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/soc/fsl/qe/ucc_slow.c | 359 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 359 insertions(+) create mode 100644 drivers/soc/fsl/qe/ucc_slow.c (limited to 'drivers/soc/fsl/qe/ucc_slow.c') diff --git a/drivers/soc/fsl/qe/ucc_slow.c b/drivers/soc/fsl/qe/ucc_slow.c new file mode 100644 index 000000000..d5ac1ac0e --- /dev/null +++ b/drivers/soc/fsl/qe/ucc_slow.c @@ -0,0 +1,359 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2006 Freescale Semiconductor, Inc. All rights reserved. + * + * Authors: Shlomi Gridish + * Li Yang + * + * Description: + * QE UCC Slow API Set - UCC Slow specific routines implementations. + */ +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include + +u32 ucc_slow_get_qe_cr_subblock(int uccs_num) +{ + switch (uccs_num) { + case 0: return QE_CR_SUBBLOCK_UCCSLOW1; + case 1: return QE_CR_SUBBLOCK_UCCSLOW2; + case 2: return QE_CR_SUBBLOCK_UCCSLOW3; + case 3: return QE_CR_SUBBLOCK_UCCSLOW4; + case 4: return QE_CR_SUBBLOCK_UCCSLOW5; + case 5: return QE_CR_SUBBLOCK_UCCSLOW6; + case 6: return QE_CR_SUBBLOCK_UCCSLOW7; + case 7: return QE_CR_SUBBLOCK_UCCSLOW8; + default: return QE_CR_SUBBLOCK_INVALID; + } +} +EXPORT_SYMBOL(ucc_slow_get_qe_cr_subblock); + +void ucc_slow_graceful_stop_tx(struct ucc_slow_private * uccs) +{ + struct ucc_slow_info *us_info = uccs->us_info; + u32 id; + + id = ucc_slow_get_qe_cr_subblock(us_info->ucc_num); + qe_issue_cmd(QE_GRACEFUL_STOP_TX, id, + QE_CR_PROTOCOL_UNSPECIFIED, 0); +} +EXPORT_SYMBOL(ucc_slow_graceful_stop_tx); + +void ucc_slow_stop_tx(struct ucc_slow_private * uccs) +{ + struct ucc_slow_info *us_info = uccs->us_info; + u32 id; + + id = ucc_slow_get_qe_cr_subblock(us_info->ucc_num); + qe_issue_cmd(QE_STOP_TX, id, QE_CR_PROTOCOL_UNSPECIFIED, 0); +} +EXPORT_SYMBOL(ucc_slow_stop_tx); + +void ucc_slow_restart_tx(struct ucc_slow_private * uccs) +{ + struct ucc_slow_info *us_info = uccs->us_info; + u32 id; + + id = ucc_slow_get_qe_cr_subblock(us_info->ucc_num); + qe_issue_cmd(QE_RESTART_TX, id, QE_CR_PROTOCOL_UNSPECIFIED, 0); +} +EXPORT_SYMBOL(ucc_slow_restart_tx); + +void ucc_slow_enable(struct ucc_slow_private * uccs, enum comm_dir mode) +{ + struct ucc_slow __iomem *us_regs; + u32 gumr_l; + + us_regs = uccs->us_regs; + + /* Enable reception and/or transmission on this UCC. */ + gumr_l = ioread32be(&us_regs->gumr_l); + if (mode & COMM_DIR_TX) { + gumr_l |= UCC_SLOW_GUMR_L_ENT; + uccs->enabled_tx = 1; + } + if (mode & COMM_DIR_RX) { + gumr_l |= UCC_SLOW_GUMR_L_ENR; + uccs->enabled_rx = 1; + } + iowrite32be(gumr_l, &us_regs->gumr_l); +} +EXPORT_SYMBOL(ucc_slow_enable); + +void ucc_slow_disable(struct ucc_slow_private * uccs, enum comm_dir mode) +{ + struct ucc_slow __iomem *us_regs; + u32 gumr_l; + + us_regs = uccs->us_regs; + + /* Disable reception and/or transmission on this UCC. */ + gumr_l = ioread32be(&us_regs->gumr_l); + if (mode & COMM_DIR_TX) { + gumr_l &= ~UCC_SLOW_GUMR_L_ENT; + uccs->enabled_tx = 0; + } + if (mode & COMM_DIR_RX) { + gumr_l &= ~UCC_SLOW_GUMR_L_ENR; + uccs->enabled_rx = 0; + } + iowrite32be(gumr_l, &us_regs->gumr_l); +} +EXPORT_SYMBOL(ucc_slow_disable); + +/* Initialize the UCC for Slow operations + * + * The caller should initialize the following us_info + */ +int ucc_slow_init(struct ucc_slow_info * us_info, struct ucc_slow_private ** uccs_ret) +{ + struct ucc_slow_private *uccs; + u32 i; + struct ucc_slow __iomem *us_regs; + u32 gumr; + struct qe_bd __iomem *bd; + u32 id; + u32 command; + int ret = 0; + + if (!us_info) + return -EINVAL; + + /* check if the UCC port number is in range. */ + if ((us_info->ucc_num < 0) || (us_info->ucc_num > UCC_MAX_NUM - 1)) { + printk(KERN_ERR "%s: illegal UCC number\n", __func__); + return -EINVAL; + } + + /* + * Set mrblr + * Check that 'max_rx_buf_length' is properly aligned (4), unless + * rfw is 1, meaning that QE accepts one byte at a time, unlike normal + * case when QE accepts 32 bits at a time. + */ + if ((!us_info->rfw) && + (us_info->max_rx_buf_length & (UCC_SLOW_MRBLR_ALIGNMENT - 1))) { + printk(KERN_ERR "max_rx_buf_length not aligned.\n"); + return -EINVAL; + } + + uccs = kzalloc(sizeof(struct ucc_slow_private), GFP_KERNEL); + if (!uccs) { + printk(KERN_ERR "%s: Cannot allocate private data\n", + __func__); + return -ENOMEM; + } + uccs->rx_base_offset = -1; + uccs->tx_base_offset = -1; + uccs->us_pram_offset = -1; + + /* Fill slow UCC structure */ + uccs->us_info = us_info; + /* Set the PHY base address */ + uccs->us_regs = ioremap(us_info->regs, sizeof(struct ucc_slow)); + if (uccs->us_regs == NULL) { + printk(KERN_ERR "%s: Cannot map UCC registers\n", __func__); + kfree(uccs); + return -ENOMEM; + } + + us_regs = uccs->us_regs; + uccs->p_ucce = &us_regs->ucce; + uccs->p_uccm = &us_regs->uccm; + + /* Get PRAM base */ + uccs->us_pram_offset = + qe_muram_alloc(UCC_SLOW_PRAM_SIZE, ALIGNMENT_OF_UCC_SLOW_PRAM); + if (uccs->us_pram_offset < 0) { + printk(KERN_ERR "%s: cannot allocate MURAM for PRAM", __func__); + ucc_slow_free(uccs); + return -ENOMEM; + } + id = ucc_slow_get_qe_cr_subblock(us_info->ucc_num); + qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, id, us_info->protocol, + uccs->us_pram_offset); + + uccs->us_pram = qe_muram_addr(uccs->us_pram_offset); + + /* Set UCC to slow type */ + ret = ucc_set_type(us_info->ucc_num, UCC_SPEED_TYPE_SLOW); + if (ret) { + printk(KERN_ERR "%s: cannot set UCC type", __func__); + ucc_slow_free(uccs); + return ret; + } + + iowrite16be(us_info->max_rx_buf_length, &uccs->us_pram->mrblr); + + INIT_LIST_HEAD(&uccs->confQ); + + /* Allocate BDs. */ + uccs->rx_base_offset = + qe_muram_alloc(us_info->rx_bd_ring_len * sizeof(struct qe_bd), + QE_ALIGNMENT_OF_BD); + if (uccs->rx_base_offset < 0) { + printk(KERN_ERR "%s: cannot allocate %u RX BDs\n", __func__, + us_info->rx_bd_ring_len); + ucc_slow_free(uccs); + return -ENOMEM; + } + + uccs->tx_base_offset = + qe_muram_alloc(us_info->tx_bd_ring_len * sizeof(struct qe_bd), + QE_ALIGNMENT_OF_BD); + if (uccs->tx_base_offset < 0) { + printk(KERN_ERR "%s: cannot allocate TX BDs", __func__); + ucc_slow_free(uccs); + return -ENOMEM; + } + + /* Init Tx bds */ + bd = uccs->confBd = uccs->tx_bd = qe_muram_addr(uccs->tx_base_offset); + for (i = 0; i < us_info->tx_bd_ring_len - 1; i++) { + /* clear bd buffer */ + iowrite32be(0, &bd->buf); + /* set bd status and length */ + iowrite32be(0, (u32 __iomem *)bd); + bd++; + } + /* for last BD set Wrap bit */ + iowrite32be(0, &bd->buf); + iowrite32be(T_W, (u32 __iomem *)bd); + + /* Init Rx bds */ + bd = uccs->rx_bd = qe_muram_addr(uccs->rx_base_offset); + for (i = 0; i < us_info->rx_bd_ring_len - 1; i++) { + /* set bd status and length */ + iowrite32be(0, (u32 __iomem *)bd); + /* clear bd buffer */ + iowrite32be(0, &bd->buf); + bd++; + } + /* for last BD set Wrap bit */ + iowrite32be(R_W, (u32 __iomem *)bd); + iowrite32be(0, &bd->buf); + + /* Set GUMR (For more details see the hardware spec.). */ + /* gumr_h */ + gumr = us_info->tcrc; + if (us_info->cdp) + gumr |= UCC_SLOW_GUMR_H_CDP; + if (us_info->ctsp) + gumr |= UCC_SLOW_GUMR_H_CTSP; + if (us_info->cds) + gumr |= UCC_SLOW_GUMR_H_CDS; + if (us_info->ctss) + gumr |= UCC_SLOW_GUMR_H_CTSS; + if (us_info->tfl) + gumr |= UCC_SLOW_GUMR_H_TFL; + if (us_info->rfw) + gumr |= UCC_SLOW_GUMR_H_RFW; + if (us_info->txsy) + gumr |= UCC_SLOW_GUMR_H_TXSY; + if (us_info->rtsm) + gumr |= UCC_SLOW_GUMR_H_RTSM; + iowrite32be(gumr, &us_regs->gumr_h); + + /* gumr_l */ + gumr = (u32)us_info->tdcr | (u32)us_info->rdcr | (u32)us_info->tenc | + (u32)us_info->renc | (u32)us_info->diag | (u32)us_info->mode; + if (us_info->tci) + gumr |= UCC_SLOW_GUMR_L_TCI; + if (us_info->rinv) + gumr |= UCC_SLOW_GUMR_L_RINV; + if (us_info->tinv) + gumr |= UCC_SLOW_GUMR_L_TINV; + if (us_info->tend) + gumr |= UCC_SLOW_GUMR_L_TEND; + iowrite32be(gumr, &us_regs->gumr_l); + + /* Function code registers */ + + /* if the data is in cachable memory, the 'global' */ + /* in the function code should be set. */ + iowrite8(UCC_BMR_BO_BE, &uccs->us_pram->tbmr); + iowrite8(UCC_BMR_BO_BE, &uccs->us_pram->rbmr); + + /* rbase, tbase are offsets from MURAM base */ + iowrite16be(uccs->rx_base_offset, &uccs->us_pram->rbase); + iowrite16be(uccs->tx_base_offset, &uccs->us_pram->tbase); + + /* Mux clocking */ + /* Grant Support */ + ucc_set_qe_mux_grant(us_info->ucc_num, us_info->grant_support); + /* Breakpoint Support */ + ucc_set_qe_mux_bkpt(us_info->ucc_num, us_info->brkpt_support); + /* Set Tsa or NMSI mode. */ + ucc_set_qe_mux_tsa(us_info->ucc_num, us_info->tsa); + /* If NMSI (not Tsa), set Tx and Rx clock. */ + if (!us_info->tsa) { + /* Rx clock routing */ + if (ucc_set_qe_mux_rxtx(us_info->ucc_num, us_info->rx_clock, + COMM_DIR_RX)) { + printk(KERN_ERR "%s: illegal value for RX clock\n", + __func__); + ucc_slow_free(uccs); + return -EINVAL; + } + /* Tx clock routing */ + if (ucc_set_qe_mux_rxtx(us_info->ucc_num, us_info->tx_clock, + COMM_DIR_TX)) { + printk(KERN_ERR "%s: illegal value for TX clock\n", + __func__); + ucc_slow_free(uccs); + return -EINVAL; + } + } + + /* Set interrupt mask register at UCC level. */ + iowrite16be(us_info->uccm_mask, &us_regs->uccm); + + /* First, clear anything pending at UCC level, + * otherwise, old garbage may come through + * as soon as the dam is opened. */ + + /* Writing '1' clears */ + iowrite16be(0xffff, &us_regs->ucce); + + /* Issue QE Init command */ + if (us_info->init_tx && us_info->init_rx) + command = QE_INIT_TX_RX; + else if (us_info->init_tx) + command = QE_INIT_TX; + else + command = QE_INIT_RX; /* We know at least one is TRUE */ + + qe_issue_cmd(command, id, us_info->protocol, 0); + + *uccs_ret = uccs; + return 0; +} +EXPORT_SYMBOL(ucc_slow_init); + +void ucc_slow_free(struct ucc_slow_private * uccs) +{ + if (!uccs) + return; + + qe_muram_free(uccs->rx_base_offset); + qe_muram_free(uccs->tx_base_offset); + qe_muram_free(uccs->us_pram_offset); + + if (uccs->us_regs) + iounmap(uccs->us_regs); + + kfree(uccs); +} +EXPORT_SYMBOL(ucc_slow_free); + -- cgit v1.2.3