diff options
| author | David S. Miller <davem@davemloft.net> | 2019-06-20 06:06:27 +0200 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2019-06-20 06:06:27 +0200 |
| commit | dca73a65a68329ee386d3ff473152bac66eaab39 (patch) | |
| tree | 97c41afb932bdd6cbe67e7ffc38bfe5952c97798 | |
| parent | page_pool: fix compile warning when CONFIG_PAGE_POOL is disabled (diff) | |
| parent | Merge branch 'bpf-bounded-loops' (diff) | |
| download | linux-dca73a65a68329ee386d3ff473152bac66eaab39.tar.xz linux-dca73a65a68329ee386d3ff473152bac66eaab39.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2019-06-19
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) new SO_REUSEPORT_DETACH_BPF setsocktopt, from Martin.
2) BTF based map definition, from Andrii.
3) support bpf_map_lookup_elem for xskmap, from Jonathan.
4) bounded loops and scalar precision logic in the verifier, from Alexei.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
101 files changed, 4048 insertions, 860 deletions
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 976e89b116e5..de6c4df61082 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -122,6 +122,8 @@ #define SO_RCVTIMEO_NEW 66 #define SO_SNDTIMEO_NEW 67 +#define SO_DETACH_REUSEPORT_BPF 68 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index d41765cfbc6e..d0a9ed2ca2d6 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -133,6 +133,8 @@ #define SO_RCVTIMEO_NEW 66 #define SO_SNDTIMEO_NEW 67 +#define SO_DETACH_REUSEPORT_BPF 68 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 66c5dd245ac7..10173c32195e 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -114,6 +114,8 @@ #define SO_RCVTIMEO_NEW 0x4040 #define SO_SNDTIMEO_NEW 0x4041 +#define SO_DETACH_REUSEPORT_BPF 0x4042 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 9265a9eece15..8029b681fc7c 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -115,6 +115,8 @@ #define SO_RCVTIMEO_NEW 0x0044 #define SO_SNDTIMEO_NEW 0x0045 +#define SO_DETACH_REUSEPORT_BPF 0x0047 + #if !defined(__KERNEL__) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9f7c453db70c..a62e7889b0b6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -277,6 +277,7 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ + PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ }; /* The information passed from prog-specific *_is_valid_access @@ -1098,6 +1099,15 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); + +bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); + +u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, @@ -1114,6 +1124,21 @@ static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, { return 0; } +static inline bool bpf_xdp_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} + +static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} #endif /* CONFIG_INET */ #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 026ba8b81e88..5fe99f322b1c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -136,6 +136,8 @@ struct bpf_reg_state { */ s32 subreg_def; enum bpf_reg_liveness live; + /* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */ + bool precise; }; enum bpf_stack_slot_type { @@ -187,14 +189,77 @@ struct bpf_func_state { struct bpf_stack_state *stack; }; +struct bpf_idx_pair { + u32 prev_idx; + u32 idx; +}; + #define MAX_CALL_FRAMES 8 struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; + struct bpf_verifier_state *parent; + /* + * 'branches' field is the number of branches left to explore: + * 0 - all possible paths from this state reached bpf_exit or + * were safely pruned + * 1 - at least one path is being explored. + * This state hasn't reached bpf_exit + * 2 - at least two paths are being explored. + * This state is an immediate parent of two children. + * One is fallthrough branch with branches==1 and another + * state is pushed into stack (to be explored later) also with + * branches==1. The parent of this state has branches==1. + * The verifier state tree connected via 'parent' pointer looks like: + * 1 + * 1 + * 2 -> 1 (first 'if' pushed into stack) + * 1 + * 2 -> 1 (second 'if' pushed into stack) + * 1 + * 1 + * 1 bpf_exit. + * + * Once do_check() reaches bpf_exit, it calls update_branch_counts() + * and the verifier state tree will look: + * 1 + * 1 + * 2 -> 1 (first 'if' pushed into stack) + * 1 + * 1 -> 1 (second 'if' pushed into stack) + * 0 + * 0 + * 0 bpf_exit. + * After pop_stack() the do_check() will resume at second 'if'. + * + * If is_state_visited() sees a state with branches > 0 it means + * there is a loop. If such state is exactly equal to the current state + * it's an infinite loop. Note states_equal() checks for states + * equvalency, so two states being 'states_equal' does not mean + * infinite loop. The exact comparison is provided by + * states_maybe_looping() function. It's a stronger pre-check and + * much faster than states_equal(). + * + * This algorithm may not find all possible infinite loops or + * loop iteration count may be too high. + * In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in. + */ + u32 branches; u32 insn_idx; u32 curframe; u32 active_spin_lock; bool speculative; + + /* first and last insn idx of this verifier state */ + u32 first_insn_idx; + u32 last_insn_idx; + /* jmp history recorded from first to last. + * backtracking is using it to go from last to first. + * For most states jmp_history_cnt is [0-3]. + * For loops can go up to ~40. + */ + struct bpf_idx_pair *jmp_history; + u32 jmp_history_cnt; }; #define bpf_get_spilled_reg(slot, frame) \ @@ -309,7 +374,9 @@ struct bpf_verifier_env { } cfg; u32 subprog_cnt; /* number of instructions analyzed by the verifier */ - u32 insn_processed; + u32 prev_insn_processed, insn_processed; + /* number of jmps, calls, exits analyzed so far */ + u32 prev_jmps_processed, jmps_processed; /* total verification time */ u64 verification_time; /* maximum number of verifier states kept in 'branching' instructions */ diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 8a5f70c7cdf2..d9112de85261 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -35,6 +35,8 @@ extern struct sock *reuseport_select_sock(struct sock *sk, struct sk_buff *skb, int hdr_len); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); +extern int reuseport_detach_prog(struct sock *sk); + int reuseport_get_id(struct sock_reuseport *reuse); #endif /* _SOCK_REUSEPORT_H */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index d074b6d60f8a..ae0f368a62bb 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -58,11 +58,11 @@ struct xdp_sock { struct xdp_umem *umem; struct list_head flush_node; u16 queue_id; - struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; bool zc; /* Protects multiple processes in the control path */ struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; + struct list_head list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8c1391c89171..77f7c1638eb1 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -117,6 +117,8 @@ #define SO_RCVTIMEO_NEW 66 #define SO_SNDTIMEO_NEW 67 +#define SO_DETACH_REUSEPORT_BPF 68 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0e879721f75a..b077507efa3f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3085,6 +3085,10 @@ struct bpf_sock_tuple { }; }; +struct bpf_xdp_sock { + __u32 queue_id; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. @@ -3245,6 +3249,7 @@ struct bpf_sock_addr { __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. * Stored in network byte order. */ + __bpf_md_ptr(struct bpf_sock *, sk); }; /* User bpf_sock_ops struct to access socket values and specify request ops @@ -3296,6 +3301,7 @@ struct bpf_sock_ops { __u32 sk_txhash; __u64 bytes_received; __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); }; /* Definitions for bpf_sock_ops_cb_flags */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 4c2fa3ac56f6..29d781061cd5 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-y := core.o +CFLAGS_core.o += $(call cc-disable-warning, override-init) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index b84c44505e06..40e86a7e0ef0 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -80,8 +80,8 @@ static u64 dev_map_bitmap_size(const union bpf_attr *attr) static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; - int err = -EINVAL; u64 cost; + int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1e9d10b32984..0e079b2298f8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -326,7 +326,8 @@ static bool type_is_sk_pointer(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_SOCK_COMMON || - type == PTR_TO_TCP_SOCK; + type == PTR_TO_TCP_SOCK || + type == PTR_TO_XDP_SOCK; } static bool reg_type_may_be_null(enum bpf_reg_type type) @@ -398,6 +399,7 @@ static const char * const reg_type_str[] = { [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", [PTR_TO_TP_BUFFER] = "tp_buffer", + [PTR_TO_XDP_SOCK] = "xdp_sock", }; static char slot_type_char[] = { @@ -445,12 +447,12 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, " R%d", i); print_liveness(env, reg->live); verbose(env, "=%s", reg_type_str[t]); + if (t == SCALAR_VALUE && reg->precise) + verbose(env, "P"); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); - if (t == PTR_TO_STACK) - verbose(env, ",call_%d", func(env, reg)->callsite); } else { verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) @@ -512,11 +514,17 @@ static void print_verifier_state(struct bpf_verifier_env *env, continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); - if (state->stack[i].slot_type[0] == STACK_SPILL) - verbose(env, "=%s", - reg_type_str[state->stack[i].spilled_ptr.type]); - else + if (state->stack[i].slot_type[0] == STACK_SPILL) { + reg = &state->stack[i].spilled_ptr; + t = reg->type; + verbose(env, "=%s", reg_type_str[t]); + if (t == SCALAR_VALUE && reg->precise) + verbose(env, "P"); + if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) + verbose(env, "%lld", reg->var_off.value + reg->off); + } else { verbose(env, "=%s", types_buf); + } } if (state->acquired_refs && state->refs[0].id) { verbose(env, " refs=%d", state->refs[0].id); @@ -665,6 +673,13 @@ static void free_func_state(struct bpf_func_state *state) kfree(state); } +static void clear_jmp_history(struct bpf_verifier_state *state) +{ + kfree(state->jmp_history); + state->jmp_history = NULL; + state->jmp_history_cnt = 0; +} + static void free_verifier_state(struct bpf_verifier_state *state, bool free_self) { @@ -674,6 +689,7 @@ static void free_verifier_state(struct bpf_verifier_state *state, free_func_state(state->frame[i]); state->frame[i] = NULL; } + clear_jmp_history(state); if (free_self) kfree(state); } @@ -701,8 +717,18 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src) { struct bpf_func_state *dst; + u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt; int i, err; + if (dst_state->jmp_history_cnt < src->jmp_history_cnt) { + kfree(dst_state->jmp_history); + dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER); + if (!dst_state->jmp_history) + return -ENOMEM; + } + memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz); + dst_state->jmp_history_cnt = src->jmp_history_cnt; + /* if dst has more stack frames then src frame, free them */ for (i = src->curframe + 1; i <= dst_state->curframe; i++) { free_func_state(dst_state->frame[i]); @@ -711,6 +737,10 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; dst_state->active_spin_lock = src->active_spin_lock; + dst_state->branches = src->branches; + dst_state->parent = src->parent; + dst_state->first_insn_idx = src->first_insn_idx; + dst_state->last_insn_idx = src->last_insn_idx; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -726,6 +756,23 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, return 0; } +static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) +{ + while (st) { + u32 br = --st->branches; + + /* WARN_ON(br > 1) technically makes sense here, + * but see comment in push_stack(), hence: + */ + WARN_ONCE((int)br < 0, + "BUG update_branch_counts:branches_to_explore=%d\n", + br); + if (br) + break; + st = st->parent; + } +} + static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, int *insn_idx) { @@ -779,6 +826,18 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, env->stack_size); goto err; } + if (elem->st.parent) { + ++elem->st.parent->branches; + /* WARN_ON(branches > 2) technically makes sense here, + * but + * 1. speculative states will bump 'branches' for non-branch + * instructions + * 2. is_state_visited() heuristics may decide not to create + * a new state for a sequence of branches and all such current + * and cloned states will be pointing to a single parent state + * which might have large 'branches' count. + */ + } return &elem->st; err: free_verifier_state(env->cur_state, true); @@ -926,6 +985,9 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; + + /* constant backtracking is enabled for root only for now */ + reg->precise = capable(CAP_SYS_ADMIN) ? false : true; } /* Mark a register as having a completely unknown (scalar) value. */ @@ -1337,6 +1399,389 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return 0; } +/* for any branch, call, exit record the history of jmps in the given state */ +static int push_jmp_history(struct bpf_verifier_env *env, + struct bpf_verifier_state *cur) +{ + u32 cnt = cur->jmp_history_cnt; + struct bpf_idx_pair *p; + + cnt++; + p = krealloc(cur->jmp_history, cnt * sizeof(*p), GFP_USER); + if (!p) + return -ENOMEM; + p[cnt - 1].idx = env->insn_idx; + p[cnt - 1].prev_idx = env->prev_insn_idx; + cur->jmp_history = p; + cur->jmp_history_cnt = cnt; + return 0; +} + +/* Backtrack one insn at a time. If idx is not at the top of recorded + * history then previous instruction came from straight line execution. + */ +static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, + u32 *history) +{ + u32 cnt = *history; + + if (cnt && st->jmp_history[cnt - 1].idx == i) { + i = st->jmp_history[cnt - 1].prev_idx; + (*history)--; + } else { + i--; + } + return i; +} + +/* For given verifier state backtrack_insn() is called from the last insn to + * the first insn. Its purpose is to compute a bitmask of registers and + * stack slots that needs precision in the parent verifier state. + */ +static int backtrack_insn(struct bpf_verifier_env *env, int idx, + u32 *reg_mask, u64 *stack_mask) +{ + const struct bpf_insn_cbs cbs = { + .cb_print = verbose, + .private_data = env, + }; + struct bpf_insn *insn = env->prog->insnsi + idx; + u8 class = BPF_CLASS(insn->code); + u8 opcode = BPF_OP(insn->code); + u8 mode = BPF_MODE(insn->code); + u32 dreg = 1u << insn->dst_reg; + u32 sreg = 1u << insn->src_reg; + u32 spi; + + if (insn->code == 0) + return 0; + if (env->log.level & BPF_LOG_LEVEL) { + verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); + verbose(env, "%d: ", idx); + print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); + } + + if (class == BPF_ALU || class == BPF_ALU64) { + if (!(*reg_mask & dreg)) + return 0; + if (opcode == BPF_MOV) { + if (BPF_SRC(insn->code) == BPF_X) { + /* dreg = sreg + * dreg needs precision after this insn + * sreg needs precision before this insn + */ + *reg_mask &= ~dreg; + *reg_mask |= sreg; + } else { + /* dreg = K + * dreg needs precision after this insn. + * Corresponding register is already marked + * as precise=true in this verifier state. + * No further markings in parent are necessary + */ + *reg_mask &= ~dreg; + } + } else { + if (BPF_SRC(insn->code) == BPF_X) { + /* dreg += sreg + * both dreg and sreg need precision + * before this insn + */ + *reg_mask |= sreg; + } /* else dreg += K + * dreg still needs precision before this insn + */ + } + } else if (class == BPF_LDX) { + if (!(*reg_mask & dreg)) + return 0; + *reg_mask &= ~dreg; + + /* scalars can only be spilled into stack w/o losing precision. + * Load from any other memory can be zero extended. + * The desire to keep that precision is already indicated + * by 'precise' mark in corresponding register of this state. + * No further tracking necessary. + */ + if (insn->src_reg != BPF_REG_FP) + return 0; + if (BPF_SIZE(insn->code) != BPF_DW) + return 0; + + /* dreg = *(u64 *)[fp - off] was a fill from the stack. + * that [fp - off] slot contains scalar that needs to be + * tracked with precision + */ + spi = (-insn->off - 1) / BPF_REG_SIZE; + if (spi >= 64) { + verbose(env, "BUG spi %d\n", spi); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + *stack_mask |= 1ull << spi; + } else if (class == BPF_STX) { + if (*reg_mask & dreg) + /* stx shouldn't be using _scalar_ dst_reg + * to access memory. It means backtracking + * encountered a case of pointer subtraction. + */ + return -ENOTSUPP; + /* scalars can only be spilled into stack */ + if (insn->dst_reg != BPF_REG_FP) + return 0; + if (BPF_SIZE(insn->code) != BPF_DW) + return 0; + spi = (-insn->off - 1) / BPF_REG_SIZE; + if (spi >= 64) { + verbose(env, "BUG spi %d\n", spi); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + if (!(*stack_mask & (1ull << spi))) + return 0; + *stack_mask &= ~(1ull << spi); + *reg_mask |= sreg; + } else if (class == BPF_JMP || class == BPF_JMP32) { + if (opcode == BPF_CALL) { + if (insn->src_reg == BPF_PSEUDO_CALL) + return -ENOTSUPP; + /* regular helper call sets R0 */ + *reg_mask &= ~1; + if (*reg_mask & 0x3f) { + /* if backtracing was looking for registers R1-R5 + * they should have been found already. + */ + verbose(env, "BUG regs %x\n", *reg_mask); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + } else if (opcode == BPF_EXIT) { + return -ENOTSUPP; + } + } else if (class == BPF_LD) { + if (!(*reg_mask & dreg)) + return 0; + *reg_mask &= ~dreg; + /* It's ld_imm64 or ld_abs or ld_ind. + * For ld_imm64 no further tracking of precision + * into parent is necessary + */ + if (mode == BPF_IND || mode == BPF_ABS) + /* to be analyzed */ + return -ENOTSUPP; + } else if (class == BPF_ST) { + if (*reg_mask & dreg) + /* likely pointer subtraction */ + return -ENOTSUPP; + } + return 0; +} + +/* the scalar precision tracking algorithm: + * . at the start all registers have precise=false. + * . scalar ranges are tracked as normal through alu and jmp insns. + * . once precise value of the scalar register is used in: + * . ptr + scalar alu + * . if (scalar cond K|scalar) + * . helper_call(.., scalar, ...) where ARG_CONST is expected + * backtrack through the verifier states and mark all registers and + * stack slots with spilled constants that these scalar regisers + * should be precise. + * . during state pruning two registers (or spilled stack slots) + * are equivalent if both are not precise. + * + * Note the verifier cannot simply walk register parentage chain, + * since many different registers and stack slots could have been + * used to compute single precise scalar. + * + * The approach of starting with precise=true for all registers and then + * backtrack to mark a register as not precise when the verifier detects + * that program doesn't care about specific value (e.g., when helper + * takes register as ARG_ANYTHING parameter) is not safe. + * + * It's ok to walk single parentage chain of the verifier states. + * It's possible that this backtracking will go all the way till 1st insn. + * All other branches will be explored for needing precision later. + * + * The backtracking needs to deal with cases like: + * R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0) + * r9 -= r8 + * r5 = r9 + * if r5 > 0x79f goto pc+7 + * R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff)) + * r5 += 1 + * ... + * call bpf_perf_event_output#25 + * where .arg5_type = ARG_CONST_SIZE_OR_ZERO + * + * and this case: + * r6 = 1 + * call foo // uses callee's r6 inside to compute r0 + * r0 += r6 + * if r0 == 0 goto + * + * to track above reg_mask/stack_mask needs to be independent for each frame. + * + * Also if parent's curframe > frame where backtracking started, + * the verifier need to mark registers in both frames, otherwise callees + * may incorrectly prune callers. This is similar to + * commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences") + * + * For now backtracking falls back into conservative marking. + */ +static void mark_all_scalars_precise(struct bpf_verifier_env *env, + struct bpf_verifier_state *st) +{ + struct bpf_func_state *func; + struct bpf_reg_state *reg; + int i, j; + + /* big hammer: mark all scalars precise in this path. + * pop_stack may still get !precise scalars. + */ + for (; st; st = st->parent) + for (i = 0; i <= st->curframe; i++) { + func = st->frame[i]; + for (j = 0; j < BPF_REG_FP; j++) { + reg = &func->regs[j]; + if (reg->type != SCALAR_VALUE) + continue; + reg->precise = true; + } + for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { + if (func->stack[j].slot_type[0] != STACK_SPILL) + continue; + reg = &func->stack[j].spilled_ptr; + if (reg->type != SCALAR_VALUE) + continue; + reg->precise = true; + } + } +} + +static int mark_chain_precision(struct bpf_verifier_env *env, int regno) +{ + struct bpf_verifier_state *st = env->cur_state; + int first_idx = st->first_insn_idx; + int last_idx = env->insn_idx; + struct bpf_func_state *func; + struct bpf_reg_state *reg; + u32 reg_mask = 1u << regno; + u64 stack_mask = 0; + bool skip_first = true; + int i, err; + + if (!env->allow_ptr_leaks) + /* backtracking is root only for now */ + return 0; + + func = st->frame[st->curframe]; + reg = &func->regs[regno]; + if (reg->type != SCALAR_VALUE) { + WARN_ONCE(1, "backtracing misuse"); + return -EFAULT; + } + if (reg->precise) + return 0; + func->regs[regno].precise = true; + + for (;;) { + DECLARE_BITMAP(mask, 64); + bool new_marks = false; + u32 history = st->jmp_history_cnt; + + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); + for (i = last_idx;;) { + if (skip_first) { + err = 0; + skip_first = false; + } else { + err = backtrack_insn(env, i, ®_mask, &stack_mask); + } + if (err == -ENOTSUPP) { + mark_all_scalars_precise(env, st); + return 0; + } else if (err) { + return err; + } + if (!reg_mask && !stack_mask) + /* Found assignment(s) into tracked register in this state. + * Since this state is already marked, just return. + * Nothing to be tracked further in the parent state. + */ + return 0; + if (i == first_idx) + break; + i = get_prev_insn_idx(st, i, &history); + if (i >= env->prog->len) { + /* This can happen if backtracking reached insn 0 + * and there are still reg_mask or stack_mask + * to backtrack. + * It means the backtracking missed the spot where + * particular register was initialized with a constant. + */ + verbose(env, "BUG backtracking idx %d\n", i); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + } + st = st->parent; + if (!st) + break; + + func = st->frame[st->curframe]; + bitmap_from_u64(mask, reg_mask); + for_each_set_bit(i, mask, 32) { + reg = &func->regs[i]; + if (reg->type != SCALAR_VALUE) + continue; + if (!reg->precise) + new_marks = true; + reg->precise = true; + } + + bitmap_from_u64(mask, stack_mask); + for_each_set_bit(i, mask, 64) { + if (i >= func->allocated_stack / BPF_REG_SIZE) { + /* This can happen if backtracking + * is propagating stack precision where + * caller has larger stack frame + * than callee, but backtrack_insn() should + * have returned -ENOTSUPP. + */ + verbose(env, "BUG spi %d stack_size %d\n", + i, func->allocated_stack); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + + if (func->stack[i].slot_type[0] != STACK_SPILL) + continue; + reg = &func->stack[i].spilled_ptr; + if (reg->type != SCALAR_VALUE) + continue; + if (!reg->precise) + new_marks = true; + reg->precise = true; + } + if (env->log.level & BPF_LOG_LEVEL) { + print_verifier_state(env, func); + verbose(env, "parent %s regs=%x stack=%llx marks\n", + new_marks ? "didn't have" : "already had", + reg_mask, stack_mask); + } + + if (!new_marks) + break; + + last_idx = st->last_insn_idx; + first_idx = st->first_insn_idx; + } + return 0; +} + + static bool is_spillable_regtype(enum bpf_reg_type type) { switch (type) { @@ -1355,6 +1800,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: + case PTR_TO_XDP_SOCK: return true; default: return false; @@ -1367,6 +1813,23 @@ static bool register_is_null(struct bpf_reg_state *reg) return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); } +static bool register_is_const(struct bpf_reg_state *reg) +{ + return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off); +} + +static void save_register_state(struct bpf_func_state *state, + int spi, struct bpf_reg_state *reg) +{ + int i; + + state->stack[spi].spilled_ptr = *reg; + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + + for (i = 0; i < BPF_REG_SIZE; i++) + state->stack[spi].slot_type[i] = STACK_SPILL; +} + /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -1376,7 +1839,8 @@ static int check_stack_write(struct bpf_verifier_env *env, { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; - enum bpf_reg_type type; + u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg; + struct bpf_reg_state *reg = NULL; err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), state->acquired_refs, true); @@ -1393,27 +1857,48 @@ static int check_stack_write(struct bpf_verifier_env *env, } cur = env->cur_state->frame[env->cur_state->curframe]; - if (value_regno >= 0 && - is_spillable_regtype((type = cur->regs[value_regno].type))) { - + if (value_regno >= 0) + reg = &cur->regs[value_regno]; + + if (reg && size == BPF_REG_SIZE && register_is_const(reg) && + !register_is_null(reg) && env->allow_ptr_leaks) { + if (dst_reg != BPF_REG_FP) { + /* The backtracking logic can only recognize explicit + * stack slot address like [fp - 8]. Other spill of + * scalar via different register has to be conervative. + * Backtrack from here and mark all registers as precise + * that contributed into 'reg' being a constant. + */ + err = mark_chain_precision(env, value_regno); + if (err) + return err; + } + save_register_state(state, spi, reg); + } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { + verbose_linfo(env, insn_idx, "; "); verbose(env, "invalid size of register spill\n"); return -EACCES; } - if (state != cur && type == PTR_TO_STACK) { + if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - /* save register state */ - state->stack[spi].spilled_ptr = cur->regs[value_regno]; - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + if (!env->allow_ptr_leaks) { + bool sanitize = false; - for (i = 0; i < BPF_REG_SIZE; i++) { - if (state->stack[spi].slot_type[i] == STACK_MISC && - !env->allow_ptr_leaks) { + if (state->stack[spi].slot_type[0] == STACK_SPILL && + register_is_const(&state->stack[spi].spilled_ptr)) + sanitize = true; + for (i = 0; i < BPF_REG_SIZE; i++) + if (state->stack[spi].slot_type[i] == STACK_MISC) { + sanitize = true; + break; + } + if (sanitize) { int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; int soff = (-spi - 1) * BPF_REG_SIZE; @@ -1436,8 +1921,8 @@ static int check_stack_write(struct bpf_verifier_env *env, } *poff = soff; } - state->stack[spi].slot_type[i] = STACK_SPILL; } + save_register_state(state, spi, reg); } else { u8 type = STACK_MISC; @@ -1460,9 +1945,13 @@ static int check_stack_write(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; /* when we zero initialize stack slots mark them as such */ - if (value_regno >= 0 && - register_is_null(&cur->regs[value_regno])) + if (reg && register_is_null(reg)) { + /* backtracking doesn't work for STACK_ZERO yet. */ + err = mark_chain_precision(env, value_regno); + if (err) + return err; type = STACK_ZERO; + } /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) @@ -1479,6 +1968,7 @@ static int check_stack_read(struct bpf_verifier_env *env, struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; + struct bpf_reg_state *reg; u8 *stype; if (reg_state->allocated_stack <= slot) { @@ -1487,11 +1977,21 @@ static int check_stack_read(struct bpf_verifier_env *env, return -EACCES; } stype = reg_state->stack[spi].slot_type; + reg = ®_state->stack[spi].spilled_ptr; if (stype[0] == STACK_SPILL) { if (size != BPF_REG_SIZE) { - verbose(env, "invalid size of register spill\n"); - return -EACCES; + if (reg->type != SCALAR_VALUE) { + verbose_linfo(env, env->insn_idx, "; "); + verbose(env, "invalid size of register fill\n"); + return -EACCES; + } + if (value_regno >= 0) { + mark_reg_unknown(env, state->regs, value_regno); + state->regs[value_regno].live |= REG_LIVE_WRITTEN; + } + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); + return 0; } for (i = 1; i < BPF_REG_SIZE; i++) { if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { @@ -1502,17 +2002,14 @@ static int check_stack_read(struct bpf_verifier_env *env, if (value_regno >= 0) { /* restore register state from stack */ - state->regs[value_regno] = reg_state->stack[spi].spilled_ptr; + state->regs[value_regno] = *reg; /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; } - mark_reg_read(env, ®_state->stack[spi].spilled_ptr, - reg_state->stack[spi].spilled_ptr.parent, - REG_LIVE_READ64); - return 0; + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { int zeros = 0; @@ -1527,23 +2024,32 @@ static int check_stack_read(struct bpf_verifier_env *env, off, i, size); return -EACCES; } - mark_reg_read(env, ®_state->stack[spi].spilled_ptr, - reg_state->stack[spi].spilled_ptr.parent, - REG_LIVE_READ64); + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (value_regno >= 0) { if (zeros == size) { /* any size read into register is zero extended, * so the whole register == const_zero */ __mark_reg_const_zero(&state->regs[value_regno]); + /* backtracking doesn't support STACK_ZERO yet, + * so mark it precise here, so that later + * backtracking can stop here. + * Backtracking may not need this if this register + * doesn't participate in pointer adjustment. + * Forward propagation of precise flag is not + * necessary either. This mark is only to stop + * backtracking. Any register that contributed + * to const 0 was marked precise before spill. + */ + state->regs[value_regno].precise = true; } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, value_regno); } state->regs[value_regno].live |= REG_LIVE_WRITTEN; } - return 0; } + return 0; } static int check_stack_access(struct bpf_verifier_env *env, @@ -1835,6 +2341,9 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, case PTR_TO_TCP_SOCK: valid = bpf_tcp_sock_is_valid_access(off, size, t, &info); break; + case PTR_TO_XDP_SOCK: + valid = bpf_xdp_sock_is_valid_access(off, size, t, &info); + break; default: valid = false; } @@ -1999,6 +2508,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_TCP_SOCK: pointer_desc = "tcp_sock "; break; + case PTR_TO_XDP_SOCK: + pointer_desc = "xdp_sock "; + break; default: break; } @@ -2398,7 +2910,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); - int err, min_off, max_off, i, slot, spi; + int err, min_off, max_off, i, j, slot, spi; if (reg->type != PTR_TO_STACK) { /* Allow zero-byte read from NULL, regardless of pointer type */ @@ -2486,6 +2998,14 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, *stype = STACK_MISC; goto mark; } + if (state->stack[spi].slot_type[0] == STACK_SPILL && + state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { + __mark_reg_unknown(&state->stack[spi].spilled_ptr); + for (j = 0; j < BPF_REG_SIZE; j++) + state->stack[spi].slot_type[j] = STACK_MISC; + goto mark; + } + err: if (tnum_is_const(reg->var_off)) { verbose(env, "invalid indirect read from stack off %d+%d size %d\n", @@ -2837,6 +3357,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_helper_mem_access(env, regno - 1, reg->umax_value, zero_size_allowed, meta); + if (!err) + err = mark_chain_precision(env, regno); } else if (arg_type_is_int_ptr(arg_type)) { int size = int_ptr_type_to_size(arg_type); @@ -2897,10 +3419,14 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, * appear. */ case BPF_MAP_TYPE_CPUMAP: - case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; + case BPF_MAP_TYPE_XSKMAP: + if (func_id != BPF_FUNC_redirect_map && + func_id != BPF_FUNC_map_lookup_elem) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) @@ -3791,6 +4317,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: + case PTR_TO_XDP_SOCK: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; @@ -4268,6 +4795,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); + int err; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; @@ -4294,11 +4822,17 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * This is legal, but we have to reverse our * src/dest handling in computing the range */ + err = mark_chain_precision(env, insn->dst_reg); + if (err) + return err; return adjust_ptr_min_max_vals(env, insn, src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ + err = mark_chain_precision(env, insn->src_reg); + if (err) + return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); } @@ -5030,6 +5564,9 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, if (reg->map_ptr->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = reg->map_ptr->inner_map_meta; + } else if (reg->map_ptr->map_type == + BPF_MAP_TYPE_XSKMAP) { + reg->type = PTR_TO_XDP_SOCK; } else { reg->type = PTR_TO_MAP_VALUE; } @@ -5201,9 +5738,10 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_verifier_state *this_branch = env->cur_state; struct bpf_verifier_state *other_branch; struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; - struct bpf_reg_state *dst_reg, *other_branch_regs; + struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; u8 opcode = BPF_OP(insn->code); bool is_jmp32; + int pred = -1; int err; /* Only conditional jumps are expected to reach here. */ @@ -5228,6 +5766,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, insn->src_reg); return -EACCES; } + src_reg = ®s[insn->src_reg]; } else { if (insn->src_reg != BPF_REG_0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); @@ -5243,20 +5782,29 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, dst_reg = ®s[insn->dst_reg]; is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - if (BPF_SRC(insn->code) == BPF_K) { - int pred = is_branch_taken(dst_reg, insn->imm, opcode, - is_jmp32); - - if (pred == 1) { - /* only follow the goto, ignore fall-through */ - *insn_idx += insn->off; - return 0; - } else if (pred == 0) { - /* only follow fall-through branch, since - * that's where the program will go - */ - return 0; - } + if (BPF_SRC(insn->code) == BPF_K) + pred = is_branch_taken(dst_reg, insn->imm, + opcode, is_jmp32); + else if (src_reg->type == SCALAR_VALUE && + tnum_is_const(src_reg->var_off)) + pred = is_branch_taken(dst_reg, src_reg->var_off.value, + opcode, is_jmp32); + if (pred >= 0) { + err = mark_chain_precision(env, insn->dst_reg); + if (BPF_SRC(insn->code) == BPF_X && !err) + err = mark_chain_precision(env, insn->src_reg); + if (err) + return err; + } + if (pred == 1) { + /* only follow the goto, ignore fall-through */ + *insn_idx += insn->off; + return 0; + } else if (pred == 0) { + /* only follow fall-through branch, since + * that's where the program will go + */ + return 0; } other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, @@ -5616,7 +6164,8 @@ static void init_explored_state(struct bpf_verifier_env *env, int idx) * w - next instruction * e - edge */ -static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) +static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, + bool loop_ok) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; @@ -5646,6 +6195,8 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) insn_stack[env->cfg.cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { + if (loop_ok && env->allow_ptr_leaks) + return 0; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); @@ -5697,7 +6248,7 @@ peek_stack: if (opcode == BPF_EXIT) { goto mark_explored; } else if (opcode == BPF_CALL) { - ret = push_insn(t, t + 1, FALLTHROUGH, env); + ret = push_insn(t, t + 1, FALLTHROUGH, env, false); if (ret == 1) goto peek_stack; else if (ret < 0) @@ -5706,7 +6257,8 @@ peek_stack: init_explored_state(env, t + 1); if (insns[t].src_reg == BPF_PSEUDO_CALL) { init_explored_state(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, + env, false); if (ret == 1) goto peek_stack; else if (ret < 0) @@ -5719,11 +6271,16 @@ peek_stack: } /* unconditional jump with single edge */ ret = push_insn(t, t + insns[t].off + 1, - FALLTHROUGH, env); + FALLTHROUGH, env, true); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; + /* unconditional jmp is not a good pruning point, + * but it's marked, since backtracking needs + * to record jmp history in is_state_visited(). + */ + init_explored_state(env, t + insns[t].off + 1); /* tell verifier to check for equivalent states * after every call and jump */ @@ -5732,13 +6289,13 @@ peek_stack: } else { /* conditional jump with two edges */ init_explored_state(env, t); - ret = push_insn(t, t + 1, FALLTHROUGH, env); + ret = push_insn(t, t + 1, FALLTHROUGH, env, true); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; - ret = push_insn(t, t + insns[t].off + 1, BRANCH, env); + ret = push_insn(t, t + insns[t].off + 1, BRANCH, env, true); if (ret == 1) goto peek_stack; else if (ret < 0) @@ -5748,7 +6305,7 @@ peek_stack: /* all other non-branch instructions with single * fall-through edge */ - ret = push_insn(t, t + 1, FALLTHROUGH, env); + ret = push_insn(t, t + 1, FALLTHROUGH, env, false); if (ret == 1) goto peek_stack; else if (ret < 0) @@ -6181,6 +6738,8 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn, sl = *explored_state(env, insn); while (sl) { + if (sl->state.branches) + goto next; if (sl->state.insn_idx != insn || sl->state.curframe != cur->curframe) goto next; @@ -6222,6 +6781,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, switch (rold->type) { case SCALAR_VALUE: if (rcur->type == SCALAR_VALUE) { + if (!rold->precise && !rcur->precise) + return true; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); @@ -6294,6 +6855,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: + case PTR_TO_XDP_SOCK: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -6544,19 +7106,52 @@ static int propagate_liveness(struct bpf_verifier_env *env, return 0; } +static bool states_maybe_looping(struct bpf_verifier_state *old, + struct bpf_verifier_state *cur) +{ + struct bpf_func_state *fold, *fcur; + int i, fr = cur->curframe; + + if (old->curframe != fr) + return false; + + fold = old->frame[fr]; + fcur = cur->frame[fr]; + for (i = 0; i < MAX_BPF_REG; i++) + if (memcmp(&fold->regs[i], &fcur->regs[i], + offsetof(struct bpf_reg_state, parent))) + return false; + return true; +} + + static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; + bool add_new_state = false; + cur->last_insn_idx = env->prev_insn_idx; if (!env->insn_aux_data[insn_idx].prune_point) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ return 0; + /* bpf progs typically have pruning point every 4 instructions + * http://vger.kernel.org/bpfconf2019.html#session-1 + * Do not add new state for future pruning if the verifier hasn't seen + * at least 2 jumps and at least 8 instructions. + * This heuristics helps decrease 'total_states' and 'peak_states' metric. + * In tests that amounts to up to 50% reduction into total verifier + * memory consumption and 20% verifier time speedup. + */ + if (env->jmps_processed - env->prev_jmps_processed >= 2 && + env->insn_processed - env->prev_insn_processed >= 8) + add_new_state = true; + pprev = explored_state(env, insn_idx); sl = *pprev; @@ -6566,6 +7161,30 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) states_cnt++; if (sl->state.insn_idx != insn_idx) goto next; + if (sl->state.branches) { + if (states_maybe_looping(&sl->state, cur) && + states_equal(env, &sl->state, cur)) { + verbose_linfo(env, insn_idx, "; "); + verbose(env, "infinite loop detected at insn %d\n", insn_idx); + return -EINVAL; + } + /* if the verifier is processing a loop, avoid adding new state + * too often, since different loop iterations have distinct + * states and may not help future pruning. + * This threshold shouldn't be too low to make sure that + * a loop with large bound will be rejected quickly. + * The most abusive loop will be: + * r1 += 1 + * if r1 < 1000000 goto pc-2 + * 1M insn_procssed limit / 100 == 10k peak states. + * This threshold shouldn't be too high either, since states + * at the end of the loop are likely to be useful in pruning. + */ + if (env->jmps_processed - env->prev_jmps_processed < 20 && + env->insn_processed - env->prev_insn_processed < 100) + add_new_state = false; + goto miss; + } if (states_equal(env, &sl->state, cur)) { sl->hit_cnt++; /* reached equivalent register/stack state, @@ -6583,7 +7202,15 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return err; return 1; } - sl->miss_cnt++; +miss: + /* when new state is not going to be added do not increase miss count. + * Otherwise several loop iterations will remove the state + * recorded earlier. The goal of these heuristics is to have + * states from some iterations of the loop (some in the beginning + * and some at the end) to help pruning. + */ + if (add_new_state) + sl->miss_cnt++; /* heuristic to determine whether this state is beneficial * to keep checking from state equivalence point of view. * Higher numbers increase max_states_per_insn and verification time, @@ -6595,6 +7222,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) */ *pprev = sl->next; if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) { + u32 br = sl->state.branches; + + WARN_ONCE(br, + "BUG live_done but branches_to_explore %d\n", + br); free_verifier_state(&sl->state, false); kfree(sl); env->peak_states--; @@ -6618,20 +7250,27 @@ next: env->max_states_per_insn = states_cnt; if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) - return 0; + return push_jmp_history(env, cur); + + if (!add_new_state) + return push_jmp_history(env, cur); - /* there were no equivalent states, remember current one. - * technically the current state is not proven to be safe yet, + /* There were no equivalent states, remember