diff options
84 files changed, 4168 insertions, 361 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 306c289b30c7..0af66fa919a8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10742,6 +10742,7 @@ L: linux-block@vger.kernel.org L: nbd@other.debian.org F: Documentation/blockdev/nbd.txt F: drivers/block/nbd.c +F: include/trace/events/nbd.h F: include/uapi/linux/nbd.h NETWORK DROP MONITOR diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 9c01f04db64d..ec894de0ed4e 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -277,6 +277,7 @@ __AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000) __AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000) __AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) +__AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0xB8200000) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) @@ -394,6 +395,13 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register state, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size); +u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size); u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 7820a4a688fa..9e2b5882cdeb 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -734,6 +734,46 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, state); } +u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size) +{ + u32 insn = aarch64_insn_get_ldadd_value(); + + switch (size) { + case AARCH64_INSN_SIZE_32: + case AARCH64_INSN_SIZE_64: + break; + default: + pr_err("%s: unimplemented size encoding %d\n", __func__, size); + return AARCH64_BREAK_FAULT; + } + + insn = aarch64_insn_encode_ldst_size(size, insn); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, + result); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, + address); + + return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn, + value); +} + +u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size) +{ + /* + * STADD is simply encoded as an alias for LDADD with XZR as + * the destination register. + */ + return aarch64_insn_gen_ldadd(AARCH64_INSN_REG_ZR, address, + value, size); +} + static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type, enum aarch64_insn_prfm_target target, enum aarch64_insn_prfm_policy policy, diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 783de51a6c4e..76606e87233f 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -100,11 +100,9 @@ #define A64_STXR(sf, Rt, Rn, Rs) \ A64_LSX(sf, Rt, Rn, Rs, STORE_EX) -/* Prefetch */ -#define A64_PRFM(Rn, type, target, policy) \ - aarch64_insn_gen_prefetch(Rn, AARCH64_INSN_PRFM_TYPE_##type, \ - AARCH64_INSN_PRFM_TARGET_##target, \ - AARCH64_INSN_PRFM_POLICY_##policy) +/* LSE atomics */ +#define A64_STADD(sf, Rn, Rs) \ + aarch64_insn_gen_stadd(Rn, Rs, A64_SIZE(sf)) /* Add/subtract (immediate) */ #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index aaddc0217e73..df845cee438e 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -365,7 +365,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, const bool is64 = BPF_CLASS(code) == BPF_ALU64 || BPF_CLASS(code) == BPF_JMP; const bool isdw = BPF_SIZE(code) == BPF_DW; - u8 jmp_cond; + u8 jmp_cond, reg; s32 jmp_offset; #define check_imm(bits, imm) do { \ @@ -756,19 +756,28 @@ emit_cond_jmp: break; } break; + /* STX XADD: lock *(u32 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_W: /* STX XADD: lock *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: - emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_ADD(1, tmp, tmp, dst), ctx); - emit(A64_PRFM(tmp, PST, L1, STRM), ctx); - emit(A64_LDXR(isdw, tmp2, tmp), ctx); - emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); - emit(A64_STXR(isdw, tmp2, tmp, tmp3), ctx); - jmp_offset = -3; - check_imm19(jmp_offset); - emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + if (!off) { + reg = dst; + } else { + emit_a64_mov_i(1, tmp, off, ctx); + emit(A64_ADD(1, tmp, tmp, dst), ctx); + reg = tmp; + } + if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) { + emit(A64_STADD(isdw, reg, src), ctx); + } else { + emit(A64_LDXR(isdw, tmp2, reg), ctx); + emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); + emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx); + jmp_offset = -3; + check_imm19(jmp_offset); + emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + } break; default: diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 6c2dd268e603..053958a8a2ba 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -44,6 +44,9 @@ #include <linux/nbd-netlink.h> #include <net/genetlink.h> +#define CREATE_TRACE_POINTS +#include <trace/events/nbd.h> + static DEFINE_IDR(nbd_index_idr); static DEFINE_MUTEX(nbd_index_mutex); static int nbd_total_devices = 0; @@ -510,6 +513,10 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) if (sent) { if (sent >= sizeof(request)) { skip = sent - sizeof(request); + + /* initialize handle for tracing purposes */ + handle = nbd_cmd_handle(cmd); + goto send_pages; } iov_iter_advance(&from, sent); @@ -526,11 +533,14 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) handle = nbd_cmd_handle(cmd); memcpy(request.handle, &handle, sizeof(handle)); + trace_nbd_send_request(&request, nbd->index, blk_mq_rq_from_pdu(cmd)); + dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", req, nbdcmd_to_ascii(type), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req)); result = sock_xmit(nbd, index, 1, &from, (type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent); + trace_nbd_header_sent(req, handle); if (result <= 0) { if (was_interrupted(result)) { /* If we havne't sent anything we can just return BUSY, @@ -603,6 +613,7 @@ send_pages: bio = next; } out: + trace_nbd_payload_sent(req, handle); nsock->pending = NULL; nsock->sent = 0; return 0; @@ -650,6 +661,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) tag, req); return ERR_PTR(-ENOENT); } + trace_nbd_header_received(req, handle); cmd = blk_mq_rq_to_pdu(req); mutex_lock(&cmd->lock); @@ -703,6 +715,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) } } out: + trace_nbd_payload_received(req, handle); mutex_unlock(&cmd->lock); return ret ? ERR_PTR(ret) : cmd; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index c64e2fb5a4f1..350e385528fd 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -354,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, hdr_len = buff->len; if (hdr_len > AQ_CFG_RX_HDR_SIZE) - hdr_len = eth_get_headlen(aq_buf_vaddr(&buff->rxdata), + hdr_len = eth_get_headlen(skb->dev, + aq_buf_vaddr(&buff->rxdata), AQ_CFG_RX_HDR_SIZE); memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata), diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6528a597367b..526f36dcb204 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -899,7 +899,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, DMA_ATTR_WEAK_ORDERING); if (unlikely(!payload)) - payload = eth_get_headlen(data_ptr, len); + payload = eth_get_headlen(bp->dev, data_ptr, len); skb = napi_alloc_skb(&rxr->bnapi->napi, payload); if (!skb) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 297b95c1b3c1..65b985acae38 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -598,7 +598,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, } else { ring->stats.seg_pkt_cnt++; - pull_len = eth_get_headlen(va, HNS_RX_HEAD_SIZE); + pull_len = eth_get_headlen(ndev, va, HNS_RX_HEAD_SIZE); memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b0f31eb481ea..96272e632afc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2588,7 +2588,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length, ring->stats.seg_pkt_cnt++; u64_stats_update_end(&ring->syncp); - ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE); + ring->pull_len = eth_get_headlen(netdev, va, HNS3_RX_HEAD_SIZE); __skb_put(skb, ring->pull_len); hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len, desc_cb); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 2325cee76211..b4d970e44163 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -280,7 +280,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer, /* we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN); + pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 1a95223c9f99..e1931701cd7e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2035,7 +2035,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > I40E_RX_HDR_SIZE) - headlen = eth_get_headlen(xdp->data, I40E_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, xdp->data, + I40E_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), xdp->data, diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index b64187753ad6..cf8be63a8a4f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1315,7 +1315,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IAVF_RX_HDR_SIZE) - headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 79043fec0187..259f118c7d8b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -699,7 +699,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, /* Determine available headroom for copy */ headlen = size; if (headlen > ICE_RX_HDR_SIZE) - headlen = eth_get_headlen(va, ICE_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, va, ICE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index acbb5b4f333d..9b8a4bb25327 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8051,7 +8051,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IGB_RX_HDR_LEN) - headlen = eth_get_headlen(va, IGB_RX_HDR_LEN); + headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f79728381e8a..e58a6e0dc4d9 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1199,7 +1199,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IGC_RX_HDR_LEN) - headlen = eth_get_headlen(va, IGC_RX_HDR_LEN); + headlen = eth_get_headlen(skb->dev, va, IGC_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 60cec3540dd7..7b903206b534 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1800,7 +1800,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, * we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE); + pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 49e23afa05a2..d189ed247665 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -895,7 +895,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring, /* Determine available headroom for copy */ headlen = size; if (headlen > IXGBEVF_RX_HDR_SIZE) - headlen = eth_get_headlen(xdp->data, IXGBEVF_RX_HDR_SIZE); + headlen = eth_get_headlen(skb->dev, xdp->data, + IXGBEVF_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), xdp->data, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 40f3f98aa279..7b61126fcec9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -163,7 +163,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode, case MLX5_INLINE_MODE_NONE: return 0; case MLX5_INLINE_MODE_TCP_UDP: - hlen = eth_get_headlen(skb->data, skb_headlen(skb)); + hlen = eth_get_headlen(skb->dev, skb->data, skb_headlen(skb)); if (hlen == ETH_HLEN && !skb_vlan_tag_present(skb)) hlen += VLAN_HLEN; break; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 24d0220b9ba0..9d72f8c76c15 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1965,7 +1965,8 @@ drop: if (frags) { /* Exercise flow dissector code path. */ - u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb)); + u32 headlen = eth_get_headlen(tun->dev, skb->data, + skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { this_cpu_inc(tun->pcpu_stats->rx_dropped); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f15432d90728..9a21848fdb07 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -184,6 +184,7 @@ enum bpf_arg_type { ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ + ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack @@ -204,6 +205,7 @@ enum bpf_arg_type { ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ + ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ }; /* type of values returned from helper functions */ @@ -272,6 +274,7 @@ enum bpf_reg_type { PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ 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 */ }; /* The information passed from prog-specific *_is_valid_access @@ -361,6 +364,7 @@ struct bpf_prog_aux { u32 used_map_cnt; u32 max_ctx_offset; u32 max_pkt_offset; + u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index d26991a16894..5a9975678d6f 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -25,6 +25,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) #endif #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) @@ -60,6 +61,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index aa8bfd6f738c..25c0d049336f 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -33,7 +33,7 @@ struct device; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); -u32 eth_get_headlen(void *data, unsigned int max_len); +u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f42942a443b..6d58fa8a65fd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1258,11 +1258,19 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, unsigned int key_count); #ifdef CONFIG_NET +int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); #else +static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { @@ -1275,12 +1283,12 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) } #endif -struct bpf_flow_keys; -bool __skb_flow_bpf_dissect(struct bpf_prog *prog, - const struct sk_buff *skb, - struct flow_dissector *flow_dissector, - struct bpf_flow_keys *flow_keys); -bool __skb_flow_dissect(const struct sk_buff *skb, +struct bpf_flow_dissector; +bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen); + +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, @@ -1290,8 +1298,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { - return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, flow_dissector, + target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, @@ -1299,18 +1307,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_dissector, flow, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, + flow, NULL, 0, 0, 0, flags); } static inline bool -skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb, +skb_flow_dissect_flow_keys_basic(const struct net *net, + const struct sk_buff *skb, struct flow_keys_basic *flow, void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, + return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } @@ -2488,7 +2497,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb) if (skb_transport_header_was_set(skb)) return; - if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) + if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index 49ba9cde7e4b..b29950a19205 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -45,6 +45,7 @@ struct bpf_raw_event_map { struct tracepoint *tp; void *bpf_func; u32 num_args; + u32 writable_size; } __aligned(32); #endif diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h new file mode 100644 index 000000000000..b9dcb02e756b --- /dev/null +++ b/include/net/bpf_sk_storage.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Facebook */ +#ifndef _BPF_SK_STORAGE_H +#define _BPF_SK_STORAGE_H + +struct sock; + +void bpf_sk_storage_free(struct sock *sk); + +extern const struct bpf_func_proto bpf_sk_storage_get_proto; +extern const struct bpf_func_proto bpf_sk_storage_delete_proto; + +#endif /* _BPF_SK_STORAGE_H */ diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 2b26979efb48..7c5a8d9a8d2a 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -305,4 +305,11 @@ static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissec return ((char *)target_container) + flow_dissector->offset[key_id]; } +struct bpf_flow_dissector { + struct bpf_flow_keys *flow_keys; + const struct sk_buff *skb; + void *data; + void *data_end; +}; + #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e8f85cd2afce..21f434f3ac9e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -364,13 +364,10 @@ struct tcf_proto { }; struct qdisc_skb_cb { - union { - struct { - unsigned int pkt_len; - u16 slave_dev_queue_mapping; - u16 tc_classid; - }; - struct bpf_flow_keys *flow_keys; + struct { + unsigned int pkt_len; + u16 slave_dev_queue_mapping; + u16 tc_classid; }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; diff --git a/include/net/sock.h b/include/net/sock.h index 784cd19d5ff7..4d208c0f9c14 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -236,6 +236,8 @@ struct sock_common { /* public: */ }; +struct bpf_sk_storage; + /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -510,6 +512,9 @@ struct sock { #endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; +#ifdef CONFIG_BPF_SYSCALL + struct bpf_sk_storage __rcu *sk_bpf_storage; +#endif struct rcu_head sk_rcu; }; diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index 505dae0bed80..d6e556c0a085 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -69,8 +69,7 @@ __bpf_trace_##call(void *__data, proto) \ * to make sure that if the tracepoint handling changes, the * bpf probe will fail to compile unless it too is updated. */ -#undef DEFINE_EVENT -#define DEFINE_EVENT(template, call, proto, args) \ +#define __DEFINE_EVENT(template, call, proto, args, size) \ static inline void bpf_test_probe_##call(void) \ { \ check_trace_callback_type_##call(__bpf_trace_##template); \ @@ -81,12 +80,36 @@ __bpf_trace_tp_map_##call = { \ .tp = &__tracepoint_##call, \ .bpf_func = (void *)__bpf_trace_##template, \ .num_args = COUNT_ARGS(args), \ + .writable_size = size, \ }; +#define FIRST(x, ...) x + +#undef DEFINE_EVENT_WRITABLE +#define DEFINE_EVENT_WRITABLE(template, call, proto, args, size) \ +static inline void bpf_test_buffer_##call(void) \ +{ \ + /* BUILD_BUG_ON() is ignored if the code is completely eliminated, but \ + * BUILD_BUG_ON_ZERO() uses a different mechanism that is not \ + * dead-code-eliminated. \ + */ \ + FIRST(proto); \ + (void)BUILD_BUG_ON_ZERO(size != sizeof(*FIRST(args))); \ +} \ +__DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size) + +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, call, proto, args) \ + __DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), 0) #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#undef DEFINE_EVENT_WRITABLE +#undef __DEFINE_EVENT +#undef FIRST + #endif /* CONFIG_BPF_EVENTS */ diff --git a/include/trace/events/bpf_test_run.h b/include/trace/events/bpf_test_run.h new file mode 100644 index 000000000000..265447e3f71a --- /dev/null +++ b/include/trace/events/bpf_test_run.