @@ static int ncsi_set_channel_mask_nl(struct sk_buff *msg, static const struct genl_ops ncsi_ops[] = { { .cmd = NCSI_CMD_PKG_INFO, - .policy = ncsi_genl_policy, .doit = ncsi_pkg_info_nl, .dumpit = ncsi_pkg_info_all_nl, .flags = 0, }, { .cmd = NCSI_CMD_SET_INTERFACE, - .policy = ncsi_genl_policy, .doit = ncsi_set_interface_nl, .flags = GENL_ADMIN_PERM, }, { .cmd = NCSI_CMD_CLEAR_INTERFACE, - .policy = ncsi_genl_policy, .doit = ncsi_clear_interface_nl, .flags = GENL_ADMIN_PERM, }, { .cmd = NCSI_CMD_SEND_CMD, - .policy = ncsi_genl_policy, .doit = ncsi_send_cmd_nl, .flags = GENL_ADMIN_PERM, }, { .cmd = NCSI_CMD_SET_PACKAGE_MASK, - .policy = ncsi_genl_policy, .doit = ncsi_set_package_mask_nl, .flags = GENL_ADMIN_PERM, }, { .cmd = NCSI_CMD_SET_CHANNEL_MASK, - .policy = ncsi_genl_policy, .doit = ncsi_set_channel_mask_nl, .flags = GENL_ADMIN_PERM, }, @@ -764,6 +758,7 @@ static struct genl_family ncsi_genl_family __ro_after_init = { .name = "NCSI", .version = 0, .maxattr = NCSI_ATTR_MAX, + .policy = ncsi_genl_policy, .module = THIS_MODULE, .ops = ncsi_ops, .n_ops = ARRAY_SIZE(ncsi_ops), diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 053cd96b9c76..4b933669fd83 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3775,19 +3775,16 @@ static const struct genl_ops ip_vs_genl_ops[] = { { .cmd = IPVS_CMD_NEW_SERVICE, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_SET_SERVICE, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_DEL_SERVICE, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { @@ -3795,42 +3792,35 @@ static const struct genl_ops ip_vs_genl_ops[] = { .flags = GENL_ADMIN_PERM, .doit = ip_vs_genl_get_cmd, .dumpit = ip_vs_genl_dump_services, - .policy = ip_vs_cmd_policy, }, { .cmd = IPVS_CMD_NEW_DEST, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_SET_DEST, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_DEL_DEST, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { .cmd = IPVS_CMD_GET_DEST, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .dumpit = ip_vs_genl_dump_dests, }, { .cmd = IPVS_CMD_NEW_DAEMON, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_DEL_DAEMON, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_daemon, }, { @@ -3841,7 +3831,6 @@ static const struct genl_ops ip_vs_genl_ops[] = { { .cmd = IPVS_CMD_SET_CONFIG, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { @@ -3857,7 +3846,6 @@ static const struct genl_ops ip_vs_genl_ops[] = { { .cmd = IPVS_CMD_ZERO, .flags = GENL_ADMIN_PERM, - .policy = ip_vs_cmd_policy, .doit = ip_vs_genl_set_cmd, }, { @@ -3872,6 +3860,7 @@ static struct genl_family ip_vs_genl_family __ro_after_init = { .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, .maxattr = IPVS_CMD_ATTR_MAX, + .policy = ip_vs_cmd_policy, .netnsok = true, /* Make ipvsadm to work on netns */ .module = THIS_MODULE, .ops = ip_vs_genl_ops, diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index 4d748975117d..80184513b2b2 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -322,28 +322,24 @@ static const struct genl_ops netlbl_calipso_ops[] = { { .cmd = NLBL_CALIPSO_C_ADD, .flags = GENL_ADMIN_PERM, - .policy = calipso_genl_policy, .doit = netlbl_calipso_add, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_REMOVE, .flags = GENL_ADMIN_PERM, - .policy = calipso_genl_policy, .doit = netlbl_calipso_remove, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LIST, .flags = 0, - .policy = calipso_genl_policy, .doit = netlbl_calipso_list, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LISTALL, .flags = 0, - .policy = calipso_genl_policy, .doit = NULL, .dumpit = netlbl_calipso_listall, }, @@ -354,6 +350,7 @@ static struct genl_family netlbl_calipso_gnl_family __ro_after_init = { .name = NETLBL_NLTYPE_CALIPSO_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_CALIPSO_A_MAX, + .policy = calipso_genl_policy, .module = THIS_MODULE, .ops = netlbl_calipso_ops, .n_ops = ARRAY_SIZE(netlbl_calipso_ops), diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 9aacf2da3d98..ba7800f94ccc 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -734,28 +734,24 @@ static const struct genl_ops netlbl_cipsov4_ops[] = { { .cmd = NLBL_CIPSOV4_C_ADD, .flags = GENL_ADMIN_PERM, - .policy = netlbl_cipsov4_genl_policy, .doit = netlbl_cipsov4_add, .dumpit = NULL, }, { .cmd = NLBL_CIPSOV4_C_REMOVE, .flags = GENL_ADMIN_PERM, - .policy = netlbl_cipsov4_genl_policy, .doit = netlbl_cipsov4_remove, .dumpit = NULL, }, { .cmd = NLBL_CIPSOV4_C_LIST, .flags = 0, - .policy = netlbl_cipsov4_genl_policy, .doit = netlbl_cipsov4_list, .dumpit = NULL, }, { .cmd = NLBL_CIPSOV4_C_LISTALL, .flags = 0, - .policy = netlbl_cipsov4_genl_policy, .doit = NULL, .dumpit = netlbl_cipsov4_listall, }, @@ -766,6 +762,7 @@ static struct genl_family netlbl_cipsov4_gnl_family __ro_after_init = { .name = NETLBL_NLTYPE_CIPSOV4_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_CIPSOV4_A_MAX, + .policy = netlbl_cipsov4_genl_policy, .module = THIS_MODULE, .ops = netlbl_cipsov4_ops, .n_ops = ARRAY_SIZE(netlbl_cipsov4_ops), diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 21e0095b1d14..a16eacfb2236 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -773,56 +773,48 @@ static const struct genl_ops netlbl_mgmt_genl_ops[] = { { .cmd = NLBL_MGMT_C_ADD, .flags = GENL_ADMIN_PERM, - .policy = netlbl_mgmt_genl_policy, .doit = netlbl_mgmt_add, .dumpit = NULL, }, { .cmd = NLBL_MGMT_C_REMOVE, .flags = GENL_ADMIN_PERM, - .policy = netlbl_mgmt_genl_policy, .doit = netlbl_mgmt_remove, .dumpit = NULL, }, { .cmd = NLBL_MGMT_C_LISTALL, .flags = 0, - .policy = netlbl_mgmt_genl_policy, .doit = NULL, .dumpit = netlbl_mgmt_listall, }, { .cmd = NLBL_MGMT_C_ADDDEF, .flags = GENL_ADMIN_PERM, - .policy = netlbl_mgmt_genl_policy, .doit = netlbl_mgmt_adddef, .dumpit = NULL, }, { .cmd = NLBL_MGMT_C_REMOVEDEF, .flags = GENL_ADMIN_PERM, - .policy = netlbl_mgmt_genl_policy, .doit = netlbl_mgmt_removedef, .dumpit = NULL, }, { .cmd = NLBL_MGMT_C_LISTDEF, .flags = 0, - .policy = netlbl_mgmt_genl_policy, .doit = netlbl_mgmt_listdef, .dumpit = NULL, }, { .cmd = NLBL_MGMT_C_PROTOCOLS, .flags = 0, - .policy = netlbl_mgmt_genl_policy, .doit = NULL, .dumpit = netlbl_mgmt_protocols, }, { .cmd = NLBL_MGMT_C_VERSION, .flags = 0, - .policy = netlbl_mgmt_genl_policy, .doit = netlbl_mgmt_version, .dumpit = NULL, }, @@ -833,6 +825,7 @@ static struct genl_family netlbl_mgmt_gnl_family __ro_after_init = { .name = NETLBL_NLTYPE_MGMT_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_MGMT_A_MAX, + .policy = netlbl_mgmt_genl_policy, .module = THIS_MODULE, .ops = netlbl_mgmt_genl_ops, .n_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops), diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index c92894c3e40a..6b1b6c2b5141 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1318,56 +1318,48 @@ static const struct genl_ops netlbl_unlabel_genl_ops[] = { { .cmd = NLBL_UNLABEL_C_STATICADD, .flags = GENL_ADMIN_PERM, - .policy = netlbl_unlabel_genl_policy, .doit = netlbl_unlabel_staticadd, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICREMOVE, .flags = GENL_ADMIN_PERM, - .policy = netlbl_unlabel_genl_policy, .doit = netlbl_unlabel_staticremove, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICLIST, .flags = 0, - .policy = netlbl_unlabel_genl_policy, .doit = NULL, .dumpit = netlbl_unlabel_staticlist, }, { .cmd = NLBL_UNLABEL_C_STATICADDDEF, .flags = GENL_ADMIN_PERM, - .policy = netlbl_unlabel_genl_policy, .doit = netlbl_unlabel_staticadddef, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICREMOVEDEF, .flags = GENL_ADMIN_PERM, - .policy = netlbl_unlabel_genl_policy, .doit = netlbl_unlabel_staticremovedef, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICLISTDEF, .flags = 0, - .policy = netlbl_unlabel_genl_policy, .doit = NULL, .dumpit = netlbl_unlabel_staticlistdef, }, { .cmd = NLBL_UNLABEL_C_ACCEPT, .flags = GENL_ADMIN_PERM, - .policy = netlbl_unlabel_genl_policy, .doit = netlbl_unlabel_accept, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_LIST, .flags = 0, - .policy = netlbl_unlabel_genl_policy, .doit = netlbl_unlabel_list, .dumpit = NULL, }, @@ -1378,6 +1370,7 @@ static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = { .name = NETLBL_NLTYPE_UNLABELED_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_UNLABEL_A_MAX, + .policy = netlbl_unlabel_genl_policy, .module = THIS_MODULE, .ops = netlbl_unlabel_genl_ops, .n_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops), diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 25eeb6d2a75a..a75ea33fb5ea 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -577,7 +577,7 @@ static int genl_family_rcv_msg(const struct genl_family *family, if (attrbuf) { err = nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, - ops->policy, extack); + family->policy, extack); if (err < 0) goto out; } @@ -677,7 +677,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, op_flags |= GENL_CMD_CAP_DUMP; if (ops->doit) op_flags |= GENL_CMD_CAP_DO; - if (ops->policy) + if (family->policy) op_flags |= GENL_CMD_CAP_HASPOL; nest = nla_nest_start(skb, i + 1); @@ -939,7 +939,6 @@ static const struct genl_ops genl_ctrl_ops[] = { .cmd = CTRL_CMD_GETFAMILY, .doit = ctrl_getfamily, .dumpit = ctrl_dumpfamily, - .policy = ctrl_policy, }, }; @@ -957,6 +956,7 @@ static struct genl_family genl_ctrl __ro_after_init = { .name = "nlctrl", .version = 0x2, .maxattr = CTRL_ATTR_MAX, + .policy = ctrl_policy, .netnsok = true, }; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 376181cc1def..4d9f3ac8d562 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1670,99 +1670,80 @@ static const struct genl_ops nfc_genl_ops[] = { .doit = nfc_genl_get_device, .dumpit = nfc_genl_dump_devices, .done = nfc_genl_dump_devices_done, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_DEV_UP, .doit = nfc_genl_dev_up, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_DEV_DOWN, .doit = nfc_genl_dev_down, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_START_POLL, .doit = nfc_genl_start_poll, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_STOP_POLL, .doit = nfc_genl_stop_poll, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_DEP_LINK_UP, .doit = nfc_genl_dep_link_up, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_DEP_LINK_DOWN, .doit = nfc_genl_dep_link_down, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_GET_TARGET, .dumpit = nfc_genl_dump_targets, .done = nfc_genl_dump_targets_done, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_LLC_GET_PARAMS, .doit = nfc_genl_llc_get_params, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_LLC_SET_PARAMS, .doit = nfc_genl_llc_set_params, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_LLC_SDREQ, .doit = nfc_genl_llc_sdreq, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_FW_DOWNLOAD, .doit = nfc_genl_fw_download, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_ENABLE_SE, .doit = nfc_genl_enable_se, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_DISABLE_SE, .doit = nfc_genl_disable_se, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_GET_SE, .dumpit = nfc_genl_dump_ses, .done = nfc_genl_dump_ses_done, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_SE_IO, .doit = nfc_genl_se_io, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_ACTIVATE_TARGET, .doit = nfc_genl_activate_target, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_VENDOR, .doit = nfc_genl_vendor_cmd, - .policy = nfc_genl_policy, }, { .cmd = NFC_CMD_DEACTIVATE_TARGET, .doit = nfc_genl_deactivate_target, - .policy = nfc_genl_policy, }, }; @@ -1771,6 +1752,7 @@ static struct genl_family nfc_genl_family __ro_after_init = { .name = NFC_GENL_NAME, .version = NFC_GENL_VERSION, .maxattr = NFC_ATTR_MAX, + .policy = nfc_genl_policy, .module = THIS_MODULE, .ops = nfc_genl_ops, .n_ops = ARRAY_SIZE(nfc_genl_ops), diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 1b6896896fff..51080004677e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -2154,18 +2154,15 @@ static struct genl_ops ct_limit_genl_ops[] = { { .cmd = OVS_CT_LIMIT_CMD_SET, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ - .policy = ct_limit_policy, .doit = ovs_ct_limit_cmd_set, }, { .cmd = OVS_CT_LIMIT_CMD_DEL, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ - .policy = ct_limit_policy, .doit = ovs_ct_limit_cmd_del, }, { .cmd = OVS_CT_LIMIT_CMD_GET, .flags = 0, /* OK for unprivileged users. */ - .policy = ct_limit_policy, .doit = ovs_ct_limit_cmd_get, }, }; @@ -2179,6 +2176,7 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { .name = OVS_CT_LIMIT_FAMILY, .version = OVS_CT_LIMIT_VERSION, .maxattr = OVS_CT_LIMIT_ATTR_MAX, + .policy = ct_limit_policy, .netnsok = true, .parallel_ops = true, .ops = ct_limit_genl_ops, diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9dd158ab51b3..a64d3eb1f9a9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -639,7 +639,6 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { static const struct genl_ops dp_packet_genl_ops[] = { { .cmd = OVS_PACKET_CMD_EXECUTE, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = packet_policy, .doit = ovs_packet_cmd_execute } }; @@ -649,6 +648,7 @@ static struct genl_family dp_packet_genl_family __ro_after_init = { .name = OVS_PACKET_FAMILY, .version = OVS_PACKET_VERSION, .maxattr = OVS_PACKET_ATTR_MAX, + .policy = packet_policy, .netnsok = true, .parallel_ops = true, .ops = dp_packet_genl_ops, @@ -1424,23 +1424,19 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { static const struct genl_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_NEW, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = flow_policy, .doit = ovs_flow_cmd_new }, { .cmd = OVS_FLOW_CMD_DEL, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = flow_policy, .doit = ovs_flow_cmd_del }, { .cmd = OVS_FLOW_CMD_GET, .flags = 0, /* OK for unprivileged users. */ - .policy = flow_policy, .doit = ovs_flow_cmd_get, .dumpit = ovs_flow_cmd_dump }, { .cmd = OVS_FLOW_CMD_SET, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = flow_policy, .doit = ovs_flow_cmd_set, }, }; @@ -1450,6 +1446,7 @@ static struct genl_family dp_flow_genl_family __ro_after_init = { .name = OVS_FLOW_FAMILY, .version = OVS_FLOW_VERSION, .maxattr = OVS_FLOW_ATTR_MAX, + .policy = flow_policy, .netnsok = true, .parallel_ops = true, .ops = dp_flow_genl_ops, @@ -1817,23 +1814,19 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { static const struct genl_ops dp_datapath_genl_ops[] = { { .cmd = OVS_DP_CMD_NEW, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = datapath_policy, .doit = ovs_dp_cmd_new }, { .cmd = OVS_DP_CMD_DEL, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = datapath_policy, .doit = ovs_dp_cmd_del }, { .cmd = OVS_DP_CMD_GET, .flags = 0, /* OK for unprivileged users. */ - .policy = datapath_policy, .doit = ovs_dp_cmd_get, .dumpit = ovs_dp_cmd_dump }, { .cmd = OVS_DP_CMD_SET, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = datapath_policy, .doit = ovs_dp_cmd_set, }, }; @@ -1843,6 +1836,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { .name = OVS_DATAPATH_FAMILY, .version = OVS_DATAPATH_VERSION, .maxattr = OVS_DP_ATTR_MAX, + .policy = datapath_policy, .netnsok = true, .parallel_ops = true, .ops = dp_datapath_genl_ops, @@ -2260,23 +2254,19 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { static const struct genl_ops dp_vport_genl_ops[] = { { .cmd = OVS_VPORT_CMD_NEW, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = vport_policy, .doit = ovs_vport_cmd_new }, { .cmd = OVS_VPORT_CMD_DEL, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = vport_policy, .doit = ovs_vport_cmd_del }, { .cmd = OVS_VPORT_CMD_GET, .flags = 0, /* OK for unprivileged users. */ - .policy = vport_policy, .doit = ovs_vport_cmd_get, .dumpit = ovs_vport_cmd_dump }, { .cmd = OVS_VPORT_CMD_SET, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ - .policy = vport_policy, .doit = ovs_vport_cmd_set, }, }; @@ -2286,6 +2276,7 @@ struct genl_family dp_vport_genl_family __ro_after_init = { .name = OVS_VPORT_FAMILY, .version = OVS_VPORT_VERSION, .maxattr = OVS_VPORT_ATTR_MAX, + .policy = vport_policy, .netnsok = true, .parallel_ops = true, .ops = dp_vport_genl_ops, diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 43849d752a1e..0be3d097ae01 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -527,26 +527,22 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, static struct genl_ops dp_meter_genl_ops[] = { { .cmd = OVS_METER_CMD_FEATURES, .flags = 0, /* OK for unprivileged users. */ - .policy = meter_policy, .doit = ovs_meter_cmd_features }, { .cmd = OVS_METER_CMD_SET, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ - .policy = meter_policy, .doit = ovs_meter_cmd_set, }, { .cmd = OVS_METER_CMD_GET, .flags = 0, /* OK for unprivileged users. */ - .policy = meter_policy, .doit = ovs_meter_cmd_get, }, { .cmd = OVS_METER_CMD_DEL, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ - .policy = meter_policy, .doit = ovs_meter_cmd_del }, }; @@ -560,6 +556,7 @@ struct genl_family dp_meter_genl_family __ro_after_init = { .name = OVS_METER_FAMILY, .version = OVS_METER_VERSION, .maxattr = OVS_METER_ATTR_MAX, + .policy = meter_policy, .netnsok = true, .parallel_ops = true, .ops = dp_meter_genl_ops, diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 8d2f6296279c..3cdf81cf97a3 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -611,7 +611,6 @@ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .flags = GENL_ADMIN_PERM, - .policy = smc_pnet_policy, .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start @@ -619,19 +618,16 @@ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_ADD, .flags = GENL_ADMIN_PERM, - .policy = smc_pnet_policy, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .flags = GENL_ADMIN_PERM, - .policy = smc_pnet_policy, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .flags = GENL_ADMIN_PERM, - .policy = smc_pnet_policy, .doit = smc_pnet_flush } }; @@ -642,6 +638,7 @@ static struct genl_family smc_pnet_nl_family __ro_after_init = { .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, + .policy = smc_pnet_policy, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 5240f64e8ccc..2d178df0a89f 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -144,114 +144,93 @@ static const struct genl_ops tipc_genl_v2_ops[] = { { .cmd = TIPC_NL_BEARER_DISABLE, .doit = tipc_nl_bearer_disable, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_ENABLE, .doit = tipc_nl_bearer_enable, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_GET, .doit = tipc_nl_bearer_get, .dumpit = tipc_nl_bearer_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_ADD, .doit = tipc_nl_bearer_add, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_SET, .doit = tipc_nl_bearer_set, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_SOCK_GET, .start = tipc_dump_start, .dumpit = tipc_nl_sk_dump, .done = tipc_dump_done, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_PUBL_GET, .dumpit = tipc_nl_publ_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_LINK_GET, .doit = tipc_nl_node_get_link, .dumpit = tipc_nl_node_dump_link, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_LINK_SET, .doit = tipc_nl_node_set_link, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_LINK_RESET_STATS, .doit = tipc_nl_node_reset_link_stats, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MEDIA_GET, .doit = tipc_nl_media_get, .dumpit = tipc_nl_media_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MEDIA_SET, .doit = tipc_nl_media_set, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NODE_GET, .dumpit = tipc_nl_node_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NET_GET, .dumpit = tipc_nl_net_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NET_SET, .doit = tipc_nl_net_set, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NAME_TABLE_GET, .dumpit = tipc_nl_name_table_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MON_SET, .doit = tipc_nl_node_set_monitor, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MON_GET, .doit = tipc_nl_node_get_monitor, .dumpit = tipc_nl_node_dump_monitor, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MON_PEER_GET, .dumpit = tipc_nl_node_dump_monitor_peer, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_PEER_REMOVE, .doit = tipc_nl_peer_rm, - .policy = tipc_nl_policy, }, #ifdef CONFIG_TIPC_MEDIA_UDP { .cmd = TIPC_NL_UDP_GET_REMOTEIP, .dumpit = tipc_udp_nl_dump_remoteip, - .policy = tipc_nl_policy, }, #endif }; @@ -261,6 +240,7 @@ struct genl_family tipc_genl_family __ro_after_init = { .version = TIPC_GENL_V2_VERSION, .hdrsize = 0, .maxattr = TIPC_NLA_MAX, + .policy = tipc_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = tipc_genl_v2_ops, diff --git a/net/wimax/stack.c b/net/wimax/stack.c index a6307813b6d5..b7f571e55448 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -420,25 +420,21 @@ static const struct genl_ops wimax_gnl_ops[] = { { .cmd = WIMAX_GNL_OP_MSG_FROM_USER, .flags = GENL_ADMIN_PERM, - .policy = wimax_gnl_policy, .doit = wimax_gnl_doit_msg_from_user, }, { .cmd = WIMAX_GNL_OP_RESET, .flags = GENL_ADMIN_PERM, - .policy = wimax_gnl_policy, .doit = wimax_gnl_doit_reset, }, { .cmd = WIMAX_GNL_OP_RFKILL, .flags = GENL_ADMIN_PERM, - .policy = wimax_gnl_policy, .doit = wimax_gnl_doit_rfkill, }, { .cmd = WIMAX_GNL_OP_STATE_GET, .flags = GENL_ADMIN_PERM, - .policy = wimax_gnl_policy, .doit = wimax_gnl_doit_state_get, }, }; @@ -582,6 +578,7 @@ struct genl_family wimax_gnl_family __ro_after_init = { .version = WIMAX_GNL_VERSION, .hdrsize = 0, .maxattr = WIMAX_GNL_ATTR_MAX, + .policy = wimax_gnl_policy, .module = THIS_MODULE, .ops = wimax_gnl_ops, .n_ops = ARRAY_SIZE(wimax_gnl_ops), diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 25a9e3b5c154..33408ba1d7ee 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13368,7 +13368,6 @@ static const struct genl_ops nl80211_ops[] = { .doit = nl80211_get_wiphy, .dumpit = nl80211_dump_wiphy, .done = nl80211_dump_wiphy_done, - .policy = nl80211_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -13376,7 +13375,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_WIPHY, .doit = nl80211_set_wiphy, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_RTNL, }, @@ -13384,7 +13382,6 @@ static const struct genl_ops nl80211_ops[] = { .cmd = NL80211_CMD_GET_INTERFACE, .doit = nl80211_get_interface, .dumpit = nl80211_dump_interface, - .policy = nl80211_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL80211_FLAG_NEED_WDEV | NL80211_FLAG_NEED_RTNL, @@ -13392,7 +13389,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_INTERFACE, .doit = nl80211_set_interface, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13400,7 +13396,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_NEW_INTERFACE, .doit = nl80211_new_interface, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -13408,7 +13403,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEL_INTERFACE, .doit = nl80211_del_interface, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV | NL80211_FLAG_NEED_RTNL, @@ -13416,7 +13410,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_KEY, .doit = nl80211_get_key, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13424,7 +13417,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_KEY, .doit = nl80211_set_key, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL | @@ -13433,7 +13425,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_NEW_KEY, .doit = nl80211_new_key, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL | @@ -13442,14 +13433,12 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEL_KEY, .doit = nl80211_del_key, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_BEACON, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_set_beacon, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | @@ -13457,7 +13446,6 @@ static const struct genl_ops nl80211_ops[] = { }, { .cmd = NL80211_CMD_START_AP, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_start_ap, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | @@ -13465,7 +13453,6 @@ static const struct genl_ops nl80211_ops[] = { }, { .cmd = NL80211_CMD_STOP_AP, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_stop_ap, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | @@ -13475,14 +13462,12 @@ static const struct genl_ops nl80211_ops[] = { .cmd = NL80211_CMD_GET_STATION, .doit = nl80211_get_station, .dumpit = nl80211_dump_station, - .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_STATION, .doit = nl80211_set_station, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13490,7 +13475,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_NEW_STATION, .doit = nl80211_new_station, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13498,7 +13482,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEL_STATION, .doit = nl80211_del_station, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13507,7 +13490,6 @@ static const struct genl_ops nl80211_ops[] = { .cmd = NL80211_CMD_GET_MPATH, .doit = nl80211_get_mpath, .dumpit = nl80211_dump_mpath, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13516,7 +13498,6 @@ static const struct genl_ops nl80211_ops[] = { .cmd = NL80211_CMD_GET_MPP, .doit = nl80211_get_mpp, .dumpit = nl80211_dump_mpp, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13524,7 +13505,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_MPATH, .doit = nl80211_set_mpath, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13532,7 +13512,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_NEW_MPATH, .doit = nl80211_new_mpath, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13540,7 +13519,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEL_MPATH, .doit = nl80211_del_mpath, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13548,7 +13526,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_BSS, .doit = nl80211_set_bss, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13557,7 +13534,6 @@ static const struct genl_ops nl80211_ops[] = { .cmd = NL80211_CMD_GET_REG, .doit = nl80211_get_reg_do, .dumpit = nl80211_get_reg_dump, - .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_RTNL, /* can be retrieved by unprivileged users */ }, @@ -13565,7 +13541,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_REG, .doit = nl80211_set_reg, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_RTNL, }, @@ -13573,19 +13548,16 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_REQ_SET_REG, .doit = nl80211_req_set_reg, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = NL80211_CMD_RELOAD_REGDB, .doit = nl80211_reload_regdb, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, { .cmd = NL80211_CMD_GET_MESH_CONFIG, .doit = nl80211_get_mesh_config, - .policy = nl80211_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13593,7 +13565,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_MESH_CONFIG, .doit = nl80211_update_mesh_config, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13601,7 +13572,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_TRIGGER_SCAN, .doit = nl80211_trigger_scan, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13609,20 +13579,17 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_ABORT_SCAN, .doit = nl80211_abort_scan, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_SCAN, - .policy = nl80211_policy, .dumpit = nl80211_dump_scan, }, { .cmd = NL80211_CMD_START_SCHED_SCAN, .doit = nl80211_start_sched_scan, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13630,7 +13597,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_STOP_SCHED_SCAN, .doit = nl80211_stop_sched_scan, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13638,7 +13604,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_AUTHENTICATE, .doit = nl80211_authenticate, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL | @@ -13647,7 +13612,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_ASSOCIATE, .doit = nl80211_associate, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13655,7 +13619,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEAUTHENTICATE, .doit = nl80211_deauthenticate, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13663,7 +13626,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DISASSOCIATE, .doit = nl80211_disassociate, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13671,7 +13633,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_JOIN_IBSS, .doit = nl80211_join_ibss, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13679,7 +13640,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_LEAVE_IBSS, .doit = nl80211_leave_ibss, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13689,7 +13649,6 @@ static const struct genl_ops nl80211_ops[] = { .cmd = NL80211_CMD_TESTMODE, .doit = nl80211_testmode_do, .dumpit = nl80211_testmode_dump, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -13698,7 +13657,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_CONNECT, .doit = nl80211_connect, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13706,7 +13664,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS, .doit = nl80211_update_connect_params, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13714,7 +13671,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DISCONNECT, .doit = nl80211_disconnect, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13722,20 +13678,17 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_WIPHY_NETNS, .doit = nl80211_wiphy_netns, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_SURVEY, - .policy = nl80211_policy, .dumpit = nl80211_dump_survey, }, { .cmd = NL80211_CMD_SET_PMKSA, .doit = nl80211_setdel_pmksa, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13743,7 +13696,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEL_PMKSA, .doit = nl80211_setdel_pmksa, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13751,7 +13703,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_FLUSH_PMKSA, .doit = nl80211_flush_pmksa, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13759,7 +13710,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_REMAIN_ON_CHANNEL, .doit = nl80211_remain_on_channel, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13767,7 +13717,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, .doit = nl80211_cancel_remain_on_channel, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13775,7 +13724,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_TX_BITRATE_MASK, .doit = nl80211_set_tx_bitrate_mask, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13783,7 +13731,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_REGISTER_FRAME, .doit = nl80211_register_mgmt, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV | NL80211_FLAG_NEED_RTNL, @@ -13791,7 +13738,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_FRAME, .doit = nl80211_tx_mgmt, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13799,7 +13745,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_FRAME_WAIT_CANCEL, .doit = nl80211_tx_mgmt_cancel_wait, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13807,7 +13752,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_POWER_SAVE, .doit = nl80211_set_power_save, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13815,7 +13759,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_POWER_SAVE, .doit = nl80211_get_power_save, - .policy = nl80211_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13823,7 +13766,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_CQM, .doit = nl80211_set_cqm, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13831,7 +13773,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_CHANNEL, .doit = nl80211_set_channel, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13839,7 +13780,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_WDS_PEER, .doit = nl80211_set_wds_peer, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13847,7 +13787,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_JOIN_MESH, .doit = nl80211_join_mesh, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13855,7 +13794,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_LEAVE_MESH, .doit = nl80211_leave_mesh, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13863,7 +13801,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_JOIN_OCB, .doit = nl80211_join_ocb, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13871,7 +13808,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_LEAVE_OCB, .doit = nl80211_leave_ocb, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13880,7 +13816,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_WOWLAN, .doit = nl80211_get_wowlan, - .policy = nl80211_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -13888,7 +13823,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_WOWLAN, .doit = nl80211_set_wowlan, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -13897,7 +13831,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_REKEY_OFFLOAD, .doit = nl80211_set_rekey_data, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL | @@ -13906,7 +13839,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_TDLS_MGMT, .doit = nl80211_tdls_mgmt, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13914,7 +13846,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_TDLS_OPER, .doit = nl80211_tdls_oper, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13922,7 +13853,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_UNEXPECTED_FRAME, .doit = nl80211_register_unexpected_frame, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13930,7 +13860,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_PROBE_CLIENT, .doit = nl80211_probe_client, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13938,7 +13867,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_REGISTER_BEACONS, .doit = nl80211_register_beacons, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -13946,7 +13874,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_NOACK_MAP, .doit = nl80211_set_noack_map, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -13954,7 +13881,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_START_P2P_DEVICE, .doit = nl80211_start_p2p_device, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV | NL80211_FLAG_NEED_RTNL, @@ -13962,7 +13888,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_STOP_P2P_DEVICE, .doit = nl80211_stop_p2p_device, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13970,7 +13895,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_START_NAN, .doit = nl80211_start_nan, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV | NL80211_FLAG_NEED_RTNL, @@ -13978,7 +13902,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_STOP_NAN, .doit = nl80211_stop_nan, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13986,7 +13909,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_ADD_NAN_FUNCTION, .doit = nl80211_nan_add_func, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -13994,7 +13916,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEL_NAN_FUNCTION, .doit = nl80211_nan_del_func, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14002,7 +13923,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_CHANGE_NAN_CONFIG, .doit = nl80211_nan_change_config, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14010,7 +13930,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_MCAST_RATE, .doit = nl80211_set_mcast_rate, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -14018,7 +13937,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_MAC_ACL, .doit = nl80211_set_mac_acl, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -14026,7 +13944,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_RADAR_DETECT, .doit = nl80211_start_radar_detection, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14034,12 +13951,10 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_PROTOCOL_FEATURES, .doit = nl80211_get_protocol_features, - .policy = nl80211_policy, }, { .cmd = NL80211_CMD_UPDATE_FT_IES, .doit = nl80211_update_ft_ies, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14047,7 +13962,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_CRIT_PROTOCOL_START, .doit = nl80211_crit_protocol_start, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14055,7 +13969,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_CRIT_PROTOCOL_STOP, .doit = nl80211_crit_protocol_stop, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14063,14 +13976,12 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_COALESCE, .doit = nl80211_get_coalesce, - .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_COALESCE, .doit = nl80211_set_coalesce, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -14078,7 +13989,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_CHANNEL_SWITCH, .doit = nl80211_channel_switch, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14087,7 +13997,6 @@ static const struct genl_ops nl80211_ops[] = { .cmd = NL80211_CMD_VENDOR, .doit = nl80211_vendor_cmd, .dumpit = nl80211_vendor_cmd_dump, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, @@ -14095,7 +14004,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_QOS_MAP, .doit = nl80211_set_qos_map, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14103,7 +14011,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_ADD_TX_TS, .doit = nl80211_add_tx_ts, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14111,7 +14018,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_DEL_TX_TS, .doit = nl80211_del_tx_ts, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14119,7 +14025,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH, .doit = nl80211_tdls_channel_switch, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14127,7 +14032,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH, .doit = nl80211_tdls_cancel_channel_switch, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14135,7 +14039,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_MULTICAST_TO_UNICAST, .doit = nl80211_set_multicast_to_unicast, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, @@ -14143,21 +14046,18 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_SET_PMK, .doit = nl80211_set_pmk, - .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEL_PMK, .doit = nl80211_del_pmk, - .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_EXTERNAL_AUTH, .doit = nl80211_external_auth, - .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14165,7 +14065,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_CONTROL_PORT_FRAME, .doit = nl80211_tx_control_port, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14173,14 +14072,12 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_FTM_RESPONDER_STATS, .doit = nl80211_get_ftm_responder_stats, - .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_PEER_MEASUREMENT_START, .doit = nl80211_pmsr_start, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14188,7 +14085,6 @@ static const struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_NOTIFY_RADAR, .doit = nl80211_notify_radar_detection, - .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, @@ -14200,6 +14096,7 @@ static struct genl_family nl80211_fam __ro_after_init = { .hdrsize = 0, /* no private header */ .version = 1, /* no particular meaning now */ .maxattr = NL80211_ATTR_MAX, + .policy = nl80211_policy, .netnsok = true, .pre_doit = nl80211_pre_doit, .post_doit = nl80211_post_doit, -- cgit v1.2.3-71-gd317 From 0eb69bb9962973f4852bb35b8151332c98741770 Mon Sep 17 00:00:00 2001 From: Eli Britstein Date: Thu, 21 Mar 2019 15:51:40 -0700 Subject: net/mlx5e: Add VLAN ID rewrite fields Add VLAN ID rewrite fields as a pre-step to support this rewrite. Signed-off-by: Eli Britstein Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 ++ include/linux/mlx5/mlx5_ifc.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b4967a0ff8c7..1b446307f448 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1827,6 +1827,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct pedit_headers { struct ethhdr eth; + struct vlan_hdr vlan; struct iphdr ip4; struct ipv6hdr ip6; struct tcphdr tcp; @@ -1884,6 +1885,7 @@ static struct mlx5_fields fields[] = { OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0), OFFLOAD(SMAC_15_0, 2, eth.h_source[4], 0), OFFLOAD(ETHERTYPE, 2, eth.h_proto, 0), + OFFLOAD(FIRST_VID, 2, vlan.h_vlan_TCI, 0), OFFLOAD(IP_TTL, 1, ip4.ttl, 0), OFFLOAD(SIPV4, 4, ip4.saddr, 0), diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3b83288749c6..b0e17c94566c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5110,6 +5110,7 @@ enum { MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0 = 0x14, MLX5_ACTION_IN_FIELD_OUT_SIPV4 = 0x15, MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16, + MLX5_ACTION_IN_FIELD_OUT_FIRST_VID = 0x17, MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47, }; -- cgit v1.2.3-71-gd317 From dc05360fee660a9dbe59824b3f7896534210432b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Mar 2019 08:56:38 -0700 Subject: net: convert rps_needed and rfs_needed to new static branch api We prefer static_branch_unlikely() over static_key_false() these days. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/net/tun.c | 2 +- include/linux/netdevice.h | 4 ++-- include/net/sock.h | 2 +- net/core/dev.c | 10 +++++----- net/core/net-sysfs.c | 4 ++-- net/core/sysctl_net_core.c | 8 ++++---- 6 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 27798aacb671..24d0220b9ba0 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1042,7 +1042,7 @@ static int tun_net_close(struct net_device *dev) static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { #ifdef CONFIG_RPS - if (tun->numqueues == 1 && static_key_false(&rps_needed)) { + if (tun->numqueues == 1 && static_branch_unlikely(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 823762291ebf..166fdc0a78b4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -194,8 +194,8 @@ struct net_device_stats { #ifdef CONFIG_RPS #include -extern struct static_key rps_needed; -extern struct static_key rfs_needed; +extern struct static_key_false rps_needed; +extern struct static_key_false rfs_needed; #endif struct neighbour; diff --git a/include/net/sock.h b/include/net/sock.h index 8de5ee258b93..fecdf639225c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -966,7 +966,7 @@ static inline void sock_rps_record_flow_hash(__u32 hash) static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS - if (static_key_false(&rfs_needed)) { + if (static_branch_unlikely(&rfs_needed)) { /* Reading sk->sk_rxhash might incur an expensive cache line * miss. * diff --git a/net/core/dev.c b/net/core/dev.c index 676c9418f8e4..9ca2d3abfd1a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3982,9 +3982,9 @@ EXPORT_SYMBOL(rps_sock_flow_table); u32 rps_cpu_mask __read_mostly; EXPORT_SYMBOL(rps_cpu_mask); -struct static_key rps_needed __read_mostly; +struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); -struct static_key rfs_needed __read_mostly; +struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); static struct rps_dev_flow * @@ -4510,7 +4510,7 @@ static int netif_rx_internal(struct sk_buff *skb) } #ifdef CONFIG_RPS - if (static_key_false(&rps_needed)) { + if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; @@ -5179,7 +5179,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) rcu_read_lock(); #ifdef CONFIG_RPS - if (static_key_false(&rps_needed)) { + if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -5227,7 +5227,7 @@ static void netif_receive_skb_list_internal(struct list_head *head) rcu_read_lock(); #ifdef CONFIG_RPS - if (static_key_false(&rps_needed)) { + if (static_branch_unlikely(&rps_needed)) { list_for_each_entry_safe(skb, next, head, list) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4ff661f6f989..851cabb90bce 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -754,9 +754,9 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, rcu_assign_pointer(queue->rps_map, map); if (map) - static_key_slow_inc(&rps_needed); + static_branch_inc(&rps_needed); if (old_map) - static_key_slow_dec(&rps_needed); + static_branch_dec(&rps_needed); mutex_unlock(&rps_map_mutex); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 84bf2861f45f..1a2685694abd 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -95,12 +95,12 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, if (sock_table != orig_sock_table) { rcu_assign_pointer(rps_sock_flow_table, sock_table); if (sock_table) { - static_key_slow_inc(&rps_needed); - static_key_slow_inc(&rfs_needed); + static_branch_inc(&rps_needed); + static_branch_inc(&rfs_needed); } if (orig_sock_table) { - static_key_slow_dec(&rps_needed); - static_key_slow_dec(&rfs_needed); + static_branch_dec(&rps_needed); + static_branch_dec(&rfs_needed); synchronize_rcu(); vfree(orig_sock_table); } -- cgit v1.2.3-71-gd317 From df453700e8d81b1bdafdf684365ee2b9431fb702 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 27 Mar 2019 12:40:33 -0700 Subject: inet: switch IP ID generator to siphash According to Amit Klein and Benny Pinkas, IP ID generation is too weak and might be used by attackers. Even with recent net_hash_mix() fix (netns: provide pure entropy for net_hash_mix()) having 64bit key and Jenkins hash is risky. It is time to switch to siphash and its 128bit keys. Signed-off-by: Eric Dumazet Reported-by: Amit Klein Reported-by: Benny Pinkas Signed-off-by: David S. Miller --- include/linux/siphash.h | 5 +++++ include/net/netns/ipv4.h | 2 ++ net/ipv4/route.c | 12 +++++++----- net/ipv6/output_core.c | 30 ++++++++++++++++-------------- 4 files changed, 30 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/siphash.h b/include/linux/siphash.h index fa7a6b9cedbf..bf21591a9e5e 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -21,6 +21,11 @@ typedef struct { u64 key[2]; } siphash_key_t; +static inline bool siphash_key_is_zero(const siphash_key_t *key) +{ + return !(key->key[0] | key->key[1]); +} + u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 104a6669e344..7698460a3dd1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -9,6 +9,7 @@ #include #include #include +#include struct tcpm_hash_bucket; struct ctl_table_header; @@ -217,5 +218,6 @@ struct netns_ipv4 { unsigned int ipmr_seq; /* protected by rtnl_mutex */ atomic_t rt_genid; + siphash_key_t ip_id_key; }; #endif diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 14c7fdacaa72..f2688fce39e1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -500,15 +500,17 @@ EXPORT_SYMBOL(ip_idents_reserve); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { - static u32 ip_idents_hashrnd __read_mostly; u32 hash, id; - net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); + /* Note the following code is not safe, but this is okay. */ + if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) + get_random_bytes(&net->ipv4.ip_id_key, + sizeof(net->ipv4.ip_id_key)); - hash = jhash_3words((__force u32)iph->daddr, + hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, - iph->protocol ^ net_hash_mix(net), - ip_idents_hashrnd); + iph->protocol, + &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 4fe7c90962dd..868ae23dbae1 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -10,15 +10,25 @@ #include #include -static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, +static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { + const struct { + struct in6_addr dst; + struct in6_addr src; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .dst = *dst, + .src = *src, + }; u32 hash, id; - hash = __ipv6_addr_jhash(dst, hashrnd); - hash = __ipv6_addr_jhash(src, hash); - hash ^= net_hash_mix(net); + /* Note the following code is not safe, but this is okay. */ + if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) + get_random_bytes(&net->ipv4.ip_id_key, + sizeof(net->ipv4.ip_id_key)); + + hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key); /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, * set the hight order instead thus minimizing possible future @@ -41,7 +51,6 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, */ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { - static u32 ip6_proxy_idents_hashrnd __read_mostly; struct in6_addr buf[2]; struct in6_addr *addrs; u32 id; @@ -53,11 +62,7 @@ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) if (!addrs) return 0; - net_get_random_once(&ip6_proxy_idents_hashrnd, - sizeof(ip6_proxy_idents_hashrnd)); - - id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd, - &addrs[1], &addrs[0]); + id = __ipv6_select_ident(net, &addrs[1], &addrs[0]); return htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); @@ -66,12 +71,9 @@ __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) { - static u32 ip6_idents_hashrnd __read_mostly; u32 id; - net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); - - id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr); + id = __ipv6_select_ident(net, daddr, saddr); return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); -- cgit v1.2.3-71-gd317 From 5dc37bb9b03586e8fdeb47d25e8d2a0399984936 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 28 Mar 2019 13:56:36 +0100 Subject: net: replace ndo_get_devlink with ndo_get_devlink_port Follow-up patch is going to need a devlink port instance according to a netdev. Devlink port instance should be always available when devlink is used. So change the recently introduced ndo_get_devlink to ndo_get_devlink_port. With that, adjust the wrapper for the only user to get devlink pointer. Signed-off-by: Jiri Pirko Reviewed-by: Michal Kubecek Reviewed-by: Florian Fainelli Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_app.h | 2 +- drivers/net/ethernet/netronome/nfp/nfp_devlink.c | 10 +++++----- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 +- drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 +- include/linux/netdevice.h | 6 +++--- include/net/devlink.h | 14 ++++++++++++-- 6 files changed, 23 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index f8d422713705..a6fda07fce43 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -433,6 +433,6 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, int nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app, struct nfp_net *nn, unsigned int id); -struct devlink *nfp_devlink_get_devlink(struct net_device *netdev); +struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev); #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index cb59a18ec6a6..919da0d84fb4 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -386,13 +386,13 @@ void nfp_devlink_port_type_clear(struct nfp_port *port) devlink_port_type_clear(&port->dl_port); } -struct devlink *nfp_devlink_get_devlink(struct net_device *netdev) +struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev) { - struct nfp_app *app; + struct nfp_port *port; - app = nfp_app_from_netdev(netdev); - if (!app) + port = nfp_port_from_netdev(netdev); + if (!port) return NULL; - return priv_to_devlink(app->pf); + return &port->dl_port; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index ad2f133bd545..b676943e54f4 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3531,7 +3531,7 @@ const struct net_device_ops nfp_net_netdev_ops = { .ndo_udp_tunnel_del = nfp_net_del_vxlan_port, .ndo_bpf = nfp_net_xdp, .ndo_get_port_parent_id = nfp_port_get_port_parent_id, - .ndo_get_devlink = nfp_devlink_get_devlink, + .ndo_get_devlink_port = nfp_devlink_get_devlink_port, }; /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index d2c803bb4e56..bf621674f583 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -273,7 +273,7 @@ const struct net_device_ops nfp_repr_netdev_ops = { .ndo_set_features = nfp_port_set_features, .ndo_set_mac_address = eth_mac_addr, .ndo_get_port_parent_id = nfp_port_get_port_parent_id, - .ndo_get_devlink = nfp_devlink_get_devlink, + .ndo_get_devlink_port = nfp_devlink_get_devlink_port, }; void diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 166fdc0a78b4..78f5ec4ebf64 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1250,8 +1250,8 @@ struct devlink; * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. - * struct devlink *(*ndo_get_devlink)(struct net_device *dev); - * Get devlink instance associated with a given netdev. + * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev); + * Get devlink port instance associated with a given netdev. * Called with a reference on the netdevice and devlink locks only, * rtnl_lock is not held. */ @@ -1451,7 +1451,7 @@ struct net_device_ops { u32 flags); int (*ndo_xsk_async_xmit)(struct net_device *dev, u32 queue_id); - struct devlink * (*ndo_get_devlink)(struct net_device *dev); + struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); }; /** diff --git a/include/net/devlink.h b/include/net/devlink.h index 03fb16f4fb6c..81b5ed04a341 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -547,10 +547,20 @@ static inline struct devlink *priv_to_devlink(void *priv) return container_of(priv, struct devlink, priv); } +static inline struct devlink_port * +netdev_to_devlink_port(struct net_device *dev) +{ + if (dev->netdev_ops->ndo_get_devlink_port) + return dev->netdev_ops->ndo_get_devlink_port(dev); + return NULL; +} + static inline struct devlink *netdev_to_devlink(struct net_device *dev) { - if (dev->netdev_ops->ndo_get_devlink) - return dev->netdev_ops->ndo_get_devlink(dev); + struct devlink_port *devlink_port = netdev_to_devlink_port(dev); + + if (devlink_port) + return devlink_port->devlink; return NULL; } -- cgit v1.2.3-71-gd317 From 331c7a402358de6206232f6aab7aa48ec6c1088a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 27 Mar 2019 20:53:47 -0700 Subject: ipv4: Move IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN to helper in_dev lookup followed by IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN check is called in several places, some with the rcu lock and others with the rtnl held. Move the check to a helper similar to what IPv6 has. Since the helper can be invoked from either context use rcu_dereference_rtnl to dereference ip_ptr. Signed-off-by: David Ahern Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 14 ++++++++++++++ net/ipv4/fib_semantics.c | 31 +++++++------------------------ net/ipv4/fib_trie.c | 4 +--- 3 files changed, 22 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a64f21a97369..367dc2a0f84a 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -237,6 +237,20 @@ static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) return rtnl_dereference(dev->ip_ptr); } +/* called with rcu_read_lock or rtnl held */ +static inline bool ip_ignore_linkdown(const struct net_device *dev) +{ + struct in_device *in_dev; + bool rc = false; + + in_dev = rcu_dereference_rtnl(dev->ip_ptr); + if (in_dev && + IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) + rc = true; + + return rc; +} + static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b5dbbdfd1e49..78631eb255f7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -558,7 +558,6 @@ static void fib_rebalance(struct fib_info *fi) { int total; int w; - struct in_device *in_dev; if (fi->fib_nhs < 2) return; @@ -568,10 +567,7 @@ static void fib_rebalance(struct fib_info *fi) if (nh->nh_flags & RTNH_F_DEAD) continue; - in_dev = __in_dev_get_rtnl(nh->nh_dev); - - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + if (ip_ignore_linkdown(nh->nh_dev) && nh->nh_flags & RTNH_F_LINKDOWN) continue; @@ -582,12 +578,9 @@ static void fib_rebalance(struct fib_info *fi) change_nexthops(fi) { int upper_bound; - in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev); - if (nexthop_nh->nh_flags & RTNH_F_DEAD) { upper_bound = -1; - } else if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + } else if (ip_ignore_linkdown(nexthop_nh->nh_dev) && nexthop_nh->nh_flags & RTNH_F_LINKDOWN) { upper_bound = -1; } else { @@ -1325,12 +1318,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif)) goto nla_put_failure; if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) { - struct in_device *in_dev; - rcu_read_lock(); - in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev); - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) + if (ip_ignore_linkdown(fi->fib_nh->nh_dev)) rtm->rtm_flags |= RTNH_F_DEAD; rcu_read_unlock(); } @@ -1361,12 +1350,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, rtnh->rtnh_flags = nh->nh_flags & 0xFF; if (nh->nh_flags & RTNH_F_LINKDOWN) { - struct in_device *in_dev; - rcu_read_lock(); - in_dev = __in_dev_get_rcu(nh->nh_dev); - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) + if (ip_ignore_linkdown(nh->nh_dev)) rtnh->rtnh_flags |= RTNH_F_DEAD; rcu_read_unlock(); } @@ -1433,7 +1418,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) static int call_fib_nh_notifiers(struct fib_nh *fib_nh, enum fib_event_type event_type) { - struct in_device *in_dev = __in_dev_get_rtnl(fib_nh->nh_dev); + bool ignore_link_down = ip_ignore_linkdown(fib_nh->nh_dev); struct fib_nh_notifier_info info = { .fib_nh = fib_nh, }; @@ -1442,14 +1427,12 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh, case FIB_EVENT_NH_ADD: if (fib_nh->nh_flags & RTNH_F_DEAD) break; - if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - fib_nh->nh_flags & RTNH_F_LINKDOWN) + if (ignore_link_down && fib_nh->nh_flags & RTNH_F_LINKDOWN) break; return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type, &info.info); case FIB_EVENT_NH_DEL: - if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - fib_nh->nh_flags & RTNH_F_LINKDOWN) || + if ((ignore_link_down && fib_nh->nh_flags & RTNH_F_LINKDOWN) || (fib_nh->nh_flags & RTNH_F_DEAD)) return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type, &info.info); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1704f432de1f..656d3d19f112 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1471,12 +1471,10 @@ found: continue; for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { const struct fib_nh *nh = &fi->fib_nh[nhsel]; - struct in_device *in_dev = __in_dev_get_rcu(nh->nh_dev); if (nh->nh_flags & RTNH_F_DEAD) continue; - if (in_dev && - IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + if (ip_ignore_linkdown(nh->nh_dev) && nh->nh_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; -- cgit v1.2.3-71-gd317 From 97cdcf37b57e3f204be3000b9eab9686f38b4356 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 1 Apr 2019 16:42:13 +0200 Subject: net: place xmit recursion in softnet data This fills a hole in softnet data, so no change in structure size. Also prepares for xmit_more placement in the same spot; skb->xmit_more will be removed in followup patch. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 40 ++++++++++++++++++++++++++++++++-------- net/core/dev.c | 10 +++------- net/core/filter.c | 6 +++--- 3 files changed, 38 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 78f5ec4ebf64..2b25824642fa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2659,14 +2659,6 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); -DECLARE_PER_CPU(int, xmit_recursion); -#define XMIT_RECURSION_LIMIT 10 - -static inline int dev_recursion_level(void) -{ - return this_cpu_read(xmit_recursion); -} - struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); @@ -3015,6 +3007,11 @@ struct softnet_data { #ifdef CONFIG_XFRM_OFFLOAD struct sk_buff_head xfrm_backlog; #endif + /* written and read only by owning cpu: */ + struct { + u16 recursion; + u8 more; + } xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. @@ -3050,6 +3047,28 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd, DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +static inline int dev_recursion_level(void) +{ + return __this_cpu_read(softnet_data.xmit.recursion); +} + +#define XMIT_RECURSION_LIMIT 10 +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} + void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -4409,6 +4428,11 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, return ops->ndo_start_xmit(skb, dev); } +static inline bool netdev_xmit_more(void) +{ + return __this_cpu_read(softnet_data.xmit.more); +} + static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { diff --git a/net/core/dev.c b/net/core/dev.c index 9823b7713f79..d5b1315218d3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3566,9 +3566,6 @@ static void skb_update_prio(struct sk_buff *skb) #define skb_update_prio(skb) #endif -DEFINE_PER_CPU(int, xmit_recursion); -EXPORT_SYMBOL(xmit_recursion); - /** * dev_loopback_xmit - loop back @skb * @net: network namespace this loopback is happening in @@ -3857,8 +3854,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) int cpu = smp_processor_id(); /* ok because BHs are off */ if (txq->xmit_lock_owner != cpu) { - if (unlikely(__this_cpu_read(xmit_recursion) > - XMIT_RECURSION_LIMIT)) + if (dev_xmit_recursion()) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); @@ -3868,9 +3864,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { - __this_cpu_inc(xmit_recursion); + dev_xmit_recursion_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); - __this_cpu_dec(xmit_recursion); + dev_xmit_recursion_dec(); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; diff --git a/net/core/filter.c b/net/core/filter.c index 4a8455757507..cdaafa3322db 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2016,7 +2016,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; - if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) { + if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); kfree_skb(skb); return -ENETDOWN; @@ -2024,9 +2024,9 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) skb->dev = dev; - __this_cpu_inc(xmit_recursion); + dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); - __this_cpu_dec(xmit_recursion); + dev_xmit_recursion_dec(); return ret; } -- cgit v1.2.3-71-gd317 From 6b16f9ee89b8d5709f24bc3ac89ae8b5452c0d7c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 1 Apr 2019 16:42:14 +0200 Subject: net: move skb->xmit_more hint to softnet data There are two reasons for this. First, the xmit_more flag conceptually doesn't fit into the skb, as xmit_more is not a property related to the skb. Its only a hint to the driver that the stack is about to transmit another packet immediately. Second, it was only done this way to not have to pass another argument to ndo_start_xmit(). We can place xmit_more in the softnet data, next to the device recursion. The recursion counter is already written to on each transmit. The "more" indicator is placed right next to it. Drivers can use the netdev_xmit_more() helper instead of skb->xmit_more to check the "more packets coming" hint. skb->xmit_more is retained (but always 0) to not cause build breakage. This change takes care of the simple s/skb->xmit_more/netdev_xmit_more()/ conversions. Remaining drivers are converted in the next patches. Suggested-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +- drivers/net/ethernet/broadcom/tg3.c | 2 +- drivers/net/ethernet/cavium/liquidio/lio_main.c | 2 +- drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 2 +- drivers/net/ethernet/cisco/enic/enic_main.c | 2 +- drivers/net/ethernet/emulex/benet/be_main.c | 2 +- drivers/net/ethernet/huawei/hinic/hinic_tx.c | 2 +- drivers/net/ethernet/intel/e1000/e1000_main.c | 2 +- drivers/net/ethernet/intel/e1000e/netdev.c | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 3 ++- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 +- drivers/net/ethernet/qlogic/qede/qede_fp.c | 4 ++-- drivers/net/ethernet/rdc/r6040.c | 2 +- drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c | 2 +- drivers/net/hyperv/netvsc.c | 2 +- drivers/net/virtio_net.c | 2 +- drivers/staging/mt7621-eth/mtk_eth_soc.c | 6 ++++-- include/linux/netdevice.h | 2 +- 29 files changed, 35 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 71c8cac6e44e..7e40d14682f7 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2236,7 +2236,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) } } - if (netif_xmit_stopped(txq) || !skb->xmit_more) { + if (netif_xmit_stopped(txq) || !netdev_xmit_more()) { /* trigger the dma engine. ena_com_write_sq_doorbell() * has a mb */ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 4666084eda16..d5fd49dd25f3 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1887,7 +1887,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) smp_wmb(); ring->cur = cur_index + 1; - if (!packet->skb->xmit_more || + if (!netdev_xmit_more() || netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev, channel->queue_index))) xgbe_tx_start_xmit(channel, ring); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 35e34e23ba33..d22691403d28 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -551,7 +551,7 @@ normal_tx: prod = NEXT_TX(prod); txr->tx_prod = prod; - if (!skb->xmit_more || netif_xmit_stopped(txq)) + if (!netdev_xmit_more() || netif_xmit_stopped(txq)) bnxt_db_write(bp, &txr->tx_db, prod); tx_done: @@ -559,7 +559,7 @@ tx_done: mmiowb(); if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) { - if (skb->xmit_more && !tx_buf->is_push) + if (netdev_xmit_more() && !tx_buf->is_push) bnxt_db_write(bp, &txr->tx_db, prod); netif_tx_stop_queue(txq); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 983245c0867c..4fd973571e4c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1665,7 +1665,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) if (ring->free_bds <= (MAX_SKB_FRAGS + 1)) netif_tx_stop_queue(txq); - if (!skb->xmit_more || netif_xmit_stopped(txq)) + if (!netdev_xmit_more() || netif_xmit_stopped(txq)) /* Packets are ready, update producer index */ bcmgenet_tdma_ring_writel(priv, ring->index, ring->prod_index, TDMA_PROD_INDEX); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 328373e0578f..45ccadee02af 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -8156,7 +8156,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_wake_queue(txq); } - if (!skb->xmit_more || netif_xmit_stopped(txq)) { + if (!netdev_xmit_more() || netif_xmit_stopped(txq)) { /* Packets are ready, update Tx producer idx on card. */ tw32_tx_mbox(tnapi->prodmbox, entry); mmiowb(); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index fb6f813cff65..eab805579f96 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2522,7 +2522,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) irh->vlan = skb_vlan_tag_get(skb) & 0xfff; } - xmit_more = skb->xmit_more; + xmit_more = netdev_xmit_more(); if (unlikely(cmdsetup.s.timestamp)) status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 54b245797d2e..db0b90555acb 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -1585,7 +1585,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) irh->vlan = skb_vlan_tag_get(skb) & VLAN_VID_MASK; } - xmit_more = skb->xmit_more; + xmit_more = netdev_xmit_more(); if (unlikely(cmdsetup.s.timestamp)) status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 733d9172425b..acb2856936d2 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -897,7 +897,7 @@ static netdev_tx_t enic_hard_start_xmit(struct sk_buff *skb, if (vnic_wq_desc_avail(wq) < MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS) netif_tx_stop_queue(txq); skb_tx_timestamp(skb); - if (!skb->xmit_more || netif_xmit_stopped(txq)) + if (!netdev_xmit_more() || netif_xmit_stopped(txq)) vnic_wq_doorbell(wq); spin_unlock(&enic->wq_lock[txq_map]); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 3c7c04406a2b..e2f9fbced174 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1376,7 +1376,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) u16 q_idx = skb_get_queue_mapping(skb); struct be_tx_obj *txo = &adapter->tx_obj[q_idx]; struct be_wrb_params wrb_params = { 0 }; - bool flush = !skb->xmit_more; + bool flush = !netdev_xmit_more(); u16 wrb_cnt; skb = be_xmit_workarounds(adapter, skb, &wrb_params); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index e17bf33eba0c..0fbe8046824b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -518,7 +518,7 @@ process_sq_wqe: flush_skbs: netdev_txq = netdev_get_tx_queue(netdev, q_id); - if ((!skb->xmit_more) || (netif_xmit_stopped(netdev_txq))) + if ((!netdev_xmit_more()) || (netif_xmit_stopped(netdev_txq))) hinic_sq_write_db(txq->sq, prod_idx, wqe_size, 0); return err; diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index a7c76732849f..6f72ab139fd9 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -3267,7 +3267,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, /* Make sure there is space in the ring for the next send. */ e1000_maybe_stop_tx(netdev, tx_ring, desc_needed); - if (!skb->xmit_more || + if (!netdev_xmit_more() || netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt); /* we need this if more than one processor can write to diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 745c1242a2d9..a8fa4a1628f5 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5897,7 +5897,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, DIV_ROUND_UP(PAGE_SIZE, adapter->tx_fifo_limit) + 2)); - if (!skb->xmit_more || + if (!netdev_xmit_more() || netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) e1000e_update_tdt_wa(tx_ring, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5a0419421511..e2fa112bed9a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1035,7 +1035,7 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring, fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED); /* notify HW of packet */ - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 6c97667d20ef..1a95223c9f99 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3469,7 +3469,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, first->next_to_watch = tx_desc; /* notify HW of packet */ - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 9b4d7cec2e18..b64187753ad6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -2358,7 +2358,7 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, first->next_to_watch = tx_desc; /* notify HW of packet */ - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index f2462799154a..a6f7b7feaf3c 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1646,7 +1646,7 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, ice_maybe_stop_tx(tx_ring, DESC_NEEDED); /* notify HW of packet */ - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index bea7175d171b..32d61d5a2706 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6029,7 +6029,7 @@ static int igb_tx_map(struct igb_ring *tx_ring, /* Make sure there is space in the ring for the next send. */ igb_maybe_stop_tx(tx_ring, DESC_NEEDED); - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index a883b3f357e7..f79728381e8a 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -939,7 +939,7 @@ static int igc_tx_map(struct igc_ring *tx_ring, /* Make sure there is space in the ring for the next send. */ igc_maybe_stop_tx(tx_ring, DESC_NEEDED); - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 16c728984164..60cec3540dd7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8297,7 +8297,7 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED); - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index a944be3c57b1..bb68737dce56 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2467,7 +2467,7 @@ out: if (txq->count >= txq->tx_stop_threshold) netif_tx_stop_queue(nq); - if (!skb->xmit_more || netif_xmit_stopped(nq) || + if (!netdev_xmit_more() || netif_xmit_stopped(nq) || txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK) mvneta_txq_pend_desc_add(pp, txq, frags); else diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 549d36497b8c..53abe925ecb1 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -767,7 +767,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, */ wmb(); - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more) + if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || + !netdev_xmit_more()) mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 99200b5dac76..961cd5e7bf2b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -909,7 +909,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) nfp_net_tx_ring_stop(nd_q, tx_ring); tx_ring->wr_ptr_add += nr_frags + 1; - if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, skb->xmit_more)) + if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, netdev_xmit_more())) nfp_net_tx_xmit_more_flush(tx_ring); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index c342b07e3a93..954015d2011a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1665,12 +1665,12 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) txq->tx_db.data.bd_prod = cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl)); - if (!skb->xmit_more || netif_xmit_stopped(netdev_txq)) + if (!netdev_xmit_more() || netif_xmit_stopped(netdev_txq)) qede_update_tx_producer(txq); if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl) < (MAX_SKB_FRAGS + 1))) { - if (skb->xmit_more) + if (netdev_xmit_more()) qede_update_tx_producer(txq); netif_tx_stop_queue(netdev_txq); diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 04aa592f35c3..ad335bca3273 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -840,7 +840,7 @@ static netdev_tx_t r6040_start_xmit(struct sk_buff *skb, skb_tx_timestamp(skb); /* Trigger the MAC to check the TX descriptor */ - if (!skb->xmit_more || netif_queue_stopped(dev)) + if (!netdev_xmit_more() || netif_queue_stopped(dev)) iowrite16(TM2TX, ioaddr + MTPR); lp->tx_insert_ptr = descptr->vndescp; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c index 99d86e39ff54..bf6c1c6779ff 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c @@ -995,7 +995,7 @@ static void xlgmac_dev_xmit(struct xlgmac_channel *channel) smp_wmb(); ring->cur = cur_index + 1; - if (!pkt_info->skb->xmit_more || + if (!netdev_xmit_more() || netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev, channel->queue_index))) xlgmac_tx_start_xmit(channel, ring); diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 813d195bbd57..9a022539d305 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -964,7 +964,7 @@ int netvsc_send(struct net_device *ndev, /* Keep aggregating only if stack says more data is coming * and not doing mixed modes send and not flow blocked */ - xmit_more = skb->xmit_more && + xmit_more = netdev_xmit_more() && !packet->cp_partial && !netif_xmit_stopped(netdev_get_tx_queue(ndev, packet->q_idx)); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1b03c4b6ebff..ba246fc475ae 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1568,7 +1568,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) struct send_queue *sq = &vi->sq[qnum]; int err; struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); - bool kick = !skb->xmit_more; + bool kick = !netdev_xmit_more(); bool use_napi = sq->napi.weight; /* Free up any pending old buffers before queueing new ones. */ diff --git a/drivers/staging/mt7621-eth/mtk_eth_soc.c b/drivers/staging/mt7621-eth/mtk_eth_soc.c index 6027b19f7bc2..02a8584b3d1d 100644 --- a/drivers/staging/mt7621-eth/mtk_eth_soc.c +++ b/drivers/staging/mt7621-eth/mtk_eth_soc.c @@ -741,7 +741,8 @@ static int mtk_pdma_tx_map(struct sk_buff *skb, struct net_device *dev, wmb(); atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring)); - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more) + if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || + !netdev_xmit_more()) mtk_reg_w32(eth, ring->tx_next_idx, MTK_REG_TX_CTX_IDX0); return 0; @@ -935,7 +936,8 @@ static int mtk_qdma_tx_map(struct sk_buff *skb, struct net_device *dev, */ wmb(); - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more) + if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || + !netdev_xmit_more()) mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); return 0; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2b25824642fa..eb9f05e0863d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4424,7 +4424,7 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) { - skb->xmit_more = more ? 1 : 0; + __this_cpu_write(softnet_data.xmit.more, more); return ops->ndo_start_xmit(skb, dev); } -- cgit v1.2.3-71-gd317 From 4f296edeb9d4cf76b876869461a7ae627c307110 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 1 Apr 2019 16:42:17 +0200 Subject: drivers: net: aurora: use netdev_xmit_more helper This is the last driver using always-0 skb->xmit_more. Switch it to netdev_xmit_more and remove the now unused xmit_more flag from sk_buff. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- drivers/net/ethernet/aurora/nb8800.c | 8 +++++--- include/linux/skbuff.h | 2 -- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 6f56276015a4..f62deeb6e941 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -404,6 +404,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int dma_len; unsigned int align; unsigned int next; + bool xmit_more; if (atomic_read(&priv->tx_free) <= NB8800_DESC_LOW) { netif_stop_queue(dev); @@ -423,9 +424,10 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + xmit_more = netdev_xmit_more(); if (atomic_dec_return(&priv->tx_free) <= NB8800_DESC_LOW) { netif_stop_queue(dev); - skb->xmit_more = 0; + xmit_more = false; } next = priv->tx_next; @@ -450,7 +452,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev) desc->n_addr = priv->tx_bufs[next].dma_desc; desc->config = DESC_BTS(2) | DESC_DS | DESC_EOF | dma_len; - if (!skb->xmit_more) + if (!xmit_more) desc->config |= DESC_EOC; txb->skb = skb; @@ -468,7 +470,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev) priv->tx_next = next; - if (!skb->xmit_more) { + if (!xmit_more) { smp_wmb(); priv->tx_chain->ready = true; priv->tx_chain = NULL; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9027a8c4219f..69b5538adcea 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -657,7 +657,6 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices - * @xmit_more: More SKBs are pending for this queue * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) @@ -764,7 +763,6 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - xmit_more:1, pfmemalloc:1; #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; -- cgit v1.2.3-71-gd317 From 38702cce547a74493687fd8bb925fbb5c3898ce3 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Fri, 29 Mar 2019 15:37:51 -0700 Subject: net/mlx5: Remove unused MLX5_*_DOORBELL_LOCK macros MLX5_*_DOORBELL_LOCK macros provided a way to avoid locking for mlx5_write64 on 64-bit platforms where it's not necessary. Currently all calls to mlx5_write64 don't use a spinlock, so the macros became unused. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/doorbell.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h index 0787de28f2fc..9ef3f9d00154 100644 --- a/include/linux/mlx5/doorbell.h +++ b/include/linux/mlx5/doorbell.h @@ -42,10 +42,6 @@ * PCI so we won't worry about it. */ -#define MLX5_DECLARE_DOORBELL_LOCK(name) -#define MLX5_INIT_DOORBELL_LOCK(ptr) do { } while (0) -#define MLX5_GET_DOORBELL_LOCK(ptr) (NULL) - static inline void mlx5_write64(__be32 val[2], void __iomem *dest, spinlock_t *doorbell_lock) { @@ -59,10 +55,6 @@ static inline void mlx5_write64(__be32 val[2], void __iomem *dest, * MMIO writes. */ -#define MLX5_DECLARE_DOORBELL_LOCK(name) spinlock_t name; -#define MLX5_INIT_DOORBELL_LOCK(ptr) spin_lock_init(ptr) -#define MLX5_GET_DOORBELL_LOCK(ptr) (ptr) - static inline void mlx5_write64(__be32 val[2], void __iomem *dest, spinlock_t *doorbell_lock) { -- cgit v1.2.3-71-gd317 From bbf29f618e8c5bfd6efdad5fdc050a84bab795ab Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Fri, 29 Mar 2019 15:37:52 -0700 Subject: net/mlx5: Remove spinlock support from mlx5_write64 As there is no user of mlx5_write64 that passes a spinlock to mlx5_write64, remove this functionality and simplify the function. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/qp.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- .../net/ethernet/mellanox/mlx5/core/fpga/conn.c | 2 +- include/linux/mlx5/cq.h | 2 +- include/linux/mlx5/doorbell.h | 31 +++++++--------------- 5 files changed, 13 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index dd2ae640bc84..816c34ee91cf 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -5015,7 +5015,7 @@ out: wmb(); /* currently we support only regular doorbells */ - mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset, NULL); + mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset); /* Make sure doorbells don't leak out of SQ spinlock * and reach the HCA out of order. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8fa8fdd30b85..2623d3fb6b96 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -916,7 +916,7 @@ void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, */ wmb(); - mlx5_write64((__be32 *)ctrl, uar_map, NULL); + mlx5_write64((__be32 *)ctrl, uar_map); } static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 873541ef4c1b..ca2296a2f9ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -135,7 +135,7 @@ static void mlx5_fpga_conn_notify_hw(struct mlx5_fpga_conn *conn, void *wqe) *conn->qp.wq.sq.db = cpu_to_be32(conn->qp.sq.pc); /* Make sure that doorbell record is visible before ringing */ wmb(); - mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET, NULL); + mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET); } static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn, diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 612c8c2f2466..769326ea1d9b 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -170,7 +170,7 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd, doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci); doorbell[1] = cpu_to_be32(cq->cqn); - mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL); + mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL); } static inline void mlx5_cq_hold(struct mlx5_core_cq *cq) diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h index 9ef3f9d00154..5c267707e1df 100644 --- a/include/linux/mlx5/doorbell.h +++ b/include/linux/mlx5/doorbell.h @@ -36,38 +36,25 @@ #define MLX5_BF_OFFSET 0x800 #define MLX5_CQ_DOORBELL 0x20 -#if BITS_PER_LONG == 64 /* Assume that we can just write a 64-bit doorbell atomically. s390 * actually doesn't have writeq() but S/390 systems don't even have * PCI so we won't worry about it. + * + * Note that the write is not atomic on 32-bit systems! In contrast to 64-bit + * ones, it requires proper locking. mlx5_write64 doesn't do any locking, so use + * it at your own discretion, protected by some kind of lock on 32 bits. + * + * TODO: use write{q,l}_relaxed() */ -static inline void mlx5_write64(__be32 val[2], void __iomem *dest, - spinlock_t *doorbell_lock) +static inline void mlx5_write64(__be32 val[2], void __iomem *dest) { +#if BITS_PER_LONG == 64 __raw_writeq(*(u64 *)val, dest); -} - #else - -/* Just fall back to a spinlock to protect the doorbell if - * BITS_PER_LONG is 32 -- there's no portable way to do atomic 64-bit - * MMIO writes. - */ - -static inline void mlx5_write64(__be32 val[2], void __iomem *dest, - spinlock_t *doorbell_lock) -{ - unsigned long flags; - - if (doorbell_lock) - spin_lock_irqsave(doorbell_lock, flags); __raw_writel((__force u32) val[0], dest); __raw_writel((__force u32) val[1], dest + 4); - if (doorbell_lock) - spin_unlock_irqrestore(doorbell_lock, flags); -} - #endif +} #endif /* MLX5_DOORBELL_H */ -- cgit v1.2.3-71-gd317 From 52c368dc3da7beb7b283133024af1b6d07bf93b9 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 29 Mar 2019 15:37:55 -0700 Subject: net/mlx5: Move health and page alloc init to mdev_init Software structure initialization should be in mdev_init stage. This provides a better logical separation of mlx5 core device initialization flow and will help to seamlessly support creating different mlx5 device types such as PF, VF and SF mlx5 sub-function virtual device. This patch does not change any functionality. Signed-off-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 7 +++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 37 +++++++++++++----------- include/linux/mlx5/driver.h | 1 + 3 files changed, 28 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 196c07383082..1ab694bc22c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -352,6 +352,13 @@ void mlx5_drain_health_recovery(struct mlx5_core_dev *dev) cancel_delayed_work_sync(&dev->priv.health.recover_work); } +void mlx5_health_flush(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + + flush_workqueue(health->wq); +} + void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e26246eacea5..4bdcbfcc5476 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1220,6 +1220,7 @@ static const struct devlink_ops mlx5_devlink_ops = { static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char *name) { struct mlx5_priv *priv = &dev->priv; + int err; strncpy(priv->name, name, MLX5_MAX_NAME_LEN); priv->name[MLX5_MAX_NAME_LEN - 1] = 0; @@ -1247,11 +1248,28 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char return -ENOMEM; } + err = mlx5_health_init(dev); + if (err) + goto err_health_init; + + err = mlx5_pagealloc_init(dev); + if (err) + goto err_pagealloc_init; + return 0; + +err_pagealloc_init: + mlx5_health_cleanup(dev); +err_health_init: + debugfs_remove(dev->priv.dbg_root); + + return err; } static void mlx5_mdev_uninit(struct mlx5_core_dev *dev) { + mlx5_pagealloc_cleanup(dev); + mlx5_health_cleanup(dev); debugfs_remove_recursive(dev->priv.dbg_root); } @@ -1280,16 +1298,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto pci_init_err; } - err = mlx5_health_init(dev); - if (err) { - dev_err(&pdev->dev, "mlx5_health_init failed with error code %d\n", err); - goto close_pci; - } - - err = mlx5_pagealloc_init(dev); - if (err) - goto err_pagealloc_init; - err = mlx5_load_one(dev, true); if (err) { dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err); @@ -1307,11 +1315,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) clean_load: mlx5_unload_one(dev, true); + err_load_one: - mlx5_pagealloc_cleanup(dev); -err_pagealloc_init: - mlx5_health_cleanup(dev); -close_pci: mlx5_pci_close(dev); pci_init_err: mlx5_mdev_uninit(dev); @@ -1331,12 +1336,10 @@ static void remove_one(struct pci_dev *pdev) if (mlx5_unload_one(dev, true)) { dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n"); - mlx5_health_cleanup(dev); + mlx5_health_flush(dev); return; } - mlx5_pagealloc_cleanup(dev); - mlx5_health_cleanup(dev); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); devlink_free(devlink); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c5454f985e1d..d7f5c0e8c47a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -883,6 +883,7 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); +void mlx5_health_flush(struct mlx5_core_dev *dev); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -- cgit v1.2.3-71-gd317 From aa8106f137b93628d531ef5ecbbcbecef99370d7 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 29 Mar 2019 15:38:01 -0700 Subject: net/mlx5: Add explicit bar address field Add bar_addr field to store bar-0 address to avoid calling pci_resource_start with hard-coded bar-0 as parameter. Also note that different mlx5 device types will have bar_addr on different bars. This patch does not change any functionality. Signed-off-by: Huy Nguyen Signed-off-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/cmd.c | 4 ++-- drivers/infiniband/hw/mlx5/main.c | 8 ++++---- drivers/infiniband/hw/mlx5/mr.c | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/uar.c | 2 +- include/linux/mlx5/driver.h | 1 + 6 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index 6bcc63aaa50b..be95ac5aeb30 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -148,7 +148,7 @@ int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr, return ret; } - *addr = pci_resource_start(dev->pdev, 0) + + *addr = dev->bar_addr + MLX5_GET64(alloc_memic_out, out, memic_start_addr); return 0; @@ -167,7 +167,7 @@ int mlx5_cmd_dealloc_memic(struct mlx5_memic *memic, u64 addr, u64 length) u64 start_page_idx; int err; - addr -= pci_resource_start(dev->pdev, 0); + addr -= dev->bar_addr; start_page_idx = (addr - hw_start_addr) >> PAGE_SHIFT; MLX5_SET(dealloc_memic_in, in, opcode, MLX5_CMD_OP_DEALLOC_MEMIC); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 581ae11e2fc9..a5333db0a4c7 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1984,7 +1984,7 @@ static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev, fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ? MLX5_UARS_IN_PAGE : 1; - return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) + uar_idx / fw_uars_per_page; + return (dev->mdev->bar_addr >> PAGE_SHIFT) + uar_idx / fw_uars_per_page; } static int get_command(unsigned long offset) @@ -2174,7 +2174,7 @@ static int dm_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) page_idx + npages) return -EINVAL; - pfn = ((pci_resource_start(dev->mdev->pdev, 0) + + pfn = ((dev->mdev->bar_addr + MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >> PAGE_SHIFT) + page_idx; @@ -2258,7 +2258,7 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev, goto err_free; start_offset = memic_addr & ~PAGE_MASK; - page_idx = (memic_addr - pci_resource_start(memic->dev->pdev, 0) - + page_idx = (memic_addr - memic->dev->bar_addr - MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >> PAGE_SHIFT; @@ -2301,7 +2301,7 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm) if (ret) return ret; - page_idx = (dm->dev_addr - pci_resource_start(memic->dev->pdev, 0) - + page_idx = (dm->dev_addr - memic->dev->bar_addr - MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >> PAGE_SHIFT; bitmap_clear(to_mucontext(ibdm->uobject->context)->dm_pages, diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index bf2b6ea23851..2b90d8dc70cd 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1232,8 +1232,7 @@ static struct ib_mr *mlx5_ib_get_memic_mr(struct ib_pd *pd, u64 memic_addr, MLX5_SET64(mkc, mkc, len, length); MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn); MLX5_SET(mkc, mkc, qpn, 0xffffff); - MLX5_SET64(mkc, mkc, start_addr, - memic_addr - pci_resource_start(dev->mdev->pdev, 0)); + MLX5_SET64(mkc, mkc, start_addr, memic_addr - dev->mdev->bar_addr); err = mlx5_core_create_mkey(mdev, &mr->mmkey, in, inlen); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8bedbe497f02..bda9c4bd17e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -739,6 +739,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, pci_set_drvdata(dev->pdev, dev); + dev->bar_addr = pci_resource_start(pdev, 0); priv->numa_node = dev_to_node(&dev->pdev->dev); err = mlx5_pci_enable_device(dev); @@ -766,7 +767,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128)) mlx5_core_dbg(dev, "Enabling pci atomics failed\n"); - dev->iseg_base = pci_resource_start(dev->pdev, 0); + dev->iseg_base = dev->bar_addr; dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg)); if (!dev->iseg) { err = -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 8b97066dd1f1..b7d52709b8b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -79,7 +79,7 @@ static u64 uar2pfn(struct mlx5_core_dev *mdev, u32 index) else system_page_index = index; - return (pci_resource_start(mdev->pdev, 0) >> PAGE_SHIFT) + system_page_index; + return (mdev->bar_addr >> PAGE_SHIFT) + system_page_index; } static void up_rel_func(struct kref *kref) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d7f5c0e8c47a..c0ee597f5457 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -658,6 +658,7 @@ struct mlx5_core_dev { u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; + phys_addr_t bar_addr; enum mlx5_device_state state; /* sync interface state */ struct mutex intf_state_mutex; -- cgit v1.2.3-71-gd317 From 4039049b5c462d3bb9ee8a68c4375582f037d5f2 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Fri, 29 Mar 2019 15:38:03 -0700 Subject: net/mlx5: Expose MPEIN (Management PCIE INfo) register layout Expose PRM layout for handling MPEIN (Management PCIE Info). It will be used in the downstream patch for querying MPEIN via the driver. Signed-off-by: Aya Levin Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 51 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 51 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c0ee597f5457..0bfb95e30e47 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -133,6 +133,7 @@ enum { MLX5_REG_MTRC_CONF = 0x9041, MLX5_REG_MTRC_STDB = 0x9042, MLX5_REG_MTRC_CTRL = 0x9043, + MLX5_REG_MPEIN = 0x9050, MLX5_REG_MPCNT = 0x9051, MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5decffe565fb..d31712af5a7b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8025,6 +8025,52 @@ struct mlx5_ifc_ppcnt_reg_bits { union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; +struct mlx5_ifc_mpein_reg_bits { + u8 reserved_at_0[0x2]; + u8 depth[0x6]; + u8 pcie_index[0x8]; + u8 node[0x8]; + u8 reserved_at_18[0x8]; + + u8 capability_mask[0x20]; + + u8 reserved_at_40[0x8]; + u8 link_width_enabled[0x8]; + u8 link_speed_enabled[0x10]; + + u8 lane0_physical_position[0x8]; + u8 link_width_active[0x8]; + u8 link_speed_active[0x10]; + + u8 num_of_pfs[0x10]; + u8 num_of_vfs[0x10]; + + u8 bdf0[0x10]; + u8 reserved_at_b0[0x10]; + + u8 max_read_request_size[0x4]; + u8 max_payload_size[0x4]; + u8 reserved_at_c8[0x5]; + u8 pwr_status[0x3]; + u8 port_type[0x4]; + u8 reserved_at_d4[0xb]; + u8 lane_reversal[0x1]; + + u8 reserved_at_e0[0x14]; + u8 pci_power[0xc]; + + u8 reserved_at_100[0x20]; + + u8 device_status[0x10]; + u8 port_state[0x8]; + u8 reserved_at_138[0x8]; + + u8 reserved_at_140[0x10]; + u8 receiver_detect_result[0x10]; + + u8 reserved_at_160[0x20]; +}; + struct mlx5_ifc_mpcnt_reg_bits { u8 reserved_at_0[0x8]; u8 pcie_index[0x8]; @@ -8344,7 +8390,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x74]; + u8 reserved_at_0[0x6e]; + u8 pci_status_and_power[0x1]; + u8 reserved_at_6f[0x5]; u8 mark_tx_action_cnp[0x1]; u8 mark_tx_action_cqe[0x1]; u8 dynamic_tx_overflow[0x1]; @@ -8944,6 +8992,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_pmtu_reg_bits pmtu_reg; struct mlx5_ifc_ppad_reg_bits ppad_reg; struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg; + struct mlx5_ifc_mpein_reg_bits mpein_reg; struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg; struct mlx5_ifc_pplm_reg_bits pplm_reg; struct mlx5_ifc_pplr_reg_bits pplr_reg; -- cgit v1.2.3-71-gd317 From 045925e3fe5b98e402337a176d154252c56cef2e Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 27 Mar 2019 21:58:44 +0100 Subject: net: phy: add genphy_read_abilities Similar to genphy_c45_pma_read_abilities() add a function to dynamically detect the abilities of a Clause 22 PHY. This is mainly copied from genphy_config_init(). Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 48 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 1 + 2 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index de2b6333e7ea..0af66f32d363 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1880,6 +1880,54 @@ int genphy_config_init(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_config_init); +/** + * genphy_read_abilities - read PHY abilities from Clause 22 registers + * @phydev: target phy_device struct + * + * Description: Reads the PHY's abilities and populates + * phydev->supported accordingly. + * + * Returns: 0 on success, < 0 on failure + */ +int genphy_read_abilities(struct phy_device *phydev) +{ + int val; + + linkmode_set_bit_array(phy_basic_ports_array, + ARRAY_SIZE(phy_basic_ports_array), + phydev->supported); + + val = phy_read(phydev, MII_BMSR); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported, + val & BMSR_ANEGCAPABLE); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, phydev->supported, + val & BMSR_100FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, phydev->supported, + val & BMSR_100HALF); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, phydev->supported, + val & BMSR_10FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, phydev->supported, + val & BMSR_10HALF); + + if (val & BMSR_ESTATEN) { + val = phy_read(phydev, MII_ESTATUS); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + phydev->supported, val & ESTATUS_1000_TFULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + phydev->supported, val & ESTATUS_1000_THALF); + } + + return 0; +} +EXPORT_SYMBOL(genphy_read_abilities); + /* This is used for the phy device which doesn't support the MMD extended * register access, but it does have side effect when we are trying to access * the MMD register via indirect method. diff --git a/include/linux/phy.h b/include/linux/phy.h index 34084892a466..ad88f063e50f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1075,6 +1075,7 @@ void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ int genphy_config_init(struct phy_device *phydev); +int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_eee_advert(struct phy_device *phydev); -- cgit v1.2.3-71-gd317 From 06ee7115b0d1742de745ad143fb5e06d77d27fba Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Apr 2019 21:27:40 -0700 Subject: bpf: add verifier stats and log_level bit 2 In order to understand the verifier bottlenecks add various stats and extend log_level: log_level 1 and 2 are kept as-is: bit 0 - level=1 - print every insn and verifier state at branch points bit 1 - level=2 - print every insn and verifier state at every insn bit 2 - level=4 - print verifier error and stats at the end of verification When verifier rejects the program the libbpf is trying to load the program twice. Once with log_level=0 (no messages, only error code is reported to user space) and second time with log_level=1 to tell the user why the verifier rejected it. With introduction of bit 2 - level=4 the libbpf can choose to always use that level and load programs once, since the verification speed is not affected and in case of error the verbose message will be available. Note that the verifier stats are not part of uapi just like all other verbose messages. They're expected to change in the future. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 21 ++++++++++++ kernel/bpf/verifier.c | 76 ++++++++++++++++++++++++++++++-------------- 2 files changed, 73 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7d8228d1c898..f7e15eeb60bb 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -248,6 +248,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) return log->len_used >= log->len_total - 1; } +#define BPF_LOG_LEVEL1 1 +#define BPF_LOG_LEVEL2 2 +#define BPF_LOG_STATS 4 +#define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) +#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) + static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { return log->level && log->ubuf && !bpf_verifier_log_full(log); @@ -284,6 +290,21 @@ struct bpf_verifier_env { struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; u32 subprog_cnt; + /* number of instructions analyzed by the verifier */ + u32 insn_processed; + /* total verification time */ + u64 verification_time; + /* maximum number of verifier states kept in 'branching' instructions */ + u32 max_states_per_insn; + /* total number of allocated verifier states */ + u32 total_states; + /* some states are freed during program analysis. + * this is peak number of states. this number dominates kernel + * memory consumption during verification + */ + u32 peak_states; + /* longest register parentage chain walked for liveness marking */ + u32 longest_mark_read_walk; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 87221fda1321..e2001c1e40b3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1092,7 +1092,7 @@ static int check_subprogs(struct bpf_verifier_env *env) */ subprog[env->subprog_cnt].start = insn_cnt; - if (env->log.level > 1) + if (env->log.level & BPF_LOG_LEVEL2) for (i = 0; i < env->subprog_cnt; i++) verbose(env, "func#%d @%d\n", i, subprog[i].start); @@ -1139,6 +1139,7 @@ static int mark_reg_read(struct bpf_verifier_env *env, struct bpf_reg_state *parent) { bool writes = parent == state->parent; /* Observe write marks */ + int cnt = 0; while (parent) { /* if read wasn't screened by an earlier write ... */ @@ -1155,7 +1156,11 @@ static int mark_reg_read(struct bpf_verifier_env *env, state = parent; parent = state->parent; writes = true; + cnt++; } + + if (env->longest_mark_read_walk < cnt) + env->longest_mark_read_walk = cnt; return 0; } @@ -1455,7 +1460,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ - if (env->log.level) + if (env->log.level & BPF_LOG_LEVEL) print_verifier_state(env, state); /* The minimum value is only important with signed @@ -2938,7 +2943,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* and go analyze first insn of the callee */ *insn_idx = target_insn; - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); print_verifier_state(env, caller); verbose(env, "callee:\n"); @@ -2978,7 +2983,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return err; *insn_idx = callee->callsite + 1; - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, callee); verbose(env, "to caller at %d:\n", *insn_idx); @@ -5001,7 +5006,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, insn->dst_reg); return -EACCES; } - if (env->log.level) + if (env->log.level & BPF_LOG_LEVEL) print_verifier_state(env, this_branch->frame[this_branch->curframe]); return 0; } @@ -6181,6 +6186,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) states_cnt++; } + if (env->max_states_per_insn < states_cnt) + env->max_states_per_insn = states_cnt; + if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) return 0; @@ -6194,6 +6202,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) return -ENOMEM; + env->total_states++; + env->peak_states++; /* add new state to the head of linked list */ new = &new_sl->state; @@ -6278,8 +6288,7 @@ static int do_check(struct bpf_verifier_env *env) struct bpf_verifier_state *state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; - int insn_cnt = env->prog->len, i; - int insn_processed = 0; + int insn_cnt = env->prog->len; bool do_print_state = false; env->prev_linfo = NULL; @@ -6314,10 +6323,10 @@ static int do_check(struct bpf_verifier_env *env) insn = &insns[env->insn_idx]; class = BPF_CLASS(insn->code); - if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { + if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, "BPF program is too large. Processed %d insn\n", - insn_processed); + env->insn_processed); return -E2BIG; } @@ -6326,7 +6335,7 @@ static int do_check(struct bpf_verifier_env *env) return err; if (err == 1) { /* found equivalent state, can prune the search */ - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { if (do_print_state) verbose(env, "\nfrom %d to %d%s: safe\n", env->prev_insn_idx, env->insn_idx, @@ -6344,8 +6353,9 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (env->log.level > 1 || (env->log.level && do_print_state)) { - if (env->log.level > 1) + if (env->log.level & BPF_LOG_LEVEL2 || + (env->log.level & BPF_LOG_LEVEL && do_print_state)) { + if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "%d:", env->insn_idx); else verbose(env, "\nfrom %d to %d%s:", @@ -6356,7 +6366,7 @@ static int do_check(struct bpf_verifier_env *env) do_print_state = false; } - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { const struct bpf_insn_cbs cbs = { .cb_print = verbose, .private_data = env, @@ -6621,16 +6631,6 @@ process_bpf_exit: env->insn_idx++; } - verbose(env, "processed %d insns (limit %d), stack depth ", - insn_processed, BPF_COMPLEXITY_LIMIT_INSNS); - for (i = 0; i < env->subprog_cnt; i++) { - u32 depth = env->subprog_info[i].stack_depth; - - verbose(env, "%d", depth); - if (i + 1 < env->subprog_cnt) - verbose(env, "+"); - } - verbose(env, "\n"); env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } @@ -7854,9 +7854,34 @@ static void free_states(struct bpf_verifier_env *env) kfree(env->explored_states); } +static void print_verification_stats(struct bpf_verifier_env *env) +{ + int i; + + if (env->log.level & BPF_LOG_STATS) { + verbose(env, "verification time %lld usec\n", + div_u64(env->verification_time, 1000)); + verbose(env, "stack depth "); + for (i = 0; i < env->subprog_cnt; i++) { + u32 depth = env->subprog_info[i].stack_depth; + + verbose(env, "%d", depth); + if (i + 1 < env->subprog_cnt) + verbose(env, "+"); + } + verbose(env, "\n"); + } + verbose(env, "processed %d insns (limit %d) max_states_per_insn %d " + "total_states %d peak_states %d mark_read %d\n", + env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS, + env->max_states_per_insn, env->total_states, + env->peak_states, env->longest_mark_read_walk); +} + int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, union bpf_attr __user *uattr) { + u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; struct bpf_verifier_log *log; int i, len, ret = -EINVAL; @@ -7899,7 +7924,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, ret = -EINVAL; /* log attributes have to be sane */ if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || - !log->level || !log->ubuf) + !