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/bench/epoll-ctl.c | 428 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 428 insertions(+) create mode 100644 tools/perf/bench/epoll-ctl.c (limited to 'tools/perf/bench/epoll-ctl.c') diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c new file mode 100644 index 000000000..521d1ff97 --- /dev/null +++ b/tools/perf/bench/epoll-ctl.c @@ -0,0 +1,428 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 Davidlohr Bueso. + * + * Benchmark the various operations allowed for epoll_ctl(2). + * The idea is to concurrently stress a single epoll instance + */ +#ifdef HAVE_EVENTFD_SUPPORT +/* For the CLR_() macros */ +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../util/mutex.h" +#include "../util/stat.h" +#include +#include "bench.h" + +#include + +#define printinfo(fmt, arg...) \ + do { if (__verbose) printf(fmt, ## arg); } while (0) + +static unsigned int nthreads = 0; +static unsigned int nsecs = 8; +static bool done, __verbose, randomize; + +/* + * epoll related shared variables. + */ + +/* Maximum number of nesting allowed inside epoll sets */ +#define EPOLL_MAXNESTS 4 + +enum { + OP_EPOLL_ADD, + OP_EPOLL_MOD, + OP_EPOLL_DEL, + EPOLL_NR_OPS, +}; + +static int epollfd; +static int *epollfdp; +static bool noaffinity; +static unsigned int nested = 0; + +/* amount of fds to monitor, per thread */ +static unsigned int nfds = 64; + +static struct mutex thread_lock; +static unsigned int threads_starting; +static struct stats all_stats[EPOLL_NR_OPS]; +static struct cond thread_parent, thread_worker; + +struct worker { + int tid; + pthread_t thread; + unsigned long ops[EPOLL_NR_OPS]; + int *fdmap; +}; + +static const struct option options[] = { + OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), + OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"), + OPT_UINTEGER('f', "nfds", &nfds, "Specify amount of file descriptors to monitor for each thread"), + OPT_BOOLEAN( 'n', "noaffinity", &noaffinity, "Disables CPU affinity"), + OPT_UINTEGER( 'N', "nested", &nested, "Nesting level epoll hierarchy (default is 0, no nesting)"), + OPT_BOOLEAN( 'R', "randomize", &randomize, "Perform random operations on random fds"), + OPT_BOOLEAN( 'v', "verbose", &__verbose, "Verbose mode"), + OPT_END() +}; + +static const char * const bench_epoll_ctl_usage[] = { + "perf bench epoll ctl ", + NULL +}; + +static void toggle_done(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + /* inform all threads that we're done for the day */ + done = true; + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); +} + +static void nest_epollfd(void) +{ + unsigned int i; + struct epoll_event ev; + + if (nested > EPOLL_MAXNESTS) + nested = EPOLL_MAXNESTS; + printinfo("Nesting level(s): %d\n", nested); + + epollfdp = calloc(nested, sizeof(int)); + if (!epollfdp) + err(EXIT_FAILURE, "calloc"); + + for (i = 0; i < nested; i++) { + epollfdp[i] = epoll_create(1); + if (epollfd < 0) + err(EXIT_FAILURE, "epoll_create"); + } + + ev.events = EPOLLHUP; /* anything */ + ev.data.u64 = i; /* any number */ + + for (i = nested - 1; i; i--) { + if (epoll_ctl(epollfdp[i - 1], EPOLL_CTL_ADD, + epollfdp[i], &ev) < 0) + err(EXIT_FAILURE, "epoll_ctl"); + } + + if (epoll_ctl(epollfd, EPOLL_CTL_ADD, *epollfdp, &ev) < 0) + err(EXIT_FAILURE, "epoll_ctl"); +} + +static inline void