diff options
Diffstat (limited to 'tools/testing/selftests/bpf/progs')
18 files changed, 937 insertions, 32 deletions
diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c index 474c6a62078a..a487f60b73ac 100644 --- a/tools/testing/selftests/bpf/progs/bind4_prog.c +++ b/tools/testing/selftests/bpf/progs/bind4_prog.c @@ -6,8 +6,6 @@ #include <linux/bpf.h> #include <linux/in.h> #include <linux/in6.h> -#include <sys/socket.h> -#include <netinet/tcp.h> #include <linux/if.h> #include <errno.h> diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c index c19cfa869f30..d62cd9e9cf0e 100644 --- a/tools/testing/selftests/bpf/progs/bind6_prog.c +++ b/tools/testing/selftests/bpf/progs/bind6_prog.c @@ -6,8 +6,6 @@ #include <linux/bpf.h> #include <linux/in.h> #include <linux/in6.h> -#include <sys/socket.h> -#include <netinet/tcp.h> #include <linux/if.h> #include <errno.h> diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index f266c757b3df..a20c5ed5e454 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -22,6 +22,8 @@ #define PROG(F) PROG_(F, _##F) #define PROG_(NUM, NAME) SEC("flow_dissector") int flow_dissector_##NUM +#define FLOW_CONTINUE_SADDR 0x7f00007f /* 127.0.0.127 */ + /* These are the identifiers of the BPF programs that will be used in tail * calls. Name is limited to 16 characters, with the terminating character and * bpf_func_ above, we have only 6 to work with, anything after will be cropped. @@ -143,6 +145,19 @@ int _dissect(struct __sk_buff *skb) { struct bpf_flow_keys *keys = skb->flow_keys; + if (keys->n_proto == bpf_htons(ETH_P_IP)) { + /* IP traffic from FLOW_CONTINUE_SADDR falls-back to + * standard dissector + */ + struct iphdr *iph, _iph; + + iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph); + if (iph && iph->ihl == 5 && + iph->saddr == bpf_htonl(FLOW_CONTINUE_SADDR)) { + return BPF_FLOW_DISSECTOR_CONTINUE; + } + } + return parse_eth_proto(skb, keys->n_proto); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h index e9846606690d..c41ee80533ca 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter.h +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -17,6 +17,7 @@ #define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used #define bpf_iter__sockmap bpf_iter__sockmap___not_used #define bpf_iter__bpf_link bpf_iter__bpf_link___not_used +#define bpf_iter__cgroup bpf_iter__cgroup___not_used #define btf_ptr btf_ptr___not_used #define BTF_F_COMPACT BTF_F_COMPACT___not_used #define BTF_F_NONAME BTF_F_NONAME___not_used @@ -40,6 +41,7 @@ #undef bpf_iter__bpf_sk_storage_map #undef bpf_iter__sockmap #undef bpf_iter__bpf_link +#undef bpf_iter__cgroup #undef btf_ptr #undef BTF_F_COMPACT #undef BTF_F_NONAME @@ -141,6 +143,11 @@ struct bpf_iter__bpf_link { struct bpf_link *link; }; +struct bpf_iter__cgroup { + struct bpf_iter_meta *meta; + struct cgroup *cgroup; +} __attribute__((preserve_access_index)); + struct btf_ptr { void *ptr; __u32 type_id; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 98dd2c4815f0..adb087aecc9e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -6,13 +6,41 @@ #define AF_INET6 10 #define SOL_SOCKET 1 +#define SO_REUSEADDR 2 #define SO_SNDBUF 7 -#define __SO_ACCEPTCON (1 << 16) +#define SO_RCVBUF 8 +#define SO_KEEPALIVE 9 #define SO_PRIORITY 12 +#define SO_REUSEPORT 15 +#define SO_RCVLOWAT 18 +#define SO_BINDTODEVICE 25 +#define SO_MARK 36 +#define SO_MAX_PACING_RATE 47 +#define SO_BINDTOIFINDEX 62 +#define SO_TXREHASH 74 +#define __SO_ACCEPTCON (1 << 16) + +#define IP_TOS 1 + +#define IPV6_TCLASS 67 +#define IPV6_AUTOFLOWLABEL 70 #define SOL_TCP 6 +#define TCP_NODELAY 1 +#define TCP_MAXSEG 2 +#define TCP_KEEPIDLE 4 +#define TCP_KEEPINTVL 5 +#define TCP_KEEPCNT 6 +#define