From a9e3760b0838299649c0d57cca44daaf40ba3c33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 14 Sep 2026 22:12:34 -1000 Subject: sched_ext: Maintain an online cid mask in the scheduler arena Schedulers on the default cid mapping treat [0, nr_online_cids) as the online set and restart on hotplug. Schedulers that install their own mapping with scx_bpf_cid_override() have no way to learn which cids are online: the count no longer identifies members and the CPU-form cpumask is unusable from cid programs. This is an obvious hole in the cid API. Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's arena, allocated alongside the per-CPU scratch masks and populated after the cid mapping is finalized and before ops.init(), for child schedulers too. The pointer stays valid through ops.exit() with no reference to take. It is the arena offset as a void pointer, the same form struct_ops arena arguments arrive in. The verifier types the void return as a scalar for the program's arena cast. The mask follows the SCX hotplug notifications: seeded from cpu_active_mask and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask only inside a hotplug transition. Updates walk the scheduler list under the lock that also serializes unlinking. Reads are live, not atomic snapshots. Root initialization excludes hotplug. v2: Reworded the getter kerneldoc (Andrea Righi). Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- samples/bpf/sock_example.c | 111 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) create mode 100644 samples/bpf/sock_example.c (limited to 'samples/bpf/sock_example.c') diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c new file mode 100644 index 000000000..5b66f2401 --- /dev/null +++ b/samples/bpf/sock_example.c @@ -0,0 +1,111 @@ +/* eBPF example program: + * - creates arraymap in kernel with key 4 bytes and value 8 bytes + * + * - loads eBPF program: + * r0 = skb->data[ETH_HLEN + offsetof(struct iphdr, protocol)]; + * *(u32*)(fp - 4) = r0; + * // assuming packet is IPv4, lookup ip->proto in a map + * value = bpf_map_lookup_elem(map_fd, fp - 4); + * if (value) + * (*(u64*)value) += 1; + * + * - attaches this program to loopback interface "lo" raw socket + * + * - every second user space reads map[tcp], map[udp], map[icmp] to see + * how many packets of given protocol were seen on "lo" + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_insn.h" +#include "sock_example.h" +#include "bpf_util.h" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int test_sock(void) +{ + int sock = -1, map_fd, prog_fd, i, key; + long long value = 0, tcp_cnt, udp_cnt, icmp_cnt; + + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(key), sizeof(value), + 256, NULL); + if (map_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + goto cleanup; + } + + struct bpf_insn prog[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, ETH_HLEN + offsetof(struct iphdr, protocol) /* R0 = ip->proto */), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = ARRAY_SIZE(prog); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = bpf_log_buf, + .log_size = BPF_LOG_BUF_SIZE, + ); + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + prog, insns_cnt, &opts); + if (prog_fd < 0) { + printf("failed to load prog '%s'\n", strerror(errno)); + goto cleanup; + } + + sock = open_raw_sock("lo"); + + if (setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, + sizeof(prog_fd)) < 0) { + printf("setsockopt %s\n", strerror(errno)); + goto cleanup; + } + + for (i = 0; i < 10; i++) { + key = IPPROTO_TCP; + assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0); + + key = IPPROTO_UDP; + assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0); + + key = IPPROTO_ICMP; + assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0); + + printf("TCP %lld UDP %lld ICMP %lld packets\n", + tcp_cnt, udp_cnt, icmp_cnt); + sleep(1); + } + +cleanup: + /* maps, programs, raw sockets will auto cleanup on process exit */ + return 0; +} + +int main(void) +{ + FILE *f; + + f = popen("ping -4 -c5 localhost", "r"); + (void)f; + + return test_sock(); +} -- cgit v1.3.1