diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst index 1af51143ff9f..3704836fe6df 100644 --- a/Documentation/bpf/instruction-set.rst +++ b/Documentation/bpf/instruction-set.rst @@ -19,23 +19,37 @@ The eBPF calling convention is defined as: R0 - R5 are scratch registers and eBPF programs needs to spill/fill them if necessary across calls. +Instruction encoding +==================== + +eBPF uses 64-bit instructions with the following encoding: + + ============= ======= =============== ==================== ============ + 32 bits (MSB) 16 bits 4 bits 4 bits 8 bits (LSB) + ============= ======= =============== ==================== ============ + immediate offset source register destination register opcode + ============= ======= =============== ==================== ============ + +Note that most instructions do not use all of the fields. +Unused fields shall be cleared to zero. + Instruction classes -=================== +------------------- The three LSB bits of the 'opcode' field store the instruction class: - ========= ===== - class value - ========= ===== - BPF_LD 0x00 - BPF_LDX 0x01 - BPF_ST 0x02 - BPF_STX 0x03 - BPF_ALU 0x04 - BPF_JMP 0x05 - BPF_JMP32 0x06 - BPF_ALU64 0x07 - ========= ===== + ========= ===== =============================== + class value description + ========= ===== =============================== + BPF_LD 0x00 non-standard load operations + BPF_LDX 0x01 load into register operations + BPF_ST 0x02 store from immediate operations + BPF_STX 0x03 store from register operations + BPF_ALU 0x04 32-bit arithmetic operations + BPF_JMP 0x05 64-bit jump operations + BPF_JMP32 0x06 32-bit jump operations + BPF_ALU64 0x07 64-bit arithmetic operations + ========= ===== =============================== Arithmetic and jump instructions ================================ @@ -60,66 +74,78 @@ The 4th bit encodes the source operand: The four MSB bits store the operation code. -For class BPF_ALU or BPF_ALU64: - ======== ===== ========================= +Arithmetic instructions +----------------------- + +BPF_ALU uses 32-bit wide operands while BPF_ALU64 uses 64-bit wide operands for +otherwise identical operations. +The code field encodes the operation as below: + + ======== ===== ========================== code value description - ======== ===== ========================= - BPF_ADD 0x00 - BPF_SUB 0x10 - BPF_MUL 0x20 - BPF_DIV 0x30 - BPF_OR 0x40 - BPF_AND 0x50 - BPF_LSH 0x60 - BPF_RSH 0x70 - BPF_NEG 0x80 - BPF_MOD 0x90 - BPF_XOR 0xa0 - BPF_MOV 0xb0 mov reg to reg + ======== ===== ========================== + BPF_ADD 0x00 dst += src + BPF_SUB 0x10 dst -= src + BPF_MUL 0x20 dst \*= src + BPF_DIV 0x30 dst /= src + BPF_OR 0x40 dst \|= src + BPF_AND 0x50 dst &= src + BPF_LSH 0x60 dst <<= src + BPF_RSH 0x70 dst >>= src + BPF_NEG 0x80 dst = ~src + BPF_MOD 0x90 dst %= src + BPF_XOR 0xa0 dst ^= src + BPF_MOV 0xb0 dst = src BPF_ARSH 0xc0 sign extending shift right BPF_END 0xd0 endianness conversion - ======== ===== ========================= + ======== ===== ========================== -For class BPF_JMP or BPF_JMP32: - - ======== ===== ========================= - code value description - ======== ===== ========================= - BPF_JA 0x00 BPF_JMP only - BPF_JEQ 0x10 - BPF_JGT 0x20 - BPF_JGE 0x30 - BPF_JSET 0x40 - BPF_JNE 0x50 jump '!=' - BPF_JSGT 0x60 signed '>' - BPF_JSGE 0x70 signed '>=' - BPF_CALL 0x80 function call - BPF_EXIT 0x90 function return - BPF_JLT 0xa0 unsigned '<' - BPF_JLE 0xb0 unsigned '<=' - BPF_JSLT 0xc0 signed '<' - BPF_JSLE 0xd0 signed '<=' - ======== ===== ========================= - -So BPF_ADD | BPF_X | BPF_ALU means:: +BPF_ADD | BPF_X | BPF_ALU means:: dst_reg = (u32) dst_reg + (u32) src_reg; -Similarly, BPF_XOR | BPF_K | BPF_ALU means:: - - src_reg = (u32) src_reg ^ (u32) imm32 - -eBPF is using BPF_MOV | BPF_X | BPF_ALU to represent A = B moves. BPF_ALU64 -is used to mean exactly the same operations as BPF_ALU, but with 64-bit wide -operands instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.:: +BPF_ADD | BPF_X | BPF_ALU64 means:: dst_reg = dst_reg + src_reg -BPF_JMP | BPF_EXIT means function exit only. The eBPF program needs to store -the return value into register R0 before doing a BPF_EXIT. Class 6 is used as -BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide -operands for the comparisons instead. +BPF_XOR | BPF_K | BPF_ALU means:: + + src_reg = (u32) src_reg ^ (u32) imm32 + +BPF_XOR | BPF_K | BPF_ALU64 means:: + + src_reg = src_reg ^ imm32 + + +Jump instructions +----------------- + +BPF_JMP32 uses 32-bit wide operands while BPF_JMP uses 64-bit wide operands for +otherwise identical operations. +The code field encodes the operation as below: + + ======== ===== ========================= ============ + code value description notes + ======== ===== ========================= ============ + BPF_JA 0x00 PC += off BPF_JMP only + BPF_JEQ 0x10 PC += off if dst == src + BPF_JGT 0x20 PC += off if dst > src unsigned + BPF_JGE 0x30 PC += off if dst >= src unsigned + BPF_JSET 0x40 PC += off if dst & src + BPF_JNE 0x50 PC += off if dst != src + BPF_JSGT 0x60 PC += off if dst > src signed + BPF_JSGE 0x70 PC += off if dst >= src signed + BPF_CALL 0x80 function call + BPF_EXIT 0x90 function / program return BPF_JMP only + BPF_JLT 0xa0 PC += off if dst < src unsigned + BPF_JLE 0xb0 PC += off if dst <= src unsigned + BPF_JSLT 0xc0 PC += off if dst < src signed + BPF_JSLE 0xd0 PC += off if dst <= src signed + ======== ===== ========================= ============ + +The eBPF program needs to store the return value into register R0 before doing a +BPF_EXIT. Load and store instructions @@ -147,15 +173,15 @@ The size modifier is one of: The mode modifier is one of: - ============= ===== ===================== + ============= ===== ==================================== mode modifier value description - ============= ===== ===================== + ============= ===== ==================================== BPF_IMM 0x00 used for 64-bit mov - BPF_ABS 0x20 - BPF_IND 0x40 - BPF_MEM 0x60 + BPF_ABS 0x20 legacy BPF packet access + BPF_IND 0x40 legacy BPF packet access + BPF_MEM 0x60 all normal load and store operations BPF_ATOMIC 0xc0 atomic operations - ============= ===== ===================== + ============= ===== ==================================== BPF_MEM | | BPF_STX means:: diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 07aad85848fa..e96d4d87291f 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -792,7 +792,10 @@ emit_cond_jmp: u64 imm64; imm64 = (u64)insn1.imm << 32 | (u32)imm; - emit_a64_mov_i64(dst, imm64, ctx); + if (bpf_pseudo_func(insn)) + emit_addr_mov_i64(dst, imm64, ctx); + else + emit_a64_mov_i64(dst, imm64, ctx); return 1; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 26753139d5b4..6e947cd91152 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1669,17 +1669,17 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ -struct xdp_buff; +struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(void); -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); @@ -1688,7 +1688,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, bool exclude_ingress); void __cpu_map_flush(void); -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); @@ -1866,26 +1866,26 @@ static inline void __dev_flush(void) { } -struct xdp_buff; +struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; @@ -1913,7 +1913,7 @@ static inline void __cpu_map_flush(void) } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, - struct xdp_buff *xdp, + struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; diff --git a/include/linux/filter.h b/include/linux/filter.h index 60eec80fa1d4..71fa57b88bfc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1019,6 +1019,10 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); +int xdp_do_redirect_frame(struct net_device *dev, + struct xdp_buff *xdp, + struct xdp_frame *xdpf, + struct bpf_prog *prog); void xdp_do_flush(void); /* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as diff --git a/include/net/page_pool.h b/include/net/page_pool.h index a4082406a003..79a805542d0f 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -80,6 +80,8 @@ struct page_pool_params { enum dma_data_direction dma_dir; /* DMA mapping direction */ unsigned int max_len; /* max DMA sync memory size */ unsigned int offset; /* DMA addr offset */ + void (*init_callback)(struct page *page, void *arg); + void *init_arg; }; struct page_pool { @@ -94,6 +96,7 @@ struct page_pool { unsigned int frag_offset; struct page *frag_page; long frag_users; + u32 