diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 10:05:34 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 10:05:34 -0700 |
commit | 1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe (patch) | |
tree | 552e03de245cdbd0780ca1215914edc4a26540f7 /drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | |
parent | 6b5f04b6cf8ebab9a65d9c0026c650bb2538fd0f (diff) | |
parent | fe30937b65354c7fec244caebbdaae68e28ca797 (diff) | |
download | op-kernel-dev-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.zip op-kernel-dev-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support more Realtek wireless chips, from Jes Sorenson.
2) New BPF types for per-cpu hash and arrap maps, from Alexei
Starovoitov.
3) Make several TCP sysctls per-namespace, from Nikolay Borisov.
4) Allow the use of SO_REUSEPORT in order to do per-thread processing
of incoming TCP/UDP connections. The muxing can be done using a
BPF program which hashes the incoming packet. From Craig Gallek.
5) Add a multiplexer for TCP streams, to provide a messaged based
interface. BPF programs can be used to determine the message
boundaries. From Tom Herbert.
6) Add 802.1AE MACSEC support, from Sabrina Dubroca.
7) Avoid factorial complexity when taking down an inetdev interface
with lots of configured addresses. We were doing things like
traversing the entire address less for each address removed, and
flushing the entire netfilter conntrack table for every address as
well.
8) Add and use SKB bulk free infrastructure, from Jesper Brouer.
9) Allow offloading u32 classifiers to hardware, and implement for
ixgbe, from John Fastabend.
10) Allow configuring IRQ coalescing parameters on a per-queue basis,
from Kan Liang.
11) Extend ethtool so that larger link mode masks can be supported.
From David Decotigny.
12) Introduce devlink, which can be used to configure port link types
(ethernet vs Infiniband, etc.), port splitting, and switch device
level attributes as a whole. From Jiri Pirko.
13) Hardware offload support for flower classifiers, from Amir Vadai.
14) Add "Local Checksum Offload". Basically, for a tunneled packet
the checksum of the outer header is 'constant' (because with the
checksum field filled into the inner protocol header, the payload
of the outer frame checksums to 'zero'), and we can take advantage
of that in various ways. From Edward Cree"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
bonding: fix bond_get_stats()
net: bcmgenet: fix dma api length mismatch
net/mlx4_core: Fix backward compatibility on VFs
phy: mdio-thunder: Fix some Kconfig typos
lan78xx: add ndo_get_stats64
lan78xx: handle statistics counter rollover
RDS: TCP: Remove unused constant
RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
net: smc911x: convert pxa dma to dmaengine
team: remove duplicate set of flag IFF_MULTICAST
bonding: remove duplicate set of flag IFF_MULTICAST
net: fix a comment typo
ethernet: micrel: fix some error codes
ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
bpf, dst: add and use dst_tclassid helper
bpf: make skb->tc_classid also readable
net: mvneta: bm: clarify dependencies
cls_bpf: reset class and reuse major in da
ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
ldmvsw: Add ldmvsw.c driver code
...
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_main.c')
-rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 275 |
1 files changed, 245 insertions, 30 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index e6035ff..569cb07 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -51,6 +51,8 @@ #include <linux/prefetch.h> #include <scsi/fc/fc_fcoe.h> #include <net/vxlan.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gact.h> #ifdef CONFIG_OF #include <linux/of_net.h> @@ -65,6 +67,7 @@ #include "ixgbe_common.h" #include "ixgbe_dcb_82599.h" #include "ixgbe_sriov.h" +#include "ixgbe_model.h" char ixgbe_driver_name[] = "ixgbe"; static const char ixgbe_driver_string[] = @@ -1089,7 +1092,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter) * @tx_ring: tx ring to clean **/ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, - struct ixgbe_ring *tx_ring) + struct ixgbe_ring *tx_ring, int napi_budget) { struct ixgbe_adapter *adapter = q_vector->adapter; struct ixgbe_tx_buffer *tx_buffer; @@ -1127,7 +1130,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, total_packets += tx_buffer->gso_segs; /* free the skb */ - dev_consume_skb_any(tx_buffer->skb); + napi_consume_skb(tx_buffer->skb, napi_budget); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -2784,7 +2787,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) #endif