diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-13 15:47:48 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-13 15:47:48 -0800 |
commit | 7e68dd7d07a28faa2e6574dd6b9dbd90cdeaae91 (patch) | |
tree | ae0427c5a3b905f24b3a44b510a9bcf35d9b67a3 /drivers/net/ethernet/intel/ice/ice_lib.c | |
parent | 1ca06f1c1acecbe02124f14a37cce347b8c1a90c (diff) | |
parent | 7c4a6309e27f411743817fe74a832ec2d2798a4b (diff) |
Merge tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Paolo Abeni:
"Core:
- Allow live renaming when an interface is up
- Add retpoline wrappers for tc, improving considerably the
performances of complex queue discipline configurations
- Add inet drop monitor support
- A few GRO performance improvements
- Add infrastructure for atomic dev stats, addressing long standing
data races
- De-duplicate common code between OVS and conntrack offloading
infrastructure
- A bunch of UBSAN_BOUNDS/FORTIFY_SOURCE improvements
- Netfilter: introduce packet parser for tunneled packets
- Replace IPVS timer-based estimators with kthreads to scale up the
workload with the number of available CPUs
- Add the helper support for connection-tracking OVS offload
BPF:
- Support for user defined BPF objects: the use case is to allocate
own objects, build own object hierarchies and use the building
blocks to build own data structures flexibly, for example, linked
lists in BPF
- Make cgroup local storage available to non-cgroup attached BPF
programs
- Avoid unnecessary deadlock detection and failures wrt BPF task
storage helpers
- A relevant bunch of BPF verifier fixes and improvements
- Veristat tool improvements to support custom filtering, sorting,
and replay of results
- Add LLVM disassembler as default library for dumping JITed code
- Lots of new BPF documentation for various BPF maps
- Add bpf_rcu_read_{,un}lock() support for sleepable programs
- Add RCU grace period chaining to BPF to wait for the completion of
access from both sleepable and non-sleepable BPF programs
- Add support storing struct task_struct objects as kptrs in maps
- Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer
values
- Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions
Protocols:
- TCP: implement Protective Load Balancing across switch links
- TCP: allow dynamically disabling TCP-MD5 static key, reverting back
to fast[er]-path
- UDP: Introduce optional per-netns hash lookup table
- IPv6: simplify and cleanup sockets disposal
- Netlink: support different type policies for each generic netlink
operation
- MPTCP: add MSG_FASTOPEN and FastOpen listener side support
- MPTCP: add netlink notification support for listener sockets events
- SCTP: add VRF support, allowing sctp sockets binding to VRF devices
- Add bridging MAC Authentication Bypass (MAB) support
- Extensions for Ethernet VPN bridging implementation to better
support multicast scenarios
- More work for Wi-Fi 7 support, comprising conversion of all the
existing drivers to internal TX queue usage
- IPSec: introduce a new offload type (packet offload) allowing
complete header processing and crypto offloading
- IPSec: extended ack support for more descriptive XFRM error
reporting
- RXRPC: increase SACK table size and move processing into a
per-local endpoint kernel thread, reducing considerably the
required locking
- IEEE 802154: synchronous send frame and extended filtering support,
initial support for scanning available 15.4 networks
- Tun: bump the link speed from 10Mbps to 10Gbps
- Tun/VirtioNet: implement UDP segmentation offload support
Driver API:
- PHY/SFP: improve power level switching between standard level 1 and
the higher power levels
- New API for netdev <-> devlink_port linkage
- PTP: convert existing drivers to new frequency adjustment
implementation
- DSA: add support for rx offloading
- Autoload DSA tagging driver when dynamically changing protocol
- Add new PCP and APPTRUST attributes to Data Center Bridging
- Add configuration support for 800Gbps link speed
- Add devlink port function attribute to enable/disable RoCE and
migratable
- Extend devlink-rate to support strict prioriry and weighted fair
queuing
- Add devlink support to directly reading from region memory