the current one. + * Technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) - * or it will be rejected. Since there are no loops, we won't be + * or it will be rejected. When there are no loops the verifier won't be * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx) - * again on the way to bpf_exit + * again on the way to bpf_exit. + * When looping the sl->state.branches will be > 0 and this state + * will not be considered for equivalence until branches == 0. */ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) return -ENOMEM; env->total_states++; env->peak_states++; + env->prev_jmps_processed = env->jmps_processed; + env->prev_insn_processed = env->insn_processed; /* add new state to the head of linked list */ new = &new_sl->state; @@ -6642,6 +7281,12 @@ next: return err; } new->insn_idx = insn_idx; + WARN_ONCE(new->branches != 1, + "BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx); + + cur->parent = new; + cur->first_insn_idx = insn_idx; + clear_jmp_history(cur); new_sl->next = *explored_state(env, insn_idx); *explored_state(env, insn_idx) = new_sl; /* connect new state to parentage chain. Current frame needs all @@ -6651,17 +7296,18 @@ next: * the state of the call instruction (with WRITTEN set), and r0 comes * from callee with its full parentage chain, anyway. */ - for (j = 0; j <= cur->curframe; j++) - for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) - cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark * their parent and current state never has children yet. Only * explored_states can get read marks.) */ - for (i = 0; i < BPF_REG_FP; i++) - cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE; + for (j = 0; j <= cur->curframe; j++) { + for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) + cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; + for (i = 0; i < BPF_REG_FP; i++) + cur->frame[j]->regs[i].live = REG_LIVE_NONE; + } /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { @@ -6688,6 +7334,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: + case PTR_TO_XDP_SOCK: return false; default: return true; @@ -6719,6 +7366,7 @@ static int do_check(struct bpf_verifier_env *env) struct bpf_reg_state *regs; int insn_cnt = env->prog->len; bool do_print_state = false; + int prev_insn_idx = -1; env->prev_linfo = NULL; @@ -6727,6 +7375,7 @@ static int do_check(struct bpf_verifier_env *env) return -ENOMEM; state->curframe = 0; state->speculative = false; + state->branches = 1; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); @@ -6743,6 +7392,7 @@ static int do_check(struct bpf_verifier_env *env) u8 class; int err; + env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", env->insn_idx, insn_cnt); @@ -6815,6 +7465,7 @@ static int do_check(struct bpf_verifier_env *env) regs = cur_regs(env); env->insn_aux_data[env->insn_idx].seen = true; + prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); @@ -6933,6 +7584,7 @@ static int do_check(struct bpf_verifier_env *env) } else if (class == BPF_JMP || class == BPF_JMP32) { u8 opcode = BPF_OP(insn->code); + env->jmps_processed++; if (opcode == BPF_CALL) { if (BPF_SRC(insn->code) != BPF_K || insn->off != 0 || @@ -6987,7 +7639,6 @@ static int do_check(struct bpf_verifier_env *env) if (state->curframe) { /* exit from nested function */ - env->prev_insn_idx = env->insn_idx; err = prepare_func_exit(env, &env->insn_idx); if (err) return err; @@ -7018,7 +7669,8 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; process_bpf_exit: - err = pop_stack(env, &env->prev_insn_idx, + update_branch_counts(env, env->cur_state); + err = pop_stack(env, &prev_insn_idx, &env->insn_idx); if (err < 0) { if (err != -ENOENT) @@ -7821,6 +8473,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) case PTR_TO_TCP_SOCK: convert_ctx_access = bpf_tcp_sock_convert_ctx_access; break; + case PTR_TO_XDP_SOCK: + convert_ctx_access = bpf_xdp_sock_convert_ctx_access; + break; default: continue; } diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index 22066c28ba61..ef7338cebd18 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -17,8 +17,8 @@ struct xsk_map { static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) { - int cpu, err = -EINVAL; struct xsk_map *m; + int cpu, err; u64 cost; if (!capable(CAP_NET_ADMIN)) @@ -152,6 +152,12 @@ void __xsk_map_flush(struct bpf_map *map) static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { + WARN_ON_ONCE(!rcu_read_lock_held()); + return __xsk_map_lookup_elem(map, *(u32 *)key); +} + +static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key) +{ return ERR_PTR(-EOPNOTSUPP); } @@ -218,6 +224,7 @@ const struct bpf_map_ops xsk_map_ops = { .map_free = xsk_map_free, .map_get_next_key = xsk_map_get_next_key, .map_lookup_elem = xsk_map_lookup_elem, + .map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only, .map_update_elem = xsk_map_update_elem, .map_delete_elem = xsk_map_delete_elem, .map_check_btf = map_check_no_btf, diff --git a/net/core/filter.c b/net/core/filter.c index 949adc3d9abb..2014d76e0d2a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5695,6 +5695,46 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) return INET_ECN_set_ce(skb); } +bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id)) + return false; + + if (off % size != 0) + return false; + + switch (off) { + default: + return size == sizeof(__u32); + } +} + +u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + +#define BPF_XDP_SOCK_GET(FIELD) \ + do { \ + BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) > \ + FIELD_SIZEOF(struct bpf_xdp_sock, FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ + si->dst_reg, si->src_reg, \ + offsetof(struct xdp_sock, FIELD)); \ + } while (0) + + switch (si->off) { + case offsetof(struct bpf_xdp_sock, queue_id): + BPF_XDP_SOCK_GET(queue_id); + break; + } + + return insn - insn_buf; +} + static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { .func = bpf_skb_ecn_set_ce, .gpl_only = false, @@ -5897,6 +5937,10 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skc_lookup_tcp: return &bpf_sock_addr_skc_lookup_tcp_proto; #endif /* CONFIG_INET */ + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; default: return bpf_base_func_proto(func_id); } @@ -5934,6 +5978,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; +#ifdef CONFIG_SOCK_CGROUP_DATA + case BPF_FUNC_skb_cgroup_id: + return &bpf_skb_cgroup_id_proto; +#endif #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; @@ -6114,6 +6162,14 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: return &bpf_sockopt_event_output_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; +#ifdef CONFIG_INET + case BPF_FUNC_tcp_sock: + return &bpf_tcp_sock_proto; +#endif /* CONFIG_INET */ default: return bpf_base_func_proto(func_id); } @@ -6801,6 +6857,13 @@ static bool sock_addr_is_valid_access(int off, int size, if (size != size_default) return false; break; + case offsetof(struct bpf_sock_addr, sk): + if (type != BPF_READ) + return false; + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_SOCKET; + break; default: if (type == BPF_READ) { if (size != size_default) @@ -6844,6 +6907,11 @@ static bool sock_ops_is_valid_access(int off, int size, if (size != sizeof(__u64)) return false; break; + case offsetof(struct bpf_sock_ops, sk): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_SOCKET_OR_NULL; + break; default: if (size != size_default) return false; @@ -7751,6 +7819,11 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, struct bpf_sock_addr_kern, struct in6_addr, t_ctx, s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; + case offsetof(struct bpf_sock_addr, sk): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_addr_kern, sk)); + break; } return insn - insn_buf; @@ -8010,6 +8083,19 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; + case offsetof(struct bpf_sock_ops, sk): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, + is_fullsock), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + is_fullsock)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + break; } return insn - insn_buf; } diff --git a/net/core/sock.c b/net/core/sock.c index af09a23e4822..ef471f643c95 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1039,6 +1039,10 @@ set_rcvbuf: } break; + case SO_DETACH_REUSEPORT_BPF: + ret = reuseport_detach_prog(sk); + break; + case SO_DETACH_FILTER: ret = sk_detach_filter(sk); break; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index dc4aefdf2a08..9408f9264d05 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -332,3 +332,27 @@ int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) return 0; } EXPORT_SYMBOL(reuseport_attach_prog); + +int reuseport_detach_prog(struct sock *sk) +{ + struct sock_reuseport *reuse; + struct bpf_prog *old_prog; + + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return sk->sk_reuseport ? -ENOENT : -EINVAL; + + old_prog = NULL; + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + rcu_swap_protected(reuse->prog, old_prog, + lockdep_is_held(&reuseport_lock)); + spin_unlock_bh(&reuseport_lock); + + if (!old_prog) + return -ENOENT; + + sk_reuseport_prog_free(old_prog); + return 0; +} +EXPORT_SYMBOL(reuseport_detach_prog); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 253e5a2856be..0917f8cf4fab 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -170,21 +170,12 @@ always += ibumad_kern.o always += hbm_out_kern.o KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include -KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ +KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable -HOSTCFLAGS_trace_helpers.o += -I$(srctree)/tools/lib/bpf/ - -HOSTCFLAGS_trace_output_user.o += -I$(srctree)/tools/lib/bpf/ -HOSTCFLAGS_offwaketime_user.o += -I$(srctree)/tools/lib/bpf/ -HOSTCFLAGS_spintest_user.o += -I$(srctree)/tools/lib/bpf/ -HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/ -HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/ -HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/ -HOSTCFLAGS_xdp_sample_pkts_user.o += -I$(srctree)/tools/lib/bpf/ KBUILD_HOSTLDLIBS += $(LIBBPF) -lelf HOSTLDLIBS_tracex4 += -lrt @@ -206,6 +197,17 @@ HOSTCC = $(CROSS_COMPILE)gcc CLANG_ARCH_ARGS = -target $(ARCH) endif +# Don't evaluate probes and warnings if we need to run make recursively +ifneq ($(src),) +HDR_PROBE := $(shell echo "\#include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \ + $(HOSTCC) $(KBUILD_HOSTCFLAGS) -x c - -o /dev/null 2>/dev/null && \ + echo okay) + +ifeq ($(HDR_PROBE),) +$(warning WARNING: Detected possible issues with include path.) +$(warning WARNING: Please install kernel headers locally (make headers_install).) +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 $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') @@ -223,6 +225,7 @@ ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),) DWARF2BTF = y endif endif +endif # Trick to allow make to be run from this directory all: diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index e51eb060244e..2d4b717726b6 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -14,7 +14,7 @@ #include <bpf/bpf.h> -#include "bpf/libbpf.h" +#include "libbpf.h" #include "bpf_insn.h" #include "sock_example.h" diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 480b7ad6a1f2..b905b32ff185 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -50,8 +50,8 @@ #include "cgroup_helpers.h" #include "hbm.h" #include "bpf_util.h" -#include "bpf/bpf.h" -#include "bpf/libbpf.h" +#include "bpf.h" +#include "libbpf.h" bool outFlag = true; int minRate = 1000; /* cgroup rate limit in Mbps */ @@ -411,7 +411,7 @@ static void Usage(void) " -l also limit flows using loopback\n" " -n <#> to create cgroup \"/hbm#\" and attach prog\n" " Default is /hbm1\n" - " --no_cn disable CN notifcations\n" + " --no_cn disable CN notifications\n" " -r <rate> Rate in Mbps\n" " -s Update HBM stats\n" " -t <time> Exit after specified seconds (default is 0)\n" diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c index 097d76143363..cb5a8f994849 100644 --- a/samples/bpf/ibumad_user.c +++ b/samples/bpf/ibumad_user.c @@ -25,7 +25,7 @@ #include "bpf_load.h" #include "bpf_util.h" -#include "bpf/libbpf.h" +#include "libbpf.h" static void dump_counts(int fd) { diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c index 7f90796ae15a..a219442afbee 100644 --- a/samples/bpf/sockex1_user.c +++ b/samples/bpf/sockex1_user.c @@ -3,7 +3,7 @@ #include <assert.h> #include <linux/bpf.h> #include <bpf/bpf.h> -#include "bpf/libbpf.h" +#include "libbpf.h" #include "sock_example.h" #include <unistd.h> #include <arpa/inet.h> diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c index bc257333ad92..6de383ddd08b 100644 --- a/samples/bpf/sockex2_user.c +++ b/samples/bpf/sockex2_user.c @@ -3,7 +3,7 @@ #include <assert.h> #include <linux/bpf.h> #include <bpf/bpf.h> -#include "bpf/libbpf.h" +#include "libbpf.h" #include "sock_example.h" #include <unistd.h> #include <arpa/inet.h> diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index 5b39421adb44..a8e5fa02e8a8 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -15,8 +15,8 @@ #include <net/if.h> #include "bpf_util.h" -#include "bpf/bpf.h" -#include "bpf/libbpf.h" +#include "bpf.h" +#include "libbpf.h" static int ifindex; static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index 07e1b9269e49..586ff751aba9 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -18,8 +18,8 @@ #include <netinet/ether.h> #include <unistd.h> #include <time.h> -#include "bpf/bpf.h" -#include "bpf/libbpf.h" +#include "bpf.h" +#include "libbpf.h" #define STATS_INTERVAL_S 2U diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c index f88e1d7093d6..5b46ee12c696 100644 --- a/samples/bpf/xdp_fwd_user.c +++ b/samples/bpf/xdp_fwd_user.c @@ -24,7 +24,7 @@ #include <fcntl.h> #include <libgen.h> -#include "bpf/libbpf.h" +#include "libbpf.h" #include <bpf/bpf.h> diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 586b294d72d3..f5dc7e1f8bc6 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -25,7 +25,7 @@ static const char *__doc__ = #define MAX_PROG 6 #include <bpf/bpf.h> -#include "bpf/libbpf.h" +#include "libbpf.h" #include "bpf_util.h" diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index be317f5f058f..15bb6f67f9c3 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -16,7 +16,7 @@ #include "bpf_util.h" #include <bpf/bpf.h> -#include "bpf/libbpf.h" +#include "libbpf.h" static int ifindex_in; static int ifindex_out; diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 09747bee6668..ce71be187205 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -16,7 +16,7 @@ #include "bpf_util.h" #include <bpf/bpf.h> -#include "bpf/libbpf.h" +#include "libbpf.h" static int ifindex_in; static int ifindex_out; diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index 1f66419631c3..1469b66ebad1 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -21,7 +21,7 @@ #include <sys/ioctl.h> #include <sys/syscall.h> #include "bpf_util.h" -#include "bpf/libbpf.h" +#include "libbpf.h" #include <sys/resource.h> #include <libgen.h> diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 1210f3b170f0..c7e4e45d824a 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -22,8 +22,8 @@ static const char *__doc__ = " XDP RX-queue info extract example\n\n" #include <arpa/inet.h> #include <linux/if_link.h> -#include "bpf/bpf.h" -#include "bpf/libbpf.h" +#include "bpf.h" +#include "libbpf.h" #include "bpf_util.h" static int ifindex = -1; diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index e746a00d122e..394896430712 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -14,7 +14,7 @@ #include <netinet/ether.h> #include <unistd.h> #include <time.h> -#include "bpf/libbpf.h" +#include "libbpf.h" #include <bpf/bpf.h> #include "bpf_util.h" #include "xdp_tx_iptunnel_common.h" diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index d08ee1ab7bb4..0f5eb0d7f2df 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -27,8 +27,8 @@ #include <time.h> #include <unistd.h> -#include "bpf/libbpf.h" -#include "bpf/xsk.h" +#include "libbpf.h" +#include "xsk.h" #include <bpf/bpf.h> #ifndef SOL_XDP diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index f7261fad45c1..5215e0870bcb 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -21,6 +21,7 @@ #include <sys/vfs.h> #include <bpf.h> +#include <libbpf.h> /* libbpf_num_possible_cpus */ #include "main.h" @@ -439,57 +440,13 @@ unsigned int get_page_size(void) unsigned int get_possible_cpus(void) { - static unsigned int result; - char buf[128]; - long int n; - char *ptr; - int fd; - - if (result) - return result; - - fd = open("/sys/devices/system/cpu/possible", O_RDONLY); - if (fd < 0) { - p_err("can't open sysfs possible cpus"); - exit(-1); - } - - n = read(fd, buf, sizeof(buf)); - if (n < 2) { - p_err("can't read sysfs possible cpus"); - exit(-1); - } - close(fd); + int cpus = libbpf_num_possible_cpus(); - if (n == sizeof(buf)) { - p_err("read sysfs possible cpus overflow"); + if (cpus < 0) { + p_err("Can't get # of possible cpus: %s", strerror(-cpus)); exit(-1); } - - ptr = buf; - n = 0; - while (*ptr && *ptr != '\n') { - unsigned int a, b; - - if (sscanf(ptr, "%u-%u", &a, &b) == 2) { - n += b - a + 1; - - ptr = strchr(ptr, '-') + 1; - } else if (sscanf(ptr, "%u", &a) == 1) { - n++; - } else { - assert(0); - } - - while (isdigit(*ptr)) - ptr++; - if (*ptr == ',') - ptr++; - } - - result = n; - - return result; + return cpus; } static char * diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h new file mode 100644 index 000000000000..77f7c1638eb1 --- /dev/null +++ b/tools/include/uapi/asm-generic/socket.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_SOCKET_H +#define __ASM_GENERIC_SOCKET_H + +#include <linux/posix_types.h> +#include <asm/sockios.h> + +/* For setsockopt(2) */ +#define SOL_SOCKET 1 + +#define SO_DEBUG 1 +#define SO_REUSEADDR 2 +#define SO_TYPE 3 +#define SO_ERROR 4 +#define SO_DONTROUTE 5 +#define SO_BROADCAST 6 +#define SO_SNDBUF 7 +#define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 +#define SO_KEEPALIVE 9 +#define SO_OOBINLINE 10 +#define SO_NO_CHECK 11 +#define SO_PRIORITY 12 +#define SO_LINGER 13 +#define SO_BSDCOMPAT 14 +#define SO_REUSEPORT 15 +#ifndef SO_PASSCRED /* powerpc only differs in these */ +#define SO_PASSCRED 16 +#define SO_PEERCRED 17 +#define SO_RCVLOWAT 18 +#define SO_SNDLOWAT 19 +#define SO_RCVTIMEO_OLD 20 +#define SO_SNDTIMEO_OLD 21 +#endif + +/* Security levels - as per NRL IPv6 - don't actually do anything */ +#define SO_SECURITY_AUTHENTICATION 22 +#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 +#define SO_SECURITY_ENCRYPTION_NETWORK 24 + +#define SO_BINDTODEVICE 25 + +/* Socket filtering */ +#define SO_ATTACH_FILTER 26 +#define SO_DETACH_FILTER 27 +#define SO_GET_FILTER SO_ATTACH_FILTER + +#define SO_PEERNAME 28 + +#define SO_ACCEPTCONN 30 + +#define SO_PEERSEC 31 +#define SO_PASSSEC 34 + +#define SO_MARK 36 + +#define SO_PROTOCOL 38 +#define SO_DOMAIN 39 + +#define SO_RXQ_OVFL 40 + +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS +#define SO_PEEK_OFF 42 + +/* Instruct lower device to use last 4-bytes of skb data as FCS */ +#define SO_NOFCS 43 + +#define SO_LOCK_FILTER 44 + +#define SO_SELECT_ERR_QUEUE 45 + +#define SO_BUSY_POLL 46 + +#define SO_MAX_PACING_RATE 47 + +#define SO_BPF_EXTENSIONS 48 + +#define SO_INCOMING_CPU 49 + +#define SO_ATTACH_BPF 50 +#define SO_DETACH_BPF SO_DETACH_FILTER + +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + +#define SO_CNX_ADVICE 53 + +#define SCM_TIMESTAMPING_OPT_STATS 54 + +#define SO_MEMINFO 55 + +#define SO_INCOMING_NAPI_ID 56 + +#define SO_COOKIE 57 + +#define SCM_TIMESTAMPING_PKTINFO 58 + +#define SO_PEERGROUPS 59 + +#define SO_ZEROCOPY 60 + +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + +#define SO_BINDTOIFINDEX 62 + +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 + +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + +#define SO_DETACH_REUSEPORT_BPF 68 + +#if !defined(__KERNEL__) + +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +/* on 64-bit and x32, avoid the ?: operator */ +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + +#endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0e879721f75a..b077507efa3f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3085,6 +3085,10 @@ struct bpf_sock_tuple { }; }; +struct bpf_xdp_sock { + __u32 queue_id; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. @@ -3245,6 +3249,7 @@ struct bpf_sock_addr { __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. * Stored in network byte order. */ + __bpf_md_ptr(struct bpf_sock *, sk); }; /* User bpf_sock_ops struct to access socket values and specify request ops @@ -3296,6 +3301,7 @@ struct bpf_sock_ops { __u32 sk_txhash; __u64 bytes_received; __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); }; /* Definitions for bpf_sock_ops_cb_flags */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 0d4b4fe10a84..c7d7993c44bb 