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM bpf_test_run + +#if !defined(_TRACE_BPF_TEST_RUN_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_BPF_TEST_RUN_H + +#include <linux/tracepoint.h> + +DECLARE_EVENT_CLASS(bpf_test_finish, + + TP_PROTO(int *err), + + TP_ARGS(err), + + TP_STRUCT__entry( + __field(int, err) + ), + + TP_fast_assign( + __entry->err = *err; + ), + + TP_printk("bpf_test_finish with err=%d", __entry->err) +); + +#ifdef DEFINE_EVENT_WRITABLE +#undef BPF_TEST_RUN_DEFINE_EVENT +#define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size) \ + DEFINE_EVENT_WRITABLE(template, call, PARAMS(proto), \ + PARAMS(args), size) +#else +#undef BPF_TEST_RUN_DEFINE_EVENT +#define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size) \ + DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args)) +#endif + +BPF_TEST_RUN_DEFINE_EVENT(bpf_test_finish, bpf_test_finish, + + TP_PROTO(int *err), + + TP_ARGS(err), + + sizeof(int) +); + +#endif + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/nbd.h b/include/trace/events/nbd.h new file mode 100644 index 000000000000..9849956f34d8 --- /dev/null +++ b/include/trace/events/nbd.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nbd + +#if !defined(_TRACE_NBD_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NBD_H + +#include <linux/tracepoint.h> + +DECLARE_EVENT_CLASS(nbd_transport_event, + + TP_PROTO(struct request *req, u64 handle), + + TP_ARGS(req, handle), + + TP_STRUCT__entry( + __field(struct request *, req) + __field(u64, handle) + ), + + TP_fast_assign( + __entry->req = req; + __entry->handle = handle; + ), + + TP_printk( + "nbd transport event: request %p, handle 0x%016llx", + __entry->req, + __entry->handle + ) +); + +DEFINE_EVENT(nbd_transport_event, nbd_header_sent, + + TP_PROTO(struct request *req, u64 handle), + + TP_ARGS(req, handle) +); + +DEFINE_EVENT(nbd_transport_event, nbd_payload_sent, + + TP_PROTO(struct request *req, u64 handle), + + TP_ARGS(req, handle) +); + +DEFINE_EVENT(nbd_transport_event, nbd_header_received, + + TP_PROTO(struct request *req, u64 handle), + + TP_ARGS(req, handle) +); + +DEFINE_EVENT(nbd_transport_event, nbd_payload_received, + + TP_PROTO(struct request *req, u64 handle), + + TP_ARGS(req, handle) +); + +DECLARE_EVENT_CLASS(nbd_send_request, + + TP_PROTO(struct nbd_request *nbd_request, int index, + struct request *rq), + + TP_ARGS(nbd_request, index, rq), + + TP_STRUCT__entry( + __field(struct nbd_request *, nbd_request) + __field(u64, dev_index) + __field(struct request *, request) + ), + + TP_fast_assign( + __entry->nbd_request = 0; + __entry->dev_index = index; + __entry->request = rq; + ), + + TP_printk("nbd%lld: request %p", __entry->dev_index, __entry->request) +); + +#ifdef DEFINE_EVENT_WRITABLE +#undef NBD_DEFINE_EVENT +#define NBD_DEFINE_EVENT(template, call, proto, args, size) \ + DEFINE_EVENT_WRITABLE(template, call, PARAMS(proto), \ + PARAMS(args), size) +#else +#undef NBD_DEFINE_EVENT +#define NBD_DEFINE_EVENT(template, call, proto, args, size) \ + DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args)) +#endif + +NBD_DEFINE_EVENT(nbd_send_request, nbd_send_request, + + TP_PROTO(struct nbd_request *nbd_request, int index, + struct request *rq), + + TP_ARGS(nbd_request, index, rq), + + sizeof(struct nbd_request) +); + +#endif + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index eaf2d3284248..72336bac7573 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -133,6 +133,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, }; /* Note that tracing related programs such as @@ -168,6 +169,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, }; enum bpf_attach_type { @@ -2629,6 +2631,42 @@ union bpf_attr { * was provided. * * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a sk. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem(map, &sk)** except this + * helper enforces the key must be a **bpf_fullsock()** + * and the map must be a BPF_MAP_TYPE_SK_STORAGE also. + * + * Underneath, the value is stored locally at *sk* instead of + * the map. The *map* is used as the bpf-local-storage **type**. + * The bpf-local-storage **type** (i.e. the *map*) is searched + * against all bpf-local-storages residing at sk. + * + * An optional *flags* (BPF_SK_STORAGE_GET_F_CREATE) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with BPF_SK_STORAGE_GET_F_CREATE to specify + * the initial value of a bpf-local-storage. If *value* is + * NULL, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a sk. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2737,7 +2775,9 @@ union bpf_attr { FN(sysctl_get_new_value), \ FN(sysctl_set_new_value), \ FN(strtol), \ - FN(strtoul), + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2813,6 +2853,9 @@ enum bpf_func_id { /* BPF_FUNC_sysctl_get_name flags. */ #define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) +/* BPF_FUNC_sk_storage_get flags */ +#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 92c9b8a32b50..ad3ccf82f31d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -526,7 +526,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EACCES; if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_SK_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { @@ -1789,12 +1790,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) } raw_tp->btp = btp; - prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd, - BPF_PROG_TYPE_RAW_TRACEPOINT); + prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) { err = PTR_ERR(prog); goto out_free_tp; } + if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && + prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { + err = -EINVAL; + goto out_put_prog; + } err = bpf_probe_register(raw_tp->btp, prog); if (err) @@ -2009,6 +2014,8 @@ static int bpf_prog_query(const union bpf_attr *attr, break; case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); + case BPF_FLOW_DISSECTOR: + return skb_flow_dissector_prog_query(attr, uattr); default: return -EINVAL; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 423f242a5efb..271717246af3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -405,6 +405,7 @@ static const char * const reg_type_str[] = { [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", + [PTR_TO_TP_BUFFER] = "tp_buffer", }; static char slot_type_char[] = { @@ -1993,6 +1994,32 @@ static int check_ctx_reg(struct bpf_verifier_env *env, return 0; } +static int check_tp_buffer_access(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + int regno, int off, int size) +{ + if (off < 0) { + verbose(env, + "R%d invalid tracepoint buffer access: off=%d, size=%d", + regno, off, size); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, + "R%d invalid variable buffer offset: off=%d, var_off=%s", + regno, off, tn_buf); + return -EACCES; + } + if (off + size > env->prog->aux->max_tp_access) + env->prog->aux->max_tp_access = off + size; + + return 0; +} + + /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ @@ -2137,6 +2164,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_TP_BUFFER) { + err = check_tp_buffer_access(env, reg, regno, off, size); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -2512,10 +2543,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || + arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { expected_type = PTR_TO_STACK; - if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && - type != expected_type) + if (register_is_null(reg) && + arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) + /* final test in check_stack_boundary() */; + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -2547,6 +2583,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } meta->ref_obj_id = reg->ref_obj_id; } + } else if (arg_type == ARG_PTR_TO_SOCKET) { + expected_type = PTR_TO_SOCKET; + if (type != expected_type) + goto err_type; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -2604,6 +2644,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, meta->map_ptr->key_size, false, NULL); } else if (arg_type == ARG_PTR_TO_MAP_VALUE || + (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && + !register_is_null(reg)) || arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -2753,6 +2795,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_map_push_elem) goto error; break; + case BPF_MAP_TYPE_SK_STORAGE: + if (func_id != BPF_FUNC_sk_storage_get && + func_id != BPF_FUNC_sk_storage_delete) + goto error; + break; default: break; } @@ -2816,6 +2863,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_sk_storage_get: + case BPF_FUNC_sk_storage_delete: + if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) + goto error; + break; default: break; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 91800be0c8eb..8607aba1d882 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -915,6 +915,27 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { const struct bpf_prog_ops raw_tracepoint_prog_ops = { }; +static bool raw_tp_writable_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off == 0) { + if (size != sizeof(u64) || type != BPF_READ) + return false; + info->reg_type = PTR_TO_TP_BUFFER; + } + return raw_tp_prog_is_valid_access(off, size, type, prog, info); +} + +const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = { + .get_func_proto = raw_tp_prog_func_proto, + .is_valid_access = raw_tp_writable_prog_is_valid_access, +}; + +const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = { +}; + static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -1204,6 +1225,9 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64)) return -EINVAL; + if (prog->aux->max_tp_access > btp->writable_size) + return -EINVAL; + return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog); } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2221573dacdb..33e0dc168c16 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -10,9 +10,13 @@ #include <linux/etherdevice.h> #include <linux/filter.h> #include <linux/sched/signal.h> +#include <net/bpf_sk_storage.h> #include <net/sock.h> #include <net/tcp.h> +#define CREATE_TRACE_POINTS +#include <trace/events/bpf_test_run.h> + static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time) { @@ -100,6 +104,7 @@ static int bpf_test_finish(const union bpf_attr *kattr, if (err != -ENOSPC) err = 0; out: + trace_bpf_test_finish(&err); return err; } @@ -331,6 +336,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, sizeof(struct __sk_buff)); out: kfree_skb(skb); + bpf_sk_storage_free(sk); kfree(sk); kfree(ctx); return ret; @@ -379,13 +385,12 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, union bpf_attr __user *uattr) { u32 size = kattr->test.data_size_in; + struct bpf_flow_dissector ctx = {}; u32 repeat = kattr->test.repeat; struct bpf_flow_keys flow_keys; u64 time_start, time_spent = 0; - struct bpf_skb_data_end *cb; + const struct ethhdr *eth; u32 retval, duration; - struct sk_buff *skb; - struct sock *sk; void *data; int ret; u32 i; @@ -396,46 +401,28 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (kattr->test.ctx_in || kattr->test.ctx_out) return -EINVAL; - data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); + if (size < ETH_HLEN) + return -EINVAL; + + data = bpf_test_init(kattr, size, 0, 0); if (IS_ERR(data)) return PTR_ERR(data); - sk = kzalloc(sizeof(*sk), GFP_USER); - if (!sk) { - kfree(data); - return -ENOMEM; - } - sock_net_set(sk, current->nsproxy->net_ns); - sock_init_data(NULL, sk); - - skb = build_skb(data, 0); - if (!skb) { - kfree(data); - kfree(sk); - return -ENOMEM; - } - skb->sk = sk; - - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - __skb_put(skb, size); - skb->protocol = eth_type_trans(skb, - current->nsproxy->net_ns->loopback_dev); - skb_reset_network_header(skb); - - cb = (struct bpf_skb_data_end *)skb->cb; - cb->qdisc_cb.flow_keys = &flow_keys; + eth = (struct ethhdr *)data; if (!repeat) repeat = 1; + ctx.flow_keys = &flow_keys; + ctx.data = data; + ctx.data_end = (__u8 *)data + size; + rcu_read_lock(); preempt_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { - retval = __skb_flow_bpf_dissect(prog, skb, - &flow_keys_dissector, - &flow_keys); + retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, + size); if (signal_pending(current)) { preempt_enable(); @@ -468,7 +455,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, retval, duration); out: - kfree_skb(skb); - kfree(sk); + kfree(data); return ret; } diff --git a/net/core/Makefile b/net/core/Makefile index f97d6254e564..a104dc8faafc 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -34,3 +34,4 @@ obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c new file mode 100644 index 000000000000..a8e9ac71b22d --- /dev/null +++ b/net/core/bpf_sk_storage.c @@ -0,0 +1,804 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <net/bpf_sk_storage.h> +#include <net/sock.h> +#include <uapi/linux/btf.h> + +static atomic_t cache_idx; + +struct bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* Thp map is not the primary owner of a bpf_sk_storage_elem. + * Instead, the sk->sk_bpf_storage is. + * + * The map (bpf_sk_storage_map) is for two purposes + * 1. Define the size of the "sk local storage". It is + * the map's value_size. + * + * 2. Maintain a list to keep track of all elems such + * that they can be cleaned up during the map destruction. + * + * When a bpf local storage is being looked up for a + * particular sk, the "bpf_map" pointer is actually used + * as the "key" to search in the list of elem in + * sk->sk_bpf_storage. + * + * Hence, consider sk->sk_bpf_storage is the mini-map + * with the "bpf_map" pointer as the searching key. + */ +struct bpf_sk_storage_map { + struct bpf_map map; + /* Lookup elem does not require accessing the map. + * + * Updating/Deleting requires a bucket lock to + * link/unlink the elem from the map. Having + * multiple buckets to improve contention. + */ + struct bucket *buckets; + u32 bucket_log; + u16 elem_size; + u16 cache_idx; +}; + +struct bpf_sk_storage_data { + /* smap is used as the searching key when looking up + * from sk->sk_bpf_storage. + * + * Put it in the same cacheline as the data to minimize + * the number of cachelines access during the cache hit case. + */ + struct bpf_sk_storage_map __rcu *smap; + u8 data[0] __aligned(8); +}; + +/* Linked to bpf_sk_storage and bpf_sk_storage_map */ +struct bpf_sk_storage_elem { + struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ + struct hlist_node snode; /* Linked to bpf_sk_storage */ + struct bpf_sk_storage __rcu *sk_storage; + struct rcu_head rcu; + /* 8 bytes hole */ + /* The data is stored in aother cacheline to minimize + * the number of cachelines access during a cache hit. + */ + struct bpf_sk_storage_data sdata ____cacheline_aligned; +}; + +#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) +#define SDATA(_SELEM) (&(_SELEM)->sdata) +#define BPF_SK_STORAGE_CACHE_SIZE 16 + +struct bpf_sk_storage { + struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_sk_storage_elem */ + struct sock *sk; /* The sk that owns the the above "list" of + * bpf_sk_storage_elem. + */ + struct rcu_head rcu; + raw_spinlock_t lock; /* Protect adding/removing from the "list" */ +}; + +static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *selem) +{ + return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; +} + +static int omem_charge(struct sock *sk, unsigned int size) +{ + /* same check as in sock_kmalloc() */ + if (size <= sysctl_optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + atomic_add(size, &sk->sk_omem_alloc); + return 0; + } + + return -ENOMEM; +} + +static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) +{ + return !hlist_unhashed(&selem->snode); +} + +static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) +{ + return !hlist_unhashed(&selem->map_node); +} + +static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, + struct sock *sk, void *value, + bool charge_omem) +{ + struct bpf_sk_storage_elem *selem; + + if (charge_omem && omem_charge(sk, smap->elem_size)) + return NULL; + + selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (selem) { + if (value) + memcpy(SDATA(selem)->data, value, smap->map.value_size); + return selem; + } + + if (charge_omem) + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + + return NULL; +} + +/* sk_storage->lock must be held and selem->sk_storage == sk_storage. + * The caller must ensure selem->smap is still valid to be + * dereferenced for its smap->elem_size and smap->cache_idx. + */ +static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_elem *selem, + bool uncharge_omem) +{ + struct bpf_sk_storage_map *smap; + bool free_sk_storage; + struct sock *sk; + + smap = rcu_dereference(SDATA(selem)->smap); + sk = sk_storage->sk; + + /* All uncharging on sk->sk_omem_alloc must be done first. + * sk may be freed once the last selem is unlinked from sk_storage. + */ + if (uncharge_omem) + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + + free_sk_storage = hlist_is_singular_node(&selem->snode, + &sk_storage->list); + if (free_sk_storage) { + atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); + sk_storage->sk = NULL; + /* After this RCU_INIT, sk may be freed and cannot be used */ + RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); + + /* sk_storage is not freed now. sk_storage->lock is + * still held and raw_spin_unlock_bh(&sk_storage->lock) + * will be done by the caller. + * + * Although the unlock will be done under + * rcu_read_lock(), it is more intutivie to + * read if kfree_rcu(sk_storage, rcu) is done + * after the raw_spin_unlock_bh(&sk_storage->lock). + * + * Hence, a "bool free_sk_storage" is returned + * to the caller which then calls the kfree_rcu() + * after unlock. + */ + } + hlist_del_init_rcu(&selem->snode); + if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == + SDATA(selem)) + RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); + + kfree_rcu(selem, rcu); + + return