From: Jussi Maki joamaki@gmail.com

mainline inclusion from mainline-v5.15-rc1 commit a815bde56b15ce626caaacc952ab12501671e45d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7NDRB CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------

In preparation for adding XDP support to the bonding driver refactor the packet hashing functions to be able to work with any linear data buffer without an skb.

Signed-off-by: Jussi Maki joamaki@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Cc: Jay Vosburgh j.vosburgh@gmail.com Cc: Veaceslav Falico vfalico@gmail.com Cc: Andy Gospodarek andy@greyhouse.net Link: https://lore.kernel.org/bpf/20210731055738.16820-2-joamaki@gmail.com

Conflicts: drivers/net/bonding/bond_main.c

Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com --- drivers/net/bonding/bond_main.c | 136 +++++++++++++++++++------------- 1 file changed, 81 insertions(+), 55 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d3827905535b..b472819f1025 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3591,66 +3591,84 @@ static struct notifier_block bond_netdev_notifier = { };

/*---------------------------- Hashing Policies -----------------------------*/ +/* Helper to access data in a packet, with or without a backing skb. + * If skb is given the data is linearized if necessary via pskb_may_pull. + */ +static inline void *bond_pull_data(struct sk_buff *skb, + void *data, int hlen, int n) +{ + if (likely(n <= hlen)) + return data; + else if (skb && likely(pskb_may_pull(skb, n))) + return skb->head; + + return NULL; +}

/* L2 hash helper */ -static inline u32 bond_eth_hash(struct sk_buff *skb) +static inline u32 bond_eth_hash(struct sk_buff *skb, void *data, int mhoff, int hlen) { - struct ethhdr *ep, hdr_tmp; + struct ethhdr *ep;

- ep = skb_header_pointer(skb, 0, sizeof(hdr_tmp), &hdr_tmp); - if (ep) - return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto; - return 0; + data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); + if (!data) + return 0; + + ep = (struct ethhdr *)(data + mhoff); + return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto; }

-static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, - int *noff, int *proto, bool l34) +static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, void *data, + int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34) { const struct ipv6hdr *iph6; const struct iphdr *iph;

- if (skb->protocol == htons(ETH_P_IP)) { - if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph)))) + if (l2_proto == htons(ETH_P_IP)) { + data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph)); + if (!data) return false; - iph = (const struct iphdr *)(skb->data + *noff); + + iph = (const struct iphdr *)(data + *nhoff); iph_to_flow_copy_v4addrs(fk, iph); - *noff += iph->ihl << 2; + *nhoff += iph->ihl << 2; if (!ip_is_fragment(iph)) - *proto = iph->protocol; - } else if (skb->protocol == htons(ETH_P_IPV6)) { - if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph6)))) + *ip_proto = iph->protocol; + } else if (l2_proto == htons(ETH_P_IPV6)) { + data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6)); + if (!data) return false; - iph6 = (const struct ipv6hdr *)(skb->data + *noff); + + iph6 = (const struct ipv6hdr *)(data + *nhoff); iph_to_flow_copy_v6addrs(fk, iph6); - *noff += sizeof(*iph6); - *proto = iph6->nexthdr; + *nhoff += sizeof(*iph6); + *ip_proto = iph6->nexthdr; } else { return false; }

- if (l34 && *proto >= 0) - fk->ports.ports = skb_flow_get_ports(skb, *noff, *proto); + if (l34 && *ip_proto >= 0) + fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);

return true; }

/* Extract the appropriate headers based on bond's xmit policy */ -static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, - struct flow_keys *fk) +static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, void *data, + __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk) { bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34; - int noff, proto = -1; + int ip_proto = -1;

if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) { memset(fk, 0, sizeof(*fk)); return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, - fk, NULL, 0, 0, 0, 0); + fk, data, l2_proto, nhoff, hlen, 0); }

fk->ports.ports = 0; memset(&fk->icmp, 0, sizeof(fk->icmp)); - noff = skb_network_offset(skb); - if (!bond_flow_ip(skb, fk, &noff, &proto, l34)) + if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34)) return false;