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -26,10 +26,11 @@ #include <memory.h> #include <unistd.h> #include <asm/unistd.h> +#include <errno.h> #include <linux/bpf.h> #include "bpf.h" #include "libbpf.h" -#include <errno.h> +#include "libbpf_internal.h" /* * When building perf, unistd.h is overridden. __NR_bpf is @@ -53,10 +54,6 @@ # endif #endif -#ifndef min -#define min(x, y) ((x) < (y) ? (x) : (y)) -#endif - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index 6978314ea7f6..8c67561c93b0 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -6,10 +6,7 @@ #include <linux/err.h> #include <linux/bpf.h> #include "libbpf.h" - -#ifndef min -#define min(x, y) ((x) < (y) ? (x) : (y)) -#endif +#include "libbpf_internal.h" struct bpf_prog_linfo { void *raw_linfo; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index b2478e98c367..467224feb43b 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -16,9 +16,6 @@ #include "libbpf_internal.h" #include "hashmap.h" -#define max(a, b) ((a) > (b) ? (a) : (b)) -#define min(a, b) ((a) < (b) ? (a) : (b)) - #define BTF_MAX_NR_TYPES 0x7fffffff #define BTF_MAX_STR_OFFSET 0x7fffffff diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index ba4ffa831aa4..88a52ae56fc6 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -17,6 +17,7 @@ extern "C" { #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" +#define MAPS_ELF_SEC ".maps" struct btf; struct btf_ext; diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 4b22db77e2cc..7065bb5b2752 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -18,9 +18,6 @@ #include "libbpf.h" #include "libbpf_internal.h" -#define min(x, y) ((x) < (y) ? (x) : (y)) -#define max(x, y) ((x) < (y) ? (y) : (x)) - static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index c8fbc050fd78..4259c9f0cfe7 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -207,7 +207,8 @@ static const char * const libbpf_type_to_btf_name[] = { struct bpf_map { int fd; char *name; - size_t offset; + int sec_idx; + size_t sec_offset; int map_ifindex; int inner_map_fd; struct bpf_map_def def; @@ -234,6 +235,7 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + size_t maps_cap; struct bpf_secdata sections; bool loaded; @@ -260,6 +262,7 @@ struct bpf_object { } *reloc; int nr_reloc; int maps_shndx; + int btf_maps_shndx; int text_shndx; int data_shndx; int rodata_shndx; @@ -512,6 +515,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.btf_maps_shndx = -1; obj->efile.data_shndx = -1; obj->efile.rodata_shndx = -1; obj->efile.bss_shndx = -1; @@ -646,7 +650,9 @@ static int compare_bpf_map(const void *_a, const void *_b) const struct bpf_map *a = _a; const struct bpf_map *b = _b; - return a->offset - b->offset; + if (a->sec_idx != b->sec_idx) + return a->sec_idx - b->sec_idx; + return a->sec_offset - b->sec_offset; } static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) @@ -763,24 +769,55 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, return -ENOENT; } -static bool bpf_object__has_maps(const struct bpf_object *obj) +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) { - return obj->efile.maps_shndx >= 0 || - obj->efile.data_shndx >= 0 || - obj->efile.rodata_shndx >= 0 || - obj->efile.bss_shndx >= 0; + struct bpf_map *new_maps; + size_t new_cap; + int i; + + if (obj->nr_maps < obj->maps_cap) + return &obj->maps[obj->nr_maps++]; + + new_cap = max(4ul, obj->maps_cap * 3 / 2); + new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps)); + if (!new_maps) { + pr_warning("alloc maps for object failed\n"); + return ERR_PTR(-ENOMEM); + } + + obj->maps_cap = new_cap; + obj->maps = new_maps; + + /* zero out new maps */ + memset(obj->maps + obj->nr_maps, 0, + (obj->maps_cap - obj->nr_maps) * sizeof(*obj->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 = obj->nr_maps; i < obj->maps_cap; i++) { + obj->maps[i].fd = -1; + obj->maps[i].inner_map_fd = -1; + } + + return &obj->maps[obj->nr_maps++]; } static int -bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, - enum libbpf_map_type type, Elf_Data *data, - void **data_buff) +bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, + int sec_idx, Elf_Data *data, void **data_buff) { - struct bpf_map_def *def = &map->def; char map_name[BPF_OBJ_NAME_LEN]; + struct bpf_map_def *def; + struct bpf_map *map; + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); map->libbpf_type = type; - map->offset = ~(typeof(map->offset))0; + map->sec_idx = sec_idx; + map->sec_offset = 0; snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, libbpf_type_to_btf_name[type]); map->name = strdup(map_name); @@ -788,7 +825,10 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, pr_warning("failed to alloc map name\n"); return -ENOMEM; } + pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; def->key_size = sizeof(int); def->value_size = data->d_size; @@ -808,29 +848,61 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, return 0; } -static int bpf_object__init_maps(struct bpf_object *obj, int flags) +static int bpf_object__init_global_data_maps(struct bpf_object *obj) +{ + int err; + + if (!obj->caps.global_data) + return 0; + /* + * Populate obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + obj->efile.data_shndx, + obj->efile.data, + &obj->sections.data); + if (err) + return err; + } + if (obj->efile.rodata_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + obj->efile.rodata_shndx, + obj->efile.rodata, + &obj->sections.rodata); + if (err) + return err; + } + if (obj->efile.bss_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + obj->efile.bss_shndx, + obj->efile.bss, NULL); + if (err) + return err; + } + return 0; +} + +static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { - int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0; - bool strict = !(flags & MAPS_RELAX_COMPAT); Elf_Data *symbols = obj->efile.symbols; + int i, map_def_sz = 0, nr_maps = 0, nr_syms; Elf_Data *data = NULL; - int ret = 0; + Elf_Scn *scn; + + if (obj->efile.maps_shndx < 0) + return 0; if (!symbols) return -EINVAL; - nr_syms = symbols->d_size / sizeof(GElf_Sym); - if (obj->efile.maps_shndx >= 0) { - Elf_Scn *scn = elf_getscn(obj->efile.elf, - obj->efile.maps_shndx); - - if (scn) - data = elf_getdata(scn, NULL); - if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); - return -EINVAL; - } + scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; } /* @@ -840,16 +912,8 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - if (obj->caps.global_data) { - if (obj->efile.data_shndx >= 0) - nr_maps_glob++; - if (obj->efile.rodata_shndx >= 0) - nr_maps_glob++; - if (obj->efile.bss_shndx >= 0) - nr_maps_glob++; - } - - for (i = 0; data && i < nr_syms; i++) { + nr_syms = symbols->d_size / sizeof(GElf_Sym); + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -858,79 +922,59 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) continue; nr_maps++; } - - if (!nr_maps && !nr_maps_glob) - return 0; - /* Assume equally sized map definitions */ - if (data) { - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); - - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; - } - } - - nr_maps += nr_maps_glob; - obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); - if (!obj->maps) { - pr_warning("alloc maps for object failed\n"); - return -ENOMEM; - } - obj->nr_maps = nr_maps; - - 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; + pr_debug("maps in %s: %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; } - /* - * Fill obj->maps using data in "maps" section. - */ - for (i = 0, map_idx = 0; data && i < nr_syms; i++) { + /* Fill obj->maps using data in "maps" section. */ + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; + struct bpf_map *map; if (!gelf_getsym(symbols, i, &sym)) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; - map_name = elf_strptr(obj->efile.elf, - obj->efile.strtabidx, + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); if (!map_name) { pr_warning("failed to get map #%d name sym string for obj %s\n", - map_idx, obj->path); + i, obj->path); return -LIBBPF_ERRNO__FORMAT; } - obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC; - obj->maps[map_idx].offset = sym.st_value; + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->sec_idx = sym.st_shndx; + map->sec_offset = sym.st_value; + pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", obj->path, map_name); return -EINVAL; } - obj->maps[map_idx].name = strdup(map_name); - if (!obj->maps[map_idx].name) { + map->name = strdup(map_name); + if (!map->name) { pr_warning("failed to alloc map name\n"); return -ENOMEM; } - pr_debug("map %d is \"%s\"\n", map_idx, - obj->maps[map_idx].name); + pr_debug("map %d is \"%s\"\n", i, map->name); def = (struct bpf_map_def *)(data->d_buf + sym.st_value); /* * If the definition of the map in the object file fits in @@ -939,7 +983,7 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) * calloc above. */ if (map_def_sz <= sizeof(struct bpf_map_def)) { - memcpy(&obj->maps[map_idx].def, def, map_def_sz); + memcpy(&map->def, def, map_def_sz); } else { /* * Here the map structure being read is bigger than what @@ -959,37 +1003,340 @@ static int bpf_object__init_maps(struct bpf_object *obj, int flags) return -EINVAL; } } - memcpy(&obj->maps[map_idx].def, def, - sizeof(struct bpf_map_def)); + memcpy(&map->def, def, sizeof(struct bpf_map_def)); } - map_idx++; } + return 0; +} - if (!obj->caps.global_data) - goto finalize; +static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, + __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); - /* - * Populate rest of obj->maps with libbpf internal maps. - */ - if (obj->efile.data_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_DATA, - obj->efile.data, - &obj->sections.data); - if (!ret && obj->efile.rodata_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_RODATA, - obj->efile.rodata, - &obj->sections.rodata); - if (!ret && obj->efile.bss_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_BSS, - obj->efile.bss, NULL); -finalize: - if (!ret) + while (true) { + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + t = btf__type_by_id(btf, t->type); + break; + default: + return t; + } + } +} + +static bool get_map_field_int(const char *map_name, + const struct btf *btf, + const struct btf_type *def, + const struct btf_member *m, + const void *data, __u32 *res) { + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type); + const char *name = btf__name_by_offset(btf, m->name_off); + __u32 int_info = *(const __u32 *)(const void *)(t + 1); + + if (BTF_INFO_KIND(t->info) != BTF_KIND_INT) { + pr_warning("map '%s': attr '%s': expected INT, got %u.\n", + map_name, name, BTF_INFO_KIND(t->info)); + return false; + } + if (t->size != 4 || BTF_INT_BITS(int_info) != 32 || + BTF_INT_OFFSET(int_info)) { + pr_warning("map '%s': attr '%s': expected 32-bit non-bitfield integer, " + "got %u-byte (%d-bit) one with bit offset %d.\n", + map_name, name, t->size, BTF_INT_BITS(int_info), + BTF_INT_OFFSET(int_info)); + return false; + } + if (BTF_INFO_KFLAG(def->info) && BTF_MEMBER_BITFIELD_SIZE(m->offset)) { + pr_warning("map '%s': attr '%s': bitfield is not supported.\n", + map_name, name); + return false; + } + if (m->offset % 32) { + pr_warning("map '%s': attr '%s': unaligned fields are not supported.\n", + map_name, name); + return false; + } + + *res = *(const __u32 *)(data + m->offset / 8); + return true; +} + +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict) +{ + const struct btf_type *var, *def, *t; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const struct btf_member *m; + const void *def_data; + const char *map_name; + struct bpf_map *map; + int vlen, i; + + vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = (const void *)(var + 1); + map_name = btf__name_by_offset(obj->btf, var->name_off); + vlen = BTF_INFO_VLEN(var->info); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warning("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warning("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) { + pr_warning("map '%s': unexpected var kind %u.\n", + map_name, BTF_INFO_KIND(var->info)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warning("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type); + if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) { + pr_warning("map '%s': unexpected def kind %u.\n", + map_name, BTF_INFO_KIND(var->info)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warning("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warning("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + def_data = data->d_buf + vi->offset; + vlen = BTF_INFO_VLEN(def->info); + m = (const void *)(def + 1); + for (i = 0; i < vlen; i++, m++) { + const char *name = btf__name_by_offset(obj->btf, m->name_off); + + if (!name) { + pr_warning("map '%s': invalid field #%d.\n", + map_name, i); + return -EINVAL; + } + if (strcmp(name, "type") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &map->def.type)) + return -EINVAL; + pr_debug("map '%s': found type = %u.\n", + map_name, map->def.type); + } else if (strcmp(name, "max_entries") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &map->def.max_entries)) + return -EINVAL; + pr_debug("map '%s': found max_entries = %u.\n", + map_name, map->def.max_entries); + } else if (strcmp(name, "map_flags") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &map->def.map_flags)) + return -EINVAL; + pr_debug("map '%s': found map_flags = %u.\n", + map_name, map->def.map_flags); + } else if (strcmp(name, "key_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &sz)) + return -EINVAL; + pr_debug("map '%s': found key_size = %u.\n", + map_name, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warning("map '%s': conflictling key size %u != %u.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + } else if (strcmp(name, "key") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warning("map '%s': key type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + pr_warning("map '%s': key spec is not PTR: %u.\n", + map_name, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found key [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warning("map '%s': conflictling key size %u != %lld.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + map->btf_key_type_id = t->type; + } else if (strcmp(name, "value_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + def_data, &sz)) + return -EINVAL; + pr_debug("map '%s': found value_size = %u.\n", + map_name, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warning("map '%s': conflictling value size %u != %u.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + } else if (strcmp(name, "value") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warning("map '%s': value type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + pr_warning("map '%s': value spec is not PTR: %u.\n", + map_name, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found value [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warning("map '%s': conflictling value size %u != %lld.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + map->btf_value_type_id = t->type; + } else { + if (strict) { + pr_warning("map '%s': unknown field '%s'.\n", + map_name, name); + return -ENOTSUP; + } + pr_debug("map '%s': ignoring unknown field '%s'.\n", + map_name, name); + } + } + + if (map->def.type == BPF_MAP_TYPE_UNSPEC) { + pr_warning("map '%s': map type isn't specified.\n", map_name); + return -EINVAL; + } + + return 0; +} + +static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) +{ + const struct btf_type *sec = NULL; + int nr_types, i, vlen, err; + const struct btf_type *t; + const char *name; + Elf_Data *data; + Elf_Scn *scn; + + if (obj->efile.btf_maps_shndx < 0) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d (%s)\n", + obj->efile.maps_shndx, MAPS_ELF_SEC); + return -EINVAL; + } + + nr_types = btf__get_nr_types(obj->btf); + for (i = 1; i <= nr_types; i++) { + t = btf__type_by_id(obj->btf, i); + if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) + continue; + name = btf__name_by_offset(obj->btf, t->name_off); + if (strcmp(name, MAPS_ELF_SEC) == 0) { + sec = t; + break; + } + } + + if (!sec) { + pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + return -ENOENT; + } + + vlen = BTF_INFO_VLEN(sec->info); + for (i = 0; i < vlen; i++) { + err = bpf_object__init_user_btf_map(obj, sec, i, + obj->efile.btf_maps_shndx, + data, strict); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_maps(struct bpf_object *obj, int flags) +{ + bool strict = !(flags & MAPS_RELAX_COMPAT); + int err; + + err = bpf_object__init_user_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_user_btf_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_global_data_maps(obj); + if (err) + return err; + + if (obj->nr_maps) { qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return ret; + } + return 0; } static bool section_have_execinstr(struct bpf_object *obj, int idx) @@ -1078,6 +1425,86 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) } } +static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) +{ + return obj->efile.btf_maps_shndx >= 0; +} + +static int bpf_object__init_btf(struct bpf_object *obj, + Elf_Data *btf_data, + Elf_Data *btf_ext_data) +{ + bool btf_required = bpf_object__is_btf_mandatory(obj); + int err = 0; + + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + err = btf__finalize_data(obj, obj->btf); + if (err) { + pr_warning("Error finalizing %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + } + if (btf_ext_data) { + if (!obj->btf) { + pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", + BTF_EXT_ELF_SEC, BTF_ELF_SEC); + goto out; + } + obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, + btf_ext_data->d_size); + 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; + goto out; + } + } +out: + if (err || IS_ERR(obj->btf)) { + if (btf_required) + err = err ? : PTR_ERR(obj->btf); + else + err = 0; + if (!IS_ERR_OR_NULL(obj->btf)) + btf__free(obj->btf); + obj->btf = NULL; + } + if (btf_required && !obj->btf) { + pr_warning("BTF is required, but is missing or corrupted.\n"); + return err == 0 ? -ENOENT : err; + } + return 0; +} + +static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) +{ + int err = 0; + + if (!obj->btf) + return 0; + + bpf_object__sanitize_btf(obj); + bpf_object__sanitize_btf_ext(obj); + + err = btf__load(obj->btf); + if (err) { + pr_warning("Error loading %s into kernel: %d.