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(). ... --- kernel/bpf/ringbuf.c | 776 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 776 insertions(+) create mode 100644 kernel/bpf/ringbuf.c (limited to 'kernel/bpf/ringbuf.c') diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c new file mode 100644 index 000000000..80f4b4d88 --- /dev/null +++ b/kernel/bpf/ringbuf.c @@ -0,0 +1,776 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) + +/* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */ +#define RINGBUF_PGOFF \ + (offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT) +/* consumer page and producer page */ +#define RINGBUF_POS_PAGES 2 + +#define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4) + +/* Maximum size of ring buffer area is limited by 32-bit page offset within + * record header, counted in pages. Reserve 8 bits for extensibility, and take + * into account few extra pages for consumer/producer pages and + * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single + * ring buffer. + */ +#define RINGBUF_MAX_DATA_SZ \ + (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE) + +struct bpf_ringbuf { + wait_queue_head_t waitq; + struct irq_work work; + u64 mask; + struct page **pages; + int nr_pages; + spinlock_t spinlock ____cacheline_aligned_in_smp; + /* For user-space producer ring buffers, an atomic_t busy bit is used + * to synchronize access to the ring buffers in the kernel, rather than + * the spinlock that is used for kernel-producer ring buffers. This is + * done because the ring buffer must hold a lock across a BPF program's + * callback: + * + * __bpf_user_ringbuf_peek() // lock acquired + * -> program callback_fn() + * -> __bpf_user_ringbuf_sample_release() // lock released + * + * It is unsafe and incorrect to hold an IRQ spinlock across what could + * be a long execution window, so we instead simply disallow concurrent + * access to the ring buffer by kernel consumers, and return -EBUSY from + * __bpf_user_ringbuf_peek() if the busy bit is held by another task. + */ + atomic_t busy ____cacheline_aligned_in_smp; + /* Consumer and producer counters are put into separate pages to + * allow each position to be mapped with different permissions. + * This prevents a user-space application from modifying the + * position and ruining in-kernel tracking. The permissions of the + * pages depend on who is producing samples: user-space or the + * kernel. + * + * Kernel-producer + * --------------- + * The producer position and data pages are mapped as r/o in + * userspace. For this approach, bits in the header of samples are + * used to signal to user-space, and to other producers, whether a + * sample is currently being written. + * + * User-space producer + * ------------------- + * Only the page containing the consumer position is mapped r/o in + * user-space. User-space producers also use bits of the header to + * communicate to the kernel, but the kernel must carefully check and + * validate each sample to ensure that they're correctly formatted, and + * fully contained within the ring buffer. + */ + unsigned long consumer_pos __aligned(PAGE_SIZE); + unsigned long producer_pos __aligned(PAGE_SIZE); + char data[] __aligned(PAGE_SIZE); +}; + +struct bpf_ringbuf_map { + struct bpf_map map; + struct bpf_ringbuf *rb; +}; + +/* 8-byte ring buffer record header structure */ +struct bpf_ringbuf_hdr { + u32 len; + u32 pg_off; +}; + +static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) +{ + const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | + __GFP_NOWARN | __GFP_ZERO; + int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; + int nr_data_pages = data_sz >> PAGE_SHIFT; + int nr_pages = nr_meta_pages + nr_data_pages; + struct page **pages, *page; + struct bpf_ringbuf *rb; + size_t array_size; + int i; + + /* Each data page is mapped twice to allow "virtual" + * continuous read of samples wrapping around the end of ring + * buffer area: + * ------------------------------------------------------ + * | meta pages | real data pages | same data pages | + * ------------------------------------------------------ + * | | 1 2 3 4 5 6 7 8 9 | 1 2 3 4 5 6 7 8 9 | + * ------------------------------------------------------ + * | | TA DA | TA DA | + * ------------------------------------------------------ + * ^^^^^^^ + * | + * Here, no need to worry about special handling of wrapped-around + * data due to double-mapped data pages. This works both in kernel and + * when mmap()'ed in user-space, simplifying both kernel and + * user-space implementations significantly. + */ + array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); + pages = bpf_map_area_alloc(array_size, numa_node); + if (!pages) + return NULL; + + for (i = 0; i < nr_pages; i++) { + page = alloc_pages_node(numa_node, flags, 0); + if (!page) { + nr_pages = i; + goto err_free_pages; + } + pages[i] = page; + if (i >= nr_meta_pages) + pages[nr_data_pages + i] = page; + } + + rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, + VM_MAP | VM_USERMAP, PAGE_KERNEL); + if (rb) { + kmemleak_not_leak(pages); + rb->pages = pages; + rb->nr_pages = nr_pages; + return rb; + } + +err_free_pages: + for (i = 0; i < nr_pages; i++) + __free_page(pages[i]); + bpf_map_area_free(pages); + return NULL; +} + +static void bpf_ringbuf_notify(struct irq_work *work) +{ + struct bpf_ringbuf *rb = container_of(work, struct bpf_ringbuf, work); + + wake_up_all(&rb->waitq); +} + +static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) +{ + struct bpf_ringbuf *rb; + + rb = bpf_ringbuf_area_alloc(data_sz, numa_node); + if (!rb) + return NULL; + + spin_lock_init(&rb->spinlock); + atomic_set(&rb->busy, 0); + init_waitqueue_head(&rb->waitq); + init_irq_work(&rb->work, bpf_ringbuf_notify); + + rb->mask = data_sz - 1; + rb->consumer_pos = 0; + rb->producer_pos = 0; + + return rb; +} + +static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) +{ + struct bpf_ringbuf_map *rb_map; + + if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) + return ERR_PTR(-EINVAL); + + if (attr->key_size || attr->value_size || + !is_power_of_2(attr->max_entries) || + !PAGE_ALIGNED(attr->max_entries)) + return ERR_PTR(-EINVAL); + +#ifdef CONFIG_64BIT + /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ + if (attr->max_entries > RINGBUF_MAX_DATA_SZ) + return ERR_PTR(-E2BIG); +#endif + + rb_map = bpf_map_area_alloc(sizeof(*rb_map), NUMA_NO_NODE); + if (!rb_map) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&rb_map->map, attr); + + rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); + if (!rb_map->rb) { + bpf_map_area_free(rb_map); + return ERR_PTR(-ENOMEM); + } + + return &rb_map->map; +} + +static void bpf_ringbuf_free(struct bpf_ringbuf *rb) +{ + /* copy pages pointer and nr_pages to local variable, as we are going + * to unmap rb itself with vunmap() below + */ + struct page **pages = rb->pages; + int i, nr_pages = rb->nr_pages; + + vunmap(rb); + for (i = 0; i < nr_pages; i++) + __free_page(pages[i]); + bpf_map_area_free(pages); +} + +static void ringbuf_map_free(struct bpf_map *map) +{ + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + bpf_ringbuf_free(rb_map->rb); + bpf_map_area_free(rb_map); +} + +static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-ENOTSUPP); +} + +static int ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 flags) +{ + return -ENOTSUPP; +} + +static int ringbuf_map_delete_elem(struct bpf_map *map, void *key) +{ + return -ENOTSUPP; +} + +static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -ENOTSUPP; +} + +static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + + if (vma->vm_flags & VM_WRITE) { + /* allow writable mapping for the consumer_pos only */ + if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EPERM; + } else { + vma->vm_flags &= ~VM_MAYWRITE; + } + /* remap_vmalloc_range() checks size and offset constraints */ + return remap_vmalloc_range(vma, rb_map->rb, + vma->vm_pgoff + RINGBUF_PGOFF); +} + +static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + + if (vma->vm_flags & VM_WRITE) { + if (vma->vm_pgoff == 0) + /* Disallow writable mappings to the consumer pointer, + * and allow writable mappings to both the producer + * position, and the ring buffer data itself. + */ + return -EPERM; + } else { + vma->vm_flags &= ~VM_MAYWRITE; + } + /* remap_vmalloc_range() checks size and offset constraints */ + return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); +} + +static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) +{ + unsigned long cons_pos, prod_pos; + + cons_pos = smp_load_acquire(&rb->consumer_pos); + prod_pos = smp_load_acquire(&rb->producer_pos); + return prod_pos - cons_pos; +} + +static u32 ringbuf_total_data_sz(const struct bpf_ringbuf *rb) +{ + return rb->mask + 1; +} + +static __poll_t ringbuf_map_poll_kern(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts) +{ + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + poll_wait(filp, &rb_map->rb->waitq, pts); + + if (ringbuf_avail_data_sz(rb_map->rb)) + return EPOLLIN | EPOLLRDNORM; + return 0; +} + +static __poll_t ringbuf_map_poll_user(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts) +{ + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + poll_wait(filp, &rb_map->rb->waitq, pts); + + if (ringbuf_avail_data_sz(rb_map->rb) < ringbuf_total_data_sz(rb_map->rb)) + return EPOLLOUT | EPOLLWRNORM; + return 0; +} + +BTF_ID_LIST_SINGLE(ringbuf_map_btf_ids, struct, bpf_ringbuf_map) +const struct bpf_map_ops ringbuf_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = ringbuf_map_alloc, + .map_free = ringbuf_map_free, + .map_mmap = ringbuf_map_mmap_kern, + .map_poll = ringbuf_map_poll_kern, + .map_lookup_elem = ringbuf_map_lookup_elem, + .map_update_elem = ringbuf_map_update_elem, + .map_delete_elem = ringbuf_map_delete_elem, + .map_get_next_key = ringbuf_map_get_next_key, + .map_btf_id = &ringbuf_map_btf_ids[0], +}; + +BTF_ID_LIST_SINGLE(user_ringbuf_map_btf_ids, struct, bpf_ringbuf_map) +const struct bpf_map_ops user_ringbuf_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = ringbuf_map_alloc, + .map_free = ringbuf_map_free, + .map_mmap = ringbuf_map_mmap_user, + .map_poll = ringbuf_map_poll_user, + .map_lookup_elem = ringbuf_map_lookup_elem, + .map_update_elem = ringbuf_map_update_elem, + .map_delete_elem = ringbuf_map_delete_elem, + .map_get_next_key = ringbuf_map_get_next_key, + .map_btf_id = &user_ringbuf_map_btf_ids[0], +}; + +/* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself, + * calculate offset from record metadata to ring buffer in pages, rounded + * down. This page offset is stored as part of record metadata and allows to + * restore struct bpf_ringbuf * from record pointer. This page offset is + * stored at offset 4 of record metadata header. + */ +static size_t bpf_ringbuf_rec_pg_off(struct bpf_ringbuf *rb, + struct bpf_ringbuf_hdr *hdr) +{ + return ((void *)hdr - (void *)rb) >> PAGE_SHIFT; +} + +/* Given pointer to ring buffer record header, restore pointer to struct + * bpf_ringbuf itself by using page offset stored at offset 4 + */ +static struct bpf_ringbuf * +bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) +{ + unsigned long addr = (unsigned long)(void *)hdr; + unsigned long off = (unsigned long)hdr->pg_off << PAGE_SHIFT; + + return (void*)((addr & PAGE_MASK) - off); +} + +static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) +{ + unsigned long cons_pos, prod_pos, new_prod_pos, flags; + u32 len, pg_off; + struct bpf_ringbuf_hdr *hdr; + + if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) + return NULL; + + len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + if (len > ringbuf_total_data_sz(rb)) + return NULL; + + cons_pos = smp_load_acquire(&rb->consumer_pos); + + if (in_nmi()) { + if (!spin_trylock_irqsave(&rb->spinlock, flags)) + return NULL; + } else { + spin_lock_irqsave(&rb->spinlock, flags); + } + + prod_pos = rb->producer_pos; + new_prod_pos = prod_pos + len; + + /* check for out of ringbuf space by ensuring producer position + * doesn't advance more than (ringbuf_size - 1) ahead + */ + if (new_prod_pos - cons_pos > rb->mask) { + spin_unlock_irqrestore(&rb->spinlock, flags); + return NULL; + } + + hdr = (void *)rb->data + (prod_pos & rb->mask); + pg_off = bpf_ringbuf_rec_pg_off(rb, hdr); + hdr->len = size | BPF_RINGBUF_BUSY_BIT; + hdr->pg_off = pg_off; + + /* pairs with consumer's smp_load_acquire() */ + smp_store_release(&rb->producer_pos, new_prod_pos); + + spin_unlock_irqrestore(&rb->spinlock, flags); + + return (void *)hdr + BPF_RINGBUF_HDR_SZ; +} + +BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags) +{ + struct bpf_ringbuf_map *rb_map; + + if (unlikely(flags)) + return 0; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + return (unsigned long)__bpf_ringbuf_reserve(rb_map->rb, size); +} + +const struct bpf_func_proto bpf_ringbuf_reserve_proto = { + .func = bpf_ringbuf_reserve, + .ret_type = RET_PTR_TO_RINGBUF_MEM_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) +{ + unsigned long rec_pos, cons_pos; + struct bpf_ringbuf_hdr *hdr; + struct bpf_ringbuf *rb; + u32 new_len; + + hdr = sample - BPF_RINGBUF_HDR_SZ; + rb = bpf_ringbuf_restore_from_rec(hdr); + new_len = hdr->len ^ BPF_RINGBUF_BUSY_BIT; + if (discard) + new_len |= BPF_RINGBUF_DISCARD_BIT; + + /* update record header with correct final size prefix */ + xchg(&hdr->len, new_len); + + /* if consumer caught up and is waiting for our record, notify about + * new data availability + */ + rec_pos = (void *)hdr - (void *)rb->data; + cons_pos = smp_load_acquire(&rb->consumer_pos) & rb->mask; + + if (flags & BPF_RB_FORCE_WAKEUP) + irq_work_queue(&rb->work); + else if (cons_pos == rec_pos && !(flags & BPF_RB_NO_WAKEUP)) + irq_work_queue(&rb->work); +} + +BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) +{ + bpf_ringbuf_commit(sample, flags, false /* discard */); + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_submit_proto = { + .func = bpf_ringbuf_submit, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) +{ + bpf_ringbuf_commit(sample, flags, true /* discard */); + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_discard_proto = { + .func = bpf_ringbuf_discard, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_ringbuf_output, struct bpf_map *, map, void *, data, u64, size, + u64, flags) +{ + struct bpf_ringbuf_map *rb_map; + void *rec; + + if (unlikely(flags & ~(BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP))) + return -EINVAL; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + rec = __bpf_ringbuf_reserve(rb_map->rb, size); + if (!rec) + return -EAGAIN; + + memcpy(rec, data, size); + bpf_ringbuf_commit(rec, flags, false /* discard */); + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_output_proto = { + .func = bpf_ringbuf_output, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) +{ + struct bpf_ringbuf *rb; + + rb = container_of(map, struct bpf_ringbuf_map, map)->rb; + + switch (flags) { + case BPF_RB_AVAIL_DATA: + return ringbuf_avail_data_sz(rb); + case BPF_RB_RING_SIZE: + return ringbuf_total_data_sz(rb); + case BPF_RB_CONS_POS: + return smp_load_acquire(&rb->consumer_pos); + case BPF_RB_PROD_POS: + return smp_load_acquire(&rb->producer_pos); + default: + return 0; + } +} + +const struct bpf_func_proto bpf_ringbuf_query_proto = { + .func = bpf_ringbuf_query, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags, + struct bpf_dynptr_kern *, ptr) +{ + struct bpf_ringbuf_map *rb_map; + void *sample; + int err; + + if (unlikely(flags)) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + err = bpf_dynptr_check_size(size); + if (err) { + bpf_dynptr_set_null(ptr); + return err; + } + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + + sample = __bpf_ringbuf_reserve(rb_map->rb, size); + if (!sample) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { + .func = bpf_ringbuf_reserve_dynptr, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, +}; + +BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, false /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = { + .func = bpf_ringbuf_submit_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, true /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = { + .func = bpf_ringbuf_discard_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +static int __bpf_user_ringbuf_peek(struct bpf_ringbuf *rb, void **sample, u32 *size) +{ + int err; + u32 hdr_len, sample_len, total_len, flags, *hdr; + u64 