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/ntb/test/ntb_msi_test.c | 432 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 432 insertions(+) create mode 100644 drivers/ntb/test/ntb_msi_test.c (limited to 'drivers/ntb/test/ntb_msi_test.c') diff --git a/drivers/ntb/test/ntb_msi_test.c b/drivers/ntb/test/ntb_msi_test.c new file mode 100644 index 000000000..4e18e0877 --- /dev/null +++ b/drivers/ntb/test/ntb_msi_test.c @@ -0,0 +1,432 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) + +#include +#include +#include +#include +#include +#include + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_VERSION("0.1"); +MODULE_AUTHOR("Logan Gunthorpe "); +MODULE_DESCRIPTION("Test for sending MSI interrupts over an NTB memory window"); + +static int num_irqs = 4; +module_param(num_irqs, int, 0644); +MODULE_PARM_DESC(num_irqs, "number of irqs to use"); + +struct ntb_msit_ctx { + struct ntb_dev *ntb; + struct dentry *dbgfs_dir; + struct work_struct setup_work; + + struct ntb_msit_isr_ctx { + int irq_idx; + int irq_num; + int occurrences; + struct ntb_msit_ctx *nm; + struct ntb_msi_desc desc; + } *isr_ctx; + + struct ntb_msit_peer { + struct ntb_msit_ctx *nm; + int pidx; + int num_irqs; + struct completion init_comp; + struct ntb_msi_desc *msi_desc; + } peers[]; +}; + +static struct dentry *ntb_msit_dbgfs_topdir; + +static irqreturn_t ntb_msit_isr(int irq, void *dev) +{ + struct ntb_msit_isr_ctx *isr_ctx = dev; + struct ntb_msit_ctx *nm = isr_ctx->nm; + + dev_dbg(&nm->ntb->dev, "Interrupt Occurred: %d", + isr_ctx->irq_idx); + + isr_ctx->occurrences++; + + return IRQ_HANDLED; +} + +static void ntb_msit_setup_work(struct work_struct *work) +{ + struct ntb_msit_ctx *nm = container_of(work, struct ntb_msit_ctx, + setup_work); + int irq_count = 0; + int irq; + int ret; + uintptr_t i; + + ret = ntb_msi_setup_mws(nm->ntb); + if (ret) { + dev_err(&nm->ntb->dev, "Unable to setup MSI windows: %d\n", + ret); + return; + } + + for (i = 0; i < num_irqs; i++) { + nm->isr_ctx[i].irq_idx = i; + nm->isr_ctx[i].nm = nm; + + if (!nm->isr_ctx[i].irq_num) { + irq = ntbm_msi_request_irq(nm->ntb, ntb_msit_isr, + KBUILD_MODNAME, + &nm->isr_ctx[i], + &nm->isr_ctx[i].desc); + if (irq < 0) + break; + + nm->isr_ctx[i].irq_num = irq; + } + + ret = ntb_spad_write(nm->ntb, 2 * i + 1, + nm->isr_ctx[i].desc.addr_offset); + if (ret) + break; + + ret = ntb_spad_write(nm->ntb, 2 * i + 2, + nm->isr_ctx[i].desc.data); + if (ret) + break; + + irq_count++; + } + + ntb_spad_write(nm->ntb, 0, irq_count); + ntb_peer_db_set(nm->ntb, BIT(ntb_port_number(nm->ntb))); +} + +static void ntb_msit_desc_changed(void *ctx) +{ + struct ntb_msit_ctx *nm = ctx; + int i; + + dev_dbg(&nm->ntb->dev, "MSI Descriptors Changed\n"); + + for (i = 0; i < num_irqs; i++) { + ntb_spad_write(nm->ntb, 2 * i + 1, + nm->isr_ctx[i].desc.addr_offset); + ntb_spad_write(nm->ntb, 2 * i + 2, + nm->isr_ctx[i].desc.data); + } + + ntb_peer_db_set(nm->ntb, BIT(ntb_port_number(nm->ntb))); +} + +static void ntb_msit_link_event(void *ctx) +{ + struct ntb_msit_ctx *nm = ctx; + + if (!ntb_link_is_up(nm->ntb, NULL, NULL)) + return; + + schedule_work(&nm->setup_work); +} + +static void ntb_msit_copy_peer_desc(struct ntb_msit_ctx *nm, int peer) +{ + int i; + struct ntb_msi_desc *desc = nm->peers[peer].msi_desc; + int irq_count = nm->peers[peer].num_irqs; + + for (i = 0; i < irq_count; i++) { + desc[i].addr_offset = ntb_peer_spad_read(nm->ntb, peer, + 2 * i + 1); + desc[i].data = ntb_peer_spad_read(nm->ntb, peer, 2 * i + 2); + } + + dev_info(&nm->ntb->dev, "Found %d interrupts on peer %d\n", + irq_count, peer); + + complete_all(&nm->peers[peer].init_comp); +} + +static void ntb_msit_db_event(void *ctx, int vec) +{ + struct ntb_msit_ctx *nm = ctx; + struct ntb_msi_desc *desc; + u64 peer_mask = ntb_db_read(nm->ntb); + u32 irq_count; + int peer; + + ntb_db_clear(nm->ntb, peer_mask); + + for (peer = 0; peer < sizeof(peer_mask) * 8; peer++) { + if (!(peer_mask & BIT(peer))) + continue; + + irq_count = ntb_peer_spad_read(nm->ntb, peer, 0); + if (irq_count == -1) + continue; + + desc = kcalloc(irq_count, sizeof(*desc), GFP_ATOMIC); + if (!desc) + continue; + + kfree(nm->peers[peer].msi_desc); + nm->peers[peer].msi_desc = desc; + nm->peers[peer].num_irqs = irq_count; + + ntb_msit_copy_peer_desc(nm, peer); + } +} + +static const struct ntb_ctx_ops ntb_msit_ops = { + .link_event = ntb_msit_link_event, + .db_event = ntb_msit_db_event, +}; + +static int ntb_msit_dbgfs_trigger(void *data, u64 idx) +{ + struct ntb_msit_peer *peer = data; + + if (idx >= peer->num_irqs) + return -EINVAL; + + dev_dbg(&peer->nm->ntb->dev, "trigger irq %llu on peer %u\n", + idx, peer->pidx); + + return ntb_msi_peer_trigger(peer->nm->ntb, peer->pidx, + &peer->msi_desc[idx]); +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_trigger_fops, NULL, + ntb_msit_dbgfs_trigger, "%llu\n"); + +static int ntb_msit_dbgfs_port_get(void *data, u64 *port) +{ + struct ntb_msit_peer *peer = data; + + *port = ntb_peer_port_number(peer->nm->ntb, peer->pidx); + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_port_fops, ntb_msit_dbgfs_port_get, + NULL, "%llu\n"); + +static int ntb_msit_dbgfs_count_get(void *data, u64 *count) +{ + struct ntb_msit_peer *peer = data; + + *count = peer->num_irqs; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_count_fops, ntb_msit_dbgfs_count_get, + NULL, "%llu\n"); + +static int ntb_msit_dbgfs_ready_get(void *data, u64 *ready) +{ + struct ntb_msit_peer *peer = data; + + *ready = try_wait_for_completion(&peer->init_comp); + + return 0; +} + +static int ntb_msit_dbgfs_ready_set(void *data, u64 ready) +{ + struct ntb_msit_peer *peer = data; + + return wait_for_completion_interruptible(&peer->init_comp); +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_ready_fops, ntb_msit_dbgfs_ready_get, + ntb_msit_dbgfs_ready_set, "%llu\n"); + +static int ntb_msit_dbgfs_occurrences_get(void *data, u64 *occurrences) +{ + struct ntb_msit_isr_ctx *isr_ctx = data; + + *occurrences = isr_ctx->occurrences; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_occurrences_fops, + ntb_msit_dbgfs_occurrences_get, + NULL, "%llu\n"); + +static int ntb_msit_dbgfs_local_port_get(void *data, u64 *port) +{ + struct ntb_msit_ctx *nm = data; + + *port = ntb_port_number(nm->ntb); + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_local_port_fops, + ntb_msit_dbgfs_local_port_get, + NULL, "%llu\n"); + +static void ntb_msit_create_dbgfs(struct ntb_msit_ctx *nm) +{ + struct pci_dev *pdev = nm->ntb->pdev; + char buf[32]; + int i; + struct dentry *peer_dir; + + nm->dbgfs_dir = debugfs_create_dir(pci_name(pdev), + ntb_msit_dbgfs_topdir); + debugfs_create_file("port", 0400, nm->dbgfs_dir, nm, + &ntb_msit_local_port_fops); + + for (i = 0; i < ntb_peer_port_count(nm->ntb); i++) { + nm->peers[i].pidx = i; + nm->peers[i].nm = nm; + init_completion(&nm->peers[i].init_comp); + + snprintf(buf, sizeof(buf), "peer%d", i); + peer_dir = debugfs_create_dir(buf, nm->dbgfs_dir); + + debugfs_create_file_unsafe("trigger", 0200, peer_dir, + &nm->peers[i], + &ntb_msit_trigger_fops); + + debugfs_create_file_unsafe("port", 0400, peer_dir, + &nm->peers[i], &ntb_msit_port_fops); + + debugfs_create_file_unsafe("count", 0400, peer_dir, + &nm->peers[i], + &ntb_msit_count_fops); + + debugfs_create_file_unsafe("ready", 0600, peer_dir, + &nm->peers[i], + &ntb_msit_ready_fops); + } + + for (i = 0; i < num_irqs; i++) { + snprintf(buf, sizeof(buf), "irq%d_occurrences", i); + debugfs_create_file_unsafe(buf, 0400, nm->dbgfs_dir, + &nm->isr_ctx[i], + &ntb_msit_occurrences_fops); + } +} + +static void ntb_msit_remove_dbgfs(struct ntb_msit_ctx *nm) +{ + debugfs_remove_recursive(nm->dbgfs_dir); +} + +static int ntb_msit_probe(struct ntb_client *client, struct ntb_dev *ntb) +{ + struct ntb_msit_ctx *nm; + int peers; + int ret; + + peers = ntb_peer_port_count(ntb); + if (peers <= 0) + return -EINVAL; + + if (ntb_spad_is_unsafe(ntb) || ntb_spad_count(ntb) < 2 * num_irqs + 1) { + dev_err(&ntb->dev, "NTB MSI test requires at least %d spads for %d irqs\n", + 2 * num_irqs + 1, num_irqs); + return -EFAULT; + } + + ret = ntb_spad_write(ntb, 0, -1); + if (ret) { + dev_err(&ntb->dev, "Unable to write spads: %d\n", ret); + return ret; + } + + ret = ntb_db_clear_mask(ntb, GENMASK(peers - 1, 0)); + if (ret) { + dev_err(&ntb->dev, "Unable to clear doorbell mask: %d\n", ret); + return ret; + } + + ret = ntb_msi_init(ntb, ntb_msit_desc_changed); + if (ret) { + dev_err(&ntb->dev, "Unable to initialize MSI library: %d\n", + ret); + return ret; + } + + nm = devm_kzalloc(&ntb->dev, struct_size(nm, peers, peers), GFP_KERNEL); + if (!nm) + return -ENOMEM; + + nm->isr_ctx = devm_kcalloc(&ntb->dev, num_irqs, sizeof(*nm->isr_ctx), + GFP_KERNEL); + if (!nm->isr_ctx) + return -ENOMEM; + + INIT_WORK(&nm->setup_work, ntb_msit_setup_work); + nm->ntb = ntb; + + ntb_msit_create_dbgfs(nm); + + ret = ntb_set_ctx(ntb, nm, &ntb_msit_ops); + if (ret) + goto remove_dbgfs; + + if (!nm->isr_ctx) { + ret = -ENOMEM; + goto remove_dbgfs; + } + + ntb_link_enable(ntb, NTB_SPEED_AUTO, NTB_WIDTH_AUTO); + + return 0; + +remove_dbgfs: + ntb_msit_remove_dbgfs(nm); + devm_kfree(&ntb->dev, nm->isr_ctx); + devm_kfree(&ntb->dev, nm); + return ret; +} + +static void ntb_msit_remove(struct ntb_client *client, struct ntb_dev *ntb) +{ + struct ntb_msit_ctx *nm = ntb->ctx; + int i; + + ntb_link_disable(ntb); + ntb_db_set_mask(ntb, ntb_db_valid_mask(ntb)); + ntb_msi_clear_mws(ntb); + + for (i = 0; i < ntb_peer_port_count(ntb); i++) + kfree(nm->peers[i].msi_desc); + + ntb_clear_ctx(ntb); + ntb_msit_remove_dbgfs(nm); +} + +static struct ntb_client ntb_msit_client = { + .ops = { + .probe = ntb_msit_probe, + .remove = ntb_msit_remove + } +}; + +static int __init ntb_msit_init(void) +{ + int ret; + + if (debugfs_initialized()) + ntb_msit_dbgfs_topdir = debugfs_create_dir(KBUILD_MODNAME, + NULL); + + ret = ntb_register_client(&ntb_msit_client); + if (ret) + debugfs_remove_recursive(ntb_msit_dbgfs_topdir); + + return ret; +} +module_init(ntb_msit_init); + +static void __exit ntb_msit_exit(void) +{ + ntb_unregister_client(&ntb_msit_client); + debugfs_remove_recursive(ntb_msit_dbgfs_topdir); +} +module_exit(ntb_msit_exit); -- cgit v1.2.3