/* ICMP error packets contains at least 8 bytes of the header @@ -3658,51 +3676,41 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, * to correlate ICMP error packets within the same flow which * generated the error. */ - if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6) { - skb_flow_get_icmp_tci(skb, &fk->icmp, skb->data, - skb_transport_offset(skb), - skb_headlen(skb)); - if (proto == IPPROTO_ICMP) { + if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) { + skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen); + if (ip_proto == IPPROTO_ICMP) { if (!icmp_is_err(fk->icmp.type)) return true;

- noff += sizeof(struct icmphdr); - } else if (proto == IPPROTO_ICMPV6) { + nhoff += sizeof(struct icmphdr); + } else if (ip_proto == IPPROTO_ICMPV6) { if (!icmpv6_is_err(fk->icmp.type)) return true;

- noff += sizeof(struct icmp6hdr); + nhoff += sizeof(struct icmp6hdr); } - return bond_flow_ip(skb, fk, &noff, &proto, l34); + return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34); }

return true; } - -/** - * bond_xmit_hash - generate a hash value based on the xmit policy - * @bond: bonding device - * @skb: buffer to use for headers - * - * This function will extract the necessary headers from the skb buffer and use - * them to generate a hash based on the xmit_policy set in the bonding device +/* Generate hash based on xmit policy. If @skb is given it is used to linearize + * the data as required, but this function can be used without it if the data is + * known to be linear (e.g. with xdp_buff). */ -u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) +static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, void *data, + __be16 l2_proto, int mhoff, int nhoff, int hlen) { struct flow_keys flow; u32 hash;

- if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && - skb->l4_hash) - return skb->hash; - if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || - !bond_flow_dissect(bond, skb, &flow)) - return bond_eth_hash(skb); + !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow)) + return bond_eth_hash(skb, data, mhoff, hlen);

if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) { - hash = bond_eth_hash(skb); + hash = bond_eth_hash(skb, data, mhoff, hlen); } else { if (flow.icmp.id) memcpy(&hash, &flow.icmp, sizeof(hash)); @@ -3717,6 +3725,25 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) return hash >> 1; }

+/** + * bond_xmit_hash - generate a hash value based on the xmit policy + * @bond: bonding device + * @skb: buffer to use for headers + * + * This function will extract the necessary headers from the skb buffer and use + * them to generate a hash based on the xmit_policy set in the bonding device + */ +u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) +{ + if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && + skb->l4_hash) + return skb->hash; + + return __bond_xmit_hash(bond, skb, skb->head, skb->protocol, + skb->mac_header, skb->network_header, + skb_headlen(skb)); +} + /*-------------------------- Device entry points ----------------------------*/

void bond_work_init_all(struct bonding *bond) @@ -4346,8 +4373,7 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, return bond_tx_drop(bond_dev, skb); }

-static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond, - struct sk_buff *skb) +static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond) { return rcu_dereference(bond->curr_active_slave); } @@ -4361,7 +4387,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, struct bonding *bond = netdev_priv(bond_dev); struct slave *slave;

- slave = bond_xmit_activebackup_slave_get(bond, skb); + slave = bond_xmit_activebackup_slave_get(bond); if (slave) return bond_dev_queue_xmit(bond, skb, slave->dev);

@@ -4673,7 +4699,7 @@ static struct net_device *bond_xmit_get_slave(struct net_device *master_dev, slave = bond_xmit_roundrobin_slave_get(bond, skb); break; case BOND_MODE_ACTIVEBACKUP: - slave = bond_xmit_activebackup_slave_get(bond, skb); + slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR:

From: Jussi Maki joamaki@gmail.com

mainline inclusion from mainline-v5.15-rc1 commit 9e2ee5c7e7c35d195e2aa0692a7241d47a433d1e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7NDRB CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------

XDP is implemented in the bonding driver by transparently delegating the XDP program loading, removal and xmit operations to the bonding slave devices. The overall goal of this work is that XDP programs can be attached to a bond device *without* any further changes (or awareness) necessary to the program itself, meaning the same XDP program can be attached to a native device but also a bonding device.

