diff options
63 files changed, 1059 insertions, 434 deletions
diff --git a/Documentation/networking/dns_resolver.rst b/Documentation/networking/dns_resolver.rst index add4d59a99a5..c0364f7070af 100644 --- a/Documentation/networking/dns_resolver.rst +++ b/Documentation/networking/dns_resolver.rst @@ -118,7 +118,7 @@ Keys of dns_resolver type can be read from userspace using keyctl_read() or Mechanism ========= -The dnsresolver module registers a key type called "dns_resolver". Keys of +The dns_resolver module registers a key type called "dns_resolver". Keys of this type are used to transport and cache DNS lookup results from userspace. When dns_query() is invoked, it calls request_key() to search the local @@ -152,4 +152,4 @@ Debugging Debugging messages can be turned on dynamically by writing a 1 into the following file:: - /sys/module/dnsresolver/parameters/debug + /sys/module/dns_resolver/parameters/debug diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1d672457d02f..01516f83a95a 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -2222,28 +2222,21 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* If building the body of the JITed code fails somehow, * we fall back to the interpretation. */ - if (build_body(&ctx) < 0) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (build_body(&ctx) < 0) + goto out_free; build_epilogue(&ctx); /* 3.) Extra pass to validate JITed Code */ - if (validate_code(&ctx)) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (validate_code(&ctx)) + goto out_free; flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); if (bpf_jit_enable > 1) /* there are 2 passes here */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_free; prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; @@ -2260,5 +2253,11 @@ out: bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); return prog; + +out_free: + image_ptr = NULL; + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_imms; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 122021f9bdfc..82d6c562e8c7 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2176,12 +2176,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size) bpf_prog_pack_free(image, size); } -void arch_protect_bpf_trampoline(void *image, unsigned int size) -{ -} - -void arch_unprotect_bpf_trampoline(void *image, unsigned int size) +int arch_protect_bpf_trampoline(void *image, unsigned int size) { + return 0; } int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index e73323d759d0..7dbefd4ba210 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1294,16 +1294,19 @@ skip_init_ctx: flush_icache_range((unsigned long)header, (unsigned long)(ctx.image + ctx.idx)); if (!prog->is_func || extra_pass) { + int err; + if (extra_pass && ctx.idx != jit_data->ctx.idx) { pr_err_once("multi-func JIT bug %d != %d\n", ctx.idx, jit_data->ctx.idx); - bpf_jit_binary_free(header); - prog->bpf_func = NULL; - prog->jited = 0; - prog->jited_len = 0; - goto out_offset; + goto out_free; + } + err = bpf_jit_binary_lock_ro(header); + if (err) { + pr_err_once("bpf_jit_binary_lock_ro() returned %d\n", + err); + goto out_free; } - bpf_jit_binary_lock_ro(header); } else { jit_data->ctx = ctx; jit_data->image = image_ptr; @@ -1334,6 +1337,13 @@ out: out_offset = -1; return prog; + +out_free: + bpf_jit_binary_free(header); + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_offset; } /* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */ diff --git a/arch/mips/net/bpf_jit_comp.c b/arch/mips/net/bpf_jit_comp.c index a40d926b6513..e355dfca4400 100644 --- a/arch/mips/net/bpf_jit_comp.c +++ b/arch/mips/net/bpf_jit_comp.c @@ -1012,7 +1012,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_prog_fill_jited_linfo(prog, &ctx.descriptors[1]); /* Set as read-only exec and flush instruction cache */ - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_err; flush_icache_range((unsigned long)header, (unsigned long)&ctx.target[ctx.jit_index]); diff --git a/arch/parisc/net/bpf_jit_core.c b/arch/parisc/net/bpf_jit_core.c index d6ee2fd45550..979f45d4d1fb 100644 --- a/arch/parisc/net/bpf_jit_core.c +++ b/arch/parisc/net/bpf_jit_core.c @@ -167,7 +167,13 @@ skip_init_ctx: bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(jit_data->header); + if (bpf_jit_binary_lock_ro(jit_data->header)) { + bpf_jit_binary_free(jit_data->header); + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_offset; + } prologue_len = ctx->epilogue_offset - ctx->body_len; for (i = 0; i < prog->len; i++) ctx->offset[i] += prologue_len; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 5af0402e94b8..fa2f824e3b06 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -2108,7 +2108,11 @@ skip_init_ctx: print_fn_code(jit.prg_buf, jit.size_prg); } if (!fp->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + fp = orig_fp; + goto free_addrs; + } } else { jit_data->header = header; jit_data->ctx = jit; diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index fa0759bfe498..73bf0aea8baf 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1602,7 +1602,11 @@ skip_init_ctx: bpf_flush_icache(header, (u8 *)header + header->size); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a7ba8e178645..3b639d6f2f54 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1351,8 +1351,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image break; case BPF_ALU64 | BPF_MOV | BPF_X: - if (insn->off == BPF_ADDR_SPACE_CAST && - insn->imm == 1U << 16) { + if (insn_is_cast_user(insn)) { if (dst_reg != src_reg) /* 32-bit mov */ emit_mov_reg(&prog, false, dst_reg, src_reg); @@ -3004,12 +3003,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size) bpf_prog_pack_free(image, size); } -void arch_protect_bpf_trampoline(void *image, unsigned int size) -{ -} - -void arch_unprotect_bpf_trampoline(void *image, unsigned int size) +int arch_protect_bpf_trampoline(void *image, unsigned int size) { + return 0; } int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index c10083a8e68e..de0f9e5f9f73 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2600,8 +2600,7 @@ out_image: if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, proglen, pass + 1, image); - if (image) { - bpf_jit_binary_lock_ro(header); + if (image && !bpf_jit_binary_lock_ro(header)) { prog->bpf_func = (void *)image; prog->jited = 1; prog->jited_len = proglen; diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index ea6cfc2095e1..c1b5e9a94308 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1796,7 +1796,6 @@ static int amd8111e_probe_one(struct pci_dev *pdev, lp = netdev_priv(dev); lp->pci_dev = pdev; lp->amd8111e_net_dev = dev; - lp->pm_cap = pdev->pm_cap; spin_lock_init(&lp->lock); diff --git a/drivers/net/ethernet/amd/amd8111e.h b/drivers/net/ethernet/amd/amd8111e.h index 9d570adb295b..305232f5476d 100644 --- a/drivers/net/ethernet/amd/amd8111e.h +++ b/drivers/net/ethernet/amd/amd8111e.h @@ -764,7 +764,6 @@ struct amd8111e_priv{ u32 ext_phy_id; struct amd8111e_link_config link_config; - int pm_cap; struct net_device *next; int mii; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c index 17faac715882..5c13bcb4550d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c @@ -406,7 +406,7 @@ free_sge_txq_uld(struct adapter *adap, struct sge_uld_txq_info *txq_info) for (i = 0; i < nq; i++) { struct sge_uld_txq *txq = &txq_info->uldtxq[i]; - if (txq && txq->q.desc) { + if (txq->q.desc) { tasklet_kill(&txq->qresume_tsk); t4_ofld_eq_free(adap, adap->mbox, adap->pf, 0, txq->q.cntxt_id); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 382e8de1255d..7ae04d8d291c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -12,10 +12,8 @@ #include <linux/clk.h> #include <linux/phy.h> #include <linux/of_net.h> -#include <linux/gpio.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_gpio.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> #include <linux/delay.h> diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f20f62f9d63..62762390c93d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1116,8 +1116,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); -void arch_protect_bpf_trampoline(void *image, unsigned int size); -void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); @@ -1608,6 +1607,12 @@ struct bpf_tracing_link { struct bpf_prog *tgt_prog; }; +struct bpf_raw_tp_link { + struct bpf_link link; + struct bpf_raw_event_map *btp; + u64 cookie; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..44934b968b57 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -228,6 +228,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } +/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers + * to pointers in user vma. + */ +static inline bool insn_is_cast_user(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST && + insn->imm == 1U << 16; +} + /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) @@ -887,20 +897,22 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); + return set_memory_ro((unsigned long)fp, fp->pages); } #endif + return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cb37817d6382..e41d30ebaca6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3287,6 +3287,7 @@ static inline void dev_xmit_recursion_dec(void) __this_cpu_dec(softnet_data.xmit.recursion); } +void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d24aec064e8..517e546a120a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4058,12 +4058,6 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len); -static inline void skb_free_datagram_locked(struct sock *sk, - struct sk_buff *skb) -{ - __skb_free_datagram_locked(sk, skb, 0); -} int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 6f9bdfb09d1d..9df3e2973626 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -765,8 +765,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); + +struct bpf_raw_tp_link; +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); + struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -794,11 +797,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info) { return -EOPNOTSUPP; } -static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p) +struct