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(). ... --- tools/perf/util/bpf_skel/lock_contention.bpf.c | 249 +++++++++++++++++++++++++ 1 file changed, 249 insertions(+) create mode 100644 tools/perf/util/bpf_skel/lock_contention.bpf.c (limited to 'tools/perf/util/bpf_skel/lock_contention.bpf.c') diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c new file mode 100644 index 000000000..ad0ca5d50 --- /dev/null +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2022 Google +#include "vmlinux.h" +#include +#include +#include + +#include "lock_data.h" + +/* default buffer size */ +#define MAX_ENTRIES 10240 + +struct tstamp_data { + __u64 timestamp; + __u64 lock; + __u32 flags; + __s32 stack_id; +}; + +/* callstack storage */ +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, MAX_ENTRIES); +} stacks SEC(".maps"); + +/* maintain timestamp at the beginning of contention */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct tstamp_data); + __uint(max_entries, MAX_ENTRIES); +} tstamp SEC(".maps"); + +/* actual lock contention statistics */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(struct contention_key)); + __uint(value_size, sizeof(struct contention_data)); + __uint(max_entries, MAX_ENTRIES); +} lock_stat SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct contention_task_data)); + __uint(max_entries, MAX_ENTRIES); +} task_data SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} cpu_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} task_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} type_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} addr_filter SEC(".maps"); + +/* control flags */ +int enabled; +int has_cpu; +int has_task; +int has_type; +int has_addr; +int stack_skip; + +/* determine the key of lock stat */ +int aggr_mode; + +/* error stat */ +int lost; + +static inline int can_record(u64 *ctx) +{ + if (has_cpu) { + __u32 cpu = bpf_get_smp_processor_id(); + __u8 *ok; + + ok = bpf_map_lookup_elem(&cpu_filter, &cpu); + if (!ok) + return 0; + } + + if (has_task) { + __u8 *ok; + __u32 pid = bpf_get_current_pid_tgid(); + + ok = bpf_map_lookup_elem(&task_filter, &pid); + if (!ok) + return 0; + } + + if (has_type) { + __u8 *ok; + __u32 flags = (__u32)ctx[1]; + + ok = bpf_map_lookup_elem(&type_filter, &flags); + if (!ok) + return 0; + } + + if (has_addr) { + __u8 *ok; + __u64 addr = ctx[0]; + + ok = bpf_map_lookup_elem(&addr_filter, &addr); + if (!ok) + return 0; + } + + return 1; +} + +static inline void update_task_data(__u32 pid) +{ + struct contention_task_data *p; + + p = bpf_map_lookup_elem(&task_data, &pid); + if (p == NULL) { + struct contention_task_data data; + + bpf_get_current_comm(data.comm, sizeof(data.comm)); + bpf_map_update_elem(&task_data, &pid, &data, BPF_NOEXIST); + } +} + +SEC("tp_btf/contention_begin") +int contention_begin(u64 *ctx) +{ + __u32 pid; + struct tstamp_data *pelem; + + if (!enabled || !can_record(ctx)) + return 0; + + pid = bpf_get_current_pid_tgid(); + pelem = bpf_map_lookup_elem(&tstamp, &pid); + if (pelem && pelem->lock) + return 0; + + if (pelem == NULL) { + struct tstamp_data zero = {}; + + bpf_map_update_elem(&tstamp, &pid, &zero, BPF_ANY); + pelem = bpf_map_lookup_elem(&tstamp, &pid); + if (pelem == NULL) { + lost++; + return 0; + } + } + + pelem->timestamp = bpf_ktime_get_ns(); + pelem->lock = (__u64)ctx[0]; + pelem->flags = (__u32)ctx[1]; + + if (aggr_mode == LOCK_AGGR_CALLER) { + pelem->stack_id = bpf_get_stackid(ctx, &stacks, + BPF_F_FAST_STACK_CMP | stack_skip); + if (pelem->stack_id < 0) + lost++; + } + + return 0; +} + +SEC("tp_btf/contention_end") +int contention_end(u64 *ctx) +{ + __u32 pid; + struct tstamp_data *pelem; + struct contention_key key; + struct contention_data *data; + __u64 duration; + + if (!enabled) + return 0; + + pid = bpf_get_current_pid_tgid(); + pelem = bpf_map_lookup_elem(&tstamp, &pid); + if (!pelem || pelem->lock != ctx[0]) + return 0; + + duration = bpf_ktime_get_ns() - pelem->timestamp; + + switch (aggr_mode) { + case LOCK_AGGR_CALLER: + key.aggr_key = pelem->stack_id; + break; + case LOCK_AGGR_TASK: + key.aggr_key = pid; + update_task_data(pid); + break; + case LOCK_AGGR_ADDR: + key.aggr_key = pelem->lock; + break; + default: + /* should not happen */ + return 0; + } + + data = bpf_map_lookup_elem(&lock_stat, &key); + if (!data) { + struct contention_data first = { + .total_time = duration, + .max_time = duration, + .min_time = duration, + .count = 1, + .flags = pelem->flags, + }; + + bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST); + bpf_map_delete_elem(&tstamp, &pid); + return 0; + } + + __sync_fetch_and_add(&data->total_time, duration); + __sync_fetch_and_add(&data->count, 1); + + /* FIXME: need atomic operations */ + if (data->max_time < duration) + data->max_time = duration; + if (data->min_time > duration) + data->min_time = duration; + + bpf_map_delete_elem(&tstamp, &pid); + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; -- cgit v1.2.3