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(). ... --- arch/sparc/kernel/pci_msi.c | 447 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 447 insertions(+) create mode 100644 arch/sparc/kernel/pci_msi.c (limited to 'arch/sparc/kernel/pci_msi.c') diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c new file mode 100644 index 000000000..9ed119857 --- /dev/null +++ b/arch/sparc/kernel/pci_msi.c @@ -0,0 +1,447 @@ +// SPDX-License-Identifier: GPL-2.0 +/* pci_msi.c: Sparc64 MSI support common layer. + * + * Copyright (C) 2007 David S. Miller (davem@davemloft.net) + */ +#include +#include +#include +#include + +#include "pci_impl.h" + +static irqreturn_t sparc64_msiq_interrupt(int irq, void *cookie) +{ + struct sparc64_msiq_cookie *msiq_cookie = cookie; + struct pci_pbm_info *pbm = msiq_cookie->pbm; + unsigned long msiqid = msiq_cookie->msiqid; + const struct sparc64_msiq_ops *ops; + unsigned long orig_head, head; + int err; + + ops = pbm->msi_ops; + + err = ops->get_head(pbm, msiqid, &head); + if (unlikely(err < 0)) + goto err_get_head; + + orig_head = head; + for (;;) { + unsigned long msi; + + err = ops->dequeue_msi(pbm, msiqid, &head, &msi); + if (likely(err > 0)) { + unsigned int irq; + + irq = pbm->msi_irq_table[msi - pbm->msi_first]; + generic_handle_irq(irq); + } + + if (unlikely(err < 0)) + goto err_dequeue; + + if (err == 0) + break; + } + if (likely(head != orig_head)) { + err = ops->set_head(pbm, msiqid, head); + if (unlikely(err < 0)) + goto err_set_head; + } + return IRQ_HANDLED; + +err_get_head: + printk(KERN_EMERG "MSI: Get head on msiqid[%lu] gives error %d\n", + msiqid, err); + goto err_out; + +err_dequeue: + printk(KERN_EMERG "MSI: Dequeue head[%lu] from msiqid[%lu] " + "gives error %d\n", + head, msiqid, err); + goto err_out; + +err_set_head: + printk(KERN_EMERG "MSI: Set head[%lu] on msiqid[%lu] " + "gives error %d\n", + head, msiqid, err); + goto err_out; + +err_out: + return IRQ_NONE; +} + +static u32 pick_msiq(struct pci_pbm_info *pbm) +{ + static DEFINE_SPINLOCK(rotor_lock); + unsigned long flags; + u32 ret, rotor; + + spin_lock_irqsave(&rotor_lock, flags); + + rotor = pbm->msiq_rotor; + ret = pbm->msiq_first + rotor; + + if (++rotor >= pbm->msiq_num) + rotor = 0; + pbm->msiq_rotor = rotor; + + spin_unlock_irqrestore(&rotor_lock, flags); + + return ret; +} + + +static int alloc_msi(struct pci_pbm_info *pbm) +{ + int i; + + for (i = 0; i < pbm->msi_num; i++) { + if (!test_and_set_bit(i, pbm->msi_bitmap)) + return i + pbm->msi_first; + } + + return -ENOENT; +} + +static void free_msi(struct pci_pbm_info *pbm, int msi_num) +{ + msi_num -= pbm->msi_first; + clear_bit(msi_num, pbm->msi_bitmap); +} + +static struct irq_chip msi_irq = { + .name = "PCI-MSI", + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + /* XXX affinity XXX */ +}; + +static int sparc64_setup_msi_irq(unsigned int *irq_p, + struct pci_dev *pdev, + struct msi_desc *entry) +{ + struct pci_pbm_info *pbm = pdev->dev.archdata.host_controller; + const struct sparc64_msiq_ops *ops = pbm->msi_ops; + struct msi_msg msg; + int msi, err; + u32 msiqid; + + *irq_p = irq_alloc(0, 0); + err = -ENOMEM; + if (!*irq_p) + goto out_err; + + irq_set_chip_and_handler_name(*irq_p, &msi_irq, handle_simple_irq, + "MSI"); + + err = alloc_msi(pbm); + if (unlikely(err < 0)) + goto out_irq_free; + + msi = err; + + msiqid = pick_msiq(pbm); + + err = ops->msi_setup(pbm, msiqid, msi, + (entry->pci.msi_attrib.is_64 ? 