TCP_SYNCNT 7 +#define TCP_WINDOW_CLAMP 10 #define TCP_CONGESTION 13 +#define TCP_THIN_LINEAR_TIMEOUTS 16 +#define TCP_USER_TIMEOUT 18 +#define TCP_NOTSENT_LOWAT 25 +#define TCP_SAVE_SYN 27 +#define TCP_SAVED_SYN 28 #define TCP_CA_NAME_MAX 16 +#define TCP_NAGLE_OFF 1 #define ICSK_TIME_RETRANS 1 #define ICSK_TIME_PROBE0 3 @@ -49,6 +77,8 @@ #define sk_state __sk_common.skc_state #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr +#define sk_flags __sk_common.skc_flags +#define sk_reuse __sk_common.skc_reuse #define s6_addr32 in6_u.u6_addr32 diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c new file mode 100644 index 000000000000..7653df1bc787 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct map_value { + struct prog_test_ref_kfunc __kptr_ref *ptr; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 16); +} array_map SEC(".maps"); + +extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; +extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; + +static __noinline int cb1(void *map, void *key, void *value, void *ctx) +{ + void *p = *(void **)ctx; + bpf_kfunc_call_test_release(p); + /* Without the fix this would cause underflow */ + return 0; +} + +SEC("?tc") +int underflow_prog(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long sl = 0; + + p = bpf_kfunc_call_test_acquire(&sl); + if (!p) + return 0; + bpf_for_each_map_elem(&array_map, cb1, &p, 0); + return 0; +} + +static __always_inline int cb2(void *map, void *key, void *value, void *ctx) +{ + unsigned long sl = 0; + + *(void **)ctx = bpf_kfunc_call_test_acquire(&sl); + /* Without the fix this would leak memory */ + return 0; +} + +SEC("?tc") +int leak_prog(void *ctx) +{ + struct prog_test_ref_kfunc *p; + struct map_value *v; + unsigned long sl; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 0; + + p = NULL; + bpf_for_each_map_elem(&array_map, cb2, &p, 0); + p = bpf_kptr_xchg(&v->ptr, p); + if (p) + bpf_kfunc_call_test_release(p); + return 0; +} + +static __always_inline int cb(void *map, void *key, void *value, void *ctx) +{ + return 0; +} + +static __always_inline int cb3(void *map, void *key, void *value, void *ctx) +{ + unsigned long sl = 0; + void *p; + + bpf_kfunc_call_test_acquire(&sl); + bpf_for_each_map_elem(&array_map, cb, &p, 0); + /* It should only complain here, not in cb. This is why we need + * callback_ref to be set to frameno. + */ + return 0; +} + +SEC("?tc") +int nested_cb(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long sl = 0; + int sp = 0; + + p = bpf_kfunc_call_test_acquire(&sl); + if (!p) + return 0; + bpf_for_each_map_elem(&array_map, cb3, &sp, 0); + bpf_kfunc_call_test_release(p); + return 0; +} + +SEC("?tc") +int non_cb_transfer_ref(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long sl = 0; + + p = bpf_kfunc_call_test_acquire(&sl); + if (!p) + return 0; + cb1(NULL, NULL, NULL, &p); + bpf_kfunc_call_test_acquire(&sl); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_hooks.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_hooks.c new file mode 100644 index 000000000000..13dfb4bbfd28 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_hooks.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define BPF_RETVAL_HOOK(name, section, ctx, expected_err) \ + __attribute__((__section__("?" section))) \ + int name(struct ctx *_ctx) \ + { \ + bpf_set_retval(bpf_get_retval()); \ + return 1; \ + } + +#include "cgroup_getset_retval_hooks.h" + +#undef BPF_RETVAL_HOOK diff --git a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c new file mode 100644 index 000000000000..8ab4253a1592 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Functions to manage eBPF programs attached to cgroup subsystems + * + * Copyright 