Semantics of XDP_TX when attached to a bond are equivalent in such setting to the case when a tc/BPF program would be attached to the bond, meaning transmitting the packet out of the bond itself using one of the bond's configured xmit methods to select a slave device (rather than XDP_TX on the slave itself). Handling of XDP_TX to transmit using the configured bonding mechanism is therefore implemented by rewriting the BPF program return value in bpf_prog_run_xdp. To avoid performance impact this check is guarded by a static key, which is incremented when a XDP program is loaded onto a bond device. This approach was chosen to avoid changes to drivers implementing XDP. If the slave device does not match the receive device, then XDP_REDIRECT is transparently used to perform the redirection in order to have the network driver release the packet from its RX ring. The bonding driver hashing functions have been refactored to allow reuse with xdp_buff's to avoid code duplication.

The motivation for this change is to enable use of bonding (and 802.3ad) in hairpinning L4 load-balancers such as [1] implemented with XDP and also to transparently support bond devices for projects that use XDP given most modern NICs have dual port adapters. An alternative to this approach would be to implement 802.3ad in user-space and implement the bonding load-balancing in the XDP program itself, but is rather a cumbersome endeavor in terms of slave device management (e.g. by watching netlink) and requires separate programs for native vs bond cases for the orchestrator. A native in-kernel implementation overcomes these issues and provides more flexibility.

Below are benchmark results done on two machines with 100Gbit Intel E810 (ice) NIC and with 32-core 3970X on sending machine, and 16-core 3950X on receiving machine. 64 byte packets were sent with pktgen-dpdk at full rate. Two issues [2, 3] were identified with the ice driver, so the tests were performed with iommu=off and patch [2] applied. Additionally the bonding round robin algorithm was modified to use per-cpu tx counters as high CPU load (50% vs 10%) and high rate of cache misses were caused by the shared rr_tx_counter (see patch 2/3). The statistics were collected using "sar -n dev -u 1 10". On top of that, for ice, further work is in progress on improving the XDP_TX numbers [4].

-----------------------| CPU |--| rxpck/s |--| txpck/s |---- without patch (1 dev): XDP_DROP: 3.15% 48.6Mpps XDP_TX: 3.12% 18.3Mpps 18.3Mpps XDP_DROP (RSS): 9.47% 116.5Mpps XDP_TX (RSS): 9.67% 25.3Mpps 24.2Mpps ----------------------- with patch, bond (1 dev): XDP_DROP: 3.14% 46.7Mpps XDP_TX: 3.15% 13.9Mpps 13.9Mpps XDP_DROP (RSS): 10.33% 117.2Mpps XDP_TX (RSS): 10.64% 25.1Mpps 24.0Mpps ----------------------- with patch, bond (2 devs): XDP_DROP: 6.27% 92.7Mpps XDP_TX: 6.26% 17.6Mpps 17.5Mpps XDP_DROP (RSS): 11.38% 117.2Mpps XDP_TX (RSS): 14.30% 28.7Mpps 27.4Mpps --------------------------------------------------------------

RSS: Receive Side Scaling, e.g. the packets were sent to a range of destination IPs.

[1]: https://cilium.io/blog/2021/05/20/cilium-110#standalonelb [2]: https://lore.kernel.org/bpf/20210601113236.42651-1-maciej.fijalkowski@intel.... [3]: https://lore.kernel.org/bpf/CAHn8xckNXci+X_Eb2WMv4uVYjO2331UWB2JLtXr_58z0Av8... [4]: https://lore.kernel.org/bpf/20210805230046.28715-1-maciej.fijalkowski@intel....