1 : 0)); + if (err) + goto out_msi_free; + + pbm->msi_irq_table[msi - pbm->msi_first] = *irq_p; + + if (entry->pci.msi_attrib.is_64) { + msg.address_hi = pbm->msi64_start >> 32; + msg.address_lo = pbm->msi64_start & 0xffffffff; + } else { + msg.address_hi = 0; + msg.address_lo = pbm->msi32_start; + } + msg.data = msi; + + irq_set_msi_desc(*irq_p, entry); + pci_write_msi_msg(*irq_p, &msg); + + return 0; + +out_msi_free: + free_msi(pbm, msi); + +out_irq_free: + irq_set_chip(*irq_p, NULL); + irq_free(*irq_p); + *irq_p = 0; + +out_err: + return err; +} + +static void sparc64_teardown_msi_irq(unsigned int irq, + struct pci_dev *pdev) +{ + struct pci_pbm_info *pbm = pdev->dev.archdata.host_controller; + const struct sparc64_msiq_ops *ops = pbm->msi_ops; + unsigned int msi_num; + int i, err; + + for (i = 0; i < pbm->msi_num; i++) { + if (pbm->msi_irq_table[i] == irq) + break; + } + if (i >= pbm->msi_num) { + pci_err(pdev, "%s: teardown: No MSI for irq %u\n", pbm->name, + irq); + return; + } + + msi_num = pbm->msi_first + i; + pbm->msi_irq_table[i] = ~0U; + + err = ops->msi_teardown(pbm, msi_num); + if (err) { + pci_err(pdev, "%s: teardown: ops->teardown() on MSI %u, " + "irq %u, gives error %d\n", pbm->name, msi_num, irq, + err); + return; + } + + free_msi(pbm, msi_num); + + irq_set_chip(irq, NULL); + irq_free(irq); +} + +static int msi_bitmap_alloc(struct pci_pbm_info *pbm) +{ + unsigned long size, bits_per_ulong; + + bits_per_ulong = sizeof(unsigned long) * 8; + size = (pbm->msi_num + (bits_per_ulong - 1)) & ~(bits_per_ulong - 1); + size /= 8; + BUG_ON(size % sizeof(unsigned long)); + + pbm->msi_bitmap = kzalloc(size, GFP_KERNEL); + if (!pbm->msi_bitmap) + return -ENOMEM; + + return 0; +} + +static void msi_bitmap_free(struct pci_pbm_info *pbm) +{ + kfree(pbm->msi_bitmap); + pbm->msi_bitmap = NULL; +} + +static int msi_table_alloc(struct pci_pbm_info *pbm) +{ + int size, i; + + size = pbm->msiq_num * sizeof(struct sparc64_msiq_cookie); + pbm->msiq_irq_cookies = kzalloc(size, GFP_KERNEL); + if (!pbm->msiq_irq_cookies) + return -ENOMEM; + + for (i = 0; i < pbm->msiq_num; i++) { + struct sparc64_msiq_cookie *p; + + p = &pbm->msiq_irq_cookies[i]; + p->pbm = pbm; + p->msiqid = pbm->msiq_first + i; + } + + size = pbm->msi_num * sizeof(unsigned int); + pbm->msi_irq_table = kzalloc(size, GFP_KERNEL); + if (!pbm->msi_irq_table) { + kfree(pbm->msiq_irq_cookies); + pbm->msiq_irq_cookies = NULL; + return -ENOMEM; + } + + return 0; +} + +static void msi_table_free(struct pci_pbm_info *pbm) +{ + kfree(pbm->msiq_irq_cookies); + pbm->msiq_irq_cookies = NULL; + + kfree(pbm->msi_irq_table); + pbm->msi_irq_table = NULL; +} + +static int bringup_one_msi_queue(struct pci_pbm_info *pbm, + const struct sparc64_msiq_ops *ops, + unsigned long msiqid, + unsigned long devino) +{ + int irq = ops->msiq_build_irq(pbm, msiqid, devino); + int err, nid; + + if (irq < 0) + return irq; + + nid = pbm->numa_node; + if (nid != -1) { + cpumask_t numa_mask; + + cpumask_copy(&numa_mask, cpumask_of_node(nid)); + irq_set_affinity(irq, &numa_mask); + } + err = request_irq(irq, sparc64_msiq_interrupt, 0, + "MSIQ", + &pbm->msiq_irq_cookies[msiqid - pbm->msiq_first]); + if (err) + return err; + + return 0; +} + +static int sparc64_bringup_msi_queues(struct pci_pbm_info *pbm, + const struct sparc64_msiq_ops *ops) +{ + int i; + + for (i = 0; i < pbm->msiq_num; i++) { + unsigned