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK) goto err_unlock; } @@ -7980,6 +8005,9 @@ skip_full_check: if (ret == 0) ret = fixup_call_args(env); + env->verification_time = ktime_get_ns() - start_time; + print_verification_stats(env); + if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; if (log->level && !log->ubuf) { -- cgit v1.2.3-71-gd317 From 9f4686c41bdff051f557accb531af79dd1773687 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Apr 2019 21:27:41 -0700 Subject: bpf: improve verification speed by droping states Branch instructions, branch targets and calls in a bpf program are the places where the verifier remembers states that led to successful verification of the program. These states are used to prune brute force program analysis. For unprivileged programs there is a limit of 64 states per such 'branching' instructions (maximum length is tracked by max_states_per_insn counter introduced in the previous patch). Simply reducing this threshold to 32 or lower increases insn_processed metric to the point that small valid programs get rejected. For root programs there is no limit and cilium programs can have max_states_per_insn to be 100 or higher. Walking 100+ states multiplied by number of 'branching' insns during verification consumes significant amount of cpu time. Turned out simple LRU-like mechanism can be used to remove states that unlikely will be helpful in future search pruning. This patch introduces hit_cnt and miss_cnt counters: hit_cnt - this many times this state successfully pruned the search miss_cnt - this many times this state was not equivalent to other states (and that other states were added to state list) The heuristic introduced in this patch is: if (sl->miss_cnt > sl->hit_cnt * 3 + 3) /* drop this state from future considerations */ Higher numbers increase max_states_per_insn (allow more states to be considered for pruning) and slow verification speed, but do not meaningfully reduce insn_processed metric. Lower numbers drop too many states and insn_processed increases too much. Many different formulas were considered. This one is simple and works well enough in practice. (the analysis was done on selftests/progs/* and on cilium programs) The end result is this heuristic improves verification speed by 10 times. Large synthetic programs that used to take a second more now take 1/10 of a second. In cases where max_states_per_insn used to be 100 or more, now it's ~10. There is a slight increase in insn_processed for cilium progs: before after bpf_lb-DLB_L3.o 1831 1838 bpf_lb-DLB_L4.o 3029 3218 bpf_lb-DUNKNOWN.o 1064 1064 bpf_lxc-DDROP_ALL.o 26309 26935 bpf_lxc-DUNKNOWN.o 33517 34439 bpf_netdev.o 9713 9721 bpf_overlay.o 6184 6184 bpf_lcx_jit.o 37335 39389 And 2-3 times improvement in the verification speed. Signed-off-by: Alexei Starovoitov Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 2 ++ kernel/bpf/verifier.c | 44 +++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 43 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f7e15eeb60bb..fc8254d6b569 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -207,6 +207,7 @@ struct bpf_verifier_state { struct bpf_verifier_state_list { struct bpf_verifier_state state; struct bpf_verifier_state_list *next; + int miss_cnt, hit_cnt; }; /* Possible states for alu_state member. */ @@ -280,6 +281,7 @@ struct bpf_verifier_env { bool strict_alignment; /* perform strict pointer alignment checks */ struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ + struct bpf_verifier_state_list *free_list; struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e2001c1e40b3..a636db4a7a4e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6152,11 +6152,13 @@ static int propagate_liveness(struct bpf_verifier_env *env, static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; - struct bpf_verifier_state_list *sl; + struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - sl = env->explored_states[insn_idx]; + pprev = &env->explored_states[insn_idx]; + sl = *pprev; + if (!sl) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here @@ -6167,6 +6169,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) while (sl != STATE_LIST_MARK) { if (states_equal(env, &sl->state, cur)) { + sl->hit_cnt++; /* reached equivalent register/stack state, * prune the search. * Registers read by the continuation are read by us. @@ -6182,8 +6185,35 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return err; return 1; } - sl = sl->next; states_cnt++; + sl->miss_cnt++; + /* heuristic to determine whether this state is beneficial + * to keep checking from state equivalence point of view. + * Higher numbers increase max_states_per_insn and verification time, + * but do not meaningfully decrease insn_processed. + */ + if (sl->miss_cnt > sl->hit_cnt * 3 + 3) { + /* the state is unlikely to be useful. Remove it to + * speed up verification + */ + *pprev = sl->next; + if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) { + free_verifier_state(&sl->state, false); + kfree(sl); + env->peak_states--; + } else { + /* cannot free this state, since parentage chain may + * walk it later. Add it for free_list instead to + * be freed at the end of verification + */ + sl->next = env->free_list; + env->free_list = sl; + } + sl = *pprev; + continue; + } + pprev = &sl->next; + sl = *pprev; } if (env->max_states_per_insn < states_cnt) @@ -7836,6 +7866,14 @@ static void free_states(struct bpf_verifier_env *env) struct bpf_verifier_state_list *sl, *sln; int i; + sl = env->free_list; + while (sl) { + sln = sl->next; + free_verifier_state(&sl->state, false); + kfree(sl); + sl = sln; + } + if (!env->explored_states) return; -- cgit v1.2.3-71-gd317 From c04c0d2b968ac45d6ef020316808ef6c82325a82 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Apr 2019 21:27:45 -0700 Subject: bpf: increase complexity limit and maximum program size Large verifier speed improvements allow to increase verifier complexity limit. Now regardless of the program composition and its size it takes little time for the verifier to hit insn_processed limit. On typical x86 machine non-debug kernel processes 1M instructions in 1/10 of a second. (before these speed improvements specially crafted programs could be hitting multi-second verification times) Full kasan kernel with debug takes ~1 second for the same 1M insns. Hence bump the BPF_COMPLEXITY_LIMIT_INSNS limit to 1M. Also increase the number of instructions per program from 4k to internal BPF_COMPLEXITY_LIMIT_INSNS limit. 4k limit was confusing to users, since small programs with hundreds of insns could be hitting BPF_COMPLEXITY_LIMIT_INSNS limit. Sometimes adding more insns and bpf_trace_printk debug statements would make the verifier accept the program while removing code would make the verifier reject it. Some user space application started to add #define MAX_FOO to their programs and do: MAX_FOO=100; again: compile with MAX_FOO; try to load; if (fails_to_load) { reduce MAX_FOO; goto again; } to be able to fit maximum amount of processing into single program. Other users artificially split their single program into a set of programs and use all 32 iterations of tail_calls to increase compute limits. And the most advanced folks used unlimited tc-bpf filter list to execute many bpf programs. Essentially the users managed to workaround 4k insn limit. This patch removes the limit for root programs from uapi. BPF_COMPLEXITY_LIMIT_INSNS is the kernel internal limit and success to load the program no longer depends on program size, but on 'smartness' of the verifier only. The verifier will continue to get smarter with every kernel release. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + kernel/bpf/syscall.c | 3 ++- kernel/bpf/verifier.c | 1 - 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f62897198844..a445194b5fb6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -421,6 +421,7 @@ struct bpf_array { }; }; +#define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 32 struct bpf_event_entry { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index afca36f53c49..1d65e56594db 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1557,7 +1557,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) /* eBPF programs must be GPL compatible to use GPL-ed functions */ is_gpl = license_is_gpl_compatible(license); - if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS) + if (attr->insn_cnt == 0 || + attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) return -E2BIG; if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6dcfeb44bb8e..b631e89e7a51 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -176,7 +176,6 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_INSNS 131072 #define BPF_COMPLEXITY_LIMIT_STACK 1024 #define BPF_COMPLEXITY_LIMIT_STATES 64 -- cgit v1.2.3-71-gd317 From 4950c2ba49cc6f2b38dbedcfa0ff67acf761419a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 2 Apr 2019 20:43:30 +0200 Subject: net: phy: fix autoneg mismatch case in genphy_read_status The original patch didn't consider the case that autoneg process finishes successfully but both link partners have no mode in common. In this case there's no link, nevertheless we may be interested in what the link partner advertised. Like phydev->link we set phydev->autoneg_complete in genphy_update_link() and use the stored value in genphy_read_status(). This way we don't have to read register BMSR again. Fixes: b6163f194c69 ("net: phy: improve genphy_read_status") Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 8 +++----- include/linux/phy.h | 1 + 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 67fc581e3598..72fc714c9427 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1723,10 +1723,8 @@ int genphy_update_link(struct phy_device *phydev) if (status < 0) return status; - if ((status & BMSR_LSTATUS) == 0) - phydev->link = 0; - else - phydev->link = 1; + phydev->link = status & BMSR_LSTATUS ? 1 : 0; + phydev->autoneg_complete = status & BMSR_ANEGCOMPLETE ? 1 : 0; return 0; } @@ -1757,7 +1755,7 @@ int genphy_read_status(struct phy_device *phydev) linkmode_zero(phydev->lp_advertising); - if (phydev->autoneg == AUTONEG_ENABLE && phydev->link) { + if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, phydev->supported) || linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, diff --git a/include/linux/phy.h b/include/linux/phy.h index ad88f063e50f..ab7439b3da2b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -390,6 +390,7 @@ struct phy_device { unsigned autoneg:1; /* The most recently read link state */ unsigned link:1; + unsigned autoneg_complete:1; /* Interrupts are enabled */ unsigned interrupts:1; -- cgit v1.2.3-71-gd317 From 28b05b92886871bdd8e6a9df73e3a15845fe8ef4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 3 Apr 2019 08:28:35 +0200 Subject: net: use correct this_cpu primitive in dev_recursion_level syzbot reports: BUG: using __this_cpu_read() in preemptible code: caller is dev_recursion_level include/linux/netdevice.h:3052 [inline] __this_cpu_preempt_check+0x246/0x270 lib/smp_processor_id.c:47 dev_recursion_level include/linux/netdevice.h:3052 [inline] ip6_skb_dst_mtu include/net/ip6_route.h:245 [inline] I erronously downgraded a this_cpu_read to __this_cpu_read when moving dev_recursion_level() around. Reported-by: syzbot+51471b4aae195285a4a3@syzkaller.appspotmail.com Fixes: 97cdcf37b57e ("net: place xmit recursion in softnet data") Signed-off-by: Florian Westphal Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eb9f05e0863d..521eb869555e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3049,7 +3049,7 @@ DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); static inline int dev_recursion_level(void) { - return __this_cpu_read(softnet_data.xmit.recursion); + return this_cpu_read(softnet_data.xmit.recursion); } #define XMIT_RECURSION_LIMIT 10 -- cgit v1.2.3-71-gd317 From 5d3c537f907036c1f18bd325ffc356e24cde664c Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Sun, 24 Mar 2019 09:21:40 +0200 Subject: net/mlx5: Handle event of power detection in the PCIE slot Handle event of power state change in the PCIE slot. When the event occurs, check if query power state and PCI power fields is supported. If so, read these fields from MPEIN (management PCIE info) register and issue a corresponding message. Signed-off-by: Aya Levin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/events.c | 75 ++++++++++++++++++++++++ include/linux/mlx5/device.h | 1 + 2 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index 5d5864e8df3c..a81e8d2168d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -21,6 +21,7 @@ struct mlx5_event_nb { static int any_notifier(struct notifier_block *, unsigned long, void *); static int temp_warn(struct notifier_block *, unsigned long, void *); static int port_module(struct notifier_block *, unsigned long, void *); +static int pcie_core(struct notifier_block *, unsigned long, void *); /* handler which forwards the event to events->nh, driver notifiers */ static int forward_event(struct notifier_block *, unsigned long, void *); @@ -30,6 +31,7 @@ static struct mlx5_nb events_nbs_ref[] = { {.nb.notifier_call = any_notifier, .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY }, {.nb.notifier_call = temp_warn, .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT }, {.nb.notifier_call = port_module, .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT }, + {.nb.notifier_call = pcie_core, .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT }, /* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_PORT_CHANGE }, @@ -51,11 +53,14 @@ static struct mlx5_nb events_nbs_ref[] = { struct mlx5_events { struct mlx5_core_dev *dev; + struct workqueue_struct *wq; struct mlx5_event_nb notifiers[ARRAY_SIZE(events_nbs_ref)]; /* driver notifier chain */ struct atomic_notifier_head nh; /* port module events stats */ struct mlx5_pme_stats pme_stats; + /*pcie_core*/ + struct work_struct pcie_core_work; }; static const char *eqe_type_str(u8 type) @@ -249,6 +254,69 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data return NOTIFY_OK; } +enum { + MLX5_PCI_POWER_COULD_NOT_BE_READ = 0x0, + MLX5_PCI_POWER_SUFFICIENT_REPORTED = 0x1, + MLX5_PCI_POWER_INSUFFICIENT_REPORTED = 0x2, +}; + +static void mlx5_pcie_event(struct work_struct *work) +{ + u32 out[MLX5_ST_SZ_DW(mpein_reg)] = {0}; + u32 in[MLX5_ST_SZ_DW(mpein_reg)] = {0}; + struct mlx5_events *events; + struct mlx5_core_dev *dev; + u8 power_status; + u16 pci_power; + + events = container_of(work, struct mlx5_events, pcie_core_work); + dev = events->dev; + + if (!MLX5_CAP_MCAM_FEATURE(dev, pci_status_and_power)) + return; + + mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), + MLX5_REG_MPEIN, 0, 0); + power_status = MLX5_GET(mpein_reg, out, pwr_status); + pci_power = MLX5_GET(mpein_reg, out, pci_power); + + switch (power_status) { + case MLX5_PCI_POWER_COULD_NOT_BE_READ: + mlx5_core_info_rl(dev, + "PCIe slot power capability was not advertised.\n"); + break; + case MLX5_PCI_POWER_INSUFFICIENT_REPORTED: + mlx5_core_warn_rl(dev, + "Detected insufficient power on the PCIe slot (%uW).\n", + pci_power); + break; + case MLX5_PCI_POWER_SUFFICIENT_REPORTED: + mlx5_core_info_rl(dev, + "PCIe slot advertised sufficient power (%uW).\n", + pci_power); + break; + } +} + +static int pcie_core(struct notifier_block *nb, unsigned long type, void *data) +{ + struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, + struct mlx5_event_nb, + nb); + struct mlx5_events *events = event_nb->ctx; + struct mlx5_eqe *eqe = data; + + switch (eqe->sub_type) { + case MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT: + queue_work(events->wq, &events->pcie_core_work); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats) { *stats = dev->priv.events->pme_stats; @@ -277,11 +345,17 @@ int mlx5_events_init(struct mlx5_core_dev *dev) ATOMIC_INIT_NOTIFIER_HEAD(&events->nh); events->dev = dev; dev->priv.events = events; + events->wq = create_singlethread_workqueue("mlx5_events"); + if (!events->wq) + return -ENOMEM; + INIT_WORK(&events->pcie_core_work, mlx5_pcie_event); + return 0; } void mlx5_events_cleanup(struct mlx5_core_dev *dev) { + destroy_workqueue(dev->priv.events->wq); kvfree(dev->priv.events); } @@ -304,6 +378,7 @@ void mlx5_events_stop(struct mlx5_core_dev *dev) for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--) mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb); + flush_workqueue(events->wq); } int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f93a5598b942..db7dca75d726 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -361,6 +361,7 @@ enum { enum { MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, + MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5, }; enum { -- cgit v1.2.3-71-gd317 From ff302db965b57c141297911ea647d36d11fedfbe Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 2 Apr 2019 10:07:45 +1100 Subject: rhashtable: allow rht_bucket_var to return NULL. Rather than returning a pointer to a static nulls, rht_bucket_var() now returns NULL if the bucket doesn't exist. This will make the next patch, which stores a bitlock in the bucket pointer, somewhat cleaner. This change involves introducing __rht_bucket_nested() which is like rht_bucket_nested(), but doesn't provide the static nulls, and changing rht_bucket_nested() to call this and possible provide a static nulls - as is still needed for the non-var case. Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 11 +++++++++-- lib/rhashtable.c | 29 ++++++++++++++++++++--------- 2 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 86dfa417848d..0c9175aeab8a 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -265,6 +265,8 @@ void rhashtable_destroy(struct rhashtable *ht); struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, unsigned int hash); +struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash); struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); @@ -294,7 +296,7 @@ static inline struct rhash_head __rcu *const *rht_bucket( static inline struct rhash_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { - return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : + return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } @@ -890,6 +892,8 @@ static inline int __rhashtable_remove_fast_one( spin_lock_bh(lock); pprev = rht_bucket_var(tbl, hash); + if (!pprev) + goto out; rht_for_each_from(he, *pprev, tbl, hash) { struct rhlist_head *list; @@ -934,6 +938,7 @@ static inline int __rhashtable_remove_fast_one( break; } +out: spin_unlock_bh(lock); if (err > 0) { @@ -1042,6 +1047,8 @@ static inline int __rhashtable_replace_fast( spin_lock_bh(lock); pprev = rht_bucket_var(tbl, hash); + if (!pprev) + goto out; rht_for_each_from(he, *pprev, tbl, hash) { if (he != obj_old) { pprev = &he->next; @@ -1053,7 +1060,7 @@ static inline int __rhashtable_replace_fast( err = 0; break; } - +out: spin_unlock_bh(lock); return err; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 6c4f5c8e9baa..b28fdd560ea9 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -237,8 +237,10 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) goto out; err = -ENOENT; + if (!pprev) + goto out; - rht_for_each(entry, old_tbl, old_hash) { + rht_for_each_from(entry, *pprev, old_tbl, old_hash) { err = 0; next = rht_dereference_bucket(entry->next, old_tbl, old_hash); @@ -496,6 +498,8 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, elasticity = RHT_ELASTICITY; pprev = rht_bucket_var(tbl, hash); + if (!pprev) + return ERR_PTR(-ENOENT); rht_for_each_from(head, *pprev, tbl, hash) { struct rhlist_head *list; struct rhlist_head *plist; @@ -1161,11 +1165,10 @@ void rhashtable_destroy(struct rhashtable *ht) } EXPORT_SYMBOL_GPL(rhashtable_destroy); -struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); - static struct rhash_head __rcu *rhnull; unsigned int index = hash & ((1 << tbl->nest) - 1); unsigned int size = tbl->size >> tbl->nest; unsigned int subhash = hash; @@ -1183,15 +1186,23 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, subhash >>= shift; } - if (!ntbl) { - if (!rhnull) - INIT_RHT_NULLS_HEAD(rhnull); - return &rhnull; - } + if (!ntbl) + return NULL; return &ntbl[subhash].bucket; } +EXPORT_SYMBOL_GPL(__rht_bucket_nested); + +struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash) +{ + static struct rhash_head __rcu *rhnull; + + if (!rhnull) + INIT_RHT_NULLS_HEAD(rhnull); + return __rht_bucket_nested(tbl, hash) ?: &rhnull; +} EXPORT_SYMBOL_GPL(rht_bucket_nested); struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, -- cgit v1.2.3-71-gd317 From 8f0db018006a421956965e1149234c4e8db718ee Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 2 Apr 2019 10:07:45 +1100 Subject: rhashtable: use bit_spin_locks to protect hash bucket. This patch changes rhashtables to use a bit_spin_lock on BIT(1) of the bucket pointer to lock the hash chain for that bucket. The benefits of a bit spin_lock are: - no need to allocate a separate array of locks. - no need to have a configuration option to guide the choice of the size of this array - locking cost is often a single test-and-set in a cache line that will have to be loaded anyway. When inserting at, or removing from, the head of the chain, the unlock is free - writing the new address in the bucket head implicitly clears the lock bit. For __rhashtable_insert_fast() we ensure this always happens when adding a new key. - even when lockings costs 2 updates (lock and unlock), they are in a cacheline that needs to be read anyway. The cost of using a bit spin_lock is a little bit of code complexity, which I think is quite manageable. Bit spin_locks are sometimes inappropriate because they are not fair - if multiple CPUs repeatedly contend of the same lock, one CPU can easily be starved. This is not a credible situation with rhashtable. Multiple CPUs may want to repeatedly add or remove objects, but they will typically do so at different buckets, so they will attempt to acquire different locks. As we have more bit-locks than we previously had spinlocks (by at least a factor of two) we can expect slightly less contention to go with the slightly better cache behavior and reduced memory consumption. To enhance type checking, a new struct is introduced to represent the pointer plus lock-bit that is stored in the bucket-table. This is "struct rhash_lock_head" and is empty. A pointer to this needs to be cast to either an unsigned lock, or a "struct rhash_head *" to be useful. Variables of this type are most often called "bkt". Previously "pprev" would sometimes point to a bucket, and sometimes a ->next pointer in an rhash_head. As these are now different types, pprev is NULL when it would have pointed to the bucket. In that case, 'blk' is used, together with correct locking protocol. Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable-types.h | 2 - include/linux/rhashtable.h | 261 +++++++++++++++++++++++++-------------- ipc/util.c | 1 - lib/rhashtable.c | 141 +++++++++++---------- lib/test_rhashtable.c | 2 +- net/bridge/br_fdb.c | 1 - net/bridge/br_multicast.c | 1 - net/bridge/br_vlan.c | 1 - net/bridge/br_vlan_tunnel.c | 1 - net/ipv4/ipmr.c | 1 - net/ipv6/ip6mr.c | 1 - net/netfilter/nf_tables_api.c | 1 - 12 files changed, 236 insertions(+), 178 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index 763d613ce2c2..57467cbf4c5b 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -48,7 +48,6 @@ typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, * @head_offset: Offset of rhash_head in struct to be hashed * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking - * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) * @automatic_shrinking: Enable automatic shrinking of tables * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object @@ -62,7 +61,6 @@ struct rhashtable_params { unsigned int max_size; u16 min_size; bool automatic_shrinking; - u8 locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; rht_obj_cmpfn_t obj_cmpfn; diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 0c9175aeab8a..ccbbafdf5547 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -24,12 +24,27 @@ #include #include #include +#include #include /* + * Objects in an rhashtable have an embedded struct rhash_head + * which is linked into as hash chain from the hash table - or one + * of two or more hash tables when the rhashtable is being resized. * The end of the chain is marked with a special nulls marks which has - * the least significant bit set. + * the least significant bit set but otherwise stores the address of + * the hash bucket. This allows us to be be sure we've found the end + * of the right list. + * The value stored in the hash bucket has BIT(2) used as a lock bit. + * This bit must be atomically set before any changes are made to + * the chain. To avoid dereferencing this pointer without clearing + * the bit first, we use an opaque 'struct rhash_lock_head *' for the + * pointer stored in the bucket. This struct needs to be defined so + * that rcu_derefernce() works on it, but it has no content so a + * cast is needed for it to be useful. This ensures it isn't + * used by mistake with clearing the lock bit first. */ +struct rhash_lock_head {}; /* Maximum chain length before rehash * @@ -52,8 +67,6 @@ * @nest: Number of bits of first-level nested table. * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash - * @locks_mask: Mask to apply before accessing locks[] - * @locks: Array of spinlocks protecting individual buckets * @walkers: List of active walkers * @rcu: RCU structure for freeing the table * @future_tbl: Table under construction during rehashing @@ -64,16 +77,70 @@ struct bucket_table { unsigned int size; unsigned int nest; u32 hash_rnd; - unsigned int locks_mask; - spinlock_t *locks; struct list_head walkers; struct rcu_head rcu; struct bucket_table __rcu *future_tbl; - struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; +/* + * We lock a bucket by setting BIT(1) in the pointer - this is always + * zero in real pointers and in the nulls marker. + * bit_spin_locks do not handle contention well, but the whole point + * of the hashtable design is to achieve minimum per-bucket contention. + * A nested hash table might not have a bucket pointer. In that case + * we cannot get a lock. For remove and replace the bucket cannot be + * interesting and doesn't need locking. + * For insert we allocate the bucket if this is the last bucket_table, + * and then take the lock. + * Sometimes we unlock a bucket by writing a new pointer there. In that + * case we don't need to unlock, but we do need to reset state such as + * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() + * provides the same release semantics that bit_spin_unlock() provides, + * this is safe. + */ + +static inline void rht_lock(struct rhash_lock_head **bkt) +{ + local_bh_disable(); + bit_spin_lock(1, (unsigned long *)bkt); +} + +static inline void rht_unlock(struct rhash_lock_head **bkt) +{ + bit_spin_unlock(1, (unsigned long *)bkt); + local_bh_enable(); +} + +static inline void rht_assign_unlock(struct rhash_lock_head **bkt, + struct rhash_head *obj) +{ + struct rhash_head **p = (struct rhash_head **)bkt; + + rcu_assign_pointer(*p, obj); + preempt_enable(); + __release(bitlock); + local_bh_enable(); +} + +/* + * If 'p' is a bucket head and might be locked: + * rht_ptr() returns the address without the lock bit. + * rht_ptr_locked() returns the address WITH the lock bit. + */ +static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p) +{ + return (void *)(((unsigned long)p) & ~BIT(1)); +} + +static inline struct rhash_lock_head __rcu *rht_ptr_locked(const + struct rhash_head *p) +{ + return (void *)(((unsigned long)p) | BIT(1)); +} + /* * NULLS_MARKER() expects a hash value with the low * bits mostly likely to be significant, and it discards @@ -206,25 +273,6 @@ static inline bool rht_grow_above_max(const struct rhashtable *ht, return atomic_read(&ht->nelems) >= ht->max_elems; } -/* The bucket lock is selected based on the hash and protects mutations - * on a group of hash buckets. - * - * A maximum of tbl->size/2 bucket locks is allocated. This ensures that - * a single lock always covers both buckets which may both contains - * entries which link to the same bucket of the old table during resizing. - * This allows to simplify the locking as locking the bucket in both - * tables during resize always guarantee protection. - * - * IMPORTANT: When holding the bucket lock of both the old and new table - * during expansions and shrinking, the old bucket lock must always be - * acquired first. - */ -static inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl, - unsigned int hash) -{ - return &tbl->locks[hash & tbl->locks_mask]; -} - #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); @@ -263,13 +311,13 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void *arg); void rhashtable_destroy(struct rhashtable *ht); -struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, +struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash); +struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, + struct bucket_table *tbl, + unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) @@ -286,21 +334,21 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) -static inline struct rhash_head __rcu *const *rht_bucket( +static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_head __rcu **rht_bucket_var( +static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_head __rcu **rht_bucket_insert( +static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : @@ -326,7 +374,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * @hash: the hash value / bucket index */ #define rht_for_each(pos, tbl, hash) \ - rht_for_each_from(pos, *rht_bucket(tbl, hash), tbl, hash) + rht_for_each_from(pos, rht_ptr(*rht_bucket(tbl, hash)), tbl, hash) /** * rht_for_each_entry_from - iterate over hash chain from given head @@ -351,7 +399,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_from(tpos, pos, *rht_bucket(tbl, hash), \ + rht_for_each_entry_from(tpos, pos, rht_ptr(*rht_bucket(tbl, hash)), \ tbl, hash, member) /** @@ -367,7 +415,8 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * remove the loop cursor from the list. */ #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ - for (pos = rht_dereference_bucket(*rht_bucket(tbl, hash), tbl, hash), \ + for (pos = rht_dereference_bucket(rht_ptr(*rht_bucket(tbl, hash)), \ + tbl, hash), \ next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ @@ -402,8 +451,12 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_rcu(pos, tbl, hash) \ - rht_for_each_rcu_from(pos, *rht_bucket(tbl, hash), tbl, hash) +#define rht_for_each_rcu(pos, tbl, hash) \ + for (({barrier(); }), \ + pos = rht_ptr(rht_dereference_bucket_rcu( \ + *rht_bucket(tbl, hash), tbl, hash)); \ + !rht_is_a_nulls(pos); \ + pos = rcu_dereference_raw(pos->next)) /** * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head @@ -437,7 +490,8 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_rcu_from(tpos, pos, *rht_bucket(tbl, hash), \ + rht_for_each_entry_rcu_from(tpos, pos, \ + rht_ptr(*rht_bucket(tbl, hash)), \ tbl, hash, member) /** @@ -483,7 +537,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; - struct rhash_head __rcu * const *head; + struct rhash_lock_head __rcu * const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -491,9 +545,10 @@ static inline struct rhash_head *__rhashtable_lookup( tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); - head = rht_bucket(tbl, hash); + bkt = rht_bucket(tbl, hash); do { - rht_for_each_rcu_from(he, *head, tbl, hash) { + he = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash)); + rht_for_each_rcu_from(he, he, tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) @@ -503,7 +558,7 @@ restart: /* An object might have been moved to a different hash chain, * while we walk along it - better check and retry. */ - } while (he != RHT_NULLS_MARKER(head)); + } while (he != RHT_NULLS_MARKER(bkt)); /* Ensure we see any new tables. */ smp_rmb(); @@ -599,10 +654,10 @@ static inline void *__rhashtable_insert_fast( .ht = ht, .key = key, }; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; - spinlock_t *lock; unsigned int hash; int elasticity; void *data; @@ -611,23 +666,22 @@ static inline void *__rhashtable_insert_fast( tbl = rht_dereference_rcu(ht->tbl, ht); hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); - spin_lock_bh(lock); + elasticity = RHT_ELASTICITY; + bkt = rht_bucket_insert(ht, tbl, hash); + data = ERR_PTR(-ENOMEM); + if (!bkt) + goto out; + pprev = NULL; + rht_lock(bkt); if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: - spin_unlock_bh(lock); + rht_unlock(bkt); rcu_read_unlock(); return rhashtable_insert_slow(ht, key, obj); } - elasticity = RHT_ELASTICITY; - pprev = rht_bucket_insert(ht, tbl, hash); - data = ERR_PTR(-ENOMEM); - if (!pprev) - goto out; - - rht_for_each_from(head, *pprev, tbl, hash) { + rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) { struct rhlist_head *plist; struct rhlist_head *list; @@ -643,7 +697,7 @@ slow_path: data = rht_obj(ht, head); if (!rhlist) - goto out; + goto out_unlock; list = container_of(obj, struct rhlist_head, rhead); @@ -652,9 +706,13 @@ slow_path: RCU_INIT_POINTER(list->next, plist); head = rht_dereference_bucket(head->next, tbl, hash); RCU_INIT_POINTER(list->rhead.next, head); - rcu_assign_pointer(*pprev, obj); - - goto good; + if (pprev) { + rcu_assign_pointer(*pprev, obj); + rht_unlock(bkt); + } else + rht_assign_unlock(bkt, obj); + data = NULL; + goto out; } if (elasticity <= 0) @@ -662,12 +720,13 @@ slow_path: data = ERR_PTR(-E2BIG); if (unlikely(rht_grow_above_max(ht, tbl))) - goto out; + goto out_unlock; if (unlikely(rht_grow_above_100(ht, tbl))) goto slow_path; - head = rht_dereference_bucket(*pprev, tbl, hash); + /* Inserting at head of list makes unlocking free. */ + head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash)); RCU_INIT_POINTER(obj->next, head); if (rhlist) { @@ -677,20 +736,21 @@ slow_path: RCU_INIT_POINTER(list->next, NULL); } - rcu_assign_pointer(*pprev, obj); - atomic_inc(&ht->nelems); + rht_assign_unlock(bkt, obj); + if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); -good: data = NULL; - out: - spin_unlock_bh(lock); rcu_read_unlock(); return data; + +out_unlock: + rht_unlock(bkt); + goto out; } /** @@ -699,9 +759,9 @@ out: * @obj: pointer to hash head inside object * @params: hash table parameters * - * Will take a per bucket spinlock to protect against mutual mutations + * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless - * they map to the same bucket lock. + * they map to the same bucket. * * It is safe to call this function from atomic context. * @@ -728,9 +788,9 @@ static inline int rhashtable_insert_fast( * @list: pointer to hash list head inside object * @params: hash table parameters * - * Will take a per bucket spinlock to protect against mutual mutations + * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless - * they map to the same bucket lock. + * they map to the same bucket. * * It is safe to call this function from atomic context. * @@ -751,9 +811,9 @@ static inline int rhltable_insert_key( * @list: pointer to hash list head inside object * @params: hash table parameters * - * Will take a per bucket spinlock to protect against mutual mutations + * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless - * they map to the same bucket lock. + * they map to the same bucket. * * It is safe to call this function from atomic context. * @@ -880,21 +940,20 @@ static inline int __rhashtable_remove_fast_one( struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; - spinlock_t * lock; unsigned int hash; int err = -ENOENT; hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); + bkt = rht_bucket_var(tbl, hash); + if (!bkt) + return -ENOENT; + pprev = NULL; + rht_lock(bkt); - spin_lock_bh(lock); - - pprev = rht_bucket_var(tbl, hash); - if (!pprev) - goto out; - rht_for_each_from(he, *pprev, tbl, hash) { + rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) { struct rhlist_head *list; list = container_of(he, struct rhlist_head, rhead); @@ -934,13 +993,17 @@ static inline int __rhashtable_remove_fast_one( } } - rcu_assign_pointer(*pprev, obj); - break; + if (pprev) { + rcu_assign_pointer(*pprev, obj); + rht_unlock(bkt); + } else { + rht_assign_unlock(bkt, obj); + } + goto unlocked; } -out: - spin_unlock_bh(lock); - + rht_unlock(bkt); +unlocked: if (err > 0) { atomic_dec(&ht->nelems); if (unlikely(ht->p.automatic_shrinking && @@ -1029,9 +1092,9 @@ static inline int __rhashtable_replace_fast( struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; - spinlock_t *lock; unsigned int hash; int err = -ENOENT; @@ -1042,27 +1105,33 @@ static inline int __rhashtable_replace_fast( if (hash != rht_head_hashfn(ht, tbl, obj_new, params)) return -EINVAL; - lock = rht_bucket_lock(tbl, hash); + bkt = rht_bucket_var(tbl, hash); + if (!bkt) + return -ENOENT; - spin_lock_bh(lock); + pprev = NULL; + rht_lock(bkt); - pprev = rht_bucket_var(tbl, hash); - if (!pprev) - goto out; - rht_for_each_from(he, *pprev, tbl, hash) { + rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) { if (he != obj_old) { pprev = &he->next; continue; } rcu_assign_pointer(obj_new->next, obj_old->next); - rcu_assign_pointer(*pprev, obj_new); + if (pprev) { + rcu_assign_pointer(*pprev, obj_new); + rht_unlock(bkt); + } else { + rht_assign_unlock(bkt, obj_new); + } err = 0; - break; + goto unlocked; } -out: - spin_unlock_bh(lock); + rht_unlock(bkt); + +unlocked: return err; } diff --git a/ipc/util.c b/ipc/util.c index 0af05752969f..095274a871f8 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -101,7 +101,6 @@ static const struct rhashtable_params ipc_kht_params = { .head_offset = offsetof(struct kern_ipc_perm, khtnode), .key_offset = offsetof(struct kern_ipc_perm, key), .key_len = FIELD_SIZEOF(struct kern_ipc_perm, key), - .locks_mul = 1, .automatic_shrinking = true, }; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index b28fdd560ea9..c5d0974467ee 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -31,11 +31,10 @@ #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U -#define BUCKET_LOCKS_PER_CPU 32UL union nested_table { union nested_table __rcu *table; - struct rhash_head __rcu *bucket; + struct rhash_lock_head __rcu *bucket; }; static u32 head_hashfn(struct rhashtable *ht, @@ -56,9 +55,11 @@ EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) { - spinlock_t *lock = rht_bucket_lock(tbl, hash); - - return (debug_locks) ? lockdep_is_held(lock) : 1; + if (!debug_locks) + return 1; + if (unlikely(tbl->nest)) + return 1; + return bit_spin_is_locked(1, (unsigned long *)&tbl->buckets[hash]); } EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held); #else @@ -104,7 +105,6 @@ static void bucket_table_free(const struct bucket_table *tbl) if (tbl->nest) nested_bucket_table_free(tbl); - free_bucket_spinlocks(tbl->locks); kvfree(tbl); } @@ -171,7 +171,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, gfp_t gfp) { struct bucket_table *tbl = NULL; - size_t size, max_locks; + size_t size; int i; size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]); @@ -189,16 +189,6 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, tbl->size = size; - max_locks = size >> 1; - if (tbl->nest) - max_locks = min_t(size_t, max_locks, 1U << tbl->nest); - - if (alloc_bucket_spinlocks(&tbl->locks, &tbl->locks_mask, max_locks, - ht->p.locks_mul, gfp) < 0) { - bucket_table_free(tbl); - return NULL; - } - rcu_head_init(&tbl->rcu); INIT_LIST_HEAD(&tbl->walkers); @@ -223,24 +213,23 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, return new_tbl; } -static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) +static int rhashtable_rehash_one(struct rhashtable *ht, + struct rhash_lock_head __rcu **bkt, + unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl); - struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash); int err = -EAGAIN; struct rhash_head *head, *next, *entry; - spinlock_t *new_bucket_lock; + struct rhash_head **pprev = NULL; unsigned int new_hash; if (new_tbl->nest) goto out; err = -ENOENT; - if (!pprev) - goto out; - rht_for_each_from(entry, *pprev, old_tbl, old_hash) { + rht_for_each_from(entry, rht_ptr(*bkt), old_tbl, old_hash) { err = 0; next = rht_dereference_bucket(entry->next, old_tbl, old_hash); @@ -255,18 +244,20 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) new_hash = head_hashfn(ht, new_tbl, entry); - new_bucket_lock = rht_bucket_lock(new_tbl, new_hash); + rht_lock(&new_tbl->buckets[new_hash]); - spin_lock_nested(new_bucket_lock, SINGLE_DEPTH_NESTING); - head = rht_dereference_bucket(new_tbl->buckets[new_hash], - new_tbl, new_hash); + head = rht_ptr(rht_dereference_bucket(new_tbl->buckets[new_hash], + new_tbl, new_hash)); RCU_INIT_POINTER(entry->next, head); - rcu_assign_pointer(new_tbl->buckets[new_hash], entry); - spin_unlock(new_bucket_lock); + rht_assign_unlock(&new_tbl->buckets[new_hash], entry); - rcu_assign_pointer(*pprev, next); + if (pprev) + rcu_assign_pointer(*pprev, next); + else + /* Need to preserved the bit lock. */ + rcu_assign_pointer(*bkt, rht_ptr_locked(next)); out: return err; @@ -276,19 +267,19 @@ static int rhashtable_rehash_chain(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - spinlock_t *old_bucket_lock; + struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash); int err; - old_bucket_lock = rht_bucket_lock(old_tbl, old_hash); + if (!bkt) + return 0; + rht_lock(bkt); - spin_lock_bh(old_bucket_lock); - while (!(err = rhashtable_rehash_one(ht, old_hash))) + while (!(err = rhashtable_rehash_one(ht, bkt, old_hash))) ; if (err == -ENOENT) err = 0; - - spin_unlock_bh(old_bucket_lock); + rht_unlock(bkt); return err; } @@ -485,6 +476,7 @@ fail: } static void *rhashtable_lookup_one(struct rhashtable *ht, + struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, const void *key, struct rhash_head *obj) { @@ -492,15 +484,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, .ht = ht, .key = key, }; - struct rhash_head __rcu **pprev; + struct rhash_head **pprev = NULL; struct rhash_head *head; int elasticity; elasticity = RHT_ELASTICITY; - pprev = rht_bucket_var(tbl, hash); - if (!pprev) - return ERR_PTR(-ENOENT); - rht_for_each_from(head, *pprev, tbl, hash) { + rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) { struct rhlist_head *list; struct rhlist_head *plist; @@ -522,7 +511,11 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, RCU_INIT_POINTER(list->next, plist); head = rht_dereference_bucket(head->next, tbl, hash); RCU_INIT_POINTER(list->rhead.next, head); - rcu_assign_pointer(*pprev, obj); + if (pprev) + rcu_assign_pointer(*pprev, obj); + else + /* Need to preserve the bit lock */ + rcu_assign_pointer(*bkt, rht_ptr_locked(obj)); return NULL; } @@ -534,12 +527,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, } static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, + struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj, void *data) { - struct rhash_head __rcu **pprev; struct bucket_table *new_tbl; struct rhash_head *head; @@ -562,11 +555,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, if (unlikely(rht_grow_above_100(ht, tbl))) return ERR_PTR(-EAGAIN); - pprev = rht_bucket_insert(ht, tbl, hash); - if (!pprev) - return ERR_PTR(-ENOMEM); - - head = rht_dereference_bucket(*pprev, tbl, hash); + head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash)); RCU_INIT_POINTER(obj->next, head); if (ht->rhlist) { @@ -576,7 +565,10 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, RCU_INIT_POINTER(list->next, NULL); } - rcu_assign_pointer(*pprev, obj); + /* bkt is always the head of the list, so it holds + * the lock, which we need to preserve + */ + rcu_assign_pointer(*bkt, rht_ptr_locked(obj)); atomic_inc(&ht->nelems); if (rht_grow_above_75(ht, tbl)) @@ -590,6 +582,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, { struct bucket_table *new_tbl; struct bucket_table *tbl; + struct rhash_lock_head __rcu **bkt; unsigned int hash; void *data; @@ -598,14 +591,25 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, do { tbl = new_tbl; hash = rht_head_hashfn(ht, tbl, obj, ht->p); - spin_lock_bh(rht_bucket_lock(tbl, hash)); - - data = rhashtable_lookup_one(ht, tbl, hash, key, obj); - new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data); - if (PTR_ERR(new_tbl) != -EEXIST) - data = ERR_CAST(new_tbl); - - spin_unlock_bh(rht_bucket_lock(tbl, hash)); + if (rcu_access_pointer(tbl->future_tbl)) + /* Failure is OK */ + bkt = rht_bucket_var(tbl, hash); + else + bkt = rht_bucket_insert(ht, tbl, hash); + if (bkt == NULL) { + new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); + data = ERR_PTR(-EAGAIN); + } else { + rht_lock(bkt); + data = rhashtable_lookup_one(ht, bkt, tbl, + hash, key, obj); + new_tbl = rhashtable_insert_one(ht, bkt, tbl, + hash, obj, data); + if (PTR_ERR(new_tbl) != -EEXIST) + data = ERR_CAST(new_tbl); + + rht_unlock(bkt); + } } while (!IS_ERR_OR_NULL(new_tbl)); if (PTR_ERR(data) == -EAGAIN) @@ -1032,11 +1036,6 @@ int rhashtable_init(struct rhashtable *ht, size = rounded_hashtable_size(&ht->p); - if (params->locks_mul) - ht->p.locks_mul = roundup_pow_of_two(params->locks_mul); - else - ht->p.locks_mul = BUCKET_LOCKS_PER_CPU; - ht->key_len = ht->p.key_len; if (!params->hashfn) { ht->p.hashfn = jhash; @@ -1138,7 +1137,7 @@ restart: struct rhash_head *pos, *next; cond_resched(); - for (pos = rht_dereference(*rht_bucket(tbl, i), ht), + for (pos = rht_ptr(rht_dereference(*rht_bucket(tbl, i), ht)), next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; !rht_is_a_nulls(pos); @@ -1165,8 +1164,8 @@ void rhashtable_destroy(struct rhashtable *ht) } EXPORT_SYMBOL_GPL(rhashtable_destroy); -struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); @@ -1194,10 +1193,10 @@ struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(__rht_bucket_nested); -struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash) { - static struct rhash_head __rcu *rhnull; + static struct rhash_lock_head __rcu *rhnull; if (!rhnull) INIT_RHT_NULLS_HEAD(rhnull); @@ -1205,9 +1204,9 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(rht_bucket_nested); -struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, + struct bucket_table *tbl, + unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 3bd2e91bfc29..02592c2a249c 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -500,7 +500,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt) struct rhash_head *pos, *next; struct test_obj_rhl *p; - pos = rht_dereference(tbl->buckets[i], ht); + pos = rht_ptr(rht_dereference(tbl->buckets[i], ht)); next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; if (!rht_is_a_nulls(pos)) { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 00573cc46c98..b1c91f66d79c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -33,7 +33,6 @@ static const struct rhashtable_params br_fdb_rht_params = { .key_offset = offsetof(struct net_bridge_fdb_entry, key), .key_len = sizeof(struct net_bridge_fdb_key), .automatic_shrinking = true, - .locks_mul = 1, }; static struct kmem_cache *br_fdb_cache __read_mostly; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8d82107c6419..812560d7f7a2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -44,7 +44,6 @@ static const struct rhashtable_params br_mdb_rht_params = { .key_offset = offsetof(struct net_bridge_mdb_entry, addr), .key_len = sizeof(struct br_ip), .automatic_shrinking = true, - .locks_mul = 1, }; static void br_multicast_start_querier(struct net_bridge *br, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 96abf8feb9dc..0a02822b5667 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -21,7 +21,6 @@ static const struct rhashtable_params br_vlan_rht_params = { .key_offset = offsetof(struct net_bridge_vlan, vid), .key_len = sizeof(u16), .nelem_hint = 3, - .locks_mul = 1, .max_size = VLAN_N_VID, .obj_cmpfn = br_vlan_cmp, .automatic_shrinking = true, diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 6d2c4eed2dc8..758151863669 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -34,7 +34,6 @@ static const struct rhashtable_params br_vlan_tunnel_rht_params = { .key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id), .key_len = sizeof(__be64), .nelem_hint = 3, - .locks_mul = 1, .obj_cmpfn = br_vlan_tunid_cmp, .automatic_shrinking = true, }; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2c931120c494..9a3f13edc98e 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -373,7 +373,6 @@ static const struct rhashtable_params ipmr_rht_params = { .key_offset = offsetof(struct mfc_cache, cmparg), .key_len = sizeof(struct mfc_cache_cmp_arg), .nelem_hint = 3, - .locks_mul = 1, .obj_cmpfn = ipmr_hash_cmp, .automatic_shrinking = true, }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e4dd57976737..4e69847ed5be 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -355,7 +355,6 @@ static const struct rhashtable_params ip6mr_rht_params = { .key_offset = offsetof(struct mfc6_cache, cmparg), .key_len = sizeof(struct mfc6_cache_cmp_arg), .nelem_hint = 3, - .locks_mul = 1, .obj_cmpfn = ip6mr_hash_cmp, .automatic_shrinking = true, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ef7772e976cc..90e6b09ef2af 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -53,7 +53,6 @@ static const struct rhashtable_params nft_chain_ht_params = { .hashfn = nft_chain_hash, .obj_hashfn = nft_chain_hash_obj, .obj_cmpfn = nft_chain_hash_cmp, - .locks_mul = 1, .automatic_shrinking = true, }; -- cgit v1.2.3-71-gd317 From 149212f07856b25a9d342bfd6d736519b2ef66dc Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 2 Apr 2019 10:07:45 +1100 Subject: rhashtable: add lockdep tracking to bucket bit-spin-locks. Native bit_spin_locks are not tracked by lockdep. The bit_spin_locks used for rhashtable buckets are local to the rhashtable implementation, so there is little opportunity for the sort of misuse that lockdep might detect. However locks are held while a hash function or compare function is called, and if one of these took a lock, a misbehaviour is possible. As it is quite easy to add lockdep support this unlikely possibility seems to be enough justification. So create a lockdep class for bucket bit_spin_lock and attach through a lockdep_map in each bucket_table. Without the 'nested' annotation in rhashtable_rehash_one(), lockdep correctly reports a possible problem as this lock is taken while another bucket lock (in another table) is held. This confirms that the added support works. With the correct nested annotation in place, lockdep reports no problems. Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 51 ++++++++++++++++++++++++++++++---------------- lib/rhashtable.c | 15 ++++++++------ 2 files changed, 43 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index ccbbafdf5547..460c0eaf6b96 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -82,6 +82,8 @@ struct bucket_table { struct bucket_table __rcu *future_tbl; + struct lockdep_map dep_map; + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; @@ -102,23 +104,38 @@ struct bucket_table { * this is safe. */ -static inline void rht_lock(struct rhash_lock_head **bkt) +static inline void rht_lock(struct bucket_table *tbl, + struct rhash_lock_head **bkt) { local_bh_disable(); bit_spin_lock(1, (unsigned long *)bkt); + lock_map_acquire(&tbl->dep_map); +} + +static inline void rht_lock_nested(struct bucket_table *tbl, + struct rhash_lock_head **bucket, + unsigned int subclass) +{ + local_bh_disable(); + bit_spin_lock(1, (unsigned long *)bucket); + lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); } -static inline void rht_unlock(struct rhash_lock_head **bkt) +static inline void rht_unlock(struct bucket_table *tbl, + struct rhash_lock_head **bkt) { + lock_map_release(&tbl->dep_map); bit_spin_unlock(1, (unsigned long *)bkt); local_bh_enable(); } -static inline void rht_assign_unlock(struct rhash_lock_head **bkt, +static inline void rht_assign_unlock(struct bucket_table *tbl, + struct rhash_lock_head **bkt, struct rhash_head *obj) { struct rhash_head **p = (struct rhash_head **)bkt; + lock_map_release(&tbl->dep_map); rcu_assign_pointer(*p, obj); preempt_enable(); __release(bitlock); @@ -672,11 +689,11 @@ static inline void *__rhashtable_insert_fast( if (!bkt) goto out; pprev = NULL; - rht_lock(bkt); + rht_lock(tbl, bkt); if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: - rht_unlock(bkt); + rht_unlock(tbl, bkt); rcu_read_unlock(); return rhashtable_insert_slow(ht, key, obj); } @@ -708,9 +725,9 @@ slow_path: RCU_INIT_POINTER(list->rhead.next, head); if (pprev) { rcu_assign_pointer(*pprev, obj); - rht_unlock(bkt); + rht_unlock(tbl, bkt); } else - rht_assign_unlock(bkt, obj); + rht_assign_unlock(tbl, bkt, obj); data = NULL; goto out; } @@ -737,7 +754,7 @@ slow_path: } atomic_inc(&ht->nelems); - rht_assign_unlock(bkt, obj); + rht_assign_unlock(tbl, bkt, obj); if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); @@ -749,7 +766,7 @@ out: return data; out_unlock: - rht_unlock(bkt); + rht_unlock(tbl, bkt); goto out; } @@ -951,7 +968,7 @@ static inline int __rhashtable_remove_fast_one( if (!bkt) return -ENOENT; pprev = NULL; - rht_lock(bkt); + rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) { struct rhlist_head *list; @@ -995,14 +1012,14 @@ static inline int __rhashtable_remove_fast_one( if (pprev) { rcu_assign_pointer(*pprev, obj); - rht_unlock(bkt); + rht_unlock(tbl, bkt); } else { - rht_assign_unlock(bkt, obj); + rht_assign_unlock(tbl, bkt, obj); } goto unlocked; } - rht_unlock(bkt); + rht_unlock(tbl, bkt); unlocked: if (err > 0) { atomic_dec(&ht->nelems); @@ -1110,7 +1127,7 @@ static inline int __rhashtable_replace_fast( return -ENOENT; pprev = NULL; - rht_lock(bkt); + rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) { if (he != obj_old) { @@ -1121,15 +1138,15 @@ static inline int __rhashtable_replace_fast( rcu_assign_pointer(obj_new->next, obj_old->next); if (pprev) { rcu_assign_pointer(*pprev, obj_new); - rht_unlock(bkt); + rht_unlock(tbl, bkt); } else { - rht_assign_unlock(bkt, obj_new); + rht_assign_unlock(tbl, bkt, obj_new); } err = 0; goto unlocked; } - rht_unlock(bkt); + rht_unlock(tbl, bkt); unlocked: return err; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index c5d0974467ee..a8583af43b59 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -173,6 +173,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, struct bucket_table *tbl = NULL; size_t size; int i; + static struct lock_class_key __key; size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]); tbl = kvzalloc(size, gfp); @@ -187,6 +188,8 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, if (tbl == NULL) return NULL; + lockdep_init_map(&tbl->dep_map, "rhashtable_bucket", &__key, 0); + tbl->size = size; rcu_head_init(&tbl->rcu); @@ -244,14 +247,14 @@ static int rhashtable_rehash_one(struct rhashtable *ht, new_hash = head_hashfn(ht, new_tbl, entry); - rht_lock(&new_tbl->buckets[new_hash]); + rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING); head = rht_ptr(rht_dereference_bucket(new_tbl->buckets[new_hash], new_tbl, new_hash)); RCU_INIT_POINTER(entry->next, head); - rht_assign_unlock(&new_tbl->buckets[new_hash], entry); + rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry); if (pprev) rcu_assign_pointer(*pprev, next); @@ -272,14 +275,14 @@ static int rhashtable_rehash_chain(struct rhashtable *ht, if (!bkt) return 0; - rht_lock(bkt); + rht_lock(old_tbl, bkt); while (!(err = rhashtable_rehash_one(ht, bkt, old_hash))) ; if (err == -ENOENT) err = 0; - rht_unlock(bkt); + rht_unlock(old_tbl, bkt); return err; } @@ -600,7 +603,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); data = ERR_PTR(-EAGAIN); } else { - rht_lock(bkt); + rht_lock(tbl, bkt); data = rhashtable_lookup_one(ht, bkt, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, bkt, tbl, @@ -608,7 +611,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); - rht_unlock(bkt); + rht_unlock(tbl, bkt); } } while (!IS_ERR_OR_NULL(new_tbl)); -- cgit v1.2.3-71-gd317 From fd69c399c7d6262086b6b820757c6aeaa71feeba Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 8 Apr 2019 10:15:59 +0200 Subject: datagram: remove rendundant 'peeked' argument After commit a297569fe00a ("net/udp: do not touch skb->peeked unless really needed") the 'peeked' argument of __skb_try_recv_datagram() and friends is always equal to !!'flags & MSG_PEEK'. Since such argument is really a boolean info, and the callers have already 'flags & MSG_PEEK' handy, we can remove it and clean-up the code a bit. Signed-off-by: Paolo Abeni Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- include/net/udp.h | 6 +++--- net/core/datagram.c | 19 ++++++++----------- net/ipv4/udp.c | 19 +++++++------------ net/ipv6/udp.c | 10 ++++------ net/unix/af_unix.c | 6 +++--- 6 files changed, 28 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 69b5538adcea..a06275a618f0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3370,17 +3370,17 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err); + int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, diff --git a/include/net/udp.h b/include/net/udp.h index fd6d948755c8..d8ce937bc395 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -269,13 +269,13 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *peeked, int *off, int *err); + int noblock, int *off, int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *err) { - int peeked, off = 0; + int off = 0; - return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err); + return __skb_recv_udp(sk, flags, noblock, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); diff --git a/net/core/datagram.c b/net/core/datagram.c index 91bb5a083fee..45a162ef5e02 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -167,7 +167,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last) { bool peek_at_off = false; @@ -194,7 +194,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, return NULL; } } - *peeked = 1; refcount_inc(&skb->users); } else { __skb_unlink(skb, queue); @@ -212,7 +211,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, * @sk: socket * @flags: MSG\_ flags * @destructor: invoked under the receive lock on successful dequeue - * @peeked: returns non-zero if this packet has been seen before * @off: an offset in bytes to peek skb from. Returns an offset * within an skb where data actually starts * @err: error code returned @@ -246,7 +244,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last) { struct sk_buff_head *queue = &sk->sk_receive_queue; @@ -260,7 +258,6 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, if (error) goto no_packet; - *peeked = 0; do { /* Again only user level code calls this function, so nothing * interrupt level will suddenly eat the receive_queue. @@ -270,7 +267,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, */ spin_lock_irqsave(&queue->lock, cpu_flags); skb = __skb_try_recv_from_queue(sk, queue, flags, destructor, - peeked, off, &error, last); + off, &error, last); spin_unlock_irqrestore(&queue->lock, cpu_flags); if (error) goto no_packet; @@ -294,7 +291,7 @@ EXPORT_SYMBOL(__skb_try_recv_datagram); struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err) + int *off, int *err) { struct sk_buff *skb, *last; long timeo; @@ -302,8 +299,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - skb = __skb_try_recv_datagram(sk, flags, destructor, peeked, - off, err, &last); + skb = __skb_try_recv_datagram(sk, flags, destructor, off, err, + &last); if (skb) return skb; @@ -319,10 +316,10 @@ EXPORT_SYMBOL(__skb_recv_datagram); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int noblock, int *err) { - int peeked, off = 0; + int off = 0; return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - NULL, &peeked, &off, err); + NULL, &off, err); } EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 372fdc5381a9..3c58ba02af7d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1631,7 +1631,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) EXPORT_SYMBOL(udp_ioctl); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *peeked, int *off, int *err) + int noblock, int *off, int *err) { struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff_head *queue; @@ -1650,13 +1650,11 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, break; error = -EAGAIN; - *peeked = 0; do { spin_lock_bh(&queue->lock); skb = __skb_try_recv_from_queue(sk, queue, flags, udp_skb_destructor, - peeked, off, err, - &last); + off, err, &last); if (skb) { spin_unlock_bh(&queue->lock); return skb; @@ -1677,8 +1675,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, skb = __skb_try_recv_from_queue(sk, queue, flags, udp_skb_dtor_locked, - peeked, off, err, - &last); + off, err, &last); spin_unlock(&sk_queue->lock); spin_unlock_bh(&queue->lock); if (skb) @@ -1713,8 +1710,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; unsigned int ulen, copied; - int peeked, peeking, off; - int err; + int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); bool checksum_valid = false; @@ -1722,9 +1718,8 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, return ip_recv_error(sk, msg, len, addr_len); try_again: - peeking = flags & MSG_PEEK; off = sk_peek_offset(sk, flags); - skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err); + skb = __skb_recv_udp(sk, flags, noblock, &off, &err); if (!skb) return err; @@ -1762,7 +1757,7 @@ try_again: } if (unlikely(err)) { - if (!peeked) { + if (!peeking) { atomic_inc(&sk->sk_drops); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); @@ -1771,7 +1766,7 @@ try_again: return err; } - if (!peeked) + if (!peeking) UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b444483cdb2b..d538fafaf4a9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -285,8 +285,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; unsigned int ulen, copied; - int peeked, peeking, off; - int err; + int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); struct udp_mib __percpu *mib; bool checksum_valid = false; @@ -299,9 +298,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: - peeking = flags & MSG_PEEK; off = sk_peek_offset(sk, flags); - skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err); + skb = __skb_recv_udp(sk, flags, noblock, &off, &err); if (!skb) return err; @@ -340,14 +338,14 @@ try_again: goto csum_copy_err; } if (unlikely(err)) { - if (!peeked) { + if (!peeking) { atomic_inc(&sk->sk_drops); SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } kfree_skb(skb); return err; } - if (!peeked) + if (!peeking) SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS); sock_recv_ts_and_drops(msg, sk, skb); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ddb838a1b74c..e68d7454f2e3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2040,8 +2040,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, struct unix_sock *u = unix_sk(sk); struct sk_buff *skb, *last; long timeo; + int skip; int err; - int peeked, skip; err = -EOPNOTSUPP; if (flags&MSG_OOB) @@ -2053,8 +2053,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); - skb = __skb_try_recv_datagram(sk, flags, NULL, &peeked, &skip, - &err, &last); + skb = __skb_try_recv_datagram(sk, flags, NULL, &skip, &err, + &last); if (skb) break; -- cgit v1.2.3-71-gd317 From 3b15d09f7e6db44065aaba5fd16dc7420035c5ad Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Thu, 28 Feb 2019 13:13:26 +0800 Subject: time: Introduce jiffies64_to_msecs() there is a similar helper in net/netfilter/nf_tables_api.c, this maybe become a common request someday, so move it to time.c Signed-off-by: Zhang Yu Signed-off-by: Li RongQing Acked-by: John Stultz Signed-off-by: Pablo Neira Ayuso --- include/linux/jiffies.h | 1 + kernel/time/time.c | 10 ++++++++++ net/netfilter/nf_tables_api.c | 4 +--- 3 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index fa928242567d..1b6d31da7cbc 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -297,6 +297,7 @@ static inline u64 jiffies_to_nsecs(const unsigned long j) } extern u64 jiffies64_to_nsecs(u64 j); +extern u64 jiffies64_to_msecs(u64 j); extern unsigned long __msecs_to_jiffies(const unsigned int m); #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) diff --git a/kernel/time/time.c b/kernel/time/time.c index c3f756f8534b..9e3f79d4f5a8 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -783,6 +783,16 @@ u64 jiffies64_to_nsecs(u64 j) } EXPORT_SYMBOL(jiffies64_to_nsecs); +u64 jiffies64_to_msecs(const u64 j) +{ +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) + return (MSEC_PER_SEC / HZ) * j; +#else + return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); +#endif +} +EXPORT_SYMBOL(jiffies64_to_msecs); + /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 90e6b09ef2af..ee1b0d1445aa 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3193,9 +3193,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) static __be64 nf_jiffies64_to_msecs(u64 input) { - u64 ms = jiffies64_to_nsecs(input); - - return cpu_to_be64(div_u64(ms, NSEC_PER_MSEC)); + return cpu_to_be64(jiffies64_to_msecs(input)); } static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, -- cgit v1.2.3-71-gd317 From 01902f8c85bfde343a4c2b7428d18762442f3a25 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Tue, 26 Mar 2019 20:06:20 +0800 Subject: netfilter: optimize nf_inet_addr_cmp optimize nf_inet_addr_cmp by 64bit xor computation similar to ipv6_addr_equal() Signed-off-by: Yuan Linsi Signed-off-by: Li RongQing Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 72cb19c3db6a..4e0145ea033e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -24,10 +24,17 @@ static inline int NF_DROP_GETERR(int verdict) static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + const unsigned long *ul1 = (const unsigned long *)a1; + const unsigned long *ul2 = (const unsigned long *)a2; + + return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; +#else return a1->all[0] == a2->all[0] && a1->all[1] == a2->all[1] && a1->all[2] == a2->all[2] && a1->all[3] == a2->all[3]; +#endif } static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, -- cgit v1.2.3-71-gd317 From c1deb065cf3b5bcd483e3f03479f930edb151b99 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 27 Mar 2019 09:22:25 +0100 Subject: netfilter: nf_tables: merge route type into core very little code, so it really doesn't make sense to have extra modules or even a kconfig knob for this. Merge them and make functionality available unconditionally. The merge makes inet family route support trivial, so add it as well here. Before: text data bss dec hex filename 835 832 0 1667 683 nft_chain_route_ipv4.ko 870 832 0 1702 6a6 nft_chain_route_ipv6.ko 111568 2556 529 114653 1bfdd nf_tables.ko After: text data bss dec hex filename 113133 2556 529 116218 1c5fa nf_tables.ko Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 15 +++ include/net/netfilter/nf_tables.h | 2 + net/ipv4/netfilter/Kconfig | 8 -- net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/nft_chain_route_ipv4.c | 89 ---------------- net/ipv6/netfilter/Kconfig | 8 -- net/ipv6/netfilter/Makefile | 1 - net/ipv6/netfilter/nft_chain_route_ipv6.c | 91 ---------------- net/netfilter/Makefile | 3 +- net/netfilter/nf_nat_proto.c | 16 +-- net/netfilter/nf_tables_api.c | 2 + net/netfilter/nft_chain_route.c | 169 ++++++++++++++++++++++++++++++ 12 files changed, 191 insertions(+), 214 deletions(-) delete mode 100644 net/ipv4/netfilter/nft_chain_route_ipv4.c delete mode 100644 net/ipv6/netfilter/nft_chain_route_ipv6.c create mode 100644 net/netfilter/nft_chain_route.c (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 471e9467105b..12113e502656 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -87,6 +87,21 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, } int ip6_route_me_harder(struct net *net, struct sk_buff *skb); + +static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return -EHOSTUNREACH; + + return v6_ops->route_me_harder(net, skb); +#else + return ip6_route_me_harder(net, skb); +#endif +} + __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3e9ab643eedf..55dff3ab44c7 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1411,4 +1411,6 @@ struct nft_trans_flowtable { int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); +void __init nft_chain_route_init(void); +void nft_chain_route_fini(void); #endif /* _NET_NF_TABLES_H */ diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index c98391d49200..ea688832fc4e 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -27,14 +27,6 @@ config NF_TABLES_IPV4 if NF_TABLES_IPV4 -config NFT_CHAIN_ROUTE_IPV4 - tristate "IPv4 nf_tables route chain support" - help - This option enables the "route" chain for IPv4 in nf_tables. This - chain type is used to force packet re-routing after mangling header - fields such as the source, destination, type of service and - the packet mark. - config NFT_REJECT_IPV4 select NF_REJECT_IPV4 default NFT_REJECT diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index e241f5188ebe..2cfdda7b109f 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -24,7 +24,6 @@ nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o $(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o -obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c deleted file mode 100644 index 7d82934c46f4..000000000000 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ /dev/null @@ -1,89 +0,0 @@ -/* - * Copyright (c) 2008 Patrick McHardy - * Copyright (c) 2012 Pablo Neira Ayuso - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static unsigned int nf_route_table_hook(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - unsigned int ret; - struct nft_pktinfo pkt; - u32 mark; - __be32 saddr, daddr; - u_int8_t tos; - const struct iphdr *iph; - int err; - - nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv4(&pkt, skb); - - mark = skb->mark; - iph = ip_hdr(skb); - saddr = iph->saddr; - daddr = iph->daddr; - tos = iph->tos; - - ret = nft_do_chain(&pkt, priv); - if (ret != NF_DROP && ret != NF_STOLEN) { - iph = ip_hdr(skb); - - if (iph->saddr != saddr || - iph->daddr != daddr || - skb->mark != mark || - iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); - if (err < 0) - ret = NF_DROP_ERR(err); - } - } - return ret; -} - -static const struct nft_chain_type nft_chain_route_ipv4 = { - .name = "route", - .type = NFT_CHAIN_T_ROUTE, - .family = NFPROTO_IPV4, - .owner = THIS_MODULE, - .hook_mask = (1 << NF_INET_LOCAL_OUT), - .hooks = { - [NF_INET_LOCAL_OUT] = nf_route_table_hook, - }, -}; - -static int __init nft_chain_route_init(void) -{ - nft_register_chain_type(&nft_chain_route_ipv4); - - return 0; -} - -static void __exit nft_chain_route_exit(void) -{ - nft_unregister_chain_type(&nft_chain_route_ipv4); -} - -module_init(nft_chain_route_init); -module_exit(nft_chain_route_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy "); -MODULE_ALIAS_NFT_CHAIN(AF_INET, "route"); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index ddc99a1653aa..3de3adb1a0c9 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -23,14 +23,6 @@ config NF_TABLES_IPV6 if NF_TABLES_IPV6 -config NFT_CHAIN_ROUTE_IPV6 - tristate "IPv6 nf_tables route chain support" - help - This option enables the "route" chain for IPv6 in nf_tables. This - chain type is used to force packet re-routing after mangling header - fields such as the source, destination, flowlabel, hop-limit and - the packet mark. - config NFT_REJECT_IPV6 select NF_REJECT_IPV6 default NFT_REJECT diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 3853c648ebaa..93aff604b243 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -27,7 +27,6 @@ obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o # nf_tables -obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c deleted file mode 100644 index da3f1f8cb325..000000000000 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ /dev/null @@ -1,91 +0,0 @@ -/* - * Copyright (c) 2008 Patrick McHardy - * Copyright (c) 2012 Pablo Neira Ayuso - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Development of this code funded by Astaro AG (http://www.astaro.com/) - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static unsigned int nf_route_table_hook(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - unsigned int ret; - struct nft_pktinfo pkt; - struct in6_addr saddr, daddr; - u_int8_t hop_limit; - u32 mark, flowlabel; - int err; - - nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv6(&pkt, skb); - - /* save source/dest address, mark, hoplimit, flowlabel, priority */ - memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); - memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); - mark = skb->mark; - hop_limit = ipv6_hdr(skb)->hop_limit; - - /* flowlabel and prio (includes version, which shouldn't change either */ - flowlabel = *((u32 *)ipv6_hdr(skb)); - - ret = nft_do_chain(&pkt, priv); - if (ret != NF_DROP && ret != NF_STOLEN && - (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || - memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || - skb->mark != mark || - ipv6_hdr(skb)->hop_limit != hop_limit || - flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(state->net, skb); - if (err < 0) - ret = NF_DROP_ERR(err); - } - - return ret; -} - -static const struct nft_chain_type nft_chain_route_ipv6 = { - .name = "route", - .type = NFT_CHAIN_T_ROUTE, - .family = NFPROTO_IPV6, - .owner = THIS_MODULE, - .hook_mask = (1 << NF_INET_LOCAL_OUT), - .hooks = { - [NF_INET_LOCAL_OUT] = nf_route_table_hook, - }, -}; - -static int __init nft_chain_route_init(void) -{ - nft_register_chain_type(&nft_chain_route_ipv6); - - return 0; -} - -static void __exit nft_chain_route_exit(void) -{ - nft_unregister_chain_type(&nft_chain_route_ipv6); -} - -module_init(nft_chain_route_init); -module_exit(nft_chain_route_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy "); -MODULE_ALIAS_NFT_CHAIN(AF_INET6, "route"); diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 4894a85cdd0b..afbf475e02b2 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -77,7 +77,8 @@ obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ - nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o + nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o \ + nft_chain_route.o nf_tables_set-objs := nf_tables_set_core.o \ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 606d0a740615..84f5c90a7f21 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -926,20 +926,6 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb, return ret; } -static int nat_route_me_harder(struct net *net, struct sk_buff *skb) -{ -#ifdef CONFIG_IPV6_MODULE - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return -EHOSTUNREACH; - - return v6_ops->route_me_harder(net, skb); -#else - return ip6_route_me_harder(net, skb); -#endif -} - static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -959,7 +945,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = nat_route_me_harder(state->net, skb); + err = nf_ip6_route_me_harder(state->net, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2d28b138ed18..a2bd439937e6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7530,6 +7530,7 @@ static int __init nf_tables_module_init(void) if (err < 0) goto err5; + nft_chain_route_init(); return err; err5: rhltable_destroy(&nft_objname_ht); @@ -7549,6 +7550,7 @@ static void __exit nf_tables_module_exit(void) nfnetlink_subsys_unregister(&nf_tables_subsys); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); + nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_destroy_work); rcu_barrier(); diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c new file mode 100644 index 000000000000..8826bbe71136 --- /dev/null +++ b/net/netfilter/nft_chain_route.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_NF_TABLES_IPV4 +static unsigned int nf_route_table_hook4(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + const struct iphdr *iph; + struct nft_pktinfo pkt; + __be32 saddr, daddr; + unsigned int ret; + u32 mark; + int err; + u8 tos; + + nft_set_pktinfo(&pkt, skb, state); + nft_set_pktinfo_ipv4(&pkt, skb); + + mark = skb->mark; + iph = ip_hdr(skb); + saddr = iph->saddr; + daddr = iph->daddr; + tos = iph->tos; + + ret = nft_do_chain(&pkt, priv); + if (ret == NF_ACCEPT) { + iph = ip_hdr(skb); + + if (iph->saddr != saddr || + iph->daddr != daddr || + skb->mark != mark || + iph->tos != tos) { + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + if (err < 0) + ret = NF_DROP_ERR(err); + } + } + return ret; +} + +static const struct nft_chain_type nft_chain_route_ipv4 = { + .name = "route", + .type = NFT_CHAIN_T_ROUTE, + .family = NFPROTO_IPV4, + .hook_mask = (1 << NF_INET_LOCAL_OUT), + .hooks = { + [NF_INET_LOCAL_OUT] = nf_route_table_hook4, + }, +}; +#endif + +#ifdef CONFIG_NF_TABLES_IPV6 +static unsigned int nf_route_table_hook6(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct in6_addr saddr, daddr; + struct nft_pktinfo pkt; + u32 mark, flowlabel; + unsigned int ret; + u8 hop_limit; + int err; + + nft_set_pktinfo(&pkt, skb, state); + nft_set_pktinfo_ipv6(&pkt, skb); + + /* save source/dest address, mark, hoplimit, flowlabel, priority */ + memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); + memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); + mark = skb->mark; + hop_limit = ipv6_hdr(skb)->hop_limit; + + /* flowlabel and prio (includes version, which shouldn't change either)*/ + flowlabel = *((u32 *)ipv6_hdr(skb)); + + ret = nft_do_chain(&pkt, priv); + if (ret == NF_ACCEPT && + (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || + memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit || + flowlabel != *((u32 *)ipv6_hdr(skb)))) { + err = nf_ip6_route_me_harder(state->net, skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } + + return ret; +} + +static const struct nft_chain_type nft_chain_route_ipv6 = { + .name = "route", + .type = NFT_CHAIN_T_ROUTE, + .family = NFPROTO_IPV6, + .hook_mask = (1 << NF_INET_LOCAL_OUT), + .hooks = { + [NF_INET_LOCAL_OUT] = nf_route_table_hook6, + }, +}; +#endif + +#ifdef CONFIG_NF_TABLES_INET +static unsigned int nf_route_table_inet(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nft_pktinfo pkt; + + switch (state->pf) { + case NFPROTO_IPV4: + return nf_route_table_hook4(priv, skb, state); + case NFPROTO_IPV6: + return nf_route_table_hook6(priv, skb, state); + default: + nft_set_pktinfo(&pkt, skb, state); + break; + } + + return nft_do_chain(&pkt, priv); +} + +static const struct nft_chain_type nft_chain_route_inet = { + .name = "route", + .type = NFT_CHAIN_T_ROUTE, + .family = NFPROTO_INET, + .hook_mask = (1 << NF_INET_LOCAL_OUT), + .hooks = { + [NF_INET_LOCAL_OUT] = nf_route_table_inet, + }, +}; +#endif + +void __init nft_chain_route_init(void) +{ +#ifdef CONFIG_NF_TABLES_IPV6 + nft_register_chain_type(&nft_chain_route_ipv6); +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + nft_register_chain_type(&nft_chain_route_ipv4); +#endif +#ifdef CONFIG_NF_TABLES_INET + nft_register_chain_type(&nft_chain_route_inet); +#endif +} + +void __exit nft_chain_route_fini(void) +{ +#ifdef CONFIG_NF_TABLES_IPV6 + nft_unregister_chain_type(&nft_chain_route_ipv6); +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + nft_unregister_chain_type(&nft_chain_route_ipv4); +#endif +#ifdef CONFIG_NF_TABLES_INET + nft_unregister_chain_type(&nft_chain_route_inet); +#endif +} -- cgit v1.2.3-71-gd317 From 4806e975729f99c7908d1688a143f1e16d464e6c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 27 Mar 2019 09:22:26 +0100 Subject: netfilter: replace NF_NAT_NEEDED with IS_ENABLED(CONFIG_NF_NAT) NF_NAT_NEEDED is true whenever nat support for either ipv4 or ipv6 is enabled. Now that the af-specific nat configuration switches have been removed, IS_ENABLED(CONFIG_NF_NAT) has the same effect. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- include/net/netfilter/nf_conntrack_expect.h | 2 +- net/netfilter/Kconfig | 5 ----- net/netfilter/nf_conntrack_expect.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 16 ++++++++-------- net/netfilter/nf_conntrack_sip.c | 2 +- net/openvswitch/conntrack.c | 18 +++++++++--------- 7 files changed, 21 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 4e0145ea033e..a7252f3baeb0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -367,7 +367,7 @@ extern struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_hook *nat_hook; rcu_read_lock(); diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 006e430d1cdf..93ce6b0daaba 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -48,7 +48,7 @@ struct nf_conntrack_expect { /* Expectation class */ unsigned int class; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) union nf_inet_addr saved_addr; /* This is the original per-proto part, used to map the * expected connection the way the recipient expects. */ diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 6548271209a0..f4384c096d0d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -404,11 +404,6 @@ config NF_NAT forms of full Network Address Port Translation. This can be controlled by iptables, ip6tables or nft. -config NF_NAT_NEEDED - bool - depends on NF_NAT - default y - config NF_NAT_AMANDA tristate depends on NF_CONNTRACK && NF_NAT diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 334d6e5b7762..59c18804a10a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -336,7 +336,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, exp->tuple.dst.u.all = *dst; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) memset(&exp->saved_addr, 0, sizeof(exp->saved_addr)); memset(&exp->saved_proto, 0, sizeof(exp->saved_proto)); #endif diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 66c596d287a5..32fe3060375a 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -45,7 +45,7 @@ #include #include #include -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) #include #include #endif @@ -655,7 +655,7 @@ static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif @@ -1494,7 +1494,7 @@ static int ctnetlink_get_ct_unconfirmed(struct net *net, struct sock *ctnl, return -EOPNOTSUPP; } -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) static int ctnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, @@ -1586,7 +1586,7 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) static int ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) int ret; if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) @@ -2369,7 +2369,7 @@ ctnetlink_glue_build_size(const struct nf_conn *ct) + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif @@ -2699,7 +2699,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conn_help *help; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; struct nf_conntrack_tuple nat_tuple = {}; #endif @@ -2717,7 +2717,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, CTA_EXPECT_MASTER) < 0) goto nla_put_failure; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED); @@ -3180,7 +3180,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, struct nf_conntrack_expect *exp, u_int8_t u3) { -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *tb[CTA_EXPECT_NAT_MAX+1]; struct nf_conntrack_tuple nat_tuple = {}; int err; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 39fcc1ed18f3..d5454d1031a3 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -928,7 +928,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, nfct_help(exp->master)->helper != nfct_help(ct)->helper || exp->class != class) break; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) if (!direct_rtp && (!nf_inet_addr_cmp(&exp->saved_addr, &exp->tuple.dst.u3) || exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) && diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 0be3ab5bde26..626629944450 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -29,7 +29,7 @@ #include #include -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) #include #endif @@ -75,7 +75,7 @@ struct ovs_conntrack_info { struct md_mark mark; struct md_labels labels; char timeout[CTNL_TIMEOUT_NAME_MAX]; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */ #endif }; @@ -721,7 +721,7 @@ static bool skb_nfct_cached(struct net *net, return ct_executed; } -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) /* Modelled after nf_nat_ipv[46]_fn(). * range is only used for new, uninitialized NAT state. * Returns either NF_ACCEPT or NF_DROP. @@ -903,7 +903,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, return err; } -#else /* !CONFIG_NF_NAT_NEEDED */ +#else /* !CONFIG_NF_NAT */ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, struct nf_conn *ct, @@ -1330,7 +1330,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, return 0; } -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) static int parse_nat(const struct nlattr *attr, struct ovs_conntrack_info *info, bool log) { @@ -1467,7 +1467,7 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, .maxlen = NF_CT_HELPER_NAME_LEN }, -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) /* NAT length is checked when parsing the nested attributes. */ [OVS_CT_ATTR_NAT] = { .minlen = 0, .maxlen = INT_MAX }, #endif @@ -1547,7 +1547,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, return -EINVAL; } break; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) case OVS_CT_ATTR_NAT: { int err = parse_nat(a, info, log); @@ -1677,7 +1677,7 @@ err_free_ct: return err; } -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, struct sk_buff *skb) { @@ -1783,7 +1783,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, return -EMSGSIZE; } -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb)) return -EMSGSIZE; #endif -- cgit v1.2.3-71-gd317 From 22c7652cdaa8cd33ce78bacceb4e826a3f795873 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 27 Mar 2019 11:36:26 +0100 Subject: netfilter: nft_osf: Add version option support Add version option support to the nftables "osf" expression. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_osf.h | 11 ++++++++--- include/uapi/linux/netfilter/nf_tables.h | 6 ++++++ net/netfilter/nfnetlink_osf.c | 14 +++++++------- net/netfilter/nft_osf.c | 30 +++++++++++++++++++++++++----- 4 files changed, 46 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h index c6000046c966..788613f36935 100644 --- a/include/linux/netfilter/nfnetlink_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -21,13 +21,18 @@ struct nf_osf_finger { struct nf_osf_user_finger finger; }; +struct nf_osf_data { + const char *genre; + const char *version; +}; + bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, int hooknum, struct net_device *in, struct net_device *out, const struct nf_osf_info *info, struct net *net, const struct list_head *nf_osf_fingers); -const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers, - const int ttl_check); +bool nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers, + const int ttl_check, struct nf_osf_data *data); #endif /* _NFOSF_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index a66c8de006cc..061bb3eb20c3 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1522,15 +1522,21 @@ enum nft_flowtable_hook_attributes { * * @NFTA_OSF_DREG: destination register (NLA_U32: nft_registers) * @NFTA_OSF_TTL: Value of the TTL osf option (NLA_U8) + * @NFTA_OSF_FLAGS: flags (NLA_U32) */ enum nft_osf_attributes { NFTA_OSF_UNSPEC, NFTA_OSF_DREG, NFTA_OSF_TTL, + NFTA_OSF_FLAGS, __NFTA_OSF_MAX, }; #define NFTA_OSF_MAX (__NFTA_OSF_MAX - 1) +enum nft_osf_flags { + NFT_OSF_F_VERSION = (1 << 0), +}; + /** * enum nft_device_attributes - nf_tables device netlink attributes * diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 1f1d90c1716b..7b827bcb412c 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -255,9 +255,9 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, } EXPORT_SYMBOL_GPL(nf_osf_match); -const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers, - const int ttl_check) +bool nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers, + const int ttl_check, struct nf_osf_data *data) { const struct iphdr *ip = ip_hdr(skb); const struct nf_osf_user_finger *f; @@ -265,24 +265,24 @@ const char *nf_osf_find(const struct sk_buff *skb, const struct nf_osf_finger *kf; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; - const char *genre = NULL; memset(&ctx, 0, sizeof(ctx)); tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); if (!tcp) - return NULL; + return false; list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) { f = &kf->finger; if (!nf_osf_match_one(skb, f, ttl_check, &ctx)) continue; - genre = f->genre; + data->genre = f->genre; + data->version = f->version; break; } - return genre; + return true; } EXPORT_SYMBOL_GPL(nf_osf_find); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index b13618c764ec..87b60d6617ef 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -7,11 +7,13 @@ struct nft_osf { enum nft_registers dreg:8; u8 ttl; + u32 flags; }; static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = { [NFTA_OSF_DREG] = { .type = NLA_U32 }, [NFTA_OSF_TTL] = { .type = NLA_U8 }, + [NFTA_OSF_FLAGS] = { .type = NLA_U32 }, }; static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, @@ -20,9 +22,10 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nft_osf *priv = nft_expr_priv(expr); u32 *dest = ®s->data[priv->dreg]; struct sk_buff *skb = pkt->skb; + char os_match[NFT_OSF_MAXGENRELEN + 1]; const struct tcphdr *tcp; + struct nf_osf_data data; struct tcphdr _tcph; - const char *os_name; tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); @@ -35,11 +38,17 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, return; } - os_name = nf_osf_find(skb, nf_osf_fingers, priv->ttl); - if (!os_name) + if (!nf_osf_find(skb, nf_osf_fingers, priv->ttl, &data)) { strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN); - else - strncpy((char *)dest, os_name, NFT_OSF_MAXGENRELEN); + } else { + if (priv->flags & NFT_OSF_F_VERSION) + snprintf(os_match, NFT_OSF_MAXGENRELEN, "%s:%s", + data.genre, data.version); + else + strlcpy(os_match, data.genre, NFT_OSF_MAXGENRELEN); + + strncpy((char *)dest, os_match, NFT_OSF_MAXGENRELEN); + } } static int nft_osf_init(const struct nft_ctx *ctx, @@ -47,6 +56,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_osf *priv = nft_expr_priv(expr); + u32 flags; int err; u8 ttl; @@ -57,6 +67,13 @@ static int nft_osf_init(const struct nft_ctx *ctx, priv->ttl = ttl; } + if (tb[NFTA_OSF_FLAGS]) { + flags = ntohl(nla_get_be32(tb[NFTA_OSF_FLAGS])); + if (flags != NFT_OSF_F_VERSION) + return -EINVAL; + priv->flags = flags; + } + priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); err = nft_validate_register_store(ctx, priv->dreg, NULL, NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN); @@ -73,6 +90,9 @@ static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_u8(skb, NFTA_OSF_TTL, priv->ttl)) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_OSF_FLAGS, ntohl(priv->flags))) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg)) goto nla_put_failure; -- cgit v1.2.3-71-gd317 From 3b0a081db1f730373993c7a27936778402a3322c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 4 Apr 2019 10:58:20 +0200 Subject: netfilter: make two functions static They have no external callers anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 1 - include/net/netfilter/nf_tables.h | 2 -- net/netfilter/nf_tables_api.c | 5 ++--- net/netfilter/x_tables.c | 3 +-- 4 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index bf384b3eedb8..1f852ef7b098 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -317,7 +317,6 @@ struct xt_table_info *xt_replace_table(struct xt_table *table, int *error); struct xt_match *xt_find_match(u8 af, const char *name, u8 revision); -struct xt_target *xt_find_target(u8 af, const char *name, u8 revision); struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision); int xt_find_revision(u8 af, const char *name, u8 revision, int target, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 55dff3ab44c7..2d5a0a1a87b8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -475,8 +475,6 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, enum nft_trans_phase phase); int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); -void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding, bool commit); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a2bd439937e6..e058273c5dde 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3782,8 +3782,8 @@ bind: } EXPORT_SYMBOL_GPL(nf_tables_bind_set); -void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding, bool event) +static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); @@ -3794,7 +3794,6 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, GFP_KERNEL); } } -EXPORT_SYMBOL_GPL(nf_tables_unbind_set); void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index e5e5c64df8d1..0a6656ed1534 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -227,7 +227,7 @@ xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision) EXPORT_SYMBOL_GPL(xt_request_find_match); /* Find target, grabs ref. Returns ERR_PTR() on error. */ -struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) +static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) { struct xt_target *t; int err = -ENOENT; @@ -255,7 +255,6 @@ struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) return ERR_PTR(err); } -EXPORT_SYMBOL(xt_find_target); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) { -- cgit v1.2.3-71-gd317 From 3b8b11f96616c2e763ebcc093b778b309fc07a92 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 5 Apr 2019 21:23:13 +0200 Subject: net: phy: improve link partner capability detection genphy_read_status() so far checks phydev->supported, not the actual PHY capabilities. This can make a difference if the supported speeds have been limited by of_set_phy_supported() or phy_set_max_speed(). It seems that this issue only affects the link partner advertisements as displayed by ethtool. Also this patch wouldn't apply to older kernels because linkmode bitmaps have been introduced recently. Therefore net-next. Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 12 ++++++++---- include/linux/phy.h | 2 ++ 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index f7a6d0ffb1ac..dab3ecbb452d 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1756,10 +1756,7 @@ int genphy_read_status(struct phy_device *phydev) linkmode_zero(phydev->lp_advertising); if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { - if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->supported) || - linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->supported)) { + if (phydev->is_gigabit_capable) { lpagb = phy_read(phydev, MII_STAT1000); if (lpagb < 0) return lpagb; @@ -2154,6 +2151,13 @@ static int phy_probe(struct device *dev) if (err) goto out; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + phydev->supported)) + phydev->is_gigabit_capable = 1; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + phydev->supported)) + phydev->is_gigabit_capable = 1; + of_set_phy_supported(phydev); linkmode_copy(phydev->advertising, phydev->supported); diff --git a/include/linux/phy.h b/include/linux/phy.h index ab7439b3da2b..0f9552b17ee7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -345,6 +345,7 @@ struct phy_c45_device_ids { * is_c45: Set to true if this phy uses clause 45 addressing. * is_internal: Set to true if this phy is internal to a MAC. * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. + * is_gigabit_capable: Set to true if PHY supports 1000Mbps * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. @@ -382,6 +383,7 @@ struct phy_device { unsigned is_c45:1; unsigned is_internal:1; unsigned is_pseudo_fixed_link:1; + unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; unsigned sysfs_links:1; -- cgit v1.2.3-71-gd317 From d8eca5bbb2be9bc7546f9e733786fa2f1a594c67 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2019 23:20:03 +0200 Subject: bpf: implement lookup-free direct value access for maps This generic extension to BPF maps allows for directly loading an address residing inside a BPF map value as a single BPF ldimm64 instruction! The idea is similar to what BPF_PSEUDO_MAP_FD does today, which is a special src_reg flag for ldimm64 instruction that indicates that inside the first part of the double insns's imm field is a file descriptor which the verifier then replaces as a full 64bit address of the map into both imm parts. For the newly added BPF_PSEUDO_MAP_VALUE src_reg flag, the idea is the following: the first part of the double insns's imm field is again a file descriptor corresponding to the map, and the second part of the imm field is an offset into the value. The verifier will then replace both imm parts with an address that points into the BPF map value at the given value offset for maps that support this operation. Currently supported is array map with single entry. It is possible to support more than just single map element by reusing both 16bit off fields of the insns as a map index, so full array map lookup could be expressed that way. It hasn't been implemented here due to lack of concrete use case, but could easily be done so in future in a compatible way, since both off fields right now have to be 0 and would correctly denote a map index 0. The BPF_PSEUDO_MAP_VALUE is a distinct flag as otherwise with BPF_PSEUDO_MAP_FD we could not differ offset 0 between load of map pointer versus load of map's value at offset 0, and changing BPF_PSEUDO_MAP_FD's encoding into off by one to differ between regular map pointer and map value pointer would add unnecessary complexity and increases barrier for debugability thus less suitable. Using the second part of the imm field as an offset into the value does /not/ come with limitations since maximum possible value size is in u32 universe anyway. This optimization allows for efficiently retrieving an address to a map value memory area without having to issue a helper call which needs to prepare registers according to calling convention, etc, without needing the extra NULL test, and without having to add the offset in an additional instruction to the value base pointer. The verifier then treats the destination register as PTR_TO_MAP_VALUE with constant reg->off from the user passed offset from the second imm field, and guarantees that this is within bounds of the map value. Any subsequent operations are normally treated as typical map value handling without anything extra needed from verification side. The two map operations for direct value access have been added to array map for now. In future other types could be supported as well depending on the use case. The main use case for this commit is to allow for BPF loader support for global variables that reside in .data/.rodata/.bss sections such that we can directly load the address of them with minimal additional infrastructure required. Loader support has been added in subsequent commits for libbpf library. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 +++ include/linux/bpf_verifier.h | 4 ++ include/uapi/linux/bpf.h | 13 +++++- kernel/bpf/arraymap.c | 32 +++++++++++++++ kernel/bpf/core.c | 3 +- kernel/bpf/disasm.c | 5 ++- kernel/bpf/syscall.c | 28 +++++++++---- kernel/bpf/verifier.c | 86 ++++++++++++++++++++++++++++++--------- tools/bpf/bpftool/xlated_dumper.c | 3 ++ 9 files changed, 149 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a445194b5fb6..bd93a592dd29 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -57,6 +57,12 @@ struct bpf_map_ops { const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); + + /* Direct value access helpers. */ + int (*map_direct_value_addr)(const struct bpf_map *map, + u64 *imm, u32 off); + int (*map_direct_value_meta)(const struct bpf_map *map, + u64 imm, u32 *off); }; struct bpf_map { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index fc8254d6b569..b3ab61fe1932 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -224,6 +224,10 @@ struct bpf_insn_aux_data { unsigned long map_state; /* pointer/poison value for maps */ s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ + struct { + u32 map_index; /* index into used_maps[] */ + u32 map_off; /* offset from value base address */ + }; }; int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 837024512baf..26cfb5b2c964 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -255,8 +255,19 @@ enum bpf_attach_type { */ #define BPF_F_ANY_ALIGNMENT (1U << 1) -/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ +/* When BPF ldimm64's insn[0].src_reg != 0 then this can have + * two extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE + * insn[0].imm: map fd map fd + * insn[1].imm: 0 offset into value + * insn[0].off: 0 0 + * insn[1].off: 0 0 + * ldimm64 rewrite: address of map address of map[0]+offset + * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE + */ #define BPF_PSEUDO_MAP_FD 1 +#define BPF_PSEUDO_MAP_VALUE 2 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c72e0d8e1e65..1a6e9861d554 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -160,6 +160,36 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) return array->value + array->elem_size * (index & array->index_mask); } +static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, + u32 off) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + + if (map->max_entries != 1) + return -ENOTSUPP; + if (off >= map->value_size) + return -EINVAL; + + *imm = (unsigned long)array->value; + return 0; +} + +static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm, + u32 *off) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u64 base = (unsigned long)array->value; + u64 range = array->elem_size; + + if (map->max_entries != 1) + return -ENOTSUPP; + if (imm < base || imm >= base + range) + return -ENOENT; + + *off = imm - base; + return 0; +} + /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { @@ -419,6 +449,8 @@ const struct bpf_map_ops array_map_ops = { .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, .map_gen_lookup = array_map_gen_lookup, + .map_direct_value_addr = array_map_direct_value_addr, + .map_direct_value_meta = array_map_direct_value_meta, .map_seq_show_elem = array_map_seq_show_elem, .map_check_btf = array_map_check_btf, }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2966cb368bf4..ace8c22c8b0e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -292,7 +292,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp) dst[i] = fp->insnsi[i]; if (!was_ld_map && dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && - dst[i].src_reg == BPF_PSEUDO_MAP_FD) { + (dst[i].src_reg == BPF_PSEUDO_MAP_FD || + dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { was_ld_map = true; dst[i].imm = 0; } else if (was_ld_map && diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index de73f55e42fd..d9ce383c0f9c 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -205,10 +205,11 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, * part of the ldimm64 insn is accessible. */ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; + bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD || + insn->src_reg == BPF_PSEUDO_MAP_VALUE; char tmp[64]; - if (map_ptr && !allow_ptr_leaks) + if (is_ptr && !allow_ptr_leaks) imm = 0; verbose(cbs->private_data, "(%02x) r%d = %s\n", diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1d65e56594db..828518bb947b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2072,13 +2072,26 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, - unsigned long addr) + unsigned long addr, u32 *off, + u32 *type) { + const struct bpf_map *map; int i; - for (i = 0; i < prog->aux->used_map_cnt; i++) - if (prog->aux->used_maps[i] == (void *)addr) - return prog->aux->used_maps[i]; + for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { + map = prog->aux->used_maps[i]; + if (map == (void *)addr) { + *type = BPF_PSEUDO_MAP_FD; + return map; + } + if (!map->ops->map_direct_value_meta) + continue; + if (!map->ops->map_direct_value_meta(map, addr, off)) { + *type = BPF_PSEUDO_MAP_VALUE; + return map; + } + } + return NULL; } @@ -2086,6 +2099,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) { const struct bpf_map *map; struct bpf_insn *insns; + u32 off, type; u64 imm; int i; @@ -2113,11 +2127,11 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; - map = bpf_map_from_imm(prog, imm); + map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { - insns[i].src_reg = BPF_PSEUDO_MAP_FD; + insns[i].src_reg = type; insns[i].imm = map->id; - insns[i + 1].imm = 0; + insns[i + 1].imm = off; continue; } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 48718e1da16d..6ab7a23fc924 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5056,18 +5056,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return 0; } -/* return the map pointer stored inside BPF_LD_IMM64 instruction */ -static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn) -{ - u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32; - - return (struct bpf_map *) (unsigned long) imm64; -} - /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { + struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); + struct bpf_map *map; int err; if (BPF_SIZE(insn->code) != BPF_DW) { @@ -5091,11 +5085,22 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } - /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */ - BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD); + map = env->used_maps[aux->map_index]; + mark_reg_known_zero(env, regs, insn->dst_reg); + regs[insn->dst_reg].map_ptr = map; + + if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) { + regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; + regs[insn->dst_reg].off = aux->map_off; + if (map_value_has_spin_lock(map)) + regs[insn->dst_reg].id = ++env->id_gen; + } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + regs[insn->dst_reg].type = CONST_PTR_TO_MAP; + } else { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } - regs[insn->dst_reg].type = CONST_PTR_TO_MAP; - regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn); return 0; } @@ -6803,8 +6808,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { + struct bpf_insn_aux_data *aux; struct bpf_map *map; struct fd f; + u64 addr; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || @@ -6813,13 +6820,19 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) return -EINVAL; } - if (insn->src_reg == 0) + if (insn[0].src_reg == 0) /* valid generic load 64-bit imm */ goto next_insn; - if (insn[0].src_reg != BPF_PSEUDO_MAP_FD || - insn[1].imm != 0) { - verbose(env, "unrecognized bpf_ld_imm64 insn\n"); + /* In final convert_pseudo_ld_imm64() step, this is + * converted into regular 64-bit imm load insn. + */ + if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD && + insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) || + (insn[0].src_reg == BPF_PSEUDO_MAP_FD && + insn[1].imm != 0)) { + verbose(env, + "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } @@ -6837,16 +6850,47 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) return err; } - /* store map pointer inside BPF_LD_IMM64 instruction */ - insn[0].imm = (u32) (unsigned long) map; - insn[1].imm = ((u64) (unsigned long) map) >> 32; + aux = &env->insn_aux_data[i]; + if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + addr = (unsigned long)map; + } else { + u32 off = insn[1].imm; + + if (off >= BPF_MAX_VAR_OFF) { + verbose(env, "direct value offset of %u is not allowed\n", off); + fdput(f); + return -EINVAL; + } + + if (!map->ops->map_direct_value_addr) { + verbose(env, "no direct value access support for this map type\n"); + fdput(f); + return -EINVAL; + } + + err = map->ops->map_direct_value_addr(map, &addr, off); + if (err) { + verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", + map->value_size, off); + fdput(f); + return err; + } + + aux->map_off = off; + addr += off; + } + + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; /* check whether we recorded this map already */ - for (j = 0; j < env->used_map_cnt; j++) + for (j = 0; j < env->used_map_cnt; j++) { if (env->used_maps[j] == map) { + aux->map_index = j; fdput(f); goto next_insn; } + } if (env->used_map_cnt >= MAX_USED_MAPS) { fdput(f); @@ -6863,6 +6907,8 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) fdput(f); return PTR_ERR(map); } + + aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 7073dbe1ff27..0bb17bf88b18 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -195,6 +195,9 @@ static const char *print_imm(void *private_data, if (insn->src_reg == BPF_PSEUDO_MAP_FD) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "map[id:%u]", insn->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm); else snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "0x%llx", (unsigned long long)full_imm); -- cgit v1.2.3-71-gd317 From 591fe9888d7809d9ee5c828020b6c6ae27c37229 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2019 23:20:05 +0200 Subject: bpf: add program side {rd, wr}only support for maps This work adds two new map creation flags BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG in order to allow for read-only or write-only BPF maps from a BPF program side. Today we have BPF_F_RDONLY and BPF_F_WRONLY, but this only applies to system call side, meaning the BPF program has full read/write access to the map as usual while bpf(2) calls with map fd can either only read or write into the map depending on the flags. BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG allows for the exact opposite such that verifier is going to reject program loads if write into a read-only map or a read into a write-only map is detected. For read-only map case also some helpers are forbidden for programs that would alter the map state such as map deletion, update, etc. As opposed to the two BPF_F_RDONLY / BPF_F_WRONLY flags, BPF_F_RDONLY_PROG as well as BPF_F_WRONLY_PROG really do correspond to the map lifetime. We've enabled this generic map extension to various non-special maps holding normal user data: array, hash, lru, lpm, local storage, queue and stack. Further generic map types could be followed up in future depending on use-case. Main use case here is to forbid writes into .rodata map values from verifier side. Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 29 +++++++++++++++++++++++++++ include/uapi/linux/bpf.h | 6 +++++- kernel/bpf/arraymap.c | 6 +++++- kernel/bpf/hashtab.c | 6 +++--- kernel/bpf/local_storage.c | 6 +++--- kernel/bpf/lpm_trie.c | 3 ++- kernel/bpf/queue_stack_maps.c | 6 +++--- kernel/bpf/syscall.c | 2 ++ kernel/bpf/verifier.c | 46 +++++++++++++++++++++++++++++++++++++++++-- 9 files changed, 96 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bd93a592dd29..be20804631b5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -430,6 +430,35 @@ struct bpf_array { #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 32 +#define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ + BPF_F_RDONLY_PROG | \ + BPF_F_WRONLY | \ + BPF_F_WRONLY_PROG) + +#define BPF_MAP_CAN_READ BIT(0) +#define BPF_MAP_CAN_WRITE BIT(1) + +static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) +{ + u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); + + /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is + * not possible. + */ + if (access_flags & BPF_F_RDONLY_PROG) + return BPF_MAP_CAN_READ; + else if (access_flags & BPF_F_WRONLY_PROG) + return BPF_MAP_CAN_WRITE; + else + return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE; +} + +static inline bool bpf_map_flags_access_ok(u32 access_flags) +{ + return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) != + (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); +} + struct bpf_event_entry { struct perf_event *event; struct file *perf_file; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 26cfb5b2c964..d275446d807c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -294,7 +294,7 @@ enum bpf_attach_type { #define BPF_OBJ_NAME_LEN 16U -/* Flags for accessing BPF object */ +/* Flags for accessing BPF object from syscall side. */ #define BPF_F_RDONLY (1U << 3) #define BPF_F_WRONLY (1U << 4) @@ -304,6 +304,10 @@ enum bpf_attach_type { /* Zero-initialize hash function seed. This should only be used for testing. */ #define BPF_F_ZERO_SEED (1U << 6) +/* Flags for accessing BPF object from program side. */ +#define BPF_F_RDONLY_PROG (1U << 7) +#define BPF_F_WRONLY_PROG (1U << 8) + /* flags for BPF_PROG_QUERY */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 1a6e9861d554..217b10bd9f48 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -22,7 +22,7 @@ #include "map_in_map.h" #define ARRAY_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) static void bpf_array_free_percpu(struct bpf_array *array) { @@ -63,6 +63,7 @@ int array_map_alloc_check(union bpf_attr *attr) if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size == 0 || attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || (percpu && numa_node != NUMA_NO_NODE)) return -EINVAL; @@ -472,6 +473,9 @@ static int fd_array_map_alloc_check(union bpf_attr *attr) /* only file descriptors can be stored in this type of map */ if (attr->value_size != sizeof(u32)) return -EINVAL; + /* Program read-only/write-only not supported for special maps yet. */ + if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) + return -EINVAL; return array_map_alloc_check(attr); } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index fed15cf94dca..192d32e77db3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -23,7 +23,7 @@ #define HTAB_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ - BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED) + BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED) struct bucket { struct hlist_nulls_head head; @@ -262,8 +262,8 @@ static int htab_map_alloc_check(union bpf_attr *attr) /* Guard against local DoS, and discourage production use. */ return -EPERM; - if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) - /* reserved bits should not be used */ + if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags)) return -EINVAL; if (!lru && percpu_lru) diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 6b572e2de7fb..980e8f1f6cb5 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -14,7 +14,7 @@ DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STO #ifdef CONFIG_CGROUP_BPF #define LOCAL_STORAGE_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) struct bpf_cgroup_storage_map { struct bpf_map map; @@ -282,8 +282,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) if (attr->value_size > PAGE_SIZE) return ERR_PTR(-E2BIG); - if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK) - /* reserved bits should not be used */ + if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags)) return ERR_PTR(-EINVAL); if (attr->max_entries) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 93a5cbbde421..e61630c2e50b 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -538,7 +538,7 @@ out: #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) #define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ - BPF_F_RDONLY | BPF_F_WRONLY) + BPF_F_ACCESS_MASK) static struct bpf_map *trie_alloc(union bpf_attr *attr) { @@ -553,6 +553,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) if (attr->max_entries == 0 || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->map_flags & ~LPM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index b384ea9f3254..0b140d236889 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -11,8 +11,7 @@ #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) - + (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) struct bpf_queue_stack { struct bpf_map map; @@ -52,7 +51,8 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || attr->value_size == 0 || - attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) + attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags)) return -EINVAL; if (attr->value_size > KMALLOC_MAX_SIZE) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 56b4b0e08b3b..0c9276b54c88 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -501,6 +501,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, map->spin_lock_off = btf_find_spin_lock(btf, value_type); if (map_value_has_spin_lock(map)) { + if (map->map_flags & BPF_F_RDONLY_PROG) + return -EACCES; if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6ab7a23fc924..b747434df89c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1439,6 +1439,28 @@ static int check_stack_access(struct bpf_verifier_env *env, return 0; } +static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, + int off, int size, enum bpf_access_type type) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_map *map = regs[regno].map_ptr; + u32 cap = bpf_map_flags_to_cap(map); + + if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) { + verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n", + map->value_size, off, size); + return -EACCES; + } + + if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) { + verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n", + map->value_size, off, size); + return -EACCES; + } + + return 0; +} + /* check read/write into map element returned by bpf_map_lookup_elem() */ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) @@ -2024,7 +2046,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } - + err = check_map_access_type(env, regno, off, size, t); + if (err) + return err; err = check_map_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); @@ -2327,6 +2351,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_VALUE: + if (check_map_access_type(env, regno, reg->off, access_size, + meta && meta->raw_mode ? BPF_WRITE : + BPF_READ)) + return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed); default: /* scalar_value|ptr_to_stack or invalid ptr */ @@ -3059,6 +3087,7 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; + struct bpf_map *map = meta->map_ptr; if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && @@ -3069,11 +3098,24 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, func_id != BPF_FUNC_map_peek_elem) return 0; - if (meta->map_ptr == NULL) { + if (map == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } + /* In case of read-only, some additional restrictions + * need to be applied in order to prevent altering the + * state of the map from program side. + */ + if ((map->map_flags & BPF_F_RDONLY_PROG) && + (func_id == BPF_FUNC_map_delete_elem || + func_id == BPF_FUNC_map_update_elem || + func_id == BPF_FUNC_map_push_elem || + func_id == BPF_FUNC_map_pop_elem)) { + verbose(env, "write into map forbidden\n"); + return -EACCES; + } + if (!BPF_MAP_PTR(aux->map_state)) bpf_map_ptr_store(aux, meta->map_ptr, meta->map_ptr->unpriv_array); -- cgit v1.2.3-71-gd317 From 87df15de441bd4add7876ef584da8cabdd9a042a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2019 23:20:06 +0200 Subject: bpf: add syscall side map freeze support This patch adds a new BPF_MAP_FREEZE command which allows to "freeze" the map globally as read-only / immutable from syscall side. Map permission handling has been refactored into map_get_sys_perms() and drops FMODE_CAN_WRITE in case of locked map. Main use case is to allow for setting up .rodata sections from the BPF ELF which are loaded into the kernel, meaning BPF loader first allocates map, sets up map value by copying .rodata section into it and once complete, it calls BPF_MAP_FREEZE on the map fd to prevent further modifications. Right now BPF_MAP_FREEZE only takes map fd as argument while remaining bpf_attr members are required to be zero. I didn't add write-only locking here as counterpart since I don't have a concrete use-case for it on my side, and I think it makes probably more sense to wait once there is actually one. In that case bpf_attr can be extended as usual with a flag field and/or others where flag 0 means that we lock the map read-only hence this doesn't prevent to add further extensions to BPF_MAP_FREEZE upon need. A map creation flag like BPF_F_WRONCE was not considered for couple of reasons: i) in case of a generic implementation, a map can consist of more than just one element, thus there could be multiple map updates needed to set the map into a state where it can then be made immutable, ii) WRONCE indicates exact one-time write before it is then set immutable. A generic implementation would set a bit atomically on map update entry (if unset), indicating that every subsequent update from then onwards will need to bail out there. However, map updates can fail, so upon failure that flag would need to be unset again and the update attempt would need to be repeated for it to be eventually made immutable. While this can be made race-free, this approach feels less clean and in combination with reason i), it's not generic enough. A dedicated BPF_MAP_FREEZE command directly sets the flag and caller has the guarantee that map is immutable from syscall side upon successful return for any future syscall invocations that would alter the map state, which is also more intuitive from an API point of view. A command name such as BPF_MAP_LOCK has been avoided as it's too close with BPF map spin locks (which already has BPF_F_LOCK flag). BPF_MAP_FREEZE is so far only enabled for privileged users. Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 ++- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 66 +++++++++++++++++++++++++++++++++++++++--------- 3 files changed, 57 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be20804631b5..65f7094c40b4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -87,7 +87,8 @@ struct bpf_map { struct btf *btf; u32 pages; bool unpriv_array; - /* 51 bytes hole */ + bool frozen; /* write-once */ + /* 48 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d275446d807c..af1cbd951f26 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -105,6 +105,7 @@ enum bpf_cmd { BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, BPF_MAP_LOOKUP_AND_DELETE_ELEM, + BPF_MAP_FREEZE, }; enum bpf_map_type { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0c9276b54c88..b3ce516e5a20 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -355,6 +355,18 @@ static int bpf_map_release(struct inode *inode, struct file *filp) return 0; } +static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) +{ + fmode_t mode = f.file->f_mode; + + /* Our file permissions may have been overridden by global + * map permissions facing syscall side. + */ + if (READ_ONCE(map->frozen)) + mode &= ~FMODE_CAN_WRITE; + return mode; +} + #ifdef CONFIG_PROC_FS static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { @@ -376,14 +388,16 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "max_entries:\t%u\n" "map_flags:\t%#x\n" "memlock:\t%llu\n" - "map_id:\t%u\n", + "map_id:\t%u\n" + "frozen:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, map->pages * 1ULL << PAGE_SHIFT, - map->id); + map->id, + READ_ONCE(map->frozen)); if (owner_prog_type) { seq_printf(m, "owner_prog_type:\t%u\n", @@ -727,8 +741,7 @@ static int map_lookup_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_READ)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } @@ -857,8 +870,7 @@ static int map_update_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -969,8 +981,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -1021,8 +1032,7 @@ static int map_get_next_key(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_READ)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } @@ -1089,8 +1099,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -1132,6 +1141,36 @@ err_put: return err; } +#define BPF_MAP_FREEZE_LAST_FIELD map_fd + +static int map_freeze(const union bpf_attr *attr) +{ + int err = 0, ufd = attr->map_fd; + struct bpf_map *map; + struct fd f; + + if (CHECK_ATTR(BPF_MAP_FREEZE)) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + if (READ_ONCE(map->frozen)) { + err = -EBUSY; + goto err_put; + } + if (!capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto err_put; + } + + WRITE_ONCE(map->frozen, true); +err_put: + fdput(f); + return err; +} + static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name) \ [_id] = & _name ## _prog_ops, @@ -2735,6 +2774,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); break; + case BPF_MAP_FREEZE: + err = map_freeze(&attr); + break; case BPF_PROG_LOAD: err = bpf_prog_load(&attr, uattr); break; -- cgit v1.2.3-71-gd317 From 2824ecb7010f6a20e9a4140512b798469ab066cc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2019 23:20:10 +0200 Subject: bpf: allow for key-less BTF in array map Given we'll be reusing BPF array maps for global data/bss/rodata sections, we need a way to associate BTF DataSec type as its map value type. In usual cases we have this ugly BPF_ANNOTATE_KV_PAIR() macro hack e.g. via 38d5d3b3d5db ("bpf: Introduce BPF_ANNOTATE_KV_PAIR") to get initial map to type association going. While more use cases for it are discouraged, this also won't work for global data since the use of array map is a BPF loader detail and therefore unknown at compilation time. For array maps with just a single entry we make an exception in terms of BTF in that key type is declared optional if value type is of DataSec type. The latter LLVM is guaranteed to emit and it also aligns with how we regard global data maps as just a plain buffer area reusing existing map facilities for allowing things like introspection with existing tools. Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 1 + kernel/bpf/arraymap.c | 15 ++++++++++++++- kernel/bpf/btf.c | 2 +- kernel/bpf/syscall.c | 15 +++++++++++---- 4 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 455d31b55828..64cdf2a23d42 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -51,6 +51,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); +bool btf_type_is_void(const struct btf_type *t); #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 217b10bd9f48..584636c9e2eb 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -391,7 +391,8 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, return; } - seq_printf(m, "%u: ", *(u32 *)key); + if (map->btf_key_type_id) + seq_printf(m, "%u: ", *(u32 *)key); btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); seq_puts(m, "\n"); @@ -428,6 +429,18 @@ static int array_map_check_btf(const struct bpf_map *map, { u32 int_data; + /* One exception for keyless BTF: .bss/.data/.rodata map */ + if (btf_type_is_void(key_type)) { + if (map->map_type != BPF_MAP_TYPE_ARRAY || + map->max_entries != 1) + return -EINVAL; + + if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC) + return -EINVAL; + + return 0; + } + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) return -EINVAL; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 0cecf6bab61b..cad09858a5f2 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -326,7 +326,7 @@ static bool btf_type_is_modifier(const struct btf_type *t) return false; } -static bool btf_type_is_void(const struct btf_type *t) +bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 198c9680bf0d..438199e2eca4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -504,9 +504,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 key_size, value_size; int ret = 0; - key_type = btf_type_id_size(btf, &btf_key_id, &key_size); - if (!key_type || key_size != map->key_size) - return -EINVAL; + /* Some maps allow key to be unspecified. */ + if (btf_key_id) { + key_type = btf_type_id_size(btf, &btf_key_id, &key_size); + if (!key_type || key_size != map->key_size) + return -EINVAL; + } else { + key_type = btf_type_by_id(btf, 0); + if (!map->ops->map_check_btf) + return -EINVAL; + } value_type = btf_type_id_size(btf, &btf_value_id, &value_size); if (!value_type || value_size != map->value_size) @@ -573,7 +580,7 @@ static int map_create(union bpf_attr *attr) if (attr->btf_key_type_id || attr->btf_value_type_id) { struct btf *btf; - if (!attr->btf_key_type_id || !attr->btf_value_type_id) { + if (!attr->btf_value_type_id) { err = -EINVAL; goto free_map_nouncharge; } -- cgit v1.2.3-71-gd317 From b6d9ccb1125049941590ea895c38e1167badba5f Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Thu, 28 Mar 2019 15:27:31 +0200 Subject: net/mlx5: E-Switch, don't use hardcoded values for FDB prios When creating the FDB prios, use the enum values already defined and not the hardcoded values. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 5 ----- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 5 +++-- include/linux/mlx5/fs.h | 5 +++++ 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1496e82b5108..8a214ada2424 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -41,11 +41,6 @@ #include "fs_core.h" #include "lib/devcom.h" -enum { - FDB_FAST_PATH = 0, - FDB_SLOW_PATH -}; - /* There are two match-all miss flows, one for unicast dst mac and * one for multicast. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 8d199c5e7c81..8b96f71332d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2479,7 +2479,8 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) return -ENOMEM; levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1); - maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, 0, + maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, + FDB_FAST_PATH, levels); if (IS_ERR(maj_prio)) { err = PTR_ERR(maj_prio); @@ -2504,7 +2505,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) steering->fdb_sub_ns[chain] = ns; } - maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, 1, 1); + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1); if (IS_ERR(maj_prio)) { err = PTR_ERR(maj_prio); goto out_err; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 9df51da04621..3eeb04154317 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -75,6 +75,11 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_EGRESS, }; +enum { + FDB_FAST_PATH, + FDB_SLOW_PATH, +}; + struct mlx5_flow_table; struct mlx5_flow_group; struct mlx5_flow_namespace; -- cgit v1.2.3-71-gd317 From d9cb06759eca5a420072b937d2a2a670db474008 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Thu, 28 Mar 2019 15:27:32 +0200 Subject: net/mlx5: E-Switch, add a new prio to be used by the RDMA side Create a new prio in the FDB, it will be used when inserting steering rules into the FDB from the RDMA side. We create a new PRIO so rules from the net side and rules from the RDMA side won't be inserted to the same PRIO, each side has it's own sandbox to play in. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 7 +++++++ include/linux/mlx5/fs.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 8b96f71332d8..72d42cc3487a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2478,6 +2478,13 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) if (!steering->fdb_sub_ns) return -ENOMEM; + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH, + 1); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1); maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, FDB_FAST_PATH, diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 3eeb04154317..fd91df3a4e09 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -76,6 +76,7 @@ enum mlx5_flow_namespace_type { }; enum { + FDB_BYPASS_PATH, FDB_FAST_PATH, FDB_SLOW_PATH, }; -- cgit v1.2.3-71-gd317 From c695865c5c9803f14eef2c99d8a49d9ad60a3383 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 11 Apr 2019 09:12:02 -0700 Subject: bpf: fix missing bpf_check_uarg_tail_zero in BPF_PROG_TEST_RUN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit b0b9395d865e ("bpf: support input __sk_buff context in BPF_PROG_TEST_RUN") started using bpf_check_uarg_tail_zero in BPF_PROG_TEST_RUN. However, bpf_check_uarg_tail_zero is not defined for !CONFIG_BPF_SYSCALL: net/bpf/test_run.c: In function ‘bpf_ctx_init’: net/bpf/test_run.c:142:9: error: implicit declaration of function ‘bpf_check_uarg_tail_zero’ [-Werror=implicit-function-declaration] err = bpf_check_uarg_tail_zero(data_in, max_size, size); ^~~~~~~~~~~~~~~~~~~~~~~~ Let's not build net/bpf/test_run.c when CONFIG_BPF_SYSCALL is not set. Reported-by: kbuild test robot Fixes: b0b9395d865e ("bpf: support input __sk_buff context in BPF_PROG_TEST_RUN") Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 36 ++++++++++++++++++++++++++++-------- net/bpf/Makefile | 2 +- 2 files changed, 29 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 65f7094c40b4..e4d4c1771ab0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -483,14 +483,6 @@ typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); -int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); -int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); -int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, - const union bpf_attr *kattr, - union bpf_attr __user *uattr); - /* an array of programs to be executed under rcu_lock. * * Typical usage: @@ -681,6 +673,13 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); int array_map_alloc_check(union bpf_attr *attr); +int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -792,6 +791,27 @@ static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, { return ERR_PTR(-EOPNOTSUPP); } + +static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + +static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + +static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, diff --git a/net/bpf/Makefile b/net/bpf/Makefile index 27b2992a0692..b0ca361742e4 100644 --- a/net/bpf/Makefile +++ b/net/bpf/Makefile @@ -1 +1 @@ -obj-y := test_run.o +obj-$(CONFIG_BPF_SYSCALL) := test_run.o -- cgit v1.2.3-71-gd317 From 223fd0adfa8af36d5d9b5d38016e579ee052f367 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 Apr 2019 16:36:42 +0200 Subject: bridge: broute: make broute a real ebtables table This makes broute a normal ebtables table, hooking at PREROUTING. The broute hook is removed. It uses skb->cb to signal to bridge rx handler that the skb should be routed instead of being bridged. This change is backwards compatible with ebtables as no userspace visible parts are changed. This means we can also remove the !ops test in ebt_register_table, it was only there for broute table sake. Signed-off-by: Florian Westphal Acked-by: David S. Miller Acked-by: Nikolay Aleksandrov Signed-off-by: Pablo Neira Ayuso --- include/linux/if_bridge.h | 3 -- net/bridge/br_input.c | 18 +++------- net/bridge/br_private.h | 3 ++ net/bridge/netfilter/ebtable_broute.c | 63 ++++++++++++++++++++++++----------- net/bridge/netfilter/ebtables.c | 7 +--- 5 files changed, 52 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 627b788ba0ff..ef0819ced0fc 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -56,9 +56,6 @@ struct br_ip_list { extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); -typedef int br_should_route_hook_t(struct sk_buff *skb); -extern br_should_route_hook_t __rcu *br_should_route_hook; - #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING) int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 4ac34fb5f943..e0aacfedcfe1 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -24,10 +24,6 @@ #include "br_private.h" #include "br_private_tunnel.h" -/* Hook for brouter */ -br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; -EXPORT_SYMBOL(br_should_route_hook); - static int br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -234,6 +230,10 @@ static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb) verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state); switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: + if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) { + *pskb = skb; + return RX_HANDLER_PASS; + } break; case NF_DROP: kfree_skb(skb); @@ -265,7 +265,6 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) struct net_bridge_port *p; struct sk_buff *skb = *pskb; const unsigned char *dest = eth_hdr(skb)->h_dest; - br_should_route_hook_t *rhook; if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; @@ -341,15 +340,6 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) forward: switch (p->state) { case BR_STATE_FORWARDING: - rhook = rcu_dereference(br_should_route_hook); - if (rhook) { - if ((*rhook)(skb)) { - *pskb = skb; - return RX_HANDLER_PASS; - } - dest = eth_hdr(skb)->h_dest; - } - /* fall through */ case BR_STATE_LEARNING: if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e7110a6e2b7e..4bea2f11da9b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -433,6 +433,9 @@ struct br_input_skb_cb { #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_filtered:1; #endif +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + u8 br_netfilter_broute:1; +#endif #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 276b60262981..ec2652a459da 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -15,6 +15,8 @@ #include #include +#include "../br_private.h" + /* EBT_ACCEPT means the frame will be bridged * EBT_DROP means the frame will be routed */ @@ -48,30 +50,63 @@ static const struct ebt_table broute_table = { .me = THIS_MODULE, }; -static int ebt_broute(struct sk_buff *skb) +static unsigned int ebt_broute(void *priv, struct sk_buff *skb, + const struct nf_hook_state *s) { + struct net_bridge_port *p = br_port_get_rcu(skb->dev); struct nf_hook_state state; + unsigned char *dest; int ret; + if (!p || p->state != BR_STATE_FORWARDING) + return NF_ACCEPT; + nf_hook_state_init(&state, NF_BR_BROUTING, - NFPROTO_BRIDGE, skb->dev, NULL, NULL, - dev_net(skb->dev), NULL); + NFPROTO_BRIDGE, s->in, NULL, NULL, + s->net, NULL); ret = ebt_do_table(skb, &state, state.net->xt.broute_table); - if (ret == NF_DROP) - return 1; /* route it */ - return 0; /* bridge it */ + + if (ret != NF_DROP) + return ret; + + /* DROP in ebtables -t broute means that the + * skb should be routed, not bridged. + * This is awkward, but can't be changed for compatibility + * reasons. + * + * We map DROP to ACCEPT and set the ->br_netfilter_broute flag. + */ + BR_INPUT_SKB_CB(skb)->br_netfilter_broute = 1; + + /* undo PACKET_HOST mangling done in br_input in case the dst + * address matches the logical bridge but not the port. + */ + dest = eth_hdr(skb)->h_dest; + if (skb->pkt_type == PACKET_HOST && + !ether_addr_equal(skb->dev->dev_addr, dest) && + ether_addr_equal(p->br->dev->dev_addr, dest)) + skb->pkt_type = PACKET_OTHERHOST; + + return NF_ACCEPT; } +static const struct nf_hook_ops ebt_ops_broute = { + .hook = ebt_broute, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_PRE_ROUTING, + .priority = NF_BR_PRI_FIRST, +}; + static int __net_init broute_net_init(struct net *net) { - return ebt_register_table(net, &broute_table, NULL, + return ebt_register_table(net, &broute_table, &ebt_ops_broute, &net->xt.broute_table); } static void __net_exit broute_net_exit(struct net *net) { - ebt_unregister_table(net, net->xt.broute_table, NULL); + ebt_unregister_table(net, net->xt.broute_table, &ebt_ops_broute); } static struct pernet_operations broute_net_ops = { @@ -81,21 +116,11 @@ static struct pernet_operations broute_net_ops = { static int __init ebtable_broute_init(void) { - int ret; - - ret = register_pernet_subsys(&broute_net_ops); - if (ret < 0) - return ret; - /* see br_input.c */ - RCU_INIT_POINTER(br_should_route_hook, - (br_should_route_hook_t *)ebt_broute); - return 0; + return register_pernet_subsys(&broute_net_ops); } static void __exit ebtable_broute_fini(void) { - RCU_INIT_POINTER(br_should_route_hook, NULL); - synchronize_net(); unregister_pernet_subsys(&broute_net_ops); } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index eb15891f8b9f..383f0328ff68 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1221,10 +1221,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, mutex_unlock(&ebt_mutex); WRITE_ONCE(*res, table); - - if (!ops) - return 0; - ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret) { __ebt_unregister_table(net, table); @@ -1248,8 +1244,7 @@ out: void ebt_unregister_table(struct net *net, struct ebt_table *table, const struct nf_hook_ops *ops) { - if (ops) - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); __ebt_unregister_table(net, table); } -- cgit v1.2.3-71-gd317 From 7b146cebe30cb481b0f70d85779da938da818637 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 27 Feb 2019 12:59:24 -0800 Subject: bpf: Sysctl hook Containerized applications may run as root and it may create problems for whole host. Specifically such applications may change a sysctl and affect applications in other containers. Furthermore in existing infrastructure it may not be possible to just completely disable writing to sysctl, instead such a process should be gradual with ability to log what sysctl are being changed by a container, investigate, limit the set of writable sysctl to currently used ones (so that new ones can not be changed) and eventually reduce this set to zero. The patch introduces new program type BPF_PROG_TYPE_CGROUP_SYSCTL and attach type BPF_CGROUP_SYSCTL to solve these problems on cgroup basis. New program type has access to following minimal context: struct bpf_sysctl { __u32 write; }; Where @write indicates whether sysctl is being read (= 0) or written (= 1). Helpers to access sysctl name and value will be introduced separately. BPF_CGROUP_SYSCTL attach point is added to sysctl code right before passing control to ctl_table->proc_handler so that BPF program can either allow or deny access to sysctl. Suggested-by: Roman Gushchin Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- fs/proc/proc_sysctl.c | 5 +++ include/linux/bpf-cgroup.h | 18 +++++++++ include/linux/bpf_types.h | 1 + include/linux/filter.h | 8 ++++ include/uapi/linux/bpf.h | 9 +++++ kernel/bpf/cgroup.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 7 ++++ kernel/bpf/verifier.c | 1 + 8 files changed, 141 insertions(+) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d65390727541..e01b02150340 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" static const struct dentry_operations proc_sys_dentry_operations; @@ -588,6 +589,10 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, if (!table->proc_handler) goto out; + error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write); + if (error) + goto out; + /* careful: calling conventions are nasty here */ res = count; error = table->proc_handler(table, write, buf, &res, ppos); diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a4c644c1c091..b1c45da20a26 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -17,6 +17,8 @@ struct bpf_map; struct bpf_prog; struct bpf_sock_ops_kern; struct bpf_cgroup_storage; +struct ctl_table; +struct ctl_table_header; #ifdef CONFIG_CGROUP_BPF @@ -109,6 +111,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, + struct ctl_table *table, int write, + enum bpf_attach_type type); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -253,6 +259,17 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, \ __ret; \ }) + + +#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ + BPF_CGROUP_SYSCTL); \ + __ret; \ +}) + int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, @@ -321,6 +338,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 08bf2f1fe553..d26991a16894 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -28,6 +28,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) #endif #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) #endif #ifdef CONFIG_BPF_LIRC_MODE2 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) diff --git a/include/linux/filter.h b/include/linux/filter.h index 6074aa064b54..a17732057880 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -33,6 +33,8 @@ struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; +struct ctl_table; +struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function @@ -1177,4 +1179,10 @@ struct bpf_sock_ops_kern { */ }; +struct bpf_sysctl_kern { + struct ctl_table_header *head; + struct ctl_table *table; + int write; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2e96d0b4bf65..cc2a2466d5f3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -167,6 +167,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LIRC_MODE2, BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_PROG_TYPE_CGROUP_SYSCTL, }; enum bpf_attach_type { @@ -188,6 +189,7 @@ enum bpf_attach_type { BPF_CGROUP_UDP6_SENDMSG, BPF_LIRC_MODE2, BPF_FLOW_DISSECTOR, + BPF_CGROUP_SYSCTL, __MAX_BPF_ATTACH_TYPE }; @@ -3308,4 +3310,11 @@ struct bpf_line_info { struct bpf_spin_lock { __u32 val; }; + +struct bpf_sysctl { + __u32 write; /* Sysctl is being read (= 0) or written (= 1). + * Allows 1,2,4-byte read, but no write. + */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index f6cd38746df2..610491b5f0aa 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -11,7 +11,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -768,3 +770,93 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { .get_func_proto = cgroup_dev_func_proto, .is_valid_access = cgroup_dev_is_valid_access, }; + +/** + * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl + * + * @head: sysctl table header + * @table: sysctl table + * @write: sysctl is being read (= 0) or written (= 1) + * @type: type of program to be executed + * + * Program is run when sysctl is being accessed, either read or written, and + * can allow or deny such access. + * + * This function will return %-EPERM if an attached program is found and + * returned value != 1 during execution. In all other cases 0 is returned. + */ +int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, + struct ctl_table *table, int write, + enum bpf_attach_type type) +{ + struct bpf_sysctl_kern ctx = { + .head = head, + .table = table, + .write = write, + }; + struct cgroup *cgrp; + int ret; + + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); + rcu_read_unlock(); + + return ret == 1 ? 0 : -EPERM; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl); + +static const struct bpf_func_proto * +sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return cgroup_base_func_proto(func_id, prog); +} + +static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + const int size_default = sizeof(__u32); + + if (off < 0 || off + size > sizeof(struct bpf_sysctl) || + off % size || type != BPF_READ) + return false; + + switch (off) { + case offsetof(struct bpf_sysctl, write): + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, size_default); + default: + return false; + } +} + +static u32 sysctl_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct bpf_sysctl, write): + *insn++ = BPF_LDX_MEM( + BPF_SIZE(si->code), si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sysctl_kern, write, + FIELD_SIZEOF(struct bpf_sysctl_kern, + write), + target_size)); + break; + } + + return insn - insn_buf; +} + +const struct bpf_verifier_ops cg_sysctl_verifier_ops = { + .get_func_proto = sysctl_func_proto, + .is_valid_access = sysctl_is_valid_access, + .convert_ctx_access = sysctl_convert_ctx_access, +}; + +const struct bpf_prog_ops cg_sysctl_prog_ops = { +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d995eedfdd16..92c9b8a32b50 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1888,6 +1888,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_FLOW_DISSECTOR: ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; break; + case BPF_CGROUP_SYSCTL: + ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; + break; default: return -EINVAL; } @@ -1966,6 +1969,9 @@ static int bpf_prog_detach(const union bpf_attr *attr) return lirc_prog_detach(attr); case BPF_FLOW_DISSECTOR: return skb_flow_dissector_bpf_prog_detach(attr); + case BPF_CGROUP_SYSCTL: + ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; + break; default: return -EINVAL; } @@ -1999,6 +2005,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: + case BPF_CGROUP_SYSCTL: break; case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f25b7c9c20ba..20808e3c95a8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5267,6 +5267,7 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SYSCTL: break; default: return 0; -- cgit v1.2.3-71-gd317 From 1d11b3016cec4ed9770b98e82a61708c8f4926e7 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Thu, 28 Feb 2019 19:22:15 -0800 Subject: bpf: Introduce bpf_sysctl_get_current_value helper Add bpf_sysctl_get_current_value() helper to copy current sysctl value into provided by BPF_PROG_TYPE_CGROUP_SYSCTL program buffer. It provides same string as user space can see by reading corresponding file in /proc/sys/, including new line, etc. Documentation for the new helper is provided in bpf.h UAPI. Since current value is kept in ctl_table->data in a parsed form, ctl_table->proc_handler() with write=0 is called to read that data and convert it to a string. Such a string can later be parsed by a program using helpers that will be introduced separately. Unfortunately it's not trivial to provide API to access parsed data due to variety of data representations (string, intvec, uintvec, ulongvec, custom structures, even NULL, etc). Instead it's assumed that user know how to handle specific sysctl they're interested in and appropriate helpers can be used. Since ctl_table->proc_handler() expects __user buffer, conversion to __user happens for kernel allocated one where the value is stored. Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 2 ++ include/uapi/linux/bpf.h | 22 +++++++++++++++- kernel/bpf/cgroup.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 88 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index a17732057880..f254ff92819f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1182,6 +1182,8 @@ struct bpf_sock_ops_kern { struct bpf_sysctl_kern { struct ctl_table_header *head; struct ctl_table *table; + void *cur_val; + size_t cur_len; int write; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9c8a2f3ccb9b..063543afa359 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2522,6 +2522,25 @@ union bpf_attr { * * **-E2BIG** if the buffer wasn't big enough (*buf* will contain * truncated name in this case). + * + * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2625,7 +2644,8 @@ union bpf_attr { FN(get_listener_sock), \ FN(skc_lookup_tcp), \ FN(tcp_check_syncookie), \ - FN(sysctl_get_name), + FN(sysctl_get_name), \ + FN(sysctl_get_current_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index a68387043244..c6b2cf29a54b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -794,15 +794,37 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, .head = head, .table = table, .write = write, + .cur_val = NULL, + .cur_len = PAGE_SIZE, }; struct cgroup *cgrp; int ret; + ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL); + if (ctx.cur_val) { + mm_segment_t old_fs; + loff_t pos = 0; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + if (table->proc_handler(table, 0, (void __user *)ctx.cur_val, + &ctx.cur_len, &pos)) { + /* Let BPF program decide how to proceed. */ + ctx.cur_len = 0; + } + set_fs(old_fs); + } else { + /* Let BPF program decide how to proceed. */ + ctx.cur_len = 0; + } + rcu_read_lock(); cgrp = task_dfl_cgroup(current); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); rcu_read_unlock(); + kfree(ctx.cur_val); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl); @@ -869,12 +891,55 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = { .arg4_type = ARG_ANYTHING, }; +static int copy_sysctl_value(char *dst, size_t dst_len, char *src, + size_t src_len) +{ + if (!dst) + return -EINVAL; + + if (!dst_len) + return -E2BIG; + + if (!src || !src_len) { + memset(dst, 0, dst_len); + return -EINVAL; + } + + memcpy(dst, src, min(dst_len, src_len)); + + if (dst_len > src_len) { + memset(dst + src_len, '\0', dst_len - src_len); + return src_len; + } + + dst[dst_len - 1] = '\0'; + + return -E2BIG; +} + +BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx, + char *, buf, size_t, buf_len) +{ + return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len); +} + +static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = { + .func = bpf_sysctl_get_current_value, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto * sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; + case BPF_FUNC_sysctl_get_current_value: + return &bpf_sysctl_get_current_value_proto; default: return cgroup_base_func_proto(func_id, prog); } -- cgit v1.2.3-71-gd317 From 4e63acdff864654cee0ac5aaeda3913798ee78f6 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Thu, 7 Mar 2019 18:38:43 -0800 Subject: bpf: Introduce bpf_sysctl_{get,set}_new_value helpers Add helpers to work with new value being written to sysctl by user space. bpf_sysctl_get_new_value() copies value being written to sysctl into provided buffer. bpf_sysctl_set_new_value() overrides new value being written by user space with a one from provided buffer. Buffer should contain string representation of the value, similar to what can be seen in /proc/sys/. Both helpers can be used only on sysctl write. File position matters and can be managed by an interface that will be introduced separately. E.g. if user space calls sys_write to a file in /proc/sys/ at file position = X, where X > 0, then the value set by bpf_sysctl_set_new_value() will be written starting from X. If program wants to override whole value with specified buffer, file position has to be set to zero. Documentation for the new helpers is provided in bpf.h UAPI. Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- fs/proc/proc_sysctl.c | 22 ++++++++++--- include/linux/bpf-cgroup.h | 8 +++-- include/linux/filter.h | 3 ++ include/uapi/linux/bpf.h | 38 +++++++++++++++++++++- kernel/bpf/cgroup.c | 81 +++++++++++++++++++++++++++++++++++++++++++++- 5 files changed, 142 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index e01b02150340..023101c6f0d7 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -570,8 +570,8 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, struct inode *inode = file_inode(filp); struct ctl_table_header *head = grab_header(inode); struct ctl_table *table = PROC_I(inode)->sysctl_entry; + void *new_buf = NULL; ssize_t error; - size_t res; if (IS_ERR(head)) return PTR_ERR(head); @@ -589,15 +589,27 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, if (!table->proc_handler) goto out; - error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write); + error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count, + &new_buf); if (error) goto out; /* careful: calling conventions are nasty here */ - res = count; - error = table->proc_handler(table, write, buf, &res, ppos); + if (new_buf) { + mm_segment_t old_fs; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + error = table->proc_handler(table, write, (void __user *)new_buf, + &count, ppos); + set_fs(old_fs); + kfree(new_buf); + } else { + error = table->proc_handler(table, write, buf, &count, ppos); + } + if (!error) - error = res; + error = count; out: sysctl_head_finish(head); diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index b1c45da20a26..1e97271f9a10 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -113,7 +113,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, - enum bpf_attach_type type); + void __user *buf, size_t *pcount, + void **new_buf, enum bpf_attach_type type); static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) @@ -261,11 +262,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) \ +#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, nbuf) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ + buf, count, nbuf, \ BPF_CGROUP_SYSCTL); \ __ret; \ }) @@ -338,7 +340,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,nbuf) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) diff --git a/include/linux/filter.h b/include/linux/filter.h index f254ff92819f..a23653f9460c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1184,6 +1184,9 @@ struct bpf_sysctl_kern { struct ctl_table *table; void *cur_val; size_t cur_len; + void *new_val; + size_t new_len; + int new_updated; int write; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 063543afa359..547b8258d731 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2541,6 +2541,40 @@ union bpf_attr { * * **-EINVAL** if current value was unavailable, e.g. because * sysctl is uninitialized and read returns -EIO for it. + * + * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2645,7 +2679,9 @@ union bpf_attr { FN(skc_lookup_tcp), \ FN(tcp_check_syncookie), \ FN(sysctl_get_name), \ - FN(sysctl_get_current_value), + FN(sysctl_get_current_value), \ + FN(sysctl_get_new_value), \ + FN(sysctl_set_new_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index c6b2cf29a54b..ba4e21986760 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -778,6 +778,13 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { * @head: sysctl table header * @table: sysctl table * @write: sysctl is being read (= 0) or written (= 1) + * @buf: pointer to buffer passed by user space + * @pcount: value-result argument: value is size of buffer pointed to by @buf, + * result is size of @new_buf if program set new value, initial value + * otherwise + * @new_buf: pointer to pointer to new buffer that will be allocated if program + * overrides new value provided by user space on sysctl write + * NOTE: it's caller responsibility to free *new_buf if it was set * @type: type of program to be executed * * Program is run when sysctl is being accessed, either read or written, and @@ -788,7 +795,8 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { */ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, - enum bpf_attach_type type) + void __user *buf, size_t *pcount, + void **new_buf, enum bpf_attach_type type) { struct bpf_sysctl_kern ctx = { .head = head, @@ -796,6 +804,9 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, .write = write, .cur_val = NULL, .cur_len = PAGE_SIZE, + .new_val = NULL, + .new_len = 0, + .new_updated = 0, }; struct cgroup *cgrp; int ret; @@ -818,6 +829,18 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, ctx.cur_len = 0; } + if (write && buf && *pcount) { + /* BPF program should be able to override new value with a + * buffer bigger than provided by user. + */ + ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL); + ctx.new_len = min(PAGE_SIZE, *pcount); + if (!ctx.new_val || + copy_from_user(ctx.new_val, buf, ctx.new_len)) + /* Let BPF program decide how to proceed. */ + ctx.new_len = 0; + } + rcu_read_lock(); cgrp = task_dfl_cgroup(current); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); @@ -825,6 +848,13 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, kfree(ctx.cur_val); + if (ret == 1 && ctx.new_updated) { + *new_buf = ctx.new_val; + *pcount = ctx.new_len; + } else { + kfree(ctx.new_val); + } + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl); @@ -932,6 +962,51 @@ static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = { .arg3_type = ARG_CONST_SIZE, }; +BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf, + size_t, buf_len) +{ + if (!ctx->write) { + if (buf && buf_len) + memset(buf, '\0', buf_len); + return -EINVAL; + } + return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len); +} + +static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = { + .func = bpf_sysctl_get_new_value, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx, + const char *, buf, size_t, buf_len) +{ + if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len) + return -EINVAL; + + if (buf_len > PAGE_SIZE - 1) + return -E2BIG; + + memcpy(ctx->new_val, buf, buf_len); + ctx->new_len = buf_len; + ctx->new_updated = 1; + + return 0; +} + +static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = { + .func = bpf_sysctl_set_new_value, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto * sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -940,6 +1015,10 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sysctl_get_name_proto; case BPF_FUNC_sysctl_get_current_value: return &bpf_sysctl_get_current_value_proto; + case BPF_FUNC_sysctl_get_new_value: + return &bpf_sysctl_get_new_value_proto; + case BPF_FUNC_sysctl_set_new_value: + return &bpf_sysctl_set_new_value_proto; default: return cgroup_base_func_proto(func_id, prog); } -- cgit v1.2.3-71-gd317 From e1550bfe0de47e30484ba91de1e50a91ec1c31f5 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Thu, 7 Mar 2019 18:50:52 -0800 Subject: bpf: Add file_pos field to bpf_sysctl ctx Add file_pos field to bpf_sysctl context to read and write sysctl file position at which sysctl is being accessed (read or written). The field can be used to e.g. override whole sysctl value on write to sysctl even when sys_write is called by user space with file_pos > 0. Or BPF program may reject such accesses. Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- fs/proc/proc_sysctl.c | 2 +- include/linux/bpf-cgroup.h | 9 ++++---- include/linux/filter.h | 3 +++ include/uapi/linux/bpf.h | 3 +++ kernel/bpf/cgroup.c | 54 +++++++++++++++++++++++++++++++++++++++++++--- 5 files changed, 63 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 023101c6f0d7..2d61e5e8c863 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -590,7 +590,7 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, goto out; error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count, - &new_buf); + ppos, &new_buf); if (error) goto out; diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 1e97271f9a10..cb3c6b3b89c8 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -114,7 +114,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, void __user *buf, size_t *pcount, - void **new_buf, enum bpf_attach_type type); + loff_t *ppos, void **new_buf, + enum bpf_attach_type type); static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) @@ -262,12 +263,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, nbuf) \ +#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ - buf, count, nbuf, \ + buf, count, pos, nbuf, \ BPF_CGROUP_SYSCTL); \ __ret; \ }) @@ -340,7 +341,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,nbuf) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) diff --git a/include/linux/filter.h b/include/linux/filter.h index a23653f9460c..fb0edad75971 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1188,6 +1188,9 @@ struct bpf_sysctl_kern { size_t new_len; int new_updated; int write; + loff_t *ppos; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; #endif /* __LINUX_FILTER_H__ */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 547b8258d731..89976de909af 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3391,6 +3391,9 @@ struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. */ + __u32 file_pos; /* Sysctl file position to read from, write to. + * Allows 1,2,4-byte read an 4-byte write. + */ }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ba4e21986760..b2adf22139b3 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -782,6 +782,9 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { * @pcount: value-result argument: value is size of buffer pointed to by @buf, * result is size of @new_buf if program set new value, initial value * otherwise + * @ppos: value-result argument: value is position at which read from or write + * to sysctl is happening, result is new position if program overrode it, + * initial value otherwise * @new_buf: pointer to pointer to new buffer that will be allocated if program * overrides new value provided by user space on sysctl write * NOTE: it's caller responsibility to free *new_buf if it was set @@ -796,12 +799,14 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, void __user *buf, size_t *pcount, - void **new_buf, enum bpf_attach_type type) + loff_t *ppos, void **new_buf, + enum bpf_attach_type type) { struct bpf_sysctl_kern ctx = { .head = head, .table = table, .write = write, + .ppos = ppos, .cur_val = NULL, .cur_len = PAGE_SIZE, .new_val = NULL, @@ -1030,14 +1035,22 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type, { const int size_default = sizeof(__u32); - if (off < 0 || off + size > sizeof(struct bpf_sysctl) || - off % size || type != BPF_READ) + if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size) return false; switch (off) { case offsetof(struct bpf_sysctl, write): + if (type != BPF_READ) + return false; bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case offsetof(struct bpf_sysctl, file_pos): + if (type == BPF_READ) { + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, size_default); + } else { + return size == size_default; + } default: return false; } @@ -1059,6 +1072,41 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, write), target_size)); break; + case offsetof(struct bpf_sysctl, file_pos): + /* ppos is a pointer so it should be accessed via indirect + * loads and stores. Also for stores additional temporary + * register is used since neither src_reg nor dst_reg can be + * overridden. + */ + if (type == BPF_WRITE) { + int treg = BPF_REG_9; + + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + *insn++ = BPF_STX_MEM( + BPF_DW, si->dst_reg, treg, + offsetof(struct bpf_sysctl_kern, tmp_reg)); + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), + treg, si->dst_reg, + offsetof(struct bpf_sysctl_kern, ppos)); + *insn++ = BPF_STX_MEM( + BPF_SIZEOF(u32), treg, si->src_reg, 0); + *insn++ = BPF_LDX_MEM( + BPF_DW, treg, si->dst_reg, + offsetof(struct bpf_sysctl_kern, tmp_reg)); + } else { + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sysctl_kern, ppos)); + *insn++ = BPF_LDX_MEM( + BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0); + } + *target_size = sizeof(u32); + break; } return insn - insn_buf; -- cgit v1.2.3-71-gd317 From 57c3bb725a3dd97d960d7e1cd0845d88de53217f Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Mon, 18 Mar 2019 16:57:10 -0700 Subject: bpf: Introduce ARG_PTR_TO_{INT,LONG} arg types Currently the way to pass result from BPF helper to BPF program is to provide memory area defined by pointer and size: func(void *, size_t). It works great for generic use-case, but for simple types, such as int, it's overkill and consumes two arguments when it could use just one. Introduce new argument types ARG_PTR_TO_INT and ARG_PTR_TO_LONG to be able to pass result from helper to program via pointer to int and long correspondingly: func(int *) or func(long *). New argument types are similar to ARG_PTR_TO_MEM with the following differences: * they don't require corresponding ARG_CONST_SIZE argument, predefined access sizes are used instead (32bit for int, 64bit for long); * it's possible to use more than one such an argument in a helper; * provided pointers have to be aligned. It's easy to introduce similar ARG_PTR_TO_CHAR and ARG_PTR_TO_SHORT argument types. It's not done due to lack of use-case though. Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ kernel/bpf/verifier.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e4d4c1771ab0..fd06ada941ad 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -202,6 +202,8 @@ enum bpf_arg_type { ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ + ARG_PTR_TO_INT, /* pointer to int */ + ARG_PTR_TO_LONG, /* pointer to long */ }; /* type of values returned from helper functions */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 20808e3c95a8..15ab6fa817ce 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2462,6 +2462,22 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type) type == ARG_CONST_SIZE_OR_ZERO; } +static bool arg_type_is_int_ptr(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_INT || + type == ARG_PTR_TO_LONG; +} + +static int int_ptr_type_to_size(enum bpf_arg_type type) +{ + if (type == ARG_PTR_TO_INT) + return sizeof(u32); + else if (type == ARG_PTR_TO_LONG) + return sizeof(u64); + + return -EINVAL; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) @@ -2554,6 +2570,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; + } else if (arg_type_is_int_ptr(arg_type)) { + expected_type = PTR_TO_STACK; + if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && + type != expected_type) + goto err_type; } else { verbose(env, "unsupported arg_type %d\n", arg_type); return -EFAULT; @@ -2635,6 +2657,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_helper_mem_access(env, regno - 1, reg->umax_value, zero_size_allowed, meta); + } else if (arg_type_is_int_ptr(arg_type)) { + int size = int_ptr_type_to_size(arg_type); + + err = check_helper_mem_access(env, regno, size, false, meta); + if (err) + return err; + err = check_ptr_alignment(env, reg, 0, size, true); } return err; -- cgit v1.2.3-71-gd317 From d7a4cb9b6705a89937d12c8158a35a3145dc967a Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Mon, 18 Mar 2019 17:55:26 -0700 Subject: bpf: Introduce bpf_strtol and bpf_strtoul helpers Add bpf_strtol and bpf_strtoul to convert a string to long and unsigned long correspondingly. It's similar to user space strtol(3) and strtoul(3) with a few changes to the API: * instead of NUL-terminated C string the helpers expect buffer and buffer length; * resulting long or unsigned long is returned in a separate result-argument; * return value is used to indicate success or failure, on success number of consumed bytes is returned that can be used to identify position to read next if the buffer is expected to contain multiple integers; * instead of *base* argument, *flags* is used that provides base in 5 LSB, other bits are reserved for future use; * number of supported bases is limited. Documentation for the new helpers is provided in bpf.h UAPI. The helpers are made available to BPF_PROG_TYPE_CGROUP_SYSCTL programs to be able to convert string input to e.g. "ulongvec" output. E.g. "net/ipv4/tcp_mem" consists of three ulong integers. They can be parsed by calling to bpf_strtoul three times. Implementation notes: Implementation includes "../../lib/kstrtox.h" to reuse integer parsing functions. It's done exactly same way as fs/proc/base.c already does. Unfortunately existing kstrtoX function can't be used directly since they fail if any invalid character is present right after integer in the string. Existing simple_strtoX functions can't be used either since they're obsolete and don't handle overflow properly. Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 51 +++++++++++++++++- kernel/bpf/cgroup.c | 4 ++ kernel/bpf/helpers.c | 131 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 187 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fd06ada941ad..f15432d90728 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -989,6 +989,8 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; +extern const struct bpf_func_proto bpf_strtol_proto; +extern const struct bpf_func_proto bpf_strtoul_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 89976de909af..c26be24fd5e2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2575,6 +2575,53 @@ union bpf_attr { * **-E2BIG** if the *buf_len* is too big. * * **-EINVAL** if sysctl is being read. + * + * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by isspace(3)) followed by a single optional '-' + * sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space strtol(3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than buf_len. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by isspace(3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space strtoul(3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than buf_len. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2681,7 +2728,9 @@ union bpf_attr { FN(sysctl_get_name), \ FN(sysctl_get_current_value), \ FN(sysctl_get_new_value), \ - FN(sysctl_set_new_value), + FN(sysctl_set_new_value), \ + FN(strtol), \ + FN(strtoul), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index b2adf22139b3..789d4ab2336e 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1016,6 +1016,10 @@ static const struct bpf_func_proto * sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { + case BPF_FUNC_strtol: + return &bpf_strtol_proto; + case BPF_FUNC_strtoul: + return &bpf_strtoul_proto; case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; case BPF_FUNC_sysctl_get_current_value: diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a411fc17d265..4266ffde07ca 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -18,6 +18,9 @@ #include #include #include +#include + +#include "../../lib/kstrtox.h" /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -363,4 +366,132 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { .arg2_type = ARG_ANYTHING, }; #endif + +#define BPF_STRTOX_BASE_MASK 0x1F + +static int __bpf_strtoull(const char *buf, size_t buf_len, u64 flags, + unsigned long long *res, bool *is_negative) +{ + unsigned int base = flags & BPF_STRTOX_BASE_MASK; + const char *cur_buf = buf; + size_t cur_len = buf_len; + unsigned int consumed; + size_t val_len; + char str[64]; + + if (!buf || !buf_len || !res || !is_negative) + return -EINVAL; + + if (base != 0 && base != 8 && base != 10 && base != 16) + return -EINVAL; + + if (flags & ~BPF_STRTOX_BASE_MASK) + return -EINVAL; + + while (cur_buf < buf + buf_len && isspace(*cur_buf)) + ++cur_buf; + + *is_negative = (cur_buf < buf + buf_len && *cur_buf == '-'); + if (*is_negative) + ++cur_buf; + + consumed = cur_buf - buf; + cur_len -= consumed; + if (!cur_len) + return -EINVAL; + + cur_len = min(cur_len, sizeof(str) - 1); + memcpy(str, cur_buf, cur_len); + str[cur_len] = '\0'; + cur_buf = str; + + cur_buf = _parse_integer_fixup_radix(cur_buf, &base); + val_len = _parse_integer(cur_buf, base, res); + + if (val_len & KSTRTOX_OVERFLOW) + return -ERANGE; + + if (val_len == 0) + return -EINVAL; + + cur_buf += val_len; + consumed += cur_buf - str; + + return consumed; +} + +static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags, + long long *res) +{ + unsigned long long _res; + bool is_negative; + int err; + + err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); + if (err < 0) + return err; + if (is_negative) { + if ((long long)-_res > 0) + return -ERANGE; + *res = -_res; + } else { + if ((long long)_res < 0) + return -ERANGE; + *res = _res; + } + return err; +} + +BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags, + long *, res) +{ + long long _res; + int err; + + err = __bpf_strtoll(buf, buf_len, flags, &_res); + if (err < 0) + return err; + if (_res != (long)_res) + return -ERANGE; + *res = _res; + return err; +} + +const struct bpf_func_proto bpf_strtol_proto = { + .func = bpf_strtol, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags, + unsigned long *, res) +{ + unsigned long long _res; + bool is_negative; + int err; + + err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); + if (err < 0) + return err; + if (is_negative) + return -EINVAL; + if (_res != (unsigned long)_res) + return -ERANGE; + *res = _res; + return err; +} + +const struct bpf_func_proto bpf_strtoul_proto = { + .func = bpf_strtoul, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; #endif -- cgit v1.2.3-71-gd317 From e4edbe3c1f44c84f319149aeb998e7e36b3b897f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 12 Apr 2019 11:52:07 +1000 Subject: rhashtable: fix some __rcu annotation errors With these annotations, the rhashtable now gets no warnings when compiled with "C=1" for sparse checking. Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 11 ++++++----- lib/rhashtable.c | 4 ++-- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 460c0eaf6b96..2711cbf01b64 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -40,7 +40,7 @@ * the chain. To avoid dereferencing this pointer without clearing * the bit first, we use an opaque 'struct rhash_lock_head *' for the * pointer stored in the bucket. This struct needs to be defined so - * that rcu_derefernce() works on it, but it has no content so a + * that rcu_dereference() works on it, but it has no content so a * cast is needed for it to be useful. This ensures it isn't * used by mistake with clearing the lock bit first. */ @@ -130,10 +130,10 @@ static inline void rht_unlock(struct bucket_table *tbl, } static inline void rht_assign_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head **p = (struct rhash_head **)bkt; + struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; lock_map_release(&tbl->dep_map); rcu_assign_pointer(*p, obj); @@ -556,6 +556,7 @@ static inline struct rhash_head *__rhashtable_lookup( }; struct rhash_lock_head __rcu * const *bkt; struct bucket_table *tbl; + struct rhash_head __rcu *head; struct rhash_head *he; unsigned int hash; @@ -564,8 +565,8 @@ restart: hash = rht_key_hashfn(ht, tbl, key, params); bkt = rht_bucket(tbl, hash); do { - he = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash)); - rht_for_each_rcu_from(he, he, tbl, hash) { + head = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash)); + rht_for_each_rcu_from(he, head, tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9c84f5cef69c..e387ceb00e86 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -223,7 +223,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht, struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl); int err = -EAGAIN; struct rhash_head *head, *next, *entry; - struct rhash_head **pprev = NULL; + struct rhash_head __rcu **pprev = NULL; unsigned int new_hash; if (new_tbl->nest) @@ -486,7 +486,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, .ht = ht, .key = key, }; - struct rhash_head **pprev = NULL; + struct rhash_head __rcu **pprev = NULL; struct rhash_head *head; int elasticity; -- cgit v1.2.3-71-gd317 From c5783311a1248c437614d438b69c5f31fe483ecb Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 12 Apr 2019 11:52:08 +1000 Subject: rhashtable: reorder some inline functions and macros. This patch only moves some code around, it doesn't change the code at all. A subsequent patch will benefit from this as it needs to add calls to functions which are now defined before the call-site, but weren't before. Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 142 ++++++++++++++++++++++----------------------- 1 file changed, 71 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 2711cbf01b64..c504cd820736 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -87,77 +87,6 @@ struct bucket_table { struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -/* - * We lock a bucket by setting BIT(1) in the pointer - this is always - * zero in real pointers and in the nulls marker. - * bit_spin_locks do not handle contention well, but the whole point - * of the hashtable design is to achieve minimum per-bucket contention. - * A nested hash table might not have a bucket pointer. In that case - * we cannot get a lock. For remove and replace the bucket cannot be - * interesting and doesn't need locking. - * For insert we allocate the bucket if this is the last bucket_table, - * and then take the lock. - * Sometimes we unlock a bucket by writing a new pointer there. In that - * case we don't need to unlock, but we do need to reset state such as - * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() - * provides the same release semantics that bit_spin_unlock() provides, - * this is safe. - */ - -static inline void rht_lock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) -{ - local_bh_disable(); - bit_spin_lock(1, (unsigned long *)bkt); - lock_map_acquire(&tbl->dep_map); -} - -static inline void rht_lock_nested(struct bucket_table *tbl, - struct rhash_lock_head **bucket, - unsigned int subclass) -{ - local_bh_disable(); - bit_spin_lock(1, (unsigned long *)bucket); - lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); -} - -static inline void rht_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) -{ - lock_map_release(&tbl->dep_map); - bit_spin_unlock(1, (unsigned long *)bkt); - local_bh_enable(); -} - -static inline void rht_assign_unlock(struct bucket_table *tbl, - struct rhash_lock_head __rcu **bkt, - struct rhash_head *obj) -{ - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - - lock_map_release(&tbl->dep_map); - rcu_assign_pointer(*p, obj); - preempt_enable(); - __release(bitlock); - local_bh_enable(); -} - -/* - * If 'p' is a bucket head and might be locked: - * rht_ptr() returns the address without the lock bit. - * rht_ptr_locked() returns the address WITH the lock bit. - */ -static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p) -{ - return (void *)(((unsigned long)p) & ~BIT(1)); -} - -static inline struct rhash_lock_head __rcu *rht_ptr_locked(const - struct rhash_head *p) -{ - return (void *)(((unsigned long)p) | BIT(1)); -} - /* * NULLS_MARKER() expects a hash value with the low * bits mostly likely to be significant, and it discards @@ -372,6 +301,77 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert( &tbl->buckets[hash]; } +/* + * We lock a bucket by setting BIT(1) in the pointer - this is always + * zero in real pointers and in the nulls marker. + * bit_spin_locks do not handle contention well, but the whole point + * of the hashtable design is to achieve minimum per-bucket contention. + * A nested hash table might not have a bucket pointer. In that case + * we cannot get a lock. For remove and replace the bucket cannot be + * interesting and doesn't need locking. + * For insert we allocate the bucket if this is the last bucket_table, + * and then take the lock. + * Sometimes we unlock a bucket by writing a new pointer there. In that + * case we don't need to unlock, but we do need to reset state such as + * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() + * provides the same release semantics that bit_spin_unlock() provides, + * this is safe. + */ + +static inline void rht_lock(struct bucket_table *tbl, + struct rhash_lock_head **bkt) +{ + local_bh_disable(); + bit_spin_lock(1, (unsigned long *)bkt); + lock_map_acquire(&tbl->dep_map); +} + +static inline void rht_lock_nested(struct bucket_table *tbl, + struct rhash_lock_head **bucket, + unsigned int subclass) +{ + local_bh_disable(); + bit_spin_lock(1, (unsigned long *)bucket); + lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); +} + +static inline void rht_unlock(struct bucket_table *tbl, + struct rhash_lock_head **bkt) +{ + lock_map_release(&tbl->dep_map); + bit_spin_unlock(1, (unsigned long *)bkt); + local_bh_enable(); +} + +/* + * If 'p' is a bucket head and might be locked: + * rht_ptr() returns the address without the lock bit. + * rht_ptr_locked() returns the address WITH the lock bit. + */ +static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p) +{ + return (void *)(((unsigned long)p) & ~BIT(1)); +} + +static inline struct rhash_lock_head __rcu *rht_ptr_locked(const + struct rhash_head *p) +{ + return (void *)(((unsigned long)p) | BIT(1)); +} + +static inline void rht_assign_unlock(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bkt, + struct rhash_head *obj) +{ + struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; + + lock_map_release(&tbl->dep_map); + rcu_assign_pointer(*p, obj); + preempt_enable(); + __release(bitlock); + local_bh_enable(); +} + /** * rht_for_each_from - iterate over hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. -- cgit v1.2.3-71-gd317 From adc6a3ab192eb40fb9d8b093c87d9aa785af4513 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 12 Apr 2019 11:52:08 +1000 Subject: rhashtable: move dereference inside rht_ptr() Rather than dereferencing a pointer to a bucket and then passing the result to rht_ptr(), we now pass in the pointer and do the dereference in rht_ptr(). This requires that we pass in the tbl and hash as well to support RCU checks, and means that the various rht_for_each functions can expect a pointer that can be dereferenced without further care. There are two places where we dereference a bucket pointer where there is no testable protection - in each case we know that we much have exclusive access without having taken a lock. The previous code used rht_dereference() to pretend that holding the mutex provided protects, but holding the mutex never provides protection for accessing buckets. So instead introduce rht_ptr_exclusive() that can be used when there is known to be exclusive access without holding any locks. Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 69 ++++++++++++++++++++++++++++------------------ lib/rhashtable.c | 12 ++++---- lib/test_rhashtable.c | 2 +- 3 files changed, 49 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index c504cd820736..b54e6436547e 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -344,12 +344,28 @@ static inline void rht_unlock(struct bucket_table *tbl, } /* - * If 'p' is a bucket head and might be locked: - * rht_ptr() returns the address without the lock bit. - * rht_ptr_locked() returns the address WITH the lock bit. + * Where 'bkt' is a bucket and might be locked: + * rht_ptr() dereferences that pointer and clears the lock bit. + * rht_ptr_exclusive() dereferences in a context where exclusive + * access is guaranteed, such as when destroying the table. */ -static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p) +static inline struct rhash_head *rht_ptr( + struct rhash_lock_head __rcu * const *bkt, + struct bucket_table *tbl, + unsigned int hash) { + const struct rhash_lock_head *p = + rht_dereference_bucket_rcu(*bkt, tbl, hash); + + return (void *)(((unsigned long)p) & ~BIT(1)); +} + +static inline struct rhash_head *rht_ptr_exclusive( + struct rhash_lock_head __rcu * const *bkt) +{ + const struct rhash_lock_head *p = + rcu_dereference_protected(*bkt, 1); + return (void *)(((unsigned long)p) & ~BIT(1)); } @@ -380,8 +396,8 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, * @hash: the hash value / bucket index */ #define rht_for_each_from(pos, head, tbl, hash) \ - for (pos = rht_dereference_bucket(head, tbl, hash); \ - !rht_is_a_nulls(pos); \ + for (pos = head; \ + !rht_is_a_nulls(pos); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** @@ -391,7 +407,8 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, * @hash: the hash value / bucket index */ #define rht_for_each(pos, tbl, hash) \ - rht_for_each_from(pos, rht_ptr(*rht_bucket(tbl, hash)), tbl, hash) + rht_for_each_from(pos, rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ + tbl, hash) /** * rht_for_each_entry_from - iterate over hash chain from given head @@ -403,7 +420,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member) \ - for (pos = rht_dereference_bucket(head, tbl, hash); \ + for (pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) @@ -416,8 +433,9 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_from(tpos, pos, rht_ptr(*rht_bucket(tbl, hash)), \ - tbl, hash, member) + rht_for_each_entry_from(tpos, pos, \ + rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ + tbl, hash, member) /** * rht_for_each_entry_safe - safely iterate over hash chain of given type @@ -432,8 +450,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, * remove the loop cursor from the list. */ #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ - for (pos = rht_dereference_bucket(rht_ptr(*rht_bucket(tbl, hash)), \ - tbl, hash), \ + for (pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ @@ -454,7 +471,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, */ #define rht_for_each_rcu_from(pos, head, tbl, hash) \ for (({barrier(); }), \ - pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos = head; \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) @@ -469,10 +486,9 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_rcu(pos, tbl, hash) \ - for (({barrier(); }), \ - pos = rht_ptr(rht_dereference_bucket_rcu( \ - *rht_bucket(tbl, hash), tbl, hash)); \ - !rht_is_a_nulls(pos); \ + for (({barrier(); }), \ + pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash); \ + !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) /** @@ -490,7 +506,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, */ #define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \ for (({barrier(); }), \ - pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket_rcu(pos->next, tbl, hash)) @@ -508,8 +524,9 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ rht_for_each_entry_rcu_from(tpos, pos, \ - rht_ptr(*rht_bucket(tbl, hash)), \ - tbl, hash, member) + rht_ptr(rht_bucket(tbl, hash), \ + tbl, hash), \ + tbl, hash, member) /** * rhl_for_each_rcu - iterate over rcu hash table list @@ -556,7 +573,6 @@ static inline struct rhash_head *__rhashtable_lookup( }; struct rhash_lock_head __rcu * const *bkt; struct bucket_table *tbl; - struct rhash_head __rcu *head; struct rhash_head *he; unsigned int hash; @@ -565,8 +581,7 @@ restart: hash = rht_key_hashfn(ht, tbl, key, params); bkt = rht_bucket(tbl, hash); do { - head = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash)); - rht_for_each_rcu_from(he, head, tbl, hash) { + rht_for_each_rcu_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) @@ -699,7 +714,7 @@ slow_path: return rhashtable_insert_slow(ht, key, obj); } - rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) { + rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *plist; struct rhlist_head *list; @@ -744,7 +759,7 @@ slow_path: goto slow_path; /* Inserting at head of list makes unlocking free. */ - head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash)); + head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (rhlist) { @@ -971,7 +986,7 @@ static inline int __rhashtable_remove_fast_one( pprev = NULL; rht_lock(tbl, bkt); - rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) { + rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; list = container_of(he, struct rhlist_head, rhead); @@ -1130,7 +1145,7 @@ static inline int __rhashtable_replace_fast( pprev = NULL; rht_lock(tbl, bkt); - rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) { + rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { if (he != obj_old) { pprev = &he->next; continue; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index e387ceb00e86..237368ea98c5 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -231,7 +231,8 @@ static int rhashtable_rehash_one(struct rhashtable *ht, err = -ENOENT; - rht_for_each_from(entry, rht_ptr(*bkt), old_tbl, old_hash) { + rht_for_each_from(entry, rht_ptr(bkt, old_tbl, old_hash), + old_tbl, old_hash) { err = 0; next = rht_dereference_bucket(entry->next, old_tbl, old_hash); @@ -248,8 +249,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht, rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING); - head = rht_ptr(rht_dereference_bucket(new_tbl->buckets[new_hash], - new_tbl, new_hash)); + head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash); RCU_INIT_POINTER(entry->next, head); @@ -491,7 +491,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, int elasticity; elasticity = RHT_ELASTICITY; - rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) { + rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; struct rhlist_head *plist; @@ -557,7 +557,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, if (unlikely(rht_grow_above_100(ht, tbl))) return ERR_PTR(-EAGAIN); - head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash)); + head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (ht->rhlist) { @@ -1139,7 +1139,7 @@ restart: struct rhash_head *pos, *next; cond_resched(); - for (pos = rht_ptr(rht_dereference(*rht_bucket(tbl, i), ht)), + for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)), next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; !rht_is_a_nulls(pos); diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 02592c2a249c..084fe5a6ac57 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -500,7 +500,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt) struct rhash_head *pos, *next; struct test_obj_rhl *p; - pos = rht_ptr(rht_dereference(tbl->buckets[i], ht)); + pos = rht_ptr_exclusive(tbl->buckets + i); next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; if (!rht_is_a_nulls(pos)) { -- cgit v1.2.3-71-gd317 From f4712b46a529ca2da078c82d5d99d367c7ebf82b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 12 Apr 2019 11:52:08 +1000 Subject: rhashtable: replace rht_ptr_locked() with rht_assign_locked() The only times rht_ptr_locked() is used, it is to store a new value in a bucket-head. This is the only time it makes sense to use it too. So replace it by a function which does the whole task: Sets the lock bit and assigns to a bucket head. Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 9 ++++++--- lib/rhashtable.c | 6 +++--- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index b54e6436547e..882bc0fcea4b 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -316,6 +316,7 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert( * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() * provides the same release semantics that bit_spin_unlock() provides, * this is safe. + * When we write to a bucket without unlocking, we use rht_assign_locked(). */ static inline void rht_lock(struct bucket_table *tbl, @@ -369,10 +370,12 @@ static inline struct rhash_head *rht_ptr_exclusive( return (void *)(((unsigned long)p) & ~BIT(1)); } -static inline struct rhash_lock_head __rcu *rht_ptr_locked(const - struct rhash_head *p) +static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, + struct rhash_head *obj) { - return (void *)(((unsigned long)p) | BIT(1)); + struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; + + rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(1))); } static inline void rht_assign_unlock(struct bucket_table *tbl, diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 237368ea98c5..ef5378efdef3 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -259,7 +259,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht, rcu_assign_pointer(*pprev, next); else /* Need to preserved the bit lock. */ - rcu_assign_pointer(*bkt, rht_ptr_locked(next)); + rht_assign_locked(bkt, next); out: return err; @@ -517,7 +517,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, rcu_assign_pointer(*pprev, obj); else /* Need to preserve the bit lock */ - rcu_assign_pointer(*bkt, rht_ptr_locked(obj)); + rht_assign_locked(bkt, obj); return NULL; } @@ -570,7 +570,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, /* bkt is always the head of the list, so it holds * the lock, which we need to preserve */ - rcu_assign_pointer(*bkt, rht_ptr_locked(obj)); + rht_assign_locked(bkt, obj); atomic_inc(&ht->nelems); if (rht_grow_above_75(ht, tbl)) -- cgit v1.2.3-71-gd317 From ca0b709d1a07b1fe1fb356d8d58f220287f85672 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 12 Apr 2019 11:52:08 +1000 Subject: rhashtable: use BIT(0) for locking. As reported by Guenter Roeck, the new bit-locking using BIT(1) doesn't work on the m68k architecture. m68k only requires 2-byte alignment for words and longwords, so there is only one unused bit in pointers to structs - We current use two, one for the NULLS marker at the end of the linked list, and one for the bit-lock in the head of the list. The two uses don't need to conflict as we never need the head of the list to be a NULLS marker - the marker is only needed to check if an object has moved to a different table, and the bucket head cannot move. The NULLS marker is only needed in a ->next pointer. As we already have different types for the bucket head pointer (struct rhash_lock_head) and the ->next pointers (struct rhash_head), it is fairly easy to treat the lsb differently in each. So: Initialize buckets heads to NULL, and use the lsb for locking. When loading the pointer from the bucket head, if it is NULL (ignoring the lock big), report as being the expected NULLS marker. When storing a value into a bucket head, if it is a NULLS marker, store NULL instead. And convert all places that used bit 1 for locking, to use bit 0. Fixes: 8f0db018006a ("rhashtable: use bit_spin_locks to protect hash bucket.") Reported-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 35 ++++++++++++++++++++++++----------- lib/rhashtable.c | 2 +- 2 files changed, 25 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 882bc0fcea4b..f7714d3b46bd 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -35,7 +35,7 @@ * the least significant bit set but otherwise stores the address of * the hash bucket. This allows us to be be sure we've found the end * of the right list. - * The value stored in the hash bucket has BIT(2) used as a lock bit. + * The value stored in the hash bucket has BIT(0) used as a lock bit. * This bit must be atomically set before any changes are made to * the chain. To avoid dereferencing this pointer without clearing * the bit first, we use an opaque 'struct rhash_lock_head *' for the @@ -91,15 +91,19 @@ struct bucket_table { * NULLS_MARKER() expects a hash value with the low * bits mostly likely to be significant, and it discards * the msb. - * We git it an address, in which the bottom 2 bits are + * We give it an address, in which the bottom bit is * always 0, and the msb might be significant. * So we shift the address down one bit to align with * expectations and avoid losing a significant bit. + * + * We never store the NULLS_MARKER in the hash table + * itself as we need the lsb for locking. + * Instead we store a NULL */ #define RHT_NULLS_MARKER(ptr) \ ((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1)) #define INIT_RHT_NULLS_HEAD(ptr) \ - ((ptr) = RHT_NULLS_MARKER(&(ptr))) + ((ptr) = NULL) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { @@ -302,8 +306,9 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert( } /* - * We lock a bucket by setting BIT(1) in the pointer - this is always - * zero in real pointers and in the nulls marker. + * We lock a bucket by setting BIT(0) in the pointer - this is always + * zero in real pointers. The NULLS mark is never stored in the bucket, + * rather we store NULL if the bucket is empty. * bit_spin_locks do not handle contention well, but the whole point * of the hashtable design is to achieve minimum per-bucket contention. * A nested hash table might not have a bucket pointer. In that case @@ -323,7 +328,7 @@ static inline void rht_lock(struct bucket_table *tbl, struct rhash_lock_head **bkt) { local_bh_disable(); - bit_spin_lock(1, (unsigned long *)bkt); + bit_spin_lock(0, (unsigned long *)bkt); lock_map_acquire(&tbl->dep_map); } @@ -332,7 +337,7 @@ static inline void rht_lock_nested(struct bucket_table *tbl, unsigned int subclass) { local_bh_disable(); - bit_spin_lock(1, (unsigned long *)bucket); + bit_spin_lock(0, (unsigned long *)bucket); lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); } @@ -340,7 +345,7 @@ static inline void rht_unlock(struct bucket_table *tbl, struct rhash_lock_head **bkt) { lock_map_release(&tbl->dep_map); - bit_spin_unlock(1, (unsigned long *)bkt); + bit_spin_unlock(0, (unsigned long *)bkt); local_bh_enable(); } @@ -358,7 +363,9 @@ static inline struct rhash_head *rht_ptr( const struct rhash_lock_head *p = rht_dereference_bucket_rcu(*bkt, tbl, hash); - return (void *)(((unsigned long)p) & ~BIT(1)); + if ((((unsigned long)p) & ~BIT(0)) == 0) + return RHT_NULLS_MARKER(bkt); + return (void *)(((unsigned long)p) & ~BIT(0)); } static inline struct rhash_head *rht_ptr_exclusive( @@ -367,7 +374,9 @@ static inline struct rhash_head *rht_ptr_exclusive( const struct rhash_lock_head *p = rcu_dereference_protected(*bkt, 1); - return (void *)(((unsigned long)p) & ~BIT(1)); + if (!p) + return RHT_NULLS_MARKER(bkt); + return (void *)(((unsigned long)p) & ~BIT(0)); } static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, @@ -375,7 +384,9 @@ static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, { struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(1))); + if (rht_is_a_nulls(obj)) + obj = NULL; + rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0))); } static inline void rht_assign_unlock(struct bucket_table *tbl, @@ -384,6 +395,8 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, { struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; + if (rht_is_a_nulls(obj)) + obj = NULL; lock_map_release(&tbl->dep_map); rcu_assign_pointer(*p, obj); preempt_enable(); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index ef5378efdef3..6529fe1b45c1 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -59,7 +59,7 @@ int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) return 1; if (unlikely(tbl->nest)) return 1; - return bit_spin_is_locked(1, (unsigned long *)&tbl->buckets[hash]); + return bit_spin_is_locked(0, (unsigned long *)&tbl->buckets[hash]); } EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held); #else -- cgit v1.2.3-71-gd317 From ba0509b6881efd0c8b26c36490cba87d8fb324c0 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 12 Apr 2019 17:07:37 +0200 Subject: net: core: introduce build_skb_around The function build_skb() also have the responsibility to allocate and clear the SKB structure. Introduce a new function build_skb_around(), that moves the responsibility of allocation and clearing to the caller. This allows caller to use kmem_cache (slab/slub) bulk allocation API. Next patch use this function combined with kmem_cache_alloc_bulk. Signed-off-by: Jesper Dangaard Brouer Acked-by: Song Liu Acked-by: Eric Dumazet Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 2 ++ net/core/skbuff.c | 71 ++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 54 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a06275a618f0..e81f2b0e8a83 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1042,6 +1042,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); +struct sk_buff *build_skb_around(struct sk_buff *skb, + void *data, unsigned int frag_size); /** * alloc_skb - allocate a network buffer diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9901f5322852..087622298d77 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -258,6 +258,33 @@ nodata: } EXPORT_SYMBOL(__alloc_skb); +/* Caller must provide SKB that is memset cleared */ +static struct sk_buff *__build_skb_around(struct sk_buff *skb, + void *data, unsigned int frag_size) +{ + struct skb_shared_info *shinfo; + unsigned int size = frag_size ? : ksize(data); + + size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + /* Assumes caller memset cleared SKB */ + skb->truesize = SKB_TRUESIZE(size); + refcount_set(&skb->users, 1); + skb->head = data; + skb->data = data; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; + skb->mac_header = (typeof(skb->mac_header))~0U; + skb->transport_header = (typeof(skb->transport_header))~0U; + + /* make sure we initialize shinfo sequentially */ + shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); + atomic_set(&shinfo->dataref, 1); + + return skb; +} + /** * __build_skb - build a network buffer * @data: data buffer provided by caller @@ -279,32 +306,15 @@ EXPORT_SYMBOL(__alloc_skb); */ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { - struct skb_shared_info *shinfo; struct sk_buff *skb; - unsigned int size = frag_size ? : ksize(data); skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); - if (!skb) + if (unlikely(!skb)) return NULL; - size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - memset(skb, 0, offsetof(struct sk_buff, tail)); - skb->truesize = SKB_TRUESIZE(size); - refcount_set(&skb->users, 1); - skb->head = data; - skb->data = data; - skb_reset_tail_pointer(skb); - skb->end = skb->tail + size; - skb->mac_header = (typeof(skb->mac_header))~0U; - skb->transport_header = (typeof(skb->transport_header))~0U; - /* make sure we initialize shinfo sequentially */ - shinfo = skb_shinfo(skb); - memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); - atomic_set(&shinfo->dataref, 1); - - return skb; + return __build_skb_around(skb, data, frag_size); } /* build_skb() is wrapper over __build_skb(), that specifically @@ -325,6 +335,29 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) } EXPORT_SYMBOL(build_skb); +/** + * build_skb_around - build a network buffer around provided skb + * @skb: sk_buff provide by caller, must be memset cleared + * @data: data buffer provided by caller + * @frag_size: size of data, or 0 if head was kmalloced + */ +struct sk_buff *build_skb_around(struct sk_buff *skb, + void *data, unsigned int frag_size) +{ + if (unlikely(!skb)) + return NULL; + + skb = __build_skb_around(skb, data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (page_is_pfmemalloc(virt_to_head_page(data))) + skb->pfmemalloc = 1; + } + return skb; +} +EXPORT_SYMBOL(build_skb_around); + #define NAPI_SKB_CACHE_SIZE 64 struct napi_alloc_cache { -- cgit v1.2.3-71-gd317 From a06eaaf7913cab9dd6cb8ece4f78cfd7a802872a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 17 Apr 2019 13:51:59 -0700 Subject: net: skb: remove unused asserts We are discouraging the use of BUG() these days, remove the unused ASSERT macros from skbuff.h. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a06275a618f0..e4ee92089dd6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2100,8 +2100,6 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); -#define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags) -#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb)) #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET -- cgit v1.2.3-71-gd317 From 71dd6c0dff51b5f1fef2e9dfa6f6a948aac975f3 Mon Sep 17 00:00:00 2001 From: David Bauer Date: Wed, 17 Apr 2019 23:59:21 +0200 Subject: net: phy: add support for reset-controller This commit adds support for PHY reset pins handled by a reset controller. Signed-off-by: David Bauer Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 27 +++++++++++++++++++++++++-- drivers/net/phy/mdio_device.c | 13 +++++++++++-- include/linux/mdio.h | 1 + 3 files changed, 37 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 4be4cc09eb90..ba3d2523808b 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -57,8 +58,23 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev) mdiodev->reset = gpiod; - /* Assert the reset signal again */ - mdio_device_reset(mdiodev, 1); + return 0; +} + +static int mdiobus_register_reset(struct mdio_device *mdiodev) +{ + struct reset_control *reset = NULL; + + if (mdiodev->dev.of_node) + reset = devm_reset_control_get_exclusive(&mdiodev->dev, + "phy"); + if (PTR_ERR(reset) == -ENOENT || + PTR_ERR(reset) == -ENOTSUPP) + reset = NULL; + else if (IS_ERR(reset)) + return PTR_ERR(reset); + + mdiodev->reset_ctrl = reset; return 0; } @@ -74,6 +90,13 @@ int mdiobus_register_device(struct mdio_device *mdiodev) err = mdiobus_register_gpiod(mdiodev); if (err) return err; + + err = mdiobus_register_reset(mdiodev); + if (err) + return err; + + /* Assert the reset signal */ + mdio_device_reset(mdiodev, 1); } mdiodev->bus->mdio_map[mdiodev->addr] = mdiodev; diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index 887076292e50..57668e0f9256 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -116,10 +117,18 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value) { unsigned int d; - if (!mdiodev->reset) + if (!mdiodev->reset && !mdiodev->reset_ctrl) return; - gpiod_set_value(mdiodev->reset, value); + if (mdiodev->reset) + gpiod_set_value(mdiodev->reset, value); + + if (mdiodev->reset_ctrl) { + if (value) + reset_control_assert(mdiodev->reset_ctrl); + else + reset_control_deassert(mdiodev->reset_ctrl); + } d = value ? mdiodev->reset_assert_delay : mdiodev->reset_deassert_delay; if (d) diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 3e99ae3ed87f..6eaf71500ef6 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -40,6 +40,7 @@ struct mdio_device { int addr; int flags; struct gpio_desc *reset; + struct reset_control *reset_ctrl; unsigned int reset_assert_delay; unsigned int reset_deassert_delay; }; -- cgit v1.2.3-71-gd317 From 6110ed2db3a41f3b9d676e58ac3d4637c2b497c4 Mon Sep 17 00:00:00 2001 From: David Bauer Date: Wed, 17 Apr 2019 23:59:22 +0200 Subject: net: mdio: rename mdio_device reset to reset_gpio This renames the GPIO reset of mdio devices from 'reset' to 'reset_gpio' to better differentiate between GPIO and reset-controller driven reset line. Signed-off-by: David Bauer Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/at803x.c | 2 +- drivers/net/phy/mdio_bus.c | 6 +++--- drivers/net/phy/mdio_device.c | 6 +++--- include/linux/mdio.h | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 406111753f7c..222ccd9ecfce 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -331,7 +331,7 @@ static void at803x_link_change_notify(struct phy_device *phydev) * in the FIFO. In such cases, the FIFO enters an error mode it * cannot recover from by software. */ - if (phydev->state == PHY_NOLINK && phydev->mdio.reset) { + if (phydev->state == PHY_NOLINK && phydev->mdio.reset_gpio) { struct at803x_context context; at803x_context_save(phydev, &context); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index ba3d2523808b..bd04fe762056 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -56,7 +56,7 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev) return PTR_ERR(gpiod); } - mdiodev->reset = gpiod; + mdiodev->reset_gpio = gpiod; return 0; } @@ -469,8 +469,8 @@ void mdiobus_unregister(struct mii_bus *bus) if (!mdiodev) continue; - if (mdiodev->reset) - gpiod_put(mdiodev->reset); + if (mdiodev->reset_gpio) + gpiod_put(mdiodev->reset_gpio); mdiodev->device_remove(mdiodev); mdiodev->device_free(mdiodev); diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index 57668e0f9256..e282600bd83e 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -117,11 +117,11 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value) { unsigned int d; - if (!mdiodev->reset && !mdiodev->reset_ctrl) + if (!mdiodev->reset_gpio && !mdiodev->reset_ctrl) return; - if (mdiodev->reset) - gpiod_set_value(mdiodev->reset, value); + if (mdiodev->reset_gpio) + gpiod_set_value(mdiodev->reset_gpio, value); if (mdiodev->reset_ctrl) { if (value) diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 6eaf71500ef6..9dc16d5705a1 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -39,7 +39,7 @@ struct mdio_device { /* Bus address of the MDIO device (0-31) */ int addr; int flags; - struct gpio_desc *reset; + struct gpio_desc *reset_gpio; struct reset_control *reset_ctrl; unsigned int reset_assert_delay; unsigned int reset_deassert_delay; -- cgit v1.2.3-71-gd317 From c7cbdbf29f488a19982cd9f4a109887f18028bbb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 Apr 2019 22:51:48 +0200 Subject: net: rework SIOCGSTAMP ioctl handling The SIOCGSTAMP/SIOCGSTAMPNS ioctl commands are implemented by many socket protocol handlers, and all of those end up calling the same sock_get_timestamp()/sock_get_timestampns() helper functions, which results in a lot of duplicate code. With the introduction of 64-bit time_t on 32-bit architectures, this gets worse, as we then need four different ioctl commands in each socket protocol implementation. To simplify that, let's add a new .gettstamp() operation in struct proto_ops, and move ioctl implementation into the common sock_ioctl()/compat_sock_ioctl_trans() functions that these all go through. We can reuse the sock_get_timestamp() implementation, but generalize it so it can deal with both native and compat mode, as well as timeval and timespec structures. Acked-by: Stefan Schmidt Acked-by: Neil Horman Acked-by: Marc Kleine-Budde Link: https://lore.kernel.org/lkml/CAK8P3a038aDQQotzua_QtKGhq8O9n+rdiz2=WDCp82ys8eUT+A@mail.gmail.com/ Signed-off-by: Arnd Bergmann Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/net.h | 2 ++ include/net/compat.h | 3 --- include/net/sock.h | 4 ++-- net/appletalk/ddp.c | 7 +----- net/atm/ioctl.c | 16 ------------- net/atm/pvc.c | 1 + net/atm/svc.c | 1 + net/ax25/af_ax25.c | 9 +------ net/bluetooth/af_bluetooth.c | 8 ------- net/bluetooth/l2cap_sock.c | 1 + net/bluetooth/rfcomm/sock.c | 1 + net/bluetooth/sco.c | 1 + net/can/af_can.c | 6 ----- net/can/bcm.c | 1 + net/can/raw.c | 1 + net/compat.c | 57 -------------------------------------------- net/core/sock.c | 51 +++++++++++++++++++++------------------ net/dccp/ipv4.c | 1 + net/dccp/ipv6.c | 1 + net/ieee802154/socket.c | 6 ++--- net/ipv4/af_inet.c | 9 +++---- net/ipv6/af_inet6.c | 8 ++----- net/ipv6/raw.c | 1 + net/l2tp/l2tp_ip.c | 1 + net/l2tp/l2tp_ip6.c | 1 + net/netrom/af_netrom.c | 14 +---------- net/packet/af_packet.c | 7 ++---- net/qrtr/qrtr.c | 4 +--- net/rose/af_rose.c | 7 +----- net/sctp/ipv6.c | 1 + net/sctp/protocol.c | 1 + net/socket.c | 48 +++++++++++-------------------------- net/x25/af_x25.c | 27 +-------------------- 33 files changed, 75 insertions(+), 232 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index c606c72311d0..50bf5206ead6 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -161,6 +161,8 @@ struct proto_ops { int (*compat_ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #endif + int (*gettstamp) (struct socket *sock, void __user *userstamp, + bool timeval, bool time32); int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, diff --git a/include/net/compat.h b/include/net/compat.h index 4c6d75612b6c..f277653c7e17 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -30,9 +30,6 @@ struct compat_cmsghdr { compat_int_t cmsg_type; }; -int compat_sock_get_timestamp(struct sock *, struct timeval __user *); -int compat_sock_get_timestampns(struct sock *, struct timespec __user *); - #else /* defined(CONFIG_COMPAT) */ /* * To avoid compiler warnings: diff --git a/include/net/sock.h b/include/net/sock.h index bdd77bbce7d8..784cd19d5ff7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1614,6 +1614,8 @@ int sock_setsockopt(struct socket *sock, int level, int op, int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); +int sock_gettstamp(struct socket *sock, void __user *userstamp, + bool timeval, bool time32); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, @@ -2503,8 +2505,6 @@ static inline bool sk_listener(const struct sock *sk) } void sock_enable_timestamp(struct sock *sk, int flag); -int sock_get_timestamp(struct sock *, struct timeval __user *); -int sock_get_timestampns(struct sock *, struct timespec __user *); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 709d2542f729..e2511027d19b 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1806,12 +1806,6 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = put_user(amount, (int __user *)argp); break; } - case SIOCGSTAMP: - rc = sock_get_timestamp(sk, argp); - break; - case SIOCGSTAMPNS: - rc = sock_get_timestampns(sk, argp); - break; /* Routing */ case SIOCADDRT: case SIOCDELRT: @@ -1871,6 +1865,7 @@ static const struct proto_ops atalk_dgram_ops = { .getname = atalk_getname, .poll = datagram_poll, .ioctl = atalk_ioctl, + .gettstamp = sock_gettstamp, #ifdef CONFIG_COMPAT .compat_ioctl = atalk_compat_ioctl, #endif diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 2ff0e5e470e3..d955b683aa7c 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -81,22 +81,6 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, (int __user *)argp) ? -EFAULT : 0; goto done; } - case SIOCGSTAMP: /* borrowed from IP */ -#ifdef CONFIG_COMPAT - if (compat) - error = compat_sock_get_timestamp(sk, argp); - else -#endif - error = sock_get_timestamp(sk, argp); - goto done; - case SIOCGSTAMPNS: /* borrowed from IP */ -#ifdef CONFIG_COMPAT - if (compat) - error = compat_sock_get_timestampns(sk, argp); - else -#endif - error = sock_get_timestampns(sk, argp); - goto done; case ATM_SETSC: net_warn_ratelimited("ATM_SETSC is obsolete; used by %s:%d\n", current->comm, task_pid_nr(current)); diff --git a/net/atm/pvc.c b/net/atm/pvc.c index 2cb10af16afc..02bd2a436bdf 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -118,6 +118,7 @@ static const struct proto_ops pvc_proto_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = vcc_compat_ioctl, #endif + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = pvc_shutdown, .setsockopt = pvc_setsockopt, diff --git a/net/atm/svc.c b/net/atm/svc.c index 2f91b766ac42..908cbb8654f5 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -641,6 +641,7 @@ static const struct proto_ops svc_proto_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = svc_compat_ioctl, #endif + .gettstamp = sock_gettstamp, .listen = svc_listen, .shutdown = svc_shutdown, .setsockopt = svc_setsockopt, diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 5d01edf8d819..449e7b7190c1 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1714,14 +1714,6 @@ static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } - case SIOCGSTAMP: - res = sock_get_timestamp(sk, argp); - break; - - case SIOCGSTAMPNS: - res = sock_get_timestampns(sk, argp); - break; - case SIOCAX25ADDUID: /* Add a uid to the uid/call map table */ case SIOCAX25DELUID: /* Delete a uid from the uid/call map table */ case SIOCAX25GETUID: { @@ -1950,6 +1942,7 @@ static const struct proto_ops ax25_proto_ops = { .getname = ax25_getname, .poll = datagram_poll, .ioctl = ax25_ioctl, + .gettstamp = sock_gettstamp, .listen = ax25_listen, .shutdown = ax25_shutdown, .setsockopt = ax25_setsockopt, diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 8d12198eaa94..94ddf19998c7 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -521,14 +521,6 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) err = put_user(amount, (int __user *) arg); break; - case SIOCGSTAMP: - err = sock_get_timestamp(sk, (struct timeval __user *) arg); - break; - - case SIOCGSTAMPNS: - err = sock_get_timestampns(sk, (struct timespec __user *) arg); - break; - default: err = -ENOIOCTLCMD; break; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index a3a2cd55e23a..dcb14abebeba 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1655,6 +1655,7 @@ static const struct proto_ops l2cap_sock_ops = { .recvmsg = l2cap_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, + .gettstamp = sock_gettstamp, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = l2cap_sock_shutdown, diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index b1f49fcc0478..90bb53aa4bee 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -1039,6 +1039,7 @@ static const struct proto_ops rfcomm_sock_ops = { .setsockopt = rfcomm_sock_setsockopt, .getsockopt = rfcomm_sock_getsockopt, .ioctl = rfcomm_sock_ioctl, + .gettstamp = sock_gettstamp, .poll = bt_sock_poll, .socketpair = sock_no_socketpair, .mmap = sock_no_mmap diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index d892b7c3cc42..b91d6b440fdf 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1190,6 +1190,7 @@ static const struct proto_ops sco_sock_ops = { .recvmsg = sco_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, + .gettstamp = sock_gettstamp, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = sco_sock_shutdown, diff --git a/net/can/af_can.c b/net/can/af_can.c index 1684ba5b51eb..e8fd5dc1780a 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -89,13 +89,7 @@ static atomic_t skbcounter = ATOMIC_INIT(0); int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { - struct sock *sk = sock->sk; - switch (cmd) { - - case SIOCGSTAMP: - return sock_get_timestamp(sk, (struct timeval __user *)arg); - default: return -ENOIOCTLCMD; } diff --git a/net/can/bcm.c b/net/can/bcm.c index 79bb8afa9c0c..a34ee52f19ea 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1689,6 +1689,7 @@ static const struct proto_ops bcm_ops = { .getname = sock_no_getname, .poll = datagram_poll, .