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/nvdimm/nd_perf.c | 329 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 329 insertions(+) create mode 100644 drivers/nvdimm/nd_perf.c (limited to 'drivers/nvdimm/nd_perf.c') diff --git a/drivers/nvdimm/nd_perf.c b/drivers/nvdimm/nd_perf.c new file mode 100644 index 000000000..433bbb68a --- /dev/null +++ b/drivers/nvdimm/nd_perf.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * nd_perf.c: NVDIMM Device Performance Monitoring Unit support + * + * Perf interface to expose nvdimm performance stats. + * + * Copyright (C) 2021 IBM Corporation + */ + +#define pr_fmt(fmt) "nvdimm_pmu: " fmt + +#include +#include + +#define EVENT(_name, _code) enum{_name = _code} + +/* + * NVDIMM Events codes. + */ + +/* Controller Reset Count */ +EVENT(CTL_RES_CNT, 0x1); +/* Controller Reset Elapsed Time */ +EVENT(CTL_RES_TM, 0x2); +/* Power-on Seconds */ +EVENT(POWERON_SECS, 0x3); +/* Life Remaining */ +EVENT(MEM_LIFE, 0x4); +/* Critical Resource Utilization */ +EVENT(CRI_RES_UTIL, 0x5); +/* Host Load Count */ +EVENT(HOST_L_CNT, 0x6); +/* Host Store Count */ +EVENT(HOST_S_CNT, 0x7); +/* Host Store Duration */ +EVENT(HOST_S_DUR, 0x8); +/* Host Load Duration */ +EVENT(HOST_L_DUR, 0x9); +/* Media Read Count */ +EVENT(MED_R_CNT, 0xa); +/* Media Write Count */ +EVENT(MED_W_CNT, 0xb); +/* Media Read Duration */ +EVENT(MED_R_DUR, 0xc); +/* Media Write Duration */ +EVENT(MED_W_DUR, 0xd); +/* Cache Read Hit Count */ +EVENT(CACHE_RH_CNT, 0xe); +/* Cache Write Hit Count */ +EVENT(CACHE_WH_CNT, 0xf); +/* Fast Write Count */ +EVENT(FAST_W_CNT, 0x10); + +NVDIMM_EVENT_ATTR(ctl_res_cnt, CTL_RES_CNT); +NVDIMM_EVENT_ATTR(ctl_res_tm, CTL_RES_TM); +NVDIMM_EVENT_ATTR(poweron_secs, POWERON_SECS); +NVDIMM_EVENT_ATTR(mem_life, MEM_LIFE); +NVDIMM_EVENT_ATTR(cri_res_util, CRI_RES_UTIL); +NVDIMM_EVENT_ATTR(host_l_cnt, HOST_L_CNT); +NVDIMM_EVENT_ATTR(host_s_cnt, HOST_S_CNT); +NVDIMM_EVENT_ATTR(host_s_dur, HOST_S_DUR); +NVDIMM_EVENT_ATTR(host_l_dur, HOST_L_DUR); +NVDIMM_EVENT_ATTR(med_r_cnt, MED_R_CNT); +NVDIMM_EVENT_ATTR(med_w_cnt, MED_W_CNT); +NVDIMM_EVENT_ATTR(med_r_dur, MED_R_DUR); +NVDIMM_EVENT_ATTR(med_w_dur, MED_W_DUR); +NVDIMM_EVENT_ATTR(cache_rh_cnt, CACHE_RH_CNT); +NVDIMM_EVENT_ATTR(cache_wh_cnt, CACHE_WH_CNT); +NVDIMM_EVENT_ATTR(fast_w_cnt, FAST_W_CNT); + +static struct attribute *nvdimm_events_attr[] = { + NVDIMM_EVENT_PTR(CTL_RES_CNT), + NVDIMM_EVENT_PTR(CTL_RES_TM), + NVDIMM_EVENT_PTR(POWERON_SECS), + NVDIMM_EVENT_PTR(MEM_LIFE), + NVDIMM_EVENT_PTR(CRI_RES_UTIL), + NVDIMM_EVENT_PTR(HOST_L_CNT), + NVDIMM_EVENT_PTR(HOST_S_CNT), + NVDIMM_EVENT_PTR(HOST_S_DUR), + NVDIMM_EVENT_PTR(HOST_L_DUR), + NVDIMM_EVENT_PTR(MED_R_CNT), + NVDIMM_EVENT_PTR(MED_W_CNT), + NVDIMM_EVENT_PTR(MED_R_DUR), + NVDIMM_EVENT_PTR(MED_W_DUR), + NVDIMM_EVENT_PTR(CACHE_RH_CNT), + NVDIMM_EVENT_PTR(CACHE_WH_CNT), + NVDIMM_EVENT_PTR(FAST_W_CNT), + NULL +}; + +static struct attribute_group nvdimm_pmu_events_group = { + .name = "events", + .attrs = nvdimm_events_attr, +}; + +PMU_FORMAT_ATTR(event, "config:0-4"); + +static struct attribute *nvdimm_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group nvdimm_pmu_format_group = { + .name = "format", + .attrs = nvdimm_pmu_format_attr, +}; + +ssize_t nvdimm_events_sysfs_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct perf_pmu_events_attr *pmu_attr; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); + + return sprintf(page, "event=0x%02llx\n", pmu_attr->id); +} + +static ssize_t nvdimm_pmu_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pmu *pmu = dev_get_drvdata(dev); + struct nvdimm_pmu *nd_pmu; + + nd_pmu = container_of(pmu, struct nvdimm_pmu, pmu); + + return cpumap_print_to_pagebuf(true, buf, cpumask_of(nd_pmu->cpu)); +} + +static int nvdimm_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct nvdimm_pmu *nd_pmu; + u32 target; + int nodeid; + const struct cpumask *cpumask; + + nd_pmu = hlist_entry_safe(node, struct nvdimm_pmu, node); + + /* Clear it, incase given cpu is set in nd_pmu->arch_cpumask */ + cpumask_test_and_clear_cpu(cpu, &nd_pmu->arch_cpumask); + + /* + * If given cpu is not same as current designated cpu for + * counter access, just return. + */ + if (cpu != nd_pmu->cpu) + return 0; + + /* Check for any active cpu in nd_pmu->arch_cpumask */ + target = cpumask_any(&nd_pmu->arch_cpumask); + + /* + * Incase we don't have any active cpu in nd_pmu->arch_cpumask, + * check in given cpu's numa node list. + */ + if (target >= nr_cpu_ids) { + nodeid = cpu_to_node(cpu); + cpumask = cpumask_of_node(nodeid); + target = cpumask_any_but(cpumask, cpu); + } + nd_pmu->cpu = target; + + /* Migrate nvdimm pmu events to the new target cpu if valid */ + if (target >= 0 && target < nr_cpu_ids) + perf_pmu_migrate_context(&nd_pmu->pmu, cpu, target); + + return 0; +} + +static int nvdimm_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct nvdimm_pmu *nd_pmu; + + nd_pmu = hlist_entry_safe(node, struct nvdimm_pmu, node); + + if (nd_pmu->cpu >= nr_cpu_ids) + nd_pmu->cpu = cpu; + + return 0; +} + +static int create_cpumask_attr_group(struct nvdimm_pmu *nd_pmu) +{ + struct perf_pmu_events_attr *pmu_events_attr; + struct attribute **attrs_group; + struct attribute_group *nvdimm_pmu_cpumask_group; + + pmu_events_attr = kzalloc(sizeof(*pmu_events_attr), GFP_KERNEL); + if (!pmu_events_attr) + return -ENOMEM; + + attrs_group = kzalloc(2 * sizeof(struct attribute *), GFP_KERNEL); + if (!attrs_group) { + kfree(pmu_events_attr); + return -ENOMEM; + } + + /* Allocate memory for cpumask attribute group */ + nvdimm_pmu_cpumask_group = kzalloc(sizeof(*nvdimm_pmu_cpumask_group), GFP_KERNEL); + if (!nvdimm_pmu_cpumask_group) { + kfree(pmu_events_attr); + kfree(attrs_group); + return -ENOMEM; + } + + sysfs_attr_init(&pmu_events_attr->attr.attr); + pmu_events_attr->attr.attr.name = "cpumask"; + pmu_events_attr->attr.attr.mode = 0444; + pmu_events_attr->attr.show = nvdimm_pmu_cpumask_show; + attrs_group[0] = &pmu_events_attr->attr.attr; + attrs_group[1] = NULL; + + nvdimm_pmu_cpumask_group->attrs = attrs_group; + nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR] = nvdimm_pmu_cpumask_group; + return 0; +} + +static int nvdimm_pmu_cpu_hotplug_init(struct nvdimm_pmu *nd_pmu) +{ + int nodeid, rc; + const struct cpumask *cpumask; + + /* + * Incase of cpu hotplug feature, arch specific code + * can provide required