do_epoll_op(struct worker *w, int op, int fd) +{ + int error; + struct epoll_event ev; + + ev.events = EPOLLIN; + ev.data.u64 = fd; + + switch (op) { + case OP_EPOLL_ADD: + error = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev); + break; + case OP_EPOLL_MOD: + ev.events = EPOLLOUT; + error = epoll_ctl(epollfd, EPOLL_CTL_MOD, fd, &ev); + break; + case OP_EPOLL_DEL: + error = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, NULL); + break; + default: + error = 1; + break; + } + + if (!error) + w->ops[op]++; +} + +static inline void do_random_epoll_op(struct worker *w) +{ + unsigned long rnd1 = random(), rnd2 = random(); + int op, fd; + + fd = w->fdmap[rnd1 % nfds]; + op = rnd2 % EPOLL_NR_OPS; + + do_epoll_op(w, op, fd); +} + +static void *workerfn(void *arg) +{ + unsigned int i; + struct worker *w = (struct worker *) arg; + struct timespec ts = { .tv_sec = 0, + .tv_nsec = 250 }; + + mutex_lock(&thread_lock); + threads_starting--; + if (!threads_starting) + cond_signal(&thread_parent); + cond_wait(&thread_worker, &thread_lock); + mutex_unlock(&thread_lock); + + /* Let 'em loose */ + do { + /* random */ + if (randomize) { + do_random_epoll_op(w); + } else { + for (i = 0; i < nfds; i++) { + do_epoll_op(w, OP_EPOLL_ADD, w->fdmap[i]); + do_epoll_op(w, OP_EPOLL_MOD, w->fdmap[i]); + do_epoll_op(w, OP_EPOLL_DEL, w->fdmap[i]); + } + } + + nanosleep(&ts, NULL); + } while (!done); + + return NULL; +} + +static void init_fdmaps(struct worker *w, int pct) +{ + unsigned int i; + int inc; + struct epoll_event ev; + + if (!pct) + return; + + inc = 100/pct; + for (i = 0; i < nfds; i+=inc) { + ev.data.fd = w->fdmap[i]; + ev.events = EPOLLIN; + + if (epoll_ctl(epollfd, EPOLL_CTL_ADD, w->fdmap[i], &ev) < 0) + err(EXIT_FAILURE, "epoll_ct"); + } +} + +static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) +{ + pthread_attr_t thread_attr, *attrp = NULL; + cpu_set_t *cpuset; + unsigned int i, j; + int ret = 0; + int nrcpus; + size_t size; + + if (!noaffinity) + pthread_attr_init(&thread_attr); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + + for (i = 0; i < nthreads; i++) { + struct worker *w = &worker[i]; + + w->tid = i; + w->fdmap = calloc(nfds, sizeof(int)); + if (!w->fdmap) + return 1; + + for (j = 0; j < nfds; j++) { + w->fdmap[j] = eventfd(0, EFD_NONBLOCK); + if (w->fdmap[j] < 0) + err(EXIT_FAILURE, "eventfd"); + } + + /* + * Lets add 50% of the fdmap to the epoll instance, and + * do it before any threads are started; otherwise there is + * an initial bias of the call failing (mod and del ops). + */ + if (randomize) + init_fdmaps(w, 50); + + if (!noaffinity) { + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); + + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); + err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } + + attrp = &thread_attr; + } + + ret = pthread_create(&w->thread, attrp, workerfn, + (void *)(struct worker *) w); + if (ret) { + CPU_FREE(cpuset); + err(EXIT_FAILURE, "pthread_create"); + } + } + + CPU_FREE(cpuset); + if (!noaffinity) + pthread_attr_destroy(&thread_attr); + + return ret; +} + +static void print_summary(void) +{ + int i; + unsigned long avg[EPOLL_NR_OPS]; + double stddev[EPOLL_NR_OPS]; + + for (i = 0; i < EPOLL_NR_OPS; i++) { + avg[i] = avg_stats(&all_stats[i]); + stddev[i] = stddev_stats(&all_stats[i]); + } + + printf("\nAveraged %ld