free_sk_storage; +} + +static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) +{ + struct bpf_sk_storage *sk_storage; + bool free_sk_storage = false; + + if (unlikely(!selem_linked_to_sk(selem))) + /* selem has already been unlinked from sk */ + return; + + sk_storage = rcu_dereference(selem->sk_storage); + raw_spin_lock_bh(&sk_storage->lock); + if (likely(selem_linked_to_sk(selem))) + free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + raw_spin_unlock_bh(&sk_storage->lock); + + if (free_sk_storage) + kfree_rcu(sk_storage, rcu); +} + +/* sk_storage->lock must be held and sk_storage->list cannot be empty */ +static void __selem_link_sk(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_elem *selem) +{ + RCU_INIT_POINTER(selem->sk_storage, sk_storage); + hlist_add_head(&selem->snode, &sk_storage->list); +} + +static void selem_unlink_map(struct bpf_sk_storage_elem *selem) +{ + struct bpf_sk_storage_map *smap; + struct bucket *b; + + if (unlikely(!selem_linked_to_map(selem))) + /* selem has already be unlinked from smap */ + return; + + smap = rcu_dereference(SDATA(selem)->smap); + b = select_bucket(smap, selem); + raw_spin_lock_bh(&b->lock); + if (likely(selem_linked_to_map(selem))) + hlist_del_init_rcu(&selem->map_node); + raw_spin_unlock_bh(&b->lock); +} + +static void selem_link_map(struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *selem) +{ + struct bucket *b = select_bucket(smap, selem); + + raw_spin_lock_bh(&b->lock); + RCU_INIT_POINTER(SDATA(selem)->smap, smap); + hlist_add_head_rcu(&selem->map_node, &b->list); + raw_spin_unlock_bh(&b->lock); +} + +static void selem_unlink(struct bpf_sk_storage_elem *selem) +{ + /* Always unlink from map before unlinking from sk_storage + * because selem will be freed after successfully unlinked from + * the sk_storage. + */ + selem_unlink_map(selem); + selem_unlink_sk(selem); +} + +static struct bpf_sk_storage_data * +__sk_storage_lookup(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_map *smap, + bool cacheit_lockit) +{ + struct bpf_sk_storage_data *sdata; + struct bpf_sk_storage_elem *selem; + + /* Fast path (cache hit) */ + sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); + if (sdata && rcu_access_pointer(sdata->smap) == smap) + return sdata; + + /* Slow path (cache miss) */ + hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) + if (rcu_access_pointer(SDATA(selem)->smap) == smap) + break; + + if (!selem) + return NULL; + + sdata = SDATA(selem); + if (cacheit_lockit) { + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next __sk_storage_lookup(). + */ + raw_spin_lock_bh(&sk_storage->lock); + if (selem_linked_to_sk(selem)) + rcu_assign_pointer(sk_storage->cache[smap->cache_idx], + sdata); + raw_spin_unlock_bh(&sk_storage->lock); + } + + return sdata; +} + +static struct bpf_sk_storage_data * +sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) +{ + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_map *smap; + + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage) + return NULL; + + smap = (struct bpf_sk_storage_map *)map; + return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); +} + +static int check_flags(const struct bpf_sk_storage_data *old_sdata, + u64 map_flags) +{ + if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) + /* elem already exists */ + return -EEXIST; + + if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) + /* elem doesn't exist, cannot update it */ + return -ENOENT; + + return 0; +} + +static int sk_storage_alloc(struct sock *sk, + struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *first_selem) +{ + struct bpf_sk_storage *prev_sk_storage, *sk_storage; + int err; + + err = omem_charge(sk, sizeof(*sk_storage)); + if (err) + return err; + + sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN); + if (!sk_storage) { + err = -ENOMEM; + goto uncharge; + } + INIT_HLIST_HEAD(&sk_storage->list); + raw_spin_lock_init(&sk_storage->lock); + sk_storage->sk = sk; + + __selem_link_sk(sk_storage, first_selem); + selem_link_map(smap, first_selem); + /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. + * Hence, atomic ops is used to set sk->sk_bpf_storage + * from NULL to the newly allocated sk_storage ptr. + * + * From now on, the sk->sk_bpf_storage pointer is protected + * by the sk_storage->lock. Hence, when freeing + * the sk->sk_bpf_storage, the sk_storage->lock must + * be held before setting sk->sk_bpf_storage to NULL. + */ + prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, + NULL, sk_storage); + if (unlikely(prev_sk_storage)) { + selem_unlink_map(first_selem); + err = -EAGAIN; + goto uncharge; + + /* Note that even first_selem was linked to smap's + * bucket->list, first_selem can be freed immediately + * (instead of kfree_rcu) because + * bpf_sk_storage_map_free() does a + * synchronize_rcu() before walking the bucket->list. + * Hence, no one is accessing selem from the + * bucket->list under rcu_read_lock(). + */ + } + + return 0; + +uncharge: + kfree(sk_storage); + atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc); + return err; +} + +/* sk cannot be going away because it is linking new elem + * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). + * Otherwise, it will become a leak (and other memory issues + * during map destruction). + */ +static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, + struct bpf_map *map, + void *value, + u64 map_flags) +{ + struct bpf_sk_storage_data *old_sdata = NULL; + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_map *smap; + int err; + + /* BPF_EXIST and BPF_NOEXIST cannot be both set */ + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || + /* BPF_F_LOCK can only be used in a value with spin_lock */ + unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + return ERR_PTR(-EINVAL); + + smap = (struct bpf_sk_storage_map *)map; + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage || hlist_empty(&sk_storage->list)) { + /* Very first elem for this sk */ + err = check_flags(NULL, map_flags); + if (err) + return ERR_PTR(err); + + selem = selem_alloc(smap, sk, value, true); + if (!selem) + return ERR_PTR(-ENOMEM); + + err = sk_storage_alloc(sk, smap, selem); + if (err) { + kfree(selem); + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + return ERR_PTR(err); + } + + return SDATA(selem); + } + + if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { + /* Hoping to find an old_sdata to do inline update + * such that it can avoid taking the sk_storage->lock + * and changing the lists. + */ + old_sdata = __sk_storage_lookup(sk_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + return ERR_PTR(err); + if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { + copy_map_value_locked(map, old_sdata->data, + value, false); + return old_sdata; + } + } + + raw_spin_lock_bh(&sk_storage->lock); + + /* Recheck sk_storage->list under sk_storage->lock */ + if (unlikely(hlist_empty(&sk_storage->list))) { + /* A parallel del is happening and sk_storage is going + * away. It has just been checked before, so very + * unlikely. Return instead of retry to keep things + * simple. + */ + err = -EAGAIN; + goto unlock_err; + } + + old_sdata = __sk_storage_lookup(sk_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + goto unlock_err; + + if (old_sdata && (map_flags & BPF_F_LOCK)) { + copy_map_value_locked(map, old_sdata->data, value, false); + selem = SELEM(old_sdata); + goto unlock; + } + + /* sk_storage->lock is held. Hence, we are sure + * we can unlink and uncharge the old_sdata successfully + * later. Hence, instead of charging the new selem now + * and then uncharge the old selem later (which may cause + * a potential but unnecessary charge failure), avoid taking + * a charge at all here (the "!old_sdata" check) and the + * old_sdata will not be uncharged later during __selem_unlink_sk(). + */ + selem = selem_alloc(smap, sk, value, !old_sdata); + if (!selem) { + err = -ENOMEM; + goto unlock_err; + } + + /* First, link the new selem to the map */ + selem_link_map(smap, selem); + + /* Second, link (and publish) the new selem to sk_storage */ + __selem_link_sk(sk_storage, selem); + + /* Third, remove old selem, SELEM(old_sdata) */ + if (old_sdata) { + selem_unlink_map(SELEM(old_sdata)); + __selem_unlink_sk(sk_storage, SELEM(old_sdata), false); + } + +unlock: + raw_spin_unlock_bh(&sk_storage->lock); + return SDATA(selem); + +unlock_err: + raw_spin_unlock_bh(&sk_storage->lock); + return ERR_PTR(err); +} + +static int sk_storage_delete(struct sock *sk, struct bpf_map *map) +{ + struct bpf_sk_storage_data *sdata; + + sdata = sk_storage_lookup(sk, map, false); + if (!sdata) + return -ENOENT; + + selem_unlink(SELEM(sdata)); + + return 0; +} + +/* Called by __sk_destruct() */ +void bpf_sk_storage_free(struct sock *sk) +{ + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage *sk_storage; + bool free_sk_storage = false; + struct hlist_node *n; + + rcu_read_lock(); + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage) { + rcu_read_unlock(); + return; + } + + /* Netiher the bpf_prog nor the bpf-map's syscall + * could be modifying the sk_storage->list now. + * Thus, no elem can be added-to or deleted-from the + * sk_storage->list by the bpf_prog or by the bpf-map's syscall. + * + * It is racing with bpf_sk_storage_map_free() alone + * when unlinking elem from the sk_storage->list and + * the map's bucket->list. + */ + raw_spin_lock_bh(&sk_storage->lock); + hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) { + /* Always unlink from map before unlinking from + * sk_storage. + */ + selem_unlink_map(selem); + free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + } + raw_spin_unlock_bh(&sk_storage->lock); + rcu_read_unlock(); + + if (free_sk_storage) + kfree_rcu(sk_storage, rcu); +} + +static void bpf_sk_storage_map_free(struct bpf_map *map) +{ + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage_map *smap; + struct bucket *b; + unsigned int i; + + smap = (struct bpf_sk_storage_map *)map; + + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the sk->sk_bpf_storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_sk_storage_elem, + map_node))) { + selem_unlink(selem); + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* bpf_sk_storage_free() may still need to access the map. + * e.g. bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exited immediately. + * + * However, the bpf_sk_storage_free() still needs to access + * the smap->elem_size to do the uncharging in + * __selem_unlink_sk(). + * + * Hence, wait another rcu grace period for the + * bpf_sk_storage_free() to finish. + */ + synchronize_rcu(); + + kvfree(smap->buckets); + kfree(map); +} + +static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) +{ + if (attr->map_flags != BPF_F_NO_PREALLOC || attr->max_entries || + attr->key_size != sizeof(int) || !attr->value_size || + /* Enforce BTF for userspace sk dumping */ + !attr->btf_key_type_id || !attr->btf_value_type_id) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->value_size >= KMALLOC_MAX_SIZE - + MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem) || + /* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ + attr->value_size > U16_MAX - sizeof(struct bpf_sk_storage_elem)) + return -E2BIG; + + return 0; +} + +static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_sk_storage_map *smap; + unsigned int i; + u32 nbuckets; + u64 cost; + + smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); + if (!smap) + return ERR_PTR(-ENOMEM); + bpf_map_init_from_attr(&smap->map, attr); + + smap->bucket_log = ilog2(roundup_pow_of_two(num_possible_cpus())); + nbuckets = 1U << smap->bucket_log; + smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, + GFP_USER | __GFP_NOWARN); + if (!smap->buckets) { + kfree(smap); + return ERR_PTR(-ENOMEM); + } + cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); + + for (i = 0; i < nbuckets; i++) { + INIT_HLIST_HEAD(&smap->buckets[i].list); + raw_spin_lock_init(&smap->buckets[i].lock); + } + + smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; + smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) % + BPF_SK_STORAGE_CACHE_SIZE; + smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + return &smap->map; +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -ENOTSUPP; +} + +static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + u32 int_data; + + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) + return -EINVAL; + + return 0; +} + +static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_sk_storage_data *sdata; + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + sdata = sk_storage_lookup(sock->sk, map, true); + sockfd_put(sock); + return sdata ? sdata->data : NULL; + } + + return ERR_PTR(err); +} + +static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_sk_storage_data *sdata; + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + sdata = sk_storage_update(sock->sk, map, value, map_flags); + sockfd_put(sock); + return IS_ERR(sdata) ? PTR_ERR(sdata) : 0; + } + + return err; +} + +static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + err = sk_storage_delete(sock->sk, map); + sockfd_put(sock); + return err; + } + + return err; +} + +BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, + void *, value, u64, flags) +{ + struct bpf_sk_storage_data *sdata; + + if (flags > BPF_SK_STORAGE_GET_F_CREATE) + return (unsigned long)NULL; + + sdata = sk_storage_lookup(sk, map, true); + if (sdata) + return (unsigned long)sdata->data; + + if (flags == BPF_SK_STORAGE_GET_F_CREATE && + /* Cannot add new elem to a going away sk. + * Otherwise, the new elem may become a leak + * (and also other memory issues during map + * destruction). + */ + refcount_inc_not_zero(&sk->sk_refcnt)) { + sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); + /* sk must be a fullsock (guaranteed by verifier), + * so sock_gen_put() is unnecessary. + */ + sock_put(sk); + return IS_ERR(sdata) ? + (unsigned long)NULL : (unsigned long)sdata->data; + } + + return (unsigned long)NULL; +} + +BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) +{ + if (refcount_inc_not_zero(&sk->sk_refcnt)) { + int err; + + err = sk_storage_delete(sk, map); + sock_put(sk); + return err; + } + + return -ENOENT; +} + +const struct bpf_map_ops sk_storage_map_ops = { + .map_alloc_check = bpf_sk_storage_map_alloc_check, + .map_alloc = bpf_sk_storage_map_alloc, + .map_free = bpf_sk_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, + .map_update_elem = bpf_fd_sk_storage_update_elem, + .map_delete_elem = bpf_fd_sk_storage_delete_elem, + .map_check_btf = bpf_sk_storage_map_check_btf, +}; + +const struct bpf_func_proto bpf_sk_storage_get_proto = { + .func = bpf_sk_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_SOCKET, + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_sk_storage_delete_proto = { + .func = bpf_sk_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_SOCKET, +}; diff --git a/net/core/filter.c b/net/core/filter.c index 9d28e7e8a4cb..55bfc941d17a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -75,6 +75,7 @@ #include <net/seg6_local.h> #include <net/lwtunnel.h> #include <net/ipv6_stubs.h> +#include <net/bpf_sk_storage.h> /** * sk_filter_trim_cap - run a packet through a socket filter @@ -1730,6 +1731,40 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_SIZE, }; +BPF_CALL_4(bpf_flow_dissector_load_bytes, + const struct bpf_flow_dissector *, ctx, u32, offset, + void *, to, u32, len) +{ + void *ptr; + + if (unlikely(offset > 0xffff)) + goto err_clear; + + if (unlikely(!ctx->skb)) + goto err_clear; + + ptr = skb_header_pointer(ctx->skb, offset, len, to); + if (unlikely(!ptr)) + goto err_clear; + if (ptr != to) + memcpy(to, ptr, len); + + return 0; +err_clear: + memset(to, 0, len); + return -EFAULT; +} + +static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { + .func = bpf_flow_dissector_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { @@ -3047,6 +3082,14 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, skb_set_transport_header(skb, mac_len + nh_len); } + + /* Match skb->protocol to new outer l3 protocol */ + if (skb->protocol == htons(ETH_P_IP) && + flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) + skb->protocol = htons(ETH_P_IPV6); + else if (skb->protocol == htons(ETH_P_IPV6) && + flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) + skb->protocol = htons(ETH_P_IP); } if (skb_is_gso(skb)) { @@ -5861,6 +5904,9 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +const struct bpf_func_proto bpf_sk_storage_get_proto __weak; +const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; + static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -5869,6 +5915,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_local_storage_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_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; @@ -5950,6 +6000,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_fib_lookup_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_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_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; @@ -6121,7 +6175,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: - return &bpf_skb_load_bytes_proto; + return &bpf_flow_dissector_load_bytes_proto; default: return bpf_base_func_proto(func_id); } @@ -6248,9 +6302,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): - if (size != sizeof(__u64)) - return false; - break; + return false; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; @@ -6285,7 +6337,6 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): @@ -6312,7 +6363,6 @@ static bool cg_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): @@ -6358,7 +6408,6 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; @@ -6601,7 +6650,6 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -6803,7 +6851,6 @@ static bool sk_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; @@ -6877,24 +6924,65 @@ static bool flow_dissector_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { + const int size_default = sizeof(__u32); + + if (off < 0 || off >= sizeof(struct __sk_buff)) + return false; + if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): + if (size != size_default) + return false; info->reg_type = PTR_TO_PACKET; - break; + return true; case bpf_ctx_range(struct __sk_buff, data_end): + if (size != size_default) + return false; info->reg_type = PTR_TO_PACKET_END; - break; + return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): + if (size != sizeof(__u64)) + return false; info->reg_type = PTR_TO_FLOW_KEYS; - break; + return true; default: return false; } +} - return bpf_skb_is_valid_access(off, size, type, prog, info); +static u32 flow_dissector_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; + + switch (si->off) { + case offsetof(struct __sk_buff, data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, data)); + break; + + case offsetof(struct __sk_buff, data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, data_end)); + break; + + case offsetof(struct __sk_buff, flow_keys): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, flow_keys)); + break; + } + + return insn - insn_buf; } static u32 bpf_convert_ctx_access(enum bpf_access_type type, @@ -7201,15 +7289,6 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, skc_num, 2, target_size)); break; - case offsetof(struct __sk_buff, flow_keys): - off = si->off; - off -= offsetof(struct __sk_buff, flow_keys); - off += offsetof(struct sk_buff, cb); - off += offsetof(struct qdisc_skb_cb, flow_keys); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, - si->src_reg, off); - break; - case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); @@ -8214,7 +8293,7 @@ const struct bpf_prog_ops sk_msg_prog_ops = { const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, - .convert_ctx_access = bpf_convert_ctx_access, + .