aboutsummaryrefslogtreecommitdiff
path: root/samples/bpf/fds_example.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /samples/bpf/fds_example.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
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(). ...
Diffstat (limited to 'samples/bpf/fds_example.c')
-rw-r--r--samples/bpf/fds_example.c195
1 files changed, 195 insertions, 0 deletions
diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c
new file mode 100644
index 000000000..88a26f3ce
--- /dev/null
+++ b/samples/bpf/fds_example.c
@@ -0,0 +1,195 @@
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <string.h>
+#include <assert.h>
+#include <errno.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf.h>
+
+#include <bpf/libbpf.h>
+#include "bpf_insn.h"
+#include "sock_example.h"
+#include "bpf_util.h"
+
+#define BPF_F_PIN (1 << 0)
+#define BPF_F_GET (1 << 1)
+#define BPF_F_PIN_GET (BPF_F_PIN | BPF_F_GET)
+
+#define BPF_F_KEY (1 << 2)
+#define BPF_F_VAL (1 << 3)
+#define BPF_F_KEY_VAL (BPF_F_KEY | BPF_F_VAL)
+
+#define BPF_M_UNSPEC 0
+#define BPF_M_MAP 1
+#define BPF_M_PROG 2
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static void usage(void)
+{
+ printf("Usage: fds_example [...]\n");
+ printf(" -F <file> File to pin/get object\n");
+ printf(" -P |- pin object\n");
+ printf(" -G `- get object\n");
+ printf(" -m eBPF map mode\n");
+ printf(" -k <key> |- map key\n");
+ printf(" -v <value> `- map value\n");
+ printf(" -p eBPF prog mode\n");
+ printf(" -o <object> `- object file\n");
+ printf(" -h Display this help.\n");
+}
+
+static int bpf_prog_create(const char *object)
+{
+ static struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ };
+ size_t insns_cnt = ARRAY_SIZE(insns);
+ struct bpf_object *obj;
+ int err;
+
+ if (object) {
+ obj = bpf_object__open_file(object, NULL);
+ assert(!libbpf_get_error(obj));
+ err = bpf_object__load(obj);
+ assert(!err);
+ return bpf_program__fd(bpf_object__next_program(obj, NULL));
+ } else {
+ LIBBPF_OPTS(bpf_prog_load_opts, opts,
+ .log_buf = bpf_log_buf,
+ .log_size = BPF_LOG_BUF_SIZE,
+ );
+
+ return bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL",
+ insns, insns_cnt, &opts);
+ }
+}
+
+static int bpf_do_map(const char *file, uint32_t flags, uint32_t key,
+ uint32_t value)
+{
+ int fd, ret;
+
+ if (flags & BPF_F_PIN) {
+ fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(uint32_t),
+ sizeof(uint32_t), 1024, NULL);
+ printf("bpf: map fd:%d (%s)\n", fd, strerror(errno));
+ assert(fd > 0);
+
+ ret = bpf_obj_pin(fd, file);
+ printf("bpf: pin ret:(%d,%s)\n", ret, strerror(errno));
+ assert(ret == 0);
+ } else {
+ fd = bpf_obj_get(file);
+ printf("bpf: get fd:%d (%s)\n", fd, strerror(errno));
+ assert(fd > 0);
+ }
+
+ if ((flags & BPF_F_KEY_VAL) == BPF_F_KEY_VAL) {
+ ret = bpf_map_update_elem(fd, &key, &value, 0);
+ printf("bpf: fd:%d u->(%u:%u) ret:(%d,%s)\n", fd, key, value,
+ ret, strerror(errno));
+ assert(ret == 0);
+ } else if (flags & BPF_F_KEY) {
+ ret = bpf_map_lookup_elem(fd, &key, &value);
+ printf("bpf: fd:%d l->(%u):%u ret:(%d,%s)\n", fd, key, value,
+ ret, strerror(errno));
+ assert(ret == 0);
+ }
+
+ return 0;
+}
+
+static int bpf_do_prog(const char *file, uint32_t flags, const char *object)
+{
+ int fd, sock, ret;
+
+ if (flags & BPF_F_PIN) {
+ fd = bpf_prog_create(object);
+ printf("bpf: prog fd:%d (%s)\n", fd, strerror(errno));
+ assert(fd > 0);
+
+ ret = bpf_obj_pin(fd, file);
+ printf("bpf: pin ret:(%d,%s)\n", ret, strerror(errno));
+ assert(ret == 0);
+ } else {
+ fd = bpf_obj_get(file);
+ printf("bpf: get fd:%d (%s)\n", fd, strerror(errno));
+ assert(fd > 0);
+ }
+
+ sock = open_raw_sock("lo");
+ assert(sock > 0);
+
+ ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &fd, sizeof(fd));
+ printf("bpf: sock:%d <- fd:%d attached ret:(%d,%s)\n", sock, fd,
+ ret, strerror(errno));
+ assert(ret == 0);
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ const char *file = NULL, *object = NULL;
+ uint32_t key = 0, value = 0, flags = 0;
+ int opt, mode = BPF_M_UNSPEC;
+
+ while ((opt = getopt(argc, argv, "F:PGmk:v:po:")) != -1) {
+ switch (opt) {
+ /* General args */
+ case 'F':
+ file = optarg;
+ break;
+ case 'P':
+ flags |= BPF_F_PIN;
+ break;
+ case 'G':
+ flags |= BPF_F_GET;
+ break;
+ /* Map-related args */
+ case 'm':
+ mode = BPF_M_MAP;
+ break;
+ case 'k':
+ key = strtoul(optarg, NULL, 0);
+ flags |= BPF_F_KEY;
+ break;
+ case 'v':
+ value = strtoul(optarg, NULL, 0);
+ flags |= BPF_F_VAL;
+ break;
+ /* Prog-related args */
+ case 'p':
+ mode = BPF_M_PROG;
+ break;
+ case 'o':
+ object = optarg;
+ break;
+ default:
+ goto out;
+ }
+ }
+
+ if (!(flags & BPF_F_PIN_GET) || !file)
+ goto out;
+
+ switch (mode) {
+ case BPF_M_MAP:
+ return bpf_do_map(file, flags, key, value);
+ case BPF_M_PROG:
+ return bpf_do_prog(file, flags, object);
+ }
+out:
+ usage();
+ return -1;
+}