xdp_mem_id; /* * Data structure for allocation side @@ -168,9 +171,12 @@ bool page_pool_return_skb_page(struct page *page); struct page_pool *page_pool_create(const struct page_pool_params *params); +struct xdp_mem_info; + #ifdef CONFIG_PAGE_POOL void page_pool_destroy(struct page_pool *pool); -void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)); +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), + struct xdp_mem_info *mem); void page_pool_release_page(struct page_pool *pool, struct page *page); void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count); @@ -180,7 +186,8 @@ static inline void page_pool_destroy(struct page_pool *pool) } static inline void page_pool_use_xdp_mem(struct page_pool *pool, - void (*disconnect)(void *)) + void (*disconnect)(void *), + struct xdp_mem_info *mem) { } static inline void page_pool_release_page(struct page_pool *pool, diff --git a/include/net/sock.h b/include/net/sock.h index 7b4b4237e6e0..ff9b508d9c5f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1209,6 +1209,7 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); + void (*put_port)(struct sock *sk); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, diff --git a/include/net/xdp.h b/include/net/xdp.h index 447f9b1578f3..8f0812e4996d 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -260,6 +260,9 @@ bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); +int xdp_reg_mem_model(struct xdp_mem_info *mem, + enum xdp_mem_type type, void *allocator); +void xdp_unreg_mem_model(struct xdp_mem_info *mem); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 0421061d95f1..b3e6b9422238 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -746,15 +746,9 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) list_add(&bq->flush_node, flush_list); } -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { - struct xdp_frame *xdpf; - - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - /* Info needed when constructing SKB on remote CPU */ xdpf->dev_rx = dev_rx; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 6feea293ff10..fe019dbdb3f0 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -467,24 +467,19 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, bq->q[bq->count++] = xdpf; } -static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct xdp_frame *xdpf; int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; - err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + err = xdp_ok_fwd_dev(dev, xdpf->len); if (unlikely(err)) return err; - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } @@ -520,27 +515,27 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev return act; } -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { - return __xdp_enqueue(dev, xdp, dev_rx, NULL); + return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; - return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog); + return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } -static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp) +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj || !obj->dev->netdev_ops->ndo_xdp_xmit) return false; - if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data)) + if (xdp_ok_fwd_dev(obj->dev, xdpf->len)) return false; return true; @@ -586,14 +581,13 @@ static int get_upper_ifindexes(struct net_device *dev, int *indexes) return n; } -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; - struct xdp_frame *xdpf; int num_excluded = 0; unsigned int i; int err; @@ -603,15 +597,11 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, excluded_devices[num_excluded++] = dev_rx->ifindex; } - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); - if (!is_valid_dst(dst, xdp)) + if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) @@ -634,7 +624,7 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { - if (!is_valid_dst(dst, xdp)) + if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b70c66c6db3b..bfb45381fb3f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6031,6 +6031,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn } if (insn->code == (BPF_JMP | BPF_CALL) && + insn->src_reg == 0 && insn->imm == BPF_FUNC_timer_set_callback) { struct bpf_verifier_state *async_cb; @@ -9079,15 +9080,15 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, { if (type_may_be_null(reg->type) && reg->id == id && !WARN_ON_ONCE(!reg->id)) { - /* Old offset (both fixed and variable parts) should - * have been known-zero, because we don't allow pointer - * arithmetic on pointers that might be NULL. - */ if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0) || reg->off)) { - __mark_reg_known_zero(reg); - reg->off = 0; + /* Old offset (both fixed and variable parts) should + * have been known-zero, because we don't allow pointer + * arithmetic on pointers that might be NULL. If we + * see this happening, don't convert the register. + */ + return; } if (is_null) { reg->type = SCALAR_VALUE; diff --git a/net/core/filter.c b/net/core/filter.c index 606ab5a98a1a..4603b7cd3cd1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3957,10 +3957,35 @@ u32 xdp_master_redirect(struct xdp_buff *xdp) } EXPORT_SYMBOL_GPL(xdp_master_redirect); -int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +static inline int __xdp_do_redirect_xsk(struct bpf_redirect_info *ri, + struct net_device *dev, + struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + enum bpf_map_type map_type = ri->map_type; + void *fwd = ri->tgt_value; + u32 map_id = ri->map_id; + int err; + + ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->map_type = BPF_MAP_TYPE_UNSPEC; + + err = __xsk_map_redirect(fwd, xdp); + if (unlikely(err)) + goto err; + + _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); + return 0; +err: + _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); + return err; +} + +static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, + struct net_device *dev, + struct xdp_frame *xdpf, + struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; @@ -3970,6 +3995,11 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; + if (unlikely(!xdpf)) { + err = -EOVERFLOW; + goto err; + } + switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; @@ -3977,17 +4007,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, map = READ_ONCE(ri->map); if (unlikely(map)) { WRITE_ONCE(ri->map, NULL); - err = dev_map_enqueue_multi(xdp, dev, map, + err = dev_map_enqueue_multi(xdpf, dev, map, ri->flags & BPF_F_EXCLUDE_INGRESS); } else { - err = dev_map_enqueue(fwd, xdp, dev); + err = dev_map_enqueue(fwd, xdpf, dev); } break; case BPF_MAP_TYPE_CPUMAP: - err = cpu_map_enqueue(fwd, xdp, dev); - break; - case BPF_MAP_TYPE_XSKMAP: - err = __xsk_map_redirect(fwd, xdp); + err = cpu_map_enqueue(fwd, xdpf, dev); break; case BPF_MAP_TYPE_UNSPEC: if (map_id == INT_MAX) { @@ -3996,7 +4023,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, err = -EINVAL; break; } - err = dev_xdp_enqueue(fwd, xdp, dev); + err = dev_xdp_enqueue(fwd, xdpf, dev); break; } fallthrough; @@ -4013,8 +4040,34 @@ err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } + +int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + enum bpf_map_type map_type = ri->map_type; + + if (map_type == BPF_MAP_TYPE_XSKMAP) + return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); + + return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), + xdp_prog); +} EXPORT_SYMBOL_GPL(xdp_do_redirect); +int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, + struct xdp_frame *xdpf, struct bpf_prog *xdp_prog) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + enum bpf_map_type map_type = ri->map_type; + + if (map_type == BPF_MAP_TYPE_XSKMAP) + return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); + + return __xdp_do_redirect_frame(ri, dev, xdpf, xdp_prog); +} +EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); + static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, @@ -4741,12 +4794,14 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case SO_RCVBUF: val = min_t(u32, val, sysctl_rmem_max); + val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: val = min_t(u32, val, sysctl_wmem_max); + val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, max_t(int, val * 2, SOCK_MIN_SNDBUF)); @@ -4967,6 +5022,12 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, goto err_clear; switch (optname) { + case SO_RCVBUF: + *((int *)optval) = sk->sk_rcvbuf; + break; + case SO_SNDBUF: + *((int *)optval) = sk->sk_sndbuf; + break; case SO_MARK: *((int *)optval) = sk->sk_mark; break; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1a6978427d6c..7347d5c7dbe0 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -217,6 +217,8 @@ static void page_pool_set_pp_info(struct page_pool *pool, { page->pp = pool; page->pp_magic |= PP_SIGNATURE; + if (pool->p.init_callback) + pool->p.init_callback(page, pool->p.init_arg); } static void page_pool_clear_pp_info(struct page *page) @@ -691,10 +693,12 @@ static void page_pool_release_retry(struct work_struct *wq) schedule_delayed_work(&pool->release_dw, DEFER_TIME); } -void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)) +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), + struct xdp_mem_info *mem) { refcount_inc(&pool->user_cnt); pool->disconnect = disconnect; + pool->xdp_mem_id = mem->id; } void page_pool_destroy(struct page_pool *pool) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 9618ab6d7cc9..1827669eedd6 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -292,15 +292,23 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) if (skb_verdict) psock_set_prog(&psock->progs.skb_verdict, skb_verdict); + /* msg_* and stream_* programs references tracked in psock after this + * point. Reference dec and cleanup will occur through psock destructor + */ ret = sock_map_init_proto(sk, psock); - if (ret < 0) - goto out_drop; + if (ret < 0) { + sk_psock_put(sk, psock); + goto out; + } write_lock_bh(&sk->sk_callback_lock); if (stream_parser && stream_verdict && !psock->saved_data_ready) { ret = sk_psock_init_strp(sk, psock); - if (ret) - goto out_unlock_drop; + if (ret) { + write_unlock_bh(&sk->sk_callback_lock); + sk_psock_put(sk, psock); + goto out; + } sk_psock_start_strp(sk, psock); } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { sk_psock_start_verdict(sk,psock); @@ -309,10 +317,6 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) } write_unlock_bh(&sk->sk_callback_lock); return 0; -out_unlock_drop: - write_unlock_bh(&sk->sk_callback_lock); -out_drop: - sk_psock_put(sk, psock); out_progs: if (skb_verdict) bpf_prog_put(skb_verdict); @@ -325,6 +329,7 @@ out_put_stream_parser: out_put_stream_verdict: if (stream_verdict) bpf_prog_put(stream_verdict); +out: return ret; } diff --git a/net/core/xdp.c b/net/core/xdp.c index 7fe1df85f505..7aba35504986 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -110,20 +110,15 @@ static void mem_allocator_disconnect(void *allocator) mutex_unlock(&mem_id_lock); } -void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +void xdp_unreg_mem_model(struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; - int type = xdp_rxq->mem.type; - int id = xdp_rxq->mem.id; + int type = mem->type; + int id = mem->id; /* Reset mem info to defaults */ - xdp_rxq->mem.id = 0; - xdp_rxq->mem.type = 0; - - if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { - WARN(1, "Missing register, driver bug"); - return; - } + mem->id = 0; + mem->type = 0; if (id == 0) return; @@ -135,6 +130,17 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) rcu_read_unlock(); } } +EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); + +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +{ + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return; + } + + xdp_unreg_mem_model(&xdp_rxq->mem); +} EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) @@ -259,28 +265,24 @@ static bool __is_supported_mem_type(enum xdp_mem_type type) return true; } -int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, - enum xdp_mem_type type, void *allocator) +static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, + enum xdp_mem_type type, + void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr; - if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { - WARN(1, "Missing register, driver bug"); - return -EFAULT; - } - if (!__is_supported_mem_type(type)) - return -EOPNOTSUPP; + return ERR_PTR(-EOPNOTSUPP); - xdp_rxq->mem.type = type; + mem->type = type; if (!allocator) { if (type == MEM_TYPE_PAGE_POOL) - return -EINVAL; /* Setup time check page_pool req */ - return 0; + return ERR_PTR(-EINVAL); /* Setup time check page_pool req */ + return NULL; } /* Delay init of rhashtable to save memory if feature isn't used */ @@ -290,13 +292,13 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, mutex_unlock(&mem_id_lock); if (ret < 0) { WARN_ON(1); - return ret; + return ERR_PTR(ret); } } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) - return -ENOMEM; + return ERR_PTR(-ENOMEM); mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); @@ -304,31 +306,61 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, errno = id; goto err; } - xdp_rxq->mem.id = id; - xdp_alloc->mem = xdp_rxq->mem; + mem->id = id; + xdp_alloc->mem = *mem; xdp_alloc->allocator = allocator; /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { - ida_simple_remove(&mem_id_pool, xdp_rxq->mem.id); - xdp_rxq->mem.id = 0; + ida_simple_remove(&mem_id_pool, mem->id); + mem->id = 0; errno = PTR_ERR(ptr); goto err; } if (type == MEM_TYPE_PAGE_POOL) - page_pool_use_xdp_mem(allocator, mem_allocator_disconnect); + page_pool_use_xdp_mem(allocator, mem_allocator_disconnect, mem); mutex_unlock(&mem_id_lock); - trace_mem_connect(xdp_alloc, xdp_rxq); - return 0; + return xdp_alloc; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); - return errno; + return ERR_PTR(errno); } + +int xdp_reg_mem_model(struct xdp_mem_info *mem, + enum xdp_mem_type type, void *allocator) +{ + struct xdp_mem_allocator *xdp_alloc; + + xdp_alloc = __xdp_reg_mem_model(mem, type, allocator); + if (IS_ERR(xdp_alloc)) + return PTR_ERR(xdp_alloc); + return 0; +} +EXPORT_SYMBOL_GPL(xdp_reg_mem_model); + +int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, + enum xdp_mem_type type, void *allocator) +{ + struct xdp_mem_allocator *xdp_alloc; + + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return -EFAULT; + } + + xdp_alloc = __xdp_reg_mem_model(&xdp_rxq->mem, type, allocator); + if (IS_ERR(xdp_alloc)) + return PTR_ERR(xdp_alloc); + + trace_mem_connect(xdp_alloc, xdp_rxq); + return 0; +} + EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /* XDP RX runs under NAPI protection, and in different delivery error diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f53184767ee7..9c465bac1eb0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -531,6 +531,8 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; + if (sk->sk_prot->put_port) + sk->sk_prot->put_port(sk); goto out_release_sock; } } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index e540b0dcf085..0e56df3a45e2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -994,6 +994,7 @@ struct proto ping_prot = { .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, + .put_port = ping_unhash, .obj_size = sizeof(struct inet_sock), }; EXPORT_SYMBOL(ping_prot); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index f70aa0932bd6..9b9b02052fd3 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -196,12 +196,39 @@ msg_bytes_ready: long timeo; int data; + if (sock_flag(sk, SOCK_DONE)) + goto out; + + if (sk->sk_err) { + copied = sock_error(sk); + goto out; + } + + if (sk->sk_shutdown & RCV_SHUTDOWN) + goto out; + + if (sk->sk_state == TCP_CLOSE) { + copied = -ENOTCONN; + goto out; + } + timeo = sock_rcvtimeo(sk, nonblock); + if (!timeo) { + copied = -EAGAIN; + goto out; + } + + if (signal_pending(current)) { + copied = sock_intr_errno(timeo); + goto out; + } + data = tcp_msg_wait_data(sk, psock, timeo); if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; } +out: release_sock(sk); sk_psock_put(sk, psock); return copied; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ac10e4cdd8d0..9861786b8336 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3076,6 +3076,7 @@ struct proto tcp_prot = { .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, + .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7b18a6f42f18..c2a4411d2b04 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2927,6 +2927,7 @@ struct proto udp_prot = { .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, + .put_port = udp_lib_unhash, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d1636425654e..8fe7900f1949 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -413,6 +413,8 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, if (err) { sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); + if (sk->sk_prot->put_port) + sk->sk_prot->put_port(sk); goto out; } } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 6ac88fe24a8e..9256f6ba87ef 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -177,6 +177,7 @@ struct proto pingv6_prot = { .