bpf_raw_tp_link; +static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } -static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p) +static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } @@ -909,31 +913,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); -void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); -void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); -void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1); +void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2); +void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3); -void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5); -void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6); -void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7); -void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9); -void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10); -void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11); -void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12); void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index e609cd7da47e..a2ea11cc912e 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -46,8 +46,7 @@ static notrace void \ __bpf_trace_##call(void *__data, proto) \ { \ - struct bpf_prog *prog = __data; \ - CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args)); \ + CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(__data, CAST_TO_U64(args)); \ } #undef DECLARE_EVENT_CLASS diff --git a/include/trace/events/net_probe_common.h b/include/trace/events/net_probe_common.h index 3930119cab08..b1f9a4d3ee13 100644 --- a/include/trace/events/net_probe_common.h +++ b/include/trace/events/net_probe_common.h @@ -41,4 +41,33 @@ #endif +#define TP_STORE_V4MAPPED(__entry, saddr, daddr) \ + do { \ + struct in6_addr *pin6; \ + \ + pin6 = (struct in6_addr *)__entry->saddr_v6; \ + ipv6_addr_set_v4mapped(saddr, pin6); \ + pin6 = (struct in6_addr *)__entry->daddr_v6; \ + ipv6_addr_set_v4mapped(daddr, pin6); \ + } while (0) + +#if IS_ENABLED(CONFIG_IPV6) +#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ + do { \ + if (sk->sk_family == AF_INET6) { \ + struct in6_addr *pin6; \ + \ + pin6 = (struct in6_addr *)__entry->saddr_v6; \ + *pin6 = saddr6; \ + pin6 = (struct in6_addr *)__entry->daddr_v6; \ + *pin6 = daddr6; \ + } else { \ + TP_STORE_V4MAPPED(__entry, saddr, daddr); \ + } \ + } while (0) +#else +#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ + TP_STORE_V4MAPPED(__entry, saddr, daddr) +#endif + #endif diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index fd206a6ab5b8..0d1c5ce4e6a6 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -10,6 +10,7 @@ #include <linux/tracepoint.h> #include <linux/ipv6.h> #include <linux/tcp.h> +#include <trace/events/net_probe_common.h> #define family_names \ EM(AF_INET) \ @@ -159,7 +160,6 @@ TRACE_EVENT(inet_sock_set_state, TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); - struct in6_addr *pin6; __be32 *p32; __entry->skaddr = sk; @@ -177,20 +177,8 @@ TRACE_EVENT(inet_sock_set_state, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = sk->sk_v6_rcv_saddr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = sk->sk_v6_daddr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); - } + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", @@ -223,7 +211,6 @@ TRACE_EVENT(inet_sk_error_report, TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); - struct in6_addr *pin6; __be32 *p32; __entry->error = sk->sk_err; @@ -238,20 +225,8 @@ TRACE_EVENT(inet_sk_error_report, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = sk->sk_v6_rcv_saddr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = sk->sk_v6_daddr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); - } + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 699dafd204ea..3c08a0846c47 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -12,35 +12,6 @@ #include <net/tcp.h> #include <linux/sock_diag.h> -#define TP_STORE_V4MAPPED(__entry, saddr, daddr) \ - do { \ - struct in6_addr *pin6; \ - \ - pin6 = (struct in6_addr *)__entry->saddr_v6; \ - ipv6_addr_set_v4mapped(saddr, pin6); \ - pin6 = (struct in6_addr *)__entry->daddr_v6; \ - ipv6_addr_set_v4mapped(daddr, pin6); \ - } while (0) - -#if IS_ENABLED(CONFIG_IPV6) -#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ - do { \ - if (sk->sk_family == AF_INET6) { \ - struct in6_addr *pin6; \ - \ - pin6 = (struct in6_addr *)__entry->saddr_v6; \ - *pin6 = saddr6; \ - pin6 = (struct in6_addr *)__entry->daddr_v6; \ - *pin6 = daddr6; \ - } else { \ - TP_STORE_V4MAPPED(__entry, saddr, daddr); \ - } \ - } while (0) -#else -#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ - TP_STORE_V4MAPPED(__entry, saddr, daddr) -#endif - /* * tcp event with arguments sk and skb * diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3c42b9f1bada..9585f5345353 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1662,8 +1662,10 @@ union bpf_attr { } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ - __u64 name; - __u32 prog_fd; + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 43356faaa057..86c7884abaf8 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -728,8 +728,6 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, cur_image = image; trampoline_start = 0; } - if (err < 0) - goto reset_unlock; *(void **)(kdata + moff) = image + trampoline_start + cfi_get_offset(); @@ -742,8 +740,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) goto reset_unlock; } - for (i = 0; i < st_map->image_pages_cnt; i++) - arch_protect_bpf_trampoline(st_map->image_pages[i], PAGE_SIZE); + for (i = 0; i < st_map->image_pages_cnt; i++) { + err = arch_protect_bpf_trampoline(st_map->image_pages[i], + PAGE_SIZE); + if (err) + goto reset_unlock; + } if (st_map->map.map_flags & BPF_F_LINK) { err = 0; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 82243cb6c54d..8ba73042a239 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -2575,8 +2575,6 @@ cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; #ifdef CONFIG_CGROUP_NET_CLASSID diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 696bc55de8e8..5aacb1d3c4cc 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -908,23 +908,30 @@ static LIST_HEAD(pack_list); static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; + int err; pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)), GFP_KERNEL); if (!pack) return NULL; pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE); - if (!pack->ptr) { - kfree(pack); - return NULL; - } + if (!pack->ptr) + goto out; bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE); bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); - list_add_tail(&pack->list, &pack_list); set_vm_flush_reset_perms(pack->ptr); - set_memory_rox((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); + err = set_memory_rox((unsigned long)pack->ptr, + BPF_PROG_PACK_SIZE / PAGE_SIZE); + if (err) + goto out; + list_add_tail(&pack->list, &pack_list); return pack; + +out: + bpf_jit_free_exec(pack->ptr); + kfree(pack); + return NULL; } void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) @@ -939,9 +946,16 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) size = round_up(size, PAGE_SIZE); ptr = bpf_jit_alloc_exec(size); if (ptr) { + int err; + bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); - set_memory_rox((unsigned long)ptr, size / PAGE_SIZE); + err = set_memory_rox((unsigned long)ptr, + size / PAGE_SIZE); + if (err) { + bpf_jit_free_exec(ptr); + ptr = NULL; + } } goto out; } @@ -2403,7 +2417,9 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } finalize: - bpf_prog_lock_ro(fp); + *err = bpf_prog_lock_ro(fp); + if (*err) + return fp; /* The tail call compatibility check can only be done at * this late stage as we need to determine, if we deal diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 449b9a5d3fe3..f860adab3eb9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1730,6 +1730,10 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_strtol_proto; case BPF_FUNC_strtoul: return &bpf_strtoul_proto; + case BPF_FUNC_get_current_pid_tgid: + return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_get_ns_current_pid_tgid: + return &bpf_get_ns_current_pid_tgid_proto; default: break; } diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 050fe1ebf0f7..939620b91c0e 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -155,16 +155,17 @@ static inline int extract_bit(const u8 *data, size_t index) } /** - * longest_prefix_match() - determine the longest prefix + * __longest_prefix_match() - determine the longest prefix * @trie: The trie to get internal sizes from * @node: The node to operate on * @key: The key to compare to @node * * Determine the longest prefix of @node that matches the bits in @key. */ -static size_t longest_prefix_match(const struct lpm_trie *trie, - const struct lpm_trie_node *node, - const struct bpf_lpm_trie_key_u8 *key) +static __always_inline +size_t __longest_prefix_match(const struct lpm_trie *trie, + const struct lpm_trie_node *node, + const struct bpf_lpm_trie_key_u8 *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; @@ -224,6 +225,13 @@ static size_t longest_prefix_match(const struct lpm_trie *trie, return prefixlen; } +static size_t longest_prefix_match(const struct lpm_trie *trie, + const struct lpm_trie_node *node, + const struct bpf_lpm_trie_key_u8 *key) +{ + return __longest_prefix_match(trie, node, key); +} + /* Called from syscall or from eBPF program */ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { @@ -245,7 +253,7 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) * If it's the maximum possible prefix for this trie, we have * an exact match and can return it directly. */ - matchlen = longest_prefix_match(trie, node, key); + matchlen = __longest_prefix_match(trie, node, key); if (matchlen == trie->max_prefixlen) { found = node; break; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ae2ff73bde7e..e44c276e8617 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3469,17 +3469,12 @@ out_put_prog: return