- New device tree helper to fetch MAC address from nvmem
- New big TCP helper to simplify temporary header stripping
New hardware / drivers:
- Ethernet:
- Marvel Octeon CNF95N and CN10KB Ethernet Switches
- Marvel Prestera AC5X Ethernet Switch
- WangXun 10 Gigabit NIC
- Motorcomm yt8521 Gigabit Ethernet
- Microchip ksz9563 Gigabit Ethernet Switch
- Microsoft Azure Network Adapter
- Linux Automation 10Base-T1L adapter
- PHY:
- Aquantia AQR112 and AQR412
- Motorcomm YT8531S
- PTP:
- Orolia ART-CARD
- WiFi:
- MediaTek Wi-Fi 7 (802.11be) devices
- RealTek rtw8821cu, rtw8822bu, rtw8822cu and rtw8723du USB
devices
- Bluetooth:
- Broadcom BCM4377/4378/4387 Bluetooth chipsets
- Realtek RTL8852BE and RTL8723DS
- Cypress.CYW4373A0 WiFi + Bluetooth combo device
Drivers:
- CAN:
- gs_usb: bus error reporting support
- kvaser_usb: listen only and bus error reporting support
- Ethernet NICs:
- Intel (100G):
- extend action skbedit to RX queue mapping
- implement devlink-rate support
- support direct read from memory
- nVidia/Mellanox (mlx5):
- SW steering improvements, increasing rules update rate
- Support for enhanced events compression
- extend H/W offload packet manipulation capabilities
- implement IPSec packet offload mode
- nVidia/Mellanox (mlx4):
- better big TCP support
- Netronome Ethernet NICs (nfp):
- IPsec offload support
- add support for multicast filter
- Broadcom:
- RSS and PTP support improvements
- AMD/SolarFlare:
- netlink extened ack improvements
- add basic flower matches to offload, and related stats
- Virtual NICs:
- ibmvnic: introduce affinity hint support
- small / embedded:
- FreeScale fec: add initial XDP support
- Marvel mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood
- TI am65-cpsw: add suspend/resume support
- Mediatek MT7986: add RX wireless wthernet dispatch support
- Realtek 8169: enable GRO software interrupt coalescing per
default
- Ethernet high-speed switches:
- Microchip (sparx5):
- add support for Sparx5 TC/flower H/W offload via VCAP
- Mellanox mlxsw:
- add 802.1X and MAC Authentication Bypass offload support
- add ip6gre support
- Embedded Ethernet switches:
- Mediatek (mtk_eth_soc):
- improve PCS implementation, add DSA untag support
- enable flow offload support
- Renesas:
- add rswitch R-Car Gen4 gPTP support
- Microchip (lan966x):
- add full XDP support
- add TC H/W offload via VCAP
- enable PTP on bridge interfaces
- Microchip (ksz8):
- add MTU support for KSZ8 series
- Qualcomm 802.11ax WiFi (ath11k):
- support configuring channel dwell time during scan
- MediaTek WiFi (mt76):
- enable Wireless Ethernet Dispatch (WED) offload support
- add ack signal support
- enable coredump support
- remain_on_channel support
- Intel WiFi (iwlwifi):
- enable Wi-Fi 7 Extremely High Throughput (EHT) PHY capabilities
- 320 MHz channels support
- RealTek WiFi (rtw89):
- new dynamic header firmware format support
- wake-over-WLAN support"
* tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2002 commits)
ipvs: fix type warning in do_div() on 32 bit
net: lan966x: Remove a useless test in lan966x_ptp_add_trap()
net: ipa: add IPA v4.7 support
dt-bindings: net: qcom,ipa: Add SM6350 compatible
bnxt: Use generic HBH removal helper in tx path
IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver
selftests: forwarding: Add bridge MDB test
selftests: forwarding: Rename bridge_mdb test
bridge: mcast: Support replacement of MDB port group entries
bridge: mcast: Allow user space to specify MDB entry routing protocol
bridge: mcast: Allow user space to add (*, G) with a source list and filter mode
bridge: mcast: Add support for (*, G) with a source list and filter mode
bridge: mcast: Avoid arming group timer when (S, G) corresponds to a source
bridge: mcast: Add a flag for user installed source entries
bridge: mcast: Expose __br_multicast_del_group_src()
bridge: mcast: Expose br_multicast_new_group_src()
bridge: mcast: Add a centralized error path
bridge: mcast: Place netlink policy before validation functions
bridge: mcast: Split (*, G) and (S, G) addition into different functions
bridge: mcast: Do not derive entry type from its filter mode
...