2022 Google LLC. + */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +char _license[] SEC("license") = "GPL"; + +/* + * Start times are stored per-task, not per-cgroup, as multiple tasks in one + * cgroup can perform reclaim concurrently. + */ +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, __u64); +} vmscan_start_time SEC(".maps"); + +struct vmscan_percpu { + /* Previous percpu state, to figure out if we have new updates */ + __u64 prev; + /* Current percpu state */ + __u64 state; +}; + +struct vmscan { + /* State propagated through children, pending aggregation */ + __u64 pending; + /* Total state, including all cpus and all children */ + __u64 state; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 100); + __type(key, __u64); + __type(value, struct vmscan_percpu); +} pcpu_cgroup_vmscan_elapsed SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 100); + __type(key, __u64); + __type(value, struct vmscan); +} cgroup_vmscan_elapsed SEC(".maps"); + +extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __ksym; +extern void cgroup_rstat_flush(struct cgroup *cgrp) __ksym; + +static struct cgroup *task_memcg(struct task_struct *task) +{ + int cgrp_id; + +#if __has_builtin(__builtin_preserve_enum_value) + cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id, memory_cgrp_id); +#else + cgrp_id = memory_cgrp_id; +#endif + return task->cgroups->subsys[cgrp_id]->cgroup; +} + +static uint64_t cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + +static int create_vmscan_percpu_elem(__u64 cg_id, __u64 state) +{ + struct vmscan_percpu pcpu_init = {.state = state, .prev = 0}; + + return bpf_map_update_elem(&pcpu_cgroup_vmscan_elapsed, &cg_id, + &pcpu_init, BPF_NOEXIST); +} + +static int create_vmscan_elem(__u64 cg_id, __u64 state, __u64 pending) +{ + struct vmscan init = {.state = state, .pending = pending}; + + return bpf_map_update_elem(&cgroup_vmscan_elapsed, &cg_id, + &init, BPF_NOEXIST); +} + +SEC("tp_btf/mm_vmscan_memcg_reclaim_begin") +int BPF_PROG(vmscan_start, int order, gfp_t gfp_flags) +{ + struct task_struct *task = bpf_get_current_task_btf(); + __u64 *start_time_ptr; + + start_time_ptr = bpf_task_storage_get(&vmscan_start_time, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (start_time_ptr) + *start_time_ptr = bpf_ktime_get_ns(); + return 0; +} + +SEC("tp_btf/mm_vmscan_memcg_reclaim_end") +int BPF_PROG(vmscan_end, unsigned long nr_reclaimed) +{ + struct vmscan_percpu *pcpu_stat; + struct task_struct *current = bpf_get_current_task_btf(); + struct cgroup *cgrp; + __u64 *start_time_ptr; + __u64 current_elapsed, cg_id; + __u64 end_time = bpf_ktime_get_ns(); + + /* + * cgrp is the first parent cgroup of current that has memcg enabled in + * its subtree_control, or NULL if memcg is disabled in the entire tree. + * In a cgroup hierarchy like this: + * a + * / \ + * b c + * If "a" has memcg enabled, while "b" doesn't, then processes in "b" + * will accumulate their stats directly to "a". This makes sure that no + * stats are lost from processes in leaf cgroups that don't have memcg + * enabled, but only exposes stats for cgroups that have memcg enabled. + */ + cgrp = task_memcg(current); + if (!cgrp) + return 0; + + cg_id = cgroup_id(cgrp); + start_time_ptr = bpf_task_storage_get(&vmscan_start_time, current, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!start_time_ptr) + return 0; + + current_elapsed = end_time - *start_time_ptr; + pcpu_stat = bpf_map_lookup_elem(&pcpu_cgroup_vmscan_elapsed, + &cg_id); + if (pcpu_stat) + pcpu_stat->state += current_elapsed; + else if (create_vmscan_percpu_elem(cg_id, current_elapsed)) + return 0; + + cgroup_rstat_updated(cgrp, bpf_get_smp_processor_id()); + return 