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = sock_no_setsockopt, diff --git a/net/can/raw.c b/net/can/raw.c index c70207537488..afcbff063a67 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -846,6 +846,7 @@ static const struct proto_ops raw_ops = { .getname = raw_getname, .poll = datagram_poll, .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = raw_setsockopt, diff --git a/net/compat.c b/net/compat.c index eeea5eb71639..a031bd333092 100644 --- a/net/compat.c +++ b/net/compat.c @@ -395,63 +395,6 @@ COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __compat_sys_setsockopt(fd, level, optname, optval, optlen); } -int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) -{ - struct compat_timeval __user *ctv; - int err; - struct timeval tv; - - if (COMPAT_USE_64BIT_TIME) - return sock_get_timestamp(sk, userstamp); - - ctv = (struct compat_timeval __user *) userstamp; - err = -ENOENT; - sock_enable_timestamp(sk, SOCK_TIMESTAMP); - tv = ktime_to_timeval(sock_read_timestamp(sk)); - - if (tv.tv_sec == -1) - return err; - if (tv.tv_sec == 0) { - ktime_t kt = ktime_get_real(); - sock_write_timestamp(sk, kt); - tv = ktime_to_timeval(kt); - } - err = 0; - if (put_user(tv.tv_sec, &ctv->tv_sec) || - put_user(tv.tv_usec, &ctv->tv_usec)) - err = -EFAULT; - return err; -} -EXPORT_SYMBOL(compat_sock_get_timestamp); - -int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) -{ - struct compat_timespec __user *ctv; - int err; - struct timespec ts; - - if (COMPAT_USE_64BIT_TIME) - return sock_get_timestampns (sk, userstamp); - - ctv = (struct compat_timespec __user *) userstamp; - err = -ENOENT; - sock_enable_timestamp(sk, SOCK_TIMESTAMP); - ts = ktime_to_timespec(sock_read_timestamp(sk)); - if (ts.tv_sec == -1) - return err; - if (ts.tv_sec == 0) { - ktime_t kt = ktime_get_real(); - sock_write_timestamp(sk, kt); - ts = ktime_to_timespec(kt); - } - err = 0; - if (put_user(ts.tv_sec, &ctv->tv_sec) || - put_user(ts.tv_nsec, &ctv->tv_nsec)) - err = -EFAULT; - return err; -} -EXPORT_SYMBOL(compat_sock_get_timestampns); - static int __compat_sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) diff --git a/net/core/sock.c b/net/core/sock.c index 067878a1e4c5..443b98d05f1e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2977,39 +2977,44 @@ bool lock_sock_fast(struct sock *sk) } EXPORT_SYMBOL(lock_sock_fast); -int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) +int sock_gettstamp(struct socket *sock, void __user *userstamp, + bool timeval, bool time32) { - struct timeval tv; + struct sock *sk = sock->sk; + struct timespec64 ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - tv = ktime_to_timeval(sock_read_timestamp(sk)); - if (tv.tv_sec == -1) + ts = ktime_to_timespec64(sock_read_timestamp(sk)); + if (ts.tv_sec == -1) return -ENOENT; - if (tv.tv_sec == 0) { + if (ts.tv_sec == 0) { ktime_t kt = ktime_get_real(); - sock_write_timestamp(sk, kt); - tv = ktime_to_timeval(kt); + sock_write_timestamp(sk, kt);; + ts = ktime_to_timespec64(kt); } - return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0; -} -EXPORT_SYMBOL(sock_get_timestamp); -int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) -{ - struct timespec ts; + if (timeval) + ts.tv_nsec /= 1000; - sock_enable_timestamp(sk, SOCK_TIMESTAMP); - ts = ktime_to_timespec(sock_read_timestamp(sk)); - if (ts.tv_sec == -1) - return -ENOENT; - if (ts.tv_sec == 0) { - ktime_t kt = ktime_get_real(); - sock_write_timestamp(sk, kt); - ts = ktime_to_timespec(sk->sk_stamp); +#ifdef CONFIG_COMPAT_32BIT_TIME + if (time32) + return put_old_timespec32(&ts, userstamp); +#endif +#ifdef CONFIG_SPARC64 + /* beware of padding in sparc64 timeval */ + if (timeval && !in_compat_syscall()) { + struct __kernel_old_timeval __user tv = { + .tv_sec = ts.tv_sec; + .tv_usec = ts.tv_nsec; + }; + if (copy_to_user(userstamp, &tv, sizeof(tv)) + return -EFAULT; + return 0; } - return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0; +#endif + return put_timespec64(&ts, userstamp); } -EXPORT_SYMBOL(sock_get_timestampns); +EXPORT_SYMBOL(sock_gettstamp); void sock_enable_timestamp(struct sock *sk, int flag) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 26a21d97b6b0..004535e4c070 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -991,6 +991,7 @@ static const struct proto_ops inet_dccp_ops = { /* FIXME: work on tcp_poll to rename it to inet_csk_poll */ .poll = dccp_poll, .ioctl = inet_ioctl, + .gettstamp = sock_gettstamp, /* FIXME: work on inet_listen to rename it to sock_common_listen */ .listen = inet_dccp_listen, .shutdown = inet_shutdown, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 57d84e9b7b6f..c4e4d1301062 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1075,6 +1075,7 @@ static const struct proto_ops inet6_dccp_ops = { .getname = inet6_getname, .poll = dccp_poll, .ioctl = inet6_ioctl, + .gettstamp = sock_gettstamp, .listen = inet_dccp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index bc6b912603f1..ce2dfb997537 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -164,10 +164,6 @@ static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd, struct sock *sk = sock->sk; switch (cmd) { - case SIOCGSTAMP: - return sock_get_timestamp(sk, (struct timeval __user *)arg); - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, (struct timespec __user *)arg); case SIOCGIFADDR: case SIOCSIFADDR: return ieee802154_dev_ioctl(sk, (struct ifreq __user *)arg, @@ -426,6 +422,7 @@ static const struct proto_ops ieee802154_raw_ops = { .getname = sock_no_getname, .poll = datagram_poll, .ioctl = ieee802154_sock_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = sock_common_setsockopt, @@ -988,6 +985,7 @@ static const struct proto_ops ieee802154_dgram_ops = { .getname = sock_no_getname, .poll = datagram_poll, .ioctl = ieee802154_sock_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = sock_common_setsockopt, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 08a8430f5647..5183a2daba64 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -915,12 +915,6 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct rtentry rt; switch (cmd) { - case SIOCGSTAMP: - err = sock_get_timestamp(sk, (struct timeval __user *)arg); - break; - case SIOCGSTAMPNS: - err = sock_get_timestampns(sk, (struct timespec __user *)arg); - break; case SIOCADDRT: case SIOCDELRT: if (copy_from_user(&rt, p, sizeof(struct rtentry))) @@ -992,6 +986,7 @@ const struct proto_ops inet_stream_ops = { .getname = inet_getname, .poll = tcp_poll, .ioctl = inet_ioctl, + .gettstamp = sock_gettstamp, .listen = inet_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, @@ -1027,6 +1022,7 @@ const struct proto_ops inet_dgram_ops = { .getname = inet_getname, .poll = udp_poll, .ioctl = inet_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, @@ -1059,6 +1055,7 @@ static const struct proto_ops inet_sockraw_ops = { .getname = inet_getname, .poll = datagram_poll, .ioctl = inet_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3d1de28aaa9e..c04ae282f4e4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -547,12 +547,6 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct net *net = sock_net(sk); switch (cmd) { - case SIOCGSTAMP: - return sock_get_timestamp(sk, (struct timeval __user *)arg); - - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, (struct timespec __user *)arg); - case SIOCADDRT: case SIOCDELRT: @@ -585,6 +579,7 @@ const struct proto_ops inet6_stream_ops = { .getname = inet6_getname, .poll = tcp_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ + .gettstamp = sock_gettstamp, .listen = inet_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ @@ -618,6 +613,7 @@ const struct proto_ops inet6_dgram_ops = { .getname = inet6_getname, .poll = udp_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ + .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5a426226c762..84dbe21b71e5 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1356,6 +1356,7 @@ const struct proto_ops inet6_sockraw_ops = { .getname = inet6_getname, .poll = datagram_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ + .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index d4c60523c549..2cac910c1cd4 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -618,6 +618,7 @@ static const struct proto_ops l2tp_ip_ops = { .getname = l2tp_ip_getname, .poll = datagram_poll, .ioctl = inet_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 37a69df17cab..4ec546cc1dd6 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -752,6 +752,7 @@ static const struct proto_ops l2tp_ip6_ops = { .getname = l2tp_ip6_getname, .poll = datagram_poll, .ioctl = inet6_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 71ffd1a6dc7c..167c09e1ea90 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1199,7 +1199,6 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; void __user *argp = (void __user *)arg; - int ret; switch (cmd) { case TIOCOUTQ: { @@ -1225,18 +1224,6 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return put_user(amount, (int __user *)argp); } - case SIOCGSTAMP: - lock_sock(sk); - ret = sock_get_timestamp(sk, argp); - release_sock(sk); - return ret; - - case SIOCGSTAMPNS: - lock_sock(sk); - ret = sock_get_timestampns(sk, argp); - release_sock(sk); - return ret; - case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFDSTADDR: @@ -1362,6 +1349,7 @@ static const struct proto_ops nr_proto_ops = { .getname = nr_getname, .poll = datagram_poll, .ioctl = nr_ioctl, + .gettstamp = sock_gettstamp, .listen = nr_listen, .shutdown = sock_no_shutdown, .setsockopt = nr_setsockopt, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 08fe8b79c0bf..5c4a118d6f96 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4075,11 +4075,6 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } - case SIOCGSTAMP: - return sock_get_timestamp(sk, (struct timeval __user *)arg); - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, (struct timespec __user *)arg); - #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: @@ -4455,6 +4450,7 @@ static const struct proto_ops packet_ops_spkt = { .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = sock_no_setsockopt, @@ -4476,6 +4472,7 @@ static const struct proto_ops packet_ops = { .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, + .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index b37e6e0a1026..7c5e8292cc0a 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -968,9 +968,6 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } break; - case SIOCGSTAMP: - rc = sock_get_timestamp(sk, argp); - break; case SIOCADDRT: case SIOCDELRT: case SIOCSIFADDR: @@ -1033,6 +1030,7 @@ static const struct proto_ops qrtr_proto_ops = { .recvmsg = qrtr_recvmsg, .getname = qrtr_getname, .ioctl = qrtr_ioctl, + .gettstamp = sock_gettstamp, .poll = datagram_poll, .shutdown = sock_no_shutdown, .setsockopt = sock_no_setsockopt, diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index c96f63ffe31e..e274bc6e1458 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1301,12 +1301,6 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return put_user(amount, (unsigned int __user *) argp); } - case SIOCGSTAMP: - return sock_get_timestamp(sk, (struct timeval __user *) argp); - - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, (struct timespec __user *) argp); - case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFDSTADDR: @@ -1474,6 +1468,7 @@ static const struct proto_ops rose_proto_ops = { .getname = rose_getname, .poll = datagram_poll, .ioctl = rose_ioctl, + .gettstamp = sock_gettstamp, .listen = rose_listen, .shutdown = sock_no_shutdown, .setsockopt = rose_setsockopt, diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 6200cd2b4b99..188c47eb206e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -1030,6 +1030,7 @@ static const struct proto_ops inet6_seqpacket_ops = { .getname = sctp_getname, .poll = sctp_poll, .ioctl = inet6_ioctl, + .gettstamp = sock_gettstamp, .listen = sctp_inet_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 951afdeea5e9..f0631bf486b6 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1026,6 +1026,7 @@ static const struct proto_ops inet_seqpacket_ops = { .getname = inet_getname, /* Semantics are different. */ .poll = sctp_poll, .ioctl = inet_ioctl, + .gettstamp = sock_gettstamp, .listen = sctp_inet_listen, .shutdown = inet_shutdown, /* Looks harmless. */ .setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */ diff --git a/net/socket.c b/net/socket.c index 8255f5bda0aa..ab624d42ead5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1164,6 +1164,15 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; + case SIOCGSTAMP: + case SIOCGSTAMPNS: + if (!sock->ops->gettstamp) { + err = -ENOIOCTLCMD; + break; + } + err = sock->ops->gettstamp(sock, argp, + cmd == SIOCGSTAMP, false); + break; default: err = sock_do_ioctl(net, sock, cmd, arg); break; @@ -2916,38 +2925,6 @@ void socket_seq_show(struct seq_file *seq) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_COMPAT -static int do_siocgstamp(struct net *net, struct socket *sock, - unsigned int cmd, void __user *up) -{ - mm_segment_t old_fs = get_fs(); - struct timeval ktv; - int err; - - set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); - set_fs(old_fs); - if (!err) - err = compat_put_timeval(&ktv, up); - - return err; -} - -static int do_siocgstampns(struct net *net, struct socket *sock, - unsigned int cmd, void __user *up) -{ - mm_segment_t old_fs = get_fs(); - struct timespec kts; - int err; - - set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); - set_fs(old_fs); - if (!err) - err = compat_put_timespec(&kts, up); - - return err; -} - static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) { struct compat_ifconf ifc32; @@ -3348,9 +3325,12 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCDELRT: return routing_ioctl(net, sock, cmd, argp); case SIOCGSTAMP: - return do_siocgstamp(net, sock, cmd, argp); case SIOCGSTAMPNS: - return do_siocgstampns(net, sock, cmd, argp); + if (!sock->ops->gettstamp) + return -ENOIOCTLCMD; + return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP, + !COMPAT_USE_64BIT_TIME); + case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 20a511398389..0ea48a52ce79 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1398,18 +1398,6 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } - case SIOCGSTAMP: - rc = -EINVAL; - if (sk) - rc = sock_get_timestamp(sk, - (struct timeval __user *)argp); - break; - case SIOCGSTAMPNS: - rc = -EINVAL; - if (sk) - rc = sock_get_timestampns(sk, - (struct timespec __user *)argp); - break; case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFDSTADDR: @@ -1681,8 +1669,6 @@ static int compat_x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); - struct sock *sk = sock->sk; - int rc = -ENOIOCTLCMD; switch(cmd) { @@ -1690,18 +1676,6 @@ static int compat_x25_ioctl(struct socket *sock, unsigned int cmd, case TIOCINQ: rc = x25_ioctl(sock, cmd, (unsigned long)argp); break; - case SIOCGSTAMP: - rc = -EINVAL; - if (sk) - rc = compat_sock_get_timestamp(sk, - (struct timeval __user*)argp); - break; - case SIOCGSTAMPNS: - rc = -EINVAL; - if (sk) - rc = compat_sock_get_timestampns(sk, - (struct timespec __user*)argp); - break; case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFDSTADDR: @@ -1765,6 +1739,7 @@ static const struct proto_ops x25_proto_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = compat_x25_ioctl, #endif + .gettstamp = sock_gettstamp, .listen = x25_listen, .shutdown = sock_no_shutdown, .setsockopt = x25_setsockopt, -- cgit v1.2.3-71-gd317 From 7df737e991069d75eec1ded1c8b37e81b8c54df9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 19 Apr 2019 07:44:54 -0700 Subject: bpf: remove global variables Move three global variables protected by bpf_verifier_lock into 'struct bpf_verifier_env' to allow parallel verification. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 5 +++++ kernel/bpf/verifier.c | 25 +++++++++++++------------ 2 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b3ab61fe1932..1305ccbd8fe6 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -295,6 +295,11 @@ struct bpf_verifier_env { const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct { + int *insn_state; + int *insn_stack; + int cur_stack; + } cfg; u32 subprog_cnt; /* number of instructions analyzed by the verifier */ u32 insn_processed; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index db301e9b5295..5f0eb5bd5589 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5369,10 +5369,6 @@ enum { #define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L) -static int *insn_stack; /* stack of insns to process */ -static int cur_stack; /* current stack index */ -static int *insn_state; - /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction @@ -5380,6 +5376,9 @@ static int *insn_state; */ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { + int *insn_stack = env->cfg.insn_stack; + int *insn_state = env->cfg.insn_state; + if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) return 0; @@ -5400,9 +5399,9 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) /* tree-edge */ insn_state[t] = DISCOVERED | e; insn_state[w] = DISCOVERED; - if (cur_stack >= env->prog->len) + if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; - insn_stack[cur_stack++] = w; + insn_stack[env->cfg.cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { verbose_linfo(env, t, "%d: ", t); @@ -5426,14 +5425,15 @@ static int check_cfg(struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; + int *insn_stack, *insn_state; int ret = 0; int i, t; - insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; - insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_stack) { kvfree(insn_state); return -ENOMEM; @@ -5441,12 +5441,12 @@ static int check_cfg(struct bpf_verifier_env *env) insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ - cur_stack = 1; + env->cfg.cur_stack = 1; peek_stack: - if (cur_stack == 0) + if (env->cfg.cur_stack == 0) goto check_state; - t = insn_stack[cur_stack - 1]; + t = insn_stack[env->cfg.cur_stack - 1]; if (BPF_CLASS(insns[t].code) == BPF_JMP || BPF_CLASS(insns[t].code) == BPF_JMP32) { @@ -5515,7 +5515,7 @@ peek_stack: mark_explored: insn_state[t] = EXPLORED; - if (cur_stack-- <= 0) { + if (env->cfg.cur_stack-- <= 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; @@ -5535,6 +5535,7 @@ check_state: err_free: kvfree(insn_state); kvfree(insn_stack); + env->cfg.insn_state = env->cfg.insn_stack = NULL; return ret; } -- cgit v1.2.3-71-gd317 From 756e161993824961fad4ba62c40045d9ab65bdb8 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Fri, 8 Mar 2019 09:15:43 +0800 Subject: mmc: add SDIO identifiers for MediaTek Bluetooth devices The SDIO identifier for MediaTek Bluetooth devices were defined in the MediaTek Bluetooth driver. Moving the definitions in MMC header file seems common sense. Signed-off-by: Sean Wang Signed-off-by: Marcel Holtmann --- include/linux/mmc/sdio_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 4332199c71c2..d1a5d5df02f5 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -59,6 +59,8 @@ #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 #define SDIO_DEVICE_ID_MARVELL_8887WLAN 0x9134 +#define SDIO_VENDOR_ID_MEDIATEK 0x037a + #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 -- cgit v1.2.3-71-gd317 From db0a390835209c1c5dce7669de3d23a8cba10f34 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Thu, 14 Mar 2019 05:01:58 +0800 Subject: mmc: sdio: Add helper macro for sdio_driver boilerplate This patch introduces the module_sdio_driver macro which is a convenience macro for SDIO driver modules similar to module_usb_driver. It is intended to be used by drivers which init/exit section does nothing but register/ unregister the SDIO driver. By using this macro it is possible to eliminate a few lines of boilerplate code per SDIO driver. Suggested-by: Marcel Holtmann Signed-off-by: Sean Wang Acked-by: Ulf Hansson Signed-off-by: Marcel Holtmann --- include/linux/mmc/sdio_func.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 97ca105347a6..5685805533b5 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -111,6 +111,18 @@ struct sdio_driver { extern int sdio_register_driver(struct sdio_driver *); extern void sdio_unregister_driver(struct sdio_driver *); +/** + * module_sdio_driver() - Helper macro for registering a SDIO driver + * @__sdio_driver: sdio_driver struct + * + * Helper macro for SDIO drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_sdio_driver(__sdio_driver) \ + module_driver(__sdio_driver, sdio_register_driver, \ + sdio_unregister_driver) + /* * SDIO I/O operations */ -- cgit v1.2.3-71-gd317 From 089b19a9204fc090793d389a265f54124eacb05d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 22 Apr 2019 08:55:44 -0700 Subject: flow_dissector: switch kernel context to struct bpf_flow_dissector struct bpf_flow_dissector has a small subset of sk_buff fields that flow dissector BPF program is allowed to access and an optional pointer to real skb. Real skb is used only in bpf_skb_load_bytes helper to read non-linear data. The real motivation for this is to be able to call flow dissector from eth_get_headlen context where we don't have an skb and need to dissect raw bytes. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 4 ++ include/net/flow_dissector.h | 7 +++ include/net/sch_generic.h | 11 ++--- net/bpf/test_run.c | 4 -- net/core/filter.c | 105 +++++++++++++++++++++++++++++++++---------- net/core/flow_dissector.c | 45 +++++++++---------- 6 files changed, 117 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f42942a443b..2b7b8228c5c3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1275,6 +1275,10 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) } #endif +struct bpf_flow_dissector; +bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen); + struct bpf_flow_keys; bool __skb_flow_bpf_dissect(struct bpf_prog *prog, const struct sk_buff *skb, diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 2b26979efb48..7c5a8d9a8d2a 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -305,4 +305,11 @@ static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissec return ((char *)target_container) + flow_dissector->offset[key_id]; } +struct bpf_flow_dissector { + struct bpf_flow_keys *flow_keys; + const struct sk_buff *skb; + void *data; + void *data_end; +}; + #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e8f85cd2afce..21f434f3ac9e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -364,13 +364,10 @@ struct tcf_proto { }; struct qdisc_skb_cb { - union { - struct { - unsigned int pkt_len; - u16 slave_dev_queue_mapping; - u16 tc_classid; - }; - struct bpf_flow_keys *flow_keys; + struct { + unsigned int pkt_len; + u16 slave_dev_queue_mapping; + u16 tc_classid; }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2221573dacdb..006ad865f7fb 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -382,7 +382,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, u32 repeat = kattr->test.repeat; struct bpf_flow_keys flow_keys; u64 time_start, time_spent = 0; - struct bpf_skb_data_end *cb; u32 retval, duration; struct sk_buff *skb; struct sock *sk; @@ -423,9 +422,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, current->nsproxy->net_ns->loopback_dev); skb_reset_network_header(skb); - cb = (struct bpf_skb_data_end *)skb->cb; - cb->qdisc_cb.flow_keys = &flow_keys; - if (!repeat) repeat = 1; diff --git a/net/core/filter.c b/net/core/filter.c index fa8fb0548217..edb3a7c22f6c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1730,6 +1730,40 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_SIZE, }; +BPF_CALL_4(bpf_flow_dissector_load_bytes, + const struct bpf_flow_dissector *, ctx, u32, offset, + void *, to, u32, len) +{ + void *ptr; + + if (unlikely(offset > 0xffff)) + goto err_clear; + + if (unlikely(!ctx->skb)) + goto err_clear; + + ptr = skb_header_pointer(ctx->skb, offset, len, to); + if (unlikely(!ptr)) + goto err_clear; + if (ptr != to) + memcpy(to, ptr, len); + + return 0; +err_clear: + memset(to, 0, len); + return -EFAULT; +} + +static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { + .func = bpf_flow_dissector_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { @@ -6121,7 +6155,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: - return &bpf_skb_load_bytes_proto; + return &bpf_flow_dissector_load_bytes_proto; default: return bpf_base_func_proto(func_id); } @@ -6248,9 +6282,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): - if (size != sizeof(__u64)) - return false; - break; + return false; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; @@ -6285,7 +6317,6 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): @@ -6312,7 +6343,6 @@ static bool cg_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): @@ -6358,7 +6388,6 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; @@ -6601,7 +6630,6 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -6803,7 +6831,6 @@ static bool sk_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; @@ -6877,24 +6904,65 @@ static bool flow_dissector_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { + const int size_default = sizeof(__u32); + + if (off < 0 || off >= sizeof(struct __sk_buff)) + return false; + if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): + if (size != size_default) + return false; info->reg_type = PTR_TO_PACKET; - break; + return true; case bpf_ctx_range(struct __sk_buff, data_end): + if (size != size_default) + return false; info->reg_type = PTR_TO_PACKET_END; - break; + return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): + if (size != sizeof(__u64)) + return false; info->reg_type = PTR_TO_FLOW_KEYS; - break; + return true; default: return false; } +} - return bpf_skb_is_valid_access(off, size, type, prog, info); +static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) + +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct __sk_buff, data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, data)); + break; + + case offsetof(struct __sk_buff, data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, data_end)); + break; + + case offsetof(struct __sk_buff, flow_keys): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, flow_keys)); + break; + } + + return insn - insn_buf; } static u32 bpf_convert_ctx_access(enum bpf_access_type type, @@ -7201,15 +7269,6 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, skc_num, 2, target_size)); break; - case offsetof(struct __sk_buff, flow_keys): - off = si->off; - off -= offsetof(struct __sk_buff, flow_keys); - off += offsetof(struct sk_buff, cb); - off += offsetof(struct qdisc_skb_cb, flow_keys); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, - si->src_reg, off); - break; - case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); @@ -8214,7 +8273,7 @@ const struct bpf_prog_ops sk_msg_prog_ops = { const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, - .convert_ctx_access = bpf_convert_ctx_access, + .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 795449713ba4..ef6d9443cc75 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -688,39 +688,34 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, struct flow_dissector *flow_dissector, struct bpf_flow_keys *flow_keys) { - struct bpf_skb_data_end cb_saved; - struct bpf_skb_data_end *cb; - u32 result; - - /* Note that even though the const qualifier is discarded - * throughout the execution of the BPF program, all changes(the - * control block) are reverted after the BPF program returns. - * Therefore, __skb_flow_dissect does not alter the skb. - */ - - cb = (struct bpf_skb_data_end *)skb->cb; + struct bpf_flow_dissector ctx = { + .flow_keys = flow_keys, + .skb = skb, + .data = skb->data, + .data_end = skb->data + skb_headlen(skb), + }; + + return bpf_flow_dissect(prog, &ctx, skb->protocol, + skb_network_offset(skb), skb_headlen(skb)); +} - /* Save Control Block */ - memcpy(&cb_saved, cb, sizeof(cb_saved)); - memset(cb, 0, sizeof(*cb)); +bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen) +{ + struct bpf_flow_keys *flow_keys = ctx->flow_keys; + u32 result; /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); - cb->qdisc_cb.flow_keys = flow_keys; - flow_keys->n_proto = skb->protocol; - flow_keys->nhoff = skb_network_offset(skb); + flow_keys->n_proto = proto; + flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; - bpf_compute_data_pointers((struct sk_buff *)skb); - result = BPF_PROG_RUN(prog, skb); - - /* Restore state */ - memcpy(cb, &cb_saved, sizeof(cb_saved)); + result = BPF_PROG_RUN(prog, ctx); - flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, - skb_network_offset(skb), skb->len); + flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, - flow_keys->nhoff, skb->len); + flow_keys->nhoff, hlen); return result == BPF_OK; } -- cgit v1.2.3-71-gd317 From 3cbf4ffba5eeec60f82868a5facc1962d8a44d00 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 22 Apr 2019 08:55:46 -0700 Subject: net: plumb network namespace into __skb_flow_dissect This new argument will be used in the next patches for the eth_get_headlen use case. eth_get_headlen calls flow dissector with only data (without skb) so there is currently no way to pull attached BPF flow dissector program. With this new argument, we can amend the callers to explicitly pass network namespace so we can use attached BPF program. Signed-off-by: Stanislav Fomichev Reviewed-by: Saeed Mahameed Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 19 +++++++++++-------- net/core/flow_dissector.c | 27 +++++++++++++++++---------- net/ethernet/eth.c | 5 +++-- 3 files changed, 31 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2b7b8228c5c3..b466fbface2e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1284,7 +1284,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, const struct sk_buff *skb, struct flow_dissector *flow_dissector, struct bpf_flow_keys *flow_keys); -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, @@ -1294,8 +1295,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { - return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, flow_dissector, + target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, @@ -1303,18 +1304,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_dissector, flow, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, + flow, NULL, 0, 0, 0, flags); } static inline bool -skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb, +skb_flow_dissect_flow_keys_basic(const struct net *net, + const struct sk_buff *skb, struct flow_keys_basic *flow, void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, + return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } @@ -2492,7 +2494,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb) if (skb_transport_header_was_set(skb)) return; - if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) + if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ef6d9443cc75..f32c7e737fc6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -722,6 +722,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, /** * __skb_flow_dissect - extract the flow_keys struct and return it + * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into @@ -738,7 +739,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, * * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, @@ -797,13 +799,17 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct bpf_prog *attached = NULL; rcu_read_lock(); + if (!net) { + if (skb->dev) + net = dev_net(skb->dev); + else if (skb->sk) + net = sock_net(skb->sk); + else + WARN_ON_ONCE(1); + } - if (skb->dev) - attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog); - else if (skb->sk) - attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog); - else - WARN_ON_ONCE(1); + if (net) + attached = rcu_dereference(net->flow_dissector_prog); if (attached) { ret = __skb_flow_bpf_dissect(attached, skb, @@ -1405,8 +1411,8 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb) __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); - __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, - NULL, 0, 0, 0, + __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, + &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(&keys, hashrnd); @@ -1507,7 +1513,8 @@ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; - if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index f7a3d7a171c7..1e439549c419 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -136,8 +136,9 @@ u32 eth_get_headlen(void *data, unsigned int len) return len; /* parse any remaining L2/L3 headers, check for L4 */ - if (!skb_flow_dissect_flow_keys_basic(NULL, &keys, data, eth->h_proto, - sizeof(*eth), len, flags)) + if (!skb_flow_dissect_flow_keys_basic(NULL, NULL, &keys, data, + eth->h_proto, sizeof(*eth), + len, flags)) return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ -- cgit v1.2.3-71-gd317 From 9b52e3f267a6835efd50ed9002d530666d16a411 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 22 Apr 2019 08:55:47 -0700 Subject: flow_dissector: handle no-skb use case When called without skb, gather all required data from the __skb_flow_dissect's arguments and use recently introduces no-skb mode of bpf flow dissector. Note: WARN_ON_ONCE(!net) will now trigger for eth_get_headlen users. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 5 ----- net/core/flow_dissector.c | 52 +++++++++++++++++++++++------------------------ 2 files changed, 25 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b466fbface2e..998256c2820b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1279,11 +1279,6 @@ struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen); -struct bpf_flow_keys; -bool __skb_flow_bpf_dissect(struct bpf_prog *prog, - const struct sk_buff *skb, - struct flow_dissector *flow_dissector, - struct bpf_flow_keys *flow_keys); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index f32c7e737fc6..fac712cee9d5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -683,22 +683,6 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, } } -bool __skb_flow_bpf_dissect(struct bpf_prog *prog, - const struct sk_buff *skb, - struct flow_dissector *flow_dissector, - struct bpf_flow_keys *flow_keys) -{ - struct bpf_flow_dissector ctx = { - .flow_keys = flow_keys, - .skb = skb, - .data = skb->data, - .data_end = skb->data + skb_headlen(skb), - }; - - return bpf_flow_dissect(prog, &ctx, skb->protocol, - skb_network_offset(skb), skb_headlen(skb)); -} - bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen) { @@ -753,6 +737,7 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; + struct bpf_prog *attached = NULL; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; int num_hdrs = 0; @@ -795,26 +780,39 @@ bool __skb_flow_dissect(const struct net *net, target_container); if (skb) { - struct bpf_flow_keys flow_keys; - struct bpf_prog *attached = NULL; - - rcu_read_lock(); if (!net) { if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); - else - WARN_ON_ONCE(1); } + } - if (net) - attached = rcu_dereference(net->flow_dissector_prog); + WARN_ON_ONCE(!net); + if (net) { + rcu_read_lock(); + attached = rcu_dereference(net->flow_dissector_prog); if (attached) { - ret = __skb_flow_bpf_dissect(attached, skb, - flow_dissector, - &flow_keys); + struct bpf_flow_keys flow_keys; + struct bpf_flow_dissector ctx = { + .flow_keys = &flow_keys, + .data = data, + .data_end = data + hlen, + }; + __be16 n_proto = proto; + + if (skb) { + ctx.skb = skb; + /* we can't use 'proto' in the skb case + * because it might be set to skb->vlan_proto + * which has been pulled from the data + */ + n_proto = skb->protocol; + } + + ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, + hlen); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); -- cgit v1.2.3-71-gd317 From c43f1255b866b423d2381f77eaa2cbc64a9c49aa Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 22 Apr 2019 08:55:48 -0700 Subject: net: pass net_device argument to the eth_get_headlen Update all users of eth_get_headlen to pass network device, fetch network namespace from it and pass it down to the flow dissector. This commit is a noop until administrator inserts BPF flow dissector program. Cc: Maxim Krasnyansky Cc: Saeed Mahameed Cc: Jeff Kirsher Cc: intel-wired-lan@lists.osuosl.org Cc: Yisen Zhuang Cc: Salil Mehta Cc: Michael Chan Cc: Igor Russkikh Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 ++- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 ++- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- drivers/net/tun.c | 3 ++- include/linux/etherdevice.h | 2 +- net/ethernet/eth.c | 5 +++-- 16 files changed, 22 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index c64e2fb5a4f1..350e385528fd 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -354,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, hdr_len = buff->len; if (hdr_len > AQ_CFG_RX_HDR_SIZE) - hdr_len = eth_get_headlen(aq_buf_vaddr(&buff->rxdata), + hdr_len = eth_get_headlen(skb->dev, + aq_buf_vaddr(&buff->rxdata), AQ_CFG_RX_HDR_SIZE); memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata), diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6528a597367b..526f36dcb204 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -899,7 +899,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, DMA_ATTR_WEAK_ORDERING); if (unlikely(!payload)) - payload = eth_get_headlen(data_ptr, len); + payload = eth_get_headlen(bp->dev, data_ptr, len); skb = napi_alloc_skb(&rxr->bnapi->napi, payload); if (!skb) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 297b95c1b3c1..65b985acae38 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -598,7 +598,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, } else { ring->stats.seg_pkt_cnt++; - pull_len = eth_get_headlen(va, HNS_RX_HEAD_SIZE); + pull_len = eth_get_headlen(ndev, va, HNS_RX_HEAD_SIZE); memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 176d4b965709..5f7b51c6ee91 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2580,7 +2580,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length, ring->stats.seg_pkt_cnt++; u64_stats_update_end(&ring->syncp); - ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE); + ring->pull_len = eth_get_headlen(netdev, va, HNS3_RX_HEAD_SIZE); __skb_put(skb, ring->pull_len); hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len, desc_cb); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 2325cee76211..b4d970e44163 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -280,7 +280,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer, /* we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN); + pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 1a95223c9f99..e1931701cd7e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2035,7 +2035,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > I40E_RX_HDR_SIZE) - headlen = eth_get_headlen(xdp->data, I40E_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, xdp->data, + I40E_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), xdp->data, diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index b64187753ad6..cf8be63a8a4f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1315,7 +1315,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IAVF_RX_HDR_SIZE) - headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 79043fec0187..259f118c7d8b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -699,7 +699,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, /* Determine available headroom for copy */ headlen = size; if (headlen > ICE_RX_HDR_SIZE) - headlen = eth_get_headlen(va, ICE_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, va, ICE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index acbb5b4f333d..9b8a4bb25327 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8051,7 +8051,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IGB_RX_HDR_LEN) - headlen = eth_get_headlen(va, IGB_RX_HDR_LEN); + headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f79728381e8a..e58a6e0dc4d9 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1199,7 +1199,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IGC_RX_HDR_LEN) - headlen = eth_get_headlen(va, IGC_RX_HDR_LEN); + headlen = eth_get_headlen(skb->dev, va, IGC_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 60cec3540dd7..7b903206b534 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1800,7 +1800,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, * we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE); + pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 49e23afa05a2..d189ed247665 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -895,7 +895,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IXGBEVF_RX_HDR_SIZE) - headlen = eth_get_headlen(xdp->data, IXGBEVF_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, xdp->data, + IXGBEVF_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), xdp->data, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 40f3f98aa279..7b61126fcec9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -163,7 +163,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode, case MLX5_INLINE_MODE_NONE: return 0; case MLX5_INLINE_MODE_TCP_UDP: - hlen = eth_get_headlen(skb->data, skb_headlen(skb)); + hlen = eth_get_headlen(skb->dev, skb->data, skb_headlen(skb)); if (hlen == ETH_HLEN && !skb_vlan_tag_present(skb)) hlen += VLAN_HLEN; break; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 24d0220b9ba0..9d72f8c76c15 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1965,7 +1965,8 @@ drop: if (frags) { /* Exercise flow dissector code path. */ - u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb)); + u32 headlen = eth_get_headlen(tun->dev, skb->data, + skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { this_cpu_inc(tun->pcpu_stats->rx_dropped); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e2f3b21cd72a..c6c1930e28a0 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -33,7 +33,7 @@ struct device; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); -u32 eth_get_headlen(void *data, unsigned int max_len); +u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 1e439549c419..0f9863dc4d44 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -119,13 +119,14 @@ EXPORT_SYMBOL(eth_header); /** * eth_get_headlen - determine the length of header for an ethernet frame + * @dev: pointer to network device * @data: pointer to start of frame * @len: total length of frame * * Make a best effort attempt to pull the length for all of the headers for * a given frame in a linear buffer. */ -u32 eth_get_headlen(void *data, unsigned int len) +u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len) { const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG; const struct ethhdr *eth = (const struct ethhdr *)data; @@ -136,7 +137,7 @@ u32 eth_get_headlen(void *data, unsigned int len) return len; /* parse any remaining L2/L3 headers, check for L4 */ - if (!skb_flow_dissect_flow_keys_basic(NULL, NULL, &keys, data, + if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data, eth->h_proto, sizeof(*eth), len, flags)) return max_t(u32, keys.control.thoff, sizeof(*eth)); -- cgit v1.2.3-71-gd317 From a93f7fe134543649cf2e2d8fc2c50a8f4d742915 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Mon, 22 Apr 2019 21:52:23 +0800 Subject: net: phy: marvell: add new default led configure for m88e151x The default m88e151x LED configuration is 0x1177, used LED[0] for 1000M link, LED[1] for 100M link, and LED[2] for active. But for some boards, which use LED[0] for link, and LED[1] for active, prefer to be 0x1040. To be compatible with this case, this patch defines a new dev_flag, and set it before connect phy in HNS3 driver. When phy initializing, using the new LED configuration if this dev_flag is set. Signed-off-by: Jian Shen Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 3 +++ drivers/net/phy/marvell.c | 6 +++++- include/linux/marvell_phy.h | 1 + 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 12be4e293fcf..1e8134892d77 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -3,6 +3,7 @@ #include #include +#include #include "hclge_cmd.h" #include "hclge_main.h" @@ -209,6 +210,8 @@ int hclge_mac_connect_phy(struct hnae3_handle *handle) linkmode_clear_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported); + phydev->dev_flags |= MARVELL_PHY_LED0_LINK_LED1_ACTIVE; + ret = phy_connect_direct(netdev, phydev, hclge_mac_adjust_link, PHY_INTERFACE_MODE_SGMII); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 8754cb883d02..a7e8c8113d97 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -137,6 +137,7 @@ #define MII_PHY_LED_CTRL 16 #define MII_88E1121_PHY_LED_DEF 0x0030 #define MII_88E1510_PHY_LED_DEF 0x1177 +#define MII_88E1510_PHY_LED0_LINK_LED1_ACTIVE 0x1040 #define MII_M1011_PHY_STATUS 0x11 #define MII_M1011_PHY_STATUS_1000 0x8000 @@ -633,7 +634,10 @@ static void marvell_config_led(struct phy_device *phydev) * LED[2] .. Blink, Activity */ case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1510): - def_config = MII_88E1510_PHY_LED_DEF; + if (phydev->dev_flags & MARVELL_PHY_LED0_LINK_LED1_ACTIVE) + def_config = MII_88E1510_PHY_LED0_LINK_LED1_ACTIVE; + else + def_config = MII_88E1510_PHY_LED_DEF; break; default: return; diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 73d04743a2bb..af6b11d4d673 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -34,5 +34,6 @@ /* struct phy_device dev_flags definitions */ #define MARVELL_PHY_M1145_FLAGS_RESISTANCE 0x00000001 #define MARVELL_PHY_M1118_DNS323_LEDS 0x00000002 +#define MARVELL_PHY_LED0_LINK_LED1_ACTIVE 0x00000004 #endif /* _MARVELL_PHY_H */ -- cgit v1.2.3-71-gd317 From c2273219baa5097a4d7c1c162b992623534f34c1 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Thu, 14 Mar 2019 14:54:07 +0200 Subject: net/mlx5e: XDP, Inline small packets into the TX MPWQE in XDP xmit flow Upon high packet rate with multiple CPUs TX workloads, much of the HCA's resources are spent on prefetching TX descriptors, thus affecting transmission rates. This patch comes to mitigate this problem by moving some workload to the CPU and reducing the HW data prefetch overhead for small packets (<= 256B). When forwarding packets with XDP, a packet that is smaller than a certain size (set to ~256 bytes) would be sent inline within its WQE TX descrptor (mem-copied), when the hardware tx queue is congested beyond a pre-defined water-mark. This is added to better utilize the HW resources (which now makes one less packet data prefetch) and allow better scalability, on the account of CPU usage (which now 'memcpy's the packet into the WQE). To load balance between HW and CPU and get max packet rate, we use watermarks to detect how much the HW is congested and move the work loads back and forth between HW and CPU. Performance: Tested packet rate for UDP 64Byte multi-stream over two dual port ConnectX-5 100Gbps NICs. CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz * Tested with hyper-threading disabled XDP_TX: | | before | after | | | 24 rings | 51Mpps | 116Mpps | +126% | | 1 ring | 12Mpps | 12Mpps | same | XDP_REDIRECT: ** Below is the transmit rate, not the redirection rate which might be larger, and is not affected by this patch. | | before | after | | | 32 rings | 64Mpps | 92Mpps | +43% | | 1 ring | 6.4Mpps | 6.4Mpps | same | As we can see, feature significantly improves scaling, without hurting single ring performance. Signed-off-by: Shay Agroskin Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 5 +- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 22 +++++---- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h | 57 ++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 8 ++- drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 3 ++ include/linux/mlx5/qp.h | 1 + 7 files changed, 83 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index a3700c57b073..c190061763fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -409,14 +409,17 @@ struct mlx5e_xdp_info_fifo { struct mlx5e_xdp_wqe_info { u8 num_wqebbs; - u8 num_ds; + u8 num_pkts; }; struct mlx5e_xdp_mpwqe { /* Current MPWQE session */ struct mlx5e_tx_wqe *wqe; u8 ds_count; + u8 pkt_count; u8 max_ds_count; + u8 complete; + u8 inline_on; }; struct mlx5e_xdpsq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index a9075b526ab9..c3d4efbf60ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -113,7 +113,9 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) mlx5e_xdpsq_fetch_wqe(sq, &session->wqe); prefetchw(session->wqe->data); - session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; + session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; + session->pkt_count = 0; + session->complete = 0; pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); @@ -132,6 +134,9 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) MLX5E_XDP_MPW_MAX_WQEBBS); session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs; + + mlx5e_xdp_update_inline_state(sq); + stats->mpwqe++; } @@ -149,7 +154,7 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq) cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_count); wi->num_wqebbs = DIV_ROUND_UP(ds_count, MLX5_SEND_WQEBB_NUM_DS); - wi->num_ds = ds_count - MLX5E_XDP_TX_EMPTY_DS_COUNT; + wi->num_pkts = session->pkt_count; sq->pc += wi->num_wqebbs; @@ -164,11 +169,9 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; - dma_addr_t dma_addr = xdpi->dma_addr; struct xdp_frame *xdpf = xdpi->xdpf; - unsigned int dma_len = xdpf->len; - if (unlikely(sq->hw_mtu < dma_len)) { + if (unlikely(sq->hw_mtu < xdpf->len)) { stats->err++; return false; } @@ -185,9 +188,10 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, mlx5e_xdp_mpwqe_session_start(sq); } - mlx5e_xdp_mpwqe_add_dseg(sq, dma_addr, dma_len); + mlx5e_xdp_mpwqe_add_dseg(sq, xdpi, stats); - if (unlikely(session->ds_count == session->max_ds_count)) + if (unlikely(session->complete || + session->ds_count == session->max_ds_count)) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi); @@ -301,7 +305,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) sqcc += wi->num_wqebbs; - for (j = 0; j < wi->num_ds; j++) { + for (j = 0; j < wi->num_pkts; j++) { struct mlx5e_xdp_info xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo); @@ -342,7 +346,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) sq->cc += wi->num_wqebbs; - for (i = 0; i < wi->num_ds; i++) { + for (i = 0; i < wi->num_pkts; i++) { struct mlx5e_xdp_info xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index ee27a7c8cd87..858e7a2a13ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -75,16 +75,68 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) } } +/* Enable inline WQEs to shift some load from a congested HCA (HW) to + * a less congested cpu (SW). + */ +static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq) +{ + u16 outstanding = sq->xdpi_fifo_pc - sq->xdpi_fifo_cc; + struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; + +#define MLX5E_XDP_INLINE_WATERMARK_LOW 10 +#define MLX5E_XDP_INLINE_WATERMARK_HIGH 128 + + if (session->inline_on) { + if (outstanding <= MLX5E_XDP_INLINE_WATERMARK_LOW) + session->inline_on = 0; + return; + } + + /* inline is false */ + if (outstanding >= MLX5E_XDP_INLINE_WATERMARK_HIGH) + session->inline_on = 1; +} + static inline void -mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, dma_addr_t dma_addr, u16 dma_len) +mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi, + struct mlx5e_xdpsq_stats *stats) { struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; + dma_addr_t dma_addr = xdpi->dma_addr; + struct xdp_frame *xdpf = xdpi->xdpf; struct mlx5_wqe_data_seg *dseg = - (struct mlx5_wqe_data_seg *)session->wqe + session->ds_count++; + (struct mlx5_wqe_data_seg *)session->wqe + session->ds_count; + u16 dma_len = xdpf->len; + session->pkt_count++; + +#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) + + if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) { + struct mlx5_wqe_inline_seg *inline_dseg = + (struct mlx5_wqe_inline_seg *)dseg; + u16 ds_len = sizeof(*inline_dseg) + dma_len; + u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS); + + if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) { + /* Not enough space for inline wqe, send with memory pointer */ + session->complete = true; + goto no_inline; + } + + inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG); + memcpy(inline_dseg->data, xdpf->data, dma_len); + + session->ds_count += ds_cnt; + stats->inlnw++; + return; + } + +no_inline: dseg->addr = cpu_to_be64(dma_addr); dseg->byte_count = cpu_to_be32(dma_len); dseg->lkey = sq->mkey_be; + session->ds_count++; } static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, @@ -111,5 +163,4 @@ mlx5e_xdpi_fifo_pop(struct mlx5e_xdp_info_fifo *fifo) { return fifo->xi[(*fifo->cc)++ & fifo->mask]; } - #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 7ab195ac7299..23df6f486c6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1532,7 +1532,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c, dseg->lkey = sq->mkey_be; wi->num_wqebbs = 1; - wi->num_ds = 1; + wi->num_pkts = 1; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 80ee48dcc0a3..ca0ff3b3fbd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -66,6 +66,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, @@ -81,6 +82,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) }, @@ -163,6 +165,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_xdp_redirect += rq_stats->xdp_redirect; s->rx_xdp_tx_xmit += xdpsq_stats->xmit; s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe; + s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw; s->rx_xdp_tx_full += xdpsq_stats->full; s->rx_xdp_tx_err += xdpsq_stats->err; s->rx_xdp_tx_cqe += xdpsq_stats->cqes; @@ -188,7 +191,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->ch_eq_rearm += ch_stats->eq_rearm; /* xdp redirect */ s->tx_xdp_xmit += xdpsq_red_stats->xmit; - s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; + s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; + s->tx_xdp_inlnw += xdpsq_red_stats->inlnw; s->tx_xdp_full += xdpsq_red_stats->full; s->tx_xdp_err += xdpsq_red_stats->err; s->tx_xdp_cqes += xdpsq_red_stats->cqes; @@ -1250,6 +1254,7 @@ static const struct counter_desc sq_stats_desc[] = { static const struct counter_desc rq_xdpsq_stats_desc[] = { { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, @@ -1258,6 +1263,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = { static const struct counter_desc xdpsq_stats_desc[] = { { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 1f05ffa086b1..ac3c7c2a0964 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -78,6 +78,7 @@ struct mlx5e_sw_stats { u64 rx_xdp_redirect; u64 rx_xdp_tx_xmit; u64 rx_xdp_tx_mpwqe; + u64 rx_xdp_tx_inlnw; u64 rx_xdp_tx_full; u64 rx_xdp_tx_err; u64 rx_xdp_tx_cqe; @@ -93,6 +94,7 @@ struct mlx5e_sw_stats { u64 tx_cqe_err; u64 tx_xdp_xmit; u64 tx_xdp_mpwqe; + u64 tx_xdp_inlnw; u64 tx_xdp_full; u64 tx_xdp_err; u64 tx_xdp_cqes; @@ -244,6 +246,7 @@ struct mlx5e_sq_stats { struct mlx5e_xdpsq_stats { u64 xmit; u64 mpwqe; + u64 inlnw; u64 full; u64 err; /* dirtied @completion */ diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 0343c81d4c5f..3ba4edbd17a6 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -395,6 +395,7 @@ struct mlx5_wqe_signature_seg { struct mlx5_wqe_inline_seg { __be32 byte_count; + __be32 data[0]; }; enum mlx5_sig_type { -- cgit v1.2.3-71-gd317 From 9fba2b9b4f1566213a4f0cec658479d8915086fa Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Sun, 31 Mar 2019 19:44:43 +0300 Subject: net/mlx5: Expose SW ICM related device memory capabilities Add SW ICM related fields to the device memory capabilities structure and sw ownership capability in flow table properties. The currently supported SW ICM types are steering and header modify and the changes exposes the device memory capabilities for each of these two types. SW ICM memory can be allocated by SW and then be accessed by RDMA operations for direct management of the HW packet handling tables. Signed-off-by: Ariel Levkovich Reviewed-by: Eli Cohen Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 45 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 43 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 11e498442134..d96eb0916a44 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -80,6 +80,14 @@ enum { MLX5_SHARED_RESOURCE_UID = 0xffff, }; +enum { + MLX5_OBJ_TYPE_SW_ICM = 0x0008, +}; + +enum { + MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), +}; + enum { MLX5_CMD_OP_QUERY_HCA_CAP = 0x100, MLX5_CMD_OP_QUERY_ADAPTER = 0x101, @@ -357,7 +365,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 pop_vlan_2[0x1]; u8 push_vlan_2[0x1]; u8 reformat_and_vlan_action[0x1]; - u8 reserved_at_10[0x2]; + u8 reserved_at_10[0x1]; + u8 sw_owner[0x1]; u8 reformat_l3_tunnel_to_l2[0x1]; u8 reformat_l2_to_l3_tunnel[0x1]; u8 reformat_and_modify_action[0x1]; @@ -770,7 +779,19 @@ struct mlx5_ifc_device_mem_cap_bits { u8 max_memic_size[0x20]; - u8 reserved_at_c0[0x740]; + u8 steering_sw_icm_start_address[0x40]; + + u8 reserved_at_100[0x8]; + u8 log_header_modify_sw_icm_size[0x8]; + u8 reserved_at_110[0x2]; + u8 log_sw_icm_alloc_granularity[0x6]; + u8 log_steering_sw_icm_size[0x8]; + + u8 reserved_at_120[0x20]; + + u8 header_modify_sw_icm_start_address[0x40]; + + u8 reserved_at_180[0x680]; }; enum { @@ -919,6 +940,7 @@ enum { enum { MLX5_UCTX_CAP_RAW_TX = 1UL << 0, + MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, }; struct mlx5_ifc_cmd_hca_cap_bits { @@ -2920,6 +2942,7 @@ enum { MLX5_MKC_ACCESS_MODE_MTT = 0x1, MLX5_MKC_ACCESS_MODE_KLMS = 0x2, MLX5_MKC_ACCESS_MODE_KSM = 0x3, + MLX5_MKC_ACCESS_MODE_SW_ICM = 0x4, MLX5_MKC_ACCESS_MODE_MEMIC = 0x5, }; @@ -9491,6 +9514,19 @@ struct mlx5_ifc_uctx_bits { u8 reserved_at_20[0x160]; }; +struct mlx5_ifc_sw_icm_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x18]; + u8 log_sw_icm_size[0x8]; + + u8 reserved_at_60[0x20]; + + u8 sw_icm_start_addr[0x40]; + + u8 reserved_at_c0[0x140]; +}; + struct mlx5_ifc_create_umem_in_bits { u8 opcode[0x10]; u8 uid[0x10]; @@ -9528,6 +9564,11 @@ struct mlx5_ifc_destroy_uctx_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_create_sw_icm_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_sw_icm_bits sw_icm; +}; + struct mlx5_ifc_mtrc_string_db_param_bits { u8 string_db_base_address[0x20]; -- cgit v1.2.3-71-gd317 From 3e07047021d36674d9051e76454e8b6a3b599036 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Sun, 31 Mar 2019 19:44:48 +0300 Subject: net/mlx5: Expose TIR ICM address in command outbox Adding the TIR ICM address to the create_tir command outbox through which the device reports the ICM address of the newly created TIR. The TIR address can be used for direct attachment to a steering rule in SW managed steering mode. Signed-off-by: Ariel Levkovich Reviewed-by: Eli Cohen Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index d96eb0916a44..4b37519bd6a5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -6897,14 +6897,14 @@ struct mlx5_ifc_create_tis_in_bits { struct mlx5_ifc_create_tir_out_bits { u8 status[0x8]; - u8 reserved_at_8[0x18]; + u8 icm_address_63_40[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x8]; + u8 icm_address_39_32[0x8]; u8 tirn[0x18]; - u8 reserved_at_60[0x20]; + u8 icm_address_31_0[0x20]; }; struct mlx5_ifc_create_tir_in_bits { -- cgit v1.2.3-71-gd317 From 96780e4f46b2fc0fc5ae2b95957002e2c42b11d3 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Sun, 31 Mar 2019 19:44:49 +0300 Subject: net/mlx5: Introduce new TIR creation core API Introducing new TIR creation core API which allows caller to receive back from the call the full command outbox. This comes as a preparation for the next patch that will retrieve the TIR ICM address from the command outbox. Signed-off-by: Ariel Levkovich Reviewed-by: Eli Cohen Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 18 +++++++++++++----- include/linux/mlx5/transobj.h | 3 +++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index c4d4b76096dc..b1068500f1df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -182,16 +182,24 @@ out: } EXPORT_SYMBOL_GPL(mlx5_core_query_sq_state); +int mlx5_core_create_tir_out(struct mlx5_core_dev *dev, + u32 *in, int inlen, + u32 *out, int outlen) +{ + MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR); + + return mlx5_cmd_exec(dev, in, inlen, out, outlen); +} +EXPORT_SYMBOL(mlx5_core_create_tir_out); + int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *tirn) { - u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {0}; + u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {}; int err; - MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR); - - memset(out, 0, sizeof(out)); - err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); + err = mlx5_core_create_tir_out(dev, in, inlen, + out, sizeof(out)); if (!err) *tirn = MLX5_GET(create_tir_out, out, tirn); diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index a261d5528ff7..dc6b1e7cb8c4 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -50,6 +50,9 @@ int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out); int mlx5_core_query_sq_state(struct mlx5_core_dev *dev, u32 sqn, u8 *state); int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *tirn); +int mlx5_core_create_tir_out(struct mlx5_core_dev *dev, + u32 *in, int inlen, + u32 *out, int outlen); int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in, int inlen); void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn); -- cgit v1.2.3-71-gd317 From 118c8e9ae629d35fa9b3d27a7b9d59298b1b4183 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 25 Apr 2019 14:37:23 -0700 Subject: bpf: support BPF_PROG_QUERY for BPF_FLOW_DISSECTOR attach_type target_fd is target namespace. If there is a flow dissector BPF program attached to that namespace, its (single) id is returned. v5: * drop net ref right after rcu unlock (Daniel Borkmann) v4: * add missing put_net (Jann Horn) v3: * add missing inline to skb_flow_dissector_prog_query static def (kbuild test robot ) v2: * don't sleep in rcu critical section (Jakub Kicinski) * check input prog_cnt (exit early) Cc: Jann Horn Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 8 ++++++++ kernel/bpf/syscall.c | 2 ++ net/core/flow_dissector.c | 39 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 998256c2820b..6d58fa8a65fd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1258,11 +1258,19 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, unsigned int key_count); #ifdef CONFIG_NET +int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); #else +static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 92c9b8a32b50..b0de49598341 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2009,6 +2009,8 @@ static int bpf_prog_query(const union bpf_attr *attr, break; case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); + case BPF_FLOW_DISSECTOR: + return skb_flow_dissector_prog_query(attr, uattr); default: return -EINVAL; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index fac712cee9d5..9ca784c592ac 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -65,6 +65,45 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); +int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + u32 prog_id, prog_cnt = 0, flags = 0; + struct bpf_prog *attached; + struct net *net; + + if (attr->query.query_flags) + return -EINVAL; + + net = get_net_ns_by_fd(attr->query.target_fd); + if (IS_ERR(net)) + return PTR_ERR(net); + + rcu_read_lock(); + attached = rcu_dereference(net->flow_dissector_prog); + if (attached) { + prog_cnt = 1; + prog_id = attached->aux->id; + } + rcu_read_unlock(); + + put_net(net); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + return -EFAULT; + + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + return 0; + + if (copy_to_user(prog_ids, &prog_id, sizeof(u32))) + return -EFAULT; + + return 0; +} + int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { -- cgit v1.2.3-71-gd317 From f7dacfb11475ba777e1e84ccec2e14b0ba5a17a3 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Fri, 15 Mar 2019 17:39:03 +0200 Subject: cfg80211: support non-inheritance element Subelement profile may specify element IDs it doesn't inherit from the management frame. Support it. Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + include/net/cfg80211.h | 8 +++++++ net/wireless/scan.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 48703ec60d06..522881f31938 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2487,6 +2487,7 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_HE_MU_EDCA = 38, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, + WLAN_EID_EXT_NON_INHERITANCE = 56, }; /* Action category code */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 70432fd638af..777c4f021610 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5534,6 +5534,14 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, u64_to_ether_addr(new_bssid_u64, new_bssid); } +/** + * cfg80211_is_element_inherited - returns if element ID should be inherited + * @element: element to check + * @non_inherit_element: non inheritance element + */ +bool cfg80211_is_element_inherited(const struct element *element, + const struct element *non_inherit_element); + /** * enum cfg80211_bss_frame_type - frame type that the BSS data came from * @CFG80211_BSS_FTYPE_UNKNOWN: driver doesn't know whether the data is diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 49f700a1460b..bda9114ded77 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -179,12 +179,63 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev, return true; } +bool cfg80211_is_element_inherited(const struct element *elem, + const struct element *non_inherit_elem) +{ + u8 id_len, ext_id_len, i, loop_len, id; + const u8 *list; + + if (elem->id == WLAN_EID_MULTIPLE_BSSID) + return false; + + if (!non_inherit_elem || non_inherit_elem->datalen < 2) + return true; + + /* + * non inheritance element format is: + * ext ID (56) | IDs list len | list | extension IDs list len | list + * Both lists are optional. Both lengths are mandatory. + * This means valid length is: + * elem_len = 1 (extension ID) + 2 (list len fields) + list lengths + */ + id_len = non_inherit_elem->data[1]; + if (non_inherit_elem->datalen < 3 + id_len) + return true; + + ext_id_len = non_inherit_elem->data[2 + id_len]; + if (non_inherit_elem->datalen < 3 + id_len + ext_id_len) + return true; + + if (elem->id == WLAN_EID_EXTENSION) { + if (!ext_id_len) + return true; + loop_len = ext_id_len; + list = &non_inherit_elem->data[3 + id_len]; + id = elem->data[0]; + } else { + if (!id_len) + return true; + loop_len = id_len; + list = &non_inherit_elem->data[2]; + id = elem->id; + } + + for (i = 0; i < loop_len; i++) { + if (list[i] == id) + return false; + } + + return true; +} +EXPORT_SYMBOL(cfg80211_is_element_inherited); + static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, const u8 *subelement, size_t subie_len, u8 *new_ie, gfp_t gfp) { u8 *pos, *tmp; const u8 *tmp_old, *tmp_new; + const struct element *non_inherit_elem; u8 *sub_copy; /* copy subelement as we need to change its content to @@ -204,6 +255,11 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, pos += (tmp_new[1] + 2); } + /* get non inheritance list if exists */ + non_inherit_elem = + cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + sub_copy, subie_len); + /* go through IEs in ie (skip SSID) and subelement, * merge them into new_ie */ @@ -224,8 +280,11 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, subie_len); if (!tmp) { + const struct element *old_elem = (void *)tmp_old; + /* ie in old ie but not in subelement */ - if (tmp_old[0] != WLAN_EID_MULTIPLE_BSSID) { + if (cfg80211_is_element_inherited(old_elem, + non_inherit_elem)) { memcpy(pos, tmp_old, tmp_old[1] + 2); pos += tmp_old[1] + 2; } -- cgit v1.2.3-71-gd317 From abaea61c79ea7a03fde7db5b48414143546b07c4 Mon Sep 17 00:00:00 2001 From: Liad Kaufman Date: Fri, 15 Mar 2019 17:39:07 +0200 Subject: ieee80211: update HE IEs to D4.0 spec Update the out-dated comments as well, and have them point to the correct sections in the D4.0 spec. Signed-off-by: Liad Kaufman Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 522881f31938..61f0a316c6ac 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1557,7 +1557,7 @@ struct ieee80211_vht_operation { * struct ieee80211_he_cap_elem - HE capabilities element * * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D3.0 section 9.4.2.237.2 and 9.4.2.237.3 + * described in P802.11ax_D4.0 section 9.4.2.242.2 and 9.4.2.242.3 */ struct ieee80211_he_cap_elem { u8 mac_cap_info[6]; @@ -1619,12 +1619,12 @@ struct ieee80211_he_mcs_nss_supp { * struct ieee80211_he_operation - HE capabilities element * * This structure is the "HE operation element" fields as - * described in P802.11ax_D3.0 section 9.4.2.238 + * described in P802.11ax_D4.0 section 9.4.2.243 */ struct ieee80211_he_operation { __le32 he_oper_params; __le16 he_mcs_nss_set; - /* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */ + /* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */ u8 optional[0]; } __packed; @@ -1632,7 +1632,7 @@ struct ieee80211_he_operation { * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field * * This structure is the "MU AC Parameter Record" fields as - * described in P802.11ax_D2.0 section 9.4.2.240 + * described in P802.11ax_D4.0 section 9.4.2.245 */ struct ieee80211_he_mu_edca_param_ac_rec { u8 aifsn; @@ -1644,7 +1644,7 @@ struct ieee80211_he_mu_edca_param_ac_rec { * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element * * This structure is the "MU EDCA Parameter Set element" fields as - * described in P802.11ax_D2.0 section 9.4.2.240 + * described in P802.11ax_D4.0 section 9.4.2.245 */ struct ieee80211_mu_edca_param_set { u8 mu_qos_info; @@ -2026,6 +2026,7 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00004000 #define IEEE80211_HE_OPERATION_CO_HOSTED_BSS 0x00008000 #define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 +#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 #define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 @@ -2056,6 +2057,8 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) oper_len += 3; if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) oper_len++; + if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) + oper_len += 4; /* Add the first byte (extension ID) to the total length */ oper_len++; -- cgit v1.2.3-71-gd317 From 9df1c28bb75217b244257152ab7d788bb2a386d0 Mon Sep 17 00:00:00 2001 From: Matt Mullins Date: Fri, 26 Apr 2019 11:49:47 -0700 Subject: bpf: add writable context for raw tracepoints This is an opt-in interface that allows a tracepoint to provide a safe buffer that can be written from a BPF_PROG_TYPE_RAW_TRACEPOINT program. The size of the buffer must be a compile-time constant, and is checked before allowing a BPF program to attach to a tracepoint that uses this feature. The pointer to this buffer will be the first argument of tracepoints that opt in; the pointer is valid and can be bpf_probe_read() by both BPF_PROG_TYPE_RAW_TRACEPOINT and BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE programs that attach to such a tracepoint, but the buffer to which it points may only be written by the latter. Signed-off-by: Matt Mullins Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ include/linux/bpf_types.h | 1 + include/linux/tracepoint-defs.h | 1 + include/trace/bpf_probe.h | 27 +++++++++++++++++++++++++-- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 8 ++++++-- kernel/bpf/verifier.c | 31 +++++++++++++++++++++++++++++++ kernel/trace/bpf_trace.c | 24 ++++++++++++++++++++++++ 8 files changed, 91 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f15432d90728..cd6341eabd74 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -272,6 +272,7 @@ enum bpf_reg_type { PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ + PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ }; /* The information passed from prog-specific *_is_valid_access @@ -361,6 +362,7 @@ struct bpf_prog_aux { u32 used_map_cnt; u32 max_ctx_offset; u32 max_pkt_offset; + u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index d26991a16894..a10d37bce364 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -25,6 +25,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) #endif #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index 49ba9cde7e4b..b29950a19205 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -45,6 +45,7 @@ struct bpf_raw_event_map { struct tracepoint *tp; void *bpf_func; u32 num_args; + u32 writable_size; } __aligned(32); #endif diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index 505dae0bed80..d6e556c0a085 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -69,8 +69,7 @@ __bpf_trace_##call(void *__data, proto) \ * to make sure that if the tracepoint handling changes, the * bpf probe will fail to compile unless it too is updated. */ -#undef DEFINE_EVENT -#define DEFINE_EVENT(template, call, proto, args) \ +#define __DEFINE_EVENT(template, call, proto, args, size) \ static inline void bpf_test_probe_##call(void) \ { \ check_trace_callback_type_##call(__bpf_trace_##template); \ @@ -81,12 +80,36 @@ __bpf_trace_tp_map_##call = { \ .tp = &__tracepoint_##call, \ .bpf_func = (void *)__bpf_trace_##template, \ .num_args = COUNT_ARGS(args), \ + .writable_size = size, \ }; +#define FIRST(x, ...) x + +#undef DEFINE_EVENT_WRITABLE +#define DEFINE_EVENT_WRITABLE(template, call, proto, args, size) \ +static inline void bpf_test_buffer_##call(void) \ +{ \ + /* BUILD_BUG_ON() is ignored if the code is completely eliminated, but \ + * BUILD_BUG_ON_ZERO() uses a different mechanism that is not \ + * dead-code-eliminated. \ + */ \ + FIRST(proto); \ + (void)BUILD_BUG_ON_ZERO(size != sizeof(*FIRST(args))); \ +} \ +__DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size) + +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, call, proto, args) \ + __DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), 0) #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#undef DEFINE_EVENT_WRITABLE +#undef __DEFINE_EVENT +#undef FIRST + #endif /* CONFIG_BPF_EVENTS */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index eaf2d3284248..f7fa7a34a62d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -168,6 +168,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, }; enum bpf_attach_type { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b0de49598341..ae141e745f92 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1789,12 +1789,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) } raw_tp->btp = btp; - prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd, - BPF_PROG_TYPE_RAW_TRACEPOINT); + prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) { err = PTR_ERR(prog); goto out_free_tp; } + if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && + prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { + err = -EINVAL; + goto out_put_prog; + } err = bpf_probe_register(raw_tp->btp, prog); if (err) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 423f242a5efb..2ef442c62c0e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -405,6 +405,7 @@ static const char * const reg_type_str[] = { [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", + [PTR_TO_TP_BUFFER] = "tp_buffer", }; static char slot_type_char[] = { @@ -1993,6 +1994,32 @@ static int check_ctx_reg(struct bpf_verifier_env *env, return 0; } +static int check_tp_buffer_access(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + int regno, int off, int size) +{ + if (off < 0) { + verbose(env, + "R%d invalid tracepoint buffer access: off=%d, size=%d", + regno, off, size); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, + "R%d invalid variable buffer offset: off=%d, var_off=%s", + regno, off, tn_buf); + return -EACCES; + } + if (off + size > env->prog->aux->max_tp_access) + env->prog->aux->max_tp_access = off + size; + + return 0; +} + + /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ @@ -2137,6 +2164,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_TP_BUFFER) { + err = check_tp_buffer_access(env, reg, regno, off, size); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 91800be0c8eb..8607aba1d882 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -915,6 +915,27 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { const struct bpf_prog_ops raw_tracepoint_prog_ops = { }; +static bool raw_tp_writable_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off == 0) { + if (size != sizeof(u64) || type != BPF_READ) + return false; + info->reg_type = PTR_TO_TP_BUFFER; + } + return raw_tp_prog_is_valid_access(off, size, type, prog, info); +} + +const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = { + .get_func_proto = raw_tp_prog_func_proto, + .is_valid_access = raw_tp_writable_prog_is_valid_access, +}; + +const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = { +}; + static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -1204,6 +1225,9 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64)) return -EINVAL; + if (prog->aux->max_tp_access > btp->writable_size) + return -EINVAL; + return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog); } -- cgit v1.2.3-71-gd317 From 6ac99e8f23d4b10258406ca0dd7bffca5f31da9d Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 26 Apr 2019 16:39:39 -0700 Subject: bpf: Introduce bpf sk local storage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After allowing a bpf prog to - directly read the skb->sk ptr - get the fullsock bpf_sock by "bpf_sk_fullsock()" - get the bpf_tcp_sock by "bpf_tcp_sock()" - get the listener sock by "bpf_get_listener_sock()" - avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock" into different bpf running context. this patch is another effort to make bpf's network programming more intuitive to do (together with memory and performance benefit). When bpf prog needs to store data for a sk, the current practice is to define a map with the usual 4-tuples (src/dst ip/port) as the key. If multiple bpf progs require to store different sk data, multiple maps have to be defined. Hence, wasting memory to store the duplicated keys (i.e. 4 tuples here) in each of the bpf map. [ The smallest key could be the sk pointer itself which requires some enhancement in the verifier and it is a separate topic. ] Also, the bpf prog needs to clean up the elem when sk is freed. Otherwise, the bpf map will become full and un-usable quickly. The sk-free tracking currently could be done during sk state transition (e.g. BPF_SOCK_OPS_STATE_CB). The size of the map needs to be predefined which then usually ended-up with an over-provisioned map in production. Even the map was re-sizable, while the sk naturally come and go away already, this potential re-size operation is arguably redundant if the data can be directly connected to the sk itself instead of proxy-ing through a bpf map. This patch introduces sk->sk_bpf_storage to provide local storage space at sk for bpf prog to use. The space will be allocated when the first bpf prog has created data for this particular sk. The design optimizes the bpf prog's lookup (and then optionally followed by an inline update). bpf_spin_lock should be used if the inline update needs to be protected. BPF_MAP_TYPE_SK_STORAGE: ----------------------- To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can be created to fit different bpf progs' needs. The map enforces BTF to allow printing the sk-local-storage during a system-wise sk dump (e.g. "ss -ta") in the future. The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete a "sk-local-storage" data from a particular sk. Think of the map as a meta-data (or "type") of a "sk-local-storage". This particular "type" of "sk-local-storage" data can then be stored in any sk. The main purposes of this map are mostly: 1. Define the size of a "sk-local-storage" type. 2. Provide a similar syscall userspace API as the map (e.g. lookup/update, map-id, map-btf...etc.) 3. Keep track of all sk's storages of this "type" and clean them up when the map is freed. sk->sk_bpf_storage: ------------------ The main lookup/update/delete is done on sk->sk_bpf_storage (which is a "struct bpf_sk_storage"). When doing a lookup, the "map" pointer is now used as the "key" to search on the sk_storage->list. The "map" pointer is actually serving as the "type" of the "sk-local-storage" that is being requested. To allow very fast lookup, it should be as fast as looking up an array at a stable-offset. At the same time, it is not ideal to set a hard limit on the number of sk-local-storage "type" that the system can have. Hence, this patch takes a cache approach. The last search result from sk_storage->list is cached in sk_storage->cache[] which is a stable sized array. Each "sk-local-storage" type has a stable offset to the cache[] array. In the future, a map's flag could be introduced to do cache opt-out/enforcement if it became necessary. The cache size is 16 (i.e. 16 types of "sk-local-storage"). Programs can share map. On the program side, having a few bpf_progs running in the networking hotpath is already a lot. The bpf_prog should have already consolidated the existing sock-key-ed map usage to minimize the map lookup penalty. 16 has enough runway to grow. All sk-local-storage data will be removed from sk->sk_bpf_storage during sk destruction. bpf_sk_storage_get() and bpf_sk_storage_delete(): ------------------------------------------------ Instead of using bpf_map_(lookup|update|delete)_elem(), the bpf prog needs to use the new helper bpf_sk_storage_get() and bpf_sk_storage_delete(). The verifier can then enforce the ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to "create" new elem if one does not exist in the sk. It is done by the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE. The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together, it has eliminated the potential use cases for an equivalent bpf_map_update_elem() API (for bpf_prog) in this patch. Misc notes: ---------- 1. map_get_next_key is not supported. From the userspace syscall perspective, the map has the socket fd as the key while the map can be shared by pinned-file or map-id. Since btf is enforced, the existing "ss" could be enhanced to pretty print the local-storage. Supporting a kernel defined btf with 4 tuples as the return key could be explored later also. 2. The sk->sk_lock cannot be acquired. Atomic operations is used instead. e.g. cmpxchg is done on the sk->sk_bpf_storage ptr. Please refer to the source code comments for the details in synchronization cases and considerations. 3. The mem is charged to the sk->sk_omem_alloc as the sk filter does. Benchmark: --------- Here is the benchmark data collected by turning on the "kernel.bpf_stats_enabled" sysctl. Two bpf progs are tested: One bpf prog with the usual bpf hashmap (max_entries = 8192) with the sk ptr as the key. (verifier is modified to support sk ptr as the key That should have shortened the key lookup time.) Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE. Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for each egress skb and then bump the cnt. netperf is used to drive data with 4096 connected UDP sockets. BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run) 27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633 loaded_at 2019-04-15T13:46:39-0700 uid 0 xlated 344B jited 258B memlock 4096B map_ids 16 btf_id 5 BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run) 30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739 loaded_at 2019-04-15T13:47:54-0700 uid 0 xlated 168B jited 156B memlock 4096B map_ids 17 btf_id 6 Here is a high-level picture on how are the objects organized: sk ┌──────┐ │ │ │ │ │ │ │*sk_bpf_storage─────▶ bpf_sk_storage └──────┘ ┌───────┐ ┌───────────┤ list │ │ │ │ │ │ │ │ │ │ │ └───────┘ │ │ elem │ ┌────────┐ ├─▶│ snode │ │ ├────────┤ │ │ data │ bpf_map │ ├────────┤ ┌─────────┐ │ │map_node│◀─┬─────┤ list │ │ └────────┘ │ │ │ │ │ │ │ │ elem │ │ │ │ ┌────────┐ │ └─────────┘ └─▶│ snode │ │ ├────────┤ │ bpf_map │ data │ │ ┌─────────┐ ├────────┤ │ │ list ├───────▶│map_node│ │ │ │ └────────┘ │ │ │ │ │ │ elem │ └─────────┘ ┌────────┐ │ ┌─▶│ snode │ │ │ ├────────┤ │ │ │ data │ │ │ ├────────┤ │ │ │map_node│◀─┘ │ └────────┘ │ │ │ ┌───────┐ sk └──────────│ list │ ┌──────┐ │ │ │ │ │ │ │ │ │ │ │ │ └───────┘ │*sk_bpf_storage───────▶bpf_sk_storage └──────┘ Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 + include/linux/bpf_types.h | 1 + include/net/bpf_sk_storage.h | 13 + include/net/sock.h | 5 + include/uapi/linux/bpf.h | 44 ++- kernel/bpf/syscall.c | 3 +- kernel/bpf/verifier.c | 27 +- net/bpf/test_run.c | 2 + net/core/Makefile | 1 + net/core/bpf_sk_storage.c | 804 +++++++++++++++++++++++++++++++++++++++++++ net/core/filter.c | 12 + net/core/sock.c | 5 + 12 files changed, 914 insertions(+), 5 deletions(-) create mode 100644 include/net/bpf_sk_storage.h create mode 100644 net/core/bpf_sk_storage.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cd6341eabd74..9a21848fdb07 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -184,6 +184,7 @@ enum bpf_arg_type { ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ + ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack @@ -204,6 +205,7 @@ enum bpf_arg_type { ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ + ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ }; /* type of values returned from helper functions */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a10d37bce364..5a9975678d6f 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -61,6 +61,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h new file mode 100644 index 000000000000..b9dcb02e756b --- /dev/null +++ b/include/net/bpf_sk_storage.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Facebook */ +#ifndef _BPF_SK_STORAGE_H +#define _BPF_SK_STORAGE_H + +struct sock; + +void bpf_sk_storage_free(struct sock *sk); + +extern const struct bpf_func_proto bpf_sk_storage_get_proto; +extern const struct bpf_func_proto bpf_sk_storage_delete_proto; + +#endif /* _BPF_SK_STORAGE_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 784cd19d5ff7..4d208c0f9c14 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -236,6 +236,8 @@ struct sock_common { /* public: */ }; +struct bpf_sk_storage; + /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -510,6 +512,9 @@ struct sock { #endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; +#ifdef CONFIG_BPF_SYSCALL + struct bpf_sk_storage __rcu *sk_bpf_storage; +#endif struct rcu_head sk_rcu; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f7fa7a34a62d..72336bac7573 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -133,6 +133,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, }; /* Note that tracing related programs such as @@ -2630,6 +2631,42 @@ union bpf_attr { * was provided. * * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a sk. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem(map, &sk)** except this + * helper enforces the key must be a **bpf_fullsock()** + * and the map must be a BPF_MAP_TYPE_SK_STORAGE also. + * + * Underneath, the value is stored locally at *sk* instead of + * the map. The *map* is used as the bpf-local-storage **type**. + * The bpf-local-storage **type** (i.e. the *map*) is searched + * against all bpf-local-storages residing at sk. + * + * An optional *flags* (BPF_SK_STORAGE_GET_F_CREATE) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with BPF_SK_STORAGE_GET_F_CREATE to specify + * the initial value of a bpf-local-storage. If *value* is + * NULL, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a sk. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2738,7 +2775,9 @@ union bpf_attr { FN(sysctl_get_new_value), \ FN(sysctl_set_new_value), \ FN(strtol), \ - FN(strtoul), + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2814,6 +2853,9 @@ enum bpf_func_id { /* BPF_FUNC_sysctl_get_name flags. */ #define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) +/* BPF_FUNC_sk_storage_get flags */ +#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ae141e745f92..ad3ccf82f31d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -526,7 +526,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EACCES; if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_SK_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2ef442c62c0e..271717246af3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2543,10 +2543,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || + arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { expected_type = PTR_TO_STACK; - if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && - type != expected_type) + if (register_is_null(reg) && + arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) + /* final test in check_stack_boundary() */; + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -2578,6 +2583,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } meta->ref_obj_id = reg->ref_obj_id; } + } else if (arg_type == ARG_PTR_TO_SOCKET) { + expected_type = PTR_TO_SOCKET; + if (type != expected_type) + goto err_type; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -2635,6 +2644,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, meta->map_ptr->key_size, false, NULL); } else if (arg_type == ARG_PTR_TO_MAP_VALUE || + (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && + !register_is_null(reg)) || arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -2784,6 +2795,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_map_push_elem) goto error; break; + case BPF_MAP_TYPE_SK_STORAGE: + if (func_id != BPF_FUNC_sk_storage_get && + func_id != BPF_FUNC_sk_storage_delete) + goto error; + break; default: break; } @@ -2847,6 +2863,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_sk_storage_get: + case BPF_FUNC_sk_storage_delete: + if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) + goto error; + break; default: break; } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6c4694ae4241..33e0dc168c16 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -335,6 +336,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, sizeof(struct __sk_buff)); out: kfree_skb(skb); + bpf_sk_storage_free(sk); kfree(sk); kfree(ctx); return ret; diff --git a/net/core/Makefile b/net/core/Makefile index f97d6254e564..a104dc8faafc 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -34,3 +34,4 @@ obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c new file mode 100644 index 000000000000..a8e9ac71b22d --- /dev/null +++ b/net/core/bpf_sk_storage.c @@ -0,0 +1,804 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static atomic_t cache_idx; + +struct bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* Thp map is not the primary owner of a bpf_sk_storage_elem. + * Instead, the sk->sk_bpf_storage is. + * + * The map (bpf_sk_storage_map) is for two purposes + * 1. Define the size of the "sk local storage". It is + * the map's value_size. + * + * 2. Maintain a list to keep track of all elems such + * that they can be cleaned up during the map destruction. + * + * When a bpf local storage is being looked up for a + * particular sk, the "bpf_map" pointer is actually used + * as the "key" to search in the list of elem in + * sk->sk_bpf_storage. + * + * Hence, consider sk->sk_bpf_storage is the mini-map + * with the "bpf_map" pointer as the searching key. + */ +struct bpf_sk_storage_map { + struct bpf_map map; + /* Lookup elem does not require accessing the map. + * + * Updating/Deleting requires a bucket lock to + * link/unlink the elem from the map. Having + * multiple buckets to improve contention. + */ + struct bucket *buckets; + u32 bucket_log; + u16 elem_size; + u16 cache_idx; +}; + +struct bpf_sk_storage_data { + /* smap is used as the searching key when looking up + * from sk->sk_bpf_storage. + * + * Put it in the same cacheline as the data to minimize + * the number of cachelines access during the cache hit case. + */ + struct bpf_sk_storage_map __rcu *smap; + u8 data[0] __aligned(8); +}; + +/* Linked to bpf_sk_storage and bpf_sk_storage_map */ +struct bpf_sk_storage_elem { + struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ + struct hlist_node snode; /* Linked to bpf_sk_storage */ + struct bpf_sk_storage __rcu *sk_storage; + struct rcu_head rcu; + /* 8 bytes hole */ + /* The data is stored in aother cacheline to minimize + * the number of cachelines access during a cache hit. + */ + struct bpf_sk_storage_data sdata ____cacheline_aligned; +}; + +#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) +#define SDATA(_SELEM) (&(_SELEM)->sdata) +#define BPF_SK_STORAGE_CACHE_SIZE 16 + +struct bpf_sk_storage { + struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_sk_storage_elem */ + struct sock *sk; /* The sk that owns the the above "list" of + * bpf_sk_storage_elem. + */ + struct rcu_head rcu; + raw_spinlock_t lock; /* Protect adding/removing from the "list" */ +}; + +static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *selem) +{ + return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; +} + +static int omem_charge(struct sock *sk, unsigned int size) +{ + /* same check as in sock_kmalloc() */ + if (size <= sysctl_optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + atomic_add(size, &sk->sk_omem_alloc); + return 0; + } + + return -ENOMEM; +} + +static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) +{ + return !hlist_unhashed(&selem->snode); +} + +static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) +{ + return !hlist_unhashed(&selem->map_node); +} + +static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, + struct sock *sk, void *value, + bool charge_omem) +{ + struct bpf_sk_storage_elem *selem; + + if (charge_omem && omem_charge(sk, smap->elem_size)) + return NULL; + + selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (selem) { + if (value) + memcpy(SDATA(selem)->data, value, smap->map.value_size); + return selem; + } + + if (charge_omem) + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + + return NULL; +} + +/* sk_storage->lock must be held and selem->sk_storage == sk_storage. + * The caller must ensure selem->smap is still valid to be + * dereferenced for its smap->elem_size and smap->cache_idx. + */ +static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_elem *selem, + bool uncharge_omem) +{ + struct bpf_sk_storage_map *smap; + bool free_sk_storage; + struct sock *sk; + + smap = rcu_dereference(SDATA(selem)->smap); + sk = sk_storage->sk; + + /* All uncharging on sk->sk_omem_alloc must be done first. + * sk may be freed once the last selem is unlinked from sk_storage. + */ + if (uncharge_omem) + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + + free_sk_storage = hlist_is_singular_node(&selem->snode, + &sk_storage->list); + if (free_sk_storage) { + atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); + sk_storage->sk = NULL; + /* After this RCU_INIT, sk may be freed and cannot be used */ + RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); + + /* sk_storage is not freed now. sk_storage->lock is + * still held and raw_spin_unlock_bh(&sk_storage->lock) + * will be done by the caller. + * + * Although the unlock will be done under + * rcu_read_lock(), it is more intutivie to + * read if kfree_rcu(sk_storage, rcu) is done + * after the raw_spin_unlock_bh(&sk_storage->lock). + * + * Hence, a "bool free_sk_storage" is returned + * to the caller which then calls the kfree_rcu() + * after unlock. + */ + } + hlist_del_init_rcu(&selem->snode); + if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == + SDATA(selem)) + RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); + + kfree_rcu(selem, rcu); + + return free_sk_storage; +} + +static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) +{ + struct bpf_sk_storage *sk_storage; + bool free_sk_storage = false; + + if (unlikely(!selem_linked_to_sk(selem))) + /* selem has already been unlinked from sk */ + return; + + sk_storage = rcu_dereference(selem->sk_storage); + raw_spin_lock_bh(&sk_storage->lock); + if (likely(selem_linked_to_sk(selem))) + free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + raw_spin_unlock_bh(&sk_storage->lock); + + if (free_sk_storage) + kfree_rcu(sk_storage, rcu); +} + +/* sk_storage->lock must be held and sk_storage->list cannot be empty */ +static void __selem_link_sk(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_elem *selem) +{ + RCU_INIT_POINTER(selem->sk_storage, sk_storage); + hlist_add_head(&selem->snode, &sk_storage->list); +} + +static void selem_unlink_map(struct bpf_sk_storage_elem *selem) +{ + struct bpf_sk_storage_map *smap; + struct bucket *b; + + if (unlikely(!selem_linked_to_map(selem))) + /* selem has already be unlinked from smap */ + return; + + smap = rcu_dereference(SDATA(selem)->smap); + b = select_bucket(smap, selem); + raw_spin_lock_bh(&b->lock); + if (likely(selem_linked_to_map(selem))) + hlist_del_init_rcu(&selem->map_node); + raw_spin_unlock_bh(&b->lock); +} + +static void selem_link_map(struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *selem) +{ + struct bucket *b = select_bucket(smap, selem); + + raw_spin_lock_bh(&b->lock); + RCU_INIT_POINTER(SDATA(selem)->smap, smap); + hlist_add_head_rcu(&selem->map_node, &b->list); + raw_spin_unlock_bh(&b->lock); +} + +static void selem_unlink(struct bpf_sk_storage_elem *selem) +{ + /* Always unlink from map before unlinking from sk_storage + * because selem will be freed after successfully unlinked from + * the sk_storage. + */ + selem_unlink_map(selem); + selem_unlink_sk(selem); +} + +static struct bpf_sk_storage_data * +__sk_storage_lookup(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_map *smap, + bool cacheit_lockit) +{ + struct bpf_sk_storage_data *sdata; + struct bpf_sk_storage_elem *selem; + + /* Fast path (cache hit) */ + sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); + if (sdata && rcu_access_pointer(sdata->smap) == smap) + return sdata; + + /* Slow path (cache miss) */ + hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) + if (rcu_access_pointer(SDATA(selem)->smap) == smap) + break; + + if (!selem) + return NULL; + + sdata = SDATA(selem); + if (cacheit_lockit) { + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next __sk_storage_lookup(). + */ + raw_spin_lock_bh(&sk_storage->lock); + if (selem_linked_to_sk(selem)) + rcu_assign_pointer(sk_storage->cache[smap->cache_idx], + sdata); + raw_spin_unlock_bh(&sk_storage->lock); + } + + return sdata; +} + +static struct bpf_sk_storage_data * +sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) +{ + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_map *smap; + + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage) + return NULL; + + smap = (struct bpf_sk_storage_map *)map; + return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); +} + +static int check_flags(const struct bpf_sk_storage_data *old_sdata, + u64 map_flags) +{ + if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) + /* elem already exists */ + return -EEXIST; + + if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) + /* elem doesn't exist, cannot update it */ + return -ENOENT; + + return 0; +} + +static int sk_storage_alloc(struct sock *sk, + struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *first_selem) +{ + struct bpf_sk_storage *prev_sk_storage, *sk_storage; + int err; + + err = omem_charge(sk, sizeof(*sk_storage)); + if (err) + return err; + + sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN); + if (!sk_storage) { + err = -ENOMEM; + goto uncharge; + } + INIT_HLIST_HEAD(&sk_storage->list); + raw_spin_lock_init(&sk_storage->lock); + sk_storage->sk = sk; + + __selem_link_sk(sk_storage, first_selem); + selem_link_map(smap, first_selem); + /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. + * Hence, atomic ops is used to set sk->sk_bpf_storage + * from NULL to the newly allocated sk_storage ptr. + * + * From now on, the sk->sk_bpf_storage pointer is protected + * by the sk_storage->lock. Hence, when freeing + * the sk->sk_bpf_storage, the sk_storage->lock must + * be held before setting sk->sk_bpf_storage to NULL. + */ + prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, + NULL, sk_storage); + if (unlikely(prev_sk_storage)) { + selem_unlink_map(first_selem); + err = -EAGAIN; + goto uncharge; + + /* Note that even first_selem was linked to smap's + * bucket->list, first_selem can be freed immediately + * (instead of kfree_rcu) because + * bpf_sk_storage_map_free() does a + * synchronize_rcu() before walking the bucket->list. + * Hence, no one is accessing selem from the + * bucket->list under rcu_read_lock(). + */ + } + + return 0; + +uncharge: + kfree(sk_storage); + atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc); + return err; +} + +/* sk cannot be going away because it is linking new elem + * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). + * Otherwise, it will become a leak (and other memory issues + * during map destruction). + */ +static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, + struct bpf_map *map, + void *value, + u64 map_flags) +{ + struct bpf_sk_storage_data *old_sdata = NULL; + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_map *smap; + int err; + + /* BPF_EXIST and BPF_NOEXIST cannot be both set */ + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || + /* BPF_F_LOCK can only be used in a value with spin_lock */ + unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + return ERR_PTR(-EINVAL); + + smap = (struct bpf_sk_storage_map *)map; + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage || hlist_empty(&sk_storage->list)) { + /* Very first elem for this sk */ + err = check_flags(NULL, map_flags); + if (err) + return ERR_PTR(err); + + selem = selem_alloc(smap, sk, value, true); + if (!selem) + return ERR_PTR(-ENOMEM); + + err = sk_storage_alloc(sk, smap, selem); + if (err) { + kfree(selem); + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + return ERR_PTR(err); + } + + return SDATA(selem); + } + + if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { + /* Hoping to find an old_sdata to do inline update + * such that it can avoid taking the sk_storage->lock + * and changing the lists. + */ + old_sdata = __sk_storage_lookup(sk_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + return ERR_PTR(err); + if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { + copy_map_value_locked(map, old_sdata->data, + value, false); + return old_sdata; + } + } + + raw_spin_lock_bh(&sk_storage->lock); + + /* Recheck sk_storage->list under sk_storage->lock */ + if (unlikely(hlist_empty(&sk_storage->list))) { + /* A parallel del is happening and sk_storage is going + * away. It has just been checked before, so very + * unlikely. Return instead of retry to keep things + * simple. + */ + err = -EAGAIN; + goto unlock_err; + } + + old_sdata = __sk_storage_lookup(sk_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + goto unlock_err; + + if (old_sdata && (map_flags & BPF_F_LOCK)) { + copy_map_value_locked(map, old_sdata->data, value, false); + selem = SELEM(old_sdata); + goto unlock; + } + + /* sk_storage->lock is held. Hence, we are sure + * we can unlink and uncharge the old_sdata successfully + * later. Hence, instead of charging the new selem now + * and then uncharge the old selem later (which may cause + * a potential but unnecessary charge failure), avoid taking + * a charge at all here (the "!old_sdata" check) and the + * old_sdata will not be uncharged later during __selem_unlink_sk(). + */ + selem = selem_alloc(smap, sk, value, !old_sdata); + if (!selem) { + err = -ENOMEM; + goto unlock_err; + } + + /* First, link the new selem to the map */ + selem_link_map(smap, selem); + + /* Second, link (and publish) the new selem to sk_storage */ + __selem_link_sk(sk_storage, selem); + + /* Third, remove old selem, SELEM(old_sdata) */ + if (old_sdata) { + selem_unlink_map(SELEM(old_sdata)); + __selem_unlink_sk(sk_storage, SELEM(old_sdata), false); + } + +unlock: + raw_spin_unlock_bh(&sk_storage->lock); + return SDATA(selem); + +unlock_err: + raw_spin_unlock_bh(&sk_storage->lock); + return ERR_PTR(err); +} + +static int sk_storage_delete(struct sock *sk, struct bpf_map *map) +{ + struct bpf_sk_storage_data *sdata; + + sdata = sk_storage_lookup(sk, map, false); + if (!sdata) + return -ENOENT; + + selem_unlink(SELEM(sdata)); + + return 0; +} + +/* Called by __sk_destruct() */ +void bpf_sk_storage_free(struct sock *sk) +{ + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage *sk_storage; + bool free_sk_storage = false; + struct hlist_node *n; + + rcu_read_lock(); + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage) { + rcu_read_unlock(); + return; + } + + /* Netiher the bpf_prog nor the bpf-map's syscall + * could be modifying the sk_storage->list now. + * Thus, no elem can be added-to or deleted-from the + * sk_storage->list by the bpf_prog or by the bpf-map's syscall. + * + * It is racing with bpf_sk_storage_map_free() alone + * when unlinking elem from the sk_storage->list and + * the map's bucket->list. + */ + raw_spin_lock_bh(&sk_storage->lock); + hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) { + /* Always unlink from map before unlinking from + * sk_storage. + */ + selem_unlink_map(selem); + free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + } + raw_spin_unlock_bh(&sk_storage->lock); + rcu_read_unlock(); + + if (free_sk_storage) + kfree_rcu(sk_storage, rcu); +} + +static void bpf_sk_storage_map_free(struct bpf_map *map) +{ + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage_map *smap; + struct bucket *b; + unsigned int i; + + smap = (struct bpf_sk_storage_map *)map; + + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the sk->sk_bpf_storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_sk_storage_elem, + map_node))) { + selem_unlink(selem); + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* bpf_sk_storage_free() may still need to access the map. + * e.g. bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exited immediately. + * + * However, the bpf_sk_storage_free() still needs to access + * the smap->elem_size to do the uncharging in + * __selem_unlink_sk(). + * + * Hence, wait another rcu grace period for the + * bpf_sk_storage_free() to finish. + */ + synchronize_rcu(); + + kvfree(smap->buckets); + kfree(map); +} + +static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) +{ + if (attr->map_flags != BPF_F_NO_PREALLOC || attr->max_entries || + attr->key_size != sizeof(int) || !attr->value_size || + /* Enforce BTF for userspace sk dumping */ + !attr->btf_key_type_id || !attr->btf_value_type_id) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->value_size >= KMALLOC_MAX_SIZE - + MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem) || + /* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ + attr->value_size > U16_MAX - sizeof(struct bpf_sk_storage_elem)) + return -E2BIG; + + return 0; +} + +static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_sk_storage_map *smap; + unsigned int i; + u32 nbuckets; + u64 cost; + + smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); + if (!smap) + return ERR_PTR(-ENOMEM); + bpf_map_init_from_attr(&smap->map, attr); + + smap->bucket_log = ilog2(roundup_pow_of_two(num_possible_cpus())); + nbuckets = 1U << smap->bucket_log; + smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, + GFP_USER | __GFP_NOWARN); + if (!smap->buckets) { + kfree(smap); + return ERR_PTR(-ENOMEM); + } + cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); + + for (i = 0; i < nbuckets; i++) { + INIT_HLIST_HEAD(&smap->buckets[i].list); + raw_spin_lock_init(&smap->buckets[i].lock); + } + + smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; + smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) % + BPF_SK_STORAGE_CACHE_SIZE; + smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + return &smap->map; +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -ENOTSUPP; +} + +static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + u32 int_data; + + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) + return -EINVAL; + + return 0; +} + +static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_sk_storage_data *sdata; + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + sdata = sk_storage_lookup(sock->sk, map, true); + sockfd_put(sock); + return sdata ? sdata->data : NULL; + } + + return ERR_PTR(err); +} + +static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_sk_storage_data *sdata; + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + sdata = sk_storage_update(sock->sk, map, value, map_flags); + sockfd_put(sock); + return IS_ERR(sdata) ? PTR_ERR(sdata) : 0; + } + + return err; +} + +static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + err = sk_storage_delete(sock->sk, map); + sockfd_put(sock); + return err; + } + + return err; +} + +BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, + void *, value, u64, flags) +{ + struct bpf_sk_storage_data *sdata; + + if (flags > BPF_SK_STORAGE_GET_F_CREATE) + return (unsigned long)NULL; + + sdata = sk_storage_lookup(sk, map, true); + if (sdata) + return (unsigned long)sdata->data; + + if (flags == BPF_SK_STORAGE_GET_F_CREATE && + /* Cannot add new elem to a going away sk. + * Otherwise, the new elem may become a leak + * (and also other memory issues during map + * destruction). + */ + refcount_inc_not_zero(&sk->sk_refcnt)) { + sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); + /* sk must be a fullsock (guaranteed by verifier), + * so sock_gen_put() is unnecessary. + */ + sock_put(sk); + return IS_ERR(sdata) ? + (unsigned long)NULL : (unsigned long)sdata->data; + } + + return (unsigned long)NULL; +} + +BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) +{ + if (refcount_inc_not_zero(&sk->sk_refcnt)) { + int err; + + err = sk_storage_delete(sk, map); + sock_put(sk); + return err; + } + + return -ENOENT; +} + +const struct bpf_map_ops sk_storage_map_ops = { + .map_alloc_check = bpf_sk_storage_map_alloc_check, + .map_alloc = bpf_sk_storage_map_alloc, + .map_free = bpf_sk_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, + .map_update_elem = bpf_fd_sk_storage_update_elem, + .map_delete_elem = bpf_fd_sk_storage_delete_elem, + .map_check_btf = bpf_sk_storage_map_check_btf, +}; + +const struct bpf_func_proto bpf_sk_storage_get_proto = { + .func = bpf_sk_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_SOCKET, + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_sk_storage_delete_proto = { + .func = bpf_sk_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_SOCKET, +}; diff --git a/net/core/filter.c b/net/core/filter.c index 2f88baf39cc2..27b0dc01dc3f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -75,6 +75,7 @@ #include #include #include +#include /** * sk_filter_trim_cap - run a packet through a socket filter @@ -5903,6 +5904,9 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +const struct bpf_func_proto bpf_sk_storage_get_proto __weak; +const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; + static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -5911,6 +5915,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_local_storage_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; @@ -5992,6 +6000,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_fib_lookup_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; diff --git a/net/core/sock.c b/net/core/sock.c index 443b98d05f1e..9773be724aa9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -137,6 +137,7 @@ #include #include +#include #include @@ -1709,6 +1710,10 @@ static void __sk_destruct(struct rcu_head *head) sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); +#ifdef CONFIG_BPF_SYSCALL + bpf_sk_storage_free(sk); +#endif + if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); -- cgit v1.2.3-71-gd317 From da68b4ad02343862fee1e3e8c6315984f16a4778 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 25 Apr 2019 12:32:03 -0700 Subject: net/tls: move definition of tls ops into net/tls.h There seems to be no reason for tls_ops to be defined in netdevice.h which is included in a lot of places. Don't wrap the struct/enum declaration in ifdefs, it trickles down unnecessary ifdefs into driver code. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 23 +---------------------- include/net/tls.h | 17 +++++++++++++++++ 2 files changed, 18 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c46d218a0456..44b47e9df94a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -914,34 +914,13 @@ struct xfrmdev_ops { }; #endif -#if IS_ENABLED(CONFIG_TLS_DEVICE) -enum tls_offload_ctx_dir { - TLS_OFFLOAD_CTX_DIR_RX, - TLS_OFFLOAD_CTX_DIR_TX, -}; - -struct tls_crypto_info; -struct tls_context; - -struct tlsdev_ops { - int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, - enum tls_offload_ctx_dir direction, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn); - void (*tls_dev_del)(struct net_device *netdev, - struct tls_context *ctx, - enum tls_offload_ctx_dir direction); - void (*tls_dev_resync_rx)(struct net_device *netdev, - struct sock *sk, u32 seq, u64 rcd_sn); -}; -#endif - struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; }; struct devlink; +struct tlsdev_ops; /* * This structure defines the management hooks for network devices. diff --git a/include/net/tls.h b/include/net/tls.h index 20196cb31ecc..41a2ee643fc5 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -277,6 +277,23 @@ struct tls_context { void (*unhash)(struct sock *sk); }; +enum tls_offload_ctx_dir { + TLS_OFFLOAD_CTX_DIR_RX, + TLS_OFFLOAD_CTX_DIR_TX, +}; + +struct tlsdev_ops { + int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, + enum tls_offload_ctx_dir direction, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn); + void (*tls_dev_del)(struct net_device *netdev, + struct tls_context *ctx, + enum tls_offload_ctx_dir direction); + void (*tls_dev_resync_rx)(struct net_device *netdev, + struct sock *sk, u32 seq, u64 rcd_sn); +}; + struct tls_offload_context_rx { /* sw must be the first member of tls_offload_context_rx */ struct tls_sw_context_rx sw; -- cgit v1.2.3-71-gd317 From ae0be8de9a53cda3505865c11826d8ff0640237c Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Fri, 26 Apr 2019 11:13:06 +0200 Subject: netlink: make nla_nest_start() add NLA_F_NESTED flag Even if the NLA_F_NESTED flag was introduced more than 11 years ago, most netlink based interfaces (including recently added ones) are still not setting it in kernel generated messages. Without the flag, message parsers not aware of attribute semantics (e.g. wireshark dissector or libmnl's mnl_nlmsg_fprintf()) cannot recognize nested attributes and won't display the structure of their contents. Unfortunately we cannot just add the flag everywhere as there may be userspace applications which check nlattr::nla_type directly rather than through a helper masking out the flags. Therefore the patch renames nla_nest_start() to nla_nest_start_noflag() and introduces nla_nest_start() as a wrapper adding NLA_F_NESTED. The calls which add NLA_F_NESTED manually are rewritten to use nla_nest_start(). Except for changes in include/net/netlink.h, the patch was generated using this semantic patch: @@ expression E1, E2; @@ -nla_nest_start(E1, E2) +nla_nest_start_noflag(E1, E2) @@ expression E1, E2; @@ -nla_nest_start_noflag(E1, E2 | NLA_F_NESTED) +nla_nest_start(E1, E2) Signed-off-by: Michal Kubecek Acked-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/block/drbd/drbd_nl.c | 8 +- drivers/block/nbd.c | 4 +- drivers/infiniband/core/nldev.c | 9 +- drivers/infiniband/hw/cxgb4/restrack.c | 8 +- drivers/net/bonding/bond_netlink.c | 8 +- drivers/net/ieee802154/mac802154_hwsim.c | 6 +- drivers/net/macsec.c | 27 ++-- drivers/net/macvlan.c | 2 +- drivers/net/team/team.c | 8 +- drivers/net/wireless/ath/wil6210/cfg80211.c | 4 +- include/linux/netfilter/ipset/ip_set.h | 2 +- include/net/netlink.h | 26 +++- kernel/taskstats.c | 2 +- net/8021q/vlan_netlink.c | 4 +- net/bridge/br_mdb.c | 17 +-- net/bridge/br_netlink.c | 6 +- net/bridge/br_netlink_tunnel.c | 2 +- net/core/devlink.c | 78 ++++++----- net/core/lwt_bpf.c | 2 +- net/core/lwtunnel.c | 2 +- net/core/neighbour.c | 2 +- net/core/rtnetlink.c | 48 +++---- net/dcb/dcbnl.c | 40 +++--- net/decnet/dn_table.c | 2 +- net/ieee802154/nl802154.c | 34 ++--- net/ipv4/fib_semantics.c | 2 +- net/ipv4/ipmr.c | 6 +- net/ipv4/ipmr_base.c | 2 +- net/ipv4/tcp_metrics.c | 2 +- net/ipv6/addrconf.c | 2 +- net/ipv6/route.c | 2 +- net/ipv6/seg6_local.c | 2 +- net/l2tp/l2tp_netlink.c | 4 +- net/mpls/af_mpls.c | 2 +- net/ncsi/ncsi-netlink.c | 12 +- net/netfilter/ipvs/ip_vs_ctl.c | 10 +- net/netfilter/nf_conntrack_netlink.c | 40 +++--- net/netfilter/nf_conntrack_proto_dccp.c | 2 +- net/netfilter/nf_conntrack_proto_sctp.c | 2 +- net/netfilter/nf_conntrack_proto_tcp.c | 2 +- net/netfilter/nf_tables_api.c | 29 +++-- net/netfilter/nfnetlink_cthelper.c | 7 +- net/netfilter/nfnetlink_cttimeout.c | 4 +- net/netfilter/nfnetlink_queue.c | 2 +- net/netfilter/nft_ct.c | 2 +- net/netfilter/nft_tunnel.c | 6 +- net/netlabel/netlabel_cipso_v4.c | 14 +- net/netlabel/netlabel_mgmt.c | 8 +- net/netlink/genetlink.c | 12 +- net/nfc/netlink.c | 4 +- net/openvswitch/conntrack.c | 6 +- net/openvswitch/datapath.c | 7 +- net/openvswitch/flow_netlink.c | 33 ++--- net/openvswitch/meter.c | 8 +- net/openvswitch/vport-vxlan.c | 2 +- net/openvswitch/vport.c | 2 +- net/packet/diag.c | 2 +- net/sched/act_api.c | 14 +- net/sched/act_ife.c | 2 +- net/sched/act_pedit.c | 5 +- net/sched/act_tunnel_key.c | 4 +- net/sched/cls_api.c | 4 +- net/sched/cls_basic.c | 2 +- net/sched/cls_bpf.c | 2 +- net/sched/cls_cgroup.c | 2 +- net/sched/cls_flow.c | 2 +- net/sched/cls_flower.c | 8 +- net/sched/cls_fw.c | 2 +- net/sched/cls_matchall.c | 2 +- net/sched/cls_route.c | 2 +- net/sched/cls_rsvp.h | 2 +- net/sched/cls_tcindex.c | 2 +- net/sched/cls_u32.c | 2 +- net/sched/ematch.c | 4 +- net/sched/sch_api.c | 2 +- net/sched/sch_atm.c | 2 +- net/sched/sch_cake.c | 10 +- net/sched/sch_cbq.c | 4 +- net/sched/sch_cbs.c | 2 +- net/sched/sch_choke.c | 2 +- net/sched/sch_codel.c | 2 +- net/sched/sch_drr.c | 2 +- net/sched/sch_dsmark.c | 4 +- net/sched/sch_etf.c | 2 +- net/sched/sch_fq.c | 2 +- net/sched/sch_fq_codel.c | 2 +- net/sched/sch_gred.c | 8 +- net/sched/sch_hfsc.c | 2 +- net/sched/sch_hhf.c | 2 +- net/sched/sch_htb.c | 4 +- net/sched/sch_ingress.c | 2 +- net/sched/sch_mqprio.c | 4 +- net/sched/sch_netem.c | 2 +- net/sched/sch_pie.c | 2 +- net/sched/sch_qfq.c | 2 +- net/sched/sch_red.c | 2 +- net/sched/sch_sfb.c | 2 +- net/sched/sch_taprio.c | 7 +- net/sched/sch_tbf.c | 2 +- net/tipc/bearer.c | 8 +- net/tipc/group.c | 2 +- net/tipc/link.c | 12 +- net/tipc/monitor.c | 4 +- net/tipc/name_table.c | 4 +- net/tipc/net.c | 2 +- net/tipc/netlink_compat.c | 24 ++-- net/tipc/node.c | 4 +- net/tipc/socket.c | 10 +- net/tipc/udp_media.c | 2 +- net/wireless/nl80211.c | 192 +++++++++++++++------------- net/wireless/pmsr.c | 12 +- 111 files changed, 539 insertions(+), 466 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index f2471172a961..1cb5a0b85fd9 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -114,7 +114,7 @@ static int drbd_msg_put_info(struct sk_buff *skb, const char *info) if (!info || !info[0]) return 0; - nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY); + nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY); if (!nla) return err; @@ -135,7 +135,7 @@ static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...) int err = -EMSGSIZE; int len; - nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY); + nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY); if (!nla) return err; @@ -3269,7 +3269,7 @@ static int nla_put_drbd_cfg_context(struct sk_buff *skb, struct drbd_device *device) { struct nlattr *nla; - nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT); + nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_CONTEXT); if (!nla) goto nla_put_failure; if (device && @@ -3837,7 +3837,7 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, if (err) goto nla_put_failure; - nla = nla_nest_start(skb, DRBD_NLA_STATE_INFO); + nla = nla_nest_start_noflag(skb, DRBD_NLA_STATE_INFO); if (!nla) goto nla_put_failure; if (nla_put_u32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) || diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 92b8aafb8bb4..cd27f236431d 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2047,7 +2047,7 @@ static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply) */ if (refcount_read(&nbd->config_refs)) connected = 1; - dev_opt = nla_nest_start(reply, NBD_DEVICE_ITEM); + dev_opt = nla_nest_start_noflag(reply, NBD_DEVICE_ITEM); if (!dev_opt) return -EMSGSIZE; ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index); @@ -2095,7 +2095,7 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) goto out; } - dev_list = nla_nest_start(reply, NBD_ATTR_DEVICE_LIST); + dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 11ed58d3fce5..ad189a29cc67 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -292,7 +292,8 @@ static int fill_res_info_entry(struct sk_buff *msg, { struct nlattr *entry_attr; - entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY); + entry_attr = nla_nest_start_noflag(msg, + RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY); if (!entry_attr) return -EMSGSIZE; @@ -327,7 +328,7 @@ static int fill_res_info(struct sk_buff *msg, struct ib_device *device) if (fill_nldev_handle(msg, device)) return -EMSGSIZE; - table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_SUMMARY); + table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_RES_SUMMARY); if (!table_attr) return -EMSGSIZE; @@ -1108,7 +1109,7 @@ static int res_get_common_dumpit(struct sk_buff *skb, goto err; } - table_attr = nla_nest_start(skb, fe->nldev_attr); + table_attr = nla_nest_start_noflag(skb, fe->nldev_attr); if (!table_attr) { ret = -EMSGSIZE; goto err; @@ -1134,7 +1135,7 @@ static int res_get_common_dumpit(struct sk_buff *skb, filled = true; - entry_attr = nla_nest_start(skb, fe->entry); + entry_attr = nla_nest_start_noflag(skb, fe->entry); if (!entry_attr) { ret = -EMSGSIZE; rdma_restrack_put(res); diff --git a/drivers/infiniband/hw/cxgb4/restrack.c b/drivers/infiniband/hw/cxgb4/restrack.c index 9a7520ee41e0..f82d46ed969d 100644 --- a/drivers/infiniband/hw/cxgb4/restrack.c +++ b/drivers/infiniband/hw/cxgb4/restrack.c @@ -149,7 +149,7 @@ static int fill_res_qp_entry(struct sk_buff *msg, if (qhp->ucontext) return 0; - table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER); + table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER); if (!table_attr) goto err; @@ -216,7 +216,7 @@ static int fill_res_ep_entry(struct sk_buff *msg, if (!uep) return 0; - table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER); + table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER); if (!table_attr) goto err_free_uep; @@ -387,7 +387,7 @@ static int fill_res_cq_entry(struct sk_buff *msg, if (ibcq->uobject) return 0; - table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER); + table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER); if (!table_attr) goto err; @@ -447,7 +447,7 @@ static int fill_res_mr_entry(struct sk_buff *msg, if (!stag) return 0; - table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER); + table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER); if (!table_attr) goto err; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index b286f591242e..022044b59d6a 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -546,7 +546,7 @@ static int bond_fill_info(struct sk_buff *skb, if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval)) goto nla_put_failure; - targets = nla_nest_start(skb, IFLA_BOND_ARP_IP_TARGET); + targets = nla_nest_start_noflag(skb, IFLA_BOND_ARP_IP_TARGET); if (!targets) goto nla_put_failure; @@ -644,7 +644,7 @@ static int bond_fill_info(struct sk_buff *skb, if (!bond_3ad_get_active_agg_info(bond, &info)) { struct nlattr *nest; - nest = nla_nest_start(skb, IFLA_BOND_AD_INFO); + nest = nla_nest_start_noflag(skb, IFLA_BOND_AD_INFO); if (!nest) goto nla_put_failure; @@ -711,7 +711,7 @@ static int bond_fill_linkxstats(struct sk_buff *skb, return -EINVAL; } - nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BOND); + nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BOND); if (!nest) return -EMSGSIZE; if (BOND_MODE(bond) == BOND_MODE_8023AD) { @@ -722,7 +722,7 @@ static int bond_fill_linkxstats(struct sk_buff *skb, else stats = &BOND_AD_INFO(bond).stats; - nest2 = nla_nest_start(skb, BOND_XSTATS_3AD); + nest2 = nla_nest_start_noflag(skb, BOND_XSTATS_3AD); if (!nest2) { nla_nest_end(skb, nest); return -EMSGSIZE; diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 707285953750..80ca300aba04 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -227,14 +227,16 @@ static int append_radio_msg(struct sk_buff *skb, struct hwsim_phy *phy) return 0; } - nl_edges = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGES); + nl_edges = nla_nest_start_noflag(skb, + MAC802154_HWSIM_ATTR_RADIO_EDGES); if (!nl_edges) { rcu_read_unlock(); return -ENOBUFS; } list_for_each_entry_rcu(e, &phy->edges, list) { - nl_edge = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGE); + nl_edge = nla_nest_start_noflag(skb, + MAC802154_HWSIM_ATTR_RADIO_EDGE); if (!nl_edge) { rcu_read_unlock(); nla_nest_cancel(skb, nl_edges); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 263bfafdb004..8dedb9a9781e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2365,7 +2365,8 @@ copy_secy_stats(struct sk_buff *skb, struct pcpu_secy_stats __percpu *pstats) static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) { struct macsec_tx_sc *tx_sc = &secy->tx_sc; - struct nlattr *secy_nest = nla_nest_start(skb, MACSEC_ATTR_SECY); + struct nlattr *secy_nest = nla_nest_start_noflag(skb, + MACSEC_ATTR_SECY); u64 csid; if (!secy_nest) @@ -2435,7 +2436,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, if (nla_put_secy(secy, skb)) goto nla_put_failure; - attr = nla_nest_start(skb, MACSEC_ATTR_TXSC_STATS); + attr = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSC_STATS); if (!attr) goto nla_put_failure; if (copy_tx_sc_stats(skb, tx_sc->stats)) { @@ -2444,7 +2445,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, } nla_nest_end(skb, attr); - attr = nla_nest_start(skb, MACSEC_ATTR_SECY_STATS); + attr = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY_STATS); if (!attr) goto nla_put_failure; if (copy_secy_stats(skb, macsec_priv(dev)->stats)) { @@ -2453,7 +2454,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, } nla_nest_end(skb, attr); - txsa_list = nla_nest_start(skb, MACSEC_ATTR_TXSA_LIST); + txsa_list = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSA_LIST); if (!txsa_list) goto nla_put_failure; for (i = 0, j = 1; i < MACSEC_NUM_AN; i++) { @@ -2463,7 +2464,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, if (!tx_sa) continue; - txsa_nest = nla_nest_start(skb, j++); + txsa_nest = nla_nest_start_noflag(skb, j++); if (!txsa_nest) { nla_nest_cancel(skb, txsa_list); goto nla_put_failure; @@ -2478,7 +2479,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, goto nla_put_failure; } - attr = nla_nest_start(skb, MACSEC_SA_ATTR_STATS); + attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); @@ -2496,7 +2497,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, } nla_nest_end(skb, txsa_list); - rxsc_list = nla_nest_start(skb, MACSEC_ATTR_RXSC_LIST); + rxsc_list = nla_nest_start_noflag(skb, MACSEC_ATTR_RXSC_LIST); if (!rxsc_list) goto nla_put_failure; @@ -2504,7 +2505,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, for_each_rxsc_rtnl(secy, rx_sc) { int k; struct nlattr *rxsa_list; - struct nlattr *rxsc_nest = nla_nest_start(skb, j++); + struct nlattr *rxsc_nest = nla_nest_start_noflag(skb, j++); if (!rxsc_nest) { nla_nest_cancel(skb, rxsc_list); @@ -2519,7 +2520,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, goto nla_put_failure; } - attr = nla_nest_start(skb, MACSEC_RXSC_ATTR_STATS); + attr = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); @@ -2533,7 +2534,8 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, } nla_nest_end(skb, attr); - rxsa_list = nla_nest_start(skb, MACSEC_RXSC_ATTR_SA_LIST); + rxsa_list = nla_nest_start_noflag(skb, + MACSEC_RXSC_ATTR_SA_LIST); if (!rxsa_list) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); @@ -2547,7 +2549,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, if (!rx_sa) continue; - rxsa_nest = nla_nest_start(skb, k++); + rxsa_nest = nla_nest_start_noflag(skb, k++); if (!rxsa_nest) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); @@ -2555,7 +2557,8 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev, goto nla_put_failure; } - attr = nla_nest_start(skb, MACSEC_SA_ATTR_STATS); + attr = nla_nest_start_noflag(skb, + MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 4a6be8fab884..b395423b19bc 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1624,7 +1624,7 @@ static int macvlan_fill_info(struct sk_buff *skb, if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count)) goto nla_put_failure; if (vlan->macaddr_count > 0) { - nest = nla_nest_start(skb, IFLA_MACVLAN_MACADDR_DATA); + nest = nla_nest_start_noflag(skb, IFLA_MACVLAN_MACADDR_DATA); if (nest == NULL) goto nla_put_failure; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index eb4711bfc52a..6306897c147f 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2290,7 +2290,7 @@ static int team_nl_fill_one_option_get(struct sk_buff *skb, struct team *team, if (err) return err; - option_item = nla_nest_start(skb, TEAM_ATTR_ITEM_OPTION); + option_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_OPTION); if (!option_item) return -EMSGSIZE; @@ -2404,7 +2404,7 @@ start_again: if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; - option_list = nla_nest_start(skb, TEAM_ATTR_LIST_OPTION); + option_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_OPTION); if (!option_list) goto nla_put_failure; @@ -2626,7 +2626,7 @@ static int team_nl_fill_one_port_get(struct sk_buff *skb, { struct nlattr *port_item; - port_item = nla_nest_start(skb, TEAM_ATTR_ITEM_PORT); + port_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_PORT); if (!port_item) goto nest_cancel; if (nla_put_u32(skb, TEAM_ATTR_PORT_IFINDEX, port->dev->ifindex)) @@ -2681,7 +2681,7 @@ start_again: if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; - port_list = nla_nest_start(skb, TEAM_ATTR_LIST_PORT); + port_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_PORT); if (!port_list) goto nla_put_failure; diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index a1e226652b4a..cac18e61474e 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -2679,13 +2679,13 @@ static int wil_rf_sector_get_cfg(struct wiphy *wiphy, QCA_ATTR_PAD)) goto nla_put_failure; - nl_cfgs = nla_nest_start(msg, QCA_ATTR_DMG_RF_SECTOR_CFG); + nl_cfgs = nla_nest_start_noflag(msg, QCA_ATTR_DMG_RF_SECTOR_CFG); if (!nl_cfgs) goto nla_put_failure; for (i = 0; i < WMI_MAX_RF_MODULES_NUM; i++) { if (!(rf_modules_vec & BIT(i))) continue; - nl_cfg = nla_nest_start(msg, i); + nl_cfg = nla_nest_start_noflag(msg, i); if (!nl_cfg) goto nla_put_failure; si = &reply.evt.sectors_info[i]; diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index f2e1e6b13ca4..965dc6c6653e 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -401,7 +401,7 @@ ip_set_get_h16(const struct nlattr *attr) return ntohs(nla_get_be16(attr)); } -#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED) +#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr) #define ipset_nest_end(skb, start) nla_nest_end(skb, start) static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr) diff --git a/include/net/netlink.h b/include/net/netlink.h index 23f27b0b3cef..1f18b47f41b4 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1415,13 +1415,18 @@ static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp) } /** - * nla_nest_start - Start a new level of nested attributes + * nla_nest_start_noflag - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * - * Returns the container attribute + * This function exists for backward compatibility to use in APIs which never + * marked their nest attributes with NLA_F_NESTED flag. New APIs should use + * nla_nest_start() which sets the flag. + * + * Returns the container attribute or NULL on error */ -static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) +static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, + int attrtype) { struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb); @@ -1431,6 +1436,21 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) return start; } +/** + * nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED + * @skb: socket buffer to add attributes to + * @attrtype: attribute type of container + * + * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED + * flag. This is the preferred function to use in new code. + * + * Returns the container attribute or NULL on error + */ +static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) +{ + return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED); +} + /** * nla_nest_end - Finalize nesting of attributes * @skb: socket buffer the attributes are stored in diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 1b942a7caf26..ef4f9cd980fd 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -375,7 +375,7 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; - na = nla_nest_start(skb, aggr); + na = nla_nest_start_noflag(skb, aggr); if (!na) goto err; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index a624dccf68fd..ab4921e7797b 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -227,7 +227,7 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } if (vlan->nr_ingress_mappings) { - nest = nla_nest_start(skb, IFLA_VLAN_INGRESS_QOS); + nest = nla_nest_start_noflag(skb, IFLA_VLAN_INGRESS_QOS); if (nest == NULL) goto nla_put_failure; @@ -245,7 +245,7 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev) } if (vlan->nr_egress_mappings) { - nest = nla_nest_start(skb, IFLA_VLAN_EGRESS_QOS); + nest = nla_nest_start_noflag(skb, IFLA_VLAN_EGRESS_QOS); if (nest == NULL) goto nla_put_failure; diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index f69c8d91dc81..3619c1a12a77 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -26,14 +26,14 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, if (!br->multicast_router || hlist_empty(&br->router_list)) return 0; - nest = nla_nest_start(skb, MDBA_ROUTER); + nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (nest == NULL) return -EMSGSIZE; hlist_for_each_entry_rcu(p, &br->router_list, rlist) { if (!p) continue; - port_nest = nla_nest_start(skb, MDBA_ROUTER_PORT); + port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); if (!port_nest) goto fail; if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) || @@ -86,7 +86,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return 0; - nest = nla_nest_start(skb, MDBA_MDB); + nest = nla_nest_start_noflag(skb, MDBA_MDB); if (nest == NULL) return -EMSGSIZE; @@ -98,7 +98,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, if (idx < s_idx) goto skip; - nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY); + nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!nest2) { err = -EMSGSIZE; break; @@ -124,7 +124,8 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, e.addr.u.ip6 = p->addr.u.ip6; #endif e.addr.proto = p->addr.proto; - nest_ent = nla_nest_start(skb, MDBA_MDB_ENTRY_INFO); + nest_ent = nla_nest_start_noflag(skb, + MDBA_MDB_ENTRY_INFO); if (!nest_ent) { nla_nest_cancel(skb, nest2); err = -EMSGSIZE; @@ -248,10 +249,10 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; - nest = nla_nest_start(skb, MDBA_MDB); + nest = nla_nest_start_noflag(skb, MDBA_MDB); if (nest == NULL) goto cancel; - nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY); + nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (nest2 == NULL) goto end; @@ -444,7 +445,7 @@ static int nlmsg_populate_rtr_fill(struct sk_buff *skb, memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; - nest = nla_nest_start(skb, MDBA_ROUTER); + nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (!nest) goto cancel; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 8dfcc2d285d8..0914477c4719 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -414,7 +414,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, if (event == RTM_NEWLINK && port) { struct nlattr *nest - = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED); + = nla_nest_start(skb, IFLA_PROTINFO); if (nest == NULL || br_port_fill_attrs(skb, port) < 0) goto nla_put_failure; @@ -439,7 +439,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, rcu_read_unlock(); goto done; } - af = nla_nest_start(skb, IFLA_AF_SPEC); + af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) { rcu_read_unlock(); goto nla_put_failure; @@ -1569,7 +1569,7 @@ static int br_fill_linkxstats(struct sk_buff *skb, return -EINVAL; } - nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE); + nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BRIDGE); if (!nest) return -EMSGSIZE; diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index da8cb99fd259..787e140dc4b5 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -97,7 +97,7 @@ static int br_fill_vlan_tinfo(struct sk_buff *skb, u16 vid, __be32 tid = tunnel_id_to_key32(tunnel_id); struct nlattr *tmap; - tmap = nla_nest_start(skb, IFLA_BRIDGE_VLAN_TUNNEL_INFO); + tmap = nla_nest_start_noflag(skb, IFLA_BRIDGE_VLAN_TUNNEL_INFO); if (!tmap) return -EMSGSIZE; if (nla_put_u32(skb, IFLA_BRIDGE_VLAN_TUNNEL_ID, diff --git a/net/core/devlink.c b/net/core/devlink.c index 7b91605e75d6..b94f326f5f06 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1671,7 +1671,7 @@ int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_field *field = &header->fields[match->field_id]; struct nlattr *match_attr; - match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH); + match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH); if (!match_attr) return -EMSGSIZE; @@ -1696,7 +1696,8 @@ static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table, { struct nlattr *matches_attr; - matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES); + matches_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_TABLE_MATCHES); if (!matches_attr) return -EMSGSIZE; @@ -1718,7 +1719,7 @@ int devlink_dpipe_action_put(struct sk_buff *skb, struct devlink_dpipe_field *field = &header->fields[action->field_id]; struct nlattr *action_attr; - action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION); + action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION); if (!action_attr) return -EMSGSIZE; @@ -1743,7 +1744,8 @@ static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table, { struct nlattr *actions_attr; - actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS); + actions_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_TABLE_ACTIONS); if (!actions_attr) return -EMSGSIZE; @@ -1765,7 +1767,7 @@ static int devlink_dpipe_table_put(struct sk_buff *skb, u64 table_size; table_size = table->table_ops->size_get(table->priv); - table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE); + table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE); if (!table_attr) return -EMSGSIZE; @@ -1845,7 +1847,7 @@ start_again: if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; - tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES); + tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES); if (!tables_attr) goto nla_put_failure; @@ -1946,8 +1948,8 @@ static int devlink_dpipe_action_values_put(struct sk_buff *skb, int err; for (i = 0; i < values_count; i++) { - action_attr = nla_nest_start(skb, - DEVLINK_ATTR_DPIPE_ACTION_VALUE); + action_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_ACTION_VALUE); if (!action_attr) return -EMSGSIZE; err = devlink_dpipe_action_value_put(skb, &values[i]); @@ -1983,8 +1985,8 @@ static int devlink_dpipe_match_values_put(struct sk_buff *skb, int err; for (i = 0; i < values_count; i++) { - match_attr = nla_nest_start(skb, - DEVLINK_ATTR_DPIPE_MATCH_VALUE); + match_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_MATCH_VALUE); if (!match_attr) return -EMSGSIZE; err = devlink_dpipe_match_value_put(skb, &values[i]); @@ -2005,7 +2007,7 @@ static int devlink_dpipe_entry_put(struct sk_buff *skb, struct nlattr *entry_attr, *matches_attr, *actions_attr; int err; - entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY); + entry_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY); if (!entry_attr) return -EMSGSIZE; @@ -2017,8 +2019,8 @@ static int devlink_dpipe_entry_put(struct sk_buff *skb, entry->counter, DEVLINK_ATTR_PAD)) goto nla_put_failure; - matches_attr = nla_nest_start(skb, - DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES); + matches_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES); if (!matches_attr) goto nla_put_failure; @@ -2030,8 +2032,8 @@ static int devlink_dpipe_entry_put(struct sk_buff *skb, } nla_nest_end(skb, matches_attr); - actions_attr = nla_nest_start(skb, - DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES); + actions_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES); if (!actions_attr) goto nla_put_failure; @@ -2088,8 +2090,8 @@ int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) devlink = dump_ctx->info->user_ptr[0]; if (devlink_nl_put_handle(dump_ctx->skb, devlink)) goto nla_put_failure; - dump_ctx->nest = nla_nest_start(dump_ctx->skb, - DEVLINK_ATTR_DPIPE_ENTRIES); + dump_ctx->nest = nla_nest_start_noflag(dump_ctx->skb, + DEVLINK_ATTR_DPIPE_ENTRIES); if (!dump_ctx->nest) goto nla_put_failure; return 0; @@ -2199,7 +2201,8 @@ static int devlink_dpipe_fields_put(struct sk_buff *skb, for (i = 0; i < header->fields_count; i++) { field = &header->fields[i]; - field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD); + field_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_FIELD); if (!field_attr) return -EMSGSIZE; if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) || @@ -2222,7 +2225,7 @@ static int devlink_dpipe_header_put(struct sk_buff *skb, struct nlattr *fields_attr, *header_attr; int err; - header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER); + header_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER); if (!header_attr) return -EMSGSIZE; @@ -2231,7 +2234,8 @@ static int devlink_dpipe_header_put(struct sk_buff *skb, nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) goto nla_put_failure; - fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS); + fields_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_HEADER_FIELDS); if (!fields_attr) goto nla_put_failure; @@ -2278,7 +2282,7 @@ start_again: if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; - headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS); + headers_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADERS); if (!headers_attr) goto nla_put_failure; @@ -2502,7 +2506,7 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, struct nlattr *child_resource_attr; struct nlattr *resource_attr; - resource_attr = nla_nest_start(skb, DEVLINK_ATTR_RESOURCE); + resource_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_RESOURCE); if (!resource_attr) return -EMSGSIZE; @@ -2526,7 +2530,8 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, resource->size_valid)) goto nla_put_failure; - child_resource_attr = nla_nest_start(skb, DEVLINK_ATTR_RESOURCE_LIST); + child_resource_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_RESOURCE_LIST); if (!child_resource_attr) goto nla_put_failure; @@ -2577,7 +2582,8 @@ start_again: if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; - resources_attr = nla_nest_start(skb, DEVLINK_ATTR_RESOURCE_LIST); + resources_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_RESOURCE_LIST); if (!resources_attr) goto nla_put_failure; @@ -2831,7 +2837,8 @@ devlink_nl_param_value_fill_one(struct sk_buff *msg, { struct nlattr *param_value_attr; - param_value_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUE); + param_value_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_PARAM_VALUE); if (!param_value_attr) goto nla_put_failure; @@ -2922,7 +2929,7 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index)) goto genlmsg_cancel; - param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM); + param_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PARAM); if (!param_attr) goto genlmsg_cancel; if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name)) @@ -2936,7 +2943,8 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type)) goto param_nest_cancel; - param_values_list = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUES_LIST); + param_values_list = nla_nest_start_noflag(msg, + DEVLINK_ATTR_PARAM_VALUES_LIST); if (!param_values_list) goto param_nest_cancel; @@ -3336,7 +3344,7 @@ static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct nlattr *snap_attr; int err; - snap_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOT); + snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT); if (!snap_attr) return -EINVAL; @@ -3360,7 +3368,8 @@ static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, struct nlattr *snapshots_attr; int err; - snapshots_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOTS); + snapshots_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_REGION_SNAPSHOTS); if (!snapshots_attr) return -EINVAL; @@ -3576,7 +3585,7 @@ static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, struct nlattr *chunk_attr; int err; - chunk_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_CHUNK); + chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK); if (!chunk_attr) return -EINVAL; @@ -3709,7 +3718,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, if (err) goto nla_put_failure; - chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS); + chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS); if (!chunks_attr) { err = -EMSGSIZE; goto nla_put_failure; @@ -3785,7 +3794,7 @@ static int devlink_info_version_put(struct devlink_info_req *req, int attr, struct nlattr *nest; int err; - nest = nla_nest_start(req->msg, attr); + nest = nla_nest_start_noflag(req->msg, attr); if (!nest) return -EMSGSIZE; @@ -4313,7 +4322,7 @@ devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb, int i = 0; int err; - fmsg_nlattr = nla_nest_start(skb, DEVLINK_ATTR_FMSG); + fmsg_nlattr = nla_nest_start_noflag(skb, DEVLINK_ATTR_FMSG); if (!fmsg_nlattr) return -EMSGSIZE; @@ -4665,7 +4674,8 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg, if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; - reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER); + reporter_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_HEALTH_REPORTER); if (!reporter_attr) goto genlmsg_cancel; if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 3c5c24a5d9f5..bbdfc8db1960 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -453,7 +453,7 @@ static int bpf_fill_lwt_prog(struct sk_buff *skb, int attr, if (!prog->prog) return 0; - nest = nla_nest_start(skb, attr); + nest = nla_nest_start_noflag(skb, attr); if (!nest) return -EMSGSIZE; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 94749e0e2cfd..69e249fbc02f 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -237,7 +237,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; - nest = nla_nest_start(skb, encap_attr); + nest = nla_nest_start_noflag(skb, encap_attr); if (!nest) return -EMSGSIZE; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 997cfa8f99ba..efd0b53d9ca4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1979,7 +1979,7 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) { struct nlattr *nest; - nest = nla_nest_start(skb, NDTA_PARMS); + nest = nla_nest_start_noflag(skb, NDTA_PARMS); if (nest == NULL) return -ENOBUFS; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5fa5bf3e9945..8ad44b299e72 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -634,7 +634,7 @@ static int rtnl_link_slave_info_fill(struct sk_buff *skb, if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0) return -EMSGSIZE; if (ops->fill_slave_info) { - slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA); + slave_data = nla_nest_start_noflag(skb, IFLA_INFO_SLAVE_DATA); if (!slave_data) return -EMSGSIZE; err = ops->fill_slave_info(skb, master_dev, dev); @@ -666,7 +666,7 @@ static int rtnl_link_info_fill(struct sk_buff *skb, return err; } if (ops->fill_info) { - data = nla_nest_start(skb, IFLA_INFO_DATA); + data = nla_nest_start_noflag(skb, IFLA_INFO_DATA); if (data == NULL) return -EMSGSIZE; err = ops->fill_info(skb, dev); @@ -686,7 +686,7 @@ static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) struct nlattr *linkinfo; int err = -EMSGSIZE; - linkinfo = nla_nest_start(skb, IFLA_LINKINFO); + linkinfo = nla_nest_start_noflag(skb, IFLA_LINKINFO); if (linkinfo == NULL) goto out; @@ -755,7 +755,7 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) struct nlattr *mx; int i, valid = 0; - mx = nla_nest_start(skb, RTA_METRICS); + mx = nla_nest_start_noflag(skb, RTA_METRICS); if (mx == NULL) return -ENOBUFS; @@ -1036,12 +1036,12 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) int vf; int err; - vf_ports = nla_nest_start(skb, IFLA_VF_PORTS); + vf_ports = nla_nest_start_noflag(skb, IFLA_VF_PORTS); if (!vf_ports) return -EMSGSIZE; for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) { - vf_port = nla_nest_start(skb, IFLA_VF_PORT); + vf_port = nla_nest_start_noflag(skb, IFLA_VF_PORT); if (!vf_port) goto nla_put_failure; if (nla_put_u32(skb, IFLA_PORT_VF, vf)) @@ -1070,7 +1070,7 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) struct nlattr *port_self; int err; - port_self = nla_nest_start(skb, IFLA_PORT_SELF); + port_self = nla_nest_start_noflag(skb, IFLA_PORT_SELF); if (!port_self) return -EMSGSIZE; @@ -1247,7 +1247,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, vf_linkstate.link_state = ivi.linkstate; vf_rss_query_en.setting = ivi.rss_query_en; vf_trust.setting = ivi.trusted; - vf = nla_nest_start(skb, IFLA_VF_INFO); + vf = nla_nest_start_noflag(skb, IFLA_VF_INFO); if (!vf) goto nla_put_vfinfo_failure; if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || @@ -1266,7 +1266,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, nla_put(skb, IFLA_VF_TRUST, sizeof(vf_trust), &vf_trust)) goto nla_put_vf_failure; - vfvlanlist = nla_nest_start(skb, IFLA_VF_VLAN_LIST); + vfvlanlist = nla_nest_start_noflag(skb, IFLA_VF_VLAN_LIST); if (!vfvlanlist) goto nla_put_vf_failure; if (nla_put(skb, IFLA_VF_VLAN_INFO, sizeof(vf_vlan_info), @@ -1279,7 +1279,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, if (dev->netdev_ops->ndo_get_vf_stats) dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, &vf_stats); - vfstats = nla_nest_start(skb, IFLA_VF_STATS); + vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS); if (!vfstats) goto nla_put_vf_failure; if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS, @@ -1329,7 +1329,7 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb, if (!dev->netdev_ops->ndo_get_vf_config) return 0; - vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); + vfinfo = nla_nest_start_noflag(skb, IFLA_VFINFO_LIST); if (!vfinfo) return -EMSGSIZE; @@ -1414,7 +1414,7 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) int err; u8 mode; - xdp = nla_nest_start(skb, IFLA_XDP); + xdp = nla_nest_start_noflag(skb, IFLA_XDP); if (!xdp) return -EMSGSIZE; @@ -1541,7 +1541,7 @@ static int rtnl_fill_link_af(struct sk_buff *skb, const struct rtnl_af_ops *af_ops; struct nlattr *af_spec; - af_spec = nla_nest_start(skb, IFLA_AF_SPEC); + af_spec = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af_spec) return -EMSGSIZE; @@ -1552,7 +1552,7 @@ static int rtnl_fill_link_af(struct sk_buff *skb, if (!af_ops->fill_link_af) continue; - af = nla_nest_start(skb, af_ops->family); + af = nla_nest_start_noflag(skb, af_ops->family); if (!af) return -EMSGSIZE; @@ -4273,7 +4273,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; - br_afspec = nla_nest_start(skb, IFLA_AF_SPEC); + br_afspec = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!br_afspec) goto nla_put_failure; @@ -4297,7 +4297,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, } nla_nest_end(skb, br_afspec); - protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED); + protinfo = nla_nest_start(skb, IFLA_PROTINFO); if (!protinfo) goto nla_put_failure; @@ -4776,8 +4776,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (ops && ops->fill_linkxstats) { *idxattr = IFLA_STATS_LINK_XSTATS; - attr = nla_nest_start(skb, - IFLA_STATS_LINK_XSTATS); + attr = nla_nest_start_noflag(skb, + IFLA_STATS_LINK_XSTATS); if (!attr) goto nla_put_failure; @@ -4799,8 +4799,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, ops = master->rtnl_link_ops; if (ops && ops->fill_linkxstats) { *idxattr = IFLA_STATS_LINK_XSTATS_SLAVE; - attr = nla_nest_start(skb, - IFLA_STATS_LINK_XSTATS_SLAVE); + attr = nla_nest_start_noflag(skb, + IFLA_STATS_LINK_XSTATS_SLAVE); if (!attr) goto nla_put_failure; @@ -4815,7 +4815,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, *idxattr)) { *idxattr = IFLA_STATS_LINK_OFFLOAD_XSTATS; - attr = nla_nest_start(skb, IFLA_STATS_LINK_OFFLOAD_XSTATS); + attr = nla_nest_start_noflag(skb, + IFLA_STATS_LINK_OFFLOAD_XSTATS); if (!attr) goto nla_put_failure; @@ -4834,7 +4835,7 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, struct rtnl_af_ops *af_ops; *idxattr = IFLA_STATS_AF_SPEC; - attr = nla_nest_start(skb, IFLA_STATS_AF_SPEC); + attr = nla_nest_start_noflag(skb, IFLA_STATS_AF_SPEC); if (!attr) goto nla_put_failure; @@ -4844,7 +4845,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, struct nlattr *af; int err; - af = nla_nest_start(skb, af_ops->family); + af = nla_nest_start_noflag(skb, + af_ops->family); if (!af) { rcu_read_unlock(); goto nla_put_failure; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index a556cd708885..3fd3aa7348bd 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -246,7 +246,7 @@ static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, if (ret) return ret; - nest = nla_nest_start(skb, DCB_ATTR_PFC_CFG); + nest = nla_nest_start_noflag(skb, DCB_ATTR_PFC_CFG); if (!nest) return -EMSGSIZE; @@ -304,7 +304,7 @@ static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh, if (ret) return ret; - nest = nla_nest_start(skb, DCB_ATTR_CAP); + nest = nla_nest_start_noflag(skb, DCB_ATTR_CAP); if (!nest) return -EMSGSIZE; @@ -348,7 +348,7 @@ static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, if (ret) return ret; - nest = nla_nest_start(skb, DCB_ATTR_NUMTCS); + nest = nla_nest_start_noflag(skb, DCB_ATTR_NUMTCS); if (!nest) return -EMSGSIZE; @@ -479,7 +479,7 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh, up = dcb_getapp(netdev, &app); } - app_nest = nla_nest_start(skb, DCB_ATTR_APP); + app_nest = nla_nest_start_noflag(skb, DCB_ATTR_APP); if (!app_nest) return -EMSGSIZE; @@ -578,7 +578,7 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, if (ret) return ret; - pg_nest = nla_nest_start(skb, DCB_ATTR_PG_CFG); + pg_nest = nla_nest_start_noflag(skb, DCB_ATTR_PG_CFG); if (!pg_nest) return -EMSGSIZE; @@ -598,7 +598,7 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, if (ret) goto err_pg; - param_nest = nla_nest_start(skb, i); + param_nest = nla_nest_start_noflag(skb, i); if (!param_nest) goto err_pg; @@ -889,7 +889,7 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, if (ret) return ret; - bcn_nest = nla_nest_start(skb, DCB_ATTR_BCN); + bcn_nest = nla_nest_start_noflag(skb, DCB_ATTR_BCN); if (!bcn_nest) return -EMSGSIZE; @@ -1002,7 +1002,7 @@ static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb, */ err = -EMSGSIZE; - app = nla_nest_start(skb, app_nested_type); + app = nla_nest_start_noflag(skb, app_nested_type); if (!app) goto nla_put_failure; @@ -1036,7 +1036,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) return -EMSGSIZE; - ieee = nla_nest_start(skb, DCB_ATTR_IEEE); + ieee = nla_nest_start_noflag(skb, DCB_ATTR_IEEE); if (!ieee) return -EMSGSIZE; @@ -1106,7 +1106,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) return -EMSGSIZE; } - app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE); + app = nla_nest_start_noflag(skb, DCB_ATTR_IEEE_APP_TABLE); if (!app) return -EMSGSIZE; @@ -1174,13 +1174,13 @@ static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, u8 pgid, up_map, prio, tc_pct; const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; int i = dir ? DCB_ATTR_CEE_TX_PG : DCB_ATTR_CEE_RX_PG; - struct nlattr *pg = nla_nest_start(skb, i); + struct nlattr *pg = nla_nest_start_noflag(skb, i); if (!pg) return -EMSGSIZE; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { - struct nlattr *tc_nest = nla_nest_start(skb, i); + struct nlattr *tc_nest = nla_nest_start_noflag(skb, i); if (!tc_nest) return -EMSGSIZE; @@ -1231,7 +1231,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) goto nla_put_failure; - cee = nla_nest_start(skb, DCB_ATTR_CEE); + cee = nla_nest_start_noflag(skb, DCB_ATTR_CEE); if (!cee) goto nla_put_failure; @@ -1250,7 +1250,8 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) /* local pfc */ if (ops->getpfccfg) { - struct nlattr *pfc_nest = nla_nest_start(skb, DCB_ATTR_CEE_PFC); + struct nlattr *pfc_nest = nla_nest_start_noflag(skb, + DCB_ATTR_CEE_PFC); if (!pfc_nest) goto nla_put_failure; @@ -1265,14 +1266,14 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) /* local app */ spin_lock_bh(&dcb_lock); - app = nla_nest_start(skb, DCB_ATTR_CEE_APP_TABLE); + app = nla_nest_start_noflag(skb, DCB_ATTR_CEE_APP_TABLE); if (!app) goto dcb_unlock; list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { - struct nlattr *app_nest = nla_nest_start(skb, - DCB_ATTR_APP); + struct nlattr *app_nest = nla_nest_start_noflag(skb, + DCB_ATTR_APP); if (!app_nest) goto dcb_unlock; @@ -1305,7 +1306,8 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) /* features flags */ if (ops->getfeatcfg) { - struct nlattr *feat = nla_nest_start(skb, DCB_ATTR_CEE_FEAT); + struct nlattr *feat = nla_nest_start_noflag(skb, + DCB_ATTR_CEE_FEAT); if (!feat) goto nla_put_failure; @@ -1607,7 +1609,7 @@ static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, if (ret) return ret; - nest = nla_nest_start(skb, DCB_ATTR_FEATCFG); + nest = nla_nest_start_noflag(skb, DCB_ATTR_FEATCFG); if (!nest) return -EMSGSIZE; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index f0710b5d037d..2fb764321b97 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -348,7 +348,7 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, struct rtnexthop *nhp; struct nlattr *mp_head; - if (!(mp_head = nla_nest_start(skb, RTA_MULTIPATH))) + if (!(mp_head = nla_nest_start_noflag(skb, RTA_MULTIPATH))) goto errout; for_nexthops(fi) { diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 308370cfd668..1a002eb85096 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -312,7 +312,7 @@ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq, static int nl802154_put_flags(struct sk_buff *msg, int attr, u32 mask) { - struct nlattr *nl_flags = nla_nest_start(msg, attr); + struct nlattr *nl_flags = nla_nest_start_noflag(msg, attr); int i; if (!nl_flags) @@ -338,7 +338,7 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, struct nlattr *nl_page; unsigned long page; - nl_page = nla_nest_start(msg, NL802154_ATTR_CHANNELS_SUPPORTED); + nl_page = nla_nest_start_noflag(msg, NL802154_ATTR_CHANNELS_SUPPORTED); if (!nl_page) return -ENOBUFS; @@ -360,11 +360,11 @@ nl802154_put_capabilities(struct sk_buff *msg, struct nlattr *nl_caps, *nl_channels; int i; - nl_caps = nla_nest_start(msg, NL802154_ATTR_WPAN_PHY_CAPS); + nl_caps = nla_nest_start_noflag(msg, NL802154_ATTR_WPAN_PHY_CAPS); if (!nl_caps) return -ENOBUFS; - nl_channels = nla_nest_start(msg, NL802154_CAP_ATTR_CHANNELS); + nl_channels = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_CHANNELS); if (!nl_channels) return -ENOBUFS; @@ -380,8 +380,8 @@ nl802154_put_capabilities(struct sk_buff *msg, if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { struct nlattr *nl_ed_lvls; - nl_ed_lvls = nla_nest_start(msg, - NL802154_CAP_ATTR_CCA_ED_LEVELS); + nl_ed_lvls = nla_nest_start_noflag(msg, + NL802154_CAP_ATTR_CCA_ED_LEVELS); if (!nl_ed_lvls) return -ENOBUFS; @@ -396,7 +396,8 @@ nl802154_put_capabilities(struct sk_buff *msg, if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { struct nlattr *nl_tx_pwrs; - nl_tx_pwrs = nla_nest_start(msg, NL802154_CAP_ATTR_TX_POWERS); + nl_tx_pwrs = nla_nest_start_noflag(msg, + NL802154_CAP_ATTR_TX_POWERS); if (!nl_tx_pwrs) return -ENOBUFS; @@ -504,7 +505,7 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, if (nl802154_put_capabilities(msg, rdev)) goto nla_put_failure; - nl_cmds = nla_nest_start(msg, NL802154_ATTR_SUPPORTED_COMMANDS); + nl_cmds = nla_nest_start_noflag(msg, NL802154_ATTR_SUPPORTED_COMMANDS); if (!nl_cmds) goto nla_put_failure; @@ -693,7 +694,8 @@ ieee802154_llsec_send_key_id(struct sk_buff *msg, switch (desc->mode) { case NL802154_KEY_ID_MODE_IMPLICIT: - nl_dev_addr = nla_nest_start(msg, NL802154_KEY_ID_ATTR_IMPLICIT); + nl_dev_addr = nla_nest_start_noflag(msg, + NL802154_KEY_ID_ATTR_IMPLICIT); if (!nl_dev_addr) return -ENOBUFS; @@ -768,7 +770,7 @@ static int nl802154_get_llsec_params(struct sk_buff *msg, params.frame_counter)) return -ENOBUFS; - nl_key_id = nla_nest_start(msg, NL802154_ATTR_SEC_OUT_KEY_ID); + nl_key_id = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_OUT_KEY_ID); if (!nl_key_id) return -ENOBUFS; @@ -1455,11 +1457,11 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid, if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; - nl_key = nla_nest_start(msg, NL802154_ATTR_SEC_KEY); + nl_key = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_KEY); if (!nl_key) goto nla_put_failure; - nl_key_id = nla_nest_start(msg, NL802154_KEY_ATTR_ID); + nl_key_id = nla_nest_start_noflag(msg, NL802154_KEY_ATTR_ID); if (!nl_key_id) goto nla_put_failure; @@ -1639,7 +1641,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid, if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; - nl_device = nla_nest_start(msg, NL802154_ATTR_SEC_DEVICE); + nl_device = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVICE); if (!nl_device) goto nla_put_failure; @@ -1808,7 +1810,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; - nl_devkey = nla_nest_start(msg, NL802154_ATTR_SEC_DEVKEY); + nl_devkey = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVKEY); if (!nl_devkey) goto nla_put_failure; @@ -1818,7 +1820,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, devkey->frame_counter)) goto nla_put_failure; - nl_key_id = nla_nest_start(msg, NL802154_DEVKEY_ATTR_ID); + nl_key_id = nla_nest_start_noflag(msg, NL802154_DEVKEY_ATTR_ID); if (!nl_key_id) goto nla_put_failure; @@ -1976,7 +1978,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid, if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; - nl_seclevel = nla_nest_start(msg, NL802154_ATTR_SEC_LEVEL); + nl_seclevel = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_LEVEL); if (!nl_seclevel) goto nla_put_failure; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 4336f1ec8ab0..71c2165a2ce3 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1550,7 +1550,7 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) { struct nlattr *mp; - mp = nla_nest_start(skb, RTA_MULTIPATH); + mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a8eb97777c0a..1322573b8228 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2783,7 +2783,7 @@ static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb) return true; vif = &mrt->vif_table[vifid]; - vif_nest = nla_nest_start(skb, IPMRA_VIF); + vif_nest = nla_nest_start_noflag(skb, IPMRA_VIF); if (!vif_nest) return false; if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif->dev->ifindex) || @@ -2867,7 +2867,7 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb) memset(hdr, 0, sizeof(*hdr)); hdr->ifi_family = RTNL_FAMILY_IPMR; - af = nla_nest_start(skb, IFLA_AF_SPEC); + af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) { nlmsg_cancel(skb, nlh); goto out; @@ -2878,7 +2878,7 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb) goto out; } - vifs = nla_nest_start(skb, IPMRA_TABLE_VIFS); + vifs = nla_nest_start_noflag(skb, IPMRA_TABLE_VIFS); if (!vifs) { nla_nest_end(skb, af); nlmsg_end(skb, nlh); diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 3e614cc824f7..278834d4babc 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -228,7 +228,7 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, if (c->mfc_flags & MFC_OFFLOAD) rtm->rtm_flags |= RTNH_F_OFFLOAD; - mp_attr = nla_nest_start(skb, RTA_MULTIPATH); + mp_attr = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp_attr) return -EMSGSIZE; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4ccec4c705f7..9a08bfb0672c 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -658,7 +658,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, { int n = 0; - nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS); + nest = nla_nest_start_noflag(msg, TCP_METRICS_ATTR_VALS); if (!nest) goto nla_put_failure; for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 340a0f06f974..01f081aa718c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5752,7 +5752,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, nla_put_u8(skb, IFLA_OPERSTATE, netif_running(dev) ? dev->operstate : IF_OPER_DOWN)) goto nla_put_failure; - protoinfo = nla_nest_start(skb, IFLA_PROTINFO); + protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO); if (!protoinfo) goto nla_put_failure; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9c0127a44f9f..e2b47f47de92 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4777,7 +4777,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *sibling, *next_sibling; struct nlattr *mp; - mp = nla_nest_start(skb, RTA_MULTIPATH); + mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 60325dbfe88b..67005ac71341 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -853,7 +853,7 @@ static int put_nla_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt) if (!slwt->bpf.prog) return 0; - nest = nla_nest_start(skb, SEG6_LOCAL_BPF); + nest = nla_nest_start_noflag(skb, SEG6_LOCAL_BPF); if (!nest) return -EMSGSIZE; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 77595fcc9f75..c31b50cc48d9 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -345,7 +345,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap)) goto nla_put_failure; - nest = nla_nest_start(skb, L2TP_ATTR_STATS); + nest = nla_nest_start_noflag(skb, L2TP_ATTR_STATS); if (nest == NULL) goto nla_put_failure; @@ -742,7 +742,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl session->reorder_timeout, L2TP_ATTR_PAD))) goto nla_put_failure; - nest = nla_nest_start(skb, L2TP_ATTR_STATS); + nest = nla_nest_start_noflag(skb, L2TP_ATTR_STATS); if (nest == NULL) goto nla_put_failure; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index e321a5fafb87..01f8a4f97872 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -2017,7 +2017,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, u8 linkdown = 0; u8 dead = 0; - mp = nla_nest_start(skb, RTA_MULTIPATH); + mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 367b2f6513e0..672ed56b5ef0 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -79,7 +79,7 @@ static int ncsi_write_channel_info(struct sk_buff *skb, nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.alpha2); nla_put_string(skb, NCSI_CHANNEL_ATTR_VERSION_STR, nc->version.fw_name); - vid_nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); + vid_nest = nla_nest_start_noflag(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); if (!vid_nest) return -ENOMEM; ncf = &nc->vlan_filter; @@ -113,19 +113,19 @@ static int ncsi_write_package_info(struct sk_buff *skb, NCSI_FOR_EACH_PACKAGE(ndp, np) { if (np->id != id) continue; - pnest = nla_nest_start(skb, NCSI_PKG_ATTR); + pnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR); if (!pnest) return -ENOMEM; nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id); if ((0x1 << np->id) == ndp->package_whitelist) nla_put_flag(skb, NCSI_PKG_ATTR_FORCED); - cnest = nla_nest_start(skb, NCSI_PKG_ATTR_CHANNEL_LIST); + cnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR_CHANNEL_LIST); if (!cnest) { nla_nest_cancel(skb, pnest); return -ENOMEM; } NCSI_FOR_EACH_CHANNEL(np, nc) { - nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR); + nest = nla_nest_start_noflag(skb, NCSI_CHANNEL_ATTR); if (!nest) { nla_nest_cancel(skb, cnest); nla_nest_cancel(skb, pnest); @@ -187,7 +187,7 @@ static int ncsi_pkg_info_nl(struct sk_buff *msg, struct genl_info *info) package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]); - attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST); + attr = nla_nest_start_noflag(skb, NCSI_ATTR_PACKAGE_LIST); if (!attr) { kfree_skb(skb); return -EMSGSIZE; @@ -250,7 +250,7 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb, goto err; } - attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST); + attr = nla_nest_start_noflag(skb, NCSI_ATTR_PACKAGE_LIST); if (!attr) { rc = -EMSGSIZE; goto err; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ab119a7540db..39892e5d38a2 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2916,7 +2916,7 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = { static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, struct ip_vs_kstats *kstats) { - struct nlattr *nl_stats = nla_nest_start(skb, container_type); + struct nlattr *nl_stats = nla_nest_start_noflag(skb, container_type); if (!nl_stats) return -EMSGSIZE; @@ -2946,7 +2946,7 @@ nla_put_failure: static int ip_vs_genl_fill_stats64(struct sk_buff *skb, int container_type, struct ip_vs_kstats *kstats) { - struct nlattr *nl_stats = nla_nest_start(skb, container_type); + struct nlattr *nl_stats = nla_nest_start_noflag(skb, container_type); if (!nl_stats) return -EMSGSIZE; @@ -2992,7 +2992,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, struct ip_vs_kstats kstats; char *sched_name; - nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE); + nl_service = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_SERVICE); if (!nl_service) return -EMSGSIZE; @@ -3203,7 +3203,7 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) struct nlattr *nl_dest; struct ip_vs_kstats kstats; - nl_dest = nla_nest_start(skb, IPVS_CMD_ATTR_DEST); + nl_dest = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_DEST); if (!nl_dest) return -EMSGSIZE; @@ -3373,7 +3373,7 @@ static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __u32 state, { struct nlattr *nl_daemon; - nl_daemon = nla_nest_start(skb, IPVS_CMD_ATTR_DAEMON); + nl_daemon = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_DAEMON); if (!nl_daemon) return -EMSGSIZE; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d547a777192f..148b99a15b21 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -63,7 +63,7 @@ static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, int ret = 0; struct nlattr *nest_parms; - nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTO_NUM, tuple->dst.protonum)) @@ -104,7 +104,7 @@ static int ctnetlink_dump_tuples_ip(struct sk_buff *skb, int ret = 0; struct nlattr *nest_parms; - nest_parms = nla_nest_start(skb, CTA_TUPLE_IP | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_IP); if (!nest_parms) goto nla_put_failure; @@ -187,7 +187,7 @@ static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct) if (!l4proto->to_nlattr) return 0; - nest_proto = nla_nest_start(skb, CTA_PROTOINFO | NLA_F_NESTED); + nest_proto = nla_nest_start(skb, CTA_PROTOINFO); if (!nest_proto) goto nla_put_failure; @@ -215,7 +215,7 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, if (!helper) goto out; - nest_helper = nla_nest_start(skb, CTA_HELP | NLA_F_NESTED); + nest_helper = nla_nest_start(skb, CTA_HELP); if (!nest_helper) goto nla_put_failure; if (nla_put_string(skb, CTA_HELP_NAME, helper->name)) @@ -249,7 +249,7 @@ dump_counters(struct sk_buff *skb, struct nf_conn_acct *acct, bytes = atomic64_read(&counter[dir].bytes); } - nest_count = nla_nest_start(skb, attr | NLA_F_NESTED); + nest_count = nla_nest_start(skb, attr); if (!nest_count) goto nla_put_failure; @@ -293,7 +293,7 @@ ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) if (!tstamp) return 0; - nest_count = nla_nest_start(skb, CTA_TIMESTAMP | NLA_F_NESTED); + nest_count = nla_nest_start(skb, CTA_TIMESTAMP); if (!nest_count) goto nla_put_failure; @@ -337,7 +337,7 @@ static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) return 0; ret = -1; - nest_secctx = nla_nest_start(skb, CTA_SECCTX | NLA_F_NESTED); + nest_secctx = nla_nest_start(skb, CTA_SECCTX); if (!nest_secctx) goto nla_put_failure; @@ -397,7 +397,7 @@ static int ctnetlink_dump_master(struct sk_buff *skb, const struct nf_conn *ct) if (!(ct->status & IPS_EXPECTED)) return 0; - nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, master_tuple(ct)) < 0) @@ -415,7 +415,7 @@ dump_ct_seq_adj(struct sk_buff *skb, const struct nf_ct_seqadj *seq, int type) { struct nlattr *nest_parms; - nest_parms = nla_nest_start(skb, type | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; @@ -467,7 +467,7 @@ static int ctnetlink_dump_ct_synproxy(struct sk_buff *skb, struct nf_conn *ct) if (!synproxy) return 0; - nest_parms = nla_nest_start(skb, CTA_SYNPROXY | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_SYNPROXY); if (!nest_parms) goto nla_put_failure; @@ -528,7 +528,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, zone = nf_ct_zone(ct); - nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) @@ -538,7 +538,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, goto nla_put_failure; nla_nest_end(skb, nest_parms); - nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) @@ -720,7 +720,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) zone = nf_ct_zone(ct); - nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) @@ -730,7 +730,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto nla_put_failure; nla_nest_end(skb, nest_parms); - nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) @@ -2400,7 +2400,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) zone = nf_ct_zone(ct); - nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) @@ -2410,7 +2410,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; nla_nest_end(skb, nest_parms); - nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) @@ -2472,7 +2472,7 @@ ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct, { struct nlattr *nest_parms; - nest_parms = nla_nest_start(skb, ct_attr | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, ct_attr); if (!nest_parms) goto nla_put_failure; @@ -2644,7 +2644,7 @@ static int ctnetlink_exp_dump_tuple(struct sk_buff *skb, { struct nlattr *nest_parms; - nest_parms = nla_nest_start(skb, type | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, tuple) < 0) @@ -2671,7 +2671,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, m.src.u.all = mask->src.u.all; m.dst.protonum = tuple->dst.protonum; - nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK); if (!nest_parms) goto nla_put_failure; @@ -2743,7 +2743,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NF_NAT) if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || exp->saved_proto.all) { - nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT); if (!nest_parms) goto nla_put_failure; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 6fca80587505..a4deddebec0a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -598,7 +598,7 @@ static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nlattr *nest_parms; spin_lock_bh(&ct->lock); - nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state) || diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index a7818101ad80..8cf36b684400 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -520,7 +520,7 @@ static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nlattr *nest_parms; spin_lock_bh(&ct->lock); - nest_parms = nla_nest_start(skb, CTA_PROTOINFO_SCTP | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_PROTOINFO_SCTP); if (!nest_parms) goto nla_put_failure; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index a06875a466a4..ec6c3618333d 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1192,7 +1192,7 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nf_ct_tcp_flags tmp = {}; spin_lock_bh(&ct->lock); - nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP); if (!nest_parms) goto nla_put_failure; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9d888dc6be38..2b79c250ecb4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1200,7 +1200,7 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) total.pkts += pkts; total.bytes += bytes; } - nest = nla_nest_start(skb, NFTA_CHAIN_COUNTERS); + nest = nla_nest_start_noflag(skb, NFTA_CHAIN_COUNTERS); if (nest == NULL) goto nla_put_failure; @@ -1248,7 +1248,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, const struct nf_hook_ops *ops = &basechain->ops; struct nlattr *nest; - nest = nla_nest_start(skb, NFTA_CHAIN_HOOK); + nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK); if (nest == NULL) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum))) @@ -2059,7 +2059,8 @@ static int nf_tables_fill_expr_info(struct sk_buff *skb, goto nla_put_failure; if (expr->ops->dump) { - struct nlattr *data = nla_nest_start(skb, NFTA_EXPR_DATA); + struct nlattr *data = nla_nest_start_noflag(skb, + NFTA_EXPR_DATA); if (data == NULL) goto nla_put_failure; if (expr->ops->dump(skb, expr) < 0) @@ -2078,7 +2079,7 @@ int nft_expr_dump(struct sk_buff *skb, unsigned int attr, { struct nlattr *nest; - nest = nla_nest_start(skb, attr); + nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; if (nf_tables_fill_expr_info(skb, expr) < 0) @@ -2289,7 +2290,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; } - list = nla_nest_start(skb, NFTA_RULE_EXPRESSIONS); + list = nla_nest_start_noflag(skb, NFTA_RULE_EXPRESSIONS); if (list == NULL) goto nla_put_failure; nft_rule_for_each_expr(expr, next, rule) { @@ -3258,7 +3259,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) goto nla_put_failure; - desc = nla_nest_start(skb, NFTA_SET_DESC); + desc = nla_nest_start_noflag(skb, NFTA_SET_DESC); if (desc == NULL) goto nla_put_failure; if (set->size && @@ -3908,7 +3909,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - nest = nla_nest_start(skb, NFTA_LIST_ELEM); + nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (nest == NULL) goto nla_put_failure; @@ -4052,7 +4053,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name)) goto nla_put_failure; - nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS); + nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS); if (nest == NULL) goto nla_put_failure; @@ -4124,7 +4125,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, if (nla_put_string(skb, NFTA_SET_NAME, set->name)) goto nla_put_failure; - nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS); + nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS); if (nest == NULL) goto nla_put_failure; @@ -5014,7 +5015,7 @@ static int nft_object_dump(struct sk_buff *skb, unsigned int attr, { struct nlattr *nest; - nest = nla_nest_start(skb, attr); + nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; if (obj->ops->dump(skb, obj, reset) < 0) @@ -5831,14 +5832,14 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, NFTA_FLOWTABLE_PAD)) goto nla_put_failure; - nest = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK); + nest = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK); if (!nest) goto nla_put_failure; if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) || nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority))) goto nla_put_failure; - nest_devs = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK_DEVS); + nest_devs = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK_DEVS); if (!nest_devs) goto nla_put_failure; @@ -7264,7 +7265,7 @@ int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v) { struct nlattr *nest; - nest = nla_nest_start(skb, type); + nest = nla_nest_start_noflag(skb, type); if (!nest) goto nla_put_failure; @@ -7377,7 +7378,7 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, struct nlattr *nest; int err; - nest = nla_nest_start(skb, attr); + nest = nla_nest_start_noflag(skb, attr); if (nest == NULL) return -1; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index e5d27b2e4eba..74c9794d28d6 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -462,7 +462,7 @@ nfnl_cthelper_dump_tuple(struct sk_buff *skb, { struct nlattr *nest_parms; - nest_parms = nla_nest_start(skb, NFCTH_TUPLE | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, NFCTH_TUPLE); if (nest_parms == NULL) goto nla_put_failure; @@ -487,7 +487,7 @@ nfnl_cthelper_dump_policy(struct sk_buff *skb, int i; struct nlattr *nest_parms1, *nest_parms2; - nest_parms1 = nla_nest_start(skb, NFCTH_POLICY | NLA_F_NESTED); + nest_parms1 = nla_nest_start(skb, NFCTH_POLICY); if (nest_parms1 == NULL) goto nla_put_failure; @@ -496,8 +496,7 @@ nfnl_cthelper_dump_policy(struct sk_buff *skb, goto nla_put_failure; for (i = 0; i < helper->expect_class_max + 1; i++) { - nest_parms2 = nla_nest_start(skb, - (NFCTH_POLICY_SET+i) | NLA_F_NESTED); + nest_parms2 = nla_nest_start(skb, (NFCTH_POLICY_SET + i)); if (nest_parms2 == NULL) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index c69b11ca5aad..572cb42e1ee1 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -184,7 +184,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, htonl(refcount_read(&timeout->refcnt)))) goto nla_put_failure; - nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA); if (!nest_parms) goto nla_put_failure; @@ -401,7 +401,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto)) goto nla_put_failure; - nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA | NLA_F_NESTED); + nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA); if (!nest_parms) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index e057b2961d31..be7d53943e2d 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -351,7 +351,7 @@ static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb) if (skb_vlan_tag_present(entskb)) { struct nlattr *nest; - nest = nla_nest_start(skb, NFQA_VLAN | NLA_F_NESTED); + nest = nla_nest_start(skb, NFQA_VLAN); if (!nest) goto nla_put_failure; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 7b717fad6cdc..1738ef6dcb56 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -928,7 +928,7 @@ static int nft_ct_timeout_obj_dump(struct sk_buff *skb, nla_put_be16(skb, NFTA_CT_TIMEOUT_L3PROTO, htons(timeout->l3num))) return -1; - nest_params = nla_nest_start(skb, NFTA_CT_TIMEOUT_DATA | NLA_F_NESTED); + nest_params = nla_nest_start(skb, NFTA_CT_TIMEOUT_DATA); if (!nest_params) return -1; diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index b113fcac94e1..66b52d015763 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -437,7 +437,7 @@ static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info) struct nlattr *nest; if (info->mode & IP_TUNNEL_INFO_IPV6) { - nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP6); + nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_IP6); if (!nest) return -1; @@ -448,7 +448,7 @@ static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info) nla_nest_end(skb, nest); } else { - nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP); + nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_IP); if (!nest) return -1; @@ -468,7 +468,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, struct nft_tunnel_opts *opts = &priv->opts; struct nlattr *nest; - nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_OPTS); + nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS); if (!nest) return -1; diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index ba7800f94ccc..c9775658fb98 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -498,7 +498,7 @@ list_start: if (ret_val != 0) goto list_failure_lock; - nla_a = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_TAGLST); + nla_a = nla_nest_start_noflag(ans_skb, NLBL_CIPSOV4_A_TAGLST); if (nla_a == NULL) { ret_val = -ENOMEM; goto list_failure_lock; @@ -517,7 +517,8 @@ list_start: switch (doi_def->type) { case CIPSO_V4_MAP_TRANS: - nla_a = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSLVLLST); + nla_a = nla_nest_start_noflag(ans_skb, + NLBL_CIPSOV4_A_MLSLVLLST); if (nla_a == NULL) { ret_val = -ENOMEM; goto list_failure_lock; @@ -529,7 +530,8 @@ list_start: CIPSO_V4_INV_LVL) continue; - nla_b = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSLVL); + nla_b = nla_nest_start_noflag(ans_skb, + NLBL_CIPSOV4_A_MLSLVL); if (nla_b == NULL) { ret_val = -ENOMEM; goto list_retry; @@ -548,7 +550,8 @@ list_start: } nla_nest_end(ans_skb, nla_a); - nla_a = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSCATLST); + nla_a = nla_nest_start_noflag(ans_skb, + NLBL_CIPSOV4_A_MLSCATLST); if (nla_a == NULL) { ret_val = -ENOMEM; goto list_retry; @@ -560,7 +563,8 @@ list_start: CIPSO_V4_INV_CAT) continue; - nla_b = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSCAT); + nla_b = nla_nest_start_noflag(ans_skb, + NLBL_CIPSOV4_A_MLSCAT); if (nla_b == NULL) { ret_val = -ENOMEM; goto list_retry; diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index a16eacfb2236..c6c8a101f2ff 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -315,7 +315,7 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, switch (entry->def.type) { case NETLBL_NLTYPE_ADDRSELECT: - nla_a = nla_nest_start(skb, NLBL_MGMT_A_SELECTORLIST); + nla_a = nla_nest_start_noflag(skb, NLBL_MGMT_A_SELECTORLIST); if (nla_a == NULL) return -ENOMEM; @@ -323,7 +323,8 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, struct netlbl_domaddr4_map *map4; struct in_addr addr_struct; - nla_b = nla_nest_start(skb, NLBL_MGMT_A_ADDRSELECTOR); + nla_b = nla_nest_start_noflag(skb, + NLBL_MGMT_A_ADDRSELECTOR); if (nla_b == NULL) return -ENOMEM; @@ -357,7 +358,8 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) { struct netlbl_domaddr6_map *map6; - nla_b = nla_nest_start(skb, NLBL_MGMT_A_ADDRSELECTOR); + nla_b = nla_nest_start_noflag(skb, + NLBL_MGMT_A_ADDRSELECTOR); if (nla_b == NULL) return -ENOMEM; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 288456090710..83e876591f6c 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -665,7 +665,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, struct nlattr *nla_ops; int i; - nla_ops = nla_nest_start(skb, CTRL_ATTR_OPS); + nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS); if (nla_ops == NULL) goto nla_put_failure; @@ -681,7 +681,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, if (family->policy) op_flags |= GENL_CMD_CAP_HASPOL; - nest = nla_nest_start(skb, i + 1); + nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; @@ -699,7 +699,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, struct nlattr *nla_grps; int i; - nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS); + nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; @@ -709,7 +709,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, grp = &family->mcgrps[i]; - nest = nla_nest_start(skb, i + 1); + nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; @@ -749,11 +749,11 @@ static int ctrl_fill_mcgrp_info(const struct genl_family *family, nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id)) goto nla_put_failure; - nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS); + nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; - nest = nla_nest_start(skb, 1); + nest = nla_nest_start_noflag(skb, 1); if (nest == NULL) goto nla_put_failure; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 4d9f3ac8d562..f91ce7c82746 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -392,7 +392,7 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list) if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; - sdp_attr = nla_nest_start(msg, NFC_ATTR_LLC_SDP); + sdp_attr = nla_nest_start_noflag(msg, NFC_ATTR_LLC_SDP); if (sdp_attr == NULL) { rc = -ENOMEM; goto nla_put_failure; @@ -402,7 +402,7 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list) hlist_for_each_entry_safe(sdres, n, sdres_list, node) { pr_debug("uri: %s, sap: %d\n", sdres->uri, sdres->sap); - uri_attr = nla_nest_start(msg, i++); + uri_attr = nla_nest_start_noflag(msg, i++); if (uri_attr == NULL) { rc = -ENOMEM; goto nla_put_failure; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 626629944450..ff8baf810bb3 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1683,7 +1683,7 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, { struct nlattr *start; - start = nla_nest_start(skb, OVS_CT_ATTR_NAT); + start = nla_nest_start_noflag(skb, OVS_CT_ATTR_NAT); if (!start) return false; @@ -1750,7 +1750,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, { struct nlattr *start; - start = nla_nest_start(skb, OVS_ACTION_ATTR_CT); + start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CT); if (!start) return -EMSGSIZE; @@ -2160,7 +2160,7 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(reply)) return PTR_ERR(reply); - nla_reply = nla_nest_start(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT); + nla_reply = nla_nest_start_noflag(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT); if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = ovs_ct_limit_get_zone_limit( diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a64d3eb1f9a9..356677c3a0c2 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -463,7 +463,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, nla_data(upcall_info->userdata)); if (upcall_info->egress_tun_info) { - nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY); + nla = nla_nest_start_noflag(user_skb, + OVS_PACKET_ATTR_EGRESS_TUN_KEY); if (!nla) { err = -EMSGSIZE; goto out; @@ -475,7 +476,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, } if (upcall_info->actions_len) { - nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_ACTIONS); + nla = nla_nest_start_noflag(user_skb, OVS_PACKET_ATTR_ACTIONS); if (!nla) { err = -EMSGSIZE; goto out; @@ -776,7 +777,7 @@ static int ovs_flow_cmd_fill_actions(const struct sw_flow *flow, * This can only fail for dump operations because the skb is always * properly sized for single flows. */ - start = nla_nest_start(skb, OVS_FLOW_ATTR_ACTIONS); + start = nla_nest_start_noflag(skb, OVS_FLOW_ATTR_ACTIONS); if (start) { const struct sw_flow_actions *sf_acts; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 3563acd5f92e..2427b672107a 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -856,7 +856,7 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb, const struct vxlan_metadata *opts = tun_opts; struct nlattr *nla; - nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); + nla = nla_nest_start_noflag(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); if (!nla) return -EMSGSIZE; @@ -948,7 +948,7 @@ static int ip_tun_to_nlattr(struct sk_buff *skb, struct nlattr *nla; int err; - nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL); + nla = nla_nest_start_noflag(skb, OVS_KEY_ATTR_TUNNEL); if (!nla) return -EMSGSIZE; @@ -1957,7 +1957,7 @@ static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask, { struct nlattr *start; - start = nla_nest_start(skb, OVS_KEY_ATTR_NSH); + start = nla_nest_start_noflag(skb, OVS_KEY_ATTR_NSH); if (!start) return -EMSGSIZE; @@ -2040,14 +2040,15 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) { if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask)) goto nla_put_failure; - encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); + encap = nla_nest_start_noflag(skb, OVS_KEY_ATTR_ENCAP); if (!swkey->eth.vlan.tci) goto unencap; if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) { if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask)) goto nla_put_failure; - in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); + in_encap = nla_nest_start_noflag(skb, + OVS_KEY_ATTR_ENCAP); if (!swkey->eth.cvlan.tci) goto unencap; } @@ -2226,7 +2227,7 @@ int ovs_nla_put_key(const struct sw_flow_key *swkey, int err; struct nlattr *nla; - nla = nla_nest_start(skb, attr); + nla = nla_nest_start_noflag(skb, attr); if (!nla) return -EMSGSIZE; err = __ovs_nla_put_key(swkey, output, is_mask, skb); @@ -3252,7 +3253,7 @@ static int sample_action_to_attr(const struct nlattr *attr, const struct sample_arg *arg; struct nlattr *actions; - start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE); + start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SAMPLE); if (!start) return -EMSGSIZE; @@ -3265,7 +3266,7 @@ static int sample_action_to_attr(const struct nlattr *attr, goto out; } - ac_start = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS); + ac_start = nla_nest_start_noflag(skb, OVS_SAMPLE_ATTR_ACTIONS); if (!ac_start) { err = -EMSGSIZE; goto out; @@ -3291,7 +3292,7 @@ static int clone_action_to_attr(const struct nlattr *attr, struct nlattr *start; int err = 0, rem = nla_len(attr); - start = nla_nest_start(skb, OVS_ACTION_ATTR_CLONE); + start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CLONE); if (!start) return -EMSGSIZE; @@ -3313,7 +3314,7 @@ static int check_pkt_len_action_to_attr(const struct nlattr *attr, const struct nlattr *a, *cpl_arg; int err = 0, rem = nla_len(attr); - start = nla_nest_start(skb, OVS_ACTION_ATTR_CHECK_PKT_LEN); + start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CHECK_PKT_LEN); if (!start) return -EMSGSIZE; @@ -3332,8 +3333,8 @@ static int check_pkt_len_action_to_attr(const struct nlattr *attr, * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'. */ a = nla_next(cpl_arg, &rem); - ac_start = nla_nest_start(skb, - OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL); + ac_start = nla_nest_start_noflag(skb, + OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL); if (!ac_start) { err = -EMSGSIZE; goto out; @@ -3351,8 +3352,8 @@ static int check_pkt_len_action_to_attr(const struct nlattr *attr, * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER. */ a = nla_next(a, &rem); - ac_start = nla_nest_start(skb, - OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER); + ac_start = nla_nest_start_noflag(skb, + OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER); if (!ac_start) { err = -EMSGSIZE; goto out; @@ -3386,7 +3387,7 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key); struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info; - start = nla_nest_start(skb, OVS_ACTION_ATTR_SET); + start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SET); if (!start) return -EMSGSIZE; @@ -3418,7 +3419,7 @@ static int masked_set_action_to_set_action_attr(const struct nlattr *a, /* Revert the conversion we did from a non-masked set action to * masked set action. */ - nla = nla_nest_start(skb, OVS_ACTION_ATTR_SET); + nla = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SET); if (!nla) return -EMSGSIZE; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 0be3d097ae01..fdc8be7fd8f3 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -127,7 +127,7 @@ static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id, OVS_METER_ATTR_PAD)) goto error; - nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS); + nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS); if (!nla) goto error; @@ -136,7 +136,7 @@ static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id, for (i = 0; i < meter->n_bands; ++i, ++band) { struct nlattr *band_nla; - band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC); + band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC); if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS, sizeof(struct ovs_flow_stats), &band->stats)) @@ -166,11 +166,11 @@ static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS)) goto nla_put_failure; - nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS); + nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS); if (!nla) goto nla_put_failure; - band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC); + band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC); if (!band_nla) goto nla_put_failure; /* Currently only DROP band type is supported. */ diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 8f16f11f7ad3..54965ff8cc66 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -43,7 +43,7 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) if (vxlan->cfg.flags & VXLAN_F_GBP) { struct nlattr *exts; - exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); + exts = nla_nest_start_noflag(skb, OVS_TUNNEL_ATTR_EXTENSION); if (!exts) return -EMSGSIZE; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 19f6765566e7..258ce3b7b452 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -319,7 +319,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb) if (!vport->ops->get_options) return 0; - nla = nla_nest_start(skb, OVS_VPORT_ATTR_OPTIONS); + nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_OPTIONS); if (!nla) return -EMSGSIZE; diff --git a/net/packet/diag.c b/net/packet/diag.c index 7ef1c881ae74..98abfd8644a4 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -39,7 +39,7 @@ static int pdiag_put_mclist(const struct packet_sock *po, struct sk_buff *nlskb) struct nlattr *mca; struct packet_mclist *ml; - mca = nla_nest_start(nlskb, PACKET_DIAG_MCLIST); + mca = nla_nest_start_noflag(nlskb, PACKET_DIAG_MCLIST); if (!mca) return -EMSGSIZE; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 5a87e271d35a..641ad7575f24 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -242,7 +242,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, (unsigned long)p->tcfa_tm.lastuse)) continue; - nest = nla_nest_start(skb, n_i); + nest = nla_nest_start_noflag(skb, n_i); if (!nest) { index--; goto nla_put_failure; @@ -299,7 +299,7 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct tc_action *p; unsigned long id = 1; - nest = nla_nest_start(skb, 0); + nest = nla_nest_start_noflag(skb, 0); if (nest == NULL) goto nla_put_failure; if (nla_put_string(skb, TCA_KIND, ops->kind)) @@ -776,7 +776,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) } rcu_read_unlock(); - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; err = tcf_action_dump_old(skb, a, bind, ref); @@ -800,7 +800,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { a = actions[i]; - nest = nla_nest_start(skb, a->order); + nest = nla_nest_start_noflag(skb, a->order); if (nest == NULL) goto nla_put_failure; err = tcf_action_dump_1(skb, a, bind, ref); @@ -1052,7 +1052,7 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], t->tca__pad1 = 0; t->tca__pad2 = 0; - nest = nla_nest_start(skb, TCA_ACT_TAB); + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); if (!nest) goto out_nlmsg_trim; @@ -1176,7 +1176,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, t->tca__pad1 = 0; t->tca__pad2 = 0; - nest = nla_nest_start(skb, TCA_ACT_TAB); + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); if (!nest) { NL_SET_ERR_MSG(extack, "Failed to add new netlink message"); goto out_module_put; @@ -1508,7 +1508,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (!count_attr) goto out_module_put; - nest = nla_nest_start(skb, TCA_ACT_TAB); + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); if (nest == NULL) goto out_module_put; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 31c6ffb6abe7..7a87ce2e5a76 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -387,7 +387,7 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) if (list_empty(&ife->metalist)) return 0; - nest = nla_nest_start(skb, TCA_IFE_METALST); + nest = nla_nest_start_noflag(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 287793abfaf9..ce4b54fa7834 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -108,14 +108,15 @@ err_out: static int tcf_pedit_key_ex_dump(struct sk_buff *skb, struct tcf_pedit_key_ex *keys_ex, int n) { - struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX); + struct nlattr *keys_start = nla_nest_start_noflag(skb, + TCA_PEDIT_KEYS_EX); if (!keys_start) goto nla_failure; for (; n > 0; n--) { struct nlattr *key_start; - key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX); + key_start = nla_nest_start_noflag(skb, TCA_PEDIT_KEY_EX); if (!key_start) goto nla_failure; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index d5aaf90a3971..45c0c253c7e8 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -426,7 +426,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, u8 *src = (u8 *)(info + 1); struct nlattr *start; - start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); if (!start) return -EMSGSIZE; @@ -460,7 +460,7 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (!info->options_len) return 0; - start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS); + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS); if (!start) return -EMSGSIZE; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9115f053883f..78de717afddf 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3111,7 +3111,7 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { - nest = nla_nest_start(skb, exts->action); + nest = nla_nest_start_noflag(skb, exts->action); if (nest == NULL) goto nla_put_failure; @@ -3120,7 +3120,7 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) nla_nest_end(skb, nest); } else if (exts->police) { struct tc_action *act = tcf_exts_first_act(exts); - nest = nla_nest_start(skb, exts->police); + nest = nla_nest_start_noflag(skb, exts->police); if (nest == NULL || !act) goto nla_put_failure; if (tcf_action_dump_old(skb, act, 0, 0) < 0) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 687b0af67878..dd5fdb62c6df 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -288,7 +288,7 @@ static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index b4ac58039cb1..6fd569c5a036 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -591,7 +591,7 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh, cls_bpf_offload_update_stats(tp, prog); - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 4c1567854f95..b680dd684282 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -176,7 +176,7 @@ static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = head->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index eece1ee26930..cb29fe7d5ed3 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -629,7 +629,7 @@ static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0d8968803e98..8d4f7a672f14 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2051,7 +2051,7 @@ static int fl_dump_key_geneve_opt(struct sk_buff *skb, struct nlattr *nest; int opt_off = 0; - nest = nla_nest_start(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE); + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE); if (!nest) goto nla_put_failure; @@ -2087,7 +2087,7 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, if (!enc_opts->len) return 0; - nest = nla_nest_start(skb, enc_opt_type); + nest = nla_nest_start_noflag(skb, enc_opt_type); if (!nest) goto nla_put_failure; @@ -2333,7 +2333,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; @@ -2384,7 +2384,7 @@ static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv) struct fl_flow_key *key, *mask; struct nlattr *nest; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index ad036b00427d..3fcc1d51b9d7 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -402,7 +402,7 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh, if (!f->res.classid && !tcf_exts_has_actions(&f->exts)) return skb->len; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index a13bc351a414..d54fa8e11b9e 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -303,7 +303,7 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = head->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index f006af23b64a..b3b9b151a61d 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -607,7 +607,7 @@ static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 0719a21d9c41..fa059cf934a6 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -706,7 +706,7 @@ static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 24e0a62a65cc..1a2e7d5a8776 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -601,7 +601,7 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, tp, fh, skb, t, p, r); pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h); - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 48e76a3acf8a..499477058b2d 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1294,7 +1294,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, t->tcm_handle = n->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 1331a4c2d8ff..6f2d6a761dbe 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -440,14 +440,14 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) struct nlattr *top_start; struct nlattr *list_start; - top_start = nla_nest_start(skb, tlv); + top_start = nla_nest_start_noflag(skb, tlv); if (top_start == NULL) goto nla_put_failure; if (nla_put(skb, TCA_EMATCH_TREE_HDR, sizeof(tree->hdr), &tree->hdr)) goto nla_put_failure; - list_start = nla_nest_start(skb, TCA_EMATCH_TREE_LIST); + list_start = nla_nest_start_noflag(skb, TCA_EMATCH_TREE_LIST); if (list_start == NULL) goto nla_put_failure; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c126b9f78d6e..6c81b22d214f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -542,7 +542,7 @@ static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab) { struct nlattr *nest; - nest = nla_nest_start(skb, TCA_STAB); + nest = nla_nest_start_noflag(skb, TCA_STAB); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts)) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index d714d3747bcb..c36aa57eb4af 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -609,7 +609,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_handle = flow->common.classid; tcm->tcm_info = flow->q->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 259d97bc2abd..50db72fe44de 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2735,7 +2735,7 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!opts) goto nla_put_failure; @@ -2806,7 +2806,7 @@ nla_put_failure: static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { - struct nlattr *stats = nla_nest_start(d->skb, TCA_STATS_APP); + struct nlattr *stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tstats, *ts; int i; @@ -2836,7 +2836,7 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) #undef PUT_STAT_U32 #undef PUT_STAT_U64 - tstats = nla_nest_start(d->skb, TCA_CAKE_STATS_TIN_STATS); + tstats = nla_nest_start_noflag(d->skb, TCA_CAKE_STATS_TIN_STATS); if (!tstats) goto nla_put_failure; @@ -2853,7 +2853,7 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[q->tin_order[i]]; - ts = nla_nest_start(d->skb, i + 1); + ts = nla_nest_start_noflag(d->skb, i + 1); if (!ts) goto nla_put_failure; @@ -2973,7 +2973,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, if (flow) { ktime_t now = ktime_get(); - stats = nla_nest_start(d->skb, TCA_STATS_APP); + stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); if (!stats) return -1; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 114b9048ea7e..243bce4b888b 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1305,7 +1305,7 @@ static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) struct cbq_sched_data *q = qdisc_priv(sch); struct nlattr *nest; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (cbq_dump_attr(skb, &q->link) < 0) @@ -1340,7 +1340,7 @@ cbq_dump_class(struct Qdisc *sch, unsigned long arg, tcm->tcm_handle = cl->common.classid; tcm->tcm_info = cl->q->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (cbq_dump_attr(skb, cl) < 0) diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index f68fd7a0e038..adffc6d68c06 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -449,7 +449,7 @@ static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_cbs_qopt opt = { }; struct nlattr *nest; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index eafc0d17d174..eda21dc94bde 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -452,7 +452,7 @@ static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) .Scell_log = q->parms.Scell_log, }; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 17cd81f84b5d..60ac4e61ce3a 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -217,7 +217,7 @@ static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 430df9a55ec4..022db73fd5a9 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -244,7 +244,7 @@ static int drr_dump_class(struct Qdisc *sch, unsigned long arg, tcm->tcm_handle = cl->common.classid; tcm->tcm_info = cl->qdisc->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_DRR_QUANTUM, cl->quantum)) diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 42471464ded3..cdf744e710f1 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -432,7 +432,7 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); tcm->tcm_info = p->q->handle; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || @@ -451,7 +451,7 @@ static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) struct dsmark_qdisc_data *p = qdisc_priv(sch); struct nlattr *opts = NULL; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index 1150f22983df..67107caa287c 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -460,7 +460,7 @@ static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_etf_qopt opt = { }; struct nlattr *nest; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 1a662f2bb7bb..5ca370e78d3a 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -823,7 +823,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) u64 ce_threshold = q->ce_threshold; struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index cd04d40c30b6..825a933b019a 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -527,7 +527,7 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 234afbf9115b..9bfa15e12d23 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -772,7 +772,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) if (gred_offload_dump_stats(sch)) goto nla_put_failure; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_GRED_DPS, sizeof(sopt), &sopt)) @@ -790,7 +790,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; /* Old style all-in-one dump of VQs */ - parms = nla_nest_start(skb, TCA_GRED_PARMS); + parms = nla_nest_start_noflag(skb, TCA_GRED_PARMS); if (parms == NULL) goto nla_put_failure; @@ -841,7 +841,7 @@ append_opt: nla_nest_end(skb, parms); /* Dump the VQs again, in more structured way */ - vqs = nla_nest_start(skb, TCA_GRED_VQ_LIST); + vqs = nla_nest_start_noflag(skb, TCA_GRED_VQ_LIST); if (!vqs) goto nla_put_failure; @@ -852,7 +852,7 @@ append_opt: if (!q) continue; - vq = nla_nest_start(skb, TCA_GRED_VQ_ENTRY); + vq = nla_nest_start_noflag(skb, TCA_GRED_VQ_ENTRY); if (!vq) goto nla_put_failure; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index d2ab463f22ae..97d2fb91c39f 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1300,7 +1300,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, if (cl->level == 0) tcm->tcm_info = cl->qdisc->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (hfsc_dump_curves(skb, cl) < 0) diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 9d6a47697406..43bc159c4f7c 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -654,7 +654,7 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 2f9883b196e8..64010aec5437 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1057,7 +1057,7 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) gopt.defcls = q->defcls; gopt.debug = 0; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) || @@ -1086,7 +1086,7 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, if (!cl->level && cl->leaf.q) tcm->tcm_info = cl->leaf.q->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index ce3f55259d0d..0bac926b46c7 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -106,7 +106,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb) { struct nlattr *nest; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index ea0dc112b38d..7afefed72d35 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -349,7 +349,7 @@ static int dump_rates(struct mqprio_sched *priv, int i; if (priv->flags & TC_MQPRIO_F_MIN_RATE) { - nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64); + nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MIN_RATE64); if (!nest) goto nla_put_failure; @@ -363,7 +363,7 @@ static int dump_rates(struct mqprio_sched *priv, } if (priv->flags & TC_MQPRIO_F_MAX_RATE) { - nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64); + nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MAX_RATE64); if (!nest) goto nla_put_failure; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index cc9d8133afcd..0242c0d4a2d0 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -1079,7 +1079,7 @@ static int dump_loss_model(const struct netem_sched_data *q, { struct nlattr *nest; - nest = nla_nest_start(skb, TCA_NETEM_LOSS); + nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 1cc0c7b74aa3..9bf41f4a2312 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -491,7 +491,7 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!opts) goto nla_put_failure; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 1589364b54da..bab2d4026e8b 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -619,7 +619,7 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, tcm->tcm_handle = cl->common.classid; tcm->tcm_info = cl->qdisc->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) || diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 4e8c0abf6194..b9f34e057e87 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -318,7 +318,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) if (err) goto nla_put_failure; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) || diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 2419fdb75966..f54b00a431a3 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -580,7 +580,7 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) }; sch->qstats.backlog = q->qdisc->qstats.backlog; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt)) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index df848a36b222..e016ee07dd1f 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -841,7 +841,7 @@ static int dump_entry(struct sk_buff *msg, { struct nlattr *item; - item = nla_nest_start(msg, TCA_TAPRIO_SCHED_ENTRY); + item = nla_nest_start_noflag(msg, TCA_TAPRIO_SCHED_ENTRY); if (!item) return -ENOSPC; @@ -883,7 +883,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[i] = dev->tc_to_txq[i].offset; } - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) return -ENOSPC; @@ -897,7 +897,8 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) goto options_error; - entry_list = nla_nest_start(skb, TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); + entry_list = nla_nest_start_noflag(skb, + TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); if (!entry_list) goto options_error; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index f71578dbb9e3..3ae5a29eeab3 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -448,7 +448,7 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_tbf_qopt opt; sch->qstats.backlog = q->qdisc->qstats.backlog; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index d27f30a9a01d..fd8e4e83f5e0 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -687,14 +687,14 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_BEARER); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_BEARER_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority)) @@ -1033,14 +1033,14 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MEDIA); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_MEDIA_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority)) diff --git a/net/tipc/group.c b/net/tipc/group.c index 63f39201e41e..992be6113676 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -917,7 +917,7 @@ void tipc_group_member_evt(struct tipc_group *grp, int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) { - struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP); + struct nlattr *group = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_GROUP); if (!group) return -EMSGSIZE; diff --git a/net/tipc/link.c b/net/tipc/link.c index 6053489c8063..0327c8ff8d48 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2228,7 +2228,7 @@ static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s) (s->accu_queue_sz / s->queue_sz_counts) : 0} }; - stats = nla_nest_start(skb, TIPC_NLA_LINK_STATS); + stats = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!stats) return -EMSGSIZE; @@ -2260,7 +2260,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; @@ -2282,7 +2282,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) @@ -2349,7 +2349,7 @@ static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, (stats->accu_queue_sz / stats->queue_sz_counts) : 0} }; - nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS); + nest = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!nest) return -EMSGSIZE; @@ -2389,7 +2389,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) return -EMSGSIZE; } - attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; @@ -2406,7 +2406,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window)) diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 67f69389ec17..6a6eae88442f 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -696,7 +696,7 @@ static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MON_PEER); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON_PEER); if (!attrs) goto msg_full; @@ -785,7 +785,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MON); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON); if (!attrs) goto msg_full; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 89993afe0fbd..66a65c2cdb23 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -829,11 +829,11 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE); if (!attrs) goto msg_full; - b = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL); + b = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE_PUBL); if (!b) goto attr_msg_full; diff --git a/net/tipc/net.c b/net/tipc/net.c index 7ce1e86b024f..0bba4e6b005c 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -187,7 +187,7 @@ static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg) if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 340a6e7c43a7..36fe2dbb6d87 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -399,7 +399,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, b = (struct tipc_bearer_config *)TLV_DATA(msg->req); - bearer = nla_nest_start(skb, TIPC_NLA_BEARER); + bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER); if (!bearer) return -EMSGSIZE; @@ -419,7 +419,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, return -EMSGSIZE; if (ntohl(b->priority) <= TIPC_MAX_LINK_PRI) { - prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP); if (!prop) return -EMSGSIZE; if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(b->priority))) @@ -441,7 +441,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, name = (char *)TLV_DATA(msg->req); - bearer = nla_nest_start(skb, TIPC_NLA_BEARER); + bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER); if (!bearer) return -EMSGSIZE; @@ -685,7 +685,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, lc = (struct tipc_link_config *)TLV_DATA(msg->req); - media = nla_nest_start(skb, TIPC_NLA_MEDIA); + media = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA); if (!media) return -EMSGSIZE; @@ -696,7 +696,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name)) return -EMSGSIZE; - prop = nla_nest_start(skb, TIPC_NLA_MEDIA_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA_PROP); if (!prop) return -EMSGSIZE; @@ -717,7 +717,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, lc = (struct tipc_link_config *)TLV_DATA(msg->req); - bearer = nla_nest_start(skb, TIPC_NLA_BEARER); + bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER); if (!bearer) return -EMSGSIZE; @@ -728,7 +728,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name)) return -EMSGSIZE; - prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP); if (!prop) return -EMSGSIZE; @@ -748,14 +748,14 @@ static int __tipc_nl_compat_link_set(struct sk_buff *skb, lc = (struct tipc_link_config *)TLV_DATA(msg->req); - link = nla_nest_start(skb, TIPC_NLA_LINK); + link = nla_nest_start_noflag(skb, TIPC_NLA_LINK); if (!link) return -EMSGSIZE; if (nla_put_string(skb, TIPC_NLA_LINK_NAME, lc->name)) return -EMSGSIZE; - prop = nla_nest_start(skb, TIPC_NLA_LINK_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_LINK_PROP); if (!prop) return -EMSGSIZE; @@ -811,7 +811,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, name = (char *)TLV_DATA(msg->req); - link = nla_nest_start(skb, TIPC_NLA_LINK); + link = nla_nest_start_noflag(skb, TIPC_NLA_LINK); if (!link) return -EMSGSIZE; @@ -973,7 +973,7 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock) return -EMSGSIZE; } - nest = nla_nest_start(args, TIPC_NLA_SOCK); + nest = nla_nest_start_noflag(args, TIPC_NLA_SOCK); if (!nest) { kfree_skb(args); return -EMSGSIZE; @@ -1100,7 +1100,7 @@ static int tipc_nl_compat_net_set(struct tipc_nl_compat_cmd_doit *cmd, val = ntohl(*(__be32 *)TLV_DATA(msg->req)); - net = nla_nest_start(skb, TIPC_NLA_NET); + net = nla_nest_start_noflag(skb, TIPC_NLA_NET); if (!net) return -EMSGSIZE; diff --git a/net/tipc/node.c b/net/tipc/node.c index 7478e2d4ec02..3777254a508f 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1359,7 +1359,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node) if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_NODE); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NODE); if (!attrs) goto msg_full; @@ -2353,7 +2353,7 @@ static int __tipc_nl_add_monitor_prop(struct net *net, struct tipc_nl_msg *msg) if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MON); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON); if (!attrs) goto msg_full; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1385207a301f..7918f4763fdc 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3273,7 +3273,7 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk) peer_node = tsk_peer_node(tsk); peer_port = tsk_peer_port(tsk); - nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON); + nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON); if (!nest) return -EMSGSIZE; @@ -3332,7 +3332,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb, if (!hdr) goto msg_cancel; - attrs = nla_nest_start(skb, TIPC_NLA_SOCK); + attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK); if (!attrs) goto genlmsg_cancel; @@ -3437,7 +3437,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, if (!