err; } -struct bpf_raw_tp_link { - struct bpf_link link; - struct bpf_raw_event_map *btp; -}; - static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); - bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog); + bpf_probe_unregister(raw_tp->btp, raw_tp); bpf_put_raw_tracepoint(raw_tp->btp); } @@ -3779,7 +3774,7 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro #endif /* CONFIG_PERF_EVENTS */ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, - const char __user *user_tp_name) + const char __user *user_tp_name, u64 cookie) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; @@ -3826,6 +3821,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog); link->btp = btp; + link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -3833,7 +3829,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, goto out_put_btp; } - err = bpf_probe_register(link->btp, prog); + err = bpf_probe_register(link->btp, link); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; @@ -3846,11 +3842,13 @@ out_put_btp: return err; } -#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd +#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_prog *prog; + void __user *tp_name; + __u64 cookie; int fd; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) @@ -3860,7 +3858,9 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - fd = bpf_raw_tp_link_attach(prog, u64_to_user_ptr(attr->raw_tracepoint.name)); + tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); + cookie = attr->raw_tracepoint.cookie; + fd = bpf_raw_tp_link_attach(prog, tp_name, cookie); if (fd < 0) bpf_prog_put(prog); return fd; @@ -5198,7 +5198,7 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) goto out; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) - ret = bpf_raw_tp_link_attach(prog, NULL); + ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index db7599c59c78..cc50607f8d8c 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -456,7 +456,9 @@ again: if (err < 0) goto out_free; - arch_protect_bpf_trampoline(im->image, im->size); + err = arch_protect_bpf_trampoline(im->image, im->size); + if (err) + goto out_free; WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) @@ -1072,17 +1074,10 @@ void __weak arch_free_bpf_trampoline(void *image, unsigned int size) bpf_jit_free_exec(image); } -void __weak arch_protect_bpf_trampoline(void *image, unsigned int size) -{ - WARN_ON_ONCE(size > PAGE_SIZE); - set_memory_rox((long)image, 1); -} - -void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size) +int __weak arch_protect_bpf_trampoline(void *image, unsigned int size) { WARN_ON_ONCE(size > PAGE_SIZE); - set_memory_nx((long)image, 1); - set_memory_rw((long)image, 1); + return set_memory_rox((long)image, 1); } int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 353985b2b6a2..17f26ba1a9e0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14564,7 +14564,19 @@ static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state struct tnum t; u64 val; -again: + /* In case of GE/GT/SGE/JST, reuse LE/LT/SLE/SLT logic from below */ + switch (opcode) { + case BPF_JGE: + case BPF_JGT: + case BPF_JSGE: + case BPF_JSGT: + opcode = flip_opcode(opcode); + swap(reg1, reg2); + break; + default: + break; + } + switch (opcode) { case BPF_JEQ: if (is_jmp32) { @@ -14707,14 +14719,6 @@ again: reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value); } break; - case BPF_JGE: - case BPF_JGT: - case BPF_JSGE: - case BPF_JSGT: - /* just reuse LE/LT logic above */ - opcode = flip_opcode(opcode); - swap(reg1, reg2); - goto again; default: return; } @@ -19178,6 +19182,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; + func[i]->sleepable = prog->sleepable; func[i]->aux->func_idx = i; /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; @@ -19282,10 +19287,14 @@ static int jit_subprogs(struct bpf_verifier_env *env) * bpf_prog_load will add the kallsyms for the main program. */ for (i = 1; i < env->subprog_cnt; i++) { - bpf_prog_lock_ro(func[i]); - bpf_prog_kallsyms_add(func[i]); + err = bpf_prog_lock_ro(func[i]); + if (err) + goto out_free; } + for (i = 1; i < env->subprog_cnt; i++) + bpf_prog_kallsyms_add(func[i]); + /* Last step: make now unused interpreter insns from main * prog consistent for later dump requests, so they can * later look the same as if they were interpreted only. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0a5c4efc73c3..6d0c95638e1b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1053,9 +1053,15 @@ static unsigned long get_entry_ip(unsigned long fentry_ip) { u32 instr; - /* Being extra safe in here in case entry ip is on the page-edge. */ - if (get_kernel_nofault(instr, (u32 *) fentry_ip - 1)) - return fentry_ip; + /* We want to be extra safe in case entry ip is on the page edge, + * but otherwise we need to avoid get_kernel_nofault()'s overhead. + */ + if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) { + if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE))) + return fentry_ip; + } else { + instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE); + } if (is_endbr(instr)) fentry_ip -= ENDBR_INSN_SIZE; return fentry_ip; @@ -1525,8 +1531,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; case BPF_FUNC_get_current_task_btf: @@ -1582,8 +1586,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_send_signal_thread_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; - case BPF_FUNC_get_ns_current_pid_tgid: - return &bpf_get_ns_current_pid_tgid_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: @@ -2008,6 +2010,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; + case BPF_FUNC_get_attach_cookie: + return &bpf_get_attach_cookie_proto_tracing; default: return bpf_tracing_func_proto(func_id, prog); } @@ -2070,6 +2074,9 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_func_arg_cnt: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; case BPF_FUNC_get_attach_cookie: + if (prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_RAW_TP) + return &bpf_get_attach_cookie_proto_tracing; return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); @@ -2370,16 +2377,26 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) } static __always_inline -void __bpf_trace_run(struct bpf_prog *prog, u64 *args) +void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args) { + struct bpf_prog *prog = link->link.prog; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; + cant_sleep(); if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); goto out; } + + run_ctx.bpf_cookie = link->cookie; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + rcu_read_lock(); (void) bpf_prog_run(prog, args); rcu_read_unlock(); + + bpf_reset_run_ctx(old_run_ctx); out: this_cpu_dec(*(prog->active)); } @@ -2408,12 +2425,12 @@ out: #define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 #define BPF_TRACE_DEFN_x(x) \ - void bpf_trace_run##x(struct bpf_prog *prog, \ + void bpf_trace_run##x(struct bpf_raw_tp_link *link, \ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \ { \ u64 args[x]; \ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \ - __bpf_trace_run(prog, args); \ + __bpf_trace_run(link, args); \ } \ EXPORT_SYMBOL_GPL(bpf_trace_run##x) BPF_TRACE_DEFN_x(1); @@ -2429,9 +2446,10 @@ BPF_TRACE_DEFN_x(10); BPF_TRACE_DEFN_x(11); BPF_TRACE_DEFN_x(12); -static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { struct tracepoint *tp = btp->tp; + struct bpf_prog *prog = link->link.prog; /* * check that program doesn't access arguments beyond what's @@ -2443,18 +2461,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * if (prog->aux->max_tp_access > btp->writable_size) return -EINVAL; - return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, - prog); -} - -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) -{ - return __bpf_probe_register(btp, prog); + return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, link); } -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { - return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, link); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index de33dc1b0daa..25b75844891a 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -133,7 +133,9 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, if (err < 0) goto out; - arch_protect_bpf_trampoline(image, PAGE_SIZE); + err = arch_protect_bpf_trampoline(image, PAGE_SIZE); + if (err) + goto out; prog_ret = dummy_ops_call_op(image, args); err = dummy_ops_copy_args(args); diff --git a/net/core/datagram.c b/net/core/datagram.c index a8b625abe242..e614cfd8e14a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -324,25 +324,6 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(skb_free_datagram); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) -{ - bool slow; - - if (!skb_unref(skb)) { - sk_peek_offset_bwd(sk, len); - return; - } - - slow = lock_sock_fast(sk); - sk_peek_offset_bwd(sk, len); - skb_orphan(skb); - unlock_sock_fast(sk, slow); - - /* skb is now orphaned, can be freed outside of locked section */ - __kfree_skb(skb); -} -EXPORT_SYMBOL(__skb_free_datagram_locked); - int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, diff --git a/net/core/dev.c b/net/core/dev.c index 9a67003e49db..5d36a634f468 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -78,6 +78,7 @@ #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/mm.h> +#include <linux/smpboot.