0; +} + +SEC("fentry/bpf_rstat_flush") +int BPF_PROG(vmscan_flush, struct cgroup *cgrp, struct cgroup *parent, int cpu) +{ + struct vmscan_percpu *pcpu_stat; + struct vmscan *total_stat, *parent_stat; + __u64 cg_id = cgroup_id(cgrp); + __u64 parent_cg_id = parent ? cgroup_id(parent) : 0; + __u64 *pcpu_vmscan; + __u64 state; + __u64 delta = 0; + + /* Add CPU changes on this level since the last flush */ + pcpu_stat = bpf_map_lookup_percpu_elem(&pcpu_cgroup_vmscan_elapsed, + &cg_id, cpu); + if (pcpu_stat) { + state = pcpu_stat->state; + delta += state - pcpu_stat->prev; + pcpu_stat->prev = state; + } + + total_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed, &cg_id); + if (!total_stat) { + if (create_vmscan_elem(cg_id, delta, 0)) + return 0; + + goto update_parent; + } + + /* Collect pending stats from subtree */ + if (total_stat->pending) { + delta += total_stat->pending; + total_stat->pending = 0; + } + + /* Propagate changes to this cgroup's total */ + total_stat->state += delta; + +update_parent: + /* Skip if there are no changes to propagate, or no parent */ + if (!delta || !parent_cg_id) + return 0; + + /* Propagate changes to cgroup's parent */ + parent_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed, + &parent_cg_id); + if (parent_stat) + parent_stat->pending += delta; + else + create_vmscan_elem(parent_cg_id, 0, delta); + return 0; +} + +SEC("iter.s/cgroup") +int BPF_PROG(dump_vmscan, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct seq_file *seq = meta->seq; + struct vmscan *total_stat; + __u64 cg_id = cgrp ? cgroup_id(cgrp) : 0; + + /* Do nothing for the terminal call */ + if (!cg_id) + return 1; + + /* Flush the stats to make sure we get the most updated numbers */ + cgroup_rstat_flush(cgrp); + + total_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed, &cg_id); + if (!total_stat) { + BPF_SEQ_PRINTF(seq, "cg_id: %llu, total_vmscan_delay: 0\n", + cg_id); + } else { + BPF_SEQ_PRINTF(seq, "cg_id: %llu, total_vmscan_delay: %llu\n", + cg_id, total_stat->state); + } + + /* + * We only dump stats for one cgroup here, so return 1 to stop + * iteration after the first cgroup. + */ + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_iter.c b/tools/testing/selftests/bpf/progs/cgroup_iter.c new file mode 100644 index 000000000000..de03997322a7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_iter.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ + +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; +int terminate_early = 0; +u64 terminal_cgroup = 0; + +static inline u64 cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + +SEC("iter/cgroup") +int cgroup_id_printer(struct bpf_iter__cgroup *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct cgroup *cgrp = ctx->cgroup; + + /* epilogue */ + if (cgrp == NULL) { + BPF_SEQ_PRINTF(seq, "epilogue\n"); + return 0; + } + + /* prologue */ + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, "prologue\n"); + + BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp)); + + if (terminal_cgroup == cgroup_id(cgrp)) + return 1; + + return terminate_early ? 1 : 0; +} diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index b241932911db..ec25371de789 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -7,14 +7,15 @@ #include <linux/bpf.h> #include <linux/in.h> #include <linux/in6.h> -#include <sys/socket.h> -#include <netinet/tcp.h> +#include <linux/tcp.h> #include <linux/if.h> #include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +#include "bpf_tcp_helpers.h" + #define SRC_REWRITE_IP4 0x7f000004U #define DST_REWRITE_IP4 0x7f000001U #define DST_REWRITE_PORT4 4444 diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c index 