Signed-off-by: Jussi Maki joamaki@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Cc: Jay Vosburgh j.vosburgh@gmail.com Cc: Veaceslav Falico vfalico@gmail.com Cc: Andy Gospodarek andy@greyhouse.net Cc: Maciej Fijalkowski maciej.fijalkowski@intel.com Cc: Magnus Karlsson magnus.karlsson@intel.com Link: https://lore.kernel.org/bpf/20210731055738.16820-4-joamaki@gmail.com

Conflicts: drivers/net/bonding/bond_main.c include/net/bonding.h

Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com --- drivers/net/bonding/bond_main.c | 309 +++++++++++++++++++++++++++++++- include/net/bonding.h | 1 + 2 files changed, 309 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b472819f1025..162ce61aa154 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -302,6 +302,19 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, return dev_queue_xmit(skb); }

+static bool bond_xdp_check(struct bonding *bond) +{ + switch (BOND_MODE(bond)) { + case BOND_MODE_ROUNDROBIN: + case BOND_MODE_ACTIVEBACKUP: + case BOND_MODE_8023AD: + case BOND_MODE_XOR: + return true; + default: + return false; + } +} + /*---------------------------------- VLAN -----------------------------------*/

/* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, @@ -2109,6 +2122,41 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond_update_slave_arr(bond, NULL);

+ if (!slave_dev->netdev_ops->ndo_bpf || + !slave_dev->netdev_ops->ndo_xdp_xmit) { + if (bond->xdp_prog) { + NL_SET_ERR_MSG(extack, "Slave does not support XDP"); + slave_err(bond_dev, slave_dev, "Slave does not support XDP\n"); + res = -EOPNOTSUPP; + goto err_sysfs_del; + } + } else { + struct netdev_bpf xdp = { + .command = XDP_SETUP_PROG, + .flags = 0, + .prog = bond->xdp_prog, + .extack = extack, + }; + + if (dev_xdp_prog_count(slave_dev) > 0) { + NL_SET_ERR_MSG(extack, + "Slave has XDP program loaded, please unload before enslaving"); + slave_err(bond_dev, slave_dev, + "Slave has XDP program loaded, please unload before enslaving\n"); + res = -EOPNOTSUPP; + goto err_sysfs_del; + } + + res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + if (res < 0) { + /* ndo_bpf() sets extack error message */ + slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); + goto err_sysfs_del; + } + if (bond->xdp_prog) + bpf_prog_inc(bond->xdp_prog); + } + slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", bond_is_active_slave(new_slave) ? "an active" : "a backup", new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); @@ -2228,6 +2276,17 @@ static int __bond_release_one(struct net_device *bond_dev, /* recompute stats just before removing the slave */ bond_get_stats(bond->dev, &bond->bond_stats);

+ if (bond->xdp_prog) { + struct netdev_bpf xdp = { + .command = XDP_SETUP_PROG, + .flags = 0, + .prog = NULL, + .extack = NULL, + }; + if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp)) + slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); + } + /* unregister rx_handler early so bond_handle_frame wouldn't be called * for this slave anymore. */ @@ -3615,7 +3674,7 @@ static inline u32 bond_eth_hash(struct sk_buff *skb, void *data, int mhoff, int return 0;

ep = (struct ethhdr *)(data + mhoff); - return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto; + return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto); }

static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, void *data, @@ -3744,6 +3803,26 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) skb_headlen(skb)); }

+/** + * bond_xmit_hash_xdp - generate a hash value based on the xmit policy + * @bond: bonding device + * @xdp: buffer to use for headers + * + * The XDP variant of bond_xmit_hash. + */ +static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp) +{ + struct ethhdr *eth; + + if (xdp->data + sizeof(struct ethhdr) > xdp->data_end) + return 0; + + eth = (struct ethhdr *)xdp->data; + + return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0, + sizeof(struct ethhdr), xdp->data_end - xdp->data); +} + /*-------------------------- Device entry points ----------------------------*/

void bond_work_init_all(struct bonding *bond) @@ -4360,6 +4439,47 @@ static struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond, return NULL; }