ixgbe_for_each_ring(ring, q_vector->tx) - clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring); + clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring, budget); /* Exit if we are called by netpoll or busy polling is active */ if ((budget <= 0) || !ixgbe_qv_lock_napi(q_vector)) @@ -5545,6 +5548,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) #endif /* CONFIG_IXGBE_DCB */ #endif /* IXGBE_FCOE */ + /* initialize static ixgbe jump table entries */ + adapter->jump_tables[0] = ixgbe_ipv4_fields; + adapter->mac_table = kzalloc(sizeof(struct ixgbe_mac_addr) * hw->mac.num_rar_entries, GFP_ATOMIC); @@ -8200,6 +8206,225 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) return 0; } +static int ixgbe_delete_clsu32(struct ixgbe_adapter *adapter, + struct tc_cls_u32_offload *cls) +{ + int err; + + spin_lock(&adapter->fdir_perfect_lock); + err = ixgbe_update_ethtool_fdir_entry(adapter, NULL, cls->knode.handle); + spin_unlock(&adapter->fdir_perfect_lock); + return err; +} + +static int ixgbe_configure_clsu32_add_hnode(struct ixgbe_adapter *adapter, + __be16 protocol, + struct tc_cls_u32_offload *cls) +{ + /* This ixgbe devices do not support hash tables at the moment + * so abort when given hash tables. + */ + if (cls->hnode.divisor > 0) + return -EINVAL; + + set_bit(TC_U32_USERHTID(cls->hnode.handle), &adapter->tables); + return 0; +} + +static int ixgbe_configure_clsu32_del_hnode(struct ixgbe_adapter *adapter, + struct tc_cls_u32_offload *cls) +{ + clear_bit(TC_U32_USERHTID(cls->hnode.handle), &adapter->tables); + return 0; +} + +static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, + __be16 protocol, + struct tc_cls_u32_offload *cls) +{ + u32 loc = cls->knode.handle & 0xfffff; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_mat_field *field_ptr; + struct ixgbe_fdir_filter *input; + union ixgbe_atr_input mask; +#ifdef CONFIG_NET_CLS_ACT + const struct tc_action *a; +#endif + int i, err = 0; + u8 queue; + u32 handle; + + memset(&mask, 0, sizeof(union ixgbe_atr_input)); + handle = cls->knode.handle; + + /* At the moment cls_u32 jumps to transport layer and skips past + * L2 headers. The canonical method to match L2 frames is to use + * negative values. However this is error prone at best but really + * just broken because there is no way to "know" what sort of hdr + * is in front of the transport layer. Fix cls_u32 to support L2 + * headers when needed. + */ + if (protocol != htons(ETH_P_IP)) + return -EINVAL; + + if (cls->knode.link_handle || + cls->knode.link_handle >= IXGBE_MAX_LINK_HANDLE) { + struct ixgbe_nexthdr *nexthdr = ixgbe_ipv4_jumps; + u32 uhtid = TC_U32_USERHTID(cls->knode.link_handle); + + if (!test_bit(uhtid, &adapter->tables)) + return -EINVAL; + + for (i = 0; nexthdr[i].jump; i++) { + if (nexthdr->o != cls->knode.sel->offoff || + nexthdr->s != cls->knode.sel->offshift || + nexthdr->m != cls->knode.sel->offmask || + /* do not support multiple key jumps its just mad */ + cls->knode.sel->nkeys > 1) + return -EINVAL; + + if (nexthdr->off != cls->knode.sel->keys[0].off || + nexthdr->val != cls->knode.sel->keys[0].val || + nexthdr->mask != cls->knode.sel->keys[0].mask) + return -EINVAL; + + if (uhtid >= IXGBE_MAX_LINK_HANDLE) + return -EINVAL; + + adapter->jump_tables[uhtid] = nexthdr->jump; + } + return 0; + } + + if (loc >= ((1024 << adapter->fdir_pballoc) - 2)) { + e_err(drv, "Location out of range\n"); + return -EINVAL; + } + + /* cls u32 is a graph starting at root node 0x800. The driver tracks + * links and also the fields used to advance the parser across each + * link (e.g. nexthdr/eat parameters from 'tc'). This way we can map + * the u32 graph onto the hardware parse graph denoted in ixgbe_model.h + * To add support for new nodes update ixgbe_model.h parse structures + * this function _should_ be generic try not to hardcode values here. + */ + if (TC_U32_USERHTID(handle) == 0x800) { + field_ptr = adapter->jump_tables[0]; + } else { + if (TC_U32_USERHTID(handle) >= ARRAY_SIZE(adapter->jump_tables)) + return -EINVAL; + + field_ptr = adapter->jump_tables[TC_U32_USERHTID(handle)]; + } + + if (!field_ptr) + return -EINVAL; + + input = kzalloc(sizeof(*input), GFP_KERNEL); + if (!input) + return -ENOMEM; + + for (i = 0; i < cls->knode.sel->nkeys; i++) { + int off = cls->knode.sel->keys[i].off; + __be32 val = cls->knode.sel->keys[i].val; + __be32 m = cls->knode.sel->keys[i].mask; + bool found_entry = false; + int j; + + for (j = 0; field_ptr[j].val; j++) { + if (field_ptr[j].off == off && + field_ptr[j].mask == m) { + field_ptr[j].val(input, &mask, val, m); + input->filter.formatted.flow_type |= + field_ptr[j].type; + found_entry = true; + break; + } + } + + if (!found_entry) + goto