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/string.h> @@ -197,35 +198,60 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } -static inline void rps_lock_irqsave(struct softnet_data *sd, - unsigned long *flags) +#ifndef CONFIG_PREEMPT_RT + +static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key); + +static int __init setup_backlog_napi_threads(char *arg) +{ + static_branch_enable(&use_backlog_threads_key); + return 0; +} +early_param("thread_backlog_napi", setup_backlog_napi_threads); + +static bool use_backlog_threads(void) +{ + return static_branch_unlikely(&use_backlog_threads_key); +} + +#else + +static bool use_backlog_threads(void) { - if (IS_ENABLED(CONFIG_RPS)) + return true; +} + +#endif + +static inline void backlog_lock_irq_save(struct softnet_data *sd, + unsigned long *flags) +{ + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_save(*flags); } -static inline void rps_lock_irq_disable(struct softnet_data *sd) +static inline void backlog_lock_irq_disable(struct softnet_data *sd) { - if (IS_ENABLED(CONFIG_RPS)) + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_disable(); } -static inline void rps_unlock_irq_restore(struct softnet_data *sd, - unsigned long *flags) +static inline void backlog_unlock_irq_restore(struct softnet_data *sd, + unsigned long *flags) { - if (IS_ENABLED(CONFIG_RPS)) + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } -static inline void rps_unlock_irq_enable(struct softnet_data *sd) +static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { - if (IS_ENABLED(CONFIG_RPS)) + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_enable(); @@ -4404,6 +4430,7 @@ EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines *************************************************************************/ +static DEFINE_PER_CPU(struct task_struct *, backlog_napi); unsigned int sysctl_skb_defer_max __read_mostly = 64; int weight_p __read_mostly = 64; /* old backlog weight */ @@ -4427,18 +4454,16 @@ static inline void ____napi_schedule(struct softnet_data *sd, */ thread = READ_ONCE(napi->thread); if (thread) { - /* Avoid doing set_bit() if the thread is in - * INTERRUPTIBLE state, cause napi_thread_wait() - * makes sure to proceed with napi polling - * if the thread is explicitly woken from here. - */ - if (READ_ONCE(thread->__state) != TASK_INTERRUPTIBLE) - set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); + if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi)) + goto use_local_napi; + + set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } } +use_local_napi: list_add_tail(&napi->poll_list, &sd->poll_list); WRITE_ONCE(napi->list_owner, smp_processor_id()); /* If not called from net_rx_action() @@ -4678,6 +4703,11 @@ static void napi_schedule_rps(struct softnet_data *sd) #ifdef CONFIG_RPS if (sd != mysd) { + if (use_backlog_threads()) { + __napi_schedule_irqoff(&sd->backlog); + return; + } + sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; @@ -4692,6 +4722,23 @@ static void napi_schedule_rps(struct softnet_data *sd) __napi_schedule_irqoff(&mysd->backlog); } +void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu) +{ + unsigned long flags; + + if (use_backlog_threads()) { + backlog_lock_irq_save(sd, &flags); + + if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) + __napi_schedule_irqoff(&sd->backlog); + + backlog_unlock_irq_restore(sd, &flags); + + } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) { + smp_call_function_single_async(cpu, &sd->defer_csd); + } +} + #ifdef CONFIG_NET_FLOW_LIMIT int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif @@ -4747,7 +4794,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, reason = SKB_DROP_REASON_NOT_SPECIFIED; sd = &per_cpu(softnet_data, cpu); - rps_lock_irqsave(sd, &flags); + backlog_lock_irq_save(sd, &flags); if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); @@ -4757,7 +4804,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); input_queue_tail_incr_save(sd, qtail); - rps_unlock_irq_restore(sd, &flags); + backlog_unlock_irq_restore(sd, &flags); return NET_RX_SUCCESS; } @@ -4772,7 +4819,7 @@ enqueue: drop: sd->dropped++; - rps_unlock_irq_restore(sd, &flags); + backlog_unlock_irq_restore(sd, &flags); dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); @@ -5838,7 +5885,7 @@ static void flush_backlog(struct work_struct *work) local_bh_disable(); sd = this_cpu_ptr(&softnet_data); - rps_lock_irq_disable(sd); + backlog_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); @@ -5846,7 +5893,7 @@ static void flush_backlog(struct work_struct *work) input_queue_head_incr(sd); } } - rps_unlock_irq_enable(sd); + backlog_unlock_irq_enable(sd); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { @@ -5864,14 +5911,14 @@ static bool flush_required(int cpu) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; - rps_lock_irq_disable(sd); + backlog_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); - rps_unlock_irq_enable(sd); + backlog_unlock_irq_enable(sd); return do_flush; #endif @@ -5937,7 +5984,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) #ifdef CONFIG_RPS struct softnet_data *remsd = sd->rps_ipi_list; - if (remsd) { + if (!use_backlog_threads() && remsd) { sd->rps_ipi_list = NULL; local_irq_enable(); @@ -5952,7 +5999,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) { #ifdef CONFIG_RPS - return sd->rps_ipi_list != NULL; + return !use_backlog_threads() && sd->rps_ipi_list; #else return false; #endif @@ -5986,7 +6033,7 @@ static int process_backlog(struct napi_struct *napi, int quota) } - rps_lock_irq_disable(sd); + backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). @@ -5996,13 +6043,13 @@ static int process_backlog(struct napi_struct *napi, int quota) * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ - napi->state = 0; + napi->state &= NAPIF_STATE_THREADED; again = false; } else { skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); } - rps_unlock_irq_enable(sd); + backlog_unlock_irq_enable(sd); } return work; @@ -6710,8 +6757,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) static int napi_thread_wait(struct napi_struct *napi) { - bool woken = false; - set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { @@ -6720,15 +6765,13 @@ static int napi_thread_wait(struct napi_struct *napi) * Testing SCHED bit is not enough because SCHED bit might be * set by some other busy poll thread or by napi_disable(). */ - if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) { + if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); - /* woken being true indicates this thread owns this napi. */ - woken = true; set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); @@ -6736,43 +6779,48 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static int napi_threaded_poll(void *data) +static void napi_threaded_poll_loop(struct napi_struct *napi) { - struct napi_struct *napi = data; struct softnet_data *sd; - void *have; + unsigned long last_qs = jiffies; - while (!napi_thread_wait(napi)) { - unsigned long last_qs = jiffies; - - for (;;) { - bool repoll = false; + for (;;) { + bool repoll = false; + void *have; - local_bh_disable(); - sd = this_cpu_ptr(&softnet_data); - sd->in_napi_threaded_poll = true; + local_bh_disable(); + sd = this_cpu_ptr(&softnet_data); + sd->in_napi_threaded_poll = true; - have = netpoll_poll_lock(napi); - __napi_poll(napi, &repoll); - netpoll_poll_unlock(have); + have = netpoll_poll_lock(napi); + __napi_poll(napi, &repoll); + netpoll_poll_unlock(have); - sd->in_napi_threaded_poll = false; - barrier(); + sd->in_napi_threaded_poll = false; + barrier(); - if (sd_has_rps_ipi_waiting(sd)) { - local_irq_disable(); - net_rps_action_and_irq_enable(sd); - } - skb_defer_free_flush(sd); - local_bh_enable(); + if (sd_has_rps_ipi_waiting(sd)) { + local_irq_disable(); + net_rps_action_and_irq_enable(sd); + } + skb_defer_free_flush(sd); + local_bh_enable(); - if (!repoll) - break; + if (!repoll) + break; - rcu_softirq_qs_periodic(last_qs); - cond_resched(); - } + rcu_softirq_qs_periodic(last_qs); + cond_resched(); } +} + +static int napi_threaded_poll(void *data) +{ + struct napi_struct *napi = data; + + while (!napi_thread_wait(napi)) + napi_threaded_poll_loop(napi); + return 0; } @@ -11373,7 +11421,7 @@ static int dev_cpu_dead(unsigned int oldcpu) list_del_init(&napi->poll_list); if (napi->poll == process_backlog) - napi->state = 0; + napi->state &= NAPIF_STATE_THREADED; else ____napi_schedule(sd, napi); } @@ -11381,12 +11429,14 @@ static int dev_cpu_dead(unsigned int oldcpu) raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); + if (!use_backlog_threads()) { #ifdef CONFIG_RPS - remsd = oldsd->rps_ipi_list; - oldsd->rps_ipi_list = NULL; + remsd = oldsd->rps_ipi_list; + oldsd->rps_ipi_list = NULL; #endif - /* send out pending IPI's on offline CPU */ - net_rps_send_ipi(remsd); + /* send out pending IPI's on offline CPU */ + net_rps_send_ipi(remsd); + } /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { @@ -11712,7 +11762,7 @@ static int net_page_pool_create(int cpuid) struct page_pool_params page_pool_params = { .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE, .flags = PP_FLAG_SYSTEM_POOL, - .nid = NUMA_NO_NODE, + .nid = cpu_to_mem(cpuid), }; struct page_pool *pp_ptr; @@ -11725,6 +11775,38 @@ static int net_page_pool_create(int cpuid) return 0; } +static int backlog_napi_should_run(unsigned int cpu) +{ + struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); + struct napi_struct *napi = &sd->backlog; + + return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state); +} + +static void run_backlog_napi(unsigned int cpu) +{ + struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); + + napi_threaded_poll_loop(&sd->backlog); +} + +static void backlog_napi_setup(unsigned int cpu) +{ + struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); + struct napi_struct *napi = &sd->backlog; + + napi->thread = this_cpu_read(backlog_napi); + set_bit(NAPI_STATE_THREADED, &napi->state); +} + +static struct smp_hotplug_thread backlog_threads = { + .store = &backlog_napi, + .thread_should_run = backlog_napi_should_run, + .thread_fn = run_backlog_napi, + .thread_comm = "backlog_napi/%u", + .setup = backlog_napi_setup, +}; + /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. @@ -11776,10 +11858,13 @@ static int __init net_dev_init(void) init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; + INIT_LIST_HEAD(&sd->backlog.poll_list); if (net_page_pool_create(i)) goto out; } + if (use_backlog_threads()) + smpboot_register_percpu_thread(&backlog_threads); dev_boot_phase = 0; diff --git a/net/core/filter.c b/net/core/filter.c index 8adf95765cdd..0c66e4a3fc5b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8342,8 +8342,6 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_event_output_data_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b99127712e67..17617c29be2d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -7039,8 +7039,8 @@ nodefer: __kfree_skb(skb); /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU * if we are unlucky enough (this seems very unlikely). */ - if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) - smp_call_function_single_async(cpu, &sd->defer_csd); + if (unlikely(kick)) + kick_defer_list_purge(sd, cpu); } static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index e9154ace80ff..b67454b45a49 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -89,6 +89,10 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif +HOST_CFLAGS := $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\ + $(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS))) +HOST_LDFLAGS := $(LDFLAGS) + INSTALL ?