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + if (bpf_object__is_btf_mandatory(obj)) + return err; + } + return 0; +} + static int bpf_object__elf_collect(struct bpf_object *obj, int flags) { Elf *elf = obj->efile.elf; @@ -1102,24 +1529,21 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (gelf_getshdr(scn, &sh) != &sh) { pr_warning("failed to get section(%d) header from %s\n", idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); if (!name) { pr_warning("failed to get section(%d) name from %s\n", idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } data = elf_getdata(scn, 0); if (!data) { pr_warning("failed to get section(%d) data from %s(%s)\n", idx, name, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", idx, name, (unsigned long)data->d_size, @@ -1130,12 +1554,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) err = bpf_object__init_license(obj, data->d_buf, data->d_size); + if (err) + return err; } else if (strcmp(name, "version") == 0) { err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); + if (err) + return err; } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; + } else if (strcmp(name, MAPS_ELF_SEC) == 0) { + obj->efile.btf_maps_shndx = idx; } else if (strcmp(name, BTF_ELF_SEC) == 0) { btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { @@ -1144,11 +1574,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); - err = -LIBBPF_ERRNO__FORMAT; - } else { - obj->efile.symbols = data; - obj->efile.strtabidx = sh.sh_link; + return -LIBBPF_ERRNO__FORMAT; } + obj->efile.symbols = data; + obj->efile.strtabidx = sh.sh_link; } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { if (sh.sh_flags & SHF_EXECINSTR) { if (strcmp(name, ".text") == 0) @@ -1162,6 +1591,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("failed to alloc program %s (%s): %s", name, obj->path, cp); + return err; } } else if (strcmp(name, ".data") == 0) { obj->efile.data = data; @@ -1173,8 +1603,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { + int nr_reloc = obj->efile.nr_reloc; void *reloc = obj->efile.reloc; - int nr_reloc = obj->efile.nr_reloc + 1; int sec = sh.sh_info; /* points to other section */ /* Only do relo for section with exec instructions */ @@ -1184,79 +1614,37 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) continue; } - reloc = reallocarray(reloc, nr_reloc, + reloc = reallocarray(reloc, nr_reloc + 1, sizeof(*obj->efile.reloc)); if (!reloc) { pr_warning("realloc failed\n"); - err = -ENOMEM; - } else { - int n = nr_reloc - 1; + return -ENOMEM; + } - obj->efile.reloc = reloc; - obj->efile.nr_reloc = nr_reloc; + obj->efile.reloc = reloc; + obj->efile.nr_reloc++; - obj->efile.reloc[n].shdr = sh; - obj->efile.reloc[n].data = data; - } + obj->efile.reloc[nr_reloc].shdr = sh; + obj->efile.reloc[nr_reloc].data = data; } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } - if (err) - goto out; } if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { pr_warning("Corrupted ELF file: index of strtab invalid\n"); return -LIBBPF_ERRNO__FORMAT; } - if (btf_data) { - obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); - if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_ELF_SEC, PTR_ERR(obj->btf)); - obj->btf = NULL; - } else { - err = btf__finalize_data(obj, obj->btf); - if (!err) { - bpf_object__sanitize_btf(obj); - err = btf__load(obj->btf); - } - if (err) { - pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - err = 0; - } - } - } - if (btf_ext_data) { - if (!obj->btf) { - pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", - BTF_EXT_ELF_SEC, BTF_ELF_SEC); - } else { - obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size); - 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 { - bpf_object__sanitize_btf_ext(obj); - } - } - } - if (bpf_object__has_maps(obj)) { + err = bpf_object__init_btf(obj, btf_data, btf_ext_data); + if (!err) err = bpf_object__init_maps(obj, flags); - if (err) - goto out; - } - err = bpf_object__init_prog_names(obj); -out: + if (!err) + err = bpf_object__sanitize_and_load_btf(obj); + if (!err) + err = bpf_object__init_prog_names(obj); return err; } @@ -1275,7 +1663,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) } struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title) { struct bpf_program *pos; @@ -1297,7 +1686,8 @@ static bool bpf_object__shndx_is_data(const struct bpf_object *obj, static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, int shndx) { - return shndx == obj->efile.maps_shndx; + return shndx == obj->efile.maps_shndx || + shndx == obj->efile.btf_maps_shndx; } static bool bpf_object__relo_in_known_section(const struct bpf_object *obj, @@ -1341,14 +1731,14 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, prog->nr_reloc = nrels; for (i = 0; i < nrels; i++) { - GElf_Sym sym; - GElf_Rel rel; - unsigned int insn_idx; - unsigned int shdr_idx; struct bpf_insn *insns = prog->insns; enum libbpf_map_type type; + unsigned int insn_idx; + unsigned int shdr_idx; const char *name; size_t map_idx; + GElf_Sym sym; + GElf_Rel rel; if (!gelf_getrel(data, i, &rel)) { pr_warning("relocation: failed to get %d reloc\n", i); @@ -1416,9 +1806,13 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, if (maps[map_idx].libbpf_type != type) continue; if (type != LIBBPF_MAP_UNSPEC || - maps[map_idx].offset == sym.st_value) { - pr_debug("relocation: find map %zd (%s) for insn %u\n", - map_idx, maps[map_idx].name, insn_idx); + (maps[map_idx].sec_idx == sym.st_shndx && + maps[map_idx].sec_offset == sym.st_value)) { + pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n", + map_idx, maps[map_idx].name, + maps[map_idx].sec_idx, + maps[map_idx].sec_offset, + insn_idx); break; } } @@ -1438,14 +1832,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return 0; } -static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) { struct bpf_map_def *def = &map->def; __u32 key_type_id = 0, value_type_id = 0; int ret; + /* if it's BTF-defined map, we don't need to search for type IDs */ + if (map->sec_idx == obj->efile.btf_maps_shndx) + return 0; + if (!bpf_map__is_internal(map)) { - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, + ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, def->value_size, &key_type_id, &value_type_id); } else { @@ -1453,7 +1851,7 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) * LLVM annotates global data differently in BTF, that is, * only as '.data', '.bss' or '.rodata'. */ - ret = btf__find_by_name(btf, + ret = btf__find_by_name(obj->btf, libbpf_type_to_btf_name[map->libbpf_type]); } if (ret < 0) @@ -1740,25 +2138,26 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; create_attr.max_entries = def->max_entries; - create_attr.btf_fd = -1; + 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)) { + if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; } *pfd = bpf_create_map_xattr(&create_attr); - if (*pfd < 0 && create_attr.btf_fd >= 0) { + if (*pfd < 0 && (create_attr.btf_key_type_id || + create_attr.btf_value_type_id)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", map->name, cp, errno); - create_attr.btf_fd = -1; + create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; @@ -2049,7 +2448,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.license = license; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; - load_attr.prog_btf_fd = prog->btf_fd; + 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 = prog->func_info_cnt; @@ -2195,8 +2594,8 @@ out: return err; } -static bool bpf_program__is_function_storage(struct bpf_program *prog, - struct bpf_object *obj) +static bool bpf_program__is_function_storage(const struct bpf_program *prog, + const struct bpf_object *obj) { return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls; } @@ -2902,17 +3301,17 @@ bpf_object__next(struct bpf_object *prev) return next; } -const char *bpf_object__name(struct bpf_object *obj) +const char *bpf_object__name(const struct bpf_object *obj) { return obj ? obj->path : ERR_PTR(-EINVAL); } -unsigned int bpf_object__kversion(struct bpf_object *obj) +unsigned int bpf_object__kversion(const struct bpf_object *obj) { return obj ? obj->kern_version : 0; } -struct btf *bpf_object__btf(struct bpf_object *obj) +struct btf *bpf_object__btf(const struct bpf_object *obj) { return obj ? obj->btf : NULL; } @@ -2933,13 +3332,14 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, return 0; } -void *bpf_object__priv(struct bpf_object *obj) +void *bpf_object__priv(const struct bpf_object *obj) { return obj ? obj->priv : ERR_PTR(-EINVAL); } static struct bpf_program * -__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) +__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, + bool forward) { size_t nr_programs = obj->nr_programs; ssize_t idx; @@ -2964,7 +3364,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) } struct bpf_program * -bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) { struct bpf_program *prog = prev; @@ -2976,7 +3376,7 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) } struct bpf_program * -bpf_program__prev(struct bpf_program *next, struct bpf_object *obj) +bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) { struct bpf_program *prog = next; @@ -2998,7 +3398,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv, return 0; } -void *bpf_program__priv(struct bpf_program *prog) +void *bpf_program__priv(const struct bpf_program *prog) { return prog ? prog->priv : ERR_PTR(-EINVAL); } @@ -3008,7 +3408,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } -const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) +const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -3024,7 +3424,7 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) return title; } -int bpf_program__fd(struct bpf_program *prog) +int bpf_program__fd(const struct bpf_program *prog) { return bpf_program__nth_fd(prog, 0); } @@ -3057,7 +3457,7 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return 0; } -int bpf_program__nth_fd(struct bpf_program *prog, int n) +int bpf_program__nth_fd(const struct bpf_program *prog, int n) { int fd; @@ -3085,25 +3485,25 @@ void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) prog->type = type; } -static bool bpf_program__is_type(struct bpf_program *prog, +static bool bpf_program__is_type(const struct bpf_program *prog, enum bpf_prog_type type) { return prog ? (prog->type == type) : false; } -#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ -int bpf_program__set_##NAME(struct bpf_program *prog) \ -{ \ - if (!prog) \ - return -EINVAL; \ - bpf_program__set_type(prog, TYPE); \ - return 0; \ -} \ - \ -bool bpf_program__is_##NAME(struct bpf_program *prog) \ -{ \ - return bpf_program__is_type(prog, TYPE); \ -} \ +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(const struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); @@ -3302,17 +3702,17 @@ bpf_program__identify_section(struct bpf_program *prog, expected_attach_type); } -int bpf_map__fd(struct bpf_map *map) +int bpf_map__fd(const struct bpf_map *map) { return map ? map->fd : -EINVAL; } -const struct bpf_map_def *bpf_map__def(struct bpf_map *map) +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) { return map ? &map->def : ERR_PTR(-EINVAL); } -const char *bpf_map__name(struct bpf_map *map) +const char *bpf_map__name(const struct bpf_map *map) { return map ? map->name : NULL; } @@ -3343,17 +3743,17 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv, return 0; } -void *bpf_map__priv(struct bpf_map *map) +void *bpf_map__priv(const struct bpf_map *map) { return map ? map->priv : ERR_PTR(-EINVAL); } -bool bpf_map__is_offload_neutral(struct bpf_map *map) +bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } -bool bpf_map__is_internal(struct bpf_map *map) +bool bpf_map__is_internal(const struct bpf_map *map) { return map->libbpf_type != LIBBPF_MAP_UNSPEC; } @@ -3378,7 +3778,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) } static struct bpf_map * -__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) +__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) { ssize_t idx; struct bpf_map *s, *e; @@ -3402,7 +3802,7 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) } struct bpf_map * -bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) { if (prev == NULL) return obj->maps; @@ -3411,7 +3811,7 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) } struct bpf_map * -bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) +bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) { if (next == NULL) { if (!obj->nr_maps) @@ -3423,7 +3823,7 @@ bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) } struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) { struct bpf_map *pos; @@ -3435,7 +3835,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) } int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) { return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); } @@ -3443,13 +3843,7 @@ bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) { - int i; - - for (i = 0; i < obj->nr_maps; i++) { - if (obj->maps[i].offset == offset) - return &obj->maps[i]; - } - return ERR_PTR(-ENOENT); + return ERR_PTR(-ENOTSUP); } long libbpf_get_error(const void *ptr) @@ -3835,3 +4229,60 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) desc->array_offset, addr); } } + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + int len = 0, n = 0, il = 0, ir = 0; + unsigned int start = 0, end = 0; + static int cpus; + char buf[128]; + int error = 0; + int fd = -1; + + if (cpus > 0) + return cpus; + + fd = open(fcpu, O_RDONLY); + if (fd < 0) { + error = errno; + pr_warning("Failed to open file %s: %s\n", + fcpu, strerror(error)); + return -error; + } + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len <= 0) { + error = len ? errno : EINVAL; + pr_warning("Failed to read # of possible cpus from %s: %s\n", + fcpu, strerror(error)); + return -error; + } + if (len == sizeof(buf)) { + pr_warning("File %s size overflow\n", fcpu); + return -EOVERFLOW; + } + buf[len] = '\0'; + + for (ir = 0, cpus = 0; ir <= len; ir++) { + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + if (buf[ir] == ',' || buf[ir] == '\0') { + buf[ir] = '\0'; + n = sscanf(&buf[il], "%u-%u", &start, &end); + if (n <= 0) { + pr_warning("Failed to get # CPUs from %s\n", + &buf[il]); + return -EINVAL; + } else if (n == 1) { + end = start; + } + cpus += end - start + 1; + il = ir + 1; + } + } + if (cpus <= 0) { + pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu); + return -EINVAL; + } + return cpus; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 1af0d48178c8..d639f47e3110 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -98,15 +98,16 @@ struct bpf_object_load_attr { LIBBPF_API int bpf_object__load(struct bpf_object *obj); LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); LIBBPF_API int bpf_object__unload(struct bpf_object *obj); -LIBBPF_API const char *bpf_object__name(struct bpf_object *obj); -LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj); +LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); +LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); struct btf; -LIBBPF_API struct btf *bpf_object__btf(struct bpf_object *obj); +LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title); +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title); LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -118,7 +119,7 @@ LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); -LIBBPF_API void *bpf_object__priv(struct bpf_object *prog); +LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); LIBBPF_API int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, @@ -129,7 +130,7 @@ LIBBPF_API int libbpf_attach_type_by_name(const char *name, /* Accessors of bpf_program */ struct bpf_program; LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, - struct bpf_object *obj); + const struct bpf_object *obj); #define bpf_object__for_each_program(pos, obj) \ for ((pos) = bpf_program__next(NULL, (obj)); \ @@ -137,24 +138,23 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, (pos) = bpf_program__next((pos), (obj))) LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog, - struct bpf_object *obj); + const struct bpf_object *obj); -typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, - void *); +typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, bpf_program_clear_priv_t clear_priv); -LIBBPF_API void *bpf_program__priv(struct bpf_program *prog); +LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); -LIBBPF_API const char *bpf_program__title(struct bpf_program *prog, +LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_version); -LIBBPF_API int bpf_program__fd(struct bpf_program *prog); +LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, const char *path, int instance); @@ -227,7 +227,7 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, bpf_program_prep_t prep); -LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n); +LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); /* * Adjust type of BPF program. Default is kprobe. @@ -246,14 +246,14 @@ LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); -LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -275,10 +275,10 @@ struct bpf_map_def { */ struct bpf_map; LIBBPF_API struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); LIBBPF_API int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name); +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); /* * Get bpf_map through the offset of corresponding struct bpf_map_def @@ -288,7 +288,7 @@ LIBBPF_API struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); LIBBPF_API struct bpf_map * -bpf_map__next(struct bpf_map *map, struct bpf_object *obj); +bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); #define bpf_object__for_each_map(pos, obj) \ for ((pos) = bpf_map__next(NULL, (obj)); \ (pos) != NULL; \ @@ -296,22 +296,22 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); #define bpf_map__for_each bpf_object__for_each_map LIBBPF_API struct bpf_map * -bpf_map__prev(struct bpf_map *map, struct bpf_object *obj); +bpf_map__prev(const struct bpf_map *map, const 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); +LIBBPF_API int bpf_map__fd(const struct bpf_map *map); +LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); -LIBBPF_API void *bpf_map__priv(struct bpf_map *map); +LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); -LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); -LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map); +LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); +LIBBPF_API bool bpf_map__is_internal(const 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); @@ -454,6 +454,22 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); +/* + * A helper function to get the number of possible CPUs before looking up + * per-CPU maps. Negative errno is returned on failure. + * + * Example usage: + * + * int ncpus = libbpf_num_possible_cpus(); + * if (ncpus < 0) { + * // error handling + * } + * long values[ncpus]; + * bpf_map_lookup_elem(per_cpu_map_fd, key, values); + * + */ +LIBBPF_API int libbpf_num_possible_cpus(void); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 46dcda89df21..2c6d835620d2 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -172,4 +172,5 @@ LIBBPF_0.0.4 { btf_dump__new; btf__parse_elf; bpf_object__load_xattr; + libbpf_num_possible_cpus; } LIBBPF_0.0.3; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 61d90eb82ee6..2ac29bd36226 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -23,6 +23,13 @@ #define BTF_PARAM_ENC(name, type) (name), (type) #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) +#ifndef min +# define min(x, y) ((x) < (y) ? (x) : (y)) +#endif +#ifndef max +# define max(x, y) ((x) < (y) ? (y) : (x)) +#endif + extern void libbpf_print(enum libbpf_print_level level, const char *format, ...) __attribute__((format(printf, 2, 3))); diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 38667b62f1fe..7ef6293b4fd7 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -60,10 +60,8 @@ struct xsk_socket { struct xsk_umem *umem; struct xsk_socket_config config; int fd; - int xsks_map; int ifindex; int prog_fd; - int qidconf_map_fd; int xsks_map_fd; __u32 queue_id; char ifname[IFNAMSIZ]; @@ -265,15 +263,11 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) /* This is the C-program: * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) * { - * int *qidconf, index = ctx->rx_queue_index; + * int index = ctx->rx_queue_index; * * // A set entry here means that the correspnding queue_id * // has an active AF_XDP socket bound to it. - * qidconf = bpf_map_lookup_elem(&qidconf_map, &index); - * if (!qidconf) - * return XDP_ABORTED; - * - * if (*qidconf) + * if (bpf_map_lookup_elem(&xsks_map, &index)) * return bpf_redirect_map(&xsks_map, index, 0); * * return XDP_PASS; @@ -286,15 +280,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_1, -4), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), - BPF_LD_MAP_FD(BPF_REG_1, xsk->qidconf_map_fd), + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), - BPF_MOV32_IMM(BPF_REG_0, 0), - /* if r1 == 0 goto +8 */ - BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8), BPF_MOV32_IMM(BPF_REG_0, 2), - /* r1 = *(u32 *)(r1 + 0) */ - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0), /* if r1 == 0 goto +5 */ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5), /* r2 = *(u32 *)(r10 - 4) */ @@ -366,18 +355,11 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) if (max_queues < 0) return max_queues; - fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "qidconf_map", + fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", sizeof(int), sizeof(int), max_queues, 0); if (fd < 0) return fd; - xsk->qidconf_map_fd = fd; - fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", - sizeof(int), sizeof(int), max_queues, 0); - if (fd < 0) { - close(xsk->qidconf_map_fd); - return fd; - } xsk->xsks_map_fd = fd; return 0; @@ -385,10 +367,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) static void xsk_delete_bpf_maps(struct xsk_socket *xsk) { - close(xsk->qidconf_map_fd); + bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); close(xsk->xsks_map_fd); - xsk->qidconf_map_fd = -1; - xsk->xsks_map_fd = -1; } static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) @@ -417,10 +397,9 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) if (err) goto out_map_ids; - for (i = 0; i < prog_info.nr_map_ids; i++) { - if (xsk->qidconf_map_fd != -1 && xsk->xsks_map_fd != -1) - break; + xsk->xsks_map_fd = -1; + for (i = 0; i < prog_info.nr_map_ids; i++) { fd = bpf_map_get_fd_by_id(map_ids[i]); if (fd < 0) continue; @@ -431,11 +410,6 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) continue; } - if (!strcmp(map_info.name, "qidconf_map")) { - xsk->qidconf_map_fd = fd; - continue; - } - if (!strcmp(map_info.name, "xsks_map")) { xsk->xsks_map_fd = fd; continue; @@ -445,40 +419,18 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) } err = 0; - if (xsk->qidconf_map_fd < 0 || xsk->xsks_map_fd < 0) { + if (xsk->xsks_map_fd == -1) err = -ENOENT; - xsk_delete_bpf_maps(xsk); - } out_map_ids: free(map_ids); return err; } -static void xsk_clear_bpf_maps(struct xsk_socket *xsk) -{ - int qid = false; - - bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0); - bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); -} - static int xsk_set_bpf_maps(struct xsk_socket *xsk) { - int qid = true, fd = xsk->fd, err; - - err = bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0); - if (err) - goto out; - - err = bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, &fd, 0); - if (err) - goto out; - - return 0; -out: - xsk_clear_bpf_maps(xsk); - return err; + return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, + &xsk->fd, 0); } static int xsk_setup_xdp_prog(struct xsk_socket *xsk) @@ -497,26 +449,27 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) return err; err = xsk_load_xdp_prog(xsk); - if (err) - goto out_maps; + if (err) { + xsk_delete_bpf_maps(xsk); + return err; + } } else { xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id); err = xsk_lookup_bpf_maps(xsk); - if (err) - goto out_load; + if (err) { + close(xsk->prog_fd); + return err; + } } err = xsk_set_bpf_maps(xsk); - if (err) - goto out_load; + if (err) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + return err; + } return 0; - -out_load: - close(xsk->prog_fd); -out_maps: - xsk_delete_bpf_maps(xsk); - return err; } int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, @@ -643,9 +596,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, goto out_mmap_tx; } - xsk->qidconf_map_fd = -1; - xsk->xsks_map_fd = -1; - + xsk->prog_fd = -1; if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { err = xsk_setup_xdp_prog(xsk); if (err) @@ -708,8 +659,10 @@ void xsk_socket__delete(struct xsk_socket *xsk) if (!xsk) return; - xsk_clear_bpf_maps(xsk); - xsk_delete_bpf_maps(xsk); + if (xsk->prog_fd != -1) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + } optlen = sizeof(off); err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index d8df5c9b5b2f..fb5ce43e28b3 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -280,4 +280,5 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES) ) > $(VERIFIER_TESTS_H)) EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \ - $(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) + $(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) \ + feature diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h index b25595ea4a78..05f036df8a4c 100644 --- a/tools/testing/selftests/bpf/bpf_endian.h +++ b/tools/testing/selftests/bpf/bpf_endian.h @@ -2,6 +2,7 @@ #ifndef __BPF_ENDIAN__ #define __BPF_ENDIAN__ +#include <linux/stddef.h> #include <linux/swab.h> /* LLVM's BPF target selects the endianness of the CPU diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index e6d243b7cd74..1a5b1accf091 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -31,7 +31,7 @@ static int (*bpf_map_pop_elem)(void *map, void *value) = (void *) BPF_FUNC_map_pop_elem; static int (*bpf_map_peek_elem)(void *map, void *value) = (void *) BPF_FUNC_map_peek_elem; -static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) = +static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) = (void *) BPF_FUNC_probe_read; static unsigned long long (*bpf_ktime_get_ns)(void) = (void *) BPF_FUNC_ktime_get_ns; @@ -62,7 +62,7 @@ static int (*bpf_perf_event_output)(void *ctx, void *map, (void *) BPF_FUNC_perf_event_output; static int (*bpf_get_stackid)(void *ctx, void *map, int flags) = (void *) BPF_FUNC_get_stackid; -static int (*bpf_probe_write_user)(void *dst, void *src, int size) = +static int (*bpf_probe_write_user)(void *dst, const void *src, int size) = (void *) BPF_FUNC_probe_write_user; static int (*bpf_current_task_under_cgroup)(void *map, int index) = (void *) BPF_FUNC_current_task_under_cgroup; diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index a29206ebbd13..ec219f84e041 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -6,44 +6,17 @@ #include <stdlib.h> #include <string.h> #include <errno.h> +#include <libbpf.h> /* libbpf_num_possible_cpus */ static inline unsigned int bpf_num_possible_cpus(void) { - static const char *fcpu = "/sys/devices/system/cpu/possible"; - unsigned int start, end, possible_cpus = 0; - char buff[128]; - FILE *fp; - int len, n, i, j = 0; + int possible_cpus = libbpf_num_possible_cpus(); - fp = fopen(fcpu, "r"); - if (!fp) { - printf("Failed to open %s: '%s'!\n", fcpu, strerror(errno)); + if (possible_cpus < 0) { + printf("Failed to get # of possible cpus: '%s'!\n", + strerror(-possible_cpus)); exit(1); } - - if (!fgets(buff, sizeof(buff), fp)) { - printf("Failed to read %s!\n", fcpu); - exit(1); - } - - len = strlen(buff); - for (i = 0; i <= len; i++) { - if (buff[i] == ',' || buff[i] == '\0') { - buff[i] = '\0'; - n = sscanf(&buff[j], "%u-%u", &start, &end); - if (n <= 0) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } else if (n == 1) { - end = start; - } - possible_cpus += end - start + 1; - j = i + 1; - } - } - - fclose(fp); - return possible_cpus; } diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 0d89f0396be4..e95c33e333a4 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -47,7 +47,7 @@ int enable_all_controllers(char *cgroup_path) char buf[PATH_MAX]; char *c, *c2; int fd, cfd; - size_t len; + ssize_t len; snprintf(path, sizeof(path), "%s/cgroup.controllers", cgroup_path); fd = open(path, O_RDONLY); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index c0091137074b..e1b55261526f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -5,7 +5,7 @@ static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { if (level != LIBBPF_DEBUG) - return 0; + return vfprintf(stderr, format, args); if (!strstr(format, "verifier log")) return 0; @@ -32,24 +32,69 @@ static int check_load(const char *file, enum bpf_prog_type type) void test_bpf_verif_scale(void) { - const char *scale[] = { - "./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o" + const char *sched_cls[] = { + "./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o", }; - const char *pyperf[] = { - "./pyperf50.o", "./pyperf100.o", "./pyperf180.o" + const char *raw_tp[] = { + /* full unroll by llvm */ + "./pyperf50.o", "./pyperf100.o", "./pyperf180.o", + + /* partial unroll. llvm will unroll loop ~150 times. + * C loop count -> 600. + * Asm loop count -> 4. + * 16k insns in loop body. + * Total of 5 such loops. Total program size ~82k insns. + */ + "./pyperf600.o", + + /* no unroll at all. + * C loop count -> 600. + * ASM loop count -> 600. + * ~110 insns in loop body. + * Total of 5 such loops. Total program size ~1500 insns. + */ + "./pyperf600_nounroll.o", + + "./loop1.o", "./loop2.o", + + /* partial unroll. 19k insn in a loop. + * Total program size 20.8k insn. + * ~350k processed_insns + */ + "./strobemeta.o", + + /* no unroll, tiny loops */ + "./strobemeta_nounroll1.o", + "./strobemeta_nounroll2.o", + }; + const char *cg_sysctl[] = { + "./test_sysctl_loop1.o", "./test_sysctl_loop2.o", }; int err, i; if (verifier_stats) libbpf_set_print(libbpf_debug_print); - for (i = 0; i < ARRAY_SIZE(scale); i++) { - err = check_load(scale[i], BPF_PROG_TYPE_SCHED_CLS); - printf("test_scale:%s:%s\n", scale[i], err ? "FAIL" : "OK"); + err = check_load("./loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT); + printf("test_scale:loop3:%s\n", err ? (error_cnt--, "OK") : "FAIL"); + + for (i = 0; i < ARRAY_SIZE(sched_cls); i++) { + err = check_load(sched_cls[i], BPF_PROG_TYPE_SCHED_CLS); + printf("test_scale:%s:%s\n", sched_cls[i], err ? "FAIL" : "OK"); } - for (i = 0; i < ARRAY_SIZE(pyperf); i++) { - err = check_load(pyperf[i], BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:%s:%s\n", pyperf[i], err ? "FAIL" : "OK"); + for (i = 0; i < ARRAY_SIZE(raw_tp); i++) { + err = check_load(raw_tp[i], BPF_PROG_TYPE_RAW_TRACEPOINT); + printf("test_scale:%s:%s\n", raw_tp[i], err ? "FAIL" : "OK"); } + + for (i = 0; i < ARRAY_SIZE(cg_sysctl); i++) { + err = check_load(cg_sysctl[i], BPF_PROG_TYPE_CGROUP_SYSCTL); + printf("test_scale:%s:%s\n", cg_sysctl[i], err ? "FAIL" : "OK"); + } + err = check_load("./test_xdp_loop.o", BPF_PROG_TYPE_XDP); + printf("test_scale:test_xdp_loop:%s\n", err ? "FAIL" : "OK"); + + err = check_load("./test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL); + printf("test_scale:test_seg6_loop:%s\n", err ? "FAIL" : "OK"); } diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 81ad9a0b29d0..849f42e548b5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -57,17 +57,25 @@ struct frag_hdr { __be32 identification; }; -struct bpf_map_def SEC("maps") jmp_table = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} jmp_table SEC(".maps") = { .type = BPF_MAP_TYPE_PROG_ARRAY, + .max_entries = 8, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 8 }; -struct bpf_map_def SEC("maps") last_dissection = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_flow_keys *value; +} last_dissection SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_flow_keys), .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c new file mode 100644 index 000000000000..dea395af9ea9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/kfree_skb") +int nested_loops(volatile struct pt_regs* ctx) +{ + int i, j, sum = 0, m; + + for (j = 0; j < 300; j++) + for (i = 0; i < j; i++) { + if (j & 1) + m = ctx->rax; + else + m = j; + sum += i * m; + } + + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c new file mode 100644 index 000000000000..0637bd8e8bcf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(volatile struct pt_regs* ctx) +{ + int i = 0; + + while (true) { + if (ctx->rax & 1) + i += 3; + else + i += 7; + if (i > 40) + break; + } + + return i; +} diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c new file mode 100644 index 000000000000..30a0f6cba080 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(volatile struct pt_regs* ctx) +{ + __u64 i = 0, sum = 0; + do { + i++; + sum += ctx->rax; + } while (i < 0x100000000ULL); + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c index 9f741e69cebe..a25c82a5b7c8 100644 --- a/tools/testing/selftests/bpf/progs/netcnt_prog.c +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c @@ -10,24 +10,22 @@ #define REFRESH_TIME_NS 100000000 #define NS_PER_SEC 1000000000 -struct bpf_map_def SEC("maps") percpu_netcnt = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct percpu_net_cnt *value; +} percpu_netcnt SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct percpu_net_cnt), }; -BPF_ANNOTATE_KV_PAIR(percpu_netcnt, struct bpf_cgroup_storage_key, - struct percpu_net_cnt); - -struct bpf_map_def SEC("maps") netcnt = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct net_cnt *value; +} netcnt SEC(".maps") = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct net_cnt), }; -BPF_ANNOTATE_KV_PAIR(netcnt, struct bpf_cgroup_storage_key, - struct net_cnt); - SEC("cgroup/skb") int bpf_nextcnt(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 0cc5e4ee90bd..6b0781391be5 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -220,7 +220,11 @@ static inline __attribute__((__always_inline__)) int __on_event(struct pt_regs * int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym); if (symbol_counter == NULL) return 0; -#pragma unroll +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma clang loop unroll(full) +#endif /* Unwind python stack */ for (int i = 0; i < STACK_MAX_LEN; ++i) { if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) { diff --git a/tools/testing/selftests/bpf/progs/pyperf600.c b/tools/testing/selftests/bpf/progs/pyperf600.c new file mode 100644 index 000000000000..cb49b89e37cd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +/* clang will not unroll the loop 600 times. + * Instead it will unroll it to the amount it deemed + * appropriate, but the loop will still execute 600 times. + * Total program size is around 90k insns + */ +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c new file mode 100644 index 000000000000..6beff7502f4d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +#define NO_UNROLL +/* clang will not unroll at all. + * Total program size is around 2k insns + */ +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c index 9ff8ac4b0bf6..6aabb681fb9a 100644 --- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c @@ -7,25 +7,36 @@ #include "bpf_helpers.h" #include "bpf_endian.h" -struct bpf_map_def SEC("maps") socket_cookies = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u64), - .value_size = sizeof(__u32), - .max_entries = 1 << 8, +struct socket_cookie { + __u64 cookie_key; + __u32 cookie_value; +}; + +struct { + __u32 type; + __u32 map_flags; + int *key; + struct socket_cookie *value; +} socket_cookies SEC(".maps") = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .map_flags = BPF_F_NO_PREALLOC, }; SEC("cgroup/connect6") int set_cookie(struct bpf_sock_addr *ctx) { - __u32 cookie_value = 0xFF; - __u64 cookie_key; + struct socket_cookie *p; if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) return 1; - cookie_key = bpf_get_socket_cookie(ctx); - if (bpf_map_update_elem(&socket_cookies, &cookie_key, &cookie_value, 0)) - return 0; + p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!p) + return 1; + + p->cookie_value = 0xFF; + p->cookie_key = bpf_get_socket_cookie(ctx); return 1; } @@ -33,9 +44,8 @@ int set_cookie(struct bpf_sock_addr *ctx) SEC("sockops") int update_cookie(struct bpf_sock_ops *ctx) { - __u32 new_cookie_value; - __u32 *cookie_value; - __u64 cookie_key; + struct bpf_sock *sk; + struct socket_cookie *p; if (ctx->family != AF_INET6) return 1; @@ -43,14 +53,17 @@ int update_cookie(struct bpf_sock_ops *ctx) if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB) return 1; - cookie_key = bpf_get_socket_cookie(ctx); + if (!ctx->sk) + return 1; + + p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, 0); + if (!p) + return 1; - cookie_value = bpf_map_lookup_elem(&socket_cookies, &cookie_key); - if (!cookie_value) + if (p->cookie_key != bpf_get_socket_cookie(ctx)) return 1; - new_cookie_value = (ctx->local_port << 8) | *cookie_value; - bpf_map_update_elem(&socket_cookies, &cookie_key, &new_cookie_value, 0); + p->cookie_value = (ctx->local_port << 8) | p->cookie_value; return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index ed3e4a551c57..9390e0244259 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -1,6 +1,5 @@ #include <linux/bpf.h> #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c index 65fbfdb6cd3a..e80484d98a1a 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c @@ -1,6 +1,6 @@ #include <linux/bpf.h> + #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index bdc22be46f2e..d85c874ef25e 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -1,6 +1,5 @@ #include <linux/bpf.h> #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/strobemeta.c b/tools/testing/selftests/bpf/progs/strobemeta.c new file mode 100644 index 000000000000..d3df3d86f092 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 100 +#define STROBE_MAX_MAP_ENTRIES 20 +/* full unroll by llvm #undef NO_UNROLL */ +#include "strobemeta.h" + diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h new file mode 100644 index 000000000000..1ff73f60a3e4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -0,0 +1,528 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/ptrace.h> +#include <linux/sched.h> +#include <linux/types.h> +#include "bpf_helpers.h" + +typedef uint32_t pid_t; +struct task_struct {}; + +#define TASK_COMM_LEN 16 +#define PERF_MAX_STACK_DEPTH 127 + +#define STROBE_TYPE_INVALID 0 +#define STROBE_TYPE_INT 1 +#define STROBE_TYPE_STR 2 +#define STROBE_TYPE_MAP 3 + +#define STACK_TABLE_EPOCH_SHIFT 20 +#define STROBE_MAX_STR_LEN 1 +#define STROBE_MAX_CFGS 32 +#define STROBE_MAX_PAYLOAD \ + (STROBE_MAX_STRS * STROBE_MAX_STR_LEN + \ + STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) + +struct strobe_value_header { + /* + * meaning depends on type: + * 1. int: 0, if value not set, 1 otherwise + * 2. str: 1 always, whether value is set or not is determined by ptr + * 3. map: 1 always, pointer points to additional struct with number + * of entries (up to STROBE_MAX_MAP_ENTRIES) + */ + uint16_t len; + /* + * _reserved might be used for some future fields/flags, but we always + * want to keep strobe_value_header to be 8 bytes, so BPF can read 16 + * bytes in one go and get both header and value + */ + uint8_t _reserved[6]; +}; + +/* + * strobe_value_generic is used from BPF probe only, but needs to be a union + * of strobe_value_int/strobe_value_str/strobe_value_map + */ +struct strobe_value_generic { + struct strobe_value_header header; + union { + int64_t val; + void *ptr; + }; +}; + +struct strobe_value_int { + struct strobe_value_header header; + int64_t value; +}; + +struct strobe_value_str { + struct strobe_value_header header; + const char* value; +}; + +struct strobe_value_map { + struct strobe_value_header header; + const struct strobe_map_raw* value; +}; + +struct strobe_map_entry { + const char* key; + const char* val; +}; + +/* + * Map of C-string key/value pairs with fixed maximum capacity. Each map has + * corresponding int64 ID, which application can use (or ignore) in whatever + * way appropriate. Map is "write-only", there is no way to get data out of + * map. Map is intended to be used to provide metadata for profilers and is + * not to be used for internal in-app communication. All methods are + * thread-safe. + */ +struct strobe_map_raw { + /* + * general purpose unique ID that's up to application to decide + * whether and how to use; for request metadata use case id is unique + * request ID that's used to match metadata with stack traces on + * Strobelight backend side + */ + int64_t id; + /* number of used entries in map */ + int64_t cnt; + /* + * having volatile doesn't change anything on BPF side, but clang + * emits warnings for passing `volatile const char *` into + * bpf_probe_read_str that expects just `const char *` + */ + const char* tag; + /* + * key/value entries, each consisting of 2 pointers to key and value + * C strings + */ + struct strobe_map_entry entries[STROBE_MAX_MAP_ENTRIES]; +}; + +/* Following values define supported values of TLS mode */ +#define TLS_NOT_SET -1 +#define TLS_LOCAL_EXEC 0 +#define TLS_IMM_EXEC 1 +#define TLS_GENERAL_DYN 2 + +/* + * structure that universally represents TLS location (both for static + * executables and shared libraries) + */ +struct strobe_value_loc { + /* + * tls_mode defines what TLS mode was used for particular metavariable: + * - -1 (TLS_NOT_SET) - no metavariable; + * - 0 (TLS_LOCAL_EXEC) - Local Executable mode; + * - 1 (TLS_IMM_EXEC) - Immediate Executable mode; + * - 2 (TLS_GENERAL_DYN) - General Dynamic mode; + * Local Dynamic mode is not yet supported, because never seen in + * practice. Mode defines how offset field is interpreted. See + * calc_location() in below for details. + */ + int64_t tls_mode; + /* + * TLS_LOCAL_EXEC: offset from thread pointer (fs:0 for x86-64, + * tpidr_el0 for aarch64). + * TLS_IMM_EXEC: absolute address of GOT entry containing offset + * from thread pointer; + * TLS_GENERAL_DYN: absolute addres of double GOT entry + * containing tls_index_t struct; + */ + int64_t offset; +}; + +struct strobemeta_cfg { + int64_t req_meta_idx; + struct strobe_value_loc int_locs[STROBE_MAX_INTS]; + struct strobe_value_loc str_locs[STROBE_MAX_STRS]; + struct strobe_value_loc map_locs[STROBE_MAX_MAPS]; +}; + +struct strobe_map_descr { + uint64_t id; + int16_t tag_len; + /* + * cnt <0 - map value isn't set; + * 0 - map has id set, but no key/value entries + */ + int16_t cnt; + /* + * both key_lens[i] and val_lens[i] should be >0 for present key/value + * entry + */ + uint16_t key_lens[STROBE_MAX_MAP_ENTRIES]; + uint16_t val_lens[STROBE_MAX_MAP_ENTRIES]; +}; + +struct strobemeta_payload { + /* req_id has valid request ID, if req_meta_valid == 1 */ + int64_t req_id; + uint8_t req_meta_valid; + /* + * mask has Nth bit set to 1, if Nth metavar was present and + * successfully read + */ + uint64_t int_vals_set_mask; + int64_t int_vals[STROBE_MAX_INTS]; + /* len is >0 for present values */ + uint16_t str_lens[STROBE_MAX_STRS]; + /* if map_descrs[i].cnt == -1, metavar is not present/set */ + struct strobe_map_descr map_descrs[STROBE_MAX_MAPS]; + /* + * payload has compactly packed values of str and map variables in the + * form: strval1\0strval2\0map1key1\0map1val1\0map2key1\0map2val1\0 + * (and so on); str_lens[i], key_lens[i] and val_lens[i] determines + * value length + */ + char payload[STROBE_MAX_PAYLOAD]; +}; + +struct strobelight_bpf_sample { + uint64_t ktime; + char comm[TASK_COMM_LEN]; + pid_t pid; + int user_stack_id; + int kernel_stack_id; + int has_meta; + struct strobemeta_payload metadata; + /* + * makes it possible to pass (<real payload size> + 1) as data size to + * perf_submit() to avoid perf_submit's paranoia about passing zero as + * size, as it deduces that <real payload size> might be + * **theoretically** zero + */ + char dummy_safeguard; +}; + +struct bpf_map_def SEC("maps") samples = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 32, +}; + +struct bpf_map_def SEC("maps") stacks_0 = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(uint32_t), + .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH, + .max_entries = 16, +}; + +struct bpf_map_def SEC("maps") stacks_1 = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(uint32_t), + .