From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c | 346 +++++++++++++++++++++ 1 file changed, 346 insertions(+) create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c (limited to 'drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c new file mode 100644 index 000000000..7dd3dba0f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c @@ -0,0 +1,346 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include +#include + +#include "spectrum.h" +#include "reg.h" + +struct mlxsw_sp_pgt { + struct idr pgt_idr; + u16 end_index; /* Exclusive. */ + struct mutex lock; /* Protects PGT. */ + bool smpe_index_valid; +}; + +struct mlxsw_sp_pgt_entry { + struct list_head ports_list; + u16 index; + u16 smpe_index; +}; + +struct mlxsw_sp_pgt_entry_port { + struct list_head list; /* Member of 'ports_list'. */ + u16 local_port; +}; + +int mlxsw_sp_pgt_mid_alloc(struct mlxsw_sp *mlxsw_sp, u16 *p_mid) +{ + int index, err = 0; + + mutex_lock(&mlxsw_sp->pgt->lock); + index = idr_alloc(&mlxsw_sp->pgt->pgt_idr, NULL, 0, + mlxsw_sp->pgt->end_index, GFP_KERNEL); + + if (index < 0) { + err = index; + goto err_idr_alloc; + } + + *p_mid = index; + mutex_unlock(&mlxsw_sp->pgt->lock); + return 0; + +err_idr_alloc: + mutex_unlock(&mlxsw_sp->pgt->lock); + return err; +} + +void mlxsw_sp_pgt_mid_free(struct mlxsw_sp *mlxsw_sp, u16 mid_base) +{ + mutex_lock(&mlxsw_sp->pgt->lock); + WARN_ON(idr_remove(&mlxsw_sp->pgt->pgt_idr, mid_base)); + mutex_unlock(&mlxsw_sp->pgt->lock); +} + +int +mlxsw_sp_pgt_mid_alloc_range(struct mlxsw_sp *mlxsw_sp, u16 mid_base, u16 count) +{ + unsigned int idr_cursor; + int i, err; + + mutex_lock(&mlxsw_sp->pgt->lock); + + /* This function is supposed to be called several times as part of + * driver init, in specific order. Verify that the mid_index is the + * first free index in the idr, to be able to free the indexes in case + * of error. + */ + idr_cursor = idr_get_cursor(&mlxsw_sp->pgt->pgt_idr); + if (WARN_ON(idr_cursor != mid_base)) { + err = -EINVAL; + goto err_idr_cursor; + } + + for (i = 0; i < count; i++) { + err = idr_alloc_cyclic(&mlxsw_sp->pgt->pgt_idr, NULL, + mid_base, mid_base + count, GFP_KERNEL); + if (err < 0) + goto err_idr_alloc_cyclic; + } + + mutex_unlock(&mlxsw_sp->pgt->lock); + return 0; + +err_idr_alloc_cyclic: + for (i--; i >= 0; i--) + idr_remove(&mlxsw_sp->pgt->pgt_idr, mid_base + i); +err_idr_cursor: + mutex_unlock(&mlxsw_sp->pgt->lock); + return err; +} + +void +mlxsw_sp_pgt_mid_free_range(struct mlxsw_sp *mlxsw_sp, u16 mid_base, u16 count) +{ + struct idr *pgt_idr = &mlxsw_sp->pgt->pgt_idr; + int i; + + mutex_lock(&mlxsw_sp->pgt->lock); + + for (i = 0; i < count; i++) + WARN_ON_ONCE(idr_remove(pgt_idr, mid_base + i)); + + mutex_unlock(&mlxsw_sp->pgt->lock); +} + +static struct mlxsw_sp_pgt_entry_port * +mlxsw_sp_pgt_entry_port_lookup(struct mlxsw_sp_pgt_entry *pgt_entry, + u16 local_port) +{ + struct mlxsw_sp_pgt_entry_port *pgt_entry_port; + + list_for_each_entry(pgt_entry_port, &pgt_entry->ports_list, list) { + if (pgt_entry_port->local_port == local_port) + return pgt_entry_port; + } + + return NULL; +} + +static struct mlxsw_sp_pgt_entry * +mlxsw_sp_pgt_entry_create(struct mlxsw_sp_pgt *pgt, u16 mid, u16 smpe) +{ + struct mlxsw_sp_pgt_entry *pgt_entry; + void *ret; + int err; + + pgt_entry = kzalloc(sizeof(*pgt_entry), GFP_KERNEL); + if (!pgt_entry) + return ERR_PTR(-ENOMEM); + + ret = idr_replace(&pgt->pgt_idr, pgt_entry, mid); + if (IS_ERR(ret)) { + err = PTR_ERR(ret); + goto err_idr_replace; + } + + INIT_LIST_HEAD(&pgt_entry->ports_list); + pgt_entry->index = mid; + pgt_entry->smpe_index = smpe; + return pgt_entry; + +err_idr_replace: + kfree(pgt_entry); + return ERR_PTR(err); +} + +static void mlxsw_sp_pgt_entry_destroy(struct mlxsw_sp_pgt *pgt, + struct mlxsw_sp_pgt_entry *pgt_entry) +{ + WARN_ON(!list_empty(&pgt_entry->ports_list)); + + pgt_entry = idr_replace(&pgt->pgt_idr, NULL, pgt_entry->index); + if (WARN_ON(IS_ERR(pgt_entry))) + return; + + kfree(pgt_entry); +} + +static struct mlxsw_sp_pgt_entry * +mlxsw_sp_pgt_entry_get(struct mlxsw_sp_pgt *pgt, u16 mid, u16 smpe) +{ + struct mlxsw_sp_pgt_entry *pgt_entry; + + pgt_entry = idr_find(&pgt->pgt_idr, mid); + if (pgt_entry) + return pgt_entry; + + return mlxsw_sp_pgt_entry_create(pgt, mid, smpe); +} + +static void mlxsw_sp_pgt_entry_put(struct mlxsw_sp_pgt *pgt, u16 mid) +{ + struct mlxsw_sp_pgt_entry *pgt_entry; + + pgt_entry = idr_find(&pgt->pgt_idr, mid); + if (WARN_ON(!pgt_entry)) + return; + + if (list_empty(&pgt_entry->ports_list)) + mlxsw_sp_pgt_entry_destroy(pgt, pgt_entry); +} + +static void mlxsw_sp_pgt_smid2_port_set(char *smid2_pl, u16 local_port, + bool member) +{ + mlxsw_reg_smid2_port_set(smid2_pl, local_port, member); + mlxsw_reg_smid2_port_mask_set(smid2_pl, local_port, 1); +} + +static int +mlxsw_sp_pgt_entry_port_write(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_pgt_entry *pgt_entry, + u16 local_port, bool member) +{ + char *smid2_pl; + int err; + + smid2_pl = kmalloc(MLXSW_REG_SMID2_LEN, GFP_KERNEL); + if (!smid2_pl) + return -ENOMEM; + + mlxsw_reg_smid2_pack(smid2_pl, pgt_entry->index, 0, 0, + mlxsw_sp->pgt->smpe_index_valid, + pgt_entry->smpe_index); + + mlxsw_sp_pgt_smid2_port_set(smid2_pl, local_port, member); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid2), smid2_pl); + + kfree(smid2_pl); + + return err; +} + +static struct mlxsw_sp_pgt_entry_port * +mlxsw_sp_pgt_entry_port_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_pgt_entry *pgt_entry, + u16 local_port) +{ + struct mlxsw_sp_pgt_entry_port *pgt_entry_port; + int err; + + pgt_entry_port = kzalloc(sizeof(*pgt_entry_port), GFP_KERNEL); + if (!pgt_entry_port) + return ERR_PTR(-ENOMEM); + + err = mlxsw_sp_pgt_entry_port_write(mlxsw_sp, pgt_entry, local_port, + true); + if (err) + goto