diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-12-16 00:22:29 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-12-16 00:22:29 +0300 |
commit | d635a69dd4981cc51f90293f5f64268620ed1565 (patch) | |
tree | 5e0a758b402ea7d624c25c3a343545dd29e80f31 /net/smc/smc_ib.c | |
parent | ac73e3dc8acd0a3be292755db30388c3580f5674 (diff) | |
parent | efd5a1584537698220578227e6467638307c2a0b (diff) | |
download | linux-d635a69dd4981cc51f90293f5f64268620ed1565.tar.xz |
Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- support "prefer busy polling" NAPI operation mode, where we defer
softirq for some time expecting applications to periodically busy
poll
- AF_XDP: improve efficiency by more batching and hindering the
adjacency cache prefetcher
- af_packet: make packet_fanout.arr size configurable up to 64K
- tcp: optimize TCP zero copy receive in presence of partial or
unaligned reads making zero copy a performance win for much smaller
messages
- XDP: add bulk APIs for returning / freeing frames
- sched: support fragmenting IP packets as they come out of conntrack
- net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs
BPF:
- BPF switch from crude rlimit-based to memcg-based memory accounting
- BPF type format information for kernel modules and related tracing
enhancements
- BPF implement task local storage for BPF LSM
- allow the FENTRY/FEXIT/RAW_TP tracing programs to use
bpf_sk_storage
Protocols:
- mptcp: improve multiple xmit streams support, memory accounting and
many smaller improvements
- TLS: support CHACHA20-POLY1305 cipher
- seg6: add support for SRv6 End.DT4/DT6 behavior
- sctp: Implement RFC 6951: UDP Encapsulation of SCTP
- ppp_generic: add ability to bridge channels directly
- bridge: Connectivity Fault Management (CFM) support as is defined
in IEEE 802.1Q section 12.14.
Drivers:
- mlx5: make use of the new auxiliary bus to organize the driver
internals
- mlx5: more accurate port TX timestamping support
- mlxsw:
- improve the efficiency of offloaded next hop updates by using
the new nexthop object API
- support blackhole nexthops
- support IEEE 802.1ad (Q-in-Q) bridging
- rtw88: major bluetooth co-existance improvements
- iwlwifi: support new 6 GHz frequency band
- ath11k: Fast Initial Link Setup (FILS)
- mt7915: dual band concurrent (DBDC) support
- net: ipa: add basic support for IPA v4.5
Refactor:
- a few pieces of in_interrupt() cleanup work from Sebastian Andrzej
Siewior
- phy: add support for shared interrupts; get rid of multiple driver
APIs and have the drivers write a full IRQ handler, slight growth
of driver code should be compensated by the simpler API which also
allows shared IRQs
- add common code for handling netdev per-cpu counters
- move TX packet re-allocation from Ethernet switch tag drivers to a
central place
- improve efficiency and rename nla_strlcpy
- number of W=1 warning cleanups as we now catch those in a patchwork
build bot
Old code removal:
- wan: delete the DLCI / SDLA drivers
- wimax: move to staging
- wifi: remove old WDS wifi bridging support"
* tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits)
net: hns3: fix expression that is currently always true
net: fix proc_fs init handling in af_packet and tls
nfc: pn533: convert comma to semicolon
af_vsock: Assign the vsock transport considering the vsock address flags
af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path
vsock_addr: Check for supported flag values
vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag
vm_sockets: Add flags field in the vsock address data structure
net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled
tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit
net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context
nfc: s3fwrn5: Release the nfc firmware
net: vxget: clean up sparse warnings
mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router
mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3
mlxsw: spectrum_router_xm: Introduce basic XM cache flushing
mlxsw: reg: Add Router LPM Cache Enable Register
mlxsw: reg: Add Router LPM Cache ML Delete Register
mlxsw: spectrum_router_xm: Implement L-value tracking for M-index
mlxsw: reg: Add XM Router M Table Register
...