+static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond, + struct xdp_buff *xdp) +{ + struct slave *slave; + int slave_cnt; + u32 slave_id; + const struct ethhdr *eth; + void *data = xdp->data; + + if (data + sizeof(struct ethhdr) > xdp->data_end) + goto non_igmp; + + eth = (struct ethhdr *)data; + data += sizeof(struct ethhdr); + + /* See comment on IGMP in bond_xmit_roundrobin_slave_get() */ + if (eth->h_proto == htons(ETH_P_IP)) { + const struct iphdr *iph; + + if (data + sizeof(struct iphdr) > xdp->data_end) + goto non_igmp; + + iph = (struct iphdr *)data; + + if (iph->protocol == IPPROTO_IGMP) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + return slave; + return bond_get_slave_by_id(bond, 0); + } + } + +non_igmp: + slave_cnt = READ_ONCE(bond->slave_cnt); + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; + return bond_get_slave_by_id(bond, slave_id); + } + return NULL; +} + static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { @@ -4575,6 +4695,22 @@ static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond, return slave; }

+static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond, + struct xdp_buff *xdp) +{ + struct bond_up_slave *slaves; + unsigned int count; + u32 hash; + + hash = bond_xmit_hash_xdp(bond, xdp); + slaves = rcu_dereference(bond->usable_slaves); + count = slaves ? READ_ONCE(slaves->count) : 0; + if (unlikely(!count)) + return NULL; + + return slaves->arr[hash % count]; +} + /* Use this Xmit function for 3AD as well as XOR modes. The current * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. @@ -4779,6 +4915,174 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; }

+static struct net_device * +bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + + /* Caller needs to hold rcu_read_lock() */ + + switch (BOND_MODE(bond)) { + case BOND_MODE_ROUNDROBIN: + slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp); + break; + + case BOND_MODE_ACTIVEBACKUP: + slave = bond_xmit_activebackup_slave_get(bond); + break; + + case BOND_MODE_8023AD: + case BOND_MODE_XOR: + slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp); + break; + + default: + /* Should never happen. Mode guarded by bond_xdp_check() */ + netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond)); + WARN_ON_ONCE(1); + return NULL; + } + + if (slave) + return slave->dev; + + return NULL; +} + +static int bond_xdp_xmit(struct net_device *bond_dev, + int n, struct xdp_frame **frames, u32 flags) +{ + int nxmit, err = -ENXIO; + + rcu_read_lock(); + + for (nxmit = 0; nxmit < n; nxmit++) { + struct xdp_frame *frame = frames[nxmit]; + struct xdp_frame *frames1[] = {frame}; + struct net_device *slave_dev; + struct xdp_buff xdp; + + xdp_convert_frame_to_buff(frame, &xdp); + + slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp); + if (!slave_dev) { + err = -ENXIO; + break; + } + + err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags); + if (err < 1) + break; + } + + rcu_read_unlock(); + + /* If error happened on the first frame then we can pass the error up, otherwise + * report the number of frames that were xmitted. + */ + if (err < 0) + return (nxmit == 0 ? err : nxmit); + + return nxmit; +} + +static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, + struct netlink_ext_ack *extack) +{ + struct bonding *bond = netdev_priv(dev); + struct list_head *iter; + struct slave *slave, *rollback_slave; + struct bpf_prog *old_prog; + struct netdev_bpf xdp = { + .command = XDP_SETUP_PROG, + .flags = 0, + .prog = prog, + .extack = extack, + }; + int err; + + ASSERT_RTNL(); + + if (!bond_xdp_check(bond)) + return -EOPNOTSUPP; + + old_prog = bond->xdp_prog; + bond->xdp_prog = prog; + + bond_for_each_slave(bond, slave, iter) { + struct net_device *slave_dev = slave->dev; + + if (!slave_dev->netdev_ops->ndo_bpf || + !slave_dev->netdev_ops->ndo_xdp_xmit) { + NL_SET_ERR_MSG(extack, "Slave device does not support XDP"); + slave_err(dev, slave_dev, "Slave does not support XDP\n"); + err = -EOPNOTSUPP; + goto err; + } + + if (dev_xdp_prog_count(slave_dev) > 0) { + NL_SET_ERR_MSG(extack, + "Slave has XDP program loaded, please unload before enslaving"); + slave_err(dev, slave_dev, + "Slave has XDP program loaded, please unload before enslaving\n"); + err = -EOPNOTSUPP; + goto err; + } + + err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + if (err < 0) { + /* ndo_bpf() sets extack error message */ + slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); + goto err; + } + if (prog) + bpf_prog_inc(prog); + } + + if (old_prog) + bpf_prog_put(old_prog); + + if (prog) + static_branch_inc(&bpf_master_redirect_enabled_key); + else + static_branch_dec(&bpf_master_redirect_enabled_key); + + return 0; + +err: + /* unwind the program changes */ + bond->xdp_prog = old_prog; + xdp.prog = old_prog; + xdp.extack = NULL; /* do not overwrite original error */ + + bond_for_each_slave(bond, rollback_slave, iter) { + struct net_device *slave_dev = rollback_slave->dev; + int err_unwind; + + if (slave == rollback_slave) + break; + + err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + if (err_unwind < 0) + slave_err(dev, slave_dev, + "Error %d when unwinding XDP program change\n", err_unwind); + else if (xdp.prog) + bpf_prog_inc(xdp.prog); + } + return err; +} + +static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return bond_xdp_set(dev, xdp->prog, xdp->extack); + default: + return -EINVAL; + } +} + static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) { if (speed == 0 || speed == SPEED_UNKNOWN) @@ -4864,6 +5168,9 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_fix_features = bond_fix_features, .ndo_features_check = passthru_features_check, .ndo_get_xmit_slave = bond_xmit_get_slave, + .ndo_bpf = bond_xdp, + .ndo_xdp_xmit = bond_xdp_xmit, + .ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave, };