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_lib.c')
-rw-r--r-- | drivers/net/ethernet/intel/ice/ice_lib.c | 272 |
1 files changed, 237 insertions, 35 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 7276badfa19e..94aa834cd9a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -448,6 +448,49 @@ static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *d } /** + * ice_vsi_alloc_stat_arrays - Allocate statistics arrays + * @vsi: VSI pointer + */ +static int ice_vsi_alloc_stat_arrays(struct ice_vsi *vsi) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + + if (vsi->type == ICE_VSI_CHNL) + return 0; + if (!pf->vsi_stats) + return -ENOENT; + + vsi_stat = kzalloc(sizeof(*vsi_stat), GFP_KERNEL); + if (!vsi_stat) + return -ENOMEM; + + vsi_stat->tx_ring_stats = + kcalloc(vsi->alloc_txq, sizeof(*vsi_stat->tx_ring_stats), + GFP_KERNEL); + if (!vsi_stat->tx_ring_stats) + goto err_alloc_tx; + + vsi_stat->rx_ring_stats = + kcalloc(vsi->alloc_rxq, sizeof(*vsi_stat->rx_ring_stats), + GFP_KERNEL); + if (!vsi_stat->rx_ring_stats) + goto err_alloc_rx; + + pf->vsi_stats[vsi->idx] = vsi_stat; + + return 0; + +err_alloc_rx: + kfree(vsi_stat->rx_ring_stats); +err_alloc_tx: + kfree(vsi_stat->tx_ring_stats); + kfree(vsi_stat); + pf->vsi_stats[vsi->idx] = NULL; + return -ENOMEM; +} + +/** * ice_vsi_alloc - Allocates the next available struct VSI in the PF * @pf: board private structure * @vsi_type: type of VSI @@ -560,6 +603,11 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, if (vsi->type == ICE_VSI_CTRL && vf) vf->ctrl_vsi_idx = vsi->idx; + + /* allocate memory for Tx/Rx ring stat pointers */ + if (ice_vsi_alloc_stat_arrays(vsi)) + goto err_rings; + goto unlock_pf; err_rings: @@ -1536,6 +1584,106 @@ err_out: } /** + * ice_vsi_free_stats - Free the ring statistics structures + * @vsi: VSI pointer + */ +static void ice_vsi_free_stats(struct ice_vsi *vsi) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + int i; + + if (vsi->type == ICE_VSI_CHNL) + return; + if (!pf->vsi_stats) + return; + + vsi_stat = pf->vsi_stats[vsi->idx]; + if (!vsi_stat) + return; + + ice_for_each_alloc_txq(vsi, i) { + if (vsi_stat->tx_ring_stats[i]) { + kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); + } + } + + ice_for_each_alloc_rxq(vsi, i) { + if (vsi_stat->rx_ring_stats[i]) { + kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); + } + } + + kfree(vsi_stat->tx_ring_stats); + kfree(vsi_stat->rx_ring_stats); + kfree(vsi_stat); + pf->vsi_stats[vsi->idx] = NULL; +} + +/** + * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI + * @vsi: VSI which is having stats allocated + */ +static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) +{ + struct ice_ring_stats **tx_ring_stats; + struct ice_ring_stats **rx_ring_stats; + struct ice_vsi_stats *vsi_stats; + struct ice_pf *pf = vsi->back; + u16 i; + + vsi_stats = pf->vsi_stats[vsi->idx]; + tx_ring_stats = vsi_stats->tx_ring_stats; + rx_ring_stats = vsi_stats->rx_ring_stats; + + /* Allocate Tx ring stats */ + ice_for_each_alloc_txq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_tx_ring *ring; + + ring = vsi->tx_rings[i]; + ring_stats = tx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(tx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + /* Allocate Rx ring stats */ + ice_for_each_alloc_rxq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_rx_ring *ring; + + ring = vsi->rx_rings[i]; + ring_stats = rx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(rx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + return 0; + +err_out: + ice_vsi_free_stats(vsi); + return -ENOMEM; +} + +/** * ice_vsi_manage_rss_lut - disable/enable RSS * @vsi: the VSI being changed * @ena: boolean value indicating if this is an enable or disable request @@ -1795,11 +1943,15 @@ void ice_update_eth_stats(struct ice_vsi *vsi) { struct ice_eth_stats *prev_es, *cur_es; struct ice_hw *hw = &vsi->back->hw; + struct ice_pf *pf = vsi->back; u16 vsi_num = vsi->vsi_num; /* HW absolute index of a VSI */ prev_es = &vsi->eth_stats_prev; cur_es = &vsi->eth_stats; + if (ice_is_reset_in_progress(pf->state)) + vsi->stat_offsets_loaded = false; + ice_stat_update40(hw, GLV_GORCL(vsi_num), vsi->stat_offsets_loaded, &prev_es->rx_bytes, &cur_es->rx_bytes); @@ -2576,6 +2728,10 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto unroll_vector_base; + ice_vsi_map_rings_to_vectors(vsi); /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ @@ -2614,6 +2770,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto unroll_vector_base; /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value @@ -2627,6 +2786,11 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, ret = ice_vsi_alloc_rings(vsi); if (ret) goto unroll_vsi_init; + + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto unroll_vector_base; + break; default: /* clean up the resources and exit */ @@ -2686,6 +2850,7 @@ unroll_vector_base: unroll_alloc_q_vector: ice_vsi_free_q_vectors(vsi); unroll_vsi_init: + ice_vsi_free_stats(vsi); ice_vsi_delete(vsi); unroll_get_qs: ice_vsi_put_qs(vsi); @@ -3077,7 +3242,7 @@ int ice_vsi_release(struct ice_vsi *vsi) vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; ice_vsi_clear_rings(vsi); - + ice_vsi_free_stats(vsi); ice_vsi_put_qs(vsi); /* retain SW VSI data structure since it is needed to unregister and @@ -3205,6 +3370,47 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, } /** + * ice_vsi_realloc_stat_arrays - Frees unused stat structures + * @vsi: VSI pointer + * @prev_txq: Number of Tx rings before ring reallocation + * @prev_rxq: Number of Rx rings before ring reallocation + */ +static int +ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + int i; + + if (!prev_txq || !prev_rxq) + return 0; + if (vsi->type == ICE_VSI_CHNL) + return 0; + + vsi_stat = pf->vsi_stats[vsi->idx]; + + if (vsi->num_txq < prev_txq) { + for (i = vsi->num_txq; i < prev_txq; i++) { + if (vsi_stat->tx_ring_stats[i]) { + kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); + } + } + } + + if (vsi->num_rxq < prev_rxq) { + for (i = vsi->num_rxq; i < prev_rxq; i++) { + if (vsi_stat->rx_ring_stats[i]) { + kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); + } + } + } + + return 0; +} + +/** * ice_vsi_rebuild - Rebuild VSI after reset * @vsi: VSI to be rebuild * @init_vsi: is this an initialization or a reconfigure of the VSI @@ -3215,10 +3421,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_coalesce_stored *coalesce; + int ret, i, prev_txq, prev_rxq; int prev_num_q_vectors = 0; enum ice_vsi_type vtype; struct ice_pf *pf; - int ret, i; if (!vsi) return -EINVAL; @@ -3237,6 +3443,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); + prev_txq = vsi->num_txq; + prev_rxq = vsi->num_rxq; + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); if (ret) @@ -3303,7 +3512,13 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) if (ret) goto err_vectors; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto err_vectors; + ice_vsi_map_rings_to_vectors(vsi); + + vsi->stat_offsets_loaded = false; if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) @@ -3340,6 +3555,11 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) if (ret) goto err_vectors; + ret = ice_vsi_alloc_ring_stats(vsi); + if (ret) + goto err_vectors; + + vsi->stat_offsets_loaded = false; break; case ICE_VSI_CHNL: if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { @@ -3387,6 +3607,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) return ice_schedule_reset(pf, ICE_RESET_PFR); } } + + if (ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq)) + goto err_vectors; + ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); kfree(coalesce); @@ -3728,9 +3952,9 @@ static void ice_update_ring_stats(struct ice_q_stats *stats, u64 pkts, u64 bytes */ void ice_update_tx_ring_stats(struct ice_tx_ring *tx_ring, u64 pkts, u64 bytes) { - u64_stats_update_begin(&tx_ring->syncp); - ice_update_ring_stats(&tx_ring->stats, pkts, bytes); - u64_stats_update_end(&tx_ring->syncp); + u64_stats_update_begin(&tx_ring->ring_stats->syncp); + ice_update_ring_stats(&tx_ring->ring_stats->stats, pkts, bytes); + u64_stats_update_end(&tx_ring->ring_stats->syncp); } /** @@ -3741,9 +3965,9 @@ void ice_update_tx_ring_stats(struct ice_tx_ring *tx_ring, u64 pkts, u64 bytes) */ void ice_update_rx_ring_stats(struct ice_rx_ring *rx_ring, u64 pkts, u64 bytes) { - u64_stats_update_begin(&rx_ring->syncp); - ice_update_ring_stats(&rx_ring->stats, pkts, bytes); - u64_stats_update_end(&rx_ring->syncp); + u64_stats_update_begin(&rx_ring->ring_stats->syncp); + ice_update_ring_stats(&rx_ring->ring_stats->stats, pkts, bytes); + u64_stats_update_end(&rx_ring->ring_stats->syncp); } /** @@ -3850,33 +4074,11 @@ int ice_clear_dflt_vsi(struct ice_vsi *vsi) */ int ice_get_link_speed_mbps(struct ice_vsi *vsi) { - switch (vsi->port_info->phy.link_info.link_speed) { - case ICE_AQ_LINK_SPEED_100GB: - return SPEED_100000; - case ICE_AQ_LINK_SPEED_50GB: - return SPEED_50000; - case ICE_AQ_LINK_SPEED_40GB: - return SPEED_40000; - case ICE_AQ_LINK_SPEED_25GB: - return SPEED_25000; - case ICE_AQ_LINK_SPEED_20GB: - return SPEED_20000; - case ICE_AQ_LINK_SPEED_10GB: - return SPEED_10000; - case ICE_AQ_LINK_SPEED_5GB: - return SPEED_5000; - case ICE_AQ_LINK_SPEED_2500MB: - return SPEED_2500; - case ICE_AQ_LINK_SPEED_1000MB: - return SPEED_1000; - case ICE_AQ_LINK_SPEED_100MB: - return SPEED_100; - case ICE_AQ_LINK_SPEED_10MB: - return SPEED_10; - case ICE_AQ_LINK_SPEED_UNKNOWN: - default: - return 0; - } + unsigned int link_speed; + + link_speed = vsi->port_info->phy.link_info.link_speed; + + return (int)ice_get_link_speed(fls(link_speed) - 1); } /** |