long msiqid = i + pbm->msiq_first; + unsigned long devino = i + pbm->msiq_first_devino; + int err; + + err = bringup_one_msi_queue(pbm, ops, msiqid, devino); + if (err) + return err; + } + + return 0; +} + +void sparc64_pbm_msi_init(struct pci_pbm_info *pbm, + const struct sparc64_msiq_ops *ops) +{ + const u32 *val; + int len; + + val = of_get_property(pbm->op->dev.of_node, "#msi-eqs", &len); + if (!val || len != 4) + goto no_msi; + pbm->msiq_num = *val; + if (pbm->msiq_num) { + const struct msiq_prop { + u32 first_msiq; + u32 num_msiq; + u32 first_devino; + } *mqp; + const struct msi_range_prop { + u32 first_msi; + u32 num_msi; + } *mrng; + const struct addr_range_prop { + u32 msi32_high; + u32 msi32_low; + u32 msi32_len; + u32 msi64_high; + u32 msi64_low; + u32 msi64_len; + } *arng; + + val = of_get_property(pbm->op->dev.of_node, "msi-eq-size", &len); + if (!val || len != 4) + goto no_msi; + + pbm->msiq_ent_count = *val; + + mqp = of_get_property(pbm->op->dev.of_node, + "msi-eq-to-devino", &len); + if (!mqp) + mqp = of_get_property(pbm->op->dev.of_node, + "msi-eq-devino", &len); + if (!mqp || len != sizeof(struct msiq_prop)) + goto no_msi; + + pbm->msiq_first = mqp->first_msiq; + pbm->msiq_first_devino = mqp->first_devino; + + val = of_get_property(pbm->op->dev.of_node, "#msi", &len); + if (!val || len != 4) + goto no_msi; + pbm->msi_num = *val; + + mrng = of_get_property(pbm->op->dev.of_node, "msi-ranges", &len); + if (!mrng || len != sizeof(struct msi_range_prop)) + goto no_msi; + pbm->msi_first = mrng->first_msi; + + val = of_get_property(pbm->op->dev.of_node, "msi-data-mask", &len); + if (!val || len != 4) + goto no_msi; + pbm->msi_data_mask = *val; + + val = of_get_property(pbm->op->dev.of_node, "msix-data-width", &len); + if (!val || len != 4) + goto no_msi; + pbm->msix_data_width = *val; + + arng = of_get_property(pbm->op->dev.of_node, "msi-address-ranges", + &len); + if (!arng || len != sizeof(struct addr_range_prop)) + goto no_msi; + pbm->msi32_start = ((u64)arng->msi32_high << 32) | + (u64) arng->msi32_low; + pbm->msi64_start = ((u64)arng->msi64_high << 32) | + (u64) arng->msi64_low; + pbm->msi32_len = arng->msi32_len; + pbm->msi64_len = arng->msi64_len; + + if (msi_bitmap_alloc(pbm)) + goto no_msi; + + if (msi_table_alloc(pbm)) { + msi_bitmap_free(pbm); + goto no_msi; + } + + if (ops->msiq_alloc(pbm)) { + msi_table_free(pbm); + msi_bitmap_free(pbm); + goto no_msi; + } + + if (sparc64_bringup_msi_queues(pbm, ops)) { + ops->msiq_free(pbm); + msi_table_free(pbm); + msi_bitmap_free(pbm); + goto no_msi; + } + + printk(KERN_INFO "%s: MSI Queue first[%u] num[%u] count[%u] " + "devino[0x%x]\n", + pbm->name, + pbm->msiq_first, pbm->msiq_num, + pbm->msiq_ent_count, + pbm->msiq_first_devino); + printk(KERN_INFO "%s: MSI first[%u] num[%u] mask[0x%x] " + "width[%u]\n", + pbm->name, + pbm->msi_first, pbm->msi_num, pbm->msi_data_mask, + pbm->msix_data_width); + printk(KERN_INFO "%s: MSI addr32[0x%llx:0x%x] " + "addr64[0x%llx:0x%x]\n", + pbm->name, + pbm->msi32_start, pbm->msi32_len, + pbm->msi64_start, pbm->msi64_len); + printk(KERN_INFO "%s: MSI queues at RA [%016lx]\n", + pbm->name, + __pa(pbm->msi_queues)); + + pbm->msi_ops = ops; + pbm->setup_msi_irq = sparc64_setup_msi_irq; + pbm->teardown_msi_irq = sparc64_teardown_msi_irq; + } + return; + +no_msi: + pbm->msiq_num = 0; + printk(KERN_INFO "%s: No MSI support.\n", pbm->name); +} -- cgit v1.2.3