static const struct device_type bond_type = { diff --git a/include/net/bonding.h b/include/net/bonding.h index 67d676059aa0..0848614424fb 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -256,6 +256,7 @@ struct bonding { /* protecting ipsec_list */ spinlock_t ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ + struct bpf_prog *xdp_prog; };

#define bond_slave_get_rcu(dev) \

From: Jussi Maki joamaki@gmail.com

mainline inclusion from mainline-v5.14-rc1 commit 848ca9182a7d25bb54955c3aab9a3a2742bf9678 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7NDRB CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------

The round-robin rr_tx_counter was shared across CPUs leading to significant cache thrashing at high packet rates. This patch switches the round-robin packet counter to use a per-cpu variable to decide the destination slave.

On a test with 2x100Gbit ICE nic with pktgen_sample_04_many_flows.sh (-s 64 -t 32) the tx rate was 19.6Mpps before and 22.3Mpps after this patch.

"perf top -e cache_misses" before: 12.31% [bonding] [k] bond_xmit_roundrobin_slave_get 10.59% [sch_fq_codel] [k] fq_codel_dequeue 9.34% [kernel] [k] skb_release_data after: 15.42% [sch_fq_codel] [k] fq_codel_dequeue 10.06% [kernel] [k] __memset 9.12% [kernel] [k] skb_release_data

Signed-off-by: Jussi Maki joamaki@gmail.com Signed-off-by: David S. Miller davem@davemloft.net

Conflicts: drivers/net/bonding/bond_main.c

Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com --- drivers/net/bonding/bond_main.c | 18 +++++++++++++++--- include/net/bonding.h | 2 +- 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 7890c9eee44f..e2ece8865a5a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4387,16 +4387,16 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond) slave_id = prandom_u32(); break; case 1: - slave_id = bond->rr_tx_counter; + slave_id = this_cpu_inc_return(*bond->rr_tx_counter); break; default: reciprocal_packets_per_slave = bond->params.reciprocal_packets_per_slave; - slave_id = reciprocal_divide(bond->rr_tx_counter, + slave_id = this_cpu_inc_return(*bond->rr_tx_counter); + slave_id = reciprocal_divide(slave_id, reciprocal_packets_per_slave); break; } - bond->rr_tx_counter++;

return slave_id; } @@ -5181,6 +5181,9 @@ static void bond_destructor(struct net_device *bond_dev) struct bonding *bond = netdev_priv(bond_dev); if (bond->wq) destroy_workqueue(bond->wq); + + if (bond->rr_tx_counter) + free_percpu(bond->rr_tx_counter); }

void bond_setup(struct net_device *bond_dev) @@ -5680,6 +5683,15 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM;