err_pgt_entry_port_write; + + pgt_entry_port->local_port = local_port; + list_add(&pgt_entry_port->list, &pgt_entry->ports_list); + + return pgt_entry_port; + +err_pgt_entry_port_write: + kfree(pgt_entry_port); + return ERR_PTR(err); +} + +static void +mlxsw_sp_pgt_entry_port_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_pgt_entry *pgt_entry, + struct mlxsw_sp_pgt_entry_port *pgt_entry_port) + +{ + list_del(&pgt_entry_port->list); + mlxsw_sp_pgt_entry_port_write(mlxsw_sp, pgt_entry, + pgt_entry_port->local_port, false); + kfree(pgt_entry_port); +} + +static int mlxsw_sp_pgt_entry_port_add(struct mlxsw_sp *mlxsw_sp, u16 mid, + u16 smpe, u16 local_port) +{ + struct mlxsw_sp_pgt_entry_port *pgt_entry_port; + struct mlxsw_sp_pgt_entry *pgt_entry; + int err; + + mutex_lock(&mlxsw_sp->pgt->lock); + + pgt_entry = mlxsw_sp_pgt_entry_get(mlxsw_sp->pgt, mid, smpe); + if (IS_ERR(pgt_entry)) { + err = PTR_ERR(pgt_entry); + goto err_pgt_entry_get; + } + + pgt_entry_port = mlxsw_sp_pgt_entry_port_create(mlxsw_sp, pgt_entry, + local_port); + if (IS_ERR(pgt_entry_port)) { + err = PTR_ERR(pgt_entry_port); + goto err_pgt_entry_port_get; + } + + mutex_unlock(&mlxsw_sp->pgt->lock); + return 0; + +err_pgt_entry_port_get: + mlxsw_sp_pgt_entry_put(mlxsw_sp->pgt, mid); +err_pgt_entry_get: + mutex_unlock(&mlxsw_sp->pgt->lock); + return err; +} + +static void mlxsw_sp_pgt_entry_port_del(struct mlxsw_sp *mlxsw_sp, + u16 mid, u16 smpe, u16 local_port) +{ + struct mlxsw_sp_pgt_entry_port *pgt_entry_port; + struct mlxsw_sp_pgt_entry *pgt_entry; + + mutex_lock(&mlxsw_sp->pgt->lock); + + pgt_entry = idr_find(&mlxsw_sp->pgt->pgt_idr, mid); + if (!pgt_entry) + goto out; + + pgt_entry_port = mlxsw_sp_pgt_entry_port_lookup(pgt_entry, local_port); + if (!pgt_entry_port) + goto out; + + mlxsw_sp_pgt_entry_port_destroy(mlxsw_sp, pgt_entry, pgt_entry_port); + mlxsw_sp_pgt_entry_put(mlxsw_sp->pgt, mid); + +out: + mutex_unlock(&mlxsw_sp->pgt->lock); +} + +int mlxsw_sp_pgt_entry_port_set(struct mlxsw_sp *mlxsw_sp, u16 mid, + u16 smpe, u16 local_port, bool member) +{ + if (member) + return mlxsw_sp_pgt_entry_port_add(mlxsw_sp, mid, smpe, + local_port); + + mlxsw_sp_pgt_entry_port_del(mlxsw_sp, mid, smpe, local_port); + return 0; +} + +int mlxsw_sp_pgt_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_pgt *pgt; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, PGT_SIZE)) + return -EIO; + + pgt = kzalloc(sizeof(*mlxsw_sp->pgt), GFP_KERNEL); + if (!pgt) + return -ENOMEM; + + idr_init(&pgt->pgt_idr); + pgt->end_index = MLXSW_CORE_RES_GET(mlxsw_sp->core, PGT_SIZE); + mutex_init(&pgt->lock); + pgt->smpe_index_valid = mlxsw_sp->pgt_smpe_index_valid; + mlxsw_sp->pgt = pgt; + return 0; +} + +void mlxsw_sp_pgt_fini(struct mlxsw_sp *mlxsw_sp) +{ + mutex_destroy(&mlxsw_sp->pgt->lock); + WARN_ON(!idr_is_empty(&mlxsw_sp->pgt->pgt_idr)); + idr_destroy(&mlxsw_sp->pgt->pgt_idr); + kfree(mlxsw_sp->pgt); +} -- cgit v1.2.3