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 795449713ba4..9ca784c592ac 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -65,6 +65,45 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); +int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + u32 prog_id, prog_cnt = 0, flags = 0; + struct bpf_prog *attached; + struct net *net; + + if (attr->query.query_flags) + return -EINVAL; + + net = get_net_ns_by_fd(attr->query.target_fd); + if (IS_ERR(net)) + return PTR_ERR(net); + + rcu_read_lock(); + attached = rcu_dereference(net->flow_dissector_prog); + if (attached) { + prog_cnt = 1; + prog_id = attached->aux->id; + } + rcu_read_unlock(); + + put_net(net); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + return -EFAULT; + + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + return 0; + + if (copy_to_user(prog_ids, &prog_id, sizeof(u32))) + return -EFAULT; + + return 0; +} + int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { @@ -683,50 +722,30 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, } } -bool __skb_flow_bpf_dissect(struct bpf_prog *prog, - const struct sk_buff *skb, - struct flow_dissector *flow_dissector, - struct bpf_flow_keys *flow_keys) +bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen) { - struct bpf_skb_data_end cb_saved; - struct bpf_skb_data_end *cb; + struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; - /* Note that even though the const qualifier is discarded - * throughout the execution of the BPF program, all changes(the - * control block) are reverted after the BPF program returns. - * Therefore, __skb_flow_dissect does not alter the skb. - */ - - cb = (struct bpf_skb_data_end *)skb->cb; - - /* Save Control Block */ - memcpy(&cb_saved, cb, sizeof(cb_saved)); - memset(cb, 0, sizeof(*cb)); - /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); - cb->qdisc_cb.flow_keys = flow_keys; - flow_keys->n_proto = skb->protocol; - flow_keys->nhoff = skb_network_offset(skb); + flow_keys->n_proto = proto; + flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; - bpf_compute_data_pointers((struct sk_buff *)skb); - result = BPF_PROG_RUN(prog, skb); + result = BPF_PROG_RUN(prog, ctx); - /* Restore state */ - memcpy(cb, &cb_saved, sizeof(cb_saved)); - - flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, - skb_network_offset(skb), skb->len); + flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, - flow_keys->nhoff, skb->len); + flow_keys->nhoff, hlen); return result == BPF_OK; } /** * __skb_flow_dissect - extract the flow_keys struct and return it + * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into @@ -743,7 +762,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, * * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, @@ -756,6 +776,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; + struct bpf_prog *attached = NULL; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; int num_hdrs = 0; @@ -798,22 +819,39 @@ bool __skb_flow_dissect(const struct sk_buff *skb, target_container); if (skb) { - struct bpf_flow_keys flow_keys; - struct bpf_prog *attached = NULL; + if (!net) { + if (skb->dev) + net = dev_net(skb->dev); + else if (skb->sk) + net = sock_net(skb->sk); + } + } + WARN_ON_ONCE(!net); + if (net) { rcu_read_lock(); - - if (skb->dev) - attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog); - else if (skb->sk) - attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog); - else - WARN_ON_ONCE(1); + attached = rcu_dereference(net->flow_dissector_prog); if (attached) { - ret = __skb_flow_bpf_dissect(attached, skb, - flow_dissector, - &flow_keys); + struct bpf_flow_keys flow_keys; + struct bpf_flow_dissector ctx = { + .flow_keys = &flow_keys, + .data = data, + .data_end = data + hlen, + }; + __be16 n_proto = proto; + + if (skb) { + ctx.skb = skb; + /* we can't use 'proto' in the skb case + * because it might be set to skb->vlan_proto + * which has been pulled from the data + */ + n_proto = skb->protocol; + } + + ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, + hlen); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); @@ -1410,8 +1448,8 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb) __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); - __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, - NULL, 0, 0, 0, + __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, + &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(&keys, hashrnd); @@ -1512,7 +1550,8 @@ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; - if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); diff --git a/net/core/sock.c b/net/core/sock.c index 925b84a872dd..75b1c950b49f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -137,6 +137,7 @@ #include <linux/filter.h> #include <net/sock_reuseport.h> +#include <net/bpf_sk_storage.h> #include <trace/events/sock.h> @@ -1709,6 +1710,10 @@ static void __sk_destruct(struct rcu_head *head) sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); +#ifdef CONFIG_BPF_SYSCALL + bpf_sk_storage_free(sk); +#endif + if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index f7a3d7a171c7..0f9863dc4d44 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -119,13 +119,14 @@ EXPORT_SYMBOL(eth_header); /** * eth_get_headlen - determine the length of header for an ethernet frame + * @dev: pointer to network device * @data: pointer to start of frame * @len: total length of frame * * Make a best effort attempt to pull the length for all of the headers for * a given frame in a linear buffer. */ -u32 eth_get_headlen(void *data, unsigned int len) +u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len) { const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG; const struct ethhdr *eth = (const struct ethhdr *)data; @@ -136,8 +137,9 @@ u32 eth_get_headlen(void *data, unsigned int len) return len; /* parse any remaining L2/L3 headers, check for L4 */ - if (!skb_flow_dissect_flow_keys_basic(NULL, &keys, data, eth->h_proto, - sizeof(*eth), len, flags)) + if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data, + eth->h_proto, sizeof(*eth), + len, flags)) return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore index 59e40998e249..c7498457595a 100644 --- a/samples/bpf/.gitignore +++ b/samples/bpf/.gitignore @@ -1,5 +1,6 @@ cpustat fds_example +hbm lathist lwt_len_hist map_perf_test diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst new file mode 100644 index 000000000000..2dbc1413fabd --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -0,0 +1,222 @@ +================ +bpftool-btf +================ +------------------------------------------------------------------------------- +tool for inspection of BTF data +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **btf** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMANDS* := { **dump** | **help** } + +BTF COMMANDS +============= + +| **bpftool** **btf dump** *BTF_SRC* +| **bpftool** **btf help** +| +| *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } + +DESCRIPTION +=========== + **bpftool btf dump** *BTF_SRC* + Dump BTF entries from a given *BTF_SRC*. + + When **id** is specified, BTF object with that ID will be + loaded and all its BTF types emitted. + + When **map** is provided, it's expected that map has + associated BTF object with BTF types describing key and + value. It's possible to select whether to dump only BTF + type(s) associated with key (**key**), value (**value**), + both key and value (**kv**), or all BTF types present in + associated BTF object (**all**). If not specified, **kv** + is assumed. + + When **prog** is provided, it's expected that program has + associated BTF object with BTF types. + + When specifying *FILE*, an ELF file is expected, containing + .BTF section with well-defined BTF binary format data, + typically produced by clang or pahole. + + **bpftool btf help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + +EXAMPLES +======== +**# bpftool btf dump id 1226** +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'dummy_tracepoint_args' size=16 vlen=2 + 'pad' type_id=3 bits_offset=0 + 'sock' type_id=4 bits_offset=64 + [3] INT 'long long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [4] PTR '(anon)' type_id=5 + [5] FWD 'sock' fwd_kind=union + +This gives an example of default output for all supported BTF kinds. + +**$ cat prog.c** +:: + + struct fwd_struct; + + enum my_enum { + VAL1 = 3, + VAL2 = 7, + }; + + typedef struct my_struct my_struct_t; + + struct my_struct { + const unsigned int const_int_field; + int bitfield_field: 4; + char arr_field[16]; + const struct fwd_struct *restrict fwd_field; + enum my_enum enum_field; + volatile my_struct_t *typedef_ptr_field; + }; + + union my_union { + int a; + struct my_struct b; + }; + + struct my_struct struct_global_var __attribute__((section("data_sec"))) = { + .bitfield_field = 3, + .enum_field = VAL1, + }; + int global_var __attribute__((section("data_sec"))) = 7; + + __attribute__((noinline)) + int my_func(union my_union *arg1, int arg2) + { + static int static_var __attribute__((section("data_sec"))) = 123; + static_var++; + return static_var; + } + +**$ bpftool btf dump file prog.o** +:: + + [1] PTR '(anon)' type_id=2 + [2] UNION 'my_union' size=48 vlen=2 + 'a' type_id=3 bits_offset=0 + 'b' type_id=4 bits_offset=0 + [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + [4] STRUCT 'my_struct' size=48 vlen=6 + 'const_int_field' type_id=5 bits_offset=0 + 'bitfield_field' type_id=3 bits_offset=32 bitfield_size=4 + 'arr_field' type_id=8 bits_offset=40 + 'fwd_field' type_id=10 bits_offset=192 + 'enum_field' type_id=14 bits_offset=256 + 'typedef_ptr_field' type_id=15 bits_offset=320 + [5] CONST '(anon)' type_id=6 + [6] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED + [8] ARRAY '(anon)' type_id=7 index_type_id=9 nr_elems=16 + [9] INT '__ARRAY_SIZE_TYPE__' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [10] RESTRICT '(anon)' type_id=11 + [11] PTR '(anon)' type_id=12 + [12] CONST '(anon)' type_id=13 + [13] FWD 'fwd_struct' fwd_kind=union + [14] ENUM 'my_enum' size=4 vlen=2 + 'VAL1' val=3 + 'VAL2' val=7 + [15] PTR '(anon)' type_id=16 + [16] VOLATILE '(anon)' type_id=17 + [17] TYPEDEF 'my_struct_t' type_id=4 + [18] FUNC_PROTO '(anon)' ret_type_id=3 vlen=2 + 'arg1' type_id=1 + 'arg2' type_id=3 + [19] FUNC 'my_func' type_id=18 + [20] VAR 'struct_global_var' type_id=4, linkage=global-alloc + [21] VAR 'global_var' type_id=3, linkage=global-alloc + [22] VAR 'my_func.static_var' type_id=3, linkage=static + [23] DATASEC 'data_sec' size=0 vlen=3 + type_id=20 offset=0 size=48 + type_id=21 offset=0 size=4 + type_id=22 offset=52 size=4 + +The following commands print BTF types associated with specified map's key, +value, both key and value, and all BTF types, respectively. By default, both +key and value types will be printed. + +**# bpftool btf dump map id 123 key** + +:: + + [39] TYPEDEF 'u32' type_id=37 + +**# bpftool btf dump map id 123 value** + +:: + + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 kv** + +:: + + [39] TYPEDEF 'u32' type_id=37 + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 all** + +:: + + [1] PTR '(anon)' type_id=0 + . + . + . + [2866] ARRAY '(anon)' type_id=52 index_type_id=51 nr_elems=4 + +All the standard ways to specify map or program are supported: + +**# bpftool btf dump map id 123** + +**# bpftool btf dump map pinned /sys/fs/bpf/map_name** + +**# bpftool btf dump prog id 456** + +**# bpftool btf dump prog tag b88e0a09b1d9759d** + +**# bpftool btf dump prog pinned /sys/fs/bpf/prog_name** + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 89b6b10e2183..ac26876389c2 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -145,4 +145,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 10177343b7ce..14180e887082 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -82,4 +82,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 55ecf80ca03e..13ef27b39f20 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -258,4 +258,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 6b692b428373..934580850f42 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -143,4 +143,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index 86154740fabb..0c7576523a21 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -85,4 +85,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-net**\ (8) + **bpftool-net**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 2f183ffd8351..e8118544d118 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -271,4 +271,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index deb2ca911ddf..3e562d7fd56f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -76,4 +76,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 9f3ffe1e26ab..50e402a5a9c8 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -217,6 +217,7 @@ _bpftool() done cur=${words[cword]} prev=${words[cword - 1]} + pprev=${words[cword - 2]} local object=${words[1]} command=${words[2]} @@ -272,17 +273,17 @@ _bpftool() "$cur" ) ) return 0 ;; - *) - _bpftool_once_attr 'file' - if _bpftool_search_list 'xlated'; then - COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ - "$cur" ) ) - else - COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ - "$cur" ) ) - fi - return 0 - ;; + *) + _bpftool_once_attr 'file' + if _bpftool_search_list 'xlated'; then + COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ + "$cur" ) ) + else + COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ + "$cur" ) ) + fi + return 0 + ;; esac ;; pin) @@ -607,6 +608,51 @@ _bpftool() ;; esac ;; + btf) + local PROG_TYPE='id pinned tag' + local MAP_TYPE='id pinned' + case $command in + dump) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id map prog file" -- \ + "$cur" ) ) + return 0 + ;; + prog) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + case $pprev in + prog) + _bpftool_get_prog_ids + ;; + map) + _bpftool_get_map_ids + ;; + esac + return 0 + ;; + *) + if [[ $cword == 6 ]] && [[ ${words[3]} == "map" ]]; then + COMPREPLY+=( $( compgen -W 'key value kv all' -- \ + "$cur" ) ) + fi + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'dump help' -- "$cur" ) ) + ;; + esac + ;; cgroup) case $command in show|list) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c new file mode 100644 index 000000000000..58a2cd002a4b --- /dev/null +++ b/tools/bpf/bpftool/btf.c @@ -0,0 +1,586 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <gelf.h> +#include <bpf.h> +#include <linux/btf.h> + +#include "btf.h" +#include "json_writer.h" +#include "main.h" + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", + [BTF_KIND_VAR] = "VAR", + [BTF_KIND_DATASEC] = "DATASEC", +}; + +static const char *btf_int_enc_str(__u8 encoding) +{ + switch (encoding) { + case 0: + return "(none)"; + case BTF_INT_SIGNED: + return "SIGNED"; + case BTF_INT_CHAR: + return "CHAR"; + case BTF_INT_BOOL: + return "BOOL"; + default: + return "UNKN"; + } +} + +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: + return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: + return "global-alloc"; + default: + return "(unknown)"; + } +} + +static const char *btf_str(const struct btf *btf, __u32 off) +{ + if (!off) + return "(anon)"; + return btf__name_by_offset(btf, off) ? : "(invalid)"; +} + +static int dump_btf_type(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + json_writer_t *w = json_wtr; + int kind, safe_kind; + + kind = BTF_INFO_KIND(t->info); + safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; + + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "id", id); + jsonw_string_field(w, "kind", btf_kind_str[safe_kind]); + jsonw_string_field(w, "name", btf_str(btf, t->name_off)); + } else { + printf("[%u] %s '%s'", id, btf_kind_str[safe_kind], + btf_str(btf, t->name_off)); + } + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: { + __u32 v = *(__u32 *)(t + 1); + const char *enc; + + enc = btf_int_enc_str(BTF_INT_ENCODING(v)); + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "bits_offset", BTF_INT_OFFSET(v)); + jsonw_uint_field(w, "nr_bits", BTF_INT_BITS(v)); + jsonw_string_field(w, "encoding", enc); + } else { + printf(" size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(v), BTF_INT_BITS(v), + enc); + } + break; + } + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *arr = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", arr->type); + jsonw_uint_field(w, "index_type_id", arr->index_type); + jsonw_uint_field(w, "nr_elems", arr->nelems); + } else { + printf(" type_id=%u index_type_id=%u nr_elems=%u", + arr->type, arr->index_type, arr->nelems); + } + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "members"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, m++) { + const char *name = btf_str(btf, m->name_off); + __u32 bit_off, bit_sz; + + if (BTF_INFO_KFLAG(t->info)) { + bit_off = BTF_MEMBER_BIT_OFFSET(m->offset); + bit_sz = BTF_MEMBER_BITFIELD_SIZE(m->offset); + } else { + bit_off = m->offset; + bit_sz = 0; + } + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", m->type); + jsonw_uint_field(w, "bits_offset", bit_off); + if (bit_sz) { + jsonw_uint_field(w, "bitfield_size", + bit_sz); + } + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u bits_offset=%u", + name, m->type, bit_off); + if (bit_sz) + printf(" bitfield_size=%u", bit_sz); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM: { + const struct btf_enum *v = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "val", v->val); + jsonw_end_object(w); + } else { + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_FWD: { + const char *fwd_kind = BTF_INFO_KIND(t->info) ? "union" + : "struct"; + + if (json_output) + jsonw_string_field(w, "fwd_kind", fwd_kind); + else + printf(" fwd_kind=%s", fwd_kind); + break; + } + case BTF_KIND_FUNC: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "ret_type_id", t->type); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "params"); + jsonw_start_array(w); + } else { + printf(" ret_type_id=%u vlen=%u", t->type, vlen); + } + for (i = 0; i < vlen; i++, p++) { + const char *name = btf_str(btf, p->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", p->type); + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u", name, p->type); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_VAR: { + const struct btf_var *v = (const void *)(t + 1); + const char *linkage; + + linkage = btf_var_linkage_str(v->linkage); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u, linkage=%s", t->type, linkage); + } + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = (const void *)(t+1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "vars"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "type_id", v->type); + jsonw_uint_field(w, "offset", v->offset); + jsonw_uint_field(w, "size", v->size); + jsonw_end_object(w); + } else { + printf("\n\ttype_id=%u offset=%u size=%u", + v->type, v->offset, v->size); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + default: + break; + } + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + return 0; +} + +static int dump_btf_raw(const struct btf *btf, + __u32 *root_type_ids, int root_type_cnt) +{ + const struct btf_type *t; + int i; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "types"); + jsonw_start_array(json_wtr); + } + + if (root_type_cnt) { + for (i = 0; i < root_type_cnt; i++) { + t = btf__type_by_id(btf, root_type_ids[i]); + dump_btf_type(btf, root_type_ids[i], t); + } + } else { + int cnt = btf__get_nr_types(btf); + + for (i = 1; i <= cnt; i++) { + t = btf__type_by_id(btf, i); + dump_btf_type(btf, i, t); + } + } + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_end_object(json_wtr); + } + return 0; +} + +static bool check_btf_endianness(GElf_Ehdr *ehdr) +{ + static unsigned int const endian = 1; + + switch (ehdr->e_ident[EI_DATA]) { + case ELFDATA2LSB: + return *(unsigned char const *)&endian == 1; + case ELFDATA2MSB: + return *(unsigned char const *)&endian == 0; + default: + return 0; + } +} + +static int btf_load_from_elf(const char *path, struct btf **btf) +{ + int err = -1, fd = -1, idx = 0; + Elf_Data *btf_data = NULL; + Elf_Scn *scn = NULL; + Elf *elf = NULL; + GElf_Ehdr ehdr; + + if (elf_version(EV_CURRENT) == EV_NONE) { + p_err("failed to init libelf for %s", path); + return -1; + } + + fd = open(path, O_RDONLY); + if (fd < 0) { + p_err("failed to open %s: %s", path, strerror(errno)); + return -1; + } + + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf) { + p_err("failed to open %s as ELF file", path); + goto done; + } + if (!gelf_getehdr(elf, &ehdr)) { + p_err("failed to get EHDR from %s", path); + goto done; + } + if (!check_btf_endianness(&ehdr)) { + p_err("non-native ELF endianness is not supported"); + goto done; + } + if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) { + p_err("failed to get e_shstrndx from %s\n", path); + goto done; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + p_err("failed to get section(%d) header from %s", + idx, path); + goto done; + } + name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!name) { + p_err("failed to get section(%d) name from %s", + idx, path); + goto done; + } + if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = elf_getdata(scn, 0); + if (!btf_data) { + p_err("failed to get section(%d, %s) data from %s", + idx, name, path); + goto done; + } + break; + } + } + + if (!btf_data) { + p_err("%s ELF section not found in %s", BTF_ELF_SEC, path); + goto done; + } + + *btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(*btf)) { + err = PTR_ERR(*btf); + *btf = NULL; + p_err("failed to load BTF data from %s: %s", + path, strerror(err)); + goto done; + } + + err = 0; +done: + if (err) { + if (*btf) { + btf__free(*btf); + *btf = NULL; + } + } + if (elf) + elf_end(elf); + close(fd); + return err; +} + +static int do_dump(int argc, char **argv) +{ + struct btf *btf = NULL; + __u32 root_type_ids[2]; + int root_type_cnt = 0; + __u32 btf_id = -1; + const char *src; + int fd = -1; + int err; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + src = GET_ARG(); + + if (is_prefix(src, "map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + btf_id = info.btf_id; + if (argc && is_prefix(*argv, "key")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "value")) { + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "all")) { + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "kv")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + } + } else if (is_prefix(src, "prog")) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + goto done; + } + + btf_id = info.btf_id; + } else if (is_prefix(src, "id")) { + char *endptr; + + btf_id = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(src, "file")) { + err = btf_load_from_elf(*argv, &btf); + if (err) + goto done; + NEXT_ARG(); + } else { + err = -1; + p_err("unrecognized BTF source specifier: '%s'", src); + goto done; + } + + if (!btf) { + err = btf__get_from_id(btf_id, &btf); + if (err) { + p_err("get btf by id (%u): %s", btf_id, strerror(err)); + goto done; + } + if (!btf) { + err = ENOENT; + p_err("can't find btf with ID (%u)", btf_id); + goto done; + } + } + + dump_btf_raw(btf, root_type_ids, root_type_cnt); + +done: + close(fd); + btf__free(btf); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s btf dump BTF_SRC\n" + " %s btf help\n" + "\n" + " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "help", do_help }, + { "dump", do_dump }, + { 0 } +}; + +int do_btf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index a9d5e9e6a732..1ac1fc520e6a 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -56,7 +56,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -188,6 +188,7 @@ static const struct cmd cmds[] = { { "perf", do_perf }, { "net", do_net }, { "feature", do_feature }, + { "btf", do_btf }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 1ccc46169a19..3d63feb7f852 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -150,6 +150,7 @@ int do_perf(int argc, char **arg); int do_net(int argc, char **arg); int do_tracelog(int argc, char **arg); int do_feature(int argc, char **argv); +int do_btf(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 10b6c9d3e525..e951d45c0131 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -46,6 +46,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", [BPF_MAP_TYPE_QUEUE] = "queue", [BPF_MAP_TYPE_STACK] = "stack", + [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -724,7 +725,7 @@ static int dump_map_elem(int fd, void *key, void *value, } else { const char *msg = NULL; - if (errno == ENOENT) + if (lookup_errno == ENOENT) msg = "<no entry>"; else if (lookup_errno == ENOSPC && map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index db0e7de49d49..67e99c56bc88 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> #include <stdlib.h> #include <string.h> #include <unistd.h> @@ -12,6 +13,8 @@ #include <linux/rtnetlink.h> #include <linux/tc_act/tc_bpf.h> #include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> #include <bpf.h> #include <nlattr.h> @@ -48,6 +51,10 @@ struct bpf_filter_t { int ifindex; }; +struct bpf_attach_info { + __u32 flow_dissector_id; +}; + static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) { struct bpf_netdev_t *netinfo = cookie; @@ -180,8 +187,45 @@ out: return 0; } +static int query_flow_dissector(struct bpf_attach_info *attach_info) +{ + __u32 attach_flags; + __u32 prog_ids[1]; + __u32 prog_cnt; + int err; + int fd; + + fd = open("/proc/self/ns/net", O_RDONLY); + if (fd < 0) { + p_err("can't open /proc/self/ns/net: %d", + strerror(errno)); + return -1; + } + prog_cnt = ARRAY_SIZE(prog_ids); + err = bpf_prog_query(fd, BPF_FLOW_DISSECTOR, 0, + &attach_flags, prog_ids, &prog_cnt); + close(fd); + if (err) { + if (errno == EINVAL) { + /* Older kernel's don't support querying + * flow dissector programs. + */ + errno = 0; + return 0; + } + p_err("can't query prog: %s", strerror(errno)); + return -1; + } + + if (prog_cnt == 1) + attach_info->flow_dissector_id = prog_ids[0]; + + return 0; +} + static int do_show(int argc, char **argv) { + struct bpf_attach_info attach_info = {}; int i, sock, ret, filter_idx = -1; struct bpf_netdev_t dev_array; unsigned int nl_pid; @@ -199,6 +243,10 @@ static int do_show(int argc, char **argv) usage(); } + ret = query_flow_dissector(&attach_info); + if (ret) + return -1; + sock = libbpf_netlink_open(&nl_pid); if (sock < 0) { fprintf(stderr, "failed to open netlink sock\n"); @@ -227,6 +275,12 @@ static int do_show(int argc, char **argv) } NET_END_ARRAY("\n"); } + + NET_START_ARRAY("flow_dissector", "%s:\n"); + if (attach_info.flow_dissector_id > 0) + NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); + NET_END_ARRAY("\n"); + NET_END_OBJECT; if (json_output) jsonw_end_array(json_wtr); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 704bb69514a2..72336bac7573 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -133,6 +133,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, }; /* Note that tracing related programs such as @@ -168,6 +169,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, }; enum bpf_attach_type { @@ -1737,12 +1739,19 @@ union bpf_attr { * error if an eBPF program tries to set a callback that is not * supported in the current kernel. * - * The supported callback values that *argval* can combine are: + * *argval* is a flag array which can combine these flags: * * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * * Here are some examples of where one could call such eBPF * program: * @@ -2622,6 +2631,42 @@ union bpf_attr { * was provided. * * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a sk. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem(map, &sk)** except this + * helper enforces the key must be a **bpf_fullsock()** + * and the map must be a BPF_MAP_TYPE_SK_STORAGE also. + * + * Underneath, the value is stored locally at *sk* instead of + * the map. The *map* is used as the bpf-local-storage **type**. + * The bpf-local-storage **type** (i.e. the *map*) is searched + * against all bpf-local-storages residing at sk. + * + * An optional *flags* (BPF_SK_STORAGE_GET_F_CREATE) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with BPF_SK_STORAGE_GET_F_CREATE to specify + * the initial value of a bpf-local-storage. If *value* is + * NULL, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a sk. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2730,7 +2775,9 @@ union bpf_attr { FN(sysctl_get_new_value), \ FN(sysctl_set_new_value), \ FN(strtol), \ - FN(strtoul), + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2806,6 +2853,9 @@ enum bpf_func_id { /* BPF_FUNC_sysctl_get_name flags. */ #define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) +/* BPF_FUNC_sk_storage_get flags */ +#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index ff2506fe6bd2..9593fec75652 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -26,6 +26,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <stddef.h> +#include <stdint.h> #ifdef __cplusplus extern "C" { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d817bf20f3d6..11a65db4b93f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -126,6 +126,8 @@ static inline __u64 ptr_to_u64(const void *ptr) struct bpf_capabilities { /* v4.14: kernel support for program & map names. */ __u32 name:1; + /* v5.2: kernel support for global data sections. */ + __u32 global_data:1; }; /* @@ -854,12 +856,15 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - 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++; + 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++) { GElf_Sym sym; @@ -870,14 +875,14 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) nr_maps++; } - /* Alloc obj->maps and fill nr_maps. */ - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); 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 " @@ -971,6 +976,9 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_idx++; } + if (!obj->caps.global_data) + goto finalize; + /* * Populate rest of obj->maps with libbpf internal maps. */ @@ -988,6 +996,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], LIBBPF_MAP_BSS, obj->efile.bss, NULL); +finalize: if (!ret) qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); @@ -1333,11 +1342,17 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, if (bpf_object__shndx_is_maps(obj, shdr_idx) || bpf_object__shndx_is_data(obj, shdr_idx)) { type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); - if (type != LIBBPF_MAP_UNSPEC && - GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { - pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", - name, insn_idx, insns[insn_idx].code); - return -LIBBPF_ERRNO__RELOC; + if (type != LIBBPF_MAP_UNSPEC) { + if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { + pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", + name, insn_idx, insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } + if (!obj->caps.global_data) { + pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", + name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } } for (map_idx = 0; map_idx < nr_maps; map_idx++) { @@ -1496,9 +1511,67 @@ bpf_object__probe_name(struct bpf_object *obj) } static int +bpf_object__probe_global_data(struct bpf_object *obj) +{ + struct bpf_load_program_attr prg_attr; + struct bpf_create_map_attr map_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map; + + memset(&map_attr, 0, sizeof(map_attr)); + map_attr.map_type = BPF_MAP_TYPE_ARRAY; + map_attr.key_size = sizeof(int); + map_attr.value_size = 32; + map_attr.max_entries = 1; + + map = bpf_create_map_xattr(&map_attr); + if (map < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, errno); + return -errno; + } + + insns[0].imm = map; + + memset(&prg_attr, 0, sizeof(prg_attr)); + prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + prg_attr.insns = insns; + prg_attr.insns_cnt = ARRAY_SIZE(insns); + prg_attr.license = "GPL"; + + ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + if (ret >= 0) { + obj->caps.global_data = 1; + close(ret); + } + + close(map); + return 0; +} + +static int bpf_object__probe_caps(struct bpf_object *obj) { - return bpf_object__probe_name(obj); + int (*probe_fn[])(struct bpf_object *obj) = { + bpf_object__probe_name, + bpf_object__probe_global_data, + }; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(probe_fn); i++) { + ret = probe_fn[i](obj); + if (ret < 0) + return ret; + } + + return 0; } static int @@ -2063,6 +2136,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) case BPF_PROG_TYPE_UNSPEC: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_CGROUP_SYSCTL: return false; @@ -2100,6 +2174,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, CHECK_ERR(bpf_object__elf_init(obj), err, out); CHECK_ERR(bpf_object__check_endianness(obj), err, out); + CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); @@ -2193,7 +2268,6 @@ int bpf_object__load(struct bpf_object *obj) obj->loaded = true; - CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__create_maps(obj), err, out); CHECK_ERR(bpf_object__relocate(obj), err, out); CHECK_ERR(bpf_object__load_progs(obj), err, out); diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 0f25541632e3..a2c64a9ce1a6 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -9,6 +9,7 @@ #include <net/if.h> #include <sys/utsname.h> +#include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> @@ -93,6 +94,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_SK_REUSEPORT: @@ -130,11 +132,65 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) return errno != EINVAL && errno != EOPNOTSUPP; } +static int load_btf(void) +{ +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) + + const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; + /* struct bpf_spin_lock { + * int val; + * }; + * struct val { + * int cnt; + * struct bpf_spin_lock l; + * }; + */ + __u32 btf_raw_types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + struct btf_header btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(btf_raw_types), + .str_off = sizeof(btf_raw_types), + .str_len = sizeof(btf_str_sec), + }; + __u8 raw_btf[sizeof(struct btf_header) + sizeof(btf_raw_types) + + sizeof(btf_str_sec)]; + + memcpy(raw_btf, &btf_hdr, sizeof(btf_hdr)); + memcpy(raw_btf + sizeof(btf_hdr), btf_raw_types, sizeof(btf_raw_types)); + memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types), + btf_str_sec, sizeof(btf_str_sec)); + + return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0); +} + bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) { int key_size, value_size, max_entries, map_flags; + __u32 btf_key_type_id = 0, btf_value_type_id = 0; struct bpf_create_map_attr attr = {}; - int fd = -1, fd_inner; + int fd = -1, btf_fd = -1, fd_inner; key_size = sizeof(__u32); value_size = sizeof(__u32); @@ -160,6 +216,16 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_STACK: key_size = 0; break; + case BPF_MAP_TYPE_SK_STORAGE: + btf_key_type_id = 1; + btf_value_type_id = 3; + value_size = 8; + max_entries = 0; + map_flags = BPF_F_NO_PREALLOC; + btf_fd = load_btf(); + if (btf_fd < 0) + return false; + break; case BPF_MAP_TYPE_UNSPEC: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: @@ -205,11 +271,18 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) attr.max_entries = max_entries; attr.map_flags = map_flags; attr.map_ifindex = ifindex; + if (btf_fd >= 0) { + attr.btf_fd = btf_fd; + attr.btf_key_type_id = btf_key_type_id; + attr.btf_value_type_id = btf_value_type_id; + } fd = bpf_create_map_xattr(&attr); } if (fd >= 0) close(fd); + if (btf_fd >= 0) + close(btf_fd); return fd >= 0; } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f9d83ba7843e..66f2dca1dee1 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -74,6 +74,8 @@ all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c $(CC) -o $@ $< -Wl,--build-id +$(OUTPUT)/test_maps: map_tests/*.c + BPFOBJ := $(OUTPUT)/libbpf.a $(TEST_GEN_PROGS): $(BPFOBJ) @@ -232,6 +234,27 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) echo '#endif' \ ) > $(PROG_TESTS_H)) +TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) +MAP_TESTS_DIR = $(OUTPUT)/map_tests +$(MAP_TESTS_DIR): + mkdir -p $@ +MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h +test_maps.c: $(MAP_TESTS_H) +$(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS) +MAP_TESTS_FILES := $(wildcard map_tests/*.c) +$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES) + $(shell ( cd map_tests/; \ + echo '/* Generated header, do not edit */'; \ + echo '#ifdef DECLARE'; \ + ls *.c 2> /dev/null | \ + sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \ + echo '#endif'; \ + echo '#ifdef CALL'; \ + ls *.c 2> /dev/null | \ + sed -e 's@\([^\.]