diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 22:03:58 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 22:03:58 -0700 |
commit | 80f232121b69cc69a31ccb2b38c1665d770b0710 (patch) | |
tree | 106263eac4ff03b899df695e00dd11e593e74fe2 /net/core/dev.c | |
parent | 82efe439599439a5e1e225ce5740e6cfb777a7dd (diff) | |
parent | a9e41a529681b38087c91ebc0bb91e12f510ca2d (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.
2) Add fib_sync_mem to control the amount of dirty memory we allow to
queue up between synchronize RCU calls, from David Ahern.
3) Make flow classifier more lockless, from Vlad Buslov.
4) Add PHY downshift support to aquantia driver, from Heiner
Kallweit.
5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
contention on SLAB spinlocks in heavy RPC workloads.
6) Partial GSO offload support in XFRM, from Boris Pismenny.
7) Add fast link down support to ethtool, from Heiner Kallweit.
8) Use siphash for IP ID generator, from Eric Dumazet.
9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
entries, from David Ahern.
10) Move skb->xmit_more into a per-cpu variable, from Florian
Westphal.
11) Improve eBPF verifier speed and increase maximum program size,
from Alexei Starovoitov.
12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
spinlocks. From Neil Brown.
13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.
14) Improve link partner cap detection in generic PHY code, from
Heiner Kallweit.
15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
Maguire.
16) Remove SKB list implementation assumptions in SCTP, your's truly.
17) Various cleanups, optimizations, and simplifications in r8169
driver. From Heiner Kallweit.
18) Add memory accounting on TX and RX path of SCTP, from Xin Long.
19) Switch PHY drivers over to use dynamic featue detection, from
Heiner Kallweit.
20) Support flow steering without masking in dpaa2-eth, from Ioana
Ciocoi.
21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
Pirko.
22) Increase the strict parsing of current and future netlink
attributes, also export such policies to userspace. From Johannes
Berg.
23) Allow DSA tag drivers to be modular, from Andrew Lunn.
24) Remove legacy DSA probing support, also from Andrew Lunn.
25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
Haabendal.
26) Add a generic tracepoint for TX queue timeouts to ease debugging,
from Cong Wang.
27) More indirect call optimizations, from Paolo Abeni"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
cxgb4: Fix error path in cxgb4_init_module
net: phy: improve pause mode reporting in phy_print_status
dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
net: macb: Change interrupt and napi enable order in open
net: ll_temac: Improve error message on error IRQ
net/sched: remove block pointer from common offload structure
net: ethernet: support of_get_mac_address new ERR_PTR error
net: usb: smsc: fix warning reported by kbuild test robot
staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
net: dsa: support of_get_mac_address new ERR_PTR error
net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
vrf: sit mtu should not be updated when vrf netdev is the link
net: dsa: Fix error cleanup path in dsa_init_module
l2tp: Fix possible NULL pointer dereference
taprio: add null check on sched_nest to avoid potential null pointer dereference
net: mvpp2: cls: fix less than zero check on a u32 variable
net_sched: sch_fq: handle non connected flows
net_sched: sch_fq: do not assume EDT packets are ordered
net: hns3: use devm_kcalloc when allocating desc_cb
net: hns3: some cleanup for struct hns3_enet_ring
...
Diffstat (limited to 'net/core/dev.c')
-rw-r--r-- | net/core/dev.c | 88 |
1 files changed, 52 insertions, 36 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index f409406254dd..108ac8137b9b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -131,7 +131,6 @@ #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> -#include <linux/pci.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> @@ -146,6 +145,7 @@ #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> +#include <net/devlink.h> #include "net-sysfs.h" @@ -3482,6 +3482,15 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; + } else if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty && + qdisc_run_begin(q)) { + qdisc_bstats_cpu_update(q, skb); + + if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) + __qdisc_run(q); + + qdisc_run_end(q); + rc = NET_XMIT_SUCCESS; } else { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; qdisc_run(q); @@ -3570,9 +3579,6 @@ 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 @@ -3703,23 +3709,21 @@ 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; } 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); @@ -3743,10 +3747,11 @@ 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_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) { int queue_index = 0; @@ -3761,10 +3766,9 @@ struct netdev_queue *netdev_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); + queue_index = netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } @@ -3838,7 +3842,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) else skb_dst_force(skb); - txq = netdev_pick_tx(dev, skb, sb_dev); + txq = netdev_core_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); @@ -3863,8 +3867,7 @@ 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); @@ -3874,9 +3877,9 @@ 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; @@ -3989,9 +3992,9 @@ 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 * @@ -4443,7 +4446,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) bool free_skb = true; int cpu, rc; - txq = netdev_pick_tx(dev, skb, NULL); + txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { @@ -4517,7 +4520,7 @@ 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; @@ -4984,7 +4987,8 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); if (pt_prev) - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, + skb->dev, pt_prev, orig_dev); return ret; } @@ -5030,7 +5034,8 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head, else list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); - pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, + skb->dev, pt_prev, orig_dev); } } @@ -5188,7 +5193,7 @@ 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); @@ -5236,7 +5241,7 @@ 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); @@ -7886,10 +7891,14 @@ int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len) { const struct net_device_ops *ops = dev->netdev_ops; + int err; - if (!ops->ndo_get_phys_port_name) - return -EOPNOTSUPP; - return ops->ndo_get_phys_port_name(dev, name, len); + if (ops->ndo_get_phys_port_name) { + err = ops->ndo_get_phys_port_name(dev, name, len); + if (err != -EOPNOTSUPP) + return err; + } + return devlink_compat_phys_port_name_get(dev, name, len); } EXPORT_SYMBOL(dev_get_phys_port_name); @@ -7909,14 +7918,21 @@ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id first = { }; struct net_device *lower_dev; struct list_head *iter; - int err = -EOPNOTSUPP; + int err; - if (ops->ndo_get_port_parent_id) - return ops->ndo_get_port_parent_id(dev, ppid); + if (ops->ndo_get_port_parent_id) { + err = ops->ndo_get_port_parent_id(dev, ppid); + if (err != -EOPNOTSUPP) + return err; + } - if (!recurse) + err = devlink_compat_switch_id_get(dev, ppid); + if (!err || err != -EOPNOTSUPP) return err; + if (!recurse) + return -EOPNOTSUPP; + netdev_for_each_lower_dev(dev, lower_dev, iter) { err = dev_get_port_parent_id(lower_dev, ppid, recurse); if (err) |