48cd14b43741..4547b059d487 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -73,10 +73,10 @@ int test_subprog2(struct args_subprog2 *ctx) __builtin_preserve_access_index(&skb->len)); ret = ctx->ret; - /* bpf_prog_test_load() loads "test_pkt_access.o" with BPF_F_TEST_RND_HI32 - * which randomizes upper 32 bits after BPF_ALU32 insns. - * Hence after 'w0 <<= 1' upper bits of $rax are random. - * That is expected and correct. Trim them. + /* bpf_prog_test_load() loads "test_pkt_access.bpf.o" with + * BPF_F_TEST_RND_HI32 which randomizes upper 32 bits after BPF_ALU32 + * insns. Hence after 'w0 <<= 1' upper bits of $rax are random. That is + * expected and correct. Trim them. */ ret = (__u32) ret; if (len != 74 || ret != 148) diff --git a/tools/testing/selftests/bpf/progs/htab_update.c b/tools/testing/selftests/bpf/progs/htab_update.c new file mode 100644 index 000000000000..7481bb30b29b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/htab_update.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} htab SEC(".maps"); + +int pid = 0; +int update_err = 0; + +SEC("?fentry/lookup_elem_raw") +int lookup_elem_raw(void *ctx) +{ + __u32 key = 0, value = 1; + + if ((bpf_get_current_pid_tgid() >> 32) != pid) + return 0; + + update_err = bpf_map_update_elem(&htab, &key, &value, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c new file mode 100644 index 000000000000..a47bb0120719 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022. Huawei Technologies Co., Ltd */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +extern bool CONFIG_PREEMPT __kconfig __weak; +extern const int bpf_task_storage_busy __ksym; + +char _license[] SEC("license") = "GPL"; + +int pid = 0; +int busy = 0; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} task SEC(".maps"); + +SEC("raw_tp/sys_enter") +int BPF_PROG(read_bpf_task_storage_busy) +{ + int *value; + int key; + + if (!CONFIG_PREEMPT) + return 0; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + value = bpf_this_cpu_ptr(&bpf_task_storage_busy); + if (value) + busy = *value; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c new file mode 100644 index 000000000000..9523333b8905 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +extern unsigned long CONFIG_HZ __kconfig; + +const volatile char veth[IFNAMSIZ]; +const volatile int veth_ifindex; + +int nr_listen; +int nr_passive; +int nr_active; +int nr_connect; +int nr_binddev; +int nr_socket_post_create; + +struct sockopt_test { + int opt; + int new; + int restore; + int expected; + int tcp_expected; + unsigned int flip:1; +}; + +static const char not_exist_cc[] = "not_exist"; +static const char cubic_cc[] = "cubic"; +static const char reno_cc[] = "reno"; + +static const struct sockopt_test sol_socket_tests[] = { + { .opt = SO_REUSEADDR, .flip = 1, }, + { .opt = SO_SNDBUF, .new = 8123, .expected = 8123 * 2, }, + { .opt = SO_RCVBUF, .new = 8123, .expected = 8123 * 2, }, + { .opt = SO_KEEPALIVE, .flip = 1, }, + { .opt = SO_PRIORITY, .new = 0xeb9f, .expected = 0xeb9f, }, + { .opt = SO_REUSEPORT, .flip = 1, }, + { .opt = SO_RCVLOWAT, .new = 8123, .expected = 8123, }, + { .opt = SO_MARK, .new = 0xeb9f, .expected = 0xeb9f, }, + { .opt = SO_MAX_PACING_RATE, .new = 0xeb9f, .expected = 0xeb9f, }, + { .opt = SO_TXREHASH, .flip = 1, }, + { .opt = 0, }, +}; + +static const struct sockopt_test sol_tcp_tests[] = { + { .opt = TCP_NODELAY, .flip = 1, }, + { .opt = TCP_KEEPIDLE, .new = 123, .expected = 123, .restore = 321, }, + { .opt = TCP_KEEPINTVL, .new = 123, .expected = 123, .restore = 321, }, + { .opt = TCP_KEEPCNT, .new = 123, .expected = 123, .restore = 124, }, + { .opt = TCP_SYNCNT, .new = 123, .expected = 123, .restore = 124, }, + { .opt = TCP_WINDOW_CLAMP, .new = 8123, .expected = 8123, .restore = 8124, }, + { .opt = TCP_CONGESTION, }, + { .opt = TCP_THIN_LINEAR_TIMEOUTS, .flip = 1, }, + { .opt = TCP_USER_TIMEOUT, .new = 123400, .expected = 123400, }, + { .