(sk_filter_state & (1 << sk->sk_state))) return 0; - attrs = nla_nest_start(skb, TIPC_NLA_SOCK); + attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK); if (!attrs) goto msg_cancel; @@ -3455,7 +3455,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, TIPC_NLA_SOCK_PAD)) goto attr_msg_cancel; - stat = nla_nest_start(skb, TIPC_NLA_SOCK_STAT); + stat = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_STAT); if (!stat) goto attr_msg_cancel; @@ -3512,7 +3512,7 @@ static int __tipc_nl_add_sk_publ(struct sk_buff *skb, if (!hdr) goto msg_cancel; - attrs = nla_nest_start(skb, TIPC_NLA_PUBL); + attrs = nla_nest_start_noflag(skb, TIPC_NLA_PUBL); if (!attrs) goto genlmsg_cancel; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 0884a1b8ad12..24d7c79598bb 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -523,7 +523,7 @@ int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b) if (!ub) return -ENODEV; - nest = nla_nest_start(msg->skb, TIPC_NLA_BEARER_UDP_OPTS); + nest = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_UDP_OPTS); if (!nest) goto msg_full; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e74d21f4108a..0bcd5ea4b4f2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -755,13 +755,13 @@ static int nl80211_msg_put_wmm_rules(struct sk_buff *msg, { int j; struct nlattr *nl_wmm_rules = - nla_nest_start(msg, NL80211_FREQUENCY_ATTR_WMM); + nla_nest_start_noflag(msg, NL80211_FREQUENCY_ATTR_WMM); if (!nl_wmm_rules) goto nla_put_failure; for (j = 0; j < IEEE80211_NUM_ACS; j++) { - struct nlattr *nl_wmm_rule = nla_nest_start(msg, j); + struct nlattr *nl_wmm_rule = nla_nest_start_noflag(msg, j); if (!nl_wmm_rule) goto nla_put_failure; @@ -890,7 +890,7 @@ static bool nl80211_put_txq_stats(struct sk_buff *msg, return false; \ } while (0) - txqattr = nla_nest_start(msg, attrtype); + txqattr = nla_nest_start_noflag(msg, attrtype); if (!txqattr) return false; @@ -1205,7 +1205,7 @@ static struct ieee80211_channel *nl80211_get_valid_chan(struct wiphy *wiphy, static int nl80211_put_iftypes(struct sk_buff *msg, u32 attr, u16 ifmodes) { - struct nlattr *nl_modes = nla_nest_start(msg, attr); + struct nlattr *nl_modes = nla_nest_start_noflag(msg, attr); int i; if (!nl_modes) @@ -1233,8 +1233,8 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, struct nlattr *nl_combis; int i, j; - nl_combis = nla_nest_start(msg, - NL80211_ATTR_INTERFACE_COMBINATIONS); + nl_combis = nla_nest_start_noflag(msg, + NL80211_ATTR_INTERFACE_COMBINATIONS); if (!nl_combis) goto nla_put_failure; @@ -1244,18 +1244,19 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, c = &wiphy->iface_combinations[i]; - nl_combi = nla_nest_start(msg, i + 1); + nl_combi = nla_nest_start_noflag(msg, i + 1); if (!nl_combi) goto nla_put_failure; - nl_limits = nla_nest_start(msg, NL80211_IFACE_COMB_LIMITS); + nl_limits = nla_nest_start_noflag(msg, + NL80211_IFACE_COMB_LIMITS); if (!nl_limits) goto nla_put_failure; for (j = 0; j < c->n_limits; j++) { struct nlattr *nl_limit; - nl_limit = nla_nest_start(msg, j + 1); + nl_limit = nla_nest_start_noflag(msg, j + 1); if (!nl_limit) goto nla_put_failure; if (nla_put_u32(msg, NL80211_IFACE_LIMIT_MAX, @@ -1308,7 +1309,8 @@ static int nl80211_send_wowlan_tcp_caps(struct cfg80211_registered_device *rdev, if (!tcp) return 0; - nl_tcp = nla_nest_start(msg, NL80211_WOWLAN_TRIG_TCP_CONNECTION); + nl_tcp = nla_nest_start_noflag(msg, + NL80211_WOWLAN_TRIG_TCP_CONNECTION); if (!nl_tcp) return -ENOBUFS; @@ -1348,7 +1350,8 @@ static int nl80211_send_wowlan(struct sk_buff *msg, if (!rdev->wiphy.wowlan) return 0; - nl_wowlan = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED); + nl_wowlan = nla_nest_start_noflag(msg, + NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED); if (!nl_wowlan) return -ENOBUFS; @@ -1477,7 +1480,8 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, if (sband->n_iftype_data) { struct nlattr *nl_iftype_data = - nla_nest_start(msg, NL80211_BAND_ATTR_IFTYPE_DATA); + nla_nest_start_noflag(msg, + NL80211_BAND_ATTR_IFTYPE_DATA); int err; if (!nl_iftype_data) @@ -1486,7 +1490,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, for (i = 0; i < sband->n_iftype_data; i++) { struct nlattr *iftdata; - iftdata = nla_nest_start(msg, i + 1); + iftdata = nla_nest_start_noflag(msg, i + 1); if (!iftdata) return -ENOBUFS; @@ -1502,12 +1506,12 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, } /* add bitrates */ - nl_rates = nla_nest_start(msg, NL80211_BAND_ATTR_RATES); + nl_rates = nla_nest_start_noflag(msg, NL80211_BAND_ATTR_RATES); if (!nl_rates) return -ENOBUFS; for (i = 0; i < sband->n_bitrates; i++) { - nl_rate = nla_nest_start(msg, i); + nl_rate = nla_nest_start_noflag(msg, i); if (!nl_rate) return -ENOBUFS; @@ -1540,12 +1544,12 @@ nl80211_send_mgmt_stypes(struct sk_buff *msg, if (!mgmt_stypes) return 0; - nl_ifs = nla_nest_start(msg, NL80211_ATTR_TX_FRAME_TYPES); + nl_ifs = nla_nest_start_noflag(msg, NL80211_ATTR_TX_FRAME_TYPES); if (!nl_ifs) return -ENOBUFS; for (ift = 0; ift < NUM_NL80211_IFTYPES; ift++) { - nl_ftypes = nla_nest_start(msg, ift); + nl_ftypes = nla_nest_start_noflag(msg, ift); if (!nl_ftypes) return -ENOBUFS; i = 0; @@ -1563,12 +1567,12 @@ nl80211_send_mgmt_stypes(struct sk_buff *msg, nla_nest_end(msg, nl_ifs); - nl_ifs = nla_nest_start(msg, NL80211_ATTR_RX_FRAME_TYPES); + nl_ifs = nla_nest_start_noflag(msg, NL80211_ATTR_RX_FRAME_TYPES); if (!nl_ifs) return -ENOBUFS; for (ift = 0; ift < NUM_NL80211_IFTYPES; ift++) { - nl_ftypes = nla_nest_start(msg, ift); + nl_ftypes = nla_nest_start_noflag(msg, ift); if (!nl_ftypes) return -ENOBUFS; i = 0; @@ -1686,7 +1690,7 @@ nl80211_send_pmsr_ftm_capa(const struct cfg80211_pmsr_capabilities *cap, if (!cap->ftm.supported) return 0; - ftm = nla_nest_start(msg, NL80211_PMSR_TYPE_FTM); + ftm = nla_nest_start_noflag(msg, NL80211_PMSR_TYPE_FTM); if (!ftm) return -ENOBUFS; @@ -1734,7 +1738,7 @@ static int nl80211_send_pmsr_capa(struct cfg80211_registered_device *rdev, * will genlmsg_cancel() if we fail */ - pmsr = nla_nest_start(msg, NL80211_ATTR_PEER_MEASUREMENTS); + pmsr = nla_nest_start_noflag(msg, NL80211_ATTR_PEER_MEASUREMENTS); if (!pmsr) return -ENOBUFS; @@ -1749,7 +1753,7 @@ static int nl80211_send_pmsr_capa(struct cfg80211_registered_device *rdev, nla_put_flag(msg, NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR)) return -ENOBUFS; - caps = nla_nest_start(msg, NL80211_PMSR_ATTR_TYPE_CAPA); + caps = nla_nest_start_noflag(msg, NL80211_PMSR_ATTR_TYPE_CAPA); if (!caps) return -ENOBUFS; @@ -1910,7 +1914,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, break; /* fall through */ case 3: - nl_bands = nla_nest_start(msg, NL80211_ATTR_WIPHY_BANDS); + nl_bands = nla_nest_start_noflag(msg, + NL80211_ATTR_WIPHY_BANDS); if (!nl_bands) goto nla_put_failure; @@ -1923,7 +1928,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (!sband) continue; - nl_band = nla_nest_start(msg, band); + nl_band = nla_nest_start_noflag(msg, band); if (!nl_band) goto nla_put_failure; @@ -1937,15 +1942,16 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, /* fall through */ default: /* add frequencies */ - nl_freqs = nla_nest_start( - msg, NL80211_BAND_ATTR_FREQS); + nl_freqs = nla_nest_start_noflag(msg, + NL80211_BAND_ATTR_FREQS); if (!nl_freqs) goto nla_put_failure; for (i = state->chan_start - 1; i < sband->n_channels; i++) { - nl_freq = nla_nest_start(msg, i); + nl_freq = nla_nest_start_noflag(msg, + i); if (!nl_freq) goto nla_put_failure; @@ -1990,7 +1996,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, break; /* fall through */ case 4: - nl_cmds = nla_nest_start(msg, NL80211_ATTR_SUPPORTED_COMMANDS); + nl_cmds = nla_nest_start_noflag(msg, + NL80211_ATTR_SUPPORTED_COMMANDS); if (!nl_cmds) goto nla_put_failure; @@ -2138,7 +2145,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, const struct nl80211_vendor_cmd_info *info; struct nlattr *nested; - nested = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA); + nested = nla_nest_start_noflag(msg, + NL80211_ATTR_VENDOR_DATA); if (!nested) goto nla_put_failure; @@ -2154,8 +2162,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, const struct nl80211_vendor_cmd_info *info; struct nlattr *nested; - nested = nla_nest_start(msg, - NL80211_ATTR_VENDOR_EVENTS); + nested = nla_nest_start_noflag(msg, + NL80211_ATTR_VENDOR_EVENTS); if (!nested) goto nla_put_failure; @@ -2192,7 +2200,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, struct nlattr *nested; u32 bss_select_support = rdev->wiphy.bss_select_support; - nested = nla_nest_start(msg, NL80211_ATTR_BSS_SELECT); + nested = nla_nest_start_noflag(msg, + NL80211_ATTR_BSS_SELECT); if (!nested) goto nla_put_failure; @@ -2214,8 +2223,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.iftype_ext_capab) { struct nlattr *nested_ext_capab, *nested; - nested = nla_nest_start(msg, - NL80211_ATTR_IFTYPE_EXT_CAPA); + nested = nla_nest_start_noflag(msg, + NL80211_ATTR_IFTYPE_EXT_CAPA); if (!nested) goto nla_put_failure; @@ -2225,7 +2234,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, capab = &rdev->wiphy.iftype_ext_capab[i]; - nested_ext_capab = nla_nest_start(msg, i); + nested_ext_capab = nla_nest_start_noflag(msg, + i); if (!nested_ext_capab || nla_put_u32(msg, NL80211_ATTR_IFTYPE, capab->iftype) || @@ -3539,7 +3549,7 @@ static void get_key_callback(void *c, struct key_params *params) params->cipher))) goto nla_put_failure; - key = nla_nest_start(cookie->msg, NL80211_ATTR_KEY); + key = nla_nest_start_noflag(cookie->msg, NL80211_ATTR_KEY); if (!key) goto nla_put_failure; @@ -4723,7 +4733,7 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) u16 bitrate_compat; enum nl80211_rate_info rate_flg; - rate = nla_nest_start(msg, attr); + rate = nla_nest_start_noflag(msg, attr); if (!rate) return false; @@ -4810,7 +4820,7 @@ static bool nl80211_put_signal(struct sk_buff *msg, u8 mask, s8 *signal, if (!mask) return true; - attr = nla_nest_start(msg, id); + attr = nla_nest_start_noflag(msg, id); if (!attr) return false; @@ -4845,7 +4855,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, nla_put_u32(msg, NL80211_ATTR_GENERATION, sinfo->generation)) goto nla_put_failure; - sinfoattr = nla_nest_start(msg, NL80211_ATTR_STA_INFO); + sinfoattr = nla_nest_start_noflag(msg, NL80211_ATTR_STA_INFO); if (!sinfoattr) goto nla_put_failure; @@ -4934,7 +4944,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO(CONNECTED_TO_GATE, connected_to_gate, u8); if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) { - bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM); + bss_param = nla_nest_start_noflag(msg, + NL80211_STA_INFO_BSS_PARAM); if (!bss_param) goto nla_put_failure; @@ -4977,7 +4988,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, struct nlattr *tidsattr; int tid; - tidsattr = nla_nest_start(msg, NL80211_STA_INFO_TID_STATS); + tidsattr = nla_nest_start_noflag(msg, + NL80211_STA_INFO_TID_STATS); if (!tidsattr) goto nla_put_failure; @@ -4990,7 +5002,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, if (!tidstats->filled) continue; - tidattr = nla_nest_start(msg, tid + 1); + tidattr = nla_nest_start_noflag(msg, tid + 1); if (!tidattr) goto nla_put_failure; @@ -5875,7 +5887,7 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, nla_put_u32(msg, NL80211_ATTR_GENERATION, pinfo->generation)) goto nla_put_failure; - pinfoattr = nla_nest_start(msg, NL80211_ATTR_MPATH_INFO); + pinfoattr = nla_nest_start_noflag(msg, NL80211_ATTR_MPATH_INFO); if (!pinfoattr) goto nla_put_failure; if ((pinfo->filled & MPATH_INFO_FRAME_QLEN) && @@ -6326,7 +6338,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, NL80211_CMD_GET_MESH_CONFIG); if (!hdr) goto out; - pinfoattr = nla_nest_start(msg, NL80211_ATTR_MESH_CONFIG); + pinfoattr = nla_nest_start_noflag(msg, NL80211_ATTR_MESH_CONFIG); if (!pinfoattr) goto nla_put_failure; if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || @@ -6705,7 +6717,7 @@ static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom, nla_put_u8(msg, NL80211_ATTR_DFS_REGION, regdom->dfs_region))) goto nla_put_failure; - nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES); + nl_reg_rules = nla_nest_start_noflag(msg, NL80211_ATTR_REG_RULES); if (!nl_reg_rules) goto nla_put_failure; @@ -6720,7 +6732,7 @@ static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom, freq_range = ®_rule->freq_range; power_rule = ®_rule->power_rule; - nl_reg_rule = nla_nest_start(msg, i); + nl_reg_rule = nla_nest_start_noflag(msg, i); if (!nl_reg_rule) goto nla_put_failure; @@ -8389,7 +8401,7 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, NL80211_ATTR_PAD)) goto nla_put_failure; - bss = nla_nest_start(msg, NL80211_ATTR_BSS); + bss = nla_nest_start_noflag(msg, NL80211_ATTR_BSS); if (!bss) goto nla_put_failure; if ((!is_zero_ether_addr(res->bssid) && @@ -8566,7 +8578,7 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; - infoattr = nla_nest_start(msg, NL80211_ATTR_SURVEY_INFO); + infoattr = nla_nest_start_noflag(msg, NL80211_ATTR_SURVEY_INFO); if (!infoattr) goto nla_put_failure; @@ -9407,7 +9419,7 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev, goto nla_put_failure; } - data = nla_nest_start(skb, attr); + data = nla_nest_start_noflag(skb, attr); if (!data) goto nla_put_failure; @@ -9581,7 +9593,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, break; } - tmdata = nla_nest_start(skb, NL80211_ATTR_TESTDATA); + tmdata = nla_nest_start_noflag(skb, NL80211_ATTR_TESTDATA); if (!tmdata) { genlmsg_cancel(skb, hdr); break; @@ -10859,12 +10871,12 @@ static int nl80211_send_wowlan_patterns(struct sk_buff *msg, if (!wowlan->n_patterns) return 0; - nl_pats = nla_nest_start(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN); + nl_pats = nla_nest_start_noflag(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN); if (!nl_pats) return -ENOBUFS; for (i = 0; i < wowlan->n_patterns; i++) { - nl_pat = nla_nest_start(msg, i + 1); + nl_pat = nla_nest_start_noflag(msg, i + 1); if (!nl_pat) return -ENOBUFS; pat_len = wowlan->patterns[i].pattern_len; @@ -10890,7 +10902,8 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg, if (!tcp) return 0; - nl_tcp = nla_nest_start(msg, NL80211_WOWLAN_TRIG_TCP_CONNECTION); + nl_tcp = nla_nest_start_noflag(msg, + NL80211_WOWLAN_TRIG_TCP_CONNECTION); if (!nl_tcp) return -ENOBUFS; @@ -10934,7 +10947,7 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, if (!req) return 0; - nd = nla_nest_start(msg, NL80211_WOWLAN_TRIG_NET_DETECT); + nd = nla_nest_start_noflag(msg, NL80211_WOWLAN_TRIG_NET_DETECT); if (!nd) return -ENOBUFS; @@ -10960,7 +10973,7 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, return -ENOBUFS; } - freqs = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES); + freqs = nla_nest_start_noflag(msg, NL80211_ATTR_SCAN_FREQUENCIES); if (!freqs) return -ENOBUFS; @@ -10972,12 +10985,13 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, nla_nest_end(msg, freqs); if (req->n_match_sets) { - matches = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_MATCH); + matches = nla_nest_start_noflag(msg, + NL80211_ATTR_SCHED_SCAN_MATCH); if (!matches) return -ENOBUFS; for (i = 0; i < req->n_match_sets; i++) { - match = nla_nest_start(msg, i); + match = nla_nest_start_noflag(msg, i); if (!match) return -ENOBUFS; @@ -10990,12 +11004,12 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, nla_nest_end(msg, matches); } - scan_plans = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_PLANS); + scan_plans = nla_nest_start_noflag(msg, NL80211_ATTR_SCHED_SCAN_PLANS); if (!scan_plans) return -ENOBUFS; for (i = 0; i < req->n_scan_plans; i++) { - scan_plan = nla_nest_start(msg, i + 1); + scan_plan = nla_nest_start_noflag(msg, i + 1); if (!scan_plan) return -ENOBUFS; @@ -11044,7 +11058,8 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info) if (rdev->wiphy.wowlan_config) { struct nlattr *nl_wowlan; - nl_wowlan = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS); + nl_wowlan = nla_nest_start_noflag(msg, + NL80211_ATTR_WOWLAN_TRIGGERS); if (!nl_wowlan) goto nla_put_failure; @@ -11478,12 +11493,12 @@ static int nl80211_send_coalesce_rules(struct sk_buff *msg, if (!rdev->coalesce->n_rules) return 0; - nl_rules = nla_nest_start(msg, NL80211_ATTR_COALESCE_RULE); + nl_rules = nla_nest_start_noflag(msg, NL80211_ATTR_COALESCE_RULE); if (!nl_rules) return -ENOBUFS; for (i = 0; i < rdev->coalesce->n_rules; i++) { - nl_rule = nla_nest_start(msg, i + 1); + nl_rule = nla_nest_start_noflag(msg, i + 1); if (!nl_rule) return -ENOBUFS; @@ -11496,13 +11511,13 @@ static int nl80211_send_coalesce_rules(struct sk_buff *msg, rule->condition)) return -ENOBUFS; - nl_pats = nla_nest_start(msg, - NL80211_ATTR_COALESCE_RULE_PKT_PATTERN); + nl_pats = nla_nest_start_noflag(msg, + NL80211_ATTR_COALESCE_RULE_PKT_PATTERN); if (!nl_pats) return -ENOBUFS; for (j = 0; j < rule->n_patterns; j++) { - nl_pat = nla_nest_start(msg, j + 1); + nl_pat = nla_nest_start_noflag(msg, j + 1); if (!nl_pat) return -ENOBUFS; pat_len = rule->patterns[j].pattern_len; @@ -12254,7 +12269,7 @@ out: NL80211_ATTR_PAD)) goto nla_put_failure; - func_attr = nla_nest_start(msg, NL80211_ATTR_NAN_FUNC); + func_attr = nla_nest_start_noflag(msg, NL80211_ATTR_NAN_FUNC); if (!func_attr) goto nla_put_failure; @@ -12371,11 +12386,12 @@ void cfg80211_nan_match(struct wireless_dev *wdev, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, match->addr)) goto nla_put_failure; - match_attr = nla_nest_start(msg, NL80211_ATTR_NAN_MATCH); + match_attr = nla_nest_start_noflag(msg, NL80211_ATTR_NAN_MATCH); if (!match_attr) goto nla_put_failure; - local_func_attr = nla_nest_start(msg, NL80211_NAN_MATCH_FUNC_LOCAL); + local_func_attr = nla_nest_start_noflag(msg, + NL80211_NAN_MATCH_FUNC_LOCAL); if (!local_func_attr) goto nla_put_failure; @@ -12384,7 +12400,8 @@ void cfg80211_nan_match(struct wireless_dev *wdev, nla_nest_end(msg, local_func_attr); - peer_func_attr = nla_nest_start(msg, NL80211_NAN_MATCH_FUNC_PEER); + peer_func_attr = nla_nest_start_noflag(msg, + NL80211_NAN_MATCH_FUNC_PEER); if (!peer_func_attr) goto nla_put_failure; @@ -12450,7 +12467,7 @@ void cfg80211_nan_func_terminated(struct wireless_dev *wdev, NL80211_ATTR_PAD)) goto nla_put_failure; - func_attr = nla_nest_start(msg, NL80211_ATTR_NAN_FUNC); + func_attr = nla_nest_start_noflag(msg, NL80211_ATTR_NAN_FUNC); if (!func_attr) goto nla_put_failure; @@ -12799,7 +12816,8 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb, break; } - vendor_data = nla_nest_start(skb, NL80211_ATTR_VENDOR_DATA); + vendor_data = nla_nest_start_noflag(skb, + NL80211_ATTR_VENDOR_DATA); if (!vendor_data) { genlmsg_cancel(skb, hdr); break; @@ -13343,7 +13361,8 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb, if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; - ftm_stats_attr = nla_nest_start(msg, NL80211_ATTR_FTM_RESPONDER_STATS); + ftm_stats_attr = nla_nest_start_noflag(msg, + NL80211_ATTR_FTM_RESPONDER_STATS); if (!ftm_stats_attr) goto nla_put_failure; @@ -14366,7 +14385,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg, if (WARN_ON(!req)) return 0; - nest = nla_nest_start(msg, NL80211_ATTR_SCAN_SSIDS); + nest = nla_nest_start_noflag(msg, NL80211_ATTR_SCAN_SSIDS); if (!nest) goto nla_put_failure; for (i = 0; i < req->n_ssids; i++) { @@ -14375,7 +14394,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg, } nla_nest_end(msg, nest); - nest = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES); + nest = nla_nest_start_noflag(msg, NL80211_ATTR_SCAN_FREQUENCIES); if (!nest) goto nla_put_failure; for (i = 0; i < req->n_channels; i++) { @@ -14637,7 +14656,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, if (uapsd_queues >= 0) { struct nlattr *nla_wmm = - nla_nest_start(msg, NL80211_ATTR_STA_WME); + nla_nest_start_noflag(msg, NL80211_ATTR_STA_WME); if (!nla_wmm) goto nla_put_failure; @@ -15078,7 +15097,7 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, goto nla_put_failure; /* Before */ - nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_BEFORE); + nl_freq = nla_nest_start_noflag(msg, NL80211_ATTR_FREQ_BEFORE); if (!nl_freq) goto nla_put_failure; @@ -15087,7 +15106,7 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, nla_nest_end(msg, nl_freq); /* After */ - nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_AFTER); + nl_freq = nla_nest_start_noflag(msg, NL80211_ATTR_FREQ_AFTER); if (!nl_freq) goto nla_put_failure; @@ -15521,7 +15540,7 @@ static struct sk_buff *cfg80211_prepare_cqm(struct net_device *dev, if (mac && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac)) goto nla_put_failure; - cb[1] = nla_nest_start(msg, NL80211_ATTR_CQM); + cb[1] = nla_nest_start_noflag(msg, NL80211_ATTR_CQM); if (!cb[1]) goto nla_put_failure; @@ -15682,7 +15701,7 @@ static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) goto nla_put_failure; - rekey_attr = nla_nest_start(msg, NL80211_ATTR_REKEY_DATA); + rekey_attr = nla_nest_start_noflag(msg, NL80211_ATTR_REKEY_DATA); if (!rekey_attr) goto nla_put_failure; @@ -15737,7 +15756,7 @@ nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) goto nla_put_failure; - attr = nla_nest_start(msg, NL80211_ATTR_PMKSA_CANDIDATE); + attr = nla_nest_start_noflag(msg, NL80211_ATTR_PMKSA_CANDIDATE); if (!attr) goto nla_put_failure; @@ -16047,15 +16066,15 @@ static int cfg80211_net_detect_results(struct sk_buff *msg, struct nlattr *nl_results, *nl_match, *nl_freqs; int i, j; - nl_results = nla_nest_start( - msg, NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS); + nl_results = nla_nest_start_noflag(msg, + NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS); if (!nl_results) return -EMSGSIZE; for (i = 0; i < nd->n_matches; i++) { struct cfg80211_wowlan_nd_match *match = nd->matches[i]; - nl_match = nla_nest_start(msg, i); + nl_match = nla_nest_start_noflag(msg, i); if (!nl_match) break; @@ -16073,8 +16092,8 @@ static int cfg80211_net_detect_results(struct sk_buff *msg, } if (match->n_channels) { - nl_freqs = nla_nest_start( - msg, NL80211_ATTR_SCAN_FREQUENCIES); + nl_freqs = nla_nest_start_noflag(msg, + NL80211_ATTR_SCAN_FREQUENCIES); if (!nl_freqs) { nla_nest_cancel(msg, nl_match); goto out; @@ -16133,7 +16152,8 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev, if (wakeup) { struct nlattr *reasons; - reasons = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS); + reasons = nla_nest_start_noflag(msg, + NL80211_ATTR_WOWLAN_TRIGGERS); if (!reasons) goto free_msg; diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 5e2ab01d325c..5c80bccc8b3c 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -420,22 +420,22 @@ static int nl80211_pmsr_send_result(struct sk_buff *msg, { struct nlattr *pmsr, *peers, *peer, *resp, *data, *typedata; - pmsr = nla_nest_start(msg, NL80211_ATTR_PEER_MEASUREMENTS); + pmsr = nla_nest_start_noflag(msg, NL80211_ATTR_PEER_MEASUREMENTS); if (!pmsr) goto error; - peers = nla_nest_start(msg, NL80211_PMSR_ATTR_PEERS); + peers = nla_nest_start_noflag(msg, NL80211_PMSR_ATTR_PEERS); if (!peers) goto error; - peer = nla_nest_start(msg, 1); + peer = nla_nest_start_noflag(msg, 1); if (!peer) goto error; if (nla_put(msg, NL80211_PMSR_PEER_ATTR_ADDR, ETH_ALEN, res->addr)) goto error; - resp = nla_nest_start(msg, NL80211_PMSR_PEER_ATTR_RESP); + resp = nla_nest_start_noflag(msg, NL80211_PMSR_PEER_ATTR_RESP); if (!resp) goto error; @@ -452,11 +452,11 @@ static int nl80211_pmsr_send_result(struct sk_buff *msg, if (res->final && nla_put_flag(msg, NL80211_PMSR_RESP_ATTR_FINAL)) goto error; - data = nla_nest_start(msg, NL80211_PMSR_RESP_ATTR_DATA); + data = nla_nest_start_noflag(msg, NL80211_PMSR_RESP_ATTR_DATA); if (!data) goto error; - typedata = nla_nest_start(msg, res->type); + typedata = nla_nest_start_noflag(msg, res->type); if (!typedata) goto error; -- cgit v1.2.3-71-gd317 From 12ad5f65f030ae7b8a2425f6f79137c4217e30d4 Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Fri, 26 Apr 2019 11:13:09 +0200 Subject: ipset: drop ipset_nest_start() and ipset_nest_end() After the previous commit, both ipset_nest_start() and ipset_nest_end() are just aliases for nla_nest_start() and nla_nest_end() so that there is no need to keep them. Signed-off-by: Michal Kubecek Acked-by: Jozsef Kadlecsik Signed-off-by: David S. Miller --- include/linux/netfilter/ipset/ip_set.h | 11 ++++------- net/netfilter/ipset/ip_set_bitmap_gen.h | 14 +++++++------- net/netfilter/ipset/ip_set_hash_gen.h | 14 +++++++------- net/netfilter/ipset/ip_set_list_set.c | 14 +++++++------- 4 files changed, 25 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 965dc6c6653e..e499d170f12d 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -401,33 +401,30 @@ ip_set_get_h16(const struct nlattr *attr) return ntohs(nla_get_be16(attr)); } -#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr) -#define ipset_nest_end(skb, start) nla_nest_end(skb, start) - static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr) { - struct nlattr *__nested = ipset_nest_start(skb, type); + struct nlattr *__nested = nla_nest_start(skb, type); int ret; if (!__nested) return -EMSGSIZE; ret = nla_put_in_addr(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); if (!ret) - ipset_nest_end(skb, __nested); + nla_nest_end(skb, __nested); return ret; } static inline int nla_put_ipaddr6(struct sk_buff *skb, int type, const struct in6_addr *ipaddrptr) { - struct nlattr *__nested = ipset_nest_start(skb, type); + struct nlattr *__nested = nla_nest_start(skb, type); int ret; if (!__nested) return -EMSGSIZE; ret = nla_put_in6_addr(skb, IPSET_ATTR_IPADDR_IPV6, ipaddrptr); if (!ret) - ipset_nest_end(skb, __nested); + nla_nest_end(skb, __nested); return ret; } diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 257ca393e6f2..38ef2ea838cb 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -99,7 +99,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) struct nlattr *nested; size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size; - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (mtype_do_head(skb, map) || @@ -109,7 +109,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; - ipset_nest_end(skb, nested); + nla_nest_end(skb, nested); return 0; nla_put_failure: @@ -213,7 +213,7 @@ mtype_list(const struct ip_set *set, u32 id, first = cb->args[IPSET_CB_ARG0]; int ret = 0; - adt = ipset_nest_start(skb, IPSET_ATTR_ADT); + adt = nla_nest_start(skb, IPSET_ATTR_ADT); if (!adt) return -EMSGSIZE; /* Extensions may be replaced */ @@ -230,7 +230,7 @@ mtype_list(const struct ip_set *set, #endif ip_set_timeout_expired(ext_timeout(x, set)))) continue; - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) { if (id == first) { nla_nest_cancel(skb, adt); @@ -244,9 +244,9 @@ mtype_list(const struct ip_set *set, goto nla_put_failure; if (ip_set_put_extensions(skb, set, x, mtype_is_filled(x))) goto nla_put_failure; - ipset_nest_end(skb, nested); + nla_nest_end(skb, nested); } - ipset_nest_end(skb, adt); + nla_nest_end(skb, adt); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; @@ -259,7 +259,7 @@ nla_put_failure: cb->args[IPSET_CB_ARG0] = 0; ret = -EMSGSIZE; } - ipset_nest_end(skb, adt); + nla_nest_end(skb, adt); out: rcu_read_unlock(); return ret; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 2c9609929c71..01d51f775f12 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1057,7 +1057,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) htable_bits = t->htable_bits; rcu_read_unlock_bh(); - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, @@ -1079,7 +1079,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; - ipset_nest_end(skb, nested); + nla_nest_end(skb, nested); return 0; nla_put_failure: @@ -1124,7 +1124,7 @@ mtype_list(const struct ip_set *set, void *incomplete; int i, ret = 0; - atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + atd = nla_nest_start(skb, IPSET_ATTR_ADT); if (!atd) return -EMSGSIZE; @@ -1150,7 +1150,7 @@ mtype_list(const struct ip_set *set, continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) { if (cb->args[IPSET_CB_ARG0] == first) { nla_nest_cancel(skb, atd); @@ -1163,10 +1163,10 @@ mtype_list(const struct ip_set *set, goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; - ipset_nest_end(skb, nested); + nla_nest_end(skb, nested); } } - ipset_nest_end(skb, atd); + nla_nest_end(skb, atd); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; @@ -1180,7 +1180,7 @@ nla_put_failure: cb->args[IPSET_CB_ARG0] = 0; ret = -EMSGSIZE; } else { - ipset_nest_end(skb, atd); + nla_nest_end(skb, atd); } out: rcu_read_unlock(); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 8da228da53ae..4f894165cdcd 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -466,7 +466,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) struct nlattr *nested; size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size; - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) || @@ -476,7 +476,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; - ipset_nest_end(skb, nested); + nla_nest_end(skb, nested); return 0; nla_put_failure: @@ -494,7 +494,7 @@ list_set_list(const struct ip_set *set, struct set_elem *e; int ret = 0; - atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + atd = nla_nest_start(skb, IPSET_ATTR_ADT); if (!atd) return -EMSGSIZE; @@ -506,7 +506,7 @@ list_set_list(const struct ip_set *set, i++; continue; } - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; ip_set_name_byindex(map->net, e->id, name); @@ -514,11 +514,11 @@ list_set_list(const struct ip_set *set, goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; - ipset_nest_end(skb, nested); + nla_nest_end(skb, nested); i++; } - ipset_nest_end(skb, atd); + nla_nest_end(skb, atd); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; goto out; @@ -531,7 +531,7 @@ nla_put_failure: ret = -EMSGSIZE; } else { cb->args[IPSET_CB_ARG0] = i; - ipset_nest_end(skb, atd); + nla_nest_end(skb, atd); } out: rcu_read_unlock(); -- cgit v1.2.3-71-gd317 From 316793fb2d907d4726b4977b6be26ec653827774 Mon Sep 17 00:00:00 2001 From: Eli Britstein Date: Mon, 29 Apr 2019 18:14:01 +0000 Subject: net/mlx5: E-Switch: Introduce prio tag mode Current ConnectX HW is unable to perform VLAN pop in TX path and VLAN push on RX path. To workaround that limitation untagged packets will be tagged with VLAN ID 0x000 (priority tag) and pop/push actions will be replaced by VLAN re-write actions (which are supported by the HW). Introduce prio tag mode as a pre-step to controlling the workaround behavior. Signed-off-by: Eli Britstein Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4b37519bd6a5..eeedf3f53ed3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -951,7 +951,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_srq_sz[0x8]; u8 log_max_qp_sz[0x8]; - u8 reserved_at_90[0xb]; + u8 reserved_at_90[0x8]; + u8 prio_tag_required[0x1]; + u8 reserved_at_99[0x2]; u8 log_max_qp[0x5]; u8 reserved_at_a0[0xb]; -- cgit v1.2.3-71-gd317 From 27b942fbbd3107d4e969ece133925cd646239ef4 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 29 Apr 2019 18:14:02 +0000 Subject: net/mlx5: Get rid of storing copy of device name Currently mlx5 core stores copy of the PCI device name in a mlx5_priv structure and uses pr_warn, pr_err helpers. Get rid of the copy of this name; instead store the parent device pointer that contains name as well as dma specific parameters. This also allows to use kernel's well defined dev_warn, dev_err, dev_dbg device specific print routines. This is also a preparation patch to access non PCI parent device in future. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +- .../mellanox/mlx5/core/diag/fw_tracer_tracepoint.h | 5 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 8 +-- drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 15 +++-- .../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 65 ++++++++++++---------- .../net/ethernet/mellanox/mlx5/core/pagealloc.c | 5 +- include/linux/mlx5/driver.h | 3 +- 9 files changed, 57 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 0a2ffe794a54..779fa1e9ee4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1347,7 +1347,7 @@ static void set_wqname(struct mlx5_core_dev *dev) struct mlx5_cmd *cmd = &dev->cmd; snprintf(cmd->wq_name, sizeof(cmd->wq_name), "mlx5_cmd_%s", - dev->priv.name); + dev_name(dev->device)); } static void clean_debug_files(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h index 7b5901d42994..3038be575923 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h @@ -47,7 +47,7 @@ TRACE_EVENT(mlx5_fw, TP_ARGS(tracer, trace_timestamp, lost, event_id, msg), TP_STRUCT__entry( - __string(dev_name, tracer->dev->priv.name) + __string(dev_name, dev_name(tracer->dev->device)) __field(u64, trace_timestamp) __field(bool, lost) __field(u8, event_id) @@ -55,7 +55,8 @@ TRACE_EVENT(mlx5_fw, ), TP_fast_assign( - __assign_str(dev_name, tracer->dev->priv.name); + __assign_str(dev_name, + dev_name(tracer->dev->device)); __entry->trace_timestamp = trace_timestamp; __entry->lost = lost; __entry->event_id = event_id; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b4967a0ff8c7..a40e801cf713 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -663,7 +663,8 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, } netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n", - hp->tirn, hp->pair->rqn[0], hp->pair->peer_mdev->priv.name, + hp->tirn, hp->pair->rqn[0], + dev_name(hp->pair->peer_mdev->device), hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets); hpe->hp = hp; @@ -700,7 +701,7 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv, hpe = list_entry(next, struct mlx5e_hairpin_entry, flows); netdev_dbg(priv->netdev, "del hairpin: peer %s\n", - hpe->hp->pair->peer_mdev->priv.name); + dev_name(hpe->hp->pair->peer_mdev->device)); mlx5e_hairpin_destroy(hpe->hp); hash_del(&hpe->hairpin_hlist); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 3f3cd32ae60a..c1d6bb90cf04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -376,11 +376,11 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0, #define MLX5_DEBUG_ESWITCH_MASK BIT(3) -#define esw_info(dev, format, ...) \ - pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__) +#define esw_info(__dev, format, ...) \ + dev_info((__dev)->device, "E-Switch: " format, ##__VA_ARGS__) -#define esw_warn(dev, format, ...) \ - pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__) +#define esw_warn(__dev, format, ...) \ + dev_warn((__dev)->device, "E-Switch: " format, ##__VA_ARGS__) #define esw_debug(dev, format, ...) \ mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 3b98fcdd7d0e..a2656f4008d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -380,7 +380,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev) return -ENOMEM; strcpy(name, "mlx5_health"); - strcat(name, dev->priv.name); + strcat(name, dev_name(dev->device)); health->wq = create_singlethread_workqueue(name); kfree(name); if (!health->wq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b200a29d1420..bedf809737b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -741,7 +741,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, struct mlx5_priv *priv = &dev->priv; int err = 0; - dev->pdev = pdev; priv->pci_dev_data = id->driver_data; pci_set_drvdata(dev->pdev, dev); @@ -1242,14 +1241,11 @@ static const struct devlink_ops mlx5_devlink_ops = { #endif }; -static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char *name) +static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) { struct mlx5_priv *priv = &dev->priv; int err; - strncpy(priv->name, name, MLX5_MAX_NAME_LEN); - priv->name[MLX5_MAX_NAME_LEN - 1] = 0; - dev->profile = &profile[profile_idx]; INIT_LIST_HEAD(&priv->ctx_list); @@ -1267,9 +1263,10 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char INIT_LIST_HEAD(&priv->pgdir_list); spin_lock_init(&priv->mkey_lock); - priv->dbg_root = debugfs_create_dir(name, mlx5_debugfs_root); + priv->dbg_root = debugfs_create_dir(dev_name(dev->device), + mlx5_debugfs_root); if (!priv->dbg_root) { - pr_err("mlx5_core: %s error, Cannot create debugfs dir, aborting\n", name); + dev_err(dev->device, "mlx5_core: error, Cannot create debugfs dir, aborting\n"); return -ENOMEM; } @@ -1312,8 +1309,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) } dev = devlink_priv(devlink); + dev->device = &pdev->dev; + dev->pdev = pdev; - err = mlx5_mdev_init(dev, prof_sel, dev_name(&pdev->dev)); + err = mlx5_mdev_init(dev, prof_sel); if (err) goto mdev_init_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index d66f4f082ef7..0e111b70c178 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -41,6 +41,7 @@ #include #include #include +#include #define DRIVER_NAME "mlx5_core" #define DRIVER_VERSION "5.0-0" @@ -48,53 +49,57 @@ extern uint mlx5_core_debug_mask; #define mlx5_core_dbg(__dev, format, ...) \ - pr_debug("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ + dev_dbg((__dev)->device, "%s:%d:(pid %d): " format, \ __func__, __LINE__, current->pid, \ ##__VA_ARGS__) -#define mlx5_core_dbg_once(__dev, format, ...) \ - pr_debug_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ - __func__, __LINE__, current->pid, \ +#define mlx5_core_dbg_once(__dev, format, ...) \ + dev_dbg_once((__dev)->device, \ + "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) -#define mlx5_core_dbg_mask(__dev, mask, format, ...) \ -do { \ - if ((mask) & mlx5_core_debug_mask) \ - mlx5_core_dbg(__dev, format, ##__VA_ARGS__); \ +#define mlx5_core_dbg_mask(__dev, mask, format, ...) \ +do { \ + if ((mask) & mlx5_core_debug_mask) \ + mlx5_core_dbg(__dev, format, ##__VA_ARGS__); \ } while (0) -#define mlx5_core_err(__dev, format, ...) \ - pr_err("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ - __func__, __LINE__, current->pid, \ +#define mlx5_core_err(__dev, format, ...) \ + dev_err((__dev)->device, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) -#define mlx5_core_err_rl(__dev, format, ...) \ - pr_err_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ - __func__, __LINE__, current->pid, \ - ##__VA_ARGS__) +#define mlx5_core_err_rl(__dev, format, ...) \ + dev_err_ratelimited((__dev)->device, \ + "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ + ##__VA_ARGS__) -#define mlx5_core_warn(__dev, format, ...) \ - pr_warn("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ - __func__, __LINE__, current->pid, \ - ##__VA_ARGS__) +#define mlx5_core_warn(__dev, format, ...) \ + dev_warn((__dev)->device, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ + ##__VA_ARGS__) #define mlx5_core_warn_once(__dev, format, ...) \ - pr_warn_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ + dev_warn_once((__dev)->device, "%s:%d:(pid %d): " format, \ __func__, __LINE__, current->pid, \ ##__VA_ARGS__) -#define mlx5_core_warn_rl(__dev, format, ...) \ - pr_warn_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ - __func__, __LINE__, current->pid, \ - ##__VA_ARGS__) +#define mlx5_core_warn_rl(__dev, format, ...) \ + dev_warn_ratelimited((__dev)->device, \ + "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ + ##__VA_ARGS__) -#define mlx5_core_info(__dev, format, ...) \ - pr_info("%s " format, (__dev)->priv.name, ##__VA_ARGS__) +#define mlx5_core_info(__dev, format, ...) \ + dev_info((__dev)->device, format, ##__VA_ARGS__) -#define mlx5_core_info_rl(__dev, format, ...) \ - pr_info_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \ - __func__, __LINE__, current->pid, \ - ##__VA_ARGS__) +#define mlx5_core_info_rl(__dev, format, ...) \ + dev_info_ratelimited((__dev)->device, \ + "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ + ##__VA_ARGS__) enum { MLX5_CMD_DATA, /* print command payload only */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 41025387ff2c..d87d42f4f6dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -600,8 +600,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) return 0; } - mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages, - dev->priv.name); + mlx5_core_dbg(dev, "Waiting for %d pages\n", prev_pages); while (*pages) { if (time_after(jiffies, end)) { mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages); @@ -614,6 +613,6 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) msleep(50); } - mlx5_core_dbg(dev, "All pages received from %s\n", dev->priv.name); + mlx5_core_dbg(dev, "All pages received\n"); return 0; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6c43191c0186..582a9680b182 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -56,7 +56,6 @@ enum { MLX5_BOARD_ID_LEN = 64, - MLX5_MAX_NAME_LEN = 16, }; enum { @@ -514,7 +513,6 @@ struct mlx5_rl_table { }; struct mlx5_priv { - char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table *eq_table; /* pages stuff */ @@ -641,6 +639,7 @@ struct mlx5_fw_tracer; struct mlx5_vxlan; struct mlx5_core_dev { + struct device *device; struct pci_dev *pdev; /* sync pci state */ struct mutex pci_status_mutex; -- cgit v1.2.3-71-gd317 From d83eb50e29de36ddc819863ab7b9d2da58bccbd0 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 29 Apr 2019 18:14:12 +0000 Subject: net/mlx5: Add support in RDMA RX steering Add new flow steering namespace - MLX5_FLOW_NAMESPACE_RDMA_RX. Flow steering rules in this namespace are used to filter RDMA traffic. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 27 +++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 2 ++ include/linux/mlx5/device.h | 6 +++++ include/linux/mlx5/fs.h | 1 + include/linux/mlx5/mlx5_ifc.h | 2 +- 6 files changed, 38 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index e89555da485e..629c5ab1c0d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -854,6 +854,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ case FS_FT_SNIFFER_RX: case FS_FT_SNIFFER_TX: case FS_FT_NIC_TX: + case FS_FT_RDMA_RX: return mlx5_fs_cmd_get_fw_cmds(); default: return mlx5_fs_cmd_get_stub_cmds(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 6024df821734..3c2302a2b9d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2054,6 +2054,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->sniffer_tx_root_ns) return &steering->sniffer_tx_root_ns->ns; return NULL; + case MLX5_FLOW_NAMESPACE_RDMA_RX: + if (steering->rdma_rx_root_ns) + return &steering->rdma_rx_root_ns->ns; + return NULL; default: break; } @@ -2450,6 +2454,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) steering->fdb_sub_ns = NULL; cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); + cleanup_root_ns(steering->rdma_rx_root_ns); cleanup_root_ns(steering->egress_root_ns); mlx5_cleanup_fc_stats(dev); kmem_cache_destroy(steering->ftes_cache); @@ -2491,6 +2496,22 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) return 0; } +static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) +{ + struct fs_prio *prio; + + steering->rdma_rx_root_ns = create_root_ns(steering, FS_FT_RDMA_RX); + if (!steering->rdma_rx_root_ns) + return -ENOMEM; + + /* Create single prio */ + prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1); + if (IS_ERR(prio)) { + cleanup_root_ns(steering->rdma_rx_root_ns); + return PTR_ERR(prio); + } + return 0; +} static int init_fdb_root_ns(struct mlx5_flow_steering *steering) { struct mlx5_flow_namespace *ns; @@ -2727,6 +2748,12 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } + if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support)) { + err = init_rdma_rx_root_ns(steering); + if (err) + goto err; + } + if (MLX5_IPSEC_DEV(dev) || MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) { err = init_egress_root_ns(steering); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 87de0e4d9124..e43c6f6d46a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -67,6 +67,7 @@ enum fs_flow_table_type { FS_FT_FDB = 0X4, FS_FT_SNIFFER_RX = 0X5, FS_FT_SNIFFER_TX = 0X6, + FS_FT_RDMA_RX = 0X7, FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX, }; @@ -90,6 +91,7 @@ struct mlx5_flow_steering { struct mlx5_flow_root_namespace **esw_ingress_root_ns; struct mlx5_flow_root_namespace *sniffer_tx_root_ns; struct mlx5_flow_root_namespace *sniffer_rx_root_ns; + struct mlx5_flow_root_namespace *rdma_rx_root_ns; struct mlx5_flow_root_namespace *egress_root_ns; }; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f93a5598b942..28ebb6c93542 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1166,6 +1166,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \ MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap) +#define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap) + +#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \ + MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap) + #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index fd91df3a4e09..e690ba0f965c 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -73,6 +73,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_SNIFFER_RX, MLX5_FLOW_NAMESPACE_SNIFFER_TX, MLX5_FLOW_NAMESPACE_EGRESS, + MLX5_FLOW_NAMESPACE_RDMA_RX, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index eeedf3f53ed3..89e7194b3d97 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -598,7 +598,7 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; - u8 reserved_at_400[0x200]; + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_rdma; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer; -- cgit v1.2.3-71-gd317 From f6f7d6b5bd818cc84eebb55ba6bcba38cfd3b385 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 29 Apr 2019 18:14:14 +0000 Subject: net/mlx5: Add new miss flow table action Flow table supports three types of miss action: 1. Default miss action - go to default miss table according to table. 2. Go to specific table. 3. Switch domain - go to the root table of an alternative steering table domain. New table miss action was added - switch_domain. The next domain for RDMA_RX namespace is the NIC RX domain. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 13 ++++++++++--- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 +++++- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 1 + include/linux/mlx5/mlx5_ifc.h | 10 +++++++++- 4 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 629c5ab1c0d1..013b1ca4a791 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -172,9 +172,14 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, case FS_FT_OP_MOD_NORMAL: if (next_ft) { MLX5_SET(create_flow_table_in, in, - flow_table_context.table_miss_action, 1); + flow_table_context.table_miss_action, + MLX5_FLOW_TABLE_MISS_ACTION_FWD); MLX5_SET(create_flow_table_in, in, flow_table_context.table_miss_id, next_ft->id); + } else { + MLX5_SET(create_flow_table_in, in, + flow_table_context.table_miss_action, + ns->def_miss_action); } break; @@ -246,13 +251,15 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID); if (next_ft) { MLX5_SET(modify_flow_table_in, in, - flow_table_context.table_miss_action, 1); + flow_table_context.table_miss_action, + MLX5_FLOW_TABLE_MISS_ACTION_FWD); MLX5_SET(modify_flow_table_in, in, flow_table_context.table_miss_id, next_ft->id); } else { MLX5_SET(modify_flow_table_in, in, - flow_table_context.table_miss_action, 0); + flow_table_context.table_miss_action, + ns->def_miss_action); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3c2302a2b9d4..fb5b61727ee7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2504,6 +2504,9 @@ static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) if (!steering->rdma_rx_root_ns) return -ENOMEM; + steering->rdma_rx_root_ns->def_miss_action = + MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN; + /* Create single prio */ prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1); if (IS_ERR(prio)) { @@ -2748,7 +2751,8 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } - if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support)) { + if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && + MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) { err = init_rdma_rx_root_ns(steering); if (err) goto err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index e43c6f6d46a7..0c6c5fef4548 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -218,6 +218,7 @@ struct mlx5_flow_root_namespace { struct mutex chain_lock; struct list_head underlay_qpns; const struct mlx5_flow_cmds *cmds; + enum mlx5_flow_table_miss_action def_miss_action; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 89e7194b3d97..7d9264b282d1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -370,7 +370,9 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reformat_l3_tunnel_to_l2[0x1]; u8 reformat_l2_to_l3_tunnel[0x1]; u8 reformat_and_modify_action[0x1]; - u8 reserved_at_15[0xb]; + u8 reserved_at_15[0x2]; + u8 table_miss_action_domain[0x1]; + u8 reserved_at_18[0x8]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; @@ -1284,6 +1286,12 @@ enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101, }; +enum mlx5_flow_table_miss_action { + MLX5_FLOW_TABLE_MISS_ACTION_DEF, + MLX5_FLOW_TABLE_MISS_ACTION_FWD, + MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN, +}; + struct mlx5_ifc_dest_format_struct_bits { u8 destination_type[0x8]; u8 destination_id[0x18]; -- cgit v1.2.3-71-gd317 From 80f09dfc237f181e92968a72d97b7a4202baa453 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 29 Apr 2019 18:14:16 +0000 Subject: net/mlx5: Eswitch, enable RoCE loopback traffic When in switchdev mode, we would like to treat loopback RoCE traffic (on eswitch manager) as RDMA and not as regular Ethernet traffic In order to enable it we add flow steering rule that forward RoCE loopback traffic to the HW RoCE filter (by adding allow rule). In addition we add RoCE address in GID index 0, which will be set in the RoCE loopback packet. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Acked-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 + drivers/net/ethernet/mellanox/mlx5/core/rdma.c | 182 +++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/rdma.h | 20 +++ include/linux/mlx5/driver.h | 7 + 5 files changed, 214 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/rdma.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/rdma.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 1a16f6d73cbc..5f0be9b36a04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o en/tc_tun.o lib/port_tu # # Core extra # -mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o ecpf.o +mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o ecpf.o rdma.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 6c8a17ca236e..9a1598bca4d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -37,6 +37,7 @@ #include #include "mlx5_core.h" #include "eswitch.h" +#include "rdma.h" #include "en.h" #include "fs_core.h" #include "lib/devcom.h" @@ -1713,6 +1714,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports, esw->host_info.num_vfs = vf_nvports; } + mlx5_rdma_enable_roce(esw->dev); + return 0; err_reps: @@ -1751,6 +1754,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw) num_vfs = esw->dev->priv.sriov.num_vfs; } + mlx5_rdma_disable_roce(esw->dev); esw_offloads_devcom_cleanup(esw); esw_offloads_unload_all_reps(esw, num_vfs); esw_offloads_steering_cleanup(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c new file mode 100644 index 000000000000..86f77456f873 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies */ + +#include +#include +#include + +#include "lib/mlx5.h" +#include "eswitch.h" +#include "fs_core.h" +#include "rdma.h" + +static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev) +{ + struct mlx5_core_roce *roce = &dev->priv.roce; + + if (!roce->ft) + return; + + mlx5_del_flow_rules(roce->allow_rule); + mlx5_destroy_flow_group(roce->fg); + mlx5_destroy_flow_table(roce->ft); +} + +static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_core_roce *roce = &dev->priv.roce; + struct mlx5_flow_handle *flow_rule = NULL; + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_namespace *ns = NULL; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_spec *spec; + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + void *match_criteria; + u32 *flow_group_in; + void *misc; + int err; + + if (!(MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && + MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain))) + return -EOPNOTSUPP; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) { + kvfree(flow_group_in); + return -ENOMEM; + } + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX); + if (!ns) { + mlx5_core_err(dev, "Failed to get RDMA RX namespace"); + err = -EOPNOTSUPP; + goto free; + } + + ft_attr.max_fte = 1; + ft = mlx5_create_flow_table(ns, &ft_attr); + if (IS_ERR(ft)) { + mlx5_core_err(dev, "Failed to create RDMA RX flow table"); + err = PTR_ERR(ft); + goto free; + } + + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_MISC_PARAMETERS); + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, + match_criteria); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + misc_parameters.source_port); + + fg = mlx5_create_flow_group(ft, flow_group_in); + if (IS_ERR(fg)) { + err = PTR_ERR(fg); + mlx5_core_err(dev, "Failed to create RDMA RX flow group err(%d)\n", err); + goto destroy_flow_table; + } + + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, + dev->priv.eswitch->manager_vport); + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; + flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + mlx5_core_err(dev, "Failed to add RoCE allow rule, err=%d\n", + err); + goto destroy_flow_group; + } + + kvfree(spec); + kvfree(flow_group_in); + roce->ft = ft; + roce->fg = fg; + roce->allow_rule = flow_rule; + + return 0; + +destroy_flow_table: + mlx5_destroy_flow_table(ft); +destroy_flow_group: + mlx5_destroy_flow_group(fg); +free: + kvfree(spec); + kvfree(flow_group_in); + return err; +} + +static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev) +{ + mlx5_core_roce_gid_set(dev, 0, 0, 0, + NULL, NULL, false, 0, 0); +} + +static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid) +{ + u8 hw_id[ETH_ALEN]; + + mlx5_query_nic_vport_mac_address(dev, 0, hw_id); + gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL); + addrconf_addr_eui48(&gid->raw[8], hw_id); +} + +static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev) +{ + union ib_gid gid; + u8 mac[ETH_ALEN]; + + mlx5_rdma_make_default_gid(dev, &gid); + return mlx5_core_roce_gid_set(dev, 0, + MLX5_ROCE_VERSION_1, + 0, gid.raw, mac, + false, 0, 1); +} + +void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) +{ + mlx5_rdma_disable_roce_steering(dev); + mlx5_rdma_del_roce_addr(dev); + mlx5_nic_vport_disable_roce(dev); +} + +void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_nic_vport_enable_roce(dev); + if (err) { + mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err); + return; + } + + err = mlx5_rdma_add_roce_addr(dev); + if (err) { + mlx5_core_err(dev, "Failed to add RoCE address: %d\n", err); + goto disable_roce; + } + + err = mlx5_rdma_enable_roce_steering(dev); + if (err) { + mlx5_core_err(dev, "Failed to enable RoCE steering: %d\n", err); + goto del_roce_addr; + } + + return; + +del_roce_addr: + mlx5_rdma_del_roce_addr(dev); +disable_roce: + mlx5_nic_vport_disable_roce(dev); + return; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h new file mode 100644 index 000000000000..750cff2a71a4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_RDMA_H__ +#define __MLX5_RDMA_H__ + +#include "mlx5_core.h" + +#ifdef CONFIG_MLX5_ESWITCH + +void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev); +void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev); + +#else /* CONFIG_MLX5_ESWITCH */ + +static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {} +static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {} + +#endif /* CONFIG_MLX5_ESWITCH */ +#endif /* __MLX5_RDMA_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 582a9680b182..7fa95270dd59 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -512,6 +512,12 @@ struct mlx5_rl_table { struct mlx5_rl_entry *rl_entry; }; +struct mlx5_core_roce { + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + struct mlx5_flow_handle *allow_rule; +}; + struct mlx5_priv { struct mlx5_eq_table *eq_table; @@ -565,6 +571,7 @@ struct mlx5_priv { struct mlx5_lag *lag; struct mlx5_devcom *devcom; unsigned long pci_dev_data; + struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; -- cgit v1.2.3-71-gd317 From 75d90e7def8e20b57c1de9e2b672c3bf9249da83 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 29 Apr 2019 18:14:18 +0000 Subject: net/mlx5: Geneve, Add basic Geneve encap/decap flow table capabilities Introduce support for Geneve flow specification and allow the creation of rules that are matching on basic Geneve protocol fields: VNI, OAM bit, protocol type, options length. Reviewed-by: Oz Shlomo Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7d9264b282d1..268ac126b3bb 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -307,7 +307,11 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_gre_protocol[0x1]; u8 outer_gre_key[0x1]; u8 outer_vxlan_vni[0x1]; - u8 reserved_at_1a[0x5]; + u8 outer_geneve_vni[0x1]; + u8 outer_geneve_oam[0x1]; + u8 outer_geneve_protocol_type[0x1]; + u8 outer_geneve_opt_len[0x1]; + u8 reserved_at_1e[0x1]; u8 source_eswitch_port[0x1]; u8 inner_dmac[0x1]; @@ -480,7 +484,9 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 vxlan_vni[0x18]; u8 reserved_at_b8[0x8]; - u8 reserved_at_c0[0x20]; + u8 geneve_vni[0x18]; + u8 reserved_at_d8[0x7]; + u8 geneve_oam[0x1]; u8 reserved_at_e0[0xc]; u8 outer_ipv6_flow_label[0x14]; @@ -488,7 +494,11 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_100[0xc]; u8 inner_ipv6_flow_label[0x14]; - u8 reserved_at_120[0x28]; + u8 reserved_at_120[0xa]; + u8 geneve_opt_len[0x6]; + u8 geneve_protocol_type[0x10]; + + u8 reserved_at_140[0x8]; u8 bth_dst_qp[0x18]; u8 reserved_at_160[0x20]; u8 outer_esp_spi[0x20]; -- cgit v1.2.3-71-gd317 From b169e64a24442e02cafee1586f17fcb713fe65a6 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 29 Apr 2019 18:14:20 +0000 Subject: net/mlx5: Geneve, Add flow table capabilities for Geneve decap with TLV options Introduce specification for Geneve decap flow with encapsulation options and allow creation of rules that are matching on Geneve TLV options. Reviewed-by: Oz Shlomo Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +- include/linux/mlx5/device.h | 4 +- include/linux/mlx5/mlx5_ifc.h | 50 ++++++++++++++++++++--- 3 files changed, 49 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 0c6c5fef4548..a08c3d09a50f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -152,7 +152,7 @@ struct mlx5_ft_underlay_qp { u32 qpn; }; -#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_800 +#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_a00 /* Calculate the fte_match_param length and without the reserved length. * Make sure the reserved field is the last. */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 28ebb6c93542..4ab801040e98 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1001,7 +1001,8 @@ enum { MLX5_MATCH_OUTER_HEADERS = 1 << 0, MLX5_MATCH_MISC_PARAMETERS = 1 << 1, MLX5_MATCH_INNER_HEADERS = 1 << 2, - + MLX5_MATCH_MISC_PARAMETERS_2 = 1 << 3, + MLX5_MATCH_MISC_PARAMETERS_3 = 1 << 4, }; enum { @@ -1045,6 +1046,7 @@ enum mlx5_mpls_supported_fields { }; enum mlx5_flex_parser_protos { + MLX5_FLEX_PROTO_GENEVE = 1 << 3, MLX5_FLEX_PROTO_CW_MPLS_GRE = 1 << 4, MLX5_FLEX_PROTO_CW_MPLS_UDP = 1 << 5, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 268ac126b3bb..6a7fc18a9fe3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -86,6 +86,11 @@ enum { enum { MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), + MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), +}; + +enum { + MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, }; enum { @@ -339,7 +344,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_tcp_flags[0x1]; u8 reserved_at_37[0x9]; - u8 reserved_at_40[0x5]; + u8 geneve_tlv_option_0_data[0x1]; + u8 reserved_at_41[0x4]; u8 outer_first_mpls_over_udp[0x4]; u8 outer_first_mpls_over_gre[0x4]; u8 inner_first_mpls[0x4]; @@ -528,6 +534,12 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 reserved_at_1a0[0x60]; }; +struct mlx5_ifc_fte_match_set_misc3_bits { + u8 reserved_at_0[0x120]; + u8 geneve_tlv_option_0_data[0x20]; + u8 reserved_at_140[0xc0]; +}; + struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; @@ -1247,9 +1259,13 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 num_of_uars_per_page[0x20]; u8 flex_parser_protocols[0x20]; - u8 reserved_at_560[0x20]; - u8 reserved_at_580[0x3c]; + u8 max_geneve_tlv_options[0x8]; + u8 reserved_at_568[0x3]; + u8 max_geneve_tlv_option_data_len[0x5]; + u8 reserved_at_570[0x10]; + + u8 reserved_at_580[0x1c]; u8 mini_cqe_resp_stride_index[0x1]; u8 cqe_128_always[0x1]; u8 cqe_compression_128[0x1]; @@ -1283,7 +1299,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 uctx_cap[0x20]; - u8 reserved_at_6c0[0x140]; + u8 reserved_at_6c0[0x4]; + u8 flex_parser_id_geneve_tlv_option_0[0x4]; + u8 reserved_at_6c8[0x138]; }; enum mlx5_flow_destination_type { @@ -1341,7 +1359,9 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_misc2_bits misc_parameters_2; - u8 reserved_at_800[0x800]; + struct mlx5_ifc_fte_match_set_misc3_bits misc_parameters_3; + + u8 reserved_at_a00[0x600]; }; enum { @@ -4850,6 +4870,7 @@ enum { MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3, + MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4, }; struct mlx5_ifc_query_flow_group_out_bits { @@ -9545,6 +9566,20 @@ struct mlx5_ifc_sw_icm_bits { u8 sw_icm_start_addr[0x40]; u8 reserved_at_c0[0x140]; +}; + +struct mlx5_ifc_geneve_tlv_option_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x18]; + u8 geneve_option_fte_index[0x8]; + + u8 option_class[0x10]; + u8 option_type[0x8]; + u8 reserved_at_78[0x3]; + u8 option_data_length[0x5]; + + u8 reserved_at_80[0x180]; }; struct mlx5_ifc_create_umem_in_bits { @@ -9589,6 +9624,11 @@ struct mlx5_ifc_create_sw_icm_in_bits { struct mlx5_ifc_sw_icm_bits sw_icm; }; +struct mlx5_ifc_create_geneve_tlv_option_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_geneve_tlv_option_bits geneve_tlv_opt; +}; + struct mlx5_ifc_mtrc_string_db_param_bits { u8 string_db_base_address[0x20]; -- cgit v1.2.3-71-gd317 From 8425c41d1ef762cc15d9501d7117f009a79f3fe9 Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Tue, 30 Apr 2019 09:17:49 +0200 Subject: net: ll_temac: Extend support to non-device-tree platforms Support initialization with platdata, so the driver can be used on non-device-tree platforms. For currently supported device-tree platforms, the driver should behave as before. Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac.h | 3 + drivers/net/ethernet/xilinx/ll_temac_main.c | 187 +++++++++++++++++--------- drivers/net/ethernet/xilinx/ll_temac_mdio.c | 23 +++- include/linux/platform_data/xilinx-ll-temac.h | 19 +++ 4 files changed, 166 insertions(+), 66 deletions(-) create mode 100644 include/linux/platform_data/xilinx-ll-temac.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h index 45575788ed54..e338b4fa3c60 100644 --- a/drivers/net/ethernet/xilinx/ll_temac.h +++ b/drivers/net/ethernet/xilinx/ll_temac.h @@ -334,6 +334,9 @@ struct temac_local { /* Connection to PHY device */ struct device_node *phy_node; + /* For non-device-tree devices */ + char phy_name[MII_BUS_ID_SIZE + 3]; + phy_interface_t phy_interface; /* MDIO bus data */ struct mii_bus *mii_bus; /* MII bus reference */ diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index c4e85a96df75..fddd1b3ac194 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +52,7 @@ #include #include #include +#include #include "ll_temac.h" @@ -187,7 +189,7 @@ static int temac_dcr_setup(struct temac_local *lp, struct platform_device *op, /* * temac_dcr_setup - This is a stub for when DCR is not supported, - * such as with MicroBlaze + * such as with MicroBlaze and x86 */ static int temac_dcr_setup(struct temac_local *lp, struct platform_device *op, struct device_node *np) @@ -857,7 +859,14 @@ static int temac_open(struct net_device *ndev) dev_err(lp->dev, "of_phy_connect() failed\n"); return -ENODEV; } - + phy_start(phydev); + } else if (strlen(lp->phy_name) > 0) { + phydev = phy_connect(lp->ndev, lp->phy_name, temac_adjust_link, + lp->phy_interface); + if (!phydev) { + dev_err(lp->dev, "phy_connect() failed\n"); + return -ENODEV; + } phy_start(phydev); } @@ -977,11 +986,13 @@ static const struct ethtool_ops temac_ethtool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, }; -static int temac_of_probe(struct platform_device *op) +static int temac_probe(struct platform_device *pdev) { - struct device_node *np; + struct ll_temac_platform_data *pdata = dev_get_platdata(&pdev->dev); + struct device_node *temac_np = dev_of_node(&pdev->dev), *dma_np; struct temac_local *lp; struct net_device *ndev; + struct resource *res; const void *addr; __be32 *p; int rc = 0; @@ -991,8 +1002,8 @@ static int temac_of_probe(struct platform_device *op) if (!ndev) return -ENOMEM; - platform_set_drvdata(op, ndev); - SET_NETDEV_DEV(ndev, &op->dev); + platform_set_drvdata(pdev, ndev); + SET_NETDEV_DEV(ndev, &pdev->dev); ndev->flags &= ~IFF_MULTICAST; /* clear multicast */ ndev->features = NETIF_F_SG; ndev->netdev_ops = &temac_netdev_ops; @@ -1014,79 +1025,129 @@ static int temac_of_probe(struct platform_device *op) /* setup temac private info structure */ lp = netdev_priv(ndev); lp->ndev = ndev; - lp->dev = &op->dev; + lp->dev = &pdev->dev; lp->options = XTE_OPTION_DEFAULTS; spin_lock_init(&lp->rx_lock); mutex_init(&lp->indirect_mutex); /* map device registers */ - lp->regs = devm_of_iomap(&op->dev, op->dev.of_node, 0, NULL); - if (!lp->regs) { - dev_err(&op->dev, "could not map temac regs.\n"); - return -ENOMEM; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + lp->regs = devm_ioremap_nocache(&pdev->dev, res->start, + resource_size(res)); + if (IS_ERR(lp->regs)) { + dev_err(&pdev->dev, "could not map TEMAC registers\n"); + return PTR_ERR(lp->regs); } /* Setup checksum offload, but default to off if not specified */ lp->temac_features = 0; - p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,txcsum", NULL); - if (p && be32_to_cpu(*p)) { - lp->temac_features |= TEMAC_FEATURE_TX_CSUM; + if (temac_np) { + p = (__be32 *)of_get_property(temac_np, "xlnx,txcsum", NULL); + if (p && be32_to_cpu(*p)) + lp->temac_features |= TEMAC_FEATURE_TX_CSUM; + p = (__be32 *)of_get_property(temac_np, "xlnx,rxcsum", NULL); + if (p && be32_to_cpu(*p)) + lp->temac_features |= TEMAC_FEATURE_RX_CSUM; + } else if (pdata) { + if (pdata->txcsum) + lp->temac_features |= TEMAC_FEATURE_TX_CSUM; + if (pdata->rxcsum) + lp->temac_features |= TEMAC_FEATURE_RX_CSUM; + } + if (lp->temac_features & TEMAC_FEATURE_TX_CSUM) /* Can checksum TCP/UDP over IPv4. */ ndev->features |= NETIF_F_IP_CSUM; - } - p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,rxcsum", NULL); - if (p && be32_to_cpu(*p)) - lp->temac_features |= TEMAC_FEATURE_RX_CSUM; - - /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ - np = of_parse_phandle(op->dev.of_node, "llink-connected", 0); - if (!np) { - dev_err(&op->dev, "could not find DMA node\n"); - return -ENODEV; - } - /* Setup the DMA register accesses, could be DCR or memory mapped */ - if (temac_dcr_setup(lp, op, np)) { + /* Setup LocalLink DMA */ + if (temac_np) { + /* Find the DMA node, map the DMA registers, and + * decode the DMA IRQs. + */ + dma_np = of_parse_phandle(temac_np, "llink-connected", 0); + if (!dma_np) { + dev_err(&pdev->dev, "could not find DMA node\n"); + return -ENODEV; + } - /* no DCR in the device tree, try non-DCR */ - lp->sdma_regs = devm_of_iomap(&op->dev, np, 0, NULL); - if (lp->sdma_regs) { + /* Setup the DMA register accesses, could be DCR or + * memory mapped. + */ + if (temac_dcr_setup(lp, pdev, dma_np)) { + /* no DCR in the device tree, try non-DCR */ + lp->sdma_regs = devm_of_iomap(&pdev->dev, dma_np, 0, + NULL); + if (IS_ERR(lp->sdma_regs)) { + dev_err(&pdev->dev, + "unable to map DMA registers\n"); + of_node_put(dma_np); + return PTR_ERR(lp->sdma_regs); + } lp->dma_in = temac_dma_in32; lp->dma_out = temac_dma_out32; - dev_dbg(&op->dev, "MEM base: %p\n", lp->sdma_regs); - } else { - dev_err(&op->dev, "unable to map DMA registers\n"); - of_node_put(np); - return -ENOMEM; + dev_dbg(&pdev->dev, "MEM base: %p\n", lp->sdma_regs); } - } - - lp->rx_irq = irq_of_parse_and_map(np, 0); - lp->tx_irq = irq_of_parse_and_map(np, 1); - of_node_put(np); /* Finished with the DMA node; drop the reference */ + /* Get DMA RX and TX interrupts */ + lp->rx_irq = irq_of_parse_and_map(dma_np, 0); + lp->tx_irq = irq_of_parse_and_map(dma_np, 1); + + /* Finished with the DMA node; drop the reference */ + of_node_put(dma_np); + } else if (pdata) { + /* 2nd memory resource specifies DMA registers */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + lp->sdma_regs = devm_ioremap_nocache(&pdev->dev, res->start, + resource_size(res)); + if (IS_ERR(lp->sdma_regs)) { + dev_err(&pdev->dev, + "could not map DMA registers\n"); + return PTR_ERR(lp->sdma_regs); + } + lp->dma_in = temac_dma_in32; + lp->dma_out = temac_dma_out32; - if (!lp->rx_irq || !lp->tx_irq) { - dev_err(&op->dev, "could not determine irqs\n"); - return -ENOMEM; + /* Get DMA RX and TX interrupts */ + lp->rx_irq = platform_get_irq(pdev, 0); + lp->tx_irq = platform_get_irq(pdev, 1); } + /* Error handle returned DMA RX and TX interrupts */ + if (lp->rx_irq < 0) { + if (lp->rx_irq != -EPROBE_DEFER) + dev_err(&pdev->dev, "could not get DMA RX irq\n"); + return lp->rx_irq; + } + if (lp->tx_irq < 0) { + if (lp->tx_irq != -EPROBE_DEFER) + dev_err(&pdev->dev, "could not get DMA TX irq\n"); + return lp->tx_irq; + } - /* Retrieve the MAC address */ - addr = of_get_mac_address(op->dev.of_node); - if (!addr) { - dev_err(&op->dev, "could not find MAC address\n"); - return -ENODEV; + if (temac_np) { + /* Retrieve the MAC address */ + addr = of_get_mac_address(temac_np); + if (!addr) { + dev_err(&pdev->dev, "could not find MAC address\n"); + return -ENODEV; + } + temac_init_mac_address(ndev, addr); + } else if (pdata) { + temac_init_mac_address(ndev, pdata->mac_addr); } - temac_init_mac_address(ndev, addr); rc = temac_mdio_setup(lp, pdev); if (rc) - dev_warn(&op->dev, "error registering MDIO bus\n"); - - lp->phy_node = of_parse_phandle(op->dev.of_node, "phy-handle", 0); - if (lp->phy_node) - dev_dbg(lp->dev, "using PHY node %pOF (%p)\n", np, np); + dev_warn(&pdev->dev, "error registering MDIO bus\n"); + + if (temac_np) { + lp->phy_node = of_parse_phandle(temac_np, "phy-handle", 0); + if (lp->phy_node) + dev_dbg(lp->dev, "using PHY node %pOF\n", temac_np); + } else if (pdata) { + snprintf(lp->phy_name, sizeof(lp->phy_name), + PHY_ID_FMT, lp->mii_bus->id, pdata->phy_addr); + lp->phy_interface = pdata->phy_interface; + } /* Add the device attributes */ rc = sysfs_create_group(&lp->dev->kobj, &temac_attr_group); @@ -1106,19 +1167,21 @@ static int temac_of_probe(struct platform_device *op) err_register_ndev: sysfs_remove_group(&lp->dev->kobj, &temac_attr_group); err_sysfs_create: - of_node_put(lp->phy_node); + if (lp->phy_node) + of_node_put(lp->phy_node); temac_mdio_teardown(lp); return rc; } -static int temac_of_remove(struct platform_device *op) +static int temac_remove(struct platform_device *pdev) { - struct net_device *ndev = platform_get_drvdata(op); + struct net_device *ndev = platform_get_drvdata(pdev); struct temac_local *lp = netdev_priv(ndev); unregister_netdev(ndev); sysfs_remove_group(&lp->dev->kobj, &temac_attr_group); - of_node_put(lp->phy_node); + if (lp->phy_node) + of_node_put(lp->phy_node); temac_mdio_teardown(lp); return 0; } @@ -1132,16 +1195,16 @@ static const struct of_device_id temac_of_match[] = { }; MODULE_DEVICE_TABLE(of, temac_of_match); -static struct platform_driver temac_of_driver = { - .probe = temac_of_probe, - .remove = temac_of_remove, +static struct platform_driver temac_driver = { + .probe = temac_probe, + .remove = temac_remove, .driver = { .name = "xilinx_temac", .of_match_table = temac_of_match, }, }; -module_platform_driver(temac_of_driver); +module_platform_driver(temac_driver); MODULE_DESCRIPTION("Xilinx LL_TEMAC Ethernet driver"); MODULE_AUTHOR("Yoshio Kashiwagi"); diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c index a0b365e43ebf..c5307e5b8e0a 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c +++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "ll_temac.h" @@ -59,6 +60,7 @@ static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val) int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev) { + struct ll_temac_platform_data *pdata = dev_get_platdata(&pdev->dev); struct device_node *np = dev_of_node(&pdev->dev); struct mii_bus *bus; u32 bus_hz; @@ -66,9 +68,16 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev) int rc; struct resource res; + /* Get MDIO bus frequency (if specified) */ + bus_hz = 0; + if (np) + of_property_read_u32(np, "clock-frequency", &bus_hz); + else if (pdata) + bus_hz = pdata->mdio_clk_freq; + /* Calculate a reasonable divisor for the clock rate */ clk_div = 0x3f; /* worst-case default setting */ - if (of_property_read_u32(np, "clock-frequency", &bus_hz) == 0) { + if (bus_hz != 0) { clk_div = bus_hz / (2500 * 1000 * 2) - 1; if (clk_div < 1) clk_div = 1; @@ -86,9 +95,15 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev) if (!bus) return -ENOMEM; - of_address_to_resource(np, 0, &res); - snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx", - (unsigned long long)res.start); + if (np) { + of_address_to_resource(np, 0, &res); + snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx", + (unsigned long long)res.start); + } else if (pdata && pdata->mdio_bus_id >= 0) { + snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx", + pdata->mdio_bus_id); + } + bus->priv = lp; bus->name = "Xilinx TEMAC MDIO"; bus->read = temac_mdio_read; diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h new file mode 100644 index 000000000000..82e2f80648b0 --- /dev/null +++ b/include/linux/platform_data/xilinx-ll-temac.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_XILINX_LL_TEMAC_H +#define __LINUX_XILINX_LL_TEMAC_H + +#include +#include + +struct ll_temac_platform_data { + bool txcsum; /* Enable/disable TX checksum */ + bool rxcsum; /* Enable/disable RX checksum */ + u8 mac_addr[ETH_ALEN]; /* MAC address (6 bytes) */ + /* Clock frequency for input to MDIO clock generator */ + u32 mdio_clk_freq; + unsigned long long mdio_bus_id; /* Unique id for MDIO bus */ + int phy_addr; /* Address of the PHY to connect to */ + phy_interface_t phy_interface; /* PHY interface mode */ +}; + +#endif /* __LINUX_XILINX_LL_TEMAC_H */ -- cgit v1.2.3-71-gd317 From a3246dc41aa3c9d799478ccc8dac5d19c509a923 Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Tue, 30 Apr 2019 09:17:51 +0200 Subject: net: ll_temac: Add support for non-native register endianness Replace the powerpc specific MMIO register access functions with the generic big-endian mmio access functions, and add support for little-endian access depending on configuration. Big-endian access is maintained as the default, but little-endian can be configured in device-tree binding or in platform data. The temac_ior()/temac_iow() functions are replaced with macro wrappers to avoid modifying existing code more than necessary. Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac.h | 12 ++-- drivers/net/ethernet/xilinx/ll_temac_main.c | 87 +++++++++++++++++++++------ include/linux/platform_data/xilinx-ll-temac.h | 2 + 3 files changed, 79 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h index e338b4fa3c60..23d8dd5330f8 100644 --- a/drivers/net/ethernet/xilinx/ll_temac.h +++ b/drivers/net/ethernet/xilinx/ll_temac.h @@ -347,8 +347,10 @@ struct temac_local { #ifdef CONFIG_PPC_DCR dcr_host_t sdma_dcrs; #endif - u32 (*dma_in)(struct temac_local *, int); - void (*dma_out)(struct temac_local *, int, u32); + u32 (*temac_ior)(struct temac_local *lp, int offset); + void (*temac_iow)(struct temac_local *lp, int offset, u32 value); + u32 (*dma_in)(struct temac_local *lp, int reg); + void (*dma_out)(struct temac_local *lp, int reg, u32 value); int tx_irq; int rx_irq; @@ -372,9 +374,11 @@ struct temac_local { int rx_bd_ci; }; +/* Wrappers for temac_ior()/temac_iow() function pointers above */ +#define temac_ior(lp, o) ((lp)->temac_ior(lp, o)) +#define temac_iow(lp, o, v) ((lp)->temac_iow(lp, o, v)) + /* xilinx_temac.c */ -u32 temac_ior(struct temac_local *lp, int offset); -void temac_iow(struct temac_local *lp, int offset, u32 value); int temac_indirect_busywait(struct temac_local *lp); u32 temac_indirect_in32(struct temac_local *lp, int reg); void temac_indirect_out32(struct temac_local *lp, int reg, u32 value); diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index bcafb8925f75..58c67138ed2b 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -63,14 +63,24 @@ * Low level register access functions */ -u32 temac_ior(struct temac_local *lp, int offset) +u32 _temac_ior_be(struct temac_local *lp, int offset) { - return in_be32(lp->regs + offset); + return ioread32be(lp->regs + offset); } -void temac_iow(struct temac_local *lp, int offset, u32 value) +void _temac_iow_be(struct temac_local *lp, int offset, u32 value) { - out_be32(lp->regs + offset, value); + return iowrite32be(value, lp->regs + offset); +} + +u32 _temac_ior_le(struct temac_local *lp, int offset) +{ + return ioread32(lp->regs + offset); +} + +void _temac_iow_le(struct temac_local *lp, int offset, u32 value) +{ + return iowrite32(value, lp->regs + offset); } int temac_indirect_busywait(struct temac_local *lp) @@ -121,23 +131,35 @@ void temac_indirect_out32(struct temac_local *lp, int reg, u32 value) } /** - * temac_dma_in32 - Memory mapped DMA read, this function expects a - * register input that is based on DCR word addresses which - * are then converted to memory mapped byte addresses + * temac_dma_in32_* - Memory mapped DMA read, these function expects a + * register input that is based on DCR word addresses which are then + * converted to memory mapped byte addresses. To be assigned to + * lp->dma_in32. */ -static u32 temac_dma_in32(struct temac_local *lp, int reg) +static u32 temac_dma_in32_be(struct temac_local *lp, int reg) { - return in_be32(lp->sdma_regs + (reg << 2)); + return ioread32be(lp->sdma_regs + (reg << 2)); +} + +static u32 temac_dma_in32_le(struct temac_local *lp, int reg) +{ + return ioread32(lp->sdma_regs + (reg << 2)); } /** - * temac_dma_out32 - Memory mapped DMA read, this function expects a - * register input that is based on DCR word addresses which - * are then converted to memory mapped byte addresses + * temac_dma_out32_* - Memory mapped DMA read, these function expects + * a register input that is based on DCR word addresses which are then + * converted to memory mapped byte addresses. To be assigned to + * lp->dma_out32. */ -static void temac_dma_out32(struct temac_local *lp, int reg, u32 value) +static void temac_dma_out32_be(struct temac_local *lp, int reg, u32 value) +{ + iowrite32be(value, lp->sdma_regs + (reg << 2)); +} + +static void temac_dma_out32_le(struct temac_local *lp, int reg, u32 value) { - out_be32(lp->sdma_regs + (reg << 2), value); + iowrite32(value, lp->sdma_regs + (reg << 2)); } /* DMA register access functions can be DCR based or memory mapped. @@ -1024,6 +1046,7 @@ static int temac_probe(struct platform_device *pdev) struct resource *res; const void *addr; __be32 *p; + bool little_endian; int rc = 0; /* Init network device structure */ @@ -1068,6 +1091,24 @@ static int temac_probe(struct platform_device *pdev) return PTR_ERR(lp->regs); } + /* Select register access functions with the specified + * endianness mode. Default for OF devices is big-endian. + */ + little_endian = false; + if (temac_np) { + if (of_get_property(temac_np, "little-endian", NULL)) + little_endian = true; + } else if (pdata) { + little_endian = pdata->reg_little_endian; + } + if (little_endian) { + lp->temac_ior = _temac_ior_le; + lp->temac_iow = _temac_iow_le; + } else { + lp->temac_ior = _temac_ior_be; + lp->temac_iow = _temac_iow_be; + } + /* Setup checksum offload, but default to off if not specified */ lp->temac_features = 0; if (temac_np) { @@ -1111,8 +1152,13 @@ static int temac_probe(struct platform_device *pdev) of_node_put(dma_np); return PTR_ERR(lp->sdma_regs); } - lp->dma_in = temac_dma_in32; - lp->dma_out = temac_dma_out32; + if (of_get_property(dma_np, "little-endian", NULL)) { + lp->dma_in = temac_dma_in32_le; + lp->dma_out = temac_dma_out32_le; + } else { + lp->dma_in = temac_dma_in32_be; + lp->dma_out = temac_dma_out32_be; + } dev_dbg(&pdev->dev, "MEM base: %p\n", lp->sdma_regs); } @@ -1132,8 +1178,13 @@ static int temac_probe(struct platform_device *pdev) "could not map DMA registers\n"); return PTR_ERR(lp->sdma_regs); } - lp->dma_in = temac_dma_in32; - lp->dma_out = temac_dma_out32; + if (pdata->dma_little_endian) { + lp->dma_in = temac_dma_in32_le; + lp->dma_out = temac_dma_out32_le; + } else { + lp->dma_in = temac_dma_in32_be; + lp->dma_out = temac_dma_out32_be; + } /* Get DMA RX and TX interrupts */ lp->rx_irq = platform_get_irq(pdev, 0); diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h index 82e2f80648b0..af87927abab3 100644 --- a/include/linux/platform_data/xilinx-ll-temac.h +++ b/include/linux/platform_data/xilinx-ll-temac.h @@ -14,6 +14,8 @@ struct ll_temac_platform_data { unsigned long long mdio_bus_id; /* Unique id for MDIO bus */ int phy_addr; /* Address of the PHY to connect to */ phy_interface_t phy_interface; /* PHY interface mode */ + bool reg_little_endian; /* Little endian TEMAC register access */ + bool dma_little_endian; /* Little endian DMA register access */ }; #endif /* __LINUX_XILINX_LL_TEMAC_H */ -- cgit v1.2.3-71-gd317 From f14f5c11f051ca4a41e65017d94408e5e702ba9d Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Tue, 30 Apr 2019 09:17:54 +0200 Subject: net: ll_temac: Support indirect_mutex share within TEMAC IP Indirect register access goes through a DCR bus bridge, which allows only one outstanding transaction. And to make matters worse, each TEMAC IP block contains two Ethernet interfaces, and although they seem to have separate registers for indirect access, they actually share the registers. Or to be more specific, MSW, LSW and CTL registers are physically shared between Ethernet interfaces in same TEMAC IP, with RDY register being (almost) specificic to the Ethernet interface. The 0x10000 bit in RDY reflects combined bus ready state though. So we need to take care to synchronize not only within a single device, but also between devices in same TEMAC IP. This commit allows to do that with legacy platform devices. For OF devices, the xlnx,compound parent of the temac node should be used to find siblings, and setup a shared indirect_mutex between them. I will leave this work to somebody else, as I don't have hardware to test that. No regression is introduced by that, as before this commit using two Ethernet interfaces in same TEMAC block is simply broken. Signed-off-by: Esben Haabendal Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac.h | 5 +++- drivers/net/ethernet/xilinx/ll_temac_main.c | 36 +++++++++++++++++++-------- drivers/net/ethernet/xilinx/ll_temac_mdio.c | 16 ++++++------ include/linux/platform_data/xilinx-ll-temac.h | 6 +++++ 4 files changed, 43 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h index 23d8dd5330f8..990f9ed151b2 100644 --- a/drivers/net/ethernet/xilinx/ll_temac.h +++ b/drivers/net/ethernet/xilinx/ll_temac.h @@ -358,7 +358,10 @@ struct temac_local { struct sk_buff **rx_skb; spinlock_t rx_lock; - struct mutex indirect_mutex; + /* For synchronization of indirect register access. Must be + * shared mutex between interfaces in same TEMAC block. + */ + struct mutex *indirect_mutex; u32 options; /* Current options word */ int last_link; unsigned int temac_features; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 179a9984bc64..d3899e7efd45 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -344,7 +344,7 @@ static void temac_do_set_mac_address(struct net_device *ndev) struct temac_local *lp = netdev_priv(ndev); /* set up unicast MAC address filter set its mac address */ - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); temac_indirect_out32(lp, XTE_UAW0_OFFSET, (ndev->dev_addr[0]) | (ndev->dev_addr[1] << 8) | @@ -355,7 +355,7 @@ static void temac_do_set_mac_address(struct net_device *ndev) temac_indirect_out32(lp, XTE_UAW1_OFFSET, (ndev->dev_addr[4] & 0x000000ff) | (ndev->dev_addr[5] << 8)); - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); } static int temac_init_mac_address(struct net_device *ndev, const void *address) @@ -384,7 +384,7 @@ static void temac_set_multicast_list(struct net_device *ndev) u32 multi_addr_msw, multi_addr_lsw, val; int i; - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) || netdev_mc_count(ndev) > MULTICAST_CAM_TABLE_NUM) { /* @@ -423,7 +423,7 @@ static void temac_set_multicast_list(struct net_device *ndev) temac_indirect_out32(lp, XTE_MAW1_OFFSET, 0); dev_info(&ndev->dev, "Promiscuous mode disabled.\n"); } - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); } static struct temac_option { @@ -515,7 +515,7 @@ static u32 temac_setoptions(struct net_device *ndev, u32 options) struct temac_option *tp = &temac_options[0]; int reg; - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); while (tp->opt) { reg = temac_indirect_in32(lp, tp->reg) & ~tp->m_or; if (options & tp->opt) @@ -524,7 +524,7 @@ static u32 temac_setoptions(struct net_device *ndev, u32 options) tp++; } lp->options |= options; - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); return 0; } @@ -543,7 +543,7 @@ static void temac_device_reset(struct net_device *ndev) dev_dbg(&ndev->dev, "%s()\n", __func__); - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); /* Reset the receiver and wait for it to finish reset */ temac_indirect_out32(lp, XTE_RXC1_OFFSET, XTE_RXC1_RXRST_MASK); timeout = 1000; @@ -595,7 +595,7 @@ static void temac_device_reset(struct net_device *ndev) temac_indirect_out32(lp, XTE_TXC_OFFSET, 0); temac_indirect_out32(lp, XTE_FCC_OFFSET, XTE_FCC_RXFLO_MASK); - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); /* Sync default options with HW * but leave receiver and transmitter disabled. */ @@ -623,7 +623,7 @@ static void temac_adjust_link(struct net_device *ndev) /* hash together the state values to decide if something has changed */ link_state = phy->speed | (phy->duplex << 1) | phy->link; - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); if (lp->last_link != link_state) { mii_speed = temac_indirect_in32(lp, XTE_EMCFG_OFFSET); mii_speed &= ~XTE_EMCFG_LINKSPD_MASK; @@ -639,7 +639,7 @@ static void temac_adjust_link(struct net_device *ndev) lp->last_link = link_state; phy_print_status(phy); } - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); } #ifdef CONFIG_64BIT @@ -1091,7 +1091,21 @@ static int temac_probe(struct platform_device *pdev) lp->dev = &pdev->dev; lp->options = XTE_OPTION_DEFAULTS; spin_lock_init(&lp->rx_lock); - mutex_init(&lp->indirect_mutex); + + /* Setup mutex for synchronization of indirect register access */ + if (pdata) { + if (!pdata->indirect_mutex) { + dev_err(&pdev->dev, + "indirect_mutex missing in platform_data\n"); + return -EINVAL; + } + lp->indirect_mutex = pdata->indirect_mutex; + } else { + lp->indirect_mutex = devm_kmalloc(&pdev->dev, + sizeof(*lp->indirect_mutex), + GFP_KERNEL); + mutex_init(lp->indirect_mutex); + } /* map device registers */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c index c5307e5b8e0a..c2a11703bc6d 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c +++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c @@ -29,10 +29,10 @@ static int temac_mdio_read(struct mii_bus *bus, int phy_id, int reg) /* Write the PHY address to the MIIM Access Initiator register. * When the transfer completes, the PHY register value will appear * in the LSW0 register */ - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); temac_iow(lp, XTE_LSW0_OFFSET, (phy_id << 5) | reg); rc = temac_indirect_in32(lp, XTE_MIIMAI_OFFSET); - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); dev_dbg(lp->dev, "temac_mdio_read(phy_id=%i, reg=%x) == %x\n", phy_id, reg, rc); @@ -50,10 +50,10 @@ static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val) /* First write the desired value into the write data register * and then write the address into the access initiator register */ - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); temac_indirect_out32(lp, XTE_MGTDR_OFFSET, val); temac_indirect_out32(lp, XTE_MIIMAI_OFFSET, (phy_id << 5) | reg); - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); return 0; } @@ -87,9 +87,9 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev) /* Enable the MDIO bus by asserting the enable bit and writing * in the clock config */ - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); temac_indirect_out32(lp, XTE_MC_OFFSET, 1 << 6 | clk_div); - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); bus = devm_mdiobus_alloc(&pdev->dev); if (!bus) @@ -116,10 +116,10 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev) if (rc) return rc; - mutex_lock(&lp->indirect_mutex); + mutex_lock(lp->indirect_mutex); dev_dbg(lp->dev, "MDIO bus registered; MC:%x\n", temac_indirect_in32(lp, XTE_MC_OFFSET)); - mutex_unlock(&lp->indirect_mutex); + mutex_unlock(lp->indirect_mutex); return 0; } diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h index af87927abab3..b0b8238a9b7d 100644 --- a/include/linux/platform_data/xilinx-ll-temac.h +++ b/include/linux/platform_data/xilinx-ll-temac.h @@ -16,6 +16,12 @@ struct ll_temac_platform_data { phy_interface_t phy_interface; /* PHY interface mode */ bool reg_little_endian; /* Little endian TEMAC register access */ bool dma_little_endian; /* Little endian DMA register access */ + /* Pre-initialized mutex to use for synchronizing indirect + * register access. When using both interfaces of a single + * TEMAC IP block, the same mutex should be passed here, as + * they share the same DCR bus bridge. + */ + struct mutex *indirect_mutex; }; #endif /* __LINUX_XILINX_LL_TEMAC_H */ -- cgit v1.2.3-71-gd317 From 7e97a194aca03c6ff86f84e46e196f5c9ed5c32c Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Tue, 30 Apr 2019 09:17:58 +0200 Subject: net: ll_temac: Allow configuration of IRQ coalescing This allows custom setup of IRQ coalescing for platforms using legacy platform_device. The irq timeout and count parameters can be used for tuning cpu load vs. latency. I have maintained the 0x00000400 bit in TX_CHNL_CTRL. It is specified as unused in the documentation I have available. It does not make any difference in the hardware I have available, so it is left in to not risk breaking other platforms where it might be used. Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac.h | 4 +++ drivers/net/ethernet/xilinx/ll_temac_main.c | 40 +++++++++++++++++++-------- include/linux/platform_data/xilinx-ll-temac.h | 5 ++++ 3 files changed, 37 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h index 990f9ed151b2..1aeda084b8f1 100644 --- a/drivers/net/ethernet/xilinx/ll_temac.h +++ b/drivers/net/ethernet/xilinx/ll_temac.h @@ -375,6 +375,10 @@ struct temac_local { int tx_bd_next; int tx_bd_tail; int rx_bd_ci; + + /* DMA channel control setup */ + u32 tx_chnl_ctrl; + u32 rx_chnl_ctrl; }; /* Wrappers for temac_ior()/temac_iow() function pointers above */ diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index fec8e4c22944..bccef30bf64e 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -304,18 +304,15 @@ static int temac_dma_bd_init(struct net_device *ndev) lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); } - lp->dma_out(lp, TX_CHNL_CTRL, 0x10220400 | - CHNL_CTRL_IRQ_EN | - CHNL_CTRL_IRQ_DLY_EN | - CHNL_CTRL_IRQ_COAL_EN); - /* 0x10220483 */ - /* 0x00100483 */ - lp->dma_out(lp, RX_CHNL_CTRL, 0xff070000 | - CHNL_CTRL_IRQ_EN | - CHNL_CTRL_IRQ_DLY_EN | - CHNL_CTRL_IRQ_COAL_EN | - CHNL_CTRL_IRQ_IOE); - /* 0xff010283 */ + /* Configure DMA channel (irq setup) */ + lp->dma_out(lp, TX_CHNL_CTRL, lp->tx_chnl_ctrl | + 0x00000400 | // Use 1 Bit Wide Counters. Currently Not Used! + CHNL_CTRL_IRQ_EN | CHNL_CTRL_IRQ_ERR_EN | + CHNL_CTRL_IRQ_DLY_EN | CHNL_CTRL_IRQ_COAL_EN); + lp->dma_out(lp, RX_CHNL_CTRL, lp->rx_chnl_ctrl | + CHNL_CTRL_IRQ_IOE | + CHNL_CTRL_IRQ_EN | CHNL_CTRL_IRQ_ERR_EN | + CHNL_CTRL_IRQ_DLY_EN | CHNL_CTRL_IRQ_COAL_EN); lp->dma_out(lp, RX_CURDESC_PTR, lp->rx_bd_p); lp->dma_out(lp, RX_TAILDESC_PTR, @@ -1191,6 +1188,13 @@ static int temac_probe(struct platform_device *pdev) lp->rx_irq = irq_of_parse_and_map(dma_np, 0); lp->tx_irq = irq_of_parse_and_map(dma_np, 1); + /* Use defaults for IRQ delay/coalescing setup. These + * are configuration values, so does not belong in + * device-tree. + */ + lp->tx_chnl_ctrl = 0x10220000; + lp->rx_chnl_ctrl = 0xff070000; + /* Finished with the DMA node; drop the reference */ of_node_put(dma_np); } else if (pdata) { @@ -1214,6 +1218,18 @@ static int temac_probe(struct platform_device *pdev) /* Get DMA RX and TX interrupts */ lp->rx_irq = platform_get_irq(pdev, 0); lp->tx_irq = platform_get_irq(pdev, 1); + + /* IRQ delay/coalescing setup */ + if (pdata->tx_irq_timeout || pdata->tx_irq_count) + lp->tx_chnl_ctrl = (pdata->tx_irq_timeout << 24) | + (pdata->tx_irq_count << 16); + else + lp->tx_chnl_ctrl = 0x10220000; + if (pdata->rx_irq_timeout || pdata->rx_irq_count) + lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) | + (pdata->rx_irq_count << 16); + else + lp->rx_chnl_ctrl = 0xff070000; } /* Error handle returned DMA RX and TX interrupts */ diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h index b0b8238a9b7d..368530f98176 100644 --- a/include/linux/platform_data/xilinx-ll-temac.h +++ b/include/linux/platform_data/xilinx-ll-temac.h @@ -22,6 +22,11 @@ struct ll_temac_platform_data { * they share the same DCR bus bridge. */ struct mutex *indirect_mutex; + /* DMA channel control setup */ + u8 tx_irq_timeout; /* TX Interrupt Delay Time-out */ + u8 tx_irq_count; /* TX Interrupt Coalescing Threshold Count */ + u8 rx_irq_timeout; /* RX Interrupt Delay Time-out */ + u8 rx_irq_count; /* RX Interrupt Coalescing Threshold Count */ }; #endif /* __LINUX_XILINX_LL_TEMAC_H */ -- cgit v1.2.3-71-gd317 From 91a40a48d52d13fbde3239d5839335cabd9a4eae Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 1 May 2019 03:21:05 +0000 Subject: net/mlx5: Fix broken hca cap offset The cited commit broke the offsets of hca cap struct, fix it. While at it, cleanup a white space introduced by the same commit. Fixes: b169e64a2444 ("net/mlx5: Geneve, Add flow table capabilities for Geneve decap with TLV options") Reported-by: Qian Cai Cc: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6a7fc18a9fe3..6b2e6b710ac0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1265,7 +1265,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_option_data_len[0x5]; u8 reserved_at_570[0x10]; - u8 reserved_at_580[0x1c]; + u8 reserved_at_580[0x3c]; u8 mini_cqe_resp_stride_index[0x1]; u8 cqe_128_always[0x1]; u8 cqe_compression_128[0x1]; @@ -9566,7 +9566,7 @@ struct mlx5_ifc_sw_icm_bits { u8 sw_icm_start_addr[0x40]; u8 reserved_at_c0[0x140]; -}; +}; struct mlx5_ifc_geneve_tlv_option_bits { u8 modify_field_select[0x40]; -- cgit v1.2.3-71-gd317 From a708fb7b1f8dcc7a8ed949839958cd5d812dd939 Mon Sep 17 00:00:00 2001 From: Erez Alfasi Date: Thu, 21 Mar 2019 15:02:13 +0200 Subject: net/mlx5e: ethtool, Add support for EEPROM high pages query Add the support to read additional EEPROM information from high pages. Information for modules such as SFF-8436 and SFF-8636: 1) Application select table 2) User writable EEPROM 3) Thresholds and alarms Signed-off-by: Erez Alfasi Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 ++--- drivers/net/ethernet/mellanox/mlx5/core/port.c | 40 ++++++++++++++++++---- include/linux/mlx5/port.h | 1 + 3 files changed, 39 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 78dc8fe2a83c..7efaa58ae034 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1561,7 +1561,7 @@ static int mlx5e_get_module_info(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *dev = priv->mdev; int size_read = 0; - u8 data[4]; + u8 data[4] = {0}; size_read = mlx5_query_module_eeprom(dev, 0, 2, data); if (size_read < 2) @@ -1571,17 +1571,17 @@ static int mlx5e_get_module_info(struct net_device *netdev, switch (data[0]) { case MLX5_MODULE_ID_QSFP: modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; break; case MLX5_MODULE_ID_QSFP_PLUS: case MLX5_MODULE_ID_QSFP28: /* data[1] = revision id */ if (data[0] == MLX5_MODULE_ID_QSFP28 || data[1] >= 0x3) { modinfo->type = ETH_MODULE_SFF_8636; - modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN; } else { modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; } break; case MLX5_MODULE_ID_SFP: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 361468e0435d..cc262b30aed5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -293,15 +293,36 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num) return 0; } +static int mlx5_eeprom_page(int offset) +{ + if (offset < MLX5_EEPROM_PAGE_LENGTH) + /* Addresses between 0-255 - page 00 */ + return 0; + + /* Addresses between 256 - 639 belongs to pages 01, 02 and 03 + * For example, offset = 400 belongs to page 02: + * 1 + ((400 - 256)/128) = 2 + */ + return 1 + ((offset - MLX5_EEPROM_PAGE_LENGTH) / + MLX5_EEPROM_HIGH_PAGE_LENGTH); +} + +static int mlx5_eeprom_high_page_offset(int page_num) +{ + if (!page_num) /* Page 0 always start from low page */ + return 0; + + /* High page */ + return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH; +} + int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, u16 offset, u16 size, u8 *data) { + int module_num, page_num, status, err; u32 out[MLX5_ST_SZ_DW(mcia_reg)]; u32 in[MLX5_ST_SZ_DW(mcia_reg)]; - int module_num; u16 i2c_addr; - int status; - int err; void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); err = mlx5_query_module_num(dev, &module_num); @@ -311,8 +332,15 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, memset(in, 0, sizeof(in)); size = min_t(int, size, MLX5_EEPROM_MAX_BYTES); - if (offset < MLX5_EEPROM_PAGE_LENGTH && - offset + size > MLX5_EEPROM_PAGE_LENGTH) + /* Get the page number related to the given offset */ + page_num = mlx5_eeprom_page(offset); + + /* Set the right offset according to the page number, + * For page_num > 0, relative offset is always >= 128 (high page). + */ + offset -= mlx5_eeprom_high_page_offset(page_num); + + if (offset + size > MLX5_EEPROM_PAGE_LENGTH) /* Cross pages read, read until offset 256 in low page */ size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; @@ -321,7 +349,7 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, MLX5_SET(mcia_reg, in, l, 0); MLX5_SET(mcia_reg, in, module, module_num); MLX5_SET(mcia_reg, in, i2c_device_address, i2c_addr); - MLX5_SET(mcia_reg, in, page_number, 0); + MLX5_SET(mcia_reg, in, page_number, page_num); MLX5_SET(mcia_reg, in, device_address, offset); MLX5_SET(mcia_reg, in, size, size); diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 64e78394fc9c..de9a272c9f3d 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -60,6 +60,7 @@ enum mlx5_an_status { #define MLX5_I2C_ADDR_LOW 0x50 #define MLX5_I2C_ADDR_HIGH 0x51 #define MLX5_EEPROM_PAGE_LENGTH 256 +#define MLX5_EEPROM_HIGH_PAGE_LENGTH 128 enum mlx5e_link_mode { MLX5E_1000BASE_CX_SGMII = 0, -- cgit v1.2.3-71-gd317 From c9bbfb378bc35fcd0b51e4a8950bd50447f39832 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Fri, 12 Apr 2019 16:14:03 -0500 Subject: net/mlx5: Remove unused mlx5_query_nic_vport_vlans mlx5_query_nic_vport_vlans() is not used anymore. Hence remove it. This patch doesn't change any functionality. Signed-off-by: Bodong Wang Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 61 ------------------------- include/linux/mlx5/vport.h | 4 -- 2 files changed, 65 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index ef95feca9961..95cdc8cbcba4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -371,67 +371,6 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list); -int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, - u16 vport, - u16 vlans[], - int *size) -{ - u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)]; - void *nic_vport_ctx; - int req_list_size; - int max_list_size; - int out_sz; - void *out; - int err; - int i; - - req_list_size = *size; - max_list_size = 1 << MLX5_CAP_GEN(dev, log_max_vlan_list); - if (req_list_size > max_list_size) { - mlx5_core_warn(dev, "Requested list size (%d) > (%d) max list size\n", - req_list_size, max_list_size); - req_list_size = max_list_size; - } - - out_sz = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in) + - req_list_size * MLX5_ST_SZ_BYTES(vlan_layout); - - memset(in, 0, sizeof(in)); - out = kzalloc(out_sz, GFP_KERNEL); - if (!out) - return -ENOMEM; - - MLX5_SET(query_nic_vport_context_in, in, opcode, - MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT); - MLX5_SET(query_nic_vport_context_in, in, allowed_list_type, - MLX5_NVPRT_LIST_TYPE_VLAN); - MLX5_SET(query_nic_vport_context_in, in, vport_number, vport); - - if (vport) - MLX5_SET(query_nic_vport_context_in, in, other_vport, 1); - - err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz); - if (err) - goto out; - - nic_vport_ctx = MLX5_ADDR_OF(query_nic_vport_context_out, out, - nic_vport_context); - req_list_size = MLX5_GET(nic_vport_context, nic_vport_ctx, - allowed_list_size); - - *size = req_list_size; - for (i = 0; i < req_list_size; i++) { - void *vlan_addr = MLX5_ADDR_OF(nic_vport_context, - nic_vport_ctx, - current_uc_mac_address[i]); - vlans[i] = MLX5_GET(vlan_layout, vlan_addr, vlan); - } -out: - kfree(out); - return err; -} -EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_vlans); - int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, u16 vlans[], int list_size) diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 0eef548b9946..3d1c6cdbbba7 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -118,10 +118,6 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev, int promisc_uc, int promisc_mc, int promisc_all); -int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, - u16 vport, - u16 vlans[], - int *size); int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, u16 vlans[], int list_size); -- cgit v1.2.3-71-gd317 From 6f4e02193c9a9ea54dd3151cf97489fa787cd0e6 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Thu, 18 Apr 2019 18:24:15 -0500 Subject: net/mlx5: E-Switch, Use atomic rep state to serialize state change When the state of rep was introduced, it was also designed to prevent duplicate unloading of the same rep. Considering the following two flows when an eswitch manager is at switchdev mode with n VF reps loaded. +--------------------------------------+--------------------------------+ | cpu-0 | cpu-1 | | -------- | -------- | | mlx5_ib_remove | mlx5_eswitch_disable_sriov | | mlx5_ib_unregister_vport_reps | esw_offloads_cleanup | | mlx5_eswitch_unregister_vport_reps | esw_offloads_unload_all_reps | | __unload_reps_all_vport | __unload_reps_all_vport | +--------------------------------------+--------------------------------+ These two flows will try to unload the same rep. Per original design, once one flow unloads the rep, the state moves to REGISTERED. The 2nd flow will no longer needs to do the unload and bails out. However, as read and write of the state is not atomic, when 1st flow is doing the unload, the state is still LOADED, 2nd flow is able to do the same unload action. Kernel crash will happen. To solve this, driver should do atomic test-and-set for the state. So that only one flow can change the rep state from LOADED to REGISTERED, and proceed to do the actual unloading. Since the state is changing to atomic type, all other read/write should be atomic action as well. Fixes: f121e0ea9586 (net/mlx5: E-Switch, Add state to eswitch vport representors) Signed-off-by: Bodong Wang Reviewed-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 36 ++++++++++------------ include/linux/mlx5/eswitch.h | 2 +- 2 files changed, 18 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index e88feaa293f6..e09ae27485ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -333,7 +333,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val) esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none"); for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) { rep = &esw->offloads.vport_reps[vf_vport]; - if (rep->rep_if[REP_ETH].state != REP_LOADED) + if (atomic_read(&rep->rep_if[REP_ETH].state) != REP_LOADED) continue; err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val); @@ -1277,7 +1277,8 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) ether_addr_copy(rep->hw_id, hw_id); for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) - rep->rep_if[rep_type].state = REP_UNREGISTERED; + atomic_set(&rep->rep_if[rep_type].state, + REP_UNREGISTERED); } return 0; @@ -1286,11 +1287,9 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, u8 rep_type) { - if (rep->rep_if[rep_type].state != REP_LOADED) - return; - - rep->rep_if[rep_type].unload(rep); - rep->rep_if[rep_type].state = REP_REGISTERED; + if (atomic_cmpxchg(&rep->rep_if[rep_type].state, + REP_LOADED, REP_REGISTERED) == REP_LOADED) + rep->rep_if[rep_type].unload(rep); } static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type) @@ -1351,16 +1350,15 @@ static int __esw_offloads_load_rep(struct mlx5_eswitch *esw, { int err = 0; - if (rep->rep_if[rep_type].state != REP_REGISTERED) - return 0; - - err = rep->rep_if[rep_type].load(esw->dev, rep); - if (err) - return err; - - rep->rep_if[rep_type].state = REP_LOADED; + if (atomic_cmpxchg(&rep->rep_if[rep_type].state, + REP_REGISTERED, REP_LOADED) == REP_REGISTERED) { + err = rep->rep_if[rep_type].load(esw->dev, rep); + if (err) + atomic_set(&rep->rep_if[rep_type].state, + REP_REGISTERED); + } - return 0; + return err; } static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type) @@ -2217,7 +2215,7 @@ void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw, rep_if->get_proto_dev = __rep_if->get_proto_dev; rep_if->priv = __rep_if->priv; - rep_if->state = REP_REGISTERED; + atomic_set(&rep_if->state, REP_REGISTERED); } } EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps); @@ -2232,7 +2230,7 @@ void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type) __unload_reps_all_vport(esw, max_vf, rep_type); mlx5_esw_for_all_reps(esw, i, rep) - rep->rep_if[rep_type].state = REP_UNREGISTERED; + atomic_set(&rep->rep_if[rep_type].state, REP_UNREGISTERED); } EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps); @@ -2252,7 +2250,7 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, rep = mlx5_eswitch_get_rep(esw, vport); - if (rep->rep_if[rep_type].state == REP_LOADED && + if (atomic_read(&rep->rep_if[rep_type].state) == REP_LOADED && rep->rep_if[rep_type].get_proto_dev) return rep->rep_if[rep_type].get_proto_dev(rep); return NULL; diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 96d8435421de..0ca77dd1429c 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -35,7 +35,7 @@ struct mlx5_eswitch_rep_if { void (*unload)(struct mlx5_eswitch_rep *rep); void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); void *priv; - u8 state; + atomic_t state; }; struct mlx5_eswitch_rep { -- cgit v1.2.3-71-gd317 From 8b952747844526cef50fa2e0ae903f586e3cb2e4 Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Fri, 3 May 2019 12:36:58 +0200 Subject: net: macb: shrink macb_platform_data structure This structure was used intensively for machine specific values when DT was not used. Since the removal of AVR32 from the kernel, this structure is only used for passing clocks from PCI macb wrapper, all other fields being 0. All other known platforms use DT. Remove the leftovers but make sure that PCI macb still works as expected by using default values: - phydev->irq is set to PHY_POLL by mdiobus_alloc() - mii_bus->phy_mask is cleared while allocating it - bp->phy_interface is set to PHY_INTERFACE_MODE_MII if mode not found in DT. This simplifies driver probe path and particularly phy handling. Signed-off-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_main.c | 59 ++++++-------------------------- include/linux/platform_data/macb.h | 9 ----- 2 files changed, 11 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 59531adcbb42..bd6a62f4bd7d 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -285,34 +285,22 @@ static void macb_set_hwaddr(struct macb *bp) static void macb_get_hwaddr(struct macb *bp) { - struct macb_platform_data *pdata; u32 bottom; u16 top; u8 addr[6]; int i; - pdata = dev_get_platdata(&bp->pdev->dev); - /* Check all 4 address register for valid address */ for (i = 0; i < 4; i++) { bottom = macb_or_gem_readl(bp, SA1B + i * 8); top = macb_or_gem_readl(bp, SA1T + i * 8); - if (pdata && pdata->rev_eth_addr) { - addr[5] = bottom & 0xff; - addr[4] = (bottom >> 8) & 0xff; - addr[3] = (bottom >> 16) & 0xff; - addr[2] = (bottom >> 24) & 0xff; - addr[1] = top & 0xff; - addr[0] = (top & 0xff00) >> 8; - } else { - addr[0] = bottom & 0xff; - addr[1] = (bottom >> 8) & 0xff; - addr[2] = (bottom >> 16) & 0xff; - addr[3] = (bottom >> 24) & 0xff; - addr[4] = top & 0xff; - addr[5] = (top >> 8) & 0xff; - } + addr[0] = bottom & 0xff; + addr[1] = (bottom >> 8) & 0xff; + addr[2] = (bottom >> 16) & 0xff; + addr[3] = (bottom >> 24) & 0xff; + addr[4] = top & 0xff; + addr[5] = (top >> 8) & 0xff; if (is_valid_ether_addr(addr)) { memcpy(bp->dev->dev_addr, addr, sizeof(addr)); @@ -510,12 +498,10 @@ static void macb_handle_link_change(struct net_device *dev) static int macb_mii_probe(struct net_device *dev) { struct macb *bp = netdev_priv(dev); - struct macb_platform_data *pdata; struct phy_device *phydev; struct device_node *np; - int phy_irq, ret, i; + int ret, i; - pdata = dev_get_platdata(&bp->pdev->dev); np = bp->pdev->dev.of_node; ret = 0; @@ -557,19 +543,6 @@ static int macb_mii_probe(struct net_device *dev) return -ENXIO; } - if (pdata) { - if (gpio_is_valid(pdata->phy_irq_pin)) { - ret = devm_gpio_request(&bp->pdev->dev, - pdata->phy_irq_pin, "phy int"); - if (!ret) { - phy_irq = gpio_to_irq(pdata->phy_irq_pin); - phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq; - } - } else { - phydev->irq = PHY_POLL; - } - } - /* attach the mac to the phy */ ret = phy_connect_direct(dev, phydev, &macb_handle_link_change, bp->phy_interface); @@ -598,7 +571,6 @@ static int macb_mii_probe(struct net_device *dev) static int macb_mii_init(struct macb *bp) { - struct macb_platform_data *pdata; struct device_node *np; int err = -ENXIO; @@ -618,7 +590,6 @@ static int macb_mii_init(struct macb *bp) bp->pdev->name, bp->pdev->id); bp->mii_bus->priv = bp; bp->mii_bus->parent = &bp->pdev->dev; - pdata = dev_get_platdata(&bp->pdev->dev); dev_set_drvdata(&bp->dev->dev, bp->mii_bus); @@ -632,9 +603,6 @@ static int macb_mii_init(struct macb *bp) err = mdiobus_register(bp->mii_bus); } else { - if (pdata) - bp->mii_bus->phy_mask = pdata->phy_mask; - err = of_mdiobus_register(bp->mii_bus, np); } @@ -4050,7 +4018,6 @@ static int macb_probe(struct platform_device *pdev) struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL; struct clk *tsu_clk = NULL; unsigned int queue_mask, num_queues; - struct macb_platform_data *pdata; bool native_io; struct phy_device *phydev; struct net_device *dev; @@ -4182,15 +4149,11 @@ static int macb_probe(struct platform_device *pdev) } err = of_get_phy_mode(np); - if (err < 0) { - pdata = dev_get_platdata(&pdev->dev); - if (pdata && pdata->is_rmii) - bp->phy_interface = PHY_INTERFACE_MODE_RMII; - else - bp->phy_interface = PHY_INTERFACE_MODE_MII; - } else { + if (err < 0) + /* not found in DT, MII by default */ + bp->phy_interface = PHY_INTERFACE_MODE_MII; + else bp->phy_interface = err; - } /* IP specific init */ err = init(pdev); diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h index 7815d50c26ff..2bc51b822956 100644 --- a/include/linux/platform_data/macb.h +++ b/include/linux/platform_data/macb.h @@ -12,19 +12,10 @@ /** * struct macb_platform_data - platform data for MACB Ethernet - * @phy_mask: phy mask passed when register the MDIO bus - * within the driver - * @phy_irq_pin: PHY IRQ - * @is_rmii: using RMII interface? - * @rev_eth_addr: reverse Ethernet address byte order * @pclk: platform clock * @hclk: AHB clock */ struct macb_platform_data { - u32 phy_mask; - int phy_irq_pin; - u8 is_rmii; - u8 rev_eth_addr; struct clk *pclk; struct clk *hclk; }; -- cgit v1.2.3-71-gd317 From 554aae35007e49f533d3d10e788295f7141725bc Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 2 May 2019 23:23:29 +0300 Subject: lib: Add support for generic packing operations This provides an unified API for accessing register bit fields regardless of memory layout. The basic unit of data for these API functions is the u64. The process of transforming an u64 from native CPU encoding into the peripheral's encoding is called 'pack', and transforming it from peripheral to native CPU encoding is 'unpack'. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- Documentation/packing.txt | 149 ++++++++++++++++++++++++++++++++ MAINTAINERS | 8 ++ include/linux/packing.h | 49 +++++++++++ lib/Kconfig | 17 ++++ lib/Makefile | 1 + lib/packing.c | 213 ++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 437 insertions(+) create mode 100644 Documentation/packing.txt create mode 100644 include/linux/packing.h create mode 100644 lib/packing.c (limited to 'include/linux') diff --git a/Documentation/packing.txt b/Documentation/packing.txt new file mode 100644 index 000000000000..f830c98645f1 --- /dev/null +++ b/Documentation/packing.txt @@ -0,0 +1,149 @@ +================================================ +Generic bitfield packing and unpacking functions +================================================ + +Problem statement +----------------- + +When working with hardware, one has to choose between several approaches of +interfacing with it. +One can memory-map a pointer to a carefully crafted struct over the hardware +device's memory region, and access its fields as struct members (potentially +declared as bitfields). But writing code this way would make it less portable, +due to potential endianness mismatches between the CPU and the hardware device. +Additionally, one has to pay close attention when translating register +definitions from the hardware documentation into bit field indices for the +structs. Also, some hardware (typically networking equipment) tends to group +its register fields in ways that violate any reasonable word boundaries +(sometimes even 64 bit ones). This creates the inconvenience of having to +define "high" and "low" portions of register fields within the struct. +A more robust alternative to struct field definitions would be to extract the +required fields by shifting the appropriate number of bits. But this would +still not protect from endianness mismatches, except if all memory accesses +were performed byte-by-byte. Also the code can easily get cluttered, and the +high-level idea might get lost among the many bit shifts required. +Many drivers take the bit-shifting approach and then attempt to reduce the +clutter with tailored macros, but more often than not these macros take +shortcuts that still prevent the code from being truly portable. + +The solution +------------ + +This API deals with 2 basic operations: + - Packing a CPU-usable number into a memory buffer (with hardware + constraints/quirks) + - Unpacking a memory buffer (which has hardware constraints/quirks) + into a CPU-usable number. + +The API offers an abstraction over said hardware constraints and quirks, +over CPU endianness and therefore between possible mismatches between +the two. + +The basic unit of these API functions is the u64. From the CPU's +perspective, bit 63 always means bit offset 7 of byte 7, albeit only +logically. The question is: where do we lay this bit out in memory? + +The following examples cover the memory layout of a packed u64 field. +The byte offsets in the packed buffer are always implicitly 0, 1, ... 7. +What the examples show is where the logical bytes and bits sit. + +1. Normally (no quirks), we would do it like this: + +63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32 +7 6 5 4 +31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 +3 2 1 0 + +That is, the MSByte (7) of the CPU-usable u64 sits at memory offset 0, and the +LSByte (0) of the u64 sits at memory offset 7. +This corresponds to what most folks would regard to as "big endian", where +bit i corresponds to the number 2^i. This is also referred to in the code +comments as "logical" notation. + + +2. If QUIRK_MSB_ON_THE_RIGHT is set, we do it like this: + +56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39 +7 6 5 4 +24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23 8 9 10 11 12 13 14 15 0 1 2 3 4 5 6 7 +3 2 1 0 + +That is, QUIRK_MSB_ON_THE_RIGHT does not affect byte positioning, but +inverts bit offsets inside a byte. + + +3. If QUIRK_LITTLE_ENDIAN is set, we do it like this: + +39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56 +4 5 6 7 +7 6 5 4 3 2 1 0 15 14 13 12 11 10 9 8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24 +0 1 2 3 + +Therefore, QUIRK_LITTLE_ENDIAN means that inside the memory region, every +byte from each 4-byte word is placed at its mirrored position compared to +the boundary of that word. + +4. If QUIRK_MSB_ON_THE_RIGHT and QUIRK_LITTLE_ENDIAN are both set, we do it + like this: + +32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 +4 5 6 7 +0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 +0 1 2 3 + + +5. If just QUIRK_LSW32_IS_FIRST is set, we do it like this: + +31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 +3 2 1 0 +63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32 +7 6 5 4 + +In this case the 8 byte memory region is interpreted as follows: first +4 bytes correspond to the least significant 4-byte word, next 4 bytes to +the more significant 4-byte word. + + +6. If QUIRK_LSW32_IS_FIRST and QUIRK_MSB_ON_THE_RIGHT are set, we do it like + this: + +24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23 8 9 10 11 12 13 14 15 0 1 2 3 4 5 6 7 +3 2 1 0 +56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39 +7 6 5 4 + + +7. If QUIRK_LSW32_IS_FIRST and QUIRK_LITTLE_ENDIAN are set, it looks like + this: + +7 6 5 4 3 2 1 0 15 14 13 12 11 10 9 8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24 +0 1 2 3 +39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56 +4 5 6 7 + + +8. If QUIRK_LSW32_IS_FIRST, QUIRK_LITTLE_ENDIAN and QUIRK_MSB_ON_THE_RIGHT + are set, it looks like this: + +0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 +0 1 2 3 +32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 +4 5 6 7 + + +We always think of our offsets as if there were no quirk, and we translate +them afterwards, before accessing the memory region. + +Intended use +------------ + +Drivers that opt to use this API first need to identify which of the above 3 +quirk combinations (for a total of 8) match what the hardware documentation +describes. Then they should wrap the packing() function, creating a new +xxx_packing() that calls it using the proper QUIRK_* one-hot bits set. + +The packing() function returns an int-encoded error code, which protects the +programmer against incorrect API use. The errors are not expected to occur +durring runtime, therefore it is reasonable for xxx_packing() to return void +and simply swallow those errors. Optionally it can dump stack or print the +error description. diff --git a/MAINTAINERS b/MAINTAINERS index 0af66fa919a8..ff029f3d0f13 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11673,6 +11673,14 @@ L: linux-i2c@vger.kernel.org S: Orphan F: drivers/i2c/busses/i2c-pasemi.c +PACKING +M: Vladimir Oltean +L: netdev@vger.kernel.org +S: Supported +F: lib/packing.c +F: include/linux/packing.h +F: Documentation/packing.txt + PADATA PARALLEL EXECUTION MECHANISM M: Steffen Klassert L: linux-crypto@vger.kernel.org diff --git a/include/linux/packing.h b/include/linux/packing.h new file mode 100644 index 000000000000..54667735cc67 --- /dev/null +++ b/include/linux/packing.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright (c) 2016-2018, NXP Semiconductors + * Copyright (c) 2018-2019, Vladimir Oltean + */ +#ifndef _LINUX_PACKING_H +#define _LINUX_PACKING_H + +#include +#include + +#define QUIRK_MSB_ON_THE_RIGHT BIT(0) +#define QUIRK_LITTLE_ENDIAN BIT(1) +#define QUIRK_LSW32_IS_FIRST BIT(2) + +enum packing_op { + PACK, + UNPACK, +}; + +/** + * packing - Convert numbers (currently u64) between a packed and an unpacked + * format. Unpacked means laid out in memory in the CPU's native + * understanding of integers, while packed means anything else that + * requires translation. + * + * @pbuf: Pointer to a buffer holding the packed value. + * @uval: Pointer to an u64 holding the unpacked value. + * @startbit: The index (in logical notation, compensated for quirks) where + * the packed value starts within pbuf. Must be larger than, or + * equal to, endbit. + * @endbit: The index (in logical notation, compensated for quirks) where + * the packed value ends within pbuf. Must be smaller than, or equal + * to, startbit. + * @op: If PACK, then uval will be treated as const pointer and copied (packed) + * into pbuf, between startbit and endbit. + * If UNPACK, then pbuf will be treated as const pointer and the logical + * value between startbit and endbit will be copied (unpacked) to uval. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming + * correct usage, return code may be discarded. + * If op is PACK, pbuf is modified. + * If op is UNPACK, uval is modified. + */ +int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, + enum packing_op op, u8 quirks); + +#endif diff --git a/lib/Kconfig b/lib/Kconfig index a9e56539bd11..ac1fcf06d8ea 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -18,6 +18,23 @@ config RAID6_PQ_BENCHMARK Benchmark all available RAID6 PQ functions on init and choose the fastest one. +config PACKING + bool "Generic bitfield packing and unpacking" + default n + help + This option provides the packing() helper function, which permits + converting bitfields between a CPU-usable representation and a + memory representation that can have any combination of these quirks: + - Is little endian (bytes are reversed within a 32-bit group) + - The least-significant 32-bit word comes first (within a 64-bit + group) + - The most significant bit of a byte is at its right (bit 0 of a + register description is numerically 2^7). + Drivers may use these helpers to match the bit indices as described + in the data sheets of the peripherals they are in control of. + + When in doubt, say N. + config BITREVERSE tristate diff --git a/lib/Makefile b/lib/Makefile index 3b08673e8881..7d4db18fabf1 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -108,6 +108,7 @@ obj-$(CONFIG_DEBUG_LIST) += list_debug.o obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o obj-$(CONFIG_BITREVERSE) += bitrev.o +obj-$(CONFIG_PACKING) += packing.o obj-$(CONFIG_RATIONAL) += rational.o obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o obj-$(CONFIG_CRC16) += crc16.o diff --git a/lib/packing.c b/lib/packing.c new file mode 100644 index 000000000000..50d1e9f2f5a7 --- /dev/null +++ b/lib/packing.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2016-2018, NXP Semiconductors + * Copyright (c) 2018-2019, Vladimir Oltean + */ +#include +#include +#include +#include +#include + +static int get_le_offset(int offset) +{ + int closest_multiple_of_4; + + closest_multiple_of_4 = (offset / 4) * 4; + offset -= closest_multiple_of_4; + return closest_multiple_of_4 + (3 - offset); +} + +static int get_reverse_lsw32_offset(int offset, size_t len) +{ + int closest_multiple_of_4; + int word_index; + + word_index = offset / 4; + closest_multiple_of_4 = word_index * 4; + offset -= closest_multiple_of_4; + word_index = (len / 4) - word_index - 1; + return word_index * 4 + offset; +} + +static u64 bit_reverse(u64 val, unsigned int width) +{ + u64 new_val = 0; + unsigned int bit; + unsigned int i; + + for (i = 0; i < width; i++) { + bit = (val & (1 << i)) != 0; + new_val |= (bit << (width - i - 1)); + } + return new_val; +} + +static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit, + int *box_end_bit, u8 *box_mask) +{ + int box_bit_width = *box_start_bit - *box_end_bit + 1; + int new_box_start_bit, new_box_end_bit; + + *to_write >>= *box_end_bit; + *to_write = bit_reverse(*to_write, box_bit_width); + *to_write <<= *box_end_bit; + + new_box_end_bit = box_bit_width - *box_start_bit - 1; + new_box_start_bit = box_bit_width - *box_end_bit - 1; + *box_mask = GENMASK_ULL(new_box_start_bit, new_box_end_bit); + *box_start_bit = new_box_start_bit; + *box_end_bit = new_box_end_bit; +} + +/** + * packing - Convert numbers (currently u64) between a packed and an unpacked + * format. Unpacked means laid out in memory in the CPU's native + * understanding of integers, while packed means anything else that + * requires translation. + * + * @pbuf: Pointer to a buffer holding the packed value. + * @uval: Pointer to an u64 holding the unpacked value. + * @startbit: The index (in logical notation, compensated for quirks) where + * the packed value starts within pbuf. Must be larger than, or + * equal to, endbit. + * @endbit: The index (in logical notation, compensated for quirks) where + * the packed value ends within pbuf. Must be smaller than, or equal + * to, startbit. + * @op: If PACK, then uval will be treated as const pointer and copied (packed) + * into pbuf, between startbit and endbit. + * If UNPACK, then pbuf will be treated as const pointer and the logical + * value between startbit and endbit will be copied (unpacked) to uval. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming + * correct usage, return code may be discarded. + * If op is PACK, pbuf is modified. + * If op is UNPACK, uval is modified. + */ +int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, + enum packing_op op, u8 quirks) +{ + /* Number of bits for storing "uval" + * also width of the field to access in the pbuf + */ + u64 value_width; + /* Logical byte indices corresponding to the + * start and end of the field. + */ + int plogical_first_u8, plogical_last_u8, box; + + /* startbit is expected to be larger than endbit */ + if (startbit < endbit) + /* Invalid function call */ + return -EINVAL; + + value_width = startbit - endbit + 1; + if (value_width > 64) + return -ERANGE; + + /* Check if "uval" fits in "value_width" bits. + * If value_width is 64, the check will fail, but any + * 64-bit uval will surely fit. + */ + if (op == PACK && value_width < 64 && (*uval >= (1ull << value_width))) + /* Cannot store "uval" inside "value_width" bits. + * Truncating "uval" is most certainly not desirable, + * so simply erroring out is appropriate. + */ + return -ERANGE; + + /* Initialize parameter */ + if (op == UNPACK) + *uval = 0; + + /* Iterate through an idealistic view of the pbuf as an u64 with + * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low + * logical bit significance. "box" denotes the current logical u8. + */ + plogical_first_u8 = startbit / 8; + plogical_last_u8 = endbit / 8; + + for (box = plogical_first_u8; box >= plogical_last_u8; box--) { + /* Bit indices into the currently accessed 8-bit box */ + int box_start_bit, box_end_bit, box_addr; + u8 box_mask; + /* Corresponding bits from the unpacked u64 parameter */ + int proj_start_bit, proj_end_bit; + u64 proj_mask; + + /* This u8 may need to be accessed in its entirety + * (from bit 7 to bit 0), or not, depending on the + * input arguments startbit and endbit. + */ + if (box == plogical_first_u8) + box_start_bit = startbit % 8; + else + box_start_bit = 7; + if (box == plogical_last_u8) + box_end_bit = endbit % 8; + else + box_end_bit = 0; + + /* We have determined the box bit start and end. + * Now we calculate where this (masked) u8 box would fit + * in the unpacked (CPU-readable) u64 - the u8 box's + * projection onto the unpacked u64. Though the + * box is u8, the projection is u64 because it may fall + * anywhere within the unpacked u64. + */ + proj_start_bit = ((box * 8) + box_start_bit) - endbit; + proj_end_bit = ((box * 8) + box_end_bit) - endbit; + proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit); + box_mask = GENMASK_ULL(box_start_bit, box_end_bit); + + /* Determine the offset of the u8 box inside the pbuf, + * adjusted for quirks. The adjusted box_addr will be used for + * effective addressing inside the pbuf (so it's not + * logical any longer). + */ + box_addr = pbuflen - box - 1; + if (quirks & QUIRK_LITTLE_ENDIAN) + box_addr = get_le_offset(box_addr); + if (quirks & QUIRK_LSW32_IS_FIRST) + box_addr = get_reverse_lsw32_offset(box_addr, + pbuflen); + + if (op == UNPACK) { + u64 pval; + + /* Read from pbuf, write to uval */ + pval = ((u8 *)pbuf)[box_addr] & box_mask; + if (quirks & QUIRK_MSB_ON_THE_RIGHT) + adjust_for_msb_right_quirk(&pval, + &box_start_bit, + &box_end_bit, + &box_mask); + + pval >>= box_end_bit; + pval <<= proj_end_bit; + *uval &= ~proj_mask; + *uval |= pval; + } else { + u64 pval; + + /* Write to pbuf, read from uval */ + pval = (*uval) & proj_mask; + pval >>= proj_end_bit; + if (quirks & QUIRK_MSB_ON_THE_RIGHT) + adjust_for_msb_right_quirk(&pval, + &box_start_bit, + &box_end_bit, + &box_mask); + + pval <<= box_end_bit; + ((u8 *)pbuf)[box_addr] &= ~box_mask; + ((u8 *)pbuf)[box_addr] |= pval; + } + } + return 0; +} +EXPORT_SYMBOL(packing); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Generic bitfield packing and unpacking"); -- cgit v1.2.3-71-gd317 From 8aa9ebccae87621d997707e4f25e53fddd7e30e4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 2 May 2019 23:23:30 +0300 Subject: net: dsa: Introduce driver for NXP SJA1105 5-port L2 switch At this moment the following is supported: * Link state management through phylib * Autonomous L2 forwarding managed through iproute2 bridge commands. IP termination must be done currently through the master netdevice, since the switch is unmanaged at this point and using DSA_TAG_PROTO_NONE. Signed-off-by: Vladimir Oltean Signed-off-by: Georg Waibel Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- MAINTAINERS | 6 + drivers/net/dsa/Kconfig | 2 + drivers/net/dsa/Makefile | 1 + drivers/net/dsa/sja1105/Kconfig | 16 + drivers/net/dsa/sja1105/Makefile | 8 + drivers/net/dsa/sja1105/sja1105.h | 138 ++++ drivers/net/dsa/sja1105/sja1105_clocking.c | 598 ++++++++++++++ drivers/net/dsa/sja1105/sja1105_dynamic_config.c | 489 ++++++++++++ drivers/net/dsa/sja1105/sja1105_dynamic_config.h | 43 + drivers/net/dsa/sja1105/sja1105_main.c | 928 ++++++++++++++++++++++ drivers/net/dsa/sja1105/sja1105_spi.c | 553 +++++++++++++ drivers/net/dsa/sja1105/sja1105_static_config.c | 949 +++++++++++++++++++++++ drivers/net/dsa/sja1105/sja1105_static_config.h | 250 ++++++ include/linux/dsa/sja1105.h | 19 + 14 files changed, 4000 insertions(+) create mode 100644 drivers/net/dsa/sja1105/Kconfig create mode 100644 drivers/net/dsa/sja1105/Makefile create mode 100644 drivers/net/dsa/sja1105/sja1105.h create mode 100644 drivers/net/dsa/sja1105/sja1105_clocking.c create mode 100644 drivers/net/dsa/sja1105/sja1105_dynamic_config.c create mode 100644 drivers/net/dsa/sja1105/sja1105_dynamic_config.h create mode 100644 drivers/net/dsa/sja1105/sja1105_main.c create mode 100644 drivers/net/dsa/sja1105/sja1105_spi.c create mode 100644 drivers/net/dsa/sja1105/sja1105_static_config.c create mode 100644 drivers/net/dsa/sja1105/sja1105_static_config.h create mode 100644 include/linux/dsa/sja1105.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index ff029f3d0f13..25db3db8fe38 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11120,6 +11120,12 @@ S: Maintained F: Documentation/devicetree/bindings/sound/sgtl5000.txt F: sound/soc/codecs/sgtl5000* +NXP SJA1105 ETHERNET SWITCH DRIVER +M: Vladimir Oltean +L: linux-kernel@vger.kernel.org +S: Maintained +F: drivers/net/dsa/sja1105 + NXP TDA998X DRM DRIVER M: Russell King S: Maintained diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 82560b710681..c6c5ecdbcaef 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -51,6 +51,8 @@ source "drivers/net/dsa/microchip/Kconfig" source "drivers/net/dsa/mv88e6xxx/Kconfig" +source "drivers/net/dsa/sja1105/Kconfig" + config NET_DSA_QCA8K tristate "Qualcomm Atheros QCA8K Ethernet switch family support" depends on NET_DSA diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index 82e5d794c41f..fefb6aaa82ba 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -18,3 +18,4 @@ obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx.o obj-y += b53/ obj-y += microchip/ obj-y += mv88e6xxx/ +obj-y += sja1105/ diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig new file mode 100644 index 000000000000..038685bb9d57 --- /dev/null +++ b/drivers/net/dsa/sja1105/Kconfig @@ -0,0 +1,16 @@ +config NET_DSA_SJA1105 +tristate "NXP SJA1105 Ethernet switch family support" + depends on NET_DSA && SPI + select PACKING + select CRC32 + help + This is the driver for the NXP SJA1105 automotive Ethernet switch + family. These are 5-port devices and are managed over an SPI + interface. Probing is handled based on OF bindings and so is the + linkage to phylib. The driver supports the following revisions: + - SJA1105E (Gen. 1, No TT-Ethernet) + - SJA1105T (Gen. 1, TT-Ethernet) + - SJA1105P (Gen. 2, No SGMII, No TT-Ethernet) + - SJA1105Q (Gen. 2, No SGMII, TT-Ethernet) + - SJA1105R (Gen. 2, SGMII, No TT-Ethernet) + - SJA1105S (Gen. 2, SGMII, TT-Ethernet) diff --git a/drivers/net/dsa/sja1105/Makefile b/drivers/net/dsa/sja1105/Makefile new file mode 100644 index 000000000000..d3237b313a4e --- /dev/null +++ b/drivers/net/dsa/sja1105/Makefile @@ -0,0 +1,8 @@ +obj-$(CONFIG_NET_DSA_SJA1105) += sja1105.o + +sja1105-objs := \ + sja1105_spi.o \ + sja1105_main.o \ + sja1105_clocking.o \ + sja1105_static_config.o \ + sja1105_dynamic_config.o \ diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h new file mode 100644 index 000000000000..e01cb854cbcd --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -0,0 +1,138 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH + * Copyright (c) 2018-2019, Vladimir Oltean + */ +#ifndef _SJA1105_H +#define _SJA1105_H + +#include +#include +#include "sja1105_static_config.h" + +#define SJA1105_NUM_PORTS 5 +#define SJA1105_NUM_TC 8 +#define SJA1105ET_FDB_BIN_SIZE 4 + +/* Keeps the different addresses between E/T and P/Q/R/S */ +struct sja1105_regs { + u64 device_id; + u64 prod_id; + u64 status; + u64 rgu; + u64 config; + u64 rmii_pll1; + u64 pad_mii_tx[SJA1105_NUM_PORTS]; + u64 cgu_idiv[SJA1105_NUM_PORTS]; + u64 rgmii_pad_mii_tx[SJA1105_NUM_PORTS]; + u64 mii_tx_clk[SJA1105_NUM_PORTS]; + u64 mii_rx_clk[SJA1105_NUM_PORTS]; + u64 mii_ext_tx_clk[SJA1105_NUM_PORTS]; + u64 mii_ext_rx_clk[SJA1105_NUM_PORTS]; + u64 rgmii_tx_clk[SJA1105_NUM_PORTS]; + u64 rmii_ref_clk[SJA1105_NUM_PORTS]; + u64 rmii_ext_tx_clk[SJA1105_NUM_PORTS]; + u64 mac[SJA1105_NUM_PORTS]; + u64 mac_hl1[SJA1105_NUM_PORTS]; + u64 mac_hl2[SJA1105_NUM_PORTS]; + u64 qlevel[SJA1105_NUM_PORTS]; +}; + +struct sja1105_info { + u64 device_id; + /* Needed for distinction between P and R, and between Q and S + * (since the parts with/without SGMII share the same + * switch core and device_id) + */ + u64 part_no; + const struct sja1105_dynamic_table_ops *dyn_ops; + const struct sja1105_table_ops *static_ops; + const struct sja1105_regs *regs; + int (*reset_cmd)(const void *ctx, const void *data); + const char *name; +}; + +struct sja1105_private { + struct sja1105_static_config static_config; + const struct sja1105_info *info; + struct gpio_desc *reset_gpio; + struct spi_device *spidev; + struct dsa_switch *ds; +}; + +#include "sja1105_dynamic_config.h" + +struct sja1105_spi_message { + u64 access; + u64 read_count; + u64 address; +}; + +typedef enum { + SPI_READ = 0, + SPI_WRITE = 1, +} sja1105_spi_rw_mode_t; + +/* From sja1105_spi.c */ +int sja1105_spi_send_packed_buf(const struct sja1105_private *priv, + sja1105_spi_rw_mode_t rw, u64 reg_addr, + void *packed_buf, size_t size_bytes); +int sja1105_spi_send_int(const struct sja1105_private *priv, + sja1105_spi_rw_mode_t rw, u64 reg_addr, + u64 *value, u64 size_bytes); +int sja1105_spi_send_long_packed_buf(const struct sja1105_private *priv, + sja1105_spi_rw_mode_t rw, u64 base_addr, + void *packed_buf, u64 buf_len); +int sja1105_static_config_upload(struct sja1105_private *priv); + +extern struct sja1105_info sja1105e_info; +extern struct sja1105_info sja1105t_info; +extern struct sja1105_info sja1105p_info; +extern struct sja1105_info sja1105q_info; +extern struct sja1105_info sja1105r_info; +extern struct sja1105_info sja1105s_info; + +/* From sja1105_clocking.c */ + +typedef enum { + XMII_MAC = 0, + XMII_PHY = 1, +} sja1105_mii_role_t; + +typedef enum { + XMII_MODE_MII = 0, + XMII_MODE_RMII = 1, + XMII_MODE_RGMII = 2, +} sja1105_phy_interface_t; + +typedef enum { + SJA1105_SPEED_10MBPS = 3, + SJA1105_SPEED_100MBPS = 2, + SJA1105_SPEED_1000MBPS = 1, + SJA1105_SPEED_AUTO = 0, +} sja1105_speed_t; + +int sja1105_clocking_setup_port(struct sja1105_private *priv, int port); +int sja1105_clocking_setup(struct sja1105_private *priv); + +/* From sja1105_dynamic_config.c */ + +int sja1105_dynamic_config_read(struct sja1105_private *priv, + enum sja1105_blk_idx blk_idx, + int index, void *entry); +int sja1105_dynamic_config_write(struct sja1105_private *priv, + enum sja1105_blk_idx blk_idx, + int index, void *entry, bool keep); + +/* Common implementations for the static and dynamic configs */ +size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); + +#endif diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c new file mode 100644 index 000000000000..598544297931 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_clocking.c @@ -0,0 +1,598 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (c) 2016-2018, NXP Semiconductors + * Copyright (c) 2018-2019, Vladimir Oltean + */ +#include +#include "sja1105.h" + +#define SJA1105_SIZE_CGU_CMD 4 + +struct sja1105_cfg_pad_mii_tx { + u64 d32_os; + u64 d32_ipud; + u64 d10_os; + u64 d10_ipud; + u64 ctrl_os; + u64 ctrl_ipud; + u64 clk_os; + u64 clk_ih; + u64 clk_ipud; +}; + +/* UM10944 Table 82. + * IDIV_0_C to IDIV_4_C control registers + * (addr. 10000Bh to 10000Fh) + */ +struct sja1105_cgu_idiv { + u64 clksrc; + u64 autoblock; + u64 idiv; + u64 pd; +}; + +/* PLL_1_C control register + * + * SJA1105 E/T: UM10944 Table 81 (address 10000Ah) + * SJA1105 P/Q/R/S: UM11040 Table 116 (address 10000Ah) + */ +struct sja1105_cgu_pll_ctrl { + u64 pllclksrc; + u64 msel; + u64 autoblock; + u64 psel; + u64 direct; + u64 fbsel; + u64 bypass; + u64 pd; +}; + +enum { + CLKSRC_MII0_TX_CLK = 0x00, + CLKSRC_MII0_RX_CLK = 0x01, + CLKSRC_MII1_TX_CLK = 0x02, + CLKSRC_MII1_RX_CLK = 0x03, + CLKSRC_MII2_TX_CLK = 0x04, + CLKSRC_MII2_RX_CLK = 0x05, + CLKSRC_MII3_TX_CLK = 0x06, + CLKSRC_MII3_RX_CLK = 0x07, + CLKSRC_MII4_TX_CLK = 0x08, + CLKSRC_MII4_RX_CLK = 0x09, + CLKSRC_PLL0 = 0x0B, + CLKSRC_PLL1 = 0x0E, + CLKSRC_IDIV0 = 0x11, + CLKSRC_IDIV1 = 0x12, + CLKSRC_IDIV2 = 0x13, + CLKSRC_IDIV3 = 0x14, + CLKSRC_IDIV4 = 0x15, +}; + +/* UM10944 Table 83. + * MIIx clock control registers 1 to 30 + * (addresses 100013h to 100035h) + */ +struct sja1105_cgu_mii_ctrl { + u64 clksrc; + u64 autoblock; + u64 pd; +}; + +static void sja1105_cgu_idiv_packing(void *buf, struct sja1105_cgu_idiv *idiv, + enum packing_op op) +{ + const int size = 4; + + sja1105_packing(buf, &idiv->clksrc, 28, 24, size, op); + sja1105_packing(buf, &idiv->autoblock, 11, 11, size, op); + sja1105_packing(buf, &idiv->idiv, 5, 2, size, op); + sja1105_packing(buf, &idiv->pd, 0, 0, size, op); +} + +static int sja1105_cgu_idiv_config(struct sja1105_private *priv, int port, + bool enabled, int factor) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct device *dev = priv->ds->dev; + struct sja1105_cgu_idiv idiv; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + + if (enabled && factor != 1 && factor != 10) { + dev_err(dev, "idiv factor must be 1 or 10\n"); + return -ERANGE; + } + + /* Payload for packed_buf */ + idiv.clksrc = 0x0A; /* 25MHz */ + idiv.autoblock = 1; /* Block clk automatically */ + idiv.idiv = factor - 1; /* Divide by 1 or 10 */ + idiv.pd = enabled ? 0 : 1; /* Power down? */ + sja1105_cgu_idiv_packing(packed_buf, &idiv, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->cgu_idiv[port], packed_buf, + SJA1105_SIZE_CGU_CMD); +} + +static void +sja1105_cgu_mii_control_packing(void *buf, struct sja1105_cgu_mii_ctrl *cmd, + enum packing_op op) +{ + const int size = 4; + + sja1105_packing(buf, &cmd->clksrc, 28, 24, size, op); + sja1105_packing(buf, &cmd->autoblock, 11, 11, size, op); + sja1105_packing(buf, &cmd->pd, 0, 0, size, op); +} + +static int sja1105_cgu_mii_tx_clk_config(struct sja1105_private *priv, + int port, sja1105_mii_role_t role) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cgu_mii_ctrl mii_tx_clk; + const int mac_clk_sources[] = { + CLKSRC_MII0_TX_CLK, + CLKSRC_MII1_TX_CLK, + CLKSRC_MII2_TX_CLK, + CLKSRC_MII3_TX_CLK, + CLKSRC_MII4_TX_CLK, + }; + const int phy_clk_sources[] = { + CLKSRC_IDIV0, + CLKSRC_IDIV1, + CLKSRC_IDIV2, + CLKSRC_IDIV3, + CLKSRC_IDIV4, + }; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + int clksrc; + + if (role == XMII_MAC) + clksrc = mac_clk_sources[port]; + else + clksrc = phy_clk_sources[port]; + + /* Payload for packed_buf */ + mii_tx_clk.clksrc = clksrc; + mii_tx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ + mii_tx_clk.pd = 0; /* Power Down off => enabled */ + sja1105_cgu_mii_control_packing(packed_buf, &mii_tx_clk, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->mii_tx_clk[port], packed_buf, + SJA1105_SIZE_CGU_CMD); +} + +static int +sja1105_cgu_mii_rx_clk_config(struct sja1105_private *priv, int port) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cgu_mii_ctrl mii_rx_clk; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + const int clk_sources[] = { + CLKSRC_MII0_RX_CLK, + CLKSRC_MII1_RX_CLK, + CLKSRC_MII2_RX_CLK, + CLKSRC_MII3_RX_CLK, + CLKSRC_MII4_RX_CLK, + }; + + /* Payload for packed_buf */ + mii_rx_clk.clksrc = clk_sources[port]; + mii_rx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ + mii_rx_clk.pd = 0; /* Power Down off => enabled */ + sja1105_cgu_mii_control_packing(packed_buf, &mii_rx_clk, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->mii_rx_clk[port], packed_buf, + SJA1105_SIZE_CGU_CMD); +} + +static int +sja1105_cgu_mii_ext_tx_clk_config(struct sja1105_private *priv, int port) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cgu_mii_ctrl mii_ext_tx_clk; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + const int clk_sources[] = { + CLKSRC_IDIV0, + CLKSRC_IDIV1, + CLKSRC_IDIV2, + CLKSRC_IDIV3, + CLKSRC_IDIV4, + }; + + /* Payload for packed_buf */ + mii_ext_tx_clk.clksrc = clk_sources[port]; + mii_ext_tx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ + mii_ext_tx_clk.pd = 0; /* Power Down off => enabled */ + sja1105_cgu_mii_control_packing(packed_buf, &mii_ext_tx_clk, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->mii_ext_tx_clk[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + +static int +sja1105_cgu_mii_ext_rx_clk_config(struct sja1105_private *priv, int port) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cgu_mii_ctrl mii_ext_rx_clk; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + const int clk_sources[] = { + CLKSRC_IDIV0, + CLKSRC_IDIV1, + CLKSRC_IDIV2, + CLKSRC_IDIV3, + CLKSRC_IDIV4, + }; + + /* Payload for packed_buf */ + mii_ext_rx_clk.clksrc = clk_sources[port]; + mii_ext_rx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ + mii_ext_rx_clk.pd = 0; /* Power Down off => enabled */ + sja1105_cgu_mii_control_packing(packed_buf, &mii_ext_rx_clk, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->mii_ext_rx_clk[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + +static int sja1105_mii_clocking_setup(struct sja1105_private *priv, int port, + sja1105_mii_role_t role) +{ + struct device *dev = priv->ds->dev; + int rc; + + dev_dbg(dev, "Configuring MII-%s clocking\n", + (role == XMII_MAC) ? "MAC" : "PHY"); + /* If role is MAC, disable IDIV + * If role is PHY, enable IDIV and configure for 1/1 divider + */ + rc = sja1105_cgu_idiv_config(priv, port, (role == XMII_PHY), 1); + if (rc < 0) + return rc; + + /* Configure CLKSRC of MII_TX_CLK_n + * * If role is MAC, select TX_CLK_n + * * If role is PHY, select IDIV_n + */ + rc = sja1105_cgu_mii_tx_clk_config(priv, port, role); + if (rc < 0) + return rc; + + /* Configure CLKSRC of MII_RX_CLK_n + * Select RX_CLK_n + */ + rc = sja1105_cgu_mii_rx_clk_config(priv, port); + if (rc < 0) + return rc; + + if (role == XMII_PHY) { + /* Per MII spec, the PHY (which is us) drives the TX_CLK pin */ + + /* Configure CLKSRC of EXT_TX_CLK_n + * Select IDIV_n + */ + rc = sja1105_cgu_mii_ext_tx_clk_config(priv, port); + if (rc < 0) + return rc; + + /* Configure CLKSRC of EXT_RX_CLK_n + * Select IDIV_n + */ + rc = sja1105_cgu_mii_ext_rx_clk_config(priv, port); + if (rc < 0) + return rc; + } + return 0; +} + +static void +sja1105_cgu_pll_control_packing(void *buf, struct sja1105_cgu_pll_ctrl *cmd, + enum packing_op op) +{ + const int size = 4; + + sja1105_packing(buf, &cmd->pllclksrc, 28, 24, size, op); + sja1105_packing(buf, &cmd->msel, 23, 16, size, op); + sja1105_packing(buf, &cmd->autoblock, 11, 11, size, op); + sja1105_packing(buf, &cmd->psel, 9, 8, size, op); + sja1105_packing(buf, &cmd->direct, 7, 7, size, op); + sja1105_packing(buf, &cmd->fbsel, 6, 6, size, op); + sja1105_packing(buf, &cmd->bypass, 1, 1, size, op); + sja1105_packing(buf, &cmd->pd, 0, 0, size, op); +} + +static int sja1105_cgu_rgmii_tx_clk_config(struct sja1105_private *priv, + int port, sja1105_speed_t speed) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cgu_mii_ctrl txc; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + int clksrc; + + if (speed == SJA1105_SPEED_1000MBPS) { + clksrc = CLKSRC_PLL0; + } else { + int clk_sources[] = {CLKSRC_IDIV0, CLKSRC_IDIV1, CLKSRC_IDIV2, + CLKSRC_IDIV3, CLKSRC_IDIV4}; + clksrc = clk_sources[port]; + } + + /* RGMII: 125MHz for 1000, 25MHz for 100, 2.5MHz for 10 */ + txc.clksrc = clksrc; + /* Autoblock clk while changing clksrc */ + txc.autoblock = 1; + /* Power Down off => enabled */ + txc.pd = 0; + sja1105_cgu_mii_control_packing(packed_buf, &txc, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->rgmii_tx_clk[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + +/* AGU */ +static void +sja1105_cfg_pad_mii_tx_packing(void *buf, struct sja1105_cfg_pad_mii_tx *cmd, + enum packing_op op) +{ + const int size = 4; + + sja1105_packing(buf, &cmd->d32_os, 28, 27, size, op); + sja1105_packing(buf, &cmd->d32_ipud, 25, 24, size, op); + sja1105_packing(buf, &cmd->d10_os, 20, 19, size, op); + sja1105_packing(buf, &cmd->d10_ipud, 17, 16, size, op); + sja1105_packing(buf, &cmd->ctrl_os, 12, 11, size, op); + sja1105_packing(buf, &cmd->ctrl_ipud, 9, 8, size, op); + sja1105_packing(buf, &cmd->clk_os, 4, 3, size, op); + sja1105_packing(buf, &cmd->clk_ih, 2, 2, size, op); + sja1105_packing(buf, &cmd->clk_ipud, 1, 0, size, op); +} + +static int sja1105_rgmii_cfg_pad_tx_config(struct sja1105_private *priv, + int port) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cfg_pad_mii_tx pad_mii_tx; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + + /* Payload */ + pad_mii_tx.d32_os = 3; /* TXD[3:2] output stage: */ + /* high noise/high speed */ + pad_mii_tx.d10_os = 3; /* TXD[1:0] output stage: */ + /* high noise/high speed */ + pad_mii_tx.d32_ipud = 2; /* TXD[3:2] input stage: */ + /* plain input (default) */ + pad_mii_tx.d10_ipud = 2; /* TXD[1:0] input stage: */ + /* plain input (default) */ + pad_mii_tx.ctrl_os = 3; /* TX_CTL / TX_ER output stage */ + pad_mii_tx.ctrl_ipud = 2; /* TX_CTL / TX_ER input stage (default) */ + pad_mii_tx.clk_os = 3; /* TX_CLK output stage */ + pad_mii_tx.clk_ih = 0; /* TX_CLK input hysteresis (default) */ + pad_mii_tx.clk_ipud = 2; /* TX_CLK input stage (default) */ + sja1105_cfg_pad_mii_tx_packing(packed_buf, &pad_mii_tx, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->rgmii_pad_mii_tx[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + +static int sja1105_rgmii_clocking_setup(struct sja1105_private *priv, int port) +{ + struct device *dev = priv->ds->dev; + struct sja1105_mac_config_entry *mac; + sja1105_speed_t speed; + int rc; + + mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; + speed = mac[port].speed; + + dev_dbg(dev, "Configuring port %d RGMII at speed %dMbps\n", + port, speed); + + switch (speed) { + case SJA1105_SPEED_1000MBPS: + /* 1000Mbps, IDIV disabled (125 MHz) */ + rc = sja1105_cgu_idiv_config(priv, port, false, 1); + break; + case SJA1105_SPEED_100MBPS: + /* 100Mbps, IDIV enabled, divide by 1 (25 MHz) */ + rc = sja1105_cgu_idiv_config(priv, port, true, 1); + break; + case SJA1105_SPEED_10MBPS: + /* 10Mbps, IDIV enabled, divide by 10 (2.5 MHz) */ + rc = sja1105_cgu_idiv_config(priv, port, true, 10); + break; + case SJA1105_SPEED_AUTO: + /* Skip CGU configuration if there is no speed available + * (e.g. link is not established yet) + */ + dev_dbg(dev, "Speed not available, skipping CGU config\n"); + return 0; + default: + rc = -EINVAL; + } + + if (rc < 0) { + dev_err(dev, "Failed to configure idiv\n"); + return rc; + } + rc = sja1105_cgu_rgmii_tx_clk_config(priv, port, speed); + if (rc < 0) { + dev_err(dev, "Failed to configure RGMII Tx clock\n"); + return rc; + } + rc = sja1105_rgmii_cfg_pad_tx_config(priv, port); + if (rc < 0) { + dev_err(dev, "Failed to configure Tx pad registers\n"); + return rc; + } + return 0; +} + +static int sja1105_cgu_rmii_ref_clk_config(struct sja1105_private *priv, + int port) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cgu_mii_ctrl ref_clk; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + const int clk_sources[] = { + CLKSRC_MII0_TX_CLK, + CLKSRC_MII1_TX_CLK, + CLKSRC_MII2_TX_CLK, + CLKSRC_MII3_TX_CLK, + CLKSRC_MII4_TX_CLK, + }; + + /* Payload for packed_buf */ + ref_clk.clksrc = clk_sources[port]; + ref_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ + ref_clk.pd = 0; /* Power Down off => enabled */ + sja1105_cgu_mii_control_packing(packed_buf, &ref_clk, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->rmii_ref_clk[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + +static int +sja1105_cgu_rmii_ext_tx_clk_config(struct sja1105_private *priv, int port) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cgu_mii_ctrl ext_tx_clk; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + + /* Payload for packed_buf */ + ext_tx_clk.clksrc = CLKSRC_PLL1; + ext_tx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ + ext_tx_clk.pd = 0; /* Power Down off => enabled */ + sja1105_cgu_mii_control_packing(packed_buf, &ext_tx_clk, PACK); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, + regs->rmii_ext_tx_clk[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + +static int sja1105_cgu_rmii_pll_config(struct sja1105_private *priv) +{ + const struct sja1105_regs *regs = priv->info->regs; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + struct sja1105_cgu_pll_ctrl pll = {0}; + struct device *dev = priv->ds->dev; + int rc; + + /* PLL1 must be enabled and output 50 Mhz. + * This is done by writing first 0x0A010941 to + * the PLL_1_C register and then deasserting + * power down (PD) 0x0A010940. + */ + + /* Step 1: PLL1 setup for 50Mhz */ + pll.pllclksrc = 0xA; + pll.msel = 0x1; + pll.autoblock = 0x1; + pll.psel = 0x1; + pll.direct = 0x0; + pll.fbsel = 0x1; + pll.bypass = 0x0; + pll.pd = 0x1; + + sja1105_cgu_pll_control_packing(packed_buf, &pll, PACK); + rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rmii_pll1, + packed_buf, SJA1105_SIZE_CGU_CMD); + if (rc < 0) { + dev_err(dev, "failed to configure PLL1 for 50MHz\n"); + return rc; + } + + /* Step 2: Enable PLL1 */ + pll.pd = 0x0; + + sja1105_cgu_pll_control_packing(packed_buf, &pll, PACK); + rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rmii_pll1, + packed_buf, SJA1105_SIZE_CGU_CMD); + if (rc < 0) { + dev_err(dev, "failed to enable PLL1\n"); + return rc; + } + return rc; +} + +static int sja1105_rmii_clocking_setup(struct sja1105_private *priv, int port, + sja1105_mii_role_t role) +{ + struct device *dev = priv->ds->dev; + int rc; + + dev_dbg(dev, "Configuring RMII-%s clocking\n", + (role == XMII_MAC) ? "MAC" : "PHY"); + /* AH1601.pdf chapter 2.5.1. Sources */ + if (role == XMII_MAC) { + /* Configure and enable PLL1 for 50Mhz output */ + rc = sja1105_cgu_rmii_pll_config(priv); + if (rc < 0) + return rc; + } + /* Disable IDIV for this port */ + rc = sja1105_cgu_idiv_config(priv, port, false, 1); + if (rc < 0) + return rc; + /* Source to sink mappings */ + rc = sja1105_cgu_rmii_ref_clk_config(priv, port); + if (rc < 0) + return rc; + if (role == XMII_MAC) { + rc = sja1105_cgu_rmii_ext_tx_clk_config(priv, port); + if (rc < 0) + return rc; + } + return 0; +} + +int sja1105_clocking_setup_port(struct sja1105_private *priv, int port) +{ + struct sja1105_xmii_params_entry *mii; + struct device *dev = priv->ds->dev; + sja1105_phy_interface_t phy_mode; + sja1105_mii_role_t role; + int rc; + + mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries; + + /* RGMII etc */ + phy_mode = mii->xmii_mode[port]; + /* MAC or PHY, for applicable types (not RGMII) */ + role = mii->phy_mac[port]; + + switch (phy_mode) { + case XMII_MODE_MII: + rc = sja1105_mii_clocking_setup(priv, port, role); + break; + case XMII_MODE_RMII: + rc = sja1105_rmii_clocking_setup(priv, port, role); + break; + case XMII_MODE_RGMII: + rc = sja1105_rgmii_clocking_setup(priv, port); + break; + default: + dev_err(dev, "Invalid interface mode specified: %d\n", + phy_mode); + return -EINVAL; + } + if (rc) + dev_err(dev, "Clocking setup for port %d failed: %d\n", + port, rc); + return rc; +} + +int sja1105_clocking_setup(struct sja1105_private *priv) +{ + int port, rc; + + for (port = 0; port < SJA1105_NUM_PORTS; port++) { + rc = sja1105_clocking_setup_port(priv, port); + if (rc < 0) + return rc; + } + return 0; +} diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c new file mode 100644 index 000000000000..d8f145488063 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018-2019, Vladimir Oltean + */ +#include "sja1105.h" + +#define SJA1105_SIZE_DYN_CMD 4 + +#define SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY \ + SJA1105_SIZE_DYN_CMD + +#define SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1105ET_SIZE_L2_LOOKUP_ENTRY) + +#define SJA1105PQRS_SIZE_L2_LOOKUP_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY) + +#define SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + 4 + SJA1105_SIZE_VLAN_LOOKUP_ENTRY) + +#define SJA1105_SIZE_L2_FORWARDING_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_L2_FORWARDING_ENTRY) + +#define SJA1105ET_SIZE_MAC_CONFIG_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY) + +#define SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY) + +#define SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD \ + SJA1105_SIZE_DYN_CMD + +#define SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD \ + SJA1105_SIZE_DYN_CMD + +#define SJA1105_MAX_DYN_CMD_SIZE \ + SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD + +static void +sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->valident, 27, 27, size, op); + /* Hack - The hardware takes the 'index' field within + * struct sja1105_l2_lookup_entry as the index on which this command + * will operate. However it will ignore everything else, so 'index' + * is logically part of command but physically part of entry. + * Populate the 'index' entry field from within the command callback, + * such that our API doesn't need to ask for a full-blown entry + * structure when e.g. a delete is requested. + */ + sja1105_packing(buf, &cmd->index, 29, 20, + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, op); + /* TODO hostcmd */ +} + +static void +sja1105et_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105ET_SIZE_L2_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->valident, 27, 27, size, op); + /* Hack - see comments above. */ + sja1105_packing(buf, &cmd->index, 29, 20, + SJA1105ET_SIZE_L2_LOOKUP_ENTRY, op); +} + +static void +sja1105et_mgmt_route_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105ET_SIZE_L2_LOOKUP_ENTRY; + u64 mgmtroute = 1; + + sja1105et_l2_lookup_cmd_packing(buf, cmd, op); + if (op == PACK) + sja1105_pack(p, &mgmtroute, 26, 26, SJA1105_SIZE_DYN_CMD); +} + +static size_t sja1105et_mgmt_route_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_mgmt_entry *entry = entry_ptr; + const size_t size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY; + + /* UM10944: To specify if a PTP egress timestamp shall be captured on + * each port upon transmission of the frame, the LSB of VLANID in the + * ENTRY field provided by the host must be set. + * Bit 1 of VLANID then specifies the register where the timestamp for + * this port is stored in. + */ + sja1105_packing(buf, &entry->tsreg, 85, 85, size, op); + sja1105_packing(buf, &entry->takets, 84, 84, size, op); + sja1105_packing(buf, &entry->macaddr, 83, 36, size, op); + sja1105_packing(buf, &entry->destports, 35, 31, size, op); + sja1105_packing(buf, &entry->enfport, 30, 30, size, op); + return size; +} + +/* In E/T, entry is at addresses 0x27-0x28. There is a 4 byte gap at 0x29, + * and command is at 0x2a. Similarly in P/Q/R/S there is a 1 register gap + * between entry (0x2d, 0x2e) and command (0x30). + */ +static void +sja1105_vlan_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_VLAN_LOOKUP_ENTRY + 4; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->valident, 27, 27, size, op); + /* Hack - see comments above, applied for 'vlanid' field of + * struct sja1105_vlan_lookup_entry. + */ + sja1105_packing(buf, &cmd->index, 38, 27, + SJA1105_SIZE_VLAN_LOOKUP_ENTRY, op); +} + +static void +sja1105_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_L2_FORWARDING_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->errors, 30, 30, size, op); + sja1105_packing(p, &cmd->rdwrset, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 4, 0, size, op); +} + +static void +sja1105et_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + const int size = SJA1105_SIZE_DYN_CMD; + /* Yup, user manual definitions are reversed */ + u8 *reg1 = buf + 4; + + sja1105_packing(reg1, &cmd->valid, 31, 31, size, op); + sja1105_packing(reg1, &cmd->index, 26, 24, size, op); +} + +static size_t sja1105et_mac_config_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const int size = SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY; + struct sja1105_mac_config_entry *entry = entry_ptr; + /* Yup, user manual definitions are reversed */ + u8 *reg1 = buf + 4; + u8 *reg2 = buf; + + sja1105_packing(reg1, &entry->speed, 30, 29, size, op); + sja1105_packing(reg1, &entry->drpdtag, 23, 23, size, op); + sja1105_packing(reg1, &entry->drpuntag, 22, 22, size, op); + sja1105_packing(reg1, &entry->retag, 21, 21, size, op); + sja1105_packing(reg1, &entry->dyn_learn, 20, 20, size, op); + sja1105_packing(reg1, &entry->egress, 19, 19, size, op); + sja1105_packing(reg1, &entry->ingress, 18, 18, size, op); + sja1105_packing(reg1, &entry->ing_mirr, 17, 17, size, op); + sja1105_packing(reg1, &entry->egr_mirr, 16, 16, size, op); + sja1105_packing(reg1, &entry->vlanprio, 14, 12, size, op); + sja1105_packing(reg1, &entry->vlanid, 11, 0, size, op); + sja1105_packing(reg2, &entry->tp_delin, 31, 16, size, op); + sja1105_packing(reg2, &entry->tp_delout, 15, 0, size, op); + /* MAC configuration table entries which can't be reconfigured: + * top, base, enabled, ifg, maxage, drpnona664 + */ + /* Bogus return value, not used anywhere */ + return 0; +} + +static void +sja1105pqrs_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + const int size = SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY; + u8 *p = buf + SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->errors, 30, 30, size, op); + sja1105_packing(p, &cmd->rdwrset, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 2, 0, size, op); +} + +static void +sja1105et_l2_lookup_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + sja1105_packing(buf, &cmd->valid, 31, 31, + SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD, op); +} + +static size_t +sja1105et_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_lookup_params_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->poly, 7, 0, + SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD, op); + /* Bogus return value, not used anywhere */ + return 0; +} + +static void +sja1105et_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + const int size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD; + + sja1105_packing(buf, &cmd->valid, 31, 31, size, op); + sja1105_packing(buf, &cmd->errors, 30, 30, size, op); +} + +static size_t +sja1105et_general_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_general_params_entry *entry = entry_ptr; + const int size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD; + + sja1105_packing(buf, &entry->mirr_port, 2, 0, size, op); + /* Bogus return value, not used anywhere */ + return 0; +} + +#define OP_READ BIT(0) +#define OP_WRITE BIT(1) +#define OP_DEL BIT(2) + +/* SJA1105E/T: First generation */ +struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { + [BLK_IDX_L2_LOOKUP] = { + .entry_packing = sja1105et_l2_lookup_entry_packing, + .cmd_packing = sja1105et_l2_lookup_cmd_packing, + .access = (OP_READ | OP_WRITE | OP_DEL), + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + .packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD, + .addr = 0x20, + }, + [BLK_IDX_MGMT_ROUTE] = { + .entry_packing = sja1105et_mgmt_route_entry_packing, + .cmd_packing = sja1105et_mgmt_route_cmd_packing, + .access = (OP_READ | OP_WRITE), + .max_entry_count = SJA1105_NUM_PORTS, + .packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD, + .addr = 0x20, + }, + [BLK_IDX_L2_POLICING] = {0}, + [BLK_IDX_VLAN_LOOKUP] = { + .entry_packing = sja1105_vlan_lookup_entry_packing, + .cmd_packing = sja1105_vlan_lookup_cmd_packing, + .access = (OP_WRITE | OP_DEL), + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + .packed_size = SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD, + .addr = 0x27, + }, + [BLK_IDX_L2_FORWARDING] = { + .entry_packing = sja1105_l2_forwarding_entry_packing, + .cmd_packing = sja1105_l2_forwarding_cmd_packing, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + .access = OP_WRITE, + .packed_size = SJA1105_SIZE_L2_FORWARDING_DYN_CMD, + .addr = 0x24, + }, + [BLK_IDX_MAC_CONFIG] = { + .entry_packing = sja1105et_mac_config_entry_packing, + .cmd_packing = sja1105et_mac_config_cmd_packing, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + .access = OP_WRITE, + .packed_size = SJA1105ET_SIZE_MAC_CONFIG_DYN_CMD, + .addr = 0x36, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .entry_packing = sja1105et_l2_lookup_params_entry_packing, + .cmd_packing = sja1105et_l2_lookup_params_cmd_packing, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + .access = OP_WRITE, + .packed_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD, + .addr = 0x38, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = {0}, + [BLK_IDX_GENERAL_PARAMS] = { + .entry_packing = sja1105et_general_params_entry_packing, + .cmd_packing = sja1105et_general_params_cmd_packing, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + .access = OP_WRITE, + .packed_size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD, + .addr = 0x34, + }, + [BLK_IDX_XMII_PARAMS] = {0}, +}; + +/* SJA1105P/Q/R/S: Second generation: TODO */ +struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = { + [BLK_IDX_L2_LOOKUP] = { + .entry_packing = sja1105pqrs_l2_lookup_entry_packing, + .cmd_packing = sja1105pqrs_l2_lookup_cmd_packing, + .access = (OP_READ | OP_WRITE | OP_DEL), + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + .packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD, + .addr = 0x24, + }, + [BLK_IDX_L2_POLICING] = {0}, + [BLK_IDX_VLAN_LOOKUP] = { + .entry_packing = sja1105_vlan_lookup_entry_packing, + .cmd_packing = sja1105_vlan_lookup_cmd_packing, + .access = (OP_READ | OP_WRITE | OP_DEL), + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + .packed_size = SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD, + .addr = 0x2D, + }, + [BLK_IDX_L2_FORWARDING] = { + .entry_packing = sja1105_l2_forwarding_entry_packing, + .cmd_packing = sja1105_l2_forwarding_cmd_packing, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + .access = OP_WRITE, + .packed_size = SJA1105_SIZE_L2_FORWARDING_DYN_CMD, + .addr = 0x2A, + }, + [BLK_IDX_MAC_CONFIG] = { + .entry_packing = sja1105pqrs_mac_config_entry_packing, + .cmd_packing = sja1105pqrs_mac_config_cmd_packing, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + .access = (OP_READ | OP_WRITE), + .packed_size = SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD, + .addr = 0x4B, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .entry_packing = sja1105et_l2_lookup_params_entry_packing, + .cmd_packing = sja1105et_l2_lookup_params_cmd_packing, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + .access = (OP_READ | OP_WRITE), + .packed_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD, + .addr = 0x38, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = {0}, + [BLK_IDX_GENERAL_PARAMS] = { + .entry_packing = sja1105et_general_params_entry_packing, + .cmd_packing = sja1105et_general_params_cmd_packing, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + .access = OP_WRITE, + .packed_size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD, + .addr = 0x34, + }, + [BLK_IDX_XMII_PARAMS] = {0}, +}; + +int sja1105_dynamic_config_read(struct sja1105_private *priv, + enum sja1105_blk_idx blk_idx, + int index, void *entry) +{ + const struct sja1105_dynamic_table_ops *ops; + struct sja1105_dyn_cmd cmd = {0}; + /* SPI payload buffer */ + u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {0}; + int retries = 3; + int rc; + + if (blk_idx >= BLK_IDX_MAX_DYN) + return -ERANGE; + + ops = &priv->info->dyn_ops[blk_idx]; + + if (index >= ops->max_entry_count) + return -ERANGE; + if (!(ops->access & OP_READ)) + return -EOPNOTSUPP; + if (ops->packed_size > SJA1105_MAX_DYN_CMD_SIZE) + return -ERANGE; + if (!ops->cmd_packing) + return -EOPNOTSUPP; + if (!ops->entry_packing) + return -EOPNOTSUPP; + + cmd.valid = true; /* Trigger action on table entry */ + cmd.rdwrset = SPI_READ; /* Action is read */ + cmd.index = index; + ops->cmd_packing(packed_buf, &cmd, PACK); + + /* Send SPI write operation: read config table entry */ + rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, ops->addr, + packed_buf, ops->packed_size); + if (rc < 0) + return rc; + + /* Loop until we have confirmation that hardware has finished + * processing the command and has cleared the VALID field + */ + do { + memset(packed_buf, 0, ops->packed_size); + + /* Retrieve the read operation's result */ + rc = sja1105_spi_send_packed_buf(priv, SPI_READ, ops->addr, + packed_buf, ops->packed_size); + if (rc < 0) + return rc; + + cmd = (struct sja1105_dyn_cmd) {0}; + ops->cmd_packing(packed_buf, &cmd, UNPACK); + /* UM10944: [valident] will always be found cleared + * during a read access with MGMTROUTE set. + * So don't error out in that case. + */ + if (!cmd.valident && blk_idx != BLK_IDX_MGMT_ROUTE) + return -EINVAL; + cpu_relax(); + } while (cmd.valid && --retries); + + if (cmd.valid) + return -ETIMEDOUT; + + /* Don't dereference possibly NULL pointer - maybe caller + * only wanted to see whether the entry existed or not. + */ + if (entry) + ops->entry_packing(packed_buf, entry, UNPACK); + return 0; +} + +int sja1105_dynamic_config_write(struct sja1105_private *priv, + enum sja1105_blk_idx blk_idx, + int index, void *entry, bool keep) +{ + const struct sja1105_dynamic_table_ops *ops; + struct sja1105_dyn_cmd cmd = {0}; + /* SPI payload buffer */ + u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {0}; + int rc; + + if (blk_idx >= BLK_IDX_MAX_DYN) + return -ERANGE; + + ops = &priv->info->dyn_ops[blk_idx]; + + if (index >= ops->max_entry_count) + return -ERANGE; + if (!(ops->access & OP_WRITE)) + return -EOPNOTSUPP; + if (!keep && !(ops->access & OP_DEL)) + return -EOPNOTSUPP; + if (ops->packed_size > SJA1105_MAX_DYN_CMD_SIZE) + return -ERANGE; + + cmd.valident = keep; /* If false, deletes entry */ + cmd.valid = true; /* Trigger action on table entry */ + cmd.rdwrset = SPI_WRITE; /* Action is write */ + cmd.index = index; + + if (!ops->cmd_packing) + return -EOPNOTSUPP; + ops->cmd_packing(packed_buf, &cmd, PACK); + + if (!ops->entry_packing) + return -EOPNOTSUPP; + /* Don't dereference potentially NULL pointer if just + * deleting a table entry is what was requested. For cases + * where 'index' field is physically part of entry structure, + * and needed here, we deal with that in the cmd_packing callback. + */ + if (keep) + ops->entry_packing(packed_buf, entry, PACK); + + /* Send SPI write operation: read config table entry */ + rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, ops->addr, + packed_buf, ops->packed_size); + if (rc < 0) + return rc; + + cmd = (struct sja1105_dyn_cmd) {0}; + ops->cmd_packing(packed_buf, &cmd, UNPACK); + if (cmd.errors) + return -EINVAL; + + return 0; +} diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h new file mode 100644 index 000000000000..77be59546a55 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2019, Vladimir Oltean + */ +#ifndef _SJA1105_DYNAMIC_CONFIG_H +#define _SJA1105_DYNAMIC_CONFIG_H + +#include "sja1105.h" +#include + +struct sja1105_dyn_cmd { + u64 valid; + u64 rdwrset; + u64 errors; + u64 valident; + u64 index; +}; + +struct sja1105_dynamic_table_ops { + /* This returns size_t just to keep same prototype as the + * static config ops, of which we are reusing some functions. + */ + size_t (*entry_packing)(void *buf, void *entry_ptr, enum packing_op op); + void (*cmd_packing)(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op); + size_t max_entry_count; + size_t packed_size; + u64 addr; + u8 access; +}; + +struct sja1105_mgmt_entry { + u64 tsreg; + u64 takets; + u64 macaddr; + u64 destports; + u64 enfport; + u64 index; +}; + +extern struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN]; +extern struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN]; + +#endif diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c new file mode 100644 index 000000000000..7d2ad2db0d88 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -0,0 +1,928 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Sensor-Technik Wiedemann GmbH + * Copyright (c) 2018-2019, Vladimir Oltean + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "sja1105.h" + +static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len, + unsigned int startup_delay) +{ + gpiod_set_value_cansleep(gpio, 1); + /* Wait for minimum reset pulse length */ + msleep(pulse_len); + gpiod_set_value_cansleep(gpio, 0); + /* Wait until chip is ready after reset */ + msleep(startup_delay); +} + +static void +sja1105_port_allow_traffic(struct sja1105_l2_forwarding_entry *l2_fwd, + int from, int to, bool allow) +{ + if (allow) { + l2_fwd[from].bc_domain |= BIT(to); + l2_fwd[from].reach_port |= BIT(to); + l2_fwd[from].fl_domain |= BIT(to); + } else { + l2_fwd[from].bc_domain &= ~BIT(to); + l2_fwd[from].reach_port &= ~BIT(to); + l2_fwd[from].fl_domain &= ~BIT(to); + } +} + +/* Structure used to temporarily transport device tree + * settings into sja1105_setup + */ +struct sja1105_dt_port { + phy_interface_t phy_mode; + sja1105_mii_role_t role; +}; + +static int sja1105_init_mac_settings(struct sja1105_private *priv) +{ + struct sja1105_mac_config_entry default_mac = { + /* Enable all 8 priority queues on egress. + * Every queue i holds top[i] - base[i] frames. + * Sum of top[i] - base[i] is 511 (max hardware limit). + */ + .top = {0x3F, 0x7F, 0xBF, 0xFF, 0x13F, 0x17F, 0x1BF, 0x1FF}, + .base = {0x0, 0x40, 0x80, 0xC0, 0x100, 0x140, 0x180, 0x1C0}, + .enabled = {true, true, true, true, true, true, true, true}, + /* Keep standard IFG of 12 bytes on egress. */ + .ifg = 0, + /* Always put the MAC speed in automatic mode, where it can be + * retrieved from the PHY object through phylib and + * sja1105_adjust_port_config. + */ + .speed = SJA1105_SPEED_AUTO, + /* No static correction for 1-step 1588 events */ + .tp_delin = 0, + .tp_delout = 0, + /* Disable aging for critical TTEthernet traffic */ + .maxage = 0xFF, + /* Internal VLAN (pvid) to apply to untagged ingress */ + .vlanprio = 0, + .vlanid = 0, + .ing_mirr = false, + .egr_mirr = false, + /* Don't drop traffic with other EtherType than ETH_P_IP */ + .drpnona664 = false, + /* Don't drop double-tagged traffic */ + .drpdtag = false, + /* Don't drop untagged traffic */ + .drpuntag = false, + /* Don't retag 802.1p (VID 0) traffic with the pvid */ + .retag = false, + /* Enable learning and I/O on user ports by default. */ + .dyn_learn = true, + .egress = false, + .ingress = false, + }; + struct sja1105_mac_config_entry *mac; + struct sja1105_table *table; + int i; + + table = &priv->static_config.tables[BLK_IDX_MAC_CONFIG]; + + /* Discard previous MAC Configuration Table */ + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(SJA1105_NUM_PORTS, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + /* Override table based on phylib DT bindings */ + table->entry_count = SJA1105_NUM_PORTS; + + mac = table->entries; + + for (i = 0; i < SJA1105_NUM_PORTS; i++) + mac[i] = default_mac; + + return 0; +} + +static int sja1105_init_mii_settings(struct sja1105_private *priv, + struct sja1105_dt_port *ports) +{ + struct device *dev = &priv->spidev->dev; + struct sja1105_xmii_params_entry *mii; + struct sja1105_table *table; + int i; + + table = &priv->static_config.tables[BLK_IDX_XMII_PARAMS]; + + /* Discard previous xMII Mode Parameters Table */ + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(SJA1105_MAX_XMII_PARAMS_COUNT, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + /* Override table based on phylib DT bindings */ + table->entry_count = SJA1105_MAX_XMII_PARAMS_COUNT; + + mii = table->entries; + + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + switch (ports[i].phy_mode) { + case PHY_INTERFACE_MODE_MII: + mii->xmii_mode[i] = XMII_MODE_MII; + break; + case PHY_INTERFACE_MODE_RMII: + mii->xmii_mode[i] = XMII_MODE_RMII; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + mii->xmii_mode[i] = XMII_MODE_RGMII; + break; + default: + dev_err(dev, "Unsupported PHY mode %s!\n", + phy_modes(ports[i].phy_mode)); + } + + mii->phy_mac[i] = ports[i].role; + } + return 0; +} + +static int sja1105_init_static_fdb(struct sja1105_private *priv) +{ + struct sja1105_table *table; + + table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP]; + + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + return 0; +} + +static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) +{ + struct sja1105_table *table; + struct sja1105_l2_lookup_params_entry default_l2_lookup_params = { + /* TODO Learned FDB entries are never forgotten */ + .maxage = 0, + /* All entries within a FDB bin are available for learning */ + .dyn_tbsz = SJA1105ET_FDB_BIN_SIZE, + /* 2^8 + 2^5 + 2^3 + 2^2 + 2^1 + 1 in Koopman notation */ + .poly = 0x97, + /* This selects between Independent VLAN Learning (IVL) and + * Shared VLAN Learning (SVL) + */ + .shared_learn = false, + /* Don't discard management traffic based on ENFPORT - + * we don't perform SMAC port enforcement anyway, so + * what we are setting here doesn't matter. + */ + .no_enf_hostprt = false, + /* Don't learn SMAC for mac_fltres1 and mac_fltres0. + * Maybe correlate with no_linklocal_learn from bridge driver? + */ + .no_mgmt_learn = true, + }; + + table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS]; + + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + table->entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT; + + /* This table only has a single entry */ + ((struct sja1105_l2_lookup_params_entry *)table->entries)[0] = + default_l2_lookup_params; + + return 0; +} + +static int sja1105_init_static_vlan(struct sja1105_private *priv) +{ + struct sja1105_table *table; + struct sja1105_vlan_lookup_entry pvid = { + .ving_mirr = 0, + .vegr_mirr = 0, + .vmemb_port = 0, + .vlan_bc = 0, + .tag_port = 0, + .vlanid = 0, + }; + int i; + + table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; + + /* The static VLAN table will only contain the initial pvid of 0. + */ + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(1, table->ops->unpacked_entry_size, + GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + table->entry_count = 1; + + /* VLAN ID 0: all DT-defined ports are members; no restrictions on + * forwarding; always transmit priority-tagged frames as untagged. + */ + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + pvid.vmemb_port |= BIT(i); + pvid.vlan_bc |= BIT(i); + pvid.tag_port &= ~BIT(i); + } + + ((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid; + return 0; +} + +static int sja1105_init_l2_forwarding(struct sja1105_private *priv) +{ + struct sja1105_l2_forwarding_entry *l2fwd; + struct sja1105_table *table; + int i, j; + + table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING]; + + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_COUNT, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + table->entry_count = SJA1105_MAX_L2_FORWARDING_COUNT; + + l2fwd = table->entries; + + /* First 5 entries define the forwarding rules */ + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + unsigned int upstream = dsa_upstream_port(priv->ds, i); + + for (j = 0; j < SJA1105_NUM_TC; j++) + l2fwd[i].vlan_pmap[j] = j; + + if (i == upstream) + continue; + + sja1105_port_allow_traffic(l2fwd, i, upstream, true); + sja1105_port_allow_traffic(l2fwd, upstream, i, true); + } + /* Next 8 entries define VLAN PCP mapping from ingress to egress. + * Create a one-to-one mapping. + */ + for (i = 0; i < SJA1105_NUM_TC; i++) + for (j = 0; j < SJA1105_NUM_PORTS; j++) + l2fwd[SJA1105_NUM_PORTS + i].vlan_pmap[j] = i; + + return 0; +} + +static int sja1105_init_l2_forwarding_params(struct sja1105_private *priv) +{ + struct sja1105_l2_forwarding_params_entry default_l2fwd_params = { + /* Disallow dynamic reconfiguration of vlan_pmap */ + .max_dynp = 0, + /* Use a single memory partition for all ingress queues */ + .part_spc = { SJA1105_MAX_FRAME_MEMORY, 0, 0, 0, 0, 0, 0, 0 }, + }; + struct sja1105_table *table; + + table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS]; + + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + table->entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT; + + /* This table only has a single entry */ + ((struct sja1105_l2_forwarding_params_entry *)table->entries)[0] = + default_l2fwd_params; + + return 0; +} + +static int sja1105_init_general_params(struct sja1105_private *priv) +{ + struct sja1105_general_params_entry default_general_params = { + /* Disallow dynamic changing of the mirror port */ + .mirr_ptacu = 0, + .switchid = priv->ds->index, + /* Priority queue for link-local frames trapped to CPU */ + .hostprio = 0, + .mac_fltres1 = SJA1105_LINKLOCAL_FILTER_A, + .mac_flt1 = SJA1105_LINKLOCAL_FILTER_A_MASK, + .incl_srcpt1 = true, + .send_meta1 = false, + .mac_fltres0 = SJA1105_LINKLOCAL_FILTER_B, + .mac_flt0 = SJA1105_LINKLOCAL_FILTER_B_MASK, + .incl_srcpt0 = true, + .send_meta0 = false, + /* The destination for traffic matching mac_fltres1 and + * mac_fltres0 on all ports except host_port. Such traffic + * receieved on host_port itself would be dropped, except + * by installing a temporary 'management route' + */ + .host_port = dsa_upstream_port(priv->ds, 0), + /* Same as host port */ + .mirr_port = dsa_upstream_port(priv->ds, 0), + /* Link-local traffic received on casc_port will be forwarded + * to host_port without embedding the source port and device ID + * info in the destination MAC address (presumably because it + * is a cascaded port and a downstream SJA switch already did + * that). Default to an invalid port (to disable the feature) + * and overwrite this if we find any DSA (cascaded) ports. + */ + .casc_port = SJA1105_NUM_PORTS, + /* No TTEthernet */ + .vllupformat = 0, + .vlmarker = 0, + .vlmask = 0, + /* Only update correctionField for 1-step PTP (L2 transport) */ + .ignore2stf = 0, + .tpid = ETH_P_8021Q, + .tpid2 = ETH_P_8021Q, + }; + struct sja1105_table *table; + int i; + + for (i = 0; i < SJA1105_NUM_PORTS; i++) + if (dsa_is_dsa_port(priv->ds, i)) + default_general_params.casc_port = i; + + table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; + + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(SJA1105_MAX_GENERAL_PARAMS_COUNT, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + table->entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT; + + /* This table only has a single entry */ + ((struct sja1105_general_params_entry *)table->entries)[0] = + default_general_params; + + return 0; +} + +#define SJA1105_RATE_MBPS(speed) (((speed) * 64000) / 1000) + +static inline void +sja1105_setup_policer(struct sja1105_l2_policing_entry *policing, + int index) +{ + policing[index].sharindx = index; + policing[index].smax = 65535; /* Burst size in bytes */ + policing[index].rate = SJA1105_RATE_MBPS(1000); + policing[index].maxlen = ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN; + policing[index].partition = 0; +} + +static int sja1105_init_l2_policing(struct sja1105_private *priv) +{ + struct sja1105_l2_policing_entry *policing; + struct sja1105_table *table; + int i, j, k; + + table = &priv->static_config.tables[BLK_IDX_L2_POLICING]; + + /* Discard previous L2 Policing Table */ + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(SJA1105_MAX_L2_POLICING_COUNT, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + table->entry_count = SJA1105_MAX_L2_POLICING_COUNT; + + policing = table->entries; + + /* k sweeps through all unicast policers (0-39). + * bcast sweeps through policers 40-44. + */ + for (i = 0, k = 0; i < SJA1105_NUM_PORTS; i++) { + int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + i; + + for (j = 0; j < SJA1105_NUM_TC; j++, k++) + sja1105_setup_policer(policing, k); + + /* Set up this port's policer for broadcast traffic */ + sja1105_setup_policer(policing, bcast); + } + return 0; +} + +static int sja1105_static_config_load(struct sja1105_private *priv, + struct sja1105_dt_port *ports) +{ + int rc; + + sja1105_static_config_free(&priv->static_config); + rc = sja1105_static_config_init(&priv->static_config, + priv->info->static_ops, + priv->info->device_id); + if (rc) + return rc; + + /* Build static configuration */ + rc = sja1105_init_mac_settings(priv); + if (rc < 0) + return rc; + rc = sja1105_init_mii_settings(priv, ports); + if (rc < 0) + return rc; + rc = sja1105_init_static_fdb(priv); + if (rc < 0) + return rc; + rc = sja1105_init_static_vlan(priv); + if (rc < 0) + return rc; + rc = sja1105_init_l2_lookup_params(priv); + if (rc < 0) + return rc; + rc = sja1105_init_l2_forwarding(priv); + if (rc < 0) + return rc; + rc = sja1105_init_l2_forwarding_params(priv); + if (rc < 0) + return rc; + rc = sja1105_init_l2_policing(priv); + if (rc < 0) + return rc; + rc = sja1105_init_general_params(priv); + if (rc < 0) + return rc; + + /* Send initial configuration to hardware via SPI */ + return sja1105_static_config_upload(priv); +} + +static int sja1105_parse_ports_node(struct sja1105_private *priv, + struct sja1105_dt_port *ports, + struct device_node *ports_node) +{ + struct device *dev = &priv->spidev->dev; + struct device_node *child; + + for_each_child_of_node(ports_node, child) { + struct device_node *phy_node; + int phy_mode; + u32 index; + + /* Get switch port number from DT */ + if (of_property_read_u32(child, "reg", &index) < 0) { + dev_err(dev, "Port number not defined in device tree " + "(property \"reg\")\n"); + return -ENODEV; + } + + /* Get PHY mode from DT */ + phy_mode = of_get_phy_mode(child); + if (phy_mode < 0) { + dev_err(dev, "Failed to read phy-mode or " + "phy-interface-type property for port %d\n", + index); + return -ENODEV; + } + ports[index].phy_mode = phy_mode; + + phy_node = of_parse_phandle(child, "phy-handle", 0); + if (!phy_node) { + if (!of_phy_is_fixed_link(child)) { + dev_err(dev, "phy-handle or fixed-link " + "properties missing!\n"); + return -ENODEV; + } + /* phy-handle is missing, but fixed-link isn't. + * So it's a fixed link. Default to PHY role. + */ + ports[index].role = XMII_PHY; + } else { + /* phy-handle present => put port in MAC role */ + ports[index].role = XMII_MAC; + of_node_put(phy_node); + } + + /* The MAC/PHY role can be overridden with explicit bindings */ + if (of_property_read_bool(child, "sja1105,role-mac")) + ports[index].role = XMII_MAC; + else if (of_property_read_bool(child, "sja1105,role-phy")) + ports[index].role = XMII_PHY; + } + + return 0; +} + +static int sja1105_parse_dt(struct sja1105_private *priv, + struct sja1105_dt_port *ports) +{ + struct device *dev = &priv->spidev->dev; + struct device_node *switch_node = dev->of_node; + struct device_node *ports_node; + int rc; + + ports_node = of_get_child_by_name(switch_node, "ports"); + if (!ports_node) { + dev_err(dev, "Incorrect bindings: absent \"ports\" node\n"); + return -ENODEV; + } + + rc = sja1105_parse_ports_node(priv, ports, ports_node); + of_node_put(ports_node); + + return rc; +} + +/* Convert back and forth MAC speed from Mbps to SJA1105 encoding */ +static int sja1105_speed[] = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 10, + [SJA1105_SPEED_100MBPS] = 100, + [SJA1105_SPEED_1000MBPS] = 1000, +}; + +static sja1105_speed_t sja1105_get_speed_cfg(unsigned int speed_mbps) +{ + int i; + + for (i = SJA1105_SPEED_AUTO; i <= SJA1105_SPEED_1000MBPS; i++) + if (sja1105_speed[i] == speed_mbps) + return i; + return -EINVAL; +} + +/* Set link speed and enable/disable traffic I/O in the MAC configuration + * for a specific port. + * + * @speed_mbps: If 0, leave the speed unchanged, else adapt MAC to PHY speed. + * @enabled: Manage Rx and Tx settings for this port. Overrides the static + * configuration settings. + */ +static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, + int speed_mbps, bool enabled) +{ + struct sja1105_xmii_params_entry *mii; + struct sja1105_mac_config_entry *mac; + struct device *dev = priv->ds->dev; + sja1105_phy_interface_t phy_mode; + sja1105_speed_t speed; + int rc; + + mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries; + mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; + + speed = sja1105_get_speed_cfg(speed_mbps); + if (speed_mbps && speed < 0) { + dev_err(dev, "Invalid speed %iMbps\n", speed_mbps); + return -EINVAL; + } + + /* If requested, overwrite SJA1105_SPEED_AUTO from the static MAC + * configuration table, since this will be used for the clocking setup, + * and we no longer need to store it in the static config (already told + * hardware we want auto during upload phase). + */ + if (speed_mbps) + mac[port].speed = speed; + else + mac[port].speed = SJA1105_SPEED_AUTO; + + /* On P/Q/R/S, one can read from the device via the MAC reconfiguration + * tables. On E/T, MAC reconfig tables are not readable, only writable. + * We have to *know* what the MAC looks like. For the sake of keeping + * the code common, we'll use the static configuration tables as a + * reasonable approximation for both E/T and P/Q/R/S. + */ + mac[port].ingress = enabled; + mac[port].egress = enabled; + + /* Write to the dynamic reconfiguration tables */ + rc = sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, + port, &mac[port], true); + if (rc < 0) { + dev_err(dev, "Failed to write MAC config: %d\n", rc); + return rc; + } + + /* Reconfigure the PLLs for the RGMII interfaces (required 125 MHz at + * gigabit, 25 MHz at 100 Mbps and 2.5 MHz at 10 Mbps). For MII and + * RMII no change of the clock setup is required. Actually, changing + * the clock setup does interrupt the clock signal for a certain time + * which causes trouble for all PHYs relying on this signal. + */ + if (!enabled) + return 0; + + phy_mode = mii->xmii_mode[port]; + if (phy_mode != XMII_MODE_RGMII) + return 0; + + return sja1105_clocking_setup_port(priv, port); +} + +static void sja1105_adjust_link(struct dsa_switch *ds, int port, + struct phy_device *phydev) +{ + struct sja1105_private *priv = ds->priv; + + if (!phydev->link) + sja1105_adjust_port_config(priv, port, 0, false); + else + sja1105_adjust_port_config(priv, port, phydev->speed, true); +} + +static int sja1105_bridge_member(struct dsa_switch *ds, int port, + struct net_device *br, bool member) +{ + struct sja1105_l2_forwarding_entry *l2_fwd; + struct sja1105_private *priv = ds->priv; + int i, rc; + + l2_fwd = priv->static_config.tables[BLK_IDX_L2_FORWARDING].entries; + + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + /* Add this port to the forwarding matrix of the + * other ports in the same bridge, and viceversa. + */ + if (!dsa_is_user_port(ds, i)) + continue; + /* For the ports already under the bridge, only one thing needs + * to be done, and that is to add this port to their + * reachability domain. So we can perform the SPI write for + * them immediately. However, for this port itself (the one + * that is new to the bridge), we need to add all other ports + * to its reachability domain. So we do that incrementally in + * this loop, and perform the SPI write only at the end, once + * the domain contains all other bridge ports. + */ + if (i == port) + continue; + if (dsa_to_port(ds, i)->bridge_dev != br) + continue; + sja1105_port_allow_traffic(l2_fwd, i, port, member); + sja1105_port_allow_traffic(l2_fwd, port, i, member); + + rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_FORWARDING, + i, &l2_fwd[i], true); + if (rc < 0) + return rc; + } + + return sja1105_dynamic_config_write(priv, BLK_IDX_L2_FORWARDING, + port, &l2_fwd[port], true); +} + +static int sja1105_bridge_join(struct dsa_switch *ds, int port, + struct net_device *br) +{ + return sja1105_bridge_member(ds, port, br, true); +} + +static void sja1105_bridge_leave(struct dsa_switch *ds, int port, + struct net_device *br) +{ + sja1105_bridge_member(ds, port, br, false); +} + +static enum dsa_tag_protocol +sja1105_get_tag_protocol(struct dsa_switch *ds, int port) +{ + return DSA_TAG_PROTO_NONE; +} + +/* The programming model for the SJA1105 switch is "all-at-once" via static + * configuration tables. Some of these can be dynamically modified at runtime, + * but not the xMII mode parameters table. + * Furthermode, some PHYs may not have crystals for generating their clocks + * (e.g. RMII). Instead, their 50MHz clock is supplied via the SJA1105 port's + * ref_clk pin. So port clocking needs to be initialized early, before + * connecting to PHYs is attempted, otherwise they won't respond through MDIO. + * Setting correct PHY link speed does not matter now. + * But dsa_slave_phy_setup is called later than sja1105_setup, so the PHY + * bindings are not yet parsed by DSA core. We need to parse early so that we + * can populate the xMII mode parameters table. + */ +static int sja1105_setup(struct dsa_switch *ds) +{ + struct sja1105_dt_port ports[SJA1105_NUM_PORTS]; + struct sja1105_private *priv = ds->priv; + int rc; + + rc = sja1105_parse_dt(priv, ports); + if (rc < 0) { + dev_err(ds->dev, "Failed to parse DT: %d\n", rc); + return rc; + } + /* Create and send configuration down to device */ + rc = sja1105_static_config_load(priv, ports); + if (rc < 0) { + dev_err(ds->dev, "Failed to load static config: %d\n", rc); + return rc; + } + /* Configure the CGU (PHY link modes and speeds) */ + rc = sja1105_clocking_setup(priv); + if (rc < 0) { + dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc); + return rc; + } + + return 0; +} + +static const struct dsa_switch_ops sja1105_switch_ops = { + .get_tag_protocol = sja1105_get_tag_protocol, + .setup = sja1105_setup, + .adjust_link = sja1105_adjust_link, + .port_bridge_join = sja1105_bridge_join, + .port_bridge_leave = sja1105_bridge_leave, +}; + +static int sja1105_check_device_id(struct sja1105_private *priv) +{ + const struct sja1105_regs *regs = priv->info->regs; + u8 prod_id[SJA1105_SIZE_DEVICE_ID] = {0}; + struct device *dev = &priv->spidev->dev; + u64 device_id; + u64 part_no; + int rc; + + rc = sja1105_spi_send_int(priv, SPI_READ, regs->device_id, + &device_id, SJA1105_SIZE_DEVICE_ID); + if (rc < 0) + return rc; + + if (device_id != priv->info->device_id) { + dev_err(dev, "Expected device ID 0x%llx but read 0x%llx\n", + priv->info->device_id, device_id); + return -ENODEV; + } + + rc = sja1105_spi_send_packed_buf(priv, SPI_READ, regs->prod_id, + prod_id, SJA1105_SIZE_DEVICE_ID); + if (rc < 0) + return rc; + + sja1105_unpack(prod_id, &part_no, 19, 4, SJA1105_SIZE_DEVICE_ID); + + if (part_no != priv->info->part_no) { + dev_err(dev, "Expected part number 0x%llx but read 0x%llx\n", + priv->info->part_no, part_no); + return -ENODEV; + } + + return 0; +} + +static int sja1105_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct sja1105_private *priv; + struct dsa_switch *ds; + int rc; + + if (!dev->of_node) { + dev_err(dev, "No DTS bindings for SJA1105 driver\n"); + return -EINVAL; + } + + priv = devm_kzalloc(dev, sizeof(struct sja1105_private), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + /* Configure the optional reset pin and bring up switch */ + priv->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(priv->reset_gpio)) + dev_dbg(dev, "reset-gpios not defined, ignoring\n"); + else + sja1105_hw_reset(priv->reset_gpio, 1, 1); + + /* Populate our driver private structure (priv) based on + * the device tree node that was probed (spi) + */ + priv->spidev = spi; + spi_set_drvdata(spi, priv); + + /* Configure the SPI bus */ + spi->bits_per_word = 8; + rc = spi_setup(spi); + if (rc < 0) { + dev_err(dev, "Could not init SPI\n"); + return rc; + } + + priv->info = of_device_get_match_data(dev); + + /* Detect hardware device */ + rc = sja1105_check_device_id(priv); + if (rc < 0) { + dev_err(dev, "Device ID check failed: %d\n", rc); + return rc; + } + + dev_info(dev, "Probed switch chip: %s\n", priv->info->name); + + ds = dsa_switch_alloc(dev, SJA1105_NUM_PORTS); + if (!ds) + return -ENOMEM; + + ds->ops = &sja1105_switch_ops; + ds->priv = priv; + priv->ds = ds; + + return dsa_register_switch(priv->ds); +} + +static int sja1105_remove(struct spi_device *spi) +{ + struct sja1105_private *priv = spi_get_drvdata(spi); + + dsa_unregister_switch(priv->ds); + sja1105_static_config_free(&priv->static_config); + return 0; +} + +static const struct of_device_id sja1105_dt_ids[] = { + { .compatible = "nxp,sja1105e", .data = &sja1105e_info }, + { .compatible = "nxp,sja1105t", .data = &sja1105t_info }, + { .compatible = "nxp,sja1105p", .data = &sja1105p_info }, + { .compatible = "nxp,sja1105q", .data = &sja1105q_info }, + { .compatible = "nxp,sja1105r", .data = &sja1105r_info }, + { .compatible = "nxp,sja1105s", .data = &sja1105s_info }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, sja1105_dt_ids); + +static struct spi_driver sja1105_driver = { + .driver = { + .name = "sja1105", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(sja1105_dt_ids), + }, + .probe = sja1105_probe, + .remove = sja1105_remove, +}; + +module_spi_driver(sja1105_driver); + +MODULE_AUTHOR("Vladimir Oltean "); +MODULE_AUTHOR("Georg Waibel "); +MODULE_DESCRIPTION("SJA1105 Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c new file mode 100644 index 000000000000..07890bbf40f8 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -0,0 +1,553 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (c) 2016-2018, NXP Semiconductors + * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH + * Copyright (c) 2018-2019, Vladimir Oltean + */ +#include +#include +#include "sja1105.h" + +#define SJA1105_SIZE_RESET_CMD 4 +#define SJA1105_SIZE_SPI_MSG_HEADER 4 +#define SJA1105_SIZE_SPI_MSG_MAXLEN (64 * 4) +#define SJA1105_SIZE_SPI_TRANSFER_MAX \ + (SJA1105_SIZE_SPI_MSG_HEADER + SJA1105_SIZE_SPI_MSG_MAXLEN) + +static int sja1105_spi_transfer(const struct sja1105_private *priv, + const void *tx, void *rx, int size) +{ + struct spi_device *spi = priv->spidev; + struct spi_transfer transfer = { + .tx_buf = tx, + .rx_buf = rx, + .len = size, + }; + struct spi_message msg; + int rc; + + if (size > SJA1105_SIZE_SPI_TRANSFER_MAX) { + dev_err(&spi->dev, "SPI message (%d) longer than max of %d\n", + size, SJA1105_SIZE_SPI_TRANSFER_MAX); + return -EMSGSIZE; + } + + spi_message_init(&msg); + spi_message_add_tail(&transfer, &msg); + + rc = spi_sync(spi, &msg); + if (rc < 0) { + dev_err(&spi->dev, "SPI transfer failed: %d\n", rc); + return rc; + } + + return rc; +} + +static void +sja1105_spi_message_pack(void *buf, const struct sja1105_spi_message *msg) +{ + const int size = SJA1105_SIZE_SPI_MSG_HEADER; + + memset(buf, 0, size); + + sja1105_pack(buf, &msg->access, 31, 31, size); + sja1105_pack(buf, &msg->read_count, 30, 25, size); + sja1105_pack(buf, &msg->address, 24, 4, size); +} + +/* If @rw is: + * - SPI_WRITE: creates and sends an SPI write message at absolute + * address reg_addr, taking size_bytes from *packed_buf + * - SPI_READ: creates and sends an SPI read message from absolute + * address reg_addr, writing size_bytes into *packed_buf + * + * This function should only be called if it is priorly known that + * @size_bytes is smaller than SIZE_SPI_MSG_MAXLEN. Larger packed buffers + * are chunked in smaller pieces by sja1105_spi_send_long_packed_buf below. + */ +int sja1105_spi_send_packed_buf(const struct sja1105_private *priv, + sja1105_spi_rw_mode_t rw, u64 reg_addr, + void *packed_buf, size_t size_bytes) +{ + u8 tx_buf[SJA1105_SIZE_SPI_TRANSFER_MAX] = {0}; + u8 rx_buf[SJA1105_SIZE_SPI_TRANSFER_MAX] = {0}; + const int msg_len = size_bytes + SJA1105_SIZE_SPI_MSG_HEADER; + struct sja1105_spi_message msg = {0}; + int rc; + + if (msg_len > SJA1105_SIZE_SPI_TRANSFER_MAX) + return -ERANGE; + + msg.access = rw; + msg.address = reg_addr; + if (rw == SPI_READ) + msg.read_count = size_bytes / 4; + + sja1105_spi_message_pack(tx_buf, &msg); + + if (rw == SPI_WRITE) + memcpy(tx_buf + SJA1105_SIZE_SPI_MSG_HEADER, + packed_buf, size_bytes); + + rc = sja1105_spi_transfer(priv, tx_buf, rx_buf, msg_len); + if (rc < 0) + return rc; + + if (rw == SPI_READ) + memcpy(packed_buf, rx_buf + SJA1105_SIZE_SPI_MSG_HEADER, + size_bytes); + + return 0; +} + +/* If @rw is: + * - SPI_WRITE: creates and sends an SPI write message at absolute + * address reg_addr, taking size_bytes from *packed_buf + * - SPI_READ: creates and sends an SPI read message from absolute + * address reg_addr, writing size_bytes into *packed_buf + * + * The u64 *value is unpacked, meaning that it's stored in the native + * CPU endianness and directly usable by software running on the core. + * + * This is a wrapper around sja1105_spi_send_packed_buf(). + */ +int sja1105_spi_send_int(const struct sja1105_private *priv, + sja1105_spi_rw_mode_t rw, u64 reg_addr, + u64 *value, u64 size_bytes) +{ + u8 packed_buf[SJA1105_SIZE_SPI_MSG_MAXLEN]; + int rc; + + if (size_bytes > SJA1105_SIZE_SPI_MSG_MAXLEN) + return -ERANGE; + + if (rw == SPI_WRITE) + sja1105_pack(packed_buf, value, 8 * size_bytes - 1, 0, + size_bytes); + + rc = sja1105_spi_send_packed_buf(priv, rw, reg_addr, packed_buf, + size_bytes); + + if (rw == SPI_READ) + sja1105_unpack(packed_buf, value, 8 * size_bytes - 1, 0, + size_bytes); + + return rc; +} + +/* Should be used if a @packed_buf larger than SJA1105_SIZE_SPI_MSG_MAXLEN + * must be sent/received. Splitting the buffer into chunks and assembling + * those into SPI messages is done automatically by this function. + */ +int sja1105_spi_send_long_packed_buf(const struct sja1105_private *priv, + sja1105_spi_rw_mode_t rw, u64 base_addr, + void *packed_buf, u64 buf_len) +{ + struct chunk { + void *buf_ptr; + int len; + u64 spi_address; + } chunk; + int distance_to_end; + int rc; + + /* Initialize chunk */ + chunk.buf_ptr = packed_buf; + chunk.spi_address = base_addr; + chunk.len = min_t(int, buf_len, SJA1105_SIZE_SPI_MSG_MAXLEN); + + while (chunk.len) { + rc = sja1105_spi_send_packed_buf(priv, rw, chunk.spi_address, + chunk.buf_ptr, chunk.len); + if (rc < 0) + return rc; + + chunk.buf_ptr += chunk.len; + chunk.spi_address += chunk.len / 4; + distance_to_end = (uintptr_t)(packed_buf + buf_len - + chunk.buf_ptr); + chunk.len = min(distance_to_end, SJA1105_SIZE_SPI_MSG_MAXLEN); + } + + return 0; +} + +/* Back-ported structure from UM11040 Table 112. + * Reset control register (addr. 100440h) + * In the SJA1105 E/T, only warm_rst and cold_rst are + * supported (exposed in UM10944 as rst_ctrl), but the bit + * offsets of warm_rst and cold_rst are actually reversed. + */ +struct sja1105_reset_cmd { + u64 switch_rst; + u64 cfg_rst; + u64 car_rst; + u64 otp_rst; + u64 warm_rst; + u64 cold_rst; + u64 por_rst; +}; + +static void +sja1105et_reset_cmd_pack(void *buf, const struct sja1105_reset_cmd *reset) +{ + const int size = SJA1105_SIZE_RESET_CMD; + + memset(buf, 0, size); + + sja1105_pack(buf, &reset->cold_rst, 3, 3, size); + sja1105_pack(buf, &reset->warm_rst, 2, 2, size); +} + +static void +sja1105pqrs_reset_cmd_pack(void *buf, const struct sja1105_reset_cmd *reset) +{ + const int size = SJA1105_SIZE_RESET_CMD; + + memset(buf, 0, size); + + sja1105_pack(buf, &reset->switch_rst, 8, 8, size); + sja1105_pack(buf, &reset->cfg_rst, 7, 7, size); + sja1105_pack(buf, &reset->car_rst, 5, 5, size); + sja1105_pack(buf, &reset->otp_rst, 4, 4, size); + sja1105_pack(buf, &reset->warm_rst, 3, 3, size); + sja1105_pack(buf, &reset->cold_rst, 2, 2, size); + sja1105_pack(buf, &reset->por_rst, 1, 1, size); +} + +static int sja1105et_reset_cmd(const void *ctx, const void *data) +{ + const struct sja1105_private *priv = ctx; + const struct sja1105_reset_cmd *reset = data; + const struct sja1105_regs *regs = priv->info->regs; + struct device *dev = priv->ds->dev; + u8 packed_buf[SJA1105_SIZE_RESET_CMD]; + + if (reset->switch_rst || + reset->cfg_rst || + reset->car_rst || + reset->otp_rst || + reset->por_rst) { + dev_err(dev, "Only warm and cold reset is supported " + "for SJA1105 E/T!