aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_idc.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/net/ethernet/intel/ice/ice_idc.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_idc.c')
-rw-r--r--drivers/net/ethernet/intel/ice/ice_idc.c391
1 files changed, 391 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
new file mode 100644
index 000000000..e6bc22850
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -0,0 +1,391 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021, Intel Corporation. */
+
+/* Inter-Driver Communication */
+#include "ice.h"
+#include "ice_lib.h"
+#include "ice_dcb_lib.h"
+
+static DEFINE_XARRAY_ALLOC1(ice_aux_id);
+
+/**
+ * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct
+ * @pf: pointer to PF struct
+ *
+ * This function has to be called with a device_lock on the
+ * pf->adev.dev to avoid race conditions.
+ */
+static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
+{
+ struct auxiliary_device *adev;
+
+ adev = pf->adev;
+ if (!adev || !adev->dev.driver)
+ return NULL;
+
+ return container_of(adev->dev.driver, struct iidc_auxiliary_drv,
+ adrv.driver);
+}
+
+/**
+ * ice_send_event_to_aux - send event to RDMA AUX driver
+ * @pf: pointer to PF struct
+ * @event: event struct
+ */
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event)
+{
+ struct iidc_auxiliary_drv *iadrv;
+
+ if (WARN_ON_ONCE(!in_task()))
+ return;
+
+ mutex_lock(&pf->adev_mutex);
+ if (!pf->adev)
+ goto finish;
+
+ device_lock(&pf->adev->dev);
+ iadrv = ice_get_auxiliary_drv(pf);
+ if (iadrv && iadrv->event_handler)
+ iadrv->event_handler(pf, event);
+ device_unlock(&pf->adev->dev);
+finish:
+ mutex_unlock(&pf->adev_mutex);
+}
+
+/**
+ * ice_add_rdma_qset - Add Leaf Node for RDMA Qset
+ * @pf: PF struct
+ * @qset: Resource to be allocated
+ */
+int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+{
+ u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS];
+ struct ice_vsi *vsi;
+ struct device *dev;
+ u32 qset_teid;
+ u16 qs_handle;
+ int status;
+ int i;
+
+ if (WARN_ON(!pf || !qset))
+ return -EINVAL;
+
+ dev = ice_pf_to_dev(pf);
+
+ if (!ice_is_rdma_ena(pf))
+ return -EINVAL;
+
+ vsi = ice_get_main_vsi(pf);
+ if (!vsi) {
+ dev_err(dev, "RDMA QSet invalid VSI\n");
+ return -EINVAL;
+ }
+
+ ice_for_each_traffic_class(i)
+ max_rdmaqs[i] = 0;
+
+ max_rdmaqs[qset->tc]++;
+ qs_handle = qset->qs_handle;
+
+ status = ice_cfg_vsi_rdma(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+ max_rdmaqs);
+ if (status) {
+ dev_err(dev, "Failed VSI RDMA Qset config\n");
+ return status;
+ }
+
+ status = ice_ena_vsi_rdma_qset(vsi->port_info, vsi->idx, qset->tc,
+ &qs_handle, 1, &qset_teid);
+ if (status) {
+ dev_err(dev, "Failed VSI RDMA Qset enable\n");
+ return status;
+ }
+ vsi->qset_handle[qset->tc] = qset->qs_handle;
+ qset->teid = qset_teid;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ice_add_rdma_qset);
+
+/**
+ * ice_del_rdma_qset - Delete leaf node for RDMA Qset
+ * @pf: PF struct
+ * @qset: Resource to be freed
+ */
+int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+{
+ struct ice_vsi *vsi;
+ u32 teid;
+ u16 q_id;
+
+ if (WARN_ON(!pf || !qset))