*\)\.c@test_\1();@'; \ + echo '#endif' \ + ) > $(MAP_TESTS_H)) + VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h test_verifier.c: $(VERIFIER_TESTS_H) $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) @@ -251,4 +274,4 @@ $(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) + $(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 59e221586cf7..6e80b66d7fb1 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -211,6 +211,11 @@ static int (*bpf_strtol)(const char *buf, unsigned long long buf_len, static int (*bpf_strtoul)(const char *buf, unsigned long long buf_len, unsigned long long flags, unsigned long *res) = (void *) BPF_FUNC_strtoul; +static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk, + void *value, __u64 flags) = + (void *) BPF_FUNC_sk_storage_get; +static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) = + (void *)BPF_FUNC_sk_storage_delete; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 8c976476f6fd..f7a0744db31e 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -33,3 +33,4 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_IPV6_SIT=m diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c index 7136ab9ffa73..3fd83b9dc1bf 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.c +++ b/tools/testing/selftests/bpf/flow_dissector_load.c @@ -26,7 +26,7 @@ static void load_and_attach_program(void) struct bpf_object *obj; ret = bpf_flow_load(&obj, cfg_path_name, cfg_section_name, - cfg_map_name, &prog_fd); + cfg_map_name, NULL, &prog_fd, NULL); if (ret) error(1, 0, "bpf_flow_load %s", cfg_path_name); diff --git a/tools/testing/selftests/bpf/flow_dissector_load.h b/tools/testing/selftests/bpf/flow_dissector_load.h index 41dd6959feb0..daeaeb518894 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.h +++ b/tools/testing/selftests/bpf/flow_dissector_load.h @@ -9,10 +9,12 @@ static inline int bpf_flow_load(struct bpf_object **obj, const char *path, const char *section_name, const char *map_name, - int *prog_fd) + const char *keys_map_name, + int *prog_fd, + int *keys_fd) { struct bpf_program *prog, *main_prog; - struct bpf_map *prog_array; + struct bpf_map *prog_array, *keys; int prog_array_fd; int ret, fd, i; @@ -23,19 +25,29 @@ static inline int bpf_flow_load(struct bpf_object **obj, main_prog = bpf_object__find_program_by_title(*obj, section_name); if (!main_prog) - return ret; + return -1; *prog_fd = bpf_program__fd(main_prog); if (*prog_fd < 0) - return ret; + return -1; prog_array = bpf_object__find_map_by_name(*obj, map_name); if (!prog_array) - return ret; + return -1; prog_array_fd = bpf_map__fd(prog_array); if (prog_array_fd < 0) - return ret; + return -1; + + if (keys_map_name && keys_fd) { + keys = bpf_object__find_map_by_name(*obj, keys_map_name); + if (!keys) + return -1; + + *keys_fd = bpf_map__fd(keys); + if (*keys_fd < 0) + return -1; + } i = 0; bpf_object__for_each_program(prog, *obj) { diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c new file mode 100644 index 000000000000..e569edc679d8 --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c @@ -0,0 +1,629 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/compiler.h> +#include <linux/err.h> + +#include <sys/resource.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <linux/btf.h> +#include <unistd.h> +#include <signal.h> +#include <errno.h> +#include <string.h> +#include <pthread.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <test_btf.h> +#include <test_maps.h> + +static struct bpf_create_map_attr xattr = { + .name = "sk_storage_map", + .map_type = BPF_MAP_TYPE_SK_STORAGE, + .map_flags = BPF_F_NO_PREALLOC, + .max_entries = 0, + .key_size = 4, + .value_size = 8, + .btf_key_type_id = 1, + .btf_value_type_id = 3, + .btf_fd = -1, +}; + +static unsigned int nr_sk_threads_done; +static unsigned int nr_sk_threads_err; +static unsigned int nr_sk_per_thread = 4096; +static unsigned int nr_sk_threads = 4; +static int sk_storage_map = -1; +static unsigned int stop; +static int runtime_s = 5; + +static bool is_stopped(void) +{ + return READ_ONCE(stop); +} + +static unsigned int threads_err(void) +{ + return READ_ONCE(nr_sk_threads_err); +} + +static void notify_thread_err(void) +{ + __sync_add_and_fetch(&nr_sk_threads_err, 1); +} + +static bool wait_for_threads_err(void) +{ + while (!is_stopped() && !threads_err()) + usleep(500); + + return !is_stopped(); +} + +static unsigned int threads_done(void) +{ + return READ_ONCE(nr_sk_threads_done); +} + +static void notify_thread_done(void) +{ + __sync_add_and_fetch(&nr_sk_threads_done, 1); +} + +static void notify_thread_redo(void) +{ + __sync_sub_and_fetch(&nr_sk_threads_done, 1); +} + +static bool wait_for_threads_done(void) +{ + while (threads_done() != nr_sk_threads && !is_stopped() && + !threads_err()) + usleep(50); + + return !is_stopped() && !threads_err(); +} + +static bool wait_for_threads_redo(void) +{ + while (threads_done() && !is_stopped() && !threads_err()) + usleep(50); + + return !is_stopped() && !threads_err(); +} + +static bool wait_for_map(void) +{ + while (READ_ONCE(sk_storage_map) == -1 && !is_stopped()) + usleep(50); + + return !is_stopped(); +} + +static bool wait_for_map_close(void) +{ + while (READ_ONCE(sk_storage_map) != -1 && !is_stopped()) + ; + + return !is_stopped(); +} + +static int load_btf(void) +{ + const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; + __u32 btf_raw_types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + struct btf_header btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(btf_raw_types), + .str_off = sizeof(btf_raw_types), + .str_len = sizeof(btf_str_sec), + }; + __u8 raw_btf[sizeof(struct btf_header) + sizeof(btf_raw_types) + + sizeof(btf_str_sec)]; + + memcpy(raw_btf, &btf_hdr, sizeof(btf_hdr)); + memcpy(raw_btf + sizeof(btf_hdr), btf_raw_types, sizeof(btf_raw_types)); + memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types), + btf_str_sec, sizeof(btf_str_sec)); + + return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0); +} + +static int create_sk_storage_map(void) +{ + int btf_fd, map_fd; + + btf_fd = load_btf(); + CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", + btf_fd, errno); + xattr.btf_fd = btf_fd; + + map_fd = bpf_create_map_xattr(&xattr); + xattr.btf_fd = -1; + close(btf_fd); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "errno:%d\n", errno); + + return map_fd; +} + +static void *insert_close_thread(void *arg) +{ + struct { + int cnt; + int lock; + } value = { .cnt = 0xeB9F, .lock = 0, }; + int i, map_fd, err, *sk_fds; + + sk_fds = malloc(sizeof(*sk_fds) * nr_sk_per_thread); + if (!sk_fds) { + notify_thread_err(); + return ERR_PTR(-ENOMEM); + } + + for (i = 0; i < nr_sk_per_thread; i++) + sk_fds[i] = -1; + + while (!is_stopped()) { + if (!wait_for_map()) + goto close_all; + + map_fd = READ_ONCE(sk_storage_map); + for (i = 0; i < nr_sk_per_thread && !is_stopped(); i++) { + sk_fds[i] = socket(AF_INET6, SOCK_STREAM, 0); + if (sk_fds[i] == -1) { + err = -errno; + fprintf(stderr, "socket(): errno:%d\n", errno); + goto errout; + } + err = bpf_map_update_elem(map_fd, &sk_fds[i], &value, + BPF_NOEXIST); + if (err) { + err = -errno; + fprintf(stderr, + "bpf_map_update_elem(): errno:%d\n", + errno); + goto errout; + } + } + + notify_thread_done(); + wait_for_map_close(); + +close_all: + for (i = 0; i < nr_sk_per_thread; i++) { + close(sk_fds[i]); + sk_fds[i] = -1; + } + + notify_thread_redo(); + } + + free(sk_fds); + return NULL; + +errout: + for (i = 0; i < nr_sk_per_thread && sk_fds[i] != -1; i++) + close(sk_fds[i]); + free(sk_fds); + notify_thread_err(); + return ERR_PTR(err); +} + +static int do_sk_storage_map_stress_free(void) +{ + int i, map_fd = -1, err = 0, nr_threads_created = 0; + pthread_t *sk_thread_ids; + void *thread_ret; + + sk_thread_ids = malloc(sizeof(pthread_t) * nr_sk_threads); + if (!sk_thread_ids) { + fprintf(stderr, "malloc(sk_threads): NULL\n"); + return -ENOMEM; + } + + for (i = 0; i < nr_sk_threads; i++) { + err = pthread_create(&sk_thread_ids[i], NULL, + insert_close_thread, NULL); + if (err) { + err = -errno; + goto done; + } + nr_threads_created++; + } + + while (!is_stopped()) { + map_fd = create_sk_storage_map(); + WRITE_ONCE(sk_storage_map, map_fd); + + if (!wait_for_threads_done()) + break; + + WRITE_ONCE(sk_storage_map, -1); + close(map_fd); + map_fd = -1; + + if (!wait_for_threads_redo()) + break; + } + +done: + WRITE_ONCE(stop, 1); + for (i = 0; i < nr_threads_created; i++) { + pthread_join(sk_thread_ids[i], &thread_ret); + if (IS_ERR(thread_ret) && !err) { + err = PTR_ERR(thread_ret); + fprintf(stderr, "threads#%u: err:%d\n", i, err); + } + } + free(sk_thread_ids); + + if (map_fd != -1) + close(map_fd); + + return err; +} + +static void *update_thread(void *arg) +{ + struct { + int cnt; + int lock; + } value = { .cnt = 0xeB9F, .lock = 0, }; + int map_fd = READ_ONCE(sk_storage_map); + int sk_fd = *(int *)arg; + int err = 0; /* Suppress compiler false alarm */ + + while (!is_stopped()) { + err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0); + if (err && errno != EAGAIN) { + err = -errno; + fprintf(stderr, "bpf_map_update_elem: %d %d\n", + err, errno); + break; + } + } + + if (!is_stopped()) { + notify_thread_err(); + return ERR_PTR(err); + } + + return NULL; +} + +static void *delete_thread(void *arg) +{ + int map_fd = READ_ONCE(sk_storage_map); + int sk_fd = *(int *)arg; + int err = 0; /* Suppress compiler false alarm */ + + while (!is_stopped()) { + err = bpf_map_delete_elem(map_fd, &sk_fd); + if (err && errno != ENOENT) { + err = -errno; + fprintf(stderr, "bpf_map_delete_elem: %d %d\n", + err, errno); + break; + } + } + + if (!is_stopped()) { + notify_thread_err(); + return ERR_PTR(err); + } + + return NULL; +} + +static int do_sk_storage_map_stress_change(void) +{ + int i, sk_fd, map_fd = -1, err = 0, nr_threads_created = 0; + pthread_t *sk_thread_ids; + void *thread_ret; + + sk_thread_ids = malloc(sizeof(pthread_t) * nr_sk_threads); + if (!sk_thread_ids) { + fprintf(stderr, "malloc(sk_threads): NULL\n"); + return -ENOMEM; + } + + sk_fd = socket(AF_INET6, SOCK_STREAM, 0); + if (sk_fd == -1) { + err = -errno; + goto done; + } + + map_fd = create_sk_storage_map(); + WRITE_ONCE(sk_storage_map, map_fd); + + for (i = 0; i < nr_sk_threads; i++) { + if (i & 0x1) + err = pthread_create(&sk_thread_ids[i], NULL, + update_thread, &sk_fd); + else + err = pthread_create(&sk_thread_ids[i], NULL, + delete_thread, &sk_fd); + if (err) { + err = -errno; + goto done; + } + nr_threads_created++; + } + + wait_for_threads_err(); + +done: + WRITE_ONCE(stop, 1); + for (i = 0; i < nr_threads_created; i++) { + pthread_join(sk_thread_ids[i], &thread_ret); + if (IS_ERR(thread_ret) && !err) { + err = PTR_ERR(thread_ret); + fprintf(stderr, "threads#%u: err:%d\n", i, err); + } + } + free(sk_thread_ids); + + if (sk_fd != -1) + close(sk_fd); + close(map_fd); + + return err; +} + +static void stop_handler(int signum) +{ + if (signum != SIGALRM) + printf("stopping...\n"); + WRITE_ONCE(stop, 1); +} + +#define BPF_SK_STORAGE_MAP_TEST_NR_THREADS "BPF_SK_STORAGE_MAP_TEST_NR_THREADS" +#define BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD "BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD" +#define BPF_SK_STORAGE_MAP_TEST_RUNTIME_S "BPF_SK_STORAGE_MAP_TEST_RUNTIME_S" +#define BPF_SK_STORAGE_MAP_TEST_NAME "BPF_SK_STORAGE_MAP_TEST_NAME" + +static void test_sk_storage_map_stress_free(void) +{ + struct rlimit rlim_old, rlim_new = {}; + int err; + + getrlimit(RLIMIT_NOFILE, &rlim_old); + + signal(SIGTERM, stop_handler); + signal(SIGINT, stop_handler); + if (runtime_s > 0) { + signal(SIGALRM, stop_handler); + alarm(runtime_s); + } + + if (rlim_old.rlim_cur < nr_sk_threads * nr_sk_per_thread) { + rlim_new.rlim_cur = nr_sk_threads * nr_sk_per_thread + 128; + rlim_new.rlim_max = rlim_new.rlim_cur + 128; + err = setrlimit(RLIMIT_NOFILE, &rlim_new); + CHECK(err, "setrlimit(RLIMIT_NOFILE)", "rlim_new:%lu errno:%d", + rlim_new.rlim_cur, errno); + } + + err = do_sk_storage_map_stress_free(); + + signal(SIGTERM, SIG_DFL); + signal(SIGINT, SIG_DFL); + if (runtime_s > 0) { + signal(SIGALRM, SIG_DFL); + alarm(0); + } + + if (rlim_new.rlim_cur) + setrlimit(RLIMIT_NOFILE, &rlim_old); + + CHECK(err, "test_sk_storage_map_stress_free", "err:%d\n", err); +} + +static void test_sk_storage_map_stress_change(void) +{ + int err; + + signal(SIGTERM, stop_handler); + signal(SIGINT, stop_handler); + if (runtime_s > 0) { + signal(SIGALRM, stop_handler); + alarm(runtime_s); + } + + err = do_sk_storage_map_stress_change(); + + signal(SIGTERM, SIG_DFL); + signal(SIGINT, SIG_DFL); + if (runtime_s > 0) { + signal(SIGALRM, SIG_DFL); + alarm(0); + } + + CHECK(err, "test_sk_storage_map_stress_change", "err:%d\n", err); +} + +static void test_sk_storage_map_basic(void) +{ + struct { + int cnt; + int lock; + } value = { .cnt = 0xeB9f, .lock = 0, }, lookup_value; + struct bpf_create_map_attr bad_xattr; + int btf_fd, map_fd, sk_fd, err; + + btf_fd = load_btf(); + CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", + btf_fd, errno); + xattr.btf_fd = btf_fd; + + sk_fd = socket(AF_INET6, SOCK_STREAM, 0); + CHECK(sk_fd == -1, "socket()", "sk_fd:%d errno:%d\n", + sk_fd, errno); + + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, "bpf_create_map_xattr(good_xattr)", + "map_fd:%d errno:%d\n", map_fd, errno); + + /* Add new elem */ + memcpy(&lookup_value, &value, sizeof(value)); + err = bpf_map_update_elem(map_fd, &sk_fd, &value, + BPF_NOEXIST | BPF_F_LOCK); + CHECK(err, "bpf_map_update_elem(BPF_NOEXIST|BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Bump the cnt and update with BPF_EXIST | BPF_F_LOCK */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, + BPF_EXIST | BPF_F_LOCK); + CHECK(err, "bpf_map_update_elem(BPF_EXIST|BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Bump the cnt and update with BPF_EXIST */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_EXIST); + CHECK(err, "bpf_map_update_elem(BPF_EXIST)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Update with BPF_NOEXIST */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, + BPF_NOEXIST | BPF_F_LOCK); + CHECK(!err || errno != EEXIST, + "bpf_map_update_elem(BPF_NOEXIST|BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_NOEXIST); + CHECK(!err || errno != EEXIST, "bpf_map_update_elem(BPF_NOEXIST)", + "err:%d errno:%d\n", err, errno); + value.cnt -= 1; + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Bump the cnt again and update with map_flags == 0 */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0); + CHECK(err, "bpf_map_update_elem()", "err:%d errno:%d\n", + err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Test delete elem */ + err = bpf_map_delete_elem(map_fd, &sk_fd); + CHECK(err, "bpf_map_delete_elem()", "err:%d errno:%d\n", + err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(!err || errno != ENOENT, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_delete_elem(map_fd, &sk_fd); + CHECK(!err || errno != ENOENT, "bpf_map_delete_elem()", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.btf_key_type_id = 0; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.btf_key_type_id = 3; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.max_entries = 1; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.map_flags = 0; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + xattr.btf_fd = -1; + close(btf_fd); + close(map_fd); + close(sk_fd); +} + +void test_sk_storage_map(void) +{ + const char *test_name, *env_opt; + bool test_ran = false; + + test_name = getenv(BPF_SK_STORAGE_MAP_TEST_NAME); + + env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_NR_THREADS); + if (env_opt) + nr_sk_threads = atoi(env_opt); + + env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD); + if (env_opt) + nr_sk_per_thread = atoi(env_opt); + + env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_RUNTIME_S); + if (env_opt) + runtime_s = atoi(env_opt); + + if (!test_name || !strcmp(test_name, "basic")) { + test_sk_storage_map_basic(); + test_ran = true; + } + if (!test_name || !strcmp(test_name, "stress_free")) { + test_sk_storage_map_stress_free(); + test_ran = true; + } + if (!test_name || !strcmp(test_name, "stress_change")) { + test_sk_storage_map_stress_change(); + test_ran = true; + } + + if (test_ran) + printf("%s:PASS\n", __func__); + else + CHECK(1, "Invalid test_name", "%s\n", test_name); +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 126319f9a97c..8b54adfd6264 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <error.h> +#include <linux/if.h> +#include <linux/if_tun.h> #define CHECK_FLOW_KEYS(desc, got, expected) \ CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ @@ -79,8 +82,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = 0, - .thoff = sizeof(struct iphdr), + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), @@ -95,8 +98,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = 0, - .thoff = sizeof(struct ipv6hdr), + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), @@ -113,8 +116,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = VLAN_HLEN, - .thoff = VLAN_HLEN + sizeof(struct iphdr), + .nhoff = ETH_HLEN + VLAN_HLEN, + .thoff = ETH_HLEN + VLAN_HLEN + sizeof(struct iphdr), .