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, }, + { .opt = 0, }, +}; + +static const struct sockopt_test sol_ip_tests[] = { + { .opt = IP_TOS, .new = 0xe1, .expected = 0xe1, .tcp_expected = 0xe0, }, + { .opt = 0, }, +}; + +static const struct sockopt_test sol_ipv6_tests[] = { + { .opt = IPV6_TCLASS, .new = 0xe1, .expected = 0xe1, .tcp_expected = 0xe0, }, + { .opt = IPV6_AUTOFLOWLABEL, .flip = 1, }, + { .opt = 0, }, +}; + +struct loop_ctx { + void *ctx; + struct sock *sk; +}; + +static int bpf_test_sockopt_flip(void *ctx, struct sock *sk, + const struct sockopt_test *t, + int level) +{ + int old, tmp, new, opt = t->opt; + + opt = t->opt; + + if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old))) + return 1; + /* kernel initialized txrehash to 255 */ + if (level == SOL_SOCKET && opt == SO_TXREHASH && old != 0 && old != 1) + old = 1; + + new = !old; + if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new))) + return 1; + if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) || + tmp != new) + return 1; + + if (bpf_setsockopt(ctx, level, opt, &old, sizeof(old))) + return 1; + + return 0; +} + +static int bpf_test_sockopt_int(void *ctx, struct sock *sk, + const struct sockopt_test *t, + int level) +{ + int old, tmp, new, expected, opt; + + opt = t->opt; + new = t->new; + if (sk->sk_type == SOCK_STREAM && t->tcp_expected) + expected = t->tcp_expected; + else + expected = t->expected; + + if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old)) || + old == new) + return 1; + + if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new))) + return 1; + if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) || + tmp != expected) + return 1; + + if (t->restore) + old = t->restore; + if (bpf_setsockopt(ctx, level, opt, &old, sizeof(old))) + return 1; + + return 0; +} + +static int bpf_test_socket_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + + if (i >= ARRAY_SIZE(sol_socket_tests)) + return 1; + + t = &sol_socket_tests[i]; + if (!t->opt) + return 1; + + if (t->flip) + return bpf_test_sockopt_flip(lc->ctx, lc->sk, t, SOL_SOCKET); + + return bpf_test_sockopt_int(lc->ctx, lc->sk, t, SOL_SOCKET); +} + +static int bpf_test_ip_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + + if (i >= ARRAY_SIZE(sol_ip_tests)) + return 1; + + t = &sol_ip_tests[i]; + if (!t->opt) + return 1; + + if (t->flip) + return bpf_test_sockopt_flip(lc->ctx, lc->sk, t, IPPROTO_IP); + + return bpf_test_sockopt_int(lc->ctx, lc->sk, t, IPPROTO_IP); +} + +static int bpf_test_ipv6_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + + if (i >= ARRAY_SIZE(sol_ipv6_tests)) + return 1; + + t = &sol_ipv6_tests[i]; + if (!t->opt) + return 1; + + if (t->flip) + return bpf_test_sockopt_flip(lc->ctx, lc->sk, t, IPPROTO_IPV6); + + return bpf_test_sockopt_int(lc->ctx, lc->sk, t, IPPROTO_IPV6); +} + +static int bpf_test_tcp_sockopt(__u32 i, struct loop_ctx *lc) +{ + const struct sockopt_test *t; + struct sock *sk; + void *ctx; + + if (i >= ARRAY_SIZE(sol_tcp_tests)) + return 1; + + t = &sol_tcp_tests[i]; + if (!t->opt) + return 1; + + ctx = lc->ctx; + sk = lc->sk; + + if (t->opt == TCP_CONGESTION) { + char old_cc[16], tmp_cc[16]; + const char *new_cc; + int new_cc_len; + + if (!bpf_setsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, + (void *)not_exist_cc, sizeof(not_exist_cc))) + return 1; + if (bpf_getsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, old_cc, sizeof(old_cc))) + return 1; + if (!bpf_strncmp(old_cc, sizeof(old_cc), cubic_cc)) { + new_cc = reno_cc; + new_cc_len = sizeof(reno_cc); + } else { + new_cc = cubic_cc; + new_cc_len = sizeof(cubic_cc); + } + if (bpf_setsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, (void *)new_cc, + new_cc_len)) + return 1; + if (bpf_getsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, tmp_cc, sizeof(tmp_cc))) + return 1; + if (bpf_strncmp(tmp_cc, sizeof(tmp_cc), new_cc)) + return 1; + if (bpf_setsockopt(ctx, IPPROTO_TCP, TCP_CONGESTION, old_cc, sizeof(old_cc))) + return 1; + return 0; + } + + if (t->flip) + return bpf_test_sockopt_flip(ctx, sk, t, IPPROTO_TCP); + + return bpf_test_sockopt_int(ctx, sk, t, IPPROTO_TCP); +} + +static int bpf_test_sockopt(void *ctx, struct sock *sk) +{ + struct loop_ctx lc = { .ctx = ctx, .sk = sk, }; + __u16 family, proto; + int n; + + family = sk->sk_family; + proto = sk->sk_protocol; + + n = bpf_loop(ARRAY_SIZE(sol_socket_tests), bpf_test_socket_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_socket_tests)) + return -1; + + if (proto == IPPROTO_TCP) { + n = bpf_loop(ARRAY_SIZE(sol_tcp_tests), bpf_test_tcp_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_tcp_tests)) + return -1; + } + + if (family == AF_INET) { + n = bpf_loop(ARRAY_SIZE(sol_ip_tests), bpf_test_ip_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_ip_tests)) + return -1; + } else { + n = bpf_loop(ARRAY_SIZE(sol_ipv6_tests), bpf_test_ipv6_sockopt, &lc, 0); + if (n != ARRAY_SIZE(sol_ipv6_tests)) + return -1; + } + + return 0; +} + +static int binddev_test(void *ctx) +{ + const char empty_ifname[] = ""; + int ifindex, zero = 0; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + (void *)veth, sizeof(veth))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != veth_ifindex) + return -1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + (void *)empty_ifname, sizeof(empty_ifname))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != 0) + return -1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + (void *)&veth_ifindex, sizeof(int))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != veth_ifindex) + return -1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &zero, sizeof(int))) + return -1; + if (bpf_getsockopt(ctx, SOL_SOCKET, SO_BINDTOIFINDEX, + &ifindex, sizeof(int)) || + ifindex != 0) + return -1; + + return 0; +} + +static int test_tcp_maxseg(void *ctx, struct sock *sk) +{ + int val = 1314, tmp; + + if (sk->sk_state != TCP_ESTABLISHED) + return bpf_setsockopt(ctx, IPPROTO_TCP, TCP_MAXSEG, + &val, sizeof(val)); + + if (bpf_getsockopt(ctx, IPPROTO_TCP, TCP_MAXSEG, &tmp, sizeof(tmp)) || + tmp > val) + return -1; + + return 0; +} + +static int test_tcp_saved_syn(void *ctx, struct sock *sk) +{ + __u8 saved_syn[20]; + int one = 1; + + if (sk->sk_state == TCP_LISTEN) + return bpf_setsockopt(ctx, IPPROTO_TCP, TCP_SAVE_SYN, + &one, sizeof(one)); + + return bpf_getsockopt(ctx, IPPROTO_TCP, TCP_SAVED_SYN, + saved_syn, sizeof(saved_syn)); +} + +SEC("lsm_cgroup/socket_post_create") +int BPF_PROG(socket_post_create, struct socket *sock, int family, + int type, int protocol, int kern) +{ + struct sock *sk = sock->sk; + + if (!sk) + return 1; + + nr_socket_post_create += !bpf_test_sockopt(sk, sk); + nr_binddev += !binddev_test(sk); + + return 1; +} + +SEC("sockops") +int skops_sockopt(struct bpf_sock_ops *skops) +{ + struct bpf_sock *bpf_sk = skops->sk; + struct sock *sk; + + if (!bpf_sk) + return 1; + + sk = (struct sock *)bpf_skc_to_tcp_sock(bpf_sk); + if (!sk) + return 1; + + switch (skops->op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + nr_listen += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk) || + test_tcp_saved_syn(skops, sk)); + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + nr_connect += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk)); + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + nr_active += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + nr_passive += !