= install RM ?= rm -f @@ -178,12 +182,9 @@ ifeq ($(filter -DHAVE_LLVM_SUPPORT -DHAVE_LIBBFD_SUPPORT,$(CFLAGS)),) SRCS := $(filter-out jit_disasm.c,$(SRCS)) endif -HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\ - $(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS))) - BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool -BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o) +BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o) $(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP) OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o @@ -231,14 +232,11 @@ endif CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) -$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c - $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ - $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) - $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ + $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(HOST_LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@ diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 540c0f2c4fda..786268f1a483 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -1131,7 +1131,8 @@ static void gen_st_ops_shadow_init(struct btf *btf, struct bpf_object *obj) continue; codegen("\ \n\ - obj->struct_ops.%1$s = bpf_map__initial_value(obj->maps.%1$s, NULL);\n\ + obj->struct_ops.%1$s = (typeof(obj->struct_ops.%1$s))\n\ + bpf_map__initial_value(obj->maps.%1$s, NULL);\n\ \n\ ", ident); } diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index 00c77edb6331..9b898571b49e 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -101,7 +101,6 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) char buf[4096 / sizeof(*e) * sizeof(*e)]; struct pid_iter_bpf *skel; int err, ret, fd = -1, i; - libbpf_print_fn_t default_print; *map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); if (IS_ERR(*map)) { @@ -118,12 +117,18 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) skel->rodata->obj_type = type; - /* we don't want output polluted with libbpf errors if bpf_iter is not - * supported - */ - default_print = libbpf_set_print(libbpf_print_none); - err = pid_iter_bpf__load(skel); - libbpf_set_print(default_print); + if (!verifier_logs) { + libbpf_print_fn_t default_print; + + /* Unless debug information is on, we don't want the output to + * be polluted with libbpf errors if bpf_iter is not supported. + */ + default_print = libbpf_set_print(libbpf_print_none); + err = pid_iter_bpf__load(skel); + libbpf_set_print(default_print); + } else { + err = pid_iter_bpf__load(skel); + } if (err) { /* too bad, kernel doesn't support BPF iterators yet */ err = 0; diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index 26004f0c5a6a..7bdbcac3cf62 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -102,8 +102,8 @@ int iter(struct bpf_iter__task_file *ctx) BPF_LINK_TYPE_PERF_EVENT___local)) { struct bpf_link *link = (struct bpf_link *) file->private_data; - if (link->type == bpf_core_enum_value(enum bpf_link_type___local, - BPF_LINK_TYPE_PERF_EVENT___local)) { + if (BPF_CORE_READ(link, type) == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { e.has_bpf_cookie = true; e.bpf_cookie = get_bpf_cookie(link); } diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 7b65566f3e42..8a63a9913495 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -58,6 +58,10 @@ #define noinline #endif +#ifndef __nocf_check +#define __nocf_check __attribute__((nocf_check)) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3c42b9f1bada..9585f5345353 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1662,8 +1662,10 @@ union bpf_attr { } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ - __u64 name; - __u32 prog_fd; + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 97ec005c3c47..c9f4e04f38fe 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -785,6 +785,7 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, uprobe_multi)) return libbpf_err(-EINVAL); break; + case BPF_TRACE_RAW_TP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: @@ -1173,20 +1174,31 @@ int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info return bpf_obj_get_info_by_fd(link_fd, info, info_len); } -int bpf_raw_tracepoint_open(const char *name, int prog_fd) +int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts) { const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint); union bpf_attr attr; int fd; + if (!OPTS_VALID(opts, bpf_raw_tp_opts)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); - attr.raw_tracepoint.name = ptr_to_u64(name); attr.raw_tracepoint.prog_fd = prog_fd; + attr.raw_tracepoint.name = ptr_to_u64(OPTS_GET(opts, tp_name, NULL)); + attr.raw_tracepoint.cookie = OPTS_GET(opts, cookie, 0); fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); return libbpf_err_errno(fd); } +int bpf_raw_tracepoint_open(const char *name, int prog_fd) +{ + LIBBPF_OPTS(bpf_raw_tp_opts, opts, .tp_name = name); + + return bpf_raw_tracepoint_open_opts(prog_fd, &opts); +} + int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) { const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index df0db2f0cdb7..972e17ec0c09 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -617,6 +617,15 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); +struct bpf_raw_tp_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + const char *tp_name; + __u64 cookie; + size_t :0; +}; +#define bpf_raw_tp_opts__last_field cookie + +LIBBPF_API int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts); LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a2061fcd612d..d7d8f78f8846 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1132,8 +1132,26 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) const char *mname; mname = btf__name_by_offset(btf, member->name_off); + moff = member->offset / 8; + mdata = data + moff; + msize = btf__resolve_size(btf, member->type); + if (msize < 0) { + pr_warn("struct_ops init_kern %s: failed to resolve the size of member %s\n", + map->name, mname); + return msize; + } + kern_member = find_member_by_name(kern_btf, kern_type, mname); if (!kern_member) { + /* Skip all zeros or null fields if they are not + * presented in the kernel BTF. + */ + if (libbpf_is_mem_zeroed(mdata, msize)) { + pr_info("struct_ops %s: member %s not found in kernel, skipping it as it's set to zero\n", + map->name, mname); + continue; + } + pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", map->name, mname); return -ENOTSUP; @@ -1147,10 +1165,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) return -ENOTSUP; } - moff = member->offset / 8; kern_moff = kern_member->offset / 8; - - mdata = data + moff; kern_mdata = kern_data + kern_moff; mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id); @@ -1230,9 +1245,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) continue; } - msize = btf__resolve_size(btf, mtype_id); kern_msize = btf__resolve_size(kern_btf, kern_mtype_id); - if (msize < 0 || kern_msize < 0 || msize != kern_msize) { + if (kern_msize < 0 || msize != kern_msize) { pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n", map->name, mname, (ssize_t)msize, (ssize_t)kern_msize); @@ -7321,9 +7335,9 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL, *tmp; - int btf_fd, ret, err; bool own_log_buf = true; __u32 log_level = prog->log_level; + int ret, err; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -7347,9 +7361,8 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.prog_ifindex = prog->prog_ifindex; /* specify func_info/line_info only if kernel supports them */ - btf_fd = btf__fd(obj->btf); - if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { - load_attr.prog_btf_fd = btf_fd; + if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { + load_attr.prog_btf_fd = btf__fd(obj->btf); load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; load_attr.func_info_cnt = prog->func_info_cnt; @@ -8563,6 +8576,11 @@ int bpf_map__pin(struct bpf_map *map, const char *path) return libbpf_err(-EINVAL); } + if (map->fd < 0) { + pr_warn("map '%s': can't pin BPF map without FD (was it created?)\n", map->name); + return libbpf_err(-EINVAL); + } + if (map->pin_path) { if (path && strcmp(path, map->pin_path)) { pr_warn("map '%s' already has pin path '%s' different from '%s'\n", @@ -9298,6 +9316,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT), SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT), SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/verdict", SK_SKB, BPF_SK_SKB_VERDICT, SEC_ATTACHABLE_OPT), SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE), SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT), SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT), @@ -10307,6 +10326,11 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz, return -EINVAL; } + if (map->fd < 0) { + pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name); + return -EINVAL; + } + if (!check_value_sz) return 0; @@ -10419,8 +10443,15 @@ long libbpf_get_error(const void *ptr) int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog) { int ret; + int prog_fd = bpf_program__fd(prog); - ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL); + if (prog_fd < 0) { + pr_warn("prog '%s': can't use BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err(-EINVAL); + } + + ret = bpf_link_update(bpf_link__fd(link), prog_fd, NULL); return libbpf_err_errno(ret); } @@ -10614,7 +10645,7 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p } prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { - pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", prog->name); return libbpf_err_ptr(-EINVAL); } @@ -11338,6 +11369,13 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, if (!OPTS_VALID(opts, bpf_kprobe_multi_opts)) return libbpf_err_ptr(-EINVAL); + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + syms = OPTS_GET(opts, syms, false); addrs = OPTS_GET(opts, addrs, false); cnt = OPTS_GET(opts, cnt, false); @@ -11378,7 +11416,6 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, } link->detach = &bpf_link__detach_fd; - prog_fd = bpf_program__fd(prog); link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts); if (link_fd < 0) { err = -errno; @@ -11761,6 +11798,13 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog, if (!OPTS_VALID(opts, bpf_uprobe_multi_opts)) return libbpf_err_ptr(-EINVAL); + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + syms = OPTS_GET(opts, syms, NULL); offsets = OPTS_GET(opts, offsets, NULL); ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL); @@ -11836,7 +11880,6 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog, } link->detach = &bpf_link__detach_fd; - prog_fd = bpf_program__fd(prog); link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &lopts); if (link_fd < 0) { err = -errno; @@ -12080,7 +12123,7 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); if (bpf_program__fd(prog) < 0) { - pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", prog->name); return libbpf_err_ptr(-EINVAL); } @@ -12271,13 +12314,19 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin return libbpf_get_error(*link); } -struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, - const char *tp_name) +struct bpf_link * +bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog, + const char *tp_name, + struct bpf_raw_tracepoint_opts *opts) { + LIBBPF_OPTS(bpf_raw_tp_opts, raw_opts); char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, pfd; + if (!OPTS_VALID(opts, bpf_raw_tracepoint_opts)) + return libbpf_err_ptr(-EINVAL); + prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach before loaded\n", prog->name); @@ -12289,7 +12338,9 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; - pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); + raw_opts.tp_name = tp_name; + raw_opts.cookie = OPTS_GET(opts, cookie, 0); + pfd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_opts); if (pfd < 0) { pfd = -errno; free(link); @@ -12301,6 +12352,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return link; } +struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, + const char *tp_name) +{ + return bpf_program__attach_raw_tracepoint_opts(prog, tp_name, NULL); +} + static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { static const char *const prefixes[] = { @@ -12662,6 +12719,12 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog) if (!prog->sec_def || !prog->sec_def->prog_attach_fn) return libbpf_err_ptr(-EOPNOTSUPP); + if (bpf_program__fd(prog) < 0) { + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link); if (err) return libbpf_err_ptr(err); @@ -12702,8 +12765,13 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) __u32 zero = 0; int err, fd; - if (!bpf_map__is_struct_ops(map) || map->fd == -1) + if (!bpf_map__is_struct_ops(map)) + return libbpf_err_ptr(-EINVAL); + + if (map->fd < 0) { + pr_warn("map '%s': can't attach BPF map without FD (was it created?)\n", map->name); return libbpf_err_ptr(-EINVAL); + } link = calloc(1, sizeof(*link)); if (!link) @@ -12751,9 +12819,14 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map) __u32 zero = 0; int err; - if (!bpf_map__is_struct_ops(map) || !map_is_created(map)) + if (!bpf_map__is_struct_ops(map)) return -EINVAL; + if (map->fd < 0) { + pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name); + return -EINVAL; + } + st_ops_link = container_of(link, struct bpf_link_struct_ops, link); /* Ensure the type of a link is correct */ if (st_ops_link->map_fd < 0) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 7b510761f545..f88ab50c0229 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -760,9 +760,20 @@ bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_name, const struct bpf_tracepoint_opts *opts); +struct bpf_raw_tracepoint_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u64 cookie; + size_t :0; +}; +#define bpf_raw_tracepoint_opts__last_field cookie + LIBBPF_API struct bpf_link * bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog, + const char *tp_name, + struct bpf_raw_tracepoint_opts *opts); struct bpf_trace_opts { /* size of this struct, for forward/backward compatibility */ diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 86804fd90dd1..51732ecb1385 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -410,6 +410,8 @@ LIBBPF_1.3.0 { LIBBPF_1.4.0 { global: + bpf_program__attach_raw_tracepoint_opts; + bpf_raw_tracepoint_open_opts; bpf_token_create; btf__new_split; btf_ext__raw_data; diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c index b36de42ee4d9..e2ff8ea1cb79 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c @@ -186,7 +186,7 @@ static void *task_producer(void *input) for (i = 0; i < batch_sz; i++) { if (!pthd_results[i]) - pthread_join(pthds[i], NULL);; + pthread_join(pthds[i], NULL); } } diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index ace0d1011a8e..d66eddacd642 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -1,15 +1,47 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ +#define _GNU_SOURCE +#include <unistd.h> #include "bench.h" #include "trigger_bench.skel.h" #include "trace_helpers.h" +/* adjust slot shift in inc_hits() if changing */ +#define MAX_BUCKETS 256 + +#pragma GCC diagnostic ignored "-Wattributes" + /* BPF triggering benchmarks */ static struct trigger_ctx { struct trigger_bench *skel; } ctx; -static struct counter base_hits; +static struct counter base_hits[MAX_BUCKETS]; + +static __always_inline void inc_counter(struct counter *counters) +{ + static __thread int tid = 0; + unsigned slot; + + if (unlikely(tid == 0)) + tid = syscall(SYS_gettid); + + /* multiplicative hashing, it's fast */ + slot = 2654435769U * tid; + slot >>= 24; + + atomic_inc(&base_hits[slot].value); /* use highest byte as an index */ +} + +static long sum_and_reset_counters(struct counter *counters) +{ + int i; + long sum = 0; + + for (i = 0; i < MAX_BUCKETS; i++) + sum += atomic_swap(&counters[i].value, 0); + return sum; +} static void trigger_validate(void) { @@ -23,14 +55,14 @@ static void *trigger_base_producer(void *input) { while (true) { (void)syscall(__NR_getpgid); - atomic_inc(&base_hits.value); + inc_counter(base_hits); } return NULL; } static void trigger_base_measure(struct bench_res *res) { - res->hits = atomic_swap(&base_hits.value, 0); + res->hits = sum_and_reset_counters(base_hits); } static void *trigger_producer(void *input) @@ -42,7 +74,7 @@ static void *trigger_producer(void *input) static void trigger_measure(struct bench_res *res) { - res->hits = atomic_swap(&ctx.skel->bss->hits, 0); + res->hits = sum_and_reset_counters(ctx.skel->bss->hits); } static void setup_ctx(void) @@ -137,7 +169,7 @@ static void trigger_fmodret_setup(void) * GCC doesn't generate stack setup preample for these functions due to them * having no input arguments and doing nothing in the body. */ -__weak void uprobe_target_nop(void) +__nocf_check __weak void uprobe_target_nop(void) { asm volatile ("nop"); } @@ -146,7 +178,7 @@ __weak void opaque_noop_func(void) { } -__weak int uprobe_target_push(void) +__nocf_check __weak int uprobe_target_push(void) { /* overhead of function call is negligible compared to uprobe * triggering, so this shouldn't affect benchmark results much @@ -155,7 +187,7 @@ __weak int uprobe_target_push(void) return 1; } -__weak void uprobe_target_ret(void) +__nocf_check __weak void uprobe_target_ret(void) { asm volatile (""); } @@ -164,7 +196,7 @@ static void *uprobe_base_producer(void *input) { while (true) { uprobe_target_nop(); - atomic_inc(&base_hits.value); + inc_counter(base_hits); } return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 1454cebc262b..4407ea428e77 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -573,6 +573,115 @@ cleanup: close(lsm_fd); } +static void tp_btf_subtest(struct test_bpf_cookie *skel) +{ + __u64 cookie; + int prog_fd, link_fd = -1; + struct bpf_link *link = NULL; + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts); + LIBBPF_OPTS(bpf_trace_opts, trace_opts); + + /* There are three different ways to attach tp_btf (BTF-aware raw + * tracepoint) programs. Let's test all of them. + */ + prog_fd = bpf_program__fd(skel->progs.handle_tp_btf); + + /* low-level BPF_RAW_TRACEPOINT_OPEN command wrapper */ + skel->bss->tp_btf_res = 0; + + raw_tp_opts.cookie = cookie = 0x11000000000000L; + link_fd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_tp_opts); + if (!ASSERT_GE(link_fd, 0, "bpf_raw_tracepoint_open_opts")) + goto cleanup; + + usleep(1); /* trigger */ + close(link_fd); /* detach */ + link_fd = -1; + + ASSERT_EQ(skel->bss->tp_btf_res, cookie, "raw_tp_open_res"); + + /* low-level generic bpf_link_create() API */ + skel->bss->tp_btf_res = 0; + + link_opts.tracing.cookie = cookie = 0x22000000000000L; + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_RAW_TP, &link_opts); + if (!ASSERT_GE(link_fd, 0, "bpf_link_create")) + goto cleanup; + + usleep(1); /* trigger */ + close(link_fd); /* detach */ + link_fd = -1; + + ASSERT_EQ(skel->bss->tp_btf_res, cookie, "link_create_res"); + + /* high-level bpf_link-based bpf_program__attach_trace_opts() API */ + skel->bss->tp_btf_res = 0; + + trace_opts.cookie = cookie = 0x33000000000000L; + link = bpf_program__attach_trace_opts(skel->progs.handle_tp_btf, &trace_opts); + if (!ASSERT_OK_PTR(link, "attach_trace_opts")) + goto cleanup; + + usleep(1); /* trigger */ + bpf_link__destroy(link); /* detach */ + link = NULL; + + ASSERT_EQ(skel->bss->tp_btf_res, cookie, "attach_trace_opts_res"); + +cleanup: + if (link_fd >= 0) + close(link_fd); + bpf_link__destroy(link); +} + +static void raw_tp_subtest(struct test_bpf_cookie *skel) +{ + __u64 cookie; + int prog_fd, link_fd = -1; + struct bpf_link *link = NULL; + LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts); + LIBBPF_OPTS(bpf_raw_tracepoint_opts, opts); + + /* There are two different ways to attach raw_tp programs */ + prog_fd = bpf_program__fd(skel->progs.handle_raw_tp); + + /* low-level BPF_RAW_TRACEPOINT_OPEN command wrapper */ + skel->bss->raw_tp_res = 0; + + raw_tp_opts.tp_name = "sys_enter"; + raw_tp_opts.cookie = cookie = 0x55000000000000L; + link_fd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_tp_opts); + if (!ASSERT_GE(link_fd, 0, "bpf_raw_tracepoint_open_opts")) + goto cleanup; + + usleep(1); /* trigger */ + close(link_fd); /* detach */ + link_fd = -1; + + ASSERT_EQ(skel->bss->raw_tp_res, cookie, "raw_tp_open_res"); + + /* high-level bpf_link-based bpf_program__attach_raw_tracepoint_opts() API */ + skel->bss->raw_tp_res = 0; + + opts.cookie = cookie = 0x66000000000000L; + link = bpf_program__attach_raw_tracepoint_opts(skel->progs.handle_raw_tp, + "sys_enter", &opts); + if (!ASSERT_OK_PTR(link, "attach_raw_tp_opts")) + goto cleanup; + + usleep(1); /* trigger */ + bpf_link__destroy(link); /* detach */ + link = NULL; + + ASSERT_EQ(skel->bss->raw_tp_res, cookie, "attach_raw_tp_opts_res"); + +cleanup: + if (link_fd >= 0) + close(link_fd); + bpf_link__destroy(link); +} + void test_bpf_cookie(void) { struct test_bpf_cookie *skel; @@ -601,6 +710,9 @@ void test_bpf_cookie(void) tracing_subtest(skel); if (test__start_subtest("lsm")) lsm_subtest(skel); - + if (test__start_subtest("tp_btf")) + tp_btf_subtest(skel); + if (test__start_subtest("raw_tp")) + raw_tp_subtest(skel); test_bpf_cookie__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index a88e6e07e4f5..94cb22b01482 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -89,7 +89,7 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) WRITE_ONCE(stop, 0); - lfd = socket(AF_INET6, SOCK_STREAM, 0); + lfd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); if (!ASSERT_NEQ(lfd, -1, "socket")) return; @@ -103,21 +103,10 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) settimeo(lfd, 0) || settimeo(fd, 0)) goto done; - /* bind, listen and start server thread to accept */ - sa6.sin6_family = AF_INET6; - sa6.sin6_addr = in6addr_loopback; - err = bind(lfd, (struct sockaddr *)&sa6, addrlen); - if (!ASSERT_NEQ(err, -1, "bind")) - goto done; - err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen); if (!ASSERT_NEQ(err, -1, "getsockname")) goto done; - err = listen(lfd, 1); - if (!ASSERT_NEQ(err, -1, "listen")) - goto done; - if (sk_stg_map) { err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd, &expected_stg, BPF_NOEXIST); diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index a8b53b8736f0..f66ceccd7029 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -25,7 +25,7 @@ static void test_lookup_update(void) int map1_fd, map2_fd, map3_fd, map4_fd, map5_fd, map1_id, map2_id; int outer_arr_fd, outer_hash_fd, outer_arr_dyn_fd; struct test_btf_map_in_map *skel; - int err, key = 0, val, i, fd; + int err, key = 0, val, i; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -102,30 +102,6 @@ static void test_lookup_update(void) CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); - test_btf_map_in_map__destroy(skel); - skel = NULL; - - /* we need to either wait for or force synchronize_rcu(), before - * checking for "still exists" condition, otherwise map could still be - * resolvable by ID, causing false positives. - * - * Older kernels (5.8 and earlier) freed map only after two - * synchronize_rcu()s, so trigger two, to be entirely sure. - */ - CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); - CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); - - fd = bpf_map_get_fd_by_id(map1_id); - if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { - close(fd); - goto cleanup; - } - fd = bpf_map_get_fd_by_id(map2_id); - if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { - close(fd); - goto cleanup; - } - cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c index 24d493482ffc..e72d75d6baa7 100644 --- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c +++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c @@ -12,77 +12,229 @@ #include <sys/wait.h> #include <sys/mount.h> #include <sys/fcntl.h> +#include "network_helpers.h" #define STACK_SIZE (1024 * 1024) static char child_stack[STACK_SIZE]; -static int test_current_pid_tgid(void *args) +static int get_pid_tgid(pid_t *pid, pid_t *tgid, + struct test_ns_current_pid_tgid__bss *bss) { - struct test_ns_current_pid_tgid__bss *bss; - struct test_ns_current_pid_tgid *skel; - int err = -1, duration = 0; - pid_t tgid, pid; struct stat st; + int err; - skel = test_ns_current_pid_tgid__open_and_load(); - if (CHECK(!skel, "skel_open_load", "failed to load skeleton\n")) - goto cleanup; - - pid = syscall(SYS_gettid); - tgid = getpid(); + *pid = syscall(SYS_gettid); + *tgid = getpid(); err = stat("/proc/self/ns/pid", &st); - if (CHECK(err, "stat", "failed /proc/self/ns/pid: %d\n", err)) - goto cleanup; + if (!ASSERT_OK(err, "stat /proc/self/ns/pid")) + return err; - bss = skel->bss; bss->dev = st.st_dev; bss->ino = st.st_ino; bss->user_pid = 0; bss->user_tgid = 0; + return 0; +} + +static int test_current_pid_tgid_tp(void *args) +{ + struct test_ns_current_pid_tgid__bss *bss; + struct test_ns_current_pid_tgid *skel; + int ret = -1, err; + pid_t tgid, pid; + + skel = test_ns_current_pid_tgid__open(); + if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open")) + return ret; + + bpf_program__set_autoload(skel->progs.tp_handler, true); + + err = test_ns_current_pid_tgid__load(skel); + if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load")) + goto cleanup; + + bss = skel->bss; + if (get_pid_tgid(&pid, &tgid, bss)) + goto cleanup; err = test_ns_current_pid_tgid__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "test_ns_current_pid_tgid__attach")) goto cleanup; /* trigger tracepoint */ usleep(1); - ASSERT_EQ(bss->user_pid, pid, "pid"); - ASSERT_EQ(bss->user_tgid, tgid, "tgid"); - err = 0; + if (!ASSERT_EQ(bss->user_pid, pid, "pid")) + goto cleanup; + if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid")) + goto cleanup; + ret = 0; + +cleanup: + test_ns_current_pid_tgid__destroy(skel); + return ret; +} + +static int test_current_pid_tgid_cgrp(void *args) +{ + struct test_ns_current_pid_tgid__bss *bss; + struct test_ns_current_pid_tgid *skel; + int server_fd = -1, ret = -1, err; + int cgroup_fd = *(int *)args; + pid_t tgid, pid; + + skel = test_ns_current_pid_tgid__open(); + if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open")) + return ret; + + bpf_program__set_autoload(skel->progs.cgroup_bind4, true); + + err = test_ns_current_pid_tgid__load(skel); + if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load")) + goto cleanup; + + bss = skel->bss; + if (get_pid_tgid(&pid, &tgid, bss)) + goto cleanup; + + skel->links.cgroup_bind4 = bpf_program__attach_cgroup( + skel->progs.cgroup_bind4, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.cgroup_bind4, "bpf_program__attach_cgroup")) + goto cleanup; + + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(server_fd, 0, "start_server")) + goto cleanup; + + if (!ASSERT_EQ(bss->user_pid, pid, "pid")) + goto cleanup; + if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid")) + goto cleanup; + ret = 0; cleanup: - test_ns_current_pid_tgid__destroy(skel); + if (server_fd >= 0) + close(server_fd); + test_ns_current_pid_tgid__destroy(skel); + return ret; +} + +static int test_current_pid_tgid_sk_msg(void *args) +{ + int verdict, map, server_fd = -1, client_fd = -1; + struct test_ns_current_pid_tgid__bss *bss; + static const char send_msg[] = "message"; + struct test_ns_current_pid_tgid *skel; + int ret = -1, err, key = 0; + pid_t tgid, pid; + + skel = test_ns_current_pid_tgid__open(); + if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open")) + return ret; + + bpf_program__set_autoload(skel->progs.sk_msg, true); + + err = test_ns_current_pid_tgid__load(skel); + if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load")) + goto cleanup; + + bss = skel->bss; + if (get_pid_tgid(&pid, &tgid, skel->bss)) + goto cleanup; + + verdict = bpf_program__fd(skel->progs.sk_msg); + map = bpf_map__fd(skel->maps.sock_map); + err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0); + if (!ASSERT_OK(err, "prog_attach")) + goto cleanup; + + server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + if (!ASSERT_GE(server_fd, 0, "start_server")) + goto cleanup; - return err; + client_fd = connect_to_fd(server_fd, 0); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto cleanup; + + err = bpf_map_update_elem(map, &key, &client_fd, BPF_ANY); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto cleanup; + + err = send(client_fd, send_msg, sizeof(send_msg), 0); + if (!ASSERT_EQ(err, sizeof(send_msg), "send(msg)")) + goto cleanup; + + if (!ASSERT_EQ(bss->user_pid, pid, "pid")) + goto cleanup; + if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid")) + goto cleanup; + ret = 0; + +cleanup: + if (server_fd >= 0) + close(server_fd); + if (client_fd >= 0) + close(client_fd); + test_ns_current_pid_tgid__destroy(skel); + return ret; } -static void test_ns_current_pid_tgid_new_ns(void) +static void test_ns_current_pid_tgid_new_ns(int (*fn)(void *), void *arg) { - int wstatus, duration = 0; + int wstatus; pid_t cpid; /* Create a process in a new namespace, this process * will be the init process of this new namespace hence will be pid 1. */ - cpid = clone(test_current_pid_tgid, child_stack + STACK_SIZE, - CLONE_NEWPID | SIGCHLD, NULL); + cpid = clone(fn, child_stack + STACK_SIZE, + CLONE_NEWPID | SIGCHLD, arg); - if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno))) + if (!ASSERT_NEQ(cpid, -1, "clone")) return; - if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", "%s\n", strerror(errno))) + if (!ASSERT_NEQ(waitpid(cpid, &wstatus, 0), -1, "waitpid")) return; - if (CHECK(WEXITSTATUS(wstatus) != 0, "newns_pidtgid", "failed")) + if (!ASSERT_OK(WEXITSTATUS(wstatus), "newns_pidtgid")) return; } +static void test_in_netns(int (*fn)(void *), void *arg) +{ + struct nstoken *nstoken = NULL; + + SYS(cleanup, "ip netns add ns_current_pid_tgid"); + SYS(cleanup, "ip -net ns_current_pid_tgid link set dev lo up"); + + nstoken = open_netns("ns_current_pid_tgid"); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto cleanup; + + test_ns_current_pid_tgid_new_ns(fn, arg); + +cleanup: + if (nstoken) + close_netns(nstoken); + SYS_NOFAIL("ip netns del ns_current_pid_tgid"); +} + /* TODO: use a different tracepoint */ void serial_test_ns_current_pid_tgid(void) { - if (test__start_subtest("ns_current_pid_tgid_root_ns")) - test_current_pid_tgid(NULL); - if (test__start_subtest("ns_current_pid_tgid_new_ns")) - test_ns_current_pid_tgid_new_ns(); + if (test__start_subtest("root_ns_tp")) + test_current_pid_tgid_tp(NULL); + if (test__start_subtest("new_ns_tp")) + test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_tp, NULL); + if (test__start_subtest("new_ns_cgrp")) { + int cgroup_fd = -1; + + cgroup_fd = test__join_cgroup("/sock_addr"); + if (ASSERT_GE(cgroup_fd, 0, "join_cgroup")) { + test_in_netns(test_current_pid_tgid_cgrp, &cgroup_fd); + close(cgroup_fd); + } + } + if (test__start_subtest("new_ns_sk_msg")) + test_in_netns(test_current_pid_tgid_sk_msg, NULL); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c index ee5372c7f2c7..098776d00ab4 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c @@ -93,9 +93,56 @@ cleanup: struct_ops_module__destroy(skel); } +static void test_struct_ops_not_zeroed(void) +{ + struct struct_ops_module *skel; + int err; + + /* zeroed is 0, and zeroed_op is null */ + skel = struct_ops_module__open(); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open")) + return; + + err = struct_ops_module__load(skel); + ASSERT_OK(err, "struct_ops_module_load"); + + struct_ops_module__destroy(skel); + + /* zeroed is not 0 */ + skel = struct_ops_module__open(); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_not_zeroed")) + return; + + /* libbpf should reject the testmod_zeroed since struct + * bpf_testmod_ops in the kernel has no "zeroed" field and the + * value of "zeroed" is non-zero. + */ + skel->struct_ops.testmod_zeroed->zeroed = 0xdeadbeef; + err = struct_ops_module__load(skel); + ASSERT_ERR(err, "struct_ops_module_load_not_zeroed"); + + struct_ops_module__destroy(skel); + + /* zeroed_op is not null */ + skel = struct_ops_module__open(); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_not_zeroed_op")) + return; + + /* libbpf should reject the testmod_zeroed since the value of its + * "zeroed_op" is not null. + */ + skel->struct_ops.testmod_zeroed->zeroed_op = skel->progs.test_3; + err = struct_ops_module__load(skel); + ASSERT_ERR(err, "struct_ops_module_load_not_zeroed_op"); + + struct_ops_module__destroy(skel); +} + void serial_test_struct_ops_module(void) { if (test__start_subtest("test_struct_ops_load")) test_struct_ops_load(); + if (test__start_subtest("test_struct_ops_not_zeroed")) + test_struct_ops_not_zeroed(); } diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 3db416606f2f..fe65e0952a1e 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -673,7 +673,7 @@ static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul) static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n) { - int *t, i, sum = 0;; + int *t, i, sum = 0; while ((t = bpf_iter_num_next(it))) { i = *t; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c index 026cabfa7f1f..86e1e50c5531 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_module.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c @@ -23,7 +23,7 @@ void BPF_PROG(test_2, int a, int b) test_2_result = a + b; } -SEC("struct_ops/test_3") +SEC("?struct_ops/test_3") int BPF_PROG(test_3, int a, int b) { test_2_result = a + b + 3; @@ -54,3 +54,17 @@ struct bpf_testmod_ops___v2 testmod_2 = { .test_1 = (void *)test_1, .test_2 = (void *)test_2_v2, }; + +struct bpf_testmod_ops___zeroed { + int (*test_1)(void); + void (*test_2)(int a, int b); + int (*test_maybe_null)(int dummy, struct task_struct *task); + void (*zeroed_op)(int a, int b); + int zeroed; +}; + +SEC(".struct_ops.link") +struct bpf_testmod_ops___zeroed testmod_zeroed = { + .test_1 = (void *)test_1, + .test_2 = (void *)test_2_v2, +}; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c index 5a3a80f751c4..c83142b55f47 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c @@ -15,6 +15,8 @@ __u64 uprobe_res; __u64 uretprobe_res; __u64 tp_res; __u64 pe_res; +__u64 raw_tp_res; +__u64 tp_btf_res; __u64 fentry_res; __u64 fexit_res; __u64 fmod_ret_res; @@ -87,6 +89,20 @@ int handle_pe(struct pt_regs *ctx) return 0; } +SEC("raw_tp/sys_enter") +int handle_raw_tp(void *ctx) +{ + update(ctx, &raw_tp_res); + return 0; +} + +SEC("tp_btf/sys_enter") +int handle_tp_btf(void *ctx) +{ + update(ctx, &tp_btf_res); + return 0; +} + SEC("fentry/bpf_fentry_test1") int BPF_PROG(fentry_test1, int a) { diff --git a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c index 0763d49f9c42..386315afad65 100644 --- a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c +++ b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c @@ -5,23 +5,48 @@ #include <stdint.h> #include <bpf/bpf_helpers.h> +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u32); +} sock_map SEC(".maps"); + __u64 user_pid = 0; __u64 user_tgid = 0; __u64 dev = 0; __u64 ino = 0; -SEC("tracepoint/syscalls/sys_enter_nanosleep") -int handler(const void *ctx) +static void get_pid_tgid(void) { struct bpf_pidns_info nsdata; if (bpf_get_ns_current_pid_tgid(dev, ino, &nsdata, sizeof(struct bpf_pidns_info))) - return 0; + return; user_pid = nsdata.pid; user_tgid = nsdata.tgid; +} +SEC("?tracepoint/syscalls/sys_enter_nanosleep") +int tp_handler(const void *ctx) +{ + get_pid_tgid(); return 0; } +SEC("?cgroup/bind4") +int cgroup_bind4(struct bpf_sock_addr *ctx) +{ + get_pid_tgid(); + return 1; +} + +SEC("?sk_msg") +int sk_msg(struct sk_msg_md *msg) +{ + get_pid_tgid(); + return SK_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 5fda43901033..42ec202015ed 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -9,12 +9,27 @@ char _license[] SEC("license") = "GPL"; -long hits = 0; +#define CPU_MASK 255 +#define MAX_CPUS (CPU_MASK + 1) /* should match MAX_BUCKETS in benchs/bench_trigger.c */ + +/* matches struct counter in bench.h */ +struct counter { + long value; +} __attribute__((aligned(128))); + +struct counter hits[MAX_CPUS]; + +static __always_inline void inc_counter(void) +{ + int cpu = bpf_get_smp_processor_id(); + + __sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1); +} SEC("tp/syscalls/sys_enter_getpgid") int bench_trigger_tp(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } @@ -22,69 +37,69 @@ SEC("raw_tp/sys_enter") int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id) { if (id == __NR_getpgid) - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("kprobe/" SYS_PREFIX "sys_getpgid") int bench_trigger_kprobe(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("kretprobe/" SYS_PREFIX "sys_getpgid") int bench_trigger_kretprobe(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("kprobe.multi/" SYS_PREFIX "sys_getpgid") int bench_trigger_kprobe_multi(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("kretprobe.multi/" SYS_PREFIX "sys_getpgid") int bench_trigger_kretprobe_multi(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("fexit/" SYS_PREFIX "sys_getpgid") int bench_trigger_fexit(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("fentry.s/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry_sleep(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } SEC("fmod_ret/" SYS_PREFIX "sys_getpgid") int bench_trigger_fmodret(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return -22; } SEC("uprobe") int bench_trigger_uprobe(void *ctx) { - __sync_add_and_fetch(&hits, 1); + inc_counter(); return 0; } diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index f4936834f76f..dde0bb16e782 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -7,6 +7,7 @@ #include <bpf/bpf.h> #include <bpf/btf.h> #include "test_core_extern.skel.h" +#include "struct_ops_module.skel.h" template <typename T> class Skeleton { @@ -98,6 +99,7 @@ int main(int argc, char *argv[]) { struct btf_dump_opts opts = { }; struct test_core_extern *skel; + struct struct_ops_module *skel2; struct btf *btf; int fd; @@ -118,6 +120,9 @@ int main(int argc, char *argv[]) skel = test_core_extern__open_and_load(); test_core_extern__destroy(skel); + skel2 = struct_ops_module__open_and_load(); + struct_ops_module__destroy(skel2); + fd = bpf_enable_stats(BPF_STATS_RUN_TIME); if (fd < 0) std::cout << "FAILED to enable stats: " << fd << std::endl; diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 910044f08908..7989ec608454 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -72,7 +72,6 @@ cleanup() { server_listen() { ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" & server_pid=$! - sleep 0.2 } client_connect() { @@ -93,6 +92,16 @@ verify_data() { fi } +wait_for_port() { + for i in $(seq 20); do + if ip netns exec "${ns2}" ss ${2:--4}OHntl | grep -q "$1"; then + return 0 + fi + sleep 0.1 + done + return 1 +} + set -e # no arguments: automated test, run all @@ -193,6 +202,7 @@ setup # basic communication works echo "test basic connectivity" server_listen +wait_for_port ${port} ${netcat_opt} client_connect verify_data @@ -204,6 +214,7 @@ ip netns exec "${ns1}" tc filter add dev veth1 egress \ section "encap_${tuntype}_${mac}" echo "test bpf encap without decap (expect failure)" server_listen +wait_for_port ${port} ${netcat_opt} ! client_connect if [[ "$tuntype" =~ "udp" ]]; then |