+ if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN) { + bond->rr_tx_counter = alloc_percpu(u32); + if (!bond->rr_tx_counter) { + destroy_workqueue(bond->wq); + bond->wq = NULL; + return -ENOMEM; + } + } + spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev);

diff --git a/include/net/bonding.h b/include/net/bonding.h index 0848614424fb..e4ed57af41b1 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -235,7 +235,7 @@ struct bonding { char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; - u32 rr_tx_counter; + u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params;

From: Jonathan Toppins jtoppins@redhat.com

mainline inclusion from mainline-v6.0-rc7 commit 0e400d602f46360752e4b32ce842dba3808e15e6 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7NDRB CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------

Fix a NULL dereference of the struct bonding.rr_tx_counter member because if a bond is initially created with an initial mode != zero (Round Robin) the memory required for the counter is never created and when the mode is changed there is never any attempt to verify the memory is allocated upon switching modes.

This causes the following Oops on an aarch64 machine: [ 334.686773] Unable to handle kernel paging request at virtual address ffff2c91ac905000 [ 334.694703] Mem abort info: [ 334.697486] ESR = 0x0000000096000004 [ 334.701234] EC = 0x25: DABT (current EL), IL = 32 bits [ 334.706536] SET = 0, FnV = 0 [ 334.709579] EA = 0, S1PTW = 0 [ 334.712719] FSC = 0x04: level 0 translation fault [ 334.717586] Data abort info: [ 334.720454] ISV = 0, ISS = 0x00000004 [ 334.724288] CM = 0, WnR = 0 [ 334.727244] swapper pgtable: 4k pages, 48-bit VAs, pgdp=000008044d662000 [ 334.733944] [ffff2c91ac905000] pgd=0000000000000000, p4d=0000000000000000 [ 334.740734] Internal error: Oops: 96000004 [#1] SMP [ 334.745602] Modules linked in: bonding tls veth rfkill sunrpc arm_spe_pmu vfat fat acpi_ipmi ipmi_ssif ixgbe igb i40e mdio ipmi_devintf ipmi_msghandler arm_cmn arm_dsu_pmu cppc_cpufreq acpi_tad fuse zram crct10dif_ce ast ghash_ce sbsa_gwdt nvme drm_vram_helper drm_ttm_helper nvme_core ttm xgene_hwmon [ 334.772217] CPU: 7 PID: 2214 Comm: ping Not tainted 6.0.0-rc4-00133-g64ae13ed4784 #4 [ 334.779950] Hardware name: GIGABYTE R272-P31-00/MP32-AR1-00, BIOS F18v (SCP: 1.08.20211002) 12/01/2021 [ 334.789244] pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 334.796196] pc : bond_rr_gen_slave_id+0x40/0x124 [bonding] [ 334.801691] lr : bond_xmit_roundrobin_slave_get+0x38/0xdc [bonding] [ 334.807962] sp : ffff8000221733e0 [ 334.811265] x29: ffff8000221733e0 x28: ffffdbac8572d198 x27: ffff80002217357c [ 334.818392] x26: 000000000000002a x25: ffffdbacb33ee000 x24: ffff07ff980fa000 [ 334.825519] x23: ffffdbacb2e398ba x22: ffff07ff98102000 x21: ffff07ff981029c0 [ 334.832646] x20: 0000000000000001 x19: ffff07ff981029c0 x18: 0000000000000014 [ 334.839773] x17: 0000000000000000 x16: ffffdbacb1004364 x15: 0000aaaabe2f5a62 [ 334.846899] x14: ffff07ff8e55d968 x13: ffff07ff8e55db30 x12: 0000000000000000 [ 334.854026] x11: ffffdbacb21532e8 x10: 0000000000000001 x9 : ffffdbac857178ec [ 334.861153] x8 : ffff07ff9f6e5a28 x7 : 