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, + .put_port = ping_unhash, .obj_size = sizeof(struct raw6_sock), }; EXPORT_SYMBOL_GPL(pingv6_prot); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1ac243d18c2b..075ee8a2df3b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2181,6 +2181,7 @@ struct proto tcpv6_prot = { .hash = inet6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, + .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index df216268cb02..528b81ef19c9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1733,6 +1733,7 @@ struct proto udpv6_prot = { .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, + .put_port = udp_lib_unhash, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 616d663d55aa..aa50864e4415 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -30,6 +31,7 @@ #include #include #include +#include #include #include @@ -56,12 +58,27 @@ #define DEBUG_HEXDUMP 0 +#define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ +#define VLAN_PRIO_SHIFT 13 +#define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ +#define VLAN_VID__DEFAULT 1 +#define VLAN_PRI__DEFAULT 0 + +#define NSEC_PER_SEC 1000000000UL +#define NSEC_PER_USEC 1000 + +#define SCHED_PRI__DEFAULT 0 + typedef __u64 u64; typedef __u32 u32; typedef __u16 u16; typedef __u8 u8; static unsigned long prev_time; +static long tx_cycle_diff_min; +static long tx_cycle_diff_max; +static double tx_cycle_diff_ave; +static long tx_cycle_cnt; enum benchmark_type { BENCH_RXDROP = 0, @@ -81,14 +98,23 @@ static u32 opt_batch_size = 64; static int opt_pkt_count; static u16 opt_pkt_size = MIN_PKT_SIZE; static u32 opt_pkt_fill_pattern = 0x12345678; +static bool opt_vlan_tag; +static u16 opt_pkt_vlan_id = VLAN_VID__DEFAULT; +static u16 opt_pkt_vlan_pri = VLAN_PRI__DEFAULT; +static struct ether_addr opt_txdmac = {{ 0x3c, 0xfd, 0xfe, + 0x9e, 0x7f, 0x71 }}; +static struct ether_addr opt_txsmac = {{ 0xec, 0xb1, 0xd7, + 0x98, 0x3a, 0xc0 }}; static bool opt_extra_stats; static bool opt_quiet; static bool opt_app_stats; static const char *opt_irq_str = ""; static u32 irq_no; static int irqs_at_init = -1; +static u32 sequence; static int opt_poll; static int opt_interval = 1; +static int opt_retries = 3; static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; static u32 opt_umem_flags; static int opt_unaligned_chunks; @@ -100,6 +126,27 @@ static u32 opt_num_xsks = 1; static u32 prog_id; static bool opt_busy_poll; static bool opt_reduced_cap; +static clockid_t opt_clock = CLOCK_MONOTONIC; +static unsigned long opt_tx_cycle_ns; +static int opt_schpolicy = SCHED_OTHER; +static int opt_schprio = SCHED_PRI__DEFAULT; +static bool opt_tstamp; + +struct vlan_ethhdr { + unsigned char h_dest[6]; + unsigned char h_source[6]; + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +#define PKTGEN_MAGIC 0xbe9be955 +struct pktgen_hdr { + __be32 pgh_magic; + __be32 seq_num; + __be32 tv_sec; + __be32 tv_usec; +}; struct xsk_ring_stats { unsigned long rx_npkts; @@ -156,15 +203,63 @@ struct xsk_socket_info { u32 outstanding_tx; }; +static const struct clockid_map { + const char *name; + clockid_t clockid; +} clockids_map[] = { + { "REALTIME", CLOCK_REALTIME }, + { "TAI", CLOCK_TAI }, + { "BOOTTIME", CLOCK_BOOTTIME }, + { "MONOTONIC", CLOCK_MONOTONIC }, + { NULL } +}; + +static const struct sched_map { + const char *name; + int policy; +} schmap[] = { + { "OTHER", SCHED_OTHER }, + { "FIFO", SCHED_FIFO }, + { NULL } +}; + static int num_socks; struct xsk_socket_info *xsks[MAX_SOCKS]; int sock; +static int get_clockid(clockid_t *id, const char *name) +{ + const struct clockid_map *clk; + + for (clk = clockids_map; clk->name; clk++) { + if (strcasecmp(clk->name, name) == 0) { + *id = clk->clockid; + return 0; + } + } + + return -1; +} + +static int get_schpolicy(int *policy, const char *name) +{ + const struct sched_map *sch; + + for (sch = schmap; sch->name; sch++) { + if (strcasecmp(sch->name, name) == 0) { + *policy = sch->policy; + return 0; + } + } + + return -1; +} + static unsigned long get_nsecs(void) { struct timespec ts; - clock_gettime(CLOCK_MONOTONIC, &ts); + clock_gettime(opt_clock, &ts); return ts.tv_sec * 1000000000UL + ts.tv_nsec; } @@ -257,6 +352,15 @@ static void dump_app_stats(long dt) xsks[i]->app_stats.prev_tx_wakeup_sendtos = xsks[i]->app_stats.tx_wakeup_sendtos; xsks[i]->app_stats.prev_opt_polls = xsks[i]->app_stats.opt_polls; } + + if (opt_tx_cycle_ns) { + printf("\n%-18s %-10s %-10s %-10s %-10s %-10s\n", + "", "period", "min", "ave", "max", "cycle"); + printf("%-18s %-10lu %-10lu %-10lu %-10lu %-10lu\n", + "Cyclic TX", opt_tx_cycle_ns, tx_cycle_diff_min, + (long)(tx_cycle_diff_ave / tx_cycle_cnt), + tx_cycle_diff_max, tx_cycle_cnt); + } } static bool get_interrupt_number(void) @@ -740,29 +844,69 @@ static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len, #define ETH_FCS_SIZE 4 -#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ - sizeof(struct udphdr)) +#define ETH_HDR_SIZE (opt_vlan_tag ? sizeof(struct vlan_ethhdr) : \ + sizeof(struct ethhdr)) +#define PKTGEN_HDR_SIZE (opt_tstamp ? sizeof(struct pktgen_hdr) : 0) +#define PKT_HDR_SIZE (ETH_HDR_SIZE + sizeof(struct iphdr) + \ + sizeof(struct udphdr) + PKTGEN_HDR_SIZE) +#define PKTGEN_HDR_OFFSET (ETH_HDR_SIZE + sizeof(struct iphdr) + \ + sizeof(struct udphdr)) +#define PKTGEN_SIZE_MIN (PKTGEN_HDR_OFFSET + sizeof(struct pktgen_hdr) + \ + ETH_FCS_SIZE) #define PKT_SIZE (opt_pkt_size - ETH_FCS_SIZE) -#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr)) +#define IP_PKT_SIZE (PKT_SIZE - ETH_HDR_SIZE) #define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr)) -#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) +#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - \ + (sizeof(struct udphdr) + PKTGEN_HDR_SIZE)) static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE]; static void gen_eth_hdr_data(void) { - struct udphdr *udp_hdr = (struct udphdr *)(pkt_data + - sizeof(struct ethhdr) + - sizeof(struct iphdr)); - struct iphdr *ip_hdr = (struct iphdr *)(pkt_data + - sizeof(struct ethhdr)); - struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data; + struct pktgen_hdr *pktgen_hdr; + struct udphdr *udp_hdr; + struct iphdr *ip_hdr; + + if (opt_vlan_tag) { + struct vlan_ethhdr *veth_hdr = (struct vlan_ethhdr *)pkt_data; + u16 vlan_tci = 0; + + udp_hdr = (struct udphdr *)(pkt_data + + sizeof(struct vlan_ethhdr) + + sizeof(struct iphdr)); + ip_hdr = (struct iphdr *)(pkt_data + + sizeof(struct vlan_ethhdr)); + pktgen_hdr = (struct pktgen_hdr *)(pkt_data + + sizeof(struct vlan_ethhdr) + + sizeof(struct iphdr) + + sizeof(struct udphdr)); + /* ethernet & VLAN header */ + memcpy(veth_hdr->h_dest, &opt_txdmac, ETH_ALEN); + memcpy(veth_hdr->h_source, &opt_txsmac, ETH_ALEN); + veth_hdr->h_vlan_proto = htons(ETH_P_8021Q); + vlan_tci = opt_pkt_vlan_id & VLAN_VID_MASK; + vlan_tci |= (opt_pkt_vlan_pri << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; + veth_hdr->h_vlan_TCI = htons(vlan_tci); + veth_hdr->h_vlan_encapsulated_proto = htons(ETH_P_IP); + } else { + struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data; + + udp_hdr = (struct udphdr *)(pkt_data + + sizeof(struct ethhdr) + + sizeof(struct iphdr)); + ip_hdr = (struct iphdr *)(pkt_data + + sizeof(struct ethhdr)); + pktgen_hdr = (struct pktgen_hdr *)(pkt_data + + sizeof(struct ethhdr) + + sizeof(struct iphdr) + + sizeof(struct udphdr)); + /* ethernet header */ + memcpy(eth_hdr->h_dest, &opt_txdmac, ETH_ALEN); + memcpy(eth_hdr->h_source, &opt_txsmac, ETH_ALEN); + eth_hdr->h_proto = htons(ETH_P_IP); + } - /* ethernet header */ - memcpy(eth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN); - memcpy(eth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN); - eth_hdr->h_proto = htons(ETH_P_IP); /* IP header */ ip_hdr->version = IPVERSION; @@ -785,6 +929,9 @@ static void gen_eth_hdr_data(void) udp_hdr->dest = htons(0x1000); udp_hdr->len = htons(UDP_PKT_SIZE); + if (opt_tstamp) + pktgen_hdr->pgh_magic = htonl(PKTGEN_MAGIC); + /* UDP data */ memset32_htonl(pkt_data + PKT_HDR_SIZE, opt_pkt_fill_pattern, UDP_PKT_DATA_SIZE); @@ -908,6 +1055,7 @@ static struct option long_options[] = { {"xdp-skb", no_argument, 0, 'S'}, {"xdp-native", no_argument, 0, 'N'}, {"interval", required_argument, 0, 'n'}, + {"retries", required_argument, 0, 'O'}, {"zero-copy", no_argument, 0, 'z'}, {"copy", no_argument, 0, 'c'}, {"frame-size", required_argument, 0, 'f'}, @@ -916,10 +1064,20 @@ static struct option long_options[] = { {"shared-umem", no_argument, 0, 'M'}, {"force", no_argument, 0, 'F'}, {"duration", required_argument, 0, 'd'}, + {"clock", required_argument, 0, 'w'}, {"batch-size", required_argument, 0, 'b'}, {"tx-pkt-count", required_argument, 0, 'C'}, {"tx-pkt-size", required_argument, 0, 's'}, {"tx-pkt-pattern", required_argument, 0, 'P'}, + {"tx-vlan", no_argument, 0, 'V'}, + {"tx-vlan-id", required_argument, 0, 'J'}, + {"tx-vlan-pri", required_argument, 0, 'K'}, + {"tx-dmac", required_argument, 0, 'G'}, + {"tx-smac", required_argument, 0, 'H'}, + {"tx-cycle", required_argument, 0, 'T'}, + {"tstamp", no_argument, 0, 'y'}, + {"policy", required_argument, 0, 'W'}, + {"schpri", required_argument, 0, 'U'}, {"extra-stats", no_argument, 0, 'x'}, {"quiet", no_argument, 0, 'Q'}, {"app-stats", no_argument, 0, 'a'}, @@ -943,6 +1101,7 @@ static void usage(const char *prog) " -S, --xdp-skb=n Use XDP skb-mod\n" " -N, --xdp-native=n Enforce XDP native mode\n" " -n, --interval=n Specify statistics update interval (default 1 sec).