+ return -EINVAL;
+
+ vsi = ice_find_vsi(pf, qset->vport_id);
+ if (!vsi) {
+ dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n");
+ return -EINVAL;
+ }
+
+ q_id = qset->qs_handle;
+ teid = qset->teid;
+
+ vsi->qset_handle[qset->tc] = 0;
+
+ return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id);
+}
+EXPORT_SYMBOL_GPL(ice_del_rdma_qset);
+
+/**
+ * ice_rdma_request_reset - accept request from RDMA to perform a reset
+ * @pf: struct for PF
+ * @reset_type: type of reset
+ */
+int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type)
+{
+ enum ice_reset_req reset;
+
+ if (WARN_ON(!pf))
+ return -EINVAL;
+
+ switch (reset_type) {
+ case IIDC_PFR:
+ reset = ICE_RESET_PFR;
+ break;
+ case IIDC_CORER:
+ reset = ICE_RESET_CORER;
+ break;
+ case IIDC_GLOBR:
+ reset = ICE_RESET_GLOBR;
+ break;
+ default:
+ dev_err(ice_pf_to_dev(pf), "incorrect reset request\n");
+ return -EINVAL;
+ }
+
+ return ice_schedule_reset(pf, reset);
+}
+EXPORT_SYMBOL_GPL(ice_rdma_request_reset);
+
+/**
+ * ice_rdma_update_vsi_filter - update main VSI filters for RDMA
+ * @pf: pointer to struct for PF
+ * @vsi_id: VSI HW idx to update filter on
+ * @enable: bool whether to enable or disable filters
+ */
+int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
+{
+ struct ice_vsi *vsi;
+ int status;
+
+ if (WARN_ON(!pf))
+ return -EINVAL;
+
+ vsi = ice_find_vsi(pf, vsi_id);
+ if (!vsi)
+ return -EINVAL;
+
+ status = ice_cfg_rdma_fltr(&pf->hw, vsi->idx, enable);
+ if (status) {
+ dev_err(ice_pf_to_dev(pf), "Failed to %sable RDMA filtering\n",
+ enable ? "en" : "dis");
+ } else {
+ if (enable)
+ vsi->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN;
+ else
+ vsi->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN;
+ }
+
+ return status;
+}
+EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter);
+
+/**
+ * ice_get_qos_params - parse QoS params for RDMA consumption
+ * @pf: pointer to PF struct
+ * @qos: set of QoS values
+ */
+void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos)
+{
+ struct ice_dcbx_cfg *dcbx_cfg;
+ unsigned int i;
+ u32 up2tc;
+
+ dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
+ up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
+
+ qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
+ for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
+ qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
+
+ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+ qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
+
+ qos->pfc_mode = dcbx_cfg->pfc_mode;
+ if (qos->pfc_mode == IIDC_DSCP_PFC_MODE)
+ for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++)
+ qos->dscp_map[i] = dcbx_cfg->dscp_map[i];
+}
+EXPORT_SYMBOL_GPL(ice_get_qos_params);
+
+/**
+ * ice_reserve_rdma_qvector - Reserve vector resources for RDMA driver
+ * @pf: board private structure to initialize
+ */
+static int ice_reserve_rdma_qvector(struct ice_pf *pf)
+{
+ if (ice_is_rdma_ena(pf)) {
+ int index;
+
+ index = ice_get_res(pf, pf->irq_tracker, pf->num_rdma_msix,
+ ICE_RES_RDMA_VEC_ID);
+ if (index < 0)
+ return index;
+ pf->num_avail_sw_msix -= pf->num_rdma_msix;
+ pf->rdma_base_vector = (u16)index;
+ }