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), @@ -131,8 +134,9 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = VLAN_HLEN * 2, - .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), + .nhoff = ETH_HLEN + VLAN_HLEN * 2, + .thoff = ETH_HLEN + VLAN_HLEN * 2 + + sizeof(struct ipv6hdr), .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), @@ -140,13 +144,73 @@ struct test tests[] = { }, }; +static int create_tap(const char *ifname) +{ + struct ifreq ifr = { + .ifr_flags = IFF_TAP | IFF_NO_PI | IFF_NAPI | IFF_NAPI_FRAGS, + }; + int fd, ret; + + strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + + fd = open("/dev/net/tun", O_RDWR); + if (fd < 0) + return -1; + + ret = ioctl(fd, TUNSETIFF, &ifr); + if (ret) + return -1; + + return fd; +} + +static int tx_tap(int fd, void *pkt, size_t len) +{ + struct iovec iov[] = { + { + .iov_len = len, + .iov_base = pkt, + }, + }; + return writev(fd, iov, ARRAY_SIZE(iov)); +} + +static int ifup(const char *ifname) +{ + struct ifreq ifr = {}; + int sk, ret; + + strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + + sk = socket(PF_INET, SOCK_DGRAM, 0); + if (sk < 0) + return -1; + + ret = ioctl(sk, SIOCGIFFLAGS, &ifr); + if (ret) { + close(sk); + return -1; + } + + ifr.ifr_flags |= IFF_UP; + ret = ioctl(sk, SIOCSIFFLAGS, &ifr); + if (ret) { + close(sk); + return -1; + } + + close(sk); + return 0; +} + void test_flow_dissector(void) { + int i, err, prog_fd, keys_fd = -1, tap_fd; struct bpf_object *obj; - int i, err, prog_fd; + __u32 duration = 0; err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector", - "jmp_table", &prog_fd); + "jmp_table", "last_dissection", &prog_fd, &keys_fd); if (err) { error_cnt++; return; @@ -171,5 +235,34 @@ void test_flow_dissector(void) CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); } + /* Do the same tests but for skb-less flow dissector. + * We use a known path in the net/tun driver that calls + * eth_get_headlen and we manually export bpf_flow_keys + * via BPF map in this case. + */ + + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + CHECK(err, "bpf_prog_attach", "err %d errno %d", err, errno); + + tap_fd = create_tap("tap0"); + CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d", tap_fd, errno); + err = ifup("tap0"); + CHECK(err, "ifup", "err %d errno %d", err, errno); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + struct bpf_flow_keys flow_keys = {}; + struct bpf_prog_test_run_attr tattr = {}; + __u32 key = 0; + + err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); + CHECK(err < 0, "tx_tap", "err %d errno %d", err, errno); + + err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); + CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err); + + CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); + CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + } + bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c new file mode 100644 index 000000000000..dc5ef155ec28 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_flow_dissector_load_bytes(void) +{ + struct bpf_flow_keys flow_keys; + __u32 duration = 0, retval, size; + struct bpf_insn prog[] = { + // BPF_REG_1 - 1st argument: context + // BPF_REG_2 - 2nd argument: offset, start at first byte + BPF_MOV64_IMM(BPF_REG_2, 0), + // BPF_REG_3 - 3rd argument: destination, reserve byte on stack + BPF_ALU64_REG(BPF_MOV, BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -1), + // BPF_REG_4 - 4th argument: copy one byte + BPF_MOV64_IMM(BPF_REG_4, 1), + // bpf_skb_load_bytes(ctx, sizeof(pkt_v4), ptr, 1) + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + // if (ret == 0) return BPF_DROP (2) + BPF_MOV64_IMM(BPF_REG_0, BPF_DROP), + BPF_EXIT_INSN(), + // if (ret != 0) return BPF_OK (0) + BPF_MOV64_IMM(BPF_REG_0, BPF_OK), + BPF_EXIT_INSN(), + }; + int fd, err; + + /* make sure bpf_skb_load_bytes is not allowed from skb-less context + */ + fd = bpf_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, + ARRAY_SIZE(prog), "GPL", 0, NULL, 0); + CHECK(fd < 0, + "flow_dissector-bpf_skb_load_bytes-load", + "fd %d errno %d\n", + fd, errno); + + err = bpf_prog_test_run(fd, 1, &pkt_v4, sizeof(pkt_v4), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, + "flow_dissector-bpf_skb_load_bytes", + "err %d errno %d retval %d duration %d size %u/%zu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + + if (fd >= -1) + close(fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c new file mode 100644 index 000000000000..9807336a3016 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <linux/nbd.h> + +void test_raw_tp_writable_reject_nbd_invalid(void) +{ + __u32 duration = 0; + char error[4096]; + int bpf_fd = -1, tp_fd = -1; + + const struct bpf_insn program[] = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* one byte beyond the end of the nbd_request struct */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, + sizeof(struct nbd_request)), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr load_attr = { + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .license = "GPL v2", + .insns = program, + .insns_cnt = sizeof(program) / sizeof(struct bpf_insn), + .log_level = 2, + }; + + bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load", + "failed: %d errno %d\n", bpf_fd, errno)) + return; + + tp_fd = bpf_raw_tracepoint_open("nbd_send_request", bpf_fd); + if (CHECK(tp_fd >= 0, "bpf_raw_tracepoint_writable open", + "erroneously succeeded\n")) + goto out_bpffd; + + close(tp_fd); +out_bpffd: + close(bpf_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c new file mode 100644 index 000000000000..5c45424cac5f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <linux/nbd.h> + +void test_raw_tp_writable_test_run(void) +{ + __u32 duration = 0; + char error[4096]; + + const struct bpf_insn trace_program[] = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr load_attr = { + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .license = "GPL v2", + .insns = trace_program, + .insns_cnt = sizeof(trace_program) / sizeof(struct bpf_insn), + .log_level = 2, + }; + + int bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded", + "failed: %d errno %d\n", bpf_fd, errno)) + return; + + const struct bpf_insn skb_program[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr skb_load_attr = { + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .license = "GPL v2", + .insns = skb_program, + .insns_cnt = sizeof(skb_program) / sizeof(struct bpf_insn), + }; + + int filter_fd = + bpf_load_program_xattr(&skb_load_attr, error, sizeof(error)); + if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", + filter_fd, errno)) + goto out_bpffd; + + int tp_fd = bpf_raw_tracepoint_open("bpf_test_finish", bpf_fd); + if (CHECK(tp_fd < 0, "bpf_raw_tracepoint_writable opened", + "failed: %d errno %d\n", tp_fd, errno)) + goto out_filterfd; + + char test_skb[128] = { + 0, + }; + + __u32 prog_ret; + int err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, + 0, &prog_ret, 0); + CHECK(err != 42, "test_run", + "tracepoint did not modify return value\n"); + CHECK(prog_ret != 0, "test_run_ret", + "socket_filter did not return 0\n"); + + close(tp_fd); + + err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, 0, + &prog_ret, 0); + CHECK(err != 0, "test_run_notrace", + "test_run failed with %d errno %d\n", err, errno); + CHECK(prog_ret != 0, "test_run_ret_notrace", + "socket_filter did not return 0\n"); + +out_filterfd: + close(filter_fd); +out_bpffd: + close(bpf_fd); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 75b17cada539..81ad9a0b29d0 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -64,6 +64,25 @@ struct bpf_map_def SEC("maps") jmp_table = { .max_entries = 8 }; +struct bpf_map_def SEC("maps") last_dissection = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct bpf_flow_keys), + .max_entries = 1, +}; + +static __always_inline int export_flow_keys(struct bpf_flow_keys *keys, + int ret) +{ + struct bpf_flow_keys *val; + __u32 key = 0; + + val = bpf_map_lookup_elem(&last_dissection, &key); + if (val) + memcpy(val, keys, sizeof(*val)); + return ret; +} + static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb, __u16 hdr_size, void *buffer) @@ -109,10 +128,10 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) break; default: /* Protocol not supported */ - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } SEC("flow_dissector") @@ -139,8 +158,8 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) case IPPROTO_ICMP: icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp); if (!icmp) - return BPF_DROP; - return BPF_OK; + return export_flow_keys(keys, BPF_DROP); + return export_flow_keys(keys, BPF_OK); case IPPROTO_IPIP: keys->is_encap = true; return parse_eth_proto(skb, bpf_htons(ETH_P_IP)); @@ -150,11 +169,11 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) case IPPROTO_GRE: gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre); if (!gre) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (bpf_htons(gre->flags & GRE_VERSION)) /* Only inspect standard GRE packets with version 0 */ - return BPF_OK; + return export_flow_keys(keys, BPF_OK); keys->thoff += sizeof(*gre); /* Step over GRE Flags and Proto */ if (GRE_IS_CSUM(gre->flags)) @@ -170,7 +189,7 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) eth = bpf_flow_dissect_get_header(skb, sizeof(*eth), &_eth); if (!eth) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->thoff += sizeof(*eth); @@ -181,31 +200,31 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) case IPPROTO_TCP: tcp = bpf_flow_dissect_get_header(skb, sizeof(*tcp), &_tcp); if (!tcp) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (tcp->doff < 5) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if ((__u8 *)tcp + (tcp->doff << 2) > data_end) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->sport = tcp->source; keys->dport = tcp->dest; - return BPF_OK; + return export_flow_keys(keys, BPF_OK); case IPPROTO_UDP: case IPPROTO_UDPLITE: udp = bpf_flow_dissect_get_header(skb, sizeof(*udp), &_udp); if (!udp) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->sport = udp->source; keys->dport = udp->dest; - return BPF_OK; + return export_flow_keys(keys, BPF_OK); default: - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) @@ -225,7 +244,7 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) return parse_ip_proto(skb, nexthdr); } - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } PROG(IP)(struct __sk_buff *skb) @@ -238,11 +257,11 @@ PROG(IP)(struct __sk_buff *skb) iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph); if (!iph) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); /* IP header cannot be smaller than 20 bytes */ if (iph->ihl < 5) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->addr_proto = ETH_P_IP; keys->ipv4_src = iph->saddr; @@ -250,7 +269,7 @@ PROG(IP)(struct __sk_buff *skb) keys->thoff += iph->ihl << 2; if (data + keys->thoff > data_end) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) { keys->is_frag = true; @@ -264,7 +283,7 @@ PROG(IP)(struct __sk_buff *skb) } if (done) - return BPF_OK; + return export_flow_keys(keys, BPF_OK); return parse_ip_proto(skb, iph->protocol); } @@ -276,7 +295,7 @@ PROG(IPV6)(struct __sk_buff *skb) ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h); if (!ip6h) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->addr_proto = ETH_P_IPV6; memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr)); @@ -288,11 +307,12 @@ PROG(IPV6)(struct __sk_buff *skb) PROG(IPV6OP)(struct __sk_buff *skb) { + struct bpf_flow_keys *keys = skb->flow_keys; struct ipv6_opt_hdr *ip6h, _ip6h; ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h); if (!ip6h) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); /* hlen is in 8-octets and does not include the first 8 bytes * of the header @@ -309,7 +329,7 @@ PROG(IPV6FR)(struct __sk_buff *skb) fragh = bpf_flow_dissect_get_header(skb, sizeof(*fragh), &_fragh); if (!fragh) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->thoff += sizeof(*fragh); keys->is_frag = true; @@ -321,13 +341,14 @@ PROG(IPV6FR)(struct __sk_buff *skb) PROG(MPLS)(struct __sk_buff *skb) { + struct bpf_flow_keys *keys = skb->flow_keys; struct mpls_label *mpls, _mpls; mpls = bpf_flow_dissect_get_header(skb, sizeof(*mpls), &_mpls); if (!mpls) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); - return BPF_OK; + return export_flow_keys(keys, BPF_OK); } PROG(VLAN)(struct __sk_buff *skb) @@ -339,10 +360,10 @@ PROG(VLAN)(struct __sk_buff *skb) if (keys->n_proto == bpf_htons(ETH_P_8021AD)) { vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q)) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); @@ -350,14 +371,14 @@ PROG(VLAN)(struct __sk_buff *skb) vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); /* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/ if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) || vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q)) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->n_proto = vlan->h_vlan_encapsulated_proto; return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto); 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 37328f148538..1c39e4ccb7f1 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -55,6 +55,31 @@ struct bpf_map_def SEC("maps") linum_map = { .max_entries = __NR_BPF_LINUM_ARRAY_IDX, }; +struct bpf_spinlock_cnt { + struct bpf_spin_lock lock; + __u32 cnt; +}; + +struct bpf_map_def SEC("maps") sk_pkt_out_cnt = { + .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 = { + .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); @@ -120,7 +145,9 @@ static void tpcpy(struct bpf_tcp_sock *dst, SEC("cgroup_skb/egress") int egress_read_sock_fields(struct __sk_buff *skb) { + struct bpf_spinlock_cnt cli_cnt_init = { .lock = 0, .cnt = 0xeB9F }; __u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx; + struct bpf_spinlock_cnt *pkt_out_cnt, *pkt_out_cnt10; struct sockaddr_in6 *srv_sa6, *cli_sa6; struct bpf_tcp_sock *tp, *tp_ret; struct bpf_sock *sk, *sk_ret; @@ -161,6 +188,32 @@ int egress_read_sock_fields(struct __sk_buff *skb) skcpy(sk_ret, sk); tpcpy(tp_ret, tp); + if (result_idx == EGRESS_SRV_IDX) { + /* The userspace has created it for srv sk */ + pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk, 0, 0); + pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, sk, + 0, 0); + } else { + pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk, + &cli_cnt_init, + BPF_SK_STORAGE_GET_F_CREATE); + pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, + sk, &cli_cnt_init, + BPF_SK_STORAGE_GET_F_CREATE); + } + + if (!pkt_out_cnt || !pkt_out_cnt10) + RETURN; + + /* Even both cnt and cnt10 have lock defined in their BTF, + * intentionally one cnt takes lock while one does not + * as a test for the spinlock support in BPF_MAP_TYPE_SK_STORAGE. + */ + pkt_out_cnt->cnt += 1; + bpf_spin_lock(&pkt_out_cnt10->lock); + pkt_out_cnt10->cnt += 10; + bpf_spin_unlock(&pkt_out_cnt10->lock); + RETURN; } diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index ab56a6a72b7a..74370e7e286d 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -77,17 +77,52 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, struct v4hdr h_outer; struct tcphdr tcph; int olen, l2_len; + int tcp_off; __u64 flags; - if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, - sizeof(iph_inner)) < 0) - return TC_ACT_OK; + /* Most tests encapsulate a packet into a tunnel with the same + * network protocol, and derive the outer header fields from + * the inner header. + * + * The 6in4 case tests different inner and outer protocols. As + * the inner is ipv6, but the outer expects an ipv4 header as + * input, manually build a struct iphdr based on the ipv6hdr. + */ + if (encap_proto == IPPROTO_IPV6) { + const __u32 saddr = (192 << 24) | (168 << 16) | (1 << 8) | 1; + const __u32 daddr = (192 << 24) | (168 << 16) | (1 << 8) | 2; + struct ipv6hdr iph6_inner; + + /* Read the IPv6 header */ + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph6_inner, + sizeof(iph6_inner)) < 0) + return TC_ACT_OK; + + /* Derive the IPv4 header fields from the IPv6 header */ + memset(&iph_inner, 0, sizeof(iph_inner)); + iph_inner.version = 4; + iph_inner.ihl = 5; + iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) + + bpf_ntohs(iph6_inner.payload_len)); + iph_inner.ttl = iph6_inner.hop_limit - 1; + iph_inner.protocol = iph6_inner.nexthdr; + iph_inner.saddr = __bpf_constant_htonl(saddr); + iph_inner.daddr = __bpf_constant_htonl(daddr); + + tcp_off = sizeof(iph6_inner); + } else { + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + tcp_off = sizeof(iph_inner); + } /* filter only packets we want */ if (iph_inner.ihl != 5 || iph_inner.protocol != IPPROTO_TCP) return TC_ACT_OK; - if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(iph_inner), + if (bpf_skb_load_bytes(skb, ETH_HLEN + tcp_off, &tcph, sizeof(tcph)) < 0) return TC_ACT_OK; @@ -129,6 +164,7 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, l2_len); break; case IPPROTO_IPIP: + case IPPROTO_IPV6: break; default: return TC_ACT_OK; @@ -164,6 +200,17 