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH, + .max_entries = 16, +}; + +struct bpf_map_def SEC("maps") sample_heap = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(uint32_t), + .value_size = sizeof(struct strobelight_bpf_sample), + .max_entries = 1, +}; + +struct bpf_map_def SEC("maps") strobemeta_cfgs = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(pid_t), + .value_size = sizeof(struct strobemeta_cfg), + .max_entries = STROBE_MAX_CFGS, +}; + +/* Type for the dtv. */ +/* https://github.com/lattera/glibc/blob/master/nptl/sysdeps/x86_64/tls.h#L34 */ +typedef union dtv { + size_t counter; + struct { + void* val; + bool is_static; + } pointer; +} dtv_t; + +/* Partial definition for tcbhead_t */ +/* https://github.com/bminor/glibc/blob/master/sysdeps/x86_64/nptl/tls.h#L42 */ +struct tcbhead { + void* tcb; + dtv_t* dtv; +}; + +/* + * TLS module/offset information for shared library case. + * For x86-64, this is mapped onto two entries in GOT. + * For aarch64, this is pointed to by second GOT entry. + */ +struct tls_index { + uint64_t module; + uint64_t offset; +}; + +static inline __attribute__((always_inline)) +void *calc_location(struct strobe_value_loc *loc, void *tls_base) +{ + /* + * tls_mode value is: + * - -1 (TLS_NOT_SET), if no metavar is present; + * - 0 (TLS_LOCAL_EXEC), if metavar uses Local Executable mode of TLS + * (offset from fs:0 for x86-64 or tpidr_el0 for aarch64); + * - 1 (TLS_IMM_EXEC), if metavar uses Immediate Executable mode of TLS; + * - 2 (TLS_GENERAL_DYN), if metavar uses General Dynamic mode of TLS; + * This schema allows to use something like: + * (tls_mode + 1) * (tls_base + offset) + * to get NULL for "no metavar" location, or correct pointer for local + * executable mode without doing extra ifs. + */ + if (loc->tls_mode <= TLS_LOCAL_EXEC) { + /* static executable is simple, we just have offset from + * tls_base */ + void *addr = tls_base + loc->offset; + /* multiply by (tls_mode + 1) to get NULL, if we have no + * metavar in this slot */ + return (void *)((loc->tls_mode + 1) * (int64_t)addr); + } + /* + * Other modes are more complicated, we need to jump through few hoops. + * + * For immediate executable mode (currently supported only for aarch64): + * - loc->offset is pointing to a GOT entry containing fixed offset + * relative to tls_base; + * + * For general dynamic mode: + * - loc->offset is pointing to a beginning of double GOT entries; + * - (for aarch64 only) second entry points to tls_index_t struct; + * - (for x86-64 only) two GOT entries are already tls_index_t; + * - tls_index_t->module is used to find start of TLS section in + * which variable resides; + * - tls_index_t->offset provides offset within that TLS section, + * pointing to value of variable. + */ + struct tls_index tls_index; + dtv_t *dtv; + void *tls_ptr; + + bpf_probe_read(&tls_index, sizeof(struct tls_index), + (void *)loc->offset); + /* valid module index is always positive */ + if (tls_index.module > 0) { + /* dtv = ((struct tcbhead *)tls_base)->dtv[tls_index.module] */ + bpf_probe_read(&dtv, sizeof(dtv), + &((struct tcbhead *)tls_base)->dtv); + dtv += tls_index.module; + } else { + dtv = NULL; + } + bpf_probe_read(&tls_ptr, sizeof(void *), dtv); + /* if pointer has (void *)-1 value, then TLS wasn't initialized yet */ + return tls_ptr && tls_ptr != (void *)-1 + ? tls_ptr + tls_index.offset + : NULL; +} + +static inline __attribute__((always_inline)) +void read_int_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data) +{ + void *location = calc_location(&cfg->int_locs[idx], tls_base); + if (!location) + return; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + data->int_vals[idx] = value->val; + if (value->header.len) + data->int_vals_set_mask |= (1 << idx); +} + +static inline __attribute__((always_inline)) +uint64_t read_str_var(struct strobemeta_cfg* cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, void *payload) +{ + void *location; + uint32_t len; + + data->str_lens[idx] = 0; + location = calc_location(&cfg->str_locs[idx], tls_base); + if (!location) + return 0; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, value->ptr); + /* + * if bpf_probe_read_str returns error (<0), due to casting to + * unsinged int, it will become big number, so next check is + * sufficient to check for errors AND prove to BPF verifier, that + * bpf_probe_read_str won't return anything bigger than + * STROBE_MAX_STR_LEN + */ + if (len > STROBE_MAX_STR_LEN) + return 0; + + data->str_lens[idx] = len; + return len; +} + +static inline __attribute__((always_inline)) +void *read_map_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload* data, void *payload) +{ + struct strobe_map_descr* descr = &data->map_descrs[idx]; + struct strobe_map_raw map; + void *location; + uint32_t len; + int i; + + descr->tag_len = 0; /* presume no tag is set */ + descr->cnt = -1; /* presume no value is set */ + + location = calc_location(&cfg->map_locs[idx], tls_base); + if (!location) + return payload; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + if (bpf_probe_read(&map, sizeof(struct strobe_map_raw), value->ptr)) + return payload; + + descr->id = map.id; + descr->cnt = map.cnt; + if (cfg->req_meta_idx == idx) { + data->req_id = map.id; + data->req_meta_valid = 1; + } + + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, map.tag); + if (len <= STROBE_MAX_STR_LEN) { + descr->tag_len = len; + payload += len; + } + +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_MAP_ENTRIES && i < map.cnt; ++i) { + descr->key_lens[i] = 0; + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, + map.entries[i].key); + if (len <= STROBE_MAX_STR_LEN) { + descr->key_lens[i] = len; + payload += len; + } + descr->val_lens[i] = 0; + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, + map.entries[i].val); + if (len <= STROBE_MAX_STR_LEN) { + descr->val_lens[i] = len; + payload += len; + } + } + + return payload; +} + +/* + * read_strobe_meta returns NULL, if no metadata was read; otherwise returns + * pointer to *right after* payload ends + */ +static inline __attribute__((always_inline)) +void *read_strobe_meta(struct task_struct* task, + struct strobemeta_payload* data) { + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobe_value_generic value = {0}; + struct strobemeta_cfg *cfg; + void *tls_base, *payload; + + cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid); + if (!cfg) + return NULL; + + data->int_vals_set_mask = 0; + data->req_meta_valid = 0; + payload = data->payload; + /* + * we don't have struct task_struct definition, it should be: + * tls_base = (void *)task->thread.fsbase; + */ + tls_base = (void *)task; + +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_INTS; ++i) { + read_int_var(cfg, i, tls_base, &value, data); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_STRS; ++i) { + payload += read_str_var(cfg, i, tls_base, &value, data, payload); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_MAPS; ++i) { + payload = read_map_var(cfg, i, tls_base, &value, data, payload); + } + /* + * return pointer right after end of payload, so it's possible to + * calculate exact amount of useful data that needs to be sent + */ + return payload; +} + +SEC("raw_tracepoint/kfree_skb") +int on_event(struct pt_regs *ctx) { + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobelight_bpf_sample* sample; + struct task_struct *task; + uint32_t zero = 0; + uint64_t ktime_ns; + void *sample_end; + + sample = bpf_map_lookup_elem(&sample_heap, &zero); + if (!sample) + return 0; /* this will never happen */ + + sample->pid = pid; + bpf_get_current_comm(&sample->comm, TASK_COMM_LEN); + ktime_ns = bpf_ktime_get_ns(); + sample->ktime = ktime_ns; + + task = (struct task_struct *)bpf_get_current_task(); + sample_end = read_strobe_meta(task, &sample->metadata); + sample->has_meta = sample_end != NULL; + sample_end = sample_end ? : &sample->metadata; + + if ((ktime_ns >> STACK_TABLE_EPOCH_SHIFT) & 1) { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_1, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_1, BPF_F_USER_STACK); + } else { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_0, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_0, BPF_F_USER_STACK); + } + + uint64_t sample_size = sample_end - (void *)sample; + /* should always be true */ + if (sample_size < sizeof(struct strobelight_bpf_sample)) + bpf_perf_event_output(ctx, &samples, 0, sample, 1 + sample_size); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c new file mode 100644 index 000000000000..f0a1669e11d6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 13 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c new file mode 100644 index 000000000000..4291a7d642e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 30 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c new file mode 100644 index 000000000000..28c16bb583b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +/* just to validate we can handle maps in multiple sections */ +struct bpf_map_def SEC("maps") btf_map_legacy = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(long long), + .max_entries = 4, +}; + +BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts); + +struct { + int *key; + struct ipv_counts *value; + unsigned int type; + unsigned int max_entries; +} btf_map SEC(".maps") = { + .type = BPF_MAP_TYPE_ARRAY, + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +__attribute__((noinline)) +static int test_long_fname_2(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + /* just verify we can reference both maps */ + counts = bpf_map_lookup_elem(&btf_map_legacy, &key); + if (!counts) + return 0; + + 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/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index f6d9f238e00a..aaa6ec250e15 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -15,17 +15,25 @@ struct stack_trace_t { struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; }; -struct bpf_map_def SEC("maps") perfmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} perfmap SEC(".maps") = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .max_entries = 2, .key_size = sizeof(int), .value_size = sizeof(__u32), - .max_entries = 2, }; -struct bpf_map_def SEC("maps") stackdata_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct stack_trace_t *value; +} stackdata_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct stack_trace_t), .max_entries = 1, }; @@ -47,10 +55,13 @@ struct bpf_map_def SEC("maps") stackdata_map = { * issue and avoid complicated C programming massaging. * This is an acceptable workaround since there is one entry here. */ -struct bpf_map_def SEC("maps") rawdata_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 (*value)[2 * MAX_STACK_RAWTP]; +} rawdata_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2, .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 5ab14e941980..866cc7ddbe43 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -7,17 +7,23 @@ #include "bpf_helpers.h" -struct bpf_map_def SEC("maps") result_number = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} result_number SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 11, }; -struct bpf_map_def SEC("maps") result_string = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + const char (*value)[32]; +} result_string SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = 32, .max_entries = 5, }; @@ -27,10 +33,13 @@ struct foo { __u64 c; }; -struct bpf_map_def SEC("maps") result_struct = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct foo *value; +} result_struct SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct foo), .max_entries = 5, }; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c index 1e10c9590991..848cbb90f581 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c @@ -169,38 +169,53 @@ struct eth_hdr { unsigned short eth_proto; }; -struct bpf_map_def SEC("maps") vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct vip_meta), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = CH_RINGS_SIZE, }; -struct bpf_map_def SEC("maps") reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = MAX_REALS, }; -struct bpf_map_def SEC("maps") stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct vip_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct vip_stats), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = CTL_MAP_SIZE, }; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c index ba44a14e6dc4..c63ecf3ca573 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c @@ -165,38 +165,53 @@ struct eth_hdr { unsigned short eth_proto; }; -struct bpf_map_def SEC("maps") vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct vip_meta), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = CH_RINGS_SIZE, }; -struct bpf_map_def SEC("maps") reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = MAX_REALS, }; -struct bpf_map_def SEC("maps") stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct vip_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct vip_stats), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = CTL_MAP_SIZE, }; diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c index af8cc68ed2f9..40d9c2853393 100644 --- a/tools/testing/selftests/bpf/progs/test_map_lock.c +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -11,29 +11,31 @@ struct hmap_elem { int var[VAR_NUM]; }; -struct bpf_map_def SEC("maps") hash_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct hmap_elem *value; +} hash_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(struct hmap_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(hash_map, int, struct hmap_elem); - struct array_elem { struct bpf_spin_lock lock; int var[VAR_NUM]; }; -struct bpf_map_def SEC("maps") array_map = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct array_elem *value; +} array_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct array_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(array_map, int, struct array_elem); - SEC("map_lock_demo") int bpf_map_lock_test(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c new file mode 100644 index 000000000000..463964d79f73 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -0,0 +1,261 @@ +#include <stddef.h> +#include <inttypes.h> +#include <errno.h> +#include <linux/seg6_local.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \ + 0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32)) +#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \ + 0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32)) +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +static __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +static __attribute__((always_inline)) +int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, + uint32_t old_pad, uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +static __attribute__((always_inline)) +int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t *tlv_off, uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + #pragma clang loop unroll(disable) + for (int i = 0; i < 100; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +static __attribute__((always_inline)) +int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("lwt_seg6local") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = htonll(lo); + addr.hi = htonll(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 5b54ec637ada..435a9527733e 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -21,38 +21,55 @@ int _version SEC("version") = 1; #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) #endif -struct bpf_map_def SEC("maps") outer_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} outer_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY_OF_MAPS, + .max_entries = 1, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 1, }; -struct bpf_map_def SEC("maps") result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = NR_RESULTS, }; -struct bpf_map_def SEC("maps") tmp_index_ovr_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + int *value; +} tmp_index_ovr_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(int), .max_entries = 1, }; -struct bpf_map_def SEC("maps") linum_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} linum_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") data_check_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct data_check *value; +} data_check_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct data_check), .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index 45a1a1a2c345..6ac68be5d68b 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -4,24 +4,26 @@ #include <linux/version.h> #include "bpf_helpers.h" -struct bpf_map_def SEC("maps") info_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} info_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(info_map, __u32, __u64); - -struct bpf_map_def SEC("maps") status_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} status_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(status_map, __u32, __u64); - SEC("send_signal_demo") int bpf_send_signal_test(void *ctx) { diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index 1c39e4ccb7f1..c3d383d650cb 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -27,31 +27,43 @@ enum bpf_linum_array_idx { __NR_BPF_LINUM_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") addr_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct sockaddr_in6 *value; +} addr_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct sockaddr_in6), .max_entries = __NR_BPF_ADDR_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") sock_result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_sock *value; +} sock_result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_sock), .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") tcp_sock_result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_tcp_sock *value; +} tcp_sock_result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_tcp_sock), .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") linum_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} linum_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = __NR_BPF_LINUM_ARRAY_IDX, }; @@ -60,26 +72,26 @@ struct bpf_spinlock_cnt { __u32 cnt; }; -struct bpf_map_def SEC("maps") sk_pkt_out_cnt = { +struct { + __u32 type; + __u32 map_flags; + int *key; + struct bpf_spinlock_cnt *value; +} sk_pkt_out_cnt SEC(".maps") = { .type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_spinlock_cnt), - .max_entries = 0, .map_flags = BPF_F_NO_PREALLOC, }; -BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt, int, struct bpf_spinlock_cnt); - -struct bpf_map_def SEC("maps") sk_pkt_out_cnt10 = { +struct { + __u32 type; + __u32 map_flags; + int *key; + struct bpf_spinlock_cnt *value; +} sk_pkt_out_cnt10 SEC(".maps") = { .type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_spinlock_cnt), - .max_entries = 0, .map_flags = BPF_F_NO_PREALLOC, }; -BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt10, int, struct bpf_spinlock_cnt); - static bool is_loopback6(__u32 *a6) { return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1); diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index 40f904312090..0a77ae36d981 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -10,30 +10,29 @@ struct hmap_elem { int test_padding; }; -struct bpf_map_def SEC("maps") hmap = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct hmap_elem *value; +} hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(struct hmap_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(hmap, int, struct hmap_elem); - - struct cls_elem { struct bpf_spin_lock lock; volatile int cnt; }; -struct bpf_map_def SEC("maps") cls_map = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct cls_elem *value; +} cls_map SEC(".maps") = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct cls_elem), }; -BPF_ANNOTATE_KV_PAIR(cls_map, struct bpf_cgroup_storage_key, - struct cls_elem); - struct bpf_vqueue { struct bpf_spin_lock lock; /* 4 byte hole */ @@ -42,14 +41,16 @@ struct bpf_vqueue { unsigned int rate; }; -struct bpf_map_def SEC("maps") vqueue = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct bpf_vqueue *value; +} vqueue SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_vqueue), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(vqueue, int, struct bpf_vqueue); #define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20) SEC("spin_lock_demo") diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index d86c281e957f..fcf2280bb60c 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -8,34 +8,50 @@ #define PERF_MAX_STACK_DEPTH 127 #endif -struct bpf_map_def SEC("maps") control_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} control_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") stackid_hmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} stackid_hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 16384, }; -struct bpf_map_def SEC("maps") stackmap = { +typedef struct bpf_stack_build_id stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __u32 type; + __u32 max_entries; + __u32 map_flags; + __u32 key_size; + __u32 value_size; +} stackmap SEC(".maps") = { .