cons_pos, prod_pos; + + /* Synchronizes with smp_store_release() in user-space producer. */ + prod_pos = smp_load_acquire(&rb->producer_pos); + if (prod_pos % 8) + return -EINVAL; + + /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_sample_release() */ + cons_pos = smp_load_acquire(&rb->consumer_pos); + if (cons_pos >= prod_pos) + return -ENODATA; + + hdr = (u32 *)((uintptr_t)rb->data + (uintptr_t)(cons_pos & rb->mask)); + /* Synchronizes with smp_store_release() in user-space producer. */ + hdr_len = smp_load_acquire(hdr); + flags = hdr_len & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT); + sample_len = hdr_len & ~flags; + total_len = round_up(sample_len + BPF_RINGBUF_HDR_SZ, 8); + + /* The sample must fit within the region advertised by the producer position. */ + if (total_len > prod_pos - cons_pos) + return -EINVAL; + + /* The sample must fit within the data region of the ring buffer. */ + if (total_len > ringbuf_total_data_sz(rb)) + return -E2BIG; + + /* The sample must fit into a struct bpf_dynptr. */ + err = bpf_dynptr_check_size(sample_len); + if (err) + return -E2BIG; + + if (flags & BPF_RINGBUF_DISCARD_BIT) { + /* If the discard bit is set, the sample should be skipped. + * + * Update the consumer pos, and return -EAGAIN so the caller + * knows to skip this sample and try to read the next one. + */ + smp_store_release(&rb->consumer_pos, cons_pos + total_len); + return -EAGAIN; + } + + if (flags & BPF_RINGBUF_BUSY_BIT) + return -ENODATA; + + *sample = (void *)((uintptr_t)rb->data + + (uintptr_t)((cons_pos + BPF_RINGBUF_HDR_SZ) & rb->mask)); + *size = sample_len; + return 0; +} + +static void __bpf_user_ringbuf_sample_release(struct bpf_ringbuf *rb, size_t size, u64 flags) +{ + u64 consumer_pos; + u32 rounded_size = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + + /* Using smp_load_acquire() is unnecessary here, as the busy-bit + * prevents another task from writing to consumer_pos after it was read + * by this task with smp_load_acquire() in __bpf_user_ringbuf_peek(). + */ + consumer_pos = rb->consumer_pos; + /* Synchronizes with smp_load_acquire() in user-space producer. */ + smp_store_release(&rb->consumer_pos, consumer_pos + rounded_size); +} + +BPF_CALL_4(bpf_user_ringbuf_drain, struct bpf_map *, map, + void *, callback_fn, void *, callback_ctx, u64, flags) +{ + struct bpf_ringbuf *rb; + long samples, discarded_samples = 0, ret = 0; + bpf_callback_t callback = (bpf_callback_t)callback_fn; + u64 wakeup_flags = BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP; + int busy = 0; + + if (unlikely(flags & ~wakeup_flags)) + return -EINVAL; + + rb = container_of(map, struct bpf_ringbuf_map, map)->rb; + + /* If another consumer is already consuming a sample, wait for them to finish. */ + if (!atomic_try_cmpxchg(&rb->busy, &busy, 1)) + return -EBUSY; + + for (samples = 0; samples < BPF_MAX_USER_RINGBUF_SAMPLES && ret == 0; samples++) { + int err; + u32 size; + void *sample; + struct bpf_dynptr_kern dynptr; + + err = __bpf_user_ringbuf_peek(rb, &sample, &size); + if (err) { + if (err == -ENODATA) { + break; + } else if (err == -EAGAIN) { + discarded_samples++; + continue; + } else { + ret = err; + goto schedule_work_return; + } + } + + bpf_dynptr_init(&dynptr, sample, BPF_DYNPTR_TYPE_LOCAL, 0, size); + ret = callback((uintptr_t)&dynptr, (uintptr_t)callback_ctx, 0, 0, 0); + __bpf_user_ringbuf_sample_release(rb, size, flags); + } + ret = samples - discarded_samples; + +schedule_work_return: + /* Prevent the clearing of the busy-bit from being reordered before the + * storing of any rb consumer or producer positions. + */ + smp_mb__before_atomic(); + atomic_set(&rb->busy, 0); + + if (flags & BPF_RB_FORCE_WAKEUP) + irq_work_queue(&rb->work); + else if (!(flags & BPF_RB_NO_WAKEUP) && samples > 0) + irq_work_queue(&rb->work); + return ret; +} + +const struct bpf_func_proto bpf_user_ringbuf_drain_proto = { + .func = bpf_user_ringbuf_drain, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_FUNC, + .arg3_type = ARG_PTR_TO_STACK_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; -- cgit v1.2.3