cpumask which can be used + * to get designatd cpu for counter access. + * Check for any active cpu in nd_pmu->arch_cpumask. + */ + if (!cpumask_empty(&nd_pmu->arch_cpumask)) { + nd_pmu->cpu = cpumask_any(&nd_pmu->arch_cpumask); + } else { + /* pick active cpu from the cpumask of device numa node. */ + nodeid = dev_to_node(nd_pmu->dev); + cpumask = cpumask_of_node(nodeid); + nd_pmu->cpu = cpumask_any(cpumask); + } + + rc = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "perf/nvdimm:online", + nvdimm_pmu_cpu_online, nvdimm_pmu_cpu_offline); + + if (rc < 0) + return rc; + + nd_pmu->cpuhp_state = rc; + + /* Register the pmu instance for cpu hotplug */ + rc = cpuhp_state_add_instance_nocalls(nd_pmu->cpuhp_state, &nd_pmu->node); + if (rc) { + cpuhp_remove_multi_state(nd_pmu->cpuhp_state); + return rc; + } + + /* Create cpumask attribute group */ + rc = create_cpumask_attr_group(nd_pmu); + if (rc) { + cpuhp_state_remove_instance_nocalls(nd_pmu->cpuhp_state, &nd_pmu->node); + cpuhp_remove_multi_state(nd_pmu->cpuhp_state); + return rc; + } + + return 0; +} + +static void nvdimm_pmu_free_hotplug_memory(struct nvdimm_pmu *nd_pmu) +{ + cpuhp_state_remove_instance_nocalls(nd_pmu->cpuhp_state, &nd_pmu->node); + cpuhp_remove_multi_state(nd_pmu->cpuhp_state); + + if (nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR]) + kfree(nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR]->attrs); + kfree(nd_pmu->pmu.attr_groups[NVDIMM_PMU_CPUMASK_ATTR]); +} + +int register_nvdimm_pmu(struct nvdimm_pmu *nd_pmu, struct platform_device *pdev) +{ + int rc; + + if (!nd_pmu || !pdev) + return -EINVAL; + + /* event functions like add/del/read/event_init and pmu name should not be NULL */ + if (WARN_ON_ONCE(!(nd_pmu->pmu.event_init && nd_pmu->pmu.add && + nd_pmu->pmu.del && nd_pmu->pmu.read && nd_pmu->pmu.name))) + return -EINVAL; + + nd_pmu->pmu.attr_groups = kzalloc((NVDIMM_PMU_NULL_ATTR + 1) * + sizeof(struct attribute_group *), GFP_KERNEL); + if (!nd_pmu->pmu.attr_groups) + return -ENOMEM; + + /* + * Add platform_device->dev pointer to nvdimm_pmu to access + * device data in events functions. + */ + nd_pmu->dev = &pdev->dev; + + /* Fill attribute groups for the nvdimm pmu device */ + nd_pmu->pmu.attr_groups[NVDIMM_PMU_FORMAT_ATTR] = &nvdimm_pmu_format_group; + nd_pmu->pmu.attr_groups[NVDIMM_PMU_EVENT_ATTR] = &nvdimm_pmu_events_group; + nd_pmu->pmu.attr_groups[NVDIMM_PMU_NULL_ATTR] = NULL; + + /* Fill attribute group for cpumask */ + rc = nvdimm_pmu_cpu_hotplug_init(nd_pmu); + if (rc) { + pr_info("cpu hotplug feature failed for device: %s\n", nd_pmu->pmu.name); + kfree(nd_pmu->pmu.attr_groups); + return rc; + } + + rc = perf_pmu_register(&nd_pmu->pmu, nd_pmu->pmu.name, -1); + if (rc) { + kfree(nd_pmu->pmu.attr_groups); + nvdimm_pmu_free_hotplug_memory(nd_pmu); + return rc; + } + + pr_info("%s NVDIMM performance monitor support registered\n", + nd_pmu->pmu.name); + + return 0; +} +EXPORT_SYMBOL_GPL(register_nvdimm_pmu); + +void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu) +{ + perf_pmu_unregister(&nd_pmu->pmu); + nvdimm_pmu_free_hotplug_memory(nd_pmu); + kfree(nd_pmu); +} +EXPORT_SYMBOL_GPL(unregister_nvdimm_pmu); -- cgit v1.2.3