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_stack_build_id) - * PERF_MAX_STACK_DEPTH, .max_entries = 128, .map_flags = BPF_F_STACK_BUILD_ID, + .key_size = sizeof(__u32), + .value_size = sizeof(stack_trace_t), }; -struct bpf_map_def SEC("maps") stack_amap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + /* there seems to be a bug in kernel not handling typedef properly */ + struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH]; +} stack_amap SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_stack_build_id) - * PERF_MAX_STACK_DEPTH, .max_entries = 128, }; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index af111af7ca1a..7ad09adbf648 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -8,31 +8,47 @@ #define PERF_MAX_STACK_DEPTH 127 #endif -struct bpf_map_def SEC("maps") control_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} control_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") stackid_hmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} stackid_hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 16384, }; -struct bpf_map_def SEC("maps") stackmap = { +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} stackmap SEC(".maps") = { .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, .max_entries = 16384, + .key_size = sizeof(__u32), + .value_size = sizeof(stack_trace_t), }; -struct bpf_map_def SEC("maps") stack_amap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 (*value)[PERF_MAX_STACK_DEPTH]; +} stack_amap SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, .max_entries = 16384, }; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c new file mode 100644 index 000000000000..608a06871572 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include "bpf_helpers.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 28 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) +{ + volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string"; + unsigned char i; + char name[64]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c new file mode 100644 index 000000000000..cb201cbe11e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include "bpf_helpers.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 20 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx) +{ + volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop"; + unsigned char i; + char name[64]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index a295cad805d7..5cbbff416998 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -8,7 +8,6 @@ #include <linux/bpf.h> #include "bpf_helpers.h" -#include "bpf_util.h" /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */ #define MAX_ULONG_STR_LEN 0xF @@ -16,6 +15,10 @@ /* Max supported length of sysctl value string (pow2). */ #define MAX_VALUE_STR_LEN 0x40 +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) { char tcp_mem_name[] = "net/ipv4/tcp_mem"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c index bee3bbecc0c4..df98f7e32832 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c @@ -148,10 +148,13 @@ struct tcp_estats_basic_event { struct tcp_estats_conn_id conn_id; }; -struct bpf_map_def SEC("maps") ev_record_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcp_estats_basic_event *value; +} ev_record_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcp_estats_basic_event), .max_entries = 1024, }; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index c7c3240e0dd4..38e10c9fd996 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -14,17 +14,23 @@ #include "bpf_endian.h" #include "test_tcpbpf.h" -struct bpf_map_def SEC("maps") global_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcpbpf_globals *value; +} global_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcpbpf_globals), .max_entries = 4, }; -struct bpf_map_def SEC("maps") sockopt_results = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + int *value; +} sockopt_results SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(int), .max_entries = 2, }; diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index ec6db6e64c41..d073d37d4e27 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -14,18 +14,26 @@ #include "bpf_endian.h" #include "test_tcpnotify.h" -struct bpf_map_def SEC("maps") global_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcpnotify_globals *value; +} global_map SEC(".maps") = { .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 = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} perf_event_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .max_entries = 2, .key_size = sizeof(int), .value_size = sizeof(__u32), - .max_entries = 2, }; int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 5e7df8bb5b5d..ec3d2c1c8cf9 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -22,17 +22,23 @@ int _version SEC("version") = 1; -struct bpf_map_def SEC("maps") rxcnt = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} rxcnt SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 256, }; -struct bpf_map_def SEC("maps") vip2tnl = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct iptnl_info *value; +} vip2tnl SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct iptnl_info), .max_entries = MAX_IPTNL_ENTRIES, }; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c new file mode 100644 index 000000000000..7fa4677df22e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#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/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_iptunnel_common.h" + +int _version SEC("version") = 1; + +struct bpf_map_def SEC("maps") rxcnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 256, +}; + +struct bpf_map_def SEC("maps") vip2tnl = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct iptnl_info), + .max_entries = MAX_IPTNL_ENTRIES, +}; + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp_tx_iptunnel") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 4fe6aaad22a4..d2eddb5553d1 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -163,52 +163,66 @@ struct lb_stats { __u64 v1; }; -struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip_definition *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip_definition), - .value_size = sizeof(struct vip_meta), .max_entries = 512, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = { +struct { + __u32 type; + __u32 max_entries; + __u32 map_flags; + struct flow_key *key; + struct real_pos_lru *value; +} lru_cache SEC(".maps") = { .type = BPF_MAP_TYPE_LRU_HASH, - .key_size = sizeof(struct flow_key), - .value_size = sizeof(struct real_pos_lru), .max_entries = 300, .map_flags = 1U << 1, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 12 * 655, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = 40, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct lb_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct lb_stats), .max_entries = 515, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = 16, - .map_flags = 0, }; struct eth_hdr { diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 289daf54dec4..8351cb5f4a20 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -4016,13 +4016,9 @@ struct btf_file_test { }; static struct btf_file_test file_tests[] = { -{ - .file = "test_btf_haskv.o", -}, -{ - .file = "test_btf_nokv.o", - .btf_kv_notfound = true, -}, + { .file = "test_btf_haskv.o", }, + { .file = "test_btf_newkv.o", }, + { .file = "test_btf_nokv.o", .btf_kv_notfound = true, }, }; static int do_test_file(unsigned int test_num) diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/test_select_reuseport.c index 75646d9b34aa..7566c13eb51a 100644 --- a/tools/testing/selftests/bpf/test_select_reuseport.c +++ b/tools/testing/selftests/bpf/test_select_reuseport.c @@ -523,6 +523,58 @@ static void test_pass_on_err(int type, sa_family_t family) printf("OK\n"); } +static void test_detach_bpf(int type, sa_family_t family) +{ +#ifdef SO_DETACH_REUSEPORT_BPF + __u32 nr_run_before = 0, nr_run_after = 0, tmp, i; + struct epoll_event ev; + int cli_fd, err, nev; + struct cmd cmd = {}; + int optvalue = 0; + + printf("%s: ", __func__); + err = setsockopt(sk_fds[0], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, + &optvalue, sizeof(optvalue)); + CHECK(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); + + err = setsockopt(sk_fds[1], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, + &optvalue, sizeof(optvalue)); + CHECK(err == 0 || errno != ENOENT, "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_lookup_elem(result_map, &i, &tmp); + CHECK(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); + nr_run_before += tmp; + } + + cli_fd = send_data(type, family, &cmd, sizeof(cmd), PASS); + nev = epoll_wait(epfd, &ev, 1, 5); + CHECK(nev <= 0, "nev <= 0", + "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", + nev, type, family); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_lookup_elem(result_map, &i, &tmp); + CHECK(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); + nr_run_after += tmp; + } + + CHECK(nr_run_before != nr_run_after, + "nr_run_before != nr_run_after", + "nr_run_before:%u nr_run_after:%u\n", + nr_run_before, nr_run_after); + + printf("OK\n"); + close(cli_fd); +#else + printf("%s: SKIP\n", __func__); +#endif +} + static void prepare_sk_fds(int type, sa_family_t family, bool inany) { const int first = REUSEPORT_ARRAY_SIZE - 1; @@ -664,6 +716,8 @@ static void test_all(void) test_pass(type, family); test_syncookie(type, family); test_pass_on_err(type, family); + /* Must be the last test */ + test_detach_bpf(type, family); cleanup_per_test(); printf("\n"); diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c index cac8ee57a013..15653b0e26eb 100644 --- a/tools/testing/selftests/bpf/test_socket_cookie.c +++ b/tools/testing/selftests/bpf/test_socket_cookie.c @@ -18,6 +18,11 @@ #define CG_PATH "/foo" #define SOCKET_COOKIE_PROG "./socket_cookie_prog.o" +struct socket_cookie { + __u64 cookie_key; + __u32 cookie_value; +}; + static int start_server(void) { struct sockaddr_in6 addr; @@ -89,8 +94,7 @@ static int validate_map(struct bpf_map *map, int client_fd) __u32 cookie_expected_value; struct sockaddr_in6 addr; socklen_t len = sizeof(addr); - __u32 cookie_value; - __u64 cookie_key; + struct socket_cookie val; int err = 0; int map_fd; @@ -101,17 +105,7 @@ static int validate_map(struct bpf_map *map, int client_fd) map_fd = bpf_map__fd(map); - err = bpf_map_get_next_key(map_fd, NULL, &cookie_key); - if (err) { - log_err("Can't get cookie key from map"); - goto out; - } - - err = bpf_map_lookup_elem(map_fd, &cookie_key, &cookie_value); - if (err) { - log_err("Can't get cookie value from map"); - goto out; - } + err = bpf_map_lookup_elem(map_fd, &client_fd, &val); err = getsockname(client_fd, (struct sockaddr *)&addr, &len); if (err) { @@ -120,8 +114,8 @@ static int validate_map(struct bpf_map *map, int client_fd) } cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF; - if (cookie_value != cookie_expected_value) { - log_err("Unexpected value in map: %x != %x", cookie_value, + if (val.cookie_value != cookie_expected_value) { + log_err("Unexpected value in map: %x != %x", val.cookie_value, cookie_expected_value); goto err; } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 6cb307201958..c5514daf8865 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -234,10 +234,10 @@ static void bpf_fill_scale1(struct bpf_test *self) insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, -8 * (k % 64 + 1)); } - /* every jump adds 1 step to insn_processed, so to stay exactly - * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT + /* is_state_visited() doesn't allocate state for pruning for every jump. + * Hence multiply jmps by 4 to accommodate that heuristic */ - while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1) + while (i < MAX_TEST_INSNS - MAX_JMP_SEQ * 4) insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42); insn[i] = BPF_EXIT_INSN(); self->prog_len = i + 1; @@ -266,10 +266,7 @@ static void bpf_fill_scale2(struct bpf_test *self) insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, -8 * (k % (64 - 4 * FUNC_NEST) + 1)); } - /* every jump adds 1 step to insn_processed, so to stay exactly - * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT - */ - while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1) + while (i < MAX_TEST_INSNS - MAX_JMP_SEQ * 4) insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42); insn[i] = BPF_EXIT_INSN(); self->prog_len = i + 1; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 9093a8f64dc6..2d752c4f8d9d 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -215,9 +215,11 @@ BPF_MOV64_IMM(BPF_REG_0, 3), BPF_JMP_IMM(BPF_JA, 0, 0, -6), }, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn", - .result = REJECT, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .errstr_unpriv = "back-edge from insn", + .result_unpriv = REJECT, + .result = ACCEPT, + .retval = 1, }, { "calls: conditional call 4", @@ -250,22 +252,24 @@ BPF_MOV64_IMM(BPF_REG_0, 3), BPF_EXIT_INSN(), }, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn", - .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 1, }, { "calls: conditional call 6", .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -3), BPF_EXIT_INSN(), BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, mark)), BPF_EXIT_INSN(), }, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "infinite loop detected", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/cfg.c b/tools/testing/selftests/bpf/verifier/cfg.c index 349c0862fb4c..4eb76ed739ce 100644 --- a/tools/testing/selftests/bpf/verifier/cfg.c +++ b/tools/testing/selftests/bpf/verifier/cfg.c @@ -41,7 +41,8 @@ BPF_JMP_IMM(BPF_JA, 0, 0, -1), BPF_EXIT_INSN(), }, - .errstr = "back-edge", + .errstr = "unreachable insn 1", + .errstr_unpriv = "back-edge", .result = REJECT, }, { @@ -53,18 +54,20 @@ BPF_JMP_IMM(BPF_JA, 0, 0, -4), BPF_EXIT_INSN(), }, - .errstr = "back-edge", + .errstr = "unreachable insn 4", + .errstr_unpriv = "back-edge", .result = REJECT, }, { "conditional loop", .insns = { - BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3), BPF_EXIT_INSN(), }, - .errstr = "back-edge", + .errstr = "infinite loop detected", + .errstr_unpriv = "back-edge", .result = REJECT, }, diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c index d5c596fdc4b9..2c5fbe7bcd27 100644 --- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c @@ -511,7 +511,8 @@ offsetof(struct __sk_buff, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct __sk_buff, data_end)), - BPF_MOV64_IMM(BPF_REG_0, 0xffffffff), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff), diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c index 1f39d845c64f..67ab12410050 100644 --- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c +++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c @@ -29,9 +29,9 @@ { "helper access to variable memory: stack, bitwise AND, zero included", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), @@ -46,9 +46,9 @@ { "helper access to variable memory: stack, bitwise AND + JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 65), @@ -122,9 +122,9 @@ { "helper access to variable memory: stack, JMP, bounds + offset", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 5), @@ -143,9 +143,9 @@ { "helper access to variable memory: stack, JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 65, 4), @@ -163,9 +163,9 @@ { "helper access to variable memory: stack, JMP, no max check", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_MOV64_IMM(BPF_REG_4, 0), @@ -183,9 +183,9 @@ { "helper access to variable memory: stack, JMP, no min check", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3), @@ -201,9 +201,9 @@ { "helper access to variable memory: stack, JMP (signed), no min check", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_MOV64_IMM(BPF_REG_2, 16), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3), @@ -244,6 +244,7 @@ { "helper access to variable memory: map, JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), @@ -251,7 +252,7 @@ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), - BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) + 1, 4), @@ -262,7 +263,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_48b = { 3 }, + .fixup_map_hash_48b = { 4 }, .errstr = "invalid access to map value, value_size=48 off=0 size=49", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, @@ -296,6 +297,7 @@ { "helper access to variable memory: map adjusted, JMP, wrong max", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), @@ -304,7 +306,7 @@ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20), - BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 19, 4), @@ -315,7 +317,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_48b = { 3 }, + .fixup_map_hash_48b = { 4 }, .errstr = "R1 min value is outside of the array range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, @@ -337,8 +339,8 @@ { "helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)", .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), BPF_MOV64_IMM(BPF_REG_1, 0), - BPF_MOV64_IMM(BPF_REG_2, 1), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), @@ -562,6 +564,7 @@ { "helper access to variable memory: 8 bytes leak", .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -572,7 +575,6 @@ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), - BPF_MOV64_IMM(BPF_REG_2, 1), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63), diff --git a/tools/testing/selftests/bpf/verifier/loops1.c b/tools/testing/selftests/bpf/verifier/loops1.c new file mode 100644 index 000000000000..5e980a5ab69d --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/loops1.c @@ -0,0 +1,161 @@ +{ + "bounded loop, count to 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop, count to 20", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 20, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded loop, count from positive unknown to 4", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop, count from totally unknown to 4", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded loop, count to 4 with equality", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded loop, start in the middle", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "back-edge", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop containing a forward jump", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -3), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .retval = 4, +}, +{ + "bounded loop that jumps out rather than in", + .insns = { + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_6, 10000, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_JMP_A(-4), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "infinite loop after a conditional jump", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 5), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_JMP_A(-2), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "program is too large", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bounded recursion", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 4, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "back-edge", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "infinite loop in two jumps", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "loop detected", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "infinite loop: three-jump trick", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, -11), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "loop detected", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, diff --git a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c index bbdba990fefb..da7a4b37cb98 100644 --- a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c +++ b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c @@ -29,21 +29,6 @@ .prog_type = BPF_PROG_TYPE_SOCK_OPS, }, { - "prevent map lookup in xskmap", - .insns = { - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - }, - .fixup_map_xskmap = { 3 }, - .result = REJECT, - .errstr = "cannot pass map_type 17 into func bpf_map_lookup_elem", - .prog_type = BPF_PROG_TYPE_XDP, -}, -{ "prevent map lookup in stack trace", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index b31cd2cf50d0..9ed192e14f5f 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -498,3 +498,21 @@ .result = REJECT, .errstr = "cannot pass map_type 24 into func bpf_map_lookup_elem", }, +{ + "bpf_map_lookup_elem(xskmap, &key); xs->queue_id", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_xdp_sock, queue_id)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_xskmap = { 3 }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = ACCEPT, +}, |