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, BPF_F_INVALIDATE_HASH) < 0) return TC_ACT_SHOT; + /* if changing outer proto type, update eth->h_proto */ + if (encap_proto == IPPROTO_IPV6) { + struct ethhdr eth; + + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0) + return TC_ACT_SHOT; + eth.h_proto = bpf_htons(ETH_P_IP); + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0) + return TC_ACT_SHOT; + } + return TC_ACT_OK; } @@ -325,6 +372,15 @@ int __encap_udp_eth(struct __sk_buff *skb) return TC_ACT_OK; } +SEC("encap_sit_none") +int __encap_sit_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv4(skb, IPPROTO_IPV6, ETH_P_IP); + else + return TC_ACT_OK; +} + SEC("encap_ip6tnl_none") int __encap_ip6tnl_none(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index f8eb7987b794..42c1ce988945 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -24,6 +24,7 @@ #include "bpf_rlimit.h" #include "bpf_util.h" +#include "test_btf.h" #define MAX_INSNS 512 #define MAX_SUBPROGS 16 @@ -58,68 +59,6 @@ static int __base_pr(enum libbpf_print_level level __attribute__((unused)), return vfprintf(stderr, format, args); } -#define BTF_INFO_ENC(kind, kind_flag, vlen) \ - ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) - -#define BTF_TYPE_ENC(name, info, size_or_type) \ - (name), (info), (size_or_type) - -#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ - ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) -#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ - BTF_INT_ENC(encoding, bits_offset, bits) - -#define BTF_FWD_ENC(name, kind_flag) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0) - -#define BTF_ARRAY_ENC(type, index_type, nr_elems) \ - (type), (index_type), (nr_elems) -#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ - BTF_ARRAY_ENC(type, index_type, nr_elems) - -#define BTF_STRUCT_ENC(name, nr_elems, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz) - -#define BTF_UNION_ENC(name, nr_elems, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz) - -#define BTF_VAR_ENC(name, type, linkage) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage) -#define BTF_VAR_SECINFO_ENC(type, offset, size) \ - (type), (offset), (size) - -#define BTF_MEMBER_ENC(name, type, bits_offset) \ - (name), (type), (bits_offset) -#define BTF_ENUM_ENC(name, val) (name), (val) -#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \ - ((bitfield_size) << 24 | (bits_offset)) - -#define BTF_TYPEDEF_ENC(name, type) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) - -#define BTF_PTR_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) - -#define BTF_CONST_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type) - -#define BTF_VOLATILE_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type) - -#define BTF_RESTRICT_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type) - -#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type) - -#define BTF_FUNC_PROTO_ARG_ENC(name, type) \ - (name), (type) - -#define BTF_FUNC_ENC(name, func_proto) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto) - #define BTF_END_RAW 0xdeadbeef #define NAME_TBD 0xdeadb33f diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h new file mode 100644 index 000000000000..2023725f1962 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Facebook */ + +#ifndef _TEST_BTF_H +#define _TEST_BTF_H + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) + +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) + +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +#define BTF_FWD_ENC(name, kind_flag) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0) + +#define BTF_ARRAY_ENC(type, index_type, nr_elems) \ + (type), (index_type), (nr_elems) +#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ + BTF_ARRAY_ENC(type, index_type, nr_elems) + +#define BTF_STRUCT_ENC(name, nr_elems, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz) + +#define BTF_UNION_ENC(name, nr_elems, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz) + +#define BTF_VAR_ENC(name, type, linkage) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage) +#define BTF_VAR_SECINFO_ENC(type, offset, size) \ + (type), (offset), (size) + +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) +#define BTF_ENUM_ENC(name, val) (name), (val) +#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \ + ((bitfield_size) << 24 | (bits_offset)) + +#define BTF_TYPEDEF_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) + +#define BTF_PTR_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) + +#define BTF_CONST_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type) + +#define BTF_VOLATILE_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type) + +#define BTF_RESTRICT_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type) + +#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type) + +#define BTF_FUNC_PROTO_ARG_ENC(name, type) \ + (name), (type) + +#define BTF_FUNC_ENC(name, func_proto) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto) + +#endif /* _TEST_BTF_H */ diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 3c627771f965..246f745cb006 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -27,6 +27,7 @@ #include "bpf_util.h" #include "bpf_rlimit.h" +#include "test_maps.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -36,15 +37,6 @@ static int skips; static int map_flags; -#define CHECK(condition, tag, format...) ({ \ - int __ret = !!(condition); \ - if (__ret) { \ - printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ - printf(format); \ - exit(-1); \ - } \ -}) - static void test_hashmap(unsigned int task, void *data) { long long key, next_key, first_key, value; @@ -1703,6 +1695,10 @@ static void run_all_tests(void) test_map_in_map(); } +#define DECLARE +#include <map_tests/tests.h> +#undef DECLARE + int main(void) { srand(time(NULL)); @@ -1713,6 +1709,10 @@ int main(void) map_flags = BPF_F_NO_PREALLOC; run_all_tests(); +#define CALL +#include <map_tests/tests.h> +#undef CALL + printf("test_maps: OK, %d SKIPPED\n", skips); return 0; } diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h new file mode 100644 index 000000000000..77d8587ac4ed --- /dev/null +++ b/tools/testing/selftests/bpf/test_maps.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TEST_MAPS_H +#define _TEST_MAPS_H + +#include <stdio.h> +#include <stdlib.h> + +#define CHECK(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ + printf(format); \ + exit(-1); \ + } \ +}) + +#endif diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c index dcae7f664dce..e089477fa0a3 100644 --- a/tools/testing/selftests/bpf/test_sock_fields.c +++ b/tools/testing/selftests/bpf/test_sock_fields.c @@ -35,6 +35,11 @@ enum bpf_linum_array_idx { __NR_BPF_LINUM_ARRAY_IDX, }; +struct bpf_spinlock_cnt { + struct bpf_spin_lock lock; + __u32 cnt; +}; + #define CHECK(condition, tag, format...) ({ \ int __ret = !!(condition); \ if (__ret) { \ @@ -50,6 +55,8 @@ enum bpf_linum_array_idx { #define DATA_LEN sizeof(DATA) static struct sockaddr_in6 srv_sa6, cli_sa6; +static int sk_pkt_out_cnt10_fd; +static int sk_pkt_out_cnt_fd; static int linum_map_fd; static int addr_map_fd; static int tp_map_fd; @@ -220,28 +227,90 @@ static void check_result(void) "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u", ingress_linum); - CHECK(srv_tp.data_segs_out != 1 || + CHECK(srv_tp.data_segs_out != 2 || srv_tp.data_segs_in || srv_tp.snd_cwnd != 10 || srv_tp.total_retrans || - srv_tp.bytes_acked != DATA_LEN, + srv_tp.bytes_acked != 2 * DATA_LEN, "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u", egress_linum); CHECK(cli_tp.data_segs_out || - cli_tp.data_segs_in != 1 || + cli_tp.data_segs_in != 2 || cli_tp.snd_cwnd != 10 || cli_tp.total_retrans || - cli_tp.bytes_received != DATA_LEN, + cli_tp.bytes_received != 2 * DATA_LEN, "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u", egress_linum); } +static void check_sk_pkt_out_cnt(int accept_fd, int cli_fd) +{ + struct bpf_spinlock_cnt pkt_out_cnt = {}, pkt_out_cnt10 = {}; + int err; + + pkt_out_cnt.cnt = ~0; + pkt_out_cnt10.cnt = ~0; + err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &accept_fd, &pkt_out_cnt); + if (!err) + err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &accept_fd, + &pkt_out_cnt10); + + /* The bpf prog only counts for fullsock and + * passive conneciton did not become fullsock until 3WHS + * had been finished. + * The bpf prog only counted two data packet out but we + * specially init accept_fd's pkt_out_cnt by 2 in + * init_sk_storage(). Hence, 4 here. + */ + CHECK(err || pkt_out_cnt.cnt != 4 || pkt_out_cnt10.cnt != 40, + "bpf_map_lookup_elem(sk_pkt_out_cnt, &accept_fd)", + "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u", + err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt); + + pkt_out_cnt.cnt = ~0; + pkt_out_cnt10.cnt = ~0; + err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &cli_fd, &pkt_out_cnt); + if (!err) + err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &cli_fd, + &pkt_out_cnt10); + /* Active connection is fullsock from the beginning. + * 1 SYN and 1 ACK during 3WHS + * 2 Acks on data packet. + * + * The bpf_prog initialized it to 0xeB9F. + */ + CHECK(err || pkt_out_cnt.cnt != 0xeB9F + 4 || + pkt_out_cnt10.cnt != 0xeB9F + 40, + "bpf_map_lookup_elem(sk_pkt_out_cnt, &cli_fd)", + "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u", + err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt); +} + +static void init_sk_storage(int sk_fd, __u32 pkt_out_cnt) +{ + struct bpf_spinlock_cnt scnt = {}; + int err; + + scnt.cnt = pkt_out_cnt; + err = bpf_map_update_elem(sk_pkt_out_cnt_fd, &sk_fd, &scnt, + BPF_NOEXIST); + CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt_fd)", + "err:%d errno:%d", err, errno); + + scnt.cnt *= 10; + err = bpf_map_update_elem(sk_pkt_out_cnt10_fd, &sk_fd, &scnt, + BPF_NOEXIST); + CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt10_fd)", + "err:%d errno:%d", err, errno); +} + static void test(void) { int listen_fd, cli_fd, accept_fd, epfd, err; struct epoll_event ev; socklen_t addrlen; + int i; addrlen = sizeof(struct sockaddr_in6); ev.events = EPOLLIN; @@ -308,24 +377,30 @@ static void test(void) accept_fd, errno); close(listen_fd); - /* Send some data from accept_fd to cli_fd */ - err = send(accept_fd, DATA, DATA_LEN, 0); - CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d", - err, errno); - - /* Have some timeout in recv(cli_fd). Just in case. */ ev.data.fd = cli_fd; err = epoll_ctl(epfd, EPOLL_CTL_ADD, cli_fd, &ev); CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, cli_fd)", "err:%d errno:%d", err, errno); - err = epoll_wait(epfd, &ev, 1, 1000); - CHECK(err != 1 || ev.data.fd != cli_fd, - "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d", - err, errno, ev.data.fd, cli_fd); + init_sk_storage(accept_fd, 2); - err = recv(cli_fd, NULL, 0, MSG_TRUNC); - CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno); + for (i = 0; i < 2; i++) { + /* Send some data from accept_fd to cli_fd */ + err = send(accept_fd, DATA, DATA_LEN, 0); + CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d", + err, errno); + + /* Have some timeout in recv(cli_fd). Just in case. */ + err = epoll_wait(epfd, &ev, 1, 1000); + CHECK(err != 1 || ev.data.fd != cli_fd, + "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d", + err, errno, ev.data.fd, cli_fd); + + err = recv(cli_fd, NULL, 0, MSG_TRUNC); + CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno); + } + + check_sk_pkt_out_cnt(accept_fd, cli_fd); close(epfd); close(accept_fd); @@ -395,6 +470,14 @@ int main(int argc, char **argv) CHECK(!map, "cannot find linum_map", "(null)"); linum_map_fd = bpf_map__fd(map); + map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt"); + CHECK(!map, "cannot find sk_pkt_out_cnt", "(null)"); + sk_pkt_out_cnt_fd = bpf_map__fd(map); + + map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt10"); + CHECK(!map, "cannot find sk_pkt_out_cnt10", "(null)"); + sk_pkt_out_cnt10_fd = bpf_map__fd(map); + test(); bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index d4d8d5d3b06e..ff0d31d38061 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -97,6 +97,9 @@ if [[ "$#" -eq "0" ]]; then echo "ip6ip6" $0 ipv6 ip6tnl none 100 + echo "sit" + $0 ipv6 sit none 100 + for mac in none mpls eth ; do echo "ip gre $mac" $0 ipv4 gre $mac 100 @@ -211,11 +214,20 @@ else targs="" fi +# tunnel address family differs from inner for SIT +if [[ "${tuntype}" == "sit" ]]; then + link_addr1="${ns1_v4}" + link_addr2="${ns2_v4}" +else + link_addr1="${addr1}" + link_addr2="${addr2}" +fi + # serverside, insert decap module # server is still running # client can connect again ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \ - ${tmode} remote "${addr1}" local "${addr2}" $targs + ${tmode} remote "${link_addr1}" local "${link_addr2}" $targs expect_tun_fail=0 @@ -260,6 +272,12 @@ else server_listen fi +# bpf_skb_net_shrink does not take tunnel flags yet, cannot update L3. +if [[ "${tuntype}" == "sit" ]]; then + echo OK + exit 0 +fi + # serverside, use BPF for decap ip netns exec "${ns2}" ip link del dev testtun0 ip netns exec "${ns2}" tc qdisc add dev veth2 clsact diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index ed9e894afef3..ccd896b98cac 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -47,12 +47,13 @@ #include "bpf_rlimit.h" #include "bpf_rand.h" #include "bpf_util.h" +#include "test_btf.h" #include "../../../include/linux/filter.h" #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 17 +#define MAX_NR_MAPS 18 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -85,6 +86,7 @@ struct bpf_test { int fixup_map_array_ro[MAX_FIXUPS]; int fixup_map_array_wo[MAX_FIXUPS]; int fixup_map_array_small[MAX_FIXUPS]; + int fixup_sk_storage_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t retval, retval_unpriv, insn_processed; @@ -497,24 +499,6 @@ static int create_cgroup_storage(bool percpu) return fd; } -#define BTF_INFO_ENC(kind, kind_flag, vlen) \ - ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) -#define BTF_TYPE_ENC(name, info, size_or_type) \ - (name), (info), (size_or_type) -#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ - ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) -#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ - BTF_INT_ENC(encoding, bits_offset, bits) -#define BTF_MEMBER_ENC(name, type, bits_offset) \ - (name), (type), (bits_offset) - -struct btf_raw_data { - __u32 raw_types[64]; - const char *str_sec; - __u32 str_sec_size; -}; - /* struct bpf_spin_lock { * int val; * }; @@ -589,6 +573,31 @@ static int create_map_spin_lock(void) return fd; } +static int create_sk_storage_map(void) +{ + struct bpf_create_map_attr attr = { + .name = "test_map", + .map_type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = 4, + .value_size = 8, + .max_entries = 0, + .map_flags = BPF_F_NO_PREALLOC, + .btf_key_type_id = 1, + .btf_value_type_id = 3, + }; + int fd, btf_fd; + + btf_fd = load_btf(); + if (btf_fd < 0) + return -1; + attr.btf_fd = btf_fd; + fd = bpf_create_map_xattr(&attr); + close(attr.btf_fd); + if (fd < 0) + printf("Failed to create sk_storage_map\n"); + return fd; +} + static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, @@ -611,6 +620,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_array_ro = test->fixup_map_array_ro; int *fixup_map_array_wo = test->fixup_map_array_wo; int *fixup_map_array_small = test->fixup_map_array_small; + int *fixup_sk_storage_map = test->fixup_sk_storage_map; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -765,6 +775,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_array_small++; } while (*fixup_map_array_small); } + if (*fixup_sk_storage_map) { + map_fds[17] = create_sk_storage_map(); + do { + prog[*fixup_sk_storage_map].imm = map_fds[17]; + fixup_sk_storage_map++; + } while (*fixup_sk_storage_map); + } } static int set_admin(bool admin) diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c new file mode 100644 index 000000000000..95b5d70a1dc1 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c @@ -0,0 +1,34 @@ +{ + "raw_tracepoint_writable: reject variable offset", + .insns = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + + BPF_LD_MAP_FD(BPF_REG_1, 0), + /* move the key (== 0) to r10-8 */ + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + /* lookup in the map */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + + /* exit clean if null */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + + /* shift the buffer pointer to a variable location */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_0), + /* clobber whatever's there */ + BPF_MOV64_IMM(BPF_REG_7, 4242), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, 0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 1, }, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)", +}, diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index 416436231fab..b31cd2cf50d0 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -382,3 +382,119 @@ .result = REJECT, .errstr = "reference has not been acquired before", }, +{ + "sk_storage_get(map, skb->sk, NULL, 0): value == NULL", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 11 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, +}, +{ + "sk_storage_get(map, skb->sk, 1, 1): value == 1", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 11 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "R3 type=inv expected=fp", +}, +{ + "sk_storage_get(map, skb->sk, &stack_value, 1): stack_value", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 14 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, +}, +{ + "sk_storage_get(map, skb->sk, &stack_value, 1): partially init stack_value", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 14 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid indirect read from stack", +}, +{ + "bpf_map_lookup_elem(smap, &key)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + 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, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 3 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "cannot pass map_type 24 into func bpf_map_lookup_elem", +}, |