+ return 0;
+}
+
+/**
+ * ice_free_rdma_qvector - free vector resources reserved for RDMA driver
+ * @pf: board private structure to initialize
+ */
+static void ice_free_rdma_qvector(struct ice_pf *pf)
+{
+ pf->num_avail_sw_msix -= pf->num_rdma_msix;
+ ice_free_res(pf->irq_tracker, pf->rdma_base_vector,
+ ICE_RES_RDMA_VEC_ID);
+}
+
+/**
+ * ice_adev_release - function to be mapped to AUX dev's release op
+ * @dev: pointer to device to free
+ */
+static void ice_adev_release(struct device *dev)
+{
+ struct iidc_auxiliary_dev *iadev;
+
+ iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev);
+ kfree(iadev);
+}
+
+/**
+ * ice_plug_aux_dev - allocate and register AUX device
+ * @pf: pointer to pf struct
+ */
+int ice_plug_aux_dev(struct ice_pf *pf)
+{
+ struct iidc_auxiliary_dev *iadev;
+ struct auxiliary_device *adev;
+ int ret;
+
+ /* if this PF doesn't support a technology that requires auxiliary
+ * devices, then gracefully exit
+ */
+ if (!ice_is_rdma_ena(pf))
+ return 0;
+
+ iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
+ if (!iadev)
+ return -ENOMEM;
+
+ adev = &iadev->adev;
+ iadev->pf = pf;
+
+ adev->id = pf->aux_idx;
+ adev->dev.release = ice_adev_release;
+ adev->dev.parent = &pf->pdev->dev;
+ adev->name = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? "roce" : "iwarp";
+
+ ret = auxiliary_device_init(adev);
+ if (ret) {
+ kfree(iadev);
+ return ret;
+ }
+
+ ret = auxiliary_device_add(adev);
+ if (ret) {
+ auxiliary_device_uninit(adev);
+ return ret;
+ }
+
+ mutex_lock(&pf->adev_mutex);
+ pf->adev = adev;
+ mutex_unlock(&pf->adev_mutex);
+
+ return 0;
+}
+
+/* ice_unplug_aux_dev - unregister and free AUX device
+ * @pf: pointer to pf struct
+ */
+void ice_unplug_aux_dev(struct ice_pf *pf)
+{
+ struct auxiliary_device *adev;
+
+ mutex_lock(&pf->adev_mutex);
+ adev = pf->adev;
+ pf->adev = NULL;
+ mutex_unlock(&pf->adev_mutex);
+
+ if (adev) {
+ auxiliary_device_delete(adev);
+ auxiliary_device_uninit(adev);
+ }
+}
+
+/**
+ * ice_init_rdma - initializes PF for RDMA use
+ * @pf: ptr to ice_pf
+ */
+int ice_init_rdma(struct ice_pf *pf)
+{
+ struct device *dev = &pf->pdev->dev;
+ int ret;
+
+ if (!ice_is_rdma_ena(pf)) {
+ dev_warn(dev, "RDMA is not supported on this device\n");
+ return 0;
+ }
+
+ ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX),
+ GFP_KERNEL);
+ if (ret) {
+ dev_err(dev, "Failed to allocate device ID for AUX driver\n");
+ return -ENOMEM;
+ }
+
+ /* Reserve vector resources */
+ ret = ice_reserve_rdma_qvector(pf);
+ if (ret < 0) {
+ dev_err(dev, "failed to reserve vectors for RDMA\n");
+ goto err_reserve_rdma_qvector;
+ }
+ pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
+ ret = ice_plug_aux_dev(pf);
+ if (ret)
+ goto err_plug_aux_dev;
+ return 0;
+
+err_plug_aux_dev:
+ ice_free_rdma_qvector(pf);
+err_reserve_rdma_qvector:
+ pf->adev = NULL;
+ xa_erase(&ice_aux_id, pf->aux_idx);
+ return ret;
+}
+
+/**
+ * ice_deinit_rdma - deinitialize RDMA on PF
+ * @pf: ptr to ice_pf
+ */
+void ice_deinit_rdma(struct ice_pf *pf)
+{
+ if (!ice_is_rdma_ena(pf))
+ return;
+
+ ice_unplug_aux_dev(pf);
+ ice_free_rdma_qvector(pf);
+ xa_erase(&ice_aux_id, pf->aux_idx);
+}