err_out; + } + + mask.formatted.flow_type = IXGBE_ATR_L4TYPE_IPV6_MASK | + IXGBE_ATR_L4TYPE_MASK; + + if (input->filter.formatted.flow_type == IXGBE_ATR_FLOW_TYPE_IPV4) + mask.formatted.flow_type &= IXGBE_ATR_L4TYPE_IPV6_MASK; + +#ifdef CONFIG_NET_CLS_ACT + if (list_empty(&cls->knode.exts->actions)) + goto err_out; + + list_for_each_entry(a, &cls->knode.exts->actions, list) { + if (!is_tcf_gact_shot(a)) + goto err_out; + } +#endif + + input->action = IXGBE_FDIR_DROP_QUEUE; + queue = IXGBE_FDIR_DROP_QUEUE; + input->sw_idx = loc; + + spin_lock(&adapter->fdir_perfect_lock); + + if (hlist_empty(&adapter->fdir_filter_list)) { + memcpy(&adapter->fdir_mask, &mask, sizeof(mask)); + err = ixgbe_fdir_set_input_mask_82599(hw, &mask); + if (err) + goto err_out_w_lock; + } else if (memcmp(&adapter->fdir_mask, &mask, sizeof(mask))) { + err = -EINVAL; + goto err_out_w_lock; + } + + ixgbe_atr_compute_perfect_hash_82599(&input->filter, &mask); + err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter, + input->sw_idx, queue); + if (!err) + ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); + spin_unlock(&adapter->fdir_perfect_lock); + + return err; +err_out_w_lock: + spin_unlock(&adapter->fdir_perfect_lock); +err_out: + kfree(input); + return -EINVAL; +} + +int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + if (TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS) && + tc->type == TC_SETUP_CLSU32) { + switch (tc->cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return ixgbe_configure_clsu32(adapter, + proto, tc->cls_u32); + case TC_CLSU32_DELETE_KNODE: + return ixgbe_delete_clsu32(adapter, tc->cls_u32); + case TC_CLSU32_NEW_HNODE: + case TC_CLSU32_REPLACE_HNODE: + return ixgbe_configure_clsu32_add_hnode(adapter, proto, + tc->cls_u32); + case TC_CLSU32_DELETE_HNODE: + return ixgbe_configure_clsu32_del_hnode(adapter, + tc->cls_u32); + default: + return -EINVAL; + } + } + + if (tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + + return ixgbe_setup_tc(dev, tc->tc); +} + #ifdef CONFIG_PCI_IOV void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter) { @@ -8262,19 +8487,17 @@ static int ixgbe_set_features(struct net_device *netdev, } /* - * Check if Flow Director n-tuple support was enabled or disabled. If - * the state changed, we need to reset. + * Check if Flow Director n-tuple support or hw_tc support was + * enabled or disabled. If the state changed, we need to reset. */ - switch (features & NETIF_F_NTUPLE) { - case NETIF_F_NTUPLE: + if ((features & NETIF_F_NTUPLE) || (features & NETIF_F_HW_TC)) { /* turn off ATR, enable perfect filters and reset */ if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) need_reset = true; adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE; - break; - default: + } else { /* turn off perfect filters, enable ATR and reset */ if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) need_reset = true; @@ -8282,23 +8505,16 @@ static int ixgbe_set_features(struct net_device *netdev, adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE; /* We cannot enable ATR if SR-IOV is enabled */ - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - break; - - /* We cannot enable ATR if we have 2 or more traffic classes */ - if (netdev_get_num_tc(netdev) > 1) - break; - - /* We cannot enable ATR if RSS is disabled */ - if (adapter->ring_feature[RING_F_RSS].limit <= 1) - break; - - /* A sample rate of 0 indicates ATR disabled */ - if (!adapter->atr_sample_rate) - break; - - adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; - break; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED || + /* We cannot enable ATR if we have 2 or more tcs */ + (netdev_get_num_tc(netdev) > 1) || + /* We cannot enable ATR if RSS is disabled */ + (adapter->ring_feature[RING_F_RSS].limit <= 1) || + /* A sample rate of 0 indicates ATR disabled */ + (!adapter->atr_sample_rate)) + ; /* do nothing not supported */ + else /* otherwise supported and set the flag */ + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; } if (features & NETIF_F_HW_VLAN_CTAG_RX) @@ -8657,9 +8873,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_set_vf_trust = ixgbe_ndo_set_vf_trust, .ndo_get_vf_config = ixgbe_ndo_get_vf_config, .ndo_get_stats64 = ixgbe_get_stats64, -#ifdef CONFIG_IXGBE_DCB - .ndo_setup_tc = ixgbe_setup_tc, -#endif + .ndo_setup_tc = __ixgbe_setup_tc, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ixgbe_netpoll, #endif @@ -9030,7 +9244,8 @@ skip_sriov: case ixgbe_mac_X550EM_x: netdev->features |= NETIF_F_SCTP_CRC; netdev->hw_features |= NETIF_F_SCTP_CRC | - NETIF_F_NTUPLE; + NETIF_F_NTUPLE | + NETIF_F_HW_TC; break; default: break; |