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/lib/bpf/ringbuf.c | 587 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 587 insertions(+) create mode 100644 tools/lib/bpf/ringbuf.c (limited to 'tools/lib/bpf/ringbuf.c') diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c new file mode 100644 index 000000000..02199364d --- /dev/null +++ b/tools/lib/bpf/ringbuf.c @@ -0,0 +1,587 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* + * Ring buffer operations. + * + * Copyright (C) 2020 Facebook, Inc. + */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "libbpf.h" +#include "libbpf_internal.h" +#include "bpf.h" + +struct ring { + ring_buffer_sample_fn sample_cb; + void *ctx; + void *data; + unsigned long *consumer_pos; + unsigned long *producer_pos; + unsigned long mask; + int map_fd; +}; + +struct ring_buffer { + struct epoll_event *events; + struct ring *rings; + size_t page_size; + int epoll_fd; + int ring_cnt; +}; + +struct user_ring_buffer { + struct epoll_event event; + unsigned long *consumer_pos; + unsigned long *producer_pos; + void *data; + unsigned long mask; + size_t page_size; + int map_fd; + int epoll_fd; +}; + +/* 8-byte ring buffer header structure */ +struct ringbuf_hdr { + __u32 len; + __u32 pad; +}; + +static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r) +{ + if (r->consumer_pos) { + munmap(r->consumer_pos, rb->page_size); + r->consumer_pos = NULL; + } + if (r->producer_pos) { + munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1)); + r->producer_pos = NULL; + } +} + +/* Add extra RINGBUF maps to this ring buffer manager */ +int ring_buffer__add(struct ring_buffer *rb, int map_fd, + ring_buffer_sample_fn sample_cb, void *ctx) +{ + struct bpf_map_info info; + __u32 len = sizeof(info); + struct epoll_event *e; + struct ring *r; + __u64 mmap_sz; + void *tmp; + int err; + + memset(&info, 0, sizeof(info)); + + err = bpf_map_get_info_by_fd(map_fd, &info, &len); + if (err) { + err = -errno; + pr_warn("ringbuf: failed to get map info for fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + + if (info.type != BPF_MAP_TYPE_RINGBUF) { + pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n", + map_fd); + return libbpf_err(-EINVAL); + } + + tmp = libbpf_reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings)); + if (!tmp) + return libbpf_err(-ENOMEM); + rb->rings = tmp; + + tmp = libbpf_reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events)); + if (!tmp) + return libbpf_err(-ENOMEM); + rb->events = tmp; + + r = &rb->rings[rb->ring_cnt]; + memset(r, 0, sizeof(*r)); + + r->map_fd = map_fd; + r->sample_cb = sample_cb; + r->ctx = ctx; + r->mask = info.max_entries - 1; + + /* Map writable consumer page */ + tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + r->consumer_pos = tmp; + + /* Map read-only producer page and data pages. We map twice as big + * data size to allow simple reading of samples that wrap around the + * end of a ring buffer. See kernel implementation for details. + */ + mmap_sz = rb->page_size + 2 * (__u64)info.max_entries; + if (mmap_sz != (__u64)(size_t)mmap_sz) { + pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries); + return libbpf_err(-E2BIG); + } + tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size); + if (tmp == MAP_FAILED) { + err = -errno; + ringbuf_unmap_ring(rb, r); + pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + r->producer_pos = tmp; + r->data = tmp + rb->page_size; + + e = &rb->events[rb->ring_cnt]; + memset(e, 0, sizeof(*e)); + + e->events = EPOLLIN; + e->data.fd = rb->ring_cnt; + if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) { + err = -errno; + ringbuf_unmap_ring(rb, r); + pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n", + map_fd, err); + return libbpf_err(err); + } + + rb->ring_cnt++; + return 0; +} + +void ring_buffer__free(struct ring_buffer *rb) +{ + int i; + + if (!rb) + return; + + for (i = 0; i < rb->ring_cnt; ++i) + ringbuf_unmap_ring(rb, &rb->rings[i]); + if (rb->epoll_fd >= 0) + close(rb->epoll_fd); + + free(rb->events); + free(rb->rings); + free(rb); +} + +struct ring_buffer * +ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, + const struct ring_buffer_opts *opts) +{ + struct ring_buffer *rb; + int err; + + if (!OPTS_VALID(opts, ring_buffer_opts)) + return errno = EINVAL, NULL; + + rb = calloc(1, sizeof(*rb)); + if (!rb) + return errno = ENOMEM, NULL; + + rb->page_size = getpagesize(); + + rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (rb->epoll_fd < 0) { + err = -errno; + pr_warn("ringbuf: failed to create epoll instance: %d\n", err); + goto err_out; + } + + err = ring_buffer__add(rb, map_fd, sample_cb, ctx); + if (err) + goto err_out; + + return rb; + +err_out: + ring_buffer__free(rb); + return errno = -err, NULL; +} + +static inline int roundup_len(__u32 len) +{ + /* clear out top 2 bits (discard and busy, if set) */ + len <<= 2; + len >>= 2; + /* add length prefix */ + len += BPF_RINGBUF_HDR_SZ; + /* round up to 8 byte alignment */ + return (len + 7) / 8 * 8; +} + +static int64_t ringbuf_process_ring(struct ring *r) +{ + int *len_ptr, len, err; + /* 64-bit to avoid overflow in case of extreme application behavior */ + int64_t cnt = 0; + unsigned long cons_pos, prod_pos; + bool got_new_data; + void *sample; + + cons_pos = smp_load_acquire(r->consumer_pos); + do { + got_new_data = false; + prod_pos = smp_load_acquire(r->producer_pos); + while (cons_pos < prod_pos) { + len_ptr = r->data + (cons_pos & r->mask); + len = smp_load_acquire(len_ptr); + + /* sample not committed yet, bail out for now */ + if (len & BPF_RINGBUF_BUSY_BIT) + goto done; + + got_new_data = true; + cons_pos += roundup_len(len); + + if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) { + sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ; + err = r->sample_cb(r->ctx, sample, len); + if (err < 0) { + /* update consumer pos and bail out */ + smp_store_release(r->consumer_pos, + cons_pos); + return err; + } + cnt++; + } + + smp_store_release(r->consumer_pos, cons_pos); + } + } while (got_new_data); +done: + return cnt; +} + +/* Consume available ring buffer(s) data without event polling. + * Returns number of records consumed across all registered ring buffers (or + * INT_MAX, whichever is less), or negative number if any of the callbacks + * return error. + */ +int ring_buffer__consume(struct ring_buffer *rb) +{ + int64_t err, res = 0; + int i; + + for (i = 0; i < rb->ring_cnt; i++) { + struct ring *ring = &rb->rings[i]; + + err = ringbuf_process_ring(ring); + if (err < 0) + return libbpf_err(err); + res += err; + } + if (res > INT_MAX) + return INT_MAX; + return res; +} + +/* Poll for available data and consume records, if any are available. + * Returns number of records consumed (or INT_MAX, whichever is less), or + * negative number, if any of the registered callbacks returned error. + */ +int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) +{ + int i, cnt; + int64_t err, res = 0; + + cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms); + if (cnt < 0) + return libbpf_err(-errno); + + for (i = 0; i < cnt; i++) { + __u32 ring_id = rb->events[i].data.fd; + struct ring *ring = &rb->rings[ring_id]; + + err = ringbuf_process_ring(ring); + if (err < 0) + return libbpf_err(err); + res += err; + } + if (res > INT_MAX) + return INT_MAX; + return res; +} + +/* Get an fd that can be used to sleep until data is available in the ring(s) */ +int ring_buffer__epoll_fd(const struct ring_buffer *rb) +{ + return rb->epoll_fd; +} + +static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb) +{ + if (rb->consumer_pos) { + munmap(rb->consumer_pos, rb->page_size); + rb->consumer_pos = NULL; + } + if (rb->producer_pos) { + munmap(rb->producer_pos, rb->page_size + 2 * (rb->mask + 1)); + rb->producer_pos = NULL; + } +} + +void user_ring_buffer__free(struct user_ring_buffer *rb) +{ + if (!rb) + return; + + user_ringbuf_unmap_ring(rb); + + if (rb->epoll_fd >= 0) + close(rb->epoll_fd); + + free(rb); +} + +static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) +{ + struct bpf_map_info info; + __u32 len = sizeof(info); + __u64 mmap_sz; + void *tmp; + struct epoll_event *rb_epoll; + int err; + + memset(&info, 0, sizeof(info)); + + err = bpf_map_get_info_by_fd(map_fd, &info, &len); + if (err) { + err = -errno; + pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); + return err; + } + + if (info.type != BPF_MAP_TYPE_USER_RINGBUF) { + pr_warn("user ringbuf: map fd=%d is not BPF_MAP_TYPE_USER_RINGBUF\n", map_fd); + return -EINVAL; + } + + rb->map_fd = map_fd; + rb->mask = info.max_entries - 1; + + /* Map read-only consumer page */ + tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n", + map_fd, err); + return err; + } + rb->consumer_pos = tmp; + + /* Map read-write the producer page and data pages. We map the data + * region as twice the total size of the ring buffer to allow the + * simple reading and writing of samples that wrap around the end of + * the buffer. See the kernel implementation for details. + */ + mmap_sz = rb->page_size + 2 * (__u64)info.max_entries; + if (mmap_sz != (__u64)(size_t)mmap_sz) { + pr_warn("user ringbuf: ring buf size (%u) is too big\n", info.max_entries); + return -E2BIG; + } + tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED, + map_fd, rb->page_size); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n", + map_fd, err); + return err; + } + + rb->producer_pos = tmp; + rb->data = tmp + rb->page_size; + + rb_epoll = &rb->event; + rb_epoll->events = EPOLLOUT; + if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) { + err = -errno; + pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err); + return err; + } + + return 0; +} + +struct user_ring_buffer * +user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts) +{ + struct user_ring_buffer *rb; + int err; + + if (!OPTS_VALID(opts, user_ring_buffer_opts)) + return errno = EINVAL, NULL; + + rb = calloc(1, sizeof(*rb)); + if (!rb) + return errno = ENOMEM, NULL; + + rb->page_size = getpagesize(); + + rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (rb->epoll_fd < 0) { + err = -errno; + pr_warn("user ringbuf: failed to create epoll instance: %d\n", err); + goto err_out; + } + + err = user_ringbuf_map(rb, map_fd); + if (err) + goto err_out; + + return rb; + +err_out: + user_ring_buffer__free(rb); + return errno = -err, NULL; +} + +static void user_ringbuf_commit(struct user_ring_buffer *rb, void *sample, bool discard) +{ + __u32 new_len; + struct ringbuf_hdr *hdr; + uintptr_t hdr_offset; + + hdr_offset = rb->mask + 1 + (sample - rb->data) - BPF_RINGBUF_HDR_SZ; + hdr = rb->data + (hdr_offset & rb->mask); + + new_len = hdr->len & ~BPF_RINGBUF_BUSY_BIT; + if (discard) + new_len |= BPF_RINGBUF_DISCARD_BIT; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + __atomic_exchange_n(&hdr->len, new_len, __ATOMIC_ACQ_REL); +} + +void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, true); +} + +void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, false); +} + +void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size) +{ + __u32 avail_size, total_size, max_size; + /* 64-bit to avoid overflow in case of extreme application behavior */ + __u64 cons_pos, prod_pos; + struct ringbuf_hdr *hdr; + + /* The top two bits are used as special flags */ + if (size & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT)) + return errno = E2BIG, NULL; + + /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + cons_pos = smp_load_acquire(rb->consumer_pos); + /* Synchronizes with smp_store_release() in user_ringbuf_commit() */ + prod_pos = smp_load_acquire(rb->producer_pos); + + max_size = rb->mask + 1; + avail_size = max_size - (prod_pos - cons_pos); + /* Round up total size to a multiple of 8. */ + total_size = (size + BPF_RINGBUF_HDR_SZ + 7) / 8 * 8; + + if (total_size > max_size) + return errno = E2BIG, NULL; + + if (avail_size < total_size) + return errno = ENOSPC, NULL; + + hdr = rb->data + (prod_pos & rb->mask); + hdr->len = size | BPF_RINGBUF_BUSY_BIT; + hdr->pad = 0; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + smp_store_release(rb->producer_pos, prod_pos + total_size); + + return (void *)rb->data + ((prod_pos + BPF_RINGBUF_HDR_SZ) & rb->mask); +} + +static __u64 ns_elapsed_timespec(const struct timespec *start, const struct timespec *end) +{ + __u64 start_ns, end_ns, ns_per_s = 1000000000; + + start_ns = (__u64)start->tv_sec * ns_per_s + start->tv_nsec; + end_ns = (__u64)end->tv_sec * ns_per_s + end->tv_nsec; + + return end_ns - start_ns; +} + +void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms) +{ + void *sample; + int err, ms_remaining = timeout_ms; + struct timespec start; + + if (timeout_ms < 0 && timeout_ms != -1) + return errno = EINVAL, NULL; + + if (timeout_ms != -1) { + err = clock_gettime(CLOCK_MONOTONIC, &start); + if (err) + return NULL; + } + + do { + int cnt, ms_elapsed; + struct timespec curr; + __u64 ns_per_ms = 1000000; + + sample = user_ring_buffer__reserve(rb, size); + if (sample) + return sample; + else if (errno != ENOSPC) + return NULL; + + /* The kernel guarantees at least one event notification + * delivery whenever at least one sample is drained from the + * ring buffer in an invocation to bpf_ringbuf_drain(). Other + * additional events may be delivered at any time, but only one + * event is guaranteed per bpf_ringbuf_drain() invocation, + * provided that a sample is drained, and the BPF program did + * not pass BPF_RB_NO_WAKEUP to bpf_ringbuf_drain(). If + * BPF_RB_FORCE_WAKEUP is passed to bpf_ringbuf_drain(), a + * wakeup event will be delivered even if no samples are + * drained. + */ + cnt = epoll_wait(rb->epoll_fd, &rb->event, 1, ms_remaining); + if (cnt < 0) + return NULL; + + if (timeout_ms == -1) + continue; + + err = clock_gettime(CLOCK_MONOTONIC, &curr); + if (err) + return NULL; + + ms_elapsed = ns_elapsed_timespec(&start, &curr) / ns_per_ms; + ms_remaining = timeout_ms - ms_elapsed; + } while (ms_remaining > 0); + + /* Try one more time to reserve a sample after the specified timeout has elapsed. */ + return user_ring_buffer__reserve(rb, size); +} -- cgit v1.2.3