ADD operations (+- %.2f%%)\n", + avg[OP_EPOLL_ADD], rel_stddev_stats(stddev[OP_EPOLL_ADD], + avg[OP_EPOLL_ADD])); + printf("Averaged %ld MOD operations (+- %.2f%%)\n", + avg[OP_EPOLL_MOD], rel_stddev_stats(stddev[OP_EPOLL_MOD], + avg[OP_EPOLL_MOD])); + printf("Averaged %ld DEL operations (+- %.2f%%)\n", + avg[OP_EPOLL_DEL], rel_stddev_stats(stddev[OP_EPOLL_DEL], + avg[OP_EPOLL_DEL])); +} + +int bench_epoll_ctl(int argc, const char **argv) +{ + int j, ret = 0; + struct sigaction act; + struct worker *worker = NULL; + struct perf_cpu_map *cpu; + struct rlimit rl, prevrl; + unsigned int i; + + argc = parse_options(argc, argv, options, bench_epoll_ctl_usage, 0); + if (argc) { + usage_with_options(bench_epoll_ctl_usage, options); + exit(EXIT_FAILURE); + } + + memset(&act, 0, sizeof(act)); + sigfillset(&act.sa_mask); + act.sa_sigaction = toggle_done; + sigaction(SIGINT, &act, NULL); + + cpu = perf_cpu_map__new(NULL); + if (!cpu) + goto errmem; + + /* a single, main epoll instance */ + epollfd = epoll_create(1); + if (epollfd < 0) + err(EXIT_FAILURE, "epoll_create"); + + /* + * Deal with nested epolls, if any. + */ + if (nested) + nest_epollfd(); + + /* default to the number of CPUs */ + if (!nthreads) + nthreads = perf_cpu_map__nr(cpu); + + worker = calloc(nthreads, sizeof(*worker)); + if (!worker) + goto errmem; + + if (getrlimit(RLIMIT_NOFILE, &prevrl)) + err(EXIT_FAILURE, "getrlimit"); + rl.rlim_cur = rl.rlim_max = nfds * nthreads * 2 + 50; + printinfo("Setting RLIMIT_NOFILE rlimit from %" PRIu64 " to: %" PRIu64 "\n", + (uint64_t)prevrl.rlim_max, (uint64_t)rl.rlim_max); + if (setrlimit(RLIMIT_NOFILE, &rl) < 0) + err(EXIT_FAILURE, "setrlimit"); + + printf("Run summary [PID %d]: %d threads doing epoll_ctl ops " + "%d file-descriptors for %d secs.\n\n", + getpid(), nthreads, nfds, nsecs); + + for (i = 0; i < EPOLL_NR_OPS; i++) + init_stats(&all_stats[i]); + + mutex_init(&thread_lock); + cond_init(&thread_parent); + cond_init(&thread_worker); + + threads_starting = nthreads; + + gettimeofday(&bench__start, NULL); + + do_threads(worker, cpu); + + mutex_lock(&thread_lock); + while (threads_starting) + cond_wait(&thread_parent, &thread_lock); + cond_broadcast(&thread_worker); + mutex_unlock(&thread_lock); + + sleep(nsecs); + toggle_done(0, NULL, NULL); + printinfo("main thread: toggling done\n"); + + for (i = 0; i < nthreads; i++) { + ret = pthread_join(worker[i].thread, NULL); + if (ret) + err(EXIT_FAILURE, "pthread_join"); + } + + /* cleanup & report results */ + cond_destroy(&thread_parent); + cond_destroy(&thread_worker); + mutex_destroy(&thread_lock); + + for (i = 0; i < nthreads; i++) { + unsigned long t[EPOLL_NR_OPS]; + + for (j = 0; j < EPOLL_NR_OPS; j++) { + t[j] = worker[i].ops[j]; + update_stats(&all_stats[j], t[j]); + } + + if (nfds == 1) + printf("[thread %2d] fdmap: %p [ add: %04ld; mod: %04ld; del: %04lds ops ]\n", + worker[i].tid, &worker[i].fdmap[0], + t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]); + else + printf("[thread %2d] fdmap: %p ... %p [ add: %04ld ops; mod: %04ld ops; del: %04ld ops ]\n", + worker[i].tid, &worker[i].fdmap[0], + &worker[i].fdmap[nfds-1], + t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]); + } + + print_summary(); + + close(epollfd); + return ret; +errmem: + err(EXIT_FAILURE, "calloc"); +} +#endif // HAVE_EVENTFD_SUPPORT -- cgit v1.2.3