(bpf_test_sockopt(skops, sk) || + test_tcp_maxseg(skops, sk) || + test_tcp_saved_syn(skops, sk)); + break; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index b67e8022d500..a017d6b2f1dd 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -19,7 +19,7 @@ struct { int count = 0; int noise = 0; -__always_inline int subprog_noise(void) +static __always_inline int subprog_noise(void) { __u32 key = 0; diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c index b596479a9ebe..125beec31834 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -15,7 +15,6 @@ #include <linux/udp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -#include <sys/socket.h> /* veth_src --- veth_src_fwd --- veth_det_fwd --- veth_dst * | | diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index df0673c4ecbe..98af55f0bcd3 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -12,6 +12,7 @@ #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> +#include <linux/if_tunnel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/icmp.h> @@ -386,7 +387,8 @@ int vxlan_get_tunnel_src(struct __sk_buff *skb) __u32 orig_daddr; __u32 index = 0; - ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_FLAGS); if (ret < 0) { log_err(ret); return TC_ACT_SHOT; @@ -398,10 +400,13 @@ int vxlan_get_tunnel_src(struct __sk_buff *skb) return TC_ACT_SHOT; } - if (key.local_ipv4 != ASSIGNED_ADDR_VETH1 || md.gbp != 0x800FF) { - bpf_printk("vxlan key %d local ip 0x%x remote ip 0x%x gbp 0x%x\n", + if (key.local_ipv4 != ASSIGNED_ADDR_VETH1 || md.gbp != 0x800FF || + !(key.tunnel_flags & TUNNEL_KEY) || + (key.tunnel_flags & TUNNEL_CSUM)) { + bpf_printk("vxlan key %d local ip 0x%x remote ip 0x%x gbp 0x%x flags 0x%x\n", key.tunnel_id, key.local_ipv4, - key.remote_ipv4, md.gbp); + key.remote_ipv4, md.gbp, + bpf_ntohs(key.tunnel_flags)); log_err(ret); return TC_ACT_SHOT; } @@ -541,16 +546,19 @@ int ip6vxlan_get_tunnel_src(struct __sk_buff *skb) } ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), - BPF_F_TUNINFO_IPV6); + BPF_F_TUNINFO_IPV6 | BPF_F_TUNINFO_FLAGS); if (ret < 0) { log_err(ret); return TC_ACT_SHOT; } - if (bpf_ntohl(key.local_ipv6[3]) != *local_ip) { - bpf_printk("ip6vxlan key %d local ip6 ::%x remote ip6 ::%x label 0x%x\n", + if (bpf_ntohl(key.local_ipv6[3]) != *local_ip || + !(key.tunnel_flags & TUNNEL_KEY) || + !(key.tunnel_flags & TUNNEL_CSUM)) { + bpf_printk("ip6vxlan key %d local ip6 ::%x remote ip6 ::%x label 0x%x flags 0x%x\n", key.tunnel_id, bpf_ntohl(key.local_ipv6[3]), - bpf_ntohl(key.remote_ipv6[3]), key.tunnel_label); + bpf_ntohl(key.remote_ipv6[3]), key.tunnel_label, + bpf_ntohs(key.tunnel_flags)); bpf_printk("local_ip 0x%x\n", *local_ip); log_err(ret); return TC_ACT_SHOT; diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c index 5f5309791649..0053c5402173 100644 --- a/tools/testing/selftests/bpf/progs/timer.c +++ b/tools/testing/selftests/bpf/progs/timer.c @@ -208,17 +208,6 @@ static int timer_cb2(void *map, int *key, struct hmap_elem *val) */ bpf_map_delete_elem(map, key); - /* in non-preallocated hashmap both 'key' and 'val' are RCU - * protected and still valid though this element was deleted - * from the map. Arm this timer for ~35 seconds. When callback - * finishes the call_rcu will invoke: - * htab_elem_free_rcu - * check_and_free_timer - * bpf_timer_cancel_and_free - * to cancel this 35 second sleep and delete the timer for real. - */ - if (bpf_timer_start(&val->timer, 1ull << 35, 0) != 0) - err |= 256; ok |= 4; } return 0; |