\n" + " -O, --retries=n Specify time-out retries (1s interval) attempt (default 3).\n" " -z, --zero-copy Force zero-copy mode.\n" " -c, --copy Force copy mode.\n" " -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n" @@ -952,6 +1111,7 @@ static void usage(const char *prog) " -F, --force Force loading the XDP prog\n" " -d, --duration=n Duration in secs to run command.\n" " Default: forever.\n" + " -w, --clock=CLOCK Clock NAME (default MONOTONIC).\n" " -b, --batch-size=n Batch size for sending or receiving\n" " packets. Default: %d\n" " -C, --tx-pkt-count=n Number of packets to send.\n" @@ -960,6 +1120,15 @@ static void usage(const char *prog) " (Default: %d bytes)\n" " Min size: %d, Max size %d.\n" " -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n" + " -V, --tx-vlan Send VLAN tagged packets (For -t|--txonly)\n" + " -J, --tx-vlan-id=n Tx VLAN ID [1-4095]. Default: %d (For -V|--tx-vlan)\n" + " -K, --tx-vlan-pri=n Tx VLAN Priority [0-7]. Default: %d (For -V|--tx-vlan)\n" + " -G, --tx-dmac= Dest MAC addr of TX frame in aa:bb:cc:dd:ee:ff format (For -V|--tx-vlan)\n" + " -H, --tx-smac= Src MAC addr of TX frame in aa:bb:cc:dd:ee:ff format (For -V|--tx-vlan)\n" + " -T, --tx-cycle=n Tx cycle time in micro-seconds (For -t|--txonly).\n" + " -y, --tstamp Add time-stamp to packet (For -t|--txonly).\n" + " -W, --policy=POLICY Schedule policy. Default: SCHED_OTHER\n" + " -U, --schpri=n Schedule priority. Default: %d\n" " -x, --extra-stats Display extra statistics.\n" " -Q, --quiet Do not display any stats.\n" " -a, --app-stats Display application (syscall) statistics.\n" @@ -969,7 +1138,9 @@ static void usage(const char *prog) "\n"; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE, opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE, - XSK_UMEM__DEFAULT_FRAME_SIZE, opt_pkt_fill_pattern); + XSK_UMEM__DEFAULT_FRAME_SIZE, opt_pkt_fill_pattern, + VLAN_VID__DEFAULT, VLAN_PRI__DEFAULT, + SCHED_PRI__DEFAULT); exit(EXIT_FAILURE); } @@ -981,7 +1152,8 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:BR", + c = getopt_long(argc, argv, + "Frtli:q:pSNn:w:O:czf:muMd:b:C:s:P:VJ:K:G:H:T:yW:U:xQaI:BR", long_options, &option_index); if (c == -1) break; @@ -1015,6 +1187,17 @@ static void parse_command_line(int argc, char **argv) case 'n': opt_interval = atoi(optarg); break; + case 'w': + if (get_clockid(&opt_clock, optarg)) { + fprintf(stderr, + "ERROR: Invalid clock %s. Default to CLOCK_MONOTONIC.\n", + optarg); + opt_clock = CLOCK_MONOTONIC; + } + break; + case 'O': + opt_retries = atoi(optarg); + break; case 'z': opt_xdp_bind_flags |= XDP_ZEROCOPY; break; @@ -1062,6 +1245,49 @@ static void parse_command_line(int argc, char **argv) case 'P': opt_pkt_fill_pattern = strtol(optarg, NULL, 16); break; + case 'V': + opt_vlan_tag = true; + break; + case 'J': + opt_pkt_vlan_id = atoi(optarg); + break; + case 'K': + opt_pkt_vlan_pri = atoi(optarg); + break; + case 'G': + if (!ether_aton_r(optarg, + (struct ether_addr *)&opt_txdmac)) { + fprintf(stderr, "Invalid dmac address:%s\n", + optarg); + usage(basename(argv[0])); + } + break; + case 'H': + if (!ether_aton_r(optarg, + (struct ether_addr *)&opt_txsmac)) { + fprintf(stderr, "Invalid smac address:%s\n", + optarg); + usage(basename(argv[0])); + } + break; + case 'T': + opt_tx_cycle_ns = atoi(optarg); + opt_tx_cycle_ns *= NSEC_PER_USEC; + break; + case 'y': + opt_tstamp = 1; + break; + case 'W': + if (get_schpolicy(&opt_schpolicy, optarg)) { + fprintf(stderr, + "ERROR: Invalid policy %s. Default to SCHED_OTHER.\n", + optarg); + opt_schpolicy = SCHED_OTHER; + } + break; + case 'U': + opt_schprio = atoi(optarg); + break; case 'x': opt_extra_stats = 1; break; @@ -1267,16 +1493,22 @@ static void rx_drop_all(void) } } -static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) +static int tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, + int batch_size, unsigned long tx_ns) { - u32 idx; + u32 idx, tv_sec, tv_usec; unsigned int i; while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < batch_size) { complete_tx_only(xsk, batch_size); if (benchmark_done) - return; + return 0; + } + + if (opt_tstamp) { + tv_sec = (u32)(tx_ns / NSEC_PER_SEC); + tv_usec = (u32)((tx_ns % NSEC_PER_SEC) / 1000); } for (i = 0; i < batch_size; i++) { @@ -1284,6 +1516,21 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) idx + i); tx_desc->addr = (*frame_nb + i) * opt_xsk_frame_size; tx_desc->len = PKT_SIZE; + + if (opt_tstamp) { + struct pktgen_hdr *pktgen_hdr; + u64 addr = tx_desc->addr; + char *pkt; + + pkt = xsk_umem__get_data(xsk->umem->buffer, addr); + pktgen_hdr = (struct pktgen_hdr *)(pkt + PKTGEN_HDR_OFFSET); + + pktgen_hdr->seq_num = htonl(sequence++); + pktgen_hdr->tv_sec = htonl(tv_sec); + pktgen_hdr->tv_usec = htonl(tv_usec); + + hex_dump(pkt, PKT_SIZE, addr); + } } xsk_ring_prod__submit(&xsk->tx, batch_size); @@ -1292,6 +1539,8 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) *frame_nb += batch_size; *frame_nb %= NUM_FRAMES; complete_tx_only(xsk, batch_size); + + return batch_size; } static inline int get_batch_size(int pkt_cnt) @@ -1318,23 +1567,48 @@ static void complete_tx_only_all(void) pending = !!xsks[i]->outstanding_tx; } } - } while (pending); + sleep(1); + } while (pending && opt_retries-- > 0); } static void tx_only_all(void) { struct pollfd fds[MAX_SOCKS] = {}; u32 frame_nb[MAX_SOCKS] = {}; + unsigned long next_tx_ns = 0; int pkt_cnt = 0; int i, ret; + if (opt_poll && opt_tx_cycle_ns) { + fprintf(stderr, + "Error: --poll and --tx-cycles are both set\n"); + return; + } + for (i = 0; i < num_socks; i++) { fds[0].fd = xsk_socket__fd(xsks[i]->xsk); fds[0].events = POLLOUT; } + if (opt_tx_cycle_ns) { + /* Align Tx time to micro-second boundary */ + next_tx_ns = (get_nsecs() / NSEC_PER_USEC + 1) * + NSEC_PER_USEC; + next_tx_ns += opt_tx_cycle_ns; + + /* Initialize periodic Tx scheduling variance */ + tx_cycle_diff_min = 1000000000; + tx_cycle_diff_max = 0; + tx_cycle_diff_ave = 0.0; + } + while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) { int batch_size = get_batch_size(pkt_cnt); + unsigned long tx_ns = 0; + struct timespec next; + int tx_cnt = 0; + long diff; + int err; if (opt_poll) { for (i = 0; i < num_socks; i++) @@ -1347,13 +1621,43 @@ static void tx_only_all(void) continue; } - for (i = 0; i < num_socks; i++) - tx_only(xsks[i], &frame_nb[i], batch_size); + if (opt_tx_cycle_ns) { + next.tv_sec = next_tx_ns / NSEC_PER_SEC; + next.tv_nsec = next_tx_ns % NSEC_PER_SEC; + err = clock_nanosleep(opt_clock, TIMER_ABSTIME, &next, NULL); + if (err) { + if (err != EINTR) + fprintf(stderr, + "clock_nanosleep failed. Err:%d errno:%d\n", + err, errno); + break; + } - pkt_cnt += batch_size; + /* Measure periodic Tx scheduling variance */ + tx_ns = get_nsecs(); + diff = tx_ns - next_tx_ns; + if (diff < tx_cycle_diff_min) + tx_cycle_diff_min = diff; + + if (diff > tx_cycle_diff_max) + tx_cycle_diff_max = diff; + + tx_cycle_diff_ave += (double)diff; + tx_cycle_cnt++; + } else if (opt_tstamp) { + tx_ns = get_nsecs(); + } + + for (i = 0; i < num_socks; i++) + tx_cnt += tx_only(xsks[i], &frame_nb[i], batch_size, tx_ns); + + pkt_cnt += tx_cnt; if (benchmark_done) break; + + if (opt_tx_cycle_ns) + next_tx_ns += opt_tx_cycle_ns; } if (opt_pkt_count) @@ -1584,6 +1888,7 @@ int main(int argc, char **argv) struct __user_cap_data_struct data[2] = { { 0 } }; struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; bool rx = false, tx = false; + struct sched_param schparam; struct xsk_umem_info *umem; struct bpf_object *obj; int xsks_map_fd = 0; @@ -1646,6 +1951,9 @@ int main(int argc, char **argv) apply_setsockopt(xsks[i]); if (opt_bench == BENCH_TXONLY) { + if (opt_tstamp && opt_pkt_size < PKTGEN_SIZE_MIN) + opt_pkt_size = PKTGEN_SIZE_MIN; + gen_eth_hdr_data(); for (i = 0; i < NUM_FRAMES; i++) @@ -1685,6 +1993,16 @@ int main(int argc, char **argv) prev_time = get_nsecs(); start_time = prev_time; + /* Configure sched priority for better wake-up accuracy */ + memset(&schparam, 0, sizeof(schparam)); + schparam.sched_priority = opt_schprio; + ret = sched_setscheduler(0, opt_schpolicy, &schparam); + if (ret) { + fprintf(stderr, "Error(%d) in setting priority(%d): %s\n", + errno, opt_schprio, strerror(errno)); + goto out; + } + if (opt_bench == BENCH_RXDROP) rx_drop_all(); else if (opt_bench == BENCH_TXONLY) @@ -1692,6 +2010,7 @@ int main(int argc, char **argv) else l2fwd_all(); +out: benchmark_done = true; if (!opt_quiet) diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 6719b9282eca..e999159fa28d 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -642,6 +642,30 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, printf("\n"); } +static void +probe_misc_feature(struct bpf_insn *insns, size_t len, + const char *define_prefix, __u32 ifindex, + const char *feat_name, const char *plain_name, + const char *define_name) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .prog_ifindex = ifindex, + ); + bool res; + int fd; + + errno = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + insns, len, &opts); + res = fd >= 0 || !errno; + + if (fd >= 0) + close(fd); + + print_bool_feature(feat_name, plain_name, define_name, res, + define_prefix); +} + /* * Probe for availability of kernel commit (5.3): * @@ -649,29 +673,81 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, */ static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex) { - LIBBPF_OPTS(bpf_prog_load_opts, opts, - .prog_ifindex = ifindex, - ); struct bpf_insn insns[BPF_MAXINSNS + 1]; - bool res; - int i, fd; + int i; for (i = 0; i < BPF_MAXINSNS; i++) insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); - errno = 0; - fd = bpf_prog_load(BPF_PROG_TYPE_SCHED_CLS, NULL, "GPL", - insns, ARRAY_SIZE(insns), &opts); - res = fd >= 0 || (errno != E2BIG && errno != EINVAL); - - if (fd >= 0) - close(fd); - - print_bool_feature("have_large_insn_limit", + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_large_insn_limit", "Large program size limit", - "LARGE_INSN_LIMIT", - res, define_prefix); + "LARGE_INSN_LIMIT"); +} + +/* + * Probe for bounded loop support introduced in commit 2589726d12a1 + * ("bpf: introduce bounded loops"). + */ +static void +probe_bounded_loops(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 10), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, -2), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_bounded_loops", + "Bounded loop support", + "BOUNDED_LOOPS"); +} + +/* + * Probe for the v2 instruction set extension introduced in commit 92b31a9af73b + * ("bpf: add BPF_J{LT,LE,SLT,SLE} instructions"). + */ +static void +probe_v2_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v2_isa_extension", + "ISA extension v2", + "V2_ISA_EXTENSION"); +} + +/* + * Probe for the v3 instruction set extension introduced in commit 092ed0968bb6 + * ("bpf: verifier support JMP32"). + */ +static void +probe_v3_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v3_isa_extension", + "ISA extension v3", + "V3_ISA_EXTENSION"); } static void @@ -788,6 +864,9 @@ static void section_misc(const char *define_prefix, __u32 ifindex) "/*** eBPF misc features ***/", define_prefix); probe_large_insn_limit(define_prefix, ifindex); + probe_bounded_loops(define_prefix, ifindex); + probe_v2_isa_extension(define_prefix, ifindex); + probe_v3_isa_extension(define_prefix, ifindex); print_end_section(); } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f874896c4154..2a21d50516bc 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1655,7 +1655,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) j = 0; idx = 0; bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_offload_neutral(map)) + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) bpf_map__set_ifindex(map, ifindex); if (j < old_map_fds && idx == map_replace[j].idx) { diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9b64eed2b003..550b4cbb6c99 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -691,11 +691,11 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, return libbpf_err_errno(ret); } -int bpf_map_delete_batch(int fd, void *keys, __u32 *count, +int bpf_map_delete_batch(int fd, const void *keys, __u32 *count, const struct bpf_map_batch_opts *opts) { return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, - NULL, keys, NULL, count, opts); + NULL, (void *)keys, NULL, count, opts); } int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, @@ -715,11 +715,11 @@ int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, count, opts); } -int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, +int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count, const struct bpf_map_batch_opts *opts) { return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, - keys, values, count, opts); + (void *)keys, (void *)values, count, opts); } int bpf_obj_pin(int fd, const char *pathname) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 00619f64a040..14e0d97ad2cf 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -254,17 +254,128 @@ struct bpf_map_batch_opts { }; #define bpf_map_batch_opts__last_field flags -LIBBPF_API int bpf_map_delete_batch(int fd, void *keys, + +/** + * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple + * elements in a BPF map. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param count input and output parameter; on input **count** represents the + * number of elements in the map to delete in batch; + * on output if a non-EFAULT error is returned, **count** represents the number of deleted + * elements if the output **count** value is not equal to the input **count** value + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch deletion works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys, __u32 *count, const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements. + * + * The parameter *in_batch* is the address of the first element in the batch to read. + * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent + * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate + * that the batched lookup starts from the beginning of the map. + * + * The *keys* and *values* are output parameters which must point to memory large enough to + * hold *count* items based on the key and value size of the map *map_fd*. The *keys* + * buffer must be of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * indicate that the batched lookup starts from the beginning of the map. + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array large enough for *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read in batch; on output it's the number of elements that were + * successfully read. + * If a non-EFAULT error is returned, count will be set as the number of elements + * that were read before the error occurred. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch lookup works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, void *values, __u32 *count, const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion + * of BPF map elements where each element is deleted after being retrieved. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * get address of the first element in *out_batch* + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array of *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read and delete in batch; on output it represents the number of + * elements that were successfully read and deleted + * If a non-**EFAULT** error code is returned and if the output **count** value + * is not equal to the input **count** value, up to **count** elements may + * have been deleted. + * if **EFAULT** is returned up to *count* elements may have been deleted without + * being returned via the *keys* and *values* output parameters. + * @param opts options for configuring the way the batch lookup and delete works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, void *keys, void *values, __u32 *count, const struct bpf_map_batch_opts *opts); -LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values, + +/** + * @brief **bpf_map_update_batch()** updates multiple elements in a map + * by specifying keys and their corresponding values. + * + * The *keys* and *values* parameters must point to memory large enough + * to hold *count* items based on the key and value size of the map. + * + * The *opts* parameter can be used to control how *bpf_map_update_batch()* + * should handle keys that either do or do not already exist in the map. + * In particular the *flags* parameter of *bpf_map_batch_opts* can be + * one of the following: + * + * Note that *count* is an input and output parameter, where on output it + * represents how many elements were successfully updated. Also note that if + * **EFAULT** then *count* should not be trusted to be correct. + * + * **BPF_ANY** + * Create new elements or update existing. + * + * **BPF_NOEXIST** + * Create new elements only if they do not exist. + * + * **BPF_EXIST** + * Update existing elements. + * + * **BPF_F_LOCK** + * Update spin_lock-ed map elements. This must be + * specified if the map value contains a spinlock. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param values pointer to an array of *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to update in batch; on output if a non-EFAULT error is returned, + * **count** represents the number of updated elements if the output **count** + * value is not equal to the input **count** value. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch update works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count, const struct bpf_map_batch_opts *opts); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 9cb99d1e2385..7f10dd501a52 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -9916,7 +9916,10 @@ static int append_to_file(const char *file, const char *fmt, ...) static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, const char *kfunc_name, size_t offset) { - snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), kfunc_name, offset); + static int index = 0; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset, + __sync_fetch_and_add(&index, 1)); } static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, @@ -10017,7 +10020,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), func_name, offset); - legacy_probe = strdup(func_name); + legacy_probe = strdup(probe_name); if (!legacy_probe) return libbpf_err_ptr(-ENOMEM); @@ -10676,10 +10679,10 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) return link; } -enum bpf_perf_event_ret -bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, - void **copy_mem, size_t *copy_size, - bpf_perf_event_print_t fn, void *private_data) +static enum bpf_perf_event_ret +perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, + void **copy_mem, size_t *copy_size, + bpf_perf_event_print_t fn, void *private_data) { struct perf_event_mmap_page *header = mmap_mem; __u64 data_head = ring_buffer_read_head(header); @@ -10724,6 +10727,12 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, return libbpf_err(ret); } +__attribute__((alias("perf_event_read_simple"))) +enum bpf_perf_event_ret +bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, + void **copy_mem, size_t *copy_size, + bpf_perf_event_print_t fn, void *private_data); + struct perf_buffer; struct perf_buffer_params { @@ -11132,10 +11141,10 @@ static int perf_buffer__process_records(struct perf_buffer *pb, { enum bpf_perf_event_ret ret; - ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size, - pb->page_size, &cpu_buf->buf, - &cpu_buf->buf_size, - perf_buffer__process_record, cpu_buf); + ret = perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); if (ret != LIBBPF_PERF_EVENT_CONT) return ret; return 0; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 85dfef88b3d2..8b9bc5e90c2b 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -677,7 +677,8 @@ 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 * in the BPF object file. */ -LIBBPF_API struct bpf_map * +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__find_map_by_name() instead") +struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead") @@ -744,6 +745,7 @@ LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__type() instead") LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); /** @@ -1026,6 +1028,7 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, void *private_data); +LIBBPF_DEPRECATED_SINCE(0, 8, "use perf_buffer__poll() or perf_buffer__consume() instead") LIBBPF_API enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c index 0a577a248d34..32fc5b3b5cf6 100644 --- a/tools/testing/selftests/bpf/prog_tests/d_path.c +++ b/tools/testing/selftests/bpf/prog_tests/d_path.c @@ -9,6 +9,7 @@ #define MAX_FILES 7 #include "test_d_path.skel.h" +#include "test_d_path_check_rdonly_mem.skel.h" static int duration; @@ -99,7 +100,7 @@ out_close: return ret; } -void test_d_path(void) +static void test_d_path_basic(void) { struct test_d_path__bss *bss; struct test_d_path *skel; @@ -155,3 +156,22 @@ void test_d_path(void) cleanup: test_d_path__destroy(skel); } + +static void test_d_path_check_rdonly_mem(void) +{ + struct test_d_path_check_rdonly_mem *skel; + + skel = test_d_path_check_rdonly_mem__open_and_load(); + ASSERT_ERR_PTR(skel, "unexpected_load_overwriting_rdonly_mem"); + + test_d_path_check_rdonly_mem__destroy(skel); +} + +void test_d_path(void) +{ + if (test__start_subtest("basic")) + test_d_path_basic(); + + if (test__start_subtest("check_rdonly_mem")) + test_d_path_check_rdonly_mem(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 4b18b73df10b..c2426df58e17 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -105,6 +105,13 @@ static int setns_by_fd(int nsfd) if (!ASSERT_OK(err, "unshare")) return err; + /* Make our /sys mount private, so the following umount won't + * trigger the global umount in case it's shared. + */ + err = mount("none", "/sys", NULL, MS_PRIVATE, NULL); + if (!ASSERT_OK(err, "remount private /sys")) + return err; + err = umount2("/sys", MNT_DETACH); if (!ASSERT_OK(err, "umount2 /sys")) return err; diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c index 76e93b31c14b..717dab14322b 100644 --- a/tools/testing/selftests/bpf/progs/loop3.c +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -12,9 +12,9 @@ char _license[] SEC("license") = "GPL"; SEC("raw_tracepoint/consume_skb") -int while_true(volatile struct pt_regs* ctx) +int while_true(struct pt_regs *ctx) { - __u64 i = 0, sum = 0; + volatile __u64 i = 0, sum = 0; do { i++; sum += PT_REGS_RC(ctx); diff --git a/tools/testing/selftests/bpf/progs/test_d_path_check_rdonly_mem.c b/tools/testing/selftests/bpf/progs/test_d_path_check_rdonly_mem.c new file mode 100644 index 000000000000..27c27cff6a3a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_d_path_check_rdonly_mem.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ + +#include "vmlinux.h" +#include +#include + +extern const int bpf_prog_active __ksym; + +SEC("fentry/security_inode_getattr") +int BPF_PROG(d_path_check_rdonly_mem, struct path *path, struct kstat *stat, + __u32 request_mask, unsigned int query_flags) +{ + void *active; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + active = (void *)bpf_per_cpu_ptr(&bpf_prog_active, cpu); + if (active) { + /* FAIL here! 'active' points to readonly memory. bpf helpers + * that update its arguments can not write into it. + */ + bpf_d_path(path, active, sizeof(int)); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index e8edd3dd3ec2..fe10f8134278 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -35,18 +35,21 @@ struct sock_test { /* Endpoint to bind() to */ const char *ip; unsigned short port; + unsigned short port_retry; /* Expected test result */ enum { LOAD_REJECT, ATTACH_REJECT, BIND_REJECT, SUCCESS, + RETRY_SUCCESS, + RETRY_REJECT } result; }; static struct sock_test tests[] = { { - "bind4 load with invalid access: src_ip6", + .descr = "bind4 load with invalid access: src_ip6", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -54,16 +57,12 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = LOAD_REJECT, }, { - "bind4 load with invalid access: mark", + .descr = "bind4 load with invalid access: mark", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -71,16 +70,12 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = LOAD_REJECT, }, { - "bind6 load with invalid access: src_ip4", + .descr = "bind6 load with invalid access: src_ip4", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -88,16 +83,12 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .result = LOAD_REJECT, }, { - "sock_create load with invalid access: src_port", + .descr = "sock_create load with invalid access: src_port", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, @@ -105,128 +96,106 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET_SOCK_CREATE, - BPF_CGROUP_INET_SOCK_CREATE, - 0, - 0, - NULL, - 0, - LOAD_REJECT, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .result = LOAD_REJECT, }, { - "sock_create load w/o expected_attach_type (compat mode)", + .descr = "sock_create load w/o expected_attach_type (compat mode)", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - 0, - BPF_CGROUP_INET_SOCK_CREATE, - AF_INET, - SOCK_STREAM, - "127.0.0.1", - 8097, - SUCCESS, + .expected_attach_type = 0, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 8097, + .result = SUCCESS, }, { - "sock_create load w/ expected_attach_type", + .descr = "sock_create load w/ expected_attach_type", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET_SOCK_CREATE, - BPF_CGROUP_INET_SOCK_CREATE, - AF_INET, - SOCK_STREAM, - "127.0.0.1", - 8097, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 8097, + .result = SUCCESS, }, { - "attach type mismatch bind4 vs bind6", + .descr = "attach type mismatch bind4 vs bind6", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .result = ATTACH_REJECT, }, { - "attach type mismatch bind6 vs bind4", + .descr = "attach type mismatch bind6 vs bind4", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = ATTACH_REJECT, }, { - "attach type mismatch default vs bind4", + .descr = "attach type mismatch default vs bind4", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - 0, - BPF_CGROUP_INET4_POST_BIND, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = 0, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .result = ATTACH_REJECT, }, { - "attach type mismatch bind6 vs sock_create", + .descr = "attach type mismatch bind6 vs sock_create", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET_SOCK_CREATE, - 0, - 0, - NULL, - 0, - ATTACH_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .result = ATTACH_REJECT, }, { - "bind4 reject all", + .descr = "bind4 reject all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - AF_INET, - SOCK_STREAM, - "0.0.0.0", - 0, - BIND_REJECT, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "0.0.0.0", + .result = BIND_REJECT, }, { - "bind6 reject all", + .descr = "bind6 reject all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - AF_INET6, - SOCK_STREAM, - "::", - 0, - BIND_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::", + .result = BIND_REJECT, }, { - "bind6 deny specific IP & port", + .descr = "bind6 deny specific IP & port", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), @@ -247,16 +216,16 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - AF_INET6, - SOCK_STREAM, - "::1", - 8193, - BIND_REJECT, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::1", + .port = 8193, + .result = BIND_REJECT, }, { - "bind4 allow specific IP & port", + .descr = "bind4 allow specific IP & port", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), @@ -277,41 +246,132 @@ static struct sock_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - AF_INET, - SOCK_STREAM, - "127.0.0.1", - 4098, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 4098, + .result = SUCCESS, }, { - "bind4 allow all", + .descr = "bind4 deny specific IP & port of TCP, and retry", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (ip == expected && port == expected) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_ip4)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x7F000001), 4), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "127.0.0.1", + .port = 4098, + .port_retry = 5000, + .result = RETRY_SUCCESS, + }, + { + .descr = "bind4 deny specific IP & port of UDP, and retry", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (ip == expected && port == expected) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_ip4)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x7F000001), 4), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_DGRAM, + .ip = "127.0.0.1", + .port = 4098, + .port_retry = 5000, + .result = RETRY_SUCCESS, + }, + { + .descr = "bind6 deny specific IP & port, and retry", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (ip == expected && port == expected) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_ip6[3])), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x00000001), 4), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock, src_port)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::1", + .port = 8193, + .port_retry = 9000, + .result = RETRY_SUCCESS, + }, + { + .descr = "bind4 allow all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET4_POST_BIND, - BPF_CGROUP_INET4_POST_BIND, - AF_INET, - SOCK_STREAM, - "0.0.0.0", - 0, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, + .attach_type = BPF_CGROUP_INET4_POST_BIND, + .domain = AF_INET, + .type = SOCK_STREAM, + .ip = "0.0.0.0", + .result = SUCCESS, }, { - "bind6 allow all", + .descr = "bind6 allow all", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - BPF_CGROUP_INET6_POST_BIND, - BPF_CGROUP_INET6_POST_BIND, - AF_INET6, - SOCK_STREAM, - "::", - 0, - SUCCESS, + .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, + .attach_type = BPF_CGROUP_INET6_POST_BIND, + .domain = AF_INET6, + .type = SOCK_STREAM, + .ip = "::", + .result = SUCCESS, }, }; @@ -351,14 +411,15 @@ static int attach_sock_prog(int cgfd, int progfd, return bpf_prog_attach(progfd, cgfd, attach_type, BPF_F_ALLOW_OVERRIDE); } -static int bind_sock(int domain, int type, const char *ip, unsigned short port) +static int bind_sock(int domain, int type, const char *ip, + unsigned short port, unsigned short port_retry) { struct sockaddr_storage addr; struct sockaddr_in6 *addr6; struct sockaddr_in *addr4; int sockfd = -1; socklen_t len; - int err = 0; + int res = SUCCESS; sockfd = socket(domain, type, 0); if (sockfd < 0) @@ -384,21 +445,44 @@ static int bind_sock(int domain, int type, const char *ip, unsigned short port) goto err; } - if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) - goto err; + if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) { + /* sys_bind() may fail for different reasons, errno has to be + * checked to confirm that BPF program rejected it. + */ + if (errno != EPERM) + goto err; + if (port_retry) + goto retry; + res = BIND_REJECT; + goto out; + } + goto out; +retry: + if (domain == AF_INET) + addr4->sin_port = htons(port_retry); + else + addr6->sin6_port = htons(port_retry); + if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) { + if (errno != EPERM) + goto err; + res = RETRY_REJECT; + } else { + res = RETRY_SUCCESS; + } goto out; err: - err = -1; + res = -1; out: close(sockfd); - return err; + return res; } static int run_test_case(int cgfd, const struct sock_test *test) { int progfd = -1; int err = 0; + int res; printf("Test case: %s .. ", test->descr); progfd = load_sock_prog(test->insns, test->expected_attach_type); @@ -416,21 +500,11 @@ static int run_test_case(int cgfd, const struct sock_test *test) goto err; } - if (bind_sock(test->domain, test->type, test->ip, test->port) == -1) { - /* sys_bind() may fail for different reasons, errno has to be - * checked to confirm that BPF program rejected it. - */ - if (test->result == BIND_REJECT && errno == EPERM) - goto out; - else - goto err; - } + res = bind_sock(test->domain, test->type, test->ip, test->port, + test->port_retry); + if (res > 0 && test->result == res) + goto out; - - if (test->result != SUCCESS) - goto err; - - goto out; err: err = -1; out: diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 6c907144311f..1a8eb9672bd1 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -58,6 +58,34 @@ .result = ACCEPT, .result_unpriv = ACCEPT, }, +{ + "check with invalid reg offset 0", + .insns = { + /* reserve 8 byte ringbuf memory */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve), + /* store a pointer to the reserved memory in R6 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* add invalid offset to memory or NULL */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), + /* check whether the reservation was successful */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* should not be able to access *(R7) = 0 */ + BPF_ST_MEM(BPF_W, BPF_REG_6, 0, 0), + /* submit the reserved ringbuf memory */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_ringbuf = { 1 }, + .result = REJECT, + .errstr = "R0 pointer arithmetic on mem_or_null prohibited", +}, { "check corrupted spill/fill", .insns = {