0000000000000000 x6 : 000000007c2b3742 [ 334.868279] x5 : ffff2c91ac905000 x4 : ffff2c91ac905000 x3 : ffff07ff9f554400 [ 334.875406] x2 : ffff2c91ac905000 x1 : 0000000000000001 x0 : ffff07ff981029c0 [ 334.882532] Call trace: [ 334.884967] bond_rr_gen_slave_id+0x40/0x124 [bonding] [ 334.890109] bond_xmit_roundrobin_slave_get+0x38/0xdc [bonding] [ 334.896033] __bond_start_xmit+0x128/0x3a0 [bonding] [ 334.901001] bond_start_xmit+0x54/0xb0 [bonding] [ 334.905622] dev_hard_start_xmit+0xb4/0x220 [ 334.909798] __dev_queue_xmit+0x1a0/0x720 [ 334.913799] arp_xmit+0x3c/0xbc [ 334.916932] arp_send_dst+0x98/0xd0 [ 334.920410] arp_solicit+0xe8/0x230 [ 334.923888] neigh_probe+0x60/0xb0 [ 334.927279] __neigh_event_send+0x3b0/0x470 [ 334.931453] neigh_resolve_output+0x70/0x90 [ 334.935626] ip_finish_output2+0x158/0x514 [ 334.939714] __ip_finish_output+0xac/0x1a4 [ 334.943800] ip_finish_output+0x40/0xfc [ 334.947626] ip_output+0xf8/0x1a4 [ 334.950931] ip_send_skb+0x5c/0x100 [ 334.954410] ip_push_pending_frames+0x3c/0x60 [ 334.958758] raw_sendmsg+0x458/0x6d0 [ 334.962325] inet_sendmsg+0x50/0x80 [ 334.965805] sock_sendmsg+0x60/0x6c [ 334.969286] __sys_sendto+0xc8/0x134 [ 334.972853] __arm64_sys_sendto+0x34/0x4c [ 334.976854] invoke_syscall+0x78/0x100 [ 334.980594] el0_svc_common.constprop.0+0x4c/0xf4 [ 334.985287] do_el0_svc+0x38/0x4c [ 334.988591] el0_svc+0x34/0x10c [ 334.991724] el0t_64_sync_handler+0x11c/0x150 [ 334.996072] el0t_64_sync+0x190/0x194 [ 334.999726] Code: b9001062 f9403c02 d53cd044 8b040042 (b8210040) [ 335.005810] ---[ end trace 0000000000000000 ]--- [ 335.010416] Kernel panic - not syncing: Oops: Fatal exception in interrupt [ 335.017279] SMP: stopping secondary CPUs [ 335.021374] Kernel Offset: 0x5baca8eb0000 from 0xffff800008000000 [ 335.027456] PHYS_OFFSET: 0x80000000 [ 335.030932] CPU features: 0x0000,0085c029,19805c82 [ 335.035713] Memory Limit: none [ 335.038756] Rebooting in 180 seconds..

The fix is to allocate the memory in bond_open() which is guaranteed to be called before any packets are processed.

Fixes: 848ca9182a7d ("net: bonding: Use per-cpu rr_tx_counter") CC: Jussi Maki joamaki@gmail.com Signed-off-by: Jonathan Toppins jtoppins@redhat.com Acked-by: Jay Vosburgh jay.vosburgh@canonical.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com --- drivers/net/bonding/bond_main.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0869d82aa324..81632f68fa17 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3852,6 +3852,12 @@ static int bond_open(struct net_device *bond_dev) struct list_head *iter; struct slave *slave;

+ if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) { + bond->rr_tx_counter = alloc_percpu(u32); + if (!bond->rr_tx_counter) + return -ENOMEM; + } + /* reset slave->backup and slave->inactive */ if (bond_has_slaves(bond)) { bond_for_each_slave(bond, slave, iter) { @@ -5683,15 +5689,6 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM;

- if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN) { - bond->rr_tx_counter = alloc_percpu(u32); - if (!bond->rr_tx_counter) { - destroy_workqueue(bond->wq); - bond->wq = NULL; - return -ENOMEM; - } - } - spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev);