diff options
63 files changed, 4208 insertions, 596 deletions
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 6243af0ab0255..dccae03192045 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -465,7 +465,7 @@ static int nfp_bpf_init(struct nfp_app *app) app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf); } - bpf->bpf_dev = bpf_offload_dev_create(); + bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops); err = PTR_ERR_OR_ZERO(bpf->bpf_dev); if (err) goto err_free_neutral_maps; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 7f591d71ab28d..941277936475c 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -509,7 +509,11 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt); int nfp_bpf_jit(struct nfp_prog *prog); bool nfp_bpf_supported_opcode(u8 code); -extern const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops; +int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, + int prev_insn_idx); +int nfp_bpf_finalize(struct bpf_verifier_env *env); + +extern const struct bpf_prog_offload_ops nfp_bpf_dev_ops; struct netdev_bpf; struct nfp_app; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index ba8ceedcf6a28..f0283854fade4 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -33,9 +33,6 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog, struct nfp_bpf_neutral_map *record; int err; - /* Map record paths are entered via ndo, update side is protected. */ - ASSERT_RTNL(); - /* Reuse path - other offloaded program is already tracking this map. */ record = rhashtable_lookup_fast(&bpf->maps_neutral, &map->id, nfp_bpf_maps_neutral_params); @@ -84,8 +81,6 @@ nfp_map_ptrs_forget(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog) bool freed = false; int i; - ASSERT_RTNL(); - for (i = 0; i < nfp_prog->map_records_cnt; i++) { if (--nfp_prog->map_records[i]->count) { nfp_prog->map_records[i] = NULL; @@ -187,11 +182,10 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog) kfree(nfp_prog); } -static int -nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn, - struct netdev_bpf *bpf) +static int nfp_bpf_verifier_prep(struct bpf_prog *prog) { - struct bpf_prog *prog = bpf->verifier.prog; + struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev); + struct nfp_app *app = nn->app; struct nfp_prog *nfp_prog; int ret; @@ -209,7 +203,6 @@ nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn, goto err_free; nfp_prog->verifier_meta = nfp_prog_first_meta(nfp_prog); - bpf->verifier.ops = &nfp_bpf_analyzer_ops; return 0; @@ -219,8 +212,9 @@ err_free: return ret; } -static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog) +static int nfp_bpf_translate(struct bpf_prog *prog) { + struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev); struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv; unsigned int max_instr; int err; @@ -242,15 +236,13 @@ static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog) return nfp_map_ptrs_record(nfp_prog->bpf, nfp_prog, prog); } -static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog) +static void nfp_bpf_destroy(struct bpf_prog *prog) { struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv; kvfree(nfp_prog->prog); nfp_map_ptrs_forget(nfp_prog->bpf, nfp_prog); nfp_prog_free(nfp_prog); - - return 0; } /* Atomic engine requires values to be in big endian, we need to byte swap @@ -422,12 +414,6 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap) int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf) { switch (bpf->command) { - case BPF_OFFLOAD_VERIFIER_PREP: - return nfp_bpf_verifier_prep(app, nn, bpf); - case BPF_OFFLOAD_TRANSLATE: - return nfp_bpf_translate(nn, bpf->offload.prog); - case BPF_OFFLOAD_DESTROY: - return nfp_bpf_destroy(nn, bpf->offload.prog); case BPF_OFFLOAD_MAP_ALLOC: return nfp_bpf_map_alloc(app->priv, bpf->offmap); case BPF_OFFLOAD_MAP_FREE: @@ -489,14 +475,15 @@ nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv; - unsigned int max_mtu, max_stack, max_prog_len; + unsigned int fw_mtu, pkt_off, max_stack, max_prog_len; dma_addr_t dma_addr; void *img; int err; - max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; - if (max_mtu < nn->dp.netdev->mtu) { - NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with MTU larger than HW packet split boundary"); + fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; + pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu); + if (fw_mtu < pkt_off) { + NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary"); return -EOPNOTSUPP; } @@ -600,3 +587,11 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog, return 0; } + +const struct bpf_prog_offload_ops nfp_bpf_dev_ops = { + .insn_hook = nfp_verify_insn, + .finalize = nfp_bpf_finalize, + .prepare = nfp_bpf_verifier_prep, + .translate = nfp_bpf_translate, + .destroy = nfp_bpf_destroy, +}; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index 99f977bfd8ccd..337bb862ec1dd 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -623,8 +623,8 @@ nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, return 0; } -static int -nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) +int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, + int prev_insn_idx) { struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv; struct nfp_insn_meta *meta = nfp_prog->verifier_meta; @@ -745,7 +745,7 @@ continue_subprog: goto continue_subprog; } -static int nfp_bpf_finalize(struct bpf_verifier_env *env) +int nfp_bpf_finalize(struct bpf_verifier_env *env) { struct bpf_subprog_info *info; struct nfp_prog *nfp_prog; @@ -788,8 +788,3 @@ static int nfp_bpf_finalize(struct bpf_verifier_env *env) return 0; } - -const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = { - .insn_hook = nfp_verify_insn, - .finalize = nfp_bpf_finalize, -}; diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index cb3518474f0e4..a1b29173ca1ce 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -91,11 +91,6 @@ static int nsim_bpf_finalize(struct bpf_verifier_env *env) return 0; } -static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = { - .insn_hook = nsim_bpf_verify_insn, - .finalize = nsim_bpf_finalize, -}; - static bool nsim_xdp_offload_active(struct netdevsim *ns) { return ns->xdp_hw.prog; @@ -263,6 +258,24 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog) return 0; } +static int nsim_bpf_verifier_prep(struct bpf_prog *prog) +{ + struct netdevsim *ns = netdev_priv(prog->aux->offload->netdev); + + if (!ns->bpf_bind_accept) + return -EOPNOTSUPP; + + return nsim_bpf_create_prog(ns, prog); +} + +static int nsim_bpf_translate(struct bpf_prog *prog) +{ + struct nsim_bpf_bound_prog *state = prog->aux->offload->dev_priv; + + state->state = "xlated"; + return 0; +} + static void nsim_bpf_destroy_prog(struct bpf_prog *prog) { struct nsim_bpf_bound_prog *state; @@ -275,6 +288,14 @@ static void nsim_bpf_destroy_prog(struct bpf_prog *prog) kfree(state); } +static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = { + .insn_hook = nsim_bpf_verify_insn, + .finalize = nsim_bpf_finalize, + .prepare = nsim_bpf_verifier_prep, + .translate = nsim_bpf_translate, + .destroy = nsim_bpf_destroy_prog, +}; + static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf) { if (bpf->prog && bpf->prog->aux->offload) { @@ -533,30 +554,11 @@ static void nsim_bpf_map_free(struct bpf_offloaded_map *offmap) int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) { struct netdevsim *ns = netdev_priv(dev); - struct nsim_bpf_bound_prog *state; int err; ASSERT_RTNL(); switch (bpf->command) { - case BPF_OFFLOAD_VERIFIER_PREP: - if (!ns->bpf_bind_accept) - return -EOPNOTSUPP; - - err = nsim_bpf_create_prog(ns, bpf->verifier.prog); - if (err) - return err; - - bpf->verifier.ops = &nsim_bpf_analyzer_ops; - return 0; - case BPF_OFFLOAD_TRANSLATE: - state = bpf->offload.prog->aux->offload->dev_priv; - - state->state = "xlated"; - return 0; - case BPF_OFFLOAD_DESTROY: - nsim_bpf_destroy_prog(bpf->offload.prog); - return 0; case XDP_QUERY_PROG: return xdp_attachment_query(&ns->xdp, bpf); case XDP_QUERY_PROG_HW: @@ -599,7 +601,7 @@ int nsim_bpf_init(struct netdevsim *ns) if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs)) return -ENOMEM; - ns->sdev->bpf_dev = bpf_offload_dev_create(); + ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops); err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev); if (err) return err; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 33014ae73103f..7f0e225bf630b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -268,15 +268,18 @@ struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); + int (*prepare)(struct bpf_prog *prog); + int (*translate)(struct bpf_prog *prog); + void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; + struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; - const struct bpf_prog_offload_ops *dev_ops; void *jited_image; u32 jited_len; }; @@ -293,6 +296,7 @@ struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; + u32 max_pkt_offset; u32 stack_depth; u32 id; u32 func_cnt; @@ -312,6 +316,8 @@ struct bpf_prog_aux { void *security; #endif struct bpf_prog_offload *offload; + struct btf *btf; + u32 type_id; /* type id for this prog/func */ union { struct work_struct work; struct rcu_head rcu; @@ -523,7 +529,8 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, + union bpf_attr __user *uattr); void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ @@ -691,7 +698,8 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); -struct bpf_offload_dev *bpf_offload_dev_create(void); +struct bpf_offload_dev * +bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d93e89761a8b4..204382f46fd88 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -204,6 +204,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u16 stack_depth; /* max. stack depth used by this function */ + u32 type_id; /* btf type_id for this subprog */ }; /* single container for all structs @@ -245,7 +246,7 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) return cur_func(env)->regs; } -int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); +int bpf_prog_offload_verifier_prep(struct bpf_prog *prog); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int bpf_prog_offload_finalize(struct bpf_verifier_env *env); diff --git a/include/linux/btf.h b/include/linux/btf.h index e076c4697049d..8c2199b5d2503 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -47,4 +47,20 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, int btf_get_fd_by_id(u32 id); u32 btf_id(const struct btf *btf); +#ifdef CONFIG_BPF_SYSCALL +const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); +const char *btf_name_by_offset(const struct btf *btf, u32 offset); +#else +static inline const struct btf_type *btf_type_by_id(const struct btf *btf, + u32 type_id) +{ + return NULL; +} +static inline const char *btf_name_by_offset(const struct btf *btf, + u32 offset) +{ + return NULL; +} +#endif + #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index de629b706d1d7..cc17f5f32fbb6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -668,24 +668,10 @@ static inline u32 bpf_ctx_off_adjust_machine(u32 size) return size; } -static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access, - u32 size_default) -{ - size_default = bpf_ctx_off_adjust_machine(size_default); - size_access = bpf_ctx_off_adjust_machine(size_access); - -#ifdef __LITTLE_ENDIAN - return (off & (size_default - 1)) == 0; -#else - return (off & (size_default - 1)) + size_access == size_default; -#endif -} - static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { - return bpf_ctx_narrow_align_ok(off, size, size_default) && - size <= size_default && (size & (size - 1)) == 0; + return size <= size_default && (size & (size - 1)) == 0; } #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9b00043effa30..94fb2e12f117e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -865,9 +865,6 @@ enum bpf_netdev_command { XDP_QUERY_PROG, XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ - BPF_OFFLOAD_VERIFIER_PREP, - BPF_OFFLOAD_TRANSLATE, - BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, XDP_QUERY_XSK_UMEM, @@ -893,15 +890,6 @@ struct netdev_bpf { /* flags with which program was installed */ u32 prog_flags; }; - /* BPF_OFFLOAD_VERIFIER_PREP */ - struct { - struct bpf_prog *prog; - const struct bpf_prog_offload_ops *ops; /* callee set */ - } verifier; - /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */ - struct { - struct bpf_prog *prog; - } offload; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 852dc17ab47a0..23e2031a43d43 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -257,9 +257,6 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) -/* flags for BPF_PROG_QUERY */ -#define BPF_F_QUERY_EFFECTIVE (1U << 0) - #define BPF_OBJ_NAME_LEN 16U /* Flags for accessing BPF object */ @@ -269,6 +266,12 @@ enum bpf_attach_type { /* Flag for stack_map, store build_id+offset instead of pointer */ #define BPF_F_STACK_BUILD_ID (1U << 5) +/* Zero-initialize hash function seed. This should only be used for testing. */ +#define BPF_F_ZERO_SEED (1U << 6) + +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + enum bpf_stack_build_id_status { /* user space need an empty entry to identify end of a trace */ BPF_STACK_BUILD_ID_EMPTY = 0, @@ -335,6 +338,10 @@ union bpf_attr { * (context accesses, allowed helpers, etc). */ __u32 expected_attach_type; + __u32 prog_btf_fd; /* fd pointing to BTF type data */ + __u32 func_info_rec_size; /* userspace bpf_func_info size */ + __aligned_u64 func_info; /* func info */ + __u32 func_info_cnt; /* number of bpf_func_info records */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -2201,6 +2208,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, *struct bpf_sock* + * return is from reuse->socks[] using hash of the packet. * * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) * Description @@ -2233,6 +2242,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, *struct bpf_sock* + * return is from reuse->socks[] using hash of the packet. * * int bpf_sk_release(struct bpf_sock *sk) * Description @@ -2457,6 +2468,7 @@ struct __sk_buff { __u32 data_meta; struct bpf_flow_keys *flow_keys; + __u64 tstamp; }; struct bpf_tunnel_key { @@ -2631,6 +2643,10 @@ struct bpf_prog_info { __u32 nr_jited_func_lens; __aligned_u64 jited_ksyms; __aligned_u64 jited_func_lens; + __u32 btf_id; + __u32 func_info_rec_size; + __aligned_u64 func_info; + __u32 func_info_cnt; } __attribute__((aligned(8))); struct bpf_map_info { @@ -2942,4 +2958,9 @@ struct bpf_flow_keys { }; }; +struct bpf_func_info { + __u32 insn_offset; + __u32 type_id; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 972265f328717..14f66948fc95f 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -40,7 +40,8 @@ struct btf_type { /* "size" is used by INT, ENUM, STRUCT and UNION. * "size" tells the size of the type it is describing. * - * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, + * FUNC and FUNC_PROTO. * "type" is a type_id referring to another type. */ union { @@ -64,8 +65,10 @@ struct btf_type { #define BTF_KIND_VOLATILE 9 /* Volatile */ #define BTF_KIND_CONST 10 /* Const */ #define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_MAX 11 -#define NR_BTF_KINDS 12 +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#define BTF_KIND_MAX 13 +#define NR_BTF_KINDS 14 /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -110,4 +113,13 @@ struct btf_member { __u32 offset; /* offset in bits */ }; +/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param". + * The exact number of btf_param is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_param { + __u32 name_off; + __u32 type; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ee4c82667d659..a09b2f94ab25b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5,6 +5,7 @@ #include <uapi/linux/types.h> #include <linux/seq_file.h> #include <linux/compiler.h> +#include <linux/ctype.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/anon_inodes.h> @@ -259,6 +260,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VOLATILE] = "VOLATILE", [BTF_KIND_CONST] = "CONST", [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", }; struct btf_kind_operations { @@ -281,6 +284,9 @@ struct btf_kind_operations { static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; static struct btf_type btf_void; +static int btf_resolve(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id); + static bool btf_type_is_modifier(const struct btf_type *t) { /* Some of them is not strictly a C modifier @@ -306,15 +312,33 @@ static bool btf_type_is_modifier(const struct btf_type *t) static bool btf_type_is_void(const struct btf_type *t) { - /* void => no type and size info. - * Hence, FWD is also treated as void. - */ - return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; + return t == &btf_void; +} + +static bool btf_type_is_fwd(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_func(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; } -static bool btf_type_is_void_or_null(const struct btf_type *t) +static bool btf_type_is_func_proto(const struct btf_type *t) { - return !t || btf_type_is_void(t); + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; +} + +static bool btf_type_nosize(const struct btf_type *t) +{ + return btf_type_is_void(t) || btf_type_is_fwd(t) || + btf_type_is_func(t) || btf_type_is_func_proto(t); +} + +static bool btf_type_nosize_or_null(const struct btf_type *t) +{ + return !t || btf_type_nosize(t); } /* union is only a special case of struct: @@ -426,7 +450,31 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset) offset < btf->hdr.str_len; } -static const char *btf_name_by_offset(const struct btf *btf, u32 offset) +/* Only C-style identifier is permitted. This can be relaxed if + * necessary. + */ +static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) +{ + /* offset must be valid */ + const char *src = &btf->strings[offset]; + const char *src_limit; + + if (!isalpha(*src) && *src != '_') + return false; + + /* set a limit on identifier length */ + src_limit = src + KSYM_NAME_LEN; + src++; + while (*src && src < src_limit) { + if (!isalnum(*src) && *src != '_') + return false; + src++; + } + + return !*src; +} + +const char *btf_name_by_offset(const struct btf *btf, u32 offset) { if (!offset) return "(anon)"; @@ -436,7 +484,7 @@ static const char *btf_name_by_offset(const struct btf *btf, u32 offset) return "(invalid-name-offset)"; } -static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) +const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { if (type_id > btf->nr_types) return NULL; @@ -740,11 +788,15 @@ static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, /* int, enum or void is a sink */ return !btf_type_needs_resolve(next_type); case RESOLVE_PTR: - /* int, enum, void, struct or array is a sink for ptr */ + /* int, enum, void, struct, array, func or func_proto is a sink + * for ptr + */ return !btf_type_is_modifier(next_type) && !btf_type_is_ptr(next_type); case RESOLVE_STRUCT_OR_ARRAY: - /* int, enum, void or ptr is a sink for struct and array */ + /* int, enum, void, ptr, func or func_proto is a sink + * for struct and array + */ return !btf_type_is_modifier(next_type) && !btf_type_is_array(next_type) && !btf_type_is_struct(next_type); @@ -826,7 +878,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, u32 size = 0; size_type = btf_type_by_id(btf, size_type_id); - if (btf_type_is_void_or_null(size_type)) + if (btf_type_nosize_or_null(size_type)) return NULL; if (btf_type_has_size(size_type)) { @@ -842,7 +894,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, size = btf->resolved_sizes[size_type_id]; size_type_id = btf->resolved_ids[size_type_id]; size_type = btf_type_by_id(btf, size_type_id); - if (btf_type_is_void(size_type)) + if (btf_type_nosize_or_null(size_type)) return NULL; } @@ -1163,10 +1215,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, return -EINVAL; } - /* "typedef void new_void", "const void"...etc */ - if (btf_type_is_void(next_type)) - goto resolved; - if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); @@ -1177,13 +1225,18 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, * save us a few type-following when we use it later (e.g. in * pretty print). */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && - !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { - btf_verifier_log_type(env, v->t, "Invalid type_id"); - return -EINVAL; + if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (env_type_is_resolved(env, next_type_id)) + next_type = btf_type_id_resolve(btf, &next_type_id); + + /* "typedef void new_void", "const void"...etc */ + if (!btf_type_is_void(next_type) && + !btf_type_is_fwd(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } } -resolved: env_stack_pop_resolved(env, next_type_id, next_type_size); return 0; @@ -1196,7 +1249,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size = 0; next_type = btf_type_by_id(btf, next_type_id); if (!next_type) { @@ -1204,10 +1256,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, return -EINVAL; } - /* "void *" */ - if (btf_type_is_void(next_type)) - goto resolved; - if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); @@ -1234,13 +1282,18 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, resolved_type_id); } - if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && - !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { - btf_verifier_log_type(env, v->t, "Invalid type_id"); - return -EINVAL; + if (!btf_type_id_size(btf, &next_type_id, NULL)) { + if (env_type_is_resolved(env, next_type_id)) + next_type = btf_type_id_resolve(btf, &next_type_id); + + if (!btf_type_is_void(next_type) && + !btf_type_is_fwd(next_type) && + !btf_type_is_func_proto(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } } -resolved: env_stack_pop_resolved(env, next_type_id, 0); return 0; @@ -1396,7 +1449,7 @@ static int btf_array_resolve(struct btf_verifier_env *env, /* Check array->index_type */ index_type_id = array->index_type; index_type = btf_type_by_id(btf, index_type_id); - if (btf_type_is_void_or_null(index_type)) { + if (btf_type_nosize_or_null(index_type)) { btf_verifier_log_type(env, v->t, "Invalid index"); return -EINVAL; } @@ -1415,7 +1468,7 @@ static int btf_array_resolve(struct btf_verifier_env *env, /* Check array->type */ elem_type_id = array->type; elem_type = btf_type_by_id(btf, elem_type_id); - if (btf_type_is_void_or_null(elem_type)) { + if (btf_type_nosize_or_null(elem_type)) { btf_verifier_log_type(env, v->t, "Invalid elem"); return -EINVAL; @@ -1568,7 +1621,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { btf_verifier_log_member(env, t, member, - "Memmber bits_offset exceeds its struct size"); + "Member bits_offset exceeds its struct size"); return -EINVAL; } @@ -1615,7 +1668,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env, const struct btf_type *member_type = btf_type_by_id(env->btf, member_type_id); - if (btf_type_is_void_or_null(member_type)) { + if (btf_type_nosize_or_null(member_type)) { btf_verifier_log_member(env, v->t, member, "Invalid member"); return -EINVAL; @@ -1780,6 +1833,232 @@ static struct btf_kind_operations enum_ops = { .seq_show = btf_enum_seq_show, }; +static s32 btf_func_proto_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 meta_needed = btf_type_vlen(t) * sizeof(struct btf_param); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (t->name_off) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static void btf_func_proto_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_param *args = (const struct btf_param *)(t + 1); + u16 nr_args = btf_type_vlen(t), i; + + btf_verifier_log(env, "return=%u args=(", t->type); + if (!nr_args) { + btf_verifier_log(env, "void"); + goto done; + } + + if (nr_args == 1 && !args[0].type) { + /* Only one vararg */ + btf_verifier_log(env, "vararg"); + goto done; + } + + btf_verifier_log(env, "%u %s", args[0].type, + btf_name_by_offset(env->btf, + args[0].name_off)); + for (i = 1; i < nr_args - 1; i++) + btf_verifier_log(env, ", %u %s", args[i].type, + btf_name_by_offset(env->btf, + args[i].name_off)); + + if (nr_args > 1) { + const struct btf_param *last_arg = &args[nr_args - 1]; + + if (last_arg->type) + btf_verifier_log(env, ", %u %s", last_arg->type, + btf_name_by_offset(env->btf, + last_arg->name_off)); + else + btf_verifier_log(env, ", vararg"); + } + +done: + btf_verifier_log(env, ")"); +} + +static struct btf_kind_operations func_proto_ops = { + .check_meta = btf_func_proto_check_meta, + .resolve = btf_df_resolve, + /* + * BTF_KIND_FUNC_PROTO cannot be directly referred by + * a struct's member. + * + * It should be a funciton pointer instead. + * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO) + * + * Hence, there is no btf_func_check_member(). + */ + .check_member = btf_df_check_member, + .log_details = btf_func_proto_log, + .seq_show = btf_df_seq_show, +}; + +static s32 btf_func_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (!t->name_off || + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static struct btf_kind_operations func_ops = { + .check_meta = btf_func_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_df_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_df_seq_show, +}; + +static int btf_func_proto_check(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_type *ret_type; + const struct btf_param *args; + const struct btf *btf; + u16 nr_args, i; + int err; + + btf = env->btf; + args = (const struct btf_param *)(t + 1); + nr_args = btf_type_vlen(t); + + /* Check func return type which could be "void" (t->type == 0) */ + if (t->type) { + u32 ret_type_id = t->type; + + ret_type = btf_type_by_id(btf, ret_type_id); + if (!ret_type) { + btf_verifier_log_type(env, t, "Invalid return type"); + return -EINVAL; + } + + if (btf_type_needs_resolve(ret_type) && + !env_type_is_resolved(env, ret_type_id)) { + err = btf_resolve(env, ret_type, ret_type_id); + if (err) + return err; + } + + /* Ensure the return type is a type that has a size */ + if (!btf_type_id_size(btf, &ret_type_id, NULL)) { + btf_verifier_log_type(env, t, "Invalid return type"); + return -EINVAL; + } + } + + if (!nr_args) + return 0; + + /* Last func arg type_id could be 0 if it is a vararg */ + if (!args[nr_args - 1].type) { + if (args[nr_args - 1].name_off) { + btf_verifier_log_type(env, t, "Invalid arg#%u", + nr_args); + return -EINVAL; + } + nr_args--; + } + + err = 0; + for (i = 0; i < nr_args; i++) { + const struct btf_type *arg_type; + u32 arg_type_id; + + arg_type_id = args[i].type; + arg_type = btf_type_by_id(btf, arg_type_id); + if (!arg_type) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + err = -EINVAL; + break; + } + + if (args[i].name_off && + (!btf_name_offset_valid(btf, args[i].name_off) || + !btf_name_valid_identifier(btf, args[i].name_off))) { + btf_verifier_log_type(env, t, + "Invalid arg#%u", i + 1); + err = -EINVAL; + break; + } + + if (btf_type_needs_resolve(arg_type) && + !env_type_is_resolved(env, arg_type_id)) { + err = btf_resolve(env, arg_type, arg_type_id); + if (err) + break; + } + + if (!btf_type_id_size(btf, &arg_type_id, NULL)) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + err = -EINVAL; + break; + } + } + + return err; +} + +static int btf_func_check(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_type *proto_type; + const struct btf_param *args; + const struct btf *btf; + u16 nr_args, i; + + btf = env->btf; + proto_type = btf_type_by_id(btf, t->type); + + if (!proto_type || !btf_type_is_func_proto(proto_type)) { + btf_verifier_log_type(env, t, "Invalid type_id"); + return -EINVAL; + } + + args = (const struct btf_param *)(proto_type + 1); + nr_args = btf_type_vlen(proto_type); + for (i = 0; i < nr_args; i++) { + if (!args[i].name_off && args[i].type) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + return -EINVAL; + } + } + + return 0; +} + static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_INT] = &int_ops, [BTF_KIND_PTR] = &ptr_ops, @@ -1792,6 +2071,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VOLATILE] = &modifier_ops, [BTF_KIND_CONST] = &modifier_ops, [BTF_KIND_RESTRICT] = &modifier_ops, + [BTF_KIND_FUNC] = &func_ops, + [BTF_KIND_FUNC_PROTO] = &func_proto_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -1863,30 +2144,6 @@ static int btf_check_all_metas(struct btf_verifier_env *env) return 0; } -static int btf_resolve(struct btf_verifier_env *env, - const struct btf_type *t, u32 type_id) -{ - const struct resolve_vertex *v; - int err = 0; - - env->resolve_mode = RESOLVE_TBD; - env_stack_push(env, t, type_id); - while (!err && (v = env_stack_peak(env))) { - env->log_type_id = v->type_id; - err = btf_type_ops(v->t)->resolve(env, v); - } - - env->log_type_id = type_id; - if (err == -E2BIG) - btf_verifier_log_type(env, t, - "Exceeded max resolving depth:%u", - MAX_RESOLVE_DEPTH); - else if (err == -EEXIST) - btf_verifier_log_type(env, t, "Loop detected"); - - return err; -} - static bool btf_resolve_valid(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) @@ -1920,6 +2177,39 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return false; } +static int btf_resolve(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + u32 save_log_type_id = env->log_type_id; + const struct resolve_vertex *v; + int err = 0; + + env->resolve_mode = RESOLVE_TBD; + env_stack_push(env, t, type_id); + while (!err && (v = env_stack_peak(env))) { + env->log_type_id = v->type_id; + err = btf_type_ops(v->t)->resolve(env, v); + } + + env->log_type_id = type_id; + if (err == -E2BIG) { + btf_verifier_log_type(env, t, + "Exceeded max resolving depth:%u", + MAX_RESOLVE_DEPTH); + } else if (err == -EEXIST) { + btf_verifier_log_type(env, t, "Loop detected"); + } + + /* Final sanity check */ + if (!err && !btf_resolve_valid(env, t, type_id)) { + btf_verifier_log_type(env, t, "Invalid resolve state"); + err = -EINVAL; + } + + env->log_type_id = save_log_type_id; + return err; +} + static int btf_check_all_types(struct btf_verifier_env *env) { struct btf *btf = env->btf; @@ -1942,10 +2232,16 @@ static int btf_check_all_types(struct btf_verifier_env *env) return err; } - if (btf_type_needs_resolve(t) && - !btf_resolve_valid(env, t, type_id)) { - btf_verifier_log_type(env, t, "Invalid resolve state"); - return -EINVAL; + if (btf_type_is_func_proto(t)) { + err = btf_func_proto_check(env, t); + if (err) + return err; + } + + if (btf_type_is_func(t)) { + err = btf_func_check(env, t); + if (err) + return err; } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1a796e0799ec4..16d77012ad3ef 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -21,12 +21,14 @@ * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ +#include <uapi/linux/btf.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/moduleloader.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/frame.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> @@ -390,6 +392,8 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) { const char *end = sym + KSYM_NAME_LEN; + const struct btf_type *type; + const char *func_name; BUILD_BUG_ON(sizeof("bpf_prog_") + sizeof(prog->tag) * 2 + @@ -404,6 +408,15 @@ static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); + + /* prog->aux->name will be ignored if full btf name is available */ + if (prog->aux->btf) { + type = btf_type_by_id(prog->aux->btf, prog->aux->type_id); + func_name = btf_name_by_offset(prog->aux->btf, type->name_off); + snprintf(sym, (size_t)(end - sym), "_%s", func_name); + return; + } + if (prog->aux->name[0]) snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); else diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 2c17902881387..4b7c76765d9d6 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -23,7 +23,7 @@ #define HTAB_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ - BPF_F_RDONLY | BPF_F_WRONLY) + BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED) struct bucket { struct hlist_nulls_head head; @@ -244,6 +244,7 @@ static int htab_map_alloc_check(union bpf_attr *attr) */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); + bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED); int numa_node = bpf_map_attr_numa_node(attr); BUILD_BUG_ON(offsetof(struct htab_elem, htab) != @@ -257,6 +258,10 @@ static int htab_map_alloc_check(union bpf_attr *attr) */ return -EPERM; + if (zero_seed && !capable(CAP_SYS_ADMIN)) + /* Guard against local DoS, and discourage production use. */ + return -EPERM; + if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) /* reserved bits should not be used */ return -EINVAL; @@ -373,7 +378,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (!htab->buckets) goto free_htab; - htab->hashrnd = get_random_int(); + if (htab->map.map_flags & BPF_F_ZERO_SEED) + htab->hashrnd = 0; + else + htab->hashrnd = get_random_int(); + for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index c97a8f968638c..9e94b1cc6cf23 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -7,8 +7,7 @@ #include <linux/rbtree.h> #include <linux/slab.h> -DEFINE_PER_CPU(struct bpf_cgroup_storage*, - bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #ifdef CONFIG_CGROUP_BPF diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 9058317ba9de2..bfd4882e1106c 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -168,20 +168,59 @@ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, const struct bpf_lpm_trie_key *key) { - size_t prefixlen = 0; - size_t i; + u32 limit = min(node->prefixlen, key->prefixlen); + u32 prefixlen = 0, i = 0; - for (i = 0; i < trie->data_size; i++) { - size_t b; + BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); + BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); - b = 8 - fls(node->data[i] ^ key->data[i]); - prefixlen += b; +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) - if (prefixlen >= node->prefixlen || prefixlen >= key->prefixlen) - return min(node->prefixlen, key->prefixlen); + /* data_size >= 16 has very small probability. + * We do not use a loop for optimal code generation. + */ + if (trie->data_size >= 8) { + u64 diff = be64_to_cpu(*(__be64 *)node->data ^ + *(__be64 *)key->data); + + prefixlen = 64 - fls64(diff); + if (prefixlen >= limit) + return limit; + if (diff) + return prefixlen; + i = 8; + } +#endif + + while (trie->data_size >= i + 4) { + u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^ + *(__be32 *)&key->data[i]); + + prefixlen += 32 - fls(diff); + if (prefixlen >= limit) + return limit; + if (diff) + return prefixlen; + i += 4; + } - if (b < 8) - break; + if (trie->data_size >= i + 2) { + u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^ + *(__be16 *)&key->data[i]); + + prefixlen += 16 - fls(diff); + if (prefixlen >= limit) + return limit; + if (diff) + return prefixlen; + i += 2; + } + + if (trie->data_size >= i + 1) { + prefixlen += 8 - fls(node->data[i] ^ key->data[i]); + + if (prefixlen >= limit) + return limit; } return prefixlen; diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 8e93c47f07796..54cf2b9c44a45 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -33,6 +33,7 @@ static DECLARE_RWSEM(bpf_devs_lock); struct bpf_offload_dev { + const struct bpf_prog_offload_ops *ops; struct list_head netdevs; }; @@ -106,6 +107,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) err = -EINVAL; goto err_unlock; } + offload->offdev = ondev->offdev; prog->aux->offload = offload; list_add_tail(&offload->offloads, &ondev->progs); dev_put(offload->netdev); @@ -121,40 +123,20 @@ err_maybe_put: return err; } -static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd, - struct netdev_bpf *data) +int bpf_prog_offload_verifier_prep(struct bpf_prog *prog) { - struct bpf_prog_offload *offload = prog->aux->offload; - struct net_device *netdev; - - ASSERT_RTNL(); - - if (!offload) - return -ENODEV; - netdev = offload->netdev; - - data->command = cmd; - - return netdev->netdev_ops->ndo_bpf(netdev, data); -} - -int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) -{ - struct netdev_bpf data = {}; - int err; - - data.verifier.prog = env->prog; + struct bpf_prog_offload *offload; + int ret = -ENODEV; - rtnl_lock(); - err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data); - if (err) - goto exit_unlock; + down_read(&bpf_devs_lock); + offload = prog->aux->offload; + if (offload) { + ret = offload->offdev->ops->prepare(prog); + offload->dev_state = !ret; + } + up_read(&bpf_devs_lock); - env->prog->aux->offload->dev_ops = data.verifier.ops; - env->prog->aux->offload->dev_state = true; -exit_unlock: - rtnl_unlock(); - return err; + return ret; } int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, @@ -166,7 +148,8 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, down_read(&bpf_devs_lock); offload = env->prog->aux->offload; if (offload) - ret = offload->dev_ops->insn_hook(env, insn_idx, prev_insn_idx); + ret = offload->offdev->ops->insn_hook(env, insn_idx, + prev_insn_idx); up_read(&bpf_devs_lock); return ret; @@ -180,8 +163,8 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env) down_read(&bpf_devs_lock); offload = env->prog->aux->offload; if (offload) { - if (offload->dev_ops->finalize) - ret = offload->dev_ops->finalize(env); + if (offload->offdev->ops->finalize) + ret = offload->offdev->ops->finalize(env); else ret = 0; } @@ -193,12 +176,9 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env) static void __bpf_prog_offload_destroy(struct bpf_prog *prog) { struct bpf_prog_offload *offload = prog->aux->offload; - struct netdev_bpf data = {}; - - data.offload.prog = prog; if (offload->dev_state) - WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data)); + offload->offdev->ops->destroy(prog); /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */ bpf_prog_free_id(prog, true); @@ -210,24 +190,22 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog) void bpf_prog_offload_destroy(struct bpf_prog *prog) { - rtnl_lock(); down_write(&bpf_devs_lock); if (prog->aux->offload) __bpf_prog_offload_destroy(prog); up_write(&bpf_devs_lock); - rtnl_unlock(); } static int bpf_prog_offload_translate(struct bpf_prog *prog) { - struct netdev_bpf data = {}; - int ret; - - data.offload.prog = prog; + struct bpf_prog_offload *offload; + int ret = -ENODEV; - rtnl_lock(); - ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data); - rtnl_unlock(); + down_read(&bpf_devs_lock); + offload = prog->aux->offload; + if (offload) + ret = offload->offdev->ops->translate(prog); + up_read(&bpf_devs_lock); return ret; } @@ -655,7 +633,8 @@ unlock: } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); -struct bpf_offload_dev *bpf_offload_dev_create(void) +struct bpf_offload_dev * +bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops) { struct bpf_offload_dev *offdev; int err; @@ -673,6 +652,7 @@ struct bpf_offload_dev *bpf_offload_dev_create(void) if (!offdev) return ERR_PTR(-ENOMEM); + offdev->ops = ops; INIT_LIST_HEAD(&offdev->netdevs); return offdev; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cf5040fd54344..9983778081021 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1213,6 +1213,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); bpf_prog_kallsyms_del_all(prog); + btf_put(prog->aux->btf); call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } @@ -1437,9 +1438,9 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD expected_attach_type +#define BPF_PROG_LOAD_LAST_FIELD func_info_cnt -static int bpf_prog_load(union bpf_attr *attr) +static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog; @@ -1525,7 +1526,7 @@ static int bpf_prog_load(union bpf_attr *attr) goto free_prog; /* run eBPF verifier */ - err = bpf_check(&prog, attr); + err = bpf_check(&prog, attr, uattr); if (err < 0) goto free_used_maps; @@ -2079,6 +2080,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; info.nr_jited_func_lens = 0; + info.func_info_cnt = 0; goto done; } @@ -2216,6 +2218,55 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } } + if (prog->aux->btf) { + u32 ucnt, urec_size; + + info.btf_id = btf_id(prog->aux->btf); + + ucnt = info.func_info_cnt; + info.func_info_cnt = prog->aux->func_cnt ? : 1; + urec_size = info.func_info_rec_size; + info.func_info_rec_size = sizeof(struct bpf_func_info); + if (ucnt) { + /* expect passed-in urec_size is what the kernel expects */ + if (urec_size != info.func_info_rec_size) + return -EINVAL; + + if (bpf_dump_raw_ok()) { + struct bpf_func_info kern_finfo; + char __user *user_finfo; + u32 i, insn_offset; + + user_finfo = u64_to_user_ptr(info.func_info); + if (prog->aux->func_cnt) { + ucnt = min_t(u32, info.func_info_cnt, ucnt); + insn_offset = 0; + for (i = 0; i < ucnt; i++) { + kern_finfo.insn_offset = insn_offset; + kern_finfo.type_id = prog->aux->func[i]->aux->type_id; + if (copy_to_user(user_finfo, &kern_finfo, + sizeof(kern_finfo))) + return -EFAULT; + + /* func[i]->len holds the prog len */ + insn_offset += prog->aux->func[i]->len; + user_finfo += urec_size; + } + } else { + kern_finfo.insn_offset = 0; + kern_finfo.type_id = prog->aux->type_id; + if (copy_to_user(user_finfo, &kern_finfo, + sizeof(kern_finfo))) + return -EFAULT; + } + } else { + info.func_info_cnt = 0; + } + } + } else { + info.func_info_cnt = 0; + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -2501,7 +2552,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = map_get_next_key(&attr); break; case BPF_PROG_LOAD: - err = bpf_prog_load(&attr); + err = bpf_prog_load(&attr, uattr); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1971ca325fb4e..f102c4fd0c5af 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11,10 +11,12 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include <uapi/linux/btf.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <net/netlink.h> @@ -1455,6 +1457,17 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, verbose(env, "R%d offset is outside of the packet\n", regno); return err; } + + /* __check_packet_access has made sure "off + size - 1" is within u16. + * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, + * otherwise find_good_pkt_pointers would have refused to set range info + * that __check_packet_access would have rejected this pkt access. + * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. + */ + env->prog->aux->max_pkt_offset = + max_t(u32, env->prog->aux->max_pkt_offset, + off + reg->umax_value + size - 1); + return err; } @@ -4628,6 +4641,114 @@ err_free: return ret; } +/* The minimum supported BTF func info size */ +#define MIN_BPF_FUNCINFO_SIZE 8 +#define MAX_FUNCINFO_REC_SIZE 252 + +static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env, + union bpf_attr *attr, union bpf_attr __user *uattr) +{ + u32 i, nfuncs, urec_size, min_size, prev_offset; + u32 krec_size = sizeof(struct bpf_func_info); + struct bpf_func_info krecord = {}; + const struct btf_type *type; + void __user *urecord; + struct btf *btf; + int ret = 0; + + nfuncs = attr->func_info_cnt; + if (!nfuncs) + return 0; + + if (nfuncs != env->subprog_cnt) { + verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); + return -EINVAL; + } + + urec_size = attr->func_info_rec_size; + if (urec_size < MIN_BPF_FUNCINFO_SIZE || + urec_size > MAX_FUNCINFO_REC_SIZE || + urec_size % sizeof(u32)) { + verbose(env, "invalid func info rec size %u\n", urec_size); + return -EINVAL; + } + + btf = btf_get_by_fd(attr->prog_btf_fd); + if (IS_ERR(btf)) { + verbose(env, "unable to get btf from fd\n"); + return PTR_ERR(btf); + } + + urecord = u64_to_user_ptr(attr->func_info); + min_size = min_t(u32, krec_size, urec_size); + + for (i = 0; i < nfuncs; i++) { + ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); + if (ret) { + if (ret == -E2BIG) { + verbose(env, "nonzero tailing record in func info"); + /* set the size kernel expects so loader can zero + * out the rest of the record. + */ + if (put_user(min_size, &uattr->func_info_rec_size)) + ret = -EFAULT; + } + goto free_btf; + } + + if (copy_from_user(&krecord, urecord, min_size)) { + ret = -EFAULT; + goto free_btf; + } + + /* check insn_offset */ + if (i == 0) { + if (krecord.insn_offset) { + verbose(env, + "nonzero insn_offset %u for the first func info record", + krecord.insn_offset); + ret = -EINVAL; + goto free_btf; + } + } else if (krecord.insn_offset <= prev_offset) { + verbose(env, + "same or smaller insn offset (%u) than previous func info record (%u)", + krecord.insn_offset, prev_offset); + ret = -EINVAL; + goto free_btf; + } + + if (env->subprog_info[i].start != krecord.insn_offset) { + verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); + ret = -EINVAL; + goto free_btf; + } + + /* check type_id */ + type = btf_type_by_id(btf, krecord.type_id); + if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) { + verbose(env, "invalid type id %d in func info", + krecord.type_id); + ret = -EINVAL; + goto free_btf; + } + + if (i == 0) + prog->aux->type_id = krecord.type_id; + env->subprog_info[i].type_id = krecord.type_id; + + prev_offset = krecord.insn_offset; + urecord += urec_size; + } + + prog->aux->btf = btf; + return 0; + +free_btf: + btf_put(btf); + return ret; +} + /* check %cur's range satisfies %old's */ static bool range_within(struct bpf_reg_state *old, struct bpf_reg_state *cur) @@ -5707,10 +5828,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; + u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; - u32 target_size; if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { @@ -5803,9 +5924,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * we will apply proper mask to the result. */ is_narrower_load = size < ctx_field_size; + size_default = bpf_ctx_off_adjust_machine(ctx_field_size); + off = insn->off; if (is_narrower_load) { - u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size); - u32 off = insn->off; u8 size_code; if (type == BPF_WRITE) { @@ -5833,12 +5954,23 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - if (ctx_field_size <= 4) + u8 shift = (off & (size_default - 1)) * 8; + + if (ctx_field_size <= 4) { + if (shift) + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, + insn->dst_reg, + shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); - else + } else { + if (shift) + insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, + insn->dst_reg, + shift); insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); + } } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); @@ -5917,6 +6049,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; + /* the btf will be freed only at prog->aux */ + func[i]->aux->btf = prog->aux->btf; + func[i]->aux->type_id = env->subprog_info[i].type_id; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; @@ -6138,6 +6273,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ prog->cb_access = 1; env->prog->aux->stack_depth = MAX_BPF_STACK; + env->prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpeter for every normal @@ -6302,7 +6438,8 @@ static void free_states(struct bpf_verifier_env *env) kfree(env->explored_states); } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, + union bpf_attr __user *uattr) { struct bpf_verifier_env *env; struct bpf_verifier_log *log; @@ -6356,7 +6493,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) goto skip_full_check; if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env); + ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; } @@ -6374,6 +6511,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (ret < 0) goto skip_full_check; + ret = check_btf_func(env->prog, env, attr, uattr); + if (ret < 0) + goto skip_full_check; + ret = do_check(env); if (env->cur_state) { free_verifier_state(env->cur_state, true); diff --git a/net/core/filter.c b/net/core/filter.c index 10acbc00ff6c1..aa274679965d1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3904,6 +3904,26 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_5(bpf_sockopt_event_output, struct bpf_sock_ops_kern *, bpf_sock, + struct bpf_map *, map, u64, flags, void *, data, u64, size) +{ + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) + return -EINVAL; + + return bpf_event_output(map, flags, data, size, NULL, 0, NULL); +} + +static const struct bpf_func_proto bpf_sockopt_event_output_proto = { + .func = bpf_sockopt_event_output, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, +}; + BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { @@ -4821,47 +4841,40 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, - struct sk_buff *skb, u8 family, u8 proto) + int dif, int sdif, u8 family, u8 proto) { bool refcounted = false; struct sock *sk = NULL; - int dif = 0; - - if (skb->dev) - dif = skb->dev->ifindex; if (family == AF_INET) { __be32 src4 = tuple->ipv4.saddr; __be32 dst4 = tuple->ipv4.daddr; - int sdif = inet_sdif(skb); if (proto == IPPROTO_TCP) - sk = __inet_lookup(net, &tcp_hashinfo, skb, 0, + sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &refcounted); else sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, - dif, sdif, &udp_table, skb); + dif, sdif, &udp_table, NULL); #if IS_ENABLED(CONFIG_IPV6) } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; - u16 hnum = ntohs(tuple->ipv6.dport); - int sdif = inet6_sdif(skb); if (proto == IPPROTO_TCP) - sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0, + sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0, src6, tuple->ipv6.sport, - dst6, hnum, + dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_bpf_stub)) sk = ipv6_bpf_stub->udp6_lib_lookup(net, src6, tuple->ipv6.sport, - dst6, hnum, + dst6, tuple->ipv6.dport, dif, sdif, - &udp_table, skb); + &udp_table, NULL); #endif } @@ -4878,31 +4891,33 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, * callers to satisfy BPF_CALL declarations. */ static unsigned long -bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, - u8 proto, u64 netns_id, u64 flags) +__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, + struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, + u64 flags) { - struct net *caller_net; struct sock *sk = NULL; u8 family = AF_UNSPEC; struct net *net; + int sdif; family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6; if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags)) goto out; - if (skb->dev) - caller_net = dev_net(skb->dev); + if (family == AF_INET) + sdif = inet_sdif(skb); else - caller_net = sock_net(skb->sk); + sdif = inet6_sdif(skb); + if (netns_id) { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; - sk = sk_lookup(net, tuple, skb, family, proto); + sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); put_net(net); } else { net = caller_net; - sk = sk_lookup(net, tuple, skb, family, proto); + sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); } if (sk) @@ -4911,6 +4926,25 @@ out: return (unsigned long) sk; } +static unsigned long +bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, + u8 proto, u64 netns_id, u64 flags) +{ + struct net *caller_net; + int ifindex; + + if (skb->dev) { + caller_net = dev_net(skb->dev); + ifindex = skb->dev->ifindex; + } else { + caller_net = sock_net(skb->sk); + ifindex = 0; + } + + return __bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, + proto, netns_id, flags); +} + BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { @@ -4960,6 +4994,87 @@ static const struct bpf_func_proto bpf_sk_release_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_SOCKET, }; + +BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, + struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) +{ + struct net *caller_net = dev_net(ctx->rxq->dev); + int ifindex = ctx->rxq->dev->ifindex; + + return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, + IPPROTO_UDP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { + .func = bpf_xdp_sk_lookup_udp, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx, + struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) +{ + struct net *caller_net = dev_net(ctx->rxq->dev); + int ifindex = ctx->rxq->dev->ifindex; + + return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, + IPPROTO_TCP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { + .func = bpf_xdp_sk_lookup_tcp, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx, + struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) +{ + return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, + IPPROTO_TCP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { + .func = bpf_sock_addr_sk_lookup_tcp, + .gpl_only = false, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx, + struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) +{ + return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, + IPPROTO_UDP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { + .func = bpf_sock_addr_sk_lookup_udp, + .gpl_only = false, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -5066,6 +5181,14 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_cookie_sock_addr_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; +#ifdef CONFIG_INET + case BPF_FUNC_sk_lookup_tcp: + return &bpf_sock_addr_sk_lookup_tcp_proto; + case BPF_FUNC_sk_lookup_udp: + return &bpf_sock_addr_sk_lookup_udp_proto; + case BPF_FUNC_sk_release: + return &bpf_sk_release_proto; +#endif /* CONFIG_INET */ default: return bpf_base_func_proto(func_id); } @@ -5210,6 +5333,14 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; +#ifdef CONFIG_INET + case BPF_FUNC_sk_lookup_udp: + return &bpf_xdp_sk_lookup_udp_proto; + case BPF_FUNC_sk_lookup_tcp: + return &bpf_xdp_sk_lookup_tcp_proto; + case BPF_FUNC_sk_release: + return &bpf_sk_release_proto; +#endif default: return bpf_base_func_proto(func_id); } @@ -5236,6 +5367,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_cookie_sock_ops_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_perf_event_output: + return &bpf_sockopt_event_output_proto; default: return bpf_base_func_proto(func_id); } @@ -5436,6 +5569,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (size != sizeof(struct bpf_flow_keys *)) return false; break; + case bpf_ctx_range(struct __sk_buff, tstamp): + if (size != sizeof(__u64)) + return false; + break; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { @@ -5463,6 +5600,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): + case bpf_ctx_range(struct __sk_buff, tstamp): return false; } @@ -5501,6 +5639,10 @@ static bool cg_skb_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; + case bpf_ctx_range(struct __sk_buff, tstamp): + if (!capable(CAP_SYS_ADMIN)) + return false; + break; default: return false; } @@ -5528,6 +5670,7 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range(struct __sk_buff, tstamp): return false; } @@ -5737,6 +5880,7 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): + case bpf_ctx_range(struct __sk_buff, tstamp): break; default: return false; @@ -5956,6 +6100,7 @@ static bool sk_skb_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range(struct __sk_buff, tstamp): return false; } @@ -6042,6 +6187,7 @@ static bool flow_dissector_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range_till(struct __sk_buff, family, local_port): + case bpf_ctx_range(struct __sk_buff, tstamp): return false; } @@ -6351,6 +6497,22 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; + + case offsetof(struct __sk_buff, tstamp): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_DW, + si->dst_reg, si->src_reg, + bpf_target_off(struct sk_buff, + tstamp, 8, + target_size)); + else + *insn++ = BPF_LDX_MEM(BPF_DW, + si->dst_reg, si->src_reg, + bpf_target_off(struct sk_buff, + tstamp, 8, + target_size)); } return insn - insn_buf; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index be0a961450bc2..35444f4a846bd 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -208,12 +208,20 @@ endif BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') +BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \ + $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \ + readelf -S ./llvm_btf_verify.o | grep BTF; \ + /bin/rm -f ./llvm_btf_verify.o) +ifneq ($(BTF_LLVM_PROBE),) + EXTRA_CFLAGS += -g +else ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),) EXTRA_CFLAGS += -g LLC_FLAGS += -mattr=dwarfris DWARF2BTF = y endif +endif # Trick to allow make to be run from this directory all: diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index e6d7e0fe155b4..434ea34a59549 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -54,6 +54,23 @@ static int populate_prog_array(const char *event, int prog_fd) return 0; } +static int write_kprobe_events(const char *val) +{ + int fd, ret, flags; + + if ((val != NULL) && (val[0] == '\0')) + flags = O_WRONLY | O_TRUNC; + else + flags = O_WRONLY | O_APPEND; + + fd = open("/sys/kernel/debug/tracing/kprobe_events", flags); + + ret = write(fd, val, strlen(val)); + close(fd); + + return ret; +} + static int load_and_attach(const char *event, struct bpf_insn *prog, int size) { bool is_socket = strncmp(event, "socket", 6) == 0; @@ -165,10 +182,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) #ifdef __x86_64__ if (strncmp(event, "sys_", 4) == 0) { - snprintf(buf, sizeof(buf), - "echo '%c:__x64_%s __x64_%s' >> /sys/kernel/debug/tracing/kprobe_events", - is_kprobe ? 'p' : 'r', event, event); - err = system(buf); + snprintf(buf, sizeof(buf), "%c:__x64_%s __x64_%s", + is_kprobe ? 'p' : 'r', event, event); + err = write_kprobe_events(buf); if (err >= 0) { need_normal_check = false; event_prefix = "__x64_"; @@ -176,10 +192,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) } #endif if (need_normal_check) { - snprintf(buf, sizeof(buf), - "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events", - is_kprobe ? 'p' : 'r', event, event); - err = system(buf); + snprintf(buf, sizeof(buf), "%c:%s %s", + is_kprobe ? 'p' : 'r', event, event); + err = write_kprobe_events(buf); if (err < 0) { printf("failed to create kprobe '%s' error '%s'\n", event, strerror(errno)); @@ -284,8 +299,8 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps, numa_node); } if (map_fd[i] < 0) { - printf("failed to create a map: %d %s\n", - errno, strerror(errno)); + printf("failed to create map %d (%s): %d %s\n", + i, maps[i].name, errno, strerror(errno)); return 1; } maps[i].fd = map_fd[i]; @@ -519,7 +534,7 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) return 1; /* clear all kprobes */ - i = system("echo \"\" > /sys/kernel/debug/tracing/kprobe_events"); + i = write_kprobe_events(""); /* scan over all elf sections to get license and map info */ for (i = 1; i < ehdr.e_shnum; i++) { diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index f55a2daed59b7..9e827e342d9e9 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -42,7 +42,8 @@ MAP COMMANDS | | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** | | **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash** -| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** } +| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** +| | **queue** | **stack** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index ac4e904b10fbd..8db78ed82a71f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -15,7 +15,8 @@ SYNOPSIS *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } *COMMANDS* := - { **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | **help** } + { **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** + | **loadall** | **help** } MAP COMMANDS ============= @@ -24,9 +25,9 @@ MAP COMMANDS | **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}] | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] -| **bpftool** **prog attach** *PROG* *ATTACH_TYPE* *MAP* -| **bpftool** **prog detach** *PROG* *ATTACH_TYPE* *MAP* +| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] +| **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] +| **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } @@ -39,7 +40,9 @@ MAP COMMANDS | **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | | **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | } -| *ATTACH_TYPE* := { **msg_verdict** | **skb_verdict** | **skb_parse** } +| *ATTACH_TYPE* := { +| **msg_verdict** | **skb_verdict** | **skb_parse** | **flow_dissector** +| } DESCRIPTION @@ -79,8 +82,11 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. - **bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] - Load bpf program from binary *OBJ* and pin as *FILE*. + **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] + Load bpf program(s) from binary *OBJ* and pin as *PATH*. + **bpftool prog load** pins only the first program from the + *OBJ* as *PATH*. **bpftool prog loadall** pins all programs + from the *OBJ* under *PATH* directory. **type** is optional, if not specified program type will be inferred from section names. By default bpftool will create new maps as declared in the ELF @@ -92,18 +98,24 @@ DESCRIPTION use, referring to it by **id** or through a **pinned** file. If **dev** *NAME* is specified program will be loaded onto given networking device (offload). + Optional **pinmaps** argument can be provided to pin all + maps under *MAP_DIR* directory. - Note: *FILE* must be located in *bpffs* mount. It must not + Note: *PATH* must be located in *bpffs* mount. It must not contain a dot character ('.'), which is reserved for future extensions of *bpffs*. - **bpftool prog attach** *PROG* *ATTACH_TYPE* *MAP* - Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*) - to the map *MAP*. - - **bpftool prog detach** *PROG* *ATTACH_TYPE* *MAP* - Detach bpf program *PROG* (with type specified by *ATTACH_TYPE*) - from the map *MAP*. + **bpftool prog attach** *PROG* *ATTACH_TYPE* [*MAP*] + Attach bpf program *PROG* (with type specified by + *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP* + parameter, with the exception of *flow_dissector* which is + attached to current networking name space. + + **bpftool prog detach** *PROG* *ATTACH_TYPE* [*MAP*] + Detach bpf program *PROG* (with type specified by + *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP* + parameter, with the exception of *flow_dissector* which is + detached from the current networking name space. **bpftool prog help** Print short help message. diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index dac7eff4c7e5d..1bea6b9790823 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -53,7 +53,7 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif -LIBS = -lelf -lbfd -lopcodes $(LIBBPF) +LIBS = -lelf $(LIBBPF) INSTALL ?= install RM ?= rm -f @@ -90,7 +90,16 @@ include $(wildcard $(OUTPUT)*.d) all: $(OUTPUT)bpftool -SRCS = $(wildcard *.c) +BFD_SRCS = jit_disasm.c + +SRCS = $(filter-out $(BFD_SRCS),$(wildcard *.c)) + +ifeq ($(feature-libbfd),1) +CFLAGS += -DHAVE_LIBBFD_SUPPORT +SRCS += $(BFD_SRCS) +LIBS += -lbfd -lopcodes +endif + OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 3f78e6404589f..45c2db257d2bf 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -243,7 +243,7 @@ _bpftool() # Completion depends on object and command in use case $object in prog) - if [[ $command != "load" ]]; then + if [[ $command != "load" && $command != "loadall" ]]; then case $prev in id) _bpftool_get_prog_ids @@ -299,7 +299,8 @@ _bpftool() fi if [[ ${#words[@]} == 6 ]]; then - COMPREPLY=( $( compgen -W "msg_verdict skb_verdict skb_parse" -- "$cur" ) ) + COMPREPLY=( $( compgen -W "msg_verdict skb_verdict \ + skb_parse flow_dissector" -- "$cur" ) ) return 0 fi @@ -309,7 +310,7 @@ _bpftool() fi return 0 ;; - load) + load|loadall) local obj if [[ ${#words[@]} -lt 6 ]]; then @@ -338,7 +339,16 @@ _bpftool() case $prev in type) - COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \ + COMPREPLY=( $( compgen -W "socket kprobe \ + kretprobe classifier flow_dissector \ + action tracepoint raw_tracepoint \ + xdp perf_event cgroup/skb cgroup/sock \ + cgroup/dev lwt_in lwt_out lwt_xmit \ + lwt_seg6local sockops sk_skb sk_msg \ + lirc_mode2 cgroup/bind4 cgroup/bind6 \ + cgroup/connect4 cgroup/connect6 \ + cgroup/sendmsg4 cgroup/sendmsg6 \ + cgroup/post_bind4 cgroup/post_bind6" -- \ "$cur" ) ) return 0 ;; @@ -346,7 +356,7 @@ _bpftool() _bpftool_get_map_ids return 0 ;; - pinned) + pinned|pinmaps) _filedir return 0 ;; @@ -358,6 +368,7 @@ _bpftool() COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) _bpftool_once_attr 'type' _bpftool_once_attr 'dev' + _bpftool_once_attr 'pinmaps' return 0 ;; esac diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 55bc512a18318..c3fd3a7cb7876 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -249,3 +249,139 @@ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, { return btf_dumper_do_type(d, type_id, 0, data); } + +#define BTF_PRINT_ARG(...) \ + do { \ + pos += snprintf(func_sig + pos, size - pos, \ + __VA_ARGS__); \ + if (pos >= size) \ + return -1; \ + } while (0) +#define BTF_PRINT_TYPE(type) \ + do { \ + pos = __btf_dumper_type_only(btf, type, func_sig, \ + pos, size); \ + if (pos == -1) \ + return -1; \ + } while (0) + +static int btf_dump_func(const struct btf *btf, char *func_sig, + const struct btf_type *func_proto, + const struct btf_type *func, int pos, int size); + +static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, + char *func_sig, int pos, int size) +{ + const struct btf_type *proto_type; + const struct btf_array *array; + const struct btf_type *t; + + if (!type_id) { + BTF_PRINT_ARG("void "); + return pos; + } + + t = btf__type_by_id(btf, type_id); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_STRUCT: + BTF_PRINT_ARG("struct %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_UNION: + BTF_PRINT_ARG("union %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_ENUM: + BTF_PRINT_ARG("enum %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_ARRAY: + array = (struct btf_array *)(t + 1); + BTF_PRINT_TYPE(array->type); + BTF_PRINT_ARG("[%d]", array->nelems); + break; + case BTF_KIND_PTR: + BTF_PRINT_TYPE(t->type); + BTF_PRINT_ARG("* "); + break; + case BTF_KIND_UNKN: + case BTF_KIND_FWD: + case BTF_KIND_TYPEDEF: + return -1; + case BTF_KIND_VOLATILE: + BTF_PRINT_ARG("volatile "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_CONST: + BTF_PRINT_ARG("const "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_RESTRICT: + BTF_PRINT_ARG("restrict "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_FUNC_PROTO: + pos = btf_dump_func(btf, func_sig, t, NULL, pos, size); + if (pos == -1) + return -1; + break; + case BTF_KIND_FUNC: + proto_type = btf__type_by_id(btf, t->type); + pos = btf_dump_func(btf, func_sig, proto_type, t, pos, size); + if (pos == -1) + return -1; + break; + default: + return -1; + } + + return pos; +} + +static int btf_dump_func(const struct btf *btf, char *func_sig, + const struct btf_type *func_proto, + const struct btf_type *func, int pos, int size) +{ + int i, vlen; + + BTF_PRINT_TYPE(func_proto->type); + if (func) + BTF_PRINT_ARG("%s(", btf__name_by_offset(btf, func->name_off)); + else + BTF_PRINT_ARG("("); + vlen = BTF_INFO_VLEN(func_proto->info); + for (i = 0; i < vlen; i++) { + struct btf_param *arg = &((struct btf_param *)(func_proto + 1))[i]; + + if (i) + BTF_PRINT_ARG(", "); + if (arg->type) { + BTF_PRINT_TYPE(arg->type); + BTF_PRINT_ARG("%s", + btf__name_by_offset(btf, arg->name_off)); + } else { + BTF_PRINT_ARG("..."); + } + } + BTF_PRINT_ARG(")"); + + return pos; +} + +void btf_dumper_type_only(const struct btf *btf, __u32 type_id, char *func_sig, + int size) +{ + int err; + + func_sig[0] = '\0'; + if (!btf) + return; + + err = __btf_dumper_type_only(btf, type_id, func_sig, 0, size); + if (err < 0) + func_sig[0] = '\0'; +} diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 25af85304ebee..cb06a5b6e0162 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -46,6 +46,7 @@ #include <linux/magic.h> #include <net/if.h> #include <sys/mount.h> +#include <sys/resource.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/vfs.h> @@ -99,6 +100,13 @@ static bool is_bpffs(char *path) return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; } +void set_max_rlimit(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + setrlimit(RLIMIT_MEMLOCK, &rinf); +} + static int mnt_bpffs(const char *target, char *buff, size_t bufflen) { bool bind_done = false; @@ -169,34 +177,23 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type) return fd; } -int do_pin_fd(int fd, const char *name) +int mount_bpffs_for_pin(const char *name) { char err_str[ERR_MAX_LEN]; char *file; char *dir; int err = 0; - err = bpf_obj_pin(fd, name); - if (!err) - goto out; - file = malloc(strlen(name) + 1); strcpy(file, name); dir = dirname(file); - if (errno != EPERM || is_bpffs(dir)) { - p_err("can't pin the object (%s): %s", name, strerror(errno)); + if (is_bpffs(dir)) + /* nothing to do if already mounted */ goto out_free; - } - /* Attempt to mount bpffs, then retry pinning. */ err = mnt_bpffs(dir, err_str, ERR_MAX_LEN); - if (!err) { - err = bpf_obj_pin(fd, name); - if (err) - p_err("can't pin the object (%s): %s", name, - strerror(errno)); - } else { + if (err) { err_str[ERR_MAX_LEN - 1] = '\0'; p_err("can't mount BPF file system to pin the object (%s): %s", name, err_str); @@ -204,10 +201,20 @@ int do_pin_fd(int fd, const char *name) out_free: free(file); -out: return err; } +int do_pin_fd(int fd, const char *name) +{ + int err; + + err = mount_bpffs_for_pin(name); + if (err) + return err; + + return bpf_obj_pin(fd, name); +} + int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) { unsigned int id; diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index c75ffd9ce2bb3..b2ed5ee1af5fe 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -109,7 +109,7 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, if (inf) { bfdf->arch_info = inf; } else { - p_err("No libfd support for %s", arch); + p_err("No libbfd support for %s", arch); return; } } @@ -183,3 +183,9 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, bfd_close(bfdf); } + +int disasm_init(void) +{ + bfd_init(); + return 0; +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 75a3296dc0bc8..5c4c1cd5a7ba2 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -31,7 +31,6 @@ * SOFTWARE. */ -#include <bfd.h> #include <ctype.h> #include <errno.h> #include <getopt.h> @@ -399,8 +398,6 @@ int main(int argc, char **argv) if (argc < 0) usage(); - bfd_init(); - ret = cmd_select(cmds, argc, argv, do_help); if (json_output) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 28322ace28565..3e8979567cf1b 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -100,6 +100,8 @@ bool is_prefix(const char *pfx, const char *str); void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep); void usage(void) __noreturn; +void set_max_rlimit(void); + struct pinned_obj_table { DECLARE_HASHTABLE(table, 16); }; @@ -129,6 +131,7 @@ const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); int open_obj_pinned(char *path); int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type); +int mount_bpffs_for_pin(const char *name); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)); int do_pin_fd(int fd, const char *name); @@ -144,8 +147,22 @@ int prog_parse_fd(int *argc, char ***argv); int map_parse_fd(int *argc, char ***argv); int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); +#ifdef HAVE_LIBBFD_SUPPORT void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, const char *arch, const char *disassembler_options); +int disasm_init(void); +#else +static inline +void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options) +{ +} +static inline int disasm_init(void) +{ + p_err("No libbfd support"); + return -1; +} +#endif void print_data_json(uint8_t *data, size_t len); void print_hex_data_json(uint8_t *data, size_t len); @@ -170,6 +187,8 @@ struct btf_dumper { */ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, const void *data); +void btf_dumper_type_only(const struct btf *btf, __u32 func_type_id, + char *func_only, int size); struct nlattr; struct ifinfomsg; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 7bf38f0e152e0..cbd3080e72c77 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -52,28 +52,30 @@ #include "main.h" static const char * const map_type_name[] = { - [BPF_MAP_TYPE_UNSPEC] = "unspec", - [BPF_MAP_TYPE_HASH] = "hash", - [BPF_MAP_TYPE_ARRAY] = "array", - [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", - [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", - [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", - [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", - [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", - [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", - [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", - [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", - [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", - [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", - [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", - [BPF_MAP_TYPE_DEVMAP] = "devmap", - [BPF_MAP_TYPE_SOCKMAP] = "sockmap", - [BPF_MAP_TYPE_CPUMAP] = "cpumap", - [BPF_MAP_TYPE_XSKMAP] = "xskmap", - [BPF_MAP_TYPE_SOCKHASH] = "sockhash", - [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", - [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", + [BPF_MAP_TYPE_UNSPEC] = "unspec", + [BPF_MAP_TYPE_HASH] = "hash", + [BPF_MAP_TYPE_ARRAY] = "array", + [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", + [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", + [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", + [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", + [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", + [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", + [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", + [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", + [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", + [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", + [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", + [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_SOCKMAP] = "sockmap", + [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_XSKMAP] = "xskmap", + [BPF_MAP_TYPE_SOCKHASH] = "sockhash", + [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", + [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", + [BPF_MAP_TYPE_QUEUE] = "queue", + [BPF_MAP_TYPE_STACK] = "stack", }; static bool map_is_per_cpu(__u32 type) @@ -215,70 +217,6 @@ err_end_obj: return ret; } -static int get_btf(struct bpf_map_info *map_info, struct btf **btf) -{ - struct bpf_btf_info btf_info = { 0 }; - __u32 len = sizeof(btf_info); - __u32 last_size; - int btf_fd; - void *ptr; - int err; - - err = 0; - *btf = NULL; - btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id); - if (btf_fd < 0) - return 0; - - /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so - * let's start with a sane default - 4KiB here - and resize it only if - * bpf_obj_get_info_by_fd() needs a bigger buffer. - */ - btf_info.btf_size = 4096; - last_size = btf_info.btf_size; - ptr = malloc(last_size); - if (!ptr) { - err = -ENOMEM; - goto exit_free; - } - - bzero(ptr, last_size); - btf_info.btf = ptr_to_u64(ptr); - err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); - - if (!err && btf_info.btf_size > last_size) { - void *temp_ptr; - - last_size = btf_info.btf_size; - temp_ptr = realloc(ptr, last_size); - if (!temp_ptr) { - err = -ENOMEM; - goto exit_free; - } - ptr = temp_ptr; - bzero(ptr, last_size); - btf_info.btf = ptr_to_u64(ptr); - err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); - } - - if (err || btf_info.btf_size > last_size) { - err = errno; - goto exit_free; - } - - *btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL); - if (IS_ERR(*btf)) { - err = PTR_ERR(*btf); - *btf = NULL; - } - -exit_free: - close(btf_fd); - free(ptr); - - return err; -} - static json_writer_t *get_btf_writer(void) { json_writer_t *jw = jsonw_new(stdout); @@ -383,7 +321,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, printf(single_line ? " " : "\n"); printf("value:%c", break_names ? '\n' : ' '); - fprint_hex(stdout, value, info->value_size, " "); + if (value) + fprint_hex(stdout, value, info->value_size, " "); + else + printf("<no entry>"); printf("\n"); } else { @@ -398,8 +339,11 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - fprint_hex(stdout, value + i * step, - info->value_size, " "); + if (value) + fprint_hex(stdout, value + i * step, + info->value_size, " "); + else + printf("<no entry>"); printf("\n"); } } @@ -731,7 +675,11 @@ static int dump_map_elem(int fd, void *key, void *value, jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); jsonw_end_object(json_wtr); } else { - print_entry_error(map_info, key, strerror(lookup_errno)); + if (errno == ENOENT) + print_entry_plain(map_info, key, NULL); + else + print_entry_error(map_info, key, + strerror(lookup_errno)); } return 0; @@ -765,7 +713,7 @@ static int do_dump(int argc, char **argv) prev_key = NULL; - err = get_btf(&info, &btf); + err = btf_get_from_id(info.btf_id, &btf); if (err) { p_err("failed to get btf"); goto exit_free; @@ -909,7 +857,7 @@ static int do_lookup(int argc, char **argv) } /* here means bpf_map_lookup_elem() succeeded */ - err = get_btf(&info, &btf); + err = btf_get_from_id(info.btf_id, &btf); if (err) { p_err("failed to get btf"); goto exit_free; @@ -1140,6 +1088,8 @@ static int do_create(int argc, char **argv) return -1; } + set_max_rlimit(); + fd = bpf_create_map_xattr(&attr); if (fd < 0) { p_err("map create failed: %s", strerror(errno)); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 5302ee282409e..37b1daf19da60 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -47,6 +47,7 @@ #include <linux/err.h> #include <bpf.h> +#include <btf.h> #include <libbpf.h> #include "cfg.h" @@ -81,6 +82,7 @@ static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", [BPF_SK_MSG_VERDICT] = "msg_verdict", + [BPF_FLOW_DISSECTOR] = "flow_dissector", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -450,14 +452,19 @@ static int do_dump(int argc, char **argv) struct bpf_prog_info info = {}; unsigned int *func_lens = NULL; const char *disasm_opt = NULL; + unsigned int finfo_rec_size; unsigned int nr_func_ksyms; unsigned int nr_func_lens; struct dump_data dd = {}; __u32 len = sizeof(info); + struct btf *btf = NULL; + void *func_info = NULL; + unsigned int finfo_cnt; unsigned int buf_size; char *filepath = NULL; bool opcodes = false; bool visual = false; + char func_sig[1024]; unsigned char *buf; __u32 *member_len; __u64 *member_ptr; @@ -466,6 +473,9 @@ static int do_dump(int argc, char **argv) int fd; if (is_prefix(*argv, "jited")) { + if (disasm_init()) + return -1; + member_len = &info.jited_prog_len; member_ptr = &info.jited_prog_insns; } else if (is_prefix(*argv, "xlated")) { @@ -547,6 +557,17 @@ static int do_dump(int argc, char **argv) } } + finfo_cnt = info.func_info_cnt; + finfo_rec_size = info.func_info_rec_size; + if (finfo_cnt && finfo_rec_size) { + func_info = malloc(finfo_cnt * finfo_rec_size); + if (!func_info) { + p_err("mem alloc failed"); + close(fd); + goto err_free; + } + } + memset(&info, 0, sizeof(info)); *member_ptr = ptr_to_u64(buf); @@ -555,6 +576,9 @@ static int do_dump(int argc, char **argv) info.nr_jited_ksyms = nr_func_ksyms; info.jited_func_lens = ptr_to_u64(func_lens); info.nr_jited_func_lens = nr_func_lens; + info.func_info_cnt = finfo_cnt; + info.func_info_rec_size = finfo_rec_size; + info.func_info = ptr_to_u64(func_info); err = bpf_obj_get_info_by_fd(fd, &info, &len); close(fd); @@ -578,6 +602,18 @@ static int do_dump(int argc, char **argv) goto err_free; } + if (info.func_info_cnt != finfo_cnt) { + p_err("incorrect func_info_cnt %d vs. expected %d", + info.func_info_cnt, finfo_cnt); + goto err_free; + } + + if (info.func_info_rec_size != finfo_rec_size) { + p_err("incorrect func_info_rec_size %d vs. expected %d", + info.func_info_rec_size, finfo_rec_size); + goto err_free; + } + if ((member_len == &info.jited_prog_len && info.jited_prog_insns == 0) || (member_len == &info.xlated_prog_len && @@ -586,6 +622,11 @@ static int do_dump(int argc, char **argv) goto err_free; } + if (info.btf_id && btf_get_from_id(info.btf_id, &btf)) { + p_err("failed to get btf"); + goto err_free; + } + if (filepath) { fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600); if (fd < 0) { @@ -618,6 +659,7 @@ static int do_dump(int argc, char **argv) if (info.nr_jited_func_lens && info.jited_func_lens) { struct kernel_sym *sym = NULL; + struct bpf_func_info *record; char sym_name[SYM_MAX_NAME]; unsigned char *img = buf; __u64 *ksyms = NULL; @@ -644,12 +686,25 @@ static int do_dump(int argc, char **argv) strcpy(sym_name, "unknown"); } + if (func_info) { + record = func_info + i * finfo_rec_size; + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + } + if (json_output) { jsonw_start_object(json_wtr); + if (func_info && func_sig[0] != '\0') { + jsonw_name(json_wtr, "proto"); + jsonw_string(json_wtr, func_sig); + } jsonw_name(json_wtr, "name"); jsonw_string(json_wtr, sym_name); jsonw_name(json_wtr, "insns"); } else { + if (func_info && func_sig[0] != '\0') + printf("%s:\n", func_sig); printf("%s:\n", sym_name); } @@ -678,6 +733,9 @@ static int do_dump(int argc, char **argv) kernel_syms_load(&dd); dd.nr_jited_ksyms = info.nr_jited_ksyms; dd.jited_ksyms = (__u64 *) info.jited_ksyms; + dd.btf = btf; + dd.func_info = func_info; + dd.finfo_rec_size = finfo_rec_size; if (json_output) dump_xlated_json(&dd, buf, *member_len, opcodes); @@ -689,12 +747,14 @@ static int do_dump(int argc, char **argv) free(buf); free(func_ksyms); free(func_lens); + free(func_info); return 0; err_free: free(buf); free(func_ksyms); free(func_lens); + free(func_info); return -1; } @@ -721,30 +781,49 @@ int map_replace_compar(const void *p1, const void *p2) return a->idx - b->idx; } -static int do_attach(int argc, char **argv) +static int parse_attach_detach_args(int argc, char **argv, int *progfd, + enum bpf_attach_type *attach_type, + int *mapfd) { - enum bpf_attach_type attach_type; - int err, mapfd, progfd; - - if (!REQ_ARGS(5)) { - p_err("too few parameters for map attach"); + if (!REQ_ARGS(3)) return -EINVAL; - } - progfd = prog_parse_fd(&argc, &argv); - if (progfd < 0) - return progfd; + *progfd = prog_parse_fd(&argc, &argv); + if (*progfd < 0) + return *progfd; - attach_type = parse_attach_type(*argv); - if (attach_type == __MAX_BPF_ATTACH_TYPE) { - p_err("invalid attach type"); + *attach_type = parse_attach_type(*argv); + if (*attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach/detach type"); return -EINVAL; } + + if (*attach_type == BPF_FLOW_DISSECTOR) { + *mapfd = -1; + return 0; + } + NEXT_ARG(); + if (!REQ_ARGS(2)) + return -EINVAL; - mapfd = map_parse_fd(&argc, &argv); - if (mapfd < 0) - return mapfd; + *mapfd = map_parse_fd(&argc, &argv); + if (*mapfd < 0) + return *mapfd; + + return 0; +} + +static int do_attach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int err, progfd; + int mapfd; + + err = parse_attach_detach_args(argc, argv, + &progfd, &attach_type, &mapfd); + if (err) + return err; err = bpf_prog_attach(progfd, mapfd, attach_type, 0); if (err) { @@ -760,27 +839,13 @@ static int do_attach(int argc, char **argv) static int do_detach(int argc, char **argv) { enum bpf_attach_type attach_type; - int err, mapfd, progfd; - - if (!REQ_ARGS(5)) { - p_err("too few parameters for map detach"); - return -EINVAL; - } + int err, progfd; + int mapfd; - progfd = prog_parse_fd(&argc, &argv); - if (progfd < 0) - return progfd; - - attach_type = parse_attach_type(*argv); - if (attach_type == __MAX_BPF_ATTACH_TYPE) { - p_err("invalid attach type"); - return -EINVAL; - } - NEXT_ARG(); - - mapfd = map_parse_fd(&argc, &argv); - if (mapfd < 0) - return mapfd; + err = parse_attach_detach_args(argc, argv, + &progfd, &attach_type, &mapfd); + if (err) + return err; err = bpf_prog_detach2(progfd, mapfd, attach_type); if (err) { @@ -792,15 +857,17 @@ static int do_detach(int argc, char **argv) jsonw_null(json_wtr); return 0; } -static int do_load(int argc, char **argv) + +static int load_with_options(int argc, char **argv, bool first_prog_only) { enum bpf_attach_type expected_attach_type; struct bpf_object_open_attr attr = { .prog_type = BPF_PROG_TYPE_UNSPEC, }; struct map_replace *map_replace = NULL; + struct bpf_program *prog = NULL, *pos; unsigned int old_map_fds = 0; - struct bpf_program *prog; + const char *pinmaps = NULL; struct bpf_object *obj; struct bpf_map *map; const char *pinfile; @@ -905,6 +972,13 @@ static int do_load(int argc, char **argv) goto err_free_reuse_maps; } NEXT_ARG(); + } else if (is_prefix(*argv, "pinmaps")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + pinmaps = GET_ARG(); } else { p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?", *argv); @@ -918,26 +992,25 @@ static int do_load(int argc, char **argv) goto err_free_reuse_maps; } - prog = bpf_program__next(NULL, obj); - if (!prog) { - p_err("object file doesn't contain any bpf program"); - goto err_close_obj; - } + bpf_object__for_each_program(pos, obj) { + enum bpf_prog_type prog_type = attr.prog_type; - bpf_program__set_ifindex(prog, ifindex); - if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) { - const char *sec_name = bpf_program__title(prog, false); + if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) { + const char *sec_name = bpf_program__title(pos, false); - err = libbpf_prog_type_by_name(sec_name, &attr.prog_type, - &expected_attach_type); - if (err < 0) { - p_err("failed to guess program type based on section name %s\n", - sec_name); - goto err_close_obj; + err = libbpf_prog_type_by_name(sec_name, &prog_type, + &expected_attach_type); + if (err < 0) { + p_err("failed to guess program type based on section name %s\n", + sec_name); + goto err_close_obj; + } } + + bpf_program__set_ifindex(pos, ifindex); + bpf_program__set_type(pos, prog_type); + bpf_program__set_expected_attach_type(pos, expected_attach_type); } - bpf_program__set_type(prog, attr.prog_type); - bpf_program__set_expected_attach_type(prog, expected_attach_type); qsort(map_replace, old_map_fds, sizeof(*map_replace), map_replace_compar); @@ -995,15 +1068,47 @@ static int do_load(int argc, char **argv) goto err_close_obj; } + set_max_rlimit(); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto err_close_obj; } - if (do_pin_fd(bpf_program__fd(prog), pinfile)) + err = mount_bpffs_for_pin(pinfile); + if (err) goto err_close_obj; + if (first_prog_only) { + prog = bpf_program__next(NULL, obj); + if (!prog) { + p_err("object file doesn't contain any bpf program"); + goto err_close_obj; + } + + err = bpf_obj_pin(bpf_program__fd(prog), pinfile); + if (err) { + p_err("failed to pin program %s", + bpf_program__title(prog, false)); + goto err_close_obj; + } + } else { + err = bpf_object__pin_programs(obj, pinfile); + if (err) { + p_err("failed to pin all programs"); + goto err_close_obj; + } + } + + if (pinmaps) { + err = bpf_object__pin_maps(obj, pinmaps); + if (err) { + p_err("failed to pin all maps"); + goto err_unpin; + } + } + if (json_output) jsonw_null(json_wtr); @@ -1014,6 +1119,11 @@ static int do_load(int argc, char **argv) return 0; +err_unpin: + if (first_prog_only) + unlink(pinfile); + else + bpf_object__unpin_programs(obj, pinfile); err_close_obj: bpf_object__close(obj); err_free_reuse_maps: @@ -1023,6 +1133,16 @@ err_free_reuse_maps: return -1; } +static int do_load(int argc, char **argv) +{ + return load_with_options(argc, argv, true); +} + +static int do_loadall(int argc, char **argv) +{ + return load_with_options(argc, argv, false); +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -1035,10 +1155,12 @@ static int do_help(int argc, char **argv) " %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n" " %s %s dump jited PROG [{ file FILE | opcodes }]\n" " %s %s pin PROG FILE\n" - " %s %s load OBJ FILE [type TYPE] [dev NAME] \\\n" - " [map { idx IDX | name NAME } MAP]\n" - " %s %s attach PROG ATTACH_TYPE MAP\n" - " %s %s detach PROG ATTACH_TYPE MAP\n" + " %s %s { load | loadall } OBJ PATH \\\n" + " [type TYPE] [dev NAME] \\\n" + " [map { idx IDX | name NAME } MAP]\\\n" + " [pinmaps MAP_DIR]\n" + " %s %s attach PROG ATTACH_TYPE [MAP]\n" + " %s %s detach PROG ATTACH_TYPE [MAP]\n" " %s %s help\n" "\n" " " HELP_SPEC_MAP "\n" @@ -1050,7 +1172,8 @@ static int do_help(int argc, char **argv) " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" " cgroup/sendmsg4 | cgroup/sendmsg6 }\n" - " ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse }\n" + " ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse |\n" + " flow_dissector }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], @@ -1067,6 +1190,7 @@ static const struct cmd cmds[] = { { "dump", do_dump }, { "pin", do_pin }, { "load", do_load }, + { "loadall", do_loadall }, { "attach", do_attach }, { "detach", do_detach }, { 0 } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 3284759df98ad..e06ac0286a750 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -242,11 +242,15 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, .cb_imm = print_imm, .private_data = dd, }; + struct bpf_func_info *record; struct bpf_insn *insn = buf; + struct btf *btf = dd->btf; bool double_insn = false; + char func_sig[1024]; unsigned int i; jsonw_start_array(json_wtr); + record = dd->func_info; for (i = 0; i < len / sizeof(*insn); i++) { if (double_insn) { double_insn = false; @@ -255,6 +259,20 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); jsonw_start_object(json_wtr); + + if (btf && record) { + if (record->insn_offset == i) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') { + jsonw_name(json_wtr, "proto"); + jsonw_string(json_wtr, func_sig); + } + record = (void *)record + dd->finfo_rec_size; + } + } + jsonw_name(json_wtr, "disasm"); print_bpf_insn(&cbs, insn + i, true); @@ -297,16 +315,31 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, .cb_imm = print_imm, .private_data = dd, }; + struct bpf_func_info *record; struct bpf_insn *insn = buf; + struct btf *btf = dd->btf; bool double_insn = false; + char func_sig[1024]; unsigned int i; + record = dd->func_info; for (i = 0; i < len / sizeof(*insn); i++) { if (double_insn) { double_insn = false; continue; } + if (btf && record) { + if (record->insn_offset == i) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') + printf("%s:\n", func_sig); + record = (void *)record + dd->finfo_rec_size; + } + } + double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); printf("% 4d: ", i); diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h index 33d86e2b369b7..aec31723e1e5d 100644 --- a/tools/bpf/bpftool/xlated_dumper.h +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -51,6 +51,9 @@ struct dump_data { __u32 sym_count; __u64 *jited_ksyms; __u32 nr_jited_ksyms; + struct btf *btf; + void *func_info; + __u32 finfo_rec_size; char scratch_buff[SYM_MAX_NAME + 8]; }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 852dc17ab47a0..23e2031a43d43 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -257,9 +257,6 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) -/* flags for BPF_PROG_QUERY */ -#define BPF_F_QUERY_EFFECTIVE (1U << 0) - #define BPF_OBJ_NAME_LEN 16U /* Flags for accessing BPF object */ @@ -269,6 +266,12 @@ enum bpf_attach_type { /* Flag for stack_map, store build_id+offset instead of pointer */ #define BPF_F_STACK_BUILD_ID (1U << 5) +/* Zero-initialize hash function seed. This should only be used for testing. */ +#define BPF_F_ZERO_SEED (1U << 6) + +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + enum bpf_stack_build_id_status { /* user space need an empty entry to identify end of a trace */ BPF_STACK_BUILD_ID_EMPTY = 0, @@ -335,6 +338,10 @@ union bpf_attr { * (context accesses, allowed helpers, etc). */ __u32 expected_attach_type; + __u32 prog_btf_fd; /* fd pointing to BTF type data */ + __u32 func_info_rec_size; /* userspace bpf_func_info size */ + __aligned_u64 func_info; /* func info */ + __u32 func_info_cnt; /* number of bpf_func_info records */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -2201,6 +2208,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, *struct bpf_sock* + * return is from reuse->socks[] using hash of the packet. * * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) * Description @@ -2233,6 +2242,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, *struct bpf_sock* + * return is from reuse->socks[] using hash of the packet. * * int bpf_sk_release(struct bpf_sock *sk) * Description @@ -2457,6 +2468,7 @@ struct __sk_buff { __u32 data_meta; struct bpf_flow_keys *flow_keys; + __u64 tstamp; }; struct bpf_tunnel_key { @@ -2631,6 +2643,10 @@ struct bpf_prog_info { __u32 nr_jited_func_lens; __aligned_u64 jited_ksyms; __aligned_u64 jited_func_lens; + __u32 btf_id; + __u32 func_info_rec_size; + __aligned_u64 func_info; + __u32 func_info_cnt; } __attribute__((aligned(8))); struct bpf_map_info { @@ -2942,4 +2958,9 @@ struct bpf_flow_keys { }; }; +struct bpf_func_info { + __u32 insn_offset; + __u32 type_id; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 972265f328717..14f66948fc95f 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -40,7 +40,8 @@ struct btf_type { /* "size" is used by INT, ENUM, STRUCT and UNION. * "size" tells the size of the type it is describing. * - * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, + * FUNC and FUNC_PROTO. * "type" is a type_id referring to another type. */ union { @@ -64,8 +65,10 @@ struct btf_type { #define BTF_KIND_VOLATILE 9 /* Volatile */ #define BTF_KIND_CONST 10 /* Const */ #define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_MAX 11 -#define NR_BTF_KINDS 12 +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#define BTF_KIND_MAX 13 +#define NR_BTF_KINDS 14 /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -110,4 +113,13 @@ struct btf_member { __u32 offset; /* offset in bits */ }; +/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param". + * The exact number of btf_param is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_param { + __u32 name_off; + __u32 type; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 425b480bda752..1b4a683a00fc4 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -66,7 +66,7 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-mmap bpf reallocarray +FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx FEATURE_DISPLAY = libelf bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi @@ -148,6 +148,12 @@ LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) CMD_TARGETS = $(LIB_FILE) +CXX_TEST_TARGET = $(OUTPUT)test_libbpf + +ifeq ($(feature-cxx), 1) + CMD_TARGETS += $(CXX_TEST_TARGET) +endif + TARGETS = $(CMD_TARGETS) all: fixdep all_cmd @@ -175,6 +181,9 @@ $(OUTPUT)libbpf.so: $(BPF_IN) $(OUTPUT)libbpf.a: $(BPF_IN) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ +$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a + $(QUIET_LINK)$(CXX) $^ -lelf -o $@ + define do_install if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ @@ -201,8 +210,8 @@ config-clean: $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: - $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so .*.d .*.cmd \ - $(RM) LIBBPF-CFLAGS + $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ + *.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 03f9bcc4ef501..ce18221945900 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -177,6 +177,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, char *log_buf, size_t log_buf_sz) { union bpf_attr attr; + void *finfo = NULL; __u32 name_len; int fd; @@ -196,6 +197,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, attr.log_level = 0; attr.kern_version = load_attr->kern_version; attr.prog_ifindex = load_attr->prog_ifindex; + attr.prog_btf_fd = load_attr->prog_btf_fd; + attr.func_info_rec_size = load_attr->func_info_rec_size; + attr.func_info_cnt = load_attr->func_info_cnt; + attr.func_info = ptr_to_u64(load_attr->func_info); memcpy(attr.prog_name, load_attr->name, min(name_len, BPF_OBJ_NAME_LEN - 1)); @@ -203,12 +208,55 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, if (fd >= 0 || !log_buf || !log_buf_sz) return fd; + /* After bpf_prog_load, the kernel may modify certain attributes + * to give user space a hint how to deal with loading failure. + * Check to see whether we can make some changes and load again. + */ + if (errno == E2BIG && attr.func_info_cnt && + attr.func_info_rec_size < load_attr->func_info_rec_size) { + __u32 actual_rec_size = load_attr->func_info_rec_size; + __u32 expected_rec_size = attr.func_info_rec_size; + __u32 finfo_cnt = load_attr->func_info_cnt; + __u64 finfo_len = actual_rec_size * finfo_cnt; + const void *orecord; + void *nrecord; + int i; + + finfo = malloc(finfo_len); + if (!finfo) + /* further try with log buffer won't help */ + return fd; + + /* zero out bytes kernel does not understand */ + orecord = load_attr->func_info; + nrecord = finfo; + for (i = 0; i < load_attr->func_info_cnt; i++) { + memcpy(nrecord, orecord, expected_rec_size); + memset(nrecord + expected_rec_size, 0, + actual_rec_size - expected_rec_size); + orecord += actual_rec_size; + nrecord += actual_rec_size; + } + + /* try with corrected func info records */ + attr.func_info = ptr_to_u64(finfo); + attr.func_info_rec_size = load_attr->func_info_rec_size; + + fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + + if (fd >= 0 || !log_buf || !log_buf_sz) + goto done; + } + /* Try again with log */ attr.log_buf = ptr_to_u64(log_buf); attr.log_size = log_buf_sz; attr.log_level = 1; log_buf[0] = 0; - return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); +done: + free(finfo); + return fd; } int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 26a51538213cd..09e8bbe111d4c 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -27,6 +27,10 @@ #include <stdbool.h> #include <stddef.h> +#ifdef __cplusplus +extern "C" { +#endif + #ifndef LIBBPF_API #define LIBBPF_API __attribute__((visibility("default"))) #endif @@ -74,6 +78,10 @@ struct bpf_load_program_attr { const char *license; __u32 kern_version; __u32 prog_ifindex; + __u32 prog_btf_fd; + __u32 func_info_rec_size; + const void *func_info; + __u32 func_info_cnt; }; /* Flags to direct loading requirements */ @@ -128,4 +136,9 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + #endif /* __LIBBPF_BPF_H */ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 449591aa99000..13ddc4bd24ee3 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -37,6 +37,23 @@ struct btf { int fd; }; +struct btf_ext { + void *func_info; + __u32 func_info_rec_size; + __u32 func_info_len; +}; + +/* The minimum bpf_func_info checked by the loader */ +struct bpf_func_info_min { + __u32 insn_offset; + __u32 type_id; +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + static int btf_add_type(struct btf *btf, struct btf_type *t) { if (btf->types_size - btf->nr_types < 2) { @@ -165,6 +182,10 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) case BTF_KIND_ENUM: next_type += vlen * sizeof(struct btf_enum); break; + case BTF_KIND_FUNC_PROTO: + next_type += vlen * sizeof(struct btf_param); + break; + case BTF_KIND_FUNC: case BTF_KIND_TYPEDEF: case BTF_KIND_PTR: case BTF_KIND_FWD: @@ -393,3 +414,329 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset) else return NULL; } + +int btf_get_from_id(__u32 id, struct btf **btf) +{ + struct bpf_btf_info btf_info = { 0 }; + __u32 len = sizeof(btf_info); + __u32 last_size; + int btf_fd; + void *ptr; + int err; + + err = 0; + *btf = NULL; + btf_fd = bpf_btf_get_fd_by_id(id); + if (btf_fd < 0) + return 0; + + /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so + * let's start with a sane default - 4KiB here - and resize it only if + * bpf_obj_get_info_by_fd() needs a bigger buffer. + */ + btf_info.btf_size = 4096; + last_size = btf_info.btf_size; + ptr = malloc(last_size); + if (!ptr) { + err = -ENOMEM; + goto exit_free; + } + + bzero(ptr, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + + if (!err && btf_info.btf_size > last_size) { + void *temp_ptr; + + last_size = btf_info.btf_size; + temp_ptr = realloc(ptr, last_size); + if (!temp_ptr) { + err = -ENOMEM; + goto exit_free; + } + ptr = temp_ptr; + bzero(ptr, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + } + + if (err || btf_info.btf_size > last_size) { + err = errno; + goto exit_free; + } + + *btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL); + if (IS_ERR(*btf)) { + err = PTR_ERR(*btf); + *btf = NULL; + } + +exit_free: + close(btf_fd); + free(ptr); + + return err; +} + +static int btf_ext_validate_func_info(const void *finfo, __u32 size, + btf_print_fn_t err_log) +{ + int sec_hdrlen = sizeof(struct btf_sec_func_info); + __u32 size_left, num_records, record_size; + const struct btf_sec_func_info *sinfo; + __u64 total_record_size; + + /* At least a func_info record size */ + if (size < sizeof(__u32)) { + elog("BTF.ext func_info record size not found"); + return -EINVAL; + } + + /* The record size needs to meet below minimum standard */ + record_size = *(__u32 *)finfo; + if (record_size < sizeof(struct bpf_func_info_min) || + record_size % sizeof(__u32)) { + elog("BTF.ext func_info invalid record size"); + return -EINVAL; + } + + sinfo = finfo + sizeof(__u32); + size_left = size - sizeof(__u32); + + /* If no func_info records, return failure now so .BTF.ext + * won't be used. + */ + if (!size_left) { + elog("BTF.ext no func info records"); + return -EINVAL; + } + + while (size_left) { + if (size_left < sec_hdrlen) { + elog("BTF.ext func_info header not found"); + return -EINVAL; + } + + num_records = sinfo->num_func_info; + if (num_records == 0) { + elog("incorrect BTF.ext num_func_info"); + return -EINVAL; + } + + total_record_size = sec_hdrlen + + (__u64)num_records * record_size; + if (size_left < total_record_size) { + elog("incorrect BTF.ext num_func_info"); + return -EINVAL; + } + + size_left -= total_record_size; + sinfo = (void *)sinfo + total_record_size; + } + + return 0; +} + +static int btf_ext_parse_hdr(__u8 *data, __u32 data_size, + btf_print_fn_t err_log) +{ + const struct btf_ext_header *hdr = (struct btf_ext_header *)data; + __u32 meta_left, last_func_info_pos; + void *finfo; + + if (data_size < offsetof(struct btf_ext_header, func_info_off) || + data_size < hdr->hdr_len) { + elog("BTF.ext header not found"); + return -EINVAL; + } + + if (hdr->magic != BTF_MAGIC) { + elog("Invalid BTF.ext magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + elog("Unsupported BTF.ext version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + elog("Unsupported BTF.ext flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + meta_left = data_size - hdr->hdr_len; + if (!meta_left) { + elog("BTF.ext has no data\n"); + return -EINVAL; + } + + if (meta_left < hdr->func_info_off) { + elog("Invalid BTF.ext func_info section offset:%u\n", + hdr->func_info_off); + return -EINVAL; + } + + if (hdr->func_info_off & 0x03) { + elog("BTF.ext func_info section is not aligned to 4 bytes\n"); + return -EINVAL; + } + + last_func_info_pos = hdr->hdr_len + hdr->func_info_off + + hdr->func_info_len; + if (last_func_info_pos > data_size) { + elog("Invalid BTF.ext func_info section size:%u\n", + hdr->func_info_len); + return -EINVAL; + } + + finfo = data + hdr->hdr_len + hdr->func_info_off; + return btf_ext_validate_func_info(finfo, hdr->func_info_len, + err_log); +} + +void btf_ext__free(struct btf_ext *btf_ext) +{ + if (!btf_ext) + return; + + free(btf_ext->func_info); + free(btf_ext); +} + +struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log) +{ + const struct btf_ext_header *hdr; + struct btf_ext *btf_ext; + void *org_fdata, *fdata; + __u32 hdrlen, size_u32; + int err; + + err = btf_ext_parse_hdr(data, size, err_log); + if (err) + return ERR_PTR(err); + + btf_ext = calloc(1, sizeof(struct btf_ext)); + if (!btf_ext) + return ERR_PTR(-ENOMEM); + + hdr = (const struct btf_ext_header *)data; + hdrlen = hdr->hdr_len; + size_u32 = sizeof(__u32); + fdata = malloc(hdr->func_info_len - size_u32); + if (!fdata) { + free(btf_ext); + return ERR_PTR(-ENOMEM); + } + + /* remember record size and copy rest of func_info data */ + org_fdata = data + hdrlen + hdr->func_info_off; + btf_ext->func_info_rec_size = *(__u32 *)org_fdata; + memcpy(fdata, org_fdata + size_u32, hdr->func_info_len - size_u32); + btf_ext->func_info = fdata; + btf_ext->func_info_len = hdr->func_info_len - size_u32; + + return btf_ext; +} + +int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext, + const char *sec_name, void **func_info, + __u32 *func_info_rec_size, __u32 *func_info_len) +{ + __u32 sec_hdrlen = sizeof(struct btf_sec_func_info); + __u32 i, record_size, records_len; + struct btf_sec_func_info *sinfo; + const char *info_sec_name; + __s64 remain_len; + void *data; + + record_size = btf_ext->func_info_rec_size; + sinfo = btf_ext->func_info; + remain_len = btf_ext->func_info_len; + + while (remain_len > 0) { + records_len = sinfo->num_func_info * record_size; + info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off); + if (strcmp(info_sec_name, sec_name)) { + remain_len -= sec_hdrlen + records_len; + sinfo = (void *)sinfo + sec_hdrlen + records_len; + continue; + } + + data = malloc(records_len); + if (!data) + return -ENOMEM; + + memcpy(data, sinfo->data, records_len); + + /* adjust the insn_offset, the data in .BTF.ext is + * the actual byte offset, and the kernel expects + * the offset in term of bpf_insn. + * + * adjust the insn offset only, the rest data will + * be passed to kernel. + */ + for (i = 0; i < sinfo->num_func_info; i++) { + struct bpf_func_info_min *record; + + record = data + i * record_size; + record->insn_offset /= sizeof(struct bpf_insn); + } + + *func_info = data; + *func_info_len = records_len; + *func_info_rec_size = record_size; + return 0; + } + + return -EINVAL; +} + +int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, + void **func_info, __u32 *func_info_len) +{ + __u32 sec_hdrlen = sizeof(struct btf_sec_func_info); + __u32 i, record_size, existing_flen, records_len; + struct btf_sec_func_info *sinfo; + const char *info_sec_name; + __u64 remain_len; + void *data; + + record_size = btf_ext->func_info_rec_size; + sinfo = btf_ext->func_info; + remain_len = btf_ext->func_info_len; + while (remain_len > 0) { + records_len = sinfo->num_func_info * record_size; + info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off); + if (strcmp(info_sec_name, sec_name)) { + remain_len -= sec_hdrlen + records_len; + sinfo = (void *)sinfo + sec_hdrlen + records_len; + continue; + } + + existing_flen = *func_info_len; + data = realloc(*func_info, existing_flen + records_len); + if (!data) + return -ENOMEM; + + memcpy(data + existing_flen, sinfo->data, records_len); + /* adjust insn_offset only, the rest data will be passed + * to the kernel. + */ + for (i = 0; i < sinfo->num_func_info; i++) { + struct bpf_func_info_min *record; + + record = data + existing_flen + i * record_size; + record->insn_offset = + record->insn_offset / sizeof(struct bpf_insn) + + insns_cnt; + } + *func_info = data; + *func_info_len = existing_flen + records_len; + return 0; + } + + return -EINVAL; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index b77e7080f7e73..701ad2b6c41fe 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -6,15 +6,60 @@ #include <linux/types.h> +#ifdef __cplusplus +extern "C" { +#endif + #ifndef LIBBPF_API #define LIBBPF_API __attribute__((visibility("default"))) #endif #define BTF_ELF_SEC ".BTF" +#define BTF_EXT_ELF_SEC ".BTF.ext" struct btf; +struct btf_ext; struct btf_type; +/* + * The .BTF.ext ELF section layout defined as + * struct btf_ext_header + * func_info subsection + * + * The func_info subsection layout: + * record size for struct bpf_func_info in the func_info subsection + * struct btf_sec_func_info for section #1 + * a list of bpf_func_info records for section #1 + * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h + * but may not be identical + * struct btf_sec_func_info for section #2 + * a list of bpf_func_info records for section #2 + * ...... + * + * Note that the bpf_func_info record size in .BTF.ext may not + * be the same as the one defined in include/uapi/linux/bpf.h. + * The loader should ensure that record_size meets minimum + * requirement and pass the record as is to the kernel. The + * kernel will handle the func_info properly based on its contents. + */ +struct btf_ext_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 func_info_off; + __u32 func_info_len; +}; + +struct btf_sec_func_info { + __u32 sec_name_off; + __u32 num_func_info; + /* Followed by num_func_info number of bpf func_info records */ + __u8 data[0]; +}; + typedef int (*btf_print_fn_t)(const char *, ...) __attribute__((format(printf, 1, 2))); @@ -28,5 +73,19 @@ LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); +LIBBPF_API int btf_get_from_id(__u32 id, struct btf **btf); + +struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log); +void btf_ext__free(struct btf_ext *btf_ext); +int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext, + const char *sec_name, void **func_info, + __u32 *func_info_rec_size, __u32 *func_info_len); +int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, void **func_info, + __u32 *func_info_len); + +#ifdef __cplusplus +} /* extern "C" */ +#endif #endif /* __LIBBPF_BTF_H */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d6e62e90e8d44..ed4212a4c5f96 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -24,6 +24,7 @@ #include <linux/kernel.h> #include <linux/bpf.h> #include <linux/btf.h> +#include <linux/filter.h> #include <linux/list.h> #include <linux/limits.h> #include <linux/perf_event.h> @@ -114,6 +115,11 @@ void libbpf_set_print(libbpf_print_fn_t warn, # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ #endif +struct bpf_capabilities { + /* v4.14: kernel support for program & map names. */ + __u32 name:1; +}; + /* * bpf_prog should be a better name but it has been used in * linux/filter.h. @@ -124,6 +130,10 @@ struct bpf_program { char *name; int prog_ifindex; char *section_name; + /* section_name with / replaced by _; makes recursive pinning + * in bpf_object__pin_programs easier + */ + char *pin_name; struct bpf_insn *insns; size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; @@ -152,6 +162,12 @@ struct bpf_program { bpf_program_clear_priv_t clear_priv; enum bpf_attach_type expected_attach_type; + int btf_fd; + void *func_info; + __u32 func_info_rec_size; + __u32 func_info_len; + + struct bpf_capabilities *caps; }; struct bpf_map { @@ -159,6 +175,7 @@ struct bpf_map { char *name; size_t offset; int map_ifindex; + int inner_map_fd; struct bpf_map_def def; __u32 btf_key_type_id; __u32 btf_value_type_id; @@ -208,10 +225,13 @@ struct bpf_object { struct list_head list; struct btf *btf; + struct btf_ext *btf_ext; void *priv; bpf_object_clear_priv_t clear_priv; + struct bpf_capabilities caps; + char path[]; }; #define obj_elf_valid(o) ((o)->efile.elf) @@ -237,6 +257,9 @@ void bpf_program__unload(struct bpf_program *prog) prog->instances.nr = -1; zfree(&prog->instances.fds); + + zclose(prog->btf_fd); + zfree(&prog->func_info); } static void bpf_program__exit(struct bpf_program *prog) @@ -253,6 +276,7 @@ static void bpf_program__exit(struct bpf_program *prog) bpf_program__unload(prog); zfree(&prog->name); zfree(&prog->section_name); + zfree(&prog->pin_name); zfree(&prog->insns); zfree(&prog->reloc_desc); @@ -261,6 +285,17 @@ static void bpf_program__exit(struct bpf_program *prog) prog->idx = -1; } +static char *__bpf_program__pin_name(struct bpf_program *prog) +{ + char *name, *p; + + name = p = strdup(prog->section_name); + while ((p = strchr(p, '/'))) + *p = '_'; + + return name; +} + static int bpf_program__init(void *data, size_t size, char *section_name, int idx, struct bpf_program *prog) @@ -279,6 +314,13 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, goto errout; } + prog->pin_name = __bpf_program__pin_name(prog); + if (!prog->pin_name) { + pr_warning("failed to alloc pin name for prog under section(%d) %s\n", + idx, section_name); + goto errout; + } + prog->insns = malloc(size); if (!prog->insns) { pr_warning("failed to alloc insns for prog under section %s\n", @@ -291,7 +333,8 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, prog->idx = idx; prog->instances.fds = NULL; prog->instances.nr = -1; - prog->type = BPF_PROG_TYPE_KPROBE; + prog->type = BPF_PROG_TYPE_UNSPEC; + prog->btf_fd = -1; return 0; errout: @@ -310,6 +353,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, if (err) return err; + prog.caps = &obj->caps; progs = obj->programs; nr_progs = obj->nr_programs; @@ -562,6 +606,14 @@ static int compare_bpf_map(const void *_a, const void *_b) return a->offset - b->offset; } +static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) +{ + if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + type == BPF_MAP_TYPE_HASH_OF_MAPS) + return true; + return false; +} + static int bpf_object__init_maps(struct bpf_object *obj, int flags) { @@ -625,13 +677,15 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) } obj->nr_maps = nr_maps; - /* - * fill all fd with -1 so won't close incorrect - * fd (fd=0 is stdin) when failure (zclose won't close - * negative fd)). - */ - for (i = 0; i < nr_maps; i++) + for (i = 0; i < nr_maps; i++) { + /* + * fill all fd with -1 so won't close incorrect + * fd (fd=0 is stdin) when failure (zclose won't close + * negative fd)). + */ obj->maps[i].fd = -1; + obj->maps[i].inner_map_fd = -1; + } /* * Fill obj->maps using data in "maps" section. @@ -784,6 +838,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) BTF_ELF_SEC, PTR_ERR(obj->btf)); obj->btf = NULL; } + } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { + obj->btf_ext = btf_ext__new(data->d_buf, data->d_size, + __pr_debug); + if (IS_ERR(obj->btf_ext)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_EXT_ELF_SEC, + PTR_ERR(obj->btf_ext)); + obj->btf_ext = NULL; + } } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", @@ -1095,6 +1158,52 @@ err_free_new_name: } static int +bpf_object__probe_name(struct bpf_object *obj) +{ + struct bpf_load_program_attr attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret; + + /* make sure basic loading works */ + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = insns; + attr.insns_cnt = ARRAY_SIZE(insns); + attr.license = "GPL"; + + ret = bpf_load_program_xattr(&attr, NULL, 0); + if (ret < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n", + __func__, cp, errno); + return -errno; + } + close(ret); + + /* now try the same program, but with the name */ + + attr.name = "test"; + ret = bpf_load_program_xattr(&attr, NULL, 0); + if (ret >= 0) { + obj->caps.name = 1; + close(ret); + } + + return 0; +} + +static int +bpf_object__probe_caps(struct bpf_object *obj) +{ + return bpf_object__probe_name(obj); +} + +static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_create_map_attr create_attr = {}; @@ -1113,7 +1222,8 @@ bpf_object__create_maps(struct bpf_object *obj) continue; } - create_attr.name = map->name; + if (obj->caps.name) + create_attr.name = map->name; create_attr.map_ifindex = map->map_ifindex; create_attr.map_type = def->type; create_attr.map_flags = def->map_flags; @@ -1123,6 +1233,9 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; + if (bpf_map_type__is_map_in_map(def->type) && + map->inner_map_fd >= 0) + create_attr.inner_map_fd = map->inner_map_fd; if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { create_attr.btf_fd = btf__fd(obj->btf); @@ -1167,6 +1280,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, struct bpf_insn *insn, *new_insn; struct bpf_program *text; size_t new_cnt; + int err; if (relo->type != RELO_CALL) return -LIBBPF_ERRNO__RELOC; @@ -1189,6 +1303,20 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, pr_warning("oom in prog realloc\n"); return -ENOMEM; } + + if (obj->btf && obj->btf_ext) { + err = btf_ext__reloc(obj->btf, obj->btf_ext, + text->section_name, + prog->insns_cnt, + &prog->func_info, + &prog->func_info_len); + if (err) { + pr_warning("error in btf_ext__reloc for sec %s\n", + text->section_name); + return err; + } + } + memcpy(new_insn + prog->insns_cnt, text->insns, text->insns_cnt * sizeof(*insn)); prog->insns = new_insn; @@ -1208,7 +1336,24 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) { int i, err; - if (!prog || !prog->reloc_desc) + if (!prog) + return 0; + + if (obj->btf && obj->btf_ext) { + err = btf_ext__reloc_init(obj->btf, obj->btf_ext, + prog->section_name, + &prog->func_info, + &prog->func_info_rec_size, + &prog->func_info_len); + if (err) { + pr_warning("err in btf_ext__reloc_init for sec %s\n", + prog->section_name); + return err; + } + prog->btf_fd = btf__fd(obj->btf); + } + + if (!prog->reloc_desc) return 0; for (i = 0; i < prog->nr_reloc; i++) { @@ -1296,9 +1441,9 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) } static int -load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, - const char *name, struct bpf_insn *insns, int insns_cnt, - char *license, __u32 kern_version, int *pfd, int prog_ifindex) +load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, + char *license, __u32 kern_version, int *pfd, + __u32 func_info_cnt) { struct bpf_load_program_attr load_attr; char *cp, errmsg[STRERR_BUFSIZE]; @@ -1306,14 +1451,19 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, int ret; memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); - load_attr.prog_type = type; - load_attr.expected_attach_type = expected_attach_type; - load_attr.name = name; + load_attr.prog_type = prog->type; + load_attr.expected_attach_type = prog->expected_attach_type; + if (prog->caps->name) + load_attr.name = prog->name; load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = license; load_attr.kern_version = kern_version; - load_attr.prog_ifindex = prog_ifindex; + load_attr.prog_ifindex = prog->prog_ifindex; + load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0; + load_attr.func_info = prog->func_info; + load_attr.func_info_rec_size = prog->func_info_rec_size; + load_attr.func_info_cnt = func_info_cnt; if (!load_attr.insns || !load_attr.insns_cnt) return -EINVAL; @@ -1371,8 +1521,14 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_version) { + __u32 func_info_cnt; int err = 0, fd, i; + if (prog->func_info_len == 0) + func_info_cnt = 0; + else + func_info_cnt = prog->func_info_len / prog->func_info_rec_size; + if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { pr_warning("Internal error: can't load program '%s'\n", @@ -1394,10 +1550,9 @@ bpf_program__load(struct bpf_program *prog, pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n", prog->section_name, prog->instances.nr); } - err = load_program(prog->type, prog->expected_attach_type, - prog->name, prog->insns, prog->insns_cnt, + err = load_program(prog, prog->insns, prog->insns_cnt, license, kern_version, &fd, - prog->prog_ifindex); + func_info_cnt); if (!err) prog->instances.fds[0] = fd; goto out; @@ -1425,11 +1580,10 @@ bpf_program__load(struct bpf_program *prog, continue; } - err = load_program(prog->type, prog->expected_attach_type, - prog->name, result.new_insn_ptr, + err = load_program(prog, result.new_insn_ptr, result.new_insn_cnt, license, kern_version, &fd, - prog->prog_ifindex); + func_info_cnt); if (err) { pr_warning("Loading the %dth instance of program '%s' failed\n", @@ -1495,12 +1649,12 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: - return false; case BPF_PROG_TYPE_UNSPEC: - case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: - case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + return false; + case BPF_PROG_TYPE_KPROBE: default: return true; } @@ -1627,6 +1781,7 @@ int bpf_object__load(struct bpf_object *obj) obj->loaded = true; + CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__create_maps(obj), err, out); CHECK_ERR(bpf_object__relocate(obj), err, out); CHECK_ERR(bpf_object__load_progs(obj), err, out); @@ -1699,6 +1854,34 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, return 0; } +int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, + int instance) +{ + int err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (instance < 0 || instance >= prog->instances.nr) { + pr_warning("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + err = unlink(path); + if (err != 0) + return -errno; + pr_debug("unpinned program '%s'\n", path); + + return 0; +} + static int make_dir(const char *path) { char *cp, errmsg[STRERR_BUFSIZE]; @@ -1733,6 +1916,11 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) return -EINVAL; } + if (prog->instances.nr == 1) { + /* don't create subdirs when pinning single instance */ + return bpf_program__pin_instance(prog, path, 0); + } + err = make_dir(path); if (err) return err; @@ -1742,16 +1930,83 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) int len; len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) { + err = -EINVAL; + goto err_unpin; + } else if (len >= PATH_MAX) { + err = -ENAMETOOLONG; + goto err_unpin; + } + + err = bpf_program__pin_instance(prog, buf, i); + if (err) + goto err_unpin; + } + + return 0; + +err_unpin: + for (i = i - 1; i >= 0; i--) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) + continue; + else if (len >= PATH_MAX) + continue; + + bpf_program__unpin_instance(prog, buf, i); + } + + rmdir(path); + + return err; +} + +int bpf_program__unpin(struct bpf_program *prog, const char *path) +{ + int i, err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (prog->instances.nr <= 0) { + pr_warning("no instances of prog %s to pin\n", + prog->section_name); + return -EINVAL; + } + + if (prog->instances.nr == 1) { + /* don't create subdirs when pinning single instance */ + return bpf_program__unpin_instance(prog, path, 0); + } + + for (i = 0; i < prog->instances.nr; i++) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); if (len < 0) return -EINVAL; else if (len >= PATH_MAX) return -ENAMETOOLONG; - err = bpf_program__pin_instance(prog, buf, i); + err = bpf_program__unpin_instance(prog, buf, i); if (err) return err; } + err = rmdir(path); + if (err) + return -errno; + return 0; } @@ -1776,12 +2031,33 @@ int bpf_map__pin(struct bpf_map *map, const char *path) } pr_debug("pinned map '%s'\n", path); + return 0; } -int bpf_object__pin(struct bpf_object *obj, const char *path) +int bpf_map__unpin(struct bpf_map *map, const char *path) +{ + int err; + + err = check_path(path); + if (err) + return err; + + if (map == NULL) { + pr_warning("invalid map pointer\n"); + return -EINVAL; + } + + err = unlink(path); + if (err != 0) + return -errno; + pr_debug("unpinned map '%s'\n", path); + + return 0; +} + +int bpf_object__pin_maps(struct bpf_object *obj, const char *path) { - struct bpf_program *prog; struct bpf_map *map; int err; @@ -1803,28 +2079,142 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map)); + if (len < 0) { + err = -EINVAL; + goto err_unpin_maps; + } else if (len >= PATH_MAX) { + err = -ENAMETOOLONG; + goto err_unpin_maps; + } + + err = bpf_map__pin(map, buf); + if (err) + goto err_unpin_maps; + } + + return 0; + +err_unpin_maps: + while ((map = bpf_map__prev(map, obj))) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) + continue; + else if (len >= PATH_MAX) + continue; + + bpf_map__unpin(map, buf); + } + + return err; +} + +int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) +{ + struct bpf_map *map; + int err; + + if (!obj) + return -ENOENT; + + bpf_map__for_each(map, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); if (len < 0) return -EINVAL; else if (len >= PATH_MAX) return -ENAMETOOLONG; - err = bpf_map__pin(map, buf); + err = bpf_map__unpin(map, buf); if (err) return err; } + return 0; +} + +int bpf_object__pin_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + int err; + + if (!obj) + return -ENOENT; + + if (!obj->loaded) { + pr_warning("object not yet loaded; load it first\n"); + return -ENOENT; + } + + err = make_dir(path); + if (err) + return err; + + bpf_object__for_each_program(prog, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->pin_name); + if (len < 0) { + err = -EINVAL; + goto err_unpin_programs; + } else if (len >= PATH_MAX) { + err = -ENAMETOOLONG; + goto err_unpin_programs; + } + + err = bpf_program__pin(prog, buf); + if (err) + goto err_unpin_programs; + } + + return 0; + +err_unpin_programs: + while ((prog = bpf_program__prev(prog, obj))) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->pin_name); + if (len < 0) + continue; + else if (len >= PATH_MAX) + continue; + + bpf_program__unpin(prog, buf); + } + + return err; +} + +int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + int err; + + if (!obj) + return -ENOENT; + bpf_object__for_each_program(prog, obj) { char buf[PATH_MAX]; int len; len = snprintf(buf, PATH_MAX, "%s/%s", path, - prog->section_name); + prog->pin_name); if (len < 0) return -EINVAL; else if (len >= PATH_MAX) return -ENAMETOOLONG; - err = bpf_program__pin(prog, buf); + err = bpf_program__unpin(prog, buf); if (err) return err; } @@ -1832,6 +2222,23 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) return 0; } +int bpf_object__pin(struct bpf_object *obj, const char *path) +{ + int err; + + err = bpf_object__pin_maps(obj, path); + if (err) + return err; + + err = bpf_object__pin_programs(obj, path); + if (err) { + bpf_object__unpin_maps(obj, path); + return err; + } + + return 0; +} + void bpf_object__close(struct bpf_object *obj) { size_t i; @@ -1845,6 +2252,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object__unload(obj); btf__free(obj->btf); + btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) { zfree(&obj->maps[i].name); @@ -1918,23 +2326,26 @@ void *bpf_object__priv(struct bpf_object *obj) } static struct bpf_program * -__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) { - size_t idx; + size_t nr_programs = obj->nr_programs; + ssize_t idx; - if (!obj->programs) + if (!nr_programs) return NULL; - /* First handler */ - if (prev == NULL) - return &obj->programs[0]; - if (prev->obj != obj) { + if (!p) + /* Iter from the beginning */ + return forward ? &obj->programs[0] : + &obj->programs[nr_programs - 1]; + + if (p->obj != obj) { pr_warning("error: program handler doesn't match object\n"); return NULL; } - idx = (prev - obj->programs) + 1; - if (idx >= obj->nr_programs) + idx = (p - obj->programs) + (forward ? 1 : -1); + if (idx >= obj->nr_programs || idx < 0) return NULL; return &obj->programs[idx]; } @@ -1945,7 +2356,19 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) struct bpf_program *prog = prev; do { - prog = __bpf_program__next(prog, obj); + prog = __bpf_program__iter(prog, obj, true); + } while (prog && bpf_program__is_function_storage(prog, obj)); + + return prog; +} + +struct bpf_program * +bpf_program__prev(struct bpf_program *next, struct bpf_object *obj) +{ + struct bpf_program *prog = next; + + do { + prog = __bpf_program__iter(prog, obj, false); } while (prog && bpf_program__is_function_storage(prog, obj)); return prog; @@ -2272,10 +2695,24 @@ void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) map->map_ifindex = ifindex; } -struct bpf_map * -bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) { - size_t idx; + if (!bpf_map_type__is_map_in_map(map->def.type)) { + pr_warning("error: unsupported map type\n"); + return -EINVAL; + } + if (map->inner_map_fd != -1) { + pr_warning("error: inner_map_fd already specified\n"); + return -EINVAL; + } + map->inner_map_fd = fd; + return 0; +} + +static struct bpf_map * +__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) +{ + ssize_t idx; struct bpf_map *s, *e; if (!obj || !obj->maps) @@ -2284,22 +2721,40 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) s = obj->maps; e = obj->maps + obj->nr_maps; - if (prev == NULL) - return s; - - if ((prev < s) || (prev >= e)) { + if ((m < s) || (m >= e)) { pr_warning("error in %s: map handler doesn't belong to object\n", __func__); return NULL; } - idx = (prev - obj->maps) + 1; - if (idx >= obj->nr_maps) + idx = (m - obj->maps) + i; + if (idx >= obj->nr_maps || idx < 0) return NULL; return &obj->maps[idx]; } struct bpf_map * +bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +{ + if (prev == NULL) + return obj->maps; + + return __bpf_map__iter(prev, obj, 1); +} + +struct bpf_map * +bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) +{ + if (next == NULL) { + if (!obj->nr_maps) + return NULL; + return obj->maps + obj->nr_maps - 1; + } + + return __bpf_map__iter(next, obj, -1); +} + +struct bpf_map * bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) { struct bpf_map *pos; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 1f3468dad8b2c..f30c3d07bb7db 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -16,6 +16,10 @@ #include <sys/types.h> // for size_t #include <linux/bpf.h> +#ifdef __cplusplus +extern "C" { +#endif + #ifndef LIBBPF_API #define LIBBPF_API __attribute__((visibility("default"))) #endif @@ -71,6 +75,13 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf, size_t obj_buf_sz, const char *name); +LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); +LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, + const char *path); +LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, + const char *path); +LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, + const char *path); LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); LIBBPF_API void bpf_object__close(struct bpf_object *object); @@ -112,6 +123,9 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, (pos) != NULL; \ (pos) = bpf_program__next((pos), (obj))) +LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog, + struct bpf_object *obj); + typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); @@ -131,7 +145,11 @@ LIBBPF_API int bpf_program__fd(struct bpf_program *prog); LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, const char *path, int instance); +LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog, + const char *path, + int instance); LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); +LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path); LIBBPF_API void bpf_program__unload(struct bpf_program *prog); struct bpf_insn; @@ -260,6 +278,9 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); (pos) != NULL; \ (pos) = bpf_map__next((pos), (obj))) +LIBBPF_API struct bpf_map * +bpf_map__prev(struct bpf_map *map, struct bpf_object *obj); + LIBBPF_API int bpf_map__fd(struct bpf_map *map); LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map); LIBBPF_API const char *bpf_map__name(struct bpf_map *map); @@ -274,6 +295,9 @@ LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); +LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); + +LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); LIBBPF_API long libbpf_get_error(const void *ptr); @@ -317,4 +341,9 @@ int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + #endif /* __LIBBPF_LIBBPF_H */ diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.cpp new file mode 100644 index 0000000000000..abf3fc25c9fa3 --- /dev/null +++ b/tools/lib/bpf/test_libbpf.cpp @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#include "libbpf.h" +#include "bpf.h" +#include "btf.h" + +/* do nothing, just make sure we can link successfully */ + +int main(int argc, char *argv[]) +{ + /* libbpf.h */ + libbpf_set_print(NULL, NULL, NULL); + + /* bpf.h */ + bpf_prog_get_fd_by_id(0); + + /* btf.h */ + btf__new(NULL, 0, NULL); +} diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4a54236475ae2..73aa6d8f4a2f8 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -24,12 +24,13 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \ test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \ - test_netcnt + test_netcnt test_tcpnotify_user TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ + test_tcpnotify_kern.o \ sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \ sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \ test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \ @@ -38,7 +39,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \ test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \ test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o \ - xdp_dummy.o + xdp_dummy.o test_map_in_map.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -75,6 +76,7 @@ $(OUTPUT)/test_sock_addr: cgroup_helpers.c $(OUTPUT)/test_socket_cookie: cgroup_helpers.c $(OUTPUT)/test_sockmap: cgroup_helpers.c $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c +$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c $(OUTPUT)/test_progs: trace_helpers.c $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c @@ -125,7 +127,14 @@ $(OUTPUT)/test_stack_map.o: test_queue_stack_map.h BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') +BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \ + $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \ + readelf -S ./llvm_btf_verify.o | grep BTF; \ + /bin/rm -f ./llvm_btf_verify.o) +ifneq ($(BTF_LLVM_PROBE),) + CLANG_FLAGS += -g +else ifneq ($(BTF_LLC_PROBE),) ifneq ($(BTF_PAHOLE_PROBE),) ifneq ($(BTF_OBJCOPY_PROBE),) @@ -135,6 +144,17 @@ ifneq ($(BTF_OBJCOPY_PROBE),) endif endif endif +endif + +# Have one program compiled without "-target bpf" to test whether libbpf loads +# it successfully +$(OUTPUT)/test_xdp.o: test_xdp.c + $(CLANG) $(CLANG_FLAGS) \ + -O2 -emit-llvm -c $< -o - | \ + $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ +ifeq ($(DWARF2BTF),y) + $(BTF_PAHOLE) -J $@ +endif $(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c index 107350a7821d0..b9798f558ca7f 100644 --- a/tools/testing/selftests/bpf/bpf_flow.c +++ b/tools/testing/selftests/bpf/bpf_flow.c @@ -116,7 +116,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) return BPF_DROP; } -SEC("dissect") +SEC("flow_dissector") int _dissect(struct __sk_buff *skb) { if (!skb->vlan_present) diff --git a/tools/testing/selftests/bpf/connect4_prog.c b/tools/testing/selftests/bpf/connect4_prog.c index 5a88a681d2abc..b8395f3c43e96 100644 --- a/tools/testing/selftests/bpf/connect4_prog.c +++ b/tools/testing/selftests/bpf/connect4_prog.c @@ -21,23 +21,48 @@ int _version SEC("version") = 1; SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { + struct bpf_sock_tuple tuple = {}; struct sockaddr_in sa; + struct bpf_sock *sk; + + /* Verify that new destination is available. */ + memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr)); + memset(&tuple.ipv4.sport, 0, sizeof(tuple.ipv4.sport)); + + tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4); + tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4); + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + else if (ctx->type == SOCK_STREAM) + sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0); + else + sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0); + + if (!sk) + return 0; + + if (sk->src_ip4 != tuple.ipv4.daddr || + sk->src_port != DST_REWRITE_PORT4) { + bpf_sk_release(sk); + return 0; + } + + bpf_sk_release(sk); /* Rewrite destination. */ ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); ctx->user_port = bpf_htons(DST_REWRITE_PORT4); - if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) { - ///* Rewrite source. */ - memset(&sa, 0, sizeof(sa)); + /* Rewrite source. */ + memset(&sa, 0, sizeof(sa)); - sa.sin_family = AF_INET; - sa.sin_port = bpf_htons(0); - sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4); + sa.sin_family = AF_INET; + sa.sin_port = bpf_htons(0); + sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4); - if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) - return 0; - } + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; return 1; } diff --git a/tools/testing/selftests/bpf/connect6_prog.c b/tools/testing/selftests/bpf/connect6_prog.c index 8ea3f7d12deec..25f5dc7b7aa05 100644 --- a/tools/testing/selftests/bpf/connect6_prog.c +++ b/tools/testing/selftests/bpf/connect6_prog.c @@ -29,7 +29,41 @@ int _version SEC("version") = 1; SEC("cgroup/connect6") int connect_v6_prog(struct bpf_sock_addr *ctx) { + struct bpf_sock_tuple tuple = {}; struct sockaddr_in6 sa; + struct bpf_sock *sk; + + /* Verify that new destination is available. */ + memset(&tuple.ipv6.saddr, 0, sizeof(tuple.ipv6.saddr)); + memset(&tuple.ipv6.sport, 0, sizeof(tuple.ipv6.sport)); + + tuple.ipv6.daddr[0] = bpf_htonl(DST_REWRITE_IP6_0); + tuple.ipv6.daddr[1] = bpf_htonl(DST_REWRITE_IP6_1); + tuple.ipv6.daddr[2] = bpf_htonl(DST_REWRITE_IP6_2); + tuple.ipv6.daddr[3] = bpf_htonl(DST_REWRITE_IP6_3); + + tuple.ipv6.dport = bpf_htons(DST_REWRITE_PORT6); + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + else if (ctx->type == SOCK_STREAM) + sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0); + else + sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0); + + if (!sk) + return 0; + + if (sk->src_ip6[0] != tuple.ipv6.daddr[0] || + sk->src_ip6[1] != tuple.ipv6.daddr[1] || + sk->src_ip6[2] != tuple.ipv6.daddr[2] || + sk->src_ip6[3] != tuple.ipv6.daddr[3] || + sk->src_port != DST_REWRITE_PORT6) { + bpf_sk_release(sk); + return 0; + } + + bpf_sk_release(sk); /* Rewrite destination. */ ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); @@ -39,21 +73,19 @@ int connect_v6_prog(struct bpf_sock_addr *ctx) ctx->user_port = bpf_htons(DST_REWRITE_PORT6); - if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) { - /* Rewrite source. */ - memset(&sa, 0, sizeof(sa)); + /* Rewrite source. */ + memset(&sa, 0, sizeof(sa)); - sa.sin6_family = AF_INET6; - sa.sin6_port = bpf_htons(0); + sa.sin6_family = AF_INET6; + sa.sin6_port = bpf_htons(0); - sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0); - sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1); - sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2); - sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3); + sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0); + sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1); + sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2); + sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3); - if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) - return 0; - } + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; return 1; } diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index f42b3396d6226..bcbda7037840e 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -5,6 +5,7 @@ #include <linux/btf.h> #include <linux/err.h> #include <linux/kernel.h> +#include <linux/filter.h> #include <bpf/bpf.h> #include <sys/resource.h> #include <libelf.h> @@ -22,9 +23,13 @@ #include "bpf_rlimit.h" #include "bpf_util.h" +#define MAX_INSNS 512 +#define MAX_SUBPROGS 16 + static uint32_t pass_cnt; static uint32_t error_cnt; static uint32_t skip_cnt; +static bool jit_enabled; #define CHECK(condition, format...) ({ \ int __ret = !!(condition); \ @@ -60,6 +65,24 @@ static int __base_pr(const char *format, ...) return err; } +static bool is_jit_enabled(void) +{ + const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + bool enabled = false; + int sysctl_fd; + + sysctl_fd = open(jit_sysctl, 0, O_RDONLY); + if (sysctl_fd != -1) { + char tmpc; + + if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) + enabled = (tmpc != '0'); + close(sysctl_fd); + } + + return enabled; +} + #define BTF_INFO_ENC(kind, root, vlen) \ ((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) @@ -85,8 +108,20 @@ static int __base_pr(const char *format, ...) #define BTF_TYPEDEF_ENC(name, type) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) -#define BTF_PTR_ENC(name, type) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) +#define BTF_PTR_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) + +#define BTF_CONST_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type) + +#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type) + +#define BTF_FUNC_PROTO_ARG_ENC(name, type) \ + (name), (type) + +#define BTF_FUNC_ENC(name, func_proto) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto) #define BTF_END_RAW 0xdeadbeef #define NAME_TBD 0xdeadb33f @@ -103,6 +138,7 @@ static struct args { bool get_info_test; bool pprint_test; bool always_log; + bool func_type_test; } args; static char btf_log_buf[BTF_LOG_BUF_SIZE]; @@ -1374,6 +1410,464 @@ static struct btf_raw_test raw_tests[] = { .map_create_err = true, }, +{ + .descr = "func proto (int (*)(int, unsigned int))", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* int (*)(int, unsigned int) */ + BTF_FUNC_PROTO_ENC(1, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(0, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "func proto (vararg)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int, unsigned int, ...) */ + BTF_FUNC_PROTO_ENC(0, 3), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(0, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 2), + BTF_FUNC_PROTO_ARG_ENC(0, 0), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "func proto (vararg with name)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int b, ... c) */ + BTF_FUNC_PROTO_ENC(0, 3), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 0), + BTF_END_RAW, + }, + .str_sec = "\0a\0b\0c", + .str_sec_size = sizeof("\0a\0b\0c"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid arg#3", +}, + +{ + .descr = "func proto (arg after vararg)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, ..., unsigned int b) */ + BTF_FUNC_PROTO_ENC(0, 3), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 0), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_END_RAW, + }, + .str_sec = "\0a\0b", + .str_sec_size = sizeof("\0a\0b"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid arg#2", +}, + +{ + .descr = "func proto (CONST=>TYPEDEF=>PTR=>FUNC_PROTO)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* typedef void (*func_ptr)(int, unsigned int) */ + BTF_TYPEDEF_ENC(NAME_TBD, 5), /* [3] */ + /* const func_ptr */ + BTF_CONST_ENC(3), /* [4] */ + BTF_PTR_ENC(6), /* [5] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [6] */ + BTF_FUNC_PROTO_ARG_ENC(0, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 2), + BTF_END_RAW, + }, + .str_sec = "\0func_ptr", + .str_sec_size = sizeof("\0func_ptr"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + BTF_CONST_ENC(4), /* [3] */ + BTF_TYPEDEF_ENC(NAME_TBD, 5), /* [4] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [5] */ + BTF_FUNC_PROTO_ARG_ENC(0, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 2), + BTF_END_RAW, + }, + .str_sec = "\0func_typedef", + .str_sec_size = sizeof("\0func_typedef"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, + +{ + .descr = "func proto (btf_resolve(arg))", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* void (*)(const void *) */ + BTF_FUNC_PROTO_ENC(0, 1), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(0, 3), + BTF_CONST_ENC(4), /* [3] */ + BTF_PTR_ENC(0), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "func proto (Not all arg has name)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int, unsigned int b) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(0, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_END_RAW, + }, + .str_sec = "\0b", + .str_sec_size = sizeof("\0b"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "func proto (Bad arg name_off)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int <bad_name_off>) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(0xffffffff, 2), + BTF_END_RAW, + }, + .str_sec = "\0a", + .str_sec_size = sizeof("\0a"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid arg#2", +}, + +{ + .descr = "func proto (Bad arg name)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int !!!) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_END_RAW, + }, + .str_sec = "\0a\0!!!", + .str_sec_size = sizeof("\0a\0!!!"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid arg#2", +}, + +{ + .descr = "func proto (Invalid return type)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* <bad_ret_type> (*)(int, unsigned int) */ + BTF_FUNC_PROTO_ENC(100, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(0, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid return type", +}, + +{ + .descr = "func proto (with func name)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void func_proto(int, unsigned int) */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 2), 0), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(0, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 2), + BTF_END_RAW, + }, + .str_sec = "\0func_proto", + .str_sec_size = sizeof("\0func_proto"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid name", +}, + +{ + .descr = "func proto (const void arg)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(const void) */ + BTF_FUNC_PROTO_ENC(0, 1), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(0, 4), + BTF_CONST_ENC(0), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_proto_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid arg#1", +}, + +{ + .descr = "func (void func(int a, unsigned int b))", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int b) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + /* void func(int a, unsigned int b) */ + BTF_FUNC_ENC(NAME_TBD, 3), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "\0a\0b\0func", + .str_sec_size = sizeof("\0a\0b\0func"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, +}, + +{ + .descr = "func (No func name)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int b) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + /* void <no_name>(int a, unsigned int b) */ + BTF_FUNC_ENC(0, 3), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "\0a\0b", + .str_sec_size = sizeof("\0a\0b"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid name", +}, + +{ + .descr = "func (Invalid func name)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int b) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + /* void !!!(int a, unsigned int b) */ + BTF_FUNC_ENC(NAME_TBD, 3), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "\0a\0b\0!!!", + .str_sec_size = sizeof("\0a\0b\0!!!"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid name", +}, + +{ + .descr = "func (Some arg has no name)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(0, 2), + /* void func(int a, unsigned int) */ + BTF_FUNC_ENC(NAME_TBD, 3), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "\0a\0func", + .str_sec_size = sizeof("\0a\0func"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid arg#2", +}, + +{ + .descr = "func (Non zero vlen)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ + /* void (*)(int a, unsigned int b) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + /* void func(int a, unsigned int b) */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 2), 3), /* [4] */ + BTF_END_RAW, + }, + .str_sec = "\0a\0b\0func", + .str_sec_size = sizeof("\0a\0b\0func"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "vlen != 0", +}, + +{ + .descr = "func (Not referring to FUNC_PROTO)", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_ENC(NAME_TBD, 1), /* [2] */ + BTF_END_RAW, + }, + .str_sec = "\0func", + .str_sec_size = sizeof("\0func"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "func_type_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) @@ -1940,13 +2434,13 @@ static struct btf_file_test file_tests[] = { }, }; -static int file_has_btf_elf(const char *fn) +static int file_has_btf_elf(const char *fn, bool *has_btf_ext) { Elf_Scn *scn = NULL; GElf_Ehdr ehdr; + int ret = 0; int elf_fd; Elf *elf; - int ret; if (CHECK(elf_version(EV_CURRENT) == EV_NONE, "elf_version(EV_CURRENT) == EV_NONE")) @@ -1978,14 +2472,12 @@ static int file_has_btf_elf(const char *fn) } sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); - if (!strcmp(sh_name, BTF_ELF_SEC)) { + if (!strcmp(sh_name, BTF_ELF_SEC)) ret = 1; - goto done; - } + if (!strcmp(sh_name, BTF_EXT_ELF_SEC)) + *has_btf_ext = true; } - ret = 0; - done: close(elf_fd); elf_end(elf); @@ -1995,15 +2487,24 @@ done: static int do_test_file(unsigned int test_num) { const struct btf_file_test *test = &file_tests[test_num - 1]; + const char *expected_fnames[] = {"_dummy_tracepoint", + "test_long_fname_1", + "test_long_fname_2"}; + struct bpf_prog_info info = {}; struct bpf_object *obj = NULL; + struct bpf_func_info *finfo; struct bpf_program *prog; + __u32 info_len, rec_size; + bool has_btf_ext = false; + struct btf *btf = NULL; + void *func_info = NULL; struct bpf_map *map; - int err; + int i, err, prog_fd; fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num, test->file); - err = file_has_btf_elf(test->file); + err = file_has_btf_elf(test->file, &has_btf_ext); if (err == -1) return err; @@ -2031,6 +2532,7 @@ static int do_test_file(unsigned int test_num) err = bpf_object__load(obj); if (CHECK(err < 0, "bpf_object__load: %d", err)) goto done; + prog_fd = bpf_program__fd(prog); map = bpf_object__find_map_by_name(obj, "btf_map"); if (CHECK(!map, "btf_map not found")) { @@ -2045,9 +2547,100 @@ static int do_test_file(unsigned int test_num) test->btf_kv_notfound)) goto done; + if (!jit_enabled || !has_btf_ext) + goto skip_jit; + + /* get necessary program info */ + info_len = sizeof(struct bpf_prog_info); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + + if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) { + fprintf(stderr, "%s\n", btf_log_buf); + err = -1; + goto done; + } + if (CHECK(info.func_info_cnt != 3, + "incorrect info.func_info_cnt (1st) %d", + info.func_info_cnt)) { + err = -1; + goto done; + } + rec_size = info.func_info_rec_size; + if (CHECK(rec_size < 4, + "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) { + err = -1; + goto done; + } + + func_info = malloc(info.func_info_cnt * rec_size); + if (CHECK(!func_info, "out of memory")) { + err = -1; + goto done; + } + + /* reset info to only retrieve func_info related data */ + memset(&info, 0, sizeof(info)); + info.func_info_cnt = 3; + info.func_info_rec_size = rec_size; + info.func_info = ptr_to_u64(func_info); + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + + if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) { + fprintf(stderr, "%s\n", btf_log_buf); + err = -1; + goto done; + } + if (CHECK(info.func_info_cnt != 3, + "incorrect info.func_info_cnt (2nd) %d", + info.func_info_cnt)) { + err = -1; + goto done; + } + if (CHECK(info.func_info_rec_size != rec_size, + "incorrect info.func_info_rec_size (2nd) %d", + info.func_info_rec_size)) { + err = -1; + goto done; + } + + err = btf_get_from_id(info.btf_id, &btf); + if (CHECK(err, "cannot get btf from kernel, err: %d", err)) + goto done; + + /* check three functions */ + finfo = func_info; + for (i = 0; i < 3; i++) { + const struct btf_type *t; + const char *fname; + + t = btf__type_by_id(btf, finfo->type_id); + if (CHECK(!t, "btf__type_by_id failure: id %u", + finfo->type_id)) { + err = -1; + goto done; + } + + fname = btf__name_by_offset(btf, t->name_off); + err = strcmp(fname, expected_fnames[i]); + /* for the second and third functions in .text section, + * the compiler may order them either way. + */ + if (i && err) + err = strcmp(fname, expected_fnames[3 - i]); + if (CHECK(err, "incorrect fname %s", fname ? : "")) { + err = -1; + goto done; + } + + finfo = (void *)finfo + rec_size; + } + +skip_jit: fprintf(stderr, "OK"); done: + free(func_info); bpf_object__close(obj); return err; } @@ -2477,16 +3070,310 @@ static int test_pprint(void) return err; } +static struct btf_func_type_test { + const char *descr; + const char *str_sec; + __u32 raw_types[MAX_NR_RAW_TYPES]; + __u32 str_sec_size; + struct bpf_insn insns[MAX_INSNS]; + __u32 prog_type; + __u32 func_info[MAX_SUBPROGS][2]; + __u32 func_info_rec_size; + __u32 func_info_cnt; + bool expected_prog_load_failure; +} func_type_test[] = { +{ + .descr = "func_type (main func + one sub)", + .raw_types = { + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */ + BTF_FUNC_PROTO_ENC(1, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ENC(1, 2), /* [4] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */ + BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */ + BTF_END_RAW, + }, + .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB", + .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"), + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .func_info = { {0, 5}, {3, 6} }, + .func_info_rec_size = 8, + .func_info_cnt = 2, +}, + +{ + .descr = "func_type (Incorrect func_info_rec_size)", + .raw_types = { + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */ + BTF_FUNC_PROTO_ENC(1, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ENC(1, 2), /* [4] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */ + BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */ + BTF_END_RAW, + }, + .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB", + .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"), + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .func_info = { {0, 5}, {3, 6} }, + .func_info_rec_size = 4, + .func_info_cnt = 2, + .expected_prog_load_failure = true, +}, + +{ + .descr = "func_type (Incorrect func_info_cnt)", + .raw_types = { + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */ + BTF_FUNC_PROTO_ENC(1, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ENC(1, 2), /* [4] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */ + BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */ + BTF_END_RAW, + }, + .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB", + .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"), + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .func_info = { {0, 5}, {3, 6} }, + .func_info_rec_size = 8, + .func_info_cnt = 1, + .expected_prog_load_failure = true, +}, + +{ + .descr = "func_type (Incorrect bpf_func_info.insn_offset)", + .raw_types = { + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), /* [2] */ + BTF_FUNC_PROTO_ENC(1, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ENC(1, 2), /* [4] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 3), /* [5] */ + BTF_FUNC_ENC(NAME_TBD, 4), /* [6] */ + BTF_END_RAW, + }, + .str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB", + .str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"), + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .func_info = { {0, 5}, {2, 6} }, + .func_info_rec_size = 8, + .func_info_cnt = 2, + .expected_prog_load_failure = true, +}, + +}; + +static size_t probe_prog_length(const struct bpf_insn *fp) +{ + size_t len; + + for (len = MAX_INSNS - 1; len > 0; --len) + if (fp[len].code != 0 || fp[len].imm != 0) + break; + return len + 1; +} + +static int do_test_func_type(int test_num) +{ + const struct btf_func_type_test *test = &func_type_test[test_num]; + unsigned int raw_btf_size, info_len, rec_size; + int i, btf_fd = -1, prog_fd = -1, err = 0; + struct bpf_load_program_attr attr = {}; + void *raw_btf, *func_info = NULL; + struct bpf_prog_info info = {}; + struct bpf_func_info *finfo; + + fprintf(stderr, "%s......", test->descr); + raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types, + test->str_sec, test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + free(raw_btf); + + if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) { + err = -1; + goto done; + } + + if (*btf_log_buf && args.always_log) + fprintf(stderr, "\n%s", btf_log_buf); + + attr.prog_type = test->prog_type; + attr.insns = test->insns; + attr.insns_cnt = probe_prog_length(attr.insns); + attr.license = "GPL"; + attr.prog_btf_fd = btf_fd; + attr.func_info_rec_size = test->func_info_rec_size; + attr.func_info_cnt = test->func_info_cnt; + attr.func_info = test->func_info; + + *btf_log_buf = '\0'; + prog_fd = bpf_load_program_xattr(&attr, btf_log_buf, + BTF_LOG_BUF_SIZE); + if (test->expected_prog_load_failure && prog_fd == -1) { + err = 0; + goto done; + } + if (CHECK(prog_fd == -1, "invalid prog_id errno:%d", errno)) { + fprintf(stderr, "%s\n", btf_log_buf); + err = -1; + goto done; + } + if (!jit_enabled) { + skip_cnt++; + fprintf(stderr, "SKIPPED, please enable sysctl bpf_jit_enable\n"); + err = 0; + goto done; + } + + /* get necessary lens */ + info_len = sizeof(struct bpf_prog_info); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) { + fprintf(stderr, "%s\n", btf_log_buf); + err = -1; + goto done; + } + if (CHECK(info.func_info_cnt != 2, + "incorrect info.func_info_cnt (1st) %d\n", + info.func_info_cnt)) { + err = -1; + goto done; + } + rec_size = info.func_info_rec_size; + if (CHECK(rec_size < 4, + "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) { + err = -1; + goto done; + } + + func_info = malloc(info.func_info_cnt * rec_size); + if (CHECK(!func_info, "out of memory")) { + err = -1; + goto done; + } + + /* reset info to only retrieve func_info related data */ + memset(&info, 0, sizeof(info)); + info.func_info_cnt = 2; + info.func_info_rec_size = rec_size; + info.func_info = ptr_to_u64(func_info); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) { + fprintf(stderr, "%s\n", btf_log_buf); + err = -1; + goto done; + } + if (CHECK(info.func_info_cnt != 2, + "incorrect info.func_info_cnt (2nd) %d\n", + info.func_info_cnt)) { + err = -1; + goto done; + } + if (CHECK(info.func_info_rec_size != rec_size, + "incorrect info.func_info_rec_size (2nd) %d\n", + info.func_info_rec_size)) { + err = -1; + goto done; + } + + finfo = func_info; + for (i = 0; i < 2; i++) { + if (CHECK(finfo->type_id != test->func_info[i][1], + "incorrect func_type %u expected %u", + finfo->type_id, test->func_info[i][1])) { + err = -1; + goto done; + } + finfo = (void *)finfo + rec_size; + } + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "\n%s", btf_log_buf); + + if (btf_fd != -1) + close(btf_fd); + if (prog_fd != -1) + close(prog_fd); + free(func_info); + return err; +} + +static int test_func_type(void) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < ARRAY_SIZE(func_type_test); i++) + err |= count_result(do_test_func_type(i)); + + return err; +} + static void usage(const char *cmd) { - fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n", + fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] |" + " [-g test_num (1 - %zu)] |" + " [-f test_num (1 - %zu)] | [-p] | [-k] ]\n", cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests), ARRAY_SIZE(file_tests)); } static int parse_args(int argc, char **argv) { - const char *optstr = "lpf:r:g:"; + const char *optstr = "lpkf:r:g:"; int opt; while ((opt = getopt(argc, argv, optstr)) != -1) { @@ -2509,6 +3396,9 @@ static int parse_args(int argc, char **argv) case 'p': args.pprint_test = true; break; + case 'k': + args.func_type_test = true; + break; case 'h': usage(argv[0]); exit(0); @@ -2562,6 +3452,8 @@ int main(int argc, char **argv) if (args.always_log) libbpf_set_print(__base_pr, __base_pr, __base_pr); + jit_enabled = is_jit_enabled(); + if (args.raw_test) err |= test_raw(); @@ -2574,8 +3466,11 @@ int main(int argc, char **argv) if (args.pprint_test) err |= test_pprint(); + if (args.func_type_test) + err |= test_func_type(); + if (args.raw_test || args.get_info_test || args.file_test || - args.pprint_test) + args.pprint_test || args.func_type_test) goto done; err |= test_raw(); diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c index b21b876f475d8..e5c79fe0ffdb2 100644 --- a/tools/testing/selftests/bpf/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/test_btf_haskv.c @@ -24,8 +24,8 @@ struct dummy_tracepoint_args { struct sock *sock; }; -SEC("dummy_tracepoint") -int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +__attribute__((noinline)) +static int test_long_fname_2(struct dummy_tracepoint_args *arg) { struct ipv_counts *counts; int key = 0; @@ -42,4 +42,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg) return 0; } +__attribute__((noinline)) +static int test_long_fname_1(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_2(arg); +} + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_1(arg); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c index 0ed8e088eebf9..434188c377743 100644 --- a/tools/testing/selftests/bpf/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/test_btf_nokv.c @@ -22,8 +22,8 @@ struct dummy_tracepoint_args { struct sock *sock; }; -SEC("dummy_tracepoint") -int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +__attribute__((noinline)) +static int test_long_fname_2(struct dummy_tracepoint_args *arg) { struct ipv_counts *counts; int key = 0; @@ -40,4 +40,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg) return 0; } +__attribute__((noinline)) +static int test_long_fname_1(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_2(arg); +} + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_1(arg); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh index c0fb073b5eab2..d23d4da66b834 100755 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ b/tools/testing/selftests/bpf/test_flow_dissector.sh @@ -59,7 +59,7 @@ else fi # Attach BPF program -./flow_dissector_load -p bpf_flow.o -s dissect +./flow_dissector_load -p bpf_flow.o -s flow_dissector # Setup tc qdisc add dev lo ingress diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh index 156d89f1edcc4..2989b2e2d856d 100755 --- a/tools/testing/selftests/bpf/test_libbpf.sh +++ b/tools/testing/selftests/bpf/test_libbpf.sh @@ -33,17 +33,11 @@ trap exit_handler 0 2 3 6 9 libbpf_open_file test_l4lb.o -# TODO: fix libbpf to load noinline functions -# [warning] libbpf: incorrect bpf_call opcode -#libbpf_open_file test_l4lb_noinline.o +# Load a program with BPF-to-BPF calls +libbpf_open_file test_l4lb_noinline.o -# TODO: fix test_xdp_meta.c to load with libbpf -# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version -#libbpf_open_file test_xdp_meta.o - -# TODO: fix libbpf to handle .eh_frame -# [warning] libbpf: relocation failed: no section(10) -#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o +# Load a program compiled without the "-target bpf" flag +libbpf_open_file test_xdp.o # Success exit 0 diff --git a/tools/testing/selftests/bpf/test_map_in_map.c b/tools/testing/selftests/bpf/test_map_in_map.c new file mode 100644 index 0000000000000..ce923e67e08e1 --- /dev/null +++ b/tools/testing/selftests/bpf/test_map_in_map.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") mim_array = { + .type = BPF_MAP_TYPE_ARRAY_OF_MAPS, + .key_size = sizeof(int), + /* must be sizeof(__u32) for map in map */ + .value_size = sizeof(__u32), + .max_entries = 1, + .map_flags = 0, +}; + +struct bpf_map_def SEC("maps") mim_hash = { + .type = BPF_MAP_TYPE_HASH_OF_MAPS, + .key_size = sizeof(int), + /* must be sizeof(__u32) for map in map */ + .value_size = sizeof(__u32), + .max_entries = 1, + .map_flags = 0, +}; + +SEC("xdp_mimtest") +int xdp_mimtest0(struct xdp_md *ctx) +{ + int value = 123; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&mim_array, &key); + if (!map) + return XDP_DROP; + + bpf_map_update_elem(map, &key, &value, 0); + + map = bpf_map_lookup_elem(&mim_hash, &key); + if (!map) + return XDP_DROP; + + bpf_map_update_elem(map, &key, &value, 0); + + return XDP_PASS; +} + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 4db2116e52be4..9c79ee017df3b 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -258,24 +258,36 @@ static void test_hashmap_percpu(int task, void *data) close(fd); } -static void test_hashmap_walk(int task, void *data) +static int helper_fill_hashmap(int max_entries) { - int fd, i, max_entries = 1000; - long long key, value, next_key; - bool next_key_valid = true; + int i, fd, ret; + long long key, value; fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), max_entries, map_flags); - if (fd < 0) { - printf("Failed to create hashmap '%s'!\n", strerror(errno)); - exit(1); - } + CHECK(fd < 0, + "failed to create hashmap", + "err: %s, flags: 0x%x\n", strerror(errno), map_flags); for (i = 0; i < max_entries; i++) { key = i; value = key; - assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0); + ret = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(ret != 0, + "can't update hashmap", + "err: %s\n", strerror(ret)); } + return fd; +} + +static void test_hashmap_walk(int task, void *data) +{ + int fd, i, max_entries = 1000; + long long key, value, next_key; + bool next_key_valid = true; + + fd = helper_fill_hashmap(max_entries); + for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key, &next_key) == 0; i++) { key = next_key; @@ -306,6 +318,39 @@ static void test_hashmap_walk(int task, void *data) close(fd); } +static void test_hashmap_zero_seed(void) +{ + int i, first, second, old_flags; + long long key, next_first, next_second; + + old_flags = map_flags; + map_flags |= BPF_F_ZERO_SEED; + + first = helper_fill_hashmap(3); + second = helper_fill_hashmap(3); + + for (i = 0; ; i++) { + void *key_ptr = !i ? NULL : &key; + + if (bpf_map_get_next_key(first, key_ptr, &next_first) != 0) + break; + + CHECK(bpf_map_get_next_key(second, key_ptr, &next_second) != 0, + "next_key for second map must succeed", + "key_ptr: %p", key_ptr); + CHECK(next_first != next_second, + "keys must match", + "i: %d first: %lld second: %lld\n", i, + next_first, next_second); + + key = next_first; + } + + map_flags = old_flags; + close(first); + close(second); +} + static void test_arraymap(int task, void *data) { int key, next_key, fd; @@ -1080,6 +1125,94 @@ out_sockmap: exit(1); } +#define MAPINMAP_PROG "./test_map_in_map.o" +static void test_map_in_map(void) +{ + struct bpf_program *prog; + struct bpf_object *obj; + struct bpf_map *map; + int mim_fd, fd, err; + int pos = 0; + + obj = bpf_object__open(MAPINMAP_PROG); + + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int), + 2, 0); + if (fd < 0) { + printf("Failed to create hashmap '%s'!\n", strerror(errno)); + exit(1); + } + + map = bpf_object__find_map_by_name(obj, "mim_array"); + if (IS_ERR(map)) { + printf("Failed to load array of maps from test prog\n"); + goto out_map_in_map; + } + err = bpf_map__set_inner_map_fd(map, fd); + if (err) { + printf("Failed to set inner_map_fd for array of maps\n"); + goto out_map_in_map; + } + + map = bpf_object__find_map_by_name(obj, "mim_hash"); + if (IS_ERR(map)) { + printf("Failed to load hash of maps from test prog\n"); + goto out_map_in_map; + } + err = bpf_map__set_inner_map_fd(map, fd); + if (err) { + printf("Failed to set inner_map_fd for hash of maps\n"); + goto out_map_in_map; + } + + bpf_object__for_each_program(prog, obj) { + bpf_program__set_xdp(prog); + } + bpf_object__load(obj); + + map = bpf_object__find_map_by_name(obj, "mim_array"); + if (IS_ERR(map)) { + printf("Failed to load array of maps from test prog\n"); + goto out_map_in_map; + } + mim_fd = bpf_map__fd(map); + if (mim_fd < 0) { + printf("Failed to get descriptor for array of maps\n"); + goto out_map_in_map; + } + + err = bpf_map_update_elem(mim_fd, &pos, &fd, 0); + if (err) { + printf("Failed to update array of maps\n"); + goto out_map_in_map; + } + + map = bpf_object__find_map_by_name(obj, "mim_hash"); + if (IS_ERR(map)) { + printf("Failed to load hash of maps from test prog\n"); + goto out_map_in_map; + } + mim_fd = bpf_map__fd(map); + if (mim_fd < 0) { + printf("Failed to get descriptor for hash of maps\n"); + goto out_map_in_map; + } + + err = bpf_map_update_elem(mim_fd, &pos, &fd, 0); + if (err) { + printf("Failed to update hash of maps\n"); + goto out_map_in_map; + } + + close(fd); + bpf_object__close(obj); + return; + +out_map_in_map: + close(fd); + exit(1); +} + #define MAP_SIZE (32 * 1024) static void test_map_large(void) @@ -1534,6 +1667,7 @@ static void run_all_tests(void) test_hashmap(0, NULL); test_hashmap_percpu(0, NULL); test_hashmap_walk(0, NULL); + test_hashmap_zero_seed(); test_arraymap(0, NULL); test_arraymap_percpu(0, NULL); @@ -1554,6 +1688,8 @@ static void run_all_tests(void) test_queuemap(0, NULL); test_stackmap(0, NULL); + + test_map_in_map(); } int main(void) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 2d3c04f455302..c1e688f61061c 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1703,7 +1703,7 @@ static void test_reference_tracking() const char *file = "./test_sk_lookup_kern.o"; struct bpf_object *obj; struct bpf_program *prog; - __u32 duration; + __u32 duration = 0; int err = 0; obj = bpf_object__open(file); diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index aeeb76a54d633..73b7493d41209 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -574,24 +574,44 @@ static int bind4_prog_load(const struct sock_addr_test *test) /* if (sk.family == AF_INET && */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, family)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 16), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 24), /* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, type)), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1), BPF_JMP_A(1), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 20), /* 1st_byte_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 10), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 18), + + /* 2nd_byte_of_user_ip4 == expected && */ + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, user_ip4) + 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 16), + + /* 3rd_byte_of_user_ip4 == expected && */ + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, user_ip4) + 2), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 14), + + /* 4th_byte_of_user_ip4 == expected && */ + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, user_ip4) + 3), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 12), /* 1st_half_of_user_ip4 == expected && */ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock_addr, user_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 8), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 10), + + /* 2nd_half_of_user_ip4 == expected && */ + BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, user_ip4) + 2), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 8), /* whole_user_ip4 == expected) { */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, diff --git a/tools/testing/selftests/bpf/test_tcpnotify.h b/tools/testing/selftests/bpf/test_tcpnotify.h new file mode 100644 index 0000000000000..8b6cea030bfc3 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpnotify.h @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef _TEST_TCPBPF_H +#define _TEST_TCPBPF_H + +struct tcpnotify_globals { + __u32 total_retrans; + __u32 ncalls; +}; + +struct tcp_notifier { + __u8 type; + __u8 subtype; + __u8 source; + __u8 hash; +}; + +#define TESTPORT 12877 +#endif diff --git a/tools/testing/selftests/bpf/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/test_tcpnotify_kern.c new file mode 100644 index 0000000000000..edbca203ce2dd --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpnotify_kern.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/tcp.h> +#include <netinet/in.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_tcpnotify.h" + +struct bpf_map_def SEC("maps") global_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct tcpnotify_globals), + .max_entries = 4, +}; + +struct bpf_map_def SEC("maps") perf_event_map = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(__u32), + .max_entries = 2, +}; + +int _version SEC("version") = 1; + +SEC("sockops") +int bpf_testcb(struct bpf_sock_ops *skops) +{ + int rv = -1; + int op; + + op = (int) skops->op; + + if (bpf_ntohl(skops->remote_port) != TESTPORT) { + skops->reply = -1; + return 0; + } + + switch (op) { + case BPF_SOCK_OPS_TIMEOUT_INIT: + case BPF_SOCK_OPS_RWND_INIT: + case BPF_SOCK_OPS_NEEDS_ECN: + case BPF_SOCK_OPS_BASE_RTT: + case BPF_SOCK_OPS_RTO_CB: + rv = 1; + break; + + case BPF_SOCK_OPS_TCP_CONNECT_CB: + case BPF_SOCK_OPS_TCP_LISTEN_CB: + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG| + BPF_SOCK_OPS_RTO_CB_FLAG)); + rv = 1; + break; + case BPF_SOCK_OPS_RETRANS_CB: { + __u32 key = 0; + struct tcpnotify_globals g, *gp; + struct tcp_notifier msg = { + .type = 0xde, + .subtype = 0xad, + .source = 0xbe, + .hash = 0xef, + }; + + rv = 1; + + /* Update results */ + gp = bpf_map_lookup_elem(&global_map, &key); + if (!gp) + break; + g = *gp; + g.total_retrans = skops->total_retrans; + g.ncalls++; + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + bpf_perf_event_output(skops, &perf_event_map, + BPF_F_CURRENT_CPU, + &msg, sizeof(msg)); + } + break; + default: + rv = -1; + } + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c new file mode 100644 index 0000000000000..ff3c4522aed68 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <pthread.h> +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <asm/types.h> +#include <sys/syscall.h> +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <sys/socket.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <sys/ioctl.h> +#include <linux/rtnetlink.h> +#include <signal.h> +#include <linux/perf_event.h> + +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" + +#include "test_tcpnotify.h" +#include "trace_helpers.h" + +#define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L) + +pthread_t tid; +int rx_callbacks; + +static int dummyfn(void *data, int size) +{ + struct tcp_notifier *t = data; + + if (t->type != 0xde || t->subtype != 0xad || + t->source != 0xbe || t->hash != 0xef) + return 1; + rx_callbacks++; + return 0; +} + +void tcp_notifier_poller(int fd) +{ + while (1) + perf_event_poller(fd, dummyfn); +} + +static void *poller_thread(void *arg) +{ + int fd = *(int *)arg; + + tcp_notifier_poller(fd); + return arg; +} + +int verify_result(const struct tcpnotify_globals *result) +{ + return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1); +} + +static int bpf_find_map(const char *test, struct bpf_object *obj, + const char *name) +{ + struct bpf_map *map; + + map = bpf_object__find_map_by_name(obj, name); + if (!map) { + printf("%s:FAIL:map '%s' not found\n", test, name); + return -1; + } + return bpf_map__fd(map); +} + +static int setup_bpf_perf_event(int mapfd) +{ + struct perf_event_attr attr = { + .sample_type = PERF_SAMPLE_RAW, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_BPF_OUTPUT, + }; + int key = 0; + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0); + if (pmu_fd < 0) + return pmu_fd; + bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY); + + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + return pmu_fd; +} + +int main(int argc, char **argv) +{ + const char *file = "test_tcpnotify_kern.o"; + int prog_fd, map_fd, perf_event_fd; + struct tcpnotify_globals g = {0}; + const char *cg_path = "/foo"; + int error = EXIT_FAILURE; + struct bpf_object *obj; + int cg_fd = -1; + __u32 key = 0; + int rv; + char test_script[80]; + int pmu_fd; + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset); + + if (setup_cgroup_environment()) + goto err; + + cg_fd = create_and_get_cgroup(cg_path); + if (!cg_fd) + goto err; + + if (join_cgroup(cg_path)) + goto err; + + if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { + printf("FAILED: load_bpf_file failed for: %s\n", file); + goto err; + } + + rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0); + if (rv) { + printf("FAILED: bpf_prog_attach: %d (%s)\n", + error, strerror(errno)); + goto err; + } + + perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map"); + if (perf_event_fd < 0) + goto err; + + map_fd = bpf_find_map(__func__, obj, "global_map"); + if (map_fd < 0) + goto err; + + pmu_fd = setup_bpf_perf_event(perf_event_fd); + if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0) + goto err; + + pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd); + + sprintf(test_script, + "/usr/sbin/iptables -A INPUT -p tcp --dport %d -j DROP", + TESTPORT); + system(test_script); + + sprintf(test_script, + "/usr/bin/nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ", + TESTPORT); + system(test_script); + + sprintf(test_script, + "/usr/sbin/iptables -D INPUT -p tcp --dport %d -j DROP", + TESTPORT); + system(test_script); + + rv = bpf_map_lookup_elem(map_fd, &key, &g); + if (rv != 0) { + printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); + goto err; + } + + sleep(10); + + if (verify_result(&g)) { + printf("FAILED: Wrong stats Expected %d calls, got %d\n", + g.ncalls, rx_callbacks); + goto err; + } + + printf("PASSED!\n"); + error = 0; +err: + bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); + close(cg_fd); + cleanup_cgroup_environment(); + return error; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 6f61df62f690c..537a8f91af02d 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -2026,29 +2026,27 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { - "check skb->hash byte load not permitted 1", + "check skb->hash byte load permitted 1", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 1), BPF_EXIT_INSN(), }, - .errstr = "invalid bpf_context access", - .result = REJECT, + .result = ACCEPT, }, { - "check skb->hash byte load not permitted 2", + "check skb->hash byte load permitted 2", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 2), BPF_EXIT_INSN(), }, - .errstr = "invalid bpf_context access", - .result = REJECT, + .result = ACCEPT, }, { - "check skb->hash byte load not permitted 3", + "check skb->hash byte load permitted 3", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), #if __BYTE_ORDER == __LITTLE_ENDIAN @@ -2060,8 +2058,7 @@ static struct bpf_test tests[] = { #endif BPF_EXIT_INSN(), }, - .errstr = "invalid bpf_context access", - .result = REJECT, + .result = ACCEPT, }, { "check cb access: byte, wrong type", @@ -2173,7 +2170,7 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { - "check skb->hash half load not permitted", + "check skb->hash half load permitted 2", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), #if __BYTE_ORDER == __LITTLE_ENDIAN @@ -2185,6 +2182,37 @@ static struct bpf_test tests[] = { #endif BPF_EXIT_INSN(), }, + .result = ACCEPT, + }, + { + "check skb->hash half load not permitted, unaligned 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 1), +#else + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 3), +#endif + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check skb->hash half load not permitted, unaligned 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 3), +#else + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 1), +#endif + BPF_EXIT_INSN(), + }, .errstr = "invalid bpf_context access", .result = REJECT, }, @@ -2418,6 +2446,10 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, tc_index)), BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, offsetof(struct __sk_buff, cb[3])), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tstamp)), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, tstamp)), BPF_EXIT_INSN(), }, .errstr_unpriv = "", @@ -5270,6 +5302,31 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_CGROUP_SKB, }, { + "write tstamp from CGROUP_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, tstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "invalid bpf_context access off=152 size=8", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + }, + { + "read tstamp from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + }, + { "multiple registers share map_lookup_elem result", .insns = { BPF_MOV64_IMM(BPF_REG_1, 10), |