Diffstat (limited to 'net/smc/smc_ib.c')
-rw-r--r-- | net/smc/smc_ib.c | 200 |
1 files changed, 200 insertions, 0 deletions
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index fc766b537ac7..89ea10675a7d 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -25,6 +25,7 @@ #include "smc_core.h" #include "smc_wr.h" #include "smc.h" +#include "smc_netlink.h" #define SMC_MAX_CQE 32766 /* max. # of completion queue elements */ @@ -326,6 +327,161 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) return rc; } +static bool smcr_diag_is_dev_critical(struct smc_lgr_list *smc_lgr, + struct smc_ib_device *smcibdev) +{ + struct smc_link_group *lgr; + bool rc = false; + int i; + + spin_lock_bh(&smc_lgr->lock); + list_for_each_entry(lgr, &smc_lgr->list, list) { + if (lgr->is_smcd) + continue; + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (lgr->lnk[i].state == SMC_LNK_UNUSED || + lgr->lnk[i].smcibdev != smcibdev) + continue; + if (lgr->type == SMC_LGR_SINGLE || + lgr->type == SMC_LGR_ASYMMETRIC_LOCAL) { + rc = true; + goto out; + } + } + } +out: + spin_unlock_bh(&smc_lgr->lock); + return rc; +} + +static int smc_nl_handle_dev_port(struct sk_buff *skb, + struct ib_device *ibdev, + struct smc_ib_device *smcibdev, + int port) +{ + char smc_pnet[SMC_MAX_PNETID_LEN + 1]; + struct nlattr *port_attrs; + unsigned char port_state; + int lnk_count = 0; + + port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT + port); + if (!port_attrs) + goto errout; + + if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, + smcibdev->pnetid_by_user[port])) + goto errattr; + snprintf(smc_pnet, sizeof(smc_pnet), "%s", + (char *)&smcibdev->pnetid[port]); + if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet)) + goto errattr; + if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV, + smcibdev->ndev_ifidx[port])) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_DEV_PORT_VALID, 1)) + goto errattr; + port_state = smc_ib_port_active(smcibdev, port + 1); + if (nla_put_u8(skb, SMC_NLA_DEV_PORT_STATE, port_state)) + goto errattr; + lnk_count = atomic_read(&smcibdev->lnk_cnt_by_port[port]); + if (nla_put_u32(skb, SMC_NLA_DEV_PORT_LNK_CNT, lnk_count)) + goto errattr; + nla_nest_end(skb, port_attrs); + return 0; +errattr: + nla_nest_cancel(skb, port_attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + char smc_ibname[IB_DEVICE_NAME_MAX + 1]; + struct smc_pci_dev smc_pci_dev; + struct pci_dev *pci_dev; + unsigned char is_crit; + struct nlattr *attrs; + void *nlh; + int i; + + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_DEV_SMCR); + if (!nlh) + goto errmsg; + attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCR); + if (!attrs) + goto errout; + is_crit = smcr_diag_is_dev_critical(&smc_lgr_list, smcibdev); + if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, is_crit)) + goto errattr; + memset(&smc_pci_dev, 0, sizeof(smc_pci_dev)); + pci_dev = to_pci_dev(smcibdev->ibdev->dev.parent); + smc_set_pci_values(pci_dev, &smc_pci_dev); + if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device)) + goto errattr; + if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id)) + goto errattr; + snprintf(smc_ibname, sizeof(smc_ibname), "%s", smcibdev->ibdev->name); + if (nla_put_string(skb, SMC_NLA_DEV_IB_NAME, smc_ibname)) + goto errattr; + for (i = 1; i <= SMC_MAX_PORTS; i++) { + if (!rdma_is_port_valid(smcibdev->ibdev, i)) + continue; + if (smc_nl_handle_dev_port(skb, smcibdev->ibdev, + smcibdev, i - 1)) + goto errattr; + } + + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +static void smc_nl_prep_smcr_dev(struct smc_ib_devices *dev_list, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct smc_ib_device *smcibdev; + int snum = cb_ctx->pos[0]; + int num = 0; + + mutex_lock(&dev_list->mutex); + list_for_each_entry(smcibdev, &dev_list->list, list) { + if (num < snum) + goto next; + if (smc_nl_handle_smcr_dev(smcibdev, skb, cb)) + goto errout; +next: + num++; + } +errout: + mutex_unlock(&dev_list->mutex); + cb_ctx->pos[0] = num; +} + +int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb) +{ + smc_nl_prep_smcr_dev(&smc_ib_devices, skb, cb); + return skb->len; +} + static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { struct smc_link *lnk = (struct smc_link *)priv; @@ -557,6 +713,49 @@ out: static struct ib_client smc_ib_client; +static void smc_copy_netdev_ifindex(struct smc_ib_device *smcibdev, int port) +{ + struct ib_device *ibdev = smcibdev->ibdev; + struct net_device *ndev; + + if (!ibdev->ops.get_netdev) + return; + ndev = ibdev->ops.get_netdev(ibdev, port + 1); + if (ndev) { + smcibdev->ndev_ifidx[port] = ndev->ifindex; + dev_put(ndev); + } +} + +void smc_ib_ndev_change(struct net_device *ndev, unsigned long event) +{ + struct smc_ib_device *smcibdev; + struct ib_device *libdev; + struct net_device *lndev; + u8 port_cnt; + int i; + + mutex_lock(&smc_ib_devices.mutex); + list_for_each_entry(smcibdev, &smc_ib_devices.list, list) { + port_cnt = smcibdev->ibdev->phys_port_cnt; + for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); i++) { + libdev = smcibdev->ibdev; + if (!libdev->ops.get_netdev) + continue; + lndev = libdev->ops.get_netdev(libdev, i + 1); + if (lndev) + dev_put(lndev); + if (lndev != ndev) + continue; + if (event == NETDEV_REGISTER) + smcibdev->ndev_ifidx[i] = ndev->ifindex; + if (event == NETDEV_UNREGISTER) + smcibdev->ndev_ifidx[i] = 0; + } + } + mutex_unlock(&smc_ib_devices.mutex); +} + /* callback function for ib_register_client() */ static int smc_ib_add_dev(struct ib_device *ibdev) { @@ -596,6 +795,7 @@ static int smc_ib_add_dev(struct ib_device *ibdev) if (smc_pnetid_by_dev_port(ibdev->dev.parent, i, smcibdev->pnetid[i])) smc_pnetid_by_table_ib(smcibdev, i + 1); + smc_copy_netdev_ifindex(smcibdev, i); pr_warn_ratelimited("smc: ib device %s port %d has pnetid " "%.16s%s\n", smcibdev->ibdev->name, i + 1, |