\n"); + return -EINVAL; + } + + if (reset->warm_rst) + dev_dbg(dev, "Warm reset requested\n"); + if (reset->cold_rst) + dev_dbg(dev, "Cold reset requested\n"); + + sja1105et_reset_cmd_pack(packed_buf, reset); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rgu, + packed_buf, SJA1105_SIZE_RESET_CMD); +} + +static int sja1105pqrs_reset_cmd(const void *ctx, const void *data) +{ + const struct sja1105_private *priv = ctx; + const struct sja1105_reset_cmd *reset = data; + const struct sja1105_regs *regs = priv->info->regs; + struct device *dev = priv->ds->dev; + u8 packed_buf[SJA1105_SIZE_RESET_CMD]; + + if (reset->switch_rst) + dev_dbg(dev, "Main reset for all functional modules requested\n"); + if (reset->cfg_rst) + dev_dbg(dev, "Chip configuration reset requested\n"); + if (reset->car_rst) + dev_dbg(dev, "Clock and reset control logic reset requested\n"); + if (reset->otp_rst) + dev_dbg(dev, "OTP read cycle for reading product " + "config settings requested\n"); + if (reset->warm_rst) + dev_dbg(dev, "Warm reset requested\n"); + if (reset->cold_rst) + dev_dbg(dev, "Cold reset requested\n"); + if (reset->por_rst) + dev_dbg(dev, "Power-on reset requested\n"); + + sja1105pqrs_reset_cmd_pack(packed_buf, reset); + + return sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rgu, + packed_buf, SJA1105_SIZE_RESET_CMD); +} + +static int sja1105_cold_reset(const struct sja1105_private *priv) +{ + struct sja1105_reset_cmd reset = {0}; + + reset.cold_rst = 1; + return priv->info->reset_cmd(priv, &reset); +} + +struct sja1105_status { + u64 configs; + u64 crcchkl; + u64 ids; + u64 crcchkg; +}; + +/* This is not reading the entire General Status area, which is also + * divergent between E/T and P/Q/R/S, but only the relevant bits for + * ensuring that the static config upload procedure was successful. + */ +static void sja1105_status_unpack(void *buf, struct sja1105_status *status) +{ + /* So that addition translates to 4 bytes */ + u32 *p = buf; + + /* device_id is missing from the buffer, but we don't + * want to diverge from the manual definition of the + * register addresses, so we'll back off one step with + * the register pointer, and never access p[0]. + */ + p--; + sja1105_unpack(p + 0x1, &status->configs, 31, 31, 4); + sja1105_unpack(p + 0x1, &status->crcchkl, 30, 30, 4); + sja1105_unpack(p + 0x1, &status->ids, 29, 29, 4); + sja1105_unpack(p + 0x1, &status->crcchkg, 28, 28, 4); +} + +static int sja1105_status_get(struct sja1105_private *priv, + struct sja1105_status *status) +{ + const struct sja1105_regs *regs = priv->info->regs; + u8 packed_buf[4]; + int rc; + + rc = sja1105_spi_send_packed_buf(priv, SPI_READ, + regs->status, + packed_buf, 4); + if (rc < 0) + return rc; + + sja1105_status_unpack(packed_buf, status); + + return 0; +} + +/* Not const because unpacking priv->static_config into buffers and preparing + * for upload requires the recalculation of table CRCs and updating the + * structures with these. + */ +static int +static_config_buf_prepare_for_upload(struct sja1105_private *priv, + void *config_buf, int buf_len) +{ + struct sja1105_static_config *config = &priv->static_config; + struct sja1105_table_header final_header; + sja1105_config_valid_t valid; + char *final_header_ptr; + int crc_len; + + valid = sja1105_static_config_check_valid(config); + if (valid != SJA1105_CONFIG_OK) { + dev_err(&priv->spidev->dev, + sja1105_static_config_error_msg[valid]); + return -EINVAL; + } + + /* Write Device ID and config tables to config_buf */ + sja1105_static_config_pack(config_buf, config); + /* Recalculate CRC of the last header (right now 0xDEADBEEF). + * Don't include the CRC field itself. + */ + crc_len = buf_len - 4; + /* Read the whole table header */ + final_header_ptr = config_buf + buf_len - SJA1105_SIZE_TABLE_HEADER; + sja1105_table_header_packing(final_header_ptr, &final_header, UNPACK); + /* Modify */ + final_header.crc = sja1105_crc32(config_buf, crc_len); + /* Rewrite */ + sja1105_table_header_packing(final_header_ptr, &final_header, PACK); + + return 0; +} + +#define RETRIES 10 + +int sja1105_static_config_upload(struct sja1105_private *priv) +{ + struct sja1105_static_config *config = &priv->static_config; + const struct sja1105_regs *regs = priv->info->regs; + struct device *dev = &priv->spidev->dev; + struct sja1105_status status; + int rc, retries = RETRIES; + u8 *config_buf; + int buf_len; + + buf_len = sja1105_static_config_get_length(config); + config_buf = kcalloc(buf_len, sizeof(char), GFP_KERNEL); + if (!config_buf) + return -ENOMEM; + + rc = static_config_buf_prepare_for_upload(priv, config_buf, buf_len); + if (rc < 0) { + dev_err(dev, "Invalid config, cannot upload\n"); + return -EINVAL; + } + do { + /* Put the SJA1105 in programming mode */ + rc = sja1105_cold_reset(priv); + if (rc < 0) { + dev_err(dev, "Failed to reset switch, retrying...\n"); + continue; + } + /* Wait for the switch to come out of reset */ + usleep_range(1000, 5000); + /* Upload the static config to the device */ + rc = sja1105_spi_send_long_packed_buf(priv, SPI_WRITE, + regs->config, + config_buf, buf_len); + if (rc < 0) { + dev_err(dev, "Failed to upload config, retrying...\n"); + continue; + } + /* Check that SJA1105 responded well to the config upload */ + rc = sja1105_status_get(priv, &status); + if (rc < 0) + continue; + + if (status.ids == 1) { + dev_err(dev, "Mismatch between hardware and static config " + "device id. Wrote 0x%llx, wants 0x%llx\n", + config->device_id, priv->info->device_id); + continue; + } + if (status.crcchkl == 1) { + dev_err(dev, "Switch reported invalid local CRC on " + "the uploaded config, retrying...\n"); + continue; + } + if (status.crcchkg == 1) { + dev_err(dev, "Switch reported invalid global CRC on " + "the uploaded config, retrying...\n"); + continue; + } + if (status.configs == 0) { + dev_err(dev, "Switch reported that configuration is " + "invalid, retrying...\n"); + continue; + } + } while (--retries && (status.crcchkl == 1 || status.crcchkg == 1 || + status.configs == 0 || status.ids == 1)); + + if (!retries) { + rc = -EIO; + dev_err(dev, "Failed to upload config to device, giving up\n"); + goto out; + } else if (retries != RETRIES - 1) { + dev_info(dev, "Succeeded after %d tried\n", RETRIES - retries); + } + + dev_info(dev, "Reset switch and programmed static config\n"); +out: + kfree(config_buf); + return rc; +} + +struct sja1105_regs sja1105et_regs = { + .device_id = 0x0, + .prod_id = 0x100BC3, + .status = 0x1, + .config = 0x020000, + .rgu = 0x100440, + .pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808}, + .rmii_pll1 = 0x10000A, + .cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F}, + /* UM10944.pdf, Table 86, ACU Register overview */ + .rgmii_pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808}, + .mac = {0x200, 0x202, 0x204, 0x206, 0x208}, + .mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440}, + .mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640}, + /* UM10944.pdf, Table 78, CGU Register overview */ + .mii_tx_clk = {0x100013, 0x10001A, 0x100021, 0x100028, 0x10002F}, + .mii_rx_clk = {0x100014, 0x10001B, 0x100022, 0x100029, 0x100030}, + .mii_ext_tx_clk = {0x100018, 0x10001F, 0x100026, 0x10002D, 0x100034}, + .mii_ext_rx_clk = {0x100019, 0x100020, 0x100027, 0x10002E, 0x100035}, + .rgmii_tx_clk = {0x100016, 0x10001D, 0x100024, 0x10002B, 0x100032}, + .rmii_ref_clk = {0x100015, 0x10001C, 0x100023, 0x10002A, 0x100031}, + .rmii_ext_tx_clk = {0x100018, 0x10001F, 0x100026, 0x10002D, 0x100034}, +}; + +struct sja1105_regs sja1105pqrs_regs = { + .device_id = 0x0, + .prod_id = 0x100BC3, + .status = 0x1, + .config = 0x020000, + .rgu = 0x100440, + .pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808}, + .rmii_pll1 = 0x10000A, + .cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F}, + /* UM10944.pdf, Table 86, ACU Register overview */ + .rgmii_pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808}, + .mac = {0x200, 0x202, 0x204, 0x206, 0x208}, + .mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440}, + .mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640}, + /* UM11040.pdf, Table 114 */ + .mii_tx_clk = {0x100013, 0x100019, 0x10001F, 0x100025, 0x10002B}, + .mii_rx_clk = {0x100014, 0x10001A, 0x100020, 0x100026, 0x10002C}, + .mii_ext_tx_clk = {0x100017, 0x10001D, 0x100023, 0x100029, 0x10002F}, + .mii_ext_rx_clk = {0x100018, 0x10001E, 0x100024, 0x10002A, 0x100030}, + .rgmii_tx_clk = {0x100016, 0x10001C, 0x100022, 0x100028, 0x10002E}, + .rmii_ref_clk = {0x100015, 0x10001B, 0x100021, 0x100027, 0x10002D}, + .rmii_ext_tx_clk = {0x100017, 0x10001D, 0x100023, 0x100029, 0x10002F}, + .qlevel = {0x604, 0x614, 0x624, 0x634, 0x644}, +}; + +struct sja1105_info sja1105e_info = { + .device_id = SJA1105E_DEVICE_ID, + .part_no = SJA1105ET_PART_NO, + .static_ops = sja1105e_table_ops, + .dyn_ops = sja1105et_dyn_ops, + .reset_cmd = sja1105et_reset_cmd, + .regs = &sja1105et_regs, + .name = "SJA1105E", +}; +struct sja1105_info sja1105t_info = { + .device_id = SJA1105T_DEVICE_ID, + .part_no = SJA1105ET_PART_NO, + .static_ops = sja1105t_table_ops, + .dyn_ops = sja1105et_dyn_ops, + .reset_cmd = sja1105et_reset_cmd, + .regs = &sja1105et_regs, + .name = "SJA1105T", +}; +struct sja1105_info sja1105p_info = { + .device_id = SJA1105PR_DEVICE_ID, + .part_no = SJA1105P_PART_NO, + .static_ops = sja1105p_table_ops, + .dyn_ops = sja1105pqrs_dyn_ops, + .reset_cmd = sja1105pqrs_reset_cmd, + .regs = &sja1105pqrs_regs, + .name = "SJA1105P", +}; +struct sja1105_info sja1105q_info = { + .device_id = SJA1105QS_DEVICE_ID, + .part_no = SJA1105Q_PART_NO, + .static_ops = sja1105q_table_ops, + .dyn_ops = sja1105pqrs_dyn_ops, + .reset_cmd = sja1105pqrs_reset_cmd, + .regs = &sja1105pqrs_regs, + .name = "SJA1105Q", +}; +struct sja1105_info sja1105r_info = { + .device_id = SJA1105PR_DEVICE_ID, + .part_no = SJA1105R_PART_NO, + .static_ops = sja1105r_table_ops, + .dyn_ops = sja1105pqrs_dyn_ops, + .reset_cmd = sja1105pqrs_reset_cmd, + .regs = &sja1105pqrs_regs, + .name = "SJA1105R", +}; +struct sja1105_info sja1105s_info = { + .device_id = SJA1105QS_DEVICE_ID, + .part_no = SJA1105S_PART_NO, + .static_ops = sja1105s_table_ops, + .dyn_ops = sja1105pqrs_dyn_ops, + .regs = &sja1105pqrs_regs, + .reset_cmd = sja1105pqrs_reset_cmd, + .name = "SJA1105S", +}; diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c new file mode 100644 index 000000000000..84ee623c6336 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -0,0 +1,949 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (c) 2016-2018, NXP Semiconductors + * Copyright (c) 2018-2019, Vladimir Oltean + */ +#include "sja1105_static_config.h" +#include +#include +#include +#include + +/* Convenience wrappers over the generic packing functions. These take into + * account the SJA1105 memory layout quirks and provide some level of + * programmer protection against incorrect API use. The errors are not expected + * to occur durring runtime, therefore printing and swallowing them here is + * appropriate instead of clutterring up higher-level code. + */ +void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len) +{ + int rc = packing(buf, (u64 *)val, start, end, len, + PACK, QUIRK_LSW32_IS_FIRST); + + if (likely(!rc)) + return; + + if (rc == -EINVAL) { + pr_err("Start bit (%d) expected to be larger than end (%d)\n", + start, end); + } else if (rc == -ERANGE) { + if ((start - end + 1) > 64) + pr_err("Field %d-%d too large for 64 bits!\n", + start, end); + else + pr_err("Cannot store %llx inside bits %d-%d (would truncate)\n", + *val, start, end); + } + dump_stack(); +} + +void sja1105_unpack(const void *buf, u64 *val, int start, int end, size_t len) +{ + int rc = packing((void *)buf, val, start, end, len, + UNPACK, QUIRK_LSW32_IS_FIRST); + + if (likely(!rc)) + return; + + if (rc == -EINVAL) + pr_err("Start bit (%d) expected to be larger than end (%d)\n", + start, end); + else if (rc == -ERANGE) + pr_err("Field %d-%d too large for 64 bits!\n", + start, end); + dump_stack(); +} + +void sja1105_packing(void *buf, u64 *val, int start, int end, + size_t len, enum packing_op op) +{ + int rc = packing(buf, val, start, end, len, op, QUIRK_LSW32_IS_FIRST); + + if (likely(!rc)) + return; + + if (rc == -EINVAL) { + pr_err("Start bit (%d) expected to be larger than end (%d)\n", + start, end); + } else if (rc == -ERANGE) { + if ((start - end + 1) > 64) + pr_err("Field %d-%d too large for 64 bits!\n", + start, end); + else + pr_err("Cannot store %llx inside bits %d-%d (would truncate)\n", + *val, start, end); + } + dump_stack(); +} + +/* Little-endian Ethernet CRC32 of data packed as big-endian u32 words */ +u32 sja1105_crc32(const void *buf, size_t len) +{ + unsigned int i; + u64 word; + u32 crc; + + /* seed */ + crc = ~0; + for (i = 0; i < len; i += 4) { + sja1105_unpack((void *)buf + i, &word, 31, 0, 4); + crc = crc32_le(crc, (u8 *)&word, 4); + } + return ~crc; +} + +static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY; + struct sja1105_general_params_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->vllupformat, 319, 319, size, op); + sja1105_packing(buf, &entry->mirr_ptacu, 318, 318, size, op); + sja1105_packing(buf, &entry->switchid, 317, 315, size, op); + sja1105_packing(buf, &entry->hostprio, 314, 312, size, op); + sja1105_packing(buf, &entry->mac_fltres1, 311, 264, size, op); + sja1105_packing(buf, &entry->mac_fltres0, 263, 216, size, op); + sja1105_packing(buf, &entry->mac_flt1, 215, 168, size, op); + sja1105_packing(buf, &entry->mac_flt0, 167, 120, size, op); + sja1105_packing(buf, &entry->incl_srcpt1, 119, 119, size, op); + sja1105_packing(buf, &entry->incl_srcpt0, 118, 118, size, op); + sja1105_packing(buf, &entry->send_meta1, 117, 117, size, op); + sja1105_packing(buf, &entry->send_meta0, 116, 116, size, op); + sja1105_packing(buf, &entry->casc_port, 115, 113, size, op); + sja1105_packing(buf, &entry->host_port, 112, 110, size, op); + sja1105_packing(buf, &entry->mirr_port, 109, 107, size, op); + sja1105_packing(buf, &entry->vlmarker, 106, 75, size, op); + sja1105_packing(buf, &entry->vlmask, 74, 43, size, op); + sja1105_packing(buf, &entry->tpid, 42, 27, size, op); + sja1105_packing(buf, &entry->ignore2stf, 26, 26, size, op); + sja1105_packing(buf, &entry->tpid2, 25, 10, size, op); + return size; +} + +static size_t +sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY; + struct sja1105_general_params_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->vllupformat, 351, 351, size, op); + sja1105_packing(buf, &entry->mirr_ptacu, 350, 350, size, op); + sja1105_packing(buf, &entry->switchid, 349, 347, size, op); + sja1105_packing(buf, &entry->hostprio, 346, 344, size, op); + sja1105_packing(buf, &entry->mac_fltres1, 343, 296, size, op); + sja1105_packing(buf, &entry->mac_fltres0, 295, 248, size, op); + sja1105_packing(buf, &entry->mac_flt1, 247, 200, size, op); + sja1105_packing(buf, &entry->mac_flt0, 199, 152, size, op); + sja1105_packing(buf, &entry->incl_srcpt1, 151, 151, size, op); + sja1105_packing(buf, &entry->incl_srcpt0, 150, 150, size, op); + sja1105_packing(buf, &entry->send_meta1, 149, 149, size, op); + sja1105_packing(buf, &entry->send_meta0, 148, 148, size, op); + sja1105_packing(buf, &entry->casc_port, 147, 145, size, op); + sja1105_packing(buf, &entry->host_port, 144, 142, size, op); + sja1105_packing(buf, &entry->mirr_port, 141, 139, size, op); + sja1105_packing(buf, &entry->vlmarker, 138, 107, size, op); + sja1105_packing(buf, &entry->vlmask, 106, 75, size, op); + sja1105_packing(buf, &entry->tpid, 74, 59, size, op); + sja1105_packing(buf, &entry->ignore2stf, 58, 58, size, op); + sja1105_packing(buf, &entry->tpid2, 57, 42, size, op); + sja1105_packing(buf, &entry->queue_ts, 41, 41, size, op); + sja1105_packing(buf, &entry->egrmirrvid, 40, 29, size, op); + sja1105_packing(buf, &entry->egrmirrpcp, 28, 26, size, op); + sja1105_packing(buf, &entry->egrmirrdei, 25, 25, size, op); + sja1105_packing(buf, &entry->replay_port, 24, 22, size, op); + return size; +} + +static size_t +sja1105_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY; + struct sja1105_l2_forwarding_params_entry *entry = entry_ptr; + int offset, i; + + sja1105_packing(buf, &entry->max_dynp, 95, 93, size, op); + for (i = 0, offset = 13; i < 8; i++, offset += 10) + sja1105_packing(buf, &entry->part_spc[i], + offset + 9, offset + 0, size, op); + return size; +} + +size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105_SIZE_L2_FORWARDING_ENTRY; + struct sja1105_l2_forwarding_entry *entry = entry_ptr; + int offset, i; + + sja1105_packing(buf, &entry->bc_domain, 63, 59, size, op); + sja1105_packing(buf, &entry->reach_port, 58, 54, size, op); + sja1105_packing(buf, &entry->fl_domain, 53, 49, size, op); + for (i = 0, offset = 25; i < 8; i++, offset += 3) + sja1105_packing(buf, &entry->vlan_pmap[i], + offset + 2, offset + 0, size, op); + return size; +} + +static size_t +sja1105et_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY; + struct sja1105_l2_lookup_params_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->maxage, 31, 17, size, op); + sja1105_packing(buf, &entry->dyn_tbsz, 16, 14, size, op); + sja1105_packing(buf, &entry->poly, 13, 6, size, op); + sja1105_packing(buf, &entry->shared_learn, 5, 5, size, op); + sja1105_packing(buf, &entry->no_enf_hostprt, 4, 4, size, op); + sja1105_packing(buf, &entry->no_mgmt_learn, 3, 3, size, op); + return size; +} + +static size_t +sja1105pqrs_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY; + struct sja1105_l2_lookup_params_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->maxage, 57, 43, size, op); + sja1105_packing(buf, &entry->shared_learn, 27, 27, size, op); + sja1105_packing(buf, &entry->no_enf_hostprt, 26, 26, size, op); + sja1105_packing(buf, &entry->no_mgmt_learn, 25, 25, size, op); + return size; +} + +size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY; + struct sja1105_l2_lookup_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->vlanid, 95, 84, size, op); + sja1105_packing(buf, &entry->macaddr, 83, 36, size, op); + sja1105_packing(buf, &entry->destports, 35, 31, size, op); + sja1105_packing(buf, &entry->enfport, 30, 30, size, op); + sja1105_packing(buf, &entry->index, 29, 20, size, op); + return size; +} + +size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY; + struct sja1105_l2_lookup_entry *entry = entry_ptr; + + /* These are static L2 lookup entries, so the structure + * should match UM11040 Table 16/17 definitions when + * LOCKEDS is 1. + */ + sja1105_packing(buf, &entry->vlanid, 81, 70, size, op); + sja1105_packing(buf, &entry->macaddr, 69, 22, size, op); + sja1105_packing(buf, &entry->destports, 21, 17, size, op); + sja1105_packing(buf, &entry->enfport, 16, 16, size, op); + sja1105_packing(buf, &entry->index, 15, 6, size, op); + return size; +} + +static size_t sja1105_l2_policing_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105_SIZE_L2_POLICING_ENTRY; + struct sja1105_l2_policing_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->sharindx, 63, 58, size, op); + sja1105_packing(buf, &entry->smax, 57, 42, size, op); + sja1105_packing(buf, &entry->rate, 41, 26, size, op); + sja1105_packing(buf, &entry->maxlen, 25, 15, size, op); + sja1105_packing(buf, &entry->partition, 14, 12, size, op); + return size; +} + +static size_t sja1105et_mac_config_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105ET_SIZE_MAC_CONFIG_ENTRY; + struct sja1105_mac_config_entry *entry = entry_ptr; + int offset, i; + + for (i = 0, offset = 72; i < 8; i++, offset += 19) { + sja1105_packing(buf, &entry->enabled[i], + offset + 0, offset + 0, size, op); + sja1105_packing(buf, &entry->base[i], + offset + 9, offset + 1, size, op); + sja1105_packing(buf, &entry->top[i], + offset + 18, offset + 10, size, op); + } + sja1105_packing(buf, &entry->ifg, 71, 67, size, op); + sja1105_packing(buf, &entry->speed, 66, 65, size, op); + sja1105_packing(buf, &entry->tp_delin, 64, 49, size, op); + sja1105_packing(buf, &entry->tp_delout, 48, 33, size, op); + sja1105_packing(buf, &entry->maxage, 32, 25, size, op); + sja1105_packing(buf, &entry->vlanprio, 24, 22, size, op); + sja1105_packing(buf, &entry->vlanid, 21, 10, size, op); + sja1105_packing(buf, &entry->ing_mirr, 9, 9, size, op); + sja1105_packing(buf, &entry->egr_mirr, 8, 8, size, op); + sja1105_packing(buf, &entry->drpnona664, 7, 7, size, op); + sja1105_packing(buf, &entry->drpdtag, 6, 6, size, op); + sja1105_packing(buf, &entry->drpuntag, 5, 5, size, op); + sja1105_packing(buf, &entry->retag, 4, 4, size, op); + sja1105_packing(buf, &entry->dyn_learn, 3, 3, size, op); + sja1105_packing(buf, &entry->egress, 2, 2, size, op); + sja1105_packing(buf, &entry->ingress, 1, 1, size, op); + return size; +} + +size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY; + struct sja1105_mac_config_entry *entry = entry_ptr; + int offset, i; + + for (i = 0, offset = 104; i < 8; i++, offset += 19) { + sja1105_packing(buf, &entry->enabled[i], + offset + 0, offset + 0, size, op); + sja1105_packing(buf, &entry->base[i], + offset + 9, offset + 1, size, op); + sja1105_packing(buf, &entry->top[i], + offset + 18, offset + 10, size, op); + } + sja1105_packing(buf, &entry->ifg, 103, 99, size, op); + sja1105_packing(buf, &entry->speed, 98, 97, size, op); + sja1105_packing(buf, &entry->tp_delin, 96, 81, size, op); + sja1105_packing(buf, &entry->tp_delout, 80, 65, size, op); + sja1105_packing(buf, &entry->maxage, 64, 57, size, op); + sja1105_packing(buf, &entry->vlanprio, 56, 54, size, op); + sja1105_packing(buf, &entry->vlanid, 53, 42, size, op); + sja1105_packing(buf, &entry->ing_mirr, 41, 41, size, op); + sja1105_packing(buf, &entry->egr_mirr, 40, 40, size, op); + sja1105_packing(buf, &entry->drpnona664, 39, 39, size, op); + sja1105_packing(buf, &entry->drpdtag, 38, 38, size, op); + sja1105_packing(buf, &entry->drpuntag, 35, 35, size, op); + sja1105_packing(buf, &entry->retag, 34, 34, size, op); + sja1105_packing(buf, &entry->dyn_learn, 33, 33, size, op); + sja1105_packing(buf, &entry->egress, 32, 32, size, op); + sja1105_packing(buf, &entry->ingress, 31, 31, size, op); + return size; +} + +size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY; + struct sja1105_vlan_lookup_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->ving_mirr, 63, 59, size, op); + sja1105_packing(buf, &entry->vegr_mirr, 58, 54, size, op); + sja1105_packing(buf, &entry->vmemb_port, 53, 49, size, op); + sja1105_packing(buf, &entry->vlan_bc, 48, 44, size, op); + sja1105_packing(buf, &entry->tag_port, 43, 39, size, op); + sja1105_packing(buf, &entry->vlanid, 38, 27, size, op); + return size; +} + +static size_t sja1105_xmii_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105_SIZE_XMII_PARAMS_ENTRY; + struct sja1105_xmii_params_entry *entry = entry_ptr; + int offset, i; + + for (i = 0, offset = 17; i < 5; i++, offset += 3) { + sja1105_packing(buf, &entry->xmii_mode[i], + offset + 1, offset + 0, size, op); + sja1105_packing(buf, &entry->phy_mac[i], + offset + 2, offset + 2, size, op); + } + return size; +} + +size_t sja1105_table_header_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105_SIZE_TABLE_HEADER; + struct sja1105_table_header *entry = entry_ptr; + + sja1105_packing(buf, &entry->block_id, 31, 24, size, op); + sja1105_packing(buf, &entry->len, 55, 32, size, op); + sja1105_packing(buf, &entry->crc, 95, 64, size, op); + return size; +} + +/* WARNING: the *hdr pointer is really non-const, because it is + * modifying the CRC of the header for a 2-stage packing operation + */ +void +sja1105_table_header_pack_with_crc(void *buf, struct sja1105_table_header *hdr) +{ + /* First pack the table as-is, then calculate the CRC, and + * finally put the proper CRC into the packed buffer + */ + memset(buf, 0, SJA1105_SIZE_TABLE_HEADER); + sja1105_table_header_packing(buf, hdr, PACK); + hdr->crc = sja1105_crc32(buf, SJA1105_SIZE_TABLE_HEADER - 4); + sja1105_pack(buf + SJA1105_SIZE_TABLE_HEADER - 4, &hdr->crc, 31, 0, 4); +} + +static void sja1105_table_write_crc(u8 *table_start, u8 *crc_ptr) +{ + u64 computed_crc; + int len_bytes; + + len_bytes = (uintptr_t)(crc_ptr - table_start); + computed_crc = sja1105_crc32(table_start, len_bytes); + sja1105_pack(crc_ptr, &computed_crc, 31, 0, 4); +} + +/* The block IDs that the switches support are unfortunately sparse, so keep a + * mapping table to "block indices" and translate back and forth so that we + * don't waste useless memory in struct sja1105_static_config. + * Also, since the block id comes from essentially untrusted input (unpacking + * the static config from userspace) it has to be sanitized (range-checked) + * before blindly indexing kernel memory with the blk_idx. + */ +static u64 blk_id_map[BLK_IDX_MAX] = { + [BLK_IDX_L2_LOOKUP] = BLKID_L2_LOOKUP, + [BLK_IDX_L2_POLICING] = BLKID_L2_POLICING, + [BLK_IDX_VLAN_LOOKUP] = BLKID_VLAN_LOOKUP, + [BLK_IDX_L2_FORWARDING] = BLKID_L2_FORWARDING, + [BLK_IDX_MAC_CONFIG] = BLKID_MAC_CONFIG, + [BLK_IDX_L2_LOOKUP_PARAMS] = BLKID_L2_LOOKUP_PARAMS, + [BLK_IDX_L2_FORWARDING_PARAMS] = BLKID_L2_FORWARDING_PARAMS, + [BLK_IDX_GENERAL_PARAMS] = BLKID_GENERAL_PARAMS, + [BLK_IDX_XMII_PARAMS] = BLKID_XMII_PARAMS, +}; + +const char *sja1105_static_config_error_msg[] = { + [SJA1105_CONFIG_OK] = "", + [SJA1105_MISSING_L2_POLICING_TABLE] = + "l2-policing-table needs to have at least one entry", + [SJA1105_MISSING_L2_FORWARDING_TABLE] = + "l2-forwarding-table is either missing or incomplete", + [SJA1105_MISSING_L2_FORWARDING_PARAMS_TABLE] = + "l2-forwarding-parameters-table is missing", + [SJA1105_MISSING_GENERAL_PARAMS_TABLE] = + "general-parameters-table is missing", + [SJA1105_MISSING_VLAN_TABLE] = + "vlan-lookup-table needs to have at least the default untagged VLAN", + [SJA1105_MISSING_XMII_TABLE] = + "xmii-table is missing", + [SJA1105_MISSING_MAC_TABLE] = + "mac-configuration-table needs to contain an entry for each port", + [SJA1105_OVERCOMMITTED_FRAME_MEMORY] = + "Not allowed to overcommit frame memory. L2 memory partitions " + "and VL memory partitions share the same space. The sum of all " + "16 memory partitions is not allowed to be larger than 929 " + "128-byte blocks (or 910 with retagging). Please adjust " + "l2-forwarding-parameters-table.part_spc and/or " + "vl-forwarding-parameters-table.partspc.", +}; + +sja1105_config_valid_t +static_config_check_memory_size(const struct sja1105_table *tables) +{ + const struct sja1105_l2_forwarding_params_entry *l2_fwd_params; + int i, mem = 0; + + l2_fwd_params = tables[BLK_IDX_L2_FORWARDING_PARAMS].entries; + + for (i = 0; i < 8; i++) + mem += l2_fwd_params->part_spc[i]; + + if (mem > SJA1105_MAX_FRAME_MEMORY) + return SJA1105_OVERCOMMITTED_FRAME_MEMORY; + + return SJA1105_CONFIG_OK; +} + +sja1105_config_valid_t +sja1105_static_config_check_valid(const struct sja1105_static_config *config) +{ + const struct sja1105_table *tables = config->tables; +#define IS_FULL(blk_idx) \ + (tables[blk_idx].entry_count == tables[blk_idx].ops->max_entry_count) + + if (tables[BLK_IDX_L2_POLICING].entry_count == 0) + return SJA1105_MISSING_L2_POLICING_TABLE; + + if (tables[BLK_IDX_VLAN_LOOKUP].entry_count == 0) + return SJA1105_MISSING_VLAN_TABLE; + + if (!IS_FULL(BLK_IDX_L2_FORWARDING)) + return SJA1105_MISSING_L2_FORWARDING_TABLE; + + if (!IS_FULL(BLK_IDX_MAC_CONFIG)) + return SJA1105_MISSING_MAC_TABLE; + + if (!IS_FULL(BLK_IDX_L2_FORWARDING_PARAMS)) + return SJA1105_MISSING_L2_FORWARDING_PARAMS_TABLE; + + if (!IS_FULL(BLK_IDX_GENERAL_PARAMS)) + return SJA1105_MISSING_GENERAL_PARAMS_TABLE; + + if (!IS_FULL(BLK_IDX_XMII_PARAMS)) + return SJA1105_MISSING_XMII_TABLE; + + return static_config_check_memory_size(tables); +#undef IS_FULL +} + +void +sja1105_static_config_pack(void *buf, struct sja1105_static_config *config) +{ + struct sja1105_table_header header = {0}; + enum sja1105_blk_idx i; + char *p = buf; + int j; + + sja1105_pack(p, &config->device_id, 31, 0, 4); + p += SJA1105_SIZE_DEVICE_ID; + + for (i = 0; i < BLK_IDX_MAX; i++) { + const struct sja1105_table *table; + char *table_start; + + table = &config->tables[i]; + if (!table->entry_count) + continue; + + header.block_id = blk_id_map[i]; + header.len = table->entry_count * + table->ops->packed_entry_size / 4; + sja1105_table_header_pack_with_crc(p, &header); + p += SJA1105_SIZE_TABLE_HEADER; + table_start = p; + for (j = 0; j < table->entry_count; j++) { + u8 *entry_ptr = table->entries; + + entry_ptr += j * table->ops->unpacked_entry_size; + memset(p, 0, table->ops->packed_entry_size); + table->ops->packing(p, entry_ptr, PACK); + p += table->ops->packed_entry_size; + } + sja1105_table_write_crc(table_start, p); + p += 4; + } + /* Final header: + * Block ID does not matter + * Length of 0 marks that header is final + * CRC will be replaced on-the-fly on "config upload" + */ + header.block_id = 0; + header.len = 0; + header.crc = 0xDEADBEEF; + memset(p, 0, SJA1105_SIZE_TABLE_HEADER); + sja1105_table_header_packing(p, &header, PACK); +} + +size_t +sja1105_static_config_get_length(const struct sja1105_static_config *config) +{ + unsigned int sum; + unsigned int header_count; + enum sja1105_blk_idx i; + + /* Ending header */ + header_count = 1; + sum = SJA1105_SIZE_DEVICE_ID; + + /* Tables (headers and entries) */ + for (i = 0; i < BLK_IDX_MAX; i++) { + const struct sja1105_table *table; + + table = &config->tables[i]; + if (table->entry_count) + header_count++; + + sum += table->ops->packed_entry_size * table->entry_count; + } + /* Headers have an additional CRC at the end */ + sum += header_count * (SJA1105_SIZE_TABLE_HEADER + 4); + /* Last header does not have an extra CRC because there is no data */ + sum -= 4; + + return sum; +} + +/* Compatibility matrices */ + +/* SJA1105E: First generation, no TTEthernet */ +struct sja1105_table_ops sja1105e_table_ops[BLK_IDX_MAX] = { + [BLK_IDX_L2_LOOKUP] = { + .packing = sja1105et_l2_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry), + .packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + }, + [BLK_IDX_L2_POLICING] = { + .packing = sja1105_l2_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry), + .packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_POLICING_COUNT, + }, + [BLK_IDX_VLAN_LOOKUP] = { + .packing = sja1105_vlan_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry), + .packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + }, + [BLK_IDX_L2_FORWARDING] = { + .packing = sja1105_l2_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + }, + [BLK_IDX_MAC_CONFIG] = { + .packing = sja1105et_mac_config_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_mac_config_entry), + .packed_entry_size = SJA1105ET_SIZE_MAC_CONFIG_ENTRY, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .packing = sja1105et_l2_lookup_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry), + .packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .packing = sja1105_l2_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_GENERAL_PARAMS] = { + .packing = sja1105et_general_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_general_params_entry), + .packed_entry_size = SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + }, + [BLK_IDX_XMII_PARAMS] = { + .packing = sja1105_xmii_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry), + .packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + }, +}; + +/* SJA1105T: First generation, TTEthernet */ +struct sja1105_table_ops sja1105t_table_ops[BLK_IDX_MAX] = { + [BLK_IDX_L2_LOOKUP] = { + .packing = sja1105et_l2_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry), + .packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + }, + [BLK_IDX_L2_POLICING] = { + .packing = sja1105_l2_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry), + .packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_POLICING_COUNT, + }, + [BLK_IDX_VLAN_LOOKUP] = { + .packing = sja1105_vlan_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry), + .packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + }, + [BLK_IDX_L2_FORWARDING] = { + .packing = sja1105_l2_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + }, + [BLK_IDX_MAC_CONFIG] = { + .packing = sja1105et_mac_config_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_mac_config_entry), + .packed_entry_size = SJA1105ET_SIZE_MAC_CONFIG_ENTRY, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .packing = sja1105et_l2_lookup_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry), + .packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .packing = sja1105_l2_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_GENERAL_PARAMS] = { + .packing = sja1105et_general_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_general_params_entry), + .packed_entry_size = SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + }, + [BLK_IDX_XMII_PARAMS] = { + .packing = sja1105_xmii_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry), + .packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + }, +}; + +/* SJA1105P: Second generation, no TTEthernet, no SGMII */ +struct sja1105_table_ops sja1105p_table_ops[BLK_IDX_MAX] = { + [BLK_IDX_L2_LOOKUP] = { + .packing = sja1105pqrs_l2_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + }, + [BLK_IDX_L2_POLICING] = { + .packing = sja1105_l2_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry), + .packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_POLICING_COUNT, + }, + [BLK_IDX_VLAN_LOOKUP] = { + .packing = sja1105_vlan_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry), + .packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + }, + [BLK_IDX_L2_FORWARDING] = { + .packing = sja1105_l2_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + }, + [BLK_IDX_MAC_CONFIG] = { + .packing = sja1105pqrs_mac_config_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_mac_config_entry), + .packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .packing = sja1105pqrs_l2_lookup_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .packing = sja1105_l2_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_GENERAL_PARAMS] = { + .packing = sja1105pqrs_general_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_general_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + }, + [BLK_IDX_XMII_PARAMS] = { + .packing = sja1105_xmii_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry), + .packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + }, +}; + +/* SJA1105Q: Second generation, TTEthernet, no SGMII */ +struct sja1105_table_ops sja1105q_table_ops[BLK_IDX_MAX] = { + [BLK_IDX_L2_LOOKUP] = { + .packing = sja1105pqrs_l2_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + }, + [BLK_IDX_L2_POLICING] = { + .packing = sja1105_l2_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry), + .packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_POLICING_COUNT, + }, + [BLK_IDX_VLAN_LOOKUP] = { + .packing = sja1105_vlan_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry), + .packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + }, + [BLK_IDX_L2_FORWARDING] = { + .packing = sja1105_l2_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + }, + [BLK_IDX_MAC_CONFIG] = { + .packing = sja1105pqrs_mac_config_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_mac_config_entry), + .packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .packing = sja1105pqrs_l2_lookup_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .packing = sja1105_l2_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_GENERAL_PARAMS] = { + .packing = sja1105pqrs_general_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_general_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + }, + [BLK_IDX_XMII_PARAMS] = { + .packing = sja1105_xmii_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry), + .packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + }, +}; + +/* SJA1105R: Second generation, no TTEthernet, SGMII */ +struct sja1105_table_ops sja1105r_table_ops[BLK_IDX_MAX] = { + [BLK_IDX_L2_LOOKUP] = { + .packing = sja1105pqrs_l2_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + }, + [BLK_IDX_L2_POLICING] = { + .packing = sja1105_l2_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry), + .packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_POLICING_COUNT, + }, + [BLK_IDX_VLAN_LOOKUP] = { + .packing = sja1105_vlan_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry), + .packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + }, + [BLK_IDX_L2_FORWARDING] = { + .packing = sja1105_l2_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + }, + [BLK_IDX_MAC_CONFIG] = { + .packing = sja1105pqrs_mac_config_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_mac_config_entry), + .packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .packing = sja1105pqrs_l2_lookup_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .packing = sja1105_l2_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_GENERAL_PARAMS] = { + .packing = sja1105pqrs_general_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_general_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + }, + [BLK_IDX_XMII_PARAMS] = { + .packing = sja1105_xmii_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry), + .packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + }, +}; + +/* SJA1105S: Second generation, TTEthernet, SGMII */ +struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX] = { + [BLK_IDX_L2_LOOKUP] = { + .packing = sja1105pqrs_l2_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + }, + [BLK_IDX_L2_POLICING] = { + .packing = sja1105_l2_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry), + .packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_POLICING_COUNT, + }, + [BLK_IDX_VLAN_LOOKUP] = { + .packing = sja1105_vlan_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry), + .packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + }, + [BLK_IDX_L2_FORWARDING] = { + .packing = sja1105_l2_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT, + }, + [BLK_IDX_MAC_CONFIG] = { + .packing = sja1105pqrs_mac_config_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_mac_config_entry), + .packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY, + .max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .packing = sja1105pqrs_l2_lookup_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .packing = sja1105_l2_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_GENERAL_PARAMS] = { + .packing = sja1105pqrs_general_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_general_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + }, + [BLK_IDX_XMII_PARAMS] = { + .packing = sja1105_xmii_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry), + .packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + }, +}; + +int sja1105_static_config_init(struct sja1105_static_config *config, + const struct sja1105_table_ops *static_ops, + u64 device_id) +{ + enum sja1105_blk_idx i; + + *config = (struct sja1105_static_config) {0}; + + /* Transfer static_ops array from priv into per-table ops + * for handier access + */ + for (i = 0; i < BLK_IDX_MAX; i++) + config->tables[i].ops = &static_ops[i]; + + config->device_id = device_id; + return 0; +} + +void sja1105_static_config_free(struct sja1105_static_config *config) +{ + enum sja1105_blk_idx i; + + for (i = 0; i < BLK_IDX_MAX; i++) { + if (config->tables[i].entry_count) { + kfree(config->tables[i].entries); + config->tables[i].entry_count = 0; + } + } +} diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h new file mode 100644 index 000000000000..7b0a02fe3147 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -0,0 +1,250 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright (c) 2016-2018, NXP Semiconductors + * Copyright (c) 2018-2019, Vladimir Oltean + */ +#ifndef _SJA1105_STATIC_CONFIG_H +#define _SJA1105_STATIC_CONFIG_H + +#include +#include +#include + +#define SJA1105_SIZE_DEVICE_ID 4 +#define SJA1105_SIZE_TABLE_HEADER 12 +#define SJA1105_SIZE_L2_POLICING_ENTRY 8 +#define SJA1105_SIZE_VLAN_LOOKUP_ENTRY 8 +#define SJA1105_SIZE_L2_FORWARDING_ENTRY 8 +#define SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY 12 +#define SJA1105_SIZE_XMII_PARAMS_ENTRY 4 +#define SJA1105ET_SIZE_L2_LOOKUP_ENTRY 12 +#define SJA1105ET_SIZE_MAC_CONFIG_ENTRY 28 +#define SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY 4 +#define SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY 40 +#define SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY 20 +#define SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY 32 +#define SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY 16 +#define SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY 44 + +/* UM10944.pdf Page 11, Table 2. Configuration Blocks */ +enum { + BLKID_L2_LOOKUP = 0x05, + BLKID_L2_POLICING = 0x06, + BLKID_VLAN_LOOKUP = 0x07, + BLKID_L2_FORWARDING = 0x08, + BLKID_MAC_CONFIG = 0x09, + BLKID_L2_LOOKUP_PARAMS = 0x0D, + BLKID_L2_FORWARDING_PARAMS = 0x0E, + BLKID_GENERAL_PARAMS = 0x11, + BLKID_XMII_PARAMS = 0x4E, +}; + +enum sja1105_blk_idx { + BLK_IDX_L2_LOOKUP = 0, + BLK_IDX_L2_POLICING, + BLK_IDX_VLAN_LOOKUP, + BLK_IDX_L2_FORWARDING, + BLK_IDX_MAC_CONFIG, + BLK_IDX_L2_LOOKUP_PARAMS, + BLK_IDX_L2_FORWARDING_PARAMS, + BLK_IDX_GENERAL_PARAMS, + BLK_IDX_XMII_PARAMS, + BLK_IDX_MAX, + /* Fake block indices that are only valid for dynamic access */ + BLK_IDX_MGMT_ROUTE, + BLK_IDX_MAX_DYN, + BLK_IDX_INVAL = -1, +}; + +#define SJA1105_MAX_L2_LOOKUP_COUNT 1024 +#define SJA1105_MAX_L2_POLICING_COUNT 45 +#define SJA1105_MAX_VLAN_LOOKUP_COUNT 4096 +#define SJA1105_MAX_L2_FORWARDING_COUNT 13 +#define SJA1105_MAX_MAC_CONFIG_COUNT 5 +#define SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT 1 +#define SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT 1 +#define SJA1105_MAX_GENERAL_PARAMS_COUNT 1 +#define SJA1105_MAX_XMII_PARAMS_COUNT 1 + +#define SJA1105_MAX_FRAME_MEMORY 929 + +#define SJA1105E_DEVICE_ID 0x9C00000Cull +#define SJA1105T_DEVICE_ID 0x9E00030Eull +#define SJA1105PR_DEVICE_ID 0xAF00030Eull +#define SJA1105QS_DEVICE_ID 0xAE00030Eull + +#define SJA1105ET_PART_NO 0x9A83 +#define SJA1105P_PART_NO 0x9A84 +#define SJA1105Q_PART_NO 0x9A85 +#define SJA1105R_PART_NO 0x9A86 +#define SJA1105S_PART_NO 0x9A87 + +struct sja1105_general_params_entry { + u64 vllupformat; + u64 mirr_ptacu; + u64 switchid; + u64 hostprio; + u64 mac_fltres1; + u64 mac_fltres0; + u64 mac_flt1; + u64 mac_flt0; + u64 incl_srcpt1; + u64 incl_srcpt0; + u64 send_meta1; + u64 send_meta0; + u64 casc_port; + u64 host_port; + u64 mirr_port; + u64 vlmarker; + u64 vlmask; + u64 tpid; + u64 ignore2stf; + u64 tpid2; + /* P/Q/R/S only */ + u64 queue_ts; + u64 egrmirrvid; + u64 egrmirrpcp; + u64 egrmirrdei; + u64 replay_port; +}; + +struct sja1105_vlan_lookup_entry { + u64 ving_mirr; + u64 vegr_mirr; + u64 vmemb_port; + u64 vlan_bc; + u64 tag_port; + u64 vlanid; +}; + +struct sja1105_l2_lookup_entry { + u64 vlanid; + u64 macaddr; + u64 destports; + u64 enfport; + u64 index; +}; + +struct sja1105_l2_lookup_params_entry { + u64 maxage; /* Shared */ + u64 dyn_tbsz; /* E/T only */ + u64 poly; /* E/T only */ + u64 shared_learn; /* Shared */ + u64 no_enf_hostprt; /* Shared */ + u64 no_mgmt_learn; /* Shared */ +}; + +struct sja1105_l2_forwarding_entry { + u64 bc_domain; + u64 reach_port; + u64 fl_domain; + u64 vlan_pmap[8]; +}; + +struct sja1105_l2_forwarding_params_entry { + u64 max_dynp; + u64 part_spc[8]; +}; + +struct sja1105_l2_policing_entry { + u64 sharindx; + u64 smax; + u64 rate; + u64 maxlen; + u64 partition; +}; + +struct sja1105_mac_config_entry { + u64 top[8]; + u64 base[8]; + u64 enabled[8]; + u64 ifg; + u64 speed; + u64 tp_delin; + u64 tp_delout; + u64 maxage; + u64 vlanprio; + u64 vlanid; + u64 ing_mirr; + u64 egr_mirr; + u64 drpnona664; + u64 drpdtag; + u64 drpuntag; + u64 retag; + u64 dyn_learn; + u64 egress; + u64 ingress; +}; + +struct sja1105_xmii_params_entry { + u64 phy_mac[5]; + u64 xmii_mode[5]; +}; + +struct sja1105_table_header { + u64 block_id; + u64 len; + u64 crc; +}; + +struct sja1105_table_ops { + size_t (*packing)(void *buf, void *entry_ptr, enum packing_op op); + size_t unpacked_entry_size; + size_t packed_entry_size; + size_t max_entry_count; +}; + +struct sja1105_table { + const struct sja1105_table_ops *ops; + size_t entry_count; + void *entries; +}; + +struct sja1105_static_config { + u64 device_id; + struct sja1105_table tables[BLK_IDX_MAX]; +}; + +extern struct sja1105_table_ops sja1105e_table_ops[BLK_IDX_MAX]; +extern struct sja1105_table_ops sja1105t_table_ops[BLK_IDX_MAX]; +extern struct sja1105_table_ops sja1105p_table_ops[BLK_IDX_MAX]; +extern struct sja1105_table_ops sja1105q_table_ops[BLK_IDX_MAX]; +extern struct sja1105_table_ops sja1105r_table_ops[BLK_IDX_MAX]; +extern struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX]; + +size_t sja1105_table_header_packing(void *buf, void *hdr, enum packing_op op); +void +sja1105_table_header_pack_with_crc(void *buf, struct sja1105_table_header *hdr); +size_t +sja1105_static_config_get_length(const struct sja1105_static_config *config); + +typedef enum { + SJA1105_CONFIG_OK = 0, + SJA1105_MISSING_L2_POLICING_TABLE, + SJA1105_MISSING_L2_FORWARDING_TABLE, + SJA1105_MISSING_L2_FORWARDING_PARAMS_TABLE, + SJA1105_MISSING_GENERAL_PARAMS_TABLE, + SJA1105_MISSING_VLAN_TABLE, + SJA1105_MISSING_XMII_TABLE, + SJA1105_MISSING_MAC_TABLE, + SJA1105_OVERCOMMITTED_FRAME_MEMORY, +} sja1105_config_valid_t; + +extern const char *sja1105_static_config_error_msg[]; + +sja1105_config_valid_t +sja1105_static_config_check_valid(const struct sja1105_static_config *config); +void +sja1105_static_config_pack(void *buf, struct sja1105_static_config *config); +int sja1105_static_config_init(struct sja1105_static_config *config, + const struct sja1105_table_ops *static_ops, + u64 device_id); +void sja1105_static_config_free(struct sja1105_static_config *config); + +u32 sja1105_crc32(const void *buf, size_t len); + +void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len); +void sja1105_unpack(const void *buf, u64 *val, int start, int end, size_t len); +void sja1105_packing(void *buf, u64 *val, int start, int end, + size_t len, enum packing_op op); + +#endif diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h new file mode 100644 index 000000000000..30559d1d0e1b --- /dev/null +++ b/include/linux/dsa/sja1105.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2019, Vladimir Oltean + */ + +/* Included by drivers/net/dsa/sja1105/sja1105.h */ + +#ifndef _NET_DSA_SJA1105_H +#define _NET_DSA_SJA1105_H + +/* The switch can only be convinced to stay in unmanaged mode and not trap any + * link-local traffic by actually telling it to filter frames sent at the + * 00:00:00:00:00:00 destination MAC. + */ +#define SJA1105_LINKLOCAL_FILTER_A 0x000000000000ull +#define SJA1105_LINKLOCAL_FILTER_A_MASK 0xFFFFFFFFFFFFull +#define SJA1105_LINKLOCAL_FILTER_B 0x000000000000ull +#define SJA1105_LINKLOCAL_FILTER_B_MASK 0xFFFFFFFFFFFFull + +#endif /* _NET_DSA_SJA1105_H */ -- cgit v1.2.3-71-gd317 From 6666cebc5e306f49a25bd20aa8c1cb8ef8950df5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 2 May 2019 23:23:34 +0300 Subject: net: dsa: sja1105: Add support for VLAN operations VLAN filtering cannot be properly disabled in SJA1105. So in order to emulate the "no VLAN awareness" behavior (not dropping traffic that is tagged with a VID that isn't configured on the port), we need to hack another switch feature: programmable TPID (which is 0x8100 for 802.1Q). We are reprogramming the TPID to a bogus value which leaves the switch thinking that all traffic is untagged, and therefore accepts it. Under a vlan_filtering bridge, the proper TPID of ETH_P_8021Q is installed again, and the switch starts identifying 802.1Q-tagged traffic. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 248 +++++++++++++++++++++++- drivers/net/dsa/sja1105/sja1105_static_config.c | 38 ++++ drivers/net/dsa/sja1105/sja1105_static_config.h | 3 + include/linux/dsa/sja1105.h | 4 + 4 files changed, 291 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index d27b9c178cba..f7b1525b388a 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -251,6 +251,13 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; /* The static VLAN table will only contain the initial pvid of 0. + * All other VLANs are to be configured through dynamic entries, + * and kept in the static configuration table as backing memory. + * The pvid of 0 is sufficient to pass traffic while the ports are + * standalone and when vlan_filtering is disabled. When filtering + * gets enabled, the switchdev core sets up the VLAN ID 1 and sets + * it as the new pvid. Actually 'pvid 1' still comes up in 'bridge + * vlan' even when vlan_filtering is off, but it has no effect. */ if (table->entry_count) { kfree(table->entries); @@ -391,8 +398,11 @@ static int sja1105_init_general_params(struct sja1105_private *priv) .vlmask = 0, /* Only update correctionField for 1-step PTP (L2 transport) */ .ignore2stf = 0, - .tpid = ETH_P_8021Q, - .tpid2 = ETH_P_8021Q, + /* Forcefully disable VLAN filtering by telling + * the switch that VLAN has a different EtherType. + */ + .tpid = ETH_P_SJA1105, + .tpid2 = ETH_P_SJA1105, }; struct sja1105_table *table; int i; @@ -954,12 +964,233 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port, sja1105_bridge_member(ds, port, br, false); } +/* For situations where we need to change a setting at runtime that is only + * available through the static configuration, resetting the switch in order + * to upload the new static config is unavoidable. Back up the settings we + * modify at runtime (currently only MAC) and restore them after uploading, + * such that this operation is relatively seamless. + */ +static int sja1105_static_config_reload(struct sja1105_private *priv) +{ + struct sja1105_mac_config_entry *mac; + int speed_mbps[SJA1105_NUM_PORTS]; + int rc, i; + + mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; + + /* Back up settings changed by sja1105_adjust_port_config and + * and restore their defaults. + */ + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + speed_mbps[i] = sja1105_speed[mac[i].speed]; + mac[i].speed = SJA1105_SPEED_AUTO; + } + + /* Reset switch and send updated static configuration */ + rc = sja1105_static_config_upload(priv); + if (rc < 0) + goto out; + + /* Configure the CGU (PLLs) for MII and RMII PHYs. + * For these interfaces there is no dynamic configuration + * needed, since PLLs have same settings at all speeds. + */ + rc = sja1105_clocking_setup(priv); + if (rc < 0) + goto out; + + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + bool enabled = (speed_mbps[i] != 0); + + rc = sja1105_adjust_port_config(priv, i, speed_mbps[i], + enabled); + if (rc < 0) + goto out; + } +out: + return rc; +} + +/* The TPID setting belongs to the General Parameters table, + * which can only be partially reconfigured at runtime (and not the TPID). + * So a switch reset is required. + */ +static int sja1105_change_tpid(struct sja1105_private *priv, + u16 tpid, u16 tpid2) +{ + struct sja1105_general_params_entry *general_params; + struct sja1105_table *table; + + table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; + general_params = table->entries; + general_params->tpid = tpid; + general_params->tpid2 = tpid2; + return sja1105_static_config_reload(priv); +} + +static int sja1105_pvid_apply(struct sja1105_private *priv, int port, u16 pvid) +{ + struct sja1105_mac_config_entry *mac; + + mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; + + mac[port].vlanid = pvid; + + return sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port, + &mac[port], true); +} + +static int sja1105_is_vlan_configured(struct sja1105_private *priv, u16 vid) +{ + struct sja1105_vlan_lookup_entry *vlan; + int count, i; + + vlan = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entries; + count = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entry_count; + + for (i = 0; i < count; i++) + if (vlan[i].vlanid == vid) + return i; + + /* Return an invalid entry index if not found */ + return -1; +} + +static int sja1105_vlan_apply(struct sja1105_private *priv, int port, u16 vid, + bool enabled, bool untagged) +{ + struct sja1105_vlan_lookup_entry *vlan; + struct sja1105_table *table; + bool keep = true; + int match, rc; + + table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; + + match = sja1105_is_vlan_configured(priv, vid); + if (match < 0) { + /* Can't delete a missing entry. */ + if (!enabled) + return 0; + rc = sja1105_table_resize(table, table->entry_count + 1); + if (rc) + return rc; + match = table->entry_count - 1; + } + /* Assign pointer after the resize (it's new memory) */ + vlan = table->entries; + vlan[match].vlanid = vid; + if (enabled) { + vlan[match].vlan_bc |= BIT(port); + vlan[match].vmemb_port |= BIT(port); + } else { + vlan[match].vlan_bc &= ~BIT(port); + vlan[match].vmemb_port &= ~BIT(port); + } + /* Also unset tag_port if removing this VLAN was requested, + * just so we don't have a confusing bitmap (no practical purpose). + */ + if (untagged || !enabled) + vlan[match].tag_port &= ~BIT(port); + else + vlan[match].tag_port |= BIT(port); + /* If there's no port left as member of this VLAN, + * it's time for it to go. + */ + if (!vlan[match].vmemb_port) + keep = false; + + dev_dbg(priv->ds->dev, + "%s: port %d, vid %llu, broadcast domain 0x%llx, " + "port members 0x%llx, tagged ports 0x%llx, keep %d\n", + __func__, port, vlan[match].vlanid, vlan[match].vlan_bc, + vlan[match].vmemb_port, vlan[match].tag_port, keep); + + rc = sja1105_dynamic_config_write(priv, BLK_IDX_VLAN_LOOKUP, vid, + &vlan[match], keep); + if (rc < 0) + return rc; + + if (!keep) + return sja1105_table_delete_entry(table, match); + + return 0; +} + static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port) { return DSA_TAG_PROTO_NONE; } +/* This callback needs to be present */ +static int sja1105_vlan_prepare(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + return 0; +} + +static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) +{ + struct sja1105_private *priv = ds->priv; + int rc; + + if (enabled) + /* Enable VLAN filtering. */ + rc = sja1105_change_tpid(priv, ETH_P_8021Q, ETH_P_8021AD); + else + /* Disable VLAN filtering. */ + rc = sja1105_change_tpid(priv, ETH_P_SJA1105, ETH_P_SJA1105); + if (rc) + dev_err(ds->dev, "Failed to change VLAN Ethertype\n"); + + return rc; +} + +static void sja1105_vlan_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct sja1105_private *priv = ds->priv; + u16 vid; + int rc; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { + rc = sja1105_vlan_apply(priv, port, vid, true, vlan->flags & + BRIDGE_VLAN_INFO_UNTAGGED); + if (rc < 0) { + dev_err(ds->dev, "Failed to add VLAN %d to port %d: %d\n", + vid, port, rc); + return; + } + if (vlan->flags & BRIDGE_VLAN_INFO_PVID) { + rc = sja1105_pvid_apply(ds->priv, port, vid); + if (rc < 0) { + dev_err(ds->dev, "Failed to set pvid %d on port %d: %d\n", + vid, port, rc); + return; + } + } + } +} + +static int sja1105_vlan_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct sja1105_private *priv = ds->priv; + u16 vid; + int rc; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { + rc = sja1105_vlan_apply(priv, port, vid, false, vlan->flags & + BRIDGE_VLAN_INFO_UNTAGGED); + if (rc < 0) { + dev_err(ds->dev, "Failed to remove VLAN %d from port %d: %d\n", + vid, port, rc); + return rc; + } + } + return 0; +} + /* The programming model for the SJA1105 switch is "all-at-once" via static * configuration tables. Some of these can be dynamically modified at runtime, * but not the xMII mode parameters table. @@ -1005,6 +1236,15 @@ static int sja1105_setup(struct dsa_switch *ds) dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc); return rc; } + /* On SJA1105, VLAN filtering per se is always enabled in hardware. + * The only thing we can do to disable it is lie about what the 802.1Q + * EtherType is. + * So it will still try to apply VLAN filtering, but all ingress + * traffic (except frames received with EtherType of ETH_P_SJA1105) + * will be internally tagged with a distorted VLAN header where the + * TPID is ETH_P_SJA1105, and the VLAN ID is the port pvid. + */ + ds->vlan_filtering_is_global = true; return 0; } @@ -1018,6 +1258,10 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .port_fdb_del = sja1105_fdb_del, .port_bridge_join = sja1105_bridge_join, .port_bridge_leave = sja1105_bridge_leave, + .port_vlan_prepare = sja1105_vlan_prepare, + .port_vlan_filtering = sja1105_vlan_filtering, + .port_vlan_add = sja1105_vlan_add, + .port_vlan_del = sja1105_vlan_del, .port_mdb_prepare = sja1105_mdb_prepare, .port_mdb_add = sja1105_mdb_add, .port_mdb_del = sja1105_mdb_del, diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 84ee623c6336..b3c992b0abb0 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -947,3 +947,41 @@ void sja1105_static_config_free(struct sja1105_static_config *config) } } } + +int sja1105_table_delete_entry(struct sja1105_table *table, int i) +{ + size_t entry_size = table->ops->unpacked_entry_size; + u8 *entries = table->entries; + + if (i > table->entry_count) + return -ERANGE; + + memmove(entries + i * entry_size, entries + (i + 1) * entry_size, + (table->entry_count - i) * entry_size); + + table->entry_count--; + + return 0; +} + +/* No pointers to table->entries should be kept when this is called. */ +int sja1105_table_resize(struct sja1105_table *table, size_t new_count) +{ + size_t entry_size = table->ops->unpacked_entry_size; + void *new_entries, *old_entries = table->entries; + + if (new_count > table->ops->max_entry_count) + return -ERANGE; + + new_entries = kcalloc(new_count, entry_size, GFP_KERNEL); + if (!new_entries) + return -ENOMEM; + + memcpy(new_entries, old_entries, min(new_count, table->entry_count) * + entry_size); + + table->entries = new_entries; + table->entry_count = new_count; + kfree(old_entries); + return 0; +} diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index 7b0a02fe3147..069ca8fd059c 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -240,6 +240,9 @@ int sja1105_static_config_init(struct sja1105_static_config *config, u64 device_id); void sja1105_static_config_free(struct sja1105_static_config *config); +int sja1105_table_delete_entry(struct sja1105_table *table, int i); +int sja1105_table_resize(struct sja1105_table *table, size_t new_count); + u32 sja1105_crc32(const void *buf, size_t len); void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 30559d1d0e1b..abf3977e34fd 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -7,6 +7,10 @@ #ifndef _NET_DSA_SJA1105_H #define _NET_DSA_SJA1105_H +#include + +#define ETH_P_SJA1105 ETH_P_DSA_8021Q + /* The switch can only be convinced to stay in unmanaged mode and not trap any * link-local traffic by actually telling it to filter frames sent at the * 00:00:00:00:00:00 destination MAC. -- cgit v1.2.3-71-gd317 From a27415decd84dac124c6185f1184b6c779d0a5ab Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 1 May 2019 00:10:50 +0200 Subject: net: dsa: mv88e6xxx: Pass interrupt number in platform data Allow an interrupt number to be passed in the platform data. The driver will then use it if not zero, otherwise it will poll for interrupts. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 13 +++++++++---- include/linux/platform_data/mv88e6xxx.h | 1 + 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 46020fe1b5e7..bad30be699bf 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -4894,12 +4894,17 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) if (err) goto out; - chip->irq = of_irq_get(np, 0); - if (chip->irq == -EPROBE_DEFER) { - err = chip->irq; - goto out; + if (np) { + chip->irq = of_irq_get(np, 0); + if (chip->irq == -EPROBE_DEFER) { + err = chip->irq; + goto out; + } } + if (pdata) + chip->irq = pdata->irq; + /* Has to be performed before the MDIO bus is created, because * the PHYs will link their interrupts to these interrupt * controllers diff --git a/include/linux/platform_data/mv88e6xxx.h b/include/linux/platform_data/mv88e6xxx.h index 963730b44aea..21452a9365e1 100644 --- a/include/linux/platform_data/mv88e6xxx.h +++ b/include/linux/platform_data/mv88e6xxx.h @@ -13,6 +13,7 @@ struct dsa_mv88e6xxx_pdata { unsigned int enabled_ports; struct net_device *netdev; u32 eeprom_len; + int irq; }; #endif -- cgit v1.2.3-71-gd317 From 22c0ef6b1475aef4765efc4aa764b8580018123c Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 1 May 2019 21:34:43 +0200 Subject: net: phy: improve pause handling When probing the phy device we set sym and asym pause in the "supported" bitmap (unless the PHY tells us otherwise). However we don't know yet whether the MAC supports pause. Simply copying phy->supported to phy->advertising will trigger advertising pause, and that's not what we want. Therefore add phy_advertise_supported() that copies all modes but doesn't touch the pause bits. In phy_support_(a)sym_pause we shouldn't set any bits in the supported bitmap because we may set a bit the PHY intentionally disabled. Effective pause support should be the AND-combined PHY and MAC pause capabilities. If the MAC supports everything, then it's only relevant what the PHY supports. If MAC supports sym pause only, then we have to clear the asym bit in phydev->supported. Copy the pause flags only and don't touch the modes, because a driver may have intentionally removed a mode from phydev->advertising. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/fixed_phy.c | 2 +- drivers/net/phy/phy-core.c | 2 +- drivers/net/phy/phy_device.c | 36 +++++++++++++++++++++++++++++------- include/linux/phy.h | 1 + 4 files changed, 32 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 1acd8bfdb3bc..3ffe46df249e 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -301,7 +301,7 @@ static struct phy_device *__fixed_phy_register(unsigned int irq, phy->supported); } - linkmode_copy(phy->advertising, phy->supported); + phy_advertise_supported(phy); ret = phy_device_register(phy); if (ret) { diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 12ce671020a5..3daf0214a242 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -228,7 +228,7 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) if (err) return err; - linkmode_copy(phydev->advertising, phydev->supported); + phy_advertise_supported(phydev); return 0; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2a2aaa5f3e74..068ab750c9ce 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1985,10 +1985,35 @@ EXPORT_SYMBOL(genphy_loopback); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode) { linkmode_clear_bit(link_mode, phydev->supported); - linkmode_copy(phydev->advertising, phydev->supported); + phy_advertise_supported(phydev); } EXPORT_SYMBOL(phy_remove_link_mode); +static void phy_copy_pause_bits(unsigned long *dst, unsigned long *src) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, dst, + linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, src)); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, dst, + linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, src)); +} + +/** + * phy_advertise_supported - Advertise all supported modes + * @phydev: target phy_device struct + * + * Description: Called to advertise all supported modes, doesn't touch + * pause mode advertising. + */ +void phy_advertise_supported(struct phy_device *phydev) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(new); + + linkmode_copy(new, phydev->supported); + phy_copy_pause_bits(new, phydev->advertising); + linkmode_copy(phydev->advertising, new); +} +EXPORT_SYMBOL(phy_advertise_supported); + /** * phy_support_sym_pause - Enable support of symmetrical pause * @phydev: target phy_device struct @@ -1999,8 +2024,7 @@ EXPORT_SYMBOL(phy_remove_link_mode); void phy_support_sym_pause(struct phy_device *phydev) { linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported); - linkmode_copy(phydev->advertising, phydev->supported); + phy_copy_pause_bits(phydev->advertising, phydev->supported); } EXPORT_SYMBOL(phy_support_sym_pause); @@ -2012,9 +2036,7 @@ EXPORT_SYMBOL(phy_support_sym_pause); */ void phy_support_asym_pause(struct phy_device *phydev) { - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported); - linkmode_copy(phydev->advertising, phydev->supported); + phy_copy_pause_bits(phydev->advertising, phydev->supported); } EXPORT_SYMBOL(phy_support_asym_pause); @@ -2177,7 +2199,7 @@ static int phy_probe(struct device *dev) phydev->is_gigabit_capable = 1; of_set_phy_supported(phydev); - linkmode_copy(phydev->advertising, phydev->supported); + phy_advertise_supported(phydev); /* Get the EEE modes we want to prohibit. We will ask * the PHY stop advertising these mode later on diff --git a/include/linux/phy.h b/include/linux/phy.h index 0f9552b17ee7..4a03f8a46d33 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1154,6 +1154,7 @@ void phy_request_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, -- cgit v1.2.3-71-gd317 From f24098f80748ea95d53603a7bb7954a41bb3ca1b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 1 May 2019 22:14:21 +0200 Subject: net: phy: improve resuming from hibernation I got an interesting report [0] that after resuming from hibernation the link has 100Mbps instead of 1Gbps. Reason is that another OS has been used whilst Linux was hibernated. And this OS speeds down the link due to WoL. Therefore, when resuming, we shouldn't expect that what the PHY advertises is what it did when hibernating. Easiest way to do this is removing state PHY_RESUMING. Instead always go via PHY_UP that configures PHY advertisement. [0] https://bugzilla.kernel.org/show_bug.cgi?id=202851 Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 7 +------ include/linux/phy.h | 9 +-------- 2 files changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 984de987241c..1a146c5c5036 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -43,7 +43,6 @@ static const char *phy_state_to_str(enum phy_state st) PHY_STATE_STR(NOLINK) PHY_STATE_STR(FORCING) PHY_STATE_STR(HALTED) - PHY_STATE_STR(RESUMING) } return NULL; @@ -859,10 +858,7 @@ void phy_start(struct phy_device *phydev) goto out; } - if (phydev->state == PHY_READY) - phydev->state = PHY_UP; - else - phydev->state = PHY_RESUMING; + phydev->state = PHY_UP; phy_start_machine(phydev); out: @@ -897,7 +893,6 @@ void phy_state_machine(struct work_struct *work) break; case PHY_NOLINK: case PHY_RUNNING: - case PHY_RESUMING: err = phy_check_link_status(phydev); break; case PHY_FORCING: diff --git a/include/linux/phy.h b/include/linux/phy.h index 4a03f8a46d33..073fb151b5a9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -308,13 +308,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * * HALTED: PHY is up, but no polling or interrupts are done. Or * PHY is in an error state. - * - * - phy_start moves to RESUMING - * - * RESUMING: PHY was halted, but now wants to run again. - * - If we are forcing, or aneg is done, timer moves to RUNNING - * - If aneg is not done, timer moves to AN - * - phy_stop moves to HALTED + * - phy_start moves to UP */ enum phy_state { PHY_DOWN = 0, @@ -324,7 +318,6 @@ enum phy_state { PHY_RUNNING, PHY_NOLINK, PHY_FORCING, - PHY_RESUMING }; /** -- cgit v1.2.3-71-gd317 From 522e4077e8dcdfc5b8e96469d3bc2324bc5d6466 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Sun, 28 Apr 2019 15:12:19 +0800 Subject: netfilter: slightly optimize nf_inet_addr_mask using 64bit computation to slightly optimize nf_inet_addr_mask Signed-off-by: Li RongQing Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index a7252f3baeb0..996bc247ef6e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -41,10 +41,19 @@ static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, union nf_inet_addr *result, const union nf_inet_addr *mask) { +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + const unsigned long *ua = (const unsigned long *)a1; + unsigned long *ur = (unsigned long *)result; + const unsigned long *um = (const unsigned long *)mask; + + ur[0] = ua[0] & um[0]; + ur[1] = ua[1] & um[1]; +#else result->all[0] = a1->all[0] & mask->all[0]; result->all[1] = a1->all[1] & mask->all[1]; result->all[2] = a1->all[2] & mask->all[2]; result->all[3] = a1->all[3] & mask->all[3]; +#endif } int netfilter_init(void); -- cgit v1.2.3-71-gd317 From f9bbe4477c30ece44296437ee26142b42ef8070b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 May 2019 13:19:22 +0300 Subject: net: dsa: Optional VLAN-based port separation for switches without tagging This patch provides generic DSA code for using VLAN (802.1Q) tags for the same purpose as a dedicated switch tag for injection/extraction. It is based on the discussions and interest that has been so far expressed in https://www.spinics.net/lists/netdev/msg556125.html. Unlike all other DSA-supported tagging protocols, CONFIG_NET_DSA_TAG_8021Q does not offer a complete solution for drivers (nor can it). Instead, it provides generic code that driver can opt into calling: - dsa_8021q_xmit: Inserts a VLAN header with the specified contents. Can be called from another tagging protocol's xmit function. Currently the LAN9303 driver is inserting headers that are simply 802.1Q with custom fields, so this is an opportunity for code reuse. - dsa_8021q_rcv: Retrieves the TPID and TCI from a VLAN-tagged skb. Removing the VLAN header is left as a decision for the caller to make. - dsa_port_setup_8021q_tagging: For each user port, installs an Rx VID and a Tx VID, for proper untagged traffic identification on ingress and steering on egress. Also sets up the VLAN trunk on the upstream (CPU or DSA) port. Drivers are intentionally left to call this function explicitly, depending on the context and hardware support. The expected switch behavior and VLAN semantics should not be violated under any conditions. That is, after calling dsa_port_setup_8021q_tagging, the hardware should still pass all ingress traffic, be it tagged or untagged. For uniformity with the other tagging protocols, a module for the dsa_8021q_netdev_ops structure is registered, but the typical usage is to set up another tagging protocol which selects CONFIG_NET_DSA_TAG_8021Q, and calls the API from tag_8021q.h. Null function definitions are also provided so that a "depends on" is not forced in the Kconfig. This tagging protocol only works when switch ports are standalone, or when they are added to a VLAN-unaware bridge. It will probably remain this way for the reasons below. When added to a bridge that has vlan_filtering 1, the bridge core will install its own VLANs and reset the pvids through switchdev. For the bridge core, switchdev is a write-only pipe. All VLAN-related state is kept in the bridge core and nothing is read from DSA/switchdev or from the driver. So the bridge core will break this port separation because it will install the vlan_default_pvid into all switchdev ports. Even if we could teach the bridge driver about switchdev preference of a certain vlan_default_pvid (task difficult in itself since the current setting is per-bridge but we would need it per-port), there would still exist many other challenges. Firstly, in the DSA rcv callback, a driver would have to perform an iterative reverse lookup to find the correct switch port. That is because the port is a bridge slave, so its Rx VID (port PVID) is subject to user configuration. How would we ensure that the user doesn't reset the pvid to a different value (which would make an O(1) translation impossible), or to a non-unique value within this DSA switch tree (which would make any translation impossible)? Finally, not all switch ports are equal in DSA, and that makes it difficult for the bridge to be completely aware of this anyway. The CPU port needs to transmit tagged packets (VLAN trunk) in order for the DSA rcv code to be able to decode source information. But the bridge code has absolutely no idea which switch port is the CPU port, if nothing else then just because there is no netdevice registered by DSA for the CPU port. Also DSA does not currently allow the user to specify that they want the CPU port to do VLAN trunking anyway. VLANs are added to the CPU port using the same flags as they were added on the user port. So the VLANs installed by dsa_port_setup_8021q_tagging per driver request should remain private from the bridge's and user's perspective, and should not alter the VLAN semantics observed by the user. In the current implementation a VLAN range ending at 4095 (VLAN_N_VID) is reserved for this purpose. Each port receives a unique Rx VLAN and a unique Tx VLAN. Separate VLANs are needed for Rx and Tx because they serve different purposes: on Rx the switch must process traffic as untagged and process it with a port-based VLAN, but with care not to hinder bridging. On the other hand, the Tx VLAN is where the reachability restrictions are imposed, since by tagging frames in the xmit callback we are telling the switch onto which port to steer the frame. Some general guidance on how this support might be employed for real-life hardware (some comments made by Florian Fainelli): - If the hardware supports VLAN tag stacking, it should somehow back up its private VLAN settings when the bridge tries to override them. Then the driver could re-apply them as outer tags. Dedicating an outer tag per bridge device would allow identical inner tag VID numbers to co-exist, yet preserve broadcast domain isolation. - If the switch cannot handle VLAN tag stacking, it should disable this port separation when added as slave to a vlan_filtering bridge, in that case having reduced functionality. - Drivers for old switches that don't support the entire VLAN_N_VID range will need to rework the current range selection mechanism. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 76 ++++++++++++++++ include/net/dsa.h | 2 + net/dsa/Kconfig | 11 +++ net/dsa/Makefile | 1 + net/dsa/tag_8021q.c | 222 ++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 312 insertions(+) create mode 100644 include/linux/dsa/8021q.h create mode 100644 net/dsa/tag_8021q.c (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h new file mode 100644 index 000000000000..3911e0586478 --- /dev/null +++ b/include/linux/dsa/8021q.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2019, Vladimir Oltean + */ + +#ifndef _NET_DSA_8021Q_H +#define _NET_DSA_8021Q_H + +#include + +struct dsa_switch; +struct sk_buff; +struct net_device; +struct packet_type; + +#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) + +int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, + bool enabled); + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci); + +struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, + struct packet_type *pt, u16 *tpid, u16 *tci); + +u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); + +u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); + +int dsa_8021q_rx_switch_id(u16 vid); + +int dsa_8021q_rx_source_port(u16 vid); + +#else + +int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, + bool enabled) +{ + return 0; +} + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci) +{ + return NULL; +} + +struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, + struct packet_type *pt, u16 *tpid, u16 *tci) +{ + return NULL; +} + +u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) +{ + return 0; +} + +u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) +{ + return 0; +} + +int dsa_8021q_rx_switch_id(u16 vid) +{ + return 0; +} + +int dsa_8021q_rx_source_port(u16 vid) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ + +#endif /* _NET_DSA_8021Q_H */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 18db7b8e7a8e..69f3714f42ba 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -42,6 +42,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 +#define DSA_TAG_PROTO_8021Q_VALUE 12 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -56,6 +57,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, + DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, }; struct packet_type; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index c0734028c7dc..fc15a7e1a6df 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -17,6 +17,17 @@ menuconfig NET_DSA if NET_DSA +# tagging formats +config NET_DSA_TAG_8021Q + tristate "Tag driver for switches using custom 802.1Q VLAN headers" + select VLAN_8021Q + help + Unlike the other tagging protocols, the 802.1Q config option simply + provides helpers for other tagging implementations that might rely on + VLAN in one way or another. It is not a complete solution. + + Drivers which use these helpers should select this as dependency. + config NET_DSA_TAG_BRCM_COMMON tristate default n diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 8a737b6ee94c..e97c794ec57b 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_NET_DSA) += dsa_core.o dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o # tagging formats +obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c new file mode 100644 index 000000000000..8ae48c7e1e76 --- /dev/null +++ b/net/dsa/tag_8021q.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019, Vladimir Oltean + * + * This module is not a complete tagger implementation. It only provides + * primitives for taggers that rely on 802.1Q VLAN tags to use. The + * dsa_8021q_netdev_ops is registered for API compliance and not used + * directly by callers. + */ +#include +#include + +#include "dsa_priv.h" + +/* Allocating two VLAN tags per port - one for the RX VID and + * the other for the TX VID - see below + */ +#define DSA_8021Q_VID_RANGE (DSA_MAX_SWITCHES * DSA_MAX_PORTS) +#define DSA_8021Q_VID_BASE (VLAN_N_VID - 2 * DSA_8021Q_VID_RANGE - 1) +#define DSA_8021Q_RX_VID_BASE (DSA_8021Q_VID_BASE) +#define DSA_8021Q_TX_VID_BASE (DSA_8021Q_VID_BASE + DSA_8021Q_VID_RANGE) + +/* Returns the VID to be inserted into the frame from xmit for switch steering + * instructions on egress. Encodes switch ID and port ID. + */ +u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) +{ + return DSA_8021Q_TX_VID_BASE + (DSA_MAX_PORTS * ds->index) + port; +} +EXPORT_SYMBOL_GPL(dsa_8021q_tx_vid); + +/* Returns the VID that will be installed as pvid for this switch port, sent as + * tagged egress towards the CPU port and decoded by the rcv function. + */ +u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) +{ + return DSA_8021Q_RX_VID_BASE + (DSA_MAX_PORTS * ds->index) + port; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid); + +/* Returns the decoded switch ID from the RX VID. */ +int dsa_8021q_rx_switch_id(u16 vid) +{ + return ((vid - DSA_8021Q_RX_VID_BASE) / DSA_MAX_PORTS); +} +EXPORT_SYMBOL_GPL(dsa_8021q_rx_switch_id); + +/* Returns the decoded port ID from the RX VID. */ +int dsa_8021q_rx_source_port(u16 vid) +{ + return ((vid - DSA_8021Q_RX_VID_BASE) % DSA_MAX_PORTS); +} +EXPORT_SYMBOL_GPL(dsa_8021q_rx_source_port); + +/* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single + * front-panel switch port (here swp0). + * + * Port identification through VLAN (802.1Q) tags has different requirements + * for it to work effectively: + * - On RX (ingress from network): each front-panel port must have a pvid + * that uniquely identifies it, and the egress of this pvid must be tagged + * towards the CPU port, so that software can recover the source port based + * on the VID in the frame. But this would only work for standalone ports; + * if bridged, this VLAN setup would break autonomous forwarding and would + * force all switched traffic to pass through the CPU. So we must also make + * the other front-panel ports members of this VID we're adding, albeit + * we're not making it their PVID (they'll still have their own). + * By the way - just because we're installing the same VID in multiple + * switch ports doesn't mean that they'll start to talk to one another, even + * while not bridged: the final forwarding decision is still an AND between + * the L2 forwarding information (which is limiting forwarding in this case) + * and the VLAN-based restrictions (of which there are none in this case, + * since all ports are members). + * - On TX (ingress from CPU and towards network) we are faced with a problem. + * If we were to tag traffic (from within DSA) with the port's pvid, all + * would be well, assuming the switch ports were standalone. Frames would + * have no choice but to be directed towards the correct front-panel port. + * But because we also want the RX VLAN to not break bridging, then + * inevitably that means that we have to give them a choice (of what + * front-panel port to go out on), and therefore we cannot steer traffic + * based on the RX VID. So what we do is simply install one more VID on the + * front-panel and CPU ports, and profit off of the fact that steering will + * work just by virtue of the fact that there is only one other port that's + * a member of the VID we're tagging the traffic with - the desired one. + * + * So at the end, each front-panel port will have one RX VID (also the PVID), + * the RX VID of all other front-panel ports, and one TX VID. Whereas the CPU + * port will have the RX and TX VIDs of all front-panel ports, and on top of + * that, is also tagged-input and tagged-output (VLAN trunk). + * + * CPU port CPU port + * +-------------+-----+-------------+ +-------------+-----+-------------+ + * | RX VID | | | | TX VID | | | + * | of swp0 | | | | of swp0 | | | + * | +-----+ | | +-----+ | + * | ^ T | | | Tagged | + * | | | | | ingress | + * | +-------+---+---+-------+ | | +-----------+ | + * | | | | | | | | Untagged | + * | | U v U v U v | | v egress | + * | +-----+ +-----+ +-----+ +-----+ | | +-----+ +-----+ +-----+ +-----+ | + * | | | | | | | | | | | | | | | | | | | | + * | |PVID | | | | | | | | | | | | | | | | | | + * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ + * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 + */ +int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) +{ + int upstream = dsa_upstream_port(ds, port); + struct dsa_port *dp = &ds->ports[port]; + struct dsa_port *upstream_dp = &ds->ports[upstream]; + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + u16 tx_vid = dsa_8021q_tx_vid(ds, port); + int i, err; + + /* The CPU port is implicitly configured by + * configuring the front-panel ports + */ + if (!dsa_is_user_port(ds, port)) + return 0; + + /* Add this user port's RX VID to the membership list of all others + * (including itself). This is so that bridging will not be hindered. + * L2 forwarding rules still take precedence when there are no VLAN + * restrictions, so there are no concerns about leaking traffic. + */ + for (i = 0; i < ds->num_ports; i++) { + struct dsa_port *other_dp = &ds->ports[i]; + u16 flags; + + if (i == upstream) + /* CPU port needs to see this port's RX VID + * as tagged egress. + */ + flags = 0; + else if (i == port) + /* The RX VID is pvid on this port */ + flags = BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_PVID; + else + /* The RX VID is a regular VLAN on all others */ + flags = BRIDGE_VLAN_INFO_UNTAGGED; + + if (enabled) + err = dsa_port_vid_add(other_dp, rx_vid, flags); + else + err = dsa_port_vid_del(other_dp, rx_vid); + if (err) { + dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", + rx_vid, port, err); + return err; + } + } + /* Finally apply the TX VID on this port and on the CPU port */ + if (enabled) + err = dsa_port_vid_add(dp, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED); + else + err = dsa_port_vid_del(dp, tx_vid); + if (err) { + dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + tx_vid, port, err); + return err; + } + if (enabled) + err = dsa_port_vid_add(upstream_dp, tx_vid, 0); + else + err = dsa_port_vid_del(upstream_dp, tx_vid); + if (err) { + dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + tx_vid, upstream, err); + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging); + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci) +{ + /* skb->data points at skb_mac_header, which + * is fine for vlan_insert_tag. + */ + return vlan_insert_tag(skb, htons(tpid), tci); +} +EXPORT_SYMBOL_GPL(dsa_8021q_xmit); + +struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, + struct packet_type *pt, u16 *tpid, u16 *tci) +{ + struct vlan_ethhdr *tag; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + return NULL; + + tag = vlan_eth_hdr(skb); + *tpid = ntohs(tag->h_vlan_proto); + *tci = ntohs(tag->h_vlan_TCI); + + /* skb->data points in the middle of the VLAN tag, + * after tpid and before tci. This is because so far, + * ETH_HLEN (DMAC, SMAC, EtherType) bytes were pulled. + * There are 2 bytes of VLAN tag left in skb->data, and upper + * layers expect the 'real' EtherType to be consumed as well. + * Coincidentally, a VLAN header is also of the same size as + * the number of bytes that need to be pulled. + */ + skb_pull_rcsum(skb, VLAN_HLEN); + + return skb; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rcv); + +static const struct dsa_device_ops dsa_8021q_netdev_ops = { + .name = "8021q", + .proto = DSA_TAG_PROTO_8021Q, + .overhead = VLAN_HLEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_8021Q); + +module_dsa_tag_driver(dsa_8021q_netdev_ops); -- cgit v1.2.3-71-gd317 From 227d07a07ef126272ea2eed97fd136cd7a803d81 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 May 2019 13:19:27 +0300 Subject: net: dsa: sja1105: Add support for traffic through standalone ports In order to support this, we are creating a make-shift switch tag out of a VLAN trunk configured on the CPU port. Termination of normal traffic on switch ports only works when not under a vlan_filtering bridge. Termination of management (PTP, BPDU) traffic works under all circumstances because it uses a different tagging mechanism (incl_srcpt). We are making use of the generic CONFIG_NET_DSA_TAG_8021Q code and leveraging it from our own CONFIG_NET_DSA_TAG_SJA1105. There are two types of traffic: regular and link-local. The link-local traffic received on the CPU port is trapped from the switch's regular forwarding decisions because it matched one of the two DMAC filters for management traffic. On transmission, the switch requires special massaging for these link-local frames. Due to a weird implementation of the switching IP, by default it drops link-local frames that originate on the CPU port. It needs to be told where to forward them to, through an SPI command ("management route") that is valid for only a single frame. So when we're sending link-local traffic, we are using the dsa_defer_xmit mechanism. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/Kconfig | 1 + drivers/net/dsa/sja1105/sja1105.h | 6 ++ drivers/net/dsa/sja1105/sja1105_main.c | 138 +++++++++++++++++++++++++++++++-- include/linux/dsa/sja1105.h | 35 ++++++--- include/net/dsa.h | 2 + net/dsa/Kconfig | 9 +++ net/dsa/Makefile | 1 + net/dsa/tag_sja1105.c | 131 +++++++++++++++++++++++++++++++ 8 files changed, 308 insertions(+), 15 deletions(-) create mode 100644 net/dsa/tag_sja1105.c (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index 038685bb9d57..757751a89819 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -1,6 +1,7 @@ config NET_DSA_SJA1105 tristate "NXP SJA1105 Ethernet switch family support" depends on NET_DSA && SPI + select NET_DSA_TAG_SJA1105 select PACKING select CRC32 help diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index b0a155b57e17..b043bfc408f2 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -7,6 +7,7 @@ #include #include +#include #include "sja1105_static_config.h" #define SJA1105_NUM_PORTS 5 @@ -65,6 +66,11 @@ struct sja1105_private { struct gpio_desc *reset_gpio; struct spi_device *spidev; struct dsa_switch *ds; + struct sja1105_port ports[SJA1105_NUM_PORTS]; + /* Serializes transmission of management frames so that + * the switch doesn't confuse them with one another. + */ + struct mutex mgmt_lock; }; #include "sja1105_dynamic_config.h" diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 74f8ff9e17e0..785bb42cb993 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "sja1105.h" static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len, @@ -406,11 +407,14 @@ static int sja1105_init_general_params(struct sja1105_private *priv) .tpid2 = ETH_P_SJA1105, }; struct sja1105_table *table; - int i; + int i, k = 0; - for (i = 0; i < SJA1105_NUM_PORTS; i++) + for (i = 0; i < SJA1105_NUM_PORTS; i++) { if (dsa_is_dsa_port(priv->ds, i)) default_general_params.casc_port = i; + else if (dsa_is_user_port(priv->ds, i)) + priv->ports[i].mgmt_slot = k++; + } table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; @@ -1146,10 +1150,27 @@ static int sja1105_vlan_apply(struct sja1105_private *priv, int port, u16 vid, return 0; } +static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled) +{ + int rc, i; + + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + rc = dsa_port_setup_8021q_tagging(ds, i, enabled); + if (rc < 0) { + dev_err(ds->dev, "Failed to setup VLAN tagging for port %d: %d\n", + i, rc); + return rc; + } + } + dev_info(ds->dev, "%s switch tagging\n", + enabled ? "Enabled" : "Disabled"); + return 0; +} + static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port) { - return DSA_TAG_PROTO_NONE; + return DSA_TAG_PROTO_SJA1105; } /* This callback needs to be present */ @@ -1173,7 +1194,11 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) if (rc) dev_err(ds->dev, "Failed to change VLAN Ethertype\n"); - return rc; + /* Switch port identification based on 802.1Q is only passable + * if we are not under a vlan_filtering bridge. So make sure + * the two configurations are mutually exclusive. + */ + return sja1105_setup_8021q_tagging(ds, !enabled); } static void sja1105_vlan_add(struct dsa_switch *ds, int port, @@ -1276,7 +1301,98 @@ static int sja1105_setup(struct dsa_switch *ds) */ ds->vlan_filtering_is_global = true; - return 0; + /* The DSA/switchdev model brings up switch ports in standalone mode by + * default, and that means vlan_filtering is 0 since they're not under + * a bridge, so it's safe to set up switch tagging at this time. + */ + return sja1105_setup_8021q_tagging(ds, true); +} + +static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, + struct sk_buff *skb) +{ + struct sja1105_mgmt_entry mgmt_route = {0}; + struct sja1105_private *priv = ds->priv; + struct ethhdr *hdr; + int timeout = 10; + int rc; + + hdr = eth_hdr(skb); + + mgmt_route.macaddr = ether_addr_to_u64(hdr->h_dest); + mgmt_route.destports = BIT(port); + mgmt_route.enfport = 1; + + rc = sja1105_dynamic_config_write(priv, BLK_IDX_MGMT_ROUTE, + slot, &mgmt_route, true); + if (rc < 0) { + kfree_skb(skb); + return rc; + } + + /* Transfer skb to the host port. */ + dsa_enqueue_skb(skb, ds->ports[port].slave); + + /* Wait until the switch has processed the frame */ + do { + rc = sja1105_dynamic_config_read(priv, BLK_IDX_MGMT_ROUTE, + slot, &mgmt_route); + if (rc < 0) { + dev_err_ratelimited(priv->ds->dev, + "failed to poll for mgmt route\n"); + continue; + } + + /* UM10944: The ENFPORT flag of the respective entry is + * cleared when a match is found. The host can use this + * flag as an acknowledgment. + */ + cpu_relax(); + } while (mgmt_route.enfport && --timeout); + + if (!timeout) { + /* Clean up the management route so that a follow-up + * frame may not match on it by mistake. + */ + sja1105_dynamic_config_write(priv, BLK_IDX_MGMT_ROUTE, + slot, &mgmt_route, false); + dev_err_ratelimited(priv->ds->dev, "xmit timed out\n"); + } + + return NETDEV_TX_OK; +} + +/* Deferred work is unfortunately necessary because setting up the management + * route cannot be done from atomit context (SPI transfer takes a sleepable + * lock on the bus) + */ +static netdev_tx_t sja1105_port_deferred_xmit(struct dsa_switch *ds, int port, + struct sk_buff *skb) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_port *sp = &priv->ports[port]; + int slot = sp->mgmt_slot; + + /* The tragic fact about the switch having 4x2 slots for installing + * management routes is that all of them except one are actually + * useless. + * If 2 slots are simultaneously configured for two BPDUs sent to the + * same (multicast) DMAC but on different egress ports, the switch + * would confuse them and redirect first frame it receives on the CPU + * port towards the port configured on the numerically first slot + * (therefore wrong port), then second received frame on second slot + * (also wrong port). + * So for all practical purposes, there needs to be a lock that + * prevents that from happening. The slot used here is utterly useless + * (could have simply been 0 just as fine), but we are doing it + * nonetheless, in case a smarter idea ever comes up in the future. + */ + mutex_lock(&priv->mgmt_lock); + + sja1105_mgmt_xmit(ds, port, slot, skb); + + mutex_unlock(&priv->mgmt_lock); + return NETDEV_TX_OK; } /* The MAXAGE setting belongs to the L2 Forwarding Parameters table, @@ -1324,6 +1440,7 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .port_mdb_prepare = sja1105_mdb_prepare, .port_mdb_add = sja1105_mdb_add, .port_mdb_del = sja1105_mdb_del, + .port_deferred_xmit = sja1105_port_deferred_xmit, }; static int sja1105_check_device_id(struct sja1105_private *priv) @@ -1367,7 +1484,7 @@ static int sja1105_probe(struct spi_device *spi) struct device *dev = &spi->dev; struct sja1105_private *priv; struct dsa_switch *ds; - int rc; + int rc, i; if (!dev->of_node) { dev_err(dev, "No DTS bindings for SJA1105 driver\n"); @@ -1418,6 +1535,15 @@ static int sja1105_probe(struct spi_device *spi) ds->priv = priv; priv->ds = ds; + /* Connections between dsa_port and sja1105_port */ + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + struct sja1105_port *sp = &priv->ports[i]; + + ds->ports[i].priv = sp; + sp->dp = &ds->ports[i]; + } + mutex_init(&priv->mgmt_lock); + return dsa_register_switch(priv->ds); } diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index abf3977e34fd..603a02e5a8cb 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -2,22 +2,39 @@ * Copyright (c) 2019, Vladimir Oltean */ -/* Included by drivers/net/dsa/sja1105/sja1105.h */ +/* Included by drivers/net/dsa/sja1105/sja1105.h and net/dsa/tag_sja1105.c */ #ifndef _NET_DSA_SJA1105_H #define _NET_DSA_SJA1105_H +#include #include +#include #define ETH_P_SJA1105 ETH_P_DSA_8021Q -/* The switch can only be convinced to stay in unmanaged mode and not trap any - * link-local traffic by actually telling it to filter frames sent at the - * 00:00:00:00:00:00 destination MAC. - */ -#define SJA1105_LINKLOCAL_FILTER_A 0x000000000000ull -#define SJA1105_LINKLOCAL_FILTER_A_MASK 0xFFFFFFFFFFFFull -#define SJA1105_LINKLOCAL_FILTER_B 0x000000000000ull -#define SJA1105_LINKLOCAL_FILTER_B_MASK 0xFFFFFFFFFFFFull +/* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ +#define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull +#define SJA1105_LINKLOCAL_FILTER_A_MASK 0xFFFFFF000000ull +/* IEEE 1588 Annex F: Transport of PTP over Ethernet (01:1B:19:xx:xx:xx) */ +#define SJA1105_LINKLOCAL_FILTER_B 0x011B19000000ull +#define SJA1105_LINKLOCAL_FILTER_B_MASK 0xFFFFFF000000ull + +enum sja1105_frame_type { + SJA1105_FRAME_TYPE_NORMAL = 0, + SJA1105_FRAME_TYPE_LINK_LOCAL, +}; + +struct sja1105_skb_cb { + enum sja1105_frame_type type; +}; + +#define SJA1105_SKB_CB(skb) \ + ((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb)) + +struct sja1105_port { + struct dsa_port *dp; + int mgmt_slot; +}; #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/net/dsa.h b/include/net/dsa.h index e20be1ceb306..6aaaadd6a413 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -43,6 +43,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 +#define DSA_TAG_PROTO_SJA1105_VALUE 13 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -58,6 +59,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, + DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, }; struct packet_type; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index fc15a7e1a6df..cf855352a440 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -102,6 +102,15 @@ config NET_DSA_TAG_LAN9303 Say Y or M if you want to enable support for tagging frames for the SMSC/Microchip LAN9303 family of switches. +config NET_DSA_TAG_SJA1105 + tristate "Tag driver for NXP SJA1105 switches" + select NET_DSA_TAG_8021Q + help + Say Y or M if you want to enable support for tagging frames with the + NXP SJA1105 switch family. Both the native tagging protocol (which + is only for link-local traffic) as well as non-native tagging (based + on a custom 802.1Q VLAN header) are available. + config NET_DSA_TAG_TRAILER tristate "Tag driver for switches using a trailer tag" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index e97c794ec57b..c342f54715ba 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -13,4 +13,5 @@ obj-$(CONFIG_NET_DSA_TAG_KSZ_COMMON) += tag_ksz.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o +obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c new file mode 100644 index 000000000000..969402c7dbf1 --- /dev/null +++ b/net/dsa/tag_sja1105.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019, Vladimir Oltean + */ +#include +#include +#include +#include +#include "dsa_priv.h" + +/* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ +static inline bool sja1105_is_link_local(const struct sk_buff *skb) +{ + const struct ethhdr *hdr = eth_hdr(skb); + u64 dmac = ether_addr_to_u64(hdr->h_dest); + + if ((dmac & SJA1105_LINKLOCAL_FILTER_A_MASK) == + SJA1105_LINKLOCAL_FILTER_A) + return true; + if ((dmac & SJA1105_LINKLOCAL_FILTER_B_MASK) == + SJA1105_LINKLOCAL_FILTER_B) + return true; + return false; +} + +/* This is the first time the tagger sees the frame on RX. + * Figure out if we can decode it, and if we can, annotate skb->cb with how we + * plan to do that, so we don't need to check again in the rcv function. + */ +static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev) +{ + if (sja1105_is_link_local(skb)) { + SJA1105_SKB_CB(skb)->type = SJA1105_FRAME_TYPE_LINK_LOCAL; + return true; + } + if (!dsa_port_is_vlan_filtering(dev->dsa_ptr)) { + SJA1105_SKB_CB(skb)->type = SJA1105_FRAME_TYPE_NORMAL; + return true; + } + return false; +} + +static struct sk_buff *sja1105_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_switch *ds = dp->ds; + u16 tx_vid = dsa_8021q_tx_vid(ds, dp->index); + u8 pcp = skb->priority; + + /* Transmitting management traffic does not rely upon switch tagging, + * but instead SPI-installed management routes. Part 2 of this + * is the .port_deferred_xmit driver callback. + */ + if (unlikely(sja1105_is_link_local(skb))) + return dsa_defer_xmit(skb, netdev); + + /* If we are under a vlan_filtering bridge, IP termination on + * switch ports based on 802.1Q tags is simply too brittle to + * be passable. So just defer to the dsa_slave_notag_xmit + * implementation. + */ + if (dsa_port_is_vlan_filtering(dp)) + return skb; + + return dsa_8021q_xmit(skb, netdev, ETH_P_SJA1105, + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); +} + +static struct sk_buff *sja1105_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + struct ethhdr *hdr = eth_hdr(skb); + u64 source_port, switch_id; + struct sk_buff *nskb; + u16 tpid, vid, tci; + bool is_tagged; + + nskb = dsa_8021q_rcv(skb, netdev, pt, &tpid, &tci); + is_tagged = (nskb && tpid == ETH_P_SJA1105); + + skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + vid = tci & VLAN_VID_MASK; + + skb->offload_fwd_mark = 1; + + if (SJA1105_SKB_CB(skb)->type == SJA1105_FRAME_TYPE_LINK_LOCAL) { + /* Management traffic path. Switch embeds the switch ID and + * port ID into bytes of the destination MAC, courtesy of + * the incl_srcpt options. + */ + source_port = hdr->h_dest[3]; + switch_id = hdr->h_dest[4]; + /* Clear the DMAC bytes that were mangled by the switch */ + hdr->h_dest[3] = 0; + hdr->h_dest[4] = 0; + } else { + /* Normal traffic path. */ + source_port = dsa_8021q_rx_source_port(vid); + switch_id = dsa_8021q_rx_switch_id(vid); + } + + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (!skb->dev) { + netdev_warn(netdev, "Couldn't decode source port\n"); + return NULL; + } + + /* Delete/overwrite fake VLAN header, DSA expects to not find + * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN). + */ + if (is_tagged) + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - VLAN_HLEN, + ETH_HLEN - VLAN_HLEN); + + return skb; +} + +static struct dsa_device_ops sja1105_netdev_ops = { + .name = "sja1105", + .proto = DSA_TAG_PROTO_SJA1105, + .xmit = sja1105_xmit, + .rcv = sja1105_rcv, + .filter = sja1105_filter, + .overhead = VLAN_HLEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); + +module_